Merge tag 'drm-next-2022-05-25' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Intel have enabled DG2 on certain SKUs for laptops, AMD has started
  some new GPU support, msm has user allocated VA controls

  dma-buf:
   - add dma_resv_replace_fences
   - add dma_resv_get_singleton
   - make dma_excl_fence private

  core:
   - EDID parser refactorings
   - switch drivers to drm_mode_copy/duplicate
   - DRM managed mutex initialization

  display-helper:
   - put HDMI, SCDC, HDCP, DSC and DP into new module

  gem:
   - rework fence handling

  ttm:
   - rework bulk move handling
   - add common debugfs for resource managers
   - convert to kvcalloc

  format helpers:
   - support monochrome formats
   - RGB888, RGB565 to XRGB8888 conversions

  fbdev:
   - cfb/sys_imageblit fixes
   - pagelist corruption fix
   - create offb platform device
   - deferred io improvements

  sysfb:
   - Kconfig rework
   - support for VESA mode selection

  bridge:
   - conversions to devm_drm_of_get_bridge
   - conversions to panel_bridge
   - analogix_dp - autosuspend support
   - it66121 - audio support
   - tc358767 - DSI to DPI support
   - icn6211 - PLL/I2C fixes, DT property
   - adv7611 - enable DRM_BRIDGE_OP_HPD
   - anx7625 - fill ELD if no monitor
   - dw_hdmi - add audio support
   - lontium LT9211 support, i.MXMP LDB
   - it6505: Kconfig fix, DPCD set power fix
   - adv7511 - CEC support for ADV7535

  panel:
   - ltk035c5444t, B133UAN01, NV3052C panel support
   - DataImage FG040346DSSWBG04 support
   - st7735r - DT bindings fix
   - ssd130x - fixes

  i915:
   - DG2 laptop PCI-IDs ("motherboard down")
   - Initial RPL-P PCI IDs
   - compute engine ABI
   - DG2 Tile4 support
   - DG2 CCS clear color compression support
   - DG2 render/media compression formats support
   - ATS-M platform info
   - RPL-S PCI IDs added
   - Bump ADL-P DMC version to v2.16
   - Support static DRRS
   - Support multiple eDP/LVDS native mode refresh rates
   - DP HDR support for HSW+
   - Lots of display refactoring + fixes
   - GuC hwconfig support and query
   - sysfs support for multi-tile
   - fdinfo per-client gpu utilisation
   - add geometry subslices query
   - fix prime mmap with LMEM
   - fix vm open count and remove vma refcounts
   - contiguous allocation fixes
   - steered register write support
   - small PCI BAR enablement
   - GuC error capture support
   - sunset igpu legacy mmap support for newer devices
   - GuC version 70.1.1 support

  amdgpu:
   - Initial SoC21 support
   - SMU 13.x enablement
   - SMU 13.0.4 support
   - ttm_eu cleanups
   - USB-C, GPUVM updates
   - TMZ fixes for RV
   - RAS support for VCN
   - PM sysfs code cleanup
   - DC FP rework
   - extend CG/PG flags to 64-bit
   - SI dpm lockdep fix
   - runtime PM fixes

  amdkfd:
   - RAS/SVM fixes
   - TLB flush fixes
   - CRIU GWS support
   - ignore bogus MEC signals more efficiently

  msm:
   - Fourcc modifier for tiled but not compressed layouts
   - Support for userspace allocated IOVA (GPU virtual address)
   - DPU: DSC (Display Stream Compression) support
   - DP: eDP support
   - DP: conversion to use drm_bridge and drm_bridge_connector
   - Merge DPU1 and MDP5 MDSS driver
   - DPU: writeback support

  nouveau:
   - make some structures static
   - make some variables static
   - switch to drm_gem_plane_helper_prepare_fb

  radeon:
   - misc fixes/cleanups

  mxsfb:
   - rework crtc mode setting
   - LCDIF CRC support

  etnaviv:
   - fencing improvements
   - fix address space collisions
   - cleanup MMU reference handling

  gma500:
   - GEM/GTT improvements
   - connector handling fixes

  komeda:
   - switch to plane reset helper

  mediatek:
   - MIPI DSI improvements

  omapdrm:
   - GEM improvements

  qxl:
   - aarch64 support

  vc4:
   - add a CL submission tracepoint
   - HDMI YUV support
   - HDMI/clock improvements
   - drop is_hdmi caching

  virtio:
   - remove restriction of non-zero blob types

  vmwgfx:
   - support for cursormob and cursorbypass 4
   - fence improvements

  tidss:
   - reset DISPC on startup

  solomon:
   - SPI support
   - DT improvements

  sun4i:
   - allwinner D1 support
   - drop is_hdmi caching

  imx:
   - use swap() instead of open-coding
   - use devm_platform_ioremap_resource
   - remove redunant initializations

  ast:
   - Displayport support

  rockchip:
   - Refactor IOMMU initialisation
   - make some structures static
   - replace drm_detect_hdmi_monitor with drm_display_info.is_hdmi
   - support swapped YUV formats,
   - clock improvements
   - rk3568 support
   - VOP2 support

  mediatek:
   - MT8186 support

  tegra:
   - debugabillity improvements"

* tag 'drm-next-2022-05-25' of git://anongit.freedesktop.org/drm/drm: (1740 commits)
  drm/i915/dsi: fix VBT send packet port selection for ICL+
  drm/i915/uc: Fix undefined behavior due to shift overflowing the constant
  drm/i915/reg: fix undefined behavior due to shift overflowing the constant
  drm/i915/gt: Fix use of static in macro mismatch
  drm/i915/audio: fix audio code enable/disable pipe logging
  drm/i915: Fix CFI violation with show_dynamic_id()
  drm/i915: Fix 'mixing different enum types' warnings in intel_display_power.c
  drm/i915/gt: Fix build error without CONFIG_PM
  drm/msm/dpu: handle pm_runtime_get_sync() errors in bind path
  drm/msm/dpu: add DRM_MODE_ROTATE_180 back to supported rotations
  drm/msm: don't free the IRQ if it was not requested
  drm/msm/dpu: limit writeback modes according to max_linewidth
  drm/amd: Don't reset dGPUs if the system is going to s2idle
  drm/amdgpu: Unmap legacy queue when MES is enabled
  drm: msm: fix possible memory leak in mdp5_crtc_cursor_set()
  drm/msm: Fix fb plane offset calculation
  drm/msm/a6xx: Fix refcount leak in a6xx_gpu_init
  drm/msm/dsi: don't powerup at modeset time for parade-ps8640
  drm/rockchip: Change register space names in vop2
  dt-bindings: display: rockchip: make reg-names mandatory for VOP2
  ...

16 files changed, 773 insertions, 202 deletions

diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig
index 6cf2621786e6..061be9a6619d 100644
--- a/drivers/gpu/drm/vc4/Kconfig
+++ b/drivers/gpu/drm/vc4/Kconfig
@@ -8,6 +8,8 @@ config DRM_VC4
 	depends on DRM
 	depends on SND && SND_SOC
 	depends on COMMON_CLK
+	select DRM_DISPLAY_HDMI_HELPER
+	select DRM_DISPLAY_HELPER
 	select DRM_KMS_HELPER
 	select DRM_GEM_CMA_HELPER
 	select DRM_PANEL_BRIDGE
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index e451cc5bcfac..49c0f2ac868b 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -738,19 +738,13 @@ static const struct drm_gem_object_funcs vc4_gem_object_funcs = {
 
 static int vc4_grab_bin_bo(struct vc4_dev *vc4, struct vc4_file *vc4file)
 {
-	int ret;
-
 	if (!vc4->v3d)
 		return -ENODEV;
 
 	if (vc4file->bin_bo_used)
 		return 0;
 
-	ret = vc4_v3d_bin_bo_get(vc4, &vc4file->bin_bo_used);
-	if (ret)
-		return ret;
-
-	return 0;
+	return vc4_v3d_bin_bo_get(vc4, &vc4file->bin_bo_used);
 }
 
 int vc4_create_bo_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 783890e8d43a..59b20c8f132b 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -70,6 +70,7 @@ static const struct debugfs_reg32 crtc_regs[] = {
 static unsigned int
 vc4_crtc_get_cob_allocation(struct vc4_dev *vc4, unsigned int channel)
 {
+	struct vc4_hvs *hvs = vc4->hvs;
 	u32 dispbase = HVS_READ(SCALER_DISPBASEX(channel));
 	/* Top/base are supposed to be 4-pixel aligned, but the
 	 * Raspberry Pi firmware fills the low bits (which are
@@ -89,6 +90,7 @@ static bool vc4_crtc_get_scanout_position(struct drm_crtc *crtc,
 {
 	struct drm_device *dev = crtc->dev;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_hvs *hvs = vc4->hvs;
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
 	struct vc4_crtc_state *vc4_crtc_state = to_vc4_crtc_state(crtc->state);
 	unsigned int cob_size;
@@ -123,7 +125,7 @@ static bool vc4_crtc_get_scanout_position(struct drm_crtc *crtc,
 		*vpos /= 2;
 
 		/* Use hpos to correct for field offset in interlaced mode. */
-		if (VC4_GET_FIELD(val, SCALER_DISPSTATX_FRAME_COUNT) % 2)
+		if (vc4_hvs_get_fifo_frame_count(hvs, vc4_crtc_state->assigned_channel) % 2)
 			*hpos += mode->crtc_htotal / 2;
 	}
 
@@ -413,6 +415,7 @@ static void vc4_crtc_config_pv(struct drm_crtc *crtc, struct drm_encoder *encode
 static void require_hvs_enabled(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_hvs *hvs = vc4->hvs;
 
 	WARN_ON_ONCE((HVS_READ(SCALER_DISPCTRL) & SCALER_DISPCTRL_ENABLE) !=
 		     SCALER_DISPCTRL_ENABLE);
@@ -426,6 +429,7 @@ static int vc4_crtc_disable(struct drm_crtc *crtc,
 	struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder);
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	int ret;
 
 	CRTC_WRITE(PV_V_CONTROL,
@@ -455,7 +459,7 @@ static int vc4_crtc_disable(struct drm_crtc *crtc,
 		vc4_encoder->post_crtc_disable(encoder, state);
 
 	vc4_crtc_pixelvalve_reset(crtc);
-	vc4_hvs_stop_channel(dev, channel);
+	vc4_hvs_stop_channel(vc4->hvs, channel);
 
 	if (vc4_encoder && vc4_encoder->post_crtc_powerdown)
 		vc4_encoder->post_crtc_powerdown(encoder, state);
@@ -481,6 +485,7 @@ static struct drm_encoder *vc4_crtc_get_encoder_by_type(struct drm_crtc *crtc,
 int vc4_crtc_disable_at_boot(struct drm_crtc *crtc)
 {
 	struct drm_device *drm = crtc->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
 	enum vc4_encoder_type encoder_type;
 	const struct vc4_pv_data *pv_data;
@@ -502,7 +507,7 @@ int vc4_crtc_disable_at_boot(struct drm_crtc *crtc)
 	if (!(CRTC_READ(PV_V_CONTROL) & PV_VCONTROL_VIDEN))
 		return 0;
 
-	channel = vc4_hvs_get_fifo_from_output(drm, vc4_crtc->data->hvs_output);
+	channel = vc4_hvs_get_fifo_from_output(vc4->hvs, vc4_crtc->data->hvs_output);
 	if (channel < 0)
 		return 0;
 
@@ -717,6 +722,7 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc)
 	struct drm_crtc *crtc = &vc4_crtc->base;
 	struct drm_device *dev = crtc->dev;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_hvs *hvs = vc4->hvs;
 	u32 chan = vc4_crtc->current_hvs_channel;
 	unsigned long flags;
 
