Merge tag 'drm-misc-next-2019-05-24' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for v5.3, try #2:

UAPI Changes:
- Add HDR source metadata property.
- Make drm.h compile on GNU/kFreeBSD by including stdint.h
- Clarify how the userspace reviewer has to review new kernel UAPI.
- Clarify that for using new UAPI, merging to drm-next or drm-misc-next should be enough.

Cross-subsystem Changes:
- video/hdmi: Add unpack function for DRM infoframes.
- Device tree bindings:
  * Updating a property for Mali Midgard GPUs
  * Updating a property for STM32 DSI panel
  * Adding support for FriendlyELEC HD702E 800x1280 panel
  * Adding support for Evervision VGG804821 800x480 5.0" WVGA TFT panel
  * Adding support for the EDT ET035012DM6 3.5" 320x240 QVGA 24-bit RGB TFT.
  * Adding support for Three Five displays TFC S9700RTWV43TR-01B 800x480 panel
    with resistive touch found on TI's AM335X-EVM.
  * Adding support for EDT ETM0430G0DH6 480x272 panel.
- Add OSD101T2587-53TS driver with DT bindings.
- Add Samsung S6E63M0 panel driver with DT bindings.
- Add VXT VL050-8048NT-C01 800x480 panel with DT bindings.
- Dma-buf:
  - Make mmap callback actually optional.
  - Documentation updates.
  - Fix debugfs refcount inbalance.
  - Remove unused sync_dump function.
- Fix device tree bindings in drm-misc-next after a botched merge.

Core Changes:
- Add support for HDR infoframes and related EDID parsing.
- Remove prime sg_table caching, now done inside dma-buf.
- Add shiny new drm_gem_vram helpers for simple VRAM drivers;
  with some fixes to the new API on top.
- Small fix to job cleanup without timeout handler.
- Documentation fixes to drm_fourcc.
- Replace lookups of drm_format with struct drm_format_info;
  remove functions that become obsolete by this conversion.
- Remove double include in bridge/panel.c and some drivers.
- Remove drmP.h include from drm/edid and drm/dp.
- Fix null pointer deref in drm_fb_helper_hotplug_event().
- Remove most members from drm_fb_helper_crtc, only mode_set is kept.
- Remove race of fb helpers with userspace; only restore mode
  when userspace is not master.
- Move legacy setup from drm_file.c to drm_legacy_misc.c
- Rework scheduler job destruction.
- drm/bus was removed, remove from TODO.
- Add __drm_atomic_helper_crtc_reset() to subclass crtc_state,
  and convert some drivers to use it (conversion is not complete yet).
- Bump vblank timeout wait to 100 ms for atomic.
- Docbook fix for drm_hdmi_infoframe_set_hdr_metadata.

Driver Changes:
- sun4i: Use DRM_GEM_CMA_VMAP_DRIVER_OPS instead of definining manually.
- v3d: Small cleanups, adding support for compute shaders,
       reservation/synchronization fixes and job management refactoring,
       fixes MMU and debugfs.
- lima: Fix null pointer in irq handler on startup, set default timeout for scheduled jobs.
- stm/ltdc: Assorted fixes and adding FB modifier support.
- amdgpu: Avoid hw reset if guilty job was already signaled.
- virtio: Add seqno to fences, add trace events, use correct flags for fence allocation.
- Convert AST, bochs, mgag200, vboxvideo, hisilicon to the new drm_gem_vram API.
- sun6i_mipi_dsi: Support DSI GENERIC_SHORT_WRITE_2 transfers.
- bochs: Small fix to use PTR_RET_OR_ZERO and driver unload.
- gma500: header fixes
- cirrus: Remove unused files.
- mediatek: Fix compiler warning after merging the HDR series.
- vc4: Rework binner bo handling.

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/052875a5-27ba-3832-60c2-193d950afdff@linux.intel.com

10 files changed, 982 insertions, 390 deletions

diff --git a/drivers/gpu/drm/v3d/v3d_debugfs.c b/drivers/gpu/drm/v3d/v3d_debugfs.c
index a24af2d2f574..78a78938e81f 100644
--- a/drivers/gpu/drm/v3d/v3d_debugfs.c
+++ b/drivers/gpu/drm/v3d/v3d_debugfs.c
@@ -26,6 +26,11 @@ static const struct v3d_reg_def v3d_hub_reg_defs[] = {
 	REGDEF(V3D_HUB_IDENT3),
 	REGDEF(V3D_HUB_INT_STS),
 	REGDEF(V3D_HUB_INT_MSK_STS),
+
+	REGDEF(V3D_MMU_CTL),
+	REGDEF(V3D_MMU_VIO_ADDR),
+	REGDEF(V3D_MMU_VIO_ID),
+	REGDEF(V3D_MMU_DEBUG_INFO),
 };
 
 static const struct v3d_reg_def v3d_gca_reg_defs[] = {
@@ -50,12 +55,25 @@ static const struct v3d_reg_def v3d_core_reg_defs[] = {
 	REGDEF(V3D_PTB_BPCA),
 	REGDEF(V3D_PTB_BPCS),
 
-	REGDEF(V3D_MMU_CTL),
-	REGDEF(V3D_MMU_VIO_ADDR),
-
 	REGDEF(V3D_GMP_STATUS),
 	REGDEF(V3D_GMP_CFG),
 	REGDEF(V3D_GMP_VIO_ADDR),
+
+	REGDEF(V3D_ERR_FDBGO),
+	REGDEF(V3D_ERR_FDBGB),
+	REGDEF(V3D_ERR_FDBGS),
+	REGDEF(V3D_ERR_STAT),
+};
+
+static const struct v3d_reg_def v3d_csd_reg_defs[] = {
+	REGDEF(V3D_CSD_STATUS),
+	REGDEF(V3D_CSD_CURRENT_CFG0),
+	REGDEF(V3D_CSD_CURRENT_CFG1),
+	REGDEF(V3D_CSD_CURRENT_CFG2),
+	REGDEF(V3D_CSD_CURRENT_CFG3),
+	REGDEF(V3D_CSD_CURRENT_CFG4),
+	REGDEF(V3D_CSD_CURRENT_CFG5),
+	REGDEF(V3D_CSD_CURRENT_CFG6),
 };
 
 static int v3d_v3d_debugfs_regs(struct seq_file *m, void *unused)
@@ -89,6 +107,17 @@ static int v3d_v3d_debugfs_regs(struct seq_file *m, void *unused)
 				   V3D_CORE_READ(core,
 						 v3d_core_reg_defs[i].reg));
 		}
+
+		if (v3d_has_csd(v3d)) {
+			for (i = 0; i < ARRAY_SIZE(v3d_csd_reg_defs); i++) {
+				seq_printf(m, "core %d %s (0x%04x): 0x%08x\n",
+					   core,
+					   v3d_csd_reg_defs[i].name,
+					   v3d_csd_reg_defs[i].reg,
+					   V3D_CORE_READ(core,
+							 v3d_csd_reg_defs[i].reg));
+			}
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index a06b05f714a5..fea597f4db8a 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -7,9 +7,9 @@
  * This driver supports the Broadcom V3D 3.3 and 4.1 OpenGL ES GPUs.
  * For V3D 2.x support, see the VC4 driver.
  *
- * Currently only single-core rendering using the binner and renderer,
- * along with TFU (texture formatting unit) rendering is supported.
- * V3D 4.x's CSD (compute shader dispatch) is not yet supported.
+ * The V3D GPU includes a tiled render (composed of a bin and render
+ * pipelines), the TFU (texture formatting unit), and the CSD (compute
+ * shader dispatch).
  */
 
 #include <linux/clk.h>
@@ -120,6 +120,9 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data,
 	case DRM_V3D_PARAM_SUPPORTS_TFU:
 		args->value = 1;
 		return 0;
+	case DRM_V3D_PARAM_SUPPORTS_CSD:
+		args->value = v3d_has_csd(v3d);
+		return 0;
 	default:
 		DRM_DEBUG("Unknown parameter %d\n", args->param);
 		return -EINVAL;
@@ -179,6 +182,7 @@ static const struct drm_ioctl_desc v3d_drm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(V3D_GET_PARAM, v3d_get_param_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(V3D_GET_BO_OFFSET, v3d_get_bo_offset_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(V3D_SUBMIT_TFU, v3d_submit_tfu_ioctl, DRM_RENDER_ALLOW | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(V3D_SUBMIT_CSD, v3d_submit_csd_ioctl, DRM_RENDER_ALLOW | DRM_AUTH),
 };
 
 static struct drm_driver v3d_drm_driver = {
@@ -235,9 +239,9 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 	struct drm_device *drm;
 	struct v3d_dev *v3d;
 	int ret;
+	u32 mmu_debug;
 	u32 ident1;
 
-	dev->coherent_dma_mask = DMA_BIT_MASK(36);
 
 	v3d = kzalloc(sizeof(*v3d), GFP_KERNEL);
 	if (!v3d)
@@ -254,6 +258,11 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 	if (ret)
 		goto dev_free;
 
+	mmu_debug = V3D_READ(V3D_MMU_DEBUG_INFO);
+	dev->coherent_dma_mask =
+		DMA_BIT_MASK(30 + V3D_GET_FIELD(mmu_debug, V3D_MMU_PA_WIDTH));
+	v3d->va_width = 30 + V3D_GET_FIELD(mmu_debug, V3D_MMU_VA_WIDTH);
+
 	ident1 = V3D_READ(V3D_HUB_IDENT1);
 	v3d->ver = (V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_TVER) * 10 +
 		    V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_REV));
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index e9d4a2fdcf44..9aad9da1eb11 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -16,9 +16,11 @@ enum v3d_queue {
 	V3D_BIN,
 	V3D_RENDER,
 	V3D_TFU,
+	V3D_CSD,
+	V3D_CACHE_CLEAN,
 };
 
-#define V3D_MAX_QUEUES (V3D_TFU + 1)
+#define V3D_MAX_QUEUES (V3D_CACHE_CLEAN + 1)
 
 struct v3d_queue_state {
 	struct drm_gpu_scheduler sched;
@@ -55,6 +57,8 @@ struct v3d_dev {
 	 */
 	void *mmu_scratch;
 	dma_addr_t mmu_scratch_paddr;
+	/* virtual address bits from V3D to the MMU. */
+	int va_width;
 
 	/* Number of V3D cores. */
 	u32 cores;
@@ -67,9 +71,10 @@ struct v3d_dev {
 
 	struct work_struct overflow_mem_work;
 
-	struct v3d_exec_info *bin_job;
-	struct v3d_exec_info *render_job;
+	struct v3d_bin_job *bin_job;
+	struct v3d_render_job *render_job;
 	struct v3d_tfu_job *tfu_job;
+	struct v3d_csd_job *csd_job;
 
 	struct v3d_queue_state queue[V3D_MAX_QUEUES];
 
