Merge tag 'du-next-20190318' of git://linuxtv.org/pinchartl/media into drm-next

Renesas display drivers changes for v5.2:

- Display writeback (includes VSP changes and DRM/KMS API changes)
(All v4l patches acked by Mauro)
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190318153613.GE12707@pendragon.ideasonboard.com

40 files changed, 774 insertions, 199 deletions

diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
index 041a64dc7167..87627219ce3b 100644
--- a/drivers/gpu/drm/arm/malidp_mw.c
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -252,8 +252,7 @@ void malidp_mw_atomic_commit(struct drm_device *drm,
 				     &mw_state->addrs[0],
 				     mw_state->format);
 
-		drm_writeback_queue_job(mw_conn, conn_state->writeback_job);
-		conn_state->writeback_job = NULL;
+		drm_writeback_queue_job(mw_conn, conn_state);
 		hwdev->hw->enable_memwrite(hwdev, mw_state->addrs,
 					   mw_state->pitches, mw_state->n_planes,
 					   fb->width, fb->height, mw_state->format,
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 3b7eb58817f0..dc8ae98071b4 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -2261,10 +2261,21 @@ EXPORT_SYMBOL(drm_atomic_helper_commit_cleanup_done);
 int drm_atomic_helper_prepare_planes(struct drm_device *dev,
 				     struct drm_atomic_state *state)
 {
+	struct drm_connector *connector;
+	struct drm_connector_state *new_conn_state;
 	struct drm_plane *plane;
 	struct drm_plane_state *new_plane_state;
 	int ret, i, j;
 
+	for_each_new_connector_in_state(state, connector, new_conn_state, i) {
+		if (!new_conn_state->writeback_job)
+			continue;
+
+		ret = drm_writeback_prepare_job(new_conn_state->writeback_job);
+		if (ret < 0)
+			return ret;
+	}
+
 	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
 		const struct drm_plane_helper_funcs *funcs;
 
diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c
index 4985384e51f6..59ffb6b9c745 100644
--- a/drivers/gpu/drm/drm_atomic_state_helper.c
+++ b/drivers/gpu/drm/drm_atomic_state_helper.c
@@ -30,6 +30,7 @@
 #include <drm/drm_connector.h>
 #include <drm/drm_atomic.h>
 #include <drm/drm_device.h>
+#include <drm/drm_writeback.h>
 
 #include <linux/slab.h>
 #include <linux/dma-fence.h>
@@ -412,6 +413,9 @@ __drm_atomic_helper_connector_destroy_state(struct drm_connector_state *state)
 
 	if (state->commit)
 		drm_crtc_commit_put(state->commit);
+
+	if (state->writeback_job)
+		drm_writeback_cleanup_job(state->writeback_job);
 }
 EXPORT_SYMBOL(__drm_atomic_helper_connector_destroy_state);
 
diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
index 0aabd401d3ca..8fa77def577f 100644
--- a/drivers/gpu/drm/drm_atomic_uapi.c
+++ b/drivers/gpu/drm/drm_atomic_uapi.c
@@ -647,28 +647,15 @@ drm_atomic_plane_get_property(struct drm_plane *plane,
 	return 0;
 }
 
-static struct drm_writeback_job *
-drm_atomic_get_writeback_job(struct drm_connector_state *conn_state)
-{
-	WARN_ON(conn_state->connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK);
-
-	if (!conn_state->writeback_job)
-		conn_state->writeback_job =
-			kzalloc(sizeof(*conn_state->writeback_job), GFP_KERNEL);
-
-	return conn_state->writeback_job;
-}
-
 static int drm_atomic_set_writeback_fb_for_connector(
 		struct drm_connector_state *conn_state,
 		struct drm_framebuffer *fb)
 {
-	struct drm_writeback_job *job =
-		drm_atomic_get_writeback_job(conn_state);
-	if (!job)
-		return -ENOMEM;
+	int ret;
 
-	drm_framebuffer_assign(&job->fb, fb);
+	ret = drm_writeback_set_fb(conn_state, fb);
+	if (ret < 0)
+		return ret;
 
 	if (fb)
 		DRM_DEBUG_ATOMIC("Set [FB:%d] for connector state %p\n",
@@ -1158,19 +1145,17 @@ static int prepare_signaling(struct drm_device *dev,
 
 	for_each_new_connector_in_state(state, conn, conn_state, i) {
 		struct drm_writeback_connector *wb_conn;
-		struct drm_writeback_job *job;
 		struct drm_out_fence_state *f;
 		struct dma_fence *fence;
 		s32 __user *fence_ptr;
 
+		if (!conn_state->writeback_job)
+			continue;
+
 		fence_ptr = get_out_fence_for_connector(state, conn);
 		if (!fence_ptr)
 			continue;
 
-		job = drm_atomic_get_writeback_job(conn_state);
-		if (!job)
-			return -ENOMEM;
-
 		f = krealloc(*fence_state, sizeof(**fence_state) *
 			     (*num_fences + 1), GFP_KERNEL);
 		if (!f)
@@ -1192,7 +1177,7 @@ static int prepare_signaling(struct drm_device *dev,
 			return ret;
 		}
 
-		job->out_fence = fence;
+		conn_state->writeback_job->out_fence = fence;
 	}
 
 	/*
diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
index c20e6fe00cb3..79ac014701c8 100644
--- a/drivers/gpu/drm/drm_writeback.c
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -239,14 +239,52 @@ fail:
 }
 EXPORT_SYMBOL(drm_writeback_connector_init);
 
+int drm_writeback_set_fb(struct drm_connector_state *conn_state,
+			 struct drm_framebuffer *fb)
+{
+	WARN_ON(conn_state->connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK);
+
+	if (!conn_state->writeback_job) {
+		conn_state->writeback_job =
+			kzalloc(sizeof(*conn_state->writeback_job), GFP_KERNEL);
+		if (!conn_state->writeback_job)
+			return -ENOMEM;
+
+		conn_state->writeback_job->connector =
+			drm_connector_to_writeback(conn_state->connector);
+	}
+
+	drm_framebuffer_assign(&conn_state->writeback_job->fb, fb);
+	return 0;
+}
+
+int drm_writeback_prepare_job(struct drm_writeback_job *job)
+{
+	struct drm_writeback_connector *connector = job->connector;
+	const struct drm_connector_helper_funcs *funcs =
+		connector->base.helper_private;
+	int ret;
+
+	if (funcs->prepare_writeback_job) {
+		ret = funcs->prepare_writeback_job(connector, job);
+		if (ret < 0)
+			return ret;
+	}
+
+	job->prepared = true;
+	return 0;
+}
+EXPORT_SYMBOL(drm_writeback_prepare_job);
+
 /**
  * drm_writeback_queue_job - Queue a writeback job for later signalling
  * @wb_connector: The writeback connector to queue a job on
- * @job: The job to queue
+ * @conn_state: The connector state containing the job to queue
  *
- * This function adds a job to the job_queue for a writeback connector. It
- * should be considered to take ownership of the writeback job, and so any other
- * references to the job must be cleared after calling this function.
+ * This function adds the job contained in @conn_state to the job_queue for a
+ * writeback connector. It takes ownership of the writeback job and sets the
+ * @conn_state->writeback_job to NULL, and so no access to the job may be
+ * performed by the caller after this function returns.
  *
  * Drivers must ensure that for a given writeback connector, jobs are queued in
  * exactly the same order as they will be completed by the hardware (and
@@ -258,16 +296,36 @@ EXPORT_SYMBOL(drm_writeback_connector_init);
  * See also: drm_writeback_signal_completion()
  */
 void drm_writeback_queue_job(struct drm_writeback_connector *wb_connector,
-			     struct drm_writeback_job *job)
+			     struct drm_connector_state *conn_state)
 {
+	struct drm_writeback_job *job;
 	unsigned long flags;
 
+	job = conn_state->writeback_job;
+	conn_state->writeback_job = NULL;
+
 	spin_lock_irqsave(&wb_connector->job_lock, flags);
 	list_add_tail(&job->list_entry, &wb_connector->job_queue);
 	spin_unlock_irqrestore(&wb_connector->job_lock, flags);
 }
 EXPORT_SYMBOL(drm_writeback_queue_job);
 
+void drm_writeback_cleanup_job(struct drm_writeback_job *job)
+{
+	struct drm_writeback_connector *connector = job->connector;
+	const struct drm_connector_helper_funcs *funcs =
+		connector->base.helper_private;
+
+	if (job->prepared && funcs->cleanup_writeback_job)
+		funcs->cleanup_writeback_job(connector, job);
+
+	if (job->fb)
+		drm_framebuffer_put(job->fb);
+
+	kfree(job);
+}
+EXPORT_SYMBOL(drm_writeback_cleanup_job);
+
 /*
  * @cleanup_work: deferred cleanup of a writeback job
  *
@@ -280,10 +338,9 @@ static void cleanup_work(struct work_struct *work)
 	struct drm_writeback_job *job = container_of(work,
 						     struct drm_writeback_job,
 						     cleanup_work);
-	drm_framebuffer_put(job->fb);
-	kfree(job);
-}
 
+	drm_writeback_cleanup_job(job);
+}
 
 /**
  * drm_writeback_signal_completion - Signal the completion of a writeback job
diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig
index 7c36e2777a15..1529849e217e 100644
--- a/drivers/gpu/drm/rcar-du/Kconfig
+++ b/drivers/gpu/drm/rcar-du/Kconfig
@@ -36,3 +36,7 @@ config DRM_RCAR_VSP
 	depends on VIDEO_RENESAS_VSP1=y || (VIDEO_RENESAS_VSP1 && DRM_RCAR_DU=m)
 	help
 	  Enable support to expose the R-Car VSP Compositor as KMS planes.
+
+config DRM_RCAR_WRITEBACK
+	bool
+	default y if ARM64
diff --git a/drivers/gpu/drm/rcar-du/Makefile b/drivers/gpu/drm/rcar-du/Makefile
index 2a3b8d7972b5..6c2ed9c46467 100644
--- a/drivers/gpu/drm/rcar-du/Makefile
+++ b/drivers/gpu/drm/rcar-du/Makefile
@@ -4,7 +4,7 @@ rcar-du-drm-y := rcar_du_crtc.o \
 		 rcar_du_encoder.o \
 		 rcar_du_group.o \
 		 rcar_du_kms.o \
-		 rcar_du_plane.o
+		 rcar_du_plane.o \
 
 rcar-du-drm-$(CONFIG_DRM_RCAR_LVDS)	+= rcar_du_of.o \
 					   rcar_du_of_lvds_r8a7790.dtb.o \
@@ -13,6 +13,7 @@ rcar-du-drm-$(CONFIG_DRM_RCAR_LVDS)	+= rcar_du_of.o \
 					   rcar_du_of_lvds_r8a7795.dtb.o \
 					   rcar_du_of_lvds_r8a7796.dtb.o
 rcar-du-drm-$(CONFIG_DRM_RCAR_VSP)	+= rcar_du_vsp.o
+rcar-du-drm-$(CONFIG_DRM_RCAR_WRITEBACK) += rcar_du_writeback.o
 
 obj-$(CONFIG_DRM_RCAR_DU)		+= rcar-du-drm.o
 obj-$(CONFIG_DRM_RCAR_DW_HDMI)		+= rcar_dw_hdmi.o
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
index 4cdea14d552f..834432cafda8 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
@@ -648,8 +648,13 @@ static int rcar_du_crtc_atomic_check(struct drm_crtc *crtc,
 	rstate->outputs = 0;
 
 	drm_for_each_encoder_mask(encoder, crtc->dev, state->encoder_mask) {
-		struct rcar_du_encoder *renc = to_rcar_encoder(encoder);
+		struct rcar_du_encoder *renc;
 
