Merge tag 'drm-next-2018-06-06-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This starts to support NVIDIA volta hardware with nouveau, and adds
  amdgpu support for the GPU in the Kabylake-G (the intel + radeon
  single package chip), along with some initial Intel icelake enabling.

  Summary:

  New Drivers:
   - v3d - driver for broadcom V3D V3.x+ hardware
   - xen-front - XEN PV display frontend

  core:
   - handle zpos normalization in the core
   - stop looking at legacy pointers in atomic paths
   - improved scheduler documentation
   - improved aspect ratio validation
   - aspect ratio support for 64:27 and 256:135
   - drop unused control node code.

  i915:
   - Icelake (ICL) enabling
   - GuC/HuC refactoring
   - PSR/PSR2 enabling and fixes
   - DPLL management refactoring
   - DP MST fixes
   - NV12 enabling
   - HDCP improvements
   - GEM/Execlist/reset improvements
   - GVT improvements
   - stolen memory first 4k fix

  amdgpu:
   - Vega 20 support
   - VEGAM support (Kabylake-G)
   - preOS scanout buffer reservation
   - power management gfxoff support for raven
   - SR-IOV fixes
   - Vega10 power profiles and clock voltage control
   - scatter/gather display support on CZ/ST

  amdkfd:
   - GFX9 dGPU support
   - userptr memory mapping

  nouveau:
   - major refactoring for Volta GV100 support

  tda998x:
   - HDMI i2c CEC support

  etnaviv:
   - removed unused logging code
   - license text cleanups
   - MMU handling improvements
   - timeout fence fix for 50 days uptime

  tegra:
   - IOMMU support in gr2d/gr3d drivers
   - zpos support

  vc4:
   - syncobj support
   - CTM, plane alpha and async cursor support

  analogix_dp:
   - HPD and aux chan fixes

  sun4i:
   - MIPI DSI support

  tilcdc:
   - clock divider fixes for OMAP-l138 LCDK board

  rcar-du:
   - R8A77965 support
   - dma-buf fences fixes
   - hardware indexed crtc/du group handling
   - generic zplane property support

  atmel-hclcdc:
   - generic zplane property support

  mediatek:
   - use generic video mode function

  exynos:
   - S5PV210 FIMD variant support
   - IPP v2 framework
   - more HW overlays support"

* tag 'drm-next-2018-06-06-1' of git://anongit.freedesktop.org/drm/drm: (1286 commits)
  drm/amdgpu: fix 32-bit build warning
  drm/exynos: fimc: signedness bug in fimc_setup_clocks()
  drm/exynos: scaler: fix static checker warning
  drm/amdgpu: Use dev_info() to report amdkfd is not supported for this ASIC
  drm/amd/display: Remove use of division operator for long longs
  drm/amdgpu: Update GFX info structure to match what vega20 used
  drm/amdgpu/pp: remove duplicate assignment
  drm/sched: add rcu_barrier after entity fini
  drm/amdgpu: move VM BOs on LRU again
  drm/amdgpu: consistenly use VM moved flag
  drm/amdgpu: kmap PDs/PTs in amdgpu_vm_update_directories
  drm/amdgpu: further optimize amdgpu_vm_handle_moved
  drm/amdgpu: cleanup amdgpu_vm_validate_pt_bos v2
  drm/amdgpu: rework VM state machine lock handling v2
  drm/amdgpu: Add runtime VCN PG support
  drm/amdgpu: Enable VCN static PG by default on RV
  drm/amdgpu: Add VCN static PG support on RV
  drm/amdgpu: Enable VCN CG by default on RV
  drm/amdgpu: Add static CG control for VCN on RV
  drm/exynos: Fix default value for zpos plane property
  ...

10 files changed, 530 insertions, 134 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index c61dff594195..c8650bbcbcb3 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -42,51 +42,18 @@
 #include "vc4_drv.h"
 #include "vc4_regs.h"
 
-struct vc4_crtc {
-	struct drm_crtc base;
-	const struct vc4_crtc_data *data;
-	void __iomem *regs;
-
-	/* Timestamp at start of vblank irq - unaffected by lock delays. */
-	ktime_t t_vblank;
-
-	/* Which HVS channel we're using for our CRTC. */
-	int channel;
-
-	u8 lut_r[256];
-	u8 lut_g[256];
-	u8 lut_b[256];
-	/* Size in pixels of the COB memory allocated to this CRTC. */
-	u32 cob_size;
-
-	struct drm_pending_vblank_event *event;
-};
-
 struct vc4_crtc_state {
 	struct drm_crtc_state base;
 	/* Dlist area for this CRTC configuration. */
 	struct drm_mm_node mm;
 };
 
-static inline struct vc4_crtc *
-to_vc4_crtc(struct drm_crtc *crtc)
-{
-	return (struct vc4_crtc *)crtc;
-}
-
 static inline struct vc4_crtc_state *
 to_vc4_crtc_state(struct drm_crtc_state *crtc_state)
 {
 	return (struct vc4_crtc_state *)crtc_state;
 }
 
-struct vc4_crtc_data {
-	/* Which channel of the HVS this pixelvalve sources from. */
-	int hvs_channel;
-
-	enum vc4_encoder_type encoder_types[4];
-};
-
 #define CRTC_WRITE(offset, val) writel(val, vc4_crtc->regs + (offset))
 #define CRTC_READ(offset) readl(vc4_crtc->regs + (offset))
 
@@ -298,23 +265,21 @@ vc4_crtc_lut_load(struct drm_crtc *crtc)
 		HVS_WRITE(SCALER_GAMDATA, vc4_crtc->lut_b[i]);
 }
 