@@ -92,6 +97,12 @@ struct v3d_dev {
 	 */
 	struct mutex sched_lock;
 
+	/* Lock taken during a cache clean and when initiating an L2
+	 * flush, to keep L2 flushes from interfering with the
+	 * synchronous L2 cleans.
+	 */
+	struct mutex cache_clean_lock;
+
 	struct {
 		u32 num_allocated;
 		u32 pages_allocated;
@@ -104,6 +115,12 @@ to_v3d_dev(struct drm_device *dev)
 	return (struct v3d_dev *)dev->dev_private;
 }
 
+static inline bool
+v3d_has_csd(struct v3d_dev *v3d)
+{
+	return v3d->ver >= 41;
+}
+
 /* The per-fd struct, which tracks the MMU mappings. */
 struct v3d_file_priv {
 	struct v3d_dev *v3d;
@@ -117,7 +134,7 @@ struct v3d_bo {
 	struct drm_mm_node node;
 
 	/* List entry for the BO's position in
-	 * v3d_exec_info->unref_list
+	 * v3d_render_job->unref_list
 	 */
 	struct list_head unref_head;
 };
@@ -157,67 +174,74 @@ to_v3d_fence(struct dma_fence *fence)
 struct v3d_job {
 	struct drm_sched_job base;
 
-	struct v3d_exec_info *exec;
+	struct kref refcount;
 
-	/* An optional fence userspace can pass in for the job to depend on. */
-	struct dma_fence *in_fence;
+	struct v3d_dev *v3d;
+
+	/* This is the array of BOs that were looked up at the start
+	 * of submission.
+	 */
+	struct drm_gem_object **bo;
+	u32 bo_count;
+
+	/* Array of struct dma_fence * to block on before submitting this job.
+	 */
+	struct xarray deps;
+	unsigned long last_dep;
 
 	/* v3d fence to be signaled by IRQ handler when the job is complete. */
 	struct dma_fence *irq_fence;
 
+	/* scheduler fence for when the job is considered complete and
+	 * the BO reservations can be released.
+	 */
+	struct dma_fence *done_fence;
+
+	/* Callback for the freeing of the job on refcount going to 0. */
+	void (*free)(struct kref *ref);
+};
+
+struct v3d_bin_job {
+	struct v3d_job base;
+
 	/* GPU virtual addresses of the start/end of the CL job. */
 	u32 start, end;
 
 	u32 timedout_ctca, timedout_ctra;
-};
 
-struct v3d_exec_info {
-	struct v3d_dev *v3d;
+	/* Corresponding render job, for attaching our overflow memory. */
+	struct v3d_render_job *render;
 
-	struct v3d_job bin, render;
-
-	/* Fence for when the scheduler considers the binner to be
-	 * done, for render to depend on.
-	 */
-	struct dma_fence *bin_done_fence;
+	/* Submitted tile memory allocation start/size, tile state. */
+	u32 qma, qms, qts;
+};
 
-	/* Fence for when the scheduler considers the render to be
-	 * done, for when the BOs reservations should be complete.
-	 */
-	struct dma_fence *render_done_fence;
+struct v3d_render_job {
+	struct v3d_job base;
 
-	struct kref refcount;
+	/* GPU virtual addresses of the start/end of the CL job. */
+	u32 start, end;
 
-	/* This is the array of BOs that were looked up at the start of exec. */
-	struct v3d_bo **bo;
-	u32 bo_count;
+	u32 timedout_ctca, timedout_ctra;
 
 	/* List of overflow BOs used in the job that need to be
 	 * released once the job is complete.
 	 */
 	struct list_head unref_list;
-
-	/* Submitted tile memory allocation start/size, tile state. */
-	u32 qma, qms, qts;
 };
 
 struct v3d_tfu_job {
-	struct drm_sched_job base;
+	struct v3d_job base;
 
 	struct drm_v3d_submit_tfu args;
+};
 
-	/* An optional fence userspace can pass in for the job to depend on. */
-	struct dma_fence *in_fence;
-
-	/* v3d fence to be signaled by IRQ handler when the job is complete. */
-	struct dma_fence *irq_fence;
-
-	struct v3d_dev *v3d;
+struct v3d_csd_job {
+	struct v3d_job base;
 
-	struct kref refcount;
+	u32 timedout_batches;
 
-	/* This is the array of BOs that were looked up at the start of exec. */
-	struct v3d_bo *bo[4];
+	struct drm_v3d_submit_csd args;
 };
 
 /**
@@ -281,12 +305,14 @@ int v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 int v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv);
+int v3d_submit_csd_ioctl(struct drm_device *dev, void *data,
+			 struct drm_file *file_priv);
 int v3d_wait_bo_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file_priv);
-void v3d_exec_put(struct v3d_exec_info *exec);
-void v3d_tfu_job_put(struct v3d_tfu_job *exec);
+void v3d_job_put(struct v3d_job *job);
 void v3d_reset(struct v3d_dev *v3d);
 void v3d_invalidate_caches(struct v3d_dev *v3d);
+void v3d_clean_caches(struct v3d_dev *v3d);
 
 /* v3d_irq.c */
 int v3d_irq_init(struct v3d_dev *v3d);
diff --git a/drivers/gpu/drm/v3d/v3d_fence.c b/drivers/gpu/drm/v3d/v3d_fence.c
index b0a2a1ae2eb1..89840ed212c0 100644
--- a/drivers/gpu/drm/v3d/v3d_fence.c
+++ b/drivers/gpu/drm/v3d/v3d_fence.c
@@ -36,6 +36,8 @@ static const char *v3d_fence_get_timeline_name(struct dma_fence *fence)
 		return "v3d-render";
 	case V3D_TFU:
 		return "v3d-tfu";
+	case V3D_CSD:
+		return "v3d-csd";
 	default:
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 93ff8fcbe475..27e0f87075d9 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -109,7 +109,9 @@ v3d_reset(struct v3d_dev *v3d)
 {
 	struct drm_device *dev = &v3d->drm;
 
-	DRM_ERROR("Resetting GPU.\n");
+	DRM_DEV_ERROR(dev->dev, "Resetting GPU for hang.\n");
+	DRM_DEV_ERROR(dev->dev, "V3D_ERR_STAT: 0x%08x\n",
+		      V3D_CORE_READ(0, V3D_ERR_STAT));
 	trace_v3d_reset_begin(dev);
 
 	/* XXX: only needed for safe powerdown, not reset. */
@@ -162,10 +164,52 @@ v3d_flush_l2t(struct v3d_dev *v3d, int core)
 	/* While there is a busy bit (V3D_L2TCACTL_L2TFLS), we don't
 	 * need to wait for completion before dispatching the job --
 	 * L2T accesses will be stalled until the flush has completed.
+	 * However, we do need to make sure we don't try to trigger a
+	 * new flush while the L2_CLEAN queue is trying to
+	 * synchronously clean after a job.
 	 */
+	mutex_lock(&v3d->cache_clean_lock);
 	V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL,
 		       V3D_L2TCACTL_L2TFLS |
 		       V3D_SET_FIELD(V3D_L2TCACTL_FLM_FLUSH, V3D_L2TCACTL_FLM));
+	mutex_unlock(&v3d->cache_clean_lock);
+}
+
+/* Cleans texture L1 and L2 cachelines (writing back dirty data).
+ *
+ * For cleaning, which happens from the CACHE_CLEAN queue after CSD has
+ * executed, we need to make sure that the clean is done before
+ * signaling job completion.  So, we synchronously wait before
+ * returning, and we make sure that L2 invalidates don't happen in the
+ * meantime to confuse our are-we-done checks.
+ */
+void
+v3d_clean_caches(struct v3d_dev *v3d)
+{
+	struct drm_device *dev = &v3d->drm;
+	int core = 0;
+
+	trace_v3d_cache_clean_begin(dev);
+
+	V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL, V3D_L2TCACTL_TMUWCF);
+	if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
+		       V3D_L2TCACTL_L2TFLS), 100)) {
+		DRM_ERROR("Timeout waiting for L1T write combiner flush\n");
+	}
+
+	mutex_lock(&v3d->cache_clean_lock);
+	V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL,
+		       V3D_L2TCACTL_L2TFLS |
+		       V3D_SET_FIELD(V3D_L2TCACTL_FLM_CLEAN, V3D_L2TCACTL_FLM));
+
+	if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
+		       V3D_L2TCACTL_L2TFLS), 100)) {
+		DRM_ERROR("Timeout waiting for L2T clean\n");
+	}
+
+	mutex_unlock(&v3d->cache_clean_lock);
+
+	trace_v3d_cache_clean_end(dev);
 }
 
 /* Invalidates the slice caches.  These are read-only caches. */
@@ -193,28 +237,6 @@ v3d_invalidate_caches(struct v3d_dev *v3d)
 	v3d_invalidate_slices(v3d, 0);
 }
 
-static void
-v3d_attach_object_fences(struct v3d_bo **bos, int bo_count,
-			 struct dma_fence *fence)
-{
-	int i;
-
-	for (i = 0; i < bo_count; i++) {
-		/* XXX: Use shared fences for read-only objects. */
-		reservation_object_add_excl_fence(bos[i]->base.base.resv,
-						  fence);
-	}
-}
-
-static void
-v3d_unlock_bo_reservations(struct v3d_bo **bos,
-			   int bo_count,
-			   struct ww_acquire_ctx *acquire_ctx)
-{
-	drm_gem_unlock_reservations((struct drm_gem_object **)bos, bo_count,
-				    acquire_ctx);
-}
-
 /* Takes the reservation lock on all the BOs being referenced, so that
  * at queue submit time we can update the reservations.
  *
@@ -223,26 +245,21 @@ v3d_unlock_bo_reservations(struct v3d_bo **bos,
  * to v3d, so we don't attach dma-buf fences to them.
  */
 static int
-v3d_lock_bo_reservations(struct v3d_bo **bos,
-			 int bo_count,
+v3d_lock_bo_reservations(struct v3d_job *job,
 			 struct ww_acquire_ctx *acquire_ctx)
 {
 	int i, ret;
 
-	ret = drm_gem_lock_reservations((struct drm_gem_object **)bos,
-					bo_count, acquire_ctx);
+	ret = drm_gem_lock_reservations(job->bo, job->bo_count, acquire_ctx);
 	if (ret)
 		return ret;
 