+		/* Skip the writeback encoder. */
+		if (encoder->encoder_type == DRM_MODE_ENCODER_VIRTUAL)
+			continue;
+
+		renc = to_rcar_encoder(encoder);
 		rstate->outputs |= BIT(renc->output);
 	}
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
index bcb35b0b7612..92f7d5f3ff80 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 @@
 #include <linux/wait.h>
 
 #include <drm/drm_crtc.h>
+#include <drm/drm_writeback.h>
 
 #include <media/vsp1.h>
 
@@ -27,7 +28,7 @@ struct rcar_du_vsp;
  * @clock: the CRTC functional clock
  * @extclock: external pixel dot clock (optional)
  * @mmio_offset: offset of the CRTC registers in the DU MMIO block
- * @index: CRTC software and hardware index
+ * @index: CRTC hardware index
  * @initialized: whether the CRTC has been initialized and clocks enabled
  * @dsysr: cached value of the DSYSR register
  * @vblank_enable: whether vblank events are enabled on this CRTC
@@ -39,6 +40,7 @@ struct rcar_du_vsp;
  * @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
+ * @writeback: the writeback connector
  */
 struct rcar_du_crtc {
 	struct drm_crtc crtc;
@@ -65,9 +67,12 @@ struct rcar_du_crtc {
 
 	const char *const *sources;
 	unsigned int sources_count;
+
+	struct drm_writeback_connector writeback;
 };
 
-#define to_rcar_crtc(c)	container_of(c, struct rcar_du_crtc, crtc)
+#define to_rcar_crtc(c)		container_of(c, struct rcar_du_crtc, crtc)
+#define wb_to_rcar_crtc(c)	container_of(c, struct rcar_du_crtc, writeback)
 
 /**
  * struct rcar_du_crtc_state - Driver-specific CRTC state
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
index 3b7d50a8fb9b..f8f7fff34dff 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
@@ -26,6 +26,7 @@
 #include "rcar_du_kms.h"
 #include "rcar_du_regs.h"
 #include "rcar_du_vsp.h"
+#include "rcar_du_writeback.h"
 
 /* -----------------------------------------------------------------------------
  * Format helpers
@@ -34,60 +35,70 @@
 static const struct rcar_du_format_info rcar_du_format_infos[] = {
 	{
 		.fourcc = DRM_FORMAT_RGB565,
+		.v4l2 = V4L2_PIX_FMT_RGB565,
 		.bpp = 16,
 		.planes = 1,
 		.pnmr = PnMR_SPIM_TP | PnMR_DDDF_16BPP,
 		.edf = PnDDCR4_EDF_NONE,
 	}, {
 		.fourcc = DRM_FORMAT_ARGB1555,
+		.v4l2 = V4L2_PIX_FMT_ARGB555,
 		.bpp = 16,
 		.planes = 1,
 		.pnmr = PnMR_SPIM_ALP | PnMR_DDDF_ARGB,
 		.edf = PnDDCR4_EDF_NONE,
 	}, {
 		.fourcc = DRM_FORMAT_XRGB1555,
+		.v4l2 = V4L2_PIX_FMT_XRGB555,
 		.bpp = 16,
 		.planes = 1,
 		.pnmr = PnMR_SPIM_ALP | PnMR_DDDF_ARGB,
 		.edf = PnDDCR4_EDF_NONE,
 	}, {
 		.fourcc = DRM_FORMAT_XRGB8888,
+		.v4l2 = V4L2_PIX_FMT_XBGR32,
 		.bpp = 32,
 		.planes = 1,
 		.pnmr = PnMR_SPIM_TP | PnMR_DDDF_16BPP,
 		.edf = PnDDCR4_EDF_RGB888,
 	}, {
 		.fourcc = DRM_FORMAT_ARGB8888,
+		.v4l2 = V4L2_PIX_FMT_ABGR32,
 		.bpp = 32,
 		.planes = 1,
 		.pnmr = PnMR_SPIM_ALP | PnMR_DDDF_16BPP,
 		.edf = PnDDCR4_EDF_ARGB8888,
 	}, {
 		.fourcc = DRM_FORMAT_UYVY,
+		.v4l2 = V4L2_PIX_FMT_UYVY,
 		.bpp = 16,
 		.planes = 1,
 		.pnmr = PnMR_SPIM_TP_OFF | PnMR_DDDF_YC,
 		.edf = PnDDCR4_EDF_NONE,
 	}, {
 		.fourcc = DRM_FORMAT_YUYV,
+		.v4l2 = V4L2_PIX_FMT_YUYV,
 		.bpp = 16,
 		.planes = 1,
 		.pnmr = PnMR_SPIM_TP_OFF | PnMR_DDDF_YC,
 		.edf = PnDDCR4_EDF_NONE,
 	}, {
 		.fourcc = DRM_FORMAT_NV12,
+		.v4l2 = V4L2_PIX_FMT_NV12M,
 		.bpp = 12,
 		.planes = 2,
 		.pnmr = PnMR_SPIM_TP_OFF | PnMR_DDDF_YC,
 		.edf = PnDDCR4_EDF_NONE,
 	}, {
 		.fourcc = DRM_FORMAT_NV21,
+		.v4l2 = V4L2_PIX_FMT_NV21M,
 		.bpp = 12,
 		.planes = 2,
 		.pnmr = PnMR_SPIM_TP_OFF | PnMR_DDDF_YC,
 		.edf = PnDDCR4_EDF_NONE,
 	}, {
 		.fourcc = DRM_FORMAT_NV16,
+		.v4l2 = V4L2_PIX_FMT_NV16M,
 		.bpp = 16,
 		.planes = 2,
 		.pnmr = PnMR_SPIM_TP_OFF | PnMR_DDDF_YC,
@@ -99,62 +110,77 @@ static const struct rcar_du_format_info rcar_du_format_infos[] = {
 	 */
 	{
 		.fourcc = DRM_FORMAT_RGB332,
+		.v4l2 = V4L2_PIX_FMT_RGB332,
 		.bpp = 8,
 		.planes = 1,
 	}, {
 		.fourcc = DRM_FORMAT_ARGB4444,
+		.v4l2 = V4L2_PIX_FMT_ARGB444,
 		.bpp = 16,
 		.planes = 1,
 	}, {
 		.fourcc = DRM_FORMAT_XRGB4444,
+		.v4l2 = V4L2_PIX_FMT_XRGB444,
 		.bpp = 16,
 		.planes = 1,
 	}, {
 		.fourcc = DRM_FORMAT_BGR888,
+		.v4l2 = V4L2_PIX_FMT_RGB24,
 		.bpp = 24,
 		.planes = 1,
 	}, {
 		.fourcc = DRM_FORMAT_RGB888,
+		.v4l2 = V4L2_PIX_FMT_BGR24,
 		.bpp = 24,
 		.planes = 1,
 	}, {
 		.fourcc = DRM_FORMAT_BGRA8888,
+		.v4l2 = V4L2_PIX_FMT_ARGB32,
 		.bpp = 32,
 		.planes = 1,
 	}, {
 		.fourcc = DRM_FORMAT_BGRX8888,
+		.v4l2 = V4L2_PIX_FMT_XRGB32,
 		.bpp = 32,
 		.planes = 1,
 	}, {
 		.fourcc = DRM_FORMAT_YVYU,
+		.v4l2 = V4L2_PIX_FMT_YVYU,
 		.bpp = 16,
 		.planes = 1,
 	}, {
 		.fourcc = DRM_FORMAT_NV61,
+		.v4l2 = V4L2_PIX_FMT_NV61M,
 		.bpp = 16,
 		.planes = 2,
 	}, {
 		.fourcc = DRM_FORMAT_YUV420,
+		.v4l2 = V4L2_PIX_FMT_YUV420M,
 		.bpp = 12,
 		.planes = 3,
 	}, {
 		.fourcc = DRM_FORMAT_YVU420,
+		.v4l2 = V4L2_PIX_FMT_YVU420M,
 		.bpp = 12,
 		.planes = 3,
 	}, {
 		.fourcc = DRM_FORMAT_YUV422,
+		.v4l2 = V4L2_PIX_FMT_YUV422M,
 		.bpp = 16,
 		.planes = 3,
 	}, {
 		.fourcc = DRM_FORMAT_YVU422,
+		.v4l2 = V4L2_PIX_FMT_YVU422M,
 		.bpp = 16,
 		.planes = 3,
 	}, {
 		.fourcc = DRM_FORMAT_YUV444,
+		.v4l2 = V4L2_PIX_FMT_YUV444M,
 		.bpp = 24,
 		.planes = 3,
 	}, {
 		.fourcc = DRM_FORMAT_YVU444,
+		.v4l2 = V4L2_PIX_FMT_YVU444M,
 		.bpp = 24,
 		.planes = 3,
 	},
@@ -639,6 +665,17 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 		encoder->possible_clones = (1 << num_encoders) - 1;
 	}
 
+	/* Create the writeback connectors. */
+	if (rcdu->info->gen >= 3) {
+		for (i = 0; i < rcdu->num_crtcs; ++i) {
+			struct rcar_du_crtc *rcrtc = &rcdu->crtcs[i];
+
+			ret = rcar_du_writeback_init(rcdu, rcrtc);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
 	/*
 	 * Initialize the default DPAD0 source to the index of the first DU
 	 * channel that can be connected to DPAD0. The exact value doesn't
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.h b/drivers/gpu/drm/rcar-du/rcar_du_kms.h
index e171527abdaa..0346504d8c59 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.h
@@ -19,6 +19,7 @@ struct rcar_du_device;
 
 struct rcar_du_format_info {
 	u32 fourcc;
+	u32 v4l2;
 	unsigned int bpp;
 	unsigned int planes;
 	unsigned int pnmr;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
index 0878accbd134..4c8bed34838c 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
@@ -10,6 +10,7 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_fourcc.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_plane_helper.h>
@@ -26,16 +27,19 @@
 #include "rcar_du_drv.h"
 #include "rcar_du_kms.h"
 #include "rcar_du_vsp.h"
+#include "rcar_du_writeback.h"
 
-static void rcar_du_vsp_complete(void *private, bool completed, u32 crc)
+static void rcar_du_vsp_complete(void *private, unsigned int status, u32 crc)
 {
 	struct rcar_du_crtc *crtc = private;
 
 	if (crtc->vblank_enable)
 		drm_crtc_handle_vblank(&crtc->crtc);
 
-	if (completed)
+	if (status & VSP1_DU_STATUS_COMPLETE)
 		rcar_du_crtc_finish_page_flip(crtc);
+	if (status & VSP1_DU_STATUS_WRITEBACK)
+		rcar_du_writeback_complete(crtc);
 
 	drm_crtc_add_crc_entry(&crtc->crtc, false, 0, &crc);
 }
@@ -107,11 +111,12 @@ void rcar_du_vsp_atomic_flush(struct rcar_du_crtc *crtc)
 	state = to_rcar_crtc_state(crtc->crtc.state);
 	cfg.crc = state->crc;
 