@@ -735,7 +741,7 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc)
 		 * the CRTC and encoder already reconfigured, leading to
 		 * underruns. This can be seen when reconfiguring the CRTC.
 		 */
-		vc4_hvs_unmask_underrun(dev, chan);
+		vc4_hvs_unmask_underrun(hvs, chan);
 	}
 	spin_unlock(&vc4_crtc->irq_lock);
 	spin_unlock_irqrestore(&dev->event_lock, flags);
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 4329e09d357c..15e0c2ac3940 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -574,8 +574,8 @@ to_vc4_crtc_state(struct drm_crtc_state *crtc_state)
 
 #define V3D_READ(offset) readl(vc4->v3d->regs + offset)
 #define V3D_WRITE(offset, val) writel(val, vc4->v3d->regs + offset)
-#define HVS_READ(offset) readl(vc4->hvs->regs + offset)
-#define HVS_WRITE(offset, val) writel(val, vc4->hvs->regs + offset)
+#define HVS_READ(offset) readl(hvs->regs + offset)
+#define HVS_WRITE(offset, val) writel(val, hvs->regs + offset)
 
 #define VC4_REG32(reg) { .name = #reg, .offset = reg }
 
@@ -933,16 +933,17 @@ void vc4_irq_reset(struct drm_device *dev);
 
 /* vc4_hvs.c */
 extern struct platform_driver vc4_hvs_driver;
-void vc4_hvs_stop_channel(struct drm_device *dev, unsigned int output);
-int vc4_hvs_get_fifo_from_output(struct drm_device *dev, unsigned int output);
+void vc4_hvs_stop_channel(struct vc4_hvs *hvs, unsigned int output);
+int vc4_hvs_get_fifo_from_output(struct vc4_hvs *hvs, unsigned int output);
+u8 vc4_hvs_get_fifo_frame_count(struct vc4_hvs *hvs, unsigned int fifo);
 int vc4_hvs_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state);
 void vc4_hvs_atomic_begin(struct drm_crtc *crtc, struct drm_atomic_state *state);
 void vc4_hvs_atomic_enable(struct drm_crtc *crtc, struct drm_atomic_state *state);
 void vc4_hvs_atomic_disable(struct drm_crtc *crtc, struct drm_atomic_state *state);
 void vc4_hvs_atomic_flush(struct drm_crtc *crtc, struct drm_atomic_state *state);
-void vc4_hvs_dump_state(struct drm_device *dev);
-void vc4_hvs_unmask_underrun(struct drm_device *dev, int channel);
-void vc4_hvs_mask_underrun(struct drm_device *dev, int channel);
+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);
 
 /* vc4_kms.c */
 int vc4_kms_load(struct drm_device *dev);
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 445d3bab89e0..9eaf304fc20d 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -485,6 +485,8 @@ again:
 	 * immediately move it to the to-be-rendered queue.
 	 */
 	if (exec->ct0ca != exec->ct0ea) {
+		trace_vc4_submit_cl(dev, false, exec->seqno, exec->ct0ca,
+				    exec->ct0ea);
 		submit_cl(dev, 0, exec->ct0ca, exec->ct0ea);
 	} else {
 		struct vc4_exec_info *next;
@@ -519,6 +521,7 @@ vc4_submit_next_render_job(struct drm_device *dev)
 	 */
 	vc4_flush_texture_caches(dev);
 
+	trace_vc4_submit_cl(dev, true, exec->seqno, exec->ct1ca, exec->ct1ea);
 	submit_cl(dev, 1, exec->ct1ca, exec->ct1ea);
 }
 
@@ -543,7 +546,8 @@ vc4_update_bo_seqnos(struct vc4_exec_info *exec, uint64_t seqno)
 		bo = to_vc4_bo(&exec->bo[i]->base);
 		bo->seqno = seqno;
 
-		dma_resv_add_shared_fence(bo->base.base.resv, exec->fence);
+		dma_resv_add_fence(bo->base.base.resv, exec->fence,
+				   DMA_RESV_USAGE_READ);
 	}
 
 	list_for_each_entry(bo, &exec->unref_list, unref_head) {
@@ -554,7 +558,8 @@ vc4_update_bo_seqnos(struct vc4_exec_info *exec, uint64_t seqno)
 		bo = to_vc4_bo(&exec->rcl_write_bo[i]->base);
 		bo->write_seqno = seqno;
 
-		dma_resv_add_excl_fence(bo->base.base.resv, exec->fence);
+		dma_resv_add_fence(bo->base.base.resv, exec->fence,
+				   DMA_RESV_USAGE_WRITE);
 	}
 }
 
@@ -641,7 +646,7 @@ retry:
 	for (i = 0; i < exec->bo_count; i++) {
 		bo = &exec->bo[i]->base;
 
-		ret = dma_resv_reserve_shared(bo->resv, 1);
+		ret = dma_resv_reserve_fences(bo->resv, 1);
 		if (ret) {
 			vc4_unlock_bo_reservations(dev, exec, acquire_ctx);
 			return ret;
@@ -1135,6 +1140,10 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 	struct dma_fence *in_fence;
 	int ret = 0;
 
+	trace_vc4_submit_cl_ioctl(dev, args->bin_cl_size,
+				  args->shader_rec_size,
+				  args->bo_handle_count);
+
 	if (!vc4->v3d) {
 		DRM_DEBUG("VC4_SUBMIT_CL with no VC4 V3D probed\n");
 		return -ENODEV;
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 98b78ec6b37d..823d812f4982 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -31,11 +31,11 @@
  * encoder block has CEC support.
  */
 
+#include <drm/display/drm_hdmi_helper.h>
+#include <drm/display/drm_scdc_helper.h>
 #include <drm/drm_atomic_helper.h>
-#include <drm/drm_edid.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_simple_kms_helper.h>
-#include <drm/drm_scdc_helper.h>
 #include <linux/clk.h>
 #include <linux/component.h>
 #include <linux/gpio/consumer.h>
@@ -100,17 +100,40 @@
 
 #define HDMI_14_MAX_TMDS_CLK   (340 * 1000 * 1000)
 
-static bool vc4_hdmi_mode_needs_scrambling(const struct drm_display_mode *mode)
+static const char * const output_format_str[] = {
+	[VC4_HDMI_OUTPUT_RGB]		= "RGB",
+	[VC4_HDMI_OUTPUT_YUV420]	= "YUV 4:2:0",
+	[VC4_HDMI_OUTPUT_YUV422]	= "YUV 4:2:2",
+	[VC4_HDMI_OUTPUT_YUV444]	= "YUV 4:4:4",
+};
+
+static const char *vc4_hdmi_output_fmt_str(enum vc4_hdmi_output_format fmt)
+{
+	if (fmt >= ARRAY_SIZE(output_format_str))
+		return "invalid";
+
+	return output_format_str[fmt];
+}
+
+static unsigned long long
+vc4_hdmi_encoder_compute_mode_clock(const struct drm_display_mode *mode,
+				    unsigned int bpc, enum vc4_hdmi_output_format fmt);
+
+static bool vc4_hdmi_mode_needs_scrambling(const struct drm_display_mode *mode,
+					   unsigned int bpc,
+					   enum vc4_hdmi_output_format fmt)
 {
-	return (mode->clock * 1000) > HDMI_14_MAX_TMDS_CLK;
+	unsigned long long clock = vc4_hdmi_encoder_compute_mode_clock(mode, bpc, fmt);
+
+	return clock > HDMI_14_MAX_TMDS_CLK;
 }
 
 static bool vc4_hdmi_is_full_range_rgb(struct vc4_hdmi *vc4_hdmi,
 				       const struct drm_display_mode *mode)
 {
-	struct vc4_hdmi_encoder *vc4_encoder = &vc4_hdmi->encoder;
+	struct drm_display_info *display = &vc4_hdmi->connector.display_info;
 
-	return !vc4_encoder->hdmi_monitor ||
+	return !display->is_hdmi ||
 		drm_default_rgb_quant_range(mode) == HDMI_QUANTIZATION_RANGE_FULL;
 }
 
@@ -217,12 +240,11 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force)
 
 			if (edid) {
 				cec_s_phys_addr_from_edid(vc4_hdmi->cec_adap, edid);
-				vc4_hdmi->encoder.hdmi_monitor = drm_detect_hdmi_monitor(edid);
 				kfree(edid);
 			}
 		}
 
-		vc4_hdmi_enable_scrambling(&vc4_hdmi->encoder.base.base);
+		vc4_hdmi_enable_scrambling(&vc4_hdmi->encoder.base);
 		pm_runtime_put(&vc4_hdmi->pdev->dev);
 		mutex_unlock(&vc4_hdmi->mutex);
 		return connector_status_connected;
@@ -243,7 +265,6 @@ static void vc4_hdmi_connector_destroy(struct drm_connector *connector)
 static int vc4_hdmi_connector_get_modes(struct drm_connector *connector)
 {
 	struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector);
-	struct vc4_hdmi_encoder *vc4_encoder = &vc4_hdmi->encoder;
 	int ret = 0;
 	struct edid *edid;
 
@@ -256,8 +277,6 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector)
 		goto out;
 	}
 
-	vc4_encoder->hdmi_monitor = drm_detect_hdmi_monitor(edid);
-
 	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
@@ -267,7 +286,7 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector)
 		struct drm_display_mode *mode;
 
 		list_for_each_entry(mode, &connector->probed_modes, head) {
-			if (vc4_hdmi_mode_needs_scrambling(mode)) {
+			if (vc4_hdmi_mode_needs_scrambling(mode, 8, VC4_HDMI_OUTPUT_RGB)) {
 				drm_warn_once(drm, "The core clock cannot reach frequencies high enough to support 4k @ 60Hz.");
 				drm_warn_once(drm, "Please change your config.txt file to add hdmi_enable_4kp60.");
 			}
@@ -324,6 +343,7 @@ static void vc4_hdmi_connector_reset(struct drm_connector *connector)
 
 	new_state->base.max_bpc = 8;
 	new_state->base.max_requested_bpc = 8;
+	new_state->output_format = VC4_HDMI_OUTPUT_RGB;
 	drm_atomic_helper_connector_tv_reset(connector);
 }
 
@@ -338,7 +358,9 @@ vc4_hdmi_connector_duplicate_state(struct drm_connector *connector)
 	if (!new_state)
 		return NULL;
 
-	new_state->pixel_rate = vc4_state->pixel_rate;
+	new_state->tmds_char_rate = vc4_state->tmds_char_rate;
+	new_state->output_bpc = vc4_state->output_bpc;
+	new_state->output_format = vc4_state->output_format;
 	__drm_atomic_helper_connector_duplicate_state(connector, &new_state->base);
 
 	return &new_state->base;
@@ -362,7 +384,7 @@ static int vc4_hdmi_connector_init(struct drm_device *dev,
 				   struct vc4_hdmi *vc4_hdmi)
 {
 	struct drm_connector *connector = &vc4_hdmi->connector;
-	struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base;
+	struct drm_encoder *encoder = &vc4_hdmi->encoder.base;
 	int ret;
 
 	drm_connector_init_with_ddc(dev, connector,
@@ -482,11 +504,38 @@ static void vc4_hdmi_write_infoframe(struct drm_encoder *encoder,
 		DRM_ERROR("Failed to wait for infoframe to start: %d\n", ret);
 }
 
