Merge tag 'drm-misc-next-2019-03-21' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for 5.2:

UAPI Changes:
- Add Colorspace connector property (Uma)
- fourcc: Several new YUV formats from ARM (Brian & Ayan)
- fourcc: Fix merge conflicts between new formats above and Swati's that
  went in via topic/hdr-formats-2019-03-07 branch (Maarten)

Cross-subsystem Changes:
- Typed component support via topic/component-typed-2019-02-11 (Maxime/Daniel)

Core Changes:
- Improve component helper documentation (Daniel)
- Avoid calling drm_dev_unregister() twice on unplugged devices (Noralf)
- Add device managed (devm) drm_device init function (Noralf)
- Graduate TINYDRM_MODE to DRM_SIMPLE_MODE in core (Noralf)
- Move MIPI/DSI rate control params computation into core from i915 (David)
- Add support for shmem backed gem objects (Noralf)

Driver Changes:
- various: Use of_node_name_eq for node name comparisons (Rob Herring)
- sun4i: Add DSI burst mode support (Konstantin)
- panel: Add Ronbo RB070D30 MIPI/DSI panel support (Konstantin)
- virtio: A few prime improvements (Gerd)
- tinydrm: Remove tinydrm_device (Noralf)
- vc4: Add load tracker to driver to detect underflow in atomic check (Boris)
- vboxvideo: Move it out of staging \o/ (Hans)
- v3d: Add support for V3D v4.2 (Eric)

Cc: Konstantin Sudakov <k.sudakov@integrasources.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Maxime Ripard <maxime.ripard@bootlin.com>
Cc: Uma Shankar <uma.shankar@intel.com>
Cc: Noralf Trønnes <noralf@tronnes.org>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: David Francis <David.Francis@amd.com>
Cc: Boris Brezillon <boris.brezillon@bootlin.com>
Cc: Eric Anholt <eric@anholt.net>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Brian Starkey <brian.starkey@arm.com>
Cc: Ayan Kumar Halder <ayan.halder@arm.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

From: Sean Paul <sean@poorly.run>
Link: https://patchwork.freedesktop.org/patch/msgid/20190321170805.GA50145@art_vandelay

11 files changed, 344 insertions, 71 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 8dcce7182bb7..92e3f98d8478 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -201,8 +201,6 @@ static void vc4_bo_destroy(struct vc4_bo *bo)
 		bo->validated_shader = NULL;
 	}
 
-	reservation_object_fini(&bo->_resv);
-
 	drm_gem_cma_free_object(obj);
 }
 
@@ -427,8 +425,6 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size)
 	vc4->bo_labels[VC4_BO_TYPE_KERNEL].num_allocated++;
 	vc4->bo_labels[VC4_BO_TYPE_KERNEL].size_allocated += size;
 	mutex_unlock(&vc4->bo_lock);
-	bo->resv = &bo->_resv;
-	reservation_object_init(bo->resv);
 
 	return &bo->base.base;
 }
@@ -684,13 +680,6 @@ static void vc4_bo_cache_time_timer(struct timer_list *t)
 	schedule_work(&vc4->bo_cache.time_work);
 }
 
-struct reservation_object *vc4_prime_res_obj(struct drm_gem_object *obj)
-{
-	struct vc4_bo *bo = to_vc4_bo(obj);
-
-	return bo->resv;
-}
-
 struct dma_buf *
 vc4_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags)
 {
@@ -822,14 +811,12 @@ vc4_prime_import_sg_table(struct drm_device *dev,
 			  struct sg_table *sgt)
 {
 	struct drm_gem_object *obj;
-	struct vc4_bo *bo;
 
 	obj = drm_gem_cma_prime_import_sg_table(dev, attach, sgt);
 	if (IS_ERR(obj))
 		return obj;
 
-	bo = to_vc4_bo(obj);
-	bo->resv = attach->dmabuf->resv;
+	obj->resv = attach->dmabuf->resv;
 
