Merge tag 'drm-misc-next-2025-12-01-1' of https://gitlab.freedesktop.org/drm/misc/kernel into drm-next

Extra drm-misc-next for v6.19-rc1:

UAPI Changes:
- Add support for drm colorop pipeline.
- Add COLOR PIPELINE plane property.
- Add DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE.

Cross-subsystem Changes:
- Attempt to use higher order mappings in system heap allocator.
- Always taint kernel with sw-sync.

Core Changes:
- Small fixes to drm/gem.
- Support emergency restore to drm-client.
- Allocate and release fb_info in single place.
- Rework ttm pipelined eviction fence handling.

Driver Changes:
- Support the drm color pipeline in vkms, amdgfx.
- Add NVJPG driver for tegra.
- Assorted small fixes and updates to rockchip, bridge/dw-hdmi-qp,
  panthor.
- Add ASL CS5263 DP-to-HDMI simple bridge.
- Add and improve support for G LD070WX3-SL01 MIPI DSI, Samsung LTL106AL0,
  Samsung LTL106AL01, Raystar RFF500F-AWH-DNN, Winstar WF70A8SYJHLNGA,
  Wanchanglong w552946aaa, Samsung SOFEF00, Lenovo X13s panel.
- Add support for it66122 to it66121.
- Support mali-G1 gpu in panthor.

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

From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patch.msgid.link/aa5cbd50-7676-4a59-bbed-e8428af86804@linux.intel.com

104 files changed, 6454 insertions, 728 deletions

diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 7789f42027ff..4b3f3ad5058a 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -41,6 +41,7 @@ drm-y := \
 	drm_bridge.o \
 	drm_cache.o \
 	drm_color_mgmt.o \
+	drm_colorop.o \
 	drm_connector.o \
 	drm_crtc.o \
 	drm_displayid.o \
@@ -76,7 +77,8 @@ drm-y := \
 drm-$(CONFIG_DRM_CLIENT) += \
 	drm_client.o \
 	drm_client_event.o \
-	drm_client_modeset.o
+	drm_client_modeset.o \
+	drm_client_sysrq.o
 drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o
 drm-$(CONFIG_COMPAT) += drm_ioc32.o
 drm-$(CONFIG_DRM_PANEL) += drm_panel.o
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 838a51b6098b..421c2bbe2b6a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2185,8 +2185,10 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 	} else {
 		drm_sched_entity_destroy(&adev->mman.high_pr);
 		drm_sched_entity_destroy(&adev->mman.low_pr);
-		dma_fence_put(man->move);
-		man->move = NULL;
+		/* Drop all the old fences since re-creating the scheduler entities
+		 * will allocate new contexts.
+		 */
+		ttm_resource_manager_cleanup(man);
 	}
 
 	/* this just adjusts TTM size idea, which sets lpfn to the correct value */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
index 7329b8cc2576..8e949fe77312 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
@@ -39,7 +39,8 @@ AMDGPUDM = \
 	amdgpu_dm_psr.o \
 	amdgpu_dm_replay.o \
 	amdgpu_dm_quirks.o \
-	amdgpu_dm_wb.o
+	amdgpu_dm_wb.o \
+	amdgpu_dm_colorop.o
 
 ifdef CONFIG_DRM_AMD_DC_FP
 AMDGPUDM += dc_fpu.o
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index e6728fd12eeb..020eb1651219 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -5888,6 +5888,10 @@ fill_plane_color_attributes(const struct drm_plane_state *plane_state,
 
 	*color_space = COLOR_SPACE_SRGB;
 
+	/* Ignore properties when DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE is set */
+	if (plane_state->state && plane_state->state->plane_color_pipeline)
+		return 0;
+
 	/* DRM color properties only affect non-RGB formats. */
 	if (format < SURFACE_PIXEL_FORMAT_VIDEO_BEGIN)
 		return 0;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index a4ac6d442278..1dcc79b35225 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -26,12 +26,39 @@
 #include "amdgpu.h"
 #include "amdgpu_mode.h"
 #include "amdgpu_dm.h"
+#include "amdgpu_dm_colorop.h"
 #include "dc.h"
 #include "modules/color/color_gamma.h"
 
 /**
  * DOC: overview
  *
+ * We have three types of color management in the AMD display driver.
+ * 1. the legacy &drm_crtc DEGAMMA, CTM, and GAMMA properties
+ * 2. AMD driver private color management on &drm_plane and &drm_crtc
+ * 3. AMD plane color pipeline
+ *
+ * The CRTC properties are the original color management. When they were
+ * implemented per-plane color management was not a thing yet. Because
+ * of that we could get away with plumbing the DEGAMMA and CTM
+ * properties to pre-blending HW functions. This is incompatible with
+ * per-plane color management, such as via the AMD private properties or
+ * the new drm_plane color pipeline. The only compatible CRTC property
+ * with per-plane color management is the GAMMA property as it is
+ * applied post-blending.
+ *
+ * The AMD driver private color management properties are only exposed
+ * when the kernel is built explicitly with -DAMD_PRIVATE_COLOR. They
+ * are temporary building blocks on the path to full-fledged &drm_plane
+ * and &drm_crtc color pipelines and lay the driver's groundwork for the
+ * color pipelines.
+ *
+ * The AMD plane color pipeline describes AMD's &drm_colorops via the
+ * &drm_plane's COLOR_PIPELINE property.
+ *
+ * drm_crtc Properties
+ * -------------------
+ *
  * The DC interface to HW gives us the following color management blocks
  * per pipe (surface):
  *
@@ -42,36 +69,93 @@
  * - Surface regamma LUT (normalized)
  * - Output CSC (normalized)
  *
- * But these aren't a direct mapping to DRM color properties. The current DRM
- * interface exposes CRTC degamma, CRTC CTM and CRTC regamma while our hardware
- * is essentially giving:
+ * But these aren't a direct mapping to DRM color properties. The
+ * current DRM interface exposes CRTC degamma, CRTC CTM and CRTC regamma
+ * while our hardware is essentially giving:
  *
  * Plane CTM -> Plane degamma -> Plane CTM -> Plane regamma -> Plane CTM
  *
- * The input gamma LUT block isn't really applicable here since it operates
- * on the actual input data itself rather than the HW fp representation. The
- * input and output CSC blocks are technically available to use as part of
- * the DC interface but are typically used internally by DC for conversions
- * between color spaces. These could be blended together with user
- * adjustments in the future but for now these should remain untouched.
+ * The input gamma LUT block isn't really applicable here since it
+ * operates on the actual input data itself rather than the HW fp
+ * representation. The input and output CSC blocks are technically
+ * available to use as part of the DC interface but are typically used
+ * internally by DC for conversions between color spaces. These could be
+ * blended together with user adjustments in the future but for now
+ * these should remain untouched.
+ *
+ * The pipe blending also happens after these blocks so we don't
+ * actually support any CRTC props with correct blending with multiple
+ * planes - but we can still support CRTC color management properties in
+ * DM in most single plane cases correctly with clever management of the
+ * DC interface in DM.
+ *
+ * As per DRM documentation, blocks should be in hardware bypass when
+ * their respective property is set to NULL. A linear DGM/RGM LUT should
+ * also considered as putting the respective block into bypass mode.
+ *
+ * This means that the following configuration is assumed to be the
+ * default:
+ *
+ * Plane DGM Bypass -> Plane CTM Bypass -> Plane RGM Bypass -> ... CRTC
+ * DGM Bypass -> CRTC CTM Bypass -> CRTC RGM Bypass
+ *
+ * AMD Private Color Management on drm_plane
+ * -----------------------------------------
+ *
+ * The AMD private color management properties on a &drm_plane are:
  *
- * The pipe blending also happens after these blocks so we don't actually
- * support any CRTC props with correct blending with multiple planes - but we
- * can still support CRTC color management properties in DM in most single
- * plane cases correctly with clever management of the DC interface in DM.
+ * - AMD_PLANE_DEGAMMA_LUT
+ * - AMD_PLANE_DEGAMMA_LUT_SIZE
+ * - AMD_PLANE_DEGAMMA_TF
+ * - AMD_PLANE_HDR_MULT
+ * - AMD_PLANE_CTM
+ * - AMD_PLANE_SHAPER_LUT
+ * - AMD_PLANE_SHAPER_LUT_SIZE
+ * - AMD_PLANE_SHAPER_TF
+ * - AMD_PLANE_LUT3D
+ * - AMD_PLANE_LUT3D_SIZE
+ * - AMD_PLANE_BLEND_LUT
+ * - AMD_PLANE_BLEND_LUT_SIZE
+ * - AMD_PLANE_BLEND_TF
  *
- * As per DRM documentation, blocks should be in hardware bypass when their
- * respective property is set to NULL. A linear DGM/RGM LUT should also
- * considered as putting the respective block into bypass mode.
+ * The AMD private color management property on a &drm_crtc is:
  *
- * This means that the following
- * configuration is assumed to be the default:
+ * - AMD_CRTC_REGAMMA_TF
+ *
+ * Use of these properties is discouraged.
+ *
+ * AMD plane color pipeline
+ * ------------------------
+ *
+ * The AMD &drm_plane color pipeline is advertised for DCN generations
+ * 3.0 and newer. It exposes these elements in this order:
+ *
+ * 1. 1D curve colorop
+ * 2. Multiplier
+ * 3. 3x4 CTM
+ * 4. 1D curve colorop
+ * 5. 1D LUT
+ * 6. 3D LUT
+ * 7. 1D curve colorop
+ * 8. 1D LUT
+ *
+ * The multiplier (#2) is a simple multiplier that is applied to all
+ * channels.
+ *
+ * The 3x4 CTM (#3) is a simple 3x4 matrix.
+ *
+ * #1, and #7 are non-linear to linear curves. #4 is a linear to
+ * non-linear curve. They support sRGB, PQ, and BT.709/BT.2020 EOTFs or
+ * their inverse.
+ *
+ * The 1D LUTs (#5 and #8) are plain 4096 entry LUTs.
+ *
+ * The 3DLUT (#6) is a tetrahedrally interpolated 17 cube LUT.
  *
- * Plane DGM Bypass -> Plane CTM Bypass -> Plane RGM Bypass -> ...
- * CRTC DGM Bypass -> CRTC CTM Bypass -> CRTC RGM Bypass
  */
 
 #define MAX_DRM_LUT_VALUE 0xFFFF
+#define MAX_DRM_LUT32_VALUE 0xFFFFFFFF
 #define SDR_WHITE_LEVEL_INIT_VALUE 80
 
 /**
@@ -342,6 +426,21 @@ __extract_blob_lut(const struct drm_property_blob *blob, uint32_t *size)
 }
 
 /**
+ * __extract_blob_lut32 - Extracts the DRM lut and lut size from a blob.
+ * @blob: DRM color mgmt property blob
+ * @size: lut size
+ *
+ * Returns:
+ * DRM LUT or NULL
+ */
+static const struct drm_color_lut32 *
+__extract_blob_lut32(const struct drm_property_blob *blob, uint32_t *size)
+{
+	*size = blob ? drm_color_lut32_size(blob) : 0;
+	return blob ? (struct drm_color_lut32 *)blob->data : NULL;
+}
+
+/**
  * __is_lut_linear - check if the given lut is a linear mapping of values
  * @lut: given lut to check values
  * @size: lut size
@@ -415,6 +514,24 @@ static void __drm_lut_to_dc_gamma(const struct drm_color_lut *lut,
 }
 
 /**
+ * __drm_lut32_to_dc_gamma - convert the drm_color_lut to dc_gamma.
+ * @lut: DRM lookup table for color conversion
+ * @gamma: DC gamma to set entries
+ *
+ * The conversion depends on the size of the lut - whether or not it's legacy.
+ */
+static void __drm_lut32_to_dc_gamma(const struct drm_color_lut32 *lut, struct dc_gamma *gamma)
+{
+	int i;
+
+	for (i = 0; i < MAX_COLOR_LUT_ENTRIES; i++) {
+		gamma->entries.red[i] = dc_fixpt_from_fraction(lut[i].red, MAX_DRM_LUT32_VALUE);
+		gamma->entries.green[i] = dc_fixpt_from_fraction(lut[i].green, MAX_DRM_LUT32_VALUE);
+		gamma->entries.blue[i] = dc_fixpt_from_fraction(lut[i].blue, MAX_DRM_LUT32_VALUE);
+	}
+}
+
+/**
  * __drm_ctm_to_dc_matrix - converts a DRM CTM to a DC CSC float matrix
  * @ctm: DRM color transformation matrix
  * @matrix: DC CSC float matrix
@@ -566,6 +683,63 @@ static int __set_output_tf(struct dc_transfer_func *func,
 	return res ? 0 : -ENOMEM;
 }
 
+/**
+ * __set_output_tf_32 - calculates the output transfer function based on expected input space.
+ * @func: transfer function
+ * @lut: lookup table that defines the color space
+ * @lut_size: size of respective lut
+ * @has_rom: if ROM can be used for hardcoded curve
+ *
+ * Returns:
+ * 0 in case of success. -ENOMEM if fails.
+ */
+static int __set_output_tf_32(struct dc_transfer_func *func,
+			      const struct drm_color_lut32 *lut, uint32_t lut_size,
+			      bool has_rom)
+{
+	struct dc_gamma *gamma = NULL;
+	struct calculate_buffer cal_buffer = {0};
+	bool res;
+
+	cal_buffer.buffer_index = -1;
+
+	if (lut_size) {
+		gamma = dc_create_gamma();
+		if (!gamma)
+			return -ENOMEM;
+
+		gamma->num_entries = lut_size;
+		__drm_lut32_to_dc_gamma(lut, gamma);
+	}
+
+	if (func->tf == TRANSFER_FUNCTION_LINEAR) {
+		/*
+		 * Color module doesn't like calculating regamma params
+		 * on top of a linear input. But degamma params can be used
+		 * instead to simulate this.
+		 */
+		if (gamma)
+			gamma->type = GAMMA_CUSTOM;
+		res = mod_color_calculate_degamma_params(NULL, func,
+							 gamma, gamma != NULL);
+	} else {
+		/*
+		 * Assume sRGB. The actual mapping will depend on whether the
+		 * input was legacy or not.
+		 */
+		if (gamma)
+			gamma->type = GAMMA_CS_TFM_1D;
+		res = mod_color_calculate_regamma_params(func, gamma, gamma != NULL,
+							 has_rom, NULL, &cal_buffer);
+	}
+
+	if (gamma)
+		dc_gamma_release(&gamma);
+
+	return res ? 0 : -ENOMEM;
+}
+
+
 static int amdgpu_dm_set_atomic_regamma(struct dc_transfer_func *out_tf,
 					const struct drm_color_lut *regamma_lut,
 					uint32_t regamma_size, bool has_rom,
@@ -638,6 +812,42 @@ static int __set_input_tf(struct dc_color_caps *caps, struct dc_transfer_func *f
 	return res ? 0 : -ENOMEM;
 }
 
+/**
+ * __set_input_tf_32 - calculates the input transfer function based on expected
+ * input space.
+ * @caps: dc color capabilities
+ * @func: transfer function
+ * @lut: lookup table that defines the color space
+ * @lut_size: size of respective lut.
+ *
+ * Returns:
+ * 0 in case of success. -ENOMEM if fails.
+ */
+static int __set_input_tf_32(struct dc_color_caps *caps, struct dc_transfer_func *func,
+			     const struct drm_color_lut32 *lut, uint32_t lut_size)
+{
+	struct dc_gamma *gamma = NULL;
+	bool res;
+
+	if (lut_size) {
+		gamma = dc_create_gamma();
+		if (!gamma)
+			return -ENOMEM;
+
+		gamma->type = GAMMA_CUSTOM;
+		gamma->num_entries = lut_size;
+
+		__drm_lut32_to_dc_gamma(lut, gamma);
+	}
+
+	res = mod_color_calculate_degamma_params(caps, func, gamma, gamma != NULL);
+
+	if (gamma)
+		dc_gamma_release(&gamma);
+
+	return res ? 0 : -ENOMEM;
+}
+
 static enum dc_transfer_func_predefined
 amdgpu_tf_to_dc_tf(enum amdgpu_transfer_function tf)
 {
@@ -667,6 +877,27 @@ amdgpu_tf_to_dc_tf(enum amdgpu_transfer_function tf)
 	}
 }
 
+static enum dc_transfer_func_predefined
+amdgpu_colorop_tf_to_dc_tf(enum drm_colorop_curve_1d_type tf)
+{
+	switch (tf) {
+	case DRM_COLOROP_1D_CURVE_SRGB_EOTF:
+	case DRM_COLOROP_1D_CURVE_SRGB_INV_EOTF:
+		return TRANSFER_FUNCTION_SRGB;
+	case DRM_COLOROP_1D_CURVE_PQ_125_EOTF:
+	case DRM_COLOROP_1D_CURVE_PQ_125_INV_EOTF:
+		return TRANSFER_FUNCTION_PQ;
+	case DRM_COLOROP_1D_CURVE_BT2020_INV_OETF:
+	case DRM_COLOROP_1D_CURVE_BT2020_OETF:
+		return TRANSFER_FUNCTION_BT709;
+	case DRM_COLOROP_1D_CURVE_GAMMA22:
+	case DRM_COLOROP_1D_CURVE_GAMMA22_INV:
+		return TRANSFER_FUNCTION_GAMMA22;
+	default:
+		return TRANSFER_FUNCTION_LINEAR;
+	}
+}
+
 static void __to_dc_lut3d_color(struct dc_rgb *rgb,
 				const struct drm_color_lut lut,
 				int bit_precision)
@@ -720,6 +951,59 @@ static void __drm_3dlut_to_dc_3dlut(const struct drm_color_lut *lut,
 	__to_dc_lut3d_color(&lut0[lut_i], lut[i], bit_depth);
 }
 
+static void __to_dc_lut3d_32_color(struct dc_rgb *rgb,
+				   const struct drm_color_lut32 lut,
+				   int bit_precision)
+{
+	rgb->red = drm_color_lut32_extract(lut.red, bit_precision);
+	rgb->green = drm_color_lut32_extract(lut.green, bit_precision);
+	rgb->blue  = drm_color_lut32_extract(lut.blue, bit_precision);
+}
+
+static void __drm_3dlut32_to_dc_3dlut(const struct drm_color_lut32 *lut,
+				       uint32_t lut3d_size,
+				       struct tetrahedral_params *params,
+				       bool use_tetrahedral_9,
+				       int bit_depth)
+{
+	struct dc_rgb *lut0;
+	struct dc_rgb *lut1;
+	struct dc_rgb *lut2;
+	struct dc_rgb *lut3;
+	int lut_i, i;
+
+
+	if (use_tetrahedral_9) {
+		lut0 = params->tetrahedral_9.lut0;
+		lut1 = params->tetrahedral_9.lut1;
+		lut2 = params->tetrahedral_9.lut2;
+		lut3 = params->tetrahedral_9.lut3;
+	} else {
+		lut0 = params->tetrahedral_17.lut0;
+		lut1 = params->tetrahedral_17.lut1;
+		lut2 = params->tetrahedral_17.lut2;
+		lut3 = params->tetrahedral_17.lut3;
+	}
+
+	for (lut_i = 0, i = 0; i < lut3d_size - 4; lut_i++, i += 4) {
+		/*
+		 * We should consider the 3D LUT RGB values are distributed
+		 * along four arrays lut0-3 where the first sizes 1229 and the
+		 * other 1228. The bit depth supported for 3dlut channel is
+		 * 12-bit, but DC also supports 10-bit.
+		 *
+		 * TODO: improve color pipeline API to enable the userspace set
+		 * bit depth and 3D LUT size/stride, as specified by VA-API.
+		 */
+		__to_dc_lut3d_32_color(&lut0[lut_i], lut[i], bit_depth);
+		__to_dc_lut3d_32_color(&lut1[lut_i], lut[i + 1], bit_depth);
+		__to_dc_lut3d_32_color(&lut2[lut_i], lut[i + 2], bit_depth);
+		__to_dc_lut3d_32_color(&lut3[lut_i], lut[i + 3], bit_depth);
+	}
+	/* lut0 has 1229 points (lut_size/4 + 1) */
+	__to_dc_lut3d_32_color(&lut0[lut_i], lut[i], bit_depth);
+}
+
 /* amdgpu_dm_atomic_lut3d - set DRM 3D LUT to DC stream
  * @drm_lut3d: user 3D LUT
  * @drm_lut3d_size: size of 3D LUT
@@ -1178,6 +1462,360 @@ __set_dm_plane_degamma(struct drm_plane_state *plane_state,
 }
 
 static int
+__set_colorop_in_tf_1d_curve(struct dc_plane_state *dc_plane_state,
+			     struct drm_colorop_state *colorop_state)
+{
+	struct dc_transfer_func *tf = &dc_plane_state->in_transfer_func;
+	struct drm_colorop *colorop = colorop_state->colorop;
+	struct drm_device *drm = colorop->dev;
+
+	if (colorop->type != DRM_COLOROP_1D_CURVE)
+		return -EINVAL;
+
+	if (!(BIT(colorop_state->curve_1d_type) & amdgpu_dm_supported_degam_tfs))
+		return -EINVAL;
+
+	if (colorop_state->bypass) {
+		tf->type = TF_TYPE_BYPASS;
+		tf->tf = TRANSFER_FUNCTION_LINEAR;
+		return 0;
+	}
+
+	drm_dbg(drm, "Degamma colorop with ID: %d\n", colorop->base.id);
+
+	tf->type = TF_TYPE_PREDEFINED;
+	tf->tf = amdgpu_colorop_tf_to_dc_tf(colorop_state->curve_1d_type);
+
+	return 0;
+}
+
+static int
+__set_dm_plane_colorop_degamma(struct drm_plane_state *plane_state,
+			       struct dc_plane_state *dc_plane_state,
+			       struct drm_colorop *colorop)
+{
+	struct drm_colorop *old_colorop;
+	struct drm_colorop_state *colorop_state = NULL, *new_colorop_state;
+	struct drm_atomic_state *state = plane_state->state;
+	int i = 0;
+
+	old_colorop = colorop;
+
+	/* 1st op: 1d curve - degamma */
+	for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) {
+		if (new_colorop_state->colorop == old_colorop &&
+		    (BIT(new_colorop_state->curve_1d_type) & amdgpu_dm_supported_degam_tfs)) {
+			colorop_state = new_colorop_state;
+			break;
+		}
+	}
+
+	if (!colorop_state)
+		return -EINVAL;
+
+	return __set_colorop_in_tf_1d_curve(dc_plane_state, colorop_state);
+}
+
+static int
+__set_dm_plane_colorop_3x4_matrix(struct drm_plane_state *plane_state,
+				  struct dc_plane_state *dc_plane_state,
+				  struct drm_colorop *colorop)
+{
+	struct drm_colorop *old_colorop;
+	struct drm_colorop_state *colorop_state = NULL, *new_colorop_state;
+	struct drm_atomic_state *state = plane_state->state;
+	const struct drm_device *dev = colorop->dev;
+	const struct drm_property_blob *blob;
+	struct drm_color_ctm_3x4 *ctm = NULL;
+	int i = 0;
+
+	/* 3x4 matrix */
+	old_colorop = colorop;
+	for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) {
+		if (new_colorop_state->colorop == old_colorop &&
+		    new_colorop_state->colorop->type == DRM_COLOROP_CTM_3X4) {
+			colorop_state = new_colorop_state;
+			break;
+		}
+	}
+
+	if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_CTM_3X4) {
+		drm_dbg(dev, "3x4 matrix colorop with ID: %d\n", colorop->base.id);
+		blob = colorop_state->data;
+		if (blob->length == sizeof(struct drm_color_ctm_3x4)) {
+			ctm = (struct drm_color_ctm_3x4 *) blob->data;
+			__drm_ctm_3x4_to_dc_matrix(ctm, dc_plane_state->gamut_remap_matrix.matrix);
+			dc_plane_state->gamut_remap_matrix.enable_remap = true;
+			dc_plane_state->input_csc_color_matrix.enable_adjustment = false;
+		} else {
+			drm_warn(dev, "blob->length (%zu) isn't equal to drm_color_ctm_3x4 (%zu)\n",
+				 blob->length, sizeof(struct drm_color_ctm_3x4));
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int
+__set_dm_plane_colorop_multiplier(struct drm_plane_state *plane_state,
+				  struct dc_plane_state *dc_plane_state,
+				  struct drm_colorop *colorop)
+{
+	struct drm_colorop *old_colorop;
+	struct drm_colorop_state *colorop_state = NULL, *new_colorop_state;
+	struct drm_atomic_state *state = plane_state->state;
+	const struct drm_device *dev = colorop->dev;
+	int i = 0;
+
+	/* Multiplier */
+	old_colorop = colorop;
+	for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) {
+		if (new_colorop_state->colorop == old_colorop &&
+		    new_colorop_state->colorop->type == DRM_COLOROP_MULTIPLIER) {
+			colorop_state = new_colorop_state;
+			break;
+		}
+	}
+
+	if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_MULTIPLIER) {
+		drm_dbg(dev, "Multiplier colorop with ID: %d\n", colorop->base.id);
+		dc_plane_state->hdr_mult = amdgpu_dm_fixpt_from_s3132(colorop_state->multiplier);
+	}
+
+	return 0;
+}
+
+static int
+__set_dm_plane_colorop_shaper(struct drm_plane_state *plane_state,
+			      struct dc_plane_state *dc_plane_state,
+			      struct drm_colorop *colorop)
+{
+	struct drm_colorop *old_colorop;
+	struct drm_colorop_state *colorop_state = NULL, *new_colorop_state;
+	struct drm_atomic_state *state = plane_state->state;
+	enum dc_transfer_func_predefined default_tf = TRANSFER_FUNCTION_LINEAR;
+	struct dc_transfer_func *tf = &dc_plane_state->in_shaper_func;
+	const struct drm_color_lut32 *shaper_lut;
+	struct drm_device *dev = colorop->dev;
+	bool enabled = false;
+	u32 shaper_size;
+	int i = 0, ret = 0;
+
+	/* 1D Curve - SHAPER TF */
+	old_colorop = colorop;
+	for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) {
+		if (new_colorop_state->colorop == old_colorop &&
+		    (BIT(new_colorop_state->curve_1d_type) & amdgpu_dm_supported_shaper_tfs)) {
+			colorop_state = new_colorop_state;
+			break;
+		}
+	}
+
+	if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_1D_CURVE) {
+		drm_dbg(dev, "Shaper TF colorop with ID: %d\n", colorop->base.id);
+		tf->type = TF_TYPE_DISTRIBUTED_POINTS;
+		tf->tf = default_tf = amdgpu_colorop_tf_to_dc_tf(colorop_state->curve_1d_type);
+		tf->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE;
+		ret = __set_output_tf(tf, 0, 0, false);
+		if (ret)
+			return ret;
+		enabled = true;
+	}
+
+	/* 1D LUT - SHAPER LUT */
+	colorop = old_colorop->next;
+	if (!colorop) {
+		drm_dbg(dev, "no Shaper LUT colorop found\n");
+		return -EINVAL;
+	}
+
+	old_colorop = colorop;
+	for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) {
+		if (new_colorop_state->colorop == old_colorop &&
+		    new_colorop_state->colorop->type == DRM_COLOROP_1D_LUT) {
+			colorop_state = new_colorop_state;
+			break;
+		}
+	}
+
+	if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_1D_LUT) {
+		drm_dbg(dev, "Shaper LUT colorop with ID: %d\n", colorop->base.id);
+		tf->type = TF_TYPE_DISTRIBUTED_POINTS;
+		tf->tf = default_tf;
+		tf->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE;
+		shaper_lut = __extract_blob_lut32(colorop_state->data, &shaper_size);
+		shaper_size = shaper_lut != NULL ? shaper_size : 0;
+
+		/* Custom LUT size must be the same as supported size */
+		if (shaper_size == colorop->size) {
+			ret = __set_output_tf_32(tf, shaper_lut, shaper_size, false);
+			if (ret)
+				return ret;
+			enabled = true;
+		}
+	}
+
+	if (!enabled)
+		tf->type = TF_TYPE_BYPASS;
+
+	return 0;
+}
+
+/* __set_colorop_3dlut - set DRM 3D LUT to DC stream
+ * @drm_lut3d: user 3D LUT
+ * @drm_lut3d_size: size of 3D LUT
+ * @lut3d: DC 3D LUT
+ *
+ * Map user 3D LUT data to DC 3D LUT and all necessary bits to program it
+ * on DCN accordingly.
+ *
+ * Returns:
+ * 0 on success. -EINVAL if drm_lut3d_size is zero.
+ */
+static int __set_colorop_3dlut(const struct drm_color_lut32 *drm_lut3d,
+				uint32_t drm_lut3d_size,
+				struct dc_3dlut *lut)
+{
+	if (!drm_lut3d_size) {
+		lut->state.bits.initialized = 0;
+		return -EINVAL;
+	}
+
+	/* Only supports 17x17x17 3D LUT (12-bit) now */
+	lut->lut_3d.use_12bits = true;
+	lut->lut_3d.use_tetrahedral_9 = false;
+
+	lut->state.bits.initialized = 1;
+	__drm_3dlut32_to_dc_3dlut(drm_lut3d, drm_lut3d_size, &lut->lut_3d,
+				   lut->lut_3d.use_tetrahedral_9, 12);
+
+	return 0;
+}
+
+static int
+__set_dm_plane_colorop_3dlut(struct drm_plane_state *plane_state,
+			     struct dc_plane_state *dc_plane_state,
+			     struct drm_colorop *colorop)
+{
+	struct drm_colorop *old_colorop;
+	struct drm_colorop_state *colorop_state = NULL, *new_colorop_state;
+	struct dc_transfer_func *tf = &dc_plane_state->in_shaper_func;
+	struct drm_atomic_state *state = plane_state->state;
+	const struct amdgpu_device *adev = drm_to_adev(colorop->dev);
+	const struct drm_device *dev = colorop->dev;
+	const struct drm_color_lut32 *lut3d;
+	uint32_t lut3d_size;
+	int i = 0, ret = 0;
+
+	/* 3D LUT */
+	old_colorop = colorop;
+	for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) {
+		if (new_colorop_state->colorop == old_colorop &&
+		    new_colorop_state->colorop->type == DRM_COLOROP_3D_LUT) {
+			colorop_state = new_colorop_state;
+			break;
+		}
+	}
+
+	if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_3D_LUT) {
+		if (!adev->dm.dc->caps.color.dpp.hw_3d_lut) {
+			drm_dbg(dev, "3D LUT is not supported by hardware\n");
+			return -EINVAL;
+		}
+
+		drm_dbg(dev, "3D LUT colorop with ID: %d\n", colorop->base.id);
+		lut3d = __extract_blob_lut32(colorop_state->data, &lut3d_size);
+		lut3d_size = lut3d != NULL ? lut3d_size : 0;
+		ret = __set_colorop_3dlut(lut3d, lut3d_size, &dc_plane_state->lut3d_func);
+		if (ret) {
+			drm_dbg(dev, "3D LUT colorop with ID: %d has LUT size = %d\n",
+				colorop->base.id, lut3d_size);
+			return ret;
+		}
+
+		/* 3D LUT requires shaper. If shaper colorop is bypassed, enable shaper curve
+		 * with TRANSFER_FUNCTION_LINEAR
+		 */
+		if (tf->type == TF_TYPE_BYPASS) {
+			tf->type = TF_TYPE_DISTRIBUTED_POINTS;
+			tf->tf = TRANSFER_FUNCTION_LINEAR;
+			tf->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE;
+			ret = __set_output_tf_32(tf, NULL, 0, false);
+		}
+	}
+
+	return ret;
+}
+
+static int
+__set_dm_plane_colorop_blend(struct drm_plane_state *plane_state,
+			     struct dc_plane_state *dc_plane_state,
+			     struct drm_colorop *colorop)
+{
+	struct drm_colorop *old_colorop;
+	struct drm_colorop_state *colorop_state = NULL, *new_colorop_state;
+	struct drm_atomic_state *state = plane_state->state;
+	enum dc_transfer_func_predefined default_tf = TRANSFER_FUNCTION_LINEAR;
+	struct dc_transfer_func *tf = &dc_plane_state->blend_tf;
+	const struct drm_color_lut32 *blend_lut = NULL;
+	struct drm_device *dev = colorop->dev;
+	uint32_t blend_size = 0;
+	int i = 0;
+
+	/* 1D Curve - BLND TF */
+	old_colorop = colorop;
+	for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) {
+		if (new_colorop_state->colorop == old_colorop &&
+		    (BIT(new_colorop_state->curve_1d_type) & amdgpu_dm_supported_blnd_tfs)) {
+			colorop_state = new_colorop_state;
+			break;
+		}
+	}
+
+	if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_1D_CURVE &&
+	    (BIT(colorop_state->curve_1d_type) & amdgpu_dm_supported_blnd_tfs)) {
+		drm_dbg(dev, "Blend TF colorop with ID: %d\n", colorop->base.id);
+		tf->type = TF_TYPE_DISTRIBUTED_POINTS;
+		tf->tf = default_tf = amdgpu_colorop_tf_to_dc_tf(colorop_state->curve_1d_type);
+		tf->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE;
+		__set_input_tf_32(NULL, tf, blend_lut, blend_size);
+	}
+
+	/* 1D Curve - BLND LUT */
+	colorop = old_colorop->next;
+	if (!colorop) {
+		drm_dbg(dev, "no Blend LUT colorop found\n");
+		return -EINVAL;
+	}
+
+	old_colorop = colorop;
+	for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) {
+		if (new_colorop_state->colorop == old_colorop &&
+		    new_colorop_state->colorop->type == DRM_COLOROP_1D_LUT) {
+			colorop_state = new_colorop_state;
+			break;
+		}
+	}
+
+	if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_1D_LUT &&
+	    (BIT(colorop_state->curve_1d_type) & amdgpu_dm_supported_blnd_tfs)) {
+		drm_dbg(dev, "Blend LUT colorop with ID: %d\n", colorop->base.id);
+		tf->type = TF_TYPE_DISTRIBUTED_POINTS;
+		tf->tf = default_tf;
+		tf->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE;
+		blend_lut = __extract_blob_lut32(colorop_state->data, &blend_size);
+		blend_size = blend_lut != NULL ? blend_size : 0;
+
+		/* Custom LUT size must be the same as supported size */
+		if (blend_size == colorop->size)
+			__set_input_tf_32(NULL, tf, blend_lut, blend_size);
+	}
+
+	return 0;
+}
+
+static int
 amdgpu_dm_plane_set_color_properties(struct drm_plane_state *plane_state,
 				     struct dc_plane_state *dc_plane_state)
 {
@@ -1227,6 +1865,93 @@ amdgpu_dm_plane_set_color_properties(struct drm_plane_state *plane_state,
 	return 0;
 }
 
+static int
+amdgpu_dm_plane_set_colorop_properties(struct drm_plane_state *plane_state,
+				       struct dc_plane_state *dc_plane_state)
+{
+	struct drm_colorop *colorop = plane_state->color_pipeline;
+	struct drm_device *dev = plane_state->plane->dev;
+	struct amdgpu_device *adev = drm_to_adev(dev);
+	int ret;
+
+	/* 1D Curve - DEGAM TF */
+	if (!colorop)
+		return -EINVAL;
+
+	ret = __set_dm_plane_colorop_degamma(plane_state, dc_plane_state, colorop);
+	if (ret)
+		return ret;
+
+	/* Multiplier */
+	colorop = colorop->next;
+	if (!colorop) {
+		drm_dbg(dev, "no multiplier colorop found\n");
+		return -EINVAL;
+	}
+
+	ret = __set_dm_plane_colorop_multiplier(plane_state, dc_plane_state, colorop);
+	if (ret)
+		return ret;
+
+	/* 3x4 matrix */
+	colorop = colorop->next;
+	if (!colorop) {
+		drm_dbg(dev, "no 3x4 matrix colorop found\n");
+		return -EINVAL;
+	}
+
+	ret = __set_dm_plane_colorop_3x4_matrix(plane_state, dc_plane_state, colorop);
+	if (ret)
+		return ret;
+
+	if (adev->dm.dc->caps.color.dpp.hw_3d_lut) {
+		/* 1D Curve & LUT - SHAPER TF & LUT */
+		colorop = colorop->next;
+		if (!colorop) {
+			drm_dbg(dev, "no Shaper TF colorop found\n");
+			return -EINVAL;
+		}
+
+		ret = __set_dm_plane_colorop_shaper(plane_state, dc_plane_state, colorop);
+		if (ret)
+			return ret;
+
+		/* Shaper LUT colorop is already handled, just skip here */
+		colorop = colorop->next;
+		if (!colorop)
+			return -EINVAL;
+
+		/* 3D LUT */
+		colorop = colorop->next;
+		if (!colorop) {
+			drm_dbg(dev, "no 3D LUT colorop found\n");
+			return -EINVAL;
+		}
+
+		ret = __set_dm_plane_colorop_3dlut(plane_state, dc_plane_state, colorop);
+		if (ret)
+			return ret;
+	}
+
+	/* 1D Curve & LUT - BLND TF & LUT */
+	colorop = colorop->next;
+	if (!colorop) {
+		drm_dbg(dev, "no Blend TF colorop found\n");
+		return -EINVAL;
+	}
+
+	ret = __set_dm_plane_colorop_blend(plane_state, dc_plane_state, colorop);
+	if (ret)
+		return ret;
+
+	/* BLND LUT colorop is already handled, just skip here */
+	colorop = colorop->next;
+	if (!colorop)
+		return -EINVAL;
+
+	return 0;
+}
+
 /**
  * amdgpu_dm_update_plane_color_mgmt: Maps DRM color management to DC plane.
  * @crtc: amdgpu_dm crtc state
@@ -1323,5 +2048,8 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 		dc_plane_state->input_csc_color_matrix.enable_adjustment = false;
 	}
 
+	if (!amdgpu_dm_plane_set_colorop_properties(plane_state, dc_plane_state))
+		return 0;
+
 	return amdgpu_dm_plane_set_color_properties(plane_state, dc_plane_state);
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
new file mode 100644
index 000000000000..d585618b8064
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
@@ -0,0 +1,209 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright 2023 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include <drm/drm_print.h>
+#include <drm/drm_plane.h>
+#include <drm/drm_property.h>
+#include <drm/drm_colorop.h>
+
+#include "amdgpu.h"
+#include "amdgpu_dm_colorop.h"
+#include "dc.h"
+
+const u64 amdgpu_dm_supported_degam_tfs =
+	BIT(DRM_COLOROP_1D_CURVE_SRGB_EOTF) |
+	BIT(DRM_COLOROP_1D_CURVE_PQ_125_EOTF) |
+	BIT(DRM_COLOROP_1D_CURVE_BT2020_INV_OETF) |
+	BIT(DRM_COLOROP_1D_CURVE_GAMMA22_INV);
+
+const u64 amdgpu_dm_supported_shaper_tfs =
+	BIT(DRM_COLOROP_1D_CURVE_SRGB_INV_EOTF) |
+	BIT(DRM_COLOROP_1D_CURVE_PQ_125_INV_EOTF) |
+	BIT(DRM_COLOROP_1D_CURVE_BT2020_OETF) |
+	BIT(DRM_COLOROP_1D_CURVE_GAMMA22);
+
+const u64 amdgpu_dm_supported_blnd_tfs =
+	BIT(DRM_COLOROP_1D_CURVE_SRGB_EOTF) |
+	BIT(DRM_COLOROP_1D_CURVE_PQ_125_EOTF) |
+	BIT(DRM_COLOROP_1D_CURVE_BT2020_INV_OETF) |
+	BIT(DRM_COLOROP_1D_CURVE_GAMMA22_INV);
+
+#define MAX_COLOR_PIPELINE_OPS 10
+
+#define LUT3D_SIZE		17
+
+int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_prop_enum_list *list)
+{
+	struct drm_colorop *ops[MAX_COLOR_PIPELINE_OPS];
+	struct drm_device *dev = plane->dev;
+	struct amdgpu_device *adev = drm_to_adev(dev);
+	int ret;
+	int i = 0;
+
+	memset(ops, 0, sizeof(ops));
+
+	/* 1D curve - DEGAM TF */
+	ops[i] = kzalloc(sizeof(*ops[0]), GFP_KERNEL);
+	if (!ops[i]) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	ret = drm_plane_colorop_curve_1d_init(dev, ops[i], plane,
+					      amdgpu_dm_supported_degam_tfs,
+					      DRM_COLOROP_FLAG_ALLOW_BYPASS);
+	if (ret)
+		goto cleanup;
+
+	list->type = ops[i]->base.id;
+	list->name = kasprintf(GFP_KERNEL, "Color Pipeline %d", ops[i]->base.id);
+
+	i++;
+
+	/* Multiplier */
+	ops[i] = kzalloc(sizeof(struct drm_colorop), GFP_KERNEL);
+	if (!ops[i]) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	ret = drm_plane_colorop_mult_init(dev, ops[i], plane, DRM_COLOROP_FLAG_ALLOW_BYPASS);
+	if (ret)
+		goto cleanup;
+
+	drm_colorop_set_next_property(ops[i-1], ops[i]);
+
+	i++;
+
+	/* 3x4 matrix */
+	ops[i] = kzalloc(sizeof(struct drm_colorop), GFP_KERNEL);
+	if (!ops[i]) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	ret = drm_plane_colorop_ctm_3x4_init(dev, ops[i], plane, DRM_COLOROP_FLAG_ALLOW_BYPASS);
+	if (ret)
+		goto cleanup;
+
+	drm_colorop_set_next_property(ops[i-1], ops[i]);
+
+	i++;
+
+	if (adev->dm.dc->caps.color.dpp.hw_3d_lut) {
+		/* 1D curve - SHAPER TF */
+		ops[i] = kzalloc(sizeof(*ops[0]), GFP_KERNEL);
+		if (!ops[i]) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+
+		ret = drm_plane_colorop_curve_1d_init(dev, ops[i], plane,
+						amdgpu_dm_supported_shaper_tfs,
+						DRM_COLOROP_FLAG_ALLOW_BYPASS);
+		if (ret)
+			goto cleanup;
+
+		drm_colorop_set_next_property(ops[i-1], ops[i]);
+
+		i++;
+
+		/* 1D LUT - SHAPER LUT */
+		ops[i] = kzalloc(sizeof(*ops[0]), GFP_KERNEL);
+		if (!ops[i]) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+
+		ret = drm_plane_colorop_curve_1d_lut_init(dev, ops[i], plane, MAX_COLOR_LUT_ENTRIES,
+							DRM_COLOROP_LUT1D_INTERPOLATION_LINEAR,
+							DRM_COLOROP_FLAG_ALLOW_BYPASS);
+		if (ret)
+			goto cleanup;
+
+		drm_colorop_set_next_property(ops[i-1], ops[i]);
+
+		i++;
+
+		/* 3D LUT */
+		ops[i] = kzalloc(sizeof(*ops[0]), GFP_KERNEL);
+		if (!ops[i]) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+
+		ret = drm_plane_colorop_3dlut_init(dev, ops[i], plane, LUT3D_SIZE,
+					DRM_COLOROP_LUT3D_INTERPOLATION_TETRAHEDRAL,
+					DRM_COLOROP_FLAG_ALLOW_BYPASS);
+		if (ret)
+			goto cleanup;
+
+		drm_colorop_set_next_property(ops[i-1], ops[i]);
+
+		i++;
+	}
+
+	/* 1D curve - BLND TF */
+	ops[i] = kzalloc(sizeof(*ops[0]), GFP_KERNEL);
+	if (!ops[i]) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	ret = drm_plane_colorop_curve_1d_init(dev, ops[i], plane,
+					      amdgpu_dm_supported_blnd_tfs,
+					      DRM_COLOROP_FLAG_ALLOW_BYPASS);
+	if (ret)
+		goto cleanup;
+
+	drm_colorop_set_next_property(ops[i - 1], ops[i]);
+
+	i++;
+
+	/* 1D LUT - BLND LUT */
+	ops[i] = kzalloc(sizeof(struct drm_colorop), GFP_KERNEL);
+	if (!ops[i]) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	ret = drm_plane_colorop_curve_1d_lut_init(dev, ops[i], plane, MAX_COLOR_LUT_ENTRIES,
+						  DRM_COLOROP_LUT1D_INTERPOLATION_LINEAR,
+						  DRM_COLOROP_FLAG_ALLOW_BYPASS);
+	if (ret)
+		goto cleanup;
+
+	drm_colorop_set_next_property(ops[i-1], ops[i]);
+	return 0;
+
+cleanup:
+	if (ret == -ENOMEM)
+		drm_err(plane->dev, "KMS: Failed to allocate colorop\n");
+
+	drm_colorop_pipeline_destroy(dev);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.h
new file mode 100644
index 000000000000..2e1617ffc8ee
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2023 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __AMDGPU_DM_COLOROP_H__
+#define __AMDGPU_DM_COLOROP_H__
+
+extern const u64 amdgpu_dm_supported_degam_tfs;
+extern const u64 amdgpu_dm_supported_shaper_tfs;
+extern const u64 amdgpu_dm_supported_blnd_tfs;
+
+int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_prop_enum_list *list);
+
+#endif /* __AMDGPU_DM_COLOROP_H__*/
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 38f9ea313dcb..697e232acebf 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -736,7 +736,7 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
 {
 	struct amdgpu_crtc *acrtc = NULL;
 	struct drm_plane *cursor_plane;
-	bool is_dcn;
+	bool has_degamma;
 	int res = -ENOMEM;
 
 	cursor_plane = kzalloc(sizeof(*cursor_plane), GFP_KERNEL);
@@ -775,20 +775,18 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
 
 	dm->adev->mode_info.crtcs[crtc_index] = acrtc;
 
-	/* Don't enable DRM CRTC degamma property for DCE since it doesn't
-	 * support programmable degamma anywhere.
+	/* Don't enable DRM CRTC degamma property for
+	 * 1. Degamma is replaced by color pipeline.
+	 * 2. DCE since it doesn't support programmable degamma anywhere.
+	 * 3. DCN401 since pre-blending degamma LUT doesn't apply to cursor.
 	 */
-	is_dcn = dm->adev->dm.dc->caps.color.dpp.dcn_arch;
-	/* Dont't enable DRM CRTC degamma property for DCN401 since the
-	 * pre-blending degamma LUT doesn't apply to cursor, and therefore
-	 * can't work similar to a post-blending degamma LUT as in other hw
-	 * versions.
-	 * TODO: revisit it once KMS plane color API is merged.
-	 */
-	drm_crtc_enable_color_mgmt(&acrtc->base,
-				   (is_dcn &&
-				    dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01) ?
-				     MAX_COLOR_LUT_ENTRIES : 0,
+	if (plane->color_pipeline_property)
+		has_degamma = false;
+	else
+		has_degamma = dm->adev->dm.dc->caps.color.dpp.dcn_arch &&
+			      dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01;
+
+	drm_crtc_enable_color_mgmt(&acrtc->base, has_degamma ? MAX_COLOR_LUT_ENTRIES : 0,
 				   true, MAX_COLOR_LUT_ENTRIES);
 
 	drm_mode_crtc_set_gamma_size(&acrtc->base, MAX_COLOR_LEGACY_LUT_ENTRIES);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index e027798ece03..2e3ee78999d9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -37,6 +37,7 @@
 #include "amdgpu_display.h"
 #include "amdgpu_dm_trace.h"
 #include "amdgpu_dm_plane.h"
+#include "amdgpu_dm_colorop.h"
 #include "gc/gc_11_0_0_offset.h"
 #include "gc/gc_11_0_0_sh_mask.h"
 
