Merge tag 'drm-misc-next-2022-08-20-1' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for v6.1:

UAPI Changes:

Cross-subsystem Changes:
- DMA-buf: documentation updates.
- Assorted small fixes to vga16fb
- Fix fbdev drivers to use the aperture helpers.
- Make removal of conflicting drivers work correctly without fbdev enabled.

Core Changes:
- bridge, scheduler, dp-mst: Assorted small fixes.
- Add more format helpers to fourcc, and use it to replace the cpp usage.
- Add DRM_FORMAT_Cxx, DRM_FORMAT_Rxx (single channel), and DRM_FORMAT_Dxx
  ("darkness", inverted single channel)
- Add packed AYUV8888 and XYUV8888 formats.
- Assorted documentation updates.
- Rename ttm_bo_init to ttm_bo_init_validate.
- Allow TTM bo's to exist without backing store.
- Convert drm selftests to kunit.
- Add managed init functions for (panel) bridge, crtc, encoder and connector.
- Fix endianness handling in various format conversion helpers.
- Make tests pass on big-endian platforms, and add test for rgb888 -> rgb565
- Move DRM_PLANE_HELPER_NO_SCALING to atomic helpers and rename, so
  drm_plane_helper is no longer needed in most drivers.
- Use idr_init_base instead of idr_init.
- Rename FB and GEM CMA helpers to DMA helpers.
- Rework XRGB8888 related conversion helpers, and add drm_fb_blit() that
  takes a iosys_map. Make drm_fb_memcpy take an iosys_map too.
- Move edid luminance calculation to core, and use it in i915.

Driver Changes:
- bridge/{adv7511,ti-sn65dsi86,parade-ps8640}, panel/{simple,nt35510,tc358767},
  nouveau, sun4i, mipi-dsi, mgag200, bochs, arm, komeda, vmwgfx, pl111:
  Assorted small fixes and doc updates.
- vc4: Rework hdmi power up, and depend on PM.
- panel/simple: Add Samsung LTL101AL01.
- ingenic: Add JZ4760(B) support, avoid a modeset when sharpness property
  is unchanged, and use the new PM ops.
- Revert some amdgpu commits that cause garbaged graphics when starting
  X, and reapply them with the real problem fixed.
- Completely rework vc4 init to use managed helpers.
- Rename via_drv to via_dri1, and move all stuff there only used by the
  dri1 implementation in preperation for atomic modeset.
- Use regmap bulk write in ssd130x.
- Power sequence and clock updates to it6505.
- Split panel-sitrox-st7701  init sequence and rework mode programming code.
- virtio: Improve error and edge conditions handling, and convert to use managed
  helpers.
- Add Samsung LTL101AL01, B120XAN01.0, R140NWF5 RH, DMT028VGHMCMI-1A T, panels.
- Add generic fbdev support to komeda.
- Split mgag200 modeset handling to make it more model-specific.
- Convert simpledrm to use atomic helpers.
- Improve udl suspend/disconnect handling.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/f0c71766-61e8-19b7-763a-5fbcdefc633d@linux.intel.com

22 files changed, 1260 insertions, 690 deletions

diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig
index 061be9a6619d..246305d17a52 100644
--- a/drivers/gpu/drm/vc4/Kconfig
+++ b/drivers/gpu/drm/vc4/Kconfig
@@ -8,10 +8,11 @@ config DRM_VC4
 	depends on DRM
 	depends on SND && SND_SOC
 	depends on COMMON_CLK
+	depends on PM
 	select DRM_DISPLAY_HDMI_HELPER
 	select DRM_DISPLAY_HELPER
 	select DRM_KMS_HELPER
-	select DRM_GEM_CMA_HELPER
+	select DRM_GEM_DMA_HELPER
 	select DRM_PANEL_BRIDGE
 	select SND_PCM
 	select SND_PCM_ELD
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 0846d56f74f2..231add8b8e12 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -8,10 +8,10 @@
  *
  * The VC4 GPU architecture (both scanout and rendering) has direct
  * access to system memory with no MMU in between.  To support it, we
- * use the GEM CMA helper functions to allocate contiguous ranges of
+ * use the GEM DMA helper functions to allocate contiguous ranges of
  * physical memory for our BOs.
  *
- * Since the CMA allocator is very slow, we keep a cache of recently
+ * Since the DMA allocator is very slow, we keep a cache of recently
  * freed BOs around so that the kernel's allocation of objects for 3D
  * rendering can return quickly.
  */
@@ -179,7 +179,7 @@ static void vc4_bo_destroy(struct vc4_bo *bo)
 		bo->validated_shader = NULL;
 	}
 
-	drm_gem_cma_free(&bo->base);
+	drm_gem_dma_free(&bo->base);
 }
 
 static void vc4_bo_remove_from_cache(struct vc4_bo *bo)
@@ -303,7 +303,7 @@ static void vc4_bo_purge(struct drm_gem_object *obj)
 
 	drm_vma_node_unmap(&obj->vma_node, dev->anon_inode->i_mapping);
 
-	dma_free_wc(dev->dev, obj->size, bo->base.vaddr, bo->base.paddr);
+	dma_free_wc(dev->dev, obj->size, bo->base.vaddr, bo->base.dma_addr);
 	bo->base.vaddr = NULL;
 	bo->madv = __VC4_MADV_PURGED;
 }
@@ -387,13 +387,14 @@ out:
  * @dev: DRM device
  * @size: Size in bytes of the memory the object will reference
  *
- * This lets the CMA helpers allocate object structs for us, and keep
+ * This lets the DMA helpers allocate object structs for us, and keep
  * our BO stats correct.
  */
 struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_bo *bo;
+	int ret;
 
 	if (WARN_ON_ONCE(vc4->is_vc5))
 		return ERR_PTR(-ENODEV);
@@ -404,7 +405,11 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size)
 
 	bo->madv = VC4_MADV_WILLNEED;
 	refcount_set(&bo->usecnt, 0);
-	mutex_init(&bo->madv_lock);
+
+	ret = drmm_mutex_init(dev, &bo->madv_lock);
+	if (ret)
+		return ERR_PTR(ret);
+
 	mutex_lock(&vc4->bo_lock);
 	bo->label = VC4_BO_TYPE_KERNEL;
 	vc4->bo_labels[VC4_BO_TYPE_KERNEL].num_allocated++;
@@ -421,7 +426,7 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size,
 {
 	size_t size = roundup(unaligned_size, PAGE_SIZE);
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
-	struct drm_gem_cma_object *cma_obj;
+	struct drm_gem_dma_object *dma_obj;
 	struct vc4_bo *bo;
 
 	if (WARN_ON_ONCE(vc4->is_vc5))
@@ -438,39 +443,39 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size,
 		return bo;
 	}
 
-	cma_obj = drm_gem_cma_create(dev, size);
-	if (IS_ERR(cma_obj)) {
+	dma_obj = drm_gem_dma_create(dev, size);
+	if (IS_ERR(dma_obj)) {
 		/*
-		 * If we've run out of CMA memory, kill the cache of
-		 * CMA allocations we've got laying around and try again.
+		 * If we've run out of DMA memory, kill the cache of
+		 * DMA allocations we've got laying around and try again.
 		 */
 		vc4_bo_cache_purge(dev);
-		cma_obj = drm_gem_cma_create(dev, size);
+		dma_obj = drm_gem_dma_create(dev, size);
 	}
 
-	if (IS_ERR(cma_obj)) {
+	if (IS_ERR(dma_obj)) {
 		/*
-		 * Still not enough CMA memory, purge the userspace BO
+		 * Still not enough DMA memory, purge the userspace BO
 		 * cache and retry.
 		 * This is sub-optimal since we purge the whole userspace
 		 * BO cache which forces user that want to re-use the BO to
 		 * restore its initial content.
 		 * Ideally, we should purge entries one by one and retry
-		 * after each to see if CMA allocation succeeds. Or even
+		 * after each to see if DMA allocation succeeds. Or even
 		 * better, try to find an entry with at least the same
 		 * size.
 		 */
 		vc4_bo_userspace_cache_purge(dev);
-		cma_obj = drm_gem_cma_create(dev, size);
+		dma_obj = drm_gem_dma_create(dev, size);
 	}
 
-	if (IS_ERR(cma_obj)) {
+	if (IS_ERR(dma_obj)) {
 		struct drm_printer p = drm_info_printer(vc4->base.dev);
-		DRM_ERROR("Failed to allocate from CMA:\n");
+		DRM_ERROR("Failed to allocate from GEM DMA helper:\n");
 		vc4_bo_stats_print(&p, vc4);
 		return ERR_PTR(-ENOMEM);
 	}
-	bo = to_vc4_bo(&cma_obj->base);
+	bo = to_vc4_bo(&dma_obj->base);
 
 	/* By default, BOs do not support the MADV ioctl. This will be enabled
 	 * only on BOs that are exposed to userspace (V3D, V3D_SHADER and DUMB
@@ -479,7 +484,7 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size,
 	bo->madv = __VC4_MADV_NOTSUPP;
 
 	mutex_lock(&vc4->bo_lock);
-	vc4_bo_set_label(&cma_obj->base, type);
+	vc4_bo_set_label(&dma_obj->base, type);
 	mutex_unlock(&vc4->bo_lock);
 
 	return bo;
@@ -564,7 +569,7 @@ static void vc4_free_object(struct drm_gem_object *gem_bo)
 		goto out;
 	}
 
-	/* If this object was partially constructed but CMA allocation
+	/* If this object was partially constructed but DMA allocation
 	 * had failed, just free it. Can also happen when the BO has been
 	 * purged.
 	 */
@@ -742,7 +747,7 @@ static int vc4_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct
 		return -EINVAL;
 	}
 
-	return drm_gem_cma_mmap(&bo->base, vma);
+	return drm_gem_dma_mmap(&bo->base, vma);
 }
 
 static const struct vm_operations_struct vc4_vm_ops = {
@@ -754,8 +759,8 @@ static const struct vm_operations_struct vc4_vm_ops = {
 static const struct drm_gem_object_funcs vc4_gem_object_funcs = {
 	.free = vc4_free_object,
 	.export = vc4_prime_export,
-	.get_sg_table = drm_gem_cma_object_get_sg_table,
-	.vmap = drm_gem_cma_object_vmap,
+	.get_sg_table = drm_gem_dma_object_get_sg_table,
+	.vmap = drm_gem_dma_object_vmap,
 	.mmap = vc4_gem_object_mmap,
 	.vm_ops = &vc4_vm_ops,
 };
@@ -984,10 +989,28 @@ int vc4_get_tiling_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
+int vc4_bo_debugfs_init(struct drm_minor *minor)
+{
+	struct drm_device *drm = minor->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
+	int ret;
+
+	if (!vc4->v3d)
+		return -ENODEV;
+
+	ret = vc4_debugfs_add_file(minor, "bo_stats",
+				   vc4_bo_stats_debugfs, NULL);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused);
 int vc4_bo_cache_init(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	int ret;
 	int i;
 
 	if (WARN_ON_ONCE(vc4->is_vc5))
@@ -1007,9 +1030,11 @@ int vc4_bo_cache_init(struct drm_device *dev)
 	for (i = 0; i < VC4_BO_TYPE_COUNT; i++)
 		vc4->bo_labels[i].name = bo_type_names[i];
 
-	mutex_init(&vc4->bo_lock);
-
-	vc4_debugfs_add_file(dev, "bo_stats", vc4_bo_stats_debugfs, NULL);
+	ret = drmm_mutex_init(dev, &vc4->bo_lock);
+	if (ret) {
+		kfree(vc4->bo_labels);
+		return ret;
+	}
 
 	INIT_LIST_HEAD(&vc4->bo_cache.time_list);
 
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 029be98660b3..2def6e2ad6f0 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -37,7 +37,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_atomic_uapi.h>
-#include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_fb_dma_helper.h>
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_print.h>
 #include <drm/drm_probe_helper.h>
@@ -206,11 +206,6 @@ static bool vc4_crtc_get_scanout_position(struct drm_crtc *crtc,
 	return ret;
 }
 
-void vc4_crtc_destroy(struct drm_crtc *crtc)
-{
-	drm_crtc_cleanup(crtc);
-}
-
 static u32 vc4_get_fifo_full_level(struct vc4_crtc *vc4_crtc, u32 format)
 {
 	const struct vc4_crtc_data *crtc_data = vc4_crtc_to_vc4_crtc_data(vc4_crtc);
@@ -544,6 +539,20 @@ int vc4_crtc_disable_at_boot(struct drm_crtc *crtc)
 	return 0;
 }
 
+void vc4_crtc_send_vblank(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	unsigned long flags;
+
+	if (!crtc->state || !crtc->state->event)
+		return;
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+	drm_crtc_send_vblank_event(crtc, crtc->state->event);
+	crtc->state->event = NULL;
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
 static void vc4_crtc_atomic_disable(struct drm_crtc *crtc,
 				    struct drm_atomic_state *state)
 {
@@ -567,14 +576,7 @@ static void vc4_crtc_atomic_disable(struct drm_crtc *crtc,
 	 * Make sure we issue a vblank event after disabling the CRTC if
 	 * someone was waiting it.
 	 */
-	if (crtc->state->event) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&dev->event_lock, flags);
-		drm_crtc_send_vblank_event(crtc, crtc->state->event);
-		crtc->state->event = NULL;
-		spin_unlock_irqrestore(&dev->event_lock, flags);
-	}
+	vc4_crtc_send_vblank(crtc);
 }
 
 static void vc4_crtc_atomic_enable(struct drm_crtc *crtc,
@@ -821,9 +823,9 @@ static void vc4_async_page_flip_seqno_complete(struct vc4_seqno_cb *cb)
 	struct vc4_bo *bo = NULL;
 
 	if (flip_state->old_fb) {
-		struct drm_gem_cma_object *cma_bo =
-			drm_fb_cma_get_gem_obj(flip_state->old_fb, 0);
-		bo = to_vc4_bo(&cma_bo->base);
+		struct drm_gem_dma_object *dma_bo =
+			drm_fb_dma_get_gem_obj(flip_state->old_fb, 0);
+		bo = to_vc4_bo(&dma_bo->base);
 	}
 
 	vc4_async_page_flip_complete(flip_state);
@@ -855,19 +857,19 @@ static int vc4_async_set_fence_cb(struct drm_device *dev,
 				  struct vc4_async_flip_state *flip_state)
 {
 	struct drm_framebuffer *fb = flip_state->fb;
-	struct drm_gem_cma_object *cma_bo = drm_fb_cma_get_gem_obj(fb, 0);
+	struct drm_gem_dma_object *dma_bo = drm_fb_dma_get_gem_obj(fb, 0);
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct dma_fence *fence;
 	int ret;
 
 	if (!vc4->is_vc5) {
-		struct vc4_bo *bo = to_vc4_bo(&cma_bo->base);
+		struct vc4_bo *bo = to_vc4_bo(&dma_bo->base);
 
 		return vc4_queue_seqno_cb(dev, &flip_state->cb.seqno, bo->seqno,
 					  vc4_async_page_flip_seqno_complete);
 	}
 
-	ret = dma_resv_get_singleton(cma_bo->base.resv, DMA_RESV_USAGE_READ, &fence);
+	ret = dma_resv_get_singleton(dma_bo->base.resv, DMA_RESV_USAGE_READ, &fence);
 	if (ret)
 		return ret;
 
@@ -943,8 +945,8 @@ static int vc4_async_page_flip(struct drm_crtc *crtc,
 {
 	struct drm_device *dev = crtc->dev;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
-	struct drm_gem_cma_object *cma_bo = drm_fb_cma_get_gem_obj(fb, 0);
-	struct vc4_bo *bo = to_vc4_bo(&cma_bo->base);
+	struct drm_gem_dma_object *dma_bo = drm_fb_dma_get_gem_obj(fb, 0);
+	struct vc4_bo *bo = to_vc4_bo(&dma_bo->base);
 	int ret;
 
 	if (WARN_ON_ONCE(vc4->is_vc5))
@@ -1050,9 +1052,23 @@ void vc4_crtc_reset(struct drm_crtc *crtc)
 	__drm_atomic_helper_crtc_reset(crtc, &vc4_crtc_state->base);
 }
 
+int vc4_crtc_late_register(struct drm_crtc *crtc)
+{
+	struct drm_device *drm = crtc->dev;
+	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
+	const struct vc4_crtc_data *crtc_data = vc4_crtc_to_vc4_crtc_data(vc4_crtc);
+	int ret;
+
+	ret = vc4_debugfs_add_regset32(drm->primary, crtc_data->debugfs_name,
+				       &vc4_crtc->regset);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 static const struct drm_crtc_funcs vc4_crtc_funcs = {
 	.set_config = drm_atomic_helper_set_config,
-	.destroy = vc4_crtc_destroy,
 	.page_flip = vc4_page_flip,
 	.set_property = NULL,
 	.cursor_set = NULL, /* handled by drm_mode_cursor_universal */
@@ -1063,6 +1079,7 @@ static const struct drm_crtc_funcs vc4_crtc_funcs = {
 	.enable_vblank = vc4_enable_vblank,
 	.disable_vblank = vc4_disable_vblank,
 	.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
+	.late_register = vc4_crtc_late_register,
 };
 
 static const struct drm_crtc_helper_funcs vc4_crtc_helper_funcs = {
@@ -1077,10 +1094,10 @@ static const struct drm_crtc_helper_funcs vc4_crtc_helper_funcs = {
 
 static const struct vc4_pv_data bcm2835_pv0_data = {
 	.base = {
+		.debugfs_name = "crtc0_regs",
 		.hvs_available_channels = BIT(0),
 		.hvs_output = 0,
 	},
-	.debugfs_name = "crtc0_regs",
 	.fifo_depth = 64,
 	.pixels_per_clock = 1,
 	.encoder_types = {
@@ -1091,10 +1108,10 @@ static const struct vc4_pv_data bcm2835_pv0_data = {
 
 static const struct vc4_pv_data bcm2835_pv1_data = {
 	.base = {
+		.debugfs_name = "crtc1_regs",
 		.hvs_available_channels = BIT(2),
 		.hvs_output = 2,
 	},
-	.debugfs_name = "crtc1_regs",
 	.fifo_depth = 64,
 	.pixels_per_clock = 1,
 	.encoder_types = {
@@ -1105,10 +1122,10 @@ static const struct vc4_pv_data bcm2835_pv1_data = {
 
 static const struct vc4_pv_data bcm2835_pv2_data = {
 	.base = {
+		.debugfs_name = "crtc2_regs",
 		.hvs_available_channels = BIT(1),
 		.hvs_output = 1,
 	},
-	.debugfs_name = "crtc2_regs",
 	.fifo_depth = 64,
 	.pixels_per_clock = 1,
 	.encoder_types = {
@@ -1119,10 +1136,10 @@ static const struct vc4_pv_data bcm2835_pv2_data = {
 
 static const struct vc4_pv_data bcm2711_pv0_data = {
 	.base = {
+		.debugfs_name = "crtc0_regs",
 		.hvs_available_channels = BIT(0),
 		.hvs_output = 0,
 	},
-	.debugfs_name = "crtc0_regs",
 	.fifo_depth = 64,
 	.pixels_per_clock = 1,
 	.encoder_types = {
@@ -1133,10 +1150,10 @@ static const struct vc4_pv_data bcm2711_pv0_data = {
 
 static const struct vc4_pv_data bcm2711_pv1_data = {
 	.base = {
+		.debugfs_name = "crtc1_regs",
 		.hvs_available_channels = BIT(0) | BIT(1) | BIT(2),
 		.hvs_output = 3,
 	},
-	.debugfs_name = "crtc1_regs",
 	.fifo_depth = 64,
 	.pixels_per_clock = 1,
 	.encoder_types = {
@@ -1147,10 +1164,10 @@ static const struct vc4_pv_data bcm2711_pv1_data = {
 
 static const struct vc4_pv_data bcm2711_pv2_data = {
 	.base = {
+		.debugfs_name = "crtc2_regs",
 		.hvs_available_channels = BIT(0) | BIT(1) | BIT(2),
 		.hvs_output = 4,
 	},
-	.debugfs_name = "crtc2_regs",
 	.fifo_depth = 256,
 	.pixels_per_clock = 2,
 	.encoder_types = {
@@ -1160,10 +1177,10 @@ static const struct vc4_pv_data bcm2711_pv2_data = {
 
 static const struct vc4_pv_data bcm2711_pv3_data = {
 	.base = {
+		.debugfs_name = "crtc3_regs",
 		.hvs_available_channels = BIT(1),
 		.hvs_output = 1,
 	},
-	.debugfs_name = "crtc3_regs",
 	.fifo_depth = 64,
 	.pixels_per_clock = 1,
 	.encoder_types = {
@@ -1173,10 +1190,10 @@ static const struct vc4_pv_data bcm2711_pv3_data = {
 
 static const struct vc4_pv_data bcm2711_pv4_data = {
 	.base = {
+		.debugfs_name = "crtc4_regs",
 		.hvs_available_channels = BIT(0) | BIT(1) | BIT(2),
 		.hvs_output = 5,
 	},
-	.debugfs_name = "crtc4_regs",
 	.fifo_depth = 64,
 	.pixels_per_clock = 2,
 	.encoder_types = {
@@ -1230,6 +1247,7 @@ int vc4_crtc_init(struct drm_device *drm, struct vc4_crtc *vc4_crtc,
 	struct drm_crtc *crtc = &vc4_crtc->base;
 	struct drm_plane *primary_plane;
 	unsigned int i;
+	int ret;
 
 	/* For now, we create just the primary and the legacy cursor
 	 * planes.  We should be able to stack more planes on easily,
@@ -1237,15 +1255,18 @@ int vc4_crtc_init(struct drm_device *drm, struct vc4_crtc *vc4_crtc,
 	 * requirement of the plane configuration, and reject ones
 	 * that will take too much.
 	 */
-	primary_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_PRIMARY);
+	primary_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_PRIMARY, 0);
 	if (IS_ERR(primary_plane)) {
 		dev_err(drm->dev, "failed to construct primary plane\n");
 		return PTR_ERR(primary_plane);
 	}
 
 	spin_lock_init(&vc4_crtc->irq_lock);
-	drm_crtc_init_with_planes(drm, crtc, primary_plane, NULL,
-				  crtc_funcs, NULL);
+	ret = drmm_crtc_init_with_planes(drm, crtc, primary_plane, NULL,
+					 crtc_funcs, NULL);
+	if (ret)
+		return ret;
+
 	drm_crtc_helper_add(crtc, crtc_helper_funcs);
 
 	if (!vc4->is_vc5) {
@@ -1275,10 +1296,9 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 	const struct vc4_pv_data *pv_data;
 	struct vc4_crtc *vc4_crtc;
 	struct drm_crtc *crtc;
-	struct drm_plane *destroy_plane, *temp;
 	int ret;
 
-	vc4_crtc = devm_kzalloc(dev, sizeof(*vc4_crtc), GFP_KERNEL);
+	vc4_crtc = drmm_kzalloc(drm, sizeof(*vc4_crtc), GFP_KERNEL);
 	if (!vc4_crtc)
 		return -ENOMEM;
 	crtc = &vc4_crtc->base;
@@ -1310,23 +1330,11 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 			       IRQF_SHARED,
 			       "vc4 crtc", vc4_crtc);
 	if (ret)
-		goto err_destroy_planes;
+		return ret;
 
 	platform_set_drvdata(pdev, vc4_crtc);
 