-	/* Reserve space for our shared (read-only) fence references,
-	 * before we commit the CL to the hardware.
-	 */
-	for (i = 0; i < bo_count; i++) {
-		ret = reservation_object_reserve_shared(bos[i]->base.base.resv,
-							1);
+	for (i = 0; i < job->bo_count; i++) {
+		ret = drm_gem_fence_array_add_implicit(&job->deps,
+						       job->bo[i], true);
 		if (ret) {
-			v3d_unlock_bo_reservations(bos, bo_count,
-						   acquire_ctx);
+			drm_gem_unlock_reservations(job->bo, job->bo_count,
+						    acquire_ctx);
 			return ret;
 		}
 	}
@@ -251,11 +268,11 @@ v3d_lock_bo_reservations(struct v3d_bo **bos,
 }
 
 /**
- * v3d_cl_lookup_bos() - Sets up exec->bo[] with the GEM objects
+ * v3d_lookup_bos() - Sets up job->bo[] with the GEM objects
  * referenced by the job.
  * @dev: DRM device
  * @file_priv: DRM file for this fd
- * @exec: V3D job being set up
+ * @job: V3D job being set up
  *
  * The command validator needs to reference BOs by their index within
  * the submitted job's BO list.  This does the validation of the job's
@@ -265,18 +282,19 @@ v3d_lock_bo_reservations(struct v3d_bo **bos,
  * failure, because that will happen at v3d_exec_cleanup() time.
  */
 static int
-v3d_cl_lookup_bos(struct drm_device *dev,
-		  struct drm_file *file_priv,
-		  struct drm_v3d_submit_cl *args,
-		  struct v3d_exec_info *exec)
+v3d_lookup_bos(struct drm_device *dev,
+	       struct drm_file *file_priv,
+	       struct v3d_job *job,
+	       u64 bo_handles,
+	       u32 bo_count)
 {
 	u32 *handles;
 	int ret = 0;
 	int i;
 
-	exec->bo_count = args->bo_handle_count;
+	job->bo_count = bo_count;
 
-	if (!exec->bo_count) {
+	if (!job->bo_count) {
 		/* See comment on bo_index for why we have to check
 		 * this.
 		 */
@@ -284,15 +302,15 @@ v3d_cl_lookup_bos(struct drm_device *dev,
 		return -EINVAL;
 	}
 
-	exec->bo = kvmalloc_array(exec->bo_count,
-				  sizeof(struct drm_gem_cma_object *),
-				  GFP_KERNEL | __GFP_ZERO);
-	if (!exec->bo) {
+	job->bo = kvmalloc_array(job->bo_count,
+				 sizeof(struct drm_gem_cma_object *),
+				 GFP_KERNEL | __GFP_ZERO);
+	if (!job->bo) {
 		DRM_DEBUG("Failed to allocate validated BO pointers\n");
 		return -ENOMEM;
 	}
 
-	handles = kvmalloc_array(exec->bo_count, sizeof(u32), GFP_KERNEL);
+	handles = kvmalloc_array(job->bo_count, sizeof(u32), GFP_KERNEL);
 	if (!handles) {
 		ret = -ENOMEM;
 		DRM_DEBUG("Failed to allocate incoming GEM handles\n");
@@ -300,15 +318,15 @@ v3d_cl_lookup_bos(struct drm_device *dev,
 	}
 
 	if (copy_from_user(handles,
-			   (void __user *)(uintptr_t)args->bo_handles,
-			   exec->bo_count * sizeof(u32))) {
+			   (void __user *)(uintptr_t)bo_handles,
+			   job->bo_count * sizeof(u32))) {
 		ret = -EFAULT;
 		DRM_DEBUG("Failed to copy in GEM handles\n");
 		goto fail;
 	}
 
 	spin_lock(&file_priv->table_lock);
-	for (i = 0; i < exec->bo_count; i++) {
+	for (i = 0; i < job->bo_count; i++) {
 		struct drm_gem_object *bo = idr_find(&file_priv->object_idr,
 						     handles[i]);
 		if (!bo) {
@@ -319,7 +337,7 @@ v3d_cl_lookup_bos(struct drm_device *dev,
 			goto fail;
 		}
 		drm_gem_object_get(bo);
-		exec->bo[i] = to_v3d_bo(bo);
+		job->bo[i] = bo;
 	}
 	spin_unlock(&file_priv->table_lock);
 
@@ -329,67 +347,50 @@ fail:
 }
 
 static void
-v3d_exec_cleanup(struct kref *ref)
+v3d_job_free(struct kref *ref)
 {
-	struct v3d_exec_info *exec = container_of(ref, struct v3d_exec_info,
-						  refcount);
-	struct v3d_dev *v3d = exec->v3d;
-	unsigned int i;
-	struct v3d_bo *bo, *save;
-
-	dma_fence_put(exec->bin.in_fence);
-	dma_fence_put(exec->render.in_fence);
-
-	dma_fence_put(exec->bin.irq_fence);
-	dma_fence_put(exec->render.irq_fence);
-
-	dma_fence_put(exec->bin_done_fence);
-	dma_fence_put(exec->render_done_fence);
+	struct v3d_job *job = container_of(ref, struct v3d_job, refcount);
+	unsigned long index;
+	struct dma_fence *fence;
+	int i;
 
-	for (i = 0; i < exec->bo_count; i++)
-		drm_gem_object_put_unlocked(&exec->bo[i]->base.base);
-	kvfree(exec->bo);
+	for (i = 0; i < job->bo_count; i++) {
+		if (job->bo[i])
+			drm_gem_object_put_unlocked(job->bo[i]);
+	}
+	kvfree(job->bo);
 
-	list_for_each_entry_safe(bo, save, &exec->unref_list, unref_head) {
-		drm_gem_object_put_unlocked(&bo->base.base);
+	xa_for_each(&job->deps, index, fence) {
+		dma_fence_put(fence);
 	}
+	xa_destroy(&job->deps);
 
-	pm_runtime_mark_last_busy(v3d->dev);
-	pm_runtime_put_autosuspend(v3d->dev);
+	dma_fence_put(job->irq_fence);
+	dma_fence_put(job->done_fence);
 
-	kfree(exec);
-}
+	pm_runtime_mark_last_busy(job->v3d->dev);
+	pm_runtime_put_autosuspend(job->v3d->dev);
 
-void v3d_exec_put(struct v3d_exec_info *exec)
-{
-	kref_put(&exec->refcount, v3d_exec_cleanup);
+	kfree(job);
 }
 
 static void
-v3d_tfu_job_cleanup(struct kref *ref)
+v3d_render_job_free(struct kref *ref)
 {
-	struct v3d_tfu_job *job = container_of(ref, struct v3d_tfu_job,
-					       refcount);
-	struct v3d_dev *v3d = job->v3d;
-	unsigned int i;
-
-	dma_fence_put(job->in_fence);
-	dma_fence_put(job->irq_fence);
+	struct v3d_render_job *job = container_of(ref, struct v3d_render_job,
+						  base.refcount);
+	struct v3d_bo *bo, *save;
 
-	for (i = 0; i < ARRAY_SIZE(job->bo); i++) {
-		if (job->bo[i])
-			drm_gem_object_put_unlocked(&job->bo[i]->base.base);
+	list_for_each_entry_safe(bo, save, &job->unref_list, unref_head) {
+		drm_gem_object_put_unlocked(&bo->base.base);
 	}
 
-	pm_runtime_mark_last_busy(v3d->dev);
-	pm_runtime_put_autosuspend(v3d->dev);
-
-	kfree(job);
+	v3d_job_free(ref);
 }
 
-void v3d_tfu_job_put(struct v3d_tfu_job *job)
+void v3d_job_put(struct v3d_job *job)
 {
-	kref_put(&job->refcount, v3d_tfu_job_cleanup);
+	kref_put(&job->refcount, job->free);
 }
 
 int
@@ -425,6 +426,87 @@ v3d_wait_bo_ioctl(struct drm_device *dev, void *data,
 	return ret;
 }
 
+static int
+v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv,
+	     struct v3d_job *job, void (*free)(struct kref *ref),
+	     u32 in_sync)
+{
+	struct dma_fence *in_fence = NULL;
+	int ret;
+
+	job->v3d = v3d;
+	job->free = free;
+
+	ret = pm_runtime_get_sync(v3d->dev);
+	if (ret < 0)
+		return ret;
+
+	xa_init_flags(&job->deps, XA_FLAGS_ALLOC);
+
+	ret = drm_syncobj_find_fence(file_priv, in_sync, 0, 0, &in_fence);
+	if (ret == -EINVAL)
+		goto fail;
+
+	ret = drm_gem_fence_array_add(&job->deps, in_fence);
+	if (ret)
+		goto fail;
+
+	kref_init(&job->refcount);
+
+	return 0;
+fail:
+	xa_destroy(&job->deps);
+	pm_runtime_put_autosuspend(v3d->dev);
+	return ret;
+}
+
+static int
+v3d_push_job(struct v3d_file_priv *v3d_priv,
+	     struct v3d_job *job, enum v3d_queue queue)
+{
+	int ret;
+
+	ret = drm_sched_job_init(&job->base, &v3d_priv->sched_entity[queue],
+				 v3d_priv);
+	if (ret)
+		return ret;
+
+	job->done_fence = dma_fence_get(&job->base.s_fence->finished);
+
+	/* put by scheduler job completion */
+	kref_get(&job->refcount);
+
+	drm_sched_entity_push_job(&job->base, &v3d_priv->sched_entity[queue]);
+
+	return 0;
+}
+
+static void
+v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv,
+					 struct v3d_job *job,
+					 struct ww_acquire_ctx *acquire_ctx,
+					 u32 out_sync,
+					 struct dma_fence *done_fence)
+{
+	struct drm_syncobj *sync_out;
+	int i;
+
+	for (i = 0; i < job->bo_count; i++) {
+		/* XXX: Use shared fences for read-only objects. */
+		reservation_object_add_excl_fence(job->bo[i]->resv,
+						  job->done_fence);
+	}
+
+	drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx);
+
+	/* Update the return sync object for the job */
+	sync_out = drm_syncobj_find(file_priv, out_sync);
+	if (sync_out) {
+		drm_syncobj_replace_fence(sync_out, done_fence);
+		drm_syncobj_put(sync_out);
+	}
+}
+
 /**
  * v3d_submit_cl_ioctl() - Submits a job (frame) to the V3D.
  * @dev: DRM device
@@ -444,9 +526,9 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	struct v3d_dev *v3d = to_v3d_dev(dev);
 	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
 	struct drm_v3d_submit_cl *args = data;
-	struct v3d_exec_info *exec;
+	struct v3d_bin_job *bin = NULL;
+	struct v3d_render_job *render;
 	struct ww_acquire_ctx acquire_ctx;
-	struct drm_syncobj *sync_out;
 	int ret = 0;
 
 	trace_v3d_submit_cl_ioctl(&v3d->drm, args->rcl_start, args->rcl_end);
@@ -456,100 +538,87 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	exec = kcalloc(1, sizeof(*exec), GFP_KERNEL);
-	if (!exec)
+	render = kcalloc(1, sizeof(*render), GFP_KERNEL);
+	if (!render)
 		return -ENOMEM;
 