@@ -1782,6 +1783,39 @@ dm_atomic_plane_get_property(struct drm_plane *plane,
 
 	return 0;
 }
+#else
+
+#define MAX_COLOR_PIPELINES 5
+
+static int
+dm_plane_init_colorops(struct drm_plane *plane)
+{
+	struct drm_prop_enum_list pipelines[MAX_COLOR_PIPELINES];
+	struct drm_device *dev = plane->dev;
+	struct amdgpu_device *adev = drm_to_adev(dev);
+	struct dc *dc = adev->dm.dc;
+	int len = 0;
+	int ret;
+
+	if (plane->type == DRM_PLANE_TYPE_CURSOR)
+		return 0;
+
+	/* initialize pipeline */
+	if (dc->ctx->dce_version >= DCN_VERSION_3_0) {
+		ret = amdgpu_dm_initialize_default_pipeline(plane, &pipelines[len]);
+		if (ret) {
+			drm_err(plane->dev, "Failed to create color pipeline for plane %d: %d\n",
+				plane->base.id, ret);
+			return ret;
+		}
+		len++;
+
+		/* Create COLOR_PIPELINE property and attach */
+		drm_plane_create_color_pipeline_property(plane, pipelines, len);
+	}
+
+	return 0;
+}
 #endif
 
 static const struct drm_plane_funcs dm_plane_funcs = {
@@ -1890,7 +1924,12 @@ int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm,
 
 #ifdef AMD_PRIVATE_COLOR
 	dm_atomic_plane_attach_color_mgmt_properties(dm, plane);
+#else
+	res = dm_plane_init_colorops(plane);
+	if (res)
+		return res;
 #endif
+
 	/* Create (reset) the plane state */
 	if (plane->funcs->reset)
 		plane->funcs->reset(plane);
diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c
index be703d35f6b7..8bbae94804f8 100644
--- a/drivers/gpu/drm/armada/armada_fbdev.c
+++ b/drivers/gpu/drm/armada/armada_fbdev.c
@@ -44,10 +44,10 @@ int armada_fbdev_driver_fbdev_probe(struct drm_fb_helper *fbh,
 				    struct drm_fb_helper_surface_size *sizes)
 {
 	struct drm_device *dev = fbh->dev;
+	struct fb_info *info = fbh->info;
 	struct drm_mode_fb_cmd2 mode;
 	struct armada_framebuffer *dfb;
 	struct armada_gem_object *obj;
-	struct fb_info *info;
 	int size, ret;
 	void *ptr;
 
@@ -91,12 +91,6 @@ int armada_fbdev_driver_fbdev_probe(struct drm_fb_helper *fbh,
 	if (IS_ERR(dfb))
 		return PTR_ERR(dfb);
 
-	info = drm_fb_helper_alloc_info(fbh);
-	if (IS_ERR(info)) {
-		ret = PTR_ERR(info);
-		goto err_fballoc;
-	}
-
 	info->fbops = &armada_fb_ops;
 	info->fix.smem_start = obj->phys_addr;
 	info->fix.smem_len = obj->obj.size;
@@ -112,8 +106,4 @@ int armada_fbdev_driver_fbdev_probe(struct drm_fb_helper *fbh,
 		(unsigned long long)obj->phys_addr);
 
 	return 0;
-
- err_fballoc:
-	dfb->fb.funcs->destroy(&dfb->fb);
-	return ret;
 }
diff --git a/drivers/gpu/drm/bridge/ite-it66121.c b/drivers/gpu/drm/bridge/ite-it66121.c
index aa7b1dcc5d70..0185f61e6e59 100644
--- a/drivers/gpu/drm/bridge/ite-it66121.c
+++ b/drivers/gpu/drm/bridge/ite-it66121.c
@@ -287,6 +287,7 @@
 enum chip_id {
 	ID_IT6610,
 	ID_IT66121,
+	ID_IT66122,
 };
 
 struct it66121_chip_info {
@@ -312,7 +313,7 @@ struct it66121_ctx {
 		u8 swl;
 		bool auto_cts;
 	} audio;
-	const struct it66121_chip_info *info;
+	enum chip_id id;
 };
 
 static const struct regmap_range_cfg it66121_regmap_banks[] = {
@@ -402,7 +403,7 @@ static int it66121_configure_afe(struct it66121_ctx *ctx,
 		if (ret)
 			return ret;
 
-		if (ctx->info->id == ID_IT66121) {
+		if (ctx->id == ID_IT66121 || ctx->id == ID_IT66122) {
 			ret = regmap_write_bits(ctx->regmap, IT66121_AFE_IP_REG,
 						IT66121_AFE_IP_EC1, 0);
 			if (ret)
@@ -428,7 +429,7 @@ static int it66121_configure_afe(struct it66121_ctx *ctx,
 		if (ret)
 			return ret;
 
-		if (ctx->info->id == ID_IT66121) {
+		if (ctx->id == ID_IT66121 || ctx->id == ID_IT66122) {
 			ret = regmap_write_bits(ctx->regmap, IT66121_AFE_IP_REG,
 						IT66121_AFE_IP_EC1,
 						IT66121_AFE_IP_EC1);
@@ -449,7 +450,7 @@ static int it66121_configure_afe(struct it66121_ctx *ctx,
 	if (ret)
 		return ret;
 
-	if (ctx->info->id == ID_IT6610) {
+	if (ctx->id == ID_IT6610) {
 		ret = regmap_write_bits(ctx->regmap, IT66121_AFE_XP_REG,
 					IT6610_AFE_XP_BYPASS,
 					IT6610_AFE_XP_BYPASS);
@@ -599,7 +600,7 @@ static int it66121_bridge_attach(struct drm_bridge *bridge,
 	if (ret)
 		return ret;
 
-	if (ctx->info->id == ID_IT66121) {
+	if (ctx->id == ID_IT66121 || ctx->id == ID_IT66122) {
 		ret = regmap_write_bits(ctx->regmap, IT66121_CLK_BANK_REG,
 					IT66121_CLK_BANK_PWROFF_RCLK, 0);
 		if (ret)
@@ -748,7 +749,7 @@ static int it66121_bridge_check(struct drm_bridge *bridge,
 {
 	struct it66121_ctx *ctx = container_of(bridge, struct it66121_ctx, bridge);
 
-	if (ctx->info->id == ID_IT6610) {
+	if (ctx->id == ID_IT6610) {
 		/* The IT6610 only supports these settings */
 		bridge_state->input_bus_cfg.flags |= DRM_BUS_FLAG_DE_HIGH |
 			DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE;
@@ -802,7 +803,7 @@ void it66121_bridge_mode_set(struct drm_bridge *bridge,
 	if (regmap_write(ctx->regmap, IT66121_HDMI_MODE_REG, IT66121_HDMI_MODE_HDMI))
 		goto unlock;
 
-	if (ctx->info->id == ID_IT66121 &&
+	if ((ctx->id == ID_IT66121 || ctx->id == ID_IT66122) &&
 	    regmap_write_bits(ctx->regmap, IT66121_CLK_BANK_REG,
 			      IT66121_CLK_BANK_PWROFF_TXCLK,
 			      IT66121_CLK_BANK_PWROFF_TXCLK)) {
@@ -815,7 +816,7 @@ void it66121_bridge_mode_set(struct drm_bridge *bridge,
 	if (it66121_configure_afe(ctx, adjusted_mode))
 		goto unlock;
 
-	if (ctx->info->id == ID_IT66121 &&
+	if ((ctx->id == ID_IT66121 || ctx->id == ID_IT66122) &&
 	    regmap_write_bits(ctx->regmap, IT66121_CLK_BANK_REG,
 			      IT66121_CLK_BANK_PWROFF_TXCLK, 0)) {
 		goto unlock;
@@ -1384,8 +1385,6 @@ static int it66121_audio_startup(struct device *dev, void *data)
 	int ret;
 	struct it66121_ctx *ctx = dev_get_drvdata(dev);
 
-	dev_dbg(dev, "%s\n", __func__);
-
 	mutex_lock(&ctx->lock);
 	ret = it661221_audio_output_enable(ctx, true);
 	if (ret)
@@ -1401,8 +1400,6 @@ static void it66121_audio_shutdown(struct device *dev, void *data)
 	int ret;
 	struct it66121_ctx *ctx = dev_get_drvdata(dev);
 
-	dev_dbg(dev, "%s\n", __func__);
-
 	mutex_lock(&ctx->lock);
 	ret = it661221_audio_output_enable(ctx, false);
 	if (ret)
@@ -1479,8 +1476,6 @@ static int it66121_audio_codec_init(struct it66121_ctx *ctx, struct device *dev)
 		.no_capture_mute = 1,
 	};
 
-	dev_dbg(dev, "%s\n", __func__);
-
 	if (!of_property_present(dev->of_node, "#sound-dai-cells")) {
 		dev_info(dev, "No \"#sound-dai-cells\", no audio\n");
 		return 0;
@@ -1504,13 +1499,20 @@ static const char * const it66121_supplies[] = {
 	"vcn33", "vcn18", "vrf12"
 };
 
+static const struct it66121_chip_info it66xx_chip_info[] = {
+	{.id = ID_IT6610, .vid = 0xca00, .pid = 0x0611 },
+	{.id = ID_IT66121, .vid = 0x4954, .pid = 0x0612 },
+	{.id = ID_IT66122, .vid = 0x4954, .pid = 0x0622 },
+};
+
 static int it66121_probe(struct i2c_client *client)
 {
 	u32 revision_id, vendor_ids[2] = { 0 }, device_ids[2] = { 0 };
 	struct device_node *ep;
-	int ret;
+	int ret, i;
 	struct it66121_ctx *ctx;
 	struct device *dev = &client->dev;
+	const struct it66121_chip_info *chip_info;
 
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
 		dev_err(dev, "I2C check functionality failed.\n");
@@ -1528,7 +1530,6 @@ static int it66121_probe(struct i2c_client *client)
 
 	ctx->dev = dev;
 	ctx->client = client;
-	ctx->info = i2c_get_match_data(client);
 
 	of_property_read_u32(ep, "bus-width", &ctx->bus_width);
 	of_node_put(ep);
@@ -1574,11 +1575,18 @@ static int it66121_probe(struct i2c_client *client)
 	revision_id = FIELD_GET(IT66121_REVISION_MASK, device_ids[1]);
 	device_ids[1] &= IT66121_DEVICE_ID1_MASK;
 
-	if ((vendor_ids[1] << 8 | vendor_ids[0]) != ctx->info->vid ||
-	    (device_ids[1] << 8 | device_ids[0]) != ctx->info->pid) {
-		return -ENODEV;
+	for (i = 0; i < ARRAY_SIZE(it66xx_chip_info); i++) {
+		chip_info = &it66xx_chip_info[i];
+		if ((vendor_ids[1] << 8 | vendor_ids[0]) == chip_info->vid &&
+		    (device_ids[1] << 8 | device_ids[0]) == chip_info->pid) {
+			ctx->id = chip_info->id;
+			break;
+		}
 	}
 
+	if (i == ARRAY_SIZE(it66xx_chip_info))
+		return -ENODEV;
+
 	ctx->bridge.of_node = dev->of_node;
 	ctx->bridge.type = DRM_MODE_CONNECTOR_HDMIA;
 	ctx->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID;
@@ -1612,28 +1620,18 @@ static void it66121_remove(struct i2c_client *client)
 	mutex_destroy(&ctx->lock);
 }
 
-static const struct it66121_chip_info it66121_chip_info = {
-	.id = ID_IT66121,
-	.vid = 0x4954,
-	.pid = 0x0612,
-};
-
-static const struct it66121_chip_info it6610_chip_info = {
-	.id = ID_IT6610,
-	.vid = 0xca00,
-	.pid = 0x0611,
-};
-
 static const struct of_device_id it66121_dt_match[] = {
-	{ .compatible = "ite,it66121", &it66121_chip_info },
-	{ .compatible = "ite,it6610", &it6610_chip_info },
+	{ .compatible = "ite,it6610" },
+	{ .compatible = "ite,it66121" },
+	{ .compatible = "ite,it66122" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, it66121_dt_match);
 
 static const struct i2c_device_id it66121_id[] = {
-	{ "it66121", (kernel_ulong_t) &it66121_chip_info },
-	{ "it6610", (kernel_ulong_t) &it6610_chip_info },
+	{ .name = "it6610" },
+	{ .name = "it66121" },
+	{ .name = "it66122" },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, it66121_id);
diff --git a/drivers/gpu/drm/bridge/simple-bridge.c b/drivers/gpu/drm/bridge/simple-bridge.c
index e4d0bc2200f8..2cd1847ba776 100644
--- a/drivers/gpu/drm/bridge/simple-bridge.c
+++ b/drivers/gpu/drm/bridge/simple-bridge.c
@@ -262,6 +262,16 @@ static const struct of_device_id simple_bridge_match[] = {
 			.connector_type = DRM_MODE_CONNECTOR_VGA,
 		},
 	}, {
+		.compatible = "asl-tek,cs5263",
+		.data = &(const struct simple_bridge_info) {
+			.connector_type = DRM_MODE_CONNECTOR_HDMIA,
+		},
+	}, {
+		.compatible = "parade,ps185hdm",
+		.data = &(const struct simple_bridge_info) {
+			.connector_type = DRM_MODE_CONNECTOR_HDMIA,
+		},
+	}, {
 		.compatible = "radxa,ra620",
 		.data = &(const struct simple_bridge_info) {
 			.connector_type = DRM_MODE_CONNECTOR_HDMIA,
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c
index 4ba7b339eff6..fe4c026280f0 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c
@@ -868,8 +868,9 @@ static void dw_hdmi_qp_bridge_atomic_enable(struct drm_bridge *bridge,
 		return;
 
 	if (connector->display_info.is_hdmi) {
-		dev_dbg(hdmi->dev, "%s mode=HDMI rate=%llu\n",
-			__func__, conn_state->hdmi.tmds_char_rate);
+		dev_dbg(hdmi->dev, "%s mode=HDMI %s rate=%llu bpc=%u\n", __func__,
+			drm_hdmi_connector_get_output_format_name(conn_state->hdmi.output_format),
+			conn_state->hdmi.tmds_char_rate, conn_state->hdmi.output_bpc);
 		op_mode = 0;
 		hdmi->tmds_char_rate = conn_state->hdmi.tmds_char_rate;
 	} else {
@@ -1287,6 +1288,12 @@ struct dw_hdmi_qp *dw_hdmi_qp_bind(struct platform_device *pdev,
 	hdmi->bridge.vendor = "Synopsys";
 	hdmi->bridge.product = "DW HDMI QP TX";
 
+	if (plat_data->supported_formats)
+		hdmi->bridge.supported_formats = plat_data->supported_formats;
+
+	if (plat_data->max_bpc)
+		hdmi->bridge.max_bpc = plat_data->max_bpc;
+
 	hdmi->bridge.ddc = dw_hdmi_qp_i2c_adapter(hdmi);
 	if (IS_ERR(hdmi->bridge.ddc))
 		return ERR_CAST(hdmi->bridge.ddc);
diff --git a/drivers/gpu/drm/clients/drm_fbdev_client.c b/drivers/gpu/drm/clients/drm_fbdev_client.c
index 47e5f27eee58..28951e392482 100644
--- a/drivers/gpu/drm/clients/drm_fbdev_client.c
+++ b/drivers/gpu/drm/clients/drm_fbdev_client.c
@@ -38,9 +38,11 @@ static void drm_fbdev_client_unregister(struct drm_client_dev *client)
 	}
 }
 
-static int drm_fbdev_client_restore(struct drm_client_dev *client)
+static int drm_fbdev_client_restore(struct drm_client_dev *client, bool force)
 {
-	drm_fb_helper_lastclose(client->dev);
+	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
+
+	drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, force);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/clients/drm_log.c b/drivers/gpu/drm/clients/drm_log.c
index 19e55aa0ed74..4d3005273b27 100644
--- a/drivers/gpu/drm/clients/drm_log.c
+++ b/drivers/gpu/drm/clients/drm_log.c
@@ -315,6 +315,18 @@ static void drm_log_client_unregister(struct drm_client_dev *client)
 	drm_client_release(client);
 }
 
+static int drm_log_client_restore(struct drm_client_dev *client, bool force)
+{
+	int ret;
+
+	if (force)
+		ret = drm_client_modeset_commit_locked(client);
+	else
+		ret = drm_client_modeset_commit(client);
+
+	return ret;
+}
+
 static int drm_log_client_hotplug(struct drm_client_dev *client)
 {
 	struct drm_log *dlog = client_to_drm_log(client);
@@ -348,6 +360,7 @@ static const struct drm_client_funcs drm_log_client_funcs = {
 	.owner		= THIS_MODULE,
 	.free		= drm_log_client_free,
 	.unregister	= drm_log_client_unregister,
+	.restore	= drm_log_client_restore,
 	.hotplug	= drm_log_client_hotplug,
 	.suspend	= drm_log_client_suspend,
 	.resume		= drm_log_client_resume,
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index e05820b18832..67e095e398a3 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -42,6 +42,7 @@
 #include <drm/drm_mode.h>
 #include <drm/drm_print.h>
 #include <drm/drm_writeback.h>
+#include <drm/drm_colorop.h>
 
 #include "drm_crtc_internal.h"
 #include "drm_internal.h"
@@ -107,6 +108,7 @@ void drm_atomic_state_default_release(struct drm_atomic_state *state)
 	kfree(state->connectors);
 	kfree(state->crtcs);
 	kfree(state->planes);
+	kfree(state->colorops);
 	kfree(state->private_objs);
 }
 EXPORT_SYMBOL(drm_atomic_state_default_release);
@@ -138,6 +140,10 @@ drm_atomic_state_init(struct drm_device *dev, struct drm_atomic_state *state)
 				sizeof(*state->planes), GFP_KERNEL);
 	if (!state->planes)
 		goto fail;
+	state->colorops = kcalloc(dev->mode_config.num_colorop,
+				  sizeof(*state->colorops), GFP_KERNEL);
+	if (!state->colorops)
+		goto fail;
 
 	/*
 	 * Because drm_atomic_state can be committed asynchronously we need our
@@ -251,6 +257,20 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state)
 		state->planes[i].new_state = NULL;
 	}
 
+	for (i = 0; i < config->num_colorop; i++) {
+		struct drm_colorop *colorop = state->colorops[i].ptr;
+
+		if (!colorop)
+			continue;
+
+		drm_colorop_atomic_destroy_state(colorop,
+						 state->colorops[i].state);
+		state->colorops[i].ptr = NULL;
+		state->colorops[i].state = NULL;
+		state->colorops[i].old_state = NULL;
+		state->colorops[i].new_state = NULL;
+	}
+
 	for (i = 0; i < state->num_private_objs; i++) {
 		struct drm_private_obj *obj = state->private_objs[i].ptr;
 
@@ -572,6 +592,55 @@ drm_atomic_get_plane_state(struct drm_atomic_state *state,
 }
 EXPORT_SYMBOL(drm_atomic_get_plane_state);
 
+/**
+ * drm_atomic_get_colorop_state - get colorop state
+ * @state: global atomic state object
+ * @colorop: colorop to get state object for
+ *
+ * This function returns the colorop state for the given colorop, allocating it
+ * if needed. It will also grab the relevant plane lock to make sure that the
+ * state is consistent.
+ *
+ * Returns:
+ *
+ * Either the allocated state or the error code encoded into the pointer. When
+ * the error is EDEADLK then the w/w mutex code has detected a deadlock and the
+ * entire atomic sequence must be restarted. All other errors are fatal.
+ */
+struct drm_colorop_state *
+drm_atomic_get_colorop_state(struct drm_atomic_state *state,
+			     struct drm_colorop *colorop)
+{
+	int ret, index = drm_colorop_index(colorop);
+	struct drm_colorop_state *colorop_state;
+
+	WARN_ON(!state->acquire_ctx);
+
+	colorop_state = drm_atomic_get_new_colorop_state(state, colorop);
+	if (colorop_state)
+		return colorop_state;
+
+	ret = drm_modeset_lock(&colorop->plane->mutex, state->acquire_ctx);
+	if (ret)
+		return ERR_PTR(ret);
+
+	colorop_state = drm_atomic_helper_colorop_duplicate_state(colorop);
+	if (!colorop_state)
+		return ERR_PTR(-ENOMEM);
+
+	state->colorops[index].state = colorop_state;
+	state->colorops[index].ptr = colorop;
+	state->colorops[index].old_state = colorop->state;
+	state->colorops[index].new_state = colorop_state;
+	colorop_state->state = state;
+
+	drm_dbg_atomic(colorop->dev, "Added [COLOROP:%d:%d] %p state to %p\n",
+		       colorop->base.id, colorop->type, colorop_state, state);
+
+	return colorop_state;
+}
+EXPORT_SYMBOL(drm_atomic_get_colorop_state);
+
 static bool
 plane_switching_crtc(const struct drm_plane_state *old_plane_state,
 		     const struct drm_plane_state *new_plane_state)
@@ -711,6 +780,46 @@ static int drm_atomic_plane_check(const struct drm_plane_state *old_plane_state,
 	return 0;
 }
 
+static void drm_atomic_colorop_print_state(struct drm_printer *p,
+					   const struct drm_colorop_state *state)
+{
+	struct drm_colorop *colorop = state->colorop;
+
+	drm_printf(p, "colorop[%u]:\n", colorop->base.id);
+	drm_printf(p, "\ttype=%s\n", drm_get_colorop_type_name(colorop->type));
+	if (colorop->bypass_property)
+		drm_printf(p, "\tbypass=%u\n", state->bypass);
+
+	switch (colorop->type) {
+	case DRM_COLOROP_1D_CURVE:
+		drm_printf(p, "\tcurve_1d_type=%s\n",
+			   drm_get_colorop_curve_1d_type_name(state->curve_1d_type));
+		break;
+	case DRM_COLOROP_1D_LUT:
+		drm_printf(p, "\tsize=%d\n", colorop->size);
+		drm_printf(p, "\tinterpolation=%s\n",
+			   drm_get_colorop_lut1d_interpolation_name(colorop->lut1d_interpolation));
+		drm_printf(p, "\tdata blob id=%d\n", state->data ? state->data->base.id : 0);
+		break;
+	case DRM_COLOROP_CTM_3X4:
+		drm_printf(p, "\tdata blob id=%d\n", state->data ? state->data->base.id : 0);
+		break;
+	case DRM_COLOROP_MULTIPLIER:
+		drm_printf(p, "\tmultiplier=%llu\n", state->multiplier);
+		break;
+	case DRM_COLOROP_3D_LUT:
+		drm_printf(p, "\tsize=%d\n", colorop->size);
+		drm_printf(p, "\tinterpolation=%s\n",
+			   drm_get_colorop_lut3d_interpolation_name(colorop->lut3d_interpolation));
+		drm_printf(p, "\tdata blob id=%d\n", state->data ? state->data->base.id : 0);
+		break;
+	default:
+		break;
+	}
+
+	drm_printf(p, "\tnext=%d\n", colorop->next ? colorop->next->base.id : 0);
+}
+
 static void drm_atomic_plane_print_state(struct drm_printer *p,
 		const struct drm_plane_state *state)
 {
@@ -732,7 +841,8 @@ static void drm_atomic_plane_print_state(struct drm_printer *p,
 	drm_printf(p, "\tcolor-range=%s\n",
 		   drm_get_color_range_name(state->color_range));
 	drm_printf(p, "\tcolor_mgmt_changed=%d\n", state->color_mgmt_changed);
-
+	drm_printf(p, "\tcolor-pipeline=%d\n",
+		   state->color_pipeline ? state->color_pipeline->base.id : 0);
 	if (plane->funcs->atomic_print_state)
 		plane->funcs->atomic_print_state(p, state);
 }
@@ -1446,6 +1556,52 @@ drm_atomic_add_affected_planes(struct drm_atomic_state *state,
 EXPORT_SYMBOL(drm_atomic_add_affected_planes);
 
 /**
+ * drm_atomic_add_affected_colorops - add colorops for plane
+ * @state: atomic state
+ * @plane: DRM plane
+ *
+ * This function walks the current configuration and adds all colorops
+ * currently used by @plane to the atomic configuration @state. This is useful
+ * when an atomic commit also needs to check all currently enabled colorop on
+ * @plane, e.g. when changing the mode. It's also useful when re-enabling a plane
+ * to avoid special code to force-enable all colorops.
+ *
+ * Since acquiring a colorop state will always also acquire the w/w mutex of the
+ * current plane for that colorop (if there is any) adding all the colorop states for
+ * a plane will not reduce parallelism of atomic updates.
+ *
+ * Returns:
+ * 0 on success or can fail with -EDEADLK or -ENOMEM. When the error is EDEADLK
+ * then the w/w mutex code has detected a deadlock and the entire atomic
+ * sequence must be restarted. All other errors are fatal.
+ */
+int
+drm_atomic_add_affected_colorops(struct drm_atomic_state *state,
+				 struct drm_plane *plane)
+{
+	struct drm_colorop *colorop;
+	struct drm_colorop_state *colorop_state;
+
+	WARN_ON(!drm_atomic_get_new_plane_state(state, plane));
+
+	drm_dbg_atomic(plane->dev,
+		       "Adding all current colorops for [PLANE:%d:%s] to %p\n",
+		       plane->base.id, plane->name, state);
+
+	drm_for_each_colorop(colorop, plane->dev) {
+		if (colorop->plane != plane)
+			continue;
+
+		colorop_state = drm_atomic_get_colorop_state(state, colorop);
+		if (IS_ERR(colorop_state))
+			return PTR_ERR(colorop_state);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_atomic_add_affected_colorops);
+
+/**
  * drm_atomic_check_only - check whether a given config would work
  * @state: atomic configuration to check
  *
@@ -1843,6 +1999,7 @@ static void __drm_state_dump(struct drm_device *dev, struct drm_printer *p,
 			     bool take_locks)
 {
 	struct drm_mode_config *config = &dev->mode_config;
+	struct drm_colorop *colorop;
 	struct drm_plane *plane;
 	struct drm_crtc *crtc;
 	struct drm_connector *connector;
@@ -1852,6 +2009,14 @@ static void __drm_state_dump(struct drm_device *dev, struct drm_printer *p,
 	if (!drm_drv_uses_atomic_modeset(dev))
 		return;
 
+	list_for_each_entry(colorop, &config->colorop_list, head) {
+		if (take_locks)
+			drm_modeset_lock(&colorop->plane->mutex, NULL);
+		drm_atomic_colorop_print_state(p, colorop->state);
+		if (take_locks)
+			drm_modeset_unlock(&colorop->plane->mutex);
+	}
+
 	list_for_each_entry(plane, &config->plane_list, head) {
 		if (take_locks)
 			drm_modeset_lock(&plane->mutex, NULL);
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index e641fcf8c568..10adac9397cf 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -3184,6 +3184,8 @@ int drm_atomic_helper_swap_state(struct drm_atomic_state *state,
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	struct drm_plane *plane;
 	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct drm_colorop *colorop;
+	struct drm_colorop_state *old_colorop_state, *new_colorop_state;
 	struct drm_crtc_commit *commit;
 	struct drm_private_obj *obj;
 	struct drm_private_state *old_obj_state, *new_obj_state;
@@ -3261,6 +3263,16 @@ int drm_atomic_helper_swap_state(struct drm_atomic_state *state,
 		}
 	}
 
+	for_each_oldnew_colorop_in_state(state, colorop, old_colorop_state, new_colorop_state, i) {
+		WARN_ON(colorop->state != old_colorop_state);
+
+		old_colorop_state->state = state;
+		new_colorop_state->state = NULL;
+
+		state->colorops[i].state = old_colorop_state;
+		colorop->state = new_colorop_state;
+	}
+
 	drm_panic_lock(state->dev, flags);
 	for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) {
 		WARN_ON(plane->state != old_plane_state);
diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c
index 7142e163e618..cee6d8fc44ad 100644
--- a/drivers/gpu/drm/drm_atomic_state_helper.c
+++ b/drivers/gpu/drm/drm_atomic_state_helper.c
@@ -268,6 +268,11 @@ void __drm_atomic_helper_plane_state_reset(struct drm_plane_state *plane_state,
 			plane_state->color_range = val;
 	}
 
+	if (plane->color_pipeline_property) {
+		/* default is always NULL, i.e., bypass */
+		plane_state->color_pipeline = NULL;
+	}
+
 	if (plane->zpos_property) {
 		if (!drm_object_property_get_default_value(&plane->base,
 							   plane->zpos_property,
diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
index b2cb5ae5a139..7320db4b8489 100644
--- a/drivers/gpu/drm/drm_atomic_uapi.c
+++ b/drivers/gpu/drm/drm_atomic_uapi.c
@@ -35,6 +35,7 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_writeback.h>
 #include <drm/drm_vblank.h>
+#include <drm/drm_colorop.h>
 
 #include <linux/export.h>
 #include <linux/dma-fence.h>
@@ -258,6 +259,34 @@ drm_atomic_set_fb_for_plane(struct drm_plane_state *plane_state,
 EXPORT_SYMBOL(drm_atomic_set_fb_for_plane);
 
 /**
+ * drm_atomic_set_colorop_for_plane - set colorop for plane
+ * @plane_state: atomic state object for the plane
+ * @colorop: colorop to use for the plane
+ *
+ * Helper function to select the color pipeline on a plane by setting
+ * it to the first drm_colorop element of the pipeline.
+ */
+void
+drm_atomic_set_colorop_for_plane(struct drm_plane_state *plane_state,
+				 struct drm_colorop *colorop)
+{
+	struct drm_plane *plane = plane_state->plane;
+
+	if (colorop)
+		drm_dbg_atomic(plane->dev,
+			       "Set [COLOROP:%d] for [PLANE:%d:%s] state %p\n",
+			       colorop->base.id, plane->base.id, plane->name,
+			       plane_state);
+	else
+		drm_dbg_atomic(plane->dev,
+			       "Set [NOCOLOROP] for [PLANE:%d:%s] state %p\n",
+			       plane->base.id, plane->name, plane_state);
+
+	plane_state->color_pipeline = colorop;
+}
+EXPORT_SYMBOL(drm_atomic_set_colorop_for_plane);
+
+/**
  * drm_atomic_set_crtc_for_connector - set CRTC for connector
  * @conn_state: atomic state object for the connector
  * @crtc: CRTC to use for the connector
@@ -544,6 +573,16 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane,
 		state->color_encoding = val;
 	} else if (property == plane->color_range_property) {
 		state->color_range = val;
+	} else if (property == plane->color_pipeline_property) {
+		/* find DRM colorop object */
+		struct drm_colorop *colorop = NULL;
+
+		colorop = drm_colorop_find(dev, file_priv, val);
+
+		if (val && !colorop)
+			return -EACCES;
+
+		drm_atomic_set_colorop_for_plane(state, colorop);
 	} else if (property == config->prop_fb_damage_clips) {
 		ret = drm_property_replace_blob_from_id(dev,
 					&state->fb_damage_clips,
@@ -626,6 +665,8 @@ drm_atomic_plane_get_property(struct drm_plane *plane,
 		*val = state->color_encoding;
 	} else if (property == plane->color_range_property) {
 		*val = state->color_range;
+	} else if (property == plane->color_pipeline_property) {
+		*val = (state->color_pipeline) ? state->color_pipeline->base.id : 0;
 	} else if (property == config->prop_fb_damage_clips) {
 		*val = (state->fb_damage_clips) ?
 			state->fb_damage_clips->base.id : 0;
@@ -648,6 +689,96 @@ drm_atomic_plane_get_property(struct drm_plane *plane,
 	return 0;
 }
 
+static int drm_atomic_color_set_data_property(struct drm_colorop *colorop,
+					      struct drm_colorop_state *state,
+					      struct drm_property *property,
+					      uint64_t val)
+{
+	ssize_t elem_size = -1;
+	ssize_t size = -1;
+	bool replaced = false;
+
+	switch (colorop->type) {
+	case DRM_COLOROP_1D_LUT:
+		size = colorop->size * sizeof(struct drm_color_lut32);
+		break;
+	case DRM_COLOROP_CTM_3X4:
+		size = sizeof(struct drm_color_ctm_3x4);
+		break;
+	case DRM_COLOROP_3D_LUT:
+		size = colorop->size * colorop->size * colorop->size *
+		       sizeof(struct drm_color_lut32);
+		break;
+	default:
+		/* should never get here */
+		return -EINVAL;
+	}
+
+	return drm_property_replace_blob_from_id(colorop->dev,
+						 &state->data,
+						 val,
+						 size,
+						 elem_size,
+						 &replaced);
+}
+
+static int drm_atomic_colorop_set_property(struct drm_colorop *colorop,
+					   struct drm_colorop_state *state,
+					   struct drm_file *file_priv,
+					   struct drm_property *property,
+					   uint64_t val)
+{
+	if (property == colorop->bypass_property) {
+		state->bypass = val;
+	} else if (property == colorop->lut1d_interpolation_property) {
+		colorop->lut1d_interpolation = val;
+	} else if (property == colorop->curve_1d_type_property) {
+		state->curve_1d_type = val;
+	} else if (property == colorop->multiplier_property) {
+		state->multiplier = val;
+	} else if (property == colorop->lut3d_interpolation_property) {
+		colorop->lut3d_interpolation = val;
+	} else if (property == colorop->data_property) {
+		return drm_atomic_color_set_data_property(colorop, state,
+							  property, val);
+	} else {
+		drm_dbg_atomic(colorop->dev,
+			       "[COLOROP:%d:%d] unknown property [PROP:%d:%s]\n",
+			       colorop->base.id, colorop->type,
+			       property->base.id, property->name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+drm_atomic_colorop_get_property(struct drm_colorop *colorop,
+				const struct drm_colorop_state *state,
+				struct drm_property *property, uint64_t *val)
+{
+	if (property == colorop->type_property)
+		*val = colorop->type;
+	else if (property == colorop->bypass_property)
+		*val = state->bypass;
+	else if (property == colorop->lut1d_interpolation_property)
+		*val = colorop->lut1d_interpolation;
+	else if (property == colorop->curve_1d_type_property)
+		*val = state->curve_1d_type;
+	else if (property == colorop->multiplier_property)
+		*val = state->multiplier;
+	else if (property == colorop->size_property)
+		*val = colorop->size;
+	else if (property == colorop->lut3d_interpolation_property)
+		*val = colorop->lut3d_interpolation;
+	else if (property == colorop->data_property)
+		*val = (state->data) ? state->data->base.id : 0;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
 static int drm_atomic_set_writeback_fb_for_connector(
 		struct drm_connector_state *conn_state,
 		struct drm_framebuffer *fb)
@@ -914,6 +1045,15 @@ int drm_atomic_get_property(struct drm_mode_object *obj,
 				plane->state, property, val);
 		break;
 	}
+	case DRM_MODE_OBJECT_COLOROP: {
+		struct drm_colorop *colorop = obj_to_colorop(obj);
+
+		if (colorop->plane)
+			WARN_ON(!drm_modeset_is_locked(&colorop->plane->mutex));
+
+		ret = drm_atomic_colorop_get_property(colorop, colorop->state, property, val);
+		break;
+	}
 	default:
 		drm_dbg_atomic(dev, "[OBJECT:%d] has no properties\n", obj->id);
 		ret = -EINVAL;
@@ -1111,6 +1251,21 @@ int drm_atomic_set_property(struct drm_atomic_state *state,
 		ret = drm_atomic_plane_set_property(plane,
 				plane_state, file_priv,
 				prop, prop_value);
+
+		break;
+	}
+	case DRM_MODE_OBJECT_COLOROP: {
+		struct drm_colorop *colorop = obj_to_colorop(obj);
+		struct drm_colorop_state *colorop_state;
+
+		colorop_state = drm_atomic_get_colorop_state(state, colorop);
+		if (IS_ERR(colorop_state)) {
+			ret = PTR_ERR(colorop_state);
+			break;
+		}
+
+		ret = drm_atomic_colorop_set_property(colorop, colorop_state,
+						      file_priv, prop, prop_value);
 		break;
 	}
 	default:
@@ -1450,6 +1605,7 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
 	drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE);
 	state->acquire_ctx = &ctx;
 	state->allow_modeset = !!(arg->flags & DRM_MODE_ATOMIC_ALLOW_MODESET);
+	state->plane_color_pipeline = file_priv->plane_color_pipeline;
 
 retry:
 	copied_objs = 0;
diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c
index 504ec5bdfa2c..a82d741e6630 100644
--- a/drivers/gpu/drm/drm_client.c
+++ b/drivers/gpu/drm/drm_client.c
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 
 #include <drm/drm_client.h>
+#include <drm/drm_client_event.h>
 #include <drm/drm_device.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
diff --git a/drivers/gpu/drm/drm_client_event.c b/drivers/gpu/drm/drm_client_event.c
index d25dc5250983..7b3e362f7926 100644
--- a/drivers/gpu/drm/drm_client_event.c
+++ b/drivers/gpu/drm/drm_client_event.c
@@ -102,7 +102,7 @@ void drm_client_dev_hotplug(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_client_dev_hotplug);
 
-void drm_client_dev_restore(struct drm_device *dev)
+void drm_client_dev_restore(struct drm_device *dev, bool force)
 {
 	struct drm_client_dev *client;
 	int ret;
@@ -115,7 +115,7 @@ void drm_client_dev_restore(struct drm_device *dev)
 		if (!client->funcs || !client->funcs->restore)
 			continue;
 