-	vc4_debugfs_add_regset32(drm, pv_data->debugfs_name,
-				 &vc4_crtc->regset);
-
 	return 0;
-
-err_destroy_planes:
-	list_for_each_entry_safe(destroy_plane, temp,
-				 &drm->mode_config.plane_list, head) {
-		if (destroy_plane->possible_crtcs == drm_crtc_mask(crtc))
-		    destroy_plane->funcs->destroy(destroy_plane);
-	}
-
-	return ret;
 }
 
 static void vc4_crtc_unbind(struct device *dev, struct device *master,
@@ -1335,8 +1343,6 @@ static void vc4_crtc_unbind(struct device *dev, struct device *master,
 	struct platform_device *pdev = to_platform_device(dev);
 	struct vc4_crtc *vc4_crtc = dev_get_drvdata(dev);
 
-	vc4_crtc_destroy(&vc4_crtc->base);
-
 	CRTC_WRITE(PV_INTEN, 0);
 
 	platform_set_drvdata(pdev, NULL);
diff --git a/drivers/gpu/drm/vc4/vc4_debugfs.c b/drivers/gpu/drm/vc4/vc4_debugfs.c
index ba2d8ea562af..19cda4f91a82 100644
--- a/drivers/gpu/drm/vc4/vc4_debugfs.c
+++ b/drivers/gpu/drm/vc4/vc4_debugfs.c
@@ -3,6 +3,8 @@
  *  Copyright © 2014 Broadcom
  */
 
+#include <drm/drm_drv.h>
+
 #include <linux/seq_file.h>
 #include <linux/circ_buf.h>
 #include <linux/ctype.h>
@@ -12,11 +14,6 @@
 #include "vc4_drv.h"
 #include "vc4_regs.h"
 
-struct vc4_debugfs_info_entry {
-	struct list_head link;
-	struct drm_info_list info;
-};
-
 /*
  * Called at drm_dev_register() time on each of the minors registered
  * by the DRM device, to attach the debugfs files.
@@ -25,62 +22,59 @@ void
 vc4_debugfs_init(struct drm_minor *minor)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(minor->dev);
-	struct vc4_debugfs_info_entry *entry;
+	struct drm_device *drm = &vc4->base;
 
-	if (!of_device_is_compatible(vc4->hvs->pdev->dev.of_node,
-				     "brcm,bcm2711-vc5"))
-		debugfs_create_bool("hvs_load_tracker", S_IRUGO | S_IWUSR,
-				    minor->debugfs_root, &vc4->load_tracker_enabled);
+	drm_WARN_ON(drm, vc4_hvs_debugfs_init(minor));
 
-	list_for_each_entry(entry, &vc4->debugfs_list, link) {
-		drm_debugfs_create_files(&entry->info, 1,
-					 minor->debugfs_root, minor);
+	if (vc4->v3d) {
+		drm_WARN_ON(drm, vc4_bo_debugfs_init(minor));
+		drm_WARN_ON(drm, vc4_v3d_debugfs_init(minor));
 	}
 }
 
 static int vc4_debugfs_regset32(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
+	struct drm_device *drm = node->minor->dev;
 	struct debugfs_regset32 *regset = node->info_ent->data;
 	struct drm_printer p = drm_seq_file_printer(m);
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return -ENODEV;
 
 	drm_print_regset32(&p, regset);
 
+	drm_dev_exit(idx);
+
 	return 0;
 }
 
-/*
- * Registers a debugfs file with a callback function for a vc4 component.
- *
- * This is like drm_debugfs_create_files(), but that can only be
- * called a given DRM minor, while the various VC4 components want to
- * register their debugfs files during the component bind process.  We
- * track the request and delay it to be called on each minor during
- * vc4_debugfs_init().
- */
-void vc4_debugfs_add_file(struct drm_device *dev,
-			  const char *name,
-			  int (*show)(struct seq_file*, void*),
-			  void *data)
+int vc4_debugfs_add_file(struct drm_minor *minor,
+			 const char *name,
+			 int (*show)(struct seq_file*, void*),
+			 void *data)
 {
-	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct drm_device *dev = minor->dev;
+	struct dentry *root = minor->debugfs_root;
+	struct drm_info_list *file;
 
-	struct vc4_debugfs_info_entry *entry =
-		devm_kzalloc(dev->dev, sizeof(*entry), GFP_KERNEL);
+	file = drmm_kzalloc(dev, sizeof(*file), GFP_KERNEL);
+	if (!file)
+		return -ENOMEM;
 
-	if (!entry)
-		return;
+	file->name = name;
+	file->show = show;
+	file->data = data;
 
-	entry->info.name = name;
-	entry->info.show = show;
-	entry->info.data = data;
+	drm_debugfs_create_files(file, 1, root, minor);
 
-	list_add(&entry->link, &vc4->debugfs_list);
+	return 0;
 }
 
-void vc4_debugfs_add_regset32(struct drm_device *drm,
-			      const char *name,
-			      struct debugfs_regset32 *regset)
+int vc4_debugfs_add_regset32(struct drm_minor *minor,
+			     const char *name,
+			     struct debugfs_regset32 *regset)
 {
-	vc4_debugfs_add_file(drm, name, vc4_debugfs_regset32, regset);
+	return vc4_debugfs_add_file(minor, name, vc4_debugfs_regset32, regset);
 }
diff --git a/drivers/gpu/drm/vc4/vc4_dpi.c b/drivers/gpu/drm/vc4/vc4_dpi.c
index ef5e3921062c..1f8f44b7b5a5 100644
--- a/drivers/gpu/drm/vc4/vc4_dpi.c
+++ b/drivers/gpu/drm/vc4/vc4_dpi.c
@@ -13,6 +13,7 @@
 
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_bridge.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_of.h>
 #include <drm/drm_panel.h>
@@ -84,9 +85,9 @@
 
 /* General DPI hardware state. */
 struct vc4_dpi {
-	struct platform_device *pdev;
+	struct vc4_encoder encoder;
 
-	struct drm_encoder *encoder;
+	struct platform_device *pdev;
 
 	void __iomem *regs;
 
@@ -96,21 +97,15 @@ struct vc4_dpi {
 	struct debugfs_regset32 regset;
 };
 
-#define DPI_READ(offset) readl(dpi->regs + (offset))
-#define DPI_WRITE(offset, val) writel(val, dpi->regs + (offset))
-
-/* VC4 DPI encoder KMS struct */
-struct vc4_dpi_encoder {
-	struct vc4_encoder base;
-	struct vc4_dpi *dpi;
-};
-
-static inline struct vc4_dpi_encoder *
-to_vc4_dpi_encoder(struct drm_encoder *encoder)
+static inline struct vc4_dpi *
+to_vc4_dpi(struct drm_encoder *encoder)
 {
-	return container_of(encoder, struct vc4_dpi_encoder, base.base);
+	return container_of(encoder, struct vc4_dpi, encoder.base);
 }
 
+#define DPI_READ(offset) readl(dpi->regs + (offset))
+#define DPI_WRITE(offset, val) writel(val, dpi->regs + (offset))
+
 static const struct debugfs_reg32 dpi_regs[] = {
 	VC4_REG32(DPI_C),
 	VC4_REG32(DPI_ID),
@@ -118,21 +113,27 @@ static const struct debugfs_reg32 dpi_regs[] = {
 
 static void vc4_dpi_encoder_disable(struct drm_encoder *encoder)
 {
-	struct vc4_dpi_encoder *vc4_encoder = to_vc4_dpi_encoder(encoder);
-	struct vc4_dpi *dpi = vc4_encoder->dpi;
+	struct drm_device *dev = encoder->dev;
+	struct vc4_dpi *dpi = to_vc4_dpi(encoder);
+	int idx;
+
+	if (!drm_dev_enter(dev, &idx))
+		return;
 
 	clk_disable_unprepare(dpi->pixel_clock);
+
+	drm_dev_exit(idx);
 }
 
 static void vc4_dpi_encoder_enable(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
 	struct drm_display_mode *mode = &encoder->crtc->mode;
-	struct vc4_dpi_encoder *vc4_encoder = to_vc4_dpi_encoder(encoder);
-	struct vc4_dpi *dpi = vc4_encoder->dpi;
+	struct vc4_dpi *dpi = to_vc4_dpi(encoder);
 	struct drm_connector_list_iter conn_iter;
 	struct drm_connector *connector = NULL, *connector_scan;
 	u32 dpi_c = DPI_ENABLE;
+	int idx;
 	int ret;
 
 	/* Look up the connector attached to DPI so we can get the
@@ -212,6 +213,9 @@ static void vc4_dpi_encoder_enable(struct drm_encoder *encoder)
 			dpi_c |= DPI_VSYNC_DISABLE;
 	}
 
+	if (!drm_dev_enter(dev, &idx))
+		return;
+
 	DPI_WRITE(DPI_C, dpi_c);
 
 	ret = clk_set_rate(dpi->pixel_clock, mode->clock * 1000);
@@ -221,6 +225,8 @@ static void vc4_dpi_encoder_enable(struct drm_encoder *encoder)
 	ret = clk_prepare_enable(dpi->pixel_clock);
 	if (ret)
 		DRM_ERROR("Failed to set clock rate: %d\n", ret);
+
+	drm_dev_exit(idx);
 }
 
 static enum drm_mode_status vc4_dpi_encoder_mode_valid(struct drm_encoder *encoder,
@@ -238,6 +244,23 @@ static const struct drm_encoder_helper_funcs vc4_dpi_encoder_helper_funcs = {
 	.mode_valid = vc4_dpi_encoder_mode_valid,
 };
 
+static int vc4_dpi_late_register(struct drm_encoder *encoder)
+{
+	struct drm_device *drm = encoder->dev;
+	struct vc4_dpi *dpi = to_vc4_dpi(encoder);
+	int ret;
+
+	ret = vc4_debugfs_add_regset32(drm->primary, "dpi_regs", &dpi->regset);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct drm_encoder_funcs vc4_dpi_encoder_funcs = {
+	.late_register = vc4_dpi_late_register,
+};
+
 static const struct of_device_id vc4_dpi_dt_match[] = {
 	{ .compatible = "brcm,bcm2835-dpi", .data = NULL },
 	{}
@@ -248,10 +271,11 @@ static const struct of_device_id vc4_dpi_dt_match[] = {
  */
 static int vc4_dpi_init_bridge(struct vc4_dpi *dpi)
 {
+	struct drm_device *drm = dpi->encoder.base.dev;
 	struct device *dev = &dpi->pdev->dev;
 	struct drm_bridge *bridge;
 
-	bridge = devm_drm_of_get_bridge(dev, dev->of_node, 0, 0);
+	bridge = drmm_of_get_bridge(drm, dev->of_node, 0, 0);
 	if (IS_ERR(bridge)) {
 		/* If nothing was connected in the DT, that's not an
 		 * error.
@@ -262,30 +286,28 @@ static int vc4_dpi_init_bridge(struct vc4_dpi *dpi)
 			return PTR_ERR(bridge);
 	}
 
-	return drm_bridge_attach(dpi->encoder, bridge, NULL, 0);
+	return drm_bridge_attach(&dpi->encoder.base, bridge, NULL, 0);
+}
+
+static void vc4_dpi_disable_clock(void *ptr)
+{
+	struct vc4_dpi *dpi = ptr;
+
+	clk_disable_unprepare(dpi->core_clock);
 }
 
 static int vc4_dpi_bind(struct device *dev, struct device *master, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct drm_device *drm = dev_get_drvdata(master);
-	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_dpi *dpi;
-	struct vc4_dpi_encoder *vc4_dpi_encoder;
 	int ret;
 
-	dpi = devm_kzalloc(dev, sizeof(*dpi), GFP_KERNEL);
+	dpi = drmm_kzalloc(drm, sizeof(*dpi), GFP_KERNEL);
 	if (!dpi)
 		return -ENOMEM;
 
-	vc4_dpi_encoder = devm_kzalloc(dev, sizeof(*vc4_dpi_encoder),
-				       GFP_KERNEL);
-	if (!vc4_dpi_encoder)
-		return -ENOMEM;
-	vc4_dpi_encoder->base.type = VC4_ENCODER_TYPE_DPI;
-	vc4_dpi_encoder->dpi = dpi;
-	dpi->encoder = &vc4_dpi_encoder->base.base;
-
+	dpi->encoder.type = VC4_ENCODER_TYPE_DPI;
 	dpi->pdev = pdev;
 	dpi->regs = vc4_ioremap_regs(pdev, 0);
 	if (IS_ERR(dpi->regs))
@@ -307,6 +329,7 @@ static int vc4_dpi_bind(struct device *dev, struct device *master, void *data)
 			DRM_ERROR("Failed to get core clock: %d\n", ret);
 		return ret;
 	}
+
 	dpi->pixel_clock = devm_clk_get(dev, "pixel");
 	if (IS_ERR(dpi->pixel_clock)) {
 		ret = PTR_ERR(dpi->pixel_clock);
@@ -316,49 +339,35 @@ static int vc4_dpi_bind(struct device *dev, struct device *master, void *data)
 	}
 
 	ret = clk_prepare_enable(dpi->core_clock);
-	if (ret)
+	if (ret) {
 		DRM_ERROR("Failed to turn on core clock: %d\n", ret);
+		return ret;
+	}
 
-	drm_simple_encoder_init(drm, dpi->encoder, DRM_MODE_ENCODER_DPI);
-	drm_encoder_helper_add(dpi->encoder, &vc4_dpi_encoder_helper_funcs);
+	ret = devm_add_action_or_reset(dev, vc4_dpi_disable_clock, dpi);
+	if (ret)
+		return ret;
 
-	ret = vc4_dpi_init_bridge(dpi);
+	ret = drmm_encoder_init(drm, &dpi->encoder.base,
+				&vc4_dpi_encoder_funcs,
+				DRM_MODE_ENCODER_DPI,
+				NULL);
 	if (ret)
-		goto err_destroy_encoder;
+		return ret;
 
-	dev_set_drvdata(dev, dpi);
+	drm_encoder_helper_add(&dpi->encoder.base, &vc4_dpi_encoder_helper_funcs);
 
-	vc4->dpi = dpi;
+	ret = vc4_dpi_init_bridge(dpi);
+	if (ret)
+		return ret;
 
-	vc4_debugfs_add_regset32(drm, "dpi_regs", &dpi->regset);
+	dev_set_drvdata(dev, dpi);
 
 	return 0;
-
-err_destroy_encoder:
-	drm_encoder_cleanup(dpi->encoder);
-	clk_disable_unprepare(dpi->core_clock);
-	return ret;
-}
-
-static void vc4_dpi_unbind(struct device *dev, struct device *master,
-			   void *data)
-{
-	struct drm_device *drm = dev_get_drvdata(master);
-	struct vc4_dev *vc4 = to_vc4_dev(drm);
-	struct vc4_dpi *dpi = dev_get_drvdata(dev);
-
-	drm_of_panel_bridge_remove(dev->of_node, 0, 0);
-
-	drm_encoder_cleanup(dpi->encoder);
-
-	clk_disable_unprepare(dpi->core_clock);
-
-	vc4->dpi = NULL;
 }
 
 static const struct component_ops vc4_dpi_ops = {
 	.bind   = vc4_dpi_bind,
-	.unbind = vc4_dpi_unbind,
 };
 
 static int vc4_dpi_dev_probe(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 292d1b6a01b6..ffbbb454c9e8 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -33,7 +33,6 @@
 #include <drm/drm_aperture.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_drv.h>
-#include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_vblank.h>
 
@@ -86,7 +85,7 @@ static int vc5_dumb_create(struct drm_file *file_priv,
 	if (ret)
 		return ret;
 
-	return drm_gem_cma_dumb_create_internal(file_priv, dev, args);
+	return drm_gem_dma_dumb_create_internal(file_priv, dev, args);
 }
 
 static int vc4_get_param_ioctl(struct drm_device *dev, void *data,
@@ -212,7 +211,7 @@ static const struct drm_driver vc4_drm_driver = {
 
 	.gem_create_object = vc4_create_object,
 
-	DRM_GEM_CMA_DRIVER_OPS_WITH_DUMB_CREATE(vc4_bo_dumb_create),
+	DRM_GEM_DMA_DRIVER_OPS_WITH_DUMB_CREATE(vc4_bo_dumb_create),
 
 	.ioctls = vc4_drm_ioctls,
 	.num_ioctls = ARRAY_SIZE(vc4_drm_ioctls),
@@ -235,7 +234,7 @@ static const struct drm_driver vc5_drm_driver = {
 	.debugfs_init = vc4_debugfs_init,
 #endif
 
-	DRM_GEM_CMA_DRIVER_OPS_WITH_DUMB_CREATE(vc5_dumb_create),
+	DRM_GEM_DMA_DRIVER_OPS_WITH_DUMB_CREATE(vc5_dumb_create),
 
 	.fops = &vc4_drm_fops,
 
@@ -267,6 +266,13 @@ static void vc4_match_add_drivers(struct device *dev,
 	}
 }
 
+static void vc4_component_unbind_all(void *ptr)
+{
+	struct vc4_dev *vc4 = ptr;
+
+	component_unbind_all(vc4->dev, &vc4->base);
+}
+
 static const struct of_device_id vc4_dma_range_matches[] = {
 	{ .compatible = "brcm,bcm2711-hvs" },
 	{ .compatible = "brcm,bcm2835-hvs" },
@@ -310,13 +316,16 @@ static int vc4_drm_bind(struct device *dev)
 	if (IS_ERR(vc4))
 		return PTR_ERR(vc4);
 	vc4->is_vc5 = is_vc5;
+	vc4->dev = dev;
 
 	drm = &vc4->base;
 	platform_set_drvdata(pdev, drm);
 	INIT_LIST_HEAD(&vc4->debugfs_list);
 
 	if (!is_vc5) {
-		mutex_init(&vc4->bin_bo_lock);
+		ret = drmm_mutex_init(drm, &vc4->bin_bo_lock);
+		if (ret)
+			return ret;
 
 		ret = vc4_bo_cache_init(drm);
 		if (ret)
@@ -360,6 +369,10 @@ static int vc4_drm_bind(struct device *dev)
 	if (ret)
 		return ret;
 
+	ret = devm_add_action_or_reset(dev, vc4_component_unbind_all, vc4);
+	if (ret)
+		return ret;
+
 	ret = vc4_plane_create_additional_planes(drm);
 	if (ret)
 		goto unbind_all;
@@ -380,8 +393,6 @@ static int vc4_drm_bind(struct device *dev)
 	return 0;
 
 unbind_all:
-	component_unbind_all(dev, drm);
-
 	return ret;
 }
 
@@ -389,8 +400,7 @@ static void vc4_drm_unbind(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
 
-	drm_dev_unregister(drm);
-
+	drm_dev_unplug(drm);
 	drm_atomic_helper_shutdown(drm);
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 1beb96b77b8c..418a8242691f 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -14,7 +14,7 @@
 #include <drm/drm_debugfs.h>
 #include <drm/drm_device.h>
 #include <drm/drm_encoder.h>
-#include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_gem_dma_helper.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_mm.h>
 #include <drm/drm_modeset_lock.h>
@@ -76,6 +76,7 @@ struct vc4_perfmon {
 
 struct vc4_dev {
 	struct drm_device base;
+	struct device *dev;
 
 	bool is_vc5;
 
@@ -83,9 +84,6 @@ struct vc4_dev {
 
 	struct vc4_hvs *hvs;
 	struct vc4_v3d *v3d;
-	struct vc4_dpi *dpi;
-	struct vc4_vec *vec;
-	struct vc4_txp *txp;
 
 	struct vc4_hang_state *hang_state;
 
@@ -241,7 +239,7 @@ to_vc4_dev(struct drm_device *dev)
 }
 
 struct vc4_bo {
-	struct drm_gem_cma_object base;
+	struct drm_gem_dma_object base;
 
 	/* seqno of the last job to render using this BO. */
 	uint64_t seqno;
@@ -290,7 +288,7 @@ struct vc4_bo {
 static inline struct vc4_bo *
 to_vc4_bo(struct drm_gem_object *bo)
 {
-	return container_of(to_drm_gem_cma_obj(bo), struct vc4_bo, base);
+	return container_of(to_drm_gem_dma_obj(bo), struct vc4_bo, base);
 }
 
 struct vc4_fence {
@@ -458,6 +456,8 @@ to_vc4_encoder(struct drm_encoder *encoder)
 }
 
 struct vc4_crtc_data {
+	const char *debugfs_name;
+
 	/* Bitmask of channels (FIFOs) of the HVS that the output can source from */
 	unsigned int hvs_available_channels;
 
@@ -475,8 +475,6 @@ struct vc4_pv_data {
 	u8 pixels_per_clock;
 
 	enum vc4_encoder_type encoder_types[4];
-	const char *debugfs_name;
-
 };
 
 struct vc4_crtc {
@@ -604,14 +602,14 @@ struct vc4_exec_info {
 	/* This is the array of BOs that were looked up at the start of exec.
 	 * Command validation will use indices into this array.
 	 */
-	struct drm_gem_cma_object **bo;
+	struct drm_gem_dma_object **bo;
 	uint32_t bo_count;
 
 	/* List of BOs that are being written by the RCL.  Other than
 	 * the binner temporary storage, this is all the BOs written
 	 * by the job.
 	 */
-	struct drm_gem_cma_object *rcl_write_bo[4];
+	struct drm_gem_dma_object *rcl_write_bo[4];
 	uint32_t rcl_write_bo_count;
 
 	/* Pointers for our position in vc4->job_list */
@@ -630,7 +628,7 @@ struct vc4_exec_info {
 	/* This is the BO where we store the validated command lists, shader
 	 * records, and uniforms.
 	 */
-	struct drm_gem_cma_object *exec_bo;
+	struct drm_gem_dma_object *exec_bo;
 
 	/**
 	 * This tracks the per-shader-record state (packet 64) that
@@ -843,6 +841,7 @@ int vc4_bo_inc_usecnt(struct vc4_bo *bo);
 void vc4_bo_dec_usecnt(struct vc4_bo *bo);
 void vc4_bo_add_to_purgeable_pool(struct vc4_bo *bo);
 void vc4_bo_remove_from_purgeable_pool(struct vc4_bo *bo);
+int vc4_bo_debugfs_init(struct drm_minor *minor);
 