+static void vc4_hdmi_avi_infoframe_colorspace(struct hdmi_avi_infoframe *frame,
+					      enum vc4_hdmi_output_format fmt)
+{
+	switch (fmt) {
+	case VC4_HDMI_OUTPUT_RGB:
+		frame->colorspace = HDMI_COLORSPACE_RGB;
+		break;
+
+	case VC4_HDMI_OUTPUT_YUV420:
+		frame->colorspace = HDMI_COLORSPACE_YUV420;
+		break;
+
+	case VC4_HDMI_OUTPUT_YUV422:
+		frame->colorspace = HDMI_COLORSPACE_YUV422;
+		break;
+
+	case VC4_HDMI_OUTPUT_YUV444:
+		frame->colorspace = HDMI_COLORSPACE_YUV444;
+		break;
+
+	default:
+		break;
+	}
+}
+
 static void vc4_hdmi_set_avi_infoframe(struct drm_encoder *encoder)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
 	struct drm_connector *connector = &vc4_hdmi->connector;
 	struct drm_connector_state *cstate = connector->state;
+	struct vc4_hdmi_connector_state *vc4_state =
+		conn_state_to_vc4_hdmi_conn_state(cstate);
 	const struct drm_display_mode *mode = &vc4_hdmi->saved_adjusted_mode;
 	union hdmi_infoframe frame;
 	int ret;
@@ -506,6 +555,7 @@ static void vc4_hdmi_set_avi_infoframe(struct drm_encoder *encoder)
 					   HDMI_QUANTIZATION_RANGE_FULL :
 					   HDMI_QUANTIZATION_RANGE_LIMITED);
 	drm_hdmi_avi_infoframe_colorimetry(&frame.avi, cstate);
+	vc4_hdmi_avi_infoframe_colorspace(&frame.avi, vc4_state->output_format);
 	drm_hdmi_avi_infoframe_bars(&frame.avi, cstate);
 
 	vc4_hdmi_write_infoframe(encoder, &frame);
@@ -579,13 +629,12 @@ static void vc4_hdmi_set_infoframes(struct drm_encoder *encoder)
 static bool vc4_hdmi_supports_scrambling(struct drm_encoder *encoder,
 					 struct drm_display_mode *mode)
 {
-	struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder);
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
 	struct drm_display_info *display = &vc4_hdmi->connector.display_info;
 
 	lockdep_assert_held(&vc4_hdmi->mutex);
 
-	if (!vc4_encoder->hdmi_monitor)
+	if (!display->is_hdmi)
 		return false;
 
 	if (!display->hdmi.scdc.supported ||
@@ -608,7 +657,9 @@ static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder)
 	if (!vc4_hdmi_supports_scrambling(encoder, mode))
 		return;
 
-	if (!vc4_hdmi_mode_needs_scrambling(mode))
+	if (!vc4_hdmi_mode_needs_scrambling(mode,
+					    vc4_hdmi->output_bpc,
+					    vc4_hdmi->output_format))
 		return;
 
 	drm_scdc_set_high_tmds_clock_ratio(vc4_hdmi->ddc, true);
@@ -803,6 +854,39 @@ static const u16 vc5_hdmi_csc_full_rgb_to_limited_rgb[3][4] = {
 	{ 0x0000, 0x0000, 0x1b80, 0x0400 },
 };
 
+/*
+ * Conversion between Full Range RGB and Full Range YUV422 using the
+ * BT.709 Colorspace
+ *
+ *
+ * [  0.181906  0.611804  0.061758  16  ]
+ * [ -0.100268 -0.337232  0.437500  128 ]
+ * [  0.437500 -0.397386 -0.040114  128 ]
+ *
+ * Matrix is signed 2p13 fixed point, with signed 9p6 offsets
+ */
+static const u16 vc5_hdmi_csc_full_rgb_to_limited_yuv422_bt709[3][4] = {
+	{ 0x05d2, 0x1394, 0x01fa, 0x0400 },
+	{ 0xfccc, 0xf536, 0x0e00, 0x2000 },
+	{ 0x0e00, 0xf34a, 0xfeb8, 0x2000 },
+};
+
+/*
+ * Conversion between Full Range RGB and Full Range YUV444 using the
+ * BT.709 Colorspace
+ *
+ * [ -0.100268 -0.337232  0.437500  128 ]
+ * [  0.437500 -0.397386 -0.040114  128 ]
+ * [  0.181906  0.611804  0.061758  16  ]
+ *
+ * Matrix is signed 2p13 fixed point, with signed 9p6 offsets
+ */
+static const u16 vc5_hdmi_csc_full_rgb_to_limited_yuv444_bt709[3][4] = {
+	{ 0xfccc, 0xf536, 0x0e00, 0x2000 },
+	{ 0x0e00, 0xf34a, 0xfeb8, 0x2000 },
+	{ 0x05d2, 0x1394, 0x01fa, 0x0400 },
+};
+
 static void vc5_hdmi_set_csc_coeffs(struct vc4_hdmi *vc4_hdmi,
 				    const u16 coeffs[3][4])
 {
@@ -820,19 +904,53 @@ static void vc5_hdmi_csc_setup(struct vc4_hdmi *vc4_hdmi,
 			       struct drm_connector_state *state,
 			       const struct drm_display_mode *mode)
 {
+	struct vc4_hdmi_connector_state *vc4_state =
+		conn_state_to_vc4_hdmi_conn_state(state);
 	unsigned long flags;
+	u32 if_cfg = 0;
+	u32 if_xbar = 0x543210;
+	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);
 
 	spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
-	HDMI_WRITE(HDMI_VEC_INTERFACE_XBAR, 0x354021);
+	switch (vc4_state->output_format) {
+	case VC4_HDMI_OUTPUT_YUV444:
+		vc5_hdmi_set_csc_coeffs(vc4_hdmi, vc5_hdmi_csc_full_rgb_to_limited_yuv444_bt709);
+		break;
 
-	if (!vc4_hdmi_is_full_range_rgb(vc4_hdmi, mode))
-		vc5_hdmi_set_csc_coeffs(vc4_hdmi, vc5_hdmi_csc_full_rgb_to_limited_rgb);
-	else
-		vc5_hdmi_set_csc_coeffs(vc4_hdmi, vc5_hdmi_csc_full_rgb_unity);
+	case VC4_HDMI_OUTPUT_YUV422:
+		csc_ctl |= VC4_SET_FIELD(VC5_MT_CP_CSC_CTL_FILTER_MODE_444_TO_422_STANDARD,
+					 VC5_MT_CP_CSC_CTL_FILTER_MODE_444_TO_422) |
+			VC5_MT_CP_CSC_CTL_USE_444_TO_422 |
+			VC5_MT_CP_CSC_CTL_USE_RNG_SUPPRESSION;
+
+		csc_chan_ctl |= VC4_SET_FIELD(VC5_MT_CP_CHANNEL_CTL_OUTPUT_REMAP_LEGACY_STYLE,
+					      VC5_MT_CP_CHANNEL_CTL_OUTPUT_REMAP);
+
+		if_cfg |= VC4_SET_FIELD(VC5_DVP_HT_VEC_INTERFACE_CFG_SEL_422_FORMAT_422_LEGACY,
+					VC5_DVP_HT_VEC_INTERFACE_CFG_SEL_422);
+
+		vc5_hdmi_set_csc_coeffs(vc4_hdmi, vc5_hdmi_csc_full_rgb_to_limited_yuv422_bt709);
+		break;
 
+	case VC4_HDMI_OUTPUT_RGB:
+		if_xbar = 0x354021;
+
+		if (!vc4_hdmi_is_full_range_rgb(vc4_hdmi, mode))
+			vc5_hdmi_set_csc_coeffs(vc4_hdmi, vc5_hdmi_csc_full_rgb_to_limited_rgb);
+		else
+			vc5_hdmi_set_csc_coeffs(vc4_hdmi, vc5_hdmi_csc_full_rgb_unity);
+		break;
+
+	default:
+		break;
+	}
+
+	HDMI_WRITE(HDMI_VEC_INTERFACE_CFG, if_cfg);
+	HDMI_WRITE(HDMI_VEC_INTERFACE_XBAR, if_xbar);
+	HDMI_WRITE(HDMI_CSC_CHANNEL_CTL, csc_chan_ctl);
 	HDMI_WRITE(HDMI_CSC_CTL, csc_ctl);
 
 	spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags);
@@ -893,6 +1011,8 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi,
 				 struct drm_connector_state *state,
 				 struct drm_display_mode *mode)
 {
+	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;
 	bool vsync_pos = mode->flags & DRM_MODE_FLAG_PVSYNC;
 	bool interlaced = mode->flags & DRM_MODE_FLAG_INTERLACE;
@@ -940,7 +1060,7 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi,
 	HDMI_WRITE(HDMI_VERTB0, vertb_even);
 	HDMI_WRITE(HDMI_VERTB1, vertb);
 
-	switch (state->max_bpc) {
+	switch (vc4_state->output_bpc) {
 	case 12:
 		gcp = 6;
 		gcp_en = true;
@@ -956,6 +1076,15 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi,
 		break;
 	}
 
+	/*
+	 * YCC422 is always 36-bit and not considered deep colour so
+	 * doesn't signal in GCP.
+	 */
+	if (vc4_state->output_format == VC4_HDMI_OUTPUT_YUV422) {
+		gcp = 4;
+		gcp_en = false;
+	}
+
 	reg = HDMI_READ(HDMI_DEEP_COLOR_CONFIG_1);
 	reg &= ~(VC5_HDMI_DEEP_COLOR_CONFIG_1_INIT_PACK_PHASE_MASK |
 		 VC5_HDMI_DEEP_COLOR_CONFIG_1_COLOR_DEPTH_MASK);
@@ -1023,7 +1152,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 	struct vc4_hdmi_connector_state *vc4_conn_state =
 		conn_state_to_vc4_hdmi_conn_state(conn_state);
 	struct drm_display_mode *mode = &vc4_hdmi->saved_adjusted_mode;
-	unsigned long pixel_rate = vc4_conn_state->pixel_rate;
+	unsigned long tmds_char_rate = vc4_conn_state->tmds_char_rate;
 	unsigned long bvb_rate, hsm_rate;
 	unsigned long flags;
 	int ret;
@@ -1046,7 +1175,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 	 * Additionally, the AXI clock needs to be at least 25% of
 	 * pixel clock, but HSM ends up being the limiting factor.
 	 */
-	hsm_rate = max_t(unsigned long, 120000000, (pixel_rate / 100) * 101);
+	hsm_rate = max_t(unsigned long, 120000000, (tmds_char_rate / 100) * 101);
 	ret = clk_set_min_rate(vc4_hdmi->hsm_clock, hsm_rate);
 	if (ret) {
 		DRM_ERROR("Failed to set HSM clock rate: %d\n", ret);
@@ -1059,7 +1188,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 		goto out;
 	}
 
-	ret = clk_set_rate(vc4_hdmi->pixel_clock, pixel_rate);
+	ret = clk_set_rate(vc4_hdmi->pixel_clock, tmds_char_rate);
 	if (ret) {
 		DRM_ERROR("Failed to set pixel clock rate: %d\n", ret);
 		goto err_put_runtime_pm;
@@ -1074,9 +1203,9 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder,
 
 	vc4_hdmi_cec_update_clk_div(vc4_hdmi);
 
-	if (pixel_rate > 297000000)
+	if (tmds_char_rate > 297000000)
 		bvb_rate = 300000000;
-	else if (pixel_rate > 148500000)
+	else if (tmds_char_rate > 148500000)
 		bvb_rate = 150000000;
 	else
 		bvb_rate = 75000000;
@@ -1148,7 +1277,7 @@ static void vc4_hdmi_encoder_post_crtc_enable(struct drm_encoder *encoder,
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
 	struct drm_display_mode *mode = &vc4_hdmi->saved_adjusted_mode;
-	struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder);
+	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;
@@ -1169,7 +1298,7 @@ static void vc4_hdmi_encoder_post_crtc_enable(struct drm_encoder *encoder,
 	HDMI_WRITE(HDMI_VID_CTL,
 		   HDMI_READ(HDMI_VID_CTL) & ~VC4_HD_VID_CTL_BLANKPIX);
 
-	if (vc4_encoder->hdmi_monitor) {
+	if (display->is_hdmi) {
 		HDMI_WRITE(HDMI_SCHEDULER_CONTROL,
 			   HDMI_READ(HDMI_SCHEDULER_CONTROL) |
 			   VC4_HDMI_SCHEDULER_CONTROL_MODE_HDMI);
@@ -1196,7 +1325,7 @@ static void vc4_hdmi_encoder_post_crtc_enable(struct drm_encoder *encoder,
 			  "!VC4_HDMI_SCHEDULER_CONTROL_HDMI_ACTIVE\n");
 	}
 