-		ret = client->funcs->restore(client);
+		ret = client->funcs->restore(client, force);
 		drm_dbg_kms(dev, "%s: ret=%d\n", client->name, ret);
 		if (!ret) /* The first one to return zero gets the privilege to restore */
 			break;
diff --git a/drivers/gpu/drm/drm_client_sysrq.c b/drivers/gpu/drm/drm_client_sysrq.c
new file mode 100644
index 000000000000..eea660096f1b
--- /dev/null
+++ b/drivers/gpu/drm/drm_client_sysrq.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0 or MIT
+
+#include <linux/sysrq.h>
+
+#include <drm/drm_client_event.h>
+#include <drm/drm_device.h>
+#include <drm/drm_print.h>
+
+#include "drm_internal.h"
+
+#ifdef CONFIG_MAGIC_SYSRQ
+static LIST_HEAD(drm_client_sysrq_dev_list);
+static DEFINE_MUTEX(drm_client_sysrq_dev_lock);
+
+/* emergency restore, don't bother with error reporting */
+static void drm_client_sysrq_restore_work_fn(struct work_struct *ignored)
+{
+	struct drm_device *dev;
+
+	guard(mutex)(&drm_client_sysrq_dev_lock);
+
+	list_for_each_entry(dev, &drm_client_sysrq_dev_list, client_sysrq_list) {
+		if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
+			continue;
+
+		drm_client_dev_restore(dev, true);
+	}
+}
+
+static DECLARE_WORK(drm_client_sysrq_restore_work, drm_client_sysrq_restore_work_fn);
+
+static void drm_client_sysrq_restore_handler(u8 ignored)
+{
+	schedule_work(&drm_client_sysrq_restore_work);
+}
+
+static const struct sysrq_key_op drm_client_sysrq_restore_op = {
+	.handler = drm_client_sysrq_restore_handler,
+	.help_msg = "force-fb(v)",
+	.action_msg = "Restore framebuffer console",
+};
+
+void drm_client_sysrq_register(struct drm_device *dev)
+{
+	guard(mutex)(&drm_client_sysrq_dev_lock);
+
+	if (list_empty(&drm_client_sysrq_dev_list))
+		register_sysrq_key('v', &drm_client_sysrq_restore_op);
+
+	list_add(&dev->client_sysrq_list, &drm_client_sysrq_dev_list);
+}
+
+void drm_client_sysrq_unregister(struct drm_device *dev)
+{
+	guard(mutex)(&drm_client_sysrq_dev_lock);
+
+	/* remove device from global restore list */
+	if (!drm_WARN_ON(dev, list_empty(&dev->client_sysrq_list)))
+		list_del(&dev->client_sysrq_list);
+
+	/* no devices left; unregister key */
+	if (list_empty(&drm_client_sysrq_dev_list))
+		unregister_sysrq_key('v', &drm_client_sysrq_restore_op);
+}
+#endif
diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c
index 131c1c9ae92f..c598b99673fc 100644
--- a/drivers/gpu/drm/drm_color_mgmt.c
+++ b/drivers/gpu/drm/drm_color_mgmt.c
@@ -874,3 +874,46 @@ void drm_crtc_fill_palette_8(struct drm_crtc *crtc, drm_crtc_set_lut_func set_pa
 		fill_palette_8(crtc, i, set_palette);
 }
 EXPORT_SYMBOL(drm_crtc_fill_palette_8);
+
+/**
+ * drm_color_lut32_check - check validity of extended lookup table
+ * @lut: property blob containing extended LUT to check
+ * @tests: bitmask of tests to run
+ *
+ * Helper to check whether a userspace-provided extended lookup table is valid and
+ * satisfies hardware requirements.  Drivers pass a bitmask indicating which of
+ * the tests in &drm_color_lut_tests should be performed.
+ *
+ * Returns 0 on success, -EINVAL on failure.
+ */
+int drm_color_lut32_check(const struct drm_property_blob *lut, u32 tests)
+{
+	const struct drm_color_lut32 *entry;
+	int i;
+
+	if (!lut || !tests)
+		return 0;
+
+	entry = lut->data;
+	for (i = 0; i < drm_color_lut32_size(lut); i++) {
+		if (tests & DRM_COLOR_LUT_EQUAL_CHANNELS) {
+			if (entry[i].red != entry[i].blue ||
+			    entry[i].red != entry[i].green) {
+				DRM_DEBUG_KMS("All LUT entries must have equal r/g/b\n");
+				return -EINVAL;
+			}
+		}
+
+		if (i > 0 && tests & DRM_COLOR_LUT_NON_DECREASING) {
+			if (entry[i].red < entry[i - 1].red ||
+			    entry[i].green < entry[i - 1].green ||
+			    entry[i].blue < entry[i - 1].blue) {
+				DRM_DEBUG_KMS("LUT entries must never decrease.\n");
+				return -EINVAL;
+			}
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_color_lut32_check);
diff --git a/drivers/gpu/drm/drm_colorop.c b/drivers/gpu/drm/drm_colorop.c
new file mode 100644
index 000000000000..44eb823585d2
--- /dev/null
+++ b/drivers/gpu/drm/drm_colorop.c
@@ -0,0 +1,599 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright (C) 2023 Advanced Micro Devices, Inc. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include <drm/drm_colorop.h>
+#include <drm/drm_print.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_plane.h>
+
+#include "drm_crtc_internal.h"
+
+/**
+ * DOC: overview
+ *
+ * When userspace signals the &DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE it
+ * should use the COLOR_PIPELINE plane property and associated colorops
+ * for any color operation on the &drm_plane. Setting of all old color
+ * properties, such as COLOR_ENCODING and COLOR_RANGE, will be rejected
+ * and the values of the properties will be ignored.
+ *
+ * Colorops are only advertised and valid for atomic drivers and atomic
+ * userspace that signals the &DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE
+ * client cap.
+ *
+ * A colorop represents a single color operation. Colorops are chained
+ * via the NEXT property and make up color pipelines. Color pipelines
+ * are advertised and selected via the COLOR_PIPELINE &drm_plane
+ * property.
+ *
+ * A colorop will be of a certain type, advertised by the read-only TYPE
+ * property. Each type of colorop will advertise a different set of
+ * properties and is programmed in a different manner. Types can be
+ * enumerated 1D curves, 1D LUTs, 3D LUTs, matrices, etc. See the
+ * &drm_colorop_type documentation for information on each type.
+ *
+ * If a colorop advertises the BYPASS property it can be bypassed.
+ *
+ * Information about colorop and color pipeline design decisions can be
+ * found at rfc/color_pipeline.rst, but note that this document will
+ * grow stale over time.
+ */
+
+static const struct drm_prop_enum_list drm_colorop_type_enum_list[] = {
+	{ DRM_COLOROP_1D_CURVE, "1D Curve" },
+	{ DRM_COLOROP_1D_LUT, "1D LUT" },
+	{ DRM_COLOROP_CTM_3X4, "3x4 Matrix"},
+	{ DRM_COLOROP_MULTIPLIER, "Multiplier"},
+	{ DRM_COLOROP_3D_LUT, "3D LUT"},
+};
+
+static const char * const colorop_curve_1d_type_names[] = {
+	[DRM_COLOROP_1D_CURVE_SRGB_EOTF] = "sRGB EOTF",
+	[DRM_COLOROP_1D_CURVE_SRGB_INV_EOTF] = "sRGB Inverse EOTF",
+	[DRM_COLOROP_1D_CURVE_PQ_125_EOTF] = "PQ 125 EOTF",
+	[DRM_COLOROP_1D_CURVE_PQ_125_INV_EOTF] = "PQ 125 Inverse EOTF",
+	[DRM_COLOROP_1D_CURVE_BT2020_INV_OETF] = "BT.2020 Inverse OETF",
+	[DRM_COLOROP_1D_CURVE_BT2020_OETF] = "BT.2020 OETF",
+	[DRM_COLOROP_1D_CURVE_GAMMA22] = "Gamma 2.2",
+	[DRM_COLOROP_1D_CURVE_GAMMA22_INV] = "Gamma 2.2 Inverse",
+};
+
+static const struct drm_prop_enum_list drm_colorop_lut1d_interpolation_list[] = {
+	{ DRM_COLOROP_LUT1D_INTERPOLATION_LINEAR, "Linear" },
+};
+
+
+static const struct drm_prop_enum_list drm_colorop_lut3d_interpolation_list[] = {
+	{ DRM_COLOROP_LUT3D_INTERPOLATION_TETRAHEDRAL, "Tetrahedral" },
+};
+
+/* Init Helpers */
+
+static int drm_plane_colorop_init(struct drm_device *dev, struct drm_colorop *colorop,
+				  struct drm_plane *plane, enum drm_colorop_type type,
+				  uint32_t flags)
+{
+	struct drm_mode_config *config = &dev->mode_config;
+	struct drm_property *prop;
+	int ret = 0;
+
+	ret = drm_mode_object_add(dev, &colorop->base, DRM_MODE_OBJECT_COLOROP);
+	if (ret)
+		return ret;
+
+	colorop->base.properties = &colorop->properties;
+	colorop->dev = dev;
+	colorop->type = type;
+	colorop->plane = plane;
+	colorop->next = NULL;
+
+	list_add_tail(&colorop->head, &config->colorop_list);
+	colorop->index = config->num_colorop++;
+
+	/* add properties */
+
+	/* type */
+	prop = drm_property_create_enum(dev,
+					DRM_MODE_PROP_IMMUTABLE,
+					"TYPE", drm_colorop_type_enum_list,
+					ARRAY_SIZE(drm_colorop_type_enum_list));
+
+	if (!prop)
+		return -ENOMEM;
+
+	colorop->type_property = prop;
+
+	drm_object_attach_property(&colorop->base,
+				   colorop->type_property,
+				   colorop->type);
+
+	if (flags & DRM_COLOROP_FLAG_ALLOW_BYPASS) {
+		/* bypass */
+		prop = drm_property_create_bool(dev, DRM_MODE_PROP_ATOMIC,
+						"BYPASS");
+		if (!prop)
+			return -ENOMEM;
+
+		colorop->bypass_property = prop;
+		drm_object_attach_property(&colorop->base,
+					colorop->bypass_property,
+					1);
+	}
+
+	/* next */
+	prop = drm_property_create_object(dev, DRM_MODE_PROP_IMMUTABLE | DRM_MODE_PROP_ATOMIC,
+					  "NEXT", DRM_MODE_OBJECT_COLOROP);
+	if (!prop)
+		return -ENOMEM;
+	colorop->next_property = prop;
+	drm_object_attach_property(&colorop->base,
+				   colorop->next_property,
+				   0);
+
+	return ret;
+}
+
+/**
+ * drm_colorop_cleanup - Cleanup a drm_colorop object in color_pipeline
+ *
+ * @colorop: The drm_colorop object to be cleaned
+ */
+void drm_colorop_cleanup(struct drm_colorop *colorop)
+{
+	struct drm_device *dev = colorop->dev;
+	struct drm_mode_config *config = &dev->mode_config;
+
+	list_del(&colorop->head);
+	config->num_colorop--;
+
+	if (colorop->state && colorop->state->data) {
+		drm_property_blob_put(colorop->state->data);
+		colorop->state->data = NULL;
+	}
+
+	kfree(colorop->state);
+}
+EXPORT_SYMBOL(drm_colorop_cleanup);
+
+/**
+ * drm_colorop_pipeline_destroy - Helper for color pipeline destruction
+ *
+ * @dev: - The drm_device containing the drm_planes with the color_pipelines
+ *
+ * Provides a default color pipeline destroy handler for drm_device.
+ */
+void drm_colorop_pipeline_destroy(struct drm_device *dev)
+{
+	struct drm_mode_config *config = &dev->mode_config;
+	struct drm_colorop *colorop, *next;
+
+	list_for_each_entry_safe(colorop, next, &config->colorop_list, head) {
+		drm_colorop_cleanup(colorop);
+		kfree(colorop);
+	}
+}
+EXPORT_SYMBOL(drm_colorop_pipeline_destroy);
+
+/**
+ * drm_plane_colorop_curve_1d_init - Initialize a DRM_COLOROP_1D_CURVE
+ *
+ * @dev: DRM device
+ * @colorop: The drm_colorop object to initialize
+ * @plane: The associated drm_plane
+ * @supported_tfs: A bitfield of supported drm_plane_colorop_curve_1d_init enum values,
+ *                 created using BIT(curve_type) and combined with the OR '|'
+ *                 operator.
+ * @flags: bitmask of misc, see DRM_COLOROP_FLAG_* defines.
+ * @return zero on success, -E value on failure
+ */
+int drm_plane_colorop_curve_1d_init(struct drm_device *dev, struct drm_colorop *colorop,
+				    struct drm_plane *plane, u64 supported_tfs, uint32_t flags)
+{
+	struct drm_prop_enum_list enum_list[DRM_COLOROP_1D_CURVE_COUNT];
+	int i, len;
+
+	struct drm_property *prop;
+	int ret;
+
+	if (!supported_tfs) {
+		drm_err(dev,
+			"No supported TFs for new 1D curve colorop on [PLANE:%d:%s]\n",
+			plane->base.id, plane->name);
+		return -EINVAL;
+	}
+
+	if ((supported_tfs & -BIT(DRM_COLOROP_1D_CURVE_COUNT)) != 0) {
+		drm_err(dev, "Unknown TF provided on [PLANE:%d:%s]\n",
+			plane->base.id, plane->name);
+		return -EINVAL;
+	}
+
+	ret = drm_plane_colorop_init(dev, colorop, plane, DRM_COLOROP_1D_CURVE, flags);
+	if (ret)
+		return ret;
+
+	len = 0;
+	for (i = 0; i < DRM_COLOROP_1D_CURVE_COUNT; i++) {
+		if ((supported_tfs & BIT(i)) == 0)
+			continue;
+
+		enum_list[len].type = i;
+		enum_list[len].name = colorop_curve_1d_type_names[i];
+		len++;
+	}
+
+	if (WARN_ON(len <= 0))
+		return -EINVAL;
+
+	/* initialize 1D curve only attribute */
+	prop = drm_property_create_enum(dev, DRM_MODE_PROP_ATOMIC, "CURVE_1D_TYPE",
+					enum_list, len);
+
+	if (!prop)
+		return -ENOMEM;
+
+	colorop->curve_1d_type_property = prop;
+	drm_object_attach_property(&colorop->base, colorop->curve_1d_type_property,
+				   enum_list[0].type);
+	drm_colorop_reset(colorop);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_plane_colorop_curve_1d_init);
+
+static int drm_colorop_create_data_prop(struct drm_device *dev, struct drm_colorop *colorop)
+{
+	struct drm_property *prop;
+
+	/* data */
+	prop = drm_property_create(dev, DRM_MODE_PROP_ATOMIC | DRM_MODE_PROP_BLOB,
+				   "DATA", 0);
+	if (!prop)
+		return -ENOMEM;
+
+	colorop->data_property = prop;
+	drm_object_attach_property(&colorop->base,
+				   colorop->data_property,
+				   0);
+
+	return 0;
+}
+
+/**
+ * drm_plane_colorop_curve_1d_lut_init - Initialize a DRM_COLOROP_1D_LUT
+ *
+ * @dev: DRM device
+ * @colorop: The drm_colorop object to initialize
+ * @plane: The associated drm_plane
+ * @lut_size: LUT size supported by driver
+ * @interpolation: 1D LUT interpolation type
+ * @flags: bitmask of misc, see DRM_COLOROP_FLAG_* defines.
+ * @return zero on success, -E value on failure
+ */
+int drm_plane_colorop_curve_1d_lut_init(struct drm_device *dev, struct drm_colorop *colorop,
+					struct drm_plane *plane, uint32_t lut_size,
+					enum drm_colorop_lut1d_interpolation_type interpolation,
+					uint32_t flags)
+{
+	struct drm_property *prop;
+	int ret;
+
+	ret = drm_plane_colorop_init(dev, colorop, plane, DRM_COLOROP_1D_LUT, flags);
+	if (ret)
+		return ret;
+
+	/* initialize 1D LUT only attribute */
+	/* LUT size */
+	prop = drm_property_create_range(dev, DRM_MODE_PROP_IMMUTABLE | DRM_MODE_PROP_ATOMIC,
+					 "SIZE", 0, UINT_MAX);
+	if (!prop)
+		return -ENOMEM;
+
+	colorop->size_property = prop;
+	drm_object_attach_property(&colorop->base, colorop->size_property, lut_size);
+	colorop->size = lut_size;
+
+	/* interpolation */
+	prop = drm_property_create_enum(dev, 0, "LUT1D_INTERPOLATION",
+					drm_colorop_lut1d_interpolation_list,
+					ARRAY_SIZE(drm_colorop_lut1d_interpolation_list));
+	if (!prop)
+		return -ENOMEM;
+
+	colorop->lut1d_interpolation_property = prop;
+	drm_object_attach_property(&colorop->base, prop, interpolation);
+	colorop->lut1d_interpolation = interpolation;
+
+	/* data */
+	ret = drm_colorop_create_data_prop(dev, colorop);
+	if (ret)
+		return ret;
+
+	drm_colorop_reset(colorop);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_plane_colorop_curve_1d_lut_init);
+
+int drm_plane_colorop_ctm_3x4_init(struct drm_device *dev, struct drm_colorop *colorop,
+				   struct drm_plane *plane, uint32_t flags)
+{
+	int ret;
+
+	ret = drm_plane_colorop_init(dev, colorop, plane, DRM_COLOROP_CTM_3X4, flags);
+	if (ret)
+		return ret;
+
+	ret = drm_colorop_create_data_prop(dev, colorop);
+	if (ret)
+		return ret;
+
+	drm_colorop_reset(colorop);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_plane_colorop_ctm_3x4_init);
+
+/**
+ * drm_plane_colorop_mult_init - Initialize a DRM_COLOROP_MULTIPLIER
+ *
+ * @dev: DRM device
+ * @colorop: The drm_colorop object to initialize
+ * @plane: The associated drm_plane
+ * @flags: bitmask of misc, see DRM_COLOROP_FLAG_* defines.
+ * @return zero on success, -E value on failure
+ */
+int drm_plane_colorop_mult_init(struct drm_device *dev, struct drm_colorop *colorop,
+				struct drm_plane *plane, uint32_t flags)
+{
+	struct drm_property *prop;
+	int ret;
+
+	ret = drm_plane_colorop_init(dev, colorop, plane, DRM_COLOROP_MULTIPLIER, flags);
+	if (ret)
+		return ret;
+
+	prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "MULTIPLIER", 0, U64_MAX);
+	if (!prop)
+		return -ENOMEM;
+
+	colorop->multiplier_property = prop;
+	drm_object_attach_property(&colorop->base, colorop->multiplier_property, 0);
+
+	drm_colorop_reset(colorop);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_plane_colorop_mult_init);
+
+int drm_plane_colorop_3dlut_init(struct drm_device *dev, struct drm_colorop *colorop,
+				 struct drm_plane *plane,
+				 uint32_t lut_size,
+				 enum drm_colorop_lut3d_interpolation_type interpolation,
+				 uint32_t flags)
+{
+	struct drm_property *prop;
+	int ret;
+
+	ret = drm_plane_colorop_init(dev, colorop, plane, DRM_COLOROP_3D_LUT, flags);
+	if (ret)
+		return ret;
+
+	/* LUT size */
+	prop = drm_property_create_range(dev, DRM_MODE_PROP_IMMUTABLE  | DRM_MODE_PROP_ATOMIC,
+					 "SIZE", 0, UINT_MAX);
+	if (!prop)
+		return -ENOMEM;
+
+	colorop->size_property = prop;
+	drm_object_attach_property(&colorop->base, colorop->size_property, lut_size);
+	colorop->size = lut_size;
+
+	/* interpolation */
+	prop = drm_property_create_enum(dev, 0, "LUT3D_INTERPOLATION",
+					drm_colorop_lut3d_interpolation_list,
+					ARRAY_SIZE(drm_colorop_lut3d_interpolation_list));
+	if (!prop)
+		return -ENOMEM;
+
+	colorop->lut3d_interpolation_property = prop;
+	drm_object_attach_property(&colorop->base, prop, interpolation);
+	colorop->lut3d_interpolation = interpolation;
+
+	/* data */
+	ret = drm_colorop_create_data_prop(dev, colorop);
+	if (ret)
+		return ret;
+
+	drm_colorop_reset(colorop);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_plane_colorop_3dlut_init);
+
+static void __drm_atomic_helper_colorop_duplicate_state(struct drm_colorop *colorop,
+							struct drm_colorop_state *state)
+{
+	memcpy(state, colorop->state, sizeof(*state));
+
+	if (state->data)
+		drm_property_blob_get(state->data);
+
+	state->bypass = true;
+}
+
+struct drm_colorop_state *
+drm_atomic_helper_colorop_duplicate_state(struct drm_colorop *colorop)
+{
+	struct drm_colorop_state *state;
+
+	if (WARN_ON(!colorop->state))
+		return NULL;
+
+	state = kmalloc(sizeof(*state), GFP_KERNEL);
+	if (state)
+		__drm_atomic_helper_colorop_duplicate_state(colorop, state);
+
+	return state;
+}
+
+void drm_colorop_atomic_destroy_state(struct drm_colorop *colorop,
+				      struct drm_colorop_state *state)
+{
+	kfree(state);
+}
+
+/**
+ * __drm_colorop_state_reset - resets colorop state to default values
+ * @colorop_state: atomic colorop state, must not be NULL
+ * @colorop: colorop object, must not be NULL
+ *
+ * Initializes the newly allocated @colorop_state with default
+ * values. This is useful for drivers that subclass the CRTC state.
+ */
+static void __drm_colorop_state_reset(struct drm_colorop_state *colorop_state,
+				      struct drm_colorop *colorop)
+{
+	u64 val;
+
+	colorop_state->colorop = colorop;
+	colorop_state->bypass = true;
+
+	if (colorop->curve_1d_type_property) {
+		drm_object_property_get_default_value(&colorop->base,
+						      colorop->curve_1d_type_property,
+						      &val);
+		colorop_state->curve_1d_type = val;
+	}
+}
+
+/**
+ * __drm_colorop_reset - reset state on colorop
+ * @colorop: drm colorop
+ * @colorop_state: colorop state to assign
+ *
+ * Initializes the newly allocated @colorop_state and assigns it to
+ * the &drm_crtc->state pointer of @colorop, usually required when
+ * initializing the drivers or when called from the &drm_colorop_funcs.reset
+ * hook.
+ *
+ * This is useful for drivers that subclass the colorop state.
+ */
+static void __drm_colorop_reset(struct drm_colorop *colorop,
+				struct drm_colorop_state *colorop_state)
+{
+	if (colorop_state)
+		__drm_colorop_state_reset(colorop_state, colorop);
+
+	colorop->state = colorop_state;
+}
+
+void drm_colorop_reset(struct drm_colorop *colorop)
+{
+	kfree(colorop->state);
+	colorop->state = kzalloc(sizeof(*colorop->state), GFP_KERNEL);
+
+	if (colorop->state)
+		__drm_colorop_reset(colorop, colorop->state);
+}
+
+static const char * const colorop_type_name[] = {
+	[DRM_COLOROP_1D_CURVE] = "1D Curve",
+	[DRM_COLOROP_1D_LUT] = "1D LUT",
+	[DRM_COLOROP_CTM_3X4] = "3x4 Matrix",
+	[DRM_COLOROP_MULTIPLIER] = "Multiplier",
+	[DRM_COLOROP_3D_LUT] = "3D LUT",
+};
+
+static const char * const colorop_lu3d_interpolation_name[] = {
+	[DRM_COLOROP_LUT3D_INTERPOLATION_TETRAHEDRAL] = "Tetrahedral",
+};
+
+static const char * const colorop_lut1d_interpolation_name[] = {
+	[DRM_COLOROP_LUT1D_INTERPOLATION_LINEAR] = "Linear",
+};
+
+const char *drm_get_colorop_type_name(enum drm_colorop_type type)
+{
+	if (WARN_ON(type >= ARRAY_SIZE(colorop_type_name)))
+		return "unknown";
+
+	return colorop_type_name[type];
+}
+
+const char *drm_get_colorop_curve_1d_type_name(enum drm_colorop_curve_1d_type type)
+{
+	if (WARN_ON(type >= ARRAY_SIZE(colorop_curve_1d_type_names)))
+		return "unknown";
+
+	return colorop_curve_1d_type_names[type];
+}
+
+/**
+ * drm_get_colorop_lut1d_interpolation_name: return a string for interpolation type
+ * @type: interpolation type to compute name of
+ *
+ * In contrast to the other drm_get_*_name functions this one here returns a
+ * const pointer and hence is threadsafe.
+ */
+const char *drm_get_colorop_lut1d_interpolation_name(enum drm_colorop_lut1d_interpolation_type type)
+{
+	if (WARN_ON(type >= ARRAY_SIZE(colorop_lut1d_interpolation_name)))
+		return "unknown";
+
+	return colorop_lut1d_interpolation_name[type];
+}
+
+/**
+ * drm_get_colorop_lut3d_interpolation_name - return a string for interpolation type
+ * @type: interpolation type to compute name of
+ *
+ * In contrast to the other drm_get_*_name functions this one here returns a
+ * const pointer and hence is threadsafe.
+ */
+const char *drm_get_colorop_lut3d_interpolation_name(enum drm_colorop_lut3d_interpolation_type type)
+{
+	if (WARN_ON(type >= ARRAY_SIZE(colorop_lu3d_interpolation_name)))
+		return "unknown";
+
+	return colorop_lu3d_interpolation_name[type];
+}
+
+/**
+ * drm_colorop_set_next_property - sets the next pointer
+ * @colorop: drm colorop
+ * @next: next colorop
+ *
+ * Should be used when constructing the color pipeline
+ */
+void drm_colorop_set_next_property(struct drm_colorop *colorop, struct drm_colorop *next)
+{
+	drm_object_property_set_value(&colorop->base,
+				      colorop->next_property,
+				      next ? next->base.id : 0);
+	colorop->next = next;
+}
+EXPORT_SYMBOL(drm_colorop_set_next_property);
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 272d6254ea47..4d6dc9ebfdb5 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -3439,6 +3439,7 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 	 * properties reflect the latest status.
 	 */
 	ret = drm_mode_object_get_properties(&connector->base, file_priv->atomic,
+			file_priv->plane_color_pipeline,
 			(uint32_t __user *)(unsigned long)(out_resp->props_ptr),
 			(uint64_t __user *)(unsigned long)(out_resp->prop_values_ptr),
 			&out_resp->count_props);
diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h
index 89706aa8232f..c09409229644 100644
--- a/drivers/gpu/drm/drm_crtc_internal.h
+++ b/drivers/gpu/drm/drm_crtc_internal.h
@@ -163,6 +163,7 @@ struct drm_mode_object *__drm_mode_object_find(struct drm_device *dev,
 void drm_mode_object_unregister(struct drm_device *dev,
 				struct drm_mode_object *object);
 int drm_mode_object_get_properties(struct drm_mode_object *obj, bool atomic,
+				   bool plane_color_pipeline,
 				   uint32_t __user *prop_ptr,
 				   uint64_t __user *prop_values,
 				   uint32_t *arg_count_props);
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 8e3cb08241c8..2915118436ce 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -733,6 +733,7 @@ static int drm_dev_init(struct drm_device *dev,
 	INIT_LIST_HEAD(&dev->filelist);
 	INIT_LIST_HEAD(&dev->filelist_internal);
 	INIT_LIST_HEAD(&dev->clientlist);
+	INIT_LIST_HEAD(&dev->client_sysrq_list);
 	INIT_LIST_HEAD(&dev->vblank_event_list);
 
 	spin_lock_init(&dev->event_lock);
@@ -1100,6 +1101,7 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags)
 			goto err_unload;
 	}
 	drm_panic_register(dev);
+	drm_client_sysrq_register(dev);
 
 	DRM_INFO("Initialized %s %d.%d.%d for %s on minor %d\n",
 		 driver->name, driver->major, driver->minor,
@@ -1144,6 +1146,7 @@ void drm_dev_unregister(struct drm_device *dev)
 {
 	dev->registered = false;
 
+	drm_client_sysrq_unregister(dev);
 	drm_panic_unregister(dev);
 
 	drm_client_dev_unregister(dev);
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 53e9dc0543de..be790fc68707 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -32,7 +32,6 @@
 #include <linux/console.h>
 #include <linux/export.h>
 #include <linux/pci.h>
-#include <linux/sysrq.h>
 #include <linux/vga_switcheroo.h>
 
 #include <drm/drm_atomic.h>
@@ -255,6 +254,7 @@ __drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper,
 /**
  * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration
  * @fb_helper: driver-allocated fbdev helper, can be NULL
+ * @force: ignore present DRM master
  *
  * This helper should be called from fbdev emulation's &drm_client_funcs.restore
  * callback. It ensures that the user isn't greeted with a black screen when the
@@ -263,48 +263,12 @@ __drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper,
  * Returns:
  * 0 on success, or a negative errno code otherwise.
  */
-int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper)
+int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper, bool force)
 {
-	return __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, false);
+	return __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, force);
 }
 EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked);
 
-#ifdef CONFIG_MAGIC_SYSRQ
-/* emergency restore, don't bother with error reporting */
-static void drm_fb_helper_restore_work_fn(struct work_struct *ignored)
-{
-	struct drm_fb_helper *helper;
-
-	mutex_lock(&kernel_fb_helper_lock);
-	list_for_each_entry(helper, &kernel_fb_helper_list, kernel_fb_list) {
-		struct drm_device *dev = helper->dev;
-
-		if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
-			continue;
-
-		mutex_lock(&helper->lock);
-		drm_client_modeset_commit_locked(&helper->client);
-		mutex_unlock(&helper->lock);
-	}
-	mutex_unlock(&kernel_fb_helper_lock);
-}
-
-static DECLARE_WORK(drm_fb_helper_restore_work, drm_fb_helper_restore_work_fn);
-
-static void drm_fb_helper_sysrq(u8 dummy1)
-{
-	schedule_work(&drm_fb_helper_restore_work);
-}
-
-static const struct sysrq_key_op sysrq_drm_fb_helper_restore_op = {
-	.handler = drm_fb_helper_sysrq,
-	.help_msg = "force-fb(v)",
-	.action_msg = "Restore framebuffer console",
-};
-#else
-static const struct sysrq_key_op sysrq_drm_fb_helper_restore_op = { };
-#endif
-
 static void drm_fb_helper_dpms(struct fb_info *info, int dpms_mode)
 {
 	struct drm_fb_helper *fb_helper = info->par;
@@ -495,20 +459,7 @@ int drm_fb_helper_init(struct drm_device *dev,
 }
 EXPORT_SYMBOL(drm_fb_helper_init);
 
-/**
- * drm_fb_helper_alloc_info - allocate fb_info and some of its members
- * @fb_helper: driver-allocated fbdev helper
- *
- * A helper to alloc fb_info and the member cmap. Called by the driver
- * within the struct &drm_driver.fbdev_probe callback function. Drivers do
- * not need to release the allocated fb_info structure themselves, this is
- * automatically done when calling drm_fb_helper_fini().
- *
- * RETURNS:
- * fb_info pointer if things went okay, pointer containing error code
- * otherwise
- */
-struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper)
+static struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper)
 {
 	struct device *dev = fb_helper->dev->dev;
 	struct fb_info *info;
@@ -535,17 +486,8 @@ err_release:
 	framebuffer_release(info);
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL(drm_fb_helper_alloc_info);
 
-/**
- * drm_fb_helper_release_info - release fb_info and its members
- * @fb_helper: driver-allocated fbdev helper
- *
- * A helper to release fb_info and the member cmap.  Drivers do not
- * need to release the allocated fb_info structure themselves, this is
- * automatically done when calling drm_fb_helper_fini().
- */
-void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper)
+static void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper)
 {
 	struct fb_info *info = fb_helper->info;
 
@@ -558,7 +500,6 @@ void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper)
 		fb_dealloc_cmap(&info->cmap);
 	framebuffer_release(info);
 }
-EXPORT_SYMBOL(drm_fb_helper_release_info);
 
 /**
  * drm_fb_helper_unregister_info - unregister fb_info framebuffer device
@@ -601,11 +542,8 @@ void drm_fb_helper_fini(struct drm_fb_helper *fb_helper)
 	drm_fb_helper_release_info(fb_helper);
 
 	mutex_lock(&kernel_fb_helper_lock);
-	if (!list_empty(&fb_helper->kernel_fb_list)) {
+	if (!list_empty(&fb_helper->kernel_fb_list))
 		list_del(&fb_helper->kernel_fb_list);
-		if (list_empty(&kernel_fb_helper_list))
-			unregister_sysrq_key('v', &sysrq_drm_fb_helper_restore_op);
-	}
 	mutex_unlock(&kernel_fb_helper_lock);
 
 	if (!fb_helper->client.funcs)
@@ -1328,9 +1266,9 @@ int drm_fb_helper_set_par(struct fb_info *info)
 	 * the KDSET IOCTL with KD_TEXT, and only after that drops the master
 	 * status when exiting.
 	 *
-	 * In the past this was caught by drm_fb_helper_lastclose(), but on
-	 * modern systems where logind always keeps a drm fd open to orchestrate
-	 * the vt switching, this doesn't work.
+	 * In the past this was caught by drm_fb_helper_restore_fbdev_mode_unlocked(),
+	 * but on modern systems where logind always keeps a drm fd open to
+	 * orchestrate the vt switching, this doesn't work.
 	 *
 	 * To not break the userspace ABI we have this special case here, which
 	 * is only used for the above case. Everything else uses the normal
@@ -1809,6 +1747,11 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper)
 	height = dev->mode_config.max_height;
 
 	drm_client_modeset_probe(&fb_helper->client, width, height);
+
+	info = drm_fb_helper_alloc_info(fb_helper);
+	if (IS_ERR(info))
+		return PTR_ERR(info);
+
 	ret = drm_fb_helper_single_fb_probe(fb_helper);
 	if (ret < 0) {
 		if (ret == -EAGAIN) {
@@ -1817,13 +1760,12 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper)
 		}
 		mutex_unlock(&fb_helper->lock);
 
-		return ret;
+		goto err_drm_fb_helper_release_info;
 	}
 	drm_setup_crtcs_fb(fb_helper);
 
 	fb_helper->deferred_setup = false;
 
-	info = fb_helper->info;
 	info->var.pixclock = 0;
 
 	/* Need to drop locks to avoid recursive deadlock in
@@ -1839,13 +1781,14 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper)
 		 info->node, info->fix.id);
 
 	mutex_lock(&kernel_fb_helper_lock);
-	if (list_empty(&kernel_fb_helper_list))
-		register_sysrq_key('v', &sysrq_drm_fb_helper_restore_op);
-
 	list_add(&fb_helper->kernel_fb_list, &kernel_fb_helper_list);
 	mutex_unlock(&kernel_fb_helper_lock);
 
 	return 0;
+
+err_drm_fb_helper_release_info:
+	drm_fb_helper_release_info(fb_helper);
+	return ret;
 }
 
 /**
@@ -1955,16 +1898,3 @@ int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper)
 	return 0;
 }
 EXPORT_SYMBOL(drm_fb_helper_hotplug_event);
-
-/**
- * drm_fb_helper_lastclose - DRM driver lastclose helper for fbdev emulation
- * @dev: DRM device
- *
- * This function is obsolete. Call drm_fb_helper_restore_fbdev_mode_unlocked()
- * instead.
- */
-void drm_fb_helper_lastclose(struct drm_device *dev)
-{
-	drm_fb_helper_restore_fbdev_mode_unlocked(dev->fb_helper);
-}
-EXPORT_SYMBOL(drm_fb_helper_lastclose);
diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c
index 12a8f5a5ada5..9412d9fdd74b 100644
--- a/drivers/gpu/drm/drm_fbdev_dma.c
+++ b/drivers/gpu/drm/drm_fbdev_dma.c
@@ -269,9 +269,9 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 {
 	struct drm_client_dev *client = &fb_helper->client;
 	struct drm_device *dev = fb_helper->dev;
+	struct fb_info *info = fb_helper->info;
 	struct drm_client_buffer *buffer;
 	struct drm_framebuffer *fb;
-	struct fb_info *info;
 	u32 format;
 	struct iosys_map map;
 	int ret;
@@ -301,12 +301,6 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 	fb_helper->buffer = buffer;
 	fb_helper->fb = fb;
 
-	info = drm_fb_helper_alloc_info(fb_helper);
-	if (IS_ERR(info)) {
-		ret = PTR_ERR(info);
-		goto err_drm_client_buffer_vunmap;
-	}
-
 	drm_fb_helper_fill_info(info, fb_helper, sizes);
 
 	if (fb->funcs->dirty)
@@ -314,12 +308,10 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 	else
 		ret = drm_fbdev_dma_driver_fbdev_probe_tail(fb_helper, sizes);
 	if (ret)
-		goto err_drm_fb_helper_release_info;
+		goto err_drm_client_buffer_vunmap;
 
 	return 0;
 
-err_drm_fb_helper_release_info:
-	drm_fb_helper_release_info(fb_helper);
 err_drm_client_buffer_vunmap:
 	fb_helper->fb = NULL;
 	fb_helper->buffer = NULL;
diff --git a/drivers/gpu/drm/drm_fbdev_shmem.c b/drivers/gpu/drm/drm_fbdev_shmem.c
index ac2b22e05cd6..458c899b5d4f 100644
--- a/drivers/gpu/drm/drm_fbdev_shmem.c
+++ b/drivers/gpu/drm/drm_fbdev_shmem.c
@@ -135,10 +135,10 @@ int drm_fbdev_shmem_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 {
 	struct drm_client_dev *client = &fb_helper->client;
 	struct drm_device *dev = fb_helper->dev;
+	struct fb_info *info = fb_helper->info;
 	struct drm_client_buffer *buffer;
 	struct drm_gem_shmem_object *shmem;
 	struct drm_framebuffer *fb;
-	struct fb_info *info;
 	u32 format;
 	struct iosys_map map;
 	int ret;
@@ -168,12 +168,6 @@ int drm_fbdev_shmem_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 	fb_helper->buffer = buffer;
 	fb_helper->fb = fb;
 
-	info = drm_fb_helper_alloc_info(fb_helper);
-	if (IS_ERR(info)) {
-		ret = PTR_ERR(info);
-		goto err_drm_client_buffer_vunmap;
-	}
-
 	drm_fb_helper_fill_info(info, fb_helper, sizes);
 
 	info->fbops = &drm_fbdev_shmem_fb_ops;
@@ -194,12 +188,10 @@ int drm_fbdev_shmem_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 	info->fbdefio = &fb_helper->fbdefio;
 	ret = fb_deferred_io_init(info);
 	if (ret)
-		goto err_drm_fb_helper_release_info;
+		goto err_drm_client_buffer_vunmap;
 
 	return 0;
 
-err_drm_fb_helper_release_info:
-	drm_fb_helper_release_info(fb_helper);
 err_drm_client_buffer_vunmap:
 	fb_helper->fb = NULL;
 	fb_helper->buffer = NULL;
diff --git a/drivers/gpu/drm/drm_fbdev_ttm.c b/drivers/gpu/drm/drm_fbdev_ttm.c
index c7ad779ba590..160bc35d8738 100644
--- a/drivers/gpu/drm/drm_fbdev_ttm.c
+++ b/drivers/gpu/drm/drm_fbdev_ttm.c
@@ -174,8 +174,8 @@ int drm_fbdev_ttm_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 {
 	struct drm_client_dev *client = &fb_helper->client;
 	struct drm_device *dev = fb_helper->dev;
+	struct fb_info *info = fb_helper->info;
 	struct drm_client_buffer *buffer;
-	struct fb_info *info;
 	size_t screen_size;
 	void *screen_buffer;
 	u32 format;
@@ -203,12 +203,6 @@ int drm_fbdev_ttm_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 		goto err_drm_client_buffer_delete;
 	}
 
-	info = drm_fb_helper_alloc_info(fb_helper);
-	if (IS_ERR(info)) {
-		ret = PTR_ERR(info);
-		goto err_vfree;
-	}
-
 	drm_fb_helper_fill_info(info, fb_helper, sizes);
 
 	info->fbops = &drm_fbdev_ttm_fb_ops;
@@ -225,12 +219,10 @@ int drm_fbdev_ttm_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 	info->fbdefio = &fb_helper->fbdefio;
 	ret = fb_deferred_io_init(info);
 	if (ret)
-		goto err_drm_fb_helper_release_info;
+		goto err_vfree;
 
 	return 0;
 
-err_drm_fb_helper_release_info:
-	drm_fb_helper_release_info(fb_helper);
 err_vfree:
 	vfree(screen_buffer);
 err_drm_client_buffer_delete:
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index eebd1a05ee97..be5e617ceb9f 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -405,7 +405,7 @@ EXPORT_SYMBOL(drm_open);
 
 static void drm_lastclose(struct drm_device *dev)
 {
-	drm_client_dev_restore(dev);
+	drm_client_dev_restore(dev, false);
 
 	if (dev_is_pci(dev->dev))
 		vga_switcheroo_process_delayed_switch();
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index a1a9c828938b..efc79bbf3c73 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -783,7 +783,6 @@ static int objects_lookup(struct drm_file *filp, u32 *handle, int count,
 int drm_gem_objects_lookup(struct drm_file *filp, void __user *bo_handles,
 			   int count, struct drm_gem_object ***objs_out)
 {
-	struct drm_device *dev = filp->minor->dev;
 	struct drm_gem_object **objs;
 	u32 *handles;
 	int ret;
@@ -798,20 +797,11 @@ int drm_gem_objects_lookup(struct drm_file *filp, void __user *bo_handles,
 
 	*objs_out = objs;
 
-	handles = kvmalloc_array(count, sizeof(u32), GFP_KERNEL);
-	if (!handles) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	if (copy_from_user(handles, bo_handles, count * sizeof(u32))) {
-		ret = -EFAULT;
-		drm_dbg_core(dev, "Failed to copy in GEM handles\n");
-		goto out;
-	}
+	handles = vmemdup_array_user(bo_handles, count, sizeof(u32));
+	if (IS_ERR(handles))
+		return PTR_ERR(handles);
 
 	ret = objects_lookup(filp, handles, count, objs);
-out:
 	kvfree(handles);
 	return ret;
 
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 5a3bed48ab1f..f893b1e3a596 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -56,6 +56,17 @@ static inline void drm_client_debugfs_init(struct drm_device *dev)
 { }
 #endif
 
+/* drm_client_sysrq.c */
+#if defined(CONFIG_DRM_CLIENT) && defined(CONFIG_MAGIC_SYSRQ)
+void drm_client_sysrq_register(struct drm_device *dev);
+void drm_client_sysrq_unregister(struct drm_device *dev);
+#else
+static inline void drm_client_sysrq_register(struct drm_device *dev)
+{ }
+static inline void drm_client_sysrq_unregister(struct drm_device *dev)
+{ }
+#endif
+
 /* drm_file.c */
 extern struct mutex drm_global_mutex;
 bool drm_dev_needs_global_mutex(struct drm_device *dev);
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index d8a24875a7ba..ff193155129e 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -373,6 +373,13 @@ drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 			return -EINVAL;
 		file_priv->supports_virtualized_cursor_plane = req->value;
 		break;
+	case DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE:
+		if (!file_priv->atomic)
+			return -EINVAL;
+		if (req->value > 1)
+			return -EINVAL;
+		file_priv->plane_color_pipeline = req->value;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/drm_mode_config.c b/drivers/gpu/drm/drm_mode_config.c
index 25f376869b3a..d12db9b0bab8 100644
--- a/drivers/gpu/drm/drm_mode_config.c
+++ b/drivers/gpu/drm/drm_mode_config.c
@@ -30,6 +30,7 @@
 #include <drm/drm_managed.h>
 #include <drm/drm_mode_config.h>
 #include <drm/drm_print.h>
+#include <drm/drm_colorop.h>
 #include <linux/dma-resv.h>
 
 #include "drm_crtc_internal.h"
@@ -192,11 +193,15 @@ int drm_mode_getresources(struct drm_device *dev, void *data,
 void drm_mode_config_reset(struct drm_device *dev)
 {
 	struct drm_crtc *crtc;
+	struct drm_colorop *colorop;
 	struct drm_plane *plane;
 	struct drm_encoder *encoder;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter conn_iter;
 
+	drm_for_each_colorop(colorop, dev)
+		drm_colorop_reset(colorop);
+
 	drm_for_each_plane(plane, dev)
 		if (plane->funcs->reset)
 			plane->funcs->reset(plane);
@@ -437,6 +442,7 @@ int drmm_mode_config_init(struct drm_device *dev)
 	INIT_LIST_HEAD(&dev->mode_config.property_list);
 	INIT_LIST_HEAD(&dev->mode_config.property_blob_list);
 	INIT_LIST_HEAD(&dev->mode_config.plane_list);
+	INIT_LIST_HEAD(&dev->mode_config.colorop_list);
 	INIT_LIST_HEAD(&dev->mode_config.privobj_list);
 	idr_init_base(&dev->mode_config.object_idr, 1);
 	idr_init_base(&dev->mode_config.tile_idr, 1);
@@ -458,6 +464,7 @@ int drmm_mode_config_init(struct drm_device *dev)
 	dev->mode_config.num_crtc = 0;
 	dev->mode_config.num_encoder = 0;
 	dev->mode_config.num_total_plane = 0;
+	dev->mode_config.num_colorop = 0;
 
 	if (IS_ENABLED(CONFIG_LOCKDEP)) {
 		struct drm_modeset_acquire_ctx modeset_ctx;
diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c
index e943205a2394..b45d501b10c8 100644
--- a/drivers/gpu/drm/drm_mode_object.c
+++ b/drivers/gpu/drm/drm_mode_object.c
@@ -28,6 +28,7 @@
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
 #include <drm/drm_mode_object.h>
+#include <drm/drm_plane.h>
 #include <drm/drm_print.h>
 
 #include "drm_crtc_internal.h"
@@ -386,6 +387,7 @@ EXPORT_SYMBOL(drm_object_property_get_default_value);
 
 /* helper for getconnector and getproperties ioctls */
 int drm_mode_object_get_properties(struct drm_mode_object *obj, bool atomic,
+				   bool plane_color_pipeline,
 				   uint32_t __user *prop_ptr,
 				   uint64_t __user *prop_values,
 				   uint32_t *arg_count_props)
@@ -399,6 +401,21 @@ int drm_mode_object_get_properties(struct drm_mode_object *obj, bool atomic,
 		if ((prop->flags & DRM_MODE_PROP_ATOMIC) && !atomic)
 			continue;
 
+		if (plane_color_pipeline && obj->type == DRM_MODE_OBJECT_PLANE) {
+			struct drm_plane *plane = obj_to_plane(obj);
+
+			if (prop == plane->color_encoding_property ||
+			    prop == plane->color_range_property)
+				continue;
+		}
+
+		if (!plane_color_pipeline && obj->type == DRM_MODE_OBJECT_PLANE) {
+			struct drm_plane *plane = obj_to_plane(obj);
+
+			if (prop == plane->color_pipeline_property)
+				continue;
+		}
+
 		if (*arg_count_props > count) {
 			ret = __drm_object_property_get_value(obj, prop, &val);
 			if (ret)
@@ -457,6 +474,7 @@ int drm_mode_obj_get_properties_ioctl(struct drm_device *dev, void *data,
 	}
 
 	ret = drm_mode_object_get_properties(obj, file_priv->atomic,
+			file_priv->plane_color_pipeline,
 			(uint32_t __user *)(unsigned long)(arg->props_ptr),
 			(uint64_t __user *)(unsigned long)(arg->prop_values_ptr),
 			&arg->count_props);
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index 38f82391bfda..f6cfa8ac090c 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -1820,3 +1820,62 @@ int drm_plane_add_size_hints_property(struct drm_plane *plane,
 	return 0;
 }
 EXPORT_SYMBOL(drm_plane_add_size_hints_property);
+
+/**
+ * drm_plane_create_color_pipeline_property - create a new color pipeline
+ * property
+ *
+ * @plane: drm plane
+ * @pipelines: list of pipelines
+ * @num_pipelines: number of pipelines
+ *
+ * Create the COLOR_PIPELINE plane property to specific color pipelines on
+ * the plane.
+ *
+ * RETURNS:
+ * Zero for success or -errno
+ */
+int drm_plane_create_color_pipeline_property(struct drm_plane *plane,
+					     const struct drm_prop_enum_list *pipelines,
+					     int num_pipelines)
+{
+	struct drm_prop_enum_list *all_pipelines;
+	struct drm_property *prop;
+	int len = 0;
+	int i;
+
+	all_pipelines = kcalloc(num_pipelines + 1,
+				sizeof(*all_pipelines),
+				GFP_KERNEL);
+
+	if (!all_pipelines) {
+		drm_err(plane->dev, "failed to allocate color pipeline\n");
+		return -ENOMEM;
+	}
+
+	/* Create default Bypass color pipeline */
+	all_pipelines[len].type = 0;
+	all_pipelines[len].name = "Bypass";
+	len++;
+
+	/* Add all other color pipelines */
+	for (i = 0; i < num_pipelines; i++, len++) {
+		all_pipelines[len].type = pipelines[i].type;
+		all_pipelines[len].name = pipelines[i].name;
+	}
+
+	prop = drm_property_create_enum(plane->dev, DRM_MODE_PROP_ATOMIC,
+					"COLOR_PIPELINE",
+					all_pipelines, len);
+	if (IS_ERR(prop)) {
+		kfree(all_pipelines);
+		return PTR_ERR(prop);
+	}
+
+	drm_object_attach_property(&plane->base, prop, 0);
+	plane->color_pipeline_property = prop;
+
+	kfree(all_pipelines);
+	return 0;
+}
+EXPORT_SYMBOL(drm_plane_create_color_pipeline_property);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index a9d35e8fca6a..637927818dfe 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -58,18 +58,11 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper,
 				   struct drm_fb_helper_surface_size *sizes,
 				   struct exynos_drm_gem *exynos_gem)
 {
-	struct fb_info *fbi;
+	struct fb_info *fbi = helper->info;
 	struct drm_framebuffer *fb = helper->fb;
 	unsigned int size = fb->width * fb->height * fb->format->cpp[0];
 	unsigned long offset;
 
-	fbi = drm_fb_helper_alloc_info(helper);
-	if (IS_ERR(fbi)) {
-		DRM_DEV_ERROR(to_dma_dev(helper->dev),
-			      "failed to allocate fb info.\n");
-		return PTR_ERR(fbi);
-	}
-
 	fbi->fbops = &exynos_drm_fb_ops;
 
 	drm_fb_helper_fill_info(fbi, helper, sizes);
diff --git a/drivers/gpu/drm/gma500/fbdev.c b/drivers/gpu/drm/gma500/fbdev.c
index bc92fa24a1e2..c26926babc2a 100644
--- a/drivers/gpu/drm/gma500/fbdev.c
+++ b/drivers/gpu/drm/gma500/fbdev.c
@@ -108,7 +108,7 @@ int psb_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 	struct drm_device *dev = fb_helper->dev;
 	struct drm_psb_private *dev_priv = to_drm_psb_private(dev);
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
-	struct fb_info *info;
+	struct fb_info *info = fb_helper->info;
 	struct drm_framebuffer *fb;
 	struct drm_mode_fb_cmd2 mode_cmd = { };
 	int size;
@@ -167,12 +167,6 @@ int psb_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 	fb_helper->funcs = &psb_fbdev_fb_helper_funcs;
 	fb_helper->fb = fb;
 
-	info = drm_fb_helper_alloc_info(fb_helper);
-	if (IS_ERR(info)) {
-		ret = PTR_ERR(info);
-		goto err_drm_framebuffer_unregister_private;
-	}
-
 	info->fbops = &psb_fbdev_fb_ops;
 
 	/* Accessed stolen memory directly */
@@ -196,10 +190,6 @@ int psb_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 
 	return 0;
 
-err_drm_framebuffer_unregister_private:
-	drm_framebuffer_unregister_private(fb);
-	drm_framebuffer_cleanup(fb);
-	kfree(fb);
 err_drm_gem_object_put:
 	drm_gem_object_put(obj);
 	return ret;
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index e5449c41cfa1..9cd03e2adeb2 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -267,8 +267,8 @@ int intel_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper,
 	struct intel_display *display = to_intel_display(helper->dev);
 	struct intel_fbdev *ifbdev = to_intel_fbdev(helper);
 	struct intel_framebuffer *fb = ifbdev->fb;
+	struct fb_info *info = helper->info;
 	struct ref_tracker *wakeref;
-	struct fb_info *info;
 	struct i915_vma *vma;
 	unsigned long flags = 0;
 	bool prealloc = false;
@@ -318,13 +318,6 @@ int intel_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper,
 		goto out_unlock;
 	}
 
-	info = drm_fb_helper_alloc_info(helper);
-	if (IS_ERR(info)) {
-		drm_err(display->drm, "Failed to allocate fb_info (%pe)\n", info);
-		ret = PTR_ERR(info);
-		goto out_unpin;
-	}
-
 	helper->funcs = &intel_fb_helper_funcs;
 	helper->fb = &fb->base;
 
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index aad6fb77f0de..fd19995b12b5 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -91,9 +91,9 @@ int msm_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper,
 {
 	struct drm_device *dev = helper->dev;
 	struct msm_drm_private *priv = dev->dev_private;
+	struct fb_info *fbi = helper->info;
 	struct drm_framebuffer *fb = NULL;
 	struct drm_gem_object *bo;
-	struct fb_info *fbi = NULL;
 	uint64_t paddr;
 	uint32_t format;
 	int ret, pitch;
@@ -126,13 +126,6 @@ int msm_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper,
 		goto fail;
 	}
 
-	fbi = drm_fb_helper_alloc_info(helper);
-	if (IS_ERR(fbi)) {
-		DRM_DEV_ERROR(dev->dev, "failed to allocate fb info\n");
-		ret = PTR_ERR(fbi);
-		goto fail;
-	}
-
 	DBG("fbi=%p, dev=%p", fbi, dev);
 
 	helper->funcs = &msm_fbdev_helper_funcs;
diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c
index d89761f13cd7..ca3fb186bf19 100644
--- a/drivers/gpu/drm/omapdrm/omap_fbdev.c
+++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c
@@ -154,9 +154,9 @@ int omap_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper,
 	struct drm_device *dev = helper->dev;
 	struct omap_drm_private *priv = dev->dev_private;
 	struct omap_fbdev *fbdev = priv->fbdev;
+	struct fb_info *fbi = helper->info;
 	struct drm_framebuffer *fb = NULL;
 	union omap_gem_size gsize;
-	struct fb_info *fbi = NULL;
 	struct drm_mode_fb_cmd2 mode_cmd = {0};
 	struct drm_gem_object *bo;
 	dma_addr_t dma_addr;
@@ -225,13 +225,6 @@ int omap_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper,
 		goto fail;
 	}
 
-	fbi = drm_fb_helper_alloc_info(helper);
-	if (IS_ERR(fbi)) {
-		dev_err(dev->dev, "failed to allocate fb info\n");
-		ret = PTR_ERR(fbi);
-		goto fail;
-	}
-
 	DBG("fbi=%p, dev=%p", fbi, dev);
 
 	helper->funcs = &omap_fbdev_helper_funcs;
diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index ad54537d914a..76f6af819037 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -408,6 +408,19 @@ config DRM_PANEL_LG_LB035Q02
 	  (found on the Gumstix Overo Palo35 board). To compile this driver as
 	  a module, choose M here.
 