-	ret = pm_runtime_get_sync(v3d->dev);
-	if (ret < 0) {
-		kfree(exec);
+	render->start = args->rcl_start;
+	render->end = args->rcl_end;
+	INIT_LIST_HEAD(&render->unref_list);
+
+	ret = v3d_job_init(v3d, file_priv, &render->base,
+			   v3d_render_job_free, args->in_sync_rcl);
+	if (ret) {
+		kfree(render);
 		return ret;
 	}
 
-	kref_init(&exec->refcount);
+	if (args->bcl_start != args->bcl_end) {
+		bin = kcalloc(1, sizeof(*bin), GFP_KERNEL);
+		if (!bin)
+			return -ENOMEM;
 
-	ret = drm_syncobj_find_fence(file_priv, args->in_sync_bcl,
-				     0, 0, &exec->bin.in_fence);
-	if (ret == -EINVAL)
-		goto fail;
+		ret = v3d_job_init(v3d, file_priv, &bin->base,
+				   v3d_job_free, args->in_sync_bcl);
+		if (ret) {
+			v3d_job_put(&render->base);
+			return ret;
+		}
 
-	ret = drm_syncobj_find_fence(file_priv, args->in_sync_rcl,
-				     0, 0, &exec->render.in_fence);
-	if (ret == -EINVAL)
-		goto fail;
+		bin->start = args->bcl_start;
+		bin->end = args->bcl_end;
+		bin->qma = args->qma;
+		bin->qms = args->qms;
+		bin->qts = args->qts;
+		bin->render = render;
+	}
 
-	exec->qma = args->qma;
-	exec->qms = args->qms;
-	exec->qts = args->qts;
-	exec->bin.exec = exec;
-	exec->bin.start = args->bcl_start;
-	exec->bin.end = args->bcl_end;
-	exec->render.exec = exec;
-	exec->render.start = args->rcl_start;
-	exec->render.end = args->rcl_end;
-	exec->v3d = v3d;
-	INIT_LIST_HEAD(&exec->unref_list);
-
-	ret = v3d_cl_lookup_bos(dev, file_priv, args, exec);
+	ret = v3d_lookup_bos(dev, file_priv, &render->base,
+			     args->bo_handles, args->bo_handle_count);
 	if (ret)
 		goto fail;
 
-	ret = v3d_lock_bo_reservations(exec->bo, exec->bo_count,
-				       &acquire_ctx);
+	ret = v3d_lock_bo_reservations(&render->base, &acquire_ctx);
 	if (ret)
 		goto fail;
 
 	mutex_lock(&v3d->sched_lock);
-	if (exec->bin.start != exec->bin.end) {
-		ret = drm_sched_job_init(&exec->bin.base,
-					 &v3d_priv->sched_entity[V3D_BIN],
-					 v3d_priv);
+	if (bin) {
+		ret = v3d_push_job(v3d_priv, &bin->base, V3D_BIN);
 		if (ret)
 			goto fail_unreserve;
 
-		exec->bin_done_fence =
-			dma_fence_get(&exec->bin.base.s_fence->finished);
-
-		kref_get(&exec->refcount); /* put by scheduler job completion */
-		drm_sched_entity_push_job(&exec->bin.base,
-					  &v3d_priv->sched_entity[V3D_BIN]);
+		ret = drm_gem_fence_array_add(&render->base.deps,
+					      dma_fence_get(bin->base.done_fence));
+		if (ret)
+			goto fail_unreserve;
 	}
 
-	ret = drm_sched_job_init(&exec->render.base,
-				 &v3d_priv->sched_entity[V3D_RENDER],
-				 v3d_priv);
+	ret = v3d_push_job(v3d_priv, &render->base, V3D_RENDER);
 	if (ret)
 		goto fail_unreserve;
-
-	exec->render_done_fence =
-		dma_fence_get(&exec->render.base.s_fence->finished);
-
-	kref_get(&exec->refcount); /* put by scheduler job completion */
-	drm_sched_entity_push_job(&exec->render.base,
-				  &v3d_priv->sched_entity[V3D_RENDER]);
 	mutex_unlock(&v3d->sched_lock);
 
-	v3d_attach_object_fences(exec->bo, exec->bo_count,
-				 exec->render_done_fence);
-
-	v3d_unlock_bo_reservations(exec->bo, exec->bo_count, &acquire_ctx);
-
-	/* Update the return sync object for the */
-	sync_out = drm_syncobj_find(file_priv, args->out_sync);
-	if (sync_out) {
-		drm_syncobj_replace_fence(sync_out, exec->render_done_fence);
-		drm_syncobj_put(sync_out);
-	}
+	v3d_attach_fences_and_unlock_reservation(file_priv,
+						 &render->base,
+						 &acquire_ctx,
+						 args->out_sync,
+						 render->base.done_fence);
 
-	v3d_exec_put(exec);
+	if (bin)
+		v3d_job_put(&bin->base);
+	v3d_job_put(&render->base);
 
 	return 0;
 
 fail_unreserve:
 	mutex_unlock(&v3d->sched_lock);
-	v3d_unlock_bo_reservations(exec->bo, exec->bo_count, &acquire_ctx);
+	drm_gem_unlock_reservations(render->base.bo,
+				    render->base.bo_count, &acquire_ctx);
 fail:
-	v3d_exec_put(exec);
+	if (bin)
+		v3d_job_put(&bin->base);
+	v3d_job_put(&render->base);
 
 	return ret;
 }
@@ -572,10 +641,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
 	struct drm_v3d_submit_tfu *args = data;
 	struct v3d_tfu_job *job;
 	struct ww_acquire_ctx acquire_ctx;
-	struct drm_syncobj *sync_out;
-	struct dma_fence *sched_done_fence;
 	int ret = 0;
-	int bo_count;
 
 	trace_v3d_submit_tfu_ioctl(&v3d->drm, args->iia);
 
@@ -583,81 +649,172 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
 	if (!job)
 		return -ENOMEM;
 
-	ret = pm_runtime_get_sync(v3d->dev);
-	if (ret < 0) {
+	ret = v3d_job_init(v3d, file_priv, &job->base,
+			   v3d_job_free, args->in_sync);
+	if (ret) {
 		kfree(job);
 		return ret;
 	}
 
-	kref_init(&job->refcount);
-
-	ret = drm_syncobj_find_fence(file_priv, args->in_sync,
-				     0, 0, &job->in_fence);
-	if (ret == -EINVAL)
-		goto fail;
+	job->base.bo = kcalloc(ARRAY_SIZE(args->bo_handles),
+			       sizeof(*job->base.bo), GFP_KERNEL);
+	if (!job->base.bo) {
+		v3d_job_put(&job->base);
+		return -ENOMEM;
+	}
 
 	job->args = *args;
-	job->v3d = v3d;
 
 	spin_lock(&file_priv->table_lock);
-	for (bo_count = 0; bo_count < ARRAY_SIZE(job->bo); bo_count++) {
+	for (job->base.bo_count = 0;
+	     job->base.bo_count < ARRAY_SIZE(args->bo_handles);
+	     job->base.bo_count++) {
 		struct drm_gem_object *bo;
 
-		if (!args->bo_handles[bo_count])
+		if (!args->bo_handles[job->base.bo_count])
 			break;
 
 		bo = idr_find(&file_priv->object_idr,
-			      args->bo_handles[bo_count]);
+			      args->bo_handles[job->base.bo_count]);
 		if (!bo) {
 			DRM_DEBUG("Failed to look up GEM BO %d: %d\n",
-				  bo_count, args->bo_handles[bo_count]);
+				  job->base.bo_count,
+				  args->bo_handles[job->base.bo_count]);
 			ret = -ENOENT;
 			spin_unlock(&file_priv->table_lock);
 			goto fail;
 		}
 		drm_gem_object_get(bo);
-		job->bo[bo_count] = to_v3d_bo(bo);
+		job->base.bo[job->base.bo_count] = bo;
 	}
 	spin_unlock(&file_priv->table_lock);
 
-	ret = v3d_lock_bo_reservations(job->bo, bo_count, &acquire_ctx);
+	ret = v3d_lock_bo_reservations(&job->base, &acquire_ctx);
 	if (ret)
 		goto fail;
 
 	mutex_lock(&v3d->sched_lock);
-	ret = drm_sched_job_init(&job->base,
-				 &v3d_priv->sched_entity[V3D_TFU],
-				 v3d_priv);
+	ret = v3d_push_job(v3d_priv, &job->base, V3D_TFU);
 	if (ret)
 		goto fail_unreserve;
+	mutex_unlock(&v3d->sched_lock);
 
-	sched_done_fence = dma_fence_get(&job->base.s_fence->finished);
+	v3d_attach_fences_and_unlock_reservation(file_priv,
+						 &job->base, &acquire_ctx,
+						 args->out_sync,
+						 job->base.done_fence);
 
-	kref_get(&job->refcount); /* put by scheduler job completion */
-	drm_sched_entity_push_job(&job->base, &v3d_priv->sched_entity[V3D_TFU]);
+	v3d_job_put(&job->base);
+
+	return 0;
+
+fail_unreserve:
 	mutex_unlock(&v3d->sched_lock);
+	drm_gem_unlock_reservations(job->base.bo, job->base.bo_count,
+				    &acquire_ctx);
+fail:
+	v3d_job_put(&job->base);
 
-	v3d_attach_object_fences(job->bo, bo_count, sched_done_fence);
+	return ret;
+}
 
-	v3d_unlock_bo_reservations(job->bo, bo_count, &acquire_ctx);
+/**
+ * v3d_submit_csd_ioctl() - Submits a CSD (texture formatting) job to the V3D.
+ * @dev: DRM device
+ * @data: ioctl argument
+ * @file_priv: DRM file for this fd
+ *
+ * Userspace provides the register setup for the CSD, which we don't
+ * need to validate since the CSD is behind the MMU.
+ */
+int
+v3d_submit_csd_ioctl(struct drm_device *dev, void *data,
+		     struct drm_file *file_priv)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+	struct drm_v3d_submit_csd *args = data;
+	struct v3d_csd_job *job;
+	struct v3d_job *clean_job;
+	struct ww_acquire_ctx acquire_ctx;
+	int ret;
 