+	rcar_du_writeback_setup(crtc, &cfg.writeback);
+
 	vsp1_du_atomic_flush(crtc->vsp->vsp, crtc->vsp_pipe, &cfg);
 }
 
-/* Keep the two tables in sync. */
-static const u32 formats_kms[] = {
+static const u32 rcar_du_vsp_formats[] = {
 	DRM_FORMAT_RGB332,
 	DRM_FORMAT_ARGB4444,
 	DRM_FORMAT_XRGB4444,
@@ -139,40 +144,13 @@ static const u32 formats_kms[] = {
 	DRM_FORMAT_YVU444,
 };
 
-static const u32 formats_v4l2[] = {
-	V4L2_PIX_FMT_RGB332,
-	V4L2_PIX_FMT_ARGB444,
-	V4L2_PIX_FMT_XRGB444,
-	V4L2_PIX_FMT_ARGB555,
-	V4L2_PIX_FMT_XRGB555,
-	V4L2_PIX_FMT_RGB565,
-	V4L2_PIX_FMT_RGB24,
-	V4L2_PIX_FMT_BGR24,
-	V4L2_PIX_FMT_ARGB32,
-	V4L2_PIX_FMT_XRGB32,
-	V4L2_PIX_FMT_ABGR32,
-	V4L2_PIX_FMT_XBGR32,
-	V4L2_PIX_FMT_UYVY,
-	V4L2_PIX_FMT_YUYV,
-	V4L2_PIX_FMT_YVYU,
-	V4L2_PIX_FMT_NV12M,
-	V4L2_PIX_FMT_NV21M,
-	V4L2_PIX_FMT_NV16M,
-	V4L2_PIX_FMT_NV61M,
-	V4L2_PIX_FMT_YUV420M,
-	V4L2_PIX_FMT_YVU420M,
-	V4L2_PIX_FMT_YUV422M,
-	V4L2_PIX_FMT_YVU422M,
-	V4L2_PIX_FMT_YUV444M,
-	V4L2_PIX_FMT_YVU444M,
-};
-
 static void rcar_du_vsp_plane_setup(struct rcar_du_vsp_plane *plane)
 {
 	struct rcar_du_vsp_plane_state *state =
 		to_rcar_vsp_plane_state(plane->plane.state);
 	struct rcar_du_crtc *crtc = to_rcar_crtc(state->state.crtc);
 	struct drm_framebuffer *fb = plane->plane.state->fb;
+	const struct rcar_du_format_info *format;
 	struct vsp1_du_atomic_config cfg = {
 		.pixelformat = 0,
 		.pitch = fb->pitches[0],
@@ -195,37 +173,23 @@ static void rcar_du_vsp_plane_setup(struct rcar_du_vsp_plane *plane)
 		cfg.mem[i] = sg_dma_address(state->sg_tables[i].sgl)
 			   + fb->offsets[i];
 
-	for (i = 0; i < ARRAY_SIZE(formats_kms); ++i) {
-		if (formats_kms[i] == state->format->fourcc) {
-			cfg.pixelformat = formats_v4l2[i];
-			break;
-		}
-	}
+	format = rcar_du_format_info(state->format->fourcc);
+	cfg.pixelformat = format->v4l2;
 
 	vsp1_du_atomic_update(plane->vsp->vsp, crtc->vsp_pipe,
 			      plane->index, &cfg);
 }
 
-static int rcar_du_vsp_plane_prepare_fb(struct drm_plane *plane,
-					struct drm_plane_state *state)
+int rcar_du_vsp_map_fb(struct rcar_du_vsp *vsp, struct drm_framebuffer *fb,
+		       struct sg_table sg_tables[3])
 {
-	struct rcar_du_vsp_plane_state *rstate = to_rcar_vsp_plane_state(state);
-	struct rcar_du_vsp *vsp = to_rcar_vsp_plane(plane)->vsp;
 	struct rcar_du_device *rcdu = vsp->dev;
 	unsigned int i;
 	int ret;
 
-	/*
-	 * There's no need to prepare (and unprepare) the framebuffer when the
-	 * plane is not visible, as it will not be displayed.
-	 */
-	if (!state->visible)
-		return 0;
-
-	for (i = 0; i < rstate->format->planes; ++i) {
-		struct drm_gem_cma_object *gem =
-			drm_fb_cma_get_gem_obj(state->fb, i);
-		struct sg_table *sgt = &rstate->sg_tables[i];
+	for (i = 0; i < fb->format->num_planes; ++i) {
+		struct drm_gem_cma_object *gem = drm_fb_cma_get_gem_obj(fb, i);
+		struct sg_table *sgt = &sg_tables[i];
 
 		ret = dma_get_sgtable(rcdu->dev, sgt, gem->vaddr, gem->paddr,
 				      gem->base.size);
@@ -240,15 +204,11 @@ static int rcar_du_vsp_plane_prepare_fb(struct drm_plane *plane,
 		}
 	}
 
-	ret = drm_gem_fb_prepare_fb(plane, state);
-	if (ret)
-		goto fail;
-
 	return 0;
 
 fail:
 	while (i--) {
-		struct sg_table *sgt = &rstate->sg_tables[i];
+		struct sg_table *sgt = &sg_tables[i];
 
 		vsp1_du_unmap_sg(vsp->vsp, sgt);
 		sg_free_table(sgt);
@@ -257,24 +217,52 @@ fail:
 	return ret;
 }
 
-static void rcar_du_vsp_plane_cleanup_fb(struct drm_plane *plane,
-					 struct drm_plane_state *state)
+static int rcar_du_vsp_plane_prepare_fb(struct drm_plane *plane,
+					struct drm_plane_state *state)
 {
 	struct rcar_du_vsp_plane_state *rstate = to_rcar_vsp_plane_state(state);
 	struct rcar_du_vsp *vsp = to_rcar_vsp_plane(plane)->vsp;
-	unsigned int i;
+	int ret;
 
+	/*
+	 * There's no need to prepare (and unprepare) the framebuffer when the
+	 * plane is not visible, as it will not be displayed.
+	 */
 	if (!state->visible)
-		return;
+		return 0;
+
+	ret = rcar_du_vsp_map_fb(vsp, state->fb, rstate->sg_tables);
+	if (ret < 0)
+		return ret;
+
+	return drm_gem_fb_prepare_fb(plane, state);
+}
+
+void rcar_du_vsp_unmap_fb(struct rcar_du_vsp *vsp, struct drm_framebuffer *fb,
+			  struct sg_table sg_tables[3])
+{
+	unsigned int i;
 
-	for (i = 0; i < rstate->format->planes; ++i) {
-		struct sg_table *sgt = &rstate->sg_tables[i];
+	for (i = 0; i < fb->format->num_planes; ++i) {
+		struct sg_table *sgt = &sg_tables[i];
 
 		vsp1_du_unmap_sg(vsp->vsp, sgt);
 		sg_free_table(sgt);
 	}
 }
 
+static void rcar_du_vsp_plane_cleanup_fb(struct drm_plane *plane,
+					 struct drm_plane_state *state)
+{
+	struct rcar_du_vsp_plane_state *rstate = to_rcar_vsp_plane_state(state);
+	struct rcar_du_vsp *vsp = to_rcar_vsp_plane(plane)->vsp;
+
+	if (!state->visible)
+		return;
+
+	rcar_du_vsp_unmap_fb(vsp, state->fb, rstate->sg_tables);
+}
+
 static int rcar_du_vsp_plane_atomic_check(struct drm_plane *plane,
 					  struct drm_plane_state *state)
 {
@@ -395,8 +383,8 @@ int rcar_du_vsp_init(struct rcar_du_vsp *vsp, struct device_node *np,
 
 		ret = drm_universal_plane_init(rcdu->ddev, &plane->plane, crtcs,
 					       &rcar_du_vsp_plane_funcs,
-					       formats_kms,
-					       ARRAY_SIZE(formats_kms),
+					       rcar_du_vsp_formats,
+					       ARRAY_SIZE(rcar_du_vsp_formats),
 					       NULL, type, NULL);
 		if (ret < 0)
 			return ret;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.h b/drivers/gpu/drm/rcar-du/rcar_du_vsp.h
index db232037f24a..9b4724159378 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.h
@@ -12,8 +12,10 @@
 
 #include <drm/drm_plane.h>
 
+struct drm_framebuffer;
 struct rcar_du_format_info;
 struct rcar_du_vsp;
+struct sg_table;
 
 struct rcar_du_vsp_plane {
 	struct drm_plane plane;
@@ -60,6 +62,10 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc);
 void rcar_du_vsp_disable(struct rcar_du_crtc *crtc);
 void rcar_du_vsp_atomic_begin(struct rcar_du_crtc *crtc);
 void rcar_du_vsp_atomic_flush(struct rcar_du_crtc *crtc);
+int rcar_du_vsp_map_fb(struct rcar_du_vsp *vsp, struct drm_framebuffer *fb,
+		       struct sg_table sg_tables[3]);
+void rcar_du_vsp_unmap_fb(struct rcar_du_vsp *vsp, struct drm_framebuffer *fb,
+			  struct sg_table sg_tables[3]);
 #else
 static inline int rcar_du_vsp_init(struct rcar_du_vsp *vsp,
 				   struct device_node *np,
@@ -71,6 +77,17 @@ static inline void rcar_du_vsp_enable(struct rcar_du_crtc *crtc) { };
 static inline void rcar_du_vsp_disable(struct rcar_du_crtc *crtc) { };
 static inline void rcar_du_vsp_atomic_begin(struct rcar_du_crtc *crtc) { };
 static inline void rcar_du_vsp_atomic_flush(struct rcar_du_crtc *crtc) { };
+static inline int rcar_du_vsp_map_fb(struct rcar_du_vsp *vsp,
+				     struct drm_framebuffer *fb,
+				     struct sg_table sg_tables[3])
+{
+	return -ENXIO;
+}
+static inline void rcar_du_vsp_unmap_fb(struct rcar_du_vsp *vsp,
+					struct drm_framebuffer *fb,
+					struct sg_table sg_tables[3])
+{
+}
 #endif
 