+config DRM_PANEL_LG_LD070WX3
+	tristate "LG LD070WX3 MIPI DSI panel"
+	depends on OF
+	depends on DRM_MIPI_DSI
+	depends on BACKLIGHT_CLASS_DEVICE
+	select VIDEOMODE_HELPERS
+	help
+	  Say Y here if you want to enable support for the LD070WX3 MIPI DSI
+	  panel found in the NVIDIA Tegra Note 7 tablet.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called panel-lg-ld070wx3.
+
 config DRM_PANEL_LG_LG4573
 	tristate "LG4573 RGB/SPI panel"
 	depends on OF && SPI
@@ -881,16 +894,17 @@ config DRM_PANEL_SAMSUNG_S6E8AA5X01_AMS561RA01
 	  DSI protocol with 4 lanes.
 
 config DRM_PANEL_SAMSUNG_SOFEF00
-	tristate "Samsung sofef00/s6e3fc2x01 OnePlus 6/6T DSI cmd mode panels"
+	tristate "Samsung SOFEF00 DSI panel controller"
 	depends on OF
 	depends on DRM_MIPI_DSI
 	depends on BACKLIGHT_CLASS_DEVICE
 	select VIDEOMODE_HELPERS
 	help
 	  Say Y or M here if you want to enable support for the Samsung AMOLED
-	  command mode panels found in the OnePlus 6/6T smartphones.
+	  panel SOFEF00 DDIC and connected panel.
+	  Currently supported panels:
 
-	  The panels are 2280x1080@60Hz and 2340x1080@60Hz respectively
+	    Samsung AMS628NW01 (found in OnePlus 6, 1080x2280@60Hz)
 
 config DRM_PANEL_SEIKO_43WVF1G
 	tristate "Seiko 43WVF1G panel"
diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile
index 4c4b6b4aefd0..b9562a6fdcb3 100644
--- a/drivers/gpu/drm/panel/Makefile
+++ b/drivers/gpu/drm/panel/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_DRM_PANEL_LEADTEK_LTK050H3146W) += panel-leadtek-ltk050h3146w.o
 obj-$(CONFIG_DRM_PANEL_LEADTEK_LTK500HD1829) += panel-leadtek-ltk500hd1829.o
 obj-$(CONFIG_DRM_PANEL_LINCOLNTECH_LCD197) += panel-lincolntech-lcd197.o
 obj-$(CONFIG_DRM_PANEL_LG_LB035Q02) += panel-lg-lb035q02.o
+obj-$(CONFIG_DRM_PANEL_LG_LD070WX3) += panel-lg-ld070wx3.o
 obj-$(CONFIG_DRM_PANEL_LG_LG4573) += panel-lg-lg4573.o
 obj-$(CONFIG_DRM_PANEL_LG_SW43408) += panel-lg-sw43408.o
 obj-$(CONFIG_DRM_PANEL_MAGNACHIP_D53E6EA8966) += panel-magnachip-d53e6ea8966.o
diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c
index 944c7c70de55..415b894890ad 100644
--- a/drivers/gpu/drm/panel/panel-edp.c
+++ b/drivers/gpu/drm/panel/panel-edp.c
@@ -1965,6 +1965,7 @@ static const struct edp_panel_entry edp_panels[] = {
 	EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a3e, &delay_200_500_e80_d50, "NV116WHM-N49"),
 	EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a5d, &delay_200_500_e50, "NV116WHM-N45"),
 	EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a6a, &delay_200_500_e80, "NV140WUM-N44"),
+	EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a84, &delay_200_500_e50, "NV133WUM-T01"),
 	EDP_PANEL_ENTRY('B', 'O', 'E', 0x0ac5, &delay_200_500_e50, "NV116WHM-N4C"),
 	EDP_PANEL_ENTRY('B', 'O', 'E', 0x0ae8, &delay_200_500_e50_p2e80, "NV140WUM-N41"),
 	EDP_PANEL_ENTRY('B', 'O', 'E', 0x0b09, &delay_200_500_e50_po2e200, "NV140FHM-NZ"),
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
index 7ecb81225981..947b47841b01 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
@@ -820,6 +820,204 @@ static const struct ili9881c_instr tl050hdv35_init[] = {
 	ILI9881C_COMMAND_INSTR(0xd3, 0x39),
 };
 
+static const struct ili9881c_instr w552946aaa_init[] = {
+	ILI9881C_SWITCH_PAGE_INSTR(3),
+	ILI9881C_COMMAND_INSTR(0x01, 0x00),
+	ILI9881C_COMMAND_INSTR(0x02, 0x00),
+	ILI9881C_COMMAND_INSTR(0x03, 0x53),
+	ILI9881C_COMMAND_INSTR(0x04, 0x53),
+	ILI9881C_COMMAND_INSTR(0x05, 0x13),
+	ILI9881C_COMMAND_INSTR(0x06, 0x04),
+	ILI9881C_COMMAND_INSTR(0x07, 0x02),
+	ILI9881C_COMMAND_INSTR(0x08, 0x02),
+	ILI9881C_COMMAND_INSTR(0x09, 0x00),
+	ILI9881C_COMMAND_INSTR(0x0a, 0x00),
+	ILI9881C_COMMAND_INSTR(0x0b, 0x00),
+	ILI9881C_COMMAND_INSTR(0x0c, 0x00),
+	ILI9881C_COMMAND_INSTR(0x0d, 0x00),
+	ILI9881C_COMMAND_INSTR(0x0e, 0x00),
+	ILI9881C_COMMAND_INSTR(0x0f, 0x00),
+	ILI9881C_COMMAND_INSTR(0x10, 0x00),
+	ILI9881C_COMMAND_INSTR(0x11, 0x00),
+	ILI9881C_COMMAND_INSTR(0x12, 0x00),
+	ILI9881C_COMMAND_INSTR(0x13, 0x00),
+	ILI9881C_COMMAND_INSTR(0x14, 0x00),
+	ILI9881C_COMMAND_INSTR(0x15, 0x08),
+	ILI9881C_COMMAND_INSTR(0x16, 0x10),
+	ILI9881C_COMMAND_INSTR(0x17, 0x00),
+	ILI9881C_COMMAND_INSTR(0x18, 0x08),
+	ILI9881C_COMMAND_INSTR(0x19, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1a, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1b, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1c, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1d, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1e, 0xc0),
+	ILI9881C_COMMAND_INSTR(0x1f, 0x80),
+	ILI9881C_COMMAND_INSTR(0x20, 0x02),
+	ILI9881C_COMMAND_INSTR(0x21, 0x09),
+	ILI9881C_COMMAND_INSTR(0x22, 0x00),
+	ILI9881C_COMMAND_INSTR(0x23, 0x00),
+	ILI9881C_COMMAND_INSTR(0x24, 0x00),
+	ILI9881C_COMMAND_INSTR(0x25, 0x00),
+	ILI9881C_COMMAND_INSTR(0x26, 0x00),
+	ILI9881C_COMMAND_INSTR(0x27, 0x00),
+	ILI9881C_COMMAND_INSTR(0x28, 0x55),
+	ILI9881C_COMMAND_INSTR(0x29, 0x03),
+	ILI9881C_COMMAND_INSTR(0x2a, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2b, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2c, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2d, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2e, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2f, 0x00),
+	ILI9881C_COMMAND_INSTR(0x30, 0x00),
+	ILI9881C_COMMAND_INSTR(0x31, 0x00),
+	ILI9881C_COMMAND_INSTR(0x32, 0x00),
+	ILI9881C_COMMAND_INSTR(0x33, 0x00),
+	ILI9881C_COMMAND_INSTR(0x34, 0x04),
+	ILI9881C_COMMAND_INSTR(0x35, 0x05),
+	ILI9881C_COMMAND_INSTR(0x36, 0x05),
+	ILI9881C_COMMAND_INSTR(0x37, 0x00),
+	ILI9881C_COMMAND_INSTR(0x38, 0x3c),
+	ILI9881C_COMMAND_INSTR(0x39, 0x35),
+	ILI9881C_COMMAND_INSTR(0x3a, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3b, 0x40),
+	ILI9881C_COMMAND_INSTR(0x3c, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3d, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3e, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3f, 0x00),
+	ILI9881C_COMMAND_INSTR(0x40, 0x00),
+	ILI9881C_COMMAND_INSTR(0x41, 0x88),
+	ILI9881C_COMMAND_INSTR(0x42, 0x00),
+	ILI9881C_COMMAND_INSTR(0x43, 0x00),
+	ILI9881C_COMMAND_INSTR(0x44, 0x1f),
+	ILI9881C_COMMAND_INSTR(0x50, 0x01),
+	ILI9881C_COMMAND_INSTR(0x51, 0x23),
+	ILI9881C_COMMAND_INSTR(0x52, 0x45),
+	ILI9881C_COMMAND_INSTR(0x53, 0x67),
+	ILI9881C_COMMAND_INSTR(0x54, 0x89),
+	ILI9881C_COMMAND_INSTR(0x55, 0xab),
+	ILI9881C_COMMAND_INSTR(0x56, 0x01),
+	ILI9881C_COMMAND_INSTR(0x57, 0x23),
+	ILI9881C_COMMAND_INSTR(0x58, 0x45),
+	ILI9881C_COMMAND_INSTR(0x59, 0x67),
+	ILI9881C_COMMAND_INSTR(0x5a, 0x89),
+	ILI9881C_COMMAND_INSTR(0x5b, 0xab),
+	ILI9881C_COMMAND_INSTR(0x5c, 0xcd),
+	ILI9881C_COMMAND_INSTR(0x5d, 0xef),
+	ILI9881C_COMMAND_INSTR(0x5e, 0x03),
+	ILI9881C_COMMAND_INSTR(0x5f, 0x14),
+	ILI9881C_COMMAND_INSTR(0x60, 0x15),
+	ILI9881C_COMMAND_INSTR(0x61, 0x0c),
+	ILI9881C_COMMAND_INSTR(0x62, 0x0d),
+	ILI9881C_COMMAND_INSTR(0x63, 0x0e),
+	ILI9881C_COMMAND_INSTR(0x64, 0x0f),
+	ILI9881C_COMMAND_INSTR(0x65, 0x10),
+	ILI9881C_COMMAND_INSTR(0x66, 0x11),
+	ILI9881C_COMMAND_INSTR(0x67, 0x08),
+	ILI9881C_COMMAND_INSTR(0x68, 0x02),
+	ILI9881C_COMMAND_INSTR(0x69, 0x0a),
+	ILI9881C_COMMAND_INSTR(0x6a, 0x02),
+	ILI9881C_COMMAND_INSTR(0x6b, 0x02),
+	ILI9881C_COMMAND_INSTR(0x6c, 0x02),
+	ILI9881C_COMMAND_INSTR(0x6d, 0x02),
+	ILI9881C_COMMAND_INSTR(0x6e, 0x02),
+	ILI9881C_COMMAND_INSTR(0x6f, 0x02),
+	ILI9881C_COMMAND_INSTR(0x70, 0x02),
+	ILI9881C_COMMAND_INSTR(0x71, 0x02),
+	ILI9881C_COMMAND_INSTR(0x72, 0x06),
+	ILI9881C_COMMAND_INSTR(0x73, 0x02),
+	ILI9881C_COMMAND_INSTR(0x74, 0x02),
+	ILI9881C_COMMAND_INSTR(0x75, 0x14),
+	ILI9881C_COMMAND_INSTR(0x76, 0x15),
+	ILI9881C_COMMAND_INSTR(0x77, 0x0f),
+	ILI9881C_COMMAND_INSTR(0x78, 0x0e),
+	ILI9881C_COMMAND_INSTR(0x79, 0x0d),
+	ILI9881C_COMMAND_INSTR(0x7a, 0x0c),
+	ILI9881C_COMMAND_INSTR(0x7b, 0x11),
+	ILI9881C_COMMAND_INSTR(0x7c, 0x10),
+	ILI9881C_COMMAND_INSTR(0x7d, 0x06),
+	ILI9881C_COMMAND_INSTR(0x7e, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7f, 0x0a),
+	ILI9881C_COMMAND_INSTR(0x80, 0x02),
+	ILI9881C_COMMAND_INSTR(0x81, 0x02),
+	ILI9881C_COMMAND_INSTR(0x82, 0x02),
+	ILI9881C_COMMAND_INSTR(0x83, 0x02),
+	ILI9881C_COMMAND_INSTR(0x84, 0x02),
+	ILI9881C_COMMAND_INSTR(0x85, 0x02),
+	ILI9881C_COMMAND_INSTR(0x86, 0x02),
+	ILI9881C_COMMAND_INSTR(0x87, 0x02),
+	ILI9881C_COMMAND_INSTR(0x88, 0x08),
+	ILI9881C_COMMAND_INSTR(0x89, 0x02),
+	ILI9881C_COMMAND_INSTR(0x8a, 0x02),
+	ILI9881C_SWITCH_PAGE_INSTR(4),
+	ILI9881C_COMMAND_INSTR(0x00, 0x80),
+	ILI9881C_COMMAND_INSTR(0x70, 0x00),
+	ILI9881C_COMMAND_INSTR(0x71, 0x00),
+	ILI9881C_COMMAND_INSTR(0x66, 0xfe),
+	ILI9881C_COMMAND_INSTR(0x82, 0x15),
+	ILI9881C_COMMAND_INSTR(0x84, 0x15),
+	ILI9881C_COMMAND_INSTR(0x85, 0x15),
+	ILI9881C_COMMAND_INSTR(0x3a, 0x24),
+	ILI9881C_COMMAND_INSTR(0x32, 0xac),
+	ILI9881C_COMMAND_INSTR(0x8c, 0x80),
+	ILI9881C_COMMAND_INSTR(0x3c, 0xf5),
+	ILI9881C_COMMAND_INSTR(0x88, 0x33),
+	ILI9881C_SWITCH_PAGE_INSTR(1),
+	ILI9881C_COMMAND_INSTR(0x22, 0x0a),
+	ILI9881C_COMMAND_INSTR(0x31, 0x00),
+	ILI9881C_COMMAND_INSTR(0x53, 0x78),
+	ILI9881C_COMMAND_INSTR(0x55, 0x7b),
+	ILI9881C_COMMAND_INSTR(0x60, 0x20),
+	ILI9881C_COMMAND_INSTR(0x61, 0x00),
+	ILI9881C_COMMAND_INSTR(0x62, 0x0d),
+	ILI9881C_COMMAND_INSTR(0x63, 0x00),
+	ILI9881C_COMMAND_INSTR(0xa0, 0x00),
+	ILI9881C_COMMAND_INSTR(0xa1, 0x10),
+	ILI9881C_COMMAND_INSTR(0xa2, 0x1c),
+	ILI9881C_COMMAND_INSTR(0xa3, 0x13),
+	ILI9881C_COMMAND_INSTR(0xa4, 0x15),
+	ILI9881C_COMMAND_INSTR(0xa5, 0x26),
+	ILI9881C_COMMAND_INSTR(0xa6, 0x1a),
+	ILI9881C_COMMAND_INSTR(0xa7, 0x1d),
+	ILI9881C_COMMAND_INSTR(0xa8, 0x67),
+	ILI9881C_COMMAND_INSTR(0xa9, 0x1c),
+	ILI9881C_COMMAND_INSTR(0xaa, 0x29),
+	ILI9881C_COMMAND_INSTR(0xab, 0x5b),
+	ILI9881C_COMMAND_INSTR(0xac, 0x26),
+	ILI9881C_COMMAND_INSTR(0xad, 0x28),
+	ILI9881C_COMMAND_INSTR(0xae, 0x5c),
+	ILI9881C_COMMAND_INSTR(0xaf, 0x30),
+	ILI9881C_COMMAND_INSTR(0xb0, 0x31),
+	ILI9881C_COMMAND_INSTR(0xb1, 0x32),
+	ILI9881C_COMMAND_INSTR(0xb2, 0x00),
+	ILI9881C_COMMAND_INSTR(0xb1, 0x2e),
+	ILI9881C_COMMAND_INSTR(0xb2, 0x32),
+	ILI9881C_COMMAND_INSTR(0xb3, 0x00),
+	ILI9881C_COMMAND_INSTR(0xb6, 0x02),
+	ILI9881C_COMMAND_INSTR(0xb7, 0x03),
+	ILI9881C_COMMAND_INSTR(0xc0, 0x00),
+	ILI9881C_COMMAND_INSTR(0xc1, 0x10),
+	ILI9881C_COMMAND_INSTR(0xc2, 0x1c),
+	ILI9881C_COMMAND_INSTR(0xc3, 0x13),
+	ILI9881C_COMMAND_INSTR(0xc4, 0x15),
+	ILI9881C_COMMAND_INSTR(0xc5, 0x26),
+	ILI9881C_COMMAND_INSTR(0xc6, 0x1a),
+	ILI9881C_COMMAND_INSTR(0xc7, 0x1d),
+	ILI9881C_COMMAND_INSTR(0xc8, 0x67),
+	ILI9881C_COMMAND_INSTR(0xc9, 0x1c),
+	ILI9881C_COMMAND_INSTR(0xca, 0x29),
+	ILI9881C_COMMAND_INSTR(0xcb, 0x5b),
+	ILI9881C_COMMAND_INSTR(0xcc, 0x26),
+	ILI9881C_COMMAND_INSTR(0xcd, 0x28),
+	ILI9881C_COMMAND_INSTR(0xce, 0x5c),
+	ILI9881C_COMMAND_INSTR(0xcf, 0x30),
+	ILI9881C_COMMAND_INSTR(0xd0, 0x31),
+	ILI9881C_COMMAND_INSTR(0xd1, 0x2e),
+	ILI9881C_COMMAND_INSTR(0xd2, 0x32),
+	ILI9881C_COMMAND_INSTR(0xd3, 0x00),
+	ILI9881C_SWITCH_PAGE_INSTR(0),
+};
+
 static const struct ili9881c_instr w552946ab_init[] = {
 	ILI9881C_SWITCH_PAGE_INSTR(3),
 	ILI9881C_COMMAND_INSTR(0x01, 0x00),
@@ -1960,6 +2158,23 @@ static const struct drm_display_mode tl050hdv35_default_mode = {
 	.height_mm	= 110,
 };
 
+static const struct drm_display_mode w552946aaa_default_mode = {
+	.clock		= 65000,
+
+	.hdisplay	= 720,
+	.hsync_start	= 720 + 52,
+	.hsync_end	= 720 + 52 + 8,
+	.htotal		= 720 + 52 + 8 + 48,
+
+	.vdisplay	= 1280,
+	.vsync_start	= 1280 + 16,
+	.vsync_end	= 1280 + 16 + 6,
+	.vtotal		= 1280 + 16 + 6 + 15,
+
+	.width_mm	= 68,
+	.height_mm	= 121,
+};
+
 static const struct drm_display_mode w552946aba_default_mode = {
 	.clock		= 64000,
 
@@ -2188,6 +2403,15 @@ static const struct ili9881c_desc tl050hdv35_desc = {
 	.default_address_mode = 0x03,
 };
 
+static const struct ili9881c_desc w552946aaa_desc = {
+	.init = w552946aaa_init,
+	.init_length = ARRAY_SIZE(w552946aaa_init),
+	.mode = &w552946aaa_default_mode,
+	.mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
+		      MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_NO_EOT_PACKET,
+	.lanes = 2,
+};
+
 static const struct ili9881c_desc w552946aba_desc = {
 	.init = w552946ab_init,
 	.init_length = ARRAY_SIZE(w552946ab_init),
@@ -2236,6 +2460,7 @@ static const struct of_device_id ili9881c_of_match[] = {
 	{ .compatible = "feixin,k101-im2byl02", .data = &k101_im2byl02_desc },
 	{ .compatible = "startek,kd050hdfia020", .data = &kd050hdfia020_desc },
 	{ .compatible = "tdo,tl050hdv35", .data = &tl050hdv35_desc },
+	{ .compatible = "wanchanglong,w552946aaa", .data = &w552946aaa_desc },
 	{ .compatible = "wanchanglong,w552946aba", .data = &w552946aba_desc },
 	{ .compatible = "ampire,am8001280g", .data = &am8001280g_desc },
 	{ .compatible = "raspberrypi,dsi-5inch", &rpi_5inch_desc },
diff --git a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
index 5c2530598ddb..aa05316dc57b 100644
--- a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
+++ b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
@@ -1132,22 +1132,19 @@ static int jadard_dsi_probe(struct mipi_dsi_device *dsi)
 	dsi->lanes = desc->lanes;
 
 	jadard->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
-	if (IS_ERR(jadard->reset)) {
-		DRM_DEV_ERROR(&dsi->dev, "failed to get our reset GPIO\n");
-		return PTR_ERR(jadard->reset);
-	}
+	if (IS_ERR(jadard->reset))
+		return dev_err_probe(&dsi->dev, PTR_ERR(jadard->reset),
+				"failed to get our reset GPIO\n");
 
 	jadard->vdd = devm_regulator_get(dev, "vdd");
-	if (IS_ERR(jadard->vdd)) {
-		DRM_DEV_ERROR(&dsi->dev, "failed to get vdd regulator\n");
-		return PTR_ERR(jadard->vdd);
-	}
+	if (IS_ERR(jadard->vdd))
+		return dev_err_probe(&dsi->dev, PTR_ERR(jadard->vdd),
+				"failed to get vdd regulator\n");
 
 	jadard->vccio = devm_regulator_get(dev, "vccio");
-	if (IS_ERR(jadard->vccio)) {
-		DRM_DEV_ERROR(&dsi->dev, "failed to get vccio regulator\n");
-		return PTR_ERR(jadard->vccio);
-	}
+	if (IS_ERR(jadard->vccio))
+		return dev_err_probe(&dsi->dev, PTR_ERR(jadard->vccio),
+				"failed to get vccio regulator\n");
 
 	ret = of_drm_get_panel_orientation(dev->of_node, &jadard->orientation);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/panel/panel-lg-ld070wx3.c b/drivers/gpu/drm/panel/panel-lg-ld070wx3.c
new file mode 100644
index 000000000000..00cbfc5518a5
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-lg-ld070wx3.c
@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/array_size.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/property.h>
+#include <linux/regulator/consumer.h>
+
+#include <video/mipi_display.h>
+
+#include <drm/drm_mipi_dsi.h>
+#include <drm/drm_modes.h>
+#include <drm/drm_panel.h>
+#include <drm/drm_probe_helper.h>
+
+static const struct regulator_bulk_data lg_ld070wx3_supplies[] = {
+	{ .supply = "vdd" }, { .supply = "vcc" },
+};
+
+struct lg_ld070wx3 {
+	struct drm_panel panel;
+	struct mipi_dsi_device *dsi;
+
+	struct regulator_bulk_data *supplies;
+};
+
+static inline struct lg_ld070wx3 *to_lg_ld070wx3(struct drm_panel *panel)
+{
+	return container_of(panel, struct lg_ld070wx3, panel);
+}
+
+static int lg_ld070wx3_prepare(struct drm_panel *panel)
+{
+	struct lg_ld070wx3 *priv = to_lg_ld070wx3(panel);
+	struct mipi_dsi_multi_context ctx = { .dsi = priv->dsi };
+	struct device *dev = panel->dev;
+	int ret;
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(lg_ld070wx3_supplies), priv->supplies);
+	if (ret < 0) {
+		dev_err(dev, "failed to enable power supplies: %d\n", ret);
+		return ret;
+	}
+
+	/*
+	 * According to spec delay between enabling supply is 0,
+	 * for regulators to reach required voltage ~5ms needed.
+	 * MIPI interface signal for setup requires additional
+	 * 110ms which in total results in 115ms.
+	 */
+	mdelay(115);
+
+	mipi_dsi_dcs_soft_reset_multi(&ctx);
+	mipi_dsi_msleep(&ctx, 20);
+
+	/* Differential input impedance selection */
+	mipi_dsi_dcs_write_seq_multi(&ctx, 0xae, 0x0b);
+
+	/* Enter test mode 1 and 2*/
+	mipi_dsi_dcs_write_seq_multi(&ctx, 0xee, 0xea);
+	mipi_dsi_dcs_write_seq_multi(&ctx, 0xef, 0x5f);
+
+	/* Increased MIPI CLK driving ability */
+	mipi_dsi_dcs_write_seq_multi(&ctx, 0xf2, 0x68);
+
+	/* Exit test mode 1 and 2 */
+	mipi_dsi_dcs_write_seq_multi(&ctx, 0xee, 0x00);
+	mipi_dsi_dcs_write_seq_multi(&ctx, 0xef, 0x00);
+
+	return ctx.accum_err;
+}
+
+static int lg_ld070wx3_unprepare(struct drm_panel *panel)
+{
+	struct lg_ld070wx3 *priv = to_lg_ld070wx3(panel);
+	struct mipi_dsi_multi_context ctx = { .dsi = priv->dsi };
+
+	mipi_dsi_dcs_enter_sleep_mode_multi(&ctx);
+
+	msleep(50);
+
+	regulator_bulk_disable(ARRAY_SIZE(lg_ld070wx3_supplies), priv->supplies);
+
+	/* power supply must be off for at least 1s after panel disable */
+	msleep(1000);
+
+	return 0;
+}
+
+static const struct drm_display_mode lg_ld070wx3_mode = {
+	.clock = (800 + 32 + 48 + 8) * (1280 + 5 + 3 + 1) * 60 / 1000,
+	.hdisplay = 800,
+	.hsync_start = 800 + 32,
+	.hsync_end = 800 + 32 + 48,
+	.htotal = 800 + 32 + 48 + 8,
+	.vdisplay = 1280,
+	.vsync_start = 1280 + 5,
+	.vsync_end = 1280 + 5 + 3,
+	.vtotal = 1280 + 5 + 3 + 1,
+	.width_mm = 94,
+	.height_mm = 151,
+	.type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED,
+};
+
+static int lg_ld070wx3_get_modes(struct drm_panel *panel,
+				 struct drm_connector *connector)
+{
+	return drm_connector_helper_get_modes_fixed(connector, &lg_ld070wx3_mode);
+}
+
+static const struct drm_panel_funcs lg_ld070wx3_panel_funcs = {
+	.prepare = lg_ld070wx3_prepare,
+	.unprepare = lg_ld070wx3_unprepare,
+	.get_modes = lg_ld070wx3_get_modes,
+};
+
+static int lg_ld070wx3_probe(struct mipi_dsi_device *dsi)
+{
+	struct device *dev = &dsi->dev;
+	struct lg_ld070wx3 *priv;
+	int ret;
+
+	priv = devm_drm_panel_alloc(dev, struct lg_ld070wx3, panel,
+				    &lg_ld070wx3_panel_funcs,
+				    DRM_MODE_CONNECTOR_DSI);
+	if (IS_ERR(priv))
+		return PTR_ERR(priv);
+
+	ret = devm_regulator_bulk_get_const(dev, ARRAY_SIZE(lg_ld070wx3_supplies),
+					    lg_ld070wx3_supplies, &priv->supplies);
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "failed to get supplies\n");
+
+	priv->dsi = dsi;
+	mipi_dsi_set_drvdata(dsi, priv);
+
+	dsi->lanes = 4;
+	dsi->format = MIPI_DSI_FMT_RGB888;
+	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_LPM;
+
+	ret = drm_panel_of_backlight(&priv->panel);
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "failed to get backlight\n");
+
+	drm_panel_add(&priv->panel);
+
+	ret = devm_mipi_dsi_attach(dev, dsi);
+	if (ret < 0) {
+		drm_panel_remove(&priv->panel);
+		return dev_err_probe(dev, ret, "failed to attach to DSI host\n");
+	}
+
+	return 0;
+}
+
+static void lg_ld070wx3_remove(struct mipi_dsi_device *dsi)
+{
+	struct lg_ld070wx3 *priv = mipi_dsi_get_drvdata(dsi);
+
+	drm_panel_remove(&priv->panel);
+}
+
+static const struct of_device_id lg_ld070wx3_of_match[] = {
+	{ .compatible = "lg,ld070wx3-sl01" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, lg_ld070wx3_of_match);
+
+static struct mipi_dsi_driver lg_ld070wx3_driver = {
+	.driver = {
+		.name = "panel-lg-ld070wx3",
+		.of_match_table = lg_ld070wx3_of_match,
+	},
+	.probe = lg_ld070wx3_probe,
+	.remove = lg_ld070wx3_remove,
+};
+module_mipi_dsi_driver(lg_ld070wx3_driver);
+
+MODULE_AUTHOR("Svyatoslav Ryhel <clamor95@gmail.com>");
+MODULE_DESCRIPTION("LG LD070WX3-SL01 DSI panel driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panel/panel-ronbo-rb070d30.c b/drivers/gpu/drm/panel/panel-ronbo-rb070d30.c
index ad35d0fb0a16..c3fbc459c7e0 100644
--- a/drivers/gpu/drm/panel/panel-ronbo-rb070d30.c
+++ b/drivers/gpu/drm/panel/panel-ronbo-rb070d30.c
@@ -54,9 +54,9 @@ static int rb070d30_panel_prepare(struct drm_panel *panel)
 	}
 
 	msleep(20);
-	gpiod_set_value(ctx->gpios.power, 1);
+	gpiod_set_value_cansleep(ctx->gpios.power, 1);
 	msleep(20);
-	gpiod_set_value(ctx->gpios.reset, 1);
+	gpiod_set_value_cansleep(ctx->gpios.reset, 1);
 	msleep(20);
 	return 0;
 }
@@ -65,8 +65,8 @@ static int rb070d30_panel_unprepare(struct drm_panel *panel)
 {
 	struct rb070d30_panel *ctx = panel_to_rb070d30_panel(panel);
 
-	gpiod_set_value(ctx->gpios.reset, 0);
-	gpiod_set_value(ctx->gpios.power, 0);
+	gpiod_set_value_cansleep(ctx->gpios.reset, 0);
+	gpiod_set_value_cansleep(ctx->gpios.power, 0);
 	regulator_disable(ctx->supply);
 
 	return 0;
diff --git a/drivers/gpu/drm/panel/panel-samsung-sofef00.c b/drivers/gpu/drm/panel/panel-samsung-sofef00.c
index 064258217d50..e00a497a7c96 100644
--- a/drivers/gpu/drm/panel/panel-samsung-sofef00.c
+++ b/drivers/gpu/drm/panel/panel-samsung-sofef00.c
@@ -16,20 +16,32 @@
 #include <drm/drm_mipi_dsi.h>
 #include <drm/drm_modes.h>
 #include <drm/drm_panel.h>
+#include <drm/drm_probe_helper.h>
 
 struct sofef00_panel {
 	struct drm_panel panel;
 	struct mipi_dsi_device *dsi;
-	struct regulator *supply;
+	struct regulator_bulk_data *supplies;
 	struct gpio_desc *reset_gpio;
 };
 
+static const struct regulator_bulk_data sofef00_supplies[] = {
+	{ .supply = "vddio" },
+	{ .supply = "vci" },
+	{ .supply = "poc" },
+};
+
 static inline
 struct sofef00_panel *to_sofef00_panel(struct drm_panel *panel)
 {
 	return container_of(panel, struct sofef00_panel, panel);
 }
 
+#define sofef00_test_key_on_lvl2(ctx) \
+	mipi_dsi_dcs_write_seq_multi(ctx, 0xf0, 0x5a, 0x5a)
+#define sofef00_test_key_off_lvl2(ctx) \
+	mipi_dsi_dcs_write_seq_multi(ctx, 0xf0, 0xa5, 0xa5)
+
 static void sofef00_panel_reset(struct sofef00_panel *ctx)
 {
 	gpiod_set_value_cansleep(ctx->reset_gpio, 0);
@@ -50,18 +62,26 @@ static int sofef00_panel_on(struct sofef00_panel *ctx)
 	mipi_dsi_dcs_exit_sleep_mode_multi(&dsi_ctx);
 	mipi_dsi_usleep_range(&dsi_ctx, 10000, 11000);
 
-	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xf0, 0x5a, 0x5a);
-
+	sofef00_test_key_on_lvl2(&dsi_ctx);
 	mipi_dsi_dcs_set_tear_on_multi(&dsi_ctx, MIPI_DSI_DCS_TEAR_MODE_VBLANK);
+	sofef00_test_key_off_lvl2(&dsi_ctx);
 
-	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xf0, 0xa5, 0xa5);
-	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xf0, 0x5a, 0x5a);
+	sofef00_test_key_on_lvl2(&dsi_ctx);
 	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xb0, 0x07);
 	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xb6, 0x12);
-	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xf0, 0xa5, 0xa5);
+	sofef00_test_key_off_lvl2(&dsi_ctx);
+
 	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, MIPI_DCS_WRITE_CONTROL_DISPLAY, 0x20);
 	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, MIPI_DCS_WRITE_POWER_SAVE, 0x00);
 
+	return dsi_ctx.accum_err;
+}
+
+static int sofef00_enable(struct drm_panel *panel)
+{
+	struct sofef00_panel *ctx = to_sofef00_panel(panel);
+	struct mipi_dsi_multi_context dsi_ctx = { .dsi = ctx->dsi };
+
 	mipi_dsi_dcs_set_display_on_multi(&dsi_ctx);
 
 	return dsi_ctx.accum_err;
@@ -72,8 +92,6 @@ static int sofef00_panel_off(struct sofef00_panel *ctx)
 	struct mipi_dsi_device *dsi = ctx->dsi;
 	struct mipi_dsi_multi_context dsi_ctx = { .dsi = dsi };
 
-	dsi->mode_flags &= ~MIPI_DSI_MODE_LPM;
-
 	mipi_dsi_dcs_set_display_off_multi(&dsi_ctx);
 	mipi_dsi_msleep(&dsi_ctx, 40);
 
@@ -86,70 +104,70 @@ static int sofef00_panel_off(struct sofef00_panel *ctx)
 static int sofef00_panel_prepare(struct drm_panel *panel)
 {
 	struct sofef00_panel *ctx = to_sofef00_panel(panel);
-	struct device *dev = &ctx->dsi->dev;
 	int ret;
 
-	ret = regulator_enable(ctx->supply);
-	if (ret < 0) {
-		dev_err(dev, "Failed to enable regulator: %d\n", ret);
+	ret = regulator_bulk_enable(ARRAY_SIZE(sofef00_supplies), ctx->supplies);
+	if (ret < 0)
 		return ret;
-	}
 
 	sofef00_panel_reset(ctx);
 
 	ret = sofef00_panel_on(ctx);
 	if (ret < 0) {
 		gpiod_set_value_cansleep(ctx->reset_gpio, 1);
+		regulator_bulk_disable(ARRAY_SIZE(sofef00_supplies), ctx->supplies);
 		return ret;
 	}
 
 	return 0;
 }
 
-static int sofef00_panel_unprepare(struct drm_panel *panel)
+static int sofef00_disable(struct drm_panel *panel)
 {
 	struct sofef00_panel *ctx = to_sofef00_panel(panel);
 
 	sofef00_panel_off(ctx);
-	regulator_disable(ctx->supply);
 
 	return 0;
 }
 
-static const struct drm_display_mode enchilada_panel_mode = {
+static int sofef00_panel_unprepare(struct drm_panel *panel)
+{
+	struct sofef00_panel *ctx = to_sofef00_panel(panel);
+
+	regulator_bulk_disable(ARRAY_SIZE(sofef00_supplies), ctx->supplies);
+
+	return 0;
+}
+
+static const struct drm_display_mode ams628nw01_panel_mode = {
 	.clock = (1080 + 112 + 16 + 36) * (2280 + 36 + 8 + 12) * 60 / 1000,
+
 	.hdisplay = 1080,
 	.hsync_start = 1080 + 112,
 	.hsync_end = 1080 + 112 + 16,
 	.htotal = 1080 + 112 + 16 + 36,
+
 	.vdisplay = 2280,
 	.vsync_start = 2280 + 36,
 	.vsync_end = 2280 + 36 + 8,
 	.vtotal = 2280 + 36 + 8 + 12,
+
 	.width_mm = 68,
 	.height_mm = 145,
+
+	.type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED,
 };
 
 static int sofef00_panel_get_modes(struct drm_panel *panel, struct drm_connector *connector)
 {
-	struct drm_display_mode *mode;
-
-	mode = drm_mode_duplicate(connector->dev, &enchilada_panel_mode);
-	if (!mode)
-		return -ENOMEM;
-
-	drm_mode_set_name(mode);
-
-	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
-	connector->display_info.width_mm = mode->width_mm;
-	connector->display_info.height_mm = mode->height_mm;
-	drm_mode_probed_add(connector, mode);
-
-	return 1;
+	return drm_connector_helper_get_modes_fixed(connector, &ams628nw01_panel_mode);
 }
 
 static const struct drm_panel_funcs sofef00_panel_panel_funcs = {
 	.prepare = sofef00_panel_prepare,
+	.enable = sofef00_enable,
+	.disable = sofef00_disable,
 	.unprepare = sofef00_panel_unprepare,
 	.get_modes = sofef00_panel_get_modes,
 };
@@ -160,10 +178,14 @@ static int sofef00_panel_bl_update_status(struct backlight_device *bl)
 	int err;
 	u16 brightness = (u16)backlight_get_brightness(bl);
 
+	dsi->mode_flags &= ~MIPI_DSI_MODE_LPM;
+
 	err = mipi_dsi_dcs_set_display_brightness_large(dsi, brightness);
 	if (err < 0)
 		return err;
 
+	dsi->mode_flags |= MIPI_DSI_MODE_LPM;
+
 	return 0;
 }
 
@@ -177,7 +199,7 @@ sofef00_create_backlight(struct mipi_dsi_device *dsi)
 	struct device *dev = &dsi->dev;
 	const struct backlight_properties props = {
 		.type = BACKLIGHT_PLATFORM,
-		.brightness = 1023,
+		.brightness = 512,
 		.max_brightness = 1023,
 	};
 
@@ -197,10 +219,12 @@ static int sofef00_panel_probe(struct mipi_dsi_device *dsi)
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	ctx->supply = devm_regulator_get(dev, "vddio");
-	if (IS_ERR(ctx->supply))
-		return dev_err_probe(dev, PTR_ERR(ctx->supply),
-				     "Failed to get vddio regulator\n");
+	ret = devm_regulator_bulk_get_const(dev,
+					    ARRAY_SIZE(sofef00_supplies),
+					    sofef00_supplies,
+					    &ctx->supplies);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to get regulators\n");
 
 	ctx->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(ctx->reset_gpio))
@@ -212,6 +236,10 @@ static int sofef00_panel_probe(struct mipi_dsi_device *dsi)
 
 	dsi->lanes = 4;
 	dsi->format = MIPI_DSI_FMT_RGB888;
+	dsi->mode_flags = MIPI_DSI_MODE_VIDEO_BURST |
+			  MIPI_DSI_CLOCK_NON_CONTINUOUS | MIPI_DSI_MODE_LPM;
+
+	ctx->panel.prepare_prev_first = true;
 
 	ctx->panel.backlight = sofef00_create_backlight(dsi);
 	if (IS_ERR(ctx->panel.backlight))
@@ -243,7 +271,8 @@ static void sofef00_panel_remove(struct mipi_dsi_device *dsi)
 }
 
 static const struct of_device_id sofef00_panel_of_match[] = {
-	{ .compatible = "samsung,sofef00" },
+	{ .compatible = "samsung,sofef00" }, /* legacy */
+	{ .compatible = "samsung,sofef00-ams628nw01" },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sofef00_panel_of_match);
@@ -252,7 +281,7 @@ static struct mipi_dsi_driver sofef00_panel_driver = {
 	.probe = sofef00_panel_probe,
 	.remove = sofef00_panel_remove,
 	.driver = {
-		.name = "panel-oneplus6",
+		.name = "panel-samsung-sofef00",
 		.of_match_table = sofef00_panel_of_match,
 	},
 };
@@ -260,5 +289,5 @@ static struct mipi_dsi_driver sofef00_panel_driver = {
 module_mipi_dsi_driver(sofef00_panel_driver);
 
 MODULE_AUTHOR("Casey Connolly <casey.connolly@linaro.org>");
-MODULE_DESCRIPTION("DRM driver for Samsung AMOLED DSI panels found in OnePlus 6/6T phones");
+MODULE_DESCRIPTION("DRM driver for Samsung SOFEF00 DDIC");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index da6b71b70a46..b26b682826bc 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -4106,6 +4106,30 @@ static const struct panel_desc qishenglong_gopher2b_lcd = {
 	.connector_type = DRM_MODE_CONNECTOR_DPI,
 };
 
+static const struct display_timing raystar_rff500f_awh_dnn_timing = {
+	.pixelclock = { 23000000, 25000000, 27000000 },
+	.hactive = { 800, 800, 800 },
+	.hback_porch = { 4, 8, 48 },
+	.hfront_porch = { 4, 8, 48 },
+	.hsync_len = { 2, 4, 8 },
+	.vactive = { 480, 480, 480 },
+	.vback_porch = { 4, 8, 12 },
+	.vfront_porch = { 4, 8, 12 },
+	.vsync_len = { 2, 4, 8 },
+};
+
+static const struct panel_desc raystar_rff500f_awh_dnn = {
+	.timings = &raystar_rff500f_awh_dnn_timing,
+	.num_timings = 1,
+	.bpc = 8,
+	.size = {
+		.width = 108,
+		.height = 65,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
+	.connector_type = DRM_MODE_CONNECTOR_LVDS,
+};
+
 static const struct display_timing rocktech_rk043fn48h_timing = {
 	.pixelclock = { 6000000, 9000000, 12000000 },
 	.hactive = { 480, 480, 480 },
@@ -4223,6 +4247,37 @@ static const struct panel_desc samsung_ltl101al01 = {
 	.connector_type = DRM_MODE_CONNECTOR_LVDS,
 };
 
+static const struct display_timing samsung_ltl106al01_timing = {
+	.pixelclock = { 71980000, 71980000, 71980000 },
+	.hactive = { 1366, 1366, 1366 },
+	.hfront_porch = { 56, 56, 56 },
+	.hback_porch = { 106, 106, 106 },
+	.hsync_len = { 14, 14, 14 },
+	.vactive = { 768, 768, 768 },
+	.vfront_porch = { 3, 3, 3 },
+	.vback_porch = { 6, 6, 6 },
+	.vsync_len = { 1, 1, 1 },
+	.flags = DISPLAY_FLAGS_HSYNC_LOW | DISPLAY_FLAGS_VSYNC_LOW,
+};
+
+static const struct panel_desc samsung_ltl106al01 = {
+	.timings = &samsung_ltl106al01_timing,
+	.num_timings = 1,
+	.bpc = 8,
+	.size = {
+		.width = 235,
+		.height = 132,
+	},
+	.delay = {
+		.prepare = 5,
+		.enable = 10,
+		.disable = 10,
+		.unprepare = 5,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
+	.connector_type = DRM_MODE_CONNECTOR_LVDS,
+};
+
 static const struct drm_display_mode samsung_ltn101nt05_mode = {
 	.clock = 54030,
 	.hdisplay = 1024,
@@ -5379,6 +5434,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "qishenglong,gopher2b-lcd",
 		.data = &qishenglong_gopher2b_lcd,
 	}, {
+		.compatible = "raystar,rff500f-awh-dnn",
+		.data = &raystar_rff500f_awh_dnn,
+	}, {
 		.compatible = "rocktech,rk043fn48h",
 		.data = &rocktech_rk043fn48h,
 	}, {
@@ -5391,6 +5449,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "samsung,ltl101al01",
 		.data = &samsung_ltl101al01,
 	}, {
+		.compatible = "samsung,ltl106al01",
+		.data = &samsung_ltl106al01,
+	}, {
 		.compatible = "samsung,ltn101nt05",
 		.data = &samsung_ltn101nt05,
 	}, {
@@ -5600,34 +5661,6 @@ static const struct panel_desc_dsi boe_tv080wum_nl0 = {
 	.lanes = 4,
 };
 
-static const struct drm_display_mode lg_ld070wx3_sl01_mode = {
-	.clock = 71000,
-	.hdisplay = 800,
-	.hsync_start = 800 + 32,
-	.hsync_end = 800 + 32 + 1,
-	.htotal = 800 + 32 + 1 + 57,
-	.vdisplay = 1280,
-	.vsync_start = 1280 + 28,
-	.vsync_end = 1280 + 28 + 1,
-	.vtotal = 1280 + 28 + 1 + 14,
-};
-
-static const struct panel_desc_dsi lg_ld070wx3_sl01 = {
-	.desc = {
-		.modes = &lg_ld070wx3_sl01_mode,
-		.num_modes = 1,
-		.bpc = 8,
-		.size = {
-			.width = 94,
-			.height = 151,
-		},
-		.connector_type = DRM_MODE_CONNECTOR_DSI,
-	},
-	.flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_CLOCK_NON_CONTINUOUS,
-	.format = MIPI_DSI_FMT_RGB888,
-	.lanes = 4,
-};
-
 static const struct drm_display_mode lg_lh500wx1_sd03_mode = {
 	.clock = 67000,
 	.hdisplay = 720,
@@ -5752,9 +5785,6 @@ static const struct of_device_id dsi_of_match[] = {
 		.compatible = "boe,tv080wum-nl0",
 		.data = &boe_tv080wum_nl0
 	}, {
-		.compatible = "lg,ld070wx3-sl01",
-		.data = &lg_ld070wx3_sl01
-	}, {
 		.compatible = "lg,lh500wx1-sd03",
 		.data = &lg_lh500wx1_sd03
 	}, {
diff --git a/drivers/gpu/drm/panthor/Makefile b/drivers/gpu/drm/panthor/Makefile
index 02db21748c12..753a32c446df 100644
--- a/drivers/gpu/drm/panthor/Makefile
+++ b/drivers/gpu/drm/panthor/Makefile
@@ -10,6 +10,7 @@ panthor-y := \
 	panthor_heap.o \
 	panthor_hw.o \
 	panthor_mmu.o \
+	panthor_pwr.o \
 	panthor_sched.o
 
 obj-$(CONFIG_DRM_PANTHOR) += panthor.o
diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c
index 31fb8ed68199..e133b1e0ad6d 100644
--- a/drivers/gpu/drm/panthor/panthor_device.c
+++ b/drivers/gpu/drm/panthor/panthor_device.c
@@ -21,6 +21,7 @@
 #include "panthor_gpu.h"
 #include "panthor_hw.h"
 #include "panthor_mmu.h"
+#include "panthor_pwr.h"
 #include "panthor_regs.h"
 #include "panthor_sched.h"
 
@@ -113,6 +114,7 @@ void panthor_device_unplug(struct panthor_device *ptdev)
 	panthor_fw_unplug(ptdev);
 	panthor_mmu_unplug(ptdev);
 	panthor_gpu_unplug(ptdev);
+	panthor_pwr_unplug(ptdev);
 
 	pm_runtime_dont_use_autosuspend(ptdev->base.dev);
 	pm_runtime_put_sync_suspend(ptdev->base.dev);
@@ -152,8 +154,8 @@ static void panthor_device_reset_work(struct work_struct *work)
 	panthor_sched_pre_reset(ptdev);
 	panthor_fw_pre_reset(ptdev, true);
 	panthor_mmu_pre_reset(ptdev);
-	panthor_gpu_soft_reset(ptdev);
-	panthor_gpu_l2_power_on(ptdev);
+	panthor_hw_soft_reset(ptdev);
+	panthor_hw_l2_power_on(ptdev);
 	panthor_mmu_post_reset(ptdev);
 	ret = panthor_fw_post_reset(ptdev);
 	atomic_set(&ptdev->reset.pending, 0);
@@ -268,10 +270,14 @@ int panthor_device_init(struct panthor_device *ptdev)
 	if (ret)
 		goto err_rpm_put;
 
-	ret = panthor_gpu_init(ptdev);
+	ret = panthor_pwr_init(ptdev);
 	if (ret)
 		goto err_rpm_put;
 
+	ret = panthor_gpu_init(ptdev);
+	if (ret)
+		goto err_unplug_pwr;
+
 	ret = panthor_gpu_coherency_init(ptdev);
 	if (ret)
 		goto err_unplug_gpu;
@@ -312,6 +318,9 @@ err_unplug_mmu:
 err_unplug_gpu:
 	panthor_gpu_unplug(ptdev);
 
+err_unplug_pwr:
+	panthor_pwr_unplug(ptdev);
+
 err_rpm_put:
 	pm_runtime_put_sync_suspend(ptdev->base.dev);
 	return ret;
@@ -465,6 +474,7 @@ static int panthor_device_resume_hw_components(struct panthor_device *ptdev)
 {
 	int ret;
 
+	panthor_pwr_resume(ptdev);
 	panthor_gpu_resume(ptdev);
 	panthor_mmu_resume(ptdev);
 