-	if (vc4_encoder->hdmi_monitor) {
+	if (display->is_hdmi) {
 		spin_lock_irqsave(&vc4_hdmi->hw_lock, flags);
 
 		WARN_ON(!(HDMI_READ(HDMI_SCHEDULER_CONTROL) &
@@ -1233,13 +1362,234 @@ static void vc4_hdmi_encoder_atomic_mode_set(struct drm_encoder *encoder,
 					     struct drm_connector_state *conn_state)
 {
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+	struct vc4_hdmi_connector_state *vc4_state =
+		conn_state_to_vc4_hdmi_conn_state(conn_state);
 
 	mutex_lock(&vc4_hdmi->mutex);
 	drm_mode_copy(&vc4_hdmi->saved_adjusted_mode,
 		      &crtc_state->adjusted_mode);
+	vc4_hdmi->output_bpc = vc4_state->output_bpc;
+	vc4_hdmi->output_format = vc4_state->output_format;
 	mutex_unlock(&vc4_hdmi->mutex);
 }
 
+static bool
+vc4_hdmi_sink_supports_format_bpc(const struct vc4_hdmi *vc4_hdmi,
+				  const struct drm_display_info *info,
+				  const struct drm_display_mode *mode,
+				  unsigned int format, unsigned int bpc)
+{
+	struct drm_device *dev = vc4_hdmi->connector.dev;
+	u8 vic = drm_match_cea_mode(mode);
+
+	if (vic == 1 && bpc != 8) {
+		drm_dbg(dev, "VIC1 requires a bpc of 8, got %u\n", bpc);
+		return false;
+	}
+
+	if (!info->is_hdmi &&
+	    (format != VC4_HDMI_OUTPUT_RGB || bpc != 8)) {
+		drm_dbg(dev, "DVI Monitors require an RGB output at 8 bpc\n");
+		return false;
+	}
+
+	switch (format) {
+	case VC4_HDMI_OUTPUT_RGB:
+		drm_dbg(dev, "RGB Format, checking the constraints.\n");
+
+		if (!(info->color_formats & DRM_COLOR_FORMAT_RGB444))
+			return false;
+
+		if (bpc == 10 && !(info->edid_hdmi_rgb444_dc_modes & DRM_EDID_HDMI_DC_30)) {
+			drm_dbg(dev, "10 BPC but sink doesn't support Deep Color 30.\n");
+			return false;
+		}
+
+		if (bpc == 12 && !(info->edid_hdmi_rgb444_dc_modes & DRM_EDID_HDMI_DC_36)) {
+			drm_dbg(dev, "12 BPC but sink doesn't support Deep Color 36.\n");
+			return false;
+		}
+
+		drm_dbg(dev, "RGB format supported in that configuration.\n");
+
+		return true;
+
+	case VC4_HDMI_OUTPUT_YUV422:
+		drm_dbg(dev, "YUV422 format, checking the constraints.\n");
+
+		if (!(info->color_formats & DRM_COLOR_FORMAT_YCBCR422)) {
+			drm_dbg(dev, "Sink doesn't support YUV422.\n");
+			return false;
+		}
+
+		if (bpc != 12) {
+			drm_dbg(dev, "YUV422 only supports 12 bpc.\n");
+			return false;
+		}
+
+		drm_dbg(dev, "YUV422 format supported in that configuration.\n");
+
+		return true;
+
+	case VC4_HDMI_OUTPUT_YUV444:
+		drm_dbg(dev, "YUV444 format, checking the constraints.\n");
+
+		if (!(info->color_formats & DRM_COLOR_FORMAT_YCBCR444)) {
+			drm_dbg(dev, "Sink doesn't support YUV444.\n");
+			return false;
+		}
+
+		if (bpc == 10 && !(info->edid_hdmi_ycbcr444_dc_modes & DRM_EDID_HDMI_DC_30)) {
+			drm_dbg(dev, "10 BPC but sink doesn't support Deep Color 30.\n");
+			return false;
+		}
+
+		if (bpc == 12 && !(info->edid_hdmi_ycbcr444_dc_modes & DRM_EDID_HDMI_DC_36)) {
+			drm_dbg(dev, "12 BPC but sink doesn't support Deep Color 36.\n");
+			return false;
+		}
+
+		drm_dbg(dev, "YUV444 format supported in that configuration.\n");
+
+		return true;
+	}
+
+	return false;
+}
+
+static enum drm_mode_status
+vc4_hdmi_encoder_clock_valid(const struct vc4_hdmi *vc4_hdmi,
+			     unsigned long long clock)
+{
+	const struct drm_connector *connector = &vc4_hdmi->connector;
+	const struct drm_display_info *info = &connector->display_info;
+
+	if (clock > vc4_hdmi->variant->max_pixel_clock)
+		return MODE_CLOCK_HIGH;
+
+	if (vc4_hdmi->disable_4kp60 && clock > HDMI_14_MAX_TMDS_CLK)
+		return MODE_CLOCK_HIGH;
+
+	if (info->max_tmds_clock && clock > (info->max_tmds_clock * 1000))
+		return MODE_CLOCK_HIGH;
+
+	return MODE_OK;
+}
+
+static unsigned long long
+vc4_hdmi_encoder_compute_mode_clock(const struct drm_display_mode *mode,
+				    unsigned int bpc,
+				    enum vc4_hdmi_output_format fmt)
+{
+	unsigned long long clock = mode->clock * 1000;
+
+	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
+		clock = clock * 2;
+
+	if (fmt == VC4_HDMI_OUTPUT_YUV422)
+		bpc = 8;
+
+	clock = clock * bpc;
+	do_div(clock, 8);
+
+	return clock;
+}
+
+static int
+vc4_hdmi_encoder_compute_clock(const struct vc4_hdmi *vc4_hdmi,
+			       struct vc4_hdmi_connector_state *vc4_state,
+			       const struct drm_display_mode *mode,
+			       unsigned int bpc, unsigned int fmt)
+{
+	unsigned long long clock;
+
+	clock = vc4_hdmi_encoder_compute_mode_clock(mode, bpc, fmt);
+	if (vc4_hdmi_encoder_clock_valid(vc4_hdmi, clock) != MODE_OK)
+		return -EINVAL;
+
+	vc4_state->tmds_char_rate = clock;
+
+	return 0;
+}
+
+static int
+vc4_hdmi_encoder_compute_format(const struct vc4_hdmi *vc4_hdmi,
+				struct vc4_hdmi_connector_state *vc4_state,
+				const struct drm_display_mode *mode,
+				unsigned int bpc)
+{
+	struct drm_device *dev = vc4_hdmi->connector.dev;
+	const struct drm_connector *connector = &vc4_hdmi->connector;
+	const struct drm_display_info *info = &connector->display_info;
+	unsigned int format;
+
+	drm_dbg(dev, "Trying with an RGB output\n");
+
+	format = VC4_HDMI_OUTPUT_RGB;
+	if (vc4_hdmi_sink_supports_format_bpc(vc4_hdmi, info, mode, format, bpc)) {
+		int ret;
+
+		ret = vc4_hdmi_encoder_compute_clock(vc4_hdmi, vc4_state,
+						     mode, bpc, format);
+		if (!ret) {
+			vc4_state->output_format = format;
+			return 0;
+		}
+	}
+
+	drm_dbg(dev, "Failed, Trying with an YUV422 output\n");
+
+	format = VC4_HDMI_OUTPUT_YUV422;
+	if (vc4_hdmi_sink_supports_format_bpc(vc4_hdmi, info, mode, format, bpc)) {
+		int ret;
+
+		ret = vc4_hdmi_encoder_compute_clock(vc4_hdmi, vc4_state,
+						     mode, bpc, format);
+		if (!ret) {
+			vc4_state->output_format = format;
+			return 0;
+		}
+	}
+
+	drm_dbg(dev, "Failed. No Format Supported for that bpc count.\n");
+
+	return -EINVAL;
+}
+
+static int
+vc4_hdmi_encoder_compute_config(const struct vc4_hdmi *vc4_hdmi,
+				struct vc4_hdmi_connector_state *vc4_state,
+				const struct drm_display_mode *mode)
+{
+	struct drm_device *dev = vc4_hdmi->connector.dev;
+	struct drm_connector_state *conn_state = &vc4_state->base;
+	unsigned int max_bpc = clamp_t(unsigned int, conn_state->max_bpc, 8, 12);
+	unsigned int bpc;
+	int ret;
+
+	for (bpc = max_bpc; bpc >= 8; bpc -= 2) {
+		drm_dbg(dev, "Trying with a %d bpc output\n", bpc);
+
+		ret = vc4_hdmi_encoder_compute_format(vc4_hdmi, vc4_state,
+						      mode, bpc);
+		if (ret)
+			continue;
+
+		vc4_state->output_bpc = bpc;
+
+		drm_dbg(dev,
+			"Mode %ux%u @ %uHz: Found configuration: bpc: %u, fmt: %s, clock: %llu\n",
+			mode->hdisplay, mode->vdisplay, drm_mode_vrefresh(mode),
+			vc4_state->output_bpc,
+			vc4_hdmi_output_fmt_str(vc4_state->output_format),
+			vc4_state->tmds_char_rate);
+
+		break;
+	}
+
+	return ret;
+}
+
 #define WIFI_2_4GHz_CH1_MIN_FREQ	2400000000ULL
 #define WIFI_2_4GHz_CH1_MAX_FREQ	2422000000ULL
 
@@ -1250,8 +1600,9 @@ static int vc4_hdmi_encoder_atomic_check(struct drm_encoder *encoder,
 	struct vc4_hdmi_connector_state *vc4_state = conn_state_to_vc4_hdmi_conn_state(conn_state);
 	struct drm_display_mode *mode = &crtc_state->adjusted_mode;
 	struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
-	unsigned long long pixel_rate = mode->clock * 1000;
-	unsigned long long tmds_rate;
+	unsigned long long tmds_char_rate = mode->clock * 1000;
+	unsigned long long tmds_bit_rate;
+	int ret;
 
 	if (vc4_hdmi->variant->unsupported_odd_h_timings &&
 	    !(mode->flags & DRM_MODE_FLAG_DBLCLK) &&
@@ -1265,32 +1616,17 @@ static int vc4_hdmi_encoder_atomic_check(struct drm_encoder *encoder,
 	 * bandwidth). Slightly lower the frequency to bring it out of
 	 * the WiFi range.
 	 */
-	tmds_rate = pixel_rate * 10;
+	tmds_bit_rate = tmds_char_rate * 10;
 	if (vc4_hdmi->disable_wifi_frequencies &&
-	    (tmds_rate >= WIFI_2_4GHz_CH1_MIN_FREQ &&
-	     tmds_rate <= WIFI_2_4GHz_CH1_MAX_FREQ)) {
+	    (tmds_bit_rate >= WIFI_2_4GHz_CH1_MIN_FREQ &&
+	     tmds_bit_rate <= WIFI_2_4GHz_CH1_MAX_FREQ)) {
 		mode->clock = 238560;
-		pixel_rate = mode->clock * 1000;
-	}
-
-	if (conn_state->max_bpc == 12) {
-		pixel_rate = pixel_rate * 150;
-		do_div(pixel_rate, 100);
-	} else if (conn_state->max_bpc == 10) {
-		pixel_rate = pixel_rate * 125;
-		do_div(pixel_rate, 100);
+		tmds_char_rate = mode->clock * 1000;
 	}
 
-	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
-		pixel_rate = pixel_rate * 2;
-
-	if (pixel_rate > vc4_hdmi->variant->max_pixel_clock)
-		return -EINVAL;
-
-	if (vc4_hdmi->disable_4kp60 && (pixel_rate > HDMI_14_MAX_TMDS_CLK))
-		return -EINVAL;
-
-	vc4_state->pixel_rate = pixel_rate;
+	ret = vc4_hdmi_encoder_compute_config(vc4_hdmi, vc4_state, mode);
+	if (ret)
+		return ret;
 
 	return 0;
 }
@@ -1307,13 +1643,7 @@ vc4_hdmi_encoder_mode_valid(struct drm_encoder *encoder,
 	     (mode->hsync_end % 2) || (mode->htotal % 2)))
 		return MODE_H_ILLEGAL;
 