-static int
-vc4_crtc_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b,
-		   uint32_t size,
-		   struct drm_modeset_acquire_ctx *ctx)
+static void
+vc4_crtc_update_gamma_lut(struct drm_crtc *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);
 	u32 i;
 
-	for (i = 0; i < size; i++) {
-		vc4_crtc->lut_r[i] = r[i] >> 8;
-		vc4_crtc->lut_g[i] = g[i] >> 8;
-		vc4_crtc->lut_b[i] = b[i] >> 8;
+	for (i = 0; i < length; i++) {
+		vc4_crtc->lut_r[i] = drm_color_lut_extract(lut[i].red, 8);
+		vc4_crtc->lut_g[i] = drm_color_lut_extract(lut[i].green, 8);
+		vc4_crtc->lut_b[i] = drm_color_lut_extract(lut[i].blue, 8);
 	}
 
 	vc4_crtc_lut_load(crtc);
-
-	return 0;
 }
 
 static u32 vc4_get_fifo_full_level(u32 format)
@@ -699,6 +664,22 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc,
 	if (crtc->state->active && old_state->active)
 		vc4_crtc_update_dlist(crtc);
 
+	if (crtc->state->color_mgmt_changed) {
+		u32 dispbkgndx = HVS_READ(SCALER_DISPBKGNDX(vc4_crtc->channel));
+
+		if (crtc->state->gamma_lut) {
+			vc4_crtc_update_gamma_lut(crtc);
+			dispbkgndx |= SCALER_DISPBKGND_GAMMA;
+		} else {
+			/* Unsetting DISPBKGND_GAMMA skips the gamma lut step
+			 * in hardware, which is the same as a linear lut that
+			 * DRM expects us to use in absence of a user lut.
+			 */
+			dispbkgndx &= ~SCALER_DISPBKGND_GAMMA;
+		}
+		HVS_WRITE(SCALER_DISPBKGNDX(vc4_crtc->channel), dispbkgndx);
+	}
+
 	if (debug_dump_regs) {
 		DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc));
 		vc4_hvs_dump_state(dev);
@@ -953,7 +934,7 @@ static const struct drm_crtc_funcs vc4_crtc_funcs = {
 	.reset = vc4_crtc_reset,
 	.atomic_duplicate_state = vc4_crtc_duplicate_state,
 	.atomic_destroy_state = vc4_crtc_destroy_state,
-	.gamma_set = vc4_crtc_gamma_set,
+	.gamma_set = drm_atomic_helper_legacy_gamma_set,
 	.enable_vblank = vc4_enable_vblank,
 	.disable_vblank = vc4_disable_vblank,
 };
@@ -1079,6 +1060,12 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 	primary_plane->crtc = crtc;
 	vc4_crtc->channel = vc4_crtc->data->hvs_channel;
 	drm_mode_crtc_set_gamma_size(crtc, ARRAY_SIZE(vc4_crtc->lut_r));
+	drm_crtc_enable_color_mgmt(crtc, 0, false, crtc->gamma_size);
+
+	/* We support CTM, but only for one CRTC at a time. It's therefore
+	 * implemented as private driver state in vc4_kms, not here.
+	 */
+	drm_crtc_enable_color_mgmt(crtc, 0, true, crtc->gamma_size);
 
 	/* Set up some arbitrary number of planes.  We're not limited
 	 * by a set number of physical registers, just the space in
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 7c95ed5c5cac..466d0a27b415 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -176,7 +176,8 @@ static struct drm_driver vc4_drm_driver = {
 			    DRIVER_GEM |
 			    DRIVER_HAVE_IRQ |
 			    DRIVER_RENDER |
-			    DRIVER_PRIME),
+			    DRIVER_PRIME |
+			    DRIVER_SYNCOBJ),
 	.lastclose = drm_fb_helper_lastclose,
 	.open = vc4_open,
 	.postclose = vc4_close,
@@ -319,8 +320,8 @@ dev_unref:
 
 static void vc4_drm_unbind(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct drm_device *drm = platform_get_drvdata(pdev);
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
 
 	drm_dev_unregister(drm);
 
@@ -328,6 +329,8 @@ static void vc4_drm_unbind(struct device *dev)
 
 	drm_mode_config_cleanup(drm);
 
+	drm_atomic_private_obj_fini(&vc4->ctm_manager);
+
 	drm_dev_unref(drm);
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 1b4cd1fabf56..554a4e810d5b 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -10,6 +10,8 @@
 #include <drm/drmP.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_syncobj.h>
 
 #include "uapi/drm/vc4_drm.h"
 
@@ -193,6 +195,9 @@ struct vc4_dev {
 	} hangcheck;
 
 	struct semaphore async_modeset;
+
+	struct drm_modeset_lock ctm_state_lock;
+	struct drm_private_obj ctm_manager;
 };
 
 static inline struct vc4_dev *
@@ -392,6 +397,39 @@ to_vc4_encoder(struct drm_encoder *encoder)
 	return container_of(encoder, struct vc4_encoder, base);
 }
 