 	return obj;
 }
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 730008d3da76..64c964b7c577 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -834,6 +834,14 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc)
 		drm_crtc_send_vblank_event(crtc, vc4_crtc->event);
 		vc4_crtc->event = NULL;
 		drm_crtc_vblank_put(crtc);
+
+		/* Wait for the page flip to unmask the underrun to ensure that
+		 * the display list was updated by the hardware. Before that
+		 * happens, the HVS will be using the previous display list with
+		 * the CRTC and encoder already reconfigured, leading to
+		 * underruns. This can be seen when reconfiguring the CRTC.
+		 */
+		vc4_hvs_unmask_underrun(dev, vc4_crtc->channel);
 	}
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
diff --git a/drivers/gpu/drm/vc4/vc4_debugfs.c b/drivers/gpu/drm/vc4/vc4_debugfs.c
index 7a0003de71ab..59cdad89f844 100644
--- a/drivers/gpu/drm/vc4/vc4_debugfs.c
+++ b/drivers/gpu/drm/vc4/vc4_debugfs.c
@@ -23,6 +23,7 @@ static const struct drm_info_list vc4_debugfs_list[] = {
 	{"vec_regs", vc4_vec_debugfs_regs, 0},
 	{"txp_regs", vc4_txp_debugfs_regs, 0},
 	{"hvs_regs", vc4_hvs_debugfs_regs, 0},
+	{"hvs_underrun",  vc4_hvs_debugfs_underrun, 0},
 	{"crtc0_regs", vc4_crtc_debugfs_regs, 0, (void *)(uintptr_t)0},
 	{"crtc1_regs", vc4_crtc_debugfs_regs, 0, (void *)(uintptr_t)1},
 	{"crtc2_regs", vc4_crtc_debugfs_regs, 0, (void *)(uintptr_t)2},
@@ -35,6 +36,15 @@ static const struct drm_info_list vc4_debugfs_list[] = {
 int
 vc4_debugfs_init(struct drm_minor *minor)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(minor->dev);
+	struct dentry *dentry;
+
+	dentry = debugfs_create_bool("hvs_load_tracker", S_IRUGO | S_IWUSR,
+				     minor->debugfs_root,
+				     &vc4->load_tracker_enabled);
+	if (!dentry)
+		return -ENOMEM;
+
 	return drm_debugfs_create_files(vc4_debugfs_list, VC4_DEBUGFS_ENTRIES,
 					minor->debugfs_root, minor);
 }
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 5fcd2f0da7f7..4daf44fd4548 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -200,7 +200,6 @@ static struct drm_driver vc4_drm_driver = {
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_import = drm_gem_prime_import,
 	.gem_prime_export = vc4_prime_export,
-	.gem_prime_res_obj = vc4_prime_res_obj,
 	.gem_prime_get_sg_table	= drm_gem_cma_prime_get_sg_table,
 	.gem_prime_import_sg_table = vc4_prime_import_sg_table,
 	.gem_prime_vmap = vc4_prime_vmap,
@@ -287,7 +286,7 @@ static int vc4_drm_bind(struct device *dev)
 
 	vc4_kms_load(drm);
 
-	drm_fbdev_generic_setup(drm, 32);
+	drm_fbdev_generic_setup(drm, 16);
 
 	return 0;
 
@@ -312,6 +311,7 @@ static void vc4_drm_unbind(struct device *dev)
 
 	drm_mode_config_cleanup(drm);
 
+	drm_atomic_private_obj_fini(&vc4->load_tracker);
 	drm_atomic_private_obj_fini(&vc4->ctm_manager);
 
 	drm_dev_put(drm);
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 2c635f001c71..7a3c093e7443 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -7,7 +7,6 @@
  */
 
 #include <linux/mm_types.h>
-#include <linux/reservation.h>
 #include <drm/drmP.h>
 #include <drm/drm_util.h>
 #include <drm/drm_encoder.h>
@@ -185,10 +184,20 @@ struct vc4_dev {
 	/* Bitmask of the current bin_alloc used for overflow memory. */
 	uint32_t bin_alloc_overflow;
 
+	/* Incremented when an underrun error happened after an atomic commit.
+	 * This is particularly useful to detect when a specific modeset is too
+	 * demanding in term of memory or HVS bandwidth which is hard to guess
+	 * at atomic check time.
+	 */
+	atomic_t underrun;
+
 	struct work_struct overflow_mem_work;
 
 	int power_refcount;
 
+	/* Set to true when the load tracker is active. */
+	bool load_tracker_enabled;
+
 	/* Mutex controlling the power refcount. */
 	struct mutex power_lock;
 
@@ -201,6 +210,7 @@ struct vc4_dev {
 
 	struct drm_modeset_lock ctm_state_lock;
 	struct drm_private_obj ctm_manager;
+	struct drm_private_obj load_tracker;
 };
 
 static inline struct vc4_dev *
@@ -240,10 +250,6 @@ struct vc4_bo {
 	 */
 	struct vc4_validated_shader_info *validated_shader;
 