-	if ((mode->clock * 1000) > vc4_hdmi->variant->max_pixel_clock)
-		return MODE_CLOCK_HIGH;
-
-	if (vc4_hdmi->disable_4kp60 && vc4_hdmi_mode_needs_scrambling(mode))
-		return MODE_CLOCK_HIGH;
-
-	return MODE_OK;
+	return vc4_hdmi_encoder_clock_valid(vc4_hdmi, mode->clock * 1000);
 }
 
 static const struct drm_encoder_helper_funcs vc4_hdmi_encoder_helper_funcs = {
@@ -1469,7 +1799,7 @@ static int vc4_hdmi_audio_startup(struct device *dev, void *data)
 
 static void vc4_hdmi_audio_reset(struct vc4_hdmi *vc4_hdmi)
 {
-	struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base;
+	struct drm_encoder *encoder = &vc4_hdmi->encoder.base;
 	struct device *dev = &vc4_hdmi->pdev->dev;
 	unsigned long flags;
 	int ret;
@@ -1559,7 +1889,7 @@ 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_encoder *encoder = &vc4_hdmi->encoder.base.base;
+	struct drm_encoder *encoder = &vc4_hdmi->encoder.base;
 	unsigned int sample_rate = params->sample_rate;
 	unsigned int channels = params->channels;
 	unsigned long flags;
@@ -2512,13 +2842,13 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 	INIT_DELAYED_WORK(&vc4_hdmi->scrambling_work, vc4_hdmi_scrambling_wq);
 
 	dev_set_drvdata(dev, vc4_hdmi);
-	encoder = &vc4_hdmi->encoder.base.base;
-	vc4_hdmi->encoder.base.type = variant->encoder_type;
-	vc4_hdmi->encoder.base.pre_crtc_configure = vc4_hdmi_encoder_pre_crtc_configure;
-	vc4_hdmi->encoder.base.pre_crtc_enable = vc4_hdmi_encoder_pre_crtc_enable;
-	vc4_hdmi->encoder.base.post_crtc_enable = vc4_hdmi_encoder_post_crtc_enable;
-	vc4_hdmi->encoder.base.post_crtc_disable = vc4_hdmi_encoder_post_crtc_disable;
-	vc4_hdmi->encoder.base.post_crtc_powerdown = vc4_hdmi_encoder_post_crtc_powerdown;
+	encoder = &vc4_hdmi->encoder.base;
+	vc4_hdmi->encoder.type = variant->encoder_type;
+	vc4_hdmi->encoder.pre_crtc_configure = vc4_hdmi_encoder_pre_crtc_configure;
+	vc4_hdmi->encoder.pre_crtc_enable = vc4_hdmi_encoder_pre_crtc_enable;
+	vc4_hdmi->encoder.post_crtc_enable = vc4_hdmi_encoder_post_crtc_enable;
+	vc4_hdmi->encoder.post_crtc_disable = vc4_hdmi_encoder_post_crtc_disable;
+	vc4_hdmi->encoder.post_crtc_powerdown = vc4_hdmi_encoder_post_crtc_powerdown;
 	vc4_hdmi->pdev = pdev;
 	vc4_hdmi->variant = variant;
 
@@ -2569,19 +2899,6 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 	}
 
 	/*
-	 * If we boot without any cable connected to the HDMI connector,
-	 * the firmware will skip the HSM initialization and leave it
-	 * with a rate of 0, resulting in a bus lockup when we're
-	 * accessing the registers even if it's enabled.
-	 *
-	 * Let's put a sensible default at runtime_resume so that we
-	 * don't end up in this situation.
-	 */
-	ret = clk_set_min_rate(vc4_hdmi->hsm_clock, HSM_MIN_CLOCK_FREQ);
-	if (ret)
-		goto err_put_ddc;
-
-	/*
 	 * We need to have the device powered up at this point to call
 	 * our reset hook and for the CEC init.
 	 */
@@ -2680,7 +2997,7 @@ static void vc4_hdmi_unbind(struct device *dev, struct device *master,
 	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.base);
+	drm_encoder_cleanup(&vc4_hdmi->encoder.base);
 
 	pm_runtime_disable(dev);
 
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h
index 1076faeab616..51b27dcdcd9b 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.h
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.h
@@ -8,18 +8,6 @@
 
 #include "vc4_drv.h"
 
-/* VC4 HDMI encoder KMS struct */
-struct vc4_hdmi_encoder {
-	struct vc4_encoder base;
-	bool hdmi_monitor;
-};
-
-static inline struct vc4_hdmi_encoder *
-to_vc4_hdmi_encoder(struct drm_encoder *encoder)
-{
-	return container_of(encoder, struct vc4_hdmi_encoder, base.base);
-}
-
 struct vc4_hdmi;
 struct vc4_hdmi_register;
 struct vc4_hdmi_connector_state;
@@ -121,6 +109,13 @@ struct vc4_hdmi_audio {
 	bool streaming;
 };
 
+enum vc4_hdmi_output_format {
+	VC4_HDMI_OUTPUT_RGB,
+	VC4_HDMI_OUTPUT_YUV422,
+	VC4_HDMI_OUTPUT_YUV444,
+	VC4_HDMI_OUTPUT_YUV420,
+};
+
 /* General HDMI hardware state. */
 struct vc4_hdmi {
 	struct vc4_hdmi_audio audio;
@@ -128,7 +123,7 @@ struct vc4_hdmi {
 	struct platform_device *pdev;
 	const struct vc4_hdmi_variant *variant;
 
-	struct vc4_hdmi_encoder encoder;
+	struct vc4_encoder encoder;
 	struct drm_connector connector;
 
 	struct delayed_work scrambling_work;
@@ -220,6 +215,18 @@ struct vc4_hdmi {
 	 * the scrambler on? Protected by @mutex.
 	 */
 	bool scdc_enabled;
+
+	/**
+	 * @output_bpc: Copy of @vc4_connector_state.output_bpc for use
+	 * outside of KMS hooks. Protected by @mutex.
+	 */
+	unsigned int output_bpc;
+
+	/**
+	 * @output_format: Copy of @vc4_connector_state.output_format
+	 * for use outside of KMS hooks. Protected by @mutex.
+	 */
+	enum vc4_hdmi_output_format output_format;
 };
 
 static inline struct vc4_hdmi *
@@ -231,14 +238,15 @@ connector_to_vc4_hdmi(struct drm_connector *connector)
 static inline struct vc4_hdmi *
 encoder_to_vc4_hdmi(struct drm_encoder *encoder)
 {
-	struct vc4_hdmi_encoder *_encoder = to_vc4_hdmi_encoder(encoder);
-
+	struct vc4_encoder *_encoder = to_vc4_encoder(encoder);
 	return container_of(_encoder, struct vc4_hdmi, encoder);
 }
 
 struct vc4_hdmi_connector_state {
 	struct drm_connector_state	base;
-	unsigned long long		pixel_rate;
+	unsigned long long		tmds_char_rate;
+	unsigned int 			output_bpc;
+	enum vc4_hdmi_output_format	output_format;
 };
 
 static inline struct vc4_hdmi_connector_state *
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi_phy.c b/drivers/gpu/drm/vc4/vc4_hdmi_phy.c
index 62148f0dc284..ec24999bf96d 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi_phy.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi_phy.c
@@ -365,7 +365,7 @@ void vc5_hdmi_phy_init(struct vc4_hdmi *vc4_hdmi,
 {
 	const struct phy_lane_settings *chan0_settings, *chan1_settings, *chan2_settings, *clock_settings;
 	const struct vc4_hdmi_variant *variant = vc4_hdmi->variant;
-	unsigned long long pixel_freq = conn_state->pixel_rate;
+	unsigned long long pixel_freq = conn_state->tmds_char_rate;
 	unsigned long long vco_freq;
 	unsigned char word_sel;
 	unsigned long flags;
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi_regs.h b/drivers/gpu/drm/vc4/vc4_hdmi_regs.h
index fc971506bd4f..a040356b6bdc 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_hdmi_regs.h
@@ -54,6 +54,7 @@ enum vc4_hdmi_field {
 	HDMI_CSC_24_23,
 	HDMI_CSC_32_31,
 	HDMI_CSC_34_33,
+	HDMI_CSC_CHANNEL_CTL,
 	HDMI_CSC_CTL,
 
 	/*
@@ -119,6 +120,7 @@ enum vc4_hdmi_field {
 	HDMI_TX_PHY_POWERDOWN_CTL,
 	HDMI_TX_PHY_RESET_CTL,
 	HDMI_TX_PHY_TMDS_CLK_WORD_SEL,
+	HDMI_VEC_INTERFACE_CFG,
 	HDMI_VEC_INTERFACE_XBAR,
 	HDMI_VERTA0,
 	HDMI_VERTA1,
@@ -244,6 +246,7 @@ static const struct vc4_hdmi_register __maybe_unused vc5_hdmi_hdmi0_fields[] = {
 	VC4_HDMI_REG(HDMI_SCRAMBLER_CTL, 0x1c4),
 
 	VC5_DVP_REG(HDMI_CLOCK_STOP, 0x0bc),
+	VC5_DVP_REG(HDMI_VEC_INTERFACE_CFG, 0x0ec),
 	VC5_DVP_REG(HDMI_VEC_INTERFACE_XBAR, 0x0f0),
 
 	VC5_PHY_REG(HDMI_TX_PHY_RESET_CTL, 0x000),
@@ -289,6 +292,7 @@ static const struct vc4_hdmi_register __maybe_unused vc5_hdmi_hdmi0_fields[] = {
 	VC5_CSC_REG(HDMI_CSC_24_23, 0x010),
 	VC5_CSC_REG(HDMI_CSC_32_31, 0x014),
 	VC5_CSC_REG(HDMI_CSC_34_33, 0x018),
+	VC5_CSC_REG(HDMI_CSC_CHANNEL_CTL, 0x02c),
 };
 
 static const struct vc4_hdmi_register __maybe_unused vc5_hdmi_hdmi1_fields[] = {
@@ -324,6 +328,7 @@ static const struct vc4_hdmi_register __maybe_unused vc5_hdmi_hdmi1_fields[] = {
 	VC4_HDMI_REG(HDMI_SCRAMBLER_CTL, 0x1c4),
 
 	VC5_DVP_REG(HDMI_CLOCK_STOP, 0x0bc),
+	VC5_DVP_REG(HDMI_VEC_INTERFACE_CFG, 0x0ec),
 	VC5_DVP_REG(HDMI_VEC_INTERFACE_XBAR, 0x0f0),
 
 	VC5_PHY_REG(HDMI_TX_PHY_RESET_CTL, 0x000),
@@ -369,6 +374,7 @@ static const struct vc4_hdmi_register __maybe_unused vc5_hdmi_hdmi1_fields[] = {
 	VC5_CSC_REG(HDMI_CSC_24_23, 0x010),
 	VC5_CSC_REG(HDMI_CSC_32_31, 0x014),
 	VC5_CSC_REG(HDMI_CSC_34_33, 0x018),
+	VC5_CSC_REG(HDMI_CSC_CHANNEL_CTL, 0x02c),
 };
 
 static inline
diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c
index 604933e20e6a..2a58fc421cf6 100644
--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -64,22 +64,21 @@ static const struct debugfs_reg32 hvs_regs[] = {
 	VC4_REG32(SCALER_OLEDCOEF2),
 };
 
-void vc4_hvs_dump_state(struct drm_device *dev)
+void vc4_hvs_dump_state(struct vc4_hvs *hvs)
 {
-	struct vc4_dev *vc4 = to_vc4_dev(dev);
-	struct drm_printer p = drm_info_printer(&vc4->hvs->pdev->dev);
+	struct drm_printer p = drm_info_printer(&hvs->pdev->dev);
 	int i;
 
-	drm_print_regset32(&p, &vc4->hvs->regset);
+	drm_print_regset32(&p, &hvs->regset);
 