+struct vc4_crtc_data {
+	/* Which channel of the HVS this pixelvalve sources from. */
+	int hvs_channel;
+
+	enum vc4_encoder_type encoder_types[4];
+};
+
+struct vc4_crtc {
+	struct drm_crtc base;
+	const struct vc4_crtc_data *data;
+	void __iomem *regs;
+
+	/* Timestamp at start of vblank irq - unaffected by lock delays. */
+	ktime_t t_vblank;
+
+	/* Which HVS channel we're using for our CRTC. */
+	int channel;
+
+	u8 lut_r[256];
+	u8 lut_g[256];
+	u8 lut_b[256];
+	/* Size in pixels of the COB memory allocated to this CRTC. */
+	u32 cob_size;
+
+	struct drm_pending_vblank_event *event;
+};
+
+static inline struct vc4_crtc *
+to_vc4_crtc(struct drm_crtc *crtc)
+{
+	return (struct vc4_crtc *)crtc;
+}
+
 #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)
diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c
index 94085f8bcd68..8aa897835118 100644
--- a/drivers/gpu/drm/vc4/vc4_dsi.c
+++ b/drivers/gpu/drm/vc4/vc4_dsi.c
@@ -753,6 +753,11 @@ static void vc4_dsi_ulps(struct vc4_dsi *dsi, bool ulps)
 			 (dsi->lanes > 2 ? DSI1_STAT_PHY_D2_STOP : 0) |
 			 (dsi->lanes > 3 ? DSI1_STAT_PHY_D3_STOP : 0));
 	int ret;
+	bool ulps_currently_enabled = (DSI_PORT_READ(PHY_AFEC0) &
+				       DSI_PORT_BIT(PHY_AFEC0_LATCH_ULPS));
+
+	if (ulps == ulps_currently_enabled)
+		return;
 
 	DSI_PORT_WRITE(STAT, stat_ulps);
 	DSI_PORT_WRITE(PHYC, DSI_PORT_READ(PHYC) | phyc_ulps);
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 2107b0daf8ef..7910b9acedd6 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -27,6 +27,7 @@
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/sched/signal.h>
+#include <linux/dma-fence-array.h>
 
 #include "uapi/drm/vc4_drm.h"
 #include "vc4_drv.h"
@@ -655,7 +656,8 @@ retry:
  */
 static int
 vc4_queue_submit(struct drm_device *dev, struct vc4_exec_info *exec,
-		 struct ww_acquire_ctx *acquire_ctx)
+		 struct ww_acquire_ctx *acquire_ctx,
+		 struct drm_syncobj *out_sync)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_exec_info *renderjob;
@@ -678,6 +680,9 @@ vc4_queue_submit(struct drm_device *dev, struct vc4_exec_info *exec,
 	fence->seqno = exec->seqno;
 	exec->fence = &fence->base;
 
+	if (out_sync)
+		drm_syncobj_replace_fence(out_sync, exec->fence);
+
 	vc4_update_bo_seqnos(exec, seqno);
 
 	vc4_unlock_bo_reservations(dev, exec, acquire_ctx);
@@ -1113,8 +1118,10 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_file *vc4file = file_priv->driver_priv;
 	struct drm_vc4_submit_cl *args = data;
+	struct drm_syncobj *out_sync = NULL;
 	struct vc4_exec_info *exec;
 	struct ww_acquire_ctx acquire_ctx;
+	struct dma_fence *in_fence;
 	int ret = 0;
 
 	if ((args->flags & ~(VC4_SUBMIT_CL_USE_CLEAR_COLOR |
@@ -1126,7 +1133,7 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 	}
 
 	if (args->pad2 != 0) {
-		DRM_DEBUG("->pad2 must be set to zero\n");
+		DRM_DEBUG("Invalid pad: 0x%08x\n", args->pad2);
 		return -EINVAL;
 	}
 
@@ -1164,6 +1171,29 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 		}
 	}
 
+	if (args->in_sync) {
+		ret = drm_syncobj_find_fence(file_priv, args->in_sync,
+					     &in_fence);
+		if (ret)
+			goto fail;
+
+		/* When the fence (or fence array) is exclusively from our
+		 * context we can skip the wait since jobs are executed in
+		 * order of their submission through this ioctl and this can
+		 * only have fences from a prior job.
+		 */
+		if (!dma_fence_match_context(in_fence,
+					     vc4->dma_fence_context)) {
+			ret = dma_fence_wait(in_fence, true);
+			if (ret) {
+				dma_fence_put(in_fence);
+				goto fail;
+			}
+		}
+
+		dma_fence_put(in_fence);
+	}
+
 	if (exec->args->bin_cl_size != 0) {
 		ret = vc4_get_bcl(dev, exec);
 		if (ret)
@@ -1181,12 +1211,33 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto fail;
 
+	if (args->out_sync) {
+		out_sync = drm_syncobj_find(file_priv, args->out_sync);
+		if (!out_sync) {
+			ret = -EINVAL;
+			goto fail;
+		}
+
+		/* We replace the fence in out_sync in vc4_queue_submit since
+		 * the render job could execute immediately after that call.
+		 * If it finishes before our ioctl processing resumes the
+		 * render job fence could already have been freed.
+		 */
+	}
+
 	/* Clear this out of the struct we'll be putting in the queue,
 	 * since it's part of our stack.
 	 */
 	exec->args = NULL;
 
-	ret = vc4_queue_submit(dev, exec, &acquire_ctx);
+	ret = vc4_queue_submit(dev, exec, &acquire_ctx, out_sync);
+
+	/* The syncobj isn't part of the exec data and we need to free our
+	 * reference even if job submission failed.
+	 */
+	if (out_sync)
+		drm_syncobj_put(out_sync);
+
 	if (ret)
 		goto fail;
 
diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c
index 2b62fc5b8d85..5d8c749c9749 100644
--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -58,6 +58,10 @@ static const struct {
 	HVS_REG(SCALER_DISPSTAT2),
 	HVS_REG(SCALER_DISPBASE2),
 	HVS_REG(SCALER_DISPALPHA2),
+	HVS_REG(SCALER_OLEDOFFS),
+	HVS_REG(SCALER_OLEDCOEF0),
+	HVS_REG(SCALER_OLEDCOEF1),
+	HVS_REG(SCALER_OLEDCOEF2),
 };
 