 #endif /* __RCAR_DU_VSP_H__ */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
new file mode 100644
index 000000000000..989a0be94131
--- /dev/null
+++ b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
@@ -0,0 +1,243 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * rcar_du_writeback.c  --  R-Car Display Unit Writeback Support
+ *
+ * Copyright (C) 2019 Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+ */
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_device.h>
+#include <drm/drm_fourcc.h>
+#include <drm/drm_probe_helper.h>
+#include <drm/drm_writeback.h>
+
+#include "rcar_du_crtc.h"
+#include "rcar_du_drv.h"
+#include "rcar_du_kms.h"
+
+/**
+ * struct rcar_du_wb_conn_state - Driver-specific writeback connector state
+ * @state: base DRM connector state
+ * @format: format of the writeback framebuffer
+ */
+struct rcar_du_wb_conn_state {
+	struct drm_connector_state state;
+	const struct rcar_du_format_info *format;
+};
+
+#define to_rcar_wb_conn_state(s) \
+	container_of(s, struct rcar_du_wb_conn_state, state)
+
+/**
+ * struct rcar_du_wb_job - Driver-private data for writeback jobs
+ * @sg_tables: scatter-gather tables for the framebuffer memory
+ */
+struct rcar_du_wb_job {
+	struct sg_table sg_tables[3];
+};
+
+static int rcar_du_wb_conn_get_modes(struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+
+	return drm_add_modes_noedid(connector, dev->mode_config.max_width,
+				    dev->mode_config.max_height);
+}
+
+static int rcar_du_wb_prepare_job(struct drm_writeback_connector *connector,
+				  struct drm_writeback_job *job)
+{
+	struct rcar_du_crtc *rcrtc = wb_to_rcar_crtc(connector);
+	struct rcar_du_wb_job *rjob;
+	int ret;
+
+	if (!job->fb)
+		return 0;
+
+	rjob = kzalloc(sizeof(*rjob), GFP_KERNEL);
+	if (!rjob)
+		return -ENOMEM;
+
+	/* Map the framebuffer to the VSP. */
+	ret = rcar_du_vsp_map_fb(rcrtc->vsp, job->fb, rjob->sg_tables);
+	if (ret < 0) {
+		kfree(rjob);
+		return ret;
+	}
+
+	job->priv = rjob;
+	return 0;
+}
+
+static void rcar_du_wb_cleanup_job(struct drm_writeback_connector *connector,
+				   struct drm_writeback_job *job)
+{
+	struct rcar_du_crtc *rcrtc = wb_to_rcar_crtc(connector);
+	struct rcar_du_wb_job *rjob = job->priv;
+
+	if (!job->fb)
+		return;
+
+	rcar_du_vsp_unmap_fb(rcrtc->vsp, job->fb, rjob->sg_tables);
+	kfree(rjob);
+}
+
+static const struct drm_connector_helper_funcs rcar_du_wb_conn_helper_funcs = {
+	.get_modes = rcar_du_wb_conn_get_modes,
+	.prepare_writeback_job = rcar_du_wb_prepare_job,
+	.cleanup_writeback_job = rcar_du_wb_cleanup_job,
+};
+
+static struct drm_connector_state *
+rcar_du_wb_conn_duplicate_state(struct drm_connector *connector)
+{
+	struct rcar_du_wb_conn_state *copy;
+
+	if (WARN_ON(!connector->state))
+		return NULL;
+
+	copy = kzalloc(sizeof(*copy), GFP_KERNEL);
+	if (!copy)
+		return NULL;
+
+	__drm_atomic_helper_connector_duplicate_state(connector, &copy->state);
+
+	return &copy->state;
+}
+
+static void rcar_du_wb_conn_destroy_state(struct drm_connector *connector,
+					  struct drm_connector_state *state)
+{
+	__drm_atomic_helper_connector_destroy_state(state);
+	kfree(to_rcar_wb_conn_state(state));
+}
+
+static void rcar_du_wb_conn_reset(struct drm_connector *connector)
+{
+	struct rcar_du_wb_conn_state *state;
+
+	if (connector->state) {
+		rcar_du_wb_conn_destroy_state(connector, connector->state);
+		connector->state = NULL;
+	}
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (state == NULL)
+		return;
+
+	__drm_atomic_helper_connector_reset(connector, &state->state);
+}
+
+static const struct drm_connector_funcs rcar_du_wb_conn_funcs = {
+	.reset = rcar_du_wb_conn_reset,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = drm_connector_cleanup,
+	.atomic_duplicate_state = rcar_du_wb_conn_duplicate_state,
+	.atomic_destroy_state = rcar_du_wb_conn_destroy_state,
+};
+
+static int rcar_du_wb_enc_atomic_check(struct drm_encoder *encoder,
+				       struct drm_crtc_state *crtc_state,
+				       struct drm_connector_state *conn_state)
+{
+	struct rcar_du_wb_conn_state *wb_state =
+		to_rcar_wb_conn_state(conn_state);
+	const struct drm_display_mode *mode = &crtc_state->mode;
+	struct drm_device *dev = encoder->dev;
+	struct drm_framebuffer *fb;
+
+	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+		return 0;
+
+	fb = conn_state->writeback_job->fb;
+
+	/*
+	 * Verify that the framebuffer format is supported and that its size
+	 * matches the current mode.
+	 */
+	if (fb->width != mode->hdisplay || fb->height != mode->vdisplay) {
+		dev_dbg(dev->dev, "%s: invalid framebuffer size %ux%u\n",
+			__func__, fb->width, fb->height);
+		return -EINVAL;
+	}
+
+	wb_state->format = rcar_du_format_info(fb->format->format);
+	if (wb_state->format == NULL) {
+		dev_dbg(dev->dev, "%s: unsupported format %08x\n", __func__,
+			fb->format->format);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct drm_encoder_helper_funcs rcar_du_wb_enc_helper_funcs = {
+	.atomic_check = rcar_du_wb_enc_atomic_check,
+};
+
+/*
+ * Only RGB formats are currently supported as the VSP outputs RGB to the DU
+ * and can't convert to YUV separately for writeback.
+ */
+static const u32 writeback_formats[] = {
+	DRM_FORMAT_RGB332,
+	DRM_FORMAT_ARGB4444,
+	DRM_FORMAT_XRGB4444,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGRA8888,
+	DRM_FORMAT_BGRX8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XRGB8888,
+};
+
+int rcar_du_writeback_init(struct rcar_du_device *rcdu,
+			   struct rcar_du_crtc *rcrtc)
+{
+	struct drm_writeback_connector *wb_conn = &rcrtc->writeback;
+
+	wb_conn->encoder.possible_crtcs = 1 << drm_crtc_index(&rcrtc->crtc);
+	drm_connector_helper_add(&wb_conn->base,
+				 &rcar_du_wb_conn_helper_funcs);
+
+	return drm_writeback_connector_init(rcdu->ddev, wb_conn,
+					    &rcar_du_wb_conn_funcs,
+					    &rcar_du_wb_enc_helper_funcs,
+					    writeback_formats,
+					    ARRAY_SIZE(writeback_formats));
+}
+
+void rcar_du_writeback_setup(struct rcar_du_crtc *rcrtc,
+			     struct vsp1_du_writeback_config *cfg)
+{
+	struct rcar_du_wb_conn_state *wb_state;
+	struct drm_connector_state *state;
+	struct rcar_du_wb_job *rjob;
+	struct drm_framebuffer *fb;
+	unsigned int i;
+
+	state = rcrtc->writeback.base.state;
+	if (!state || !state->writeback_job || !state->writeback_job->fb)
+		return;
+
+	fb = state->writeback_job->fb;
+	rjob = state->writeback_job->priv;
+	wb_state = to_rcar_wb_conn_state(state);
+
+	cfg->pixelformat = wb_state->format->v4l2;
+	cfg->pitch = fb->pitches[0];
+
+	for (i = 0; i < wb_state->format->planes; ++i)
+		cfg->mem[i] = sg_dma_address(rjob->sg_tables[i].sgl)
+			    + fb->offsets[i];
+
+	drm_writeback_queue_job(&rcrtc->writeback, state);
+}
+
+void rcar_du_writeback_complete(struct rcar_du_crtc *rcrtc)
+{
+	drm_writeback_signal_completion(&rcrtc->writeback, 0);
+}
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_writeback.h b/drivers/gpu/drm/rcar-du/rcar_du_writeback.h
new file mode 100644
index 000000000000..fa87ebf8d21f
--- /dev/null
+++ b/drivers/gpu/drm/rcar-du/rcar_du_writeback.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * rcar_du_writeback.h  --  R-Car Display Unit Writeback Support
+ *
+ * Copyright (C) 2019 Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+ */
+
+#ifndef __RCAR_DU_WRITEBACK_H__
+#define __RCAR_DU_WRITEBACK_H__
+
+#include <drm/drm_plane.h>
+
+struct rcar_du_crtc;
+struct rcar_du_device;
+struct vsp1_du_atomic_pipe_config;
+
+#ifdef CONFIG_DRM_RCAR_WRITEBACK
+int rcar_du_writeback_init(struct rcar_du_device *rcdu,
+			   struct rcar_du_crtc *rcrtc);
+void rcar_du_writeback_setup(struct rcar_du_crtc *rcrtc,
+			     struct vsp1_du_writeback_config *cfg);
+void rcar_du_writeback_complete(struct rcar_du_crtc *rcrtc);
+#else
+static inline int rcar_du_writeback_init(struct rcar_du_device *rcdu,
+					 struct rcar_du_crtc *rcrtc)
+{
+	return -ENXIO;
+}
+static inline void
+rcar_du_writeback_setup(struct rcar_du_crtc *rcrtc,
+			struct vsp1_du_writeback_config *cfg)
+{
+}
+static inline void rcar_du_writeback_complete(struct rcar_du_crtc *rcrtc)
+{
+}
+#endif
+
+#endif /* __RCAR_DU_WRITEBACK_H__ */
diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c
index aa279b5b0de7..5dabd91f2d7e 100644
--- a/drivers/gpu/drm/vc4/vc4_txp.c
+++ b/drivers/gpu/drm/vc4/vc4_txp.c
@@ -327,7 +327,7 @@ static void vc4_txp_connector_atomic_commit(struct drm_connector *conn,
 
 	TXP_WRITE(TXP_DST_CTRL, ctrl);
 
-	drm_writeback_queue_job(&txp->connector, conn_state->writeback_job);
+	drm_writeback_queue_job(&txp->connector, conn_state);
 }
 
 static const struct drm_connector_helper_funcs vc4_txp_connector_helper_funcs = {
diff --git a/drivers/media/platform/vsp1/vsp1_brx.c b/drivers/media/platform/vsp1/vsp1_brx.c
index 58ad248cd7f7..2d86c718a5cf 100644
--- a/drivers/media/platform/vsp1/vsp1_brx.c
+++ b/drivers/media/platform/vsp1/vsp1_brx.c
@@ -283,6 +283,7 @@ static const struct v4l2_subdev_ops brx_ops = {
 
 static void brx_configure_stream(struct vsp1_entity *entity,
 				 struct vsp1_pipeline *pipe,
+				 struct vsp1_dl_list *dl,
 				 struct vsp1_dl_body *dlb)
 {
 	struct vsp1_brx *brx = to_brx(&entity->subdev);
diff --git a/drivers/media/platform/vsp1/vsp1_clu.c b/drivers/media/platform/vsp1/vsp1_clu.c
index 942fc14c19d1..a47b23bf5abf 100644
--- a/drivers/media/platform/vsp1/vsp1_clu.c
+++ b/drivers/media/platform/vsp1/vsp1_clu.c
@@ -171,6 +171,7 @@ static const struct v4l2_subdev_ops clu_ops = {
 
 static void clu_configure_stream(struct vsp1_entity *entity,
 				 struct vsp1_pipeline *pipe,
+				 struct vsp1_dl_list *dl,
 				 struct vsp1_dl_body *dlb)
 {
 	struct vsp1_clu *clu = to_clu(&entity->subdev);
diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index 26289adaf658..104b6f514536 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -178,7 +178,7 @@ struct vsp1_dl_cmd_pool {
  * @post_cmd: post command to be issued through extended dl header
  * @has_chain: if true, indicates that there's a partition chain
  * @chain: entry in the display list partition chain
- * @internal: whether the display list is used for internal purpose
+ * @flags: display list flags, a combination of VSP1_DL_FRAME_END_*
  */
 struct vsp1_dl_list {
 	struct list_head list;
@@ -197,7 +197,7 @@ struct vsp1_dl_list {
 	bool has_chain;
 	struct list_head chain;
 