 /* vc4_crtc.c */
 extern struct platform_driver vc4_crtc_driver;
@@ -850,7 +849,6 @@ int vc4_crtc_disable_at_boot(struct drm_crtc *crtc);
 int vc4_crtc_init(struct drm_device *drm, struct vc4_crtc *vc4_crtc,
 		  const struct drm_crtc_funcs *crtc_funcs,
 		  const struct drm_crtc_helper_funcs *crtc_helper_funcs);
-void vc4_crtc_destroy(struct drm_crtc *crtc);
 int vc4_page_flip(struct drm_crtc *crtc,
 		  struct drm_framebuffer *fb,
 		  struct drm_pending_vblank_event *event,
@@ -861,6 +859,8 @@ void vc4_crtc_destroy_state(struct drm_crtc *crtc,
 			    struct drm_crtc_state *state);
 void vc4_crtc_reset(struct drm_crtc *crtc);
 void vc4_crtc_handle_vblank(struct vc4_crtc *crtc);
+void vc4_crtc_send_vblank(struct drm_crtc *crtc);
+int vc4_crtc_late_register(struct drm_crtc *crtc);
 void vc4_crtc_get_margins(struct drm_crtc_state *state,
 			  unsigned int *left, unsigned int *right,
 			  unsigned int *top, unsigned int *bottom);
@@ -868,25 +868,27 @@ void vc4_crtc_get_margins(struct drm_crtc_state *state,
 /* vc4_debugfs.c */
 void vc4_debugfs_init(struct drm_minor *minor);
 #ifdef CONFIG_DEBUG_FS
-void vc4_debugfs_add_file(struct drm_device *drm,
-			  const char *filename,
-			  int (*show)(struct seq_file*, void*),
-			  void *data);
-void vc4_debugfs_add_regset32(struct drm_device *drm,
-			      const char *filename,
-			      struct debugfs_regset32 *regset);
+int vc4_debugfs_add_file(struct drm_minor *minor,
+			 const char *filename,
+			 int (*show)(struct seq_file*, void*),
+			 void *data);
+int vc4_debugfs_add_regset32(struct drm_minor *minor,
+			     const char *filename,
+			     struct debugfs_regset32 *regset);
 #else
-static inline void vc4_debugfs_add_file(struct drm_device *drm,
-					const char *filename,
-					int (*show)(struct seq_file*, void*),
-					void *data)
+static inline int vc4_debugfs_add_file(struct drm_minor *minor,
+				       const char *filename,
+				       int (*show)(struct seq_file*, void*),
+				       void *data)
 {
+	return 0;
 }
 
-static inline void vc4_debugfs_add_regset32(struct drm_device *drm,
-					    const char *filename,
-					    struct debugfs_regset32 *regset)
+static inline int vc4_debugfs_add_regset32(struct drm_minor *minor,
+					   const char *filename,
+					   struct debugfs_regset32 *regset)
 {
+	return 0;
 }
 #endif
 
@@ -952,13 +954,15 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc, struct drm_atomic_state *state)
 void vc4_hvs_dump_state(struct vc4_hvs *hvs);
 void vc4_hvs_unmask_underrun(struct vc4_hvs *hvs, int channel);
 void vc4_hvs_mask_underrun(struct vc4_hvs *hvs, int channel);
+int vc4_hvs_debugfs_init(struct drm_minor *minor);
 
 /* vc4_kms.c */
 int vc4_kms_load(struct drm_device *dev);
 
 /* vc4_plane.c */
 struct drm_plane *vc4_plane_init(struct drm_device *dev,
-				 enum drm_plane_type type);
+				 enum drm_plane_type type,
+				 uint32_t possible_crtcs);
 int vc4_plane_create_additional_planes(struct drm_device *dev);
 u32 vc4_plane_write_dlist(struct drm_plane *plane, u32 __iomem *dlist);
 u32 vc4_plane_dlist_size(const struct drm_plane_state *state);
@@ -973,6 +977,7 @@ int vc4_v3d_bin_bo_get(struct vc4_dev *vc4, bool *used);
 void vc4_v3d_bin_bo_put(struct vc4_dev *vc4);
 int vc4_v3d_pm_get(struct vc4_dev *vc4);
 void vc4_v3d_pm_put(struct vc4_dev *vc4);
+int vc4_v3d_debugfs_init(struct drm_minor *minor);
 
 /* vc4_validate.c */
 int
@@ -984,19 +989,19 @@ vc4_validate_bin_cl(struct drm_device *dev,
 int
 vc4_validate_shader_recs(struct drm_device *dev, struct vc4_exec_info *exec);
 
-struct drm_gem_cma_object *vc4_use_bo(struct vc4_exec_info *exec,
+struct drm_gem_dma_object *vc4_use_bo(struct vc4_exec_info *exec,
 				      uint32_t hindex);
 
 int vc4_get_rcl(struct drm_device *dev, struct vc4_exec_info *exec);
 
 bool vc4_check_tex_size(struct vc4_exec_info *exec,
-			struct drm_gem_cma_object *fbo,
+			struct drm_gem_dma_object *fbo,
 			uint32_t offset, uint8_t tiling_format,
 			uint32_t width, uint32_t height, uint8_t cpp);
 
 /* vc4_validate_shader.c */
 struct vc4_validated_shader_info *
-vc4_validate_shader(struct drm_gem_cma_object *shader_obj);
+vc4_validate_shader(struct drm_gem_dma_object *shader_obj);
 
 /* vc4_perfmon.c */
 void vc4_perfmon_get(struct vc4_perfmon *perfmon);
diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c
index b7b2c76770dc..878e05d79e81 100644
--- a/drivers/gpu/drm/vc4/vc4_dsi.c
+++ b/drivers/gpu/drm/vc4/vc4_dsi.c
@@ -549,10 +549,13 @@ struct vc4_dsi_variant {
 
 /* General DSI hardware state. */
 struct vc4_dsi {
+	struct vc4_encoder encoder;
+	struct mipi_dsi_host dsi_host;
+
+	struct kref kref;
+
 	struct platform_device *pdev;
 
-	struct mipi_dsi_host dsi_host;
-	struct drm_encoder *encoder;
 	struct drm_bridge *bridge;
 	struct list_head bridge_chain;
 
@@ -600,6 +603,12 @@ struct vc4_dsi {
 
 #define host_to_dsi(host) container_of(host, struct vc4_dsi, dsi_host)
 
+static inline struct vc4_dsi *
+to_vc4_dsi(struct drm_encoder *encoder)
+{
+	return container_of(encoder, struct vc4_dsi, encoder.base);
+}
+
 static inline void
 dsi_dma_workaround_write(struct vc4_dsi *dsi, u32 offset, u32 val)
 {
@@ -644,18 +653,6 @@ dsi_dma_workaround_write(struct vc4_dsi *dsi, u32 offset, u32 val)
 	DSI_WRITE(dsi->variant->port ? DSI1_##offset : DSI0_##offset, val)
 #define DSI_PORT_BIT(bit) (dsi->variant->port ? DSI1_##bit : DSI0_##bit)
 
-/* VC4 DSI encoder KMS struct */
-struct vc4_dsi_encoder {
-	struct vc4_encoder base;
-	struct vc4_dsi *dsi;
-};
-
-static inline struct vc4_dsi_encoder *
-to_vc4_dsi_encoder(struct drm_encoder *encoder)
-{
-	return container_of(encoder, struct vc4_dsi_encoder, base.base);
-}
-
 static const struct debugfs_reg32 dsi0_regs[] = {
 	VC4_REG32(DSI0_CTRL),
 	VC4_REG32(DSI0_STAT),
@@ -795,8 +792,7 @@ dsi_esc_timing(u32 ns)
 
 static void vc4_dsi_encoder_disable(struct drm_encoder *encoder)
 {
-	struct vc4_dsi_encoder *vc4_encoder = to_vc4_dsi_encoder(encoder);
-	struct vc4_dsi *dsi = vc4_encoder->dsi;
+	struct vc4_dsi *dsi = to_vc4_dsi(encoder);
 	struct device *dev = &dsi->pdev->dev;
 	struct drm_bridge *iter;
 
@@ -839,8 +835,7 @@ static bool vc4_dsi_encoder_mode_fixup(struct drm_encoder *encoder,
 				       const struct drm_display_mode *mode,
 				       struct drm_display_mode *adjusted_mode)
 {
-	struct vc4_dsi_encoder *vc4_encoder = to_vc4_dsi_encoder(encoder);
-	struct vc4_dsi *dsi = vc4_encoder->dsi;
+	struct vc4_dsi *dsi = to_vc4_dsi(encoder);
 	struct clk *phy_parent = clk_get_parent(dsi->pll_phy_clock);
 	unsigned long parent_rate = clk_get_rate(phy_parent);
 	unsigned long pixel_clock_hz = mode->clock * 1000;
@@ -875,8 +870,7 @@ static bool vc4_dsi_encoder_mode_fixup(struct drm_encoder *encoder,
 static void vc4_dsi_encoder_enable(struct drm_encoder *encoder)
 {
 	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
-	struct vc4_dsi_encoder *vc4_encoder = to_vc4_dsi_encoder(encoder);
-	struct vc4_dsi *dsi = vc4_encoder->dsi;
+	struct vc4_dsi *dsi = to_vc4_dsi(encoder);
 	struct device *dev = &dsi->pdev->dev;
 	bool debug_dump_regs = false;
 	struct drm_bridge *iter;
@@ -1378,6 +1372,24 @@ static const struct drm_encoder_helper_funcs vc4_dsi_encoder_helper_funcs = {
 	.mode_fixup = vc4_dsi_encoder_mode_fixup,
 };
 
+static int vc4_dsi_late_register(struct drm_encoder *encoder)
+{
+	struct drm_device *drm = encoder->dev;
+	struct vc4_dsi *dsi = to_vc4_dsi(encoder);
+	int ret;
+
+	ret = vc4_debugfs_add_regset32(drm->primary, dsi->variant->debugfs_name,
+				       &dsi->regset);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct drm_encoder_funcs vc4_dsi_encoder_funcs = {
+	.late_register = vc4_dsi_late_register,
+};
+
 static const struct vc4_dsi_variant bcm2711_dsi1_variant = {
 	.port			= 1,
 	.debugfs_name		= "dsi1_regs",
@@ -1564,26 +1576,50 @@ static void vc4_dsi_dma_chan_release(void *ptr)
 	dsi->reg_dma_chan = NULL;
 }
 
+static void vc4_dsi_release(struct kref *kref)
+{
+	struct vc4_dsi *dsi =
+		container_of(kref, struct vc4_dsi, kref);
+
+	kfree(dsi);
+}
+
+static void vc4_dsi_get(struct vc4_dsi *dsi)
+{
+	kref_get(&dsi->kref);
+}
+
+static void vc4_dsi_put(struct vc4_dsi *dsi)
+{
+	kref_put(&dsi->kref, &vc4_dsi_release);
+}
+
+static void vc4_dsi_release_action(struct drm_device *drm, void *ptr)
+{
+	struct vc4_dsi *dsi = ptr;
+
+	vc4_dsi_put(dsi);
+}
+
 static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct drm_device *drm = dev_get_drvdata(master);
 	struct vc4_dsi *dsi = dev_get_drvdata(dev);
-	struct vc4_dsi_encoder *vc4_dsi_encoder;
+	struct drm_encoder *encoder = &dsi->encoder.base;
 	int ret;
 
-	dsi->variant = of_device_get_match_data(dev);
+	vc4_dsi_get(dsi);
 
-	vc4_dsi_encoder = devm_kzalloc(dev, sizeof(*vc4_dsi_encoder),
-				       GFP_KERNEL);
-	if (!vc4_dsi_encoder)
-		return -ENOMEM;
+	ret = drmm_add_action_or_reset(drm, vc4_dsi_release_action, dsi);
+	if (ret)
+		return ret;
+
+	dsi->variant = of_device_get_match_data(dev);
 
 	INIT_LIST_HEAD(&dsi->bridge_chain);
-	vc4_dsi_encoder->base.type = dsi->variant->port ?
-			VC4_ENCODER_TYPE_DSI1 : VC4_ENCODER_TYPE_DSI0;
-	vc4_dsi_encoder->dsi = dsi;
-	dsi->encoder = &vc4_dsi_encoder->base.base;
+	dsi->encoder.type = dsi->variant->port ?
+		VC4_ENCODER_TYPE_DSI1 : VC4_ENCODER_TYPE_DSI0;
 
 	dsi->regs = vc4_ioremap_regs(pdev, 0);
 	if (IS_ERR(dsi->regs))
@@ -1687,7 +1723,7 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 	}
 
-	dsi->bridge = devm_drm_of_get_bridge(dev, dev->of_node, 0, 0);
+	dsi->bridge = drmm_of_get_bridge(drm, dev->of_node, 0, 0);
 	if (IS_ERR(dsi->bridge))
 		return PTR_ERR(dsi->bridge);
 
@@ -1702,10 +1738,20 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 	if (ret)
 		return ret;
 
-	drm_simple_encoder_init(drm, dsi->encoder, DRM_MODE_ENCODER_DSI);
-	drm_encoder_helper_add(dsi->encoder, &vc4_dsi_encoder_helper_funcs);
+	ret = drmm_encoder_init(drm, encoder,
+				&vc4_dsi_encoder_funcs,
+				DRM_MODE_ENCODER_DSI,
+				NULL);
+	if (ret)
+		return ret;
+
+	drm_encoder_helper_add(encoder, &vc4_dsi_encoder_helper_funcs);
 
-	ret = drm_bridge_attach(dsi->encoder, dsi->bridge, NULL, 0);
+	ret = devm_pm_runtime_enable(dev);
+	if (ret)
+		return ret;
+
+	ret = drm_bridge_attach(encoder, dsi->bridge, NULL, 0);
 	if (ret)
 		return ret;
 	/* Disable the atomic helper calls into the bridge.  We
@@ -1713,11 +1759,7 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 	 * from our driver, since we need to sequence them within the
 	 * encoder's enable/disable paths.
 	 */
-	list_splice_init(&dsi->encoder->bridge_chain, &dsi->bridge_chain);
-
-	vc4_debugfs_add_regset32(drm, dsi->variant->debugfs_name, &dsi->regset);
-
-	pm_runtime_enable(dev);
+	list_splice_init(&encoder->bridge_chain, &dsi->bridge_chain);
 
 	return 0;
 }
@@ -1726,15 +1768,13 @@ static void vc4_dsi_unbind(struct device *dev, struct device *master,
 			   void *data)
 {
 	struct vc4_dsi *dsi = dev_get_drvdata(dev);
-
-	pm_runtime_disable(dev);
+	struct drm_encoder *encoder = &dsi->encoder.base;
 
 	/*
 	 * Restore the bridge_chain so the bridge detach procedure can happen
 	 * normally.
 	 */
-	list_splice_init(&dsi->bridge_chain, &dsi->encoder->bridge_chain);
-	drm_encoder_cleanup(dsi->encoder);
+	list_splice_init(&dsi->bridge_chain, &encoder->bridge_chain);
 }
 
 static const struct component_ops vc4_dsi_ops = {
@@ -1747,11 +1787,12 @@ static int vc4_dsi_dev_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct vc4_dsi *dsi;
 
-	dsi = devm_kzalloc(dev, sizeof(*dsi), GFP_KERNEL);
+	dsi = kzalloc(sizeof(*dsi), GFP_KERNEL);
 	if (!dsi)
 		return -ENOMEM;
 	dev_set_drvdata(dev, dsi);
 
+	kref_init(&dsi->kref);
 	dsi->pdev = pdev;
 	dsi->dsi_host.ops = &vc4_dsi_host_ops;
 	dsi->dsi_host.dev = dev;
@@ -1766,6 +1807,8 @@ static int vc4_dsi_dev_remove(struct platform_device *pdev)
 	struct vc4_dsi *dsi = dev_get_drvdata(dev);
 
 	mipi_dsi_host_unregister(&dsi->dsi_host);
+	vc4_dsi_put(dsi);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index fe10d9c3fff8..628d40ff3aa1 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -126,7 +126,7 @@ vc4_get_hang_state_ioctl(struct drm_device *dev, void *data,
 			goto err_delete_handle;
 		}
 		bo_state[i].handle = handle;
-		bo_state[i].paddr = vc4_bo->base.paddr;
+		bo_state[i].paddr = vc4_bo->base.dma_addr;
 		bo_state[i].size = vc4_bo->base.base.size;
 	}
 
@@ -764,7 +764,7 @@ vc4_cl_lookup_bos(struct drm_device *dev,
 	}
 
 	exec->bo = kvmalloc_array(exec->bo_count,
-				    sizeof(struct drm_gem_cma_object *),
+				    sizeof(struct drm_gem_dma_object *),
 				    GFP_KERNEL | __GFP_ZERO);
 	if (!exec->bo) {
 		DRM_ERROR("Failed to allocate validated BO pointers\n");
@@ -797,7 +797,7 @@ vc4_cl_lookup_bos(struct drm_device *dev,
 		}
 
 		drm_gem_object_get(bo);
-		exec->bo[i] = (struct drm_gem_cma_object *)bo;
+		exec->bo[i] = (struct drm_gem_dma_object *)bo;
 	}
 	spin_unlock(&file_priv->table_lock);
 
@@ -917,16 +917,16 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec)
 	list_add_tail(&to_vc4_bo(&exec->exec_bo->base)->unref_head,
 		      &exec->unref_list);
 
-	exec->ct0ca = exec->exec_bo->paddr + bin_offset;
+	exec->ct0ca = exec->exec_bo->dma_addr + bin_offset;
 
 	exec->bin_u = bin;
 
 	exec->shader_rec_v = exec->exec_bo->vaddr + shader_rec_offset;
-	exec->shader_rec_p = exec->exec_bo->paddr + shader_rec_offset;
+	exec->shader_rec_p = exec->exec_bo->dma_addr + shader_rec_offset;
 	exec->shader_rec_size = args->shader_rec_size;
 
 	exec->uniforms_v = exec->exec_bo->vaddr + uniforms_offset;
-	exec->uniforms_p = exec->exec_bo->paddr + uniforms_offset;
+	exec->uniforms_p = exec->exec_bo->dma_addr + uniforms_offset;
 	exec->uniforms_size = args->uniforms_size;
 
 	ret = vc4_validate_bin_cl(dev,
@@ -1308,6 +1308,7 @@ static void vc4_gem_destroy(struct drm_device *dev, void *unused);
 int vc4_gem_init(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	int ret;
 
 	if (WARN_ON_ONCE(vc4->is_vc5))
 		return -ENODEV;
@@ -1325,10 +1326,15 @@ int vc4_gem_init(struct drm_device *dev)
 
 	INIT_WORK(&vc4->job_done_work, vc4_job_done_work);
 
-	mutex_init(&vc4->power_lock);
+	ret = drmm_mutex_init(dev, &vc4->power_lock);
+	if (ret)
+		return ret;
 
 	INIT_LIST_HEAD(&vc4->purgeable.list);
-	mutex_init(&vc4->purgeable.lock);
+
+	ret = drmm_mutex_init(dev, &vc4->purgeable.lock);
+	if (ret)
+		return ret;
 
 	return drmm_add_action_or_reset(dev, vc4_gem_destroy, NULL);
 }
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 592c3b5d03e6..fda450185c36 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -34,6 +34,7 @@
 #include <drm/display/drm_hdmi_helper.h>
 #include <drm/display/drm_scdc_helper.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_simple_kms_helper.h>
 #include <linux/clk.h>
@@ -41,7 +42,6 @@
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/of_address.h>
-#include <linux/of_gpio.h>
 #include <linux/of_platform.h>
 #include <linux/pm_runtime.h>
 #include <linux/rational.h>
@@ -146,7 +146,12 @@ static int vc4_hdmi_debugfs_regs(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct vc4_hdmi *vc4_hdmi = node->info_ent->data;
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	struct drm_printer p = drm_seq_file_printer(m);
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return -ENODEV;
 
 	drm_print_regset32(&p, &vc4_hdmi->hdmi_regset);
 	drm_print_regset32(&p, &vc4_hdmi->hd_regset);
@@ -157,12 +162,23 @@ static int vc4_hdmi_debugfs_regs(struct seq_file *m, void *unused)
 	drm_print_regset32(&p, &vc4_hdmi->ram_regset);
 	drm_print_regset32(&p, &vc4_hdmi->rm_regset);
 
+	drm_dev_exit(idx);
+
 	return 0;
 }
 
 static void vc4_hdmi_reset(struct vc4_hdmi *vc4_hdmi)
 {
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	unsigned long flags;
+	int idx;
+
+	/*
+	 * We can be called by our bind callback, when the
+	 * connector->dev pointer might not be initialised yet.
+	 */
+	if (drm && !drm_dev_enter(drm, &idx))
+		return;
 
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
@@ -179,11 +195,23 @@ static void vc4_hdmi_reset(struct vc4_hdmi *vc4_hdmi)
 	HDMI_WRITE(HDMI_SW_RESET_CONTROL, 0);
 
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
+
+	if (drm)
+		drm_dev_exit(idx);
 }
 
 static void vc5_hdmi_reset(struct vc4_hdmi *vc4_hdmi)
 {
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	unsigned long flags;
+	int idx;
+
+	/*
+	 * We can be called by our bind callback, when the
+	 * connector->dev pointer might not be initialised yet.
+	 */
+	if (drm && !drm_dev_enter(drm, &idx))
+		return;
 
 	reset_control_reset(vc4_hdmi->reset);
 
@@ -195,15 +223,31 @@ static void vc5_hdmi_reset(struct vc4_hdmi *vc4_hdmi)
 		   HDMI_READ(HDMI_CLOCK_STOP) | VC4_DVP_HT_CLOCK_STOP_PIXEL);
 
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
+
+	if (drm)
+		drm_dev_exit(idx);
 }
 
 #ifdef CONFIG_DRM_VC4_HDMI_CEC
 static void vc4_hdmi_cec_update_clk_div(struct vc4_hdmi *vc4_hdmi)
 {
-	unsigned long cec_rate = clk_get_rate(vc4_hdmi->cec_clock);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
+	unsigned long cec_rate;
 	unsigned long flags;
 	u16 clk_cnt;
 	u32 value;
+	int idx;
+
+	/*
+	 * This function is called by our runtime_resume implementation
+	 * and thus at bind time, when we haven't registered our
+	 * connector yet and thus don't have a pointer to the DRM
+	 * device.
+	 */
+	if (drm && !drm_dev_enter(drm, &idx))
+		return;
+
+	cec_rate = clk_get_rate(vc4_hdmi->cec_clock);
 
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
@@ -219,6 +263,9 @@ static void vc4_hdmi_cec_update_clk_div(struct vc4_hdmi *vc4_hdmi)
 	HDMI_WRITE(HDMI_CEC_CNTRL_1, value);
 
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
+
+	if (drm)
+		drm_dev_exit(idx);
 }
 #else
 static void vc4_hdmi_cec_update_clk_div(struct vc4_hdmi *vc4_hdmi) {}
@@ -267,12 +314,6 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force)
 	return connector_status_disconnected;
 }
 
-static void vc4_hdmi_connector_destroy(struct drm_connector *connector)
-{
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-}
-
 static int vc4_hdmi_connector_get_modes(struct drm_connector *connector)
 {
 	struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector);
@@ -380,7 +421,6 @@ vc4_hdmi_connector_duplicate_state(struct drm_connector *connector)
 static const struct drm_connector_funcs vc4_hdmi_connector_funcs = {
 	.detect = vc4_hdmi_connector_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = vc4_hdmi_connector_destroy,
 	.reset = vc4_hdmi_connector_reset,
 	.atomic_duplicate_state = vc4_hdmi_connector_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
@@ -398,10 +438,13 @@ static int vc4_hdmi_connector_init(struct drm_device *dev,
 	struct drm_encoder *encoder = &vc4_hdmi->encoder.base;
 	int ret;
 