 void vc4_hvs_dump_state(struct drm_device *dev)
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index ba60153dddb5..8a411e5f8776 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -23,6 +23,117 @@
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include "vc4_drv.h"
+#include "vc4_regs.h"
+
+struct vc4_ctm_state {
+	struct drm_private_state base;
+	struct drm_color_ctm *ctm;
+	int fifo;
+};
+
+static struct vc4_ctm_state *to_vc4_ctm_state(struct drm_private_state *priv)
+{
+	return container_of(priv, struct vc4_ctm_state, base);
+}
+
+static struct vc4_ctm_state *vc4_get_ctm_state(struct drm_atomic_state *state,
+					       struct drm_private_obj *manager)
+{
+	struct drm_device *dev = state->dev;
+	struct vc4_dev *vc4 = dev->dev_private;
+	struct drm_private_state *priv_state;
+	int ret;
+
+	ret = drm_modeset_lock(&vc4->ctm_state_lock, state->acquire_ctx);
+	if (ret)
+		return ERR_PTR(ret);
+
+	priv_state = drm_atomic_get_private_obj_state(state, manager);
+	if (IS_ERR(priv_state))
+		return ERR_CAST(priv_state);
+
+	return to_vc4_ctm_state(priv_state);
+}
+
+static struct drm_private_state *
+vc4_ctm_duplicate_state(struct drm_private_obj *obj)
+{
+	struct vc4_ctm_state *state;
+
+	state = kmemdup(obj->state, sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return NULL;
+
+	__drm_atomic_helper_private_obj_duplicate_state(obj, &state->base);
+
+	return &state->base;
+}
+
+static void vc4_ctm_destroy_state(struct drm_private_obj *obj,
+				  struct drm_private_state *state)
+{
+	struct vc4_ctm_state *ctm_state = to_vc4_ctm_state(state);
+
+	kfree(ctm_state);
+}
+
+static const struct drm_private_state_funcs vc4_ctm_state_funcs = {
+	.atomic_duplicate_state = vc4_ctm_duplicate_state,
+	.atomic_destroy_state = vc4_ctm_destroy_state,
+};
+
+/* Converts a DRM S31.32 value to the HW S0.9 format. */
+static u16 vc4_ctm_s31_32_to_s0_9(u64 in)
+{
+	u16 r;
+
+	/* Sign bit. */
+	r = in & BIT_ULL(63) ? BIT(9) : 0;
+
+	if ((in & GENMASK_ULL(62, 32)) > 0) {
+		/* We have zero integer bits so we can only saturate here. */
+		r |= GENMASK(8, 0);
+	} else {
+		/* Otherwise take the 9 most important fractional bits. */
+		r |= (in >> 23) & GENMASK(8, 0);
+	}
+
+	return r;
+}
+
+static void
+vc4_ctm_commit(struct vc4_dev *vc4, struct drm_atomic_state *state)
+{
+	struct vc4_ctm_state *ctm_state = to_vc4_ctm_state(vc4->ctm_manager.state);
+	struct drm_color_ctm *ctm = ctm_state->ctm;
+
+	if (ctm_state->fifo) {
+		HVS_WRITE(SCALER_OLEDCOEF2,
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[0]),
+					SCALER_OLEDCOEF2_R_TO_R) |
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[3]),
+					SCALER_OLEDCOEF2_R_TO_G) |
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[6]),
+					SCALER_OLEDCOEF2_R_TO_B));
+		HVS_WRITE(SCALER_OLEDCOEF1,
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[1]),
+					SCALER_OLEDCOEF1_G_TO_R) |
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[4]),
+					SCALER_OLEDCOEF1_G_TO_G) |
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[7]),
+					SCALER_OLEDCOEF1_G_TO_B));
+		HVS_WRITE(SCALER_OLEDCOEF0,
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[2]),
+					SCALER_OLEDCOEF0_B_TO_R) |
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[5]),
+					SCALER_OLEDCOEF0_B_TO_G) |
+			  VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[8]),
+					SCALER_OLEDCOEF0_B_TO_B));
+	}
+
+	HVS_WRITE(SCALER_OLEDOFFS,
+		  VC4_SET_FIELD(ctm_state->fifo, SCALER_OLEDOFFS_DISPFIFO));
+}
 
 static void
 vc4_atomic_complete_commit(struct drm_atomic_state *state)
@@ -36,6 +147,8 @@ vc4_atomic_complete_commit(struct drm_atomic_state *state)
 
 	drm_atomic_helper_commit_modeset_disables(dev, state);
 
+	vc4_ctm_commit(vc4, state);
+
 	drm_atomic_helper_commit_planes(dev, state, 0);
 
 	drm_atomic_helper_commit_modeset_enables(dev, state);
@@ -90,6 +203,26 @@ static int vc4_atomic_commit(struct drm_device *dev,
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	int ret;
 
+	if (state->async_update) {
+		ret = down_interruptible(&vc4->async_modeset);
+		if (ret)
+			return ret;
+
+		ret = drm_atomic_helper_prepare_planes(dev, state);
+		if (ret) {
+			up(&vc4->async_modeset);
+			return ret;
+		}
+
+		drm_atomic_helper_async_commit(dev, state);
+
+		drm_atomic_helper_cleanup_planes(dev, state);
+
+		up(&vc4->async_modeset);
+
+		return 0;
+	}
+
 	ret = drm_atomic_helper_setup_commit(state, nonblock);
 	if (ret)
 		return ret;
@@ -187,9 +320,89 @@ static struct drm_framebuffer *vc4_fb_create(struct drm_device *dev,
 	return drm_gem_fb_create(dev, file_priv, mode_cmd);
 }
 