@@ -474,6 +484,7 @@ static int panthor_device_resume_hw_components(struct panthor_device *ptdev)
 
 	panthor_mmu_suspend(ptdev);
 	panthor_gpu_suspend(ptdev);
+	panthor_pwr_suspend(ptdev);
 	return ret;
 }
 
@@ -587,6 +598,7 @@ int panthor_device_suspend(struct device *dev)
 		panthor_fw_suspend(ptdev);
 		panthor_mmu_suspend(ptdev);
 		panthor_gpu_suspend(ptdev);
+		panthor_pwr_suspend(ptdev);
 		drm_dev_exit(cookie);
 	}
 
diff --git a/drivers/gpu/drm/panthor/panthor_device.h b/drivers/gpu/drm/panthor/panthor_device.h
index f32c1868bf6d..f35e52b9546a 100644
--- a/drivers/gpu/drm/panthor/panthor_device.h
+++ b/drivers/gpu/drm/panthor/panthor_device.h
@@ -24,10 +24,12 @@ struct panthor_device;
 struct panthor_gpu;
 struct panthor_group_pool;
 struct panthor_heap_pool;
+struct panthor_hw;
 struct panthor_job;
 struct panthor_mmu;
 struct panthor_fw;
 struct panthor_perfcnt;
+struct panthor_pwr;
 struct panthor_vm;
 struct panthor_vm_pool;
 
@@ -134,6 +136,12 @@ struct panthor_device {
 	/** @csif_info: Command stream interface information. */
 	struct drm_panthor_csif_info csif_info;
 
+	/** @hw: GPU-specific data. */
+	struct panthor_hw *hw;
+
+	/** @pwr: Power control management data. */
+	struct panthor_pwr *pwr;
+
 	/** @gpu: GPU management data. */
 	struct panthor_gpu *gpu;
 
diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c
index 38d87ab92eda..1a5e3c1a27fb 100644
--- a/drivers/gpu/drm/panthor/panthor_fw.c
+++ b/drivers/gpu/drm/panthor/panthor_fw.c
@@ -22,6 +22,7 @@
 #include "panthor_fw.h"
 #include "panthor_gem.h"
 #include "panthor_gpu.h"
+#include "panthor_hw.h"
 #include "panthor_mmu.h"
 #include "panthor_regs.h"
 #include "panthor_sched.h"
@@ -33,6 +34,7 @@
 #define PROGRESS_TIMEOUT_SCALE_SHIFT		10
 #define IDLE_HYSTERESIS_US			800
 #define PWROFF_HYSTERESIS_US			10000
+#define MCU_HALT_TIMEOUT_US			(1ULL * USEC_PER_SEC)
 
 /**
  * struct panthor_fw_binary_hdr - Firmware binary header.
@@ -317,6 +319,49 @@ panthor_fw_get_cs_iface(struct panthor_device *ptdev, u32 csg_slot, u32 cs_slot)
 	return &ptdev->fw->iface.streams[csg_slot][cs_slot];
 }
 
+static bool panthor_fw_has_glb_state(struct panthor_device *ptdev)
+{
+	struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
+
+	return glb_iface->control->version >= CSF_IFACE_VERSION(4, 1, 0);
+}
+
+static bool panthor_fw_has_64bit_ep_req(struct panthor_device *ptdev)
+{
+	struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
+
+	return glb_iface->control->version >= CSF_IFACE_VERSION(4, 0, 0);
+}
+
+u64 panthor_fw_csg_endpoint_req_get(struct panthor_device *ptdev,
+				    struct panthor_fw_csg_iface *csg_iface)
+{
+	if (panthor_fw_has_64bit_ep_req(ptdev))
+		return csg_iface->input->endpoint_req2;
+	else
+		return csg_iface->input->endpoint_req;
+}
+
+void panthor_fw_csg_endpoint_req_set(struct panthor_device *ptdev,
+				     struct panthor_fw_csg_iface *csg_iface, u64 value)
+{
+	if (panthor_fw_has_64bit_ep_req(ptdev))
+		csg_iface->input->endpoint_req2 = value;
+	else
+		csg_iface->input->endpoint_req = lower_32_bits(value);
+}
+
+void panthor_fw_csg_endpoint_req_update(struct panthor_device *ptdev,
+					struct panthor_fw_csg_iface *csg_iface, u64 value,
+					u64 mask)
+{
+	if (panthor_fw_has_64bit_ep_req(ptdev))
+		panthor_fw_update_reqs64(csg_iface, endpoint_req2, value, mask);
+	else
+		panthor_fw_update_reqs(csg_iface, endpoint_req, lower_32_bits(value),
+				       lower_32_bits(mask));
+}
+
 /**
  * panthor_fw_conv_timeout() - Convert a timeout into a cycle-count
  * @ptdev: Device.
@@ -996,6 +1041,9 @@ static void panthor_fw_init_global_iface(struct panthor_device *ptdev)
 					 GLB_IDLE_EN |
 					 GLB_IDLE;
 
+	if (panthor_fw_has_glb_state(ptdev))
+		glb_iface->input->ack_irq_mask |= GLB_STATE_MASK;
+
 	panthor_fw_update_reqs(glb_iface, req, GLB_IDLE_EN, GLB_IDLE_EN);
 	panthor_fw_toggle_reqs(glb_iface, req, ack,
 			       GLB_CFG_ALLOC_EN |
@@ -1069,6 +1117,54 @@ static void panthor_fw_stop(struct panthor_device *ptdev)
 		drm_err(&ptdev->base, "Failed to stop MCU");
 }
 
+static bool panthor_fw_mcu_halted(struct panthor_device *ptdev)
+{
+	struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
+	bool halted;
+
+	halted = gpu_read(ptdev, MCU_STATUS) == MCU_STATUS_HALT;
+
+	if (panthor_fw_has_glb_state(ptdev))
+		halted &= (GLB_STATE_GET(glb_iface->output->ack) == GLB_STATE_HALT);
+
+	return halted;
+}
+
+static void panthor_fw_halt_mcu(struct panthor_device *ptdev)
+{
+	struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
+
+	if (panthor_fw_has_glb_state(ptdev))
+		panthor_fw_update_reqs(glb_iface, req, GLB_STATE(GLB_STATE_HALT), GLB_STATE_MASK);
+	else
+		panthor_fw_update_reqs(glb_iface, req, GLB_HALT, GLB_HALT);
+
+	gpu_write(ptdev, CSF_DOORBELL(CSF_GLB_DOORBELL_ID), 1);
+}
+
+static bool panthor_fw_wait_mcu_halted(struct panthor_device *ptdev)
+{
+	bool halted = false;
+
+	if (read_poll_timeout_atomic(panthor_fw_mcu_halted, halted, halted, 10,
+				     MCU_HALT_TIMEOUT_US, 0, ptdev)) {
+		drm_warn(&ptdev->base, "Timed out waiting for MCU to halt");
+		return false;
+	}
+
+	return true;
+}
+
+static void panthor_fw_mcu_set_active(struct panthor_device *ptdev)
+{
+	struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
+
+	if (panthor_fw_has_glb_state(ptdev))
+		panthor_fw_update_reqs(glb_iface, req, GLB_STATE(GLB_STATE_ACTIVE), GLB_STATE_MASK);
+	else
+		panthor_fw_update_reqs(glb_iface, req, 0, GLB_HALT);
+}
+
 /**
  * panthor_fw_pre_reset() - Call before a reset.
  * @ptdev: Device.
@@ -1085,19 +1181,13 @@ void panthor_fw_pre_reset(struct panthor_device *ptdev, bool on_hang)
 	ptdev->reset.fast = false;
 
 	if (!on_hang) {
-		struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
-		u32 status;
-
-		panthor_fw_update_reqs(glb_iface, req, GLB_HALT, GLB_HALT);
-		gpu_write(ptdev, CSF_DOORBELL(CSF_GLB_DOORBELL_ID), 1);
-		if (!gpu_read_poll_timeout(ptdev, MCU_STATUS, status,
-					   status == MCU_STATUS_HALT, 10,
-					   100000)) {
-			ptdev->reset.fast = true;
-		} else {
+		panthor_fw_halt_mcu(ptdev);
+		if (!panthor_fw_wait_mcu_halted(ptdev))
 			drm_warn(&ptdev->base, "Failed to cleanly suspend MCU");
-		}
+		else
+			ptdev->reset.fast = true;
 	}
+	panthor_fw_stop(ptdev);
 
 	panthor_job_irq_suspend(&ptdev->fw->irq);
 	panthor_fw_stop(ptdev);
@@ -1126,14 +1216,14 @@ int panthor_fw_post_reset(struct panthor_device *ptdev)
 		 */
 		panthor_reload_fw_sections(ptdev, true);
 	} else {
-		/* The FW detects 0 -> 1 transitions. Make sure we reset
-		 * the HALT bit before the FW is rebooted.
+		/*
+		 * If the FW was previously successfully halted in the pre-reset
+		 * operation, we need to transition it to active again before
+		 * the FW is rebooted.
 		 * This is not needed on a slow reset because FW sections are
 		 * re-initialized.
 		 */
-		struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
-
-		panthor_fw_update_reqs(glb_iface, req, 0, GLB_HALT);
+		panthor_fw_mcu_set_active(ptdev);
 	}
 
 	ret = panthor_fw_start(ptdev);
@@ -1171,6 +1261,10 @@ void panthor_fw_unplug(struct panthor_device *ptdev)
 		if (ptdev->fw->irq.irq)
 			panthor_job_irq_suspend(&ptdev->fw->irq);
 
+		panthor_fw_halt_mcu(ptdev);
+		if (!panthor_fw_wait_mcu_halted(ptdev))
+			drm_warn(&ptdev->base, "Failed to halt MCU on unplug");
+
 		panthor_fw_stop(ptdev);
 	}
 
@@ -1186,7 +1280,7 @@ void panthor_fw_unplug(struct panthor_device *ptdev)
 	ptdev->fw->vm = NULL;
 
 	if (!IS_ENABLED(CONFIG_PM) || pm_runtime_active(ptdev->base.dev))
-		panthor_gpu_power_off(ptdev, L2, ptdev->gpu_info.l2_present, 20000);
+		panthor_hw_l2_power_off(ptdev);
 }
 
 /**
@@ -1365,7 +1459,7 @@ int panthor_fw_init(struct panthor_device *ptdev)
 		return ret;
 	}
 
-	ret = panthor_gpu_l2_power_on(ptdev);
+	ret = panthor_hw_l2_power_on(ptdev);
 	if (ret)
 		return ret;
 
@@ -1409,3 +1503,4 @@ MODULE_FIRMWARE("arm/mali/arch10.12/mali_csffw.bin");
 MODULE_FIRMWARE("arm/mali/arch11.8/mali_csffw.bin");
 MODULE_FIRMWARE("arm/mali/arch12.8/mali_csffw.bin");
 MODULE_FIRMWARE("arm/mali/arch13.8/mali_csffw.bin");
+MODULE_FIRMWARE("arm/mali/arch14.8/mali_csffw.bin");
diff --git a/drivers/gpu/drm/panthor/panthor_fw.h b/drivers/gpu/drm/panthor/panthor_fw.h
index 6598d96c6d2a..fbdc21469ba3 100644
--- a/drivers/gpu/drm/panthor/panthor_fw.h
+++ b/drivers/gpu/drm/panthor/panthor_fw.h
@@ -167,10 +167,11 @@ struct panthor_fw_csg_input_iface {
 #define CSG_EP_REQ_TILER(x)			(((x) << 16) & GENMASK(19, 16))
 #define CSG_EP_REQ_EXCL_COMPUTE			BIT(20)
 #define CSG_EP_REQ_EXCL_FRAGMENT		BIT(21)
-#define CSG_EP_REQ_PRIORITY(x)			(((x) << 28) & GENMASK(31, 28))
 #define CSG_EP_REQ_PRIORITY_MASK		GENMASK(31, 28)
+#define CSG_EP_REQ_PRIORITY(x)			(((x) << 28) & CSG_EP_REQ_PRIORITY_MASK)
+#define CSG_EP_REQ_PRIORITY_GET(x)		(((x) & CSG_EP_REQ_PRIORITY_MASK) >> 28)
 	u32 endpoint_req;
-	u32 reserved2[2];
+	u64 endpoint_req2;
 	u64 suspend_buf;
 	u64 protm_suspend_buf;
 	u32 config;
@@ -214,6 +215,13 @@ struct panthor_fw_global_input_iface {
 #define GLB_FWCFG_UPDATE			BIT(9)
 #define GLB_IDLE_EN				BIT(10)
 #define GLB_SLEEP				BIT(12)
+#define GLB_STATE_MASK				GENMASK(14, 12)
+#define   GLB_STATE_ACTIVE			0
+#define   GLB_STATE_HALT			1
+#define   GLB_STATE_SLEEP			2
+#define   GLB_STATE_SUSPEND			3
+#define   GLB_STATE(x)				(((x) << 12) & GLB_STATE_MASK)
+#define   GLB_STATE_GET(x)			(((x) & GLB_STATE_MASK) >> 12)
 #define GLB_INACTIVE_COMPUTE			BIT(20)
 #define GLB_INACTIVE_FRAGMENT			BIT(21)
 #define GLB_INACTIVE_TILER			BIT(22)
@@ -457,6 +465,16 @@ struct panthor_fw_global_iface {
 		spin_unlock(&(__iface)->lock); \
 	} while (0)
 
+#define panthor_fw_update_reqs64(__iface, __in_reg, __val, __mask) \
+	do { \
+		u64 __cur_val, __new_val; \
+		spin_lock(&(__iface)->lock); \
+		__cur_val = READ_ONCE((__iface)->input->__in_reg); \
+		__new_val = (__cur_val & ~(__mask)) | ((__val) & (__mask)); \
+		WRITE_ONCE((__iface)->input->__in_reg, __new_val); \
+		spin_unlock(&(__iface)->lock); \
+	} while (0)
+
 struct panthor_fw_global_iface *
 panthor_fw_get_glb_iface(struct panthor_device *ptdev);
 
@@ -466,6 +484,16 @@ panthor_fw_get_csg_iface(struct panthor_device *ptdev, u32 csg_slot);
 struct panthor_fw_cs_iface *
 panthor_fw_get_cs_iface(struct panthor_device *ptdev, u32 csg_slot, u32 cs_slot);
 
+u64 panthor_fw_csg_endpoint_req_get(struct panthor_device *ptdev,
+				    struct panthor_fw_csg_iface *csg_iface);
+
+void panthor_fw_csg_endpoint_req_set(struct panthor_device *ptdev,
+				     struct panthor_fw_csg_iface *csg_iface, u64 value);
+
+void panthor_fw_csg_endpoint_req_update(struct panthor_device *ptdev,
+					struct panthor_fw_csg_iface *csg_iface, u64 value,
+					u64 mask);
+
 int panthor_fw_csg_wait_acks(struct panthor_device *ptdev, u32 csg_id, u32 req_mask,
 			     u32 *acked, u32 timeout_ms);
 
diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c
index 2c12c1c58e2b..fbde78db270a 100644
--- a/drivers/gpu/drm/panthor/panthor_gem.c
+++ b/drivers/gpu/drm/panthor/panthor_gem.c
@@ -145,6 +145,9 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm,
 	bo = to_panthor_bo(&obj->base);
 	kbo->obj = &obj->base;
 	bo->flags = bo_flags;
+	bo->exclusive_vm_root_gem = panthor_vm_root_gem(vm);
+	drm_gem_object_get(bo->exclusive_vm_root_gem);
+	bo->base.base.resv = bo->exclusive_vm_root_gem->resv;
 
 	if (vm == panthor_fw_vm(ptdev))
 		debug_flags |= PANTHOR_DEBUGFS_GEM_USAGE_FLAG_FW_MAPPED;
@@ -168,9 +171,6 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm,
 		goto err_free_va;
 
 	kbo->vm = panthor_vm_get(vm);
-	bo->exclusive_vm_root_gem = panthor_vm_root_gem(vm);
-	drm_gem_object_get(bo->exclusive_vm_root_gem);
-	bo->base.base.resv = bo->exclusive_vm_root_gem->resv;
 	return kbo;
 
 err_free_va:
diff --git a/drivers/gpu/drm/panthor/panthor_gpu.c b/drivers/gpu/drm/panthor/panthor_gpu.c
index eda670229184..06b231b2460a 100644
--- a/drivers/gpu/drm/panthor/panthor_gpu.c
+++ b/drivers/gpu/drm/panthor/panthor_gpu.c
@@ -19,6 +19,7 @@
 
 #include "panthor_device.h"
 #include "panthor_gpu.h"
+#include "panthor_hw.h"
 #include "panthor_regs.h"
 
 /**
@@ -241,6 +242,11 @@ int panthor_gpu_block_power_on(struct panthor_device *ptdev,
 	return 0;
 }
 
+void panthor_gpu_l2_power_off(struct panthor_device *ptdev)
+{
+	panthor_gpu_power_off(ptdev, L2, ptdev->gpu_info.l2_present, 20000);
+}
+
 /**
  * panthor_gpu_l2_power_on() - Power-on the L2-cache
  * @ptdev: Device.
@@ -368,9 +374,9 @@ void panthor_gpu_suspend(struct panthor_device *ptdev)
 {
 	/* On a fast reset, simply power down the L2. */
 	if (!ptdev->reset.fast)
-		panthor_gpu_soft_reset(ptdev);
+		panthor_hw_soft_reset(ptdev);
 	else
-		panthor_gpu_power_off(ptdev, L2, 1, 20000);
+		panthor_hw_l2_power_off(ptdev);
 
 	panthor_gpu_irq_suspend(&ptdev->gpu->irq);
 }
@@ -385,6 +391,6 @@ void panthor_gpu_suspend(struct panthor_device *ptdev)
 void panthor_gpu_resume(struct panthor_device *ptdev)
 {
 	panthor_gpu_irq_resume(&ptdev->gpu->irq, GPU_INTERRUPTS_MASK);
-	panthor_gpu_l2_power_on(ptdev);
+	panthor_hw_l2_power_on(ptdev);
 }
 
diff --git a/drivers/gpu/drm/panthor/panthor_gpu.h b/drivers/gpu/drm/panthor/panthor_gpu.h
index 7c17a8c06858..12e66f48ced1 100644
--- a/drivers/gpu/drm/panthor/panthor_gpu.h
+++ b/drivers/gpu/drm/panthor/panthor_gpu.h
@@ -46,6 +46,7 @@ int panthor_gpu_block_power_off(struct panthor_device *ptdev,
 				   type ## _PWRTRANS, \
 				   mask, timeout_us)
 
+void panthor_gpu_l2_power_off(struct panthor_device *ptdev);
 int panthor_gpu_l2_power_on(struct panthor_device *ptdev);
 int panthor_gpu_flush_caches(struct panthor_device *ptdev,
 			     u32 l2, u32 lsc, u32 other);
diff --git a/drivers/gpu/drm/panthor/panthor_hw.c b/drivers/gpu/drm/panthor/panthor_hw.c
index c44033a0bba8..87ebb7ae42c4 100644
--- a/drivers/gpu/drm/panthor/panthor_hw.c
+++ b/drivers/gpu/drm/panthor/panthor_hw.c
@@ -4,12 +4,55 @@
 #include <drm/drm_print.h>
 
 #include "panthor_device.h"
+#include "panthor_gpu.h"
 #include "panthor_hw.h"
+#include "panthor_pwr.h"
 #include "panthor_regs.h"
 
 #define GPU_PROD_ID_MAKE(arch_major, prod_major) \
 	(((arch_major) << 24) | (prod_major))
 
+/** struct panthor_hw_entry - HW arch major to panthor_hw binding entry */
+struct panthor_hw_entry {
+	/** @arch_min: Minimum supported architecture major value (inclusive) */
+	u8 arch_min;
+
+	/** @arch_max: Maximum supported architecture major value (inclusive) */
+	u8 arch_max;
+
+	/** @hwdev: Pointer to panthor_hw structure */
+	struct panthor_hw *hwdev;
+};
+
+static struct panthor_hw panthor_hw_arch_v10 = {
+	.ops = {
+		.soft_reset = panthor_gpu_soft_reset,
+		.l2_power_off = panthor_gpu_l2_power_off,
+		.l2_power_on = panthor_gpu_l2_power_on,
+	},
+};
+
+static struct panthor_hw panthor_hw_arch_v14 = {
+	.ops = {
+		.soft_reset = panthor_pwr_reset_soft,
+		.l2_power_off = panthor_pwr_l2_power_off,
+		.l2_power_on = panthor_pwr_l2_power_on,
+	},
+};
+
+static struct panthor_hw_entry panthor_hw_match[] = {
+	{
+		.arch_min = 10,
+		.arch_max = 13,
+		.hwdev = &panthor_hw_arch_v10,
+	},
+	{
+		.arch_min = 14,
+		.arch_max = 14,
+		.hwdev = &panthor_hw_arch_v14,
+	},
+};
+
 static char *get_gpu_model_name(struct panthor_device *ptdev)
 {
 	const u32 gpu_id = ptdev->gpu_info.gpu_id;
@@ -55,6 +98,12 @@ static char *get_gpu_model_name(struct panthor_device *ptdev)
 		fallthrough;
 	case GPU_PROD_ID_MAKE(13, 1):
 		return "Mali-G625";
+	case GPU_PROD_ID_MAKE(14, 0):
+		return "Mali-G1-Ultra";
+	case GPU_PROD_ID_MAKE(14, 1):
+		return "Mali-G1-Premium";
+	case GPU_PROD_ID_MAKE(14, 3):
+		return "Mali-G1-Pro";
 	}
 
 	return "(Unknown Mali GPU)";
@@ -64,7 +113,6 @@ static void panthor_gpu_info_init(struct panthor_device *ptdev)
 {
 	unsigned int i;
 
-	ptdev->gpu_info.gpu_id = gpu_read(ptdev, GPU_ID);
 	ptdev->gpu_info.csf_id = gpu_read(ptdev, GPU_CSF_ID);
 	ptdev->gpu_info.gpu_rev = gpu_read(ptdev, GPU_REVID);
 	ptdev->gpu_info.core_features = gpu_read(ptdev, GPU_CORE_FEATURES);
@@ -82,12 +130,19 @@ static void panthor_gpu_info_init(struct panthor_device *ptdev)
 
 	ptdev->gpu_info.as_present = gpu_read(ptdev, GPU_AS_PRESENT);
 
-	ptdev->gpu_info.shader_present = gpu_read64(ptdev, GPU_SHADER_PRESENT);
-	ptdev->gpu_info.tiler_present = gpu_read64(ptdev, GPU_TILER_PRESENT);
-	ptdev->gpu_info.l2_present = gpu_read64(ptdev, GPU_L2_PRESENT);
-
 	/* Introduced in arch 11.x */
 	ptdev->gpu_info.gpu_features = gpu_read64(ptdev, GPU_FEATURES);
+
+	if (panthor_hw_has_pwr_ctrl(ptdev)) {
+		/* Introduced in arch 14.x */
+		ptdev->gpu_info.l2_present = gpu_read64(ptdev, PWR_L2_PRESENT);
+		ptdev->gpu_info.tiler_present = gpu_read64(ptdev, PWR_TILER_PRESENT);
+		ptdev->gpu_info.shader_present = gpu_read64(ptdev, PWR_SHADER_PRESENT);
+	} else {
+		ptdev->gpu_info.shader_present = gpu_read64(ptdev, GPU_SHADER_PRESENT);
+		ptdev->gpu_info.tiler_present = gpu_read64(ptdev, GPU_TILER_PRESENT);
+		ptdev->gpu_info.l2_present = gpu_read64(ptdev, GPU_L2_PRESENT);
+	}
 }
 
 static void panthor_hw_info_init(struct panthor_device *ptdev)
@@ -119,8 +174,50 @@ static void panthor_hw_info_init(struct panthor_device *ptdev)
 		 ptdev->gpu_info.tiler_present);
 }
 
+static int panthor_hw_bind_device(struct panthor_device *ptdev)
+{
+	struct panthor_hw *hdev = NULL;
+	const u32 arch_major = GPU_ARCH_MAJOR(ptdev->gpu_info.gpu_id);
+	int i = 0;
+
+	for (i = 0; i < ARRAY_SIZE(panthor_hw_match); i++) {
+		struct panthor_hw_entry *entry = &panthor_hw_match[i];
+
+		if (arch_major >= entry->arch_min && arch_major <= entry->arch_max) {
+			hdev = entry->hwdev;
+			break;
+		}
+	}
+
+	if (!hdev)
+		return -EOPNOTSUPP;
+
+	ptdev->hw = hdev;
+
+	return 0;
+}
+
+static int panthor_hw_gpu_id_init(struct panthor_device *ptdev)
+{
+	ptdev->gpu_info.gpu_id = gpu_read(ptdev, GPU_ID);
+	if (!ptdev->gpu_info.gpu_id)
+		return -ENXIO;
+
+	return 0;
+}
+
 int panthor_hw_init(struct panthor_device *ptdev)
 {
+	int ret = 0;
+
+	ret = panthor_hw_gpu_id_init(ptdev);
+	if (ret)
+		return ret;
+
+	ret = panthor_hw_bind_device(ptdev);
+	if (ret)
+		return ret;
+
 	panthor_hw_info_init(ptdev);
 
 	return 0;
diff --git a/drivers/gpu/drm/panthor/panthor_hw.h b/drivers/gpu/drm/panthor/panthor_hw.h
index 0af6acc6aa6a..56c68c1e9c26 100644
--- a/drivers/gpu/drm/panthor/panthor_hw.h
+++ b/drivers/gpu/drm/panthor/panthor_hw.h
@@ -4,8 +4,53 @@
 #ifndef __PANTHOR_HW_H__
 #define __PANTHOR_HW_H__
 
-struct panthor_device;
+#include "panthor_device.h"
+#include "panthor_regs.h"
+
+/**
+ * struct panthor_hw_ops - HW operations that are specific to a GPU
+ */
+struct panthor_hw_ops {
+	/** @soft_reset: Soft reset function pointer */
+	int (*soft_reset)(struct panthor_device *ptdev);
+
+	/** @l2_power_off: L2 power off function pointer */
+	void (*l2_power_off)(struct panthor_device *ptdev);
+
+	/** @l2_power_on: L2 power on function pointer */
+	int (*l2_power_on)(struct panthor_device *ptdev);
+};
+
+/**
+ * struct panthor_hw - GPU specific register mapping and functions
+ */
+struct panthor_hw {
+	/** @features: Bitmap containing panthor_hw_feature */
+
+	/** @ops: Panthor HW specific operations */
+	struct panthor_hw_ops ops;
+};
 
 int panthor_hw_init(struct panthor_device *ptdev);
 
+static inline int panthor_hw_soft_reset(struct panthor_device *ptdev)
+{
+	return ptdev->hw->ops.soft_reset(ptdev);
+}
+
+static inline int panthor_hw_l2_power_on(struct panthor_device *ptdev)
+{
+	return ptdev->hw->ops.l2_power_on(ptdev);
+}
+
+static inline void panthor_hw_l2_power_off(struct panthor_device *ptdev)
+{
+	ptdev->hw->ops.l2_power_off(ptdev);
+}
+
+static inline bool panthor_hw_has_pwr_ctrl(struct panthor_device *ptdev)
+{
+	return GPU_ARCH_MAJOR(ptdev->gpu_info.gpu_id) >= 14;
+}
+
 #endif /* __PANTHOR_HW_H__ */
diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c
index 478ea98db95c..d4839d282689 100644
--- a/drivers/gpu/drm/panthor/panthor_mmu.c
+++ b/drivers/gpu/drm/panthor/panthor_mmu.c
@@ -904,10 +904,9 @@ static int panthor_vm_unmap_pages(struct panthor_vm *vm, u64 iova, u64 size)
 {
 	struct panthor_device *ptdev = vm->ptdev;
 	struct io_pgtable_ops *ops = vm->pgtbl_ops;
+	u64 start_iova = iova;
 	u64 offset = 0;
 
-	drm_dbg(&ptdev->base, "unmap: as=%d, iova=%llx, len=%llx", vm->as.id, iova, size);
-
 	while (offset < size) {
 		size_t unmapped_sz = 0, pgcount;
 		size_t pgsize = get_pgsize(iova + offset, size - offset, &pgcount);
@@ -922,6 +921,12 @@ static int panthor_vm_unmap_pages(struct panthor_vm *vm, u64 iova, u64 size)
 			panthor_vm_flush_range(vm, iova, offset + unmapped_sz);
 			return  -EINVAL;
 		}
+
+		drm_dbg(&ptdev->base,
+			"unmap: as=%d, iova=0x%llx, sz=%llu, va=0x%llx, pgcnt=%zu, pgsz=%zu",
+			vm->as.id, start_iova, size, iova + offset,
+			unmapped_sz / pgsize, pgsize);
+
 		offset += unmapped_sz;
 	}
 
@@ -937,6 +942,7 @@ panthor_vm_map_pages(struct panthor_vm *vm, u64 iova, int prot,
 	struct scatterlist *sgl;
 	struct io_pgtable_ops *ops = vm->pgtbl_ops;
 	u64 start_iova = iova;
+	u64 start_size = size;
 	int ret;
 
 	if (!size)
@@ -956,15 +962,18 @@ panthor_vm_map_pages(struct panthor_vm *vm, u64 iova, int prot,
 		len = min_t(size_t, len, size);
 		size -= len;
 
-		drm_dbg(&ptdev->base, "map: as=%d, iova=%llx, paddr=%pad, len=%zx",
-			vm->as.id, iova, &paddr, len);
-
 		while (len) {
 			size_t pgcount, mapped = 0;
 			size_t pgsize = get_pgsize(iova | paddr, len, &pgcount);
 
 			ret = ops->map_pages(ops, iova, paddr, pgsize, pgcount, prot,
 					     GFP_KERNEL, &mapped);
+
+			drm_dbg(&ptdev->base,
+				"map: as=%d, iova=0x%llx, sz=%llu, va=0x%llx, pa=%pad, pgcnt=%zu, pgsz=%zu",
+				vm->as.id, start_iova, start_size, iova, &paddr,
+				mapped / pgsize, pgsize);
+
 			iova += mapped;
 			paddr += mapped;
 			len -= mapped;
diff --git a/drivers/gpu/drm/panthor/panthor_pwr.c b/drivers/gpu/drm/panthor/panthor_pwr.c
new file mode 100644
index 000000000000..57cfc7ce715b
--- /dev/null
+++ b/drivers/gpu/drm/panthor/panthor_pwr.c
@@ -0,0 +1,549 @@
+// SPDX-License-Identifier: GPL-2.0 or MIT
+/* Copyright 2025 ARM Limited. All rights reserved. */
+
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/cleanup.h>
+#include <linux/iopoll.h>
+#include <linux/wait.h>
+
+#include <drm/drm_managed.h>
+#include <drm/drm_print.h>
+
+#include "panthor_device.h"
+#include "panthor_hw.h"
+#include "panthor_pwr.h"
+#include "panthor_regs.h"
+
+#define PWR_INTERRUPTS_MASK \
+	(PWR_IRQ_POWER_CHANGED_SINGLE | \
+	 PWR_IRQ_POWER_CHANGED_ALL | \
+	 PWR_IRQ_DELEGATION_CHANGED | \
+	 PWR_IRQ_RESET_COMPLETED | \
+	 PWR_IRQ_RETRACT_COMPLETED | \
+	 PWR_IRQ_INSPECT_COMPLETED | \
+	 PWR_IRQ_COMMAND_NOT_ALLOWED | \
+	 PWR_IRQ_COMMAND_INVALID)
+
+#define PWR_ALL_CORES_MASK		GENMASK_U64(63, 0)
+
+#define PWR_DOMAIN_MAX_BITS		16
+
+#define PWR_TRANSITION_TIMEOUT_US	(2ULL * USEC_PER_SEC)
+
+#define PWR_RETRACT_TIMEOUT_US		(2ULL * USEC_PER_MSEC)
+
+#define PWR_RESET_TIMEOUT_MS		500
+
+/**
+ * struct panthor_pwr - PWR_CONTROL block management data.
+ */
+struct panthor_pwr {
+	/** @irq: PWR irq. */
+	struct panthor_irq irq;
+
+	/** @reqs_lock: Lock protecting access to pending_reqs. */
+	spinlock_t reqs_lock;
+
+	/** @pending_reqs: Pending PWR requests. */
+	u32 pending_reqs;
+
+	/** @reqs_acked: PWR request wait queue. */
+	wait_queue_head_t reqs_acked;
+};
+
+static void panthor_pwr_irq_handler(struct panthor_device *ptdev, u32 status)
+{
+	spin_lock(&ptdev->pwr->reqs_lock);
+	gpu_write(ptdev, PWR_INT_CLEAR, status);
+
+	if (unlikely(status & PWR_IRQ_COMMAND_NOT_ALLOWED))
+		drm_err(&ptdev->base, "PWR_IRQ: COMMAND_NOT_ALLOWED");
+
+	if (unlikely(status & PWR_IRQ_COMMAND_INVALID))
+		drm_err(&ptdev->base, "PWR_IRQ: COMMAND_INVALID");
+
+	if (status & ptdev->pwr->pending_reqs) {
+		ptdev->pwr->pending_reqs &= ~status;
+		wake_up_all(&ptdev->pwr->reqs_acked);
+	}
+	spin_unlock(&ptdev->pwr->reqs_lock);
+}
+PANTHOR_IRQ_HANDLER(pwr, PWR, panthor_pwr_irq_handler);
+
+static void panthor_pwr_write_command(struct panthor_device *ptdev, u32 command, u64 args)
+{
+	if (args)
+		gpu_write64(ptdev, PWR_CMDARG, args);
+
+	gpu_write(ptdev, PWR_COMMAND, command);
+}
+
+static bool reset_irq_raised(struct panthor_device *ptdev)
+{
+	return gpu_read(ptdev, PWR_INT_RAWSTAT) & PWR_IRQ_RESET_COMPLETED;
+}
+
+static bool reset_pending(struct panthor_device *ptdev)
+{
+	return (ptdev->pwr->pending_reqs & PWR_IRQ_RESET_COMPLETED);
+}
+
+static int panthor_pwr_reset(struct panthor_device *ptdev, u32 reset_cmd)
+{
+	scoped_guard(spinlock_irqsave, &ptdev->pwr->reqs_lock) {
+		if (reset_pending(ptdev)) {
+			drm_WARN(&ptdev->base, 1, "Reset already pending");
+		} else {
+			ptdev->pwr->pending_reqs |= PWR_IRQ_RESET_COMPLETED;
+			gpu_write(ptdev, PWR_INT_CLEAR, PWR_IRQ_RESET_COMPLETED);
+			panthor_pwr_write_command(ptdev, reset_cmd, 0);
+		}
+	}
+
+	if (!wait_event_timeout(ptdev->pwr->reqs_acked, !reset_pending(ptdev),
+				msecs_to_jiffies(PWR_RESET_TIMEOUT_MS))) {
+		guard(spinlock_irqsave)(&ptdev->pwr->reqs_lock);
+
+		if (reset_pending(ptdev) && !reset_irq_raised(ptdev)) {
+			drm_err(&ptdev->base, "RESET timed out (0x%x)", reset_cmd);
+			return -ETIMEDOUT;
+		}
+
+		ptdev->pwr->pending_reqs &= ~PWR_IRQ_RESET_COMPLETED;
+	}
+
+	return 0;
+}
+
+static const char *get_domain_name(u8 domain)
+{
+	switch (domain) {
+	case PWR_COMMAND_DOMAIN_L2:
+		return "L2";
+	case PWR_COMMAND_DOMAIN_TILER:
+		return "Tiler";
+	case PWR_COMMAND_DOMAIN_SHADER:
+		return "Shader";
+	case PWR_COMMAND_DOMAIN_BASE:
+		return "Base";
+	case PWR_COMMAND_DOMAIN_STACK:
+		return "Stack";
+	}
+	return "Unknown";
+}
+
+static u32 get_domain_base(u8 domain)
+{
+	switch (domain) {
+	case PWR_COMMAND_DOMAIN_L2:
+		return PWR_L2_PRESENT;
+	case PWR_COMMAND_DOMAIN_TILER:
+		return PWR_TILER_PRESENT;
+	case PWR_COMMAND_DOMAIN_SHADER:
+		return PWR_SHADER_PRESENT;
+	case PWR_COMMAND_DOMAIN_BASE:
+		return PWR_BASE_PRESENT;
+	case PWR_COMMAND_DOMAIN_STACK:
+		return PWR_STACK_PRESENT;
+	}
+	return 0;
+}
+
+static u32 get_domain_ready_reg(u32 domain)
+{
+	return get_domain_base(domain) + (PWR_L2_READY - PWR_L2_PRESENT);
+}
+
+static u32 get_domain_pwrtrans_reg(u32 domain)
+{
+	return get_domain_base(domain) + (PWR_L2_PWRTRANS - PWR_L2_PRESENT);
+}
+
+static bool is_valid_domain(u32 domain)
+{
+	return get_domain_base(domain) != 0;
+}
+
+static bool has_rtu(struct panthor_device *ptdev)
+{
+	return ptdev->gpu_info.gpu_features & GPU_FEATURES_RAY_TRAVERSAL;
+}
+
+static u8 get_domain_subdomain(struct panthor_device *ptdev, u32 domain)
+{
+	if (domain == PWR_COMMAND_DOMAIN_SHADER && has_rtu(ptdev))
+		return PWR_COMMAND_SUBDOMAIN_RTU;
+
+	return 0;
+}
+
+static int panthor_pwr_domain_wait_transition(struct panthor_device *ptdev, u32 domain,
+					      u32 timeout_us)
+{
+	u32 pwrtrans_reg = get_domain_pwrtrans_reg(domain);
+	u64 val;
+	int ret = 0;
+
+	ret = gpu_read64_poll_timeout(ptdev, pwrtrans_reg, val, !(PWR_ALL_CORES_MASK & val), 100,
+				      timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base, "%s domain power in transition, pwrtrans(0x%llx)",
+			get_domain_name(domain), val);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void panthor_pwr_debug_info_show(struct panthor_device *ptdev)
+{
+	drm_info(&ptdev->base, "GPU_FEATURES:    0x%016llx", gpu_read64(ptdev, GPU_FEATURES));
+	drm_info(&ptdev->base, "PWR_STATUS:      0x%016llx", gpu_read64(ptdev, PWR_STATUS));
+	drm_info(&ptdev->base, "L2_PRESENT:      0x%016llx", gpu_read64(ptdev, PWR_L2_PRESENT));
+	drm_info(&ptdev->base, "L2_PWRTRANS:     0x%016llx", gpu_read64(ptdev, PWR_L2_PWRTRANS));
+	drm_info(&ptdev->base, "L2_READY:        0x%016llx", gpu_read64(ptdev, PWR_L2_READY));
+	drm_info(&ptdev->base, "TILER_PRESENT:   0x%016llx", gpu_read64(ptdev, PWR_TILER_PRESENT));
+	drm_info(&ptdev->base, "TILER_PWRTRANS:  0x%016llx", gpu_read64(ptdev, PWR_TILER_PWRTRANS));
+	drm_info(&ptdev->base, "TILER_READY:     0x%016llx", gpu_read64(ptdev, PWR_TILER_READY));
+	drm_info(&ptdev->base, "SHADER_PRESENT:  0x%016llx", gpu_read64(ptdev, PWR_SHADER_PRESENT));
+	drm_info(&ptdev->base, "SHADER_PWRTRANS: 0x%016llx", gpu_read64(ptdev, PWR_SHADER_PWRTRANS));
+	drm_info(&ptdev->base, "SHADER_READY:    0x%016llx", gpu_read64(ptdev, PWR_SHADER_READY));
+}
+
+static int panthor_pwr_domain_transition(struct panthor_device *ptdev, u32 cmd, u32 domain,
+					 u64 mask, u32 timeout_us)
+{
+	u32 ready_reg = get_domain_ready_reg(domain);
+	u32 pwr_cmd = PWR_COMMAND_DEF(cmd, domain, get_domain_subdomain(ptdev, domain));
+	u64 expected_val = 0;
+	u64 val;
+	int ret = 0;
+
+	if (drm_WARN_ON(&ptdev->base, !is_valid_domain(domain)))
+		return -EINVAL;
+
+	switch (cmd) {
+	case PWR_COMMAND_POWER_DOWN:
+		expected_val = 0;
+		break;
+	case PWR_COMMAND_POWER_UP:
+		expected_val = mask;
+		break;
+	default:
+		drm_err(&ptdev->base, "Invalid power domain transition command (0x%x)", cmd);
+		return -EINVAL;
+	}
+
+	ret = panthor_pwr_domain_wait_transition(ptdev, domain, timeout_us);
+	if (ret)
+		return ret;
+
+	/* domain already in target state, return early */
+	if ((gpu_read64(ptdev, ready_reg) & mask) == expected_val)
+		return 0;
+
+	panthor_pwr_write_command(ptdev, pwr_cmd, mask);
+
+	ret = gpu_read64_poll_timeout(ptdev, ready_reg, val, (mask & val) == expected_val, 100,
+				      timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base,
+			"timeout waiting on %s power domain transition, cmd(0x%x), arg(0x%llx)",
+			get_domain_name(domain), pwr_cmd, mask);
+		panthor_pwr_debug_info_show(ptdev);
+		return ret;
+	}
+
+	return 0;
+}
+
+#define panthor_pwr_domain_power_off(__ptdev, __domain, __mask, __timeout_us)            \
+	panthor_pwr_domain_transition(__ptdev, PWR_COMMAND_POWER_DOWN, __domain, __mask, \
+				      __timeout_us)
+
+#define panthor_pwr_domain_power_on(__ptdev, __domain, __mask, __timeout_us) \
+	panthor_pwr_domain_transition(__ptdev, PWR_COMMAND_POWER_UP, __domain, __mask, __timeout_us)
+
+/**
+ * retract_domain() - Retract control of a domain from MCU
+ * @ptdev: Device.
+ * @domain: Domain to retract the control
+ *
+ * Retracting L2 domain is not expected since it won't be delegated.
+ *
+ * Return: 0 on success or retracted already.
+ *         -EPERM if domain is L2.
+ *         A negative error code otherwise.
+ */
+static int retract_domain(struct panthor_device *ptdev, u32 domain)
+{
+	const u32 pwr_cmd = PWR_COMMAND_DEF(PWR_COMMAND_RETRACT, domain, 0);
+	const u64 pwr_status = gpu_read64(ptdev, PWR_STATUS);
+	const u64 delegated_mask = PWR_STATUS_DOMAIN_DELEGATED(domain);
+	const u64 allow_mask = PWR_STATUS_DOMAIN_ALLOWED(domain);
+	u64 val;
+	int ret;
+
+	if (drm_WARN_ON(&ptdev->base, domain == PWR_COMMAND_DOMAIN_L2))
+		return -EPERM;
+
+	ret = gpu_read64_poll_timeout(ptdev, PWR_STATUS, val, !(PWR_STATUS_RETRACT_PENDING & val),
+				      0, PWR_RETRACT_TIMEOUT_US);
+	if (ret) {
+		drm_err(&ptdev->base, "%s domain retract pending", get_domain_name(domain));
+		return ret;
+	}
+
+	if (!(pwr_status & delegated_mask)) {
+		drm_dbg(&ptdev->base, "%s domain already retracted", get_domain_name(domain));
+		return 0;
+	}
+
+	panthor_pwr_write_command(ptdev, pwr_cmd, 0);
+
+	/*
+	 * On successful retraction
+	 * allow-flag will be set with delegated-flag being cleared.
+	 */
+	ret = gpu_read64_poll_timeout(ptdev, PWR_STATUS, val,
+				      ((delegated_mask | allow_mask) & val) == allow_mask, 10,
+				      PWR_TRANSITION_TIMEOUT_US);
+	if (ret) {
+		drm_err(&ptdev->base, "Retracting %s domain timeout, cmd(0x%x)",
+			get_domain_name(domain), pwr_cmd);
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * delegate_domain() - Delegate control of a domain to MCU
+ * @ptdev: Device.
+ * @domain: Domain to delegate the control
+ *
+ * Delegating L2 domain is prohibited.
+ *
+ * Return:
+ * *       0 on success or delegated already.
+ * *       -EPERM if domain is L2.
+ * *       A negative error code otherwise.
+ */
+static int delegate_domain(struct panthor_device *ptdev, u32 domain)
+{
+	const u32 pwr_cmd = PWR_COMMAND_DEF(PWR_COMMAND_DELEGATE, domain, 0);
+	const u64 pwr_status = gpu_read64(ptdev, PWR_STATUS);
+	const u64 allow_mask = PWR_STATUS_DOMAIN_ALLOWED(domain);
+	const u64 delegated_mask = PWR_STATUS_DOMAIN_DELEGATED(domain);
+	u64 val;
+	int ret;
+
+	if (drm_WARN_ON(&ptdev->base, domain == PWR_COMMAND_DOMAIN_L2))
+		return -EPERM;
+
+	/* Already delegated, exit early */
+	if (pwr_status & delegated_mask)
+		return 0;
+
+	/* Check if the command is allowed before delegating. */
+	if (!(pwr_status & allow_mask)) {
+		drm_warn(&ptdev->base, "Delegating %s domain not allowed", get_domain_name(domain));
+		return -EPERM;
+	}
+
+	ret = panthor_pwr_domain_wait_transition(ptdev, domain, PWR_TRANSITION_TIMEOUT_US);
+	if (ret)
+		return ret;
+
+	panthor_pwr_write_command(ptdev, pwr_cmd, 0);
+
+	/*
+	 * On successful delegation
+	 * allow-flag will be cleared with delegated-flag being set.
+	 */
+	ret = gpu_read64_poll_timeout(ptdev, PWR_STATUS, val,
+				      ((delegated_mask | allow_mask) & val) == delegated_mask,
+				      10, PWR_TRANSITION_TIMEOUT_US);
+	if (ret) {
+		drm_err(&ptdev->base, "Delegating %s domain timeout, cmd(0x%x)",
+			get_domain_name(domain), pwr_cmd);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int panthor_pwr_delegate_domains(struct panthor_device *ptdev)
+{
+	int ret;
+
+	if (!ptdev->pwr)
+		return 0;
+
+	ret = delegate_domain(ptdev, PWR_COMMAND_DOMAIN_SHADER);
+	if (ret)
+		return ret;
+
+	ret = delegate_domain(ptdev, PWR_COMMAND_DOMAIN_TILER);
+	if (ret)
+		goto err_retract_shader;
+
+	return 0;
+
+err_retract_shader:
+	retract_domain(ptdev, PWR_COMMAND_DOMAIN_SHADER);
+
+	return ret;
+}
+
+/**
+ * panthor_pwr_domain_force_off - Forcefully power down a domain.
+ * @ptdev: Device.
+ * @domain: Domain to forcefully power down.
+ *
+ * This function will attempt to retract and power off the requested power
+ * domain. However, if retraction fails, the operation is aborted. If power off
+ * fails, the domain will remain retracted and under the host control.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+static int panthor_pwr_domain_force_off(struct panthor_device *ptdev, u32 domain)
+{
+	const u64 domain_ready = gpu_read64(ptdev, get_domain_ready_reg(domain));
+	int ret;
+
+	/* Domain already powered down, early exit. */
+	if (!domain_ready)
+		return 0;
+
+	/* Domain has to be in host control to issue power off command. */
+	ret = retract_domain(ptdev, domain);
+	if (ret)
+		return ret;
+
+	return panthor_pwr_domain_power_off(ptdev, domain, domain_ready, PWR_TRANSITION_TIMEOUT_US);
+}
+
+void panthor_pwr_unplug(struct panthor_device *ptdev)
+{
+	unsigned long flags;
+
+	if (!ptdev->pwr)
+		return;
+
+	/* Make sure the IRQ handler is not running after that point. */
+	panthor_pwr_irq_suspend(&ptdev->pwr->irq);
+
+	/* Wake-up all waiters. */
+	spin_lock_irqsave(&ptdev->pwr->reqs_lock, flags);
+	ptdev->pwr->pending_reqs = 0;
+	wake_up_all(&ptdev->pwr->reqs_acked);
+	spin_unlock_irqrestore(&ptdev->pwr->reqs_lock, flags);
+}
+
+int panthor_pwr_init(struct panthor_device *ptdev)
+{
+	struct panthor_pwr *pwr;
+	int err, irq;
+
+	if (!panthor_hw_has_pwr_ctrl(ptdev))
+		return 0;
+
+	pwr = drmm_kzalloc(&ptdev->base, sizeof(*pwr), GFP_KERNEL);
+	if (!pwr)
+		return -ENOMEM;
+
+	spin_lock_init(&pwr->reqs_lock);
+	init_waitqueue_head(&pwr->reqs_acked);
+	ptdev->pwr = pwr;
+
+	irq = platform_get_irq_byname(to_platform_device(ptdev->base.dev), "gpu");
+	if (irq < 0)
+		return irq;
+
+	err = panthor_request_pwr_irq(ptdev, &pwr->irq, irq, PWR_INTERRUPTS_MASK);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int panthor_pwr_reset_soft(struct panthor_device *ptdev)
+{
+	if (!(gpu_read64(ptdev, PWR_STATUS) & PWR_STATUS_ALLOW_SOFT_RESET)) {
+		drm_err(&ptdev->base, "RESET_SOFT not allowed");
+		return -EOPNOTSUPP;
+	}
+
+	return panthor_pwr_reset(ptdev, PWR_COMMAND_RESET_SOFT);
+}
+
+void panthor_pwr_l2_power_off(struct panthor_device *ptdev)
+{
+	const u64 l2_allow_mask = PWR_STATUS_DOMAIN_ALLOWED(PWR_COMMAND_DOMAIN_L2);
+	const u64 pwr_status = gpu_read64(ptdev, PWR_STATUS);
+
+	/* Abort if L2 power off constraints are not satisfied */
+	if (!(pwr_status & l2_allow_mask)) {
+		drm_warn(&ptdev->base, "Power off L2 domain not allowed");
+		return;
+	}
+
+	/* It is expected that when halting the MCU, it would power down its
+	 * delegated domains. However, an unresponsive or hung MCU may not do
+	 * so, which is why we need to check and retract the domains back into
+	 * host control to be powered down in the right order before powering
+	 * down the L2.
+	 */
+	if (panthor_pwr_domain_force_off(ptdev, PWR_COMMAND_DOMAIN_TILER))
+		return;
+
+	if (panthor_pwr_domain_force_off(ptdev, PWR_COMMAND_DOMAIN_SHADER))
+		return;
+
+	panthor_pwr_domain_power_off(ptdev, PWR_COMMAND_DOMAIN_L2, ptdev->gpu_info.l2_present,
+				     PWR_TRANSITION_TIMEOUT_US);
+}
+
+int panthor_pwr_l2_power_on(struct panthor_device *ptdev)
+{
+	const u32 pwr_status = gpu_read64(ptdev, PWR_STATUS);
+	const u32 l2_allow_mask = PWR_STATUS_DOMAIN_ALLOWED(PWR_COMMAND_DOMAIN_L2);
+	int ret;
+
+	if ((pwr_status & l2_allow_mask) == 0) {
+		drm_warn(&ptdev->base, "Power on L2 domain not allowed");
+		return -EPERM;
+	}
+
+	ret = panthor_pwr_domain_power_on(ptdev, PWR_COMMAND_DOMAIN_L2, ptdev->gpu_info.l2_present,
+					  PWR_TRANSITION_TIMEOUT_US);
+	if (ret)
+		return ret;
+
+	/* Delegate control of the shader and tiler power domains to the MCU as
+	 * it can better manage which shader/tiler cores need to be powered up
+	 * or can be powered down based on currently running jobs.
+	 *
+	 * If the shader and tiler domains are already delegated to the MCU,
+	 * this call would just return early.
+	 */
+	return panthor_pwr_delegate_domains(ptdev);
+}
+
+void panthor_pwr_suspend(struct panthor_device *ptdev)
+{
+	if (!ptdev->pwr)
+		return;
+
+	panthor_pwr_irq_suspend(&ptdev->pwr->irq);
+}
+
+void panthor_pwr_resume(struct panthor_device *ptdev)
+{
+	if (!ptdev->pwr)
+		return;
+
+	panthor_pwr_irq_resume(&ptdev->pwr->irq, PWR_INTERRUPTS_MASK);
+}
diff --git a/drivers/gpu/drm/panthor/panthor_pwr.h b/drivers/gpu/drm/panthor/panthor_pwr.h
new file mode 100644
index 000000000000..adf1f6136abc
--- /dev/null
+++ b/drivers/gpu/drm/panthor/panthor_pwr.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2025 ARM Limited. All rights reserved. */
+
+#ifndef __PANTHOR_PWR_H__
+#define __PANTHOR_PWR_H__
+
+struct panthor_device;
+
+void panthor_pwr_unplug(struct panthor_device *ptdev);
+
+int panthor_pwr_init(struct panthor_device *ptdev);
+
+int panthor_pwr_reset_soft(struct panthor_device *ptdev);
+
+void panthor_pwr_l2_power_off(struct panthor_device *ptdev);
+
+int panthor_pwr_l2_power_on(struct panthor_device *ptdev);
+
+void panthor_pwr_suspend(struct panthor_device *ptdev);
+
+void panthor_pwr_resume(struct panthor_device *ptdev);
+
+#endif /* __PANTHOR_PWR_H__ */
diff --git a/drivers/gpu/drm/panthor/panthor_regs.h b/drivers/gpu/drm/panthor/panthor_regs.h
index 8fa69f33e911..08bf06c452d6 100644
--- a/drivers/gpu/drm/panthor/panthor_regs.h
+++ b/drivers/gpu/drm/panthor/panthor_regs.h
@@ -74,6 +74,7 @@
 
