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

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

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

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

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

  Summary:

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

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

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

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

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

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

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

  nouveau:
   - misc fixes

  etnaviv:
   - misc fixes

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

  exynos:
   - Logging cleanups

  tegra:
   - Shared reset fix
   - CPU cache maintenance fix

  cirrus:
   - driver rewritten using simple helpers

  meson:
   - G12A support

  vmwgfx:
   - Resource dirtying management improvements
   - Userspace logging improvements

  virtio:
   - PRIME fixes

  rockchip:
   - rk3066 hdmi support

  sun4i:
   - DSI burst mode support

  vc4:
   - load tracker to detect underflow

  v3d:
   - v3d v4.2 support

  malidp:
   - initial Mali D71 support in komeda driver

  tfp410:
   - omap related improvement

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

  rcar-du:
   - Display writeback support"

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

21 files changed, 221 insertions, 92 deletions

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,