-	drm_connector_init_with_ddc(dev, connector,
-				    &vc4_hdmi_connector_funcs,
-				    DRM_MODE_CONNECTOR_HDMIA,
-				    vc4_hdmi->ddc);
+	ret = drmm_connector_init(dev, connector,
+				  &vc4_hdmi_connector_funcs,
+				  DRM_MODE_CONNECTOR_HDMIA,
+				  vc4_hdmi->ddc);
+	if (ret)
+		return ret;
+
 	drm_connector_helper_add(connector, &vc4_hdmi_connector_helper_funcs);
 
 	/*
@@ -444,25 +487,34 @@ static int vc4_hdmi_stop_packet(struct drm_encoder *encoder,
 				bool poll)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	u32 packet_id = type - 0x80;
 	unsigned long flags;
+	int ret = 0;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return -ENODEV;
 
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 	HDMI_WRITE(HDMI_RAM_PACKET_CONFIG,
 		   HDMI_READ(HDMI_RAM_PACKET_CONFIG) & ~BIT(packet_id));
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
 
-	if (!poll)
-		return 0;
+	if (poll) {
+		ret = wait_for(!(HDMI_READ(HDMI_RAM_PACKET_STATUS) &
+				 BIT(packet_id)), 100);
+	}
 
-	return wait_for(!(HDMI_READ(HDMI_RAM_PACKET_STATUS) &
-			  BIT(packet_id)), 100);
+	drm_dev_exit(idx);
+	return ret;
 }
 
 static void vc4_hdmi_write_infoframe(struct drm_encoder *encoder,
 				     union hdmi_infoframe *frame)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	u32 packet_id = frame->any.type - 0x80;
 	const struct vc4_hdmi_register *ram_packet_start =
 		&vc4_hdmi->variant->registers[HDMI_RAM_PACKET_START];
@@ -475,6 +527,10 @@ static void vc4_hdmi_write_infoframe(struct drm_encoder *encoder,
 	unsigned long flags;
 	ssize_t len, i;
 	int ret;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
 
 	WARN_ONCE(!(HDMI_READ(HDMI_RAM_PACKET_CONFIG) &
 		    VC4_HDMI_RAM_PACKET_ENABLE),
@@ -482,12 +538,12 @@ static void vc4_hdmi_write_infoframe(struct drm_encoder *encoder,
 
 	len = hdmi_infoframe_pack(frame, buffer, sizeof(buffer));
 	if (len < 0)
-		return;
+		goto out;
 
 	ret = vc4_hdmi_stop_packet(encoder, frame->any.type, true);
 	if (ret) {
 		DRM_ERROR("Failed to wait for infoframe to go idle: %d\n", ret);
-		return;
+		goto out;
 	}
 
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
@@ -523,6 +579,9 @@ static void vc4_hdmi_write_infoframe(struct drm_encoder *encoder,
 			BIT(packet_id)), 100);
 	if (ret)
 		DRM_ERROR("Failed to wait for infoframe to start: %d\n", ret);
+
+out:
+	drm_dev_exit(idx);
 }
 
 static void vc4_hdmi_avi_infoframe_colorspace(struct hdmi_avi_infoframe *frame,
@@ -672,8 +731,10 @@ static bool vc4_hdmi_supports_scrambling(struct drm_encoder *encoder,
 static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	struct drm_display_mode *mode = &vc4_hdmi->saved_adjusted_mode;
 	unsigned long flags;
+	int idx;
 
 	lockdep_assert_held(&vc4_hdmi->mutex);
 
@@ -685,6 +746,9 @@ static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder)
 					    vc4_hdmi->output_format))
 		return;
 
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
 	drm_scdc_set_high_tmds_clock_ratio(vc4_hdmi->ddc, true);
 	drm_scdc_set_scrambling(vc4_hdmi->ddc, true);
 
@@ -693,6 +757,8 @@ static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder)
 		   VC5_HDMI_SCRAMBLER_CTL_ENABLE);
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
 
+	drm_dev_exit(idx);
+
 	vc4_hdmi->scdc_enabled = true;
 
 	queue_delayed_work(system_wq, &vc4_hdmi->scrambling_work,
@@ -702,7 +768,9 @@ static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder)
 static void vc4_hdmi_disable_scrambling(struct drm_encoder *encoder)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	unsigned long flags;
+	int idx;
 
 	lockdep_assert_held(&vc4_hdmi->mutex);
 
@@ -714,6 +782,9 @@ static void vc4_hdmi_disable_scrambling(struct drm_encoder *encoder)
 	if (delayed_work_pending(&vc4_hdmi->scrambling_work))
 		cancel_delayed_work_sync(&vc4_hdmi->scrambling_work);
 
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 	HDMI_WRITE(HDMI_SCRAMBLER_CTL, HDMI_READ(HDMI_SCRAMBLER_CTL) &
 		   ~VC5_HDMI_SCRAMBLER_CTL_ENABLE);
@@ -721,6 +792,8 @@ static void vc4_hdmi_disable_scrambling(struct drm_encoder *encoder)
 
 	drm_scdc_set_scrambling(vc4_hdmi->ddc, false);
 	drm_scdc_set_high_tmds_clock_ratio(vc4_hdmi->ddc, false);
+
+	drm_dev_exit(idx);
 }
 
 static void vc4_hdmi_scrambling_wq(struct work_struct *work)
@@ -743,12 +816,17 @@ static void vc4_hdmi_encoder_post_crtc_disable(struct drm_encoder *encoder,
 					       struct drm_atomic_state *state)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	unsigned long flags;
+	int idx;
 
 	mutex_lock(&vc4_hdmi->mutex);
 
 	vc4_hdmi->packet_ram_enabled = false;
 
+	if (!drm_dev_enter(drm, &idx))
+		goto out;
+
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
 	HDMI_WRITE(HDMI_RAM_PACKET_CONFIG, 0);
@@ -766,6 +844,9 @@ static void vc4_hdmi_encoder_post_crtc_disable(struct drm_encoder *encoder,
 
 	vc4_hdmi_disable_scrambling(encoder);
 
+	drm_dev_exit(idx);
+
+out:
 	mutex_unlock(&vc4_hdmi->mutex);
 }
 
@@ -773,11 +854,16 @@ static void vc4_hdmi_encoder_post_crtc_powerdown(struct drm_encoder *encoder,
 						 struct drm_atomic_state *state)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	unsigned long flags;
 	int ret;
+	int idx;
 
 	mutex_lock(&vc4_hdmi->mutex);
 
+	if (!drm_dev_enter(drm, &idx))
+		goto out;
+
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 	HDMI_WRITE(HDMI_VID_CTL,
 		   HDMI_READ(HDMI_VID_CTL) | VC4_HD_VID_CTL_BLANKPIX);
@@ -793,6 +879,9 @@ static void vc4_hdmi_encoder_post_crtc_powerdown(struct drm_encoder *encoder,
 	if (ret < 0)
 		DRM_ERROR("Failed to release power domain: %d\n", ret);
 
+	drm_dev_exit(idx);
+
+out:
 	mutex_unlock(&vc4_hdmi->mutex);
 }
 
@@ -800,8 +889,13 @@ static void vc4_hdmi_csc_setup(struct vc4_hdmi *vc4_hdmi,
 			       struct drm_connector_state *state,
 			       const struct drm_display_mode *mode)
 {
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	unsigned long flags;
 	u32 csc_ctl;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
 
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
@@ -836,6 +930,8 @@ static void vc4_hdmi_csc_setup(struct vc4_hdmi *vc4_hdmi,
 	HDMI_WRITE(HDMI_CSC_CTL, csc_ctl);
 
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
+
+	drm_dev_exit(idx);
 }
 
 /*
@@ -920,6 +1016,7 @@ static void vc5_hdmi_csc_setup(struct vc4_hdmi *vc4_hdmi,
 			       struct drm_connector_state *state,
 			       const struct drm_display_mode *mode)
 {
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	struct vc4_hdmi_connector_state *vc4_state =
 		conn_state_to_vc4_hdmi_conn_state(state);
 	unsigned long flags;
@@ -928,6 +1025,10 @@ static void vc5_hdmi_csc_setup(struct vc4_hdmi *vc4_hdmi,
 	u32 csc_chan_ctl = 0;
 	u32 csc_ctl = VC5_MT_CP_CSC_CTL_ENABLE | VC4_SET_FIELD(VC4_HD_CSC_CTL_MODE_CUSTOM,
 							       VC5_MT_CP_CSC_CTL_MODE);
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
 
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
@@ -970,12 +1071,15 @@ static void vc5_hdmi_csc_setup(struct vc4_hdmi *vc4_hdmi,
 	HDMI_WRITE(HDMI_CSC_CTL, csc_ctl);
 
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
+
+	drm_dev_exit(idx);
 }
 
 static void vc4_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi,
 				 struct drm_connector_state *state,
 				 struct drm_display_mode *mode)
 {
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	bool hsync_pos = mode->flags & DRM_MODE_FLAG_PHSYNC;
 	bool vsync_pos = mode->flags & DRM_MODE_FLAG_PVSYNC;
 	bool interlaced = mode->flags & DRM_MODE_FLAG_INTERLACE;
@@ -995,6 +1099,10 @@ static void vc4_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi,
 					VC4_HDMI_VERTB_VBP));
 	unsigned long flags;
 	u32 reg;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
 
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
@@ -1027,12 +1135,15 @@ static void vc4_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi,
 	HDMI_WRITE(HDMI_MISC_CONTROL, reg);
 
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
+
+	drm_dev_exit(idx);
 }
 
 static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi,
 				 struct drm_connector_state *state,
 				 struct drm_display_mode *mode)
 {
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	const struct vc4_hdmi_connector_state *vc4_state =
 		conn_state_to_vc4_hdmi_conn_state(state);
 	bool hsync_pos = mode->flags & DRM_MODE_FLAG_PHSYNC;
@@ -1056,6 +1167,10 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi,
 	unsigned char gcp;
 	bool gcp_en;
 	u32 reg;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
 
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
@@ -1132,13 +1247,20 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi,
 	HDMI_WRITE(HDMI_CLOCK_STOP, 0);
 
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
+
+	drm_dev_exit(idx);
 }
 
 static void vc4_hdmi_recenter_fifo(struct vc4_hdmi *vc4_hdmi)
 {
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	unsigned long flags;
 	u32 drift;
 	int ret;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
 
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
@@ -1167,12 +1289,15 @@ static void vc4_hdmi_recenter_fifo(struct vc4_hdmi *vc4_hdmi)
 		       VC4_HDMI_FIFO_CTL_RECENTER_DONE, 1);
 	WARN_ONCE(ret, "Timeout waiting for "
 		  "VC4_HDMI_FIFO_CTL_RECENTER_DONE");
+
+	drm_dev_exit(idx);
 }
 
 static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 						struct drm_atomic_state *state)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	struct drm_connector *connector = &vc4_hdmi->connector;
 	struct drm_connector_state *conn_state =
 		drm_atomic_get_new_connector_state(state, connector);
@@ -1183,9 +1308,13 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 	unsigned long bvb_rate, hsm_rate;
 	unsigned long flags;
 	int ret;
+	int idx;
 
 	mutex_lock(&vc4_hdmi->mutex);
 
+	if (!drm_dev_enter(drm, &idx))
+		goto out;
+
 	/*
 	 * As stated in RPi's vc4 firmware "HDMI state machine (HSM) clock must
 	 * be faster than pixel clock, infinitesimally faster, tested in
@@ -1206,13 +1335,13 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 	ret = clk_set_min_rate(vc4_hdmi->hsm_clock, hsm_rate);
 	if (ret) {
 		DRM_ERROR("Failed to set HSM clock rate: %d\n", ret);
-		goto out;
+		goto err_dev_exit;
 	}
 
 	ret = pm_runtime_resume_and_get(&vc4_hdmi->pdev->dev);
 	if (ret < 0) {
 		DRM_ERROR("Failed to retain power domain: %d\n", ret);
-		goto out;
+		goto err_dev_exit;
 	}
 
 	ret = clk_set_rate(vc4_hdmi->pixel_clock, tmds_char_rate);
@@ -1264,6 +1393,8 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 	if (vc4_hdmi->variant->set_timings)
 		vc4_hdmi->variant->set_timings(vc4_hdmi, conn_state, mode);
 
+	drm_dev_exit(idx);
+
 	mutex_unlock(&vc4_hdmi->mutex);
 
 	return;
@@ -1272,6 +1403,8 @@ err_disable_pixel_clock:
 	clk_disable_unprepare(vc4_hdmi->pixel_clock);
 err_put_runtime_pm:
 	pm_runtime_put(&vc4_hdmi->pdev->dev);
+err_dev_exit:
+	drm_dev_exit(idx);
 out:
 	mutex_unlock(&vc4_hdmi->mutex);
 	return;
@@ -1281,14 +1414,19 @@ static void vc4_hdmi_encoder_pre_crtc_enable(struct drm_encoder *encoder,
 					     struct drm_atomic_state *state)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	struct drm_connector *connector = &vc4_hdmi->connector;
 	struct drm_display_mode *mode = &vc4_hdmi->saved_adjusted_mode;
 	struct drm_connector_state *conn_state =
 		drm_atomic_get_new_connector_state(state, connector);
 	unsigned long flags;
+	int idx;
 
 	mutex_lock(&vc4_hdmi->mutex);
 
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
 	if (vc4_hdmi->variant->csc_setup)
 		vc4_hdmi->variant->csc_setup(vc4_hdmi, conn_state, mode);
 
@@ -1296,6 +1434,8 @@ static void vc4_hdmi_encoder_pre_crtc_enable(struct drm_encoder *encoder,
 	HDMI_WRITE(HDMI_FIFO_CTL, VC4_HDMI_FIFO_CTL_MASTER_SLAVE_N);
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
 
+	drm_dev_exit(idx);
+
 	mutex_unlock(&vc4_hdmi->mutex);
 }
 
@@ -1303,15 +1443,20 @@ static void vc4_hdmi_encoder_post_crtc_enable(struct drm_encoder *encoder,
 					      struct drm_atomic_state *state)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	struct drm_display_mode *mode = &vc4_hdmi->saved_adjusted_mode;
 	struct drm_display_info *display = &vc4_hdmi->connector.display_info;
 	bool hsync_pos = mode->flags & DRM_MODE_FLAG_PHSYNC;
 	bool vsync_pos = mode->flags & DRM_MODE_FLAG_PVSYNC;
 	unsigned long flags;
 	int ret;
+	int idx;
 
 	mutex_lock(&vc4_hdmi->mutex);
 
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
 	HDMI_WRITE(HDMI_VID_CTL,
@@ -1370,6 +1515,7 @@ static void vc4_hdmi_encoder_post_crtc_enable(struct drm_encoder *encoder,
 	vc4_hdmi_recenter_fifo(vc4_hdmi);
 	vc4_hdmi_enable_scrambling(encoder);
 
+	drm_dev_exit(idx);
 	mutex_unlock(&vc4_hdmi->mutex);
 }
 
@@ -1692,6 +1838,26 @@ static const struct drm_encoder_helper_funcs vc4_hdmi_encoder_helper_funcs = {
 	.mode_valid = vc4_hdmi_encoder_mode_valid,
 };
 
+static int vc4_hdmi_late_register(struct drm_encoder *encoder)
+{
+	struct drm_device *drm = encoder->dev;
+	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	const struct vc4_hdmi_variant *variant = vc4_hdmi->variant;
+	int ret;
+
+	ret = vc4_debugfs_add_file(drm->primary, variant->debugfs_name,
+				   vc4_hdmi_debugfs_regs,
+				   vc4_hdmi);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct drm_encoder_funcs vc4_hdmi_encoder_funcs = {
+	.late_register = vc4_hdmi_late_register,
+};
+
 static u32 vc4_hdmi_channel_map(struct vc4_hdmi *vc4_hdmi, u32 channel_mask)
 {
 	int i;
@@ -1718,13 +1884,20 @@ static u32 vc5_hdmi_channel_map(struct vc4_hdmi *vc4_hdmi, u32 channel_mask)
 
 static bool vc5_hdmi_hp_detect(struct vc4_hdmi *vc4_hdmi)
 {
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	unsigned long flags;
 	u32 hotplug;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return false;
 
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 	hotplug = HDMI_READ(HDMI_HOTPLUG);
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
 
+	drm_dev_exit(idx);
+
 	return !!(hotplug & VC4_HDMI_HOTPLUG_CONNECTED);
 }
 
@@ -1732,10 +1905,16 @@ static bool vc5_hdmi_hp_detect(struct vc4_hdmi *vc4_hdmi)
 static void vc4_hdmi_audio_set_mai_clock(struct vc4_hdmi *vc4_hdmi,
 					 unsigned int samplerate)
 {
-	u32 hsm_clock = clk_get_rate(vc4_hdmi->audio_clock);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
+	u32 hsm_clock;
 	unsigned long flags;
 	unsigned long n, m;
+	int idx;
 
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
+	hsm_clock = clk_get_rate(vc4_hdmi->audio_clock);
 	rational_best_approximation(hsm_clock, samplerate,
 				    VC4_HD_MAI_SMP_N_MASK >>
 				    VC4_HD_MAI_SMP_N_SHIFT,
@@ -1748,6 +1927,8 @@ static void vc4_hdmi_audio_set_mai_clock(struct vc4_hdmi *vc4_hdmi,
 		   VC4_SET_FIELD(n, VC4_HD_MAI_SMP_N) |
 		   VC4_SET_FIELD(m - 1, VC4_HD_MAI_SMP_M));
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
+
+	drm_dev_exit(idx);
 }
 
 static void vc4_hdmi_set_n_cts(struct vc4_hdmi *vc4_hdmi, unsigned int samplerate)
@@ -1803,13 +1984,21 @@ static bool vc4_hdmi_audio_can_stream(struct vc4_hdmi *vc4_hdmi)
 static int vc4_hdmi_audio_startup(struct device *dev, void *data)
 {
 	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	unsigned long flags;
+	int ret = 0;
+	int idx;
 
 	mutex_lock(&vc4_hdmi->mutex);
 
+	if (!drm_dev_enter(drm, &idx)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	if (!vc4_hdmi_audio_can_stream(vc4_hdmi)) {
-		mutex_unlock(&vc4_hdmi->mutex);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out_dev_exit;
 	}
 
 	vc4_hdmi->audio.streaming = true;
@@ -1826,9 +2015,12 @@ static int vc4_hdmi_audio_startup(struct device *dev, void *data)
 	if (vc4_hdmi->variant->phy_rng_enable)
 		vc4_hdmi->variant->phy_rng_enable(vc4_hdmi);
 
+out_dev_exit:
+	drm_dev_exit(idx);
+out:
 	mutex_unlock(&vc4_hdmi->mutex);
 
-	return 0;
+	return ret;
 }
 
 static void vc4_hdmi_audio_reset(struct vc4_hdmi *vc4_hdmi)
@@ -1857,10 +2049,15 @@ static void vc4_hdmi_audio_reset(struct vc4_hdmi *vc4_hdmi)
 static void vc4_hdmi_audio_shutdown(struct device *dev, void *data)
 {
 	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	unsigned long flags;
+	int idx;
 
 	mutex_lock(&vc4_hdmi->mutex);
 
+	if (!drm_dev_enter(drm, &idx))
+		goto out;
+
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
 	HDMI_WRITE(HDMI_MAI_CTL,
@@ -1876,6 +2073,9 @@ static void vc4_hdmi_audio_shutdown(struct device *dev, void *data)
 	vc4_hdmi->audio.streaming = false;
 	vc4_hdmi_audio_reset(vc4_hdmi);
 
+	drm_dev_exit(idx);
+
+out:
 	mutex_unlock(&vc4_hdmi->mutex);
 }
 
@@ -1923,6 +2123,7 @@ static int vc4_hdmi_audio_prepare(struct device *dev, void *data,
 				  struct hdmi_codec_params *params)
 {
 	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	struct drm_encoder *encoder = &vc4_hdmi->encoder.base;
 	unsigned int sample_rate = params->sample_rate;
 	unsigned int channels = params->channels;
@@ -1931,15 +2132,22 @@ static int vc4_hdmi_audio_prepare(struct device *dev, void *data,
 	u32 channel_map;
 	u32 mai_audio_format;
 	u32 mai_sample_rate;
+	int ret = 0;
+	int idx;
 
 	dev_dbg(dev, "%s: %u Hz, %d bit, %d channels\n", __func__,
 		sample_rate, params->sample_width, channels);
 
 	mutex_lock(&vc4_hdmi->mutex);
 
+	if (!drm_dev_enter(drm, &idx)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	if (!vc4_hdmi_audio_can_stream(vc4_hdmi)) {
-		mutex_unlock(&vc4_hdmi->mutex);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out_dev_exit;
 	}
 
 	vc4_hdmi_audio_set_mai_clock(vc4_hdmi, sample_rate);
@@ -1996,9 +2204,12 @@ static int vc4_hdmi_audio_prepare(struct device *dev, void *data,
 	memcpy(&vc4_hdmi->audio.infoframe, &params->cea, sizeof(params->cea));
 	vc4_hdmi_set_audio_infoframe(encoder);
 
+out_dev_exit:
+	drm_dev_exit(idx);
+out:
 	mutex_unlock(&vc4_hdmi->mutex);
 
-	return 0;
+	return ret;
 }
 
 static const struct snd_soc_component_driver vc4_hdmi_audio_cpu_dai_comp = {
@@ -2061,6 +2272,14 @@ static struct hdmi_codec_pdata vc4_hdmi_codec_pdata = {
 	.i2s = 1,
 };
 
+static void vc4_hdmi_audio_codec_release(void *ptr)
+{
+	struct vc4_hdmi *vc4_hdmi = ptr;
+
+	platform_device_unregister(vc4_hdmi->audio.codec_pdev);
+	vc4_hdmi->audio.codec_pdev = NULL;
+}
+
 static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 {
 	const struct vc4_hdmi_register *mai_data =
@@ -2073,6 +2292,26 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 	int index, len;
 	int ret;
 
+	/*
+	 * ASoC makes it a bit hard to retrieve a pointer to the
+	 * vc4_hdmi structure. Registering the card will overwrite our
+	 * device drvdata with a pointer to the snd_soc_card structure,
+	 * which can then be used to retrieve whatever drvdata we want
+	 * to associate.
+	 *
+	 * However, that doesn't fly in the case where we wouldn't
+	 * register an ASoC card (because of an old DT that is missing
+	 * the dmas properties for example), then the card isn't
+	 * registered and the device drvdata wouldn't be set.
+	 *
+	 * We can deal with both cases by making sure a snd_soc_card
+	 * pointer and a vc4_hdmi structure are pointing to the same
+	 * memory address, so we can treat them indistinctly without any
+	 * issue.
+	 */
+	BUILD_BUG_ON(offsetof(struct vc4_hdmi_audio, card) != 0);
+	BUILD_BUG_ON(offsetof(struct vc4_hdmi, audio) != 0);
+
 	if (!of_find_property(dev->of_node, "dmas", &len) || !len) {
 		dev_warn(dev,
 			 "'dmas' DT property is missing or empty, no HDMI audio\n");
@@ -2102,6 +2341,30 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 	vc4_hdmi->audio.dma_data.addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	vc4_hdmi->audio.dma_data.maxburst = 2;
 