-	bool internal;
+	unsigned int flags;
 };
 
 /**
@@ -699,8 +699,8 @@ struct vsp1_dl_body *vsp1_dl_list_get_body0(struct vsp1_dl_list *dl)
  * which bodies are added.
  *
  * Adding a body to a display list passes ownership of the body to the list. The
- * caller retains its reference to the fragment when adding it to the display
- * list, but is not allowed to add new entries to the body.
+ * caller retains its reference to the body when adding it to the display list,
+ * but is not allowed to add new entries to the body.
  *
  * The reference must be explicitly released by a call to vsp1_dl_body_put()
  * when the body isn't needed anymore.
@@ -770,17 +770,35 @@ static void vsp1_dl_list_fill_header(struct vsp1_dl_list *dl, bool is_last)
 	}
 
 	dl->header->num_lists = num_lists;
+	dl->header->flags = 0;
 
-	if (!list_empty(&dl->chain) && !is_last) {
+	/*
+	 * Enable the interrupt for the end of each frame. In continuous mode
+	 * chained lists are used with one list per frame, so enable the
+	 * interrupt for each list. In singleshot mode chained lists are used
+	 * to partition a single frame, so enable the interrupt for the last
+	 * list only.
+	 */
+	if (!dlm->singleshot || is_last)
+		dl->header->flags |= VSP1_DLH_INT_ENABLE;
+
+	/*
+	 * In continuous mode enable auto-start for all lists, as the VSP must
+	 * loop on the same list until a new one is queued. In singleshot mode
+	 * enable auto-start for all lists but the last to chain processing of
+	 * partitions without software intervention.
+	 */
+	if (!dlm->singleshot || !is_last)
+		dl->header->flags |= VSP1_DLH_AUTO_START;
+
+	if (!is_last) {
 		/*
-		 * If this display list's chain is not empty, we are on a list,
-		 * and the next item is the display list that we must queue for
-		 * automatic processing by the hardware.
+		 * If this is not the last display list in the chain, queue the
+		 * next item for automatic processing by the hardware.
 		 */
 		struct vsp1_dl_list *next = list_next_entry(dl, chain);
 
 		dl->header->next_header = next->dma;
-		dl->header->flags = VSP1_DLH_AUTO_START;
 	} else if (!dlm->singleshot) {
 		/*
 		 * if the display list manager works in continuous mode, the VSP
@@ -788,13 +806,6 @@ static void vsp1_dl_list_fill_header(struct vsp1_dl_list *dl, bool is_last)
 		 * instructed to do otherwise.
 		 */
 		dl->header->next_header = dl->dma;
-		dl->header->flags = VSP1_DLH_INT_ENABLE | VSP1_DLH_AUTO_START;
-	} else {
-		/*
-		 * Otherwise, in mem-to-mem mode, we work in single-shot mode
-		 * and the next display list must not be started automatically.
-		 */
-		dl->header->flags = VSP1_DLH_INT_ENABLE;
 	}
 
 	if (!dl->extension)
@@ -861,13 +872,15 @@ static void vsp1_dl_list_commit_continuous(struct vsp1_dl_list *dl)
 	 *
 	 * If a display list is already pending we simply drop it as the new
 	 * display list is assumed to contain a more recent configuration. It is
-	 * an error if the already pending list has the internal flag set, as
-	 * there is then a process waiting for that list to complete. This
-	 * shouldn't happen as the waiting process should perform proper
-	 * locking, but warn just in case.
+	 * an error if the already pending list has the
+	 * VSP1_DL_FRAME_END_INTERNAL flag set, as there is then a process
+	 * waiting for that list to complete. This shouldn't happen as the
+	 * waiting process should perform proper locking, but warn just in
+	 * case.
 	 */
 	if (vsp1_dl_list_hw_update_pending(dlm)) {
-		WARN_ON(dlm->pending && dlm->pending->internal);
+		WARN_ON(dlm->pending &&
+			(dlm->pending->flags & VSP1_DL_FRAME_END_INTERNAL));
 		__vsp1_dl_list_put(dlm->pending);
 		dlm->pending = dl;
 		return;
@@ -897,7 +910,7 @@ static void vsp1_dl_list_commit_singleshot(struct vsp1_dl_list *dl)
 	dlm->active = dl;
 }
 
-void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal)
+void vsp1_dl_list_commit(struct vsp1_dl_list *dl, unsigned int dl_flags)
 {
 	struct vsp1_dl_manager *dlm = dl->dlm;
 	struct vsp1_dl_list *dl_next;
@@ -912,7 +925,7 @@ void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal)
 		vsp1_dl_list_fill_header(dl_next, last);
 	}
 
-	dl->internal = internal;
+	dl->flags = dl_flags & ~VSP1_DL_FRAME_END_COMPLETED;
 
 	spin_lock_irqsave(&dlm->lock, flags);
 
@@ -941,9 +954,13 @@ void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal)
  * set in single-shot mode as display list processing is then not continuous and
  * races never occur.
  *
- * The VSP1_DL_FRAME_END_INTERNAL flag indicates that the previous display list
- * has completed and had been queued with the internal notification flag.
- * Internal notification is only supported for continuous mode.
+ * The following flags are only supported for continuous mode.
+ *
+ * The VSP1_DL_FRAME_END_INTERNAL flag indicates that the display list that just
+ * became active had been queued with the internal notification flag.
+ *
+ * The VSP1_DL_FRAME_END_WRITEBACK flag indicates that the previously active
+ * display list had been queued with the writeback flag.
  */
 unsigned int vsp1_dlm_irq_frame_end(struct vsp1_dl_manager *dlm)
 {
@@ -982,13 +999,24 @@ unsigned int vsp1_dlm_irq_frame_end(struct vsp1_dl_manager *dlm)
 		goto done;
 
 	/*
+	 * If the active display list has the writeback flag set, the frame
+	 * completion marks the end of the writeback capture. Return the
+	 * VSP1_DL_FRAME_END_WRITEBACK flag and reset the display list's
+	 * writeback flag.
+	 */
+	if (dlm->active && (dlm->active->flags & VSP1_DL_FRAME_END_WRITEBACK)) {
+		flags |= VSP1_DL_FRAME_END_WRITEBACK;
+		dlm->active->flags &= ~VSP1_DL_FRAME_END_WRITEBACK;
+	}
+
+	/*
 	 * The device starts processing the queued display list right after the
 	 * frame end interrupt. The display list thus becomes active.
 	 */
 	if (dlm->queued) {
-		if (dlm->queued->internal)
+		if (dlm->queued->flags & VSP1_DL_FRAME_END_INTERNAL)
 			flags |= VSP1_DL_FRAME_END_INTERNAL;
-		dlm->queued->internal = false;
+		dlm->queued->flags &= ~VSP1_DL_FRAME_END_INTERNAL;
 
 		__vsp1_dl_list_put(dlm->active);
 		dlm->active = dlm->queued;
diff --git a/drivers/media/platform/vsp1/vsp1_dl.h b/drivers/media/platform/vsp1/vsp1_dl.h
index 125750dc8b5c..bebe16483ca5 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.h
+++ b/drivers/media/platform/vsp1/vsp1_dl.h
@@ -17,8 +17,10 @@ struct vsp1_dl_body_pool;
 struct vsp1_dl_list;
 struct vsp1_dl_manager;
 
+/* Keep these flags in sync with VSP1_DU_STATUS_* in include/media/vsp1.h. */
 #define VSP1_DL_FRAME_END_COMPLETED		BIT(0)
-#define VSP1_DL_FRAME_END_INTERNAL		BIT(1)
+#define VSP1_DL_FRAME_END_WRITEBACK		BIT(1)
+#define VSP1_DL_FRAME_END_INTERNAL		BIT(2)
 
 /**
  * struct vsp1_dl_ext_cmd - Extended Display command
@@ -61,7 +63,7 @@ struct vsp1_dl_list *vsp1_dl_list_get(struct vsp1_dl_manager *dlm);
 void vsp1_dl_list_put(struct vsp1_dl_list *dl);
 struct vsp1_dl_body *vsp1_dl_list_get_body0(struct vsp1_dl_list *dl);
 struct vsp1_dl_ext_cmd *vsp1_dl_get_pre_cmd(struct vsp1_dl_list *dl);
-void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal);
+void vsp1_dl_list_commit(struct vsp1_dl_list *dl, unsigned int dl_flags);
 
 struct vsp1_dl_body_pool *
 vsp1_dl_body_pool_create(struct vsp1_device *vsp1, unsigned int num_bodies,
diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
index 84895385d2e5..a4a45d68a6ef 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.c
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -34,14 +34,16 @@ static void vsp1_du_pipeline_frame_end(struct vsp1_pipeline *pipe,
 				       unsigned int completion)
 {
 	struct vsp1_drm_pipeline *drm_pipe = to_vsp1_drm_pipeline(pipe);
-	bool complete = completion == VSP1_DL_FRAME_END_COMPLETED;
 
 	if (drm_pipe->du_complete) {
 		struct vsp1_entity *uif = drm_pipe->uif;
+		unsigned int status = completion
+				    & (VSP1_DU_STATUS_COMPLETE |
+				       VSP1_DU_STATUS_WRITEBACK);
 		u32 crc;
 
 		crc = uif ? vsp1_uif_get_crc(to_uif(&uif->subdev)) : 0;
-		drm_pipe->du_complete(drm_pipe->du_private, complete, crc);
+		drm_pipe->du_complete(drm_pipe->du_private, status, crc);
 	}
 
 	if (completion & VSP1_DL_FRAME_END_INTERNAL) {
@@ -537,6 +539,12 @@ static void vsp1_du_pipeline_configure(struct vsp1_pipeline *pipe)
 	struct vsp1_entity *next;
 	struct vsp1_dl_list *dl;
 	struct vsp1_dl_body *dlb;
+	unsigned int dl_flags = 0;
+
+	if (drm_pipe->force_brx_release)
+		dl_flags |= VSP1_DL_FRAME_END_INTERNAL;
+	if (pipe->output->writeback)
+		dl_flags |= VSP1_DL_FRAME_END_WRITEBACK;
 
 	dl = vsp1_dl_list_get(pipe->output->dlm);
 	dlb = vsp1_dl_list_get_body0(dl);
@@ -554,12 +562,42 @@ static void vsp1_du_pipeline_configure(struct vsp1_pipeline *pipe)
 		}
 
 		vsp1_entity_route_setup(entity, pipe, dlb);
-		vsp1_entity_configure_stream(entity, pipe, dlb);
+		vsp1_entity_configure_stream(entity, pipe, dl, dlb);
 		vsp1_entity_configure_frame(entity, pipe, dl, dlb);
 		vsp1_entity_configure_partition(entity, pipe, dl, dlb);
 	}
 