+/* Our CTM has some peculiar limitations: we can only enable it for one CRTC
+ * at a time and the HW only supports S0.9 scalars. To account for the latter,
+ * we don't allow userland to set a CTM that we have no hope of approximating.
+ */
+static int
+vc4_ctm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_ctm_state *ctm_state = NULL;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	struct drm_color_ctm *ctm;
+	int i;
+
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		/* CTM is being disabled. */
+		if (!new_crtc_state->ctm && old_crtc_state->ctm) {
+			ctm_state = vc4_get_ctm_state(state, &vc4->ctm_manager);
+			if (IS_ERR(ctm_state))
+				return PTR_ERR(ctm_state);
+			ctm_state->fifo = 0;
+		}
+	}
+
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		if (new_crtc_state->ctm == old_crtc_state->ctm)
+			continue;
+
+		if (!ctm_state) {
+			ctm_state = vc4_get_ctm_state(state, &vc4->ctm_manager);
+			if (IS_ERR(ctm_state))
+				return PTR_ERR(ctm_state);
+		}
+
+		/* CTM is being enabled or the matrix changed. */
+		if (new_crtc_state->ctm) {
+			/* fifo is 1-based since 0 disables CTM. */
+			int fifo = to_vc4_crtc(crtc)->channel + 1;
+
+			/* Check userland isn't trying to turn on CTM for more
+			 * than one CRTC at a time.
+			 */
+			if (ctm_state->fifo && ctm_state->fifo != fifo) {
+				DRM_DEBUG_DRIVER("Too many CTM configured\n");
+				return -EINVAL;
+			}
+
+			/* Check we can approximate the specified CTM.
+			 * We disallow scalars |c| > 1.0 since the HW has
+			 * no integer bits.
+			 */
+			ctm = new_crtc_state->ctm->data;
+			for (i = 0; i < ARRAY_SIZE(ctm->matrix); i++) {
+				u64 val = ctm->matrix[i];
+
+				val &= ~BIT_ULL(63);
+				if (val > BIT_ULL(32))
+					return -EINVAL;
+			}
+
+			ctm_state->fifo = fifo;
+			ctm_state->ctm = ctm;
+		}
+	}
+
+	return 0;
+}
+
+static int
+vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
+{
+	int ret;
+
+	ret = vc4_ctm_atomic_check(dev, state);
+	if (ret < 0)
+		return ret;
+
+	return drm_atomic_helper_check(dev, state);
+}
+
 static const struct drm_mode_config_funcs vc4_mode_funcs = {
 	.output_poll_changed = drm_fb_helper_output_poll_changed,
-	.atomic_check = drm_atomic_helper_check,
+	.atomic_check = vc4_atomic_check,
 	.atomic_commit = vc4_atomic_commit,
 	.fb_create = vc4_fb_create,
 };
@@ -197,6 +410,7 @@ static const struct drm_mode_config_funcs vc4_mode_funcs = {
 int vc4_kms_load(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_ctm_state *ctm_state;
 	int ret;
 
 	sema_init(&vc4->async_modeset, 1);
@@ -217,6 +431,14 @@ int vc4_kms_load(struct drm_device *dev)
 	dev->mode_config.async_page_flip = true;
 	dev->mode_config.allow_fb_modifiers = true;
 
+	drm_modeset_lock_init(&vc4->ctm_state_lock);
+
+	ctm_state = kzalloc(sizeof(*ctm_state), GFP_KERNEL);
+	if (!ctm_state)
+		return -ENOMEM;
+	drm_atomic_private_obj_init(&vc4->ctm_manager, &ctm_state->base,
+				    &vc4_ctm_state_funcs);
+
 	drm_mode_config_reset(dev);
 
 	if (dev->mode_config.num_connector)
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 13dcaad06798..71d44c357d35 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -201,6 +201,7 @@ static void vc4_plane_reset(struct drm_plane *plane)
 		return;
 
 	plane->state = &vc4_state->base;
+	plane->state->alpha = DRM_BLEND_ALPHA_OPAQUE;
 	vc4_state->base.plane = plane;
 }
 
@@ -467,6 +468,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	u32 ctl0_offset = vc4_state->dlist_count;
 	const struct hvs_format *format = vc4_get_hvs_format(fb->format->format);
 	int num_planes = drm_format_num_planes(format->drm);
+	bool mix_plane_alpha;
 	bool covers_screen;
 	u32 scl0, scl1, pitch0;
 	u32 lbm_size, tiling;
@@ -552,7 +554,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	/* Position Word 0: Image Positions and Alpha Value */
 	vc4_state->pos0_offset = vc4_state->dlist_count;
 	vc4_dlist_write(vc4_state,
-			VC4_SET_FIELD(0xff, SCALER_POS0_FIXED_ALPHA) |
+			VC4_SET_FIELD(state->alpha >> 8, SCALER_POS0_FIXED_ALPHA) |
 			VC4_SET_FIELD(vc4_state->crtc_x, SCALER_POS0_START_X) |
 			VC4_SET_FIELD(vc4_state->crtc_y, SCALER_POS0_START_Y));
 
@@ -565,6 +567,13 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 					      SCALER_POS1_SCL_HEIGHT));
 	}
 