 #define GPU_FEATURES					0x60
 #define   GPU_FEATURES_RAY_INTERSECTION			BIT(2)
+#define   GPU_FEATURES_RAY_TRAVERSAL			BIT(5)
 
 #define GPU_TIMESTAMP_OFFSET				0x88
 #define GPU_CYCLE_COUNT					0x90
@@ -209,4 +210,82 @@
 #define CSF_DOORBELL(i)					(0x80000 + ((i) * 0x10000))
 #define CSF_GLB_DOORBELL_ID				0
 
+/* PWR Control registers */
+
+#define PWR_CONTROL_BASE				0x800
+#define PWR_CTRL_REG(x)					(PWR_CONTROL_BASE + (x))
+
+#define PWR_INT_RAWSTAT					PWR_CTRL_REG(0x0)
+#define PWR_INT_CLEAR					PWR_CTRL_REG(0x4)
+#define PWR_INT_MASK					PWR_CTRL_REG(0x8)
+#define PWR_INT_STAT					PWR_CTRL_REG(0xc)
+#define   PWR_IRQ_POWER_CHANGED_SINGLE			BIT(0)
+#define   PWR_IRQ_POWER_CHANGED_ALL			BIT(1)
+#define   PWR_IRQ_DELEGATION_CHANGED			BIT(2)
+#define   PWR_IRQ_RESET_COMPLETED			BIT(3)
+#define   PWR_IRQ_RETRACT_COMPLETED			BIT(4)
+#define   PWR_IRQ_INSPECT_COMPLETED			BIT(5)
+#define   PWR_IRQ_COMMAND_NOT_ALLOWED			BIT(30)
+#define   PWR_IRQ_COMMAND_INVALID			BIT(31)
+
+#define PWR_STATUS					PWR_CTRL_REG(0x20)
+#define   PWR_STATUS_ALLOW_L2				BIT_U64(0)
+#define   PWR_STATUS_ALLOW_TILER			BIT_U64(1)
+#define   PWR_STATUS_ALLOW_SHADER			BIT_U64(8)
+#define   PWR_STATUS_ALLOW_BASE				BIT_U64(14)
+#define   PWR_STATUS_ALLOW_STACK			BIT_U64(15)
+#define   PWR_STATUS_DOMAIN_ALLOWED(x)			BIT_U64(x)
+#define   PWR_STATUS_DELEGATED_L2			BIT_U64(16)
+#define   PWR_STATUS_DELEGATED_TILER			BIT_U64(17)
+#define   PWR_STATUS_DELEGATED_SHADER			BIT_U64(24)
+#define   PWR_STATUS_DELEGATED_BASE			BIT_U64(30)
+#define   PWR_STATUS_DELEGATED_STACK			BIT_U64(31)
+#define   PWR_STATUS_DELEGATED_SHIFT			16
+#define   PWR_STATUS_DOMAIN_DELEGATED(x)		BIT_U64((x) + PWR_STATUS_DELEGATED_SHIFT)
+#define   PWR_STATUS_ALLOW_SOFT_RESET			BIT_U64(33)
+#define   PWR_STATUS_ALLOW_FAST_RESET			BIT_U64(34)
+#define   PWR_STATUS_POWER_PENDING			BIT_U64(41)
+#define   PWR_STATUS_RESET_PENDING			BIT_U64(42)
+#define   PWR_STATUS_RETRACT_PENDING			BIT_U64(43)
+#define   PWR_STATUS_INSPECT_PENDING			BIT_U64(44)
+
+#define PWR_COMMAND					PWR_CTRL_REG(0x28)
+#define   PWR_COMMAND_POWER_UP				0x10
+#define   PWR_COMMAND_POWER_DOWN			0x11
+#define   PWR_COMMAND_DELEGATE				0x20
+#define   PWR_COMMAND_RETRACT				0x21
+#define   PWR_COMMAND_RESET_SOFT			0x31
+#define   PWR_COMMAND_RESET_FAST			0x32
+#define   PWR_COMMAND_INSPECT				0xF0
+#define   PWR_COMMAND_DOMAIN_L2				0
+#define   PWR_COMMAND_DOMAIN_TILER			1
+#define   PWR_COMMAND_DOMAIN_SHADER			8
+#define   PWR_COMMAND_DOMAIN_BASE			14
+#define   PWR_COMMAND_DOMAIN_STACK			15
+#define   PWR_COMMAND_SUBDOMAIN_RTU			BIT(0)
+#define   PWR_COMMAND_DEF(cmd, domain, subdomain)	\
+	(((subdomain) << 16) | ((domain) << 8) | (cmd))
+
+#define PWR_CMDARG					PWR_CTRL_REG(0x30)
+
+#define PWR_L2_PRESENT					PWR_CTRL_REG(0x100)
+#define PWR_L2_READY					PWR_CTRL_REG(0x108)
+#define PWR_L2_PWRTRANS					PWR_CTRL_REG(0x110)
+#define PWR_L2_PWRACTIVE				PWR_CTRL_REG(0x118)
+#define PWR_TILER_PRESENT				PWR_CTRL_REG(0x140)
+#define PWR_TILER_READY					PWR_CTRL_REG(0x148)
+#define PWR_TILER_PWRTRANS				PWR_CTRL_REG(0x150)
+#define PWR_TILER_PWRACTIVE				PWR_CTRL_REG(0x158)
+#define PWR_SHADER_PRESENT				PWR_CTRL_REG(0x200)
+#define PWR_SHADER_READY				PWR_CTRL_REG(0x208)
+#define PWR_SHADER_PWRTRANS				PWR_CTRL_REG(0x210)
+#define PWR_SHADER_PWRACTIVE				PWR_CTRL_REG(0x218)
+#define PWR_BASE_PRESENT				PWR_CTRL_REG(0x380)
+#define PWR_BASE_READY					PWR_CTRL_REG(0x388)
+#define PWR_BASE_PWRTRANS				PWR_CTRL_REG(0x390)
+#define PWR_BASE_PWRACTIVE				PWR_CTRL_REG(0x398)
+#define PWR_STACK_PRESENT				PWR_CTRL_REG(0x3c0)
+#define PWR_STACK_READY					PWR_CTRL_REG(0x3c8)
+#define PWR_STACK_PWRTRANS				PWR_CTRL_REG(0x3d0)
+
 #endif
diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
index e74ca071159d..b834123a6560 100644
--- a/drivers/gpu/drm/panthor/panthor_sched.c
+++ b/drivers/gpu/drm/panthor/panthor_sched.c
@@ -364,17 +364,20 @@ struct panthor_queue {
 	/** @name: DRM scheduler name for this queue. */
 	char *name;
 
-	/**
-	 * @remaining_time: Time remaining before the job timeout expires.
-	 *
-	 * The job timeout is suspended when the queue is not scheduled by the
-	 * FW. Every time we suspend the timer, we need to save the remaining
-	 * time so we can restore it later on.
-	 */
-	unsigned long remaining_time;
+	/** @timeout: Queue timeout related fields. */
+	struct {
+		/** @timeout.work: Work executed when a queue timeout occurs. */
+		struct delayed_work work;
 
-	/** @timeout_suspended: True if the job timeout was suspended. */
-	bool timeout_suspended;
+		/**
+		 * @timeout.remaining: Time remaining before a queue timeout.
+		 *
+		 * When the timer is running, this value is set to MAX_SCHEDULE_TIMEOUT.
+		 * When the timer is suspended, it's set to the time remaining when the
+		 * timer was suspended.
+		 */
+		unsigned long remaining;
+	} timeout;
 
 	/**
 	 * @doorbell_id: Doorbell assigned to this queue.
@@ -899,6 +902,10 @@ static void group_free_queue(struct panthor_group *group, struct panthor_queue *
 	if (IS_ERR_OR_NULL(queue))
 		return;
 
+	/* This should have been disabled before that point. */
+	drm_WARN_ON(&group->ptdev->base,
+		    disable_delayed_work_sync(&queue->timeout.work));
+
 	if (queue->entity.fence_context)
 		drm_sched_entity_destroy(&queue->entity);
 
@@ -1046,6 +1053,115 @@ group_unbind_locked(struct panthor_group *group)
 	return 0;
 }
 
+static bool
+group_is_idle(struct panthor_group *group)
+{
+	struct panthor_device *ptdev = group->ptdev;
+	u32 inactive_queues;
+
+	if (group->csg_id >= 0)
+		return ptdev->scheduler->csg_slots[group->csg_id].idle;
+
+	inactive_queues = group->idle_queues | group->blocked_queues;
+	return hweight32(inactive_queues) == group->queue_count;
+}
+
+static void
+queue_reset_timeout_locked(struct panthor_queue *queue)
+{
+	lockdep_assert_held(&queue->fence_ctx.lock);
+
+	if (queue->timeout.remaining != MAX_SCHEDULE_TIMEOUT) {
+		mod_delayed_work(queue->scheduler.timeout_wq,
+				 &queue->timeout.work,
+				 msecs_to_jiffies(JOB_TIMEOUT_MS));
+	}
+}
+
+static bool
+group_can_run(struct panthor_group *group)
+{
+	return group->state != PANTHOR_CS_GROUP_TERMINATED &&
+	       group->state != PANTHOR_CS_GROUP_UNKNOWN_STATE &&
+	       !group->destroyed && group->fatal_queues == 0 &&
+	       !group->timedout;
+}
+
+static bool
+queue_timeout_is_suspended(struct panthor_queue *queue)
+{
+	/* When running, the remaining time is set to MAX_SCHEDULE_TIMEOUT. */
+	return queue->timeout.remaining != MAX_SCHEDULE_TIMEOUT;
+}
+
+static void
+queue_suspend_timeout_locked(struct panthor_queue *queue)
+{
+	unsigned long qtimeout, now;
+	struct panthor_group *group;
+	struct panthor_job *job;
+	bool timer_was_active;
+
+	lockdep_assert_held(&queue->fence_ctx.lock);
+
+	/* Already suspended, nothing to do. */
+	if (queue_timeout_is_suspended(queue))
+		return;
+
+	job = list_first_entry_or_null(&queue->fence_ctx.in_flight_jobs,
+				       struct panthor_job, node);
+	group = job ? job->group : NULL;
+
+	/* If the queue is blocked and the group is idle, we want the timer to
+	 * keep running because the group can't be unblocked by other queues,
+	 * so it has to come from an external source, and we want to timebox
+	 * this external signalling.
+	 */
+	if (group && group_can_run(group) &&
+	    (group->blocked_queues & BIT(job->queue_idx)) &&
+	    group_is_idle(group))
+		return;
+
+	now = jiffies;
+	qtimeout = queue->timeout.work.timer.expires;
+
+	/* Cancel the timer. */
+	timer_was_active = cancel_delayed_work(&queue->timeout.work);
+	if (!timer_was_active || !job)
+		queue->timeout.remaining = msecs_to_jiffies(JOB_TIMEOUT_MS);
+	else if (time_after(qtimeout, now))
+		queue->timeout.remaining = qtimeout - now;
+	else
+		queue->timeout.remaining = 0;
+
+	if (WARN_ON_ONCE(queue->timeout.remaining > msecs_to_jiffies(JOB_TIMEOUT_MS)))
+		queue->timeout.remaining = msecs_to_jiffies(JOB_TIMEOUT_MS);
+}
+
+static void
+queue_suspend_timeout(struct panthor_queue *queue)
+{
+	spin_lock(&queue->fence_ctx.lock);
+	queue_suspend_timeout_locked(queue);
+	spin_unlock(&queue->fence_ctx.lock);
+}
+
+static void
+queue_resume_timeout(struct panthor_queue *queue)
+{
+	spin_lock(&queue->fence_ctx.lock);
+
+	if (queue_timeout_is_suspended(queue)) {
+		mod_delayed_work(queue->scheduler.timeout_wq,
+				 &queue->timeout.work,
+				 queue->timeout.remaining);
+
+		queue->timeout.remaining = MAX_SCHEDULE_TIMEOUT;
+	}
+
+	spin_unlock(&queue->fence_ctx.lock);
+}
+
 /**
  * cs_slot_prog_locked() - Program a queue slot
  * @ptdev: Device.
@@ -1084,10 +1200,8 @@ cs_slot_prog_locked(struct panthor_device *ptdev, u32 csg_id, u32 cs_id)
 			       CS_IDLE_EMPTY |
 			       CS_STATE_MASK |
 			       CS_EXTRACT_EVENT);
-	if (queue->iface.input->insert != queue->iface.input->extract && queue->timeout_suspended) {
-		drm_sched_resume_timeout(&queue->scheduler, queue->remaining_time);
-		queue->timeout_suspended = false;
-	}
+	if (queue->iface.input->insert != queue->iface.input->extract)
+		queue_resume_timeout(queue);
 }
 
 /**
@@ -1114,14 +1228,7 @@ cs_slot_reset_locked(struct panthor_device *ptdev, u32 csg_id, u32 cs_id)
 			       CS_STATE_STOP,
 			       CS_STATE_MASK);
 
-	/* If the queue is blocked, we want to keep the timeout running, so
-	 * we can detect unbounded waits and kill the group when that happens.
-	 */
-	if (!(group->blocked_queues & BIT(cs_id)) && !queue->timeout_suspended) {
-		queue->remaining_time = drm_sched_suspend_timeout(&queue->scheduler);
-		queue->timeout_suspended = true;
-		WARN_ON(queue->remaining_time > msecs_to_jiffies(JOB_TIMEOUT_MS));
-	}
+	queue_suspend_timeout(queue);
 
 	return 0;
 }
@@ -1140,11 +1247,13 @@ csg_slot_sync_priority_locked(struct panthor_device *ptdev, u32 csg_id)
 {
 	struct panthor_csg_slot *csg_slot = &ptdev->scheduler->csg_slots[csg_id];
 	struct panthor_fw_csg_iface *csg_iface;
+	u64 endpoint_req;
 
 	lockdep_assert_held(&ptdev->scheduler->lock);
 
 	csg_iface = panthor_fw_get_csg_iface(ptdev, csg_id);
-	csg_slot->priority = (csg_iface->input->endpoint_req & CSG_EP_REQ_PRIORITY_MASK) >> 28;
+	endpoint_req = panthor_fw_csg_endpoint_req_get(ptdev, csg_iface);
+	csg_slot->priority = CSG_EP_REQ_PRIORITY_GET(endpoint_req);
 }
 
 /**
@@ -1304,6 +1413,7 @@ csg_slot_prog_locked(struct panthor_device *ptdev, u32 csg_id, u32 priority)
 	struct panthor_csg_slot *csg_slot;
 	struct panthor_group *group;
 	u32 queue_mask = 0, i;
+	u64 endpoint_req;
 
 	lockdep_assert_held(&ptdev->scheduler->lock);
 
@@ -1330,10 +1440,12 @@ csg_slot_prog_locked(struct panthor_device *ptdev, u32 csg_id, u32 priority)
 	csg_iface->input->allow_compute = group->compute_core_mask;
 	csg_iface->input->allow_fragment = group->fragment_core_mask;
 	csg_iface->input->allow_other = group->tiler_core_mask;
-	csg_iface->input->endpoint_req = CSG_EP_REQ_COMPUTE(group->max_compute_cores) |
-					 CSG_EP_REQ_FRAGMENT(group->max_fragment_cores) |
-					 CSG_EP_REQ_TILER(group->max_tiler_cores) |
-					 CSG_EP_REQ_PRIORITY(priority);
+	endpoint_req = CSG_EP_REQ_COMPUTE(group->max_compute_cores) |
+		       CSG_EP_REQ_FRAGMENT(group->max_fragment_cores) |
+		       CSG_EP_REQ_TILER(group->max_tiler_cores) |
+		       CSG_EP_REQ_PRIORITY(priority);
+	panthor_fw_csg_endpoint_req_set(ptdev, csg_iface, endpoint_req);
+
 	csg_iface->input->config = panthor_vm_as(group->vm);
 
 	if (group->suspend_buf)
@@ -1916,28 +2028,6 @@ tick_ctx_is_full(const struct panthor_scheduler *sched,
 	return ctx->group_count == sched->csg_slot_count;
 }
 
-static bool
-group_is_idle(struct panthor_group *group)
-{
-	struct panthor_device *ptdev = group->ptdev;
-	u32 inactive_queues;
-
-	if (group->csg_id >= 0)
-		return ptdev->scheduler->csg_slots[group->csg_id].idle;
-
-	inactive_queues = group->idle_queues | group->blocked_queues;
-	return hweight32(inactive_queues) == group->queue_count;
-}
-
-static bool
-group_can_run(struct panthor_group *group)
-{
-	return group->state != PANTHOR_CS_GROUP_TERMINATED &&
-	       group->state != PANTHOR_CS_GROUP_UNKNOWN_STATE &&
-	       !group->destroyed && group->fatal_queues == 0 &&
-	       !group->timedout;
-}
-
 static void
 tick_ctx_pick_groups_from_list(const struct panthor_scheduler *sched,
 			       struct panthor_sched_tick_ctx *ctx,
@@ -2231,9 +2321,9 @@ tick_ctx_apply(struct panthor_scheduler *sched, struct panthor_sched_tick_ctx *c
 				continue;
 			}
 
-			panthor_fw_update_reqs(csg_iface, endpoint_req,
-					       CSG_EP_REQ_PRIORITY(new_csg_prio),
-					       CSG_EP_REQ_PRIORITY_MASK);
+			panthor_fw_csg_endpoint_req_update(ptdev, csg_iface,
+							   CSG_EP_REQ_PRIORITY(new_csg_prio),
+							   CSG_EP_REQ_PRIORITY_MASK);
 			csgs_upd_ctx_queue_reqs(ptdev, &upd_ctx, csg_id,
 						csg_iface->output->ack ^ CSG_ENDPOINT_CONFIG,
 						CSG_ENDPOINT_CONFIG);
@@ -2619,6 +2709,7 @@ static void group_schedule_locked(struct panthor_group *group, u32 queue_mask)
 static void queue_stop(struct panthor_queue *queue,
 		       struct panthor_job *bad_job)
 {
+	disable_delayed_work_sync(&queue->timeout.work);
 	drm_sched_stop(&queue->scheduler, bad_job ? &bad_job->base : NULL);
 }
 
@@ -2630,6 +2721,7 @@ static void queue_start(struct panthor_queue *queue)
 	list_for_each_entry(job, &queue->scheduler.pending_list, base.list)
 		job->base.s_fence->parent = dma_fence_get(job->done_fence);
 
+	enable_delayed_work(&queue->timeout.work);
 	drm_sched_start(&queue->scheduler, 0);
 }
 
@@ -2696,7 +2788,6 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 {
 	struct panthor_scheduler *sched = ptdev->scheduler;
 	struct panthor_csg_slots_upd_ctx upd_ctx;
-	struct panthor_group *group;
 	u32 suspended_slots;
 	u32 i;
 
@@ -2750,13 +2841,23 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 		while (slot_mask) {
 			u32 csg_id = ffs(slot_mask) - 1;
 			struct panthor_csg_slot *csg_slot = &sched->csg_slots[csg_id];
+			struct panthor_group *group = csg_slot->group;
 
 			/* Terminate command timedout, but the soft-reset will
 			 * automatically terminate all active groups, so let's
 			 * force the state to halted here.
 			 */
-			if (csg_slot->group->state != PANTHOR_CS_GROUP_TERMINATED)
-				csg_slot->group->state = PANTHOR_CS_GROUP_TERMINATED;
+			if (group->state != PANTHOR_CS_GROUP_TERMINATED) {
+				group->state = PANTHOR_CS_GROUP_TERMINATED;
+
+				/* Reset the queue slots manually if the termination
+				 * request failed.
+				 */
+				for (i = 0; i < group->queue_count; i++) {
+					if (group->queues[i])
+						cs_slot_reset_locked(ptdev, csg_id, i);
+				}
+			}
 			slot_mask &= ~BIT(csg_id);
 		}
 	}
@@ -2786,8 +2887,8 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 
 	for (i = 0; i < sched->csg_slot_count; i++) {
 		struct panthor_csg_slot *csg_slot = &sched->csg_slots[i];
+		struct panthor_group *group = csg_slot->group;
 
-		group = csg_slot->group;
 		if (!group)
 			continue;
 
@@ -2916,35 +3017,47 @@ void panthor_fdinfo_gather_group_samples(struct panthor_file *pfile)
 	xa_unlock(&gpool->xa);
 }
 
-static void group_sync_upd_work(struct work_struct *work)
+static bool queue_check_job_completion(struct panthor_queue *queue)
 {
-	struct panthor_group *group =
-		container_of(work, struct panthor_group, sync_upd_work);
+	struct panthor_syncobj_64b *syncobj = NULL;
 	struct panthor_job *job, *job_tmp;
+	bool cookie, progress = false;
 	LIST_HEAD(done_jobs);
-	u32 queue_idx;
-	bool cookie;
 
 	cookie = dma_fence_begin_signalling();
-	for (queue_idx = 0; queue_idx < group->queue_count; queue_idx++) {
-		struct panthor_queue *queue = group->queues[queue_idx];
-		struct panthor_syncobj_64b *syncobj;
+	spin_lock(&queue->fence_ctx.lock);
+	list_for_each_entry_safe(job, job_tmp, &queue->fence_ctx.in_flight_jobs, node) {
+		if (!syncobj) {
+			struct panthor_group *group = job->group;
 
-		if (!queue)
-			continue;
+			syncobj = group->syncobjs->kmap +
+				  (job->queue_idx * sizeof(*syncobj));
+		}
 
-		syncobj = group->syncobjs->kmap + (queue_idx * sizeof(*syncobj));
+		if (syncobj->seqno < job->done_fence->seqno)
+			break;
 
-		spin_lock(&queue->fence_ctx.lock);
-		list_for_each_entry_safe(job, job_tmp, &queue->fence_ctx.in_flight_jobs, node) {
-			if (syncobj->seqno < job->done_fence->seqno)
-				break;
+		list_move_tail(&job->node, &done_jobs);
+		dma_fence_signal_locked(job->done_fence);
+	}
 
-			list_move_tail(&job->node, &done_jobs);
-			dma_fence_signal_locked(job->done_fence);
-		}
-		spin_unlock(&queue->fence_ctx.lock);
+	if (list_empty(&queue->fence_ctx.in_flight_jobs)) {
+		/* If we have no job left, we cancel the timer, and reset remaining
+		 * time to its default so it can be restarted next time
+		 * queue_resume_timeout() is called.
+		 */
+		queue_suspend_timeout_locked(queue);
+
+		/* If there's no job pending, we consider it progress to avoid a
+		 * spurious timeout if the timeout handler and the sync update
+		 * handler raced.
+		 */
+		progress = true;
+	} else if (!list_empty(&done_jobs)) {
+		queue_reset_timeout_locked(queue);
+		progress = true;
 	}
+	spin_unlock(&queue->fence_ctx.lock);
 	dma_fence_end_signalling(cookie);
 
 	list_for_each_entry_safe(job, job_tmp, &done_jobs, node) {
@@ -2954,6 +3067,27 @@ static void group_sync_upd_work(struct work_struct *work)
 		panthor_job_put(&job->base);
 	}
 
+	return progress;
+}
+
+static void group_sync_upd_work(struct work_struct *work)
+{
+	struct panthor_group *group =
+		container_of(work, struct panthor_group, sync_upd_work);
+	u32 queue_idx;
+	bool cookie;
+
+	cookie = dma_fence_begin_signalling();
+	for (queue_idx = 0; queue_idx < group->queue_count; queue_idx++) {
+		struct panthor_queue *queue = group->queues[queue_idx];
+
+		if (!queue)
+			continue;
+
+		queue_check_job_completion(queue);
+	}
+	dma_fence_end_signalling(cookie);
+
 	group_put(group);
 }
 
@@ -3201,17 +3335,6 @@ queue_run_job(struct drm_sched_job *sched_job)
 	queue->iface.input->insert = job->ringbuf.end;
 
 	if (group->csg_id < 0) {
-		/* If the queue is blocked, we want to keep the timeout running, so we
-		 * can detect unbounded waits and kill the group when that happens.
-		 * Otherwise, we suspend the timeout so the time we spend waiting for
-		 * a CSG slot is not counted.
-		 */
-		if (!(group->blocked_queues & BIT(job->queue_idx)) &&
-		    !queue->timeout_suspended) {
-			queue->remaining_time = drm_sched_suspend_timeout(&queue->scheduler);
-			queue->timeout_suspended = true;
-		}
-
 		group_schedule_locked(group, BIT(job->queue_idx));
 	} else {
 		gpu_write(ptdev, CSF_DOORBELL(queue->doorbell_id), 1);
@@ -3220,6 +3343,7 @@ queue_run_job(struct drm_sched_job *sched_job)
 			pm_runtime_get(ptdev->base.dev);
 			sched->pm.has_ref = true;
 		}
+		queue_resume_timeout(queue);
 		panthor_devfreq_record_busy(sched->ptdev);
 	}
 
@@ -3269,7 +3393,6 @@ queue_timedout_job(struct drm_sched_job *sched_job)
 	mutex_unlock(&sched->lock);
 
 	queue_start(queue);
-
 	return DRM_GPU_SCHED_STAT_RESET;
 }
 
@@ -3312,6 +3435,17 @@ static u32 calc_profiling_ringbuf_num_slots(struct panthor_device *ptdev,
 	return DIV_ROUND_UP(cs_ringbuf_size, min_profiled_job_instrs * sizeof(u64));
 }
 
+static void queue_timeout_work(struct work_struct *work)
+{
+	struct panthor_queue *queue = container_of(work, struct panthor_queue,
+						   timeout.work.work);
+	bool progress;
+
+	progress = queue_check_job_completion(queue);
+	if (!progress)
+		drm_sched_fault(&queue->scheduler);
+}
+
 static struct panthor_queue *
 group_create_queue(struct panthor_group *group,
 		   const struct drm_panthor_queue_create *args,
@@ -3328,7 +3462,7 @@ group_create_queue(struct panthor_group *group,
 		 * their profiling status.
 		 */
 		.credit_limit = args->ringbuf_size / sizeof(u64),
-		.timeout = msecs_to_jiffies(JOB_TIMEOUT_MS),
+		.timeout = MAX_SCHEDULE_TIMEOUT,
 		.timeout_wq = group->ptdev->reset.wq,
 		.dev = group->ptdev->base.dev,
 	};
@@ -3350,6 +3484,8 @@ group_create_queue(struct panthor_group *group,
 	if (!queue)
 		return ERR_PTR(-ENOMEM);
 
+	queue->timeout.remaining = msecs_to_jiffies(JOB_TIMEOUT_MS);
+	INIT_DELAYED_WORK(&queue->timeout.work, queue_timeout_work);
 	queue->fence_ctx.id = dma_fence_context_alloc(1);
 	spin_lock_init(&queue->fence_ctx.lock);
 	INIT_LIST_HEAD(&queue->fence_ctx.in_flight_jobs);
diff --git a/drivers/gpu/drm/radeon/radeon_fbdev.c b/drivers/gpu/drm/radeon/radeon_fbdev.c
index c2cfe2d7915f..fd083aaa91bb 100644
--- a/drivers/gpu/drm/radeon/radeon_fbdev.c
+++ b/drivers/gpu/drm/radeon/radeon_fbdev.c
@@ -202,7 +202,7 @@ int radeon_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 	struct radeon_device *rdev = fb_helper->dev->dev_private;
 	const struct drm_format_info *format_info;
 	struct drm_mode_fb_cmd2 mode_cmd = { };
-	struct fb_info *info;
+	struct fb_info *info = fb_helper->info;
 	struct drm_gem_object *gobj;
 	struct radeon_bo *rbo;
 	struct drm_framebuffer *fb;
@@ -243,13 +243,6 @@ int radeon_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 	fb_helper->funcs = &radeon_fbdev_fb_helper_funcs;
 	fb_helper->fb = fb;
 
-	/* okay we have an object now allocate the framebuffer */
-	info = drm_fb_helper_alloc_info(fb_helper);
-	if (IS_ERR(info)) {
-		ret = PTR_ERR(info);
-		goto err_drm_framebuffer_unregister_private;
-	}
-
 	info->fbops = &radeon_fbdev_fb_ops;
 
 	/* radeon resume is fragile and needs a vt switch to help it along */
@@ -275,10 +268,6 @@ int radeon_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 
 	return 0;
 
-err_drm_framebuffer_unregister_private:
-	fb_helper->fb = NULL;
-	drm_framebuffer_unregister_private(fb);
-	drm_framebuffer_cleanup(fb);
 err_kfree:
 	kfree(fb);
 err_radeon_fbdev_destroy_pinned_object:
diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
index d30fef00c34c..fdab71d51e2a 100644
--- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
+++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
@@ -331,32 +331,29 @@ static int rockchip_dp_of_probe(struct rockchip_dp_device *dp)
 	struct device_node *np = dev->of_node;
 
 	dp->grf = syscon_regmap_lookup_by_phandle(np, "rockchip,grf");
-	if (IS_ERR(dp->grf)) {
-		DRM_DEV_ERROR(dev, "failed to get rockchip,grf property\n");
-		return PTR_ERR(dp->grf);
-	}
+	if (IS_ERR(dp->grf))
+		return dev_err_probe(dev, PTR_ERR(dp->grf),
+				     "failed to get rockchip,grf property\n");
 
 	dp->grfclk = devm_clk_get_optional(dev, "grf");
 	if (IS_ERR(dp->grfclk))
-		return dev_err_probe(dev, PTR_ERR(dp->grfclk), "failed to get grf clock\n");
+		return dev_err_probe(dev, PTR_ERR(dp->grfclk),
+				     "failed to get grf clock\n");
 
 	dp->pclk = devm_clk_get(dev, "pclk");
-	if (IS_ERR(dp->pclk)) {
-		DRM_DEV_ERROR(dev, "failed to get pclk property\n");
-		return PTR_ERR(dp->pclk);
-	}
+	if (IS_ERR(dp->pclk))
+		return dev_err_probe(dev, PTR_ERR(dp->pclk),
+				     "failed to get pclk property\n");
 
 	dp->rst = devm_reset_control_get(dev, "dp");
-	if (IS_ERR(dp->rst)) {
-		DRM_DEV_ERROR(dev, "failed to get dp reset control\n");
-		return PTR_ERR(dp->rst);
-	}
+	if (IS_ERR(dp->rst))
+		return dev_err_probe(dev, PTR_ERR(dp->rst),
+				     "failed to get dp reset control\n");
 
 	dp->apbrst = devm_reset_control_get_optional(dev, "apb");
-	if (IS_ERR(dp->apbrst)) {
-		DRM_DEV_ERROR(dev, "failed to get apb reset control\n");
-		return PTR_ERR(dp->apbrst);
-	}
+	if (IS_ERR(dp->apbrst))
+		return dev_err_probe(dev, PTR_ERR(dp->apbrst),
+				     "failed to get apb reset control\n");
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c
index 931343b072ad..c9fe6aa3e3e3 100644
--- a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/phy/phy.h>
+#include <linux/phy/phy-hdmi.h>
 #include <linux/regmap.h>
 #include <linux/workqueue.h>
 
@@ -38,21 +39,16 @@
 #define RK3576_HDMI_HDCP14_MEM_EN	BIT(15)
 
 #define RK3576_VO0_GRF_SOC_CON8		0x0020
-#define RK3576_COLOR_FORMAT_MASK	(0xf << 4)
-#define RK3576_COLOR_DEPTH_MASK		(0xf << 8)
-#define RK3576_RGB			(0 << 4)
-#define RK3576_YUV422			(0x1 << 4)
-#define RK3576_YUV444			(0x2 << 4)
-#define RK3576_YUV420			(0x3 << 4)
-#define RK3576_8BPC			(0x0 << 8)
-#define RK3576_10BPC			(0x6 << 8)
+#define RK3576_COLOR_DEPTH_MASK		GENMASK(11, 8)
+#define RK3576_8BPC			0x0
+#define RK3576_10BPC			0x6
+#define RK3576_COLOR_FORMAT_MASK	GENMASK(7, 4)
+#define RK3576_RGB			0x9
+#define RK3576_YUV422			0x1
+#define RK3576_YUV444			0x2
+#define RK3576_YUV420			0x3
 #define RK3576_CECIN_MASK		BIT(3)
 
-#define RK3576_VO0_GRF_SOC_CON12	0x0030
-#define RK3576_GRF_OSDA_DLYN		(0xf << 12)
-#define RK3576_GRF_OSDA_DIV		(0x7f << 1)
-#define RK3576_GRF_OSDA_DLY_EN		BIT(0)
-
 #define RK3576_VO0_GRF_SOC_CON14	0x0038
 #define RK3576_I2S_SEL_MASK		BIT(0)
 #define RK3576_SPDIF_SEL_MASK		BIT(1)
@@ -74,6 +70,12 @@
 #define RK3588_HDMI1_LEVEL_INT		BIT(24)
 #define RK3588_GRF_VO1_CON3		0x000c
 #define RK3588_GRF_VO1_CON6		0x0018
+#define RK3588_COLOR_DEPTH_MASK		GENMASK(7, 4)
+#define RK3588_8BPC			0x0
+#define RK3588_10BPC			0x6
+#define RK3588_COLOR_FORMAT_MASK	GENMASK(3, 0)
+#define RK3588_RGB			0x0
+#define RK3588_YUV420			0x3
 #define RK3588_SCLIN_MASK		BIT(9)
 #define RK3588_SDAIN_MASK		BIT(10)
 #define RK3588_MODE_MASK		BIT(11)
@@ -92,14 +94,16 @@ struct rockchip_hdmi_qp {
 	struct rockchip_encoder encoder;
 	struct dw_hdmi_qp *hdmi;
 	struct phy *phy;
-	struct gpio_desc *enable_gpio;
+	struct gpio_desc *frl_enable_gpio;
 	struct delayed_work hpd_work;
 	int port_id;
 	const struct rockchip_hdmi_qp_ctrl_ops *ctrl_ops;
+	unsigned long long tmds_char_rate;
 };
 
 struct rockchip_hdmi_qp_ctrl_ops {
 	void (*io_init)(struct rockchip_hdmi_qp *hdmi);
+	void (*enc_init)(struct rockchip_hdmi_qp *hdmi, struct rockchip_crtc_state *state);
 	irqreturn_t (*irq_callback)(int irq, void *dev_id);
 	irqreturn_t (*hardirq_callback)(int irq, void *dev_id);
 };
@@ -115,23 +119,15 @@ static void dw_hdmi_qp_rockchip_encoder_enable(struct drm_encoder *encoder)
 {
 	struct rockchip_hdmi_qp *hdmi = to_rockchip_hdmi_qp(encoder);
 	struct drm_crtc *crtc = encoder->crtc;
-	unsigned long long rate;
 
 	/* Unconditionally switch to TMDS as FRL is not yet supported */
-	gpiod_set_value(hdmi->enable_gpio, 1);
-
-	if (crtc && crtc->state) {
-		rate = drm_hdmi_compute_mode_clock(&crtc->state->adjusted_mode,
-						   8, HDMI_COLORSPACE_RGB);
-		/*
-		 * FIXME: Temporary workaround to pass pixel clock rate
-		 * to the PHY driver until phy_configure_opts_hdmi
-		 * becomes available in the PHY API. See also the related
-		 * comment in rk_hdptx_phy_power_on() from
-		 * drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
-		 */
-		phy_set_bus_width(hdmi->phy, div_u64(rate, 100));
-	}
+	gpiod_set_value(hdmi->frl_enable_gpio, 0);
+
+	if (!crtc || !crtc->state)
+		return;
+
+	if (hdmi->ctrl_ops->enc_init)
+		hdmi->ctrl_ops->enc_init(hdmi, to_rockchip_crtc_state(crtc->state));
 }
 
 static int
@@ -139,12 +135,29 @@ dw_hdmi_qp_rockchip_encoder_atomic_check(struct drm_encoder *encoder,
 					 struct drm_crtc_state *crtc_state,
 					 struct drm_connector_state *conn_state)
 {
+	struct rockchip_hdmi_qp *hdmi = to_rockchip_hdmi_qp(encoder);
 	struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc_state);
+	union phy_configure_opts phy_cfg = {};
+	int ret;
+
+	if (hdmi->tmds_char_rate == conn_state->hdmi.tmds_char_rate &&
+	    s->output_bpc == conn_state->hdmi.output_bpc)
+		return 0;
+
+	phy_cfg.hdmi.tmds_char_rate = conn_state->hdmi.tmds_char_rate;
+	phy_cfg.hdmi.bpc = conn_state->hdmi.output_bpc;
+
+	ret = phy_configure(hdmi->phy, &phy_cfg);
+	if (!ret) {
+		hdmi->tmds_char_rate = conn_state->hdmi.tmds_char_rate;
+		s->output_mode = ROCKCHIP_OUT_MODE_AAAA;
+		s->output_type = DRM_MODE_CONNECTOR_HDMIA;
+		s->output_bpc = conn_state->hdmi.output_bpc;
+	} else {
+		dev_err(hdmi->dev, "Failed to configure phy: %d\n", ret);
+	}
 
-	s->output_mode = ROCKCHIP_OUT_MODE_AAAA;
-	s->output_type = DRM_MODE_CONNECTOR_HDMIA;
-
-	return 0;
+	return ret;
 }
 
 static const struct
@@ -375,15 +388,45 @@ static void dw_hdmi_qp_rk3588_io_init(struct rockchip_hdmi_qp *hdmi)
 	regmap_write(hdmi->regmap, RK3588_GRF_SOC_CON2, val);
 }
 
+static void dw_hdmi_qp_rk3576_enc_init(struct rockchip_hdmi_qp *hdmi,
+				       struct rockchip_crtc_state *state)
+{
+	u32 val;
+
+	if (state->output_bpc == 10)
+		val = FIELD_PREP_WM16(RK3576_COLOR_DEPTH_MASK, RK3576_10BPC);
+	else
+		val = FIELD_PREP_WM16(RK3576_COLOR_DEPTH_MASK, RK3576_8BPC);
+
+	regmap_write(hdmi->vo_regmap, RK3576_VO0_GRF_SOC_CON8, val);
+}
+
+static void dw_hdmi_qp_rk3588_enc_init(struct rockchip_hdmi_qp *hdmi,
+				       struct rockchip_crtc_state *state)
+{
+	u32 val;
+
+	if (state->output_bpc == 10)
+		val = FIELD_PREP_WM16(RK3588_COLOR_DEPTH_MASK, RK3588_10BPC);
+	else
+		val = FIELD_PREP_WM16(RK3588_COLOR_DEPTH_MASK, RK3588_8BPC);
+
+	regmap_write(hdmi->vo_regmap,
+		     hdmi->port_id ? RK3588_GRF_VO1_CON6 : RK3588_GRF_VO1_CON3,
+		     val);
+}
+
 static const struct rockchip_hdmi_qp_ctrl_ops rk3576_hdmi_ctrl_ops = {
 	.io_init		= dw_hdmi_qp_rk3576_io_init,
-	.irq_callback	        = dw_hdmi_qp_rk3576_irq,
+	.enc_init		= dw_hdmi_qp_rk3576_enc_init,
+	.irq_callback		= dw_hdmi_qp_rk3576_irq,
 	.hardirq_callback	= dw_hdmi_qp_rk3576_hardirq,
 };
 
 static const struct rockchip_hdmi_qp_ctrl_ops rk3588_hdmi_ctrl_ops = {
 	.io_init		= dw_hdmi_qp_rk3588_io_init,
-	.irq_callback	        = dw_hdmi_qp_rk3588_irq,
+	.enc_init		= dw_hdmi_qp_rk3588_enc_init,
+	.irq_callback		= dw_hdmi_qp_rk3588_irq,
 	.hardirq_callback	= dw_hdmi_qp_rk3588_hardirq,
 };
 
@@ -476,6 +519,7 @@ static int dw_hdmi_qp_rockchip_bind(struct device *dev, struct device *master,
 
 	plat_data.phy_ops = cfg->phy_ops;
 	plat_data.phy_data = hdmi;
+	plat_data.max_bpc = 10;
 
 	encoder = &hdmi->encoder.encoder;
 	encoder->possible_crtcs = drm_of_find_possible_crtcs(drm, dev->of_node);
@@ -515,11 +559,11 @@ static int dw_hdmi_qp_rockchip_bind(struct device *dev, struct device *master,
 	plat_data.ref_clk_rate = clk_get_rate(ref_clk);
 	clk_put(ref_clk);
 