+	/*
+	 * NOTE: Strictly speaking, we should probably use a DRM-managed
+	 * registration there to avoid removing all the audio components
+	 * by the time the driver doesn't have any user anymore.
+	 *
+	 * However, the ASoC core uses a number of devm_kzalloc calls
+	 * when registering, even when using non-device-managed
+	 * functions (such as in snd_soc_register_component()).
+	 *
+	 * If we call snd_soc_unregister_component() in a DRM-managed
+	 * action, the device-managed actions have already been executed
+	 * and thus we would access memory that has been freed.
+	 *
+	 * Using device-managed hooks here probably leaves us open to a
+	 * bunch of issues if userspace still has a handle on the ALSA
+	 * device when the device is removed. However, this is mitigated
+	 * by the use of drm_dev_enter()/drm_dev_exit() in the audio
+	 * path to prevent the access to the device resources if it
+	 * isn't there anymore.
+	 *
+	 * Then, the vc4_hdmi structure is DRM-managed and thus only
+	 * freed whenever the last user has closed the DRM device file.
+	 * It should thus outlive ALSA in most situations.
+	 */
 	ret = devm_snd_dmaengine_pcm_register(dev, &pcm_conf, 0);
 	if (ret) {
 		dev_err(dev, "Could not register PCM component: %d\n", ret);
@@ -2125,6 +2388,10 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 	}
 	vc4_hdmi->audio.codec_pdev = codec_pdev;
 
+	ret = devm_add_action_or_reset(dev, vc4_hdmi_audio_codec_release, vc4_hdmi);
+	if (ret)
+		return ret;
+
 	dai_link->cpus		= &vc4_hdmi->audio.cpu;
 	dai_link->codecs	= &vc4_hdmi->audio.codec;
 	dai_link->platforms	= &vc4_hdmi->audio.platform;
@@ -2163,12 +2430,6 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 
 }
 
-static void vc4_hdmi_audio_exit(struct vc4_hdmi *vc4_hdmi)
-{
-	platform_device_unregister(vc4_hdmi->audio.codec_pdev);
-	vc4_hdmi->audio.codec_pdev = NULL;
-}
-
 static irqreturn_t vc4_hdmi_hpd_irq_thread(int irq, void *priv)
 {
 	struct vc4_hdmi *vc4_hdmi = priv;
@@ -2191,21 +2452,19 @@ static int vc4_hdmi_hotplug_init(struct vc4_hdmi *vc4_hdmi)
 		unsigned int hpd_con = platform_get_irq_byname(pdev, "hpd-connected");
 		unsigned int hpd_rm = platform_get_irq_byname(pdev, "hpd-removed");
 
-		ret = request_threaded_irq(hpd_con,
-					   NULL,
-					   vc4_hdmi_hpd_irq_thread, IRQF_ONESHOT,
-					   "vc4 hdmi hpd connected", vc4_hdmi);
+		ret = devm_request_threaded_irq(&pdev->dev, hpd_con,
+						NULL,
+						vc4_hdmi_hpd_irq_thread, IRQF_ONESHOT,
+						"vc4 hdmi hpd connected", vc4_hdmi);
 		if (ret)
 			return ret;
 
-		ret = request_threaded_irq(hpd_rm,
-					   NULL,
-					   vc4_hdmi_hpd_irq_thread, IRQF_ONESHOT,
-					   "vc4 hdmi hpd disconnected", vc4_hdmi);
-		if (ret) {
-			free_irq(hpd_con, vc4_hdmi);
+		ret = devm_request_threaded_irq(&pdev->dev, hpd_rm,
+						NULL,
+						vc4_hdmi_hpd_irq_thread, IRQF_ONESHOT,
+						"vc4 hdmi hpd disconnected", vc4_hdmi);
+		if (ret)
 			return ret;
-		}
 
 		connector->polled = DRM_CONNECTOR_POLL_HPD;
 	}
@@ -2213,16 +2472,6 @@ static int vc4_hdmi_hotplug_init(struct vc4_hdmi *vc4_hdmi)
 	return 0;
 }
 
-static void vc4_hdmi_hotplug_exit(struct vc4_hdmi *vc4_hdmi)
-{
-	struct platform_device *pdev = vc4_hdmi->pdev;
-
-	if (vc4_hdmi->variant->external_irq_controller) {
-		free_irq(platform_get_irq_byname(pdev, "hpd-connected"), vc4_hdmi);
-		free_irq(platform_get_irq_byname(pdev, "hpd-removed"), vc4_hdmi);
-	}
-}
-
 #ifdef CONFIG_DRM_VC4_HDMI_CEC
 static irqreturn_t vc4_cec_irq_handler_rx_thread(int irq, void *priv)
 {
@@ -2296,6 +2545,17 @@ static irqreturn_t vc4_cec_irq_handler_tx_bare_locked(struct vc4_hdmi *vc4_hdmi)
 {
 	u32 cntrl1;
 
+	/*
+	 * We don't need to protect the register access using
+	 * drm_dev_enter() there because the interrupt handler lifetime
+	 * is tied to the device itself, and not to the DRM device.
+	 *
+	 * So when the device will be gone, one of the first thing we
+	 * will be doing will be to unregister the interrupt handler,
+	 * and then unregister the DRM device. drm_dev_enter() would
+	 * thus always succeed if we are here.
+	 */
+
 	lockdep_assert_held(&vc4_hdmi->hw_lock);
 
 	cntrl1 = HDMI_READ(HDMI_CEC_CNTRL_1);
@@ -2324,6 +2584,17 @@ static irqreturn_t vc4_cec_irq_handler_rx_bare_locked(struct vc4_hdmi *vc4_hdmi)
 
 	lockdep_assert_held(&vc4_hdmi->hw_lock);
 
+	/*
+	 * We don't need to protect the register access using
+	 * drm_dev_enter() there because the interrupt handler lifetime
+	 * is tied to the device itself, and not to the DRM device.
+	 *
+	 * So when the device will be gone, one of the first thing we
+	 * will be doing will be to unregister the interrupt handler,
+	 * and then unregister the DRM device. drm_dev_enter() would
+	 * thus always succeed if we are here.
+	 */
+
 	vc4_hdmi->cec_rx_msg.len = 0;
 	cntrl1 = HDMI_READ(HDMI_CEC_CNTRL_1);
 	vc4_cec_read_msg(vc4_hdmi, cntrl1);
@@ -2355,6 +2626,17 @@ static irqreturn_t vc4_cec_irq_handler(int irq, void *priv)
 	irqreturn_t ret;
 	u32 cntrl5;
 
+	/*
+	 * We don't need to protect the register access using
+	 * drm_dev_enter() there because the interrupt handler lifetime
+	 * is tied to the device itself, and not to the DRM device.
+	 *
+	 * So when the device will be gone, one of the first thing we
+	 * will be doing will be to unregister the interrupt handler,
+	 * and then unregister the DRM device. drm_dev_enter() would
+	 * thus always succeed if we are here.
+	 */
+
 	if (!(stat & VC4_HDMI_CPU_CEC))
 		return IRQ_NONE;
 
@@ -2375,11 +2657,13 @@ static irqreturn_t vc4_cec_irq_handler(int irq, void *priv)
 static int vc4_hdmi_cec_enable(struct cec_adapter *adap)
 {
 	struct vc4_hdmi *vc4_hdmi = cec_get_drvdata(adap);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	/* clock period in microseconds */
 	const u32 usecs = 1000000 / CEC_CLOCK_FREQ;
 	unsigned long flags;
 	u32 val;
 	int ret;
+	int idx;
 
 	/*
 	 * NOTE: This function should really take vc4_hdmi->mutex, but doing so
@@ -2392,9 +2676,19 @@ static int vc4_hdmi_cec_enable(struct cec_adapter *adap)
 	 * keep it in mind if we were to change that assumption.
 	 */
 
+	if (!drm_dev_enter(drm, &idx))
+		/*
+		 * We can't return an error code, because the CEC
+		 * framework will emit WARN_ON messages at unbind
+		 * otherwise.
+		 */
+		return 0;
+
 	ret = pm_runtime_resume_and_get(&vc4_hdmi->pdev->dev);
-	if (ret)
+	if (ret) {
+		drm_dev_exit(idx);
 		return ret;
+	}
 
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
@@ -2430,13 +2724,25 @@ static int vc4_hdmi_cec_enable(struct cec_adapter *adap)
 
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
 
+	drm_dev_exit(idx);
+
 	return 0;
 }
 
 static int vc4_hdmi_cec_disable(struct cec_adapter *adap)
 {
 	struct vc4_hdmi *vc4_hdmi = cec_get_drvdata(adap);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	unsigned long flags;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		/*
+		 * We can't return an error code, because the CEC
+		 * framework will emit WARN_ON messages at unbind
+		 * otherwise.
+		 */
+		return 0;
 
 	/*
 	 * NOTE: This function should really take vc4_hdmi->mutex, but doing so
@@ -2461,6 +2767,8 @@ static int vc4_hdmi_cec_disable(struct cec_adapter *adap)
 
 	pm_runtime_put(&vc4_hdmi->pdev->dev);
 
+	drm_dev_exit(idx);
+
 	return 0;
 }
 
@@ -2475,7 +2783,9 @@ static int vc4_hdmi_cec_adap_enable(struct cec_adapter *adap, bool enable)
 static int vc4_hdmi_cec_adap_log_addr(struct cec_adapter *adap, u8 log_addr)
 {
 	struct vc4_hdmi *vc4_hdmi = cec_get_drvdata(adap);
+	struct drm_device *drm = vc4_hdmi->connector.dev;
 	unsigned long flags;
+	int idx;
 
 	/*
 	 * NOTE: This function should really take vc4_hdmi->mutex, but doing so
@@ -2488,12 +2798,22 @@ static int vc4_hdmi_cec_adap_log_addr(struct cec_adapter *adap, u8 log_addr)
 	 * keep it in mind if we were to change that assumption.
 	 */
 
+	if (!drm_dev_enter(drm, &idx))
+		/*
+		 * We can't return an error code, because the CEC
+		 * framework will emit WARN_ON messages at unbind
+		 * otherwise.
+		 */
+		return 0;
+
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 	HDMI_WRITE(HDMI_CEC_CNTRL_1,
 		   (HDMI_READ(HDMI_CEC_CNTRL_1) & ~VC4_HDMI_CEC_ADDR_MASK) |
 		   (log_addr & 0xf) << VC4_HDMI_CEC_ADDR_SHIFT);
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
 
+	drm_dev_exit(idx);
+
 	return 0;
 }
 
@@ -2505,6 +2825,7 @@ static int vc4_hdmi_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
 	unsigned long flags;
 	u32 val;
 	unsigned int i;
+	int idx;
 
 	/*
 	 * NOTE: This function should really take vc4_hdmi->mutex, but doing so
@@ -2517,8 +2838,12 @@ static int vc4_hdmi_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
 	 * keep it in mind if we were to change that assumption.
 	 */
 
+	if (!drm_dev_enter(dev, &idx))
+		return -ENODEV;
+
 	if (msg->len > 16) {
 		drm_err(dev, "Attempting to transmit too much data (%d)\n", msg->len);
+		drm_dev_exit(idx);
 		return -ENOMEM;
 	}
 
@@ -2542,6 +2867,8 @@ static int vc4_hdmi_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
 
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
 
+	drm_dev_exit(idx);
+
 	return 0;
 }
 
@@ -2551,6 +2878,14 @@ static const struct cec_adap_ops vc4_hdmi_cec_adap_ops = {
 	.adap_transmit = vc4_hdmi_cec_adap_transmit,
 };
 
+static void vc4_hdmi_cec_release(void *ptr)
+{
+	struct vc4_hdmi *vc4_hdmi = ptr;
+
+	cec_unregister_adapter(vc4_hdmi->cec_adap);
+	vc4_hdmi->cec_adap = NULL;
+}
+
 static int vc4_hdmi_cec_init(struct vc4_hdmi *vc4_hdmi)
 {
 	struct cec_connector_info conn_info;
@@ -2575,73 +2910,82 @@ static int vc4_hdmi_cec_init(struct vc4_hdmi *vc4_hdmi)
 	cec_s_conn_info(vc4_hdmi->cec_adap, &conn_info);
 
 	if (vc4_hdmi->variant->external_irq_controller) {
-		ret = request_threaded_irq(platform_get_irq_byname(pdev, "cec-rx"),
-					   vc4_cec_irq_handler_rx_bare,
-					   vc4_cec_irq_handler_rx_thread, 0,
-					   "vc4 hdmi cec rx", vc4_hdmi);
+		ret = devm_request_threaded_irq(dev, platform_get_irq_byname(pdev, "cec-rx"),
+						vc4_cec_irq_handler_rx_bare,
+						vc4_cec_irq_handler_rx_thread, 0,
+						"vc4 hdmi cec rx", vc4_hdmi);
 		if (ret)
 			goto err_delete_cec_adap;
 
-		ret = request_threaded_irq(platform_get_irq_byname(pdev, "cec-tx"),
-					   vc4_cec_irq_handler_tx_bare,
-					   vc4_cec_irq_handler_tx_thread, 0,
-					   "vc4 hdmi cec tx", vc4_hdmi);
+		ret = devm_request_threaded_irq(dev, platform_get_irq_byname(pdev, "cec-tx"),
+						vc4_cec_irq_handler_tx_bare,
+						vc4_cec_irq_handler_tx_thread, 0,
+						"vc4 hdmi cec tx", vc4_hdmi);
 		if (ret)
-			goto err_remove_cec_rx_handler;
+			goto err_delete_cec_adap;
 	} else {
-		ret = request_threaded_irq(platform_get_irq(pdev, 0),
-					   vc4_cec_irq_handler,
-					   vc4_cec_irq_handler_thread, 0,
-					   "vc4 hdmi cec", vc4_hdmi);
+		ret = devm_request_threaded_irq(dev, platform_get_irq(pdev, 0),
+						vc4_cec_irq_handler,
+						vc4_cec_irq_handler_thread, 0,
+						"vc4 hdmi cec", vc4_hdmi);
 		if (ret)
 			goto err_delete_cec_adap;
 	}
 
 	ret = cec_register_adapter(vc4_hdmi->cec_adap, &pdev->dev);
 	if (ret < 0)
-		goto err_remove_handlers;
+		goto err_delete_cec_adap;
 
-	return 0;
-
-err_remove_handlers:
-	if (vc4_hdmi->variant->external_irq_controller)
-		free_irq(platform_get_irq_byname(pdev, "cec-tx"), vc4_hdmi);
-	else
-		free_irq(platform_get_irq(pdev, 0), vc4_hdmi);
+	/*
+	 * NOTE: Strictly speaking, we should probably use a DRM-managed
+	 * registration there to avoid removing the CEC adapter by the
+	 * time the DRM driver doesn't have any user anymore.
+	 *
+	 * However, the CEC framework already cleans up the CEC adapter
+	 * only when the last user has closed its file descriptor, so we
+	 * don't need to handle it in DRM.
+	 *
+	 * By the time the device-managed hook is executed, we will give
+	 * up our reference to the CEC adapter and therefore don't
+	 * really care when it's actually freed.
+	 *
+	 * There's still a problematic sequence: if we unregister our
+	 * CEC adapter, but the userspace keeps a handle on the CEC
+	 * adapter but not the DRM device for some reason. In such a
+	 * case, our vc4_hdmi structure will be freed, but the
+	 * cec_adapter structure will have a dangling pointer to what
+	 * used to be our HDMI controller. If we get a CEC call at that
+	 * moment, we could end up with a use-after-free. Fortunately,
+	 * the CEC framework already handles this too, by calling
+	 * cec_is_registered() in cec_ioctl() and cec_poll().
+	 */
+	ret = devm_add_action_or_reset(dev, vc4_hdmi_cec_release, vc4_hdmi);
+	if (ret)
+		return ret;
 
-err_remove_cec_rx_handler:
-	if (vc4_hdmi->variant->external_irq_controller)
-		free_irq(platform_get_irq_byname(pdev, "cec-rx"), vc4_hdmi);
+	return 0;
 
 err_delete_cec_adap:
 	cec_delete_adapter(vc4_hdmi->cec_adap);
 
 	return ret;
 }
-
-static void vc4_hdmi_cec_exit(struct vc4_hdmi *vc4_hdmi)
-{
-	struct platform_device *pdev = vc4_hdmi->pdev;
-
-	if (vc4_hdmi->variant->external_irq_controller) {
-		free_irq(platform_get_irq_byname(pdev, "cec-rx"), vc4_hdmi);
-		free_irq(platform_get_irq_byname(pdev, "cec-tx"), vc4_hdmi);
-	} else {
-		free_irq(platform_get_irq(pdev, 0), vc4_hdmi);
-	}
-
-	cec_unregister_adapter(vc4_hdmi->cec_adap);
-}
 #else
 static int vc4_hdmi_cec_init(struct vc4_hdmi *vc4_hdmi)
 {
 	return 0;
 }
-
-static void vc4_hdmi_cec_exit(struct vc4_hdmi *vc4_hdmi) {};
 #endif
 
-static int vc4_hdmi_build_regset(struct vc4_hdmi *vc4_hdmi,
+static void vc4_hdmi_free_regset(struct drm_device *drm, void *ptr)
+{
+	struct debugfs_reg32 *regs = ptr;
+
+	kfree(regs);
+}
+
+static int vc4_hdmi_build_regset(struct drm_device *drm,
+				 struct vc4_hdmi *vc4_hdmi,
 				 struct debugfs_regset32 *regset,
 				 enum vc4_hdmi_regs reg)
 {
@@ -2649,6 +2993,7 @@ static int vc4_hdmi_build_regset(struct vc4_hdmi *vc4_hdmi,
 	struct debugfs_reg32 *regs, *new_regs;
 	unsigned int count = 0;
 	unsigned int i;
+	int ret;
 
 	regs = kcalloc(variant->num_registers, sizeof(*regs),
 		       GFP_KERNEL);
@@ -2674,10 +3019,15 @@ static int vc4_hdmi_build_regset(struct vc4_hdmi *vc4_hdmi,
 	regset->regs = new_regs;
 	regset->nregs = count;
 
+	ret = drmm_add_action_or_reset(drm, vc4_hdmi_free_regset, new_regs);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
-static int vc4_hdmi_init_resources(struct vc4_hdmi *vc4_hdmi)
+static int vc4_hdmi_init_resources(struct drm_device *drm,
+				   struct vc4_hdmi *vc4_hdmi)
 {
 	struct platform_device *pdev = vc4_hdmi->pdev;
 	struct device *dev = &pdev->dev;
@@ -2691,11 +3041,11 @@ static int vc4_hdmi_init_resources(struct vc4_hdmi *vc4_hdmi)
 	if (IS_ERR(vc4_hdmi->hd_regs))
 		return PTR_ERR(vc4_hdmi->hd_regs);
 
-	ret = vc4_hdmi_build_regset(vc4_hdmi, &vc4_hdmi->hd_regset, VC4_HD);
+	ret = vc4_hdmi_build_regset(drm, vc4_hdmi, &vc4_hdmi->hd_regset, VC4_HD);
 	if (ret)
 		return ret;
 
-	ret = vc4_hdmi_build_regset(vc4_hdmi, &vc4_hdmi->hdmi_regset, VC4_HDMI);
+	ret = vc4_hdmi_build_regset(drm, vc4_hdmi, &vc4_hdmi->hdmi_regset, VC4_HDMI);
 	if (ret)
 		return ret;
 
@@ -2718,7 +3068,8 @@ static int vc4_hdmi_init_resources(struct vc4_hdmi *vc4_hdmi)
 	return 0;
 }
 
-static int vc5_hdmi_init_resources(struct vc4_hdmi *vc4_hdmi)
+static int vc5_hdmi_init_resources(struct drm_device *drm,
+				   struct vc4_hdmi *vc4_hdmi)
 {
 	struct platform_device *pdev = vc4_hdmi->pdev;
 	struct device *dev = &pdev->dev;
@@ -2820,42 +3171,42 @@ static int vc5_hdmi_init_resources(struct vc4_hdmi *vc4_hdmi)
 		return PTR_ERR(vc4_hdmi->reset);
 	}
 
-	ret = vc4_hdmi_build_regset(vc4_hdmi, &vc4_hdmi->hdmi_regset, VC4_HDMI);
+	ret = vc4_hdmi_build_regset(drm, vc4_hdmi, &vc4_hdmi->hdmi_regset, VC4_HDMI);
 	if (ret)
 		return ret;
 
-	ret = vc4_hdmi_build_regset(vc4_hdmi, &vc4_hdmi->hd_regset, VC4_HD);
+	ret = vc4_hdmi_build_regset(drm, vc4_hdmi, &vc4_hdmi->hd_regset, VC4_HD);
 	if (ret)
 		return ret;
 
-	ret = vc4_hdmi_build_regset(vc4_hdmi, &vc4_hdmi->cec_regset, VC5_CEC);
+	ret = vc4_hdmi_build_regset(drm, vc4_hdmi, &vc4_hdmi->cec_regset, VC5_CEC);
 	if (ret)
 		return ret;
 
-	ret = vc4_hdmi_build_regset(vc4_hdmi, &vc4_hdmi->csc_regset, VC5_CSC);
+	ret = vc4_hdmi_build_regset(drm, vc4_hdmi, &vc4_hdmi->csc_regset, VC5_CSC);
 	if (ret)
 		return ret;
 
-	ret = vc4_hdmi_build_regset(vc4_hdmi, &vc4_hdmi->dvp_regset, VC5_DVP);
+	ret = vc4_hdmi_build_regset(drm, vc4_hdmi, &vc4_hdmi->dvp_regset, VC5_DVP);
 	if (ret)
 		return ret;
 
-	ret = vc4_hdmi_build_regset(vc4_hdmi, &vc4_hdmi->phy_regset, VC5_PHY);
+	ret = vc4_hdmi_build_regset(drm, vc4_hdmi, &vc4_hdmi->phy_regset, VC5_PHY);
 	if (ret)
 		return ret;
 
-	ret = vc4_hdmi_build_regset(vc4_hdmi, &vc4_hdmi->ram_regset, VC5_RAM);
+	ret = vc4_hdmi_build_regset(drm, vc4_hdmi, &vc4_hdmi->ram_regset, VC5_RAM);
 	if (ret)
 		return ret;
 
-	ret = vc4_hdmi_build_regset(vc4_hdmi, &vc4_hdmi->rm_regset, VC5_RM);
+	ret = vc4_hdmi_build_regset(drm, vc4_hdmi, &vc4_hdmi->rm_regset, VC5_RM);
 	if (ret)
 		return ret;
 
 	return 0;
 }
 
-static int __maybe_unused vc4_hdmi_runtime_suspend(struct device *dev)
+static int vc4_hdmi_runtime_suspend(struct device *dev)
 {
 	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
 
@@ -2898,6 +3249,13 @@ static int vc4_hdmi_runtime_resume(struct device *dev)
 	return 0;
 }
 