+	/* Don't waste cycles mixing with plane alpha if the set alpha
+	 * is opaque or there is no per-pixel alpha information.
+	 * In any case we use the alpha property value as the fixed alpha.
+	 */
+	mix_plane_alpha = state->alpha != DRM_BLEND_ALPHA_OPAQUE &&
+			  fb->format->has_alpha;
+
 	/* Position Word 2: Source Image Size, Alpha */
 	vc4_state->pos2_offset = vc4_state->dlist_count;
 	vc4_dlist_write(vc4_state,
@@ -572,6 +581,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 				      SCALER_POS2_ALPHA_MODE_PIPELINE :
 				      SCALER_POS2_ALPHA_MODE_FIXED,
 				      SCALER_POS2_ALPHA_MODE) |
+			(mix_plane_alpha ? SCALER_POS2_ALPHA_MIX : 0) |
 			(fb->format->has_alpha ? SCALER_POS2_ALPHA_PREMULT : 0) |
 			VC4_SET_FIELD(vc4_state->src_w[0], SCALER_POS2_WIDTH) |
 			VC4_SET_FIELD(vc4_state->src_h[0], SCALER_POS2_HEIGHT));
@@ -653,10 +663,11 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 			vc4_state->crtc_w == state->crtc->mode.hdisplay &&
 			vc4_state->crtc_h == state->crtc->mode.vdisplay;
 	/* Background fill might be necessary when the plane has per-pixel
-	 * alpha content and blends from the background or does not cover
-	 * the entire screen.
+	 * alpha content or a non-opaque plane alpha and could blend from the
+	 * background or does not cover the entire screen.
 	 */
-	vc4_state->needs_bg_fill = fb->format->has_alpha || !covers_screen;
+	vc4_state->needs_bg_fill = fb->format->has_alpha || !covers_screen ||
+				   state->alpha != DRM_BLEND_ALPHA_OPAQUE;
 
 	return 0;
 }
@@ -741,6 +752,57 @@ void vc4_plane_async_set_fb(struct drm_plane *plane, struct drm_framebuffer *fb)
 	vc4_state->dlist[vc4_state->ptr0_offset] = addr;
 }
 
+static void vc4_plane_atomic_async_update(struct drm_plane *plane,
+					  struct drm_plane_state *state)
+{
+	struct vc4_plane_state *vc4_state = to_vc4_plane_state(plane->state);
+
+	if (plane->state->fb != state->fb) {
+		vc4_plane_async_set_fb(plane, state->fb);
+		drm_atomic_set_fb_for_plane(plane->state, state->fb);
+	}
+
+	/* Set the cursor's position on the screen.  This is the
+	 * expected change from the drm_mode_cursor_universal()
+	 * helper.
+	 */
+	plane->state->crtc_x = state->crtc_x;
+	plane->state->crtc_y = state->crtc_y;
+
+	/* Allow changing the start position within the cursor BO, if
+	 * that matters.
+	 */
+	plane->state->src_x = state->src_x;
+	plane->state->src_y = state->src_y;
+
+	/* Update the display list based on the new crtc_x/y. */
+	vc4_plane_atomic_check(plane, plane->state);
+
+	/* Note that we can't just call vc4_plane_write_dlist()
+	 * because that would smash the context data that the HVS is
+	 * currently using.
+	 */
+	writel(vc4_state->dlist[vc4_state->pos0_offset],
+	       &vc4_state->hw_dlist[vc4_state->pos0_offset]);
+	writel(vc4_state->dlist[vc4_state->pos2_offset],
+	       &vc4_state->hw_dlist[vc4_state->pos2_offset]);
+	writel(vc4_state->dlist[vc4_state->ptr0_offset],
+	       &vc4_state->hw_dlist[vc4_state->ptr0_offset]);
+}
+
+static int vc4_plane_atomic_async_check(struct drm_plane *plane,
+					struct drm_plane_state *state)
+{
+	/* No configuring new scaling in the fast path. */
+	if (plane->state->crtc_w != state->crtc_w ||
+	    plane->state->crtc_h != state->crtc_h ||
+	    plane->state->src_w != state->src_w ||
+	    plane->state->src_h != state->src_h)
+		return -EINVAL;
+
+	return 0;
+}
+
 static int vc4_prepare_fb(struct drm_plane *plane,
 			  struct drm_plane_state *state)
 {
@@ -780,6 +842,8 @@ static const struct drm_plane_helper_funcs vc4_plane_helper_funcs = {
 	.atomic_update = vc4_plane_atomic_update,
 	.prepare_fb = vc4_prepare_fb,
 	.cleanup_fb = vc4_cleanup_fb,
+	.atomic_async_check = vc4_plane_atomic_async_check,
+	.atomic_async_update = vc4_plane_atomic_async_update,
 };
 
 static void vc4_plane_destroy(struct drm_plane *plane)
@@ -788,82 +852,6 @@ static void vc4_plane_destroy(struct drm_plane *plane)
 	drm_plane_cleanup(plane);
 }
 