-	vsp1_dl_list_commit(dl, drm_pipe->force_brx_release);
+	vsp1_dl_list_commit(dl, dl_flags);
+}
+
+static int vsp1_du_pipeline_set_rwpf_format(struct vsp1_device *vsp1,
+					    struct vsp1_rwpf *rwpf,
+					    u32 pixelformat, unsigned int pitch)
+{
+	const struct vsp1_format_info *fmtinfo;
+	unsigned int chroma_hsub;
+
+	fmtinfo = vsp1_get_format_info(vsp1, pixelformat);
+	if (!fmtinfo) {
+		dev_dbg(vsp1->dev, "Unsupported pixel format %08x\n",
+			pixelformat);
+		return -EINVAL;
+	}
+
+	/*
+	 * Only formats with three planes can affect the chroma planes pitch.
+	 * All formats with two planes have a horizontal subsampling value of 2,
+	 * but combine U and V in a single chroma plane, which thus results in
+	 * the luma plane and chroma plane having the same pitch.
+	 */
+	chroma_hsub = (fmtinfo->planes == 3) ? fmtinfo->hsub : 1;
+
+	rwpf->fmtinfo = fmtinfo;
+	rwpf->format.num_planes = fmtinfo->planes;
+	rwpf->format.plane_fmt[0].bytesperline = pitch;
+	rwpf->format.plane_fmt[1].bytesperline = pitch / chroma_hsub;
+
+	return 0;
 }
 
 /* -----------------------------------------------------------------------------
@@ -700,8 +738,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int pipe_index,
 	drm_pipe->du_private = cfg->callback_data;
 
 	/* Disable the display interrupts. */
-	vsp1_write(vsp1, VI6_DISP_IRQ_STA, 0);
-	vsp1_write(vsp1, VI6_DISP_IRQ_ENB, 0);
+	vsp1_write(vsp1, VI6_DISP_IRQ_STA(pipe_index), 0);
+	vsp1_write(vsp1, VI6_DISP_IRQ_ENB(pipe_index), 0);
 
 	/* Configure all entities in the pipeline. */
 	vsp1_du_pipeline_configure(pipe);
@@ -769,9 +807,8 @@ int vsp1_du_atomic_update(struct device *dev, unsigned int pipe_index,
 {
 	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
 	struct vsp1_drm_pipeline *drm_pipe = &vsp1->drm->pipe[pipe_index];
-	const struct vsp1_format_info *fmtinfo;
-	unsigned int chroma_hsub;
 	struct vsp1_rwpf *rpf;
+	int ret;
 
 	if (rpf_index >= vsp1->info->rpf_count)
 		return -EINVAL;
@@ -804,25 +841,11 @@ int vsp1_du_atomic_update(struct device *dev, unsigned int pipe_index,
 	 * Store the format, stride, memory buffer address, crop and compose
 	 * rectangles and Z-order position and for the input.
 	 */
-	fmtinfo = vsp1_get_format_info(vsp1, cfg->pixelformat);
-	if (!fmtinfo) {
-		dev_dbg(vsp1->dev, "Unsupported pixel format %08x for RPF\n",
-			cfg->pixelformat);
-		return -EINVAL;
-	}
-
-	/*
-	 * Only formats with three planes can affect the chroma planes pitch.
-	 * All formats with two planes have a horizontal subsampling value of 2,
-	 * but combine U and V in a single chroma plane, which thus results in
-	 * the luma plane and chroma plane having the same pitch.
-	 */
-	chroma_hsub = (fmtinfo->planes == 3) ? fmtinfo->hsub : 1;
+	ret = vsp1_du_pipeline_set_rwpf_format(vsp1, rpf, cfg->pixelformat,
+					       cfg->pitch);
+	if (ret < 0)
+		return ret;
 
-	rpf->fmtinfo = fmtinfo;
-	rpf->format.num_planes = fmtinfo->planes;
-	rpf->format.plane_fmt[0].bytesperline = cfg->pitch;
-	rpf->format.plane_fmt[1].bytesperline = cfg->pitch / chroma_hsub;
 	rpf->alpha = cfg->alpha;
 
 	rpf->mem.addr[0] = cfg->mem[0];
@@ -851,12 +874,31 @@ void vsp1_du_atomic_flush(struct device *dev, unsigned int pipe_index,
 	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
 	struct vsp1_drm_pipeline *drm_pipe = &vsp1->drm->pipe[pipe_index];
 	struct vsp1_pipeline *pipe = &drm_pipe->pipe;
+	int ret;
 
 	drm_pipe->crc = cfg->crc;
 
 	mutex_lock(&vsp1->drm->lock);
+
+	if (cfg->writeback.pixelformat) {
+		const struct vsp1_du_writeback_config *wb_cfg = &cfg->writeback;
+
+		ret = vsp1_du_pipeline_set_rwpf_format(vsp1, pipe->output,
+						       wb_cfg->pixelformat,
+						       wb_cfg->pitch);
+		if (WARN_ON(ret < 0))
+			goto done;
+
+		pipe->output->mem.addr[0] = wb_cfg->mem[0];
+		pipe->output->mem.addr[1] = wb_cfg->mem[1];
+		pipe->output->mem.addr[2] = wb_cfg->mem[2];
+		pipe->output->writeback = true;
+	}
+
 	vsp1_du_pipeline_setup_inputs(vsp1, pipe);
 	vsp1_du_pipeline_configure(pipe);
+
+done:
 	mutex_unlock(&vsp1->drm->lock);
 }
 EXPORT_SYMBOL_GPL(vsp1_du_atomic_flush);
diff --git a/drivers/media/platform/vsp1/vsp1_drm.h b/drivers/media/platform/vsp1/vsp1_drm.h
index 8dfd274a59e2..e85ad4366fbb 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.h
+++ b/drivers/media/platform/vsp1/vsp1_drm.h
@@ -42,7 +42,7 @@ struct vsp1_drm_pipeline {
 	struct vsp1_du_crc_config crc;
 
 	/* Frame synchronisation */
-	void (*du_complete)(void *data, bool completed, u32 crc);
+	void (*du_complete)(void *data, unsigned int status, u32 crc);
 	void *du_private;
 };
 
diff --git a/drivers/media/platform/vsp1/vsp1_entity.c b/drivers/media/platform/vsp1/vsp1_entity.c
index a54ab528b060..aa9d2286056e 100644
--- a/drivers/media/platform/vsp1/vsp1_entity.c
+++ b/drivers/media/platform/vsp1/vsp1_entity.c
@@ -71,10 +71,11 @@ void vsp1_entity_route_setup(struct vsp1_entity *entity,
 
 void vsp1_entity_configure_stream(struct vsp1_entity *entity,
 				  struct vsp1_pipeline *pipe,
+				  struct vsp1_dl_list *dl,
 				  struct vsp1_dl_body *dlb)
 {
 	if (entity->ops->configure_stream)
-		entity->ops->configure_stream(entity, pipe, dlb);
+		entity->ops->configure_stream(entity, pipe, dl, dlb);
 }
 
 void vsp1_entity_configure_frame(struct vsp1_entity *entity,
diff --git a/drivers/media/platform/vsp1/vsp1_entity.h b/drivers/media/platform/vsp1/vsp1_entity.h
index 97acb7795cf1..a1ceb37bb837 100644
--- a/drivers/media/platform/vsp1/vsp1_entity.h
+++ b/drivers/media/platform/vsp1/vsp1_entity.h
@@ -67,7 +67,9 @@ struct vsp1_route {
  * struct vsp1_entity_operations - Entity operations
  * @destroy:	Destroy the entity.
  * @configure_stream:	Setup the hardware parameters for the stream which do
- *			not vary between frames (pipeline, formats).
+ *			not vary between frames (pipeline, formats). Note that
+ *			the vsp1_dl_list argument is only valid for display
+ *			pipeline and will be NULL for mem-to-mem pipelines.
  * @configure_frame:	Configure the runtime parameters for each frame.
  * @configure_partition: Configure partition specific parameters.
  * @max_width:	Return the max supported width of data that the entity can
@@ -78,7 +80,7 @@ struct vsp1_route {
 struct vsp1_entity_operations {
 	void (*destroy)(struct vsp1_entity *);
 	void (*configure_stream)(struct vsp1_entity *, struct vsp1_pipeline *,
-				 struct vsp1_dl_body *);
+				 struct vsp1_dl_list *, struct vsp1_dl_body *);
 	void (*configure_frame)(struct vsp1_entity *, struct vsp1_pipeline *,
 				struct vsp1_dl_list *, struct vsp1_dl_body *);
 	void (*configure_partition)(struct vsp1_entity *,
@@ -155,6 +157,7 @@ void vsp1_entity_route_setup(struct vsp1_entity *entity,
 
 void vsp1_entity_configure_stream(struct vsp1_entity *entity,
 				  struct vsp1_pipeline *pipe,
+				  struct vsp1_dl_list *dl,
 				  struct vsp1_dl_body *dlb);
 
 void vsp1_entity_configure_frame(struct vsp1_entity *entity,
diff --git a/drivers/media/platform/vsp1/vsp1_hgo.c b/drivers/media/platform/vsp1/vsp1_hgo.c
index 827373c25351..bf3f981f93a1 100644
--- a/drivers/media/platform/vsp1/vsp1_hgo.c
+++ b/drivers/media/platform/vsp1/vsp1_hgo.c
@@ -131,6 +131,7 @@ static const struct v4l2_ctrl_config hgo_num_bins_control = {
 
 static void hgo_configure_stream(struct vsp1_entity *entity,
 				 struct vsp1_pipeline *pipe,
+				 struct vsp1_dl_list *dl,
 				 struct vsp1_dl_body *dlb)
 {
 	struct vsp1_hgo *hgo = to_hgo(&entity->subdev);
diff --git a/drivers/media/platform/vsp1/vsp1_hgt.c b/drivers/media/platform/vsp1/vsp1_hgt.c
index bb6ce6fdd5f4..aa1c718e0453 100644
--- a/drivers/media/platform/vsp1/vsp1_hgt.c
+++ b/drivers/media/platform/vsp1/vsp1_hgt.c
@@ -127,6 +127,7 @@ static const struct v4l2_ctrl_config hgt_hue_areas = {
 
 static void hgt_configure_stream(struct vsp1_entity *entity,
 				 struct vsp1_pipeline *pipe,
+				 struct vsp1_dl_list *dl,
 				 struct vsp1_dl_body *dlb)
 {
 	struct vsp1_hgt *hgt = to_hgt(&entity->subdev);
diff --git a/drivers/media/platform/vsp1/vsp1_hsit.c b/drivers/media/platform/vsp1/vsp1_hsit.c
index 39ab2e0c7c18..d5ebd9d08c8a 100644
--- a/drivers/media/platform/vsp1/vsp1_hsit.c
+++ b/drivers/media/platform/vsp1/vsp1_hsit.c
@@ -129,6 +129,7 @@ static const struct v4l2_subdev_ops hsit_ops = {
 
 static void hsit_configure_stream(struct vsp1_entity *entity,
 				  struct vsp1_pipeline *pipe,
+				  struct vsp1_dl_list *dl,
 				  struct vsp1_dl_body *dlb)
 {
 	struct vsp1_hsit *hsit = to_hsit(&entity->subdev);
diff --git a/drivers/media/platform/vsp1/vsp1_lif.c b/drivers/media/platform/vsp1/vsp1_lif.c
index 8b0a26335d70..14ed5d7bd061 100644
--- a/drivers/media/platform/vsp1/vsp1_lif.c
+++ b/drivers/media/platform/vsp1/vsp1_lif.c
@@ -84,6 +84,7 @@ static const struct v4l2_subdev_ops lif_ops = {
 
 static void lif_configure_stream(struct vsp1_entity *entity,
 				 struct vsp1_pipeline *pipe,
+				 struct vsp1_dl_list *dl,
 				 struct vsp1_dl_body *dlb)
 {
 	const struct v4l2_mbus_framefmt *format;
diff --git a/drivers/media/platform/vsp1/vsp1_lut.c b/drivers/media/platform/vsp1/vsp1_lut.c
index 64c48d9459b0..9f88842d7048 100644
--- a/drivers/media/platform/vsp1/vsp1_lut.c
+++ b/drivers/media/platform/vsp1/vsp1_lut.c
@@ -147,6 +147,7 @@ static const struct v4l2_subdev_ops lut_ops = {
 
 static void lut_configure_stream(struct vsp1_entity *entity,
 				 struct vsp1_pipeline *pipe,
+				 struct vsp1_dl_list *dl,
 				 struct vsp1_dl_body *dlb)
 {
 	struct vsp1_lut *lut = to_lut(&entity->subdev);
diff --git a/drivers/media/platform/vsp1/vsp1_regs.h b/drivers/media/platform/vsp1/vsp1_regs.h
index f6e4157095cc..1bb1d39c60d9 100644
--- a/drivers/media/platform/vsp1/vsp1_regs.h
+++ b/drivers/media/platform/vsp1/vsp1_regs.h
@@ -39,12 +39,12 @@
 #define VI6_WFP_IRQ_STA_DFE		(1 << 1)
 #define VI6_WFP_IRQ_STA_FRE		(1 << 0)
 