 	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",
 			 i * 4, i < HVS_BOOTLOADER_DLIST_END ? "B" : "D",
-			 readl((u32 __iomem *)vc4->hvs->dlist + i + 0),
-			 readl((u32 __iomem *)vc4->hvs->dlist + i + 1),
-			 readl((u32 __iomem *)vc4->hvs->dlist + i + 2),
-			 readl((u32 __iomem *)vc4->hvs->dlist + i + 3));
+			 readl((u32 __iomem *)hvs->dlist + i + 0),
+			 readl((u32 __iomem *)hvs->dlist + i + 1),
+			 readl((u32 __iomem *)hvs->dlist + i + 2),
+			 readl((u32 __iomem *)hvs->dlist + i + 3));
 	}
 }
 
@@ -157,11 +156,10 @@ static int vc4_hvs_upload_linear_kernel(struct vc4_hvs *hvs,
 	return 0;
 }
 
-static void vc4_hvs_lut_load(struct drm_crtc *crtc)
+static void vc4_hvs_lut_load(struct vc4_hvs *hvs,
+			     struct vc4_crtc *vc4_crtc)
 {
-	struct drm_device *dev = crtc->dev;
-	struct vc4_dev *vc4 = to_vc4_dev(dev);
-	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
+	struct drm_crtc *crtc = &vc4_crtc->base;
 	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
 	u32 i;
 
@@ -181,11 +179,12 @@ static void vc4_hvs_lut_load(struct drm_crtc *crtc)
 		HVS_WRITE(SCALER_GAMDATA, vc4_crtc->lut_b[i]);
 }
 
-static void vc4_hvs_update_gamma_lut(struct drm_crtc *crtc)
+static void vc4_hvs_update_gamma_lut(struct vc4_hvs *hvs,
+				     struct vc4_crtc *vc4_crtc)
 {
-	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
-	struct drm_color_lut *lut = crtc->state->gamma_lut->data;
-	u32 length = drm_color_lut_size(crtc->state->gamma_lut);
+	struct drm_crtc_state *crtc_state = vc4_crtc->base.state;
+	struct drm_color_lut *lut = crtc_state->gamma_lut->data;
+	u32 length = drm_color_lut_size(crtc_state->gamma_lut);
 	u32 i;
 
 	for (i = 0; i < length; i++) {
@@ -194,16 +193,37 @@ static void vc4_hvs_update_gamma_lut(struct drm_crtc *crtc)
 		vc4_crtc->lut_b[i] = drm_color_lut_extract(lut[i].blue, 8);
 	}
 
-	vc4_hvs_lut_load(crtc);
+	vc4_hvs_lut_load(hvs, vc4_crtc);
 }
 
-int vc4_hvs_get_fifo_from_output(struct drm_device *dev, unsigned int output)
+u8 vc4_hvs_get_fifo_frame_count(struct vc4_hvs *hvs, unsigned int fifo)
+{
+	u8 field = 0;
+
+	switch (fifo) {
+	case 0:
+		field = VC4_GET_FIELD(HVS_READ(SCALER_DISPSTAT1),
+				      SCALER_DISPSTAT1_FRCNT0);
+		break;
+	case 1:
+		field = VC4_GET_FIELD(HVS_READ(SCALER_DISPSTAT1),
+				      SCALER_DISPSTAT1_FRCNT1);
+		break;
+	case 2:
+		field = VC4_GET_FIELD(HVS_READ(SCALER_DISPSTAT2),
+				      SCALER_DISPSTAT2_FRCNT2);
+		break;
+	}
+
+	return field;
+}
+
+int vc4_hvs_get_fifo_from_output(struct vc4_hvs *hvs, unsigned int output)
 {
-	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	u32 reg;
 	int ret;
 
-	if (!vc4->hvs->hvs5)
+	if (!hvs->hvs5)
 		return output;
 
 	switch (output) {
@@ -250,9 +270,10 @@ int vc4_hvs_get_fifo_from_output(struct drm_device *dev, unsigned int output)
 	}
 }
 
-static int vc4_hvs_init_channel(struct vc4_dev *vc4, struct drm_crtc *crtc,
+static int vc4_hvs_init_channel(struct vc4_hvs *hvs, struct drm_crtc *crtc,
 				struct drm_display_mode *mode, bool oneshot)
 {
+	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;
@@ -270,7 +291,7 @@ static int vc4_hvs_init_channel(struct vc4_dev *vc4, struct drm_crtc *crtc,
 	 */
 	dispctrl = SCALER_DISPCTRLX_ENABLE;
 
-	if (!vc4->hvs->hvs5)
+	if (!hvs->hvs5)
 		dispctrl |= VC4_SET_FIELD(mode->hdisplay,
 					  SCALER_DISPCTRLX_WIDTH) |
 			    VC4_SET_FIELD(mode->vdisplay,
@@ -291,21 +312,19 @@ static int vc4_hvs_init_channel(struct vc4_dev *vc4, struct drm_crtc *crtc,
 
 	HVS_WRITE(SCALER_DISPBKGNDX(chan), dispbkgndx |
 		  SCALER_DISPBKGND_AUTOHS |
-		  ((!vc4->hvs->hvs5) ? SCALER_DISPBKGND_GAMMA : 0) |
+		  ((!hvs->hvs5) ? SCALER_DISPBKGND_GAMMA : 0) |
 		  (interlace ? SCALER_DISPBKGND_INTERLACE : 0));
 
 	/* Reload the LUT, since the SRAMs would have been disabled if
 	 * all CRTCs had SCALER_DISPBKGND_GAMMA unset at once.
 	 */
-	vc4_hvs_lut_load(crtc);
+	vc4_hvs_lut_load(hvs, vc4_crtc);
 
 	return 0;
 }
 
-void vc4_hvs_stop_channel(struct drm_device *dev, unsigned int chan)
+void vc4_hvs_stop_channel(struct vc4_hvs *hvs, unsigned int chan)
 {
-	struct vc4_dev *vc4 = to_vc4_dev(dev);
-
 	if (HVS_READ(SCALER_DISPCTRLX(chan)) & SCALER_DISPCTRLX_ENABLE)
 		return;
 
@@ -359,10 +378,20 @@ int vc4_hvs_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state)
 	return 0;
 }
 
-static void vc4_hvs_update_dlist(struct drm_crtc *crtc)
+static void vc4_hvs_install_dlist(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	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);
+
+	HVS_WRITE(SCALER_DISPLISTX(vc4_state->assigned_channel),
+		  vc4_state->mm.start);
+}
+
+static void vc4_hvs_update_dlist(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
 	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
 	unsigned long flags;
@@ -379,13 +408,7 @@ static void vc4_hvs_update_dlist(struct drm_crtc *crtc)
 			crtc->state->event = NULL;
 		}
 
-		HVS_WRITE(SCALER_DISPLISTX(vc4_state->assigned_channel),
-			  vc4_state->mm.start);
-
 		spin_unlock_irqrestore(&dev->event_lock, flags);
-	} else {
-		HVS_WRITE(SCALER_DISPLISTX(vc4_state->assigned_channel),
-			  vc4_state->mm.start);
 	}
 
 	spin_lock_irqsave(&vc4_crtc->irq_lock, flags);
@@ -414,19 +437,21 @@ void vc4_hvs_atomic_enable(struct drm_crtc *crtc,
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
 	bool oneshot = vc4_crtc->feeds_txp;
 
+	vc4_hvs_install_dlist(crtc);
 	vc4_hvs_update_dlist(crtc);
-	vc4_hvs_init_channel(vc4, crtc, mode, oneshot);
+	vc4_hvs_init_channel(vc4->hvs, crtc, mode, oneshot);
 }
 
 void vc4_hvs_atomic_disable(struct drm_crtc *crtc,
 			    struct drm_atomic_state *state)
 {
 	struct drm_device *dev = crtc->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_crtc_state *old_state = drm_atomic_get_old_crtc_state(state, crtc);
 	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(old_state);
 	unsigned int chan = vc4_state->assigned_channel;
 
-	vc4_hvs_stop_channel(dev, chan);
+	vc4_hvs_stop_channel(vc4->hvs, chan);
 }
 
 void vc4_hvs_atomic_flush(struct drm_crtc *crtc,
@@ -436,7 +461,10 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc,
 									 crtc);
 	struct drm_device *dev = crtc->dev;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_hvs *hvs = vc4->hvs;
+	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
 	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
+	unsigned int channel = vc4_state->assigned_channel;
 	struct drm_plane *plane;
 	struct vc4_plane_state *vc4_plane_state;
 	bool debug_dump_regs = false;
@@ -446,7 +474,7 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc,
 
 	if (debug_dump_regs) {
 		DRM_INFO("CRTC %d HVS before:\n", drm_crtc_index(crtc));
-		vc4_hvs_dump_state(dev);
+		vc4_hvs_dump_state(hvs);
 	}
 
 	/* Copy all the active planes' dlist contents to the hardware dlist. */
@@ -477,8 +505,8 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc,
 		/* This sets a black background color fill, as is the case
 		 * with other DRM drivers.
 		 */
-		HVS_WRITE(SCALER_DISPBKGNDX(vc4_state->assigned_channel),
-			  HVS_READ(SCALER_DISPBKGNDX(vc4_state->assigned_channel)) |
+		HVS_WRITE(SCALER_DISPBKGNDX(channel),
+			  HVS_READ(SCALER_DISPBKGNDX(channel)) |
 			  SCALER_DISPBKGND_FILL);
 
 	/* Only update DISPLIST if the CRTC was already running and is not
@@ -488,14 +516,16 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc,
 	 * If the CRTC is being disabled, there's no point in updating this
 	 * information.
 	 */
-	if (crtc->state->active && old_state->active)
+	if (crtc->state->active && old_state->active) {
+		vc4_hvs_install_dlist(crtc);
 		vc4_hvs_update_dlist(crtc);
+	}
 
 	if (crtc->state->color_mgmt_changed) {
-		u32 dispbkgndx = HVS_READ(SCALER_DISPBKGNDX(vc4_state->assigned_channel));
+		u32 dispbkgndx = HVS_READ(SCALER_DISPBKGNDX(channel));
 
 		if (crtc->state->gamma_lut) {
-			vc4_hvs_update_gamma_lut(crtc);
+			vc4_hvs_update_gamma_lut(hvs, vc4_crtc);
 			dispbkgndx |= SCALER_DISPBKGND_GAMMA;
 		} else {
 			/* Unsetting DISPBKGND_GAMMA skips the gamma lut step
@@ -504,18 +534,17 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc,
 			 */
 			dispbkgndx &= ~SCALER_DISPBKGND_GAMMA;
 		}
-		HVS_WRITE(SCALER_DISPBKGNDX(vc4_state->assigned_channel), dispbkgndx);
+		HVS_WRITE(SCALER_DISPBKGNDX(channel), dispbkgndx);
 	}
 
 	if (debug_dump_regs) {
 		DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc));
-		vc4_hvs_dump_state(dev);
+		vc4_hvs_dump_state(hvs);
 	}
 }
 
-void vc4_hvs_mask_underrun(struct drm_device *dev, int channel)
+void vc4_hvs_mask_underrun(struct vc4_hvs *hvs, int channel)
 {
-	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	u32 dispctrl = HVS_READ(SCALER_DISPCTRL);
 
 	dispctrl &= ~SCALER_DISPCTRL_DSPEISLUR(channel);
@@ -523,9 +552,8 @@ void vc4_hvs_mask_underrun(struct drm_device *dev, int channel)
 	HVS_WRITE(SCALER_DISPCTRL, dispctrl);
 }
 