-/* Implements immediate (non-vblank-synced) updates of the cursor
- * position, or falls back to the atomic helper otherwise.
- */
-static int
-vc4_update_plane(struct drm_plane *plane,
-		 struct drm_crtc *crtc,
-		 struct drm_framebuffer *fb,
-		 int crtc_x, int crtc_y,
-		 unsigned int crtc_w, unsigned int crtc_h,
-		 uint32_t src_x, uint32_t src_y,
-		 uint32_t src_w, uint32_t src_h,
-		 struct drm_modeset_acquire_ctx *ctx)
-{
-	struct drm_plane_state *plane_state;
-	struct vc4_plane_state *vc4_state;
-
-	if (plane != crtc->cursor)
-		goto out;
-
-	plane_state = plane->state;
-	vc4_state = to_vc4_plane_state(plane_state);
-
-	if (!plane_state)
-		goto out;
-
-	/* No configuring new scaling in the fast path. */
-	if (crtc_w != plane_state->crtc_w ||
-	    crtc_h != plane_state->crtc_h ||
-	    src_w != plane_state->src_w ||
-	    src_h != plane_state->src_h) {
-		goto out;
-	}
-
-	if (fb != plane_state->fb) {
-		drm_atomic_set_fb_for_plane(plane->state, fb);
-		vc4_plane_async_set_fb(plane, fb);
-	}
-
-	/* Set the cursor's position on the screen.  This is the
-	 * expected change from the drm_mode_cursor_universal()
-	 * helper.
-	 */
-	plane_state->crtc_x = crtc_x;
-	plane_state->crtc_y = crtc_y;
-
-	/* Allow changing the start position within the cursor BO, if
-	 * that matters.
-	 */
-	plane_state->src_x = src_x;
-	plane_state->src_y = src_y;
-
-	/* Update the display list based on the new crtc_x/y. */
-	vc4_plane_atomic_check(plane, plane_state);
-
-	/* Note that we can't just call vc4_plane_write_dlist()
-	 * because that would smash the context data that the HVS is
-	 * currently using.
-	 */
-	writel(vc4_state->dlist[vc4_state->pos0_offset],
-	       &vc4_state->hw_dlist[vc4_state->pos0_offset]);
-	writel(vc4_state->dlist[vc4_state->pos2_offset],
-	       &vc4_state->hw_dlist[vc4_state->pos2_offset]);
-	writel(vc4_state->dlist[vc4_state->ptr0_offset],
-	       &vc4_state->hw_dlist[vc4_state->ptr0_offset]);
-
-	return 0;
-
-out:
-	return drm_atomic_helper_update_plane(plane, crtc, fb,
-					      crtc_x, crtc_y,
-					      crtc_w, crtc_h,
-					      src_x, src_y,
-					      src_w, src_h,
-					      ctx);
-}
-
 static bool vc4_format_mod_supported(struct drm_plane *plane,
 				     uint32_t format,
 				     uint64_t modifier)
@@ -891,7 +879,7 @@ static bool vc4_format_mod_supported(struct drm_plane *plane,
 }
 
 static const struct drm_plane_funcs vc4_plane_funcs = {
-	.update_plane = vc4_update_plane,
+	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
 	.destroy = vc4_plane_destroy,
 	.set_property = NULL,
@@ -939,5 +927,7 @@ struct drm_plane *vc4_plane_init(struct drm_device *dev,
 
 	drm_plane_helper_add(plane, &vc4_plane_helper_funcs);
 
+	drm_plane_create_alpha_property(plane);
+
 	return plane;
 }
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index a141496104a6..d1fb6fec46eb 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -330,6 +330,21 @@
 #define SCALER_DISPCTRL0                        0x00000040
 # define SCALER_DISPCTRLX_ENABLE		BIT(31)
 # define SCALER_DISPCTRLX_RESET			BIT(30)
+/* Generates a single frame when VSTART is seen and stops at the last
+ * pixel read from the FIFO.
+ */
+# define SCALER_DISPCTRLX_ONESHOT		BIT(29)
+/* Processes a single context in the dlist and then task switch,
+ * instead of an entire line.
+ */
+# define SCALER_DISPCTRLX_ONECTX		BIT(28)
+/* Set to have DISPSLAVE return 2 16bpp pixels and no status data. */
+# define SCALER_DISPCTRLX_FIFO32		BIT(27)
+/* Turns on output to the DISPSLAVE register instead of the normal
+ * FIFO.
+ */
+# define SCALER_DISPCTRLX_FIFOREG		BIT(26)
+
 # define SCALER_DISPCTRLX_WIDTH_MASK		VC4_MASK(23, 12)
 # define SCALER_DISPCTRLX_WIDTH_SHIFT		12
 # define SCALER_DISPCTRLX_HEIGHT_MASK		VC4_MASK(11, 0)
@@ -402,6 +417,68 @@
  */
 # define SCALER_GAMADDR_SRAMENB			BIT(30)
 