-	/* Update the return sync object */
-	sync_out = drm_syncobj_find(file_priv, args->out_sync);
-	if (sync_out) {
-		drm_syncobj_replace_fence(sync_out, sched_done_fence);
-		drm_syncobj_put(sync_out);
+	trace_v3d_submit_csd_ioctl(&v3d->drm, args->cfg[5], args->cfg[6]);
+
+	if (!v3d_has_csd(v3d)) {
+		DRM_DEBUG("Attempting CSD submit on non-CSD hardware\n");
+		return -EINVAL;
+	}
+
+	job = kcalloc(1, sizeof(*job), GFP_KERNEL);
+	if (!job)
+		return -ENOMEM;
+
+	ret = v3d_job_init(v3d, file_priv, &job->base,
+			   v3d_job_free, args->in_sync);
+	if (ret) {
+		kfree(job);
+		return ret;
+	}
+
+	clean_job = kcalloc(1, sizeof(*clean_job), GFP_KERNEL);
+	if (!clean_job) {
+		v3d_job_put(&job->base);
+		kfree(job);
+		return -ENOMEM;
 	}
-	dma_fence_put(sched_done_fence);
 
-	v3d_tfu_job_put(job);
+	ret = v3d_job_init(v3d, file_priv, clean_job, v3d_job_free, 0);
+	if (ret) {
+		v3d_job_put(&job->base);
+		kfree(clean_job);
+		return ret;
+	}
+
+	job->args = *args;
+
+	ret = v3d_lookup_bos(dev, file_priv, clean_job,
+			     args->bo_handles, args->bo_handle_count);
+	if (ret)
+		goto fail;
+
+	ret = v3d_lock_bo_reservations(clean_job, &acquire_ctx);
+	if (ret)
+		goto fail;
+
+	mutex_lock(&v3d->sched_lock);
+	ret = v3d_push_job(v3d_priv, &job->base, V3D_CSD);
+	if (ret)
+		goto fail_unreserve;
+
+	ret = drm_gem_fence_array_add(&clean_job->deps,
+				      dma_fence_get(job->base.done_fence));
+	if (ret)
+		goto fail_unreserve;
+
+	ret = v3d_push_job(v3d_priv, clean_job, V3D_CACHE_CLEAN);
+	if (ret)
+		goto fail_unreserve;
+	mutex_unlock(&v3d->sched_lock);
+
+	v3d_attach_fences_and_unlock_reservation(file_priv,
+						 clean_job,
+						 &acquire_ctx,
+						 args->out_sync,
+						 clean_job->done_fence);
+
+	v3d_job_put(&job->base);
+	v3d_job_put(clean_job);
 
 	return 0;
 
 fail_unreserve:
 	mutex_unlock(&v3d->sched_lock);
-	v3d_unlock_bo_reservations(job->bo, bo_count, &acquire_ctx);
+	drm_gem_unlock_reservations(clean_job->bo, clean_job->bo_count,
+				    &acquire_ctx);
 fail:
-	v3d_tfu_job_put(job);
+	v3d_job_put(&job->base);
+	v3d_job_put(clean_job);
 
 	return ret;
 }
@@ -677,6 +834,7 @@ v3d_gem_init(struct drm_device *dev)
 	mutex_init(&v3d->bo_lock);
 	mutex_init(&v3d->reset_lock);
 	mutex_init(&v3d->sched_lock);
+	mutex_init(&v3d->cache_clean_lock);
 
 	/* Note: We don't allocate address 0.  Various bits of HW
 	 * treat 0 as special, such as the occlusion query counters
@@ -715,7 +873,7 @@ v3d_gem_destroy(struct drm_device *dev)
 
 	v3d_sched_fini(v3d);
 
-	/* Waiting for exec to finish would need to be done before
+	/* Waiting for jobs to finish would need to be done before
 	 * unregistering V3D.
 	 */
 	WARN_ON(v3d->bin_job);
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index aa0a180ae700..268d8a889ac5 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -4,9 +4,9 @@
 /**
  * DOC: Interrupt management for the V3D engine
  *
- * When we take a bin, render, or TFU done interrupt, we need to
- * signal the fence for that job so that the scheduler can queue up
- * the next one and unblock any waiters.
+ * When we take a bin, render, TFU done, or CSD done interrupt, we
+ * need to signal the fence for that job so that the scheduler can
+ * queue up the next one and unblock any waiters.
  *
  * When we take the binner out of memory interrupt, we need to
  * allocate some new memory and pass it to the binner so that the
@@ -20,6 +20,7 @@
 #define V3D_CORE_IRQS ((u32)(V3D_INT_OUTOMEM |	\
 			     V3D_INT_FLDONE |	\
 			     V3D_INT_FRDONE |	\
+			     V3D_INT_CSDDONE |	\
 			     V3D_INT_GMPV))
 
 #define V3D_HUB_IRQS ((u32)(V3D_HUB_INT_MMU_WRV |	\
@@ -62,7 +63,7 @@ v3d_overflow_mem_work(struct work_struct *work)
 	}
 
 	drm_gem_object_get(obj);
-	list_add_tail(&bo->unref_head, &v3d->bin_job->unref_list);
+	list_add_tail(&bo->unref_head, &v3d->bin_job->render->unref_list);
 	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
 
 	V3D_CORE_WRITE(0, V3D_PTB_BPOA, bo->node.start << PAGE_SHIFT);
@@ -96,7 +97,7 @@ v3d_irq(int irq, void *arg)
 
 	if (intsts & V3D_INT_FLDONE) {
 		struct v3d_fence *fence =
-			to_v3d_fence(v3d->bin_job->bin.irq_fence);
+			to_v3d_fence(v3d->bin_job->base.irq_fence);
 
 		trace_v3d_bcl_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
@@ -105,13 +106,22 @@ v3d_irq(int irq, void *arg)
 
 	if (intsts & V3D_INT_FRDONE) {
 		struct v3d_fence *fence =
-			to_v3d_fence(v3d->render_job->render.irq_fence);
+			to_v3d_fence(v3d->render_job->base.irq_fence);
 
 		trace_v3d_rcl_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
 		status = IRQ_HANDLED;
 	}
 
+	if (intsts & V3D_INT_CSDDONE) {
+		struct v3d_fence *fence =
+			to_v3d_fence(v3d->csd_job->base.irq_fence);
+
+		trace_v3d_csd_irq(&v3d->drm, fence->seqno);
+		dma_fence_signal(&fence->base);
+		status = IRQ_HANDLED;
+	}
+
 	/* We shouldn't be triggering these if we have GMP in
 	 * always-allowed mode.
 	 */
@@ -141,7 +151,7 @@ v3d_hub_irq(int irq, void *arg)
 
 	if (intsts & V3D_HUB_INT_TFUC) {
 		struct v3d_fence *fence =
-			to_v3d_fence(v3d->tfu_job->irq_fence);
+			to_v3d_fence(v3d->tfu_job->base.irq_fence);
 
 		trace_v3d_tfu_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
@@ -152,10 +162,33 @@ v3d_hub_irq(int irq, void *arg)
 		      V3D_HUB_INT_MMU_PTI |
 		      V3D_HUB_INT_MMU_CAP)) {
 		u32 axi_id = V3D_READ(V3D_MMU_VIO_ID);
-		u64 vio_addr = (u64)V3D_READ(V3D_MMU_VIO_ADDR) << 8;
-
-		dev_err(v3d->dev, "MMU error from client %d at 0x%08llx%s%s%s\n",
-			axi_id, (long long)vio_addr,
+		u64 vio_addr = ((u64)V3D_READ(V3D_MMU_VIO_ADDR) <<
+				(v3d->va_width - 32));
+		static const char *const v3d41_axi_ids[] = {
+			"L2T",
+			"PTB",
+			"PSE",
+			"TLB",
+			"CLE",
+			"TFU",
+			"MMU",
+			"GMP",
+		};
+		const char *client = "?";
+
+		V3D_WRITE(V3D_MMU_CTL,
+			  V3D_READ(V3D_MMU_CTL) & (V3D_MMU_CTL_CAP_EXCEEDED |
+						   V3D_MMU_CTL_PT_INVALID |
+						   V3D_MMU_CTL_WRITE_VIOLATION));
+
+		if (v3d->ver >= 41) {
+			axi_id = axi_id >> 5;
+			if (axi_id < ARRAY_SIZE(v3d41_axi_ids))
+				client = v3d41_axi_ids[axi_id];
+		}
+
+		dev_err(v3d->dev, "MMU error from client %s (%d) at 0x%llx%s%s%s\n",
+			client, axi_id, (long long)vio_addr,
 			((intsts & V3D_HUB_INT_MMU_WRV) ?
 			 ", write violation" : ""),
 			((intsts & V3D_HUB_INT_MMU_PTI) ?
diff --git a/drivers/gpu/drm/v3d/v3d_mmu.c b/drivers/gpu/drm/v3d/v3d_mmu.c
index 7a21f1787ab1..395e81d97163 100644
--- a/drivers/gpu/drm/v3d/v3d_mmu.c
+++ b/drivers/gpu/drm/v3d/v3d_mmu.c
@@ -69,10 +69,13 @@ int v3d_mmu_set_page_table(struct v3d_dev *v3d)
 	V3D_WRITE(V3D_MMU_PT_PA_BASE, v3d->pt_paddr >> V3D_MMU_PAGE_SHIFT);
 	V3D_WRITE(V3D_MMU_CTL,
 		  V3D_MMU_CTL_ENABLE |
-		  V3D_MMU_CTL_PT_INVALID |
+		  V3D_MMU_CTL_PT_INVALID_ENABLE |
 		  V3D_MMU_CTL_PT_INVALID_ABORT |
+		  V3D_MMU_CTL_PT_INVALID_INT |
 		  V3D_MMU_CTL_WRITE_VIOLATION_ABORT |
-		  V3D_MMU_CTL_CAP_EXCEEDED_ABORT);
+		  V3D_MMU_CTL_WRITE_VIOLATION_INT |
+		  V3D_MMU_CTL_CAP_EXCEEDED_ABORT |
+		  V3D_MMU_CTL_CAP_EXCEEDED_INT);
 	V3D_WRITE(V3D_MMU_ILLEGAL_ADDR,
 		  (v3d->mmu_scratch_paddr >> V3D_MMU_PAGE_SHIFT) |
 		  V3D_MMU_ILLEGAL_ADDR_ENABLE);
diff --git a/drivers/gpu/drm/v3d/v3d_regs.h b/drivers/gpu/drm/v3d/v3d_regs.h
index 8e88af237610..9bcb57781d31 100644
--- a/drivers/gpu/drm/v3d/v3d_regs.h
+++ b/drivers/gpu/drm/v3d/v3d_regs.h
@@ -152,7 +152,8 @@
 # define V3D_MMU_CTL_PT_INVALID_ABORT                  BIT(19)
 # define V3D_MMU_CTL_PT_INVALID_INT                    BIT(18)
 # define V3D_MMU_CTL_PT_INVALID_EXCEPTION              BIT(17)
-# define V3D_MMU_CTL_WRITE_VIOLATION                   BIT(16)
+# define V3D_MMU_CTL_PT_INVALID_ENABLE                 BIT(16)
+# define V3D_MMU_CTL_WRITE_VIOLATION                   BIT(12)
 # define V3D_MMU_CTL_WRITE_VIOLATION_ABORT             BIT(11)
 # define V3D_MMU_CTL_WRITE_VIOLATION_INT               BIT(10)
 # define V3D_MMU_CTL_WRITE_VIOLATION_EXCEPTION         BIT(9)
@@ -191,6 +192,14 @@
 /* Address that faulted */
 #define V3D_MMU_VIO_ADDR                               0x01234
 