-	/* normally (resv == &_resv) except for imported bo's */
-	struct reservation_object *resv;
-	struct reservation_object _resv;
-
 	/* One of enum vc4_kernel_bo_type, or VC4_BO_TYPE_COUNT + i
 	 * for user-allocated labels.
 	 */
@@ -376,6 +382,16 @@ struct vc4_plane_state {
 	 * when async update is not possible.
 	 */
 	bool dlist_initialized;
+
+	/* Load of this plane on the HVS block. The load is expressed in HVS
+	 * cycles/sec.
+	 */
+	u64 hvs_load;
+
+	/* Memory bandwidth needed for this plane. This is expressed in
+	 * bytes/sec.
+	 */
+	u64 membus_load;
 };
 
 static inline struct vc4_plane_state *
@@ -685,7 +701,6 @@ int vc4_label_bo_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
 vm_fault_t vc4_fault(struct vm_fault *vmf);
 int vc4_mmap(struct file *filp, struct vm_area_struct *vma);
-struct reservation_object *vc4_prime_res_obj(struct drm_gem_object *obj);
 int vc4_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
 struct drm_gem_object *vc4_prime_import_sg_table(struct drm_device *dev,
 						 struct dma_buf_attachment *attach,
@@ -773,6 +788,9 @@ void vc4_irq_reset(struct drm_device *dev);
 extern struct platform_driver vc4_hvs_driver;
 void vc4_hvs_dump_state(struct drm_device *dev);
 int vc4_hvs_debugfs_regs(struct seq_file *m, void *unused);
+int vc4_hvs_debugfs_underrun(struct seq_file *m, void *unused);
+void vc4_hvs_unmask_underrun(struct drm_device *dev, int channel);
+void vc4_hvs_mask_underrun(struct drm_device *dev, int channel);
 
 /* vc4_kms.c */
 int vc4_kms_load(struct drm_device *dev);
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index aea2b8dfec17..5ee5bf7fedf7 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -536,7 +536,7 @@ vc4_update_bo_seqnos(struct vc4_exec_info *exec, uint64_t seqno)
 		bo = to_vc4_bo(&exec->bo[i]->base);
 		bo->seqno = seqno;
 
-		reservation_object_add_shared_fence(bo->resv, exec->fence);
+		reservation_object_add_shared_fence(bo->base.base.resv, exec->fence);
 	}
 
 	list_for_each_entry(bo, &exec->unref_list, unref_head) {
@@ -547,7 +547,7 @@ vc4_update_bo_seqnos(struct vc4_exec_info *exec, uint64_t seqno)
 		bo = to_vc4_bo(&exec->rcl_write_bo[i]->base);
 		bo->write_seqno = seqno;
 
-		reservation_object_add_excl_fence(bo->resv, exec->fence);
+		reservation_object_add_excl_fence(bo->base.base.resv, exec->fence);
 	}
 }
 
@@ -559,7 +559,7 @@ vc4_unlock_bo_reservations(struct drm_device *dev,
 	int i;
 
 	for (i = 0; i < exec->bo_count; i++) {
-		struct vc4_bo *bo = to_vc4_bo(&exec->bo[i]->base);
+		struct drm_gem_object *bo = &exec->bo[i]->base;
 
 		ww_mutex_unlock(&bo->resv->lock);
 	}
@@ -581,13 +581,13 @@ vc4_lock_bo_reservations(struct drm_device *dev,
 {
 	int contended_lock = -1;
 	int i, ret;
-	struct vc4_bo *bo;
+	struct drm_gem_object *bo;
 
 	ww_acquire_init(acquire_ctx, &reservation_ww_class);
 
 retry:
 	if (contended_lock != -1) {
-		bo = to_vc4_bo(&exec->bo[contended_lock]->base);
+		bo = &exec->bo[contended_lock]->base;
 		ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock,
 						       acquire_ctx);
 		if (ret) {
@@ -600,19 +600,19 @@ retry:
 		if (i == contended_lock)
 			continue;
 
-		bo = to_vc4_bo(&exec->bo[i]->base);
+		bo = &exec->bo[i]->base;
 
 		ret = ww_mutex_lock_interruptible(&bo->resv->lock, acquire_ctx);
 		if (ret) {
 			int j;
 
 			for (j = 0; j < i; j++) {
-				bo = to_vc4_bo(&exec->bo[j]->base);
+				bo = &exec->bo[j]->base;
 				ww_mutex_unlock(&bo->resv->lock);
 			}
 
 			if (contended_lock != -1 && contended_lock >= i) {
-				bo = to_vc4_bo(&exec->bo[contended_lock]->base);
+				bo = &exec->bo[contended_lock]->base;
 
 				ww_mutex_unlock(&bo->resv->lock);
 			}
@@ -633,7 +633,7 @@ retry:
 	 * before we commit the CL to the hardware.
 	 */
 	for (i = 0; i < exec->bo_count; i++) {
-		bo = to_vc4_bo(&exec->bo[i]->base);
+		bo = &exec->bo[i]->base;
 
 		ret = reservation_object_reserve_shared(bo->resv, 1);
 		if (ret) {
diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c
index 5d8c749c9749..918e71256ecc 100644
--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -22,6 +22,7 @@
  * each CRTC.
  */
 