+static void vc4_hdmi_put_ddc_device(void *ptr)
+{
+	struct vc4_hdmi *vc4_hdmi = ptr;
+
+	put_device(&vc4_hdmi->ddc->dev);
+}
+
 static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 {
 	const struct vc4_hdmi_variant *variant = of_device_get_match_data(dev);
@@ -2908,10 +3266,14 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 	struct device_node *ddc_node;
 	int ret;
 
-	vc4_hdmi = devm_kzalloc(dev, sizeof(*vc4_hdmi), GFP_KERNEL);
+	vc4_hdmi = drmm_kzalloc(drm, sizeof(*vc4_hdmi), GFP_KERNEL);
 	if (!vc4_hdmi)
 		return -ENOMEM;
-	mutex_init(&vc4_hdmi->mutex);
+
+	ret = drmm_mutex_init(drm, &vc4_hdmi->mutex);
+	if (ret)
+		return ret;
+
 	spin_lock_init(&vc4_hdmi->hw_lock);
 	INIT_DELAYED_WORK(&vc4_hdmi->scrambling_work, vc4_hdmi_scrambling_wq);
 
@@ -2935,7 +3297,7 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 	if (variant->max_pixel_clock > HDMI_14_MAX_TMDS_CLK)
 		vc4_hdmi->scdc_enabled = true;
 
-	ret = variant->init_resources(vc4_hdmi);
+	ret = variant->init_resources(drm, vc4_hdmi);
 	if (ret)
 		return ret;
 
@@ -2952,13 +3314,16 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 		return -EPROBE_DEFER;
 	}
 
+	ret = devm_add_action_or_reset(dev, vc4_hdmi_put_ddc_device, vc4_hdmi);
+	if (ret)
+		return ret;
+
 	/* Only use the GPIO HPD pin if present in the DT, otherwise
 	 * we'll use the HDMI core's register.
 	 */
 	vc4_hdmi->hpd_gpio = devm_gpiod_get_optional(dev, "hpd", GPIOD_IN);
 	if (IS_ERR(vc4_hdmi->hpd_gpio)) {
-		ret = PTR_ERR(vc4_hdmi->hpd_gpio);
-		goto err_put_ddc;
+		return PTR_ERR(vc4_hdmi->hpd_gpio);
 	}
 
 	vc4_hdmi->disable_wifi_frequencies =
@@ -2972,17 +3337,17 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 			vc4_hdmi->disable_4kp60 = true;
 	}
 
+	ret = devm_pm_runtime_enable(dev);
+	if (ret)
+		return ret;
+
 	/*
-	 * We need to have the device powered up at this point to call
-	 * our reset hook and for the CEC init.
+	 *  We need to have the device powered up at this point to call
+	 *  our reset hook and for the CEC init.
 	 */
-	ret = vc4_hdmi_runtime_resume(dev);
+	ret = pm_runtime_resume_and_get(dev);
 	if (ret)
-		goto err_put_ddc;
-
-	pm_runtime_get_noresume(dev);
-	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
+		return ret;
 
 	if ((of_device_is_compatible(dev->of_node, "brcm,bcm2711-hdmi0") ||
 	     of_device_is_compatible(dev->of_node, "brcm,bcm2711-hdmi1")) &&
@@ -2992,92 +3357,43 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 		clk_prepare_enable(vc4_hdmi->pixel_bvb_clock);
 	}
 
-	drm_simple_encoder_init(drm, encoder, DRM_MODE_ENCODER_TMDS);
+	ret = drmm_encoder_init(drm, encoder,
+				&vc4_hdmi_encoder_funcs,
+				DRM_MODE_ENCODER_TMDS,
+				NULL);
+	if (ret)
+		goto err_put_runtime_pm;
+
 	drm_encoder_helper_add(encoder, &vc4_hdmi_encoder_helper_funcs);
 
 	ret = vc4_hdmi_connector_init(drm, vc4_hdmi);
 	if (ret)
-		goto err_destroy_encoder;
+		goto err_put_runtime_pm;
 
 	ret = vc4_hdmi_hotplug_init(vc4_hdmi);
 	if (ret)
-		goto err_destroy_conn;
+		goto err_put_runtime_pm;
 
 	ret = vc4_hdmi_cec_init(vc4_hdmi);
 	if (ret)
-		goto err_free_hotplug;
+		goto err_put_runtime_pm;
 
 	ret = vc4_hdmi_audio_init(vc4_hdmi);
 	if (ret)
-		goto err_free_cec;
-
-	vc4_debugfs_add_file(drm, variant->debugfs_name,
-			     vc4_hdmi_debugfs_regs,
-			     vc4_hdmi);
+		goto err_put_runtime_pm;
 
 	pm_runtime_put_sync(dev);
 
 	return 0;
 
-err_free_cec:
-	vc4_hdmi_cec_exit(vc4_hdmi);
-err_free_hotplug:
-	vc4_hdmi_hotplug_exit(vc4_hdmi);
-err_destroy_conn:
-	vc4_hdmi_connector_destroy(&vc4_hdmi->connector);
-err_destroy_encoder:
-	drm_encoder_cleanup(encoder);
+err_put_runtime_pm:
 	pm_runtime_put_sync(dev);
-	pm_runtime_disable(dev);
-err_put_ddc:
-	put_device(&vc4_hdmi->ddc->dev);
 
 	return ret;
 }
 
-static void vc4_hdmi_unbind(struct device *dev, struct device *master,
-			    void *data)
-{
-	struct vc4_hdmi *vc4_hdmi;
-
-	/*
-	 * ASoC makes it a bit hard to retrieve a pointer to the
-	 * vc4_hdmi structure. Registering the card will overwrite our
-	 * device drvdata with a pointer to the snd_soc_card structure,
-	 * which can then be used to retrieve whatever drvdata we want
-	 * to associate.
-	 *
-	 * However, that doesn't fly in the case where we wouldn't
-	 * register an ASoC card (because of an old DT that is missing
-	 * the dmas properties for example), then the card isn't
-	 * registered and the device drvdata wouldn't be set.
-	 *
-	 * We can deal with both cases by making sure a snd_soc_card
-	 * pointer and a vc4_hdmi structure are pointing to the same
-	 * memory address, so we can treat them indistinctly without any
-	 * issue.
-	 */
-	BUILD_BUG_ON(offsetof(struct vc4_hdmi_audio, card) != 0);
-	BUILD_BUG_ON(offsetof(struct vc4_hdmi, audio) != 0);
-	vc4_hdmi = dev_get_drvdata(dev);
-
-	kfree(vc4_hdmi->hdmi_regset.regs);
-	kfree(vc4_hdmi->hd_regset.regs);
-
-	vc4_hdmi_audio_exit(vc4_hdmi);
-	vc4_hdmi_cec_exit(vc4_hdmi);
-	vc4_hdmi_hotplug_exit(vc4_hdmi);
-	vc4_hdmi_connector_destroy(&vc4_hdmi->connector);
-	drm_encoder_cleanup(&vc4_hdmi->encoder.base);
-
-	pm_runtime_disable(dev);
-
-	put_device(&vc4_hdmi->ddc->dev);
-}
-
 static const struct component_ops vc4_hdmi_ops = {
 	.bind   = vc4_hdmi_bind,
-	.unbind = vc4_hdmi_unbind,
 };
 
 static int vc4_hdmi_dev_probe(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h
index c3ed2b07df23..99b0bc1297be 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.h
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.h
@@ -58,7 +58,8 @@ struct vc4_hdmi_variant {
 	/* Callback to get the resources (memory region, interrupts,
 	 * clocks, etc) for that variant.
 	 */
-	int (*init_resources)(struct vc4_hdmi *vc4_hdmi);
+	int (*init_resources)(struct drm_device *drm,
+			      struct vc4_hdmi *vc4_hdmi);
 
 	/* Callback to reset the HDMI block */
 	void (*reset)(struct vc4_hdmi *vc4_hdmi);
diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c
index fbaa741dda5f..9e823e0de197 100644
--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -25,6 +25,7 @@
 #include <linux/platform_device.h>
 
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_vblank.h>
 
 #include "vc4_drv.h"
@@ -66,11 +67,15 @@ static const struct debugfs_reg32 hvs_regs[] = {
 
 void vc4_hvs_dump_state(struct vc4_hvs *hvs)
 {
+	struct drm_device *drm = &hvs->vc4->base;
 	struct drm_printer p = drm_info_printer(&hvs->pdev->dev);
-	int i;
+	int idx, i;
 
 	drm_print_regset32(&p, &hvs->regset);
 
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
 	DRM_INFO("HVS ctx:\n");
 	for (i = 0; i < 64; i += 4) {
 		DRM_INFO("0x%08x (%s): 0x%08x 0x%08x 0x%08x 0x%08x\n",
@@ -80,6 +85,8 @@ void vc4_hvs_dump_state(struct vc4_hvs *hvs)
 			 readl((u32 __iomem *)hvs->dlist + i + 2),
 			 readl((u32 __iomem *)hvs->dlist + i + 3));
 	}
+
+	drm_dev_exit(idx);
 }
 
 static int vc4_hvs_debugfs_underrun(struct seq_file *m, void *data)
@@ -175,6 +182,11 @@ static int vc4_hvs_upload_linear_kernel(struct vc4_hvs *hvs,
 	int ret, i;
 	u32 __iomem *dst_kernel;
 
+	/*
+	 * NOTE: We don't need a call to drm_dev_enter()/drm_dev_exit()
+	 * here since that function is only called from vc4_hvs_bind().
+	 */
+
 	ret = drm_mm_insert_node(&hvs->dlist_mm, space, VC4_KERNEL_DWORDS);
 	if (ret) {
 		DRM_ERROR("Failed to allocate space for filter kernel: %d\n",
@@ -199,10 +211,15 @@ static int vc4_hvs_upload_linear_kernel(struct vc4_hvs *hvs,
 static void vc4_hvs_lut_load(struct vc4_hvs *hvs,
 			     struct vc4_crtc *vc4_crtc)
 {
+	struct drm_device *drm = &hvs->vc4->base;
 	struct drm_crtc *crtc = &vc4_crtc->base;
 	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
+	int idx;
 	u32 i;
 
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
 	/* The LUT memory is laid out with each HVS channel in order,
 	 * each of which takes 256 writes for R, 256 for G, then 256
 	 * for B.
@@ -217,6 +234,8 @@ static void vc4_hvs_lut_load(struct vc4_hvs *hvs,
 		HVS_WRITE(SCALER_GAMDATA, vc4_crtc->lut_g[i]);
 	for (i = 0; i < crtc->gamma_size; i++)
 		HVS_WRITE(SCALER_GAMDATA, vc4_crtc->lut_b[i]);
+
+	drm_dev_exit(idx);
 }
 
 static void vc4_hvs_update_gamma_lut(struct vc4_hvs *hvs,
@@ -238,7 +257,12 @@ static void vc4_hvs_update_gamma_lut(struct vc4_hvs *hvs,
 
 u8 vc4_hvs_get_fifo_frame_count(struct vc4_hvs *hvs, unsigned int fifo)
 {
+	struct drm_device *drm = &hvs->vc4->base;
 	u8 field = 0;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return 0;
 
 	switch (fifo) {
 	case 0:
@@ -255,6 +279,7 @@ u8 vc4_hvs_get_fifo_frame_count(struct vc4_hvs *hvs, unsigned int fifo)
 		break;
 	}
 
+	drm_dev_exit(idx);
 	return field;
 }
 
@@ -267,6 +292,12 @@ int vc4_hvs_get_fifo_from_output(struct vc4_hvs *hvs, unsigned int output)
 	if (!vc4->is_vc5)
 		return output;
 
+	/*
+	 * NOTE: We should probably use drm_dev_enter()/drm_dev_exit()
+	 * here, but this function is only used during the DRM device
+	 * initialization, so we should be fine.
+	 */
+
 	switch (output) {
 	case 0:
 		return 0;
@@ -315,12 +346,17 @@ static int vc4_hvs_init_channel(struct vc4_hvs *hvs, struct drm_crtc *crtc,
 				struct drm_display_mode *mode, bool oneshot)
 {
 	struct vc4_dev *vc4 = hvs->vc4;
+	struct drm_device *drm = &vc4->base;
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
 	struct vc4_crtc_state *vc4_crtc_state = to_vc4_crtc_state(crtc->state);
 	unsigned int chan = vc4_crtc_state->assigned_channel;
 	bool interlace = mode->flags & DRM_MODE_FLAG_INTERLACE;
 	u32 dispbkgndx;
 	u32 dispctrl;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return -ENODEV;
 
 	HVS_WRITE(SCALER_DISPCTRLX(chan), 0);
 	HVS_WRITE(SCALER_DISPCTRLX(chan), SCALER_DISPCTRLX_RESET);
@@ -362,14 +398,22 @@ static int vc4_hvs_init_channel(struct vc4_hvs *hvs, struct drm_crtc *crtc,
 	 */
 	vc4_hvs_lut_load(hvs, vc4_crtc);
 
+	drm_dev_exit(idx);
+
 	return 0;
 }
 
 void vc4_hvs_stop_channel(struct vc4_hvs *hvs, unsigned int chan)
 {
-	if (HVS_READ(SCALER_DISPCTRLX(chan)) & SCALER_DISPCTRLX_ENABLE)
+	struct drm_device *drm = &hvs->vc4->base;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
 		return;
 
+	if (HVS_READ(SCALER_DISPCTRLX(chan)) & SCALER_DISPCTRLX_ENABLE)
+		goto out;
+
 	HVS_WRITE(SCALER_DISPCTRLX(chan),
 		  HVS_READ(SCALER_DISPCTRLX(chan)) | SCALER_DISPCTRLX_RESET);
 	HVS_WRITE(SCALER_DISPCTRLX(chan),
@@ -385,6 +429,9 @@ void vc4_hvs_stop_channel(struct vc4_hvs *hvs, unsigned int chan)
 	WARN_ON_ONCE((HVS_READ(SCALER_DISPSTATX(chan)) &
 		      (SCALER_DISPSTATX_FULL | SCALER_DISPSTATX_EMPTY)) !=
 		     SCALER_DISPSTATX_EMPTY);
+
+out:
+	drm_dev_exit(idx);
 }
 
 int vc4_hvs_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state)
@@ -426,9 +473,15 @@ static void vc4_hvs_install_dlist(struct drm_crtc *crtc)
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_hvs *hvs = vc4->hvs;
 	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
+	int idx;
+
+	if (!drm_dev_enter(dev, &idx))
+		return;
 
 	HVS_WRITE(SCALER_DISPLISTX(vc4_state->assigned_channel),
 		  vc4_state->mm.start);
+
+	drm_dev_exit(idx);
 }
 
 static void vc4_hvs_update_dlist(struct drm_crtc *crtc)
@@ -513,6 +566,12 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc,
 	bool enable_bg_fill = false;
 	u32 __iomem *dlist_start = vc4->hvs->dlist + vc4_state->mm.start;
 	u32 __iomem *dlist_next = dlist_start;
+	int idx;
+
+	if (!drm_dev_enter(dev, &idx)) {
+		vc4_crtc_send_vblank(crtc);
+		return;
+	}
 
 	if (debug_dump_regs) {
 		DRM_INFO("CRTC %d HVS before:\n", drm_crtc_index(crtc));
@@ -583,26 +642,44 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc,
 		DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc));
 		vc4_hvs_dump_state(hvs);
 	}
+
+	drm_dev_exit(idx);
 }
 
 void vc4_hvs_mask_underrun(struct vc4_hvs *hvs, int channel)
 {
-	u32 dispctrl = HVS_READ(SCALER_DISPCTRL);
+	struct drm_device *drm = &hvs->vc4->base;
+	u32 dispctrl;
+	int idx;
 
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
+	dispctrl = HVS_READ(SCALER_DISPCTRL);
 	dispctrl &= ~SCALER_DISPCTRL_DSPEISLUR(channel);
 
 	HVS_WRITE(SCALER_DISPCTRL, dispctrl);
+
+	drm_dev_exit(idx);
 }
 
 void vc4_hvs_unmask_underrun(struct vc4_hvs *hvs, int channel)
 {
-	u32 dispctrl = HVS_READ(SCALER_DISPCTRL);
+	struct drm_device *drm = &hvs->vc4->base;
+	u32 dispctrl;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
 
+	dispctrl = HVS_READ(SCALER_DISPCTRL);
 	dispctrl |= SCALER_DISPCTRL_DSPEISLUR(channel);
 
 	HVS_WRITE(SCALER_DISPSTAT,
 		  SCALER_DISPSTAT_EUFLOW(channel));
 	HVS_WRITE(SCALER_DISPCTRL, dispctrl);
+
+	drm_dev_exit(idx);
 }
 
 static void vc4_hvs_report_underrun(struct drm_device *dev)
@@ -623,6 +700,17 @@ static irqreturn_t vc4_hvs_irq_handler(int irq, void *data)
 	u32 control;
 	u32 status;
 
+	/*
+	 * NOTE: We don't need to protect the register access using
+	 * drm_dev_enter() there because the interrupt handler lifetime
+	 * is tied to the device itself, and not to the DRM device.
+	 *
+	 * So when the device will be gone, one of the first thing we
+	 * will be doing will be to unregister the interrupt handler,
+	 * and then unregister the DRM device. drm_dev_enter() would
+	 * thus always succeed if we are here.
+	 */
+
 	status = HVS_READ(SCALER_DISPSTAT);
 	control = HVS_READ(SCALER_DISPCTRL);
 
@@ -645,6 +733,39 @@ static irqreturn_t vc4_hvs_irq_handler(int irq, void *data)
 	return irqret;
 }
 
+int vc4_hvs_debugfs_init(struct drm_minor *minor)
+{
+	struct drm_device *drm = minor->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
+	struct vc4_hvs *hvs = vc4->hvs;
+	int ret;
+
+	if (!vc4->hvs)
+		return -ENODEV;
+
+	if (!vc4->is_vc5)
+		debugfs_create_bool("hvs_load_tracker", S_IRUGO | S_IWUSR,
+				    minor->debugfs_root,
+				    &vc4->load_tracker_enabled);
+
+	ret = vc4_debugfs_add_file(minor, "hvs_dlists",
+				   vc4_hvs_debugfs_dlist, NULL);
+	if (ret)
+		return ret;
+
+	ret = vc4_debugfs_add_file(minor, "hvs_underrun",
+				   vc4_hvs_debugfs_underrun, NULL);
+	if (ret)
+		return ret;
+
+	ret = vc4_debugfs_add_regset32(minor, "hvs_regs",
+				       &hvs->regset);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -655,10 +776,9 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 	u32 dispctrl;
 	u32 reg;
 
-	hvs = devm_kzalloc(&pdev->dev, sizeof(*hvs), GFP_KERNEL);
+	hvs = drmm_kzalloc(drm, sizeof(*hvs), GFP_KERNEL);
 	if (!hvs)
 		return -ENOMEM;
-
 	hvs->vc4 = vc4;
 	hvs->pdev = pdev;
 
@@ -771,12 +891,6 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 	if (ret)
 		return ret;
 
-	vc4_debugfs_add_regset32(drm, "hvs_regs", &hvs->regset);
-	vc4_debugfs_add_file(drm, "hvs_underrun", vc4_hvs_debugfs_underrun,
-			     NULL);
-	vc4_debugfs_add_file(drm, "hvs_dlists", vc4_hvs_debugfs_dlist,
-			     NULL);
-
 	return 0;
 }
 
@@ -786,11 +900,18 @@ static void vc4_hvs_unbind(struct device *dev, struct device *master,
 	struct drm_device *drm = dev_get_drvdata(master);
 	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_hvs *hvs = vc4->hvs;
+	struct drm_mm_node *node, *next;
 
 	if (drm_mm_node_allocated(&vc4->hvs->mitchell_netravali_filter))
 		drm_mm_remove_node(&vc4->hvs->mitchell_netravali_filter);
 
+	drm_mm_for_each_node_safe(node, next, &vc4->hvs->dlist_mm)
+		drm_mm_remove_node(node);
+
 	drm_mm_takedown(&vc4->hvs->dlist_mm);
+
+	drm_mm_for_each_node_safe(node, next, &vc4->hvs->lbm_mm)
+		drm_mm_remove_node(node);
 	drm_mm_takedown(&vc4->hvs->lbm_mm);
 
 	clk_disable_unprepare(hvs->core_clk);
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index 2eacfb6773d2..1e6db0121ccd 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -105,7 +105,7 @@ vc4_overflow_mem_work(struct work_struct *work)
 	}
 	vc4->bin_alloc_overflow = BIT(bin_bo_slot);
 
-	V3D_WRITE(V3D_BPOA, bo->base.paddr + bin_bo_slot * vc4->bin_alloc_size);
+	V3D_WRITE(V3D_BPOA, bo->base.dma_addr + bin_bo_slot * vc4->bin_alloc_size);
 	V3D_WRITE(V3D_BPOS, bo->base.base.size);
 	V3D_WRITE(V3D_INTCTL, V3D_INT_OUTOMEM);
 	V3D_WRITE(V3D_INTENA, V3D_INT_OUTOMEM);
@@ -295,7 +295,7 @@ vc4_irq_disable(struct drm_device *dev)
 	V3D_WRITE(V3D_INTCTL, V3D_DRIVER_IRQS);
 
 	/* Finish any interrupt handler still in flight. */
-	disable_irq(vc4->irq);
+	synchronize_irq(vc4->irq);
 
 	cancel_work_sync(&vc4->overflow_mem_work);
 }
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index b45dcdfd7306..4419e810103d 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -18,7 +18,6 @@
 #include <drm/drm_crtc.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_plane_helper.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
 
diff --git a/drivers/gpu/drm/vc4/vc4_perfmon.c b/drivers/gpu/drm/vc4/vc4_perfmon.c
index 79a74184d732..c4ac2c946238 100644
--- a/drivers/gpu/drm/vc4/vc4_perfmon.c
+++ b/drivers/gpu/drm/vc4/vc4_perfmon.c
@@ -133,6 +133,7 @@ void vc4_perfmon_close_file(struct vc4_file *vc4file)
 	idr_for_each(&vc4file->perfmon.idr, vc4_perfmon_idr_del, NULL);
 	idr_destroy(&vc4file->perfmon.idr);
 	mutex_unlock(&vc4file->perfmon.lock);
+	mutex_destroy(&vc4file->perfmon.lock);
 }
 
 int vc4_perfmon_create_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index f27e87a23df7..eff9c63adfa7 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -19,11 +19,10 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_atomic_uapi.h>
 #include <drm/drm_blend.h>
-#include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_fb_dma_helper.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_gem_atomic_helper.h>
-#include <drm/drm_plane_helper.h>
 
 #include "uapi/drm/vc4_drm.h"
 
@@ -340,7 +339,7 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state)
 {
 	struct vc4_plane_state *vc4_state = to_vc4_plane_state(state);
 	struct drm_framebuffer *fb = state->fb;
-	struct drm_gem_cma_object *bo = drm_fb_cma_get_gem_obj(fb, 0);
+	struct drm_gem_dma_object *bo = drm_fb_dma_get_gem_obj(fb, 0);
 	int num_planes = fb->format->num_planes;
 	struct drm_crtc_state *crtc_state;
 	u32 h_subsample = fb->format->hsub;
@@ -360,7 +359,7 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state)
 		return ret;
 
 	for (i = 0; i < num_planes; i++)
-		vc4_state->offsets[i] = bo->paddr + fb->offsets[i];
+		vc4_state->offsets[i] = bo->dma_addr + fb->offsets[i];
 