-	hdmi->enable_gpio = devm_gpiod_get_optional(hdmi->dev, "enable",
-						    GPIOD_OUT_HIGH);
-	if (IS_ERR(hdmi->enable_gpio))
-		return dev_err_probe(hdmi->dev, PTR_ERR(hdmi->enable_gpio),
-				     "Failed to request enable GPIO\n");
+	hdmi->frl_enable_gpio = devm_gpiod_get_optional(hdmi->dev, "frl-enable",
+							GPIOD_OUT_LOW);
+	if (IS_ERR(hdmi->frl_enable_gpio))
+		return dev_err_probe(hdmi->dev, PTR_ERR(hdmi->frl_enable_gpio),
+				     "Failed to request FRL enable GPIO\n");
 
 	hdmi->phy = devm_of_phy_get_by_index(dev, dev->of_node, 0);
 	if (IS_ERR(hdmi->phy))
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
index c5c6e2b5772d..3099408e9d05 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
@@ -97,6 +97,9 @@ void rockchip_drm_dma_init_device(struct drm_device *drm_dev,
 		private->iommu_dev = ERR_PTR(-ENODEV);
 	else if (!private->iommu_dev)
 		private->iommu_dev = dev;
+
+	if (!IS_ERR(private->iommu_dev))
+		drm_dev_set_dma_dev(drm_dev, private->iommu_dev);
 }
 
 static int rockchip_drm_init_iommu(struct drm_device *drm_dev)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index e979d5e02ff4..498df0ce4680 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -102,7 +102,7 @@ enum vop2_afbc_format {
 	VOP2_AFBC_FMT_INVALID = -1,
 };
 
-#define VOP2_MAX_DCLK_RATE		600000000
+#define VOP2_MAX_DCLK_RATE		600000000UL
 
 /*
  * bus-format types.
@@ -1743,36 +1743,42 @@ static void vop2_crtc_atomic_enable(struct drm_crtc *crtc,
 	 * Switch to HDMI PHY PLL as DCLK source for display modes up
 	 * to 4K@60Hz, if available, otherwise keep using the system CRU.
 	 */
-	if ((vop2->pll_hdmiphy0 || vop2->pll_hdmiphy1) && clock <= VOP2_MAX_DCLK_RATE) {
-		drm_for_each_encoder_mask(encoder, crtc->dev, crtc_state->encoder_mask) {
-			struct rockchip_encoder *rkencoder = to_rockchip_encoder(encoder);
-
-			if (rkencoder->crtc_endpoint_id == ROCKCHIP_VOP2_EP_HDMI0) {
-				if (!vop2->pll_hdmiphy0)
+	if (vop2->pll_hdmiphy0 || vop2->pll_hdmiphy1) {
+		unsigned long max_dclk = DIV_ROUND_CLOSEST_ULL(VOP2_MAX_DCLK_RATE * 8,
+							       vcstate->output_bpc);
+		if (clock <= max_dclk) {
+			drm_for_each_encoder_mask(encoder, crtc->dev, crtc_state->encoder_mask) {
+				struct rockchip_encoder *rkencoder = to_rockchip_encoder(encoder);
+
+				if (rkencoder->crtc_endpoint_id == ROCKCHIP_VOP2_EP_HDMI0) {
+					if (!vop2->pll_hdmiphy0)
+						break;
+
+					if (!vp->dclk_src)
+						vp->dclk_src = clk_get_parent(vp->dclk);
+
+					ret = clk_set_parent(vp->dclk, vop2->pll_hdmiphy0);
+					if (ret < 0)
+						drm_warn(vop2->drm,
+							 "Could not switch to HDMI0 PHY PLL: %d\n",
+							 ret);
 					break;
+				}
 
-				if (!vp->dclk_src)
-					vp->dclk_src = clk_get_parent(vp->dclk);
+				if (rkencoder->crtc_endpoint_id == ROCKCHIP_VOP2_EP_HDMI1) {
+					if (!vop2->pll_hdmiphy1)
+						break;
 
-				ret = clk_set_parent(vp->dclk, vop2->pll_hdmiphy0);
-				if (ret < 0)
-					drm_warn(vop2->drm,
-						 "Could not switch to HDMI0 PHY PLL: %d\n", ret);
-				break;
-			}
+					if (!vp->dclk_src)
+						vp->dclk_src = clk_get_parent(vp->dclk);
 
-			if (rkencoder->crtc_endpoint_id == ROCKCHIP_VOP2_EP_HDMI1) {
-				if (!vop2->pll_hdmiphy1)
+					ret = clk_set_parent(vp->dclk, vop2->pll_hdmiphy1);
+					if (ret < 0)
+						drm_warn(vop2->drm,
+							 "Could not switch to HDMI1 PHY PLL: %d\n",
+							 ret);
 					break;
-
-				if (!vp->dclk_src)
-					vp->dclk_src = clk_get_parent(vp->dclk);
-
-				ret = clk_set_parent(vp->dclk, vop2->pll_hdmiphy1);
-				if (ret < 0)
-					drm_warn(vop2->drm,
-						 "Could not switch to HDMI1 PHY PLL: %d\n", ret);
-				break;
+				}
 			}
 		}
 	}
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
index 38c49030c7ab..cd8380f0eddc 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
@@ -1369,6 +1369,25 @@ static const struct vop2_regs_dump rk3588_regs_dump[] = {
 	},
 };
 
+/*
+ * phys_id is used to identify a main window(Cluster Win/Smart Win, not
+ * include the sub win of a cluster or the multi area) that can do overlay
+ * in main overlay stage.
+ */
+static struct vop2_win *vop2_find_win_by_phys_id(struct vop2 *vop2, uint8_t phys_id)
+{
+	struct vop2_win *win;
+	int i;
+
+	for (i = 0; i < vop2->data->win_size; i++) {
+		win = &vop2->win[i];
+		if (win->data->phys_id == phys_id)
+			return win;
+	}
+
+	return NULL;
+}
+
 static unsigned long rk3568_set_intf_mux(struct vop2_video_port *vp, int id, u32 polflags)
 {
 	struct vop2 *vop2 = vp->vop2;
@@ -1842,15 +1861,31 @@ static void vop2_parse_alpha(struct vop2_alpha_config *alpha_config,
 	alpha->dst_alpha_ctrl.bits.factor_mode = ALPHA_SRC_INVERSE;
 }
 
-static int vop2_find_start_mixer_id_for_vp(struct vop2 *vop2, u8 port_id)
+static int vop2_find_start_mixer_id_for_vp(struct vop2_video_port *vp)
 {
-	struct vop2_video_port *vp;
-	int used_layer = 0;
+	struct vop2 *vop2 = vp->vop2;
+	struct vop2_win *win;
+	u32 layer_sel = vop2->old_layer_sel;
+	u32 used_layer = 0;
+	unsigned long win_mask = vp->win_mask;
+	unsigned long phys_id;
+	bool match;
 	int i;
 
-	for (i = 0; i < port_id; i++) {
-		vp = &vop2->vps[i];
-		used_layer += hweight32(vp->win_mask);
+	for (i = 0; i < 31; i += 4) {
+		match = false;
+		for_each_set_bit(phys_id, &win_mask, ROCKCHIP_VOP2_ESMART3) {
+			win = vop2_find_win_by_phys_id(vop2, phys_id);
+			if (win->data->layer_sel_id[vp->id] == ((layer_sel >> i) & 0xf)) {
+				match = true;
+				break;
+			}
+		}
+
+		if (!match)
+			used_layer += 1;
+		else
+			break;
 	}
 
 	return used_layer;
@@ -1935,7 +1970,7 @@ static void vop2_setup_alpha(struct vop2_video_port *vp)
 	u32 dst_global_alpha = DRM_BLEND_ALPHA_OPAQUE;
 
 	if (vop2->version <= VOP_VERSION_RK3588)
-		mixer_id = vop2_find_start_mixer_id_for_vp(vop2, vp->id);
+		mixer_id = vop2_find_start_mixer_id_for_vp(vp);
 	else
 		mixer_id = 0;
 
diff --git a/drivers/gpu/drm/tegra/Makefile b/drivers/gpu/drm/tegra/Makefile
index 6fc4b504e786..e399b40d64a1 100644
--- a/drivers/gpu/drm/tegra/Makefile
+++ b/drivers/gpu/drm/tegra/Makefile
@@ -25,6 +25,7 @@ tegra-drm-y := \
 	falcon.o \
 	vic.o \
 	nvdec.o \
+	nvjpg.o \
 	riscv.o
 
 tegra-drm-y += trace.o
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 4bf10c1bc373..1d18d43292dc 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -1384,6 +1384,7 @@ static const struct of_device_id host1x_drm_subdevs[] = {
 	{ .compatible = "nvidia,tegra210-sor1", },
 	{ .compatible = "nvidia,tegra210-vic", },
 	{ .compatible = "nvidia,tegra210-nvdec", },
+	{ .compatible = "nvidia,tegra210-nvjpg", },
 	{ .compatible = "nvidia,tegra186-display", },
 	{ .compatible = "nvidia,tegra186-dc", },
 	{ .compatible = "nvidia,tegra186-sor", },
@@ -1422,6 +1423,7 @@ static struct platform_driver * const drivers[] = {
 	&tegra_gr3d_driver,
 	&tegra_vic_driver,
 	&tegra_nvdec_driver,
+	&tegra_nvjpg_driver,
 };
 
 static int __init host1x_drm_init(void)
diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h
index 1dd3670f37db..ae68b03d8483 100644
--- a/drivers/gpu/drm/tegra/drm.h
+++ b/drivers/gpu/drm/tegra/drm.h
@@ -214,5 +214,6 @@ extern struct platform_driver tegra_gr2d_driver;
 extern struct platform_driver tegra_gr3d_driver;
 extern struct platform_driver tegra_vic_driver;
 extern struct platform_driver tegra_nvdec_driver;
+extern struct platform_driver tegra_nvjpg_driver;
 
 #endif /* HOST1X_DRM_H */
diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index ae7aeb8e90ef..ae13b7a6837c 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -546,12 +546,19 @@ static void tegra_dsi_configure(struct tegra_dsi *dsi, unsigned int pipe,
 		/* horizontal back porch */
 		hbp = (mode->htotal - mode->hsync_end) * mul / div;
 
-		if ((dsi->flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) == 0)
-			hbp += hsw;
-
 		/* horizontal front porch */
 		hfp = (mode->hsync_start - mode->hdisplay) * mul / div;
 
+		if (dsi->master || dsi->slave) {
+			hact /= 2;
+			hsw /= 2;
+			hbp /= 2;
+			hfp /= 2;
+		}
+
+		if ((dsi->flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) == 0)
+			hbp += hsw;
+
 		/* subtract packet overhead */
 		hsw -= 10;
 		hbp -= 14;
@@ -561,11 +568,6 @@ static void tegra_dsi_configure(struct tegra_dsi *dsi, unsigned int pipe,
 		tegra_dsi_writel(dsi, hact << 16 | hbp, DSI_PKT_LEN_2_3);
 		tegra_dsi_writel(dsi, hfp, DSI_PKT_LEN_4_5);
 		tegra_dsi_writel(dsi, 0x0f0f << 16, DSI_PKT_LEN_6_7);
-
-		/* set SOL delay (for non-burst mode only) */
-		tegra_dsi_writel(dsi, 8 * mul / div, DSI_SOL_DELAY);
-
-		/* TODO: implement ganged mode */
 	} else {
 		u16 bytes;
 
@@ -587,29 +589,28 @@ static void tegra_dsi_configure(struct tegra_dsi *dsi, unsigned int pipe,
 		value = MIPI_DCS_WRITE_MEMORY_START << 8 |
 			MIPI_DCS_WRITE_MEMORY_CONTINUE;
 		tegra_dsi_writel(dsi, value, DSI_DCS_CMDS);
+	}
 
-		/* set SOL delay */
-		if (dsi->master || dsi->slave) {
-			unsigned long delay, bclk, bclk_ganged;
-			unsigned int lanes = state->lanes;
-
-			/* SOL to valid, valid to FIFO and FIFO write delay */
-			delay = 4 + 4 + 2;
-			delay = DIV_ROUND_UP(delay * mul, div * lanes);
-			/* FIFO read delay */
-			delay = delay + 6;
-
-			bclk = DIV_ROUND_UP(mode->htotal * mul, div * lanes);
-			bclk_ganged = DIV_ROUND_UP(bclk * lanes / 2, lanes);
-			value = bclk - bclk_ganged + delay + 20;
-		} else {
-			/* TODO: revisit for non-ganged mode */
-			value = 8 * mul / div;
-		}
+	/* set SOL delay */
+	if (dsi->master || dsi->slave) {
+		unsigned long delay, bclk, bclk_ganged;
+		unsigned int lanes = state->lanes;
+
+		/* SOL to valid, valid to FIFO and FIFO write delay */
+		delay = 4 + 4 + 2;
+		delay = DIV_ROUND_UP(delay * mul, div * lanes);
+		/* FIFO read delay */
+		delay = delay + 6;
 
-		tegra_dsi_writel(dsi, value, DSI_SOL_DELAY);
+		bclk = DIV_ROUND_UP(mode->htotal * mul, div * lanes);
+		bclk_ganged = DIV_ROUND_UP(bclk * lanes / 2, lanes);
+		value = bclk - bclk_ganged + delay + 20;
+	} else {
+		value = 8 * mul / div;
 	}
 
+	tegra_dsi_writel(dsi, value, DSI_SOL_DELAY);
+
 	if (dsi->slave) {
 		tegra_dsi_configure(dsi->slave, pipe, mode);
 
diff --git a/drivers/gpu/drm/tegra/fbdev.c b/drivers/gpu/drm/tegra/fbdev.c
index 91aece6f34e0..8f40882aa76e 100644
--- a/drivers/gpu/drm/tegra/fbdev.c
+++ b/drivers/gpu/drm/tegra/fbdev.c
@@ -73,10 +73,10 @@ int tegra_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper,
 	struct tegra_drm *tegra = helper->dev->dev_private;
 	struct drm_device *drm = helper->dev;
 	struct drm_mode_fb_cmd2 cmd = { 0 };
+	struct fb_info *info = helper->info;
 	unsigned int bytes_per_pixel;
 	struct drm_framebuffer *fb;
 	unsigned long offset;
-	struct fb_info *info;
 	struct tegra_bo *bo;
 	size_t size;
 	int err;
@@ -97,13 +97,6 @@ int tegra_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper,
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
 
-	info = drm_fb_helper_alloc_info(helper);
-	if (IS_ERR(info)) {
-		dev_err(drm->dev, "failed to allocate framebuffer info\n");
-		drm_gem_object_put(&bo->gem);
-		return PTR_ERR(info);
-	}
-
 	fb = tegra_fb_alloc(drm,
 			    drm_get_format_info(drm, cmd.pixel_format, cmd.modifier[0]),
 			    &cmd, &bo, 1);
diff --git a/drivers/gpu/drm/tegra/nvjpg.c b/drivers/gpu/drm/tegra/nvjpg.c
new file mode 100644
index 000000000000..94503fd0d52d
--- /dev/null
+++ b/drivers/gpu/drm/tegra/nvjpg.c
@@ -0,0 +1,330 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/host1x.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#include "drm.h"
+#include "falcon.h"
+
+struct nvjpg_config {
+	const char *firmware;
+	unsigned int version;
+};
+
+struct nvjpg {
+	struct falcon falcon;
+
+	void __iomem *regs;
+	struct tegra_drm_client client;
+	struct device *dev;
+	struct clk *clk;
+
+	/* Platform configuration */
+	const struct nvjpg_config *config;
+};
+
+static inline struct nvjpg *to_nvjpg(struct tegra_drm_client *client)
+{
+	return container_of(client, struct nvjpg, client);
+}
+
+static int nvjpg_init(struct host1x_client *client)
+{
+	struct tegra_drm_client *drm = host1x_to_drm_client(client);
+	struct drm_device *dev = dev_get_drvdata(client->host);
+	struct tegra_drm *tegra = dev->dev_private;
+	struct nvjpg *nvjpg = to_nvjpg(drm);
+	int err;
+
+	err = host1x_client_iommu_attach(client);
+	if (err < 0 && err != -ENODEV) {
+		dev_err(nvjpg->dev, "failed to attach to domain: %d\n", err);
+		return err;
+	}
+
+	err = tegra_drm_register_client(tegra, drm);
+	if (err < 0)
+		goto detach;
+
+	/*
+	 * Inherit the DMA parameters (such as maximum segment size) from the
+	 * parent host1x device.
+	 */
+	client->dev->dma_parms = client->host->dma_parms;
+
+	return 0;
+
+detach:
+	host1x_client_iommu_detach(client);
+
+	return err;
+}
+
+static int nvjpg_exit(struct host1x_client *client)
+{
+	struct tegra_drm_client *drm = host1x_to_drm_client(client);
+	struct drm_device *dev = dev_get_drvdata(client->host);
+	struct tegra_drm *tegra = dev->dev_private;
+	struct nvjpg *nvjpg = to_nvjpg(drm);
+	int err;
+
+	/* avoid a dangling pointer just in case this disappears */
+	client->dev->dma_parms = NULL;
+
+	err = tegra_drm_unregister_client(tegra, drm);
+	if (err < 0)
+		return err;
+
+	pm_runtime_dont_use_autosuspend(client->dev);
+	pm_runtime_force_suspend(client->dev);
+
+	host1x_client_iommu_detach(client);
+
+	if (client->group) {
+		dma_unmap_single(nvjpg->dev, nvjpg->falcon.firmware.phys,
+				 nvjpg->falcon.firmware.size, DMA_TO_DEVICE);
+		tegra_drm_free(tegra, nvjpg->falcon.firmware.size,
+			       nvjpg->falcon.firmware.virt,
+			       nvjpg->falcon.firmware.iova);
+	} else {
+		dma_free_coherent(nvjpg->dev, nvjpg->falcon.firmware.size,
+				  nvjpg->falcon.firmware.virt,
+				  nvjpg->falcon.firmware.iova);
+	}
+
+	return 0;
+}
+
+static const struct host1x_client_ops nvjpg_client_ops = {
+	.init = nvjpg_init,
+	.exit = nvjpg_exit,
+};
+
+static int nvjpg_load_falcon_firmware(struct nvjpg *nvjpg)
+{
+	struct host1x_client *client = &nvjpg->client.base;
+	struct tegra_drm *tegra = nvjpg->client.drm;
+	dma_addr_t iova;
+	size_t size;
+	void *virt;
+	int err;
+
+	if (nvjpg->falcon.firmware.virt)
+		return 0;
+
+	err = falcon_read_firmware(&nvjpg->falcon, nvjpg->config->firmware);
+	if (err < 0)
+		return err;
+
+	size = nvjpg->falcon.firmware.size;
+
+	if (!client->group) {
+		virt = dma_alloc_coherent(nvjpg->dev, size, &iova, GFP_KERNEL);
+		if (!virt)
+			return -ENOMEM;
+	} else {
+		virt = tegra_drm_alloc(tegra, size, &iova);
+		if (IS_ERR(virt))
+			return PTR_ERR(virt);
+	}
+
+	nvjpg->falcon.firmware.virt = virt;
+	nvjpg->falcon.firmware.iova = iova;
+
+	err = falcon_load_firmware(&nvjpg->falcon);
+	if (err < 0)
+		goto cleanup;
+
+	/*
+	 * In this case we have received an IOVA from the shared domain, so we
+	 * need to make sure to get the physical address so that the DMA API
+	 * knows what memory pages to flush the cache for.
+	 */
+	if (client->group) {
+		dma_addr_t phys;
+
+		phys = dma_map_single(nvjpg->dev, virt, size, DMA_TO_DEVICE);
+
+		err = dma_mapping_error(nvjpg->dev, phys);
+		if (err < 0)
+			goto cleanup;
+
+		nvjpg->falcon.firmware.phys = phys;
+	}
+
+	return 0;
+
+cleanup:
+	if (!client->group)
+		dma_free_coherent(nvjpg->dev, size, virt, iova);
+	else
+		tegra_drm_free(tegra, size, virt, iova);
+
+	return err;
+}
+
+static __maybe_unused int nvjpg_runtime_resume(struct device *dev)
+{
+	struct nvjpg *nvjpg = dev_get_drvdata(dev);
+	int err;
+
+	err = clk_prepare_enable(nvjpg->clk);
+	if (err < 0)
+		return err;
+
+	usleep_range(20, 30);
+
+	err = nvjpg_load_falcon_firmware(nvjpg);
+	if (err < 0)
+		goto disable_clk;
+
+	err = falcon_boot(&nvjpg->falcon);
+	if (err < 0)
+		goto disable_clk;
+
+	return 0;
+
+disable_clk:
+	clk_disable_unprepare(nvjpg->clk);
+	return err;
+}
+
+static __maybe_unused int nvjpg_runtime_suspend(struct device *dev)
+{
+	struct nvjpg *nvjpg = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(nvjpg->clk);
+
+	return 0;
+}
+
+static int nvjpg_can_use_memory_ctx(struct tegra_drm_client *client, bool *supported)
+{
+	*supported = false;
+
+	return 0;
+}
+
+static const struct tegra_drm_client_ops nvjpg_ops = {
+	.get_streamid_offset = NULL,
+	.can_use_memory_ctx = nvjpg_can_use_memory_ctx,
+};
+
+#define NVIDIA_TEGRA_210_NVJPG_FIRMWARE "nvidia/tegra210/nvjpg.bin"
+
+static const struct nvjpg_config tegra210_nvjpg_config = {
+	.firmware = NVIDIA_TEGRA_210_NVJPG_FIRMWARE,
+	.version = 0x21,
+};
+
+static const struct of_device_id tegra_nvjpg_of_match[] = {
+	{ .compatible = "nvidia,tegra210-nvjpg", .data = &tegra210_nvjpg_config },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, tegra_nvjpg_of_match);
+
+static int nvjpg_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct nvjpg *nvjpg;
+	int err;
+
+	/* inherit DMA mask from host1x parent */
+	err = dma_coerce_mask_and_coherent(dev, *dev->parent->dma_mask);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to set DMA mask: %d\n", err);
+		return err;
+	}
+
+	nvjpg = devm_kzalloc(dev, sizeof(*nvjpg), GFP_KERNEL);
+	if (!nvjpg)
+		return -ENOMEM;
+
+	nvjpg->config = of_device_get_match_data(dev);
+
+	nvjpg->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(nvjpg->regs))
+		return PTR_ERR(nvjpg->regs);
+
+	nvjpg->clk = devm_clk_get(dev, "nvjpg");
+	if (IS_ERR(nvjpg->clk)) {
+		dev_err(&pdev->dev, "failed to get clock\n");
+		return PTR_ERR(nvjpg->clk);
+	}
+
+	err = clk_set_rate(nvjpg->clk, ULONG_MAX);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to set clock rate\n");
+		return err;
+	}
+
+	nvjpg->falcon.dev = dev;
+	nvjpg->falcon.regs = nvjpg->regs;
+
+	err = falcon_init(&nvjpg->falcon);
+	if (err < 0)
+		return err;
+
+	platform_set_drvdata(pdev, nvjpg);
+
+	INIT_LIST_HEAD(&nvjpg->client.base.list);
+	nvjpg->client.base.ops = &nvjpg_client_ops;
+	nvjpg->client.base.dev = dev;
+	nvjpg->client.base.class = HOST1X_CLASS_NVJPG;
+	nvjpg->dev = dev;
+
+	INIT_LIST_HEAD(&nvjpg->client.list);
+	nvjpg->client.version = nvjpg->config->version;
+	nvjpg->client.ops = &nvjpg_ops;
+
+	err = host1x_client_register(&nvjpg->client.base);
+	if (err < 0) {
+		dev_err(dev, "failed to register host1x client: %d\n", err);
+		goto exit_falcon;
+	}
+
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_autosuspend_delay(dev, 500);
+	devm_pm_runtime_enable(dev);
+
+	return 0;
+
+exit_falcon:
+	falcon_exit(&nvjpg->falcon);
+
+	return err;
+}
+
+static void nvjpg_remove(struct platform_device *pdev)
+{
+	struct nvjpg *nvjpg = platform_get_drvdata(pdev);
+
+	host1x_client_unregister(&nvjpg->client.base);
+	falcon_exit(&nvjpg->falcon);
+}
+
+static const struct dev_pm_ops nvjpg_pm_ops = {
+	RUNTIME_PM_OPS(nvjpg_runtime_suspend, nvjpg_runtime_resume, NULL)
+	SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
+};
+
+struct platform_driver tegra_nvjpg_driver = {
+	.driver = {
+		.name = "tegra-nvjpg",
+		.of_match_table = tegra_nvjpg_of_match,
+		.pm = &nvjpg_pm_ops
+	},
+	.probe = nvjpg_probe,
+	.remove = nvjpg_remove,
+};
+
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
+MODULE_FIRMWARE(NVIDIA_TEGRA_210_NVJPG_FIRMWARE);
+#endif
diff --git a/drivers/gpu/drm/tests/Makefile b/drivers/gpu/drm/tests/Makefile
index c0e952293ad0..87d5d5f9332a 100644
--- a/drivers/gpu/drm/tests/Makefile
+++ b/drivers/gpu/drm/tests/Makefile
@@ -24,6 +24,7 @@ obj-$(CONFIG_DRM_KUNIT_TEST) += \
 	drm_plane_helper_test.o \
 	drm_probe_helper_test.o \
 	drm_rect_test.o \
-	drm_sysfb_modeset_test.o
+	drm_sysfb_modeset_test.o \
+	drm_fixp_test.o
 
 CFLAGS_drm_mm_test.o := $(DISABLE_STRUCTLEAK_PLUGIN)
diff --git a/drivers/gpu/drm/tests/drm_fixp_test.c b/drivers/gpu/drm/tests/drm_fixp_test.c
new file mode 100644
index 000000000000..dd77fdedb2a9
--- /dev/null
+++ b/drivers/gpu/drm/tests/drm_fixp_test.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright 2022 Advanced Micro Devices, Inc.
+ */
+
+#include <kunit/test.h>
+#include <drm/drm_fixed.h>
+
+static void drm_test_sm2fixp(struct kunit *test)
+{
+	KUNIT_EXPECT_EQ(test, 0x7fffffffffffffffll, ((1ull << 63) - 1));
+
+	/* 1 */
+	KUNIT_EXPECT_EQ(test, drm_int2fixp(1), drm_sm2fixp(1ull << DRM_FIXED_POINT));
+
+	/* -1 */
+	KUNIT_EXPECT_EQ(test, drm_int2fixp(-1),
+			drm_sm2fixp((1ull << 63) | (1ull << DRM_FIXED_POINT)));
+
+	/* 0.5 */
+	KUNIT_EXPECT_EQ(test, drm_fixp_from_fraction(1, 2),
+			drm_sm2fixp(1ull << (DRM_FIXED_POINT - 1)));
+
+	/* -0.5 */
+	KUNIT_EXPECT_EQ(test, drm_fixp_from_fraction(-1, 2),
+			drm_sm2fixp((1ull << 63) | (1ull << (DRM_FIXED_POINT - 1))));
+}
+
+static void drm_test_int2fixp(struct kunit *test)
+{
+	/* 1 */
+	KUNIT_EXPECT_EQ(test, 1ll << 32, drm_int2fixp(1));
+
+	/* -1 */
+	KUNIT_EXPECT_EQ(test, -(1ll << 32), drm_int2fixp(-1));
+
+	/* 1 + (-1) = 0 */
+	KUNIT_EXPECT_EQ(test, 0, drm_int2fixp(1) + drm_int2fixp(-1));
+
+	/* 1 / 2 */
+	KUNIT_EXPECT_EQ(test, 1ll << 31, drm_fixp_from_fraction(1, 2));
+
+	/* -0.5 */
+	KUNIT_EXPECT_EQ(test, -(1ll << 31), drm_fixp_from_fraction(-1, 2));
+
+	/* (1 / 2) + (-1) = 0.5 */
+	KUNIT_EXPECT_EQ(test, 1ll << 31, drm_fixp_from_fraction(-1, 2) + drm_int2fixp(1));
+
+	/* (1 / 2) - 1) = 0.5 */
+	KUNIT_EXPECT_EQ(test, -(1ll << 31), drm_fixp_from_fraction(1, 2) + drm_int2fixp(-1));
+
+	/* (1 / 2) - 1) = 0.5 */
+	KUNIT_EXPECT_EQ(test, -(1ll << 31), drm_fixp_from_fraction(1, 2) - drm_int2fixp(1));
+}
+
+static struct kunit_case drm_fixp_tests[] = {
+	KUNIT_CASE(drm_test_int2fixp),
+	KUNIT_CASE(drm_test_sm2fixp),
+	{ }
+};
+
+static struct kunit_suite drm_fixp_test_suite = {
+	.name = "drm_fixp",
+	.test_cases = drm_fixp_tests,
+};
+
+kunit_test_suite(drm_fixp_test_suite);
+
+MODULE_AUTHOR("AMD");
+MODULE_LICENSE("Dual MIT/GPL");
+MODULE_DESCRIPTION("Unit tests for drm_fixed.h");
diff --git a/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c b/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c
index 17a570af296c..2eda87882e65 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c
@@ -652,7 +652,7 @@ static void ttm_bo_validate_move_fence_signaled(struct kunit *test)
 	int err;
 
 	man = ttm_manager_type(priv->ttm_dev, mem_type);
-	man->move = dma_fence_get_stub();
+	man->eviction_fences[0] = dma_fence_get_stub();
 
 	bo = ttm_bo_kunit_init(test, test->priv, size, NULL);
 	bo->type = bo_type;
@@ -669,7 +669,7 @@ static void ttm_bo_validate_move_fence_signaled(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, ctx.bytes_moved, size);
 
 	ttm_bo_fini(bo);
-	dma_fence_put(man->move);
+	dma_fence_put(man->eviction_fences[0]);
 }
 
 static const struct ttm_bo_validate_test_case ttm_bo_validate_wait_cases[] = {
@@ -733,9 +733,9 @@ static void ttm_bo_validate_move_fence_not_signaled(struct kunit *test)
 
 	spin_lock_init(&fence_lock);
 	man = ttm_manager_type(priv->ttm_dev, fst_mem);
-	man->move = alloc_mock_fence(test);
+	man->eviction_fences[0] = alloc_mock_fence(test);
 
-	task = kthread_create(threaded_fence_signal, man->move, "move-fence-signal");
+	task = kthread_create(threaded_fence_signal, man->eviction_fences[0], "move-fence-signal");
 	if (IS_ERR(task))
 		KUNIT_FAIL(test, "Couldn't create move fence signal task\n");
 
@@ -743,7 +743,8 @@ static void ttm_bo_validate_move_fence_not_signaled(struct kunit *test)
 	err = ttm_bo_validate(bo, placement_val, &ctx_val);
 	dma_resv_unlock(bo->base.resv);
 
-	dma_fence_wait_timeout(man->move, false, MAX_SCHEDULE_TIMEOUT);
+	dma_fence_wait_timeout(man->eviction_fences[0], false, MAX_SCHEDULE_TIMEOUT);
+	man->eviction_fences[0] = NULL;
 
 	KUNIT_EXPECT_EQ(test, err, 0);
 	KUNIT_EXPECT_EQ(test, ctx_val.bytes_moved, size);
diff --git a/drivers/gpu/drm/ttm/tests/ttm_resource_test.c b/drivers/gpu/drm/ttm/tests/ttm_resource_test.c
index e6ea2bd01f07..c0e4e35e0442 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_resource_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_resource_test.c
@@ -207,6 +207,7 @@ static void ttm_resource_manager_init_basic(struct kunit *test)
 	struct ttm_resource_test_priv *priv = test->priv;
 	struct ttm_resource_manager *man;
 	size_t size = SZ_16K;
+	int i;
 
 	man = kunit_kzalloc(test, sizeof(*man), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, man);
@@ -216,8 +217,8 @@ static void ttm_resource_manager_init_basic(struct kunit *test)
 	KUNIT_ASSERT_PTR_EQ(test, man->bdev, priv->devs->ttm_dev);
 	KUNIT_ASSERT_EQ(test, man->size, size);
 	KUNIT_ASSERT_EQ(test, man->usage, 0);
-	KUNIT_ASSERT_NULL(test, man->move);
-	KUNIT_ASSERT_NOT_NULL(test, &man->move_lock);
+	for (i = 0; i < TTM_NUM_MOVE_FENCES; i++)
+		KUNIT_ASSERT_NULL(test, man->eviction_fences[i]);
 
 	for (int i = 0; i < TTM_MAX_BO_PRIORITY; ++i)
 		KUNIT_ASSERT_TRUE(test, list_empty(&man->lru[i]));
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index c4e669686fd6..bd27607f8076 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -659,34 +659,35 @@ void ttm_bo_unpin(struct ttm_buffer_object *bo)
 EXPORT_SYMBOL(ttm_bo_unpin);
 
 /*
- * Add the last move fence to the BO as kernel dependency and reserve a new
- * fence slot.
+ * Add the pipelined eviction fencesto the BO as kernel dependency and reserve new
+ * fence slots.
  */
-static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
-				 struct ttm_resource_manager *man,
-				 bool no_wait_gpu)
+static int ttm_bo_add_pipelined_eviction_fences(struct ttm_buffer_object *bo,
+						struct ttm_resource_manager *man,
+						bool no_wait_gpu)
 {
 	struct dma_fence *fence;
-	int ret;
-
-	spin_lock(&man->move_lock);
-	fence = dma_fence_get(man->move);
-	spin_unlock(&man->move_lock);
+	int i;
 
-	if (!fence)
-		return 0;
+	spin_lock(&man->eviction_lock);
+	for (i = 0; i < TTM_NUM_MOVE_FENCES; i++) {
+		fence = man->eviction_fences[i];
+		if (!fence)
+			continue;
 
-	if (no_wait_gpu) {
-		ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY;
-		dma_fence_put(fence);
-		return ret;
+		if (no_wait_gpu) {
+			if (!dma_fence_is_signaled(fence)) {
+				spin_unlock(&man->eviction_lock);
+				return -EBUSY;
+			}
+		} else {
+			dma_resv_add_fence(bo->base.resv, fence, DMA_RESV_USAGE_KERNEL);
+		}
 	}
+	spin_unlock(&man->eviction_lock);
 
-	dma_resv_add_fence(bo->base.resv, fence, DMA_RESV_USAGE_KERNEL);
-
-	ret = dma_resv_reserve_fences(bo->base.resv, 1);
-	dma_fence_put(fence);
-	return ret;
+	/* TODO: this call should be removed. */
+	return dma_resv_reserve_fences(bo->base.resv, 1);
 }
 
 /**
@@ -719,7 +720,7 @@ static int ttm_bo_alloc_resource(struct ttm_buffer_object *bo,
 	int i, ret;
 
 	ticket = dma_resv_locking_ctx(bo->base.resv);
-	ret = dma_resv_reserve_fences(bo->base.resv, 1);
+	ret = dma_resv_reserve_fences(bo->base.resv, TTM_NUM_MOVE_FENCES);
 	if (unlikely(ret))
 		return ret;
 
@@ -758,7 +759,7 @@ static int ttm_bo_alloc_resource(struct ttm_buffer_object *bo,
 				return ret;
 		}
 
-		ret = ttm_bo_add_move_fence(bo, man, ctx->no_wait_gpu);
+		ret = ttm_bo_add_pipelined_eviction_fences(bo, man, ctx->no_wait_gpu);
 		if (unlikely(ret)) {
 			ttm_resource_free(bo, res);
 			if (ret == -EBUSY)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index acbbca9d5c92..2ff35d55e462 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -258,7 +258,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	ret = dma_resv_trylock(&fbo->base.base._resv);
 	WARN_ON(!ret);
 
-	ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1);
+	ret = dma_resv_reserve_fences(&fbo->base.base._resv, TTM_NUM_MOVE_FENCES);
 	if (ret) {
 		dma_resv_unlock(&fbo->base.base._resv);
 		kfree(fbo);
@@ -646,20 +646,44 @@ static void ttm_bo_move_pipeline_evict(struct ttm_buffer_object *bo,
 {
 	struct ttm_device *bdev = bo->bdev;
 	struct ttm_resource_manager *from;
+	struct dma_fence *tmp;
+	int i;
 
 	from = ttm_manager_type(bdev, bo->resource->mem_type);
 
 	/**
 	 * BO doesn't have a TTM we need to bind/unbind. Just remember
-	 * this eviction and free up the allocation
+	 * this eviction and free up the allocation.
+	 * The fence will be saved in the first free slot or in the slot
+	 * already used to store a fence from the same context. Since
+	 * drivers can't use more than TTM_NUM_MOVE_FENCES contexts for
+	 * evictions we should always find a slot to use.
 	 */
-	spin_lock(&from->move_lock);
-	if (!from->move || dma_fence_is_later(fence, from->move)) {
-		dma_fence_put(from->move);
-		from->move = dma_fence_get(fence);
+	spin_lock(&from->eviction_lock);
+	for (i = 0; i < TTM_NUM_MOVE_FENCES; i++) {
+		tmp = from->eviction_fences[i];
+		if (!tmp)
+			break;
+		if (fence->context != tmp->context)
+			continue;
+		if (dma_fence_is_later(fence, tmp)) {
+			dma_fence_put(tmp);
+			break;
+		}
+		goto unlock;
+	}
+	if (i < TTM_NUM_MOVE_FENCES) {
+		from->eviction_fences[i] = dma_fence_get(fence);
+	} else {
+		WARN(1, "not enough fence slots for all fence contexts");
+		spin_unlock(&from->eviction_lock);
+		dma_fence_wait(fence, false);
+		goto end;
 	}
-	spin_unlock(&from->move_lock);
 
+unlock:
+	spin_unlock(&from->eviction_lock);
+end:
 	ttm_resource_free(bo, &bo->resource);
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index 1a39c30f22fb..f5aa29dc6ec0 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -524,14 +524,15 @@ void ttm_resource_manager_init(struct ttm_resource_manager *man,
 {
 	unsigned i;
 
-	spin_lock_init(&man->move_lock);
 	man->bdev = bdev;
 	man->size = size;
 	man->usage = 0;
 
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i)
 		INIT_LIST_HEAD(&man->lru[i]);
-	man->move = NULL;
+	spin_lock_init(&man->eviction_lock);
+	for (i = 0; i < TTM_NUM_MOVE_FENCES; i++)
+		man->eviction_fences[i] = NULL;
 }
 EXPORT_SYMBOL(ttm_resource_manager_init);
 
@@ -552,7 +553,7 @@ int ttm_resource_manager_evict_all(struct ttm_device *bdev,
 		.no_wait_gpu = false,
 	};
 	struct dma_fence *fence;
-	int ret;
+	int ret, i;
 
 	do {
 		ret = ttm_bo_evict_first(bdev, man, &ctx);
@@ -562,18 +563,24 @@ int ttm_resource_manager_evict_all(struct ttm_device *bdev,
 	if (ret && ret != -ENOENT)
 		return ret;
 
-	spin_lock(&man->move_lock);
-	fence = dma_fence_get(man->move);
-	spin_unlock(&man->move_lock);
-
-	if (fence) {
-		ret = dma_fence_wait(fence, false);
-		dma_fence_put(fence);
-		if (ret)
-			return ret;
+	ret = 0;
+
+	spin_lock(&man->eviction_lock);
+	for (i = 0; i < TTM_NUM_MOVE_FENCES; i++) {
+		fence = man->eviction_fences[i];
+		if (fence && !dma_fence_is_signaled(fence)) {
+			dma_fence_get(fence);
+			spin_unlock(&man->eviction_lock);
+			ret = dma_fence_wait(fence, false);
+			dma_fence_put(fence);
+			if (ret)
+				return ret;
+			spin_lock(&man->eviction_lock);
+		}
 	}
+	spin_unlock(&man->eviction_lock);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(ttm_resource_manager_evict_all);
 
diff --git a/drivers/gpu/drm/vkms/Makefile b/drivers/gpu/drm/vkms/Makefile
index 939991fc8233..9bb264091c38 100644
--- a/drivers/gpu/drm/vkms/Makefile
+++ b/drivers/gpu/drm/vkms/Makefile
@@ -9,7 +9,9 @@ vkms-y := \
 	vkms_writeback.o \
 	vkms_connector.o \
 	vkms_config.o \
-	vkms_configfs.o
+	vkms_configfs.o \
+	vkms_colorop.o \
+	vkms_luts.o
 
 obj-$(CONFIG_DRM_VKMS) += vkms.o
 obj-$(CONFIG_DRM_VKMS_KUNIT_TEST) += tests/
diff --git a/drivers/gpu/drm/vkms/tests/Makefile b/drivers/gpu/drm/vkms/tests/Makefile
index 5750f0bd9d40..d4d9ba8d4c54 100644
--- a/drivers/gpu/drm/vkms/tests/Makefile
+++ b/drivers/gpu/drm/vkms/tests/Makefile
@@ -2,6 +2,7 @@
 
 vkms-kunit-tests-y := \
 	vkms_config_test.o \
-	vkms_format_test.o
+	vkms_format_test.o \
+	vkms_color_test.o
 