+#include <drm/drm_atomic_helper.h>
 #include <linux/component.h>
 #include "vc4_drv.h"
 #include "vc4_regs.h"
@@ -102,6 +103,18 @@ int vc4_hvs_debugfs_regs(struct seq_file *m, void *unused)
 
 	return 0;
 }
+
+int vc4_hvs_debugfs_underrun(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct drm_printer p = drm_seq_file_printer(m);
+
+	drm_printf(&p, "%d\n", atomic_read(&vc4->underrun));
+
+	return 0;
+}
 #endif
 
 /* The filter kernel is composed of dwords each containing 3 9-bit
@@ -166,6 +179,67 @@ static int vc4_hvs_upload_linear_kernel(struct vc4_hvs *hvs,
 	return 0;
 }
 
+void vc4_hvs_mask_underrun(struct drm_device *dev, int channel)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	u32 dispctrl = HVS_READ(SCALER_DISPCTRL);
+
+	dispctrl &= ~SCALER_DISPCTRL_DSPEISLUR(channel);
+
+	HVS_WRITE(SCALER_DISPCTRL, dispctrl);
+}
+
+void vc4_hvs_unmask_underrun(struct drm_device *dev, int channel)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	u32 dispctrl = HVS_READ(SCALER_DISPCTRL);
+
+	dispctrl |= SCALER_DISPCTRL_DSPEISLUR(channel);
+
+	HVS_WRITE(SCALER_DISPSTAT,
+		  SCALER_DISPSTAT_EUFLOW(channel));
+	HVS_WRITE(SCALER_DISPCTRL, dispctrl);
+}
+
+static void vc4_hvs_report_underrun(struct drm_device *dev)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+	atomic_inc(&vc4->underrun);
+	DRM_DEV_ERROR(dev->dev, "HVS underrun\n");
+}
+
+static irqreturn_t vc4_hvs_irq_handler(int irq, void *data)
+{
+	struct drm_device *dev = data;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	irqreturn_t irqret = IRQ_NONE;
+	int channel;
+	u32 control;
+	u32 status;
+
+	status = HVS_READ(SCALER_DISPSTAT);
+	control = HVS_READ(SCALER_DISPCTRL);
+
+	for (channel = 0; channel < SCALER_CHANNELS_COUNT; channel++) {
+		/* Interrupt masking is not always honored, so check it here. */
+		if (status & SCALER_DISPSTAT_EUFLOW(channel) &&
+		    control & SCALER_DISPCTRL_DSPEISLUR(channel)) {
+			vc4_hvs_mask_underrun(dev, channel);
+			vc4_hvs_report_underrun(dev);
+
+			irqret = IRQ_HANDLED;
+		}
+	}
+
+	/* Clear every per-channel interrupt flag. */
+	HVS_WRITE(SCALER_DISPSTAT, SCALER_DISPSTAT_IRQMASK(0) |
+				   SCALER_DISPSTAT_IRQMASK(1) |
+				   SCALER_DISPSTAT_IRQMASK(2));
+
+	return irqret;
+}
+
 static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -219,15 +293,36 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 	dispctrl = HVS_READ(SCALER_DISPCTRL);
 
 	dispctrl |= SCALER_DISPCTRL_ENABLE;
+	dispctrl |= SCALER_DISPCTRL_DISPEIRQ(0) |
+		    SCALER_DISPCTRL_DISPEIRQ(1) |
+		    SCALER_DISPCTRL_DISPEIRQ(2);
 
 	/* Set DSP3 (PV1) to use HVS channel 2, which would otherwise
 	 * be unused.
 	 */
 	dispctrl &= ~SCALER_DISPCTRL_DSP3_MUX_MASK;
+	dispctrl &= ~(SCALER_DISPCTRL_DMAEIRQ |
+		      SCALER_DISPCTRL_SLVWREIRQ |
+		      SCALER_DISPCTRL_SLVRDEIRQ |
+		      SCALER_DISPCTRL_DSPEIEOF(0) |
+		      SCALER_DISPCTRL_DSPEIEOF(1) |
+		      SCALER_DISPCTRL_DSPEIEOF(2) |
+		      SCALER_DISPCTRL_DSPEIEOLN(0) |
+		      SCALER_DISPCTRL_DSPEIEOLN(1) |
+		      SCALER_DISPCTRL_DSPEIEOLN(2) |
+		      SCALER_DISPCTRL_DSPEISLUR(0) |
+		      SCALER_DISPCTRL_DSPEISLUR(1) |
+		      SCALER_DISPCTRL_DSPEISLUR(2) |
+		      SCALER_DISPCTRL_SCLEIRQ);
 	dispctrl |= VC4_SET_FIELD(2, SCALER_DISPCTRL_DSP3_MUX);
 