+#define V3D_MMU_DEBUG_INFO                             0x01238
+# define V3D_MMU_PA_WIDTH_MASK                         V3D_MASK(11, 8)
+# define V3D_MMU_PA_WIDTH_SHIFT                        8
+# define V3D_MMU_VA_WIDTH_MASK                         V3D_MASK(7, 4)
+# define V3D_MMU_VA_WIDTH_SHIFT                        4
+# define V3D_MMU_VERSION_MASK                          V3D_MASK(3, 0)
+# define V3D_MMU_VERSION_SHIFT                         0
+
 /* Per-V3D-core registers */
 
 #define V3D_CTL_IDENT0                                 0x00000
@@ -238,8 +247,11 @@
 #define V3D_CTL_L2TCACTL                               0x00030
 # define V3D_L2TCACTL_TMUWCF                           BIT(8)
 # define V3D_L2TCACTL_L2T_NO_WM                        BIT(4)
+/* Invalidates cache lines. */
 # define V3D_L2TCACTL_FLM_FLUSH                        0
+/* Removes cachelines without writing dirty lines back. */
 # define V3D_L2TCACTL_FLM_CLEAR                        1
+/* Writes out dirty cachelines and marks them clean, but doesn't invalidate. */
 # define V3D_L2TCACTL_FLM_CLEAN                        2
 # define V3D_L2TCACTL_FLM_MASK                         V3D_MASK(2, 1)
 # define V3D_L2TCACTL_FLM_SHIFT                        1
@@ -255,6 +267,8 @@
 #define V3D_CTL_INT_MSK_CLR                            0x00064
 # define V3D_INT_QPU_MASK                              V3D_MASK(27, 16)
 # define V3D_INT_QPU_SHIFT                             16
+# define V3D_INT_CSDDONE                               BIT(7)
+# define V3D_INT_PCTR                                  BIT(6)
 # define V3D_INT_GMPV                                  BIT(5)
 # define V3D_INT_TRFB                                  BIT(4)
 # define V3D_INT_SPILLUSE                              BIT(3)
@@ -374,4 +388,110 @@
 #define V3D_GMP_PRESERVE_LOAD                          0x00818
 #define V3D_GMP_VALID_LINES                            0x00820
 
+#define V3D_CSD_STATUS                                 0x00900
+# define V3D_CSD_STATUS_NUM_COMPLETED_MASK             V3D_MASK(11, 4)
+# define V3D_CSD_STATUS_NUM_COMPLETED_SHIFT            4
+# define V3D_CSD_STATUS_NUM_ACTIVE_MASK                V3D_MASK(3, 2)
+# define V3D_CSD_STATUS_NUM_ACTIVE_SHIFT               2
+# define V3D_CSD_STATUS_HAVE_CURRENT_DISPATCH          BIT(1)
+# define V3D_CSD_STATUS_HAVE_QUEUED_DISPATCH           BIT(0)
+
+#define V3D_CSD_QUEUED_CFG0                            0x00904
+# define V3D_CSD_QUEUED_CFG0_NUM_WGS_X_MASK            V3D_MASK(31, 16)
+# define V3D_CSD_QUEUED_CFG0_NUM_WGS_X_SHIFT           16
+# define V3D_CSD_QUEUED_CFG0_WG_X_OFFSET_MASK          V3D_MASK(15, 0)
+# define V3D_CSD_QUEUED_CFG0_WG_X_OFFSET_SHIFT         0
+
+#define V3D_CSD_QUEUED_CFG1                            0x00908
+# define V3D_CSD_QUEUED_CFG1_NUM_WGS_Y_MASK            V3D_MASK(31, 16)
+# define V3D_CSD_QUEUED_CFG1_NUM_WGS_Y_SHIFT           16
+# define V3D_CSD_QUEUED_CFG1_WG_Y_OFFSET_MASK          V3D_MASK(15, 0)
+# define V3D_CSD_QUEUED_CFG1_WG_Y_OFFSET_SHIFT         0
+
+#define V3D_CSD_QUEUED_CFG2                            0x0090c
+# define V3D_CSD_QUEUED_CFG2_NUM_WGS_Z_MASK            V3D_MASK(31, 16)
+# define V3D_CSD_QUEUED_CFG2_NUM_WGS_Z_SHIFT           16
+# define V3D_CSD_QUEUED_CFG2_WG_Z_OFFSET_MASK          V3D_MASK(15, 0)
+# define V3D_CSD_QUEUED_CFG2_WG_Z_OFFSET_SHIFT         0
+
+#define V3D_CSD_QUEUED_CFG3                            0x00910
+# define V3D_CSD_QUEUED_CFG3_OVERLAP_WITH_PREV         BIT(26)
+# define V3D_CSD_QUEUED_CFG3_MAX_SG_ID_MASK            V3D_MASK(25, 20)
+# define V3D_CSD_QUEUED_CFG3_MAX_SG_ID_SHIFT           20
+# define V3D_CSD_QUEUED_CFG3_BATCHES_PER_SG_M1_MASK    V3D_MASK(19, 12)
+# define V3D_CSD_QUEUED_CFG3_BATCHES_PER_SG_M1_SHIFT   12
+# define V3D_CSD_QUEUED_CFG3_WGS_PER_SG_MASK           V3D_MASK(11, 8)
+# define V3D_CSD_QUEUED_CFG3_WGS_PER_SG_SHIFT          8
+# define V3D_CSD_QUEUED_CFG3_WG_SIZE_MASK              V3D_MASK(7, 0)
+# define V3D_CSD_QUEUED_CFG3_WG_SIZE_SHIFT             0
+
+/* Number of batches, minus 1 */
+#define V3D_CSD_QUEUED_CFG4                            0x00914
+
+/* Shader address, pnan, singleseg, threading, like a shader record. */
+#define V3D_CSD_QUEUED_CFG5                            0x00918
+
+/* Uniforms address (4 byte aligned) */
+#define V3D_CSD_QUEUED_CFG6                            0x0091c
+
+#define V3D_CSD_CURRENT_CFG0                          0x00920
+#define V3D_CSD_CURRENT_CFG1                          0x00924
+#define V3D_CSD_CURRENT_CFG2                          0x00928
+#define V3D_CSD_CURRENT_CFG3                          0x0092c
+#define V3D_CSD_CURRENT_CFG4                          0x00930
+#define V3D_CSD_CURRENT_CFG5                          0x00934
+#define V3D_CSD_CURRENT_CFG6                          0x00938
+
+#define V3D_CSD_CURRENT_ID0                            0x0093c
+# define V3D_CSD_CURRENT_ID0_WG_X_MASK                 V3D_MASK(31, 16)
+# define V3D_CSD_CURRENT_ID0_WG_X_SHIFT                16
+# define V3D_CSD_CURRENT_ID0_WG_IN_SG_MASK             V3D_MASK(11, 8)
+# define V3D_CSD_CURRENT_ID0_WG_IN_SG_SHIFT            8
+# define V3D_CSD_CURRENT_ID0_L_IDX_MASK                V3D_MASK(7, 0)
+# define V3D_CSD_CURRENT_ID0_L_IDX_SHIFT               0
+
+#define V3D_CSD_CURRENT_ID1                            0x00940
+# define V3D_CSD_CURRENT_ID0_WG_Z_MASK                 V3D_MASK(31, 16)
+# define V3D_CSD_CURRENT_ID0_WG_Z_SHIFT                16
+# define V3D_CSD_CURRENT_ID0_WG_Y_MASK                 V3D_MASK(15, 0)
+# define V3D_CSD_CURRENT_ID0_WG_Y_SHIFT                0
+
+#define V3D_ERR_FDBGO                                  0x00f04
+#define V3D_ERR_FDBGB                                  0x00f08
+#define V3D_ERR_FDBGR                                  0x00f0c
+
+#define V3D_ERR_FDBGS                                  0x00f10
+# define V3D_ERR_FDBGS_INTERPZ_IP_STALL                BIT(17)
+# define V3D_ERR_FDBGS_DEPTHO_FIFO_IP_STALL            BIT(16)
+# define V3D_ERR_FDBGS_XYNRM_IP_STALL                  BIT(14)
+# define V3D_ERR_FDBGS_EZREQ_FIFO_OP_VALID             BIT(13)
+# define V3D_ERR_FDBGS_QXYF_FIFO_OP_VALID              BIT(12)
+# define V3D_ERR_FDBGS_QXYF_FIFO_OP_LAST               BIT(11)
+# define V3D_ERR_FDBGS_EZTEST_ANYQVALID                BIT(7)
+# define V3D_ERR_FDBGS_EZTEST_PASS                     BIT(6)
+# define V3D_ERR_FDBGS_EZTEST_QREADY                   BIT(5)
+# define V3D_ERR_FDBGS_EZTEST_VLF_OKNOVALID            BIT(4)
+# define V3D_ERR_FDBGS_EZTEST_QSTALL                   BIT(3)
+# define V3D_ERR_FDBGS_EZTEST_IP_VLFSTALL              BIT(2)
+# define V3D_ERR_FDBGS_EZTEST_IP_PRSTALL               BIT(1)
+# define V3D_ERR_FDBGS_EZTEST_IP_QSTALL                BIT(0)
+
+#define V3D_ERR_STAT                                   0x00f20
+# define V3D_ERR_L2CARE                                BIT(15)
+# define V3D_ERR_VCMBE                                 BIT(14)
+# define V3D_ERR_VCMRE                                 BIT(13)
+# define V3D_ERR_VCDI                                  BIT(12)
+# define V3D_ERR_VCDE                                  BIT(11)
+# define V3D_ERR_VDWE                                  BIT(10)
+# define V3D_ERR_VPMEAS                                BIT(9)
+# define V3D_ERR_VPMEFNA                               BIT(8)
+# define V3D_ERR_VPMEWNA                               BIT(7)
+# define V3D_ERR_VPMERNA                               BIT(6)
+# define V3D_ERR_VPMERR                                BIT(5)
+# define V3D_ERR_VPMEWR                                BIT(4)
+# define V3D_ERR_VPAERRGL                              BIT(3)
+# define V3D_ERR_VPAEBRGL                              BIT(2)
+# define V3D_ERR_VPAERGS                               BIT(1)
+# define V3D_ERR_VPAEABB                               BIT(0)
+
 #endif /* V3D_REGS_H */
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index e740f3b99aa5..8c2df6d95283 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -30,158 +30,152 @@ to_v3d_job(struct drm_sched_job *sched_job)
 	return container_of(sched_job, struct v3d_job, base);
 }
 