-void vc4_hvs_unmask_underrun(struct drm_device *dev, int channel)
+void vc4_hvs_unmask_underrun(struct vc4_hvs *hvs, int channel)
 {
-	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	u32 dispctrl = HVS_READ(SCALER_DISPCTRL);
 
 	dispctrl |= SCALER_DISPCTRL_DSPEISLUR(channel);
@@ -547,6 +575,7 @@ static irqreturn_t vc4_hvs_irq_handler(int irq, void *data)
 {
 	struct drm_device *dev = data;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_hvs *hvs = vc4->hvs;
 	irqreturn_t irqret = IRQ_NONE;
 	int channel;
 	u32 control;
@@ -559,7 +588,7 @@ static irqreturn_t vc4_hvs_irq_handler(int irq, void *data)
 		/* Interrupt masking is not always honored, so check it here. */
 		if (status & SCALER_DISPSTAT_EUFLOW(channel) &&
 		    control & SCALER_DISPCTRL_DSPEISLUR(channel)) {
-			vc4_hvs_mask_underrun(dev, channel);
+			vc4_hvs_mask_underrun(hvs, channel);
 			vc4_hvs_report_underrun(dev);
 
 			irqret = IRQ_HANDLED;
@@ -582,6 +611,7 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 	struct vc4_hvs *hvs = NULL;
 	int ret;
 	u32 dispctrl;
+	u32 reg;
 
 	hvs = devm_kzalloc(&pdev->dev, sizeof(*hvs), GFP_KERNEL);
 	if (!hvs)
@@ -653,6 +683,26 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 
 	vc4->hvs = hvs;
 
+	reg = HVS_READ(SCALER_DISPECTRL);
+	reg &= ~SCALER_DISPECTRL_DSP2_MUX_MASK;
+	HVS_WRITE(SCALER_DISPECTRL,
+		  reg | VC4_SET_FIELD(0, SCALER_DISPECTRL_DSP2_MUX));
+
+	reg = HVS_READ(SCALER_DISPCTRL);
+	reg &= ~SCALER_DISPCTRL_DSP3_MUX_MASK;
+	HVS_WRITE(SCALER_DISPCTRL,
+		  reg | VC4_SET_FIELD(3, SCALER_DISPCTRL_DSP3_MUX));
+
+	reg = HVS_READ(SCALER_DISPEOLN);
+	reg &= ~SCALER_DISPEOLN_DSP4_MUX_MASK;
+	HVS_WRITE(SCALER_DISPEOLN,
+		  reg | VC4_SET_FIELD(3, SCALER_DISPEOLN_DSP4_MUX));
+
+	reg = HVS_READ(SCALER_DISPDITHER);
+	reg &= ~SCALER_DISPDITHER_DSP5_MUX_MASK;
+	HVS_WRITE(SCALER_DISPDITHER,
+		  reg | VC4_SET_FIELD(3, SCALER_DISPDITHER_DSP5_MUX));
+
 	dispctrl = HVS_READ(SCALER_DISPCTRL);
 
 	dispctrl |= SCALER_DISPCTRL_ENABLE;
@@ -660,10 +710,6 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 		    SCALER_DISPCTRL_DISPEIRQ(1) |
 		    SCALER_DISPCTRL_DISPEIRQ(2);
 
-	/* Set DSP3 (PV1) to use HVS channel 2, which would otherwise
-	 * be unused.
-	 */
-	dispctrl &= ~SCALER_DISPCTRL_DSP3_MUX_MASK;
 	dispctrl &= ~(SCALER_DISPCTRL_DMAEIRQ |
 		      SCALER_DISPCTRL_SLVWREIRQ |
 		      SCALER_DISPCTRL_SLVRDEIRQ |
@@ -677,7 +723,6 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 		      SCALER_DISPCTRL_DSPEISLUR(1) |
 		      SCALER_DISPCTRL_DSPEISLUR(2) |
 		      SCALER_DISPCTRL_SCLEIRQ);
-	dispctrl |= VC4_SET_FIELD(2, SCALER_DISPCTRL_DSP3_MUX);
 
 	HVS_WRITE(SCALER_DISPCTRL, dispctrl);
 
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index 20fa8e34c20b..4342fb43e8c1 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -51,6 +51,7 @@
 
 #include "vc4_drv.h"
 #include "vc4_regs.h"
+#include "vc4_trace.h"
 
 #define V3D_DRIVER_IRQS (V3D_INT_OUTOMEM | \
 			 V3D_INT_FLDONE | \
@@ -123,6 +124,8 @@ vc4_irq_finish_bin_job(struct drm_device *dev)
 	if (!exec)
 		return;
 
+	trace_vc4_bcl_end_irq(dev, exec->seqno);
+
 	vc4_move_job_to_render(dev, exec);
 	next = vc4_first_bin_job(vc4);
 
@@ -161,6 +164,8 @@ vc4_irq_finish_render_job(struct drm_device *dev)
 	if (!exec)
 		return;
 
+	trace_vc4_rcl_end_irq(dev, exec->seqno);
+
 	vc4->finished_seqno++;
 	list_move_tail(&exec->head, &vc4->job_done_list);
 
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index 24de29bc1cda..c169bd72e53b 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -32,7 +32,8 @@ struct vc4_ctm_state {
 	int fifo;
 };
 
-static struct vc4_ctm_state *to_vc4_ctm_state(struct drm_private_state *priv)
+static struct vc4_ctm_state *
+to_vc4_ctm_state(const struct drm_private_state *priv)
 {
 	return container_of(priv, struct vc4_ctm_state, base);
 }
@@ -49,7 +50,7 @@ struct vc4_hvs_state {
 };
 
 static struct vc4_hvs_state *
-to_vc4_hvs_state(struct drm_private_state *priv)
+to_vc4_hvs_state(const struct drm_private_state *priv)
 {
 	return container_of(priv, struct vc4_hvs_state, base);
 }
@@ -61,7 +62,7 @@ struct vc4_load_tracker_state {
 };
 
 static struct vc4_load_tracker_state *
-to_vc4_load_tracker_state(struct drm_private_state *priv)
+to_vc4_load_tracker_state(const struct drm_private_state *priv)
 {
 	return container_of(priv, struct vc4_load_tracker_state, base);
 }
@@ -157,6 +158,7 @@ static u16 vc4_ctm_s31_32_to_s0_9(u64 in)
 static void
 vc4_ctm_commit(struct vc4_dev *vc4, struct drm_atomic_state *state)
 {
+	struct vc4_hvs *hvs = vc4->hvs;
 	struct vc4_ctm_state *ctm_state = to_vc4_ctm_state(vc4->ctm_manager.state);
 	struct drm_color_ctm *ctm = ctm_state->ctm;
 
@@ -230,6 +232,7 @@ vc4_hvs_get_global_state(struct drm_atomic_state *state)
 static void vc4_hvs_pv_muxing_commit(struct vc4_dev *vc4,
 				     struct drm_atomic_state *state)
 {
+	struct vc4_hvs *hvs = vc4->hvs;
 	struct drm_crtc_state *crtc_state;
 	struct drm_crtc *crtc;
 	unsigned int i;
@@ -270,6 +273,7 @@ static void vc4_hvs_pv_muxing_commit(struct vc4_dev *vc4,
 static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4,
 				     struct drm_atomic_state *state)
 {
+	struct vc4_hvs *hvs = vc4->hvs;
 	struct drm_crtc_state *crtc_state;
 	struct drm_crtc *crtc;
 	unsigned char mux;
@@ -279,13 +283,18 @@ static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4,
 	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
 		struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc_state);
 		struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
+		unsigned int channel = vc4_state->assigned_channel;
 
 		if (!vc4_state->update_muxing)
 			continue;
 
 		switch (vc4_crtc->data->hvs_output) {
 		case 2:
-			mux = (vc4_state->assigned_channel == 2) ? 0 : 1;
+			drm_WARN_ON(&vc4->base,
+				    VC4_GET_FIELD(HVS_READ(SCALER_DISPCTRL),
+						  SCALER_DISPCTRL_DSP3_MUX) == channel);
+
+			mux = (channel == 2) ? 0 : 1;
 			reg = HVS_READ(SCALER_DISPECTRL);
 			HVS_WRITE(SCALER_DISPECTRL,
 				  (reg & ~SCALER_DISPECTRL_DSP2_MUX_MASK) |
@@ -293,10 +302,10 @@ static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4,
 			break;
 
 		case 3:
-			if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED)
+			if (channel == VC4_HVS_CHANNEL_DISABLED)
 				mux = 3;
 			else
-				mux = vc4_state->assigned_channel;
+				mux = channel;
 
 			reg = HVS_READ(SCALER_DISPCTRL);
 			HVS_WRITE(SCALER_DISPCTRL,
@@ -305,10 +314,10 @@ static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4,
 			break;
 
 		case 4:
-			if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED)
+			if (channel == VC4_HVS_CHANNEL_DISABLED)
 				mux = 3;
 			else
-				mux = vc4_state->assigned_channel;
+				mux = channel;
 
 			reg = HVS_READ(SCALER_DISPEOLN);
 			HVS_WRITE(SCALER_DISPEOLN,
@@ -318,10 +327,10 @@ static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4,
 			break;
 
 		case 5:
-			if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED)
+			if (channel == VC4_HVS_CHANNEL_DISABLED)
 				mux = 3;
 			else
-				mux = vc4_state->assigned_channel;
+				mux = channel;
 
 			reg = HVS_READ(SCALER_DISPDITHER);
 			HVS_WRITE(SCALER_DISPDITHER,
@@ -362,7 +371,7 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state)
 			continue;
 
 		vc4_crtc_state = to_vc4_crtc_state(new_crtc_state);
-		vc4_hvs_mask_underrun(dev, vc4_crtc_state->assigned_channel);
+		vc4_hvs_mask_underrun(hvs, vc4_crtc_state->assigned_channel);
 	}
 
 	for (channel = 0; channel < HVS_NUM_CHANNELS; channel++) {
@@ -385,12 +394,20 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state)
 	}
 
 	if (vc4->hvs->hvs5) {
+		unsigned long state_rate = max(old_hvs_state->core_clock_rate,
+					       new_hvs_state->core_clock_rate);
 		unsigned long core_rate = max_t(unsigned long,
-						500000000,
-						new_hvs_state->core_clock_rate);
+						500000000, state_rate);
 
+		drm_dbg(dev, "Raising the core clock at %lu Hz\n", core_rate);
+
+		/*
+		 * Do a temporary request on the core clock during the
+		 * modeset.
+		 */
 		clk_set_min_rate(hvs->core_clk, core_rate);
 	}
+
 	drm_atomic_helper_commit_modeset_disables(dev, state);
 
 	vc4_ctm_commit(vc4, state);
@@ -400,7 +417,8 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state)
 	else
 		vc4_hvs_pv_muxing_commit(vc4, state);
 
-	drm_atomic_helper_commit_planes(dev, state, 0);
+	drm_atomic_helper_commit_planes(dev, state,
+					DRM_PLANE_COMMIT_ACTIVE_ONLY);
 
 	drm_atomic_helper_commit_modeset_enables(dev, state);
 
@@ -416,7 +434,14 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state)
 		drm_dbg(dev, "Running the core clock at %lu Hz\n",
 			new_hvs_state->core_clock_rate);
 
+		/*
+		 * Request a clock rate based on the current HVS
+		 * requirements.
+		 */
 		clk_set_min_rate(hvs->core_clk, new_hvs_state->core_clock_rate);
+
+		drm_dbg(dev, "Core clock actual rate: %lu Hz\n",
+			clk_get_rate(hvs->core_clk));
 	}
 }
 
@@ -700,9 +725,26 @@ static void vc4_hvs_channels_destroy_state(struct drm_private_obj *obj,
 	kfree(hvs_state);
 }
 