 	HVS_WRITE(SCALER_DISPCTRL, dispctrl);
 
+	ret = devm_request_irq(dev, platform_get_irq(pdev, 0),
+			       vc4_hvs_irq_handler, 0, "vc4 hvs", drm);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index 91b8c72ff361..5160cad25fce 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -34,6 +34,18 @@ static struct vc4_ctm_state *to_vc4_ctm_state(struct drm_private_state *priv)
 	return container_of(priv, struct vc4_ctm_state, base);
 }
 
+struct vc4_load_tracker_state {
+	struct drm_private_state base;
+	u64 hvs_load;
+	u64 membus_load;
+};
+
+static struct vc4_load_tracker_state *
+to_vc4_load_tracker_state(struct drm_private_state *priv)
+{
+	return container_of(priv, struct vc4_load_tracker_state, base);
+}
+
 static struct vc4_ctm_state *vc4_get_ctm_state(struct drm_atomic_state *state,
 					       struct drm_private_obj *manager)
 {
@@ -138,6 +150,16 @@ vc4_atomic_complete_commit(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_crtc *vc4_crtc;
+	int i;
+
+	for (i = 0; i < dev->mode_config.num_crtc; i++) {
+		if (!state->crtcs[i].ptr || !state->crtcs[i].commit)
+			continue;
+
+		vc4_crtc = to_vc4_crtc(state->crtcs[i].ptr);
+		vc4_hvs_mask_underrun(dev, vc4_crtc->channel);
+	}
 
 	drm_atomic_helper_wait_for_fences(dev, state, false);
 
@@ -385,6 +407,85 @@ vc4_ctm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
 	return 0;
 }
 
+static int vc4_load_tracker_atomic_check(struct drm_atomic_state *state)
+{
+	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct vc4_dev *vc4 = to_vc4_dev(state->dev);
+	struct vc4_load_tracker_state *load_state;
+	struct drm_private_state *priv_state;
+	struct drm_plane *plane;
+	int i;
+
+	priv_state = drm_atomic_get_private_obj_state(state,
+						      &vc4->load_tracker);
+	if (IS_ERR(priv_state))
+		return PTR_ERR(priv_state);
+
+	load_state = to_vc4_load_tracker_state(priv_state);
+	for_each_oldnew_plane_in_state(state, plane, old_plane_state,
+				       new_plane_state, i) {
+		struct vc4_plane_state *vc4_plane_state;
+
+		if (old_plane_state->fb && old_plane_state->crtc) {
+			vc4_plane_state = to_vc4_plane_state(old_plane_state);
+			load_state->membus_load -= vc4_plane_state->membus_load;
+			load_state->hvs_load -= vc4_plane_state->hvs_load;
+		}
+
+		if (new_plane_state->fb && new_plane_state->crtc) {
+			vc4_plane_state = to_vc4_plane_state(new_plane_state);
+			load_state->membus_load += vc4_plane_state->membus_load;
+			load_state->hvs_load += vc4_plane_state->hvs_load;
+		}
+	}
+
+	/* Don't check the load when the tracker is disabled. */
+	if (!vc4->load_tracker_enabled)
+		return 0;
+
+	/* The absolute limit is 2Gbyte/sec, but let's take a margin to let
+	 * the system work when other blocks are accessing the memory.
+	 */
+	if (load_state->membus_load > SZ_1G + SZ_512M)
+		return -ENOSPC;
+
+	/* HVS clock is supposed to run @ 250Mhz, let's take a margin and
+	 * consider the maximum number of cycles is 240M.
+	 */
+	if (load_state->hvs_load > 240000000ULL)
+		return -ENOSPC;
+
+	return 0;
+}
+
+static struct drm_private_state *
+vc4_load_tracker_duplicate_state(struct drm_private_obj *obj)
+{
+	struct vc4_load_tracker_state *state;
+
+	state = kmemdup(obj->state, sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return NULL;
+
+	__drm_atomic_helper_private_obj_duplicate_state(obj, &state->base);
+
+	return &state->base;
+}
+
+static void vc4_load_tracker_destroy_state(struct drm_private_obj *obj,
+					   struct drm_private_state *state)
+{
+	struct vc4_load_tracker_state *load_state;
+
+	load_state = to_vc4_load_tracker_state(state);
+	kfree(load_state);
+}
+
+static const struct drm_private_state_funcs vc4_load_tracker_state_funcs = {
+	.atomic_duplicate_state = vc4_load_tracker_duplicate_state,
+	.atomic_destroy_state = vc4_load_tracker_destroy_state,
+};
+
 static int
 vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
 {
@@ -394,7 +495,11 @@ vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
 	if (ret < 0)
 		return ret;
 