+#define SCALER_OLEDOFFS                         0x00000080
+/* Clamps R to [16,235] and G/B to [16,240]. */
+# define SCALER_OLEDOFFS_YUVCLAMP               BIT(31)
+
+/* Chooses which display FIFO the matrix applies to. */
+# define SCALER_OLEDOFFS_DISPFIFO_MASK          VC4_MASK(25, 24)
+# define SCALER_OLEDOFFS_DISPFIFO_SHIFT         24
+# define SCALER_OLEDOFFS_DISPFIFO_DISABLED      0
+# define SCALER_OLEDOFFS_DISPFIFO_0             1
+# define SCALER_OLEDOFFS_DISPFIFO_1             2
+# define SCALER_OLEDOFFS_DISPFIFO_2             3
+
+/* Offsets are 8-bit 2s-complement. */
+# define SCALER_OLEDOFFS_RED_MASK               VC4_MASK(23, 16)
+# define SCALER_OLEDOFFS_RED_SHIFT              16
+# define SCALER_OLEDOFFS_GREEN_MASK             VC4_MASK(15, 8)
+# define SCALER_OLEDOFFS_GREEN_SHIFT            8
+# define SCALER_OLEDOFFS_BLUE_MASK              VC4_MASK(7, 0)
+# define SCALER_OLEDOFFS_BLUE_SHIFT             0
+
+/* The coefficients are S0.9 fractions. */
+#define SCALER_OLEDCOEF0                        0x00000084
+# define SCALER_OLEDCOEF0_B_TO_R_MASK           VC4_MASK(29, 20)
+# define SCALER_OLEDCOEF0_B_TO_R_SHIFT          20
+# define SCALER_OLEDCOEF0_B_TO_G_MASK           VC4_MASK(19, 10)
+# define SCALER_OLEDCOEF0_B_TO_G_SHIFT          10
+# define SCALER_OLEDCOEF0_B_TO_B_MASK           VC4_MASK(9, 0)
+# define SCALER_OLEDCOEF0_B_TO_B_SHIFT          0
+
+#define SCALER_OLEDCOEF1                        0x00000088
+# define SCALER_OLEDCOEF1_G_TO_R_MASK           VC4_MASK(29, 20)
+# define SCALER_OLEDCOEF1_G_TO_R_SHIFT          20
+# define SCALER_OLEDCOEF1_G_TO_G_MASK           VC4_MASK(19, 10)
+# define SCALER_OLEDCOEF1_G_TO_G_SHIFT          10
+# define SCALER_OLEDCOEF1_G_TO_B_MASK           VC4_MASK(9, 0)
+# define SCALER_OLEDCOEF1_G_TO_B_SHIFT          0
+
+#define SCALER_OLEDCOEF2                        0x0000008c
+# define SCALER_OLEDCOEF2_R_TO_R_MASK           VC4_MASK(29, 20)
+# define SCALER_OLEDCOEF2_R_TO_R_SHIFT          20
+# define SCALER_OLEDCOEF2_R_TO_G_MASK           VC4_MASK(19, 10)
+# define SCALER_OLEDCOEF2_R_TO_G_SHIFT          10
+# define SCALER_OLEDCOEF2_R_TO_B_MASK           VC4_MASK(9, 0)
+# define SCALER_OLEDCOEF2_R_TO_B_SHIFT          0
+
+/* Slave addresses for DMAing from HVS composition output to other
+ * devices.  The top bits are valid only in !FIFO32 mode.
+ */
+#define SCALER_DISPSLAVE0                       0x000000c0
+#define SCALER_DISPSLAVE1                       0x000000c9
+#define SCALER_DISPSLAVE2                       0x000000d0
+# define SCALER_DISPSLAVE_ISSUE_VSTART          BIT(31)
+# define SCALER_DISPSLAVE_ISSUE_HSTART          BIT(30)
+/* Set when the current line has been read and an HSTART is required. */
+# define SCALER_DISPSLAVE_EOL                   BIT(26)
+/* Set when the display FIFO is empty. */
+# define SCALER_DISPSLAVE_EMPTY                 BIT(25)
+/* Set when there is RGB data ready to read. */
+# define SCALER_DISPSLAVE_VALID                 BIT(24)
+# define SCALER_DISPSLAVE_RGB_MASK              VC4_MASK(23, 0)
+# define SCALER_DISPSLAVE_RGB_SHIFT             0
+
 #define SCALER_GAMDATA                          0x000000e0
 #define SCALER_DLIST_START                      0x00002000
 #define SCALER_DLIST_SIZE                       0x00004000
@@ -767,6 +844,10 @@ enum hvs_pixel_format {
 	HVS_PIXEL_FORMAT_YCBCR_YUV420_2PLANE = 9,
 	HVS_PIXEL_FORMAT_YCBCR_YUV422_3PLANE = 10,
 	HVS_PIXEL_FORMAT_YCBCR_YUV422_2PLANE = 11,
+	HVS_PIXEL_FORMAT_H264 = 12,
+	HVS_PIXEL_FORMAT_PALETTE = 13,
+	HVS_PIXEL_FORMAT_YUV444_RGB = 14,
+	HVS_PIXEL_FORMAT_AYUV444_RGB = 15,
 };
 
 /* Note: the LSB is the rightmost character shown.  Only valid for
@@ -800,12 +881,27 @@ enum hvs_pixel_format {
 #define SCALER_CTL0_TILING_128B			2
 #define SCALER_CTL0_TILING_256B_OR_T		3
 
+#define SCALER_CTL0_ALPHA_MASK                  BIT(19)
 #define SCALER_CTL0_HFLIP                       BIT(16)
 #define SCALER_CTL0_VFLIP                       BIT(15)
 
+#define SCALER_CTL0_KEY_MODE_MASK		VC4_MASK(18, 17)
+#define SCALER_CTL0_KEY_MODE_SHIFT		17
+#define SCALER_CTL0_KEY_DISABLED		0
+#define SCALER_CTL0_KEY_LUMA_OR_COMMON_RGB	1
+#define SCALER_CTL0_KEY_MATCH			2 /* turn transparent */
+#define SCALER_CTL0_KEY_REPLACE			3 /* replace with value from key mask word 2 */
+
 #define SCALER_CTL0_ORDER_MASK			VC4_MASK(14, 13)
 #define SCALER_CTL0_ORDER_SHIFT			13
 
+#define SCALER_CTL0_RGBA_EXPAND_MASK		VC4_MASK(12, 11)
+#define SCALER_CTL0_RGBA_EXPAND_SHIFT		11
+#define SCALER_CTL0_RGBA_EXPAND_ZERO		0
+#define SCALER_CTL0_RGBA_EXPAND_LSB		1
+#define SCALER_CTL0_RGBA_EXPAND_MSB		2
+#define SCALER_CTL0_RGBA_EXPAND_ROUND		3
+
 #define SCALER_CTL0_SCL1_MASK			VC4_MASK(10, 8)
 #define SCALER_CTL0_SCL1_SHIFT			8
 
@@ -849,6 +945,7 @@ enum hvs_pixel_format {
 #define SCALER_POS2_ALPHA_MODE_FIXED_NONZERO	2
 #define SCALER_POS2_ALPHA_MODE_FIXED_OVER_0x07	3
 #define SCALER_POS2_ALPHA_PREMULT		BIT(29)
+#define SCALER_POS2_ALPHA_MIX			BIT(28)
 
 #define SCALER_POS2_HEIGHT_MASK			VC4_MASK(27, 16)
 #define SCALER_POS2_HEIGHT_SHIFT		16
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index bfc2fa73d2ae..e47e29426078 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -218,8 +218,7 @@ try_again:
  * overall CMA pool before they make scenes complicated enough to run
  * out of bin space.
  */
-int
-vc4_allocate_bin_bo(struct drm_device *drm)
+static int vc4_allocate_bin_bo(struct drm_device *drm)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_v3d *v3d = vc4->v3d;