+static void vc4_hvs_channels_print_state(struct drm_printer *p,
+					 const struct drm_private_state *state)
+{
+	struct vc4_hvs_state *hvs_state = to_vc4_hvs_state(state);
+	unsigned int i;
+
+	drm_printf(p, "HVS State\n");
+	drm_printf(p, "\tCore Clock Rate: %lu\n", hvs_state->core_clock_rate);
+
+	for (i = 0; i < HVS_NUM_CHANNELS; i++) {
+		drm_printf(p, "\tChannel %d\n", i);
+		drm_printf(p, "\t\tin use=%d\n", hvs_state->fifo_state[i].in_use);
+		drm_printf(p, "\t\tload=%lu\n", hvs_state->fifo_state[i].fifo_load);
+	}
+}
+
 static const struct drm_private_state_funcs vc4_hvs_state_funcs = {
 	.atomic_duplicate_state = vc4_hvs_channels_duplicate_state,
 	.atomic_destroy_state = vc4_hvs_channels_destroy_state,
+	.atomic_print_state = vc4_hvs_channels_print_state,
 };
 
 static void vc4_hvs_channels_obj_fini(struct drm_device *dev, void *unused)
@@ -783,9 +825,18 @@ static int vc4_pv_muxing_atomic_check(struct drm_device *dev,
 		unsigned int matching_channels;
 		unsigned int channel;
 
+		drm_dbg(dev, "%s: Trying to find a channel.\n", crtc->name);
+
 		/* Nothing to do here, let's skip it */
-		if (old_crtc_state->enable == new_crtc_state->enable)
+		if (old_crtc_state->enable == new_crtc_state->enable) {
+			if (new_crtc_state->enable)
+				drm_dbg(dev, "%s: Already enabled, reusing channel %d.\n",
+					crtc->name, new_vc4_crtc_state->assigned_channel);
+			else
+				drm_dbg(dev, "%s: Disabled, ignoring.\n", crtc->name);
+
 			continue;
+		}
 
 		/* Muxing will need to be modified, mark it as such */
 		new_vc4_crtc_state->update_muxing = true;
@@ -793,6 +844,10 @@ static int vc4_pv_muxing_atomic_check(struct drm_device *dev,
 		/* If we're disabling our CRTC, we put back our channel */
 		if (!new_crtc_state->enable) {
 			channel = old_vc4_crtc_state->assigned_channel;
+
+			drm_dbg(dev, "%s: Disabling, Freeing channel %d\n",
+				crtc->name, channel);
+
 			hvs_new_state->fifo_state[channel].in_use = false;
 			new_vc4_crtc_state->assigned_channel = VC4_HVS_CHANNEL_DISABLED;
 			continue;
@@ -827,6 +882,8 @@ static int vc4_pv_muxing_atomic_check(struct drm_device *dev,
 			return -EINVAL;
 
 		channel = ffs(matching_channels) - 1;
+
+		drm_dbg(dev, "Assigned HVS channel %d to CRTC %s\n", channel, crtc->name);
 		new_vc4_crtc_state->assigned_channel = channel;
 		unassigned_channels &= ~BIT(channel);
 		hvs_new_state->fifo_state[channel].in_use = true;
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 920a9eefe426..b3438f4a81ce 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -1350,7 +1350,6 @@ static int vc4_prepare_fb(struct drm_plane *plane,
 			  struct drm_plane_state *state)
 {
 	struct vc4_bo *bo;
-	int ret;
 
 	if (!state->fb)
 		return 0;
@@ -1362,11 +1361,7 @@ static int vc4_prepare_fb(struct drm_plane *plane,
 	if (plane->state->fb == state->fb)
 		return 0;
 
-	ret = vc4_bo_inc_usecnt(bo);
-	if (ret)
-		return ret;
-
-	return 0;
+	return vc4_bo_inc_usecnt(bo);
 }
 
 static void vc4_cleanup_fb(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index 33410718089e..a2b5cbbbc1b0 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -379,8 +379,6 @@
 # define SCALER_DISPSTATX_MODE_EOF		3
 # define SCALER_DISPSTATX_FULL			BIT(29)
 # define SCALER_DISPSTATX_EMPTY			BIT(28)
-# define SCALER_DISPSTATX_FRAME_COUNT_MASK	VC4_MASK(17, 12)
-# define SCALER_DISPSTATX_FRAME_COUNT_SHIFT	12
 # define SCALER_DISPSTATX_LINE_MASK		VC4_MASK(11, 0)
 # define SCALER_DISPSTATX_LINE_SHIFT		0
 
@@ -403,9 +401,15 @@
 						 (x) * (SCALER_DISPBKGND1 - \
 							SCALER_DISPBKGND0))
 #define SCALER_DISPSTAT1                        0x00000058
+# define SCALER_DISPSTAT1_FRCNT0_MASK		VC4_MASK(23, 18)
+# define SCALER_DISPSTAT1_FRCNT0_SHIFT		18
+# define SCALER_DISPSTAT1_FRCNT1_MASK		VC4_MASK(17, 12)
+# define SCALER_DISPSTAT1_FRCNT1_SHIFT		12
+
 #define SCALER_DISPSTATX(x)			(SCALER_DISPSTAT0 +        \
 						 (x) * (SCALER_DISPSTAT1 - \
 							SCALER_DISPSTAT0))
+
 #define SCALER_DISPBASE1                        0x0000005c
 #define SCALER_DISPBASEX(x)			(SCALER_DISPBASE0 +        \
 						 (x) * (SCALER_DISPBASE1 - \
@@ -415,7 +419,11 @@
 						 (x) * (SCALER_DISPCTRL1 - \
 							SCALER_DISPCTRL0))
 #define SCALER_DISPBKGND2                       0x00000064
+
 #define SCALER_DISPSTAT2                        0x00000068
+# define SCALER_DISPSTAT2_FRCNT2_MASK		VC4_MASK(17, 12)
+# define SCALER_DISPSTAT2_FRCNT2_SHIFT		12
+
 #define SCALER_DISPBASE2                        0x0000006c
 #define SCALER_DISPALPHA2                       0x00000070
 #define SCALER_GAMADDR                          0x00000078
@@ -774,11 +782,27 @@ enum {
 # define VC4_HD_CSC_CTL_RGB2YCC			BIT(1)
 # define VC4_HD_CSC_CTL_ENABLE			BIT(0)
 
+# define VC5_MT_CP_CSC_CTL_USE_444_TO_422	BIT(6)
+# define VC5_MT_CP_CSC_CTL_FILTER_MODE_444_TO_422_MASK \
+						VC4_MASK(5, 4)
+# define VC5_MT_CP_CSC_CTL_FILTER_MODE_444_TO_422_STANDARD \
+						3
+# define VC5_MT_CP_CSC_CTL_USE_RNG_SUPPRESSION	BIT(3)
 # define VC5_MT_CP_CSC_CTL_ENABLE		BIT(2)
 # define VC5_MT_CP_CSC_CTL_MODE_MASK		VC4_MASK(1, 0)
 
+# define VC5_MT_CP_CHANNEL_CTL_OUTPUT_REMAP_MASK \
+						VC4_MASK(7, 6)
+# define VC5_MT_CP_CHANNEL_CTL_OUTPUT_REMAP_LEGACY_STYLE \
+						2
+
 # define VC4_DVP_HT_CLOCK_STOP_PIXEL		BIT(1)
 
+# define VC5_DVP_HT_VEC_INTERFACE_CFG_SEL_422_MASK \
+						VC4_MASK(3, 2)
+# define VC5_DVP_HT_VEC_INTERFACE_CFG_SEL_422_FORMAT_422_LEGACY \
+						2
+
 /* HVS display list information. */
 #define HVS_BOOTLOADER_DLIST_END                32
 
diff --git a/drivers/gpu/drm/vc4/vc4_trace.h b/drivers/gpu/drm/vc4/vc4_trace.h
index 1cccde0b09a7..7f4c49e7e011 100644
--- a/drivers/gpu/drm/vc4/vc4_trace.h
+++ b/drivers/gpu/drm/vc4/vc4_trace.h
@@ -52,6 +52,101 @@ TRACE_EVENT(vc4_wait_for_seqno_end,
 		      __entry->dev, __entry->seqno)
 );
 
+TRACE_EVENT(vc4_submit_cl_ioctl,
+	    TP_PROTO(struct drm_device *dev, u32 bin_cl_size, u32 shader_rec_size, u32 bo_count),
+	    TP_ARGS(dev, bin_cl_size, shader_rec_size, bo_count),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u32, bin_cl_size)
+			     __field(u32, shader_rec_size)
+			     __field(u32, bo_count)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->bin_cl_size = bin_cl_size;
+			   __entry->shader_rec_size = shader_rec_size;
+			   __entry->bo_count = bo_count;
+			   ),
+
+	    TP_printk("dev=%u, bin_cl_size=%u, shader_rec_size=%u, bo_count=%u",
+		      __entry->dev,
+		      __entry->bin_cl_size,
+		      __entry->shader_rec_size,
+		      __entry->bo_count)
+);
+
+TRACE_EVENT(vc4_submit_cl,
+	    TP_PROTO(struct drm_device *dev, bool is_render,
+		     uint64_t seqno,
+		     u32 ctnqba, u32 ctnqea),
+	    TP_ARGS(dev, is_render, seqno, ctnqba, ctnqea),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(bool, is_render)
+			     __field(u64, seqno)
+			     __field(u32, ctnqba)
+			     __field(u32, ctnqea)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->is_render = is_render;
+			   __entry->seqno = seqno;
+			   __entry->ctnqba = ctnqba;
+			   __entry->ctnqea = ctnqea;
+			   ),
+
+	    TP_printk("dev=%u, %s, seqno=%llu, 0x%08x..0x%08x",
+		      __entry->dev,
+		      __entry->is_render ? "RCL" : "BCL",
+		      __entry->seqno,
+		      __entry->ctnqba,
+		      __entry->ctnqea)
+);
+
+TRACE_EVENT(vc4_bcl_end_irq,
+	    TP_PROTO(struct drm_device *dev,
+		     uint64_t seqno),
+	    TP_ARGS(dev, seqno),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u64, seqno)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->seqno = seqno;
+			   ),
+
+	    TP_printk("dev=%u, seqno=%llu",
+		      __entry->dev,
+		      __entry->seqno)
+);
+
+TRACE_EVENT(vc4_rcl_end_irq,
+	    TP_PROTO(struct drm_device *dev,
+		     uint64_t seqno),
+	    TP_ARGS(dev, seqno),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u64, seqno)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->seqno = seqno;
+			   ),
+
+	    TP_printk("dev=%u, seqno=%llu",
+		      __entry->dev,
+		      __entry->seqno)
+);
+
 #endif /* _VC4_TRACE_H_ */
 
 /* This part must be outside protection */
diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c
index 9809ca3e2945..3579d487402e 100644
--- a/drivers/gpu/drm/vc4/vc4_txp.c
+++ b/drivers/gpu/drm/vc4/vc4_txp.c
@@ -298,12 +298,18 @@ static void vc4_txp_connector_atomic_commit(struct drm_connector *conn,
 	if (WARN_ON(i == ARRAY_SIZE(drm_fmts)))
 		return;
 
-	ctrl = TXP_GO | TXP_VSTART_AT_EOF | TXP_EI |
+	ctrl = TXP_GO | TXP_EI |
 	       VC4_SET_FIELD(0xf, TXP_BYTE_ENABLE) |
 	       VC4_SET_FIELD(txp_fmts[i], TXP_FORMAT);
 
 	if (fb->format->has_alpha)
 		ctrl |= TXP_ALPHA_ENABLE;
+	else
+		/*
+		 * If TXP_ALPHA_ENABLE isn't set and TXP_ALPHA_INVERT is, the
+		 * hardware will force the output padding to be 0xff.
+		 */
+		ctrl |= TXP_ALPHA_INVERT;
 
 	gem = drm_fb_cma_get_gem_obj(fb, 0);
 	TXP_WRITE(TXP_DST_PTR, gem->paddr + fb->offsets[0]);
@@ -497,7 +503,8 @@ static int vc4_txp_bind(struct device *dev, struct device *master, void *data)
 	ret = drm_writeback_connector_init(drm, &txp->connector,
 					   &vc4_txp_connector_funcs,
 					   &vc4_txp_encoder_helper_funcs,
-					   drm_fmts, ARRAY_SIZE(drm_fmts));
+					   drm_fmts, ARRAY_SIZE(drm_fmts),
+					   0);
 	if (ret)
 		return ret;