-	return drm_atomic_helper_check(dev, state);
+	ret = drm_atomic_helper_check(dev, state);
+	if (ret)
+		return ret;
+
+	return vc4_load_tracker_atomic_check(state);
 }
 
 static const struct drm_mode_config_funcs vc4_mode_funcs = {
@@ -407,8 +512,14 @@ int vc4_kms_load(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_ctm_state *ctm_state;
+	struct vc4_load_tracker_state *load_state;
 	int ret;
 
+	/* Start with the load tracker enabled. Can be disabled through the
+	 * debugfs load_tracker file.
+	 */
+	vc4->load_tracker_enabled = true;
+
 	sema_init(&vc4->async_modeset, 1);
 
 	/* Set support for vblank irq fast disable, before drm_vblank_init() */
@@ -436,6 +547,15 @@ int vc4_kms_load(struct drm_device *dev)
 	drm_atomic_private_obj_init(dev, &vc4->ctm_manager, &ctm_state->base,
 				    &vc4_ctm_state_funcs);
 
+	load_state = kzalloc(sizeof(*load_state), GFP_KERNEL);
+	if (!load_state) {
+		drm_atomic_private_obj_fini(&vc4->ctm_manager);
+		return -ENOMEM;
+	}
+
+	drm_atomic_private_obj_init(dev, &vc4->load_tracker, &load_state->base,
+				    &vc4_load_tracker_state_funcs);
+
 	drm_mode_config_reset(dev);
 
 	drm_kms_helper_poll_init(dev);
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index d098337c10e9..4d918d3e4858 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -488,6 +488,61 @@ static void vc4_write_scaling_parameters(struct drm_plane_state *state,
 	}
 }
 
+static void vc4_plane_calc_load(struct drm_plane_state *state)
+{
+	unsigned int hvs_load_shift, vrefresh, i;
+	struct drm_framebuffer *fb = state->fb;
+	struct vc4_plane_state *vc4_state;
+	struct drm_crtc_state *crtc_state;
+	unsigned int vscale_factor;
+
+	vc4_state = to_vc4_plane_state(state);
+	crtc_state = drm_atomic_get_existing_crtc_state(state->state,
+							state->crtc);
+	vrefresh = drm_mode_vrefresh(&crtc_state->adjusted_mode);
+
+	/* The HVS is able to process 2 pixels/cycle when scaling the source,
+	 * 4 pixels/cycle otherwise.
+	 * Alpha blending step seems to be pipelined and it's always operating
+	 * at 4 pixels/cycle, so the limiting aspect here seems to be the
+	 * scaler block.
+	 * HVS load is expressed in clk-cycles/sec (AKA Hz).
+	 */
+	if (vc4_state->x_scaling[0] != VC4_SCALING_NONE ||
+	    vc4_state->x_scaling[1] != VC4_SCALING_NONE ||
+	    vc4_state->y_scaling[0] != VC4_SCALING_NONE ||
+	    vc4_state->y_scaling[1] != VC4_SCALING_NONE)
+		hvs_load_shift = 1;
+	else
+		hvs_load_shift = 2;
+
+	vc4_state->membus_load = 0;
+	vc4_state->hvs_load = 0;
+	for (i = 0; i < fb->format->num_planes; i++) {
+		/* Even if the bandwidth/plane required for a single frame is
+		 *
+		 * vc4_state->src_w[i] * vc4_state->src_h[i] * cpp * vrefresh
+		 *
+		 * when downscaling, we have to read more pixels per line in
+		 * the time frame reserved for a single line, so the bandwidth
+		 * demand can be punctually higher. To account for that, we
+		 * calculate the down-scaling factor and multiply the plane
+		 * load by this number. We're likely over-estimating the read
+		 * demand, but that's better than under-estimating it.
+		 */
+		vscale_factor = DIV_ROUND_UP(vc4_state->src_h[i],
+					     vc4_state->crtc_h);
+		vc4_state->membus_load += vc4_state->src_w[i] *
+					  vc4_state->src_h[i] * vscale_factor *
+					  fb->format->cpp[i];
+		vc4_state->hvs_load += vc4_state->crtc_h * vc4_state->crtc_w;
+	}
+
+	vc4_state->hvs_load *= vrefresh;
+	vc4_state->hvs_load >>= hvs_load_shift;
+	vc4_state->membus_load *= vrefresh;
+}
+
 static int vc4_plane_allocate_lbm(struct drm_plane_state *state)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(state->plane->dev);
@@ -875,6 +930,8 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	 */
 	vc4_state->dlist_initialized = 1;
 