-static struct v3d_tfu_job *
-to_tfu_job(struct drm_sched_job *sched_job)
+static struct v3d_bin_job *
+to_bin_job(struct drm_sched_job *sched_job)
 {
-	return container_of(sched_job, struct v3d_tfu_job, base);
+	return container_of(sched_job, struct v3d_bin_job, base.base);
 }
 
-static void
-v3d_job_free(struct drm_sched_job *sched_job)
+static struct v3d_render_job *
+to_render_job(struct drm_sched_job *sched_job)
 {
-	struct v3d_job *job = to_v3d_job(sched_job);
+	return container_of(sched_job, struct v3d_render_job, base.base);
+}
 
-	drm_sched_job_cleanup(sched_job);
+static struct v3d_tfu_job *
+to_tfu_job(struct drm_sched_job *sched_job)
+{
+	return container_of(sched_job, struct v3d_tfu_job, base.base);
+}
 
-	v3d_exec_put(job->exec);
+static struct v3d_csd_job *
+to_csd_job(struct drm_sched_job *sched_job)
+{
+	return container_of(sched_job, struct v3d_csd_job, base.base);
 }
 
 static void
-v3d_tfu_job_free(struct drm_sched_job *sched_job)
+v3d_job_free(struct drm_sched_job *sched_job)
 {
-	struct v3d_tfu_job *job = to_tfu_job(sched_job);
+	struct v3d_job *job = to_v3d_job(sched_job);
 
 	drm_sched_job_cleanup(sched_job);
-
-	v3d_tfu_job_put(job);
+	v3d_job_put(job);
 }
 
 /**
- * Returns the fences that the bin or render job depends on, one by one.
- * v3d_job_run() won't be called until all of them have been signaled.
+ * Returns the fences that the job depends on, one by one.
+ *
+ * If placed in the scheduler's .dependency method, the corresponding
+ * .run_job won't be called until all of them have been signaled.
  */
 static struct dma_fence *
 v3d_job_dependency(struct drm_sched_job *sched_job,
 		   struct drm_sched_entity *s_entity)
 {
 	struct v3d_job *job = to_v3d_job(sched_job);
-	struct v3d_exec_info *exec = job->exec;
-	enum v3d_queue q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
-	struct dma_fence *fence;
-
-	fence = job->in_fence;
-	if (fence) {
-		job->in_fence = NULL;
-		return fence;
-	}
-
-	if (q == V3D_RENDER) {
-		/* If we had a bin job, the render job definitely depends on
-		 * it. We first have to wait for bin to be scheduled, so that
-		 * its done_fence is created.
-		 */
-		fence = exec->bin_done_fence;
-		if (fence) {
-			exec->bin_done_fence = NULL;
-			return fence;
-		}
-	}
 
 	/* XXX: Wait on a fence for switching the GMP if necessary,
 	 * and then do so.
 	 */
 
-	return fence;
-}
-
-/**
- * Returns the fences that the TFU job depends on, one by one.
- * v3d_tfu_job_run() won't be called until all of them have been
- * signaled.
- */
-static struct dma_fence *
-v3d_tfu_job_dependency(struct drm_sched_job *sched_job,
-		       struct drm_sched_entity *s_entity)
-{
-	struct v3d_tfu_job *job = to_tfu_job(sched_job);
-	struct dma_fence *fence;
-
-	fence = job->in_fence;
-	if (fence) {
-		job->in_fence = NULL;
-		return fence;
-	}
+	if (!xa_empty(&job->deps))
+		return xa_erase(&job->deps, job->last_dep++);
 
 	return NULL;
 }
 
-static struct dma_fence *v3d_job_run(struct drm_sched_job *sched_job)
+static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
 {
-	struct v3d_job *job = to_v3d_job(sched_job);
-	struct v3d_exec_info *exec = job->exec;
-	enum v3d_queue q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
-	struct v3d_dev *v3d = exec->v3d;
+	struct v3d_bin_job *job = to_bin_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
 	unsigned long irqflags;
 
-	if (unlikely(job->base.s_fence->finished.error))
+	if (unlikely(job->base.base.s_fence->finished.error))
 		return NULL;
 
 	/* Lock required around bin_job update vs
 	 * v3d_overflow_mem_work().
 	 */
 	spin_lock_irqsave(&v3d->job_lock, irqflags);
-	if (q == V3D_BIN) {
-		v3d->bin_job = job->exec;
-
-		/* Clear out the overflow allocation, so we don't
-		 * reuse the overflow attached to a previous job.
-		 */
-		V3D_CORE_WRITE(0, V3D_PTB_BPOS, 0);
-	} else {
-		v3d->render_job = job->exec;
-	}
+	v3d->bin_job = job;
+	/* Clear out the overflow allocation, so we don't
+	 * reuse the overflow attached to a previous job.
+	 */
+	V3D_CORE_WRITE(0, V3D_PTB_BPOS, 0);
 	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
 
-	/* Can we avoid this flush when q==RENDER?  We need to be
-	 * careful of scheduling, though -- imagine job0 rendering to
-	 * texture and job1 reading, and them being executed as bin0,
-	 * bin1, render0, render1, so that render1's flush at bin time
+	v3d_invalidate_caches(v3d);
+
+	fence = v3d_fence_create(v3d, V3D_BIN);
+	if (IS_ERR(fence))
+		return NULL;
+
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
+
+	trace_v3d_submit_cl(dev, false, to_v3d_fence(fence)->seqno,
+			    job->start, job->end);
+
+	/* Set the current and end address of the control list.
+	 * Writing the end register is what starts the job.
+	 */
+	if (job->qma) {
+		V3D_CORE_WRITE(0, V3D_CLE_CT0QMA, job->qma);
+		V3D_CORE_WRITE(0, V3D_CLE_CT0QMS, job->qms);
+	}
+	if (job->qts) {
+		V3D_CORE_WRITE(0, V3D_CLE_CT0QTS,
+			       V3D_CLE_CT0QTS_ENABLE |
+			       job->qts);
+	}
+	V3D_CORE_WRITE(0, V3D_CLE_CT0QBA, job->start);
+	V3D_CORE_WRITE(0, V3D_CLE_CT0QEA, job->end);
+
+	return fence;
+}
+
+static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job)
+{
+	struct v3d_render_job *job = to_render_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
+	struct drm_device *dev = &v3d->drm;
+	struct dma_fence *fence;
+
+	if (unlikely(job->base.base.s_fence->finished.error))
+		return NULL;
+
+	v3d->render_job = job;
+
+	/* Can we avoid this flush?  We need to be careful of
+	 * scheduling, though -- imagine job0 rendering to texture and
+	 * job1 reading, and them being executed as bin0, bin1,
+	 * render0, render1, so that render1's flush at bin time
 	 * wasn't enough.
 	 */
 	v3d_invalidate_caches(v3d);
 
-	fence = v3d_fence_create(v3d, q);
+	fence = v3d_fence_create(v3d, V3D_RENDER);
 	if (IS_ERR(fence))
 		return NULL;
 
-	if (job->irq_fence)
-		dma_fence_put(job->irq_fence);
-	job->irq_fence = dma_fence_get(fence);
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
 
-	trace_v3d_submit_cl(dev, q == V3D_RENDER, to_v3d_fence(fence)->seqno,
+	trace_v3d_submit_cl(dev, true, to_v3d_fence(fence)->seqno,
 			    job->start, job->end);
 
-	if (q == V3D_BIN) {
-		if (exec->qma) {
-			V3D_CORE_WRITE(0, V3D_CLE_CT0QMA, exec->qma);
-			V3D_CORE_WRITE(0, V3D_CLE_CT0QMS, exec->qms);
-		}
-		if (exec->qts) {
-			V3D_CORE_WRITE(0, V3D_CLE_CT0QTS,
-				       V3D_CLE_CT0QTS_ENABLE |
-				       exec->qts);
-		}
-	} else {
-		/* XXX: Set the QCFG */
-	}
+	/* XXX: Set the QCFG */
 
 	/* Set the current and end address of the control list.
 	 * Writing the end register is what starts the job.
 	 */
-	V3D_CORE_WRITE(0, V3D_CLE_CTNQBA(q), job->start);
-	V3D_CORE_WRITE(0, V3D_CLE_CTNQEA(q), job->end);
+	V3D_CORE_WRITE(0, V3D_CLE_CT1QBA, job->start);
+	V3D_CORE_WRITE(0, V3D_CLE_CT1QEA, job->end);
 
 	return fence;
 }
@@ -190,7 +184,7 @@ static struct dma_fence *
 v3d_tfu_job_run(struct drm_sched_job *sched_job)
 {
 	struct v3d_tfu_job *job = to_tfu_job(sched_job);
-	struct v3d_dev *v3d = job->v3d;
+	struct v3d_dev *v3d = job->base.v3d;
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
 
@@ -199,9 +193,9 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job)
 		return NULL;
 
 	v3d->tfu_job = job;
-	if (job->irq_fence)
-		dma_fence_put(job->irq_fence);
-	job->irq_fence = dma_fence_get(fence);
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
 
 	trace_v3d_submit_tfu(dev, to_v3d_fence(fence)->seqno);
 
@@ -223,6 +217,48 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job)
 	return fence;
 }
 
+static struct dma_fence *
+v3d_csd_job_run(struct drm_sched_job *sched_job)
+{
+	struct v3d_csd_job *job = to_csd_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
+	struct drm_device *dev = &v3d->drm;
+	struct dma_fence *fence;
+	int i;
+
+	v3d->csd_job = job;
+
+	v3d_invalidate_caches(v3d);
+
+	fence = v3d_fence_create(v3d, V3D_CSD);
+	if (IS_ERR(fence))
+		return NULL;
+
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
+
+	trace_v3d_submit_csd(dev, to_v3d_fence(fence)->seqno);
+
+	for (i = 1; i <= 6; i++)
+		V3D_CORE_WRITE(0, V3D_CSD_QUEUED_CFG0 + 4 * i, job->args.cfg[i]);
+	/* CFG0 write kicks off the job. */
+	V3D_CORE_WRITE(0, V3D_CSD_QUEUED_CFG0, job->args.cfg[0]);
+
+	return fence;
+}
+
+static struct dma_fence *
+v3d_cache_clean_job_run(struct drm_sched_job *sched_job)
+{
+	struct v3d_job *job = to_v3d_job(sched_job);
+	struct v3d_dev *v3d = job->v3d;
+
+	v3d_clean_caches(v3d);
+
+	return NULL;
+}
+
 static void
 v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job)
 {
@@ -232,7 +268,7 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job)
 