 	/*
 	 * We don't support subpixel source positioning for scaling,
@@ -1244,14 +1243,14 @@ u32 vc4_plane_dlist_size(const struct drm_plane_state *state)
 void vc4_plane_async_set_fb(struct drm_plane *plane, struct drm_framebuffer *fb)
 {
 	struct vc4_plane_state *vc4_state = to_vc4_plane_state(plane->state);
-	struct drm_gem_cma_object *bo = drm_fb_cma_get_gem_obj(fb, 0);
+	struct drm_gem_dma_object *bo = drm_fb_dma_get_gem_obj(fb, 0);
 	uint32_t addr;
 
 	/* We're skipping the address adjustment for negative origin,
 	 * because this is only called on the primary plane.
 	 */
 	WARN_ON_ONCE(plane->state->crtc_x < 0 || plane->state->crtc_y < 0);
-	addr = bo->paddr + fb->offsets[0];
+	addr = bo->dma_addr + fb->offsets[0];
 
 	/* Write the new address into the hardware immediately.  The
 	 * scanout will start from this address as soon as the FIFO
@@ -1388,7 +1387,7 @@ static int vc4_prepare_fb(struct drm_plane *plane,
 	if (!state->fb)
 		return 0;
 
-	bo = to_vc4_bo(&drm_fb_cma_get_gem_obj(state->fb, 0)->base);
+	bo = to_vc4_bo(&drm_fb_dma_get_gem_obj(state->fb, 0)->base);
 
 	drm_gem_plane_helper_prepare_fb(plane, state);
 
@@ -1406,7 +1405,7 @@ static void vc4_cleanup_fb(struct drm_plane *plane,
 	if (plane->state->fb == state->fb || !state->fb)
 		return;
 
-	bo = to_vc4_bo(&drm_fb_cma_get_gem_obj(state->fb, 0)->base);
+	bo = to_vc4_bo(&drm_fb_dma_get_gem_obj(state->fb, 0)->base);
 	vc4_bo_dec_usecnt(bo);
 }
 
@@ -1483,8 +1482,6 @@ static bool vc4_format_mod_supported(struct drm_plane *plane,
 static const struct drm_plane_funcs vc4_plane_funcs = {
 	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
-	.destroy = drm_plane_cleanup,
-	.set_property = NULL,
 	.reset = vc4_plane_reset,
 	.atomic_duplicate_state = vc4_plane_duplicate_state,
 	.atomic_destroy_state = vc4_plane_destroy_state,
@@ -1492,14 +1489,14 @@ static const struct drm_plane_funcs vc4_plane_funcs = {
 };
 
 struct drm_plane *vc4_plane_init(struct drm_device *dev,
-				 enum drm_plane_type type)
+				 enum drm_plane_type type,
+				 uint32_t possible_crtcs)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
-	struct drm_plane *plane = NULL;
+	struct drm_plane *plane;
 	struct vc4_plane *vc4_plane;
 	u32 formats[ARRAY_SIZE(hvs_formats)];
 	int num_formats = 0;
-	int ret = 0;
 	unsigned i;
 	static const uint64_t modifiers[] = {
 		DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED,
@@ -1510,11 +1507,6 @@ struct drm_plane *vc4_plane_init(struct drm_device *dev,
 		DRM_FORMAT_MOD_INVALID
 	};
 
-	vc4_plane = devm_kzalloc(dev->dev, sizeof(*vc4_plane),
-				 GFP_KERNEL);
-	if (!vc4_plane)
-		return ERR_PTR(-ENOMEM);
-
 	for (i = 0; i < ARRAY_SIZE(hvs_formats); i++) {
 		if (!hvs_formats[i].hvs5_only || vc4->is_vc5) {
 			formats[num_formats] = hvs_formats[i].drm;
@@ -1522,13 +1514,14 @@ struct drm_plane *vc4_plane_init(struct drm_device *dev,
 		}
 	}
 
+	vc4_plane = drmm_universal_plane_alloc(dev, struct vc4_plane, base,
+					       possible_crtcs,
+					       &vc4_plane_funcs,
+					       formats, num_formats,
+					       modifiers, type, NULL);
+	if (IS_ERR(vc4_plane))
+		return ERR_CAST(vc4_plane);
 	plane = &vc4_plane->base;
-	ret = drm_universal_plane_init(dev, plane, 0,
-				       &vc4_plane_funcs,
-				       formats, num_formats,
-				       modifiers, type, NULL);
-	if (ret)
-		return ERR_PTR(ret);
 
 	if (vc4->is_vc5)
 		drm_plane_helper_add(plane, &vc5_plane_helper_funcs);
@@ -1575,13 +1568,11 @@ int vc4_plane_create_additional_planes(struct drm_device *drm)
 	 */
 	for (i = 0; i < 16; i++) {
 		struct drm_plane *plane =
-			vc4_plane_init(drm, DRM_PLANE_TYPE_OVERLAY);
+			vc4_plane_init(drm, DRM_PLANE_TYPE_OVERLAY,
+				       GENMASK(drm->mode_config.num_crtc - 1, 0));
 
 		if (IS_ERR(plane))
 			continue;
-
-		plane->possible_crtcs =
-			GENMASK(drm->mode_config.num_crtc - 1, 0);
 	}
 
 	drm_for_each_crtc(crtc, drm) {
@@ -1589,9 +1580,9 @@ int vc4_plane_create_additional_planes(struct drm_device *drm)
 		 * since we overlay planes on the CRTC in the order they were
 		 * initialized.
 		 */
-		cursor_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_CURSOR);
+		cursor_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_CURSOR,
+					      drm_crtc_mask(crtc));
 		if (!IS_ERR(cursor_plane)) {
-			cursor_plane->possible_crtcs = drm_crtc_mask(crtc);
 			crtc->cursor = cursor_plane;
 		}
 	}
diff --git a/drivers/gpu/drm/vc4/vc4_render_cl.c b/drivers/gpu/drm/vc4/vc4_render_cl.c
index f6b7dc3df08c..1bda5010f15a 100644
--- a/drivers/gpu/drm/vc4/vc4_render_cl.c
+++ b/drivers/gpu/drm/vc4/vc4_render_cl.c
@@ -40,14 +40,14 @@
 #include "vc4_packet.h"
 
 struct vc4_rcl_setup {
-	struct drm_gem_cma_object *color_read;
-	struct drm_gem_cma_object *color_write;
-	struct drm_gem_cma_object *zs_read;
-	struct drm_gem_cma_object *zs_write;
-	struct drm_gem_cma_object *msaa_color_write;
-	struct drm_gem_cma_object *msaa_zs_write;
-
-	struct drm_gem_cma_object *rcl;
+	struct drm_gem_dma_object *color_read;
+	struct drm_gem_dma_object *color_write;
+	struct drm_gem_dma_object *zs_read;
+	struct drm_gem_dma_object *zs_write;
+	struct drm_gem_dma_object *msaa_color_write;
+	struct drm_gem_dma_object *msaa_zs_write;
+
+	struct drm_gem_dma_object *rcl;
 	u32 next_offset;
 
 	u32 next_write_bo_index;
@@ -97,11 +97,11 @@ static void vc4_store_before_load(struct vc4_rcl_setup *setup)
  * coordinates packet, and instead just store to the address given.
  */
 static uint32_t vc4_full_res_offset(struct vc4_exec_info *exec,
-				    struct drm_gem_cma_object *bo,
+				    struct drm_gem_dma_object *bo,
 				    struct drm_vc4_submit_rcl_surface *surf,
 				    uint8_t x, uint8_t y)
 {
-	return bo->paddr + surf->offset + VC4_TILE_BUFFER_SIZE *
+	return bo->dma_addr + surf->offset + VC4_TILE_BUFFER_SIZE *
 		(DIV_ROUND_UP(exec->args->width, 32) * y + x);
 }
 
@@ -142,7 +142,7 @@ static void emit_tile(struct vc4_exec_info *exec,
 		} else {
 			rcl_u8(setup, VC4_PACKET_LOAD_TILE_BUFFER_GENERAL);
 			rcl_u16(setup, args->color_read.bits);
-			rcl_u32(setup, setup->color_read->paddr +
+			rcl_u32(setup, setup->color_read->dma_addr +
 				args->color_read.offset);
 		}
 	}
@@ -164,7 +164,7 @@ static void emit_tile(struct vc4_exec_info *exec,
 		} else {
 			rcl_u8(setup, VC4_PACKET_LOAD_TILE_BUFFER_GENERAL);
 			rcl_u16(setup, args->zs_read.bits);
-			rcl_u32(setup, setup->zs_read->paddr +
+			rcl_u32(setup, setup->zs_read->dma_addr +
 				args->zs_read.offset);
 		}
 	}
@@ -232,7 +232,7 @@ static void emit_tile(struct vc4_exec_info *exec,
 			(last_tile_write ?
 			 0 : VC4_STORE_TILE_BUFFER_DISABLE_COLOR_CLEAR));
 		rcl_u32(setup,
-			(setup->zs_write->paddr + args->zs_write.offset) |
+			(setup->zs_write->dma_addr + args->zs_write.offset) |
 			((last && last_tile_write) ?
 			 VC4_LOADSTORE_TILE_BUFFER_EOF : 0));
 	}
@@ -355,7 +355,7 @@ static int vc4_create_rcl_bo(struct drm_device *dev, struct vc4_exec_info *exec,
 
 	rcl_u8(setup, VC4_PACKET_TILE_RENDERING_MODE_CONFIG);
 	rcl_u32(setup,
-		(setup->color_write ? (setup->color_write->paddr +
+		(setup->color_write ? (setup->color_write->dma_addr +
 				       args->color_write.offset) :
 		 0));
 	rcl_u16(setup, args->width);
@@ -374,14 +374,14 @@ static int vc4_create_rcl_bo(struct drm_device *dev, struct vc4_exec_info *exec,
 	}
 
 	BUG_ON(setup->next_offset != size);
-	exec->ct1ca = setup->rcl->paddr;
-	exec->ct1ea = setup->rcl->paddr + setup->next_offset;
+	exec->ct1ca = setup->rcl->dma_addr;
+	exec->ct1ea = setup->rcl->dma_addr + setup->next_offset;
 
 	return 0;
 }
 
 static int vc4_full_res_bounds_check(struct vc4_exec_info *exec,
-				     struct drm_gem_cma_object *obj,
+				     struct drm_gem_dma_object *obj,
 				     struct drm_vc4_submit_rcl_surface *surf)
 {
 	struct drm_vc4_submit_cl *args = exec->args;
@@ -407,7 +407,7 @@ static int vc4_full_res_bounds_check(struct vc4_exec_info *exec,
 }
 
 static int vc4_rcl_msaa_surface_setup(struct vc4_exec_info *exec,
-				      struct drm_gem_cma_object **obj,
+				      struct drm_gem_dma_object **obj,
 				      struct drm_vc4_submit_rcl_surface *surf)
 {
 	if (surf->flags != 0 || surf->bits != 0) {
@@ -433,7 +433,7 @@ static int vc4_rcl_msaa_surface_setup(struct vc4_exec_info *exec,
 }
 
 static int vc4_rcl_surface_setup(struct vc4_exec_info *exec,
-				 struct drm_gem_cma_object **obj,
+				 struct drm_gem_dma_object **obj,
 				 struct drm_vc4_submit_rcl_surface *surf,
 				 bool is_write)
 {
@@ -533,7 +533,7 @@ static int vc4_rcl_surface_setup(struct vc4_exec_info *exec,
 static int
 vc4_rcl_render_config_surface_setup(struct vc4_exec_info *exec,
 				    struct vc4_rcl_setup *setup,
-				    struct drm_gem_cma_object **obj,
+				    struct drm_gem_dma_object **obj,
 				    struct drm_vc4_submit_rcl_surface *surf)
 {
 	uint8_t tiling = VC4_GET_FIELD(surf->bits,
diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c
index d20b0bc51a18..bd181b5a7b52 100644
--- a/drivers/gpu/drm/vc4/vc4_txp.c
+++ b/drivers/gpu/drm/vc4/vc4_txp.c
@@ -15,8 +15,9 @@
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_edid.h>
-#include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_fb_dma_helper.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_panel.h>
@@ -155,7 +156,6 @@ struct vc4_txp {
 	struct drm_writeback_connector connector;
 
 	void __iomem *regs;
-	struct debugfs_regset32 regset;
 };
 
 static inline struct vc4_txp *encoder_to_vc4_txp(struct drm_encoder *encoder)
@@ -276,13 +276,15 @@ static int vc4_txp_connector_atomic_check(struct drm_connector *conn,
 static void vc4_txp_connector_atomic_commit(struct drm_connector *conn,
 					struct drm_atomic_state *state)
 {
+	struct drm_device *drm = conn->dev;
 	struct drm_connector_state *conn_state = drm_atomic_get_new_connector_state(state,
 										    conn);
 	struct vc4_txp *txp = connector_to_vc4_txp(conn);
-	struct drm_gem_cma_object *gem;
+	struct drm_gem_dma_object *gem;
 	struct drm_display_mode *mode;
 	struct drm_framebuffer *fb;
 	u32 ctrl;
+	int idx;
 	int i;
 
 	if (WARN_ON(!conn_state->writeback_job))
@@ -312,8 +314,11 @@ static void vc4_txp_connector_atomic_commit(struct drm_connector *conn,
 		 */
 		ctrl |= TXP_ALPHA_INVERT;
 
-	gem = drm_fb_cma_get_gem_obj(fb, 0);
-	TXP_WRITE(TXP_DST_PTR, gem->paddr + fb->offsets[0]);
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
+	gem = drm_fb_dma_get_gem_obj(fb, 0);
+	TXP_WRITE(TXP_DST_PTR, gem->dma_addr + fb->offsets[0]);
 	TXP_WRITE(TXP_DST_PITCH, fb->pitches[0]);
 	TXP_WRITE(TXP_DIM,
 		  VC4_SET_FIELD(mode->hdisplay, TXP_WIDTH) |
@@ -322,6 +327,8 @@ static void vc4_txp_connector_atomic_commit(struct drm_connector *conn,
 	TXP_WRITE(TXP_DST_CTRL, ctrl);
 
 	drm_writeback_queue_job(&txp->connector, conn_state);
+
+	drm_dev_exit(idx);
 }
 
 static const struct drm_connector_helper_funcs vc4_txp_connector_helper_funcs = {
@@ -337,16 +344,10 @@ vc4_txp_connector_detect(struct drm_connector *connector, bool force)
 	return connector_status_connected;
 }
 
-static void vc4_txp_connector_destroy(struct drm_connector *connector)
-{
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-}
-
 static const struct drm_connector_funcs vc4_txp_connector_funcs = {
 	.detect = vc4_txp_connector_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = vc4_txp_connector_destroy,
+	.destroy = drm_connector_cleanup,
 	.reset = drm_atomic_helper_connector_reset,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
@@ -354,7 +355,12 @@ static const struct drm_connector_funcs vc4_txp_connector_funcs = {
 
 static void vc4_txp_encoder_disable(struct drm_encoder *encoder)
 {
+	struct drm_device *drm = encoder->dev;
 	struct vc4_txp *txp = encoder_to_vc4_txp(encoder);
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
 
 	if (TXP_READ(TXP_DST_CTRL) & TXP_BUSY) {
 		unsigned long timeout = jiffies + msecs_to_jiffies(1000);
@@ -369,6 +375,8 @@ static void vc4_txp_encoder_disable(struct drm_encoder *encoder)
 	}
 
 	TXP_WRITE(TXP_DST_CTRL, TXP_POWERDOWN);
+
+	drm_dev_exit(idx);
 }
 
 static const struct drm_encoder_helper_funcs vc4_txp_encoder_helper_funcs = {
@@ -384,13 +392,13 @@ static void vc4_txp_disable_vblank(struct drm_crtc *crtc) {}
 
 static const struct drm_crtc_funcs vc4_txp_crtc_funcs = {
 	.set_config		= drm_atomic_helper_set_config,
-	.destroy		= vc4_crtc_destroy,
 	.page_flip		= vc4_page_flip,
 	.reset			= vc4_crtc_reset,
 	.atomic_duplicate_state	= vc4_crtc_duplicate_state,
 	.atomic_destroy_state	= vc4_crtc_destroy_state,
 	.enable_vblank		= vc4_txp_enable_vblank,
 	.disable_vblank		= vc4_txp_disable_vblank,
+	.late_register		= vc4_crtc_late_register,
 };
 
 static int vc4_txp_atomic_check(struct drm_crtc *crtc,
@@ -453,6 +461,16 @@ static irqreturn_t vc4_txp_interrupt(int irq, void *data)
 	struct vc4_txp *txp = data;
 	struct vc4_crtc *vc4_crtc = &txp->base;
 
+	/*
+	 * We don't need to protect the register access using
+	 * drm_dev_enter() there because the interrupt handler lifetime
+	 * is tied to the device itself, and not to the DRM device.
+	 *
+	 * So when the device will be gone, one of the first thing we
+	 * will be doing will be to unregister the interrupt handler,
+	 * and then unregister the DRM device. drm_dev_enter() would
+	 * thus always succeed if we are here.
+	 */
 	TXP_WRITE(TXP_DST_CTRL, TXP_READ(TXP_DST_CTRL) & ~TXP_EI);
 	vc4_crtc_handle_vblank(vc4_crtc);
 	drm_writeback_signal_completion(&txp->connector, 0);
@@ -461,6 +479,7 @@ static irqreturn_t vc4_txp_interrupt(int irq, void *data)
 }
 
 static const struct vc4_crtc_data vc4_txp_crtc_data = {
+	.debugfs_name = "txp_regs",
 	.hvs_available_channels = BIT(2),
 	.hvs_output = 2,
 };
@@ -469,7 +488,6 @@ static int vc4_txp_bind(struct device *dev, struct device *master, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct drm_device *drm = dev_get_drvdata(master);
-	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_crtc *vc4_crtc;
 	struct vc4_txp *txp;
 	struct drm_crtc *crtc;
@@ -480,7 +498,7 @@ static int vc4_txp_bind(struct device *dev, struct device *master, void *data)
 	if (irq < 0)
 		return irq;
 
-	txp = devm_kzalloc(dev, sizeof(*txp), GFP_KERNEL);
+	txp = drmm_kzalloc(drm, sizeof(*txp), GFP_KERNEL);
 	if (!txp)
 		return -ENOMEM;
 	vc4_crtc = &txp->base;
@@ -495,9 +513,9 @@ static int vc4_txp_bind(struct device *dev, struct device *master, void *data)
 	txp->regs = vc4_ioremap_regs(pdev, 0);
 	if (IS_ERR(txp->regs))
 		return PTR_ERR(txp->regs);
-	txp->regset.base = txp->regs;
-	txp->regset.regs = txp_regs;
-	txp->regset.nregs = ARRAY_SIZE(txp_regs);
+	vc4_crtc->regset.base = txp->regs;
+	vc4_crtc->regset.regs = txp_regs;
+	vc4_crtc->regset.nregs = ARRAY_SIZE(txp_regs);
 
 	drm_connector_helper_add(&txp->connector.base,
 				 &vc4_txp_connector_helper_funcs);
@@ -523,9 +541,6 @@ static int vc4_txp_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 
 	dev_set_drvdata(dev, txp);
-	vc4->txp = txp;
-
-	vc4_debugfs_add_regset32(drm, "txp_regs", &txp->regset);
 
 	return 0;
 }
@@ -533,13 +548,9 @@ static int vc4_txp_bind(struct device *dev, struct device *master, void *data)
 static void vc4_txp_unbind(struct device *dev, struct device *master,
 			   void *data)
 {
-	struct drm_device *drm = dev_get_drvdata(master);
-	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_txp *txp = dev_get_drvdata(dev);
 
-	vc4_txp_connector_destroy(&txp->connector.base);
-
-	vc4->txp = NULL;
+	drm_connector_cleanup(&txp->connector.base);
 }
 
 static const struct component_ops vc4_txp_ops = {
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index cc714dcfe1f2..56abb0d6bc39 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -231,7 +231,7 @@ try_again:
  * if it doesn't fit within the buffer that we allocated up front.
  * However, it turns out that 16MB is "enough for anybody", and
  * real-world applications run into allocation failures from the
- * overall CMA pool before they make scenes complicated enough to run
+ * overall DMA pool before they make scenes complicated enough to run
  * out of bin space.
  */
 static int bin_bo_alloc(struct vc4_dev *vc4)
@@ -261,15 +261,15 @@ static int bin_bo_alloc(struct vc4_dev *vc4)
 
 			dev_err(&v3d->pdev->dev,
 				"Failed to allocate memory for tile binning: "
-				"%d. You may need to enable CMA or give it "
+				"%d. You may need to enable DMA or give it "
 				"more memory.",
 				ret);
 			break;
 		}
 
 		/* Check if this BO won't trigger the addressing bug. */
-		if ((bo->base.paddr & 0xf0000000) ==
-		    ((bo->base.paddr + bo->base.base.size - 1) & 0xf0000000)) {
+		if ((bo->base.dma_addr & 0xf0000000) ==
+		    ((bo->base.dma_addr + bo->base.base.size - 1) & 0xf0000000)) {
 			vc4->bin_bo = bo;
 
 			/* Set up for allocating 512KB chunks of
@@ -393,14 +393,34 @@ static int vc4_v3d_runtime_resume(struct device *dev)
 
 	vc4_v3d_init_hw(&vc4->base);
 
-	/* We disabled the IRQ as part of vc4_irq_uninstall in suspend. */
-	enable_irq(vc4->irq);
 	vc4_irq_enable(&vc4->base);
 
 	return 0;
 }
 #endif
 
+int vc4_v3d_debugfs_init(struct drm_minor *minor)
+{
+	struct drm_device *drm = minor->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
+	struct vc4_v3d *v3d = vc4->v3d;
+	int ret;
+
+	if (!vc4->v3d)
+		return -ENODEV;
+
+	ret = vc4_debugfs_add_file(minor, "v3d_ident",
+				   vc4_v3d_debugfs_ident, NULL);
+	if (ret)
+		return ret;
+
+	ret = vc4_debugfs_add_regset32(minor, "v3d_regs", &v3d->regset);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -443,44 +463,47 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 		}
 	}
 
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		return ret;
+	vc4->irq = ret;
+
+	ret = devm_pm_runtime_enable(dev);
+	if (ret)
+		return ret;
+
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret)
+		return ret;
+
 	if (V3D_READ(V3D_IDENT0) != V3D_EXPECTED_IDENT0) {
 		DRM_ERROR("V3D_IDENT0 read 0x%08x instead of 0x%08x\n",
 			  V3D_READ(V3D_IDENT0), V3D_EXPECTED_IDENT0);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_put_runtime_pm;
 	}
 
-	ret = clk_prepare_enable(v3d->clk);
-	if (ret != 0)
-		return ret;
-
 	/* Reset the binner overflow address/size at setup, to be sure
 	 * we don't reuse an old one.
 	 */
 	V3D_WRITE(V3D_BPOA, 0);
 	V3D_WRITE(V3D_BPOS, 0);
 