+	vc4_plane_calc_load(state);
+
 	return 0;
 }
 
@@ -1082,7 +1139,7 @@ static int vc4_prepare_fb(struct drm_plane *plane,
 
 	bo = to_vc4_bo(&drm_fb_cma_get_gem_obj(state->fb, 0)->base);
 
-	fence = reservation_object_get_excl_rcu(bo->resv);
+	fence = reservation_object_get_excl_rcu(bo->base.base.resv);
 	drm_atomic_set_fence_for_plane(state, fence);
 
 	if (plane->state->fb == state->fb)
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index 931088014272..c0c5fadaf7e3 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -212,11 +212,11 @@
 
 #define PV_HACT_ACT				0x30
 
+#define SCALER_CHANNELS_COUNT			3
+
 #define SCALER_DISPCTRL                         0x00000000
 /* Global register for clock gating the HVS */
 # define SCALER_DISPCTRL_ENABLE			BIT(31)
-# define SCALER_DISPCTRL_DSP2EISLUR		BIT(15)
-# define SCALER_DISPCTRL_DSP1EISLUR		BIT(14)
 # define SCALER_DISPCTRL_DSP3_MUX_MASK		VC4_MASK(19, 18)
 # define SCALER_DISPCTRL_DSP3_MUX_SHIFT		18
 
@@ -224,45 +224,25 @@
  * SCALER_DISPSTAT_IRQDISP0.  Note that short frame contributions are
  * always enabled.
  */
-# define SCALER_DISPCTRL_DSP0EISLUR		BIT(13)
-# define SCALER_DISPCTRL_DSP2EIEOLN		BIT(12)
-# define SCALER_DISPCTRL_DSP2EIEOF		BIT(11)
-# define SCALER_DISPCTRL_DSP1EIEOLN		BIT(10)
-# define SCALER_DISPCTRL_DSP1EIEOF		BIT(9)
+# define SCALER_DISPCTRL_DSPEISLUR(x)		BIT(13 + (x))
 /* Enables Display 0 end-of-line-N contribution to
  * SCALER_DISPSTAT_IRQDISP0
  */
-# define SCALER_DISPCTRL_DSP0EIEOLN		BIT(8)
+# define SCALER_DISPCTRL_DSPEIEOLN(x)		BIT(8 + ((x) * 2))
 /* Enables Display 0 EOF contribution to SCALER_DISPSTAT_IRQDISP0 */
-# define SCALER_DISPCTRL_DSP0EIEOF		BIT(7)
+# define SCALER_DISPCTRL_DSPEIEOF(x)		BIT(7 + ((x) * 2))
 
 # define SCALER_DISPCTRL_SLVRDEIRQ		BIT(6)
 # define SCALER_DISPCTRL_SLVWREIRQ		BIT(5)
 # define SCALER_DISPCTRL_DMAEIRQ		BIT(4)
-# define SCALER_DISPCTRL_DISP2EIRQ		BIT(3)
-# define SCALER_DISPCTRL_DISP1EIRQ		BIT(2)
 /* Enables interrupt generation on the enabled EOF/EOLN/EISLUR
  * bits and short frames..
  */
-# define SCALER_DISPCTRL_DISP0EIRQ		BIT(1)
+# define SCALER_DISPCTRL_DISPEIRQ(x)		BIT(1 + (x))
 /* Enables interrupt generation on scaler profiler interrupt. */
 # define SCALER_DISPCTRL_SCLEIRQ		BIT(0)
 