-#define VI6_DISP_IRQ_ENB		0x0078
+#define VI6_DISP_IRQ_ENB(n)		(0x0078 + (n) * 60)
 #define VI6_DISP_IRQ_ENB_DSTE		(1 << 8)
 #define VI6_DISP_IRQ_ENB_MAEE		(1 << 5)
 #define VI6_DISP_IRQ_ENB_LNEE(n)	(1 << (n))
 
-#define VI6_DISP_IRQ_STA		0x007c
+#define VI6_DISP_IRQ_STA(n)		(0x007c + (n) * 60)
 #define VI6_DISP_IRQ_STA_DST		(1 << 8)
 #define VI6_DISP_IRQ_STA_MAE		(1 << 5)
 #define VI6_DISP_IRQ_STA_LNE(n)		(1 << (n))
@@ -307,7 +307,7 @@
 #define VI6_WPF_DSTM_ADDR_C0		0x1028
 #define VI6_WPF_DSTM_ADDR_C1		0x102c
 
-#define VI6_WPF_WRBCK_CTRL		0x1034
+#define VI6_WPF_WRBCK_CTRL(n)		(0x1034 + (n) * 0x100)
 #define VI6_WPF_WRBCK_CTRL_WBMD		(1 << 0)
 
 /* -----------------------------------------------------------------------------
diff --git a/drivers/media/platform/vsp1/vsp1_rpf.c b/drivers/media/platform/vsp1/vsp1_rpf.c
index 616afa7e165f..85587c1b6a37 100644
--- a/drivers/media/platform/vsp1/vsp1_rpf.c
+++ b/drivers/media/platform/vsp1/vsp1_rpf.c
@@ -57,6 +57,7 @@ static const struct v4l2_subdev_ops rpf_ops = {
 
 static void rpf_configure_stream(struct vsp1_entity *entity,
 				 struct vsp1_pipeline *pipe,
+				 struct vsp1_dl_list *dl,
 				 struct vsp1_dl_body *dlb)
 {
 	struct vsp1_rwpf *rpf = to_rwpf(&entity->subdev);
diff --git a/drivers/media/platform/vsp1/vsp1_rwpf.h b/drivers/media/platform/vsp1/vsp1_rwpf.h
index 70742ecf766f..2f3582590618 100644
--- a/drivers/media/platform/vsp1/vsp1_rwpf.h
+++ b/drivers/media/platform/vsp1/vsp1_rwpf.h
@@ -61,6 +61,7 @@ struct vsp1_rwpf {
 	} flip;
 
 	struct vsp1_rwpf_memory mem;
+	bool writeback;
 
 	struct vsp1_dl_manager *dlm;
 };
diff --git a/drivers/media/platform/vsp1/vsp1_sru.c b/drivers/media/platform/vsp1/vsp1_sru.c
index b1617cb1f2b9..2b65457ee12f 100644
--- a/drivers/media/platform/vsp1/vsp1_sru.c
+++ b/drivers/media/platform/vsp1/vsp1_sru.c
@@ -269,6 +269,7 @@ static const struct v4l2_subdev_ops sru_ops = {
 
 static void sru_configure_stream(struct vsp1_entity *entity,
 				 struct vsp1_pipeline *pipe,
+				 struct vsp1_dl_list *dl,
 				 struct vsp1_dl_body *dlb)
 {
 	const struct vsp1_sru_param *param;
diff --git a/drivers/media/platform/vsp1/vsp1_uds.c b/drivers/media/platform/vsp1/vsp1_uds.c
index 27012af973b2..5fc04c082d1a 100644
--- a/drivers/media/platform/vsp1/vsp1_uds.c
+++ b/drivers/media/platform/vsp1/vsp1_uds.c
@@ -257,6 +257,7 @@ static const struct v4l2_subdev_ops uds_ops = {
 
 static void uds_configure_stream(struct vsp1_entity *entity,
 				 struct vsp1_pipeline *pipe,
+				 struct vsp1_dl_list *dl,
 				 struct vsp1_dl_body *dlb)
 {
 	struct vsp1_uds *uds = to_uds(&entity->subdev);
diff --git a/drivers/media/platform/vsp1/vsp1_uif.c b/drivers/media/platform/vsp1/vsp1_uif.c
index 4b58d51df231..467d1072577b 100644
--- a/drivers/media/platform/vsp1/vsp1_uif.c
+++ b/drivers/media/platform/vsp1/vsp1_uif.c
@@ -192,6 +192,7 @@ static const struct v4l2_subdev_ops uif_ops = {
 
 static void uif_configure_stream(struct vsp1_entity *entity,
 				 struct vsp1_pipeline *pipe,
+				 struct vsp1_dl_list *dl,
 				 struct vsp1_dl_body *dlb)
 {
 	struct vsp1_uif *uif = to_uif(&entity->subdev);
diff --git a/drivers/media/platform/vsp1/vsp1_video.c b/drivers/media/platform/vsp1/vsp1_video.c
index 7ceaf3222145..fd98e483b2f4 100644
--- a/drivers/media/platform/vsp1/vsp1_video.c
+++ b/drivers/media/platform/vsp1/vsp1_video.c
@@ -307,11 +307,6 @@ static int vsp1_video_pipeline_setup_partitions(struct vsp1_pipeline *pipe)
  * This function completes the current buffer by filling its sequence number,
  * time stamp and payload size, and hands it back to the videobuf core.
  *
- * When operating in DU output mode (deep pipeline to the DU through the LIF),
- * the VSP1 needs to constantly supply frames to the display. In that case, if
- * no other buffer is queued, reuse the one that has just been processed instead
- * of handing it back to the videobuf core.
- *
  * Return the next queued buffer or NULL if the queue is empty.
  */
 static struct vsp1_vb2_buffer *
@@ -333,12 +328,6 @@ vsp1_video_complete_buffer(struct vsp1_video *video)
 	done = list_first_entry(&video->irqqueue,
 				struct vsp1_vb2_buffer, queue);
 
-	/* In DU output mode reuse the buffer if the list is singular. */
-	if (pipe->lif && list_is_singular(&video->irqqueue)) {
-		spin_unlock_irqrestore(&video->irqlock, flags);
-		return done;
-	}
-
 	list_del(&done->queue);
 
 	if (!list_empty(&video->irqqueue))
@@ -432,7 +421,7 @@ static void vsp1_video_pipeline_run(struct vsp1_pipeline *pipe)
 	}
 
 	/* Complete, and commit the head display list. */
-	vsp1_dl_list_commit(dl, false);
+	vsp1_dl_list_commit(dl, 0);
 	pipe->configured = true;
 
 	vsp1_pipeline_run(pipe);
@@ -836,7 +825,8 @@ static int vsp1_video_setup_pipeline(struct vsp1_pipeline *pipe)
 
 	list_for_each_entry(entity, &pipe->entities, list_pipe) {
 		vsp1_entity_route_setup(entity, pipe, pipe->stream_config);
-		vsp1_entity_configure_stream(entity, pipe, pipe->stream_config);
+		vsp1_entity_configure_stream(entity, pipe, NULL,
+					     pipe->stream_config);
 	}
 
 	return 0;
diff --git a/drivers/media/platform/vsp1/vsp1_wpf.c b/drivers/media/platform/vsp1/vsp1_wpf.c
index 32bb207b2007..208498fa6ed7 100644
--- a/drivers/media/platform/vsp1/vsp1_wpf.c
+++ b/drivers/media/platform/vsp1/vsp1_wpf.c
@@ -232,17 +232,41 @@ static void vsp1_wpf_destroy(struct vsp1_entity *entity)
 	vsp1_dlm_destroy(wpf->dlm);
 }
 
+static int wpf_configure_writeback_chain(struct vsp1_rwpf *wpf,
+					 struct vsp1_dl_list *dl)
+{
+	unsigned int index = wpf->entity.index;
+	struct vsp1_dl_list *dl_next;
+	struct vsp1_dl_body *dlb;
+
+	dl_next = vsp1_dl_list_get(wpf->dlm);
+	if (!dl_next) {
+		dev_err(wpf->entity.vsp1->dev,
+			"Failed to obtain a dl list, disabling writeback\n");
+		return -ENOMEM;
+	}
+
+	dlb = vsp1_dl_list_get_body0(dl_next);
+	vsp1_dl_body_write(dlb, VI6_WPF_WRBCK_CTRL(index), 0);
+	vsp1_dl_list_add_chain(dl, dl_next);
+
+	return 0;
+}
+
 static void wpf_configure_stream(struct vsp1_entity *entity,
 				 struct vsp1_pipeline *pipe,
+				 struct vsp1_dl_list *dl,
 				 struct vsp1_dl_body *dlb)
 {
 	struct vsp1_rwpf *wpf = to_rwpf(&entity->subdev);
 	struct vsp1_device *vsp1 = wpf->entity.vsp1;
 	const struct v4l2_mbus_framefmt *source_format;
 	const struct v4l2_mbus_framefmt *sink_format;
+	unsigned int index = wpf->entity.index;
 	unsigned int i;
 	u32 outfmt = 0;
 	u32 srcrpf = 0;
+	int ret;
 
 	sink_format = vsp1_entity_get_pad_format(&wpf->entity,
 						 wpf->entity.config,
@@ -250,8 +274,9 @@ static void wpf_configure_stream(struct vsp1_entity *entity,
 	source_format = vsp1_entity_get_pad_format(&wpf->entity,
 						   wpf->entity.config,
 						   RWPF_PAD_SOURCE);
+
 	/* Format */
-	if (!pipe->lif) {
+	if (!pipe->lif || wpf->writeback) {
 		const struct v4l2_pix_format_mplane *format = &wpf->format;
 		const struct vsp1_format_info *fmtinfo = wpf->fmtinfo;
 