-	vc4_v3d_init_hw(drm);
-
-	ret = platform_get_irq(pdev, 0);
-	if (ret < 0)
-		return ret;
-	vc4->irq = ret;
-
 	ret = vc4_irq_install(drm, vc4->irq);
 	if (ret) {
 		DRM_ERROR("Failed to install IRQ handler\n");
-		return ret;
+		goto err_put_runtime_pm;
 	}
 
-	pm_runtime_set_active(dev);
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_set_autosuspend_delay(dev, 40); /* a little over 2 frames. */
-	pm_runtime_enable(dev);
-
-	vc4_debugfs_add_file(drm, "v3d_ident", vc4_v3d_debugfs_ident, NULL);
-	vc4_debugfs_add_regset32(drm, "v3d_regs", &v3d->regset);
 
 	return 0;
+
+err_put_runtime_pm:
+	pm_runtime_put(dev);
+
+	return ret;
 }
 
 static void vc4_v3d_unbind(struct device *dev, struct device *master,
@@ -489,8 +512,6 @@ static void vc4_v3d_unbind(struct device *dev, struct device *master,
 	struct drm_device *drm = dev_get_drvdata(master);
 	struct vc4_dev *vc4 = to_vc4_dev(drm);
 
-	pm_runtime_disable(dev);
-
 	vc4_irq_uninstall(drm);
 
 	/* Disable the binner's overflow memory address, so the next
diff --git a/drivers/gpu/drm/vc4/vc4_validate.c b/drivers/gpu/drm/vc4/vc4_validate.c
index 2feba55bcef7..520231af4df9 100644
--- a/drivers/gpu/drm/vc4/vc4_validate.c
+++ b/drivers/gpu/drm/vc4/vc4_validate.c
@@ -102,11 +102,11 @@ size_is_lt(uint32_t width, uint32_t height, int cpp)
 		height <= 4 * utile_height(cpp));
 }
 
-struct drm_gem_cma_object *
+struct drm_gem_dma_object *
 vc4_use_bo(struct vc4_exec_info *exec, uint32_t hindex)
 {
 	struct vc4_dev *vc4 = exec->dev;
-	struct drm_gem_cma_object *obj;
+	struct drm_gem_dma_object *obj;
 	struct vc4_bo *bo;
 
 	if (WARN_ON_ONCE(vc4->is_vc5))
@@ -129,7 +129,7 @@ vc4_use_bo(struct vc4_exec_info *exec, uint32_t hindex)
 	return obj;
 }
 
-static struct drm_gem_cma_object *
+static struct drm_gem_dma_object *
 vc4_use_handle(struct vc4_exec_info *exec, uint32_t gem_handles_packet_index)
 {
 	return vc4_use_bo(exec, exec->bo_index[gem_handles_packet_index]);
@@ -160,7 +160,7 @@ gl_shader_rec_size(uint32_t pointer_bits)
 }
 
 bool
-vc4_check_tex_size(struct vc4_exec_info *exec, struct drm_gem_cma_object *fbo,
+vc4_check_tex_size(struct vc4_exec_info *exec, struct drm_gem_dma_object *fbo,
 		   uint32_t offset, uint8_t tiling_format,
 		   uint32_t width, uint32_t height, uint8_t cpp)
 {
@@ -263,7 +263,7 @@ validate_increment_semaphore(VALIDATE_ARGS)
 static int
 validate_indexed_prim_list(VALIDATE_ARGS)
 {
-	struct drm_gem_cma_object *ib;
+	struct drm_gem_dma_object *ib;
 	uint32_t length = *(uint32_t *)(untrusted + 1);
 	uint32_t offset = *(uint32_t *)(untrusted + 5);
 	uint32_t max_index = *(uint32_t *)(untrusted + 9);
@@ -294,7 +294,7 @@ validate_indexed_prim_list(VALIDATE_ARGS)
 		return -EINVAL;
 	}
 
-	*(uint32_t *)(validated + 5) = ib->paddr + offset;
+	*(uint32_t *)(validated + 5) = ib->dma_addr + offset;
 
 	return 0;
 }
@@ -400,7 +400,7 @@ validate_tile_binning_config(VALIDATE_ARGS)
 	 * free when the job completes rendering.
 	 */
 	exec->bin_slots |= BIT(bin_slot);
-	bin_addr = vc4->bin_bo->base.paddr + bin_slot * vc4->bin_alloc_size;
+	bin_addr = vc4->bin_bo->base.dma_addr + bin_slot * vc4->bin_alloc_size;
 
 	/* The tile state data array is 48 bytes per tile, and we put it at
 	 * the start of a BO containing both it and the tile alloc.
@@ -575,7 +575,7 @@ reloc_tex(struct vc4_exec_info *exec,
 	  struct vc4_texture_sample_info *sample,
 	  uint32_t texture_handle_index, bool is_cs)
 {
-	struct drm_gem_cma_object *tex;
+	struct drm_gem_dma_object *tex;
 	uint32_t p0 = *(uint32_t *)(uniform_data_u + sample->p_offset[0]);
 	uint32_t p1 = *(uint32_t *)(uniform_data_u + sample->p_offset[1]);
 	uint32_t p2 = (sample->p_offset[2] != ~0 ?
@@ -608,7 +608,7 @@ reloc_tex(struct vc4_exec_info *exec,
 				  "outside of UBO\n");
 			goto fail;
 		}
-		*validated_p0 = tex->paddr + p0;
+		*validated_p0 = tex->dma_addr + p0;
 		return true;
 	}
 
@@ -736,7 +736,7 @@ reloc_tex(struct vc4_exec_info *exec,
 		offset -= level_size;
 	}
 
-	*validated_p0 = tex->paddr + p0;
+	*validated_p0 = tex->dma_addr + p0;
 
 	if (is_cs) {
 		exec->bin_dep_seqno = max(exec->bin_dep_seqno,
@@ -765,7 +765,7 @@ validate_gl_shader_rec(struct drm_device *dev,
 		28, /* cs */
 	};
 	uint32_t shader_reloc_count = ARRAY_SIZE(shader_reloc_offsets);
-	struct drm_gem_cma_object *bo[ARRAY_SIZE(shader_reloc_offsets) + 8];
+	struct drm_gem_dma_object *bo[ARRAY_SIZE(shader_reloc_offsets) + 8];
 	uint32_t nr_attributes, nr_relocs, packet_size;
 	int i;
 
@@ -840,7 +840,7 @@ validate_gl_shader_rec(struct drm_device *dev,
 		void *uniform_data_u;
 		uint32_t tex, uni;
 
-		*(uint32_t *)(pkt_v + o) = bo[i]->paddr + src_offset;
+		*(uint32_t *)(pkt_v + o) = bo[i]->dma_addr + src_offset;
 
 		if (src_offset != 0) {
 			DRM_DEBUG("Shaders must be at offset 0 of "
@@ -896,7 +896,7 @@ validate_gl_shader_rec(struct drm_device *dev,
 	}
 
 	for (i = 0; i < nr_attributes; i++) {
-		struct drm_gem_cma_object *vbo =
+		struct drm_gem_dma_object *vbo =
 			bo[ARRAY_SIZE(shader_reloc_offsets) + i];
 		uint32_t o = 36 + i * 8;
 		uint32_t offset = *(uint32_t *)(pkt_u + o + 0);
@@ -928,7 +928,7 @@ validate_gl_shader_rec(struct drm_device *dev,
 			}
 		}
 
-		*(uint32_t *)(pkt_v + o) = vbo->paddr + offset;
+		*(uint32_t *)(pkt_v + o) = vbo->dma_addr + offset;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/vc4/vc4_validate_shaders.c b/drivers/gpu/drm/vc4/vc4_validate_shaders.c
index e315aeb5fef5..9745f8810eca 100644
--- a/drivers/gpu/drm/vc4/vc4_validate_shaders.c
+++ b/drivers/gpu/drm/vc4/vc4_validate_shaders.c
@@ -776,7 +776,7 @@ vc4_handle_branch_target(struct vc4_shader_validation_state *validation_state)
 }
 
 struct vc4_validated_shader_info *
-vc4_validate_shader(struct drm_gem_cma_object *shader_obj)
+vc4_validate_shader(struct drm_gem_dma_object *shader_obj)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(shader_obj->base.dev);
 	bool found_shader_end = false;
diff --git a/drivers/gpu/drm/vc4/vc4_vec.c b/drivers/gpu/drm/vc4/vc4_vec.c
index 11fc3d6f66b1..4a788c1c9058 100644
--- a/drivers/gpu/drm/vc4/vc4_vec.c
+++ b/drivers/gpu/drm/vc4/vc4_vec.c
@@ -14,6 +14,7 @@
  */
 
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_panel.h>
 #include <drm/drm_probe_helper.h>
@@ -160,12 +161,12 @@ struct vc4_vec_variant {
 
 /* General VEC hardware state. */
 struct vc4_vec {
+	struct vc4_encoder encoder;
+	struct drm_connector connector;
+
 	struct platform_device *pdev;
 	const struct vc4_vec_variant *variant;
 
-	struct drm_encoder *encoder;
-	struct drm_connector *connector;
-
 	void __iomem *regs;
 
 	struct clk *clock;
@@ -178,30 +179,12 @@ struct vc4_vec {
 #define VEC_READ(offset) readl(vec->regs + (offset))
 #define VEC_WRITE(offset, val) writel(val, vec->regs + (offset))
 
-/* VC4 VEC encoder KMS struct */
-struct vc4_vec_encoder {
-	struct vc4_encoder base;
-	struct vc4_vec *vec;
-};
-
-static inline struct vc4_vec_encoder *
-to_vc4_vec_encoder(struct drm_encoder *encoder)
+static inline struct vc4_vec *
+encoder_to_vc4_vec(struct drm_encoder *encoder)
 {
-	return container_of(encoder, struct vc4_vec_encoder, base.base);
+	return container_of(encoder, struct vc4_vec, encoder.base);
 }
 
-/* VC4 VEC connector KMS struct */
-struct vc4_vec_connector {
-	struct drm_connector base;
-	struct vc4_vec *vec;
-
-	/* Since the connector is attached to just the one encoder,
-	 * this is the reference to it so we can do the best_encoder()
-	 * hook.
-	 */
-	struct drm_encoder *encoder;
-};
-
 enum vc4_vec_tv_mode_id {
 	VC4_VEC_TV_MODE_NTSC,
 	VC4_VEC_TV_MODE_NTSC_J,
@@ -243,14 +226,30 @@ static const struct debugfs_reg32 vec_regs[] = {
 
 static void vc4_vec_ntsc_mode_set(struct vc4_vec *vec)
 {
+	struct drm_device *drm = vec->connector.dev;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
 	VEC_WRITE(VEC_CONFIG0, VEC_CONFIG0_NTSC_STD | VEC_CONFIG0_PDEN);
 	VEC_WRITE(VEC_CONFIG1, VEC_CONFIG1_C_CVBS_CVBS);
+
+	drm_dev_exit(idx);
 }
 
 static void vc4_vec_ntsc_j_mode_set(struct vc4_vec *vec)
 {
+	struct drm_device *drm = vec->connector.dev;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
 	VEC_WRITE(VEC_CONFIG0, VEC_CONFIG0_NTSC_STD);
 	VEC_WRITE(VEC_CONFIG1, VEC_CONFIG1_C_CVBS_CVBS);
+
+	drm_dev_exit(idx);
 }
 
 static const struct drm_display_mode ntsc_mode = {
@@ -262,17 +261,33 @@ static const struct drm_display_mode ntsc_mode = {
 
 static void vc4_vec_pal_mode_set(struct vc4_vec *vec)
 {
+	struct drm_device *drm = vec->connector.dev;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
 	VEC_WRITE(VEC_CONFIG0, VEC_CONFIG0_PAL_BDGHI_STD);
 	VEC_WRITE(VEC_CONFIG1, VEC_CONFIG1_C_CVBS_CVBS);
+
+	drm_dev_exit(idx);
 }
 
 static void vc4_vec_pal_m_mode_set(struct vc4_vec *vec)
 {
+	struct drm_device *drm = vec->connector.dev;
+	int idx;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
+
 	VEC_WRITE(VEC_CONFIG0, VEC_CONFIG0_PAL_BDGHI_STD);
 	VEC_WRITE(VEC_CONFIG1,
 		  VEC_CONFIG1_C_CVBS_CVBS | VEC_CONFIG1_CUSTOM_FREQ);
 	VEC_WRITE(VEC_FREQ3_2, 0x223b);
 	VEC_WRITE(VEC_FREQ1_0, 0x61d1);
+
+	drm_dev_exit(idx);
 }
 
 static const struct drm_display_mode pal_mode = {
@@ -307,12 +322,6 @@ vc4_vec_connector_detect(struct drm_connector *connector, bool force)
 	return connector_status_unknown;
 }
 
-static void vc4_vec_connector_destroy(struct drm_connector *connector)
-{
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-}
-
 static int vc4_vec_connector_get_modes(struct drm_connector *connector)
 {
 	struct drm_connector_state *state = connector->state;
@@ -333,7 +342,6 @@ static int vc4_vec_connector_get_modes(struct drm_connector *connector)
 static const struct drm_connector_funcs vc4_vec_connector_funcs = {
 	.detect = vc4_vec_connector_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = vc4_vec_connector_destroy,
 	.reset = drm_atomic_helper_connector_reset,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
@@ -343,25 +351,18 @@ static const struct drm_connector_helper_funcs vc4_vec_connector_helper_funcs =
 	.get_modes = vc4_vec_connector_get_modes,
 };
 
-static struct drm_connector *vc4_vec_connector_init(struct drm_device *dev,
-						    struct vc4_vec *vec)
+static int vc4_vec_connector_init(struct drm_device *dev, struct vc4_vec *vec)
 {
-	struct drm_connector *connector = NULL;
-	struct vc4_vec_connector *vec_connector;
-
-	vec_connector = devm_kzalloc(dev->dev, sizeof(*vec_connector),
-				     GFP_KERNEL);
-	if (!vec_connector)
-		return ERR_PTR(-ENOMEM);
+	struct drm_connector *connector = &vec->connector;
+	int ret;
 
-	connector = &vec_connector->base;
 	connector->interlace_allowed = true;
 
-	vec_connector->encoder = vec->encoder;
-	vec_connector->vec = vec;
+	ret = drmm_connector_init(dev, connector, &vc4_vec_connector_funcs,
+				 DRM_MODE_CONNECTOR_Composite, NULL);
+	if (ret)
+		return ret;
 
-	drm_connector_init(dev, connector, &vc4_vec_connector_funcs,
-			   DRM_MODE_CONNECTOR_Composite);
 	drm_connector_helper_add(connector, &vc4_vec_connector_helper_funcs);
 
 	drm_object_attach_property(&connector->base,
@@ -369,16 +370,19 @@ static struct drm_connector *vc4_vec_connector_init(struct drm_device *dev,
 				   VC4_VEC_TV_MODE_NTSC);
 	vec->tv_mode = &vc4_vec_tv_modes[VC4_VEC_TV_MODE_NTSC];
 
-	drm_connector_attach_encoder(connector, vec->encoder);
+	drm_connector_attach_encoder(connector, &vec->encoder.base);
 
-	return connector;
+	return 0;
 }
 
 static void vc4_vec_encoder_disable(struct drm_encoder *encoder)
 {
-	struct vc4_vec_encoder *vc4_vec_encoder = to_vc4_vec_encoder(encoder);
-	struct vc4_vec *vec = vc4_vec_encoder->vec;
-	int ret;
+	struct drm_device *drm = encoder->dev;
+	struct vc4_vec *vec = encoder_to_vc4_vec(encoder);
+	int idx, ret;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
 
 	VEC_WRITE(VEC_CFG, 0);
 	VEC_WRITE(VEC_DAC_MISC,
@@ -392,20 +396,29 @@ static void vc4_vec_encoder_disable(struct drm_encoder *encoder)
 	ret = pm_runtime_put(&vec->pdev->dev);
 	if (ret < 0) {
 		DRM_ERROR("Failed to release power domain: %d\n", ret);
-		return;
+		goto err_dev_exit;
 	}
+
+	drm_dev_exit(idx);
+	return;
+
+err_dev_exit:
+	drm_dev_exit(idx);
 }
 
 static void vc4_vec_encoder_enable(struct drm_encoder *encoder)
 {
-	struct vc4_vec_encoder *vc4_vec_encoder = to_vc4_vec_encoder(encoder);
-	struct vc4_vec *vec = vc4_vec_encoder->vec;
-	int ret;
+	struct drm_device *drm = encoder->dev;
+	struct vc4_vec *vec = encoder_to_vc4_vec(encoder);
+	int idx, ret;
+
+	if (!drm_dev_enter(drm, &idx))
+		return;
 
 	ret = pm_runtime_get_sync(&vec->pdev->dev);
 	if (ret < 0) {
 		DRM_ERROR("Failed to retain power domain: %d\n", ret);
-		return;
+		goto err_dev_exit;
 	}
 
 	/*
@@ -418,13 +431,13 @@ static void vc4_vec_encoder_enable(struct drm_encoder *encoder)
 	ret = clk_set_rate(vec->clock, 108000000);
 	if (ret) {
 		DRM_ERROR("Failed to set clock rate: %d\n", ret);
-		return;
+		goto err_put_runtime_pm;
 	}
 
 	ret = clk_prepare_enable(vec->clock);
 	if (ret) {
 		DRM_ERROR("Failed to turn on core clock: %d\n", ret);
-		return;
+		goto err_put_runtime_pm;
 	}
 
 	/* Reset the different blocks */
@@ -460,6 +473,14 @@ static void vc4_vec_encoder_enable(struct drm_encoder *encoder)
 	VEC_WRITE(VEC_DAC_MISC,
 		  VEC_DAC_MISC_VID_ACT | VEC_DAC_MISC_DAC_RST_N);
 	VEC_WRITE(VEC_CFG, VEC_CFG_VEC_EN);
+
+	drm_dev_exit(idx);
+	return;
+
+err_put_runtime_pm:
+	pm_runtime_put(&vec->pdev->dev);
+err_dev_exit:
+	drm_dev_exit(idx);
 }
 
 
@@ -474,8 +495,7 @@ static void vc4_vec_encoder_atomic_mode_set(struct drm_encoder *encoder,
 					struct drm_crtc_state *crtc_state,
 					struct drm_connector_state *conn_state)
 {
-	struct vc4_vec_encoder *vc4_vec_encoder = to_vc4_vec_encoder(encoder);
-	struct vc4_vec *vec = vc4_vec_encoder->vec;
+	struct vc4_vec *vec = encoder_to_vc4_vec(encoder);
 
 	vec->tv_mode = &vc4_vec_tv_modes[conn_state->tv.mode];
 }
@@ -503,6 +523,24 @@ static const struct drm_encoder_helper_funcs vc4_vec_encoder_helper_funcs = {
 	.atomic_mode_set = vc4_vec_encoder_atomic_mode_set,
 };
 
+static int vc4_vec_late_register(struct drm_encoder *encoder)
+{
+	struct drm_device *drm = encoder->dev;
+	struct vc4_vec *vec = encoder_to_vc4_vec(encoder);
+	int ret;
+
+	ret = vc4_debugfs_add_regset32(drm->primary, "vec_regs",
+				       &vec->regset);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct drm_encoder_funcs vc4_vec_encoder_funcs = {
+	.late_register = vc4_vec_late_register,
+};
+
 static const struct vc4_vec_variant bcm2835_vec_variant = {
 	.dac_config = VEC_DAC_CONFIG_DAC_CTRL(0xc) |
 		      VEC_DAC_CONFIG_DRIVER_CTRL(0xc) |
@@ -532,9 +570,7 @@ static int vc4_vec_bind(struct device *dev, struct device *master, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct drm_device *drm = dev_get_drvdata(master);
-	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_vec *vec;
-	struct vc4_vec_encoder *vc4_vec_encoder;
 	int ret;
 
 	ret = drm_mode_create_tv_properties(drm, ARRAY_SIZE(tv_mode_names),
@@ -542,18 +578,11 @@ static int vc4_vec_bind(struct device *dev, struct device *master, void *data)
 	if (ret)
 		return ret;
 
-	vec = devm_kzalloc(dev, sizeof(*vec), GFP_KERNEL);
+	vec = drmm_kzalloc(drm, sizeof(*vec), GFP_KERNEL);
 	if (!vec)
 		return -ENOMEM;
 
-	vc4_vec_encoder = devm_kzalloc(dev, sizeof(*vc4_vec_encoder),
-				       GFP_KERNEL);
-	if (!vc4_vec_encoder)
-		return -ENOMEM;
-	vc4_vec_encoder->base.type = VC4_ENCODER_TYPE_VEC;
-	vc4_vec_encoder->vec = vec;
-	vec->encoder = &vc4_vec_encoder->base.base;
-
+	vec->encoder.type = VC4_ENCODER_TYPE_VEC;
 	vec->pdev = pdev;
 	vec->variant = (const struct vc4_vec_variant *)
 		of_device_get_match_data(dev);
@@ -572,49 +601,30 @@ static int vc4_vec_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 	}
 
-	pm_runtime_enable(dev);
-
-	drm_simple_encoder_init(drm, vec->encoder, DRM_MODE_ENCODER_TVDAC);
-	drm_encoder_helper_add(vec->encoder, &vc4_vec_encoder_helper_funcs);
+	ret = devm_pm_runtime_enable(dev);
+	if (ret)
+		return ret;
 
-	vec->connector = vc4_vec_connector_init(drm, vec);
-	if (IS_ERR(vec->connector)) {
-		ret = PTR_ERR(vec->connector);
-		goto err_destroy_encoder;
-	}
+	ret = drmm_encoder_init(drm, &vec->encoder.base,
+				&vc4_vec_encoder_funcs,
+				DRM_MODE_ENCODER_TVDAC,
+				NULL);
+	if (ret)
+		return ret;
 
-	dev_set_drvdata(dev, vec);
+	drm_encoder_helper_add(&vec->encoder.base, &vc4_vec_encoder_helper_funcs);
 
-	vc4->vec = vec;
+	ret = vc4_vec_connector_init(drm, vec);
+	if (ret)
+		return ret;
 
-	vc4_debugfs_add_regset32(drm, "vec_regs", &vec->regset);
+	dev_set_drvdata(dev, vec);
 
 	return 0;
-
-err_destroy_encoder:
-	drm_encoder_cleanup(vec->encoder);
-	pm_runtime_disable(dev);
-
-	return ret;
-}
-
-static void vc4_vec_unbind(struct device *dev, struct device *master,
-			   void *data)
-{
-	struct drm_device *drm = dev_get_drvdata(master);
-	struct vc4_dev *vc4 = to_vc4_dev(drm);
-	struct vc4_vec *vec = dev_get_drvdata(dev);
-
-	vc4_vec_connector_destroy(vec->connector);
-	drm_encoder_cleanup(vec->encoder);
-	pm_runtime_disable(dev);
-
-	vc4->vec = NULL;
 }
 
 static const struct component_ops vc4_vec_ops = {
 	.bind   = vc4_vec_bind,
-	.unbind = vc4_vec_unbind,
 };
 
 static int vc4_vec_dev_probe(struct platform_device *pdev)