 #define SCALER_DISPSTAT                         0x00000004
-# define SCALER_DISPSTAT_COBLOW2		BIT(29)
-# define SCALER_DISPSTAT_EOLN2			BIT(28)
-# define SCALER_DISPSTAT_ESFRAME2		BIT(27)
-# define SCALER_DISPSTAT_ESLINE2		BIT(26)
-# define SCALER_DISPSTAT_EUFLOW2		BIT(25)
-# define SCALER_DISPSTAT_EOF2			BIT(24)
-
-# define SCALER_DISPSTAT_COBLOW1		BIT(21)
-# define SCALER_DISPSTAT_EOLN1			BIT(20)
-# define SCALER_DISPSTAT_ESFRAME1		BIT(19)
-# define SCALER_DISPSTAT_ESLINE1		BIT(18)
-# define SCALER_DISPSTAT_EUFLOW1		BIT(17)
-# define SCALER_DISPSTAT_EOF1			BIT(16)
-
 # define SCALER_DISPSTAT_RESP_MASK		VC4_MASK(15, 14)
 # define SCALER_DISPSTAT_RESP_SHIFT		14
 # define SCALER_DISPSTAT_RESP_OKAY		0
@@ -270,23 +250,26 @@
 # define SCALER_DISPSTAT_RESP_SLVERR		2
 # define SCALER_DISPSTAT_RESP_DECERR		3
 
-# define SCALER_DISPSTAT_COBLOW0		BIT(13)
+# define SCALER_DISPSTAT_COBLOW(x)		BIT(13 + ((x) * 8))
 /* Set when the DISPEOLN line is done compositing. */
-# define SCALER_DISPSTAT_EOLN0			BIT(12)
+# define SCALER_DISPSTAT_EOLN(x)		BIT(12 + ((x) * 8))
 /* Set when VSTART is seen but there are still pixels in the current
  * output line.
  */
-# define SCALER_DISPSTAT_ESFRAME0		BIT(11)
+# define SCALER_DISPSTAT_ESFRAME(x)		BIT(11 + ((x) * 8))
 /* Set when HSTART is seen but there are still pixels in the current
  * output line.
  */
-# define SCALER_DISPSTAT_ESLINE0		BIT(10)
+# define SCALER_DISPSTAT_ESLINE(x)		BIT(10 + ((x) * 8))
 /* Set when the the downstream tries to read from the display FIFO
  * while it's empty.
  */
-# define SCALER_DISPSTAT_EUFLOW0		BIT(9)
+# define SCALER_DISPSTAT_EUFLOW(x)		BIT(9 + ((x) * 8))
 /* Set when the display mode changes from RUN to EOF */
-# define SCALER_DISPSTAT_EOF0			BIT(8)
+# define SCALER_DISPSTAT_EOF(x)			BIT(8 + ((x) * 8))
+
+# define SCALER_DISPSTAT_IRQMASK(x)		VC4_MASK(13 + ((x) * 8), \
+							 8 + ((x) * 8))
 
 /* Set on AXI invalid DMA ID error. */
 # define SCALER_DISPSTAT_DMA_ERROR		BIT(7)
@@ -298,12 +281,10 @@
  * SCALER_DISPSTAT_RESP_ERROR is not SCALER_DISPSTAT_RESP_OKAY.
  */
 # define SCALER_DISPSTAT_IRQDMA			BIT(4)
-# define SCALER_DISPSTAT_IRQDISP2		BIT(3)
-# define SCALER_DISPSTAT_IRQDISP1		BIT(2)
 /* Set when any of the EOF/EOLN/ESFRAME/ESLINE bits are set and their
  * corresponding interrupt bit is enabled in DISPCTRL.
  */
-# define SCALER_DISPSTAT_IRQDISP0		BIT(1)
+# define SCALER_DISPSTAT_IRQDISP(x)		BIT(1 + (x))
 /* On read, the profiler interrupt.  On write, clear *all* interrupt bits. */
 # define SCALER_DISPSTAT_IRQSCL			BIT(0)
 
diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c
index 5dabd91f2d7e..cc2888dd7171 100644
--- a/drivers/gpu/drm/vc4/vc4_txp.c
+++ b/drivers/gpu/drm/vc4/vc4_txp.c
@@ -249,7 +249,6 @@ static int vc4_txp_connector_atomic_check(struct drm_connector *conn,
 					struct drm_connector_state *conn_state)
 {
 	struct drm_crtc_state *crtc_state;
-	struct drm_gem_cma_object *gem;
 	struct drm_framebuffer *fb;
 	int i;
 
@@ -275,8 +274,6 @@ static int vc4_txp_connector_atomic_check(struct drm_connector *conn,
 	if (i == ARRAY_SIZE(drm_fmts))
 		return -EINVAL;
 
-	gem = drm_fb_cma_get_gem_obj(fb, 0);
-
 	/* Pitch must be aligned on 16 bytes. */
 	if (fb->pitches[0] & GENMASK(3, 0))
 		return -EINVAL;