@@ -276,8 +301,7 @@ static void wpf_configure_stream(struct vsp1_entity *entity,
 
 		vsp1_wpf_write(wpf, dlb, VI6_WPF_DSWAP, fmtinfo->swap);
 
-		if (vsp1_feature(vsp1, VSP1_HAS_WPF_HFLIP) &&
-		    wpf->entity.index == 0)
+		if (vsp1_feature(vsp1, VSP1_HAS_WPF_HFLIP) && index == 0)
 			vsp1_wpf_write(wpf, dlb, VI6_WPF_ROT_CTRL,
 				       VI6_WPF_ROT_CTRL_LN16 |
 				       (256 << VI6_WPF_ROT_CTRL_LMEM_WD_SHIFT));
@@ -288,11 +312,9 @@ static void wpf_configure_stream(struct vsp1_entity *entity,
 
 	wpf->outfmt = outfmt;
 
-	vsp1_dl_body_write(dlb, VI6_DPR_WPF_FPORCH(wpf->entity.index),
+	vsp1_dl_body_write(dlb, VI6_DPR_WPF_FPORCH(index),
 			   VI6_DPR_WPF_FPORCH_FP_WPFN);
 
-	vsp1_dl_body_write(dlb, VI6_WPF_WRBCK_CTRL, 0);
-
 	/*
 	 * Sources. If the pipeline has a single input and BRx is not used,
 	 * configure it as the master layer. Otherwise configure all
@@ -318,9 +340,26 @@ static void wpf_configure_stream(struct vsp1_entity *entity,
 	vsp1_wpf_write(wpf, dlb, VI6_WPF_SRCRPF, srcrpf);
 
 	/* Enable interrupts. */
-	vsp1_dl_body_write(dlb, VI6_WPF_IRQ_STA(wpf->entity.index), 0);
-	vsp1_dl_body_write(dlb, VI6_WPF_IRQ_ENB(wpf->entity.index),
+	vsp1_dl_body_write(dlb, VI6_WPF_IRQ_STA(index), 0);
+	vsp1_dl_body_write(dlb, VI6_WPF_IRQ_ENB(index),
 			   VI6_WFP_IRQ_ENB_DFEE);
+
+	/*
+	 * Configure writeback for display pipelines (the wpf writeback flag is
+	 * never set for memory-to-memory pipelines). Start by adding a chained
+	 * display list to disable writeback after a single frame, and process
+	 * to enable writeback. If the display list allocation fails don't
+	 * enable writeback as we wouldn't be able to safely disable it,
+	 * resulting in possible memory corruption.
+	 */
+	if (wpf->writeback) {
+		ret = wpf_configure_writeback_chain(wpf, dl);
+		if (ret < 0)
+			wpf->writeback = false;
+	}
+
+	vsp1_dl_body_write(dlb, VI6_WPF_WRBCK_CTRL(index),
+			   wpf->writeback ? VI6_WPF_WRBCK_CTRL_WBMD : 0);
 }
 
 static void wpf_configure_frame(struct vsp1_entity *entity,
@@ -362,6 +401,7 @@ static void wpf_configure_partition(struct vsp1_entity *entity,
 	const struct vsp1_format_info *fmtinfo = wpf->fmtinfo;
 	unsigned int width;
 	unsigned int height;
+	unsigned int left;
 	unsigned int offset;
 	unsigned int flip;
 	unsigned int i;
@@ -371,13 +411,16 @@ static void wpf_configure_partition(struct vsp1_entity *entity,
 						 RWPF_PAD_SINK);
 	width = sink_format->width;
 	height = sink_format->height;
+	left = 0;
 
 	/*
 	 * Cropping. The partition algorithm can split the image into
 	 * multiple slices.
 	 */
-	if (pipe->partitions > 1)
+	if (pipe->partitions > 1) {
 		width = pipe->partition->wpf.width;
+		left = pipe->partition->wpf.left;
+	}
 
 	vsp1_wpf_write(wpf, dlb, VI6_WPF_HSZCLIP, VI6_WPF_SZCLIP_EN |
 		       (0 << VI6_WPF_SZCLIP_OFST_SHIFT) |
@@ -386,7 +429,11 @@ static void wpf_configure_partition(struct vsp1_entity *entity,
 		       (0 << VI6_WPF_SZCLIP_OFST_SHIFT) |
 		       (height << VI6_WPF_SZCLIP_SIZE_SHIFT));
 
-	if (pipe->lif)
+	/*
+	 * For display pipelines without writeback enabled there's no memory
+	 * address to configure, return now.
+	 */
+	if (pipe->lif && !wpf->writeback)
 		return;
 
 	/*
@@ -408,13 +455,11 @@ static void wpf_configure_partition(struct vsp1_entity *entity,
 	flip = wpf->flip.active;
 
 	if (flip & BIT(WPF_CTRL_HFLIP) && !wpf->flip.rotate)
-		offset = format->width - pipe->partition->wpf.left
-			- pipe->partition->wpf.width;
+		offset = format->width - left - width;
 	else if (flip & BIT(WPF_CTRL_VFLIP) && wpf->flip.rotate)
-		offset = format->height - pipe->partition->wpf.left
-			- pipe->partition->wpf.width;
+		offset = format->height - left - width;
 	else
-		offset = pipe->partition->wpf.left;
+		offset = left;
 
 	for (i = 0; i < format->num_planes; ++i) {
 		unsigned int hsub = i > 0 ? fmtinfo->hsub : 1;
@@ -436,7 +481,7 @@ static void wpf_configure_partition(struct vsp1_entity *entity,
 		 * image height.
 		 */
 		if (wpf->flip.rotate)
-			height = pipe->partition->wpf.width;
+			height = width;
 		else
 			height = format->height;
 
@@ -477,6 +522,12 @@ static void wpf_configure_partition(struct vsp1_entity *entity,
 	vsp1_wpf_write(wpf, dlb, VI6_WPF_DSTM_ADDR_Y, mem.addr[0]);
 	vsp1_wpf_write(wpf, dlb, VI6_WPF_DSTM_ADDR_C0, mem.addr[1]);
 	vsp1_wpf_write(wpf, dlb, VI6_WPF_DSTM_ADDR_C1, mem.addr[2]);
+
+	/*
+	 * Writeback operates in single-shot mode and lasts for a single frame,
+	 * reset the writeback flag to false for the next frame.
+	 */
+	wpf->writeback = false;
 }
 
 static unsigned int wpf_max_width(struct vsp1_entity *entity,
diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h
index cfb7be40bed7..8f3602811eb5 100644
--- a/include/drm/drm_modeset_helper_vtables.h
+++ b/include/drm/drm_modeset_helper_vtables.h
@@ -49,6 +49,8 @@
  */
 
 enum mode_set_atomic;
+struct drm_writeback_connector;
+struct drm_writeback_job;
 
 /**
  * struct drm_crtc_helper_funcs - helper operations for CRTCs
@@ -989,6 +991,11 @@ struct drm_connector_helper_funcs {
 	 */
 	void (*atomic_commit)(struct drm_connector *connector,
 			      struct drm_connector_state *state);
+
+	int (*prepare_writeback_job)(struct drm_writeback_connector *connector,
+				     struct drm_writeback_job *job);
+	void (*cleanup_writeback_job)(struct drm_writeback_connector *connector,
+				      struct drm_writeback_job *job);
 };
 
 /**
diff --git a/include/drm/drm_writeback.h b/include/drm/drm_writeback.h
index 23df9d463003..777c14c847f0 100644
--- a/include/drm/drm_writeback.h
+++ b/include/drm/drm_writeback.h
@@ -80,6 +80,20 @@ struct drm_writeback_connector {
 
 struct drm_writeback_job {
 	/**
+	 * @connector:
+	 *
+	 * Back-pointer to the writeback connector associated with the job
+	 */
+	struct drm_writeback_connector *connector;
+
+	/**
+	 * @prepared:
+	 *
+	 * Set when the job has been prepared with drm_writeback_prepare_job()
+	 */
+	bool prepared;
+
+	/**
 	 * @cleanup_work:
 	 *
 	 * Used to allow drm_writeback_signal_completion to defer dropping the
@@ -98,7 +112,7 @@ struct drm_writeback_job {
 	 * @fb:
 	 *
 	 * Framebuffer to be written to by the writeback connector. Do not set
-	 * directly, use drm_atomic_set_writeback_fb_for_connector()
+	 * directly, use drm_writeback_set_fb()
 	 */
 	struct drm_framebuffer *fb;
 
@@ -108,6 +122,13 @@ struct drm_writeback_job {
 	 * Fence which will signal once the writeback has completed
 	 */
 	struct dma_fence *out_fence;
+
+	/**
+	 * @priv:
+	 *
+	 * Driver-private data
+	 */
+	void *priv;
 };
 
 static inline struct drm_writeback_connector *
@@ -122,8 +143,13 @@ int drm_writeback_connector_init(struct drm_device *dev,
 				 const struct drm_encoder_helper_funcs *enc_helper_funcs,
 				 const u32 *formats, int n_formats);
 
+int drm_writeback_set_fb(struct drm_connector_state *conn_state,
+			 struct drm_framebuffer *fb);
+
+int drm_writeback_prepare_job(struct drm_writeback_job *job);
+
 void drm_writeback_queue_job(struct drm_writeback_connector *wb_connector,
-			     struct drm_writeback_job *job);
+			     struct drm_connector_state *conn_state);
 
 void drm_writeback_cleanup_job(struct drm_writeback_job *job);
 
diff --git a/include/media/vsp1.h b/include/media/vsp1.h
index 1cf868360701..cc1b0d42ce95 100644
--- a/include/media/vsp1.h
+++ b/include/media/vsp1.h
@@ -17,6 +17,9 @@ struct device;
 
 int vsp1_du_init(struct device *dev);
 
+#define VSP1_DU_STATUS_COMPLETE		BIT(0)
+#define VSP1_DU_STATUS_WRITEBACK	BIT(1)
+
 /**
  * struct vsp1_du_lif_config - VSP LIF configuration
  * @width: output frame width
@@ -32,7 +35,7 @@ struct vsp1_du_lif_config {
 	unsigned int height;
 	bool interlaced;
 
-	void (*callback)(void *data, bool completed, u32 crc);
+	void (*callback)(void *data, unsigned int status, u32 crc);
 	void *callback_data;
 };
 
@@ -82,11 +85,25 @@ struct vsp1_du_crc_config {
 };
 
 /**
+ * struct vsp1_du_writeback_config - VSP writeback configuration parameters
+ * @pixelformat: plane pixel format (V4L2 4CC)
+ * @pitch: line pitch in bytes for the first plane
+ * @mem: DMA memory address for each plane of the frame buffer
+ */
+struct vsp1_du_writeback_config {
+	u32 pixelformat;
+	unsigned int pitch;
+	dma_addr_t mem[3];
+};
+
+/**
  * struct vsp1_du_atomic_pipe_config - VSP atomic pipe configuration parameters
  * @crc: CRC computation configuration
+ * @writeback: writeback configuration
  */
 struct vsp1_du_atomic_pipe_config {
 	struct vsp1_du_crc_config crc;
+	struct vsp1_du_writeback_config writeback;
 };
 
 void vsp1_du_atomic_begin(struct device *dev, unsigned int pipe_index);