 	/* block scheduler */
 	for (q = 0; q < V3D_MAX_QUEUES; q++)
-		drm_sched_stop(&v3d->queue[q].sched);
+		drm_sched_stop(&v3d->queue[q].sched, sched_job);
 
 	if (sched_job)
 		drm_sched_increase_karma(sched_job);
@@ -251,25 +287,23 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job)
 	mutex_unlock(&v3d->reset_lock);
 }
 
+/* If the current address or return address have changed, then the GPU
+ * has probably made progress and we should delay the reset.  This
+ * could fail if the GPU got in an infinite loop in the CL, but that
+ * is pretty unlikely outside of an i-g-t testcase.
+ */
 static void
-v3d_job_timedout(struct drm_sched_job *sched_job)
+v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q,
+		    u32 *timedout_ctca, u32 *timedout_ctra)
 {
 	struct v3d_job *job = to_v3d_job(sched_job);
-	struct v3d_exec_info *exec = job->exec;
-	struct v3d_dev *v3d = exec->v3d;
-	enum v3d_queue job_q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
-	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(job_q));
-	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(job_q));
-
-	/* If the current address or return address have changed, then
-	 * the GPU has probably made progress and we should delay the
-	 * reset.  This could fail if the GPU got in an infinite loop
-	 * in the CL, but that is pretty unlikely outside of an i-g-t
-	 * testcase.
-	 */
-	if (job->timedout_ctca != ctca || job->timedout_ctra != ctra) {
-		job->timedout_ctca = ctca;
-		job->timedout_ctra = ctra;
+	struct v3d_dev *v3d = job->v3d;
+	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(q));
+	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(q));
+
+	if (*timedout_ctca != ctca || *timedout_ctra != ctra) {
+		*timedout_ctca = ctca;
+		*timedout_ctra = ctra;
 		return;
 	}
 
@@ -277,25 +311,82 @@ v3d_job_timedout(struct drm_sched_job *sched_job)
 }
 
 static void
-v3d_tfu_job_timedout(struct drm_sched_job *sched_job)
+v3d_bin_job_timedout(struct drm_sched_job *sched_job)
 {
-	struct v3d_tfu_job *job = to_tfu_job(sched_job);
+	struct v3d_bin_job *job = to_bin_job(sched_job);
+
+	v3d_cl_job_timedout(sched_job, V3D_BIN,
+			    &job->timedout_ctca, &job->timedout_ctra);
+}
+
+static void
+v3d_render_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct v3d_render_job *job = to_render_job(sched_job);
+
+	v3d_cl_job_timedout(sched_job, V3D_RENDER,
+			    &job->timedout_ctca, &job->timedout_ctra);
+}
+
+static void
+v3d_generic_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct v3d_job *job = to_v3d_job(sched_job);
 
 	v3d_gpu_reset_for_timeout(job->v3d, sched_job);
 }
 
-static const struct drm_sched_backend_ops v3d_sched_ops = {
+static void
+v3d_csd_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct v3d_csd_job *job = to_csd_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
+	u32 batches = V3D_CORE_READ(0, V3D_CSD_CURRENT_CFG4);
+
+	/* If we've made progress, skip reset and let the timer get
+	 * rearmed.
+	 */
+	if (job->timedout_batches != batches) {
+		job->timedout_batches = batches;
+		return;
+	}
+
+	v3d_gpu_reset_for_timeout(v3d, sched_job);
+}
+
+static const struct drm_sched_backend_ops v3d_bin_sched_ops = {
 	.dependency = v3d_job_dependency,
-	.run_job = v3d_job_run,
-	.timedout_job = v3d_job_timedout,
-	.free_job = v3d_job_free
+	.run_job = v3d_bin_job_run,
+	.timedout_job = v3d_bin_job_timedout,
+	.free_job = v3d_job_free,
+};
+
+static const struct drm_sched_backend_ops v3d_render_sched_ops = {
+	.dependency = v3d_job_dependency,
+	.run_job = v3d_render_job_run,
+	.timedout_job = v3d_render_job_timedout,
+	.free_job = v3d_job_free,
 };
 
 static const struct drm_sched_backend_ops v3d_tfu_sched_ops = {
-	.dependency = v3d_tfu_job_dependency,
+	.dependency = v3d_job_dependency,
 	.run_job = v3d_tfu_job_run,
-	.timedout_job = v3d_tfu_job_timedout,
-	.free_job = v3d_tfu_job_free
+	.timedout_job = v3d_generic_job_timedout,
+	.free_job = v3d_job_free,
+};
+
+static const struct drm_sched_backend_ops v3d_csd_sched_ops = {
+	.dependency = v3d_job_dependency,
+	.run_job = v3d_csd_job_run,
+	.timedout_job = v3d_csd_job_timedout,
+	.free_job = v3d_job_free
+};
+
+static const struct drm_sched_backend_ops v3d_cache_clean_sched_ops = {
+	.dependency = v3d_job_dependency,
+	.run_job = v3d_cache_clean_job_run,
+	.timedout_job = v3d_generic_job_timedout,
+	.free_job = v3d_job_free
 };
 
 int
@@ -307,7 +398,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 	int ret;
 
 	ret = drm_sched_init(&v3d->queue[V3D_BIN].sched,
-			     &v3d_sched_ops,
+			     &v3d_bin_sched_ops,
 			     hw_jobs_limit, job_hang_limit,
 			     msecs_to_jiffies(hang_limit_ms),
 			     "v3d_bin");
@@ -317,14 +408,14 @@ v3d_sched_init(struct v3d_dev *v3d)
 	}
 
 	ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched,
-			     &v3d_sched_ops,
+			     &v3d_render_sched_ops,
 			     hw_jobs_limit, job_hang_limit,
 			     msecs_to_jiffies(hang_limit_ms),
 			     "v3d_render");
 	if (ret) {
 		dev_err(v3d->dev, "Failed to create render scheduler: %d.",
 			ret);
-		drm_sched_fini(&v3d->queue[V3D_BIN].sched);
+		v3d_sched_fini(v3d);
 		return ret;
 	}
 
@@ -336,11 +427,36 @@ v3d_sched_init(struct v3d_dev *v3d)
 	if (ret) {
 		dev_err(v3d->dev, "Failed to create TFU scheduler: %d.",
 			ret);
-		drm_sched_fini(&v3d->queue[V3D_RENDER].sched);
-		drm_sched_fini(&v3d->queue[V3D_BIN].sched);
+		v3d_sched_fini(v3d);
 		return ret;
 	}
 
+	if (v3d_has_csd(v3d)) {
+		ret = drm_sched_init(&v3d->queue[V3D_CSD].sched,
+				     &v3d_csd_sched_ops,
+				     hw_jobs_limit, job_hang_limit,
+				     msecs_to_jiffies(hang_limit_ms),
+				     "v3d_csd");
+		if (ret) {
+			dev_err(v3d->dev, "Failed to create CSD scheduler: %d.",
+				ret);
+			v3d_sched_fini(v3d);
+			return ret;
+		}
+
+		ret = drm_sched_init(&v3d->queue[V3D_CACHE_CLEAN].sched,
+				     &v3d_cache_clean_sched_ops,
+				     hw_jobs_limit, job_hang_limit,
+				     msecs_to_jiffies(hang_limit_ms),
+				     "v3d_cache_clean");
+		if (ret) {
+			dev_err(v3d->dev, "Failed to create CACHE_CLEAN scheduler: %d.",
+				ret);
+			v3d_sched_fini(v3d);
+			return ret;
+		}
+	}
+
 	return 0;
 }
 
@@ -349,6 +465,8 @@ v3d_sched_fini(struct v3d_dev *v3d)
 {
 	enum v3d_queue q;
 
-	for (q = 0; q < V3D_MAX_QUEUES; q++)
-		drm_sched_fini(&v3d->queue[q].sched);
+	for (q = 0; q < V3D_MAX_QUEUES; q++) {
+		if (v3d->queue[q].sched.ready)
+			drm_sched_fini(&v3d->queue[q].sched);
+	}
 }
diff --git a/drivers/gpu/drm/v3d/v3d_trace.h b/drivers/gpu/drm/v3d/v3d_trace.h
index edd984afa33f..7aa8dc356e54 100644
--- a/drivers/gpu/drm/v3d/v3d_trace.h
+++ b/drivers/gpu/drm/v3d/v3d_trace.h
@@ -124,6 +124,26 @@ TRACE_EVENT(v3d_tfu_irq,
 		      __entry->seqno)
 );
 
+TRACE_EVENT(v3d_csd_irq,
+	    TP_PROTO(struct drm_device *dev,
+		     uint64_t seqno),
+	    TP_ARGS(dev, seqno),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u64, seqno)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->seqno = seqno;
+			   ),
+
+	    TP_printk("dev=%u, seqno=%llu",
+		      __entry->dev,
+		      __entry->seqno)
+);
+
 TRACE_EVENT(v3d_submit_tfu_ioctl,
 	    TP_PROTO(struct drm_device *dev, u32 iia),
 	    TP_ARGS(dev, iia),
@@ -163,6 +183,80 @@ TRACE_EVENT(v3d_submit_tfu,
 		      __entry->seqno)
 );
 
+TRACE_EVENT(v3d_submit_csd_ioctl,
+	    TP_PROTO(struct drm_device *dev, u32 cfg5, u32 cfg6),
+	    TP_ARGS(dev, cfg5, cfg6),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u32, cfg5)
+			     __field(u32, cfg6)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->cfg5 = cfg5;
+			   __entry->cfg6 = cfg6;
+			   ),
+
+	    TP_printk("dev=%u, CFG5 0x%08x, CFG6 0x%08x",
+		      __entry->dev,
+		      __entry->cfg5,
+		      __entry->cfg6)
+);
+
+TRACE_EVENT(v3d_submit_csd,
+	    TP_PROTO(struct drm_device *dev,
+		     uint64_t seqno),
+	    TP_ARGS(dev, seqno),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u64, seqno)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->seqno = seqno;
+			   ),
+
+	    TP_printk("dev=%u, seqno=%llu",
+		      __entry->dev,
+		      __entry->seqno)
+);
+
+TRACE_EVENT(v3d_cache_clean_begin,
+	    TP_PROTO(struct drm_device *dev),
+	    TP_ARGS(dev),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   ),
+
+	    TP_printk("dev=%u",
+		      __entry->dev)
+);
+
+TRACE_EVENT(v3d_cache_clean_end,
+	    TP_PROTO(struct drm_device *dev),
+	    TP_ARGS(dev),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   ),
+
+	    TP_printk("dev=%u",
+		      __entry->dev)
+);
+
 TRACE_EVENT(v3d_reset_begin,
 	    TP_PROTO(struct drm_device *dev),
 	    TP_ARGS(dev),