 obj-$(CONFIG_DRM_VKMS_KUNIT_TEST) += vkms-kunit-tests.o
diff --git a/drivers/gpu/drm/vkms/tests/vkms_color_test.c b/drivers/gpu/drm/vkms/tests/vkms_color_test.c
new file mode 100644
index 000000000000..1a1c7cac2f15
--- /dev/null
+++ b/drivers/gpu/drm/vkms/tests/vkms_color_test.c
@@ -0,0 +1,414 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <kunit/test.h>
+
+#include <drm/drm_fixed.h>
+#include <drm/drm_mode.h>
+#include "../vkms_composer.h"
+#include "../vkms_drv.h"
+#include "../vkms_luts.h"
+
+#define TEST_LUT_SIZE 16
+
+MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
+
+static struct drm_color_lut test_linear_array[TEST_LUT_SIZE] = {
+	{ 0x0, 0x0, 0x0, 0 },
+	{ 0x1111, 0x1111, 0x1111, 0 },
+	{ 0x2222, 0x2222, 0x2222, 0 },
+	{ 0x3333, 0x3333, 0x3333, 0 },
+	{ 0x4444, 0x4444, 0x4444, 0 },
+	{ 0x5555, 0x5555, 0x5555, 0 },
+	{ 0x6666, 0x6666, 0x6666, 0 },
+	{ 0x7777, 0x7777, 0x7777, 0 },
+	{ 0x8888, 0x8888, 0x8888, 0 },
+	{ 0x9999, 0x9999, 0x9999, 0 },
+	{ 0xaaaa, 0xaaaa, 0xaaaa, 0 },
+	{ 0xbbbb, 0xbbbb, 0xbbbb, 0 },
+	{ 0xcccc, 0xcccc, 0xcccc, 0 },
+	{ 0xdddd, 0xdddd, 0xdddd, 0 },
+	{ 0xeeee, 0xeeee, 0xeeee, 0 },
+	{ 0xffff, 0xffff, 0xffff, 0 },
+};
+
+/* lerp test parameters */
+struct vkms_color_test_lerp_params {
+	s64 t;
+	__u16 a;
+	__u16 b;
+	__u16 expected;
+};
+
+/* lerp test cases */
+static const struct vkms_color_test_lerp_params color_test_lerp_cases[] = {
+	/* Half-way round down */
+	{ 0x80000000 - 1, 0x0, 0x10, 0x8 },
+	{ 0x80000000 - 1, 0x1, 0x10, 0x8 },	/* Odd a */
+	{ 0x80000000 - 1, 0x1, 0xf, 0x8 },	/* Odd b */
+	{ 0x80000000 - 1, 0x10, 0x10, 0x10 },	/* b = a */
+	{ 0x80000000 - 1, 0x10, 0x11, 0x10 },	/* b = a + 1*/
+	/* Half-way round up */
+	{ 0x80000000, 0x0, 0x10, 0x8 },
+	{ 0x80000000, 0x1, 0x10, 0x9 },		/* Odd a */
+	{ 0x80000000, 0x1, 0xf, 0x8 },		/* Odd b */
+	{ 0x80000000, 0x10, 0x10, 0x10 },	/* b = a */
+	{ 0x80000000, 0x10, 0x11, 0x11 },	/* b = a + 1*/
+	/*  t = 0.0 */
+	{ 0x0, 0x0, 0x10, 0x0 },
+	{ 0x0, 0x1, 0x10, 0x1 },		/* Odd a */
+	{ 0x0, 0x1, 0xf, 0x1 },			/* Odd b */
+	{ 0x0, 0x10, 0x10, 0x10 },		/* b = a */
+	{ 0x0, 0x10, 0x11, 0x10 },		/* b = a + 1*/
+	/*  t = 1.0 */
+	{ 0x100000000, 0x0, 0x10, 0x10 },
+	{ 0x100000000, 0x1, 0x10, 0x10 },	/* Odd a */
+	{ 0x100000000, 0x1, 0xf, 0xf },		/* Odd b */
+	{ 0x100000000, 0x10, 0x10, 0x10 },	/* b = a */
+	{ 0x100000000, 0x10, 0x11, 0x11 },	/* b = a + 1*/
+	/*  t = 0.0 + 1 */
+	{ 0x0 + 1, 0x0, 0x10, 0x0 },
+	{ 0x0 + 1, 0x1, 0x10, 0x1 },		/* Odd a */
+	{ 0x0 + 1, 0x1, 0xf, 0x1 },		/* Odd b */
+	{ 0x0 + 1, 0x10, 0x10, 0x10 },		/* b = a */
+	{ 0x0 + 1, 0x10, 0x11, 0x10 },		/* b = a + 1*/
+	/*  t = 1.0 - 1 */
+	{ 0x100000000 - 1, 0x0, 0x10, 0x10 },
+	{ 0x100000000 - 1, 0x1, 0x10, 0x10 },	/* Odd a */
+	{ 0x100000000 - 1, 0x1, 0xf, 0xf },	/* Odd b */
+	{ 0x100000000 - 1, 0x10, 0x10, 0x10 },	/* b = a */
+	{ 0x100000000 - 1, 0x10, 0x11, 0x11 },	/* b = a + 1*/
+	/*  t chosen to verify the flipping point of result a (or b) to a+1 (or b-1) */
+	{ 0x80000000 - 1, 0x0, 0x1, 0x0 },
+	{ 0x80000000, 0x0, 0x1, 0x1 },
+};
+
+static const struct vkms_color_lut test_linear_lut = {
+	.base = test_linear_array,
+	.lut_length = TEST_LUT_SIZE,
+	.channel_value2index_ratio = 0xf000fll
+};
+
+static void vkms_color_test_get_lut_index(struct kunit *test)
+{
+	s64 lut_index;
+	int i;
+
+	lut_index = get_lut_index(&test_linear_lut, test_linear_array[0].red);
+	KUNIT_EXPECT_EQ(test, drm_fixp2int(lut_index), 0);
+
+	for (i = 0; i < TEST_LUT_SIZE; i++) {
+		lut_index = get_lut_index(&test_linear_lut, test_linear_array[i].red);
+		KUNIT_EXPECT_EQ(test, drm_fixp2int_ceil(lut_index), i);
+	}
+
+	KUNIT_EXPECT_EQ(test, drm_fixp2int(get_lut_index(&srgb_eotf, 0x0)), 0x0);
+	KUNIT_EXPECT_EQ(test, drm_fixp2int_ceil(get_lut_index(&srgb_eotf, 0x0)), 0x0);
+	KUNIT_EXPECT_EQ(test, drm_fixp2int_ceil(get_lut_index(&srgb_eotf, 0x101)), 0x1);
+	KUNIT_EXPECT_EQ(test, drm_fixp2int_ceil(get_lut_index(&srgb_eotf, 0x202)), 0x2);
+
+	KUNIT_EXPECT_EQ(test, drm_fixp2int(get_lut_index(&srgb_inv_eotf, 0x0)), 0x0);
+	KUNIT_EXPECT_EQ(test, drm_fixp2int_ceil(get_lut_index(&srgb_inv_eotf, 0x0)), 0x0);
+	KUNIT_EXPECT_EQ(test, drm_fixp2int_ceil(get_lut_index(&srgb_inv_eotf, 0x101)), 0x1);
+	KUNIT_EXPECT_EQ(test, drm_fixp2int_ceil(get_lut_index(&srgb_inv_eotf, 0x202)), 0x2);
+
+	KUNIT_EXPECT_EQ(test, drm_fixp2int_ceil(get_lut_index(&srgb_eotf, 0xfefe)), 0xfe);
+	KUNIT_EXPECT_EQ(test, drm_fixp2int_ceil(get_lut_index(&srgb_eotf, 0xffff)), 0xff);
+}
+
+static void vkms_color_test_lerp(struct kunit *test)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(color_test_lerp_cases); i++) {
+		const struct vkms_color_test_lerp_params *params = &color_test_lerp_cases[i];
+
+		KUNIT_EXPECT_EQ(test, lerp_u16(params->a, params->b, params->t), params->expected);
+	}
+}
+
+static void vkms_color_test_linear(struct kunit *test)
+{
+	for (int i = 0; i < LUT_SIZE; i++) {
+		int linear = apply_lut_to_channel_value(&linear_eotf, i * 0x101, LUT_RED);
+
+		KUNIT_EXPECT_EQ(test, DIV_ROUND_CLOSEST(linear, 0x101), i);
+	}
+}
+
+static void vkms_color_srgb_inv_srgb(struct kunit *test)
+{
+	u16 srgb, final;
+
+	for (int i = 0; i < LUT_SIZE; i++) {
+		srgb = apply_lut_to_channel_value(&srgb_eotf, i * 0x101, LUT_RED);
+		final = apply_lut_to_channel_value(&srgb_inv_eotf, srgb, LUT_RED);
+
+		KUNIT_EXPECT_GE(test, final / 0x101, i - 1);
+		KUNIT_EXPECT_LE(test, final / 0x101, i + 1);
+	}
+}
+
+#define FIXPT_HALF        (DRM_FIXED_ONE >> 1)
+#define FIXPT_QUARTER     (DRM_FIXED_ONE >> 2)
+
+static const struct drm_color_ctm_3x4 test_matrix_3x4_50_desat = { {
+	FIXPT_HALF, FIXPT_QUARTER, FIXPT_QUARTER, 0,
+	FIXPT_QUARTER, FIXPT_HALF, FIXPT_QUARTER, 0,
+	FIXPT_QUARTER, FIXPT_QUARTER, FIXPT_HALF, 0
+} };
+
+static void vkms_color_ctm_3x4_50_desat(struct kunit *test)
+{
+	struct pixel_argb_s32 ref, out;
+
+	/* full white */
+	ref.a = 0xffff;
+	ref.r = 0xffff;
+	ref.g = 0xffff;
+	ref.b = 0xffff;
+
+	memcpy(&out, &ref, sizeof(out));
+	apply_3x4_matrix(&out, &test_matrix_3x4_50_desat);
+
+	KUNIT_EXPECT_MEMEQ(test, &ref, &out, sizeof(out));
+
+	/* full black */
+	ref.a = 0xffff;
+	ref.r = 0x0;
+	ref.g = 0x0;
+	ref.b = 0x0;
+
+	memcpy(&out, &ref, sizeof(out));
+	apply_3x4_matrix(&out, &test_matrix_3x4_50_desat);
+
+	KUNIT_EXPECT_MEMEQ(test, &ref, &out, sizeof(out));
+
+	/* 50% grey */
+	ref.a = 0xffff;
+	ref.r = 0x8000;
+	ref.g = 0x8000;
+	ref.b = 0x8000;
+
+	memcpy(&out, &ref, sizeof(out));
+	apply_3x4_matrix(&out, &test_matrix_3x4_50_desat);
+
+	KUNIT_EXPECT_MEMEQ(test, &ref, &out, sizeof(out));
+
+	/* full red to 50% desat */
+	ref.a = 0xffff;
+	ref.r = 0x8000;
+	ref.g = 0x4000;
+	ref.b = 0x4000;
+
+	out.a = 0xffff;
+	out.r = 0xffff;
+	out.g = 0x0;
+	out.b = 0x0;
+
+	apply_3x4_matrix(&out, &test_matrix_3x4_50_desat);
+
+	KUNIT_EXPECT_MEMEQ(test, &ref, &out, sizeof(out));
+}
+
+/*
+ * BT.709 encoding matrix
+ *
+ * Values printed from within IGT when converting
+ * igt_matrix_3x4_bt709_enc to the fixed-point format expected
+ * by DRM/KMS.
+ */
+static const struct drm_color_ctm_3x4 test_matrix_3x4_bt709_enc = { {
+	0x00000000366cf400ull, 0x00000000b7175900ull, 0x0000000127bb300ull, 0,
+	0x800000001993b3a0ull, 0x800000005609fe80ull, 0x000000006f9db200ull, 0,
+	0x000000009d70a400ull, 0x800000008f011100ull, 0x800000000e6f9330ull, 0
+} };
+
+static void vkms_color_ctm_3x4_bt709(struct kunit *test)
+{
+	struct pixel_argb_s32 out;
+
+	/* full white to bt709 */
+	out.a = 0xffff;
+	out.r = 0xffff;
+	out.g = 0xffff;
+	out.b = 0xffff;
+
+	apply_3x4_matrix(&out, &test_matrix_3x4_bt709_enc);
+
+	/* Y 255 */
+	KUNIT_EXPECT_GT(test, out.r, 0xfe00);
+	KUNIT_EXPECT_LT(test, out.r, 0x10000);
+
+	/* U 0 */
+	KUNIT_EXPECT_LT(test, out.g, 0x0100);
+
+	/* V 0 */
+	KUNIT_EXPECT_LT(test, out.b, 0x0100);
+
+	/* full black to bt709 */
+	out.a = 0xffff;
+	out.r = 0x0;
+	out.g = 0x0;
+	out.b = 0x0;
+
+	apply_3x4_matrix(&out, &test_matrix_3x4_bt709_enc);
+
+	/* Y 0 */
+	KUNIT_EXPECT_LT(test, out.r, 0x100);
+
+	/* U 0 */
+	KUNIT_EXPECT_LT(test, out.g, 0x0100);
+
+	/* V 0 */
+	KUNIT_EXPECT_LT(test, out.b, 0x0100);
+
+	/* gray to bt709 */
+	out.a = 0xffff;
+	out.r = 0x7fff;
+	out.g = 0x7fff;
+	out.b = 0x7fff;
+
+	apply_3x4_matrix(&out, &test_matrix_3x4_bt709_enc);
+
+	/* Y 127 */
+	KUNIT_EXPECT_GT(test, out.r, 0x7e00);
+	KUNIT_EXPECT_LT(test, out.r, 0x8000);
+
+	/* U 0 */
+	KUNIT_EXPECT_LT(test, out.g, 0x0100);
+
+	/* V 0 */
+	KUNIT_EXPECT_LT(test, out.b, 0x0100);
+
+	/* == red 255 - bt709 enc == */
+	out.a = 0xffff;
+	out.r = 0xffff;
+	out.g = 0x0;
+	out.b = 0x0;
+
+	apply_3x4_matrix(&out, &test_matrix_3x4_bt709_enc);
+
+	/* Y 54 */
+	KUNIT_EXPECT_GT(test, out.r, 0x3500);
+	KUNIT_EXPECT_LT(test, out.r, 0x3700);
+
+	/* U 0 */
+	KUNIT_EXPECT_LT(test, out.g, 0x0100);
+
+	/* V 157 */
+	KUNIT_EXPECT_GT(test, out.b, 0x9C00);
+	KUNIT_EXPECT_LT(test, out.b, 0x9E00);
+
+	/* == green 255 - bt709 enc == */
+	out.a = 0xffff;
+	out.r = 0x0;
+	out.g = 0xffff;
+	out.b = 0x0;
+
+	apply_3x4_matrix(&out, &test_matrix_3x4_bt709_enc);
+
+	/* Y 182 */
+	KUNIT_EXPECT_GT(test, out.r, 0xB500);
+	KUNIT_EXPECT_LT(test, out.r, 0xB780); /* laxed by half*/
+
+	/* U 0 */
+	KUNIT_EXPECT_LT(test, out.g, 0x0100);
+
+	/* V 0 */
+	KUNIT_EXPECT_LT(test, out.b, 0x0100);
+
+	/* == blue 255 - bt709 enc == */
+	out.a = 0xffff;
+	out.r = 0x0;
+	out.g = 0x0;
+	out.b = 0xffff;
+
+	apply_3x4_matrix(&out, &test_matrix_3x4_bt709_enc);
+
+	/* Y 18 */
+	KUNIT_EXPECT_GT(test, out.r, 0x1100);
+	KUNIT_EXPECT_LT(test, out.r, 0x1300);
+
+	/* U 111 */
+	KUNIT_EXPECT_GT(test, out.g, 0x6E00);
+	KUNIT_EXPECT_LT(test, out.g, 0x7000);
+
+	/* V 0 */
+	KUNIT_EXPECT_LT(test, out.b, 0x0100);
+
+	/* == red 140 - bt709 enc == */
+	out.a = 0xffff;
+	out.r = 0x8c8c;
+	out.g = 0x0;
+	out.b = 0x0;
+
+	apply_3x4_matrix(&out, &test_matrix_3x4_bt709_enc);
+
+	/* Y 30 */
+	KUNIT_EXPECT_GT(test, out.r, 0x1D00);
+	KUNIT_EXPECT_LT(test, out.r, 0x1F00);
+
+	/* U 0 */
+	KUNIT_EXPECT_LT(test, out.g, 0x100);
+
+	/* V 87 */
+	KUNIT_EXPECT_GT(test, out.b, 0x5600);
+	KUNIT_EXPECT_LT(test, out.b, 0x5800);
+
+	/* == green 140 - bt709 enc == */
+	out.a = 0xffff;
+	out.r = 0x0;
+	out.g = 0x8c8c;
+	out.b = 0x0;
+
+	apply_3x4_matrix(&out, &test_matrix_3x4_bt709_enc);
+
+	/* Y 30 */
+	KUNIT_EXPECT_GT(test, out.r, 0x6400);
+	KUNIT_EXPECT_LT(test, out.r, 0x6600);
+
+	/* U 0 */
+	KUNIT_EXPECT_LT(test, out.g, 0x100);
+
+	/* V 0 */
+	KUNIT_EXPECT_LT(test, out.b, 0x100);
+
+	/* == blue 140 - bt709 enc == */
+	out.a = 0xffff;
+	out.r = 0x0;
+	out.g = 0x0;
+	out.b = 0x8c8c;
+
+	apply_3x4_matrix(&out, &test_matrix_3x4_bt709_enc);
+
+	/* Y 30 */
+	KUNIT_EXPECT_GT(test, out.r, 0x900);
+	KUNIT_EXPECT_LT(test, out.r, 0xB00);
+
+	/* U 61 */
+	KUNIT_EXPECT_GT(test, out.g, 0x3C00);
+	KUNIT_EXPECT_LT(test, out.g, 0x3E00);
+
+	/* V 0 */
+	KUNIT_EXPECT_LT(test, out.b, 0x100);
+}
+
+static struct kunit_case vkms_color_test_cases[] = {
+	KUNIT_CASE(vkms_color_test_get_lut_index),
+	KUNIT_CASE(vkms_color_test_lerp),
+	KUNIT_CASE(vkms_color_test_linear),
+	KUNIT_CASE(vkms_color_srgb_inv_srgb),
+	KUNIT_CASE(vkms_color_ctm_3x4_50_desat),
+	KUNIT_CASE(vkms_color_ctm_3x4_bt709),
+	{}
+};
+
+static struct kunit_suite vkms_color_test_suite = {
+	.name = "vkms-color",
+	.test_cases = vkms_color_test_cases,
+};
+
+kunit_test_suite(vkms_color_test_suite);
+
+MODULE_DESCRIPTION("Kunit test for VKMS LUT handling");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/vkms/tests/vkms_config_test.c b/drivers/gpu/drm/vkms/tests/vkms_config_test.c
index d75a6252e4d2..1e4ea1863420 100644
--- a/drivers/gpu/drm/vkms/tests/vkms_config_test.c
+++ b/drivers/gpu/drm/vkms/tests/vkms_config_test.c
@@ -83,6 +83,7 @@ struct default_config_case {
 	bool enable_cursor;
 	bool enable_writeback;
 	bool enable_overlay;
+	bool enable_plane_pipeline;
 };
 
 static void vkms_config_test_empty_config(struct kunit *test)
@@ -108,14 +109,22 @@ static void vkms_config_test_empty_config(struct kunit *test)
 }
 
 static struct default_config_case default_config_cases[] = {
-	{ false, false, false },
-	{ true, false, false },
-	{ true, true, false },
-	{ true, false, true },
-	{ false, true, false },
-	{ false, true, true },
-	{ false, false, true },
-	{ true, true, true },
+	{ false, false, false, false },
+	{ true, false, false, false },
+	{ true, true, false, false },
+	{ true, false, true, false },
+	{ false, true, false, false },
+	{ false, true, true, false },
+	{ false, false, true, false },
+	{ true, true, true, false },
+	{ false, false, false, true },
+	{ true, false, false, true },
+	{ true, true, false, true },
+	{ true, false, true, true },
+	{ false, true, false, true },
+	{ false, true, true, true },
+	{ false, false, true, true },
+	{ true, true, true, true },
 };
 
 KUNIT_ARRAY_PARAM(default_config, default_config_cases, NULL);
@@ -132,11 +141,15 @@ static void vkms_config_test_default_config(struct kunit *test)
 
 	config = vkms_config_default_create(params->enable_cursor,
 					    params->enable_writeback,
-					    params->enable_overlay);
+					    params->enable_overlay,
+					    params->enable_plane_pipeline);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, config);
 
 	/* Planes */
 	vkms_config_for_each_plane(config, plane_cfg) {
+		KUNIT_EXPECT_EQ(test,
+				vkms_config_plane_get_default_pipeline(plane_cfg),
+				params->enable_plane_pipeline);
 		switch (vkms_config_plane_get_type(plane_cfg)) {
 		case DRM_PLANE_TYPE_PRIMARY:
 			n_primaries++;
@@ -368,7 +381,7 @@ static void vkms_config_test_invalid_plane_number(struct kunit *test)
 	struct vkms_config_plane *plane_cfg;
 	int n;
 
-	config = vkms_config_default_create(false, false, false);
+	config = vkms_config_default_create(false, false, false, false);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, config);
 
 	/* Invalid: No planes */
@@ -393,7 +406,7 @@ static void vkms_config_test_valid_plane_type(struct kunit *test)
 	struct vkms_config_encoder *encoder_cfg;
 	int err;
 
-	config = vkms_config_default_create(false, false, false);
+	config = vkms_config_default_create(false, false, false, false);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, config);
 
 	plane_cfg = get_first_plane(config);
@@ -474,7 +487,7 @@ static void vkms_config_test_valid_plane_possible_crtcs(struct kunit *test)
 	struct vkms_config_plane *plane_cfg;
 	struct vkms_config_crtc *crtc_cfg;
 
-	config = vkms_config_default_create(false, false, false);
+	config = vkms_config_default_create(false, false, false, false);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, config);
 
 	plane_cfg = get_first_plane(config);
@@ -493,7 +506,7 @@ static void vkms_config_test_invalid_crtc_number(struct kunit *test)
 	struct vkms_config_crtc *crtc_cfg;
 	int n;
 
-	config = vkms_config_default_create(false, false, false);
+	config = vkms_config_default_create(false, false, false, false);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, config);
 
 	/* Invalid: No CRTCs */
@@ -516,7 +529,7 @@ static void vkms_config_test_invalid_encoder_number(struct kunit *test)
 	struct vkms_config_encoder *encoder_cfg;
 	int n;
 
-	config = vkms_config_default_create(false, false, false);
+	config = vkms_config_default_create(false, false, false, false);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, config);
 
 	/* Invalid: No encoders */
@@ -541,7 +554,7 @@ static void vkms_config_test_valid_encoder_possible_crtcs(struct kunit *test)
 	struct vkms_config_encoder *encoder_cfg;
 	int err;
 
-	config = vkms_config_default_create(false, false, false);
+	config = vkms_config_default_create(false, false, false, false);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, config);
 
 	crtc_cfg1 = get_first_crtc(config);
@@ -587,7 +600,7 @@ static void vkms_config_test_invalid_connector_number(struct kunit *test)
 	struct vkms_config_connector *connector_cfg;
 	int n;
 
-	config = vkms_config_default_create(false, false, false);
+	config = vkms_config_default_create(false, false, false, false);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, config);
 
 	/* Invalid: No connectors */
@@ -610,7 +623,7 @@ static void vkms_config_test_valid_connector_possible_encoders(struct kunit *tes
 	struct vkms_config_encoder *encoder_cfg;
 	struct vkms_config_connector *connector_cfg;
 
-	config = vkms_config_default_create(false, false, false);
+	config = vkms_config_default_create(false, false, false, false);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, config);
 
 	encoder_cfg = get_first_encoder(config);
diff --git a/drivers/gpu/drm/vkms/vkms_colorop.c b/drivers/gpu/drm/vkms/vkms_colorop.c
new file mode 100644
index 000000000000..5c3ffc78aea0
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_colorop.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/slab.h>
+#include <drm/drm_colorop.h>
+#include <drm/drm_print.h>
+#include <drm/drm_property.h>
+#include <drm/drm_plane.h>
+
+#include "vkms_drv.h"
+
+static const u64 supported_tfs =
+	BIT(DRM_COLOROP_1D_CURVE_SRGB_EOTF) |
+	BIT(DRM_COLOROP_1D_CURVE_SRGB_INV_EOTF);
+
+#define MAX_COLOR_PIPELINE_OPS 4
+
+static int vkms_initialize_color_pipeline(struct drm_plane *plane, struct drm_prop_enum_list *list)
+{
+	struct drm_colorop *ops[MAX_COLOR_PIPELINE_OPS];
+	struct drm_device *dev = plane->dev;
+	int ret;
+	int i = 0, j = 0;
+
+	memset(ops, 0, sizeof(ops));
+
+	/* 1st op: 1d curve */
+	ops[i] = kzalloc(sizeof(*ops[i]), GFP_KERNEL);
+	if (!ops[i]) {
+		drm_err(dev, "KMS: Failed to allocate colorop\n");
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	ret = drm_plane_colorop_curve_1d_init(dev, ops[i], plane, supported_tfs,
+					      DRM_COLOROP_FLAG_ALLOW_BYPASS);
+	if (ret)
+		goto cleanup;
+
+	list->type = ops[i]->base.id;
+	list->name = kasprintf(GFP_KERNEL, "Color Pipeline %d", ops[i]->base.id);
+
+	i++;
+
+	/* 2nd op: 3x4 matrix */
+	ops[i] = kzalloc(sizeof(*ops[i]), GFP_KERNEL);
+	if (!ops[i]) {
+		drm_err(dev, "KMS: Failed to allocate colorop\n");
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	ret = drm_plane_colorop_ctm_3x4_init(dev, ops[i], plane, DRM_COLOROP_FLAG_ALLOW_BYPASS);
+	if (ret)
+		goto cleanup;
+
+	drm_colorop_set_next_property(ops[i - 1], ops[i]);
+
+	i++;
+
+	/* 3rd op: 3x4 matrix */
+	ops[i] = kzalloc(sizeof(*ops[i]), GFP_KERNEL);
+	if (!ops[i]) {
+		drm_err(dev, "KMS: Failed to allocate colorop\n");
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	ret = drm_plane_colorop_ctm_3x4_init(dev, ops[i], plane, DRM_COLOROP_FLAG_ALLOW_BYPASS);
+	if (ret)
+		goto cleanup;
+
+	drm_colorop_set_next_property(ops[i - 1], ops[i]);
+
+	i++;
+
+	/* 4th op: 1d curve */
+	ops[i] = kzalloc(sizeof(*ops[i]), GFP_KERNEL);
+	if (!ops[i]) {
+		drm_err(dev, "KMS: Failed to allocate colorop\n");
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	ret = drm_plane_colorop_curve_1d_init(dev, ops[i], plane, supported_tfs,
+					      DRM_COLOROP_FLAG_ALLOW_BYPASS);
+	if (ret)
+		goto cleanup;
+
+	drm_colorop_set_next_property(ops[i - 1], ops[i]);
+
+	return 0;
+
+cleanup:
+	for (j = 0; j < i; j++) {
+		if (ops[j]) {
+			drm_colorop_cleanup(ops[j]);
+			kfree(ops[j]);
+		}
+	}
+
+	return ret;
+}
+
+int vkms_initialize_colorops(struct drm_plane *plane)
+{
+	struct drm_prop_enum_list pipeline;
+	int ret;
+
+	/* Add color pipeline */
+	ret = vkms_initialize_color_pipeline(plane, &pipeline);
+	if (ret)
+		return ret;
+
+	/* Create COLOR_PIPELINE property and attach */
+	ret = drm_plane_create_color_pipeline_property(plane, &pipeline, 1);
+	if (ret)
+		return ret;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c
index c1ab12a44621..3cf3f26e0d8e 100644
--- a/drivers/gpu/drm/vkms/vkms_composer.c
+++ b/drivers/gpu/drm/vkms/vkms_composer.c
@@ -11,8 +11,10 @@
 #include <drm/drm_print.h>
 #include <drm/drm_vblank.h>
 #include <linux/minmax.h>
+#include <kunit/visibility.h>
 
-#include "vkms_drv.h"
+#include "vkms_composer.h"
+#include "vkms_luts.h"
 
 static u16 pre_mul_blend_channel(u16 src, u16 dst, u16 alpha)
 {
@@ -61,7 +63,7 @@ static void fill_background(const struct pixel_argb_u16 *background_color,
 }
 
 // lerp(a, b, t) = a + (b - a) * t
-static u16 lerp_u16(u16 a, u16 b, s64 t)
+VISIBLE_IF_KUNIT u16 lerp_u16(u16 a, u16 b, s64 t)
 {
 	s64 a_fp = drm_int2fixp(a);
 	s64 b_fp = drm_int2fixp(b);
@@ -70,27 +72,18 @@ static u16 lerp_u16(u16 a, u16 b, s64 t)
 
 	return drm_fixp2int_round(a_fp + delta);
 }
+EXPORT_SYMBOL_IF_KUNIT(lerp_u16);
 
-static s64 get_lut_index(const struct vkms_color_lut *lut, u16 channel_value)
+VISIBLE_IF_KUNIT s64 get_lut_index(const struct vkms_color_lut *lut, u16 channel_value)
 {
 	s64 color_channel_fp = drm_int2fixp(channel_value);
 
 	return drm_fixp_mul(color_channel_fp, lut->channel_value2index_ratio);
 }
+EXPORT_SYMBOL_IF_KUNIT(get_lut_index);
 
-/*
- * This enum is related to the positions of the variables inside
- * `struct drm_color_lut`, so the order of both needs to be the same.
- */
-enum lut_channel {
-	LUT_RED = 0,
-	LUT_GREEN,
-	LUT_BLUE,
-	LUT_RESERVED
-};
-
-static u16 apply_lut_to_channel_value(const struct vkms_color_lut *lut, u16 channel_value,
-				      enum lut_channel channel)
+VISIBLE_IF_KUNIT u16 apply_lut_to_channel_value(const struct vkms_color_lut *lut, u16 channel_value,
+						enum lut_channel channel)
 {
 	s64 lut_index = get_lut_index(lut, channel_value);
 	u16 *floor_lut_value, *ceil_lut_value;
@@ -115,6 +108,8 @@ static u16 apply_lut_to_channel_value(const struct vkms_color_lut *lut, u16 chan
 	return lerp_u16(floor_channel_value, ceil_channel_value,
 			lut_index & DRM_FIXED_DECIMAL_MASK);
 }
+EXPORT_SYMBOL_IF_KUNIT(apply_lut_to_channel_value);
+
 
 static void apply_lut(const struct vkms_crtc_state *crtc_state, struct line_buffer *output_buffer)
 {
@@ -133,6 +128,112 @@ static void apply_lut(const struct vkms_crtc_state *crtc_state, struct line_buff
 	}
 }
 
+VISIBLE_IF_KUNIT void apply_3x4_matrix(struct pixel_argb_s32 *pixel,
+				       const struct drm_color_ctm_3x4 *matrix)
+{
+	s64 rf, gf, bf;
+	s64 r, g, b;
+
+	r = drm_int2fixp(pixel->r);
+	g = drm_int2fixp(pixel->g);
+	b = drm_int2fixp(pixel->b);
+
+	rf = drm_fixp_mul(drm_sm2fixp(matrix->matrix[0]), r) +
+	     drm_fixp_mul(drm_sm2fixp(matrix->matrix[1]), g) +
+	     drm_fixp_mul(drm_sm2fixp(matrix->matrix[2]), b) +
+	     drm_sm2fixp(matrix->matrix[3]);
+
+	gf = drm_fixp_mul(drm_sm2fixp(matrix->matrix[4]), r) +
+	     drm_fixp_mul(drm_sm2fixp(matrix->matrix[5]), g) +
+	     drm_fixp_mul(drm_sm2fixp(matrix->matrix[6]), b) +
+	     drm_sm2fixp(matrix->matrix[7]);
+
+	bf = drm_fixp_mul(drm_sm2fixp(matrix->matrix[8]), r) +
+	     drm_fixp_mul(drm_sm2fixp(matrix->matrix[9]), g) +
+	     drm_fixp_mul(drm_sm2fixp(matrix->matrix[10]), b) +
+	     drm_sm2fixp(matrix->matrix[11]);
+
+	pixel->r = drm_fixp2int_round(rf);
+	pixel->g = drm_fixp2int_round(gf);
+	pixel->b = drm_fixp2int_round(bf);
+}
+EXPORT_SYMBOL_IF_KUNIT(apply_3x4_matrix);
+
+static void apply_colorop(struct pixel_argb_s32 *pixel, struct drm_colorop *colorop)
+{
+	struct drm_colorop_state *colorop_state = colorop->state;
+	struct drm_device *dev = colorop->dev;
+
+	if (colorop->type == DRM_COLOROP_1D_CURVE) {
+		switch (colorop_state->curve_1d_type) {
+		case DRM_COLOROP_1D_CURVE_SRGB_INV_EOTF:
+			pixel->r = apply_lut_to_channel_value(&srgb_inv_eotf, pixel->r, LUT_RED);
+			pixel->g = apply_lut_to_channel_value(&srgb_inv_eotf, pixel->g, LUT_GREEN);
+			pixel->b = apply_lut_to_channel_value(&srgb_inv_eotf, pixel->b, LUT_BLUE);
+			break;
+		case DRM_COLOROP_1D_CURVE_SRGB_EOTF:
+			pixel->r = apply_lut_to_channel_value(&srgb_eotf, pixel->r, LUT_RED);
+			pixel->g = apply_lut_to_channel_value(&srgb_eotf, pixel->g, LUT_GREEN);
+			pixel->b = apply_lut_to_channel_value(&srgb_eotf, pixel->b, LUT_BLUE);
+			break;
+		default:
+			drm_WARN_ONCE(dev, true,
+				      "unknown colorop 1D curve type %d\n",
+				      colorop_state->curve_1d_type);
+			break;
+		}
+	} else if (colorop->type == DRM_COLOROP_CTM_3X4) {
+		if (colorop_state->data)
+			apply_3x4_matrix(pixel,
+					 (struct drm_color_ctm_3x4 *)colorop_state->data->data);
+	}
+}
+
+static void pre_blend_color_transform(const struct vkms_plane_state *plane_state,
+				      struct line_buffer *output_buffer)
+{
+	struct pixel_argb_s32 pixel;
+
+	for (size_t x = 0; x < output_buffer->n_pixels; x++) {
+		struct drm_colorop *colorop = plane_state->base.base.color_pipeline;
+
+		/*
+		 * Some operations, such as applying a BT709 encoding matrix,
+		 * followed by a decoding matrix, require that we preserve
+		 * values above 1.0 and below 0.0 until the end of the pipeline.
+		 *
+		 * Pack the 16-bit UNORM values into s32 to give us head-room to
+		 * avoid clipping until we're at the end of the pipeline. Clip
+		 * intentionally at the end of the pipeline before packing
+		 * UNORM values back into u16.
+		 */
+		pixel.a = output_buffer->pixels[x].a;
+		pixel.r = output_buffer->pixels[x].r;
+		pixel.g = output_buffer->pixels[x].g;
+		pixel.b = output_buffer->pixels[x].b;
+
+		while (colorop) {
+			struct drm_colorop_state *colorop_state;
+
+			colorop_state = colorop->state;
+
+			if (!colorop_state)
+				return;
+
+			if (!colorop_state->bypass)
+				apply_colorop(&pixel, colorop);
+
+			colorop = colorop->next;
+		}
+
+		/* clamp values */
+		output_buffer->pixels[x].a = clamp_val(pixel.a, 0, 0xffff);
+		output_buffer->pixels[x].r = clamp_val(pixel.r, 0, 0xffff);
+		output_buffer->pixels[x].g = clamp_val(pixel.g, 0, 0xffff);
+		output_buffer->pixels[x].b = clamp_val(pixel.b, 0, 0xffff);
+	}
+}
+
 /**
  * direction_for_rotation() - Get the correct reading direction for a given rotation
  *
@@ -348,7 +449,7 @@ static void blend_line(struct vkms_plane_state *current_plane, int y,
 	 */
 	current_plane->pixel_read_line(current_plane, src_x_start, src_y_start, direction,
 				       pixel_count, &stage_buffer->pixels[dst_x_start]);
-
+	pre_blend_color_transform(current_plane, stage_buffer);
 	pre_mul_alpha_blend(stage_buffer, output_buffer,
 			    dst_x_start, pixel_count);
 }
diff --git a/drivers/gpu/drm/vkms/vkms_composer.h b/drivers/gpu/drm/vkms/vkms_composer.h
new file mode 100644
index 000000000000..04dd5646f672
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_composer.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _VKMS_COMPOSER_H_
+#define _VKMS_COMPOSER_H_
+
+#include <kunit/visibility.h>
+#include "vkms_drv.h"
+
+/*
+ * This enum is related to the positions of the variables inside
+ * `struct drm_color_lut`, so the order of both needs to be the same.
+ */
+enum lut_channel {
+	LUT_RED = 0,
+	LUT_GREEN,
+	LUT_BLUE,
+	LUT_RESERVED
+};
+
+#if IS_ENABLED(CONFIG_KUNIT)
+u16 lerp_u16(u16 a, u16 b, s64 t);
+s64 get_lut_index(const struct vkms_color_lut *lut, u16 channel_value);
+u16 apply_lut_to_channel_value(const struct vkms_color_lut *lut, u16 channel_value,
+			       enum lut_channel channel);
+void apply_3x4_matrix(struct pixel_argb_s32 *pixel, const struct drm_color_ctm_3x4 *matrix);
+#endif
+
+#endif /* _VKMS_COMPOSER_H_ */
diff --git a/drivers/gpu/drm/vkms/vkms_config.c b/drivers/gpu/drm/vkms/vkms_config.c
index f8394a063ecf..8788df9edb7c 100644
--- a/drivers/gpu/drm/vkms/vkms_config.c
+++ b/drivers/gpu/drm/vkms/vkms_config.c
@@ -33,7 +33,8 @@ EXPORT_SYMBOL_IF_KUNIT(vkms_config_create);
 
 struct vkms_config *vkms_config_default_create(bool enable_cursor,
 					       bool enable_writeback,
-					       bool enable_overlay)
+					       bool enable_overlay,
+					       bool enable_plane_pipeline)
 {
 	struct vkms_config *config;
 	struct vkms_config_plane *plane_cfg;
@@ -58,6 +59,7 @@ struct vkms_config *vkms_config_default_create(bool enable_cursor,
 
 	if (vkms_config_plane_attach_crtc(plane_cfg, crtc_cfg))
 		goto err_alloc;
+	vkms_config_plane_set_default_pipeline(plane_cfg, enable_plane_pipeline);
 
 	if (enable_overlay) {
 		for (n = 0; n < NUM_OVERLAY_PLANES; n++) {
@@ -67,6 +69,7 @@ struct vkms_config *vkms_config_default_create(bool enable_cursor,
 
 			vkms_config_plane_set_type(plane_cfg,
 						   DRM_PLANE_TYPE_OVERLAY);
+			vkms_config_plane_set_default_pipeline(plane_cfg, enable_plane_pipeline);
 
 			if (vkms_config_plane_attach_crtc(plane_cfg, crtc_cfg))
 				goto err_alloc;
@@ -79,6 +82,7 @@ struct vkms_config *vkms_config_default_create(bool enable_cursor,
 			goto err_alloc;
 
 		vkms_config_plane_set_type(plane_cfg, DRM_PLANE_TYPE_CURSOR);
+		vkms_config_plane_set_default_pipeline(plane_cfg, enable_plane_pipeline);
 
 		if (vkms_config_plane_attach_crtc(plane_cfg, crtc_cfg))
 			goto err_alloc;
@@ -389,6 +393,7 @@ struct vkms_config_plane *vkms_config_create_plane(struct vkms_config *config)
 		return ERR_PTR(-ENOMEM);
 
 	plane_cfg->config = config;
+	plane_cfg->default_pipeline = false;
 	vkms_config_plane_set_type(plane_cfg, DRM_PLANE_TYPE_OVERLAY);
 	xa_init_flags(&plane_cfg->possible_crtcs, XA_FLAGS_ALLOC);
 
diff --git a/drivers/gpu/drm/vkms/vkms_config.h b/drivers/gpu/drm/vkms/vkms_config.h
index 4c8d668e7ef8..8f7f286a4bdd 100644
--- a/drivers/gpu/drm/vkms/vkms_config.h
+++ b/drivers/gpu/drm/vkms/vkms_config.h
@@ -49,6 +49,7 @@ struct vkms_config_plane {
 
 	enum drm_plane_type type;
 	struct xarray possible_crtcs;
+	bool default_pipeline;
 
 	/* Internal usage */
 	struct vkms_plane *plane;
@@ -203,7 +204,8 @@ struct vkms_config *vkms_config_create(const char *dev_name);
  */
 struct vkms_config *vkms_config_default_create(bool enable_cursor,
 					       bool enable_writeback,
-					       bool enable_overlay);
+					       bool enable_overlay,
+					       bool enable_plane_pipeline);
 
 /**
  * vkms_config_destroy() - Free a VKMS configuration
@@ -289,6 +291,30 @@ vkms_config_plane_set_type(struct vkms_config_plane *plane_cfg,
 }
 
 /**
+ * vkms_config_plane_get_default_pipeline() - Return if the plane will
+ * be created with the default pipeline
+ * @plane_cfg: Plane to get the information from
+ */
+static inline bool
+vkms_config_plane_get_default_pipeline(struct vkms_config_plane *plane_cfg)
+{
+	return plane_cfg->default_pipeline;
+}
+
+/**
+ * vkms_config_plane_set_default_pipeline() - Set if the plane will
+ * be created with the default pipeline
+ * @plane_cfg: Plane to configure the pipeline
+ * @default_pipeline: New default pipeline value
+ */
+static inline void
+vkms_config_plane_set_default_pipeline(struct vkms_config_plane *plane_cfg,
+				       bool default_pipeline)
+{
+	plane_cfg->default_pipeline = default_pipeline;
+}
+
+/**
  * vkms_config_plane_attach_crtc - Attach a plane to a CRTC
  * @plane_cfg: Plane to attach
  * @crtc_cfg: CRTC to attach @plane_cfg to
diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index 1f80b1f126b6..dd1402f43773 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -51,6 +51,10 @@ static bool enable_overlay;
 module_param_named(enable_overlay, enable_overlay, bool, 0444);
 MODULE_PARM_DESC(enable_overlay, "Enable/Disable overlay support");
 
+static bool enable_plane_pipeline;
+module_param_named(enable_plane_pipeline, enable_plane_pipeline, bool, 0444);
+MODULE_PARM_DESC(enable_plane_pipeline, "Enable/Disable plane pipeline support");
+
 static bool create_default_dev = true;
 module_param_named(create_default_dev, create_default_dev, bool, 0444);
 MODULE_PARM_DESC(create_default_dev, "Create or not the default VKMS device");
@@ -227,7 +231,8 @@ static int __init vkms_init(void)
 	if (!create_default_dev)
 		return 0;
 
-	config = vkms_config_default_create(enable_cursor, enable_writeback, enable_overlay);
+	config = vkms_config_default_create(enable_cursor, enable_writeback,
+					    enable_overlay, enable_plane_pipeline);
 	if (IS_ERR(config))
 		return PTR_ERR(config);
 
@@ -253,6 +258,7 @@ void vkms_destroy(struct vkms_config *config)
 
 	fdev = config->dev->faux_dev;
 
+	drm_colorop_pipeline_destroy(&config->dev->drm);
 	drm_dev_unregister(&config->dev->drm);
 	drm_atomic_helper_shutdown(&config->dev->drm);
 	devres_release_group(&fdev->dev, NULL);
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
index db260df1d4f6..0933e4ce0ff0 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.h
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -45,6 +45,10 @@ struct vkms_frame_info {
 	unsigned int rotation;
 };
 
+struct pixel_argb_s32 {
+	s32 a, r, g, b;
+};
+
 /**
  * struct pixel_argb_u16 - Internal representation of a pixel color.
  * @a: Alpha component value, stored in 16 bits, without padding, using
@@ -225,6 +229,7 @@ struct vkms_output {
 };
 
 struct vkms_config;
+struct vkms_config_plane;
 
 /**
  * struct vkms_device - Description of a VKMS device
@@ -298,10 +303,10 @@ int vkms_output_init(struct vkms_device *vkmsdev);
  * vkms_plane_init() - Initialize a plane
  *
  * @vkmsdev: VKMS device containing the plane
- * @type: type of plane to initialize
+ * @plane_cfg: plane configuration
  */
 struct vkms_plane *vkms_plane_init(struct vkms_device *vkmsdev,
-				   enum drm_plane_type type);
+				   struct vkms_config_plane *plane_cfg);
 
 /* CRC Support */
 const char *const *vkms_get_crc_sources(struct drm_crtc *crtc,
@@ -318,4 +323,7 @@ void vkms_writeback_row(struct vkms_writeback_job *wb, const struct line_buffer
 /* Writeback */
 int vkms_enable_writeback_connector(struct vkms_device *vkmsdev, struct vkms_output *vkms_out);
 
+/* Colorops */
+int vkms_initialize_colorops(struct drm_plane *plane);
+
 #endif /* _VKMS_DRV_H_ */
diff --git a/drivers/gpu/drm/vkms/vkms_luts.c b/drivers/gpu/drm/vkms/vkms_luts.c
new file mode 100644
index 000000000000..82cb792f10d8
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_luts.c
@@ -0,0 +1,811 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <drm/drm_mode.h>
+
+#include "vkms_drv.h"
+#include "vkms_luts.h"
+
+/*
+ * These luts were generated with a LUT generated based on
+ * skia's transfer function code. The LUT generator can be
+ * found at
+ * https://gitlab.freedesktop.org/hwentland/lutgen
+ */
+
+static struct drm_color_lut linear_array[LUT_SIZE] = {
+	{ 0x0, 0x0, 0x0, 0 },
+	{ 0x101, 0x101, 0x101, 0 },
+	{ 0x202, 0x202, 0x202, 0 },
+	{ 0x303, 0x303, 0x303, 0 },
+	{ 0x404, 0x404, 0x404, 0 },
+	{ 0x505, 0x505, 0x505, 0 },
+	{ 0x606, 0x606, 0x606, 0 },
+	{ 0x707, 0x707, 0x707, 0 },
+	{ 0x808, 0x808, 0x808, 0 },
+	{ 0x909, 0x909, 0x909, 0 },
+	{ 0xa0a, 0xa0a, 0xa0a, 0 },
+	{ 0xb0b, 0xb0b, 0xb0b, 0 },
+	{ 0xc0c, 0xc0c, 0xc0c, 0 },
+	{ 0xd0d, 0xd0d, 0xd0d, 0 },
+	{ 0xe0e, 0xe0e, 0xe0e, 0 },
+	{ 0xf0f, 0xf0f, 0xf0f, 0 },
+	{ 0x1010, 0x1010, 0x1010, 0 },
+	{ 0x1111, 0x1111, 0x1111, 0 },
+	{ 0x1212, 0x1212, 0x1212, 0 },
+	{ 0x1313, 0x1313, 0x1313, 0 },
+	{ 0x1414, 0x1414, 0x1414, 0 },
+	{ 0x1515, 0x1515, 0x1515, 0 },
+	{ 0x1616, 0x1616, 0x1616, 0 },
+	{ 0x1717, 0x1717, 0x1717, 0 },
+	{ 0x1818, 0x1818, 0x1818, 0 },
+	{ 0x1919, 0x1919, 0x1919, 0 },
+	{ 0x1a1a, 0x1a1a, 0x1a1a, 0 },
+	{ 0x1b1b, 0x1b1b, 0x1b1b, 0 },
+	{ 0x1c1c, 0x1c1c, 0x1c1c, 0 },
+	{ 0x1d1d, 0x1d1d, 0x1d1d, 0 },
+	{ 0x1e1e, 0x1e1e, 0x1e1e, 0 },
+	{ 0x1f1f, 0x1f1f, 0x1f1f, 0 },
+	{ 0x2020, 0x2020, 0x2020, 0 },
+	{ 0x2121, 0x2121, 0x2121, 0 },
+	{ 0x2222, 0x2222, 0x2222, 0 },
+	{ 0x2323, 0x2323, 0x2323, 0 },
+	{ 0x2424, 0x2424, 0x2424, 0 },
+	{ 0x2525, 0x2525, 0x2525, 0 },
+	{ 0x2626, 0x2626, 0x2626, 0 },
+	{ 0x2727, 0x2727, 0x2727, 0 },
+	{ 0x2828, 0x2828, 0x2828, 0 },
+	{ 0x2929, 0x2929, 0x2929, 0 },
+	{ 0x2a2a, 0x2a2a, 0x2a2a, 0 },
+	{ 0x2b2b, 0x2b2b, 0x2b2b, 0 },
+	{ 0x2c2c, 0x2c2c, 0x2c2c, 0 },
+	{ 0x2d2d, 0x2d2d, 0x2d2d, 0 },
+	{ 0x2e2e, 0x2e2e, 0x2e2e, 0 },
+	{ 0x2f2f, 0x2f2f, 0x2f2f, 0 },
+	{ 0x3030, 0x3030, 0x3030, 0 },
+	{ 0x3131, 0x3131, 0x3131, 0 },
+	{ 0x3232, 0x3232, 0x3232, 0 },
+	{ 0x3333, 0x3333, 0x3333, 0 },
+	{ 0x3434, 0x3434, 0x3434, 0 },
+	{ 0x3535, 0x3535, 0x3535, 0 },
+	{ 0x3636, 0x3636, 0x3636, 0 },
+	{ 0x3737, 0x3737, 0x3737, 0 },
+	{ 0x3838, 0x3838, 0x3838, 0 },
+	{ 0x3939, 0x3939, 0x3939, 0 },
+	{ 0x3a3a, 0x3a3a, 0x3a3a, 0 },
+	{ 0x3b3b, 0x3b3b, 0x3b3b, 0 },
+	{ 0x3c3c, 0x3c3c, 0x3c3c, 0 },
+	{ 0x3d3d, 0x3d3d, 0x3d3d, 0 },
+	{ 0x3e3e, 0x3e3e, 0x3e3e, 0 },
+	{ 0x3f3f, 0x3f3f, 0x3f3f, 0 },
+	{ 0x4040, 0x4040, 0x4040, 0 },
+	{ 0x4141, 0x4141, 0x4141, 0 },
+	{ 0x4242, 0x4242, 0x4242, 0 },
+	{ 0x4343, 0x4343, 0x4343, 0 },
+	{ 0x4444, 0x4444, 0x4444, 0 },
+	{ 0x4545, 0x4545, 0x4545, 0 },
+	{ 0x4646, 0x4646, 0x4646, 0 },
+	{ 0x4747, 0x4747, 0x4747, 0 },
+	{ 0x4848, 0x4848, 0x4848, 0 },
+	{ 0x4949, 0x4949, 0x4949, 0 },
+	{ 0x4a4a, 0x4a4a, 0x4a4a, 0 },
+	{ 0x4b4b, 0x4b4b, 0x4b4b, 0 },
+	{ 0x4c4c, 0x4c4c, 0x4c4c, 0 },
+	{ 0x4d4d, 0x4d4d, 0x4d4d, 0 },
+	{ 0x4e4e, 0x4e4e, 0x4e4e, 0 },
+	{ 0x4f4f, 0x4f4f, 0x4f4f, 0 },
+	{ 0x5050, 0x5050, 0x5050, 0 },
+	{ 0x5151, 0x5151, 0x5151, 0 },
+	{ 0x5252, 0x5252, 0x5252, 0 },
+	{ 0x5353, 0x5353, 0x5353, 0 },
+	{ 0x5454, 0x5454, 0x5454, 0 },
+	{ 0x5555, 0x5555, 0x5555, 0 },
+	{ 0x5656, 0x5656, 0x5656, 0 },
+	{ 0x5757, 0x5757, 0x5757, 0 },
+	{ 0x5858, 0x5858, 0x5858, 0 },
+	{ 0x5959, 0x5959, 0x5959, 0 },
+	{ 0x5a5a, 0x5a5a, 0x5a5a, 0 },
+	{ 0x5b5b, 0x5b5b, 0x5b5b, 0 },
+	{ 0x5c5c, 0x5c5c, 0x5c5c, 0 },
+	{ 0x5d5d, 0x5d5d, 0x5d5d, 0 },
+	{ 0x5e5e, 0x5e5e, 0x5e5e, 0 },
+	{ 0x5f5f, 0x5f5f, 0x5f5f, 0 },
+	{ 0x6060, 0x6060, 0x6060, 0 },
+	{ 0x6161, 0x6161, 0x6161, 0 },
+	{ 0x6262, 0x6262, 0x6262, 0 },
+	{ 0x6363, 0x6363, 0x6363, 0 },
+	{ 0x6464, 0x6464, 0x6464, 0 },
+	{ 0x6565, 0x6565, 0x6565, 0 },
+	{ 0x6666, 0x6666, 0x6666, 0 },
+	{ 0x6767, 0x6767, 0x6767, 0 },
+	{ 0x6868, 0x6868, 0x6868, 0 },
+	{ 0x6969, 0x6969, 0x6969, 0 },
+	{ 0x6a6a, 0x6a6a, 0x6a6a, 0 },
+	{ 0x6b6b, 0x6b6b, 0x6b6b, 0 },
+	{ 0x6c6c, 0x6c6c, 0x6c6c, 0 },
+	{ 0x6d6d, 0x6d6d, 0x6d6d, 0 },
+	{ 0x6e6e, 0x6e6e, 0x6e6e, 0 },
+	{ 0x6f6f, 0x6f6f, 0x6f6f, 0 },
+	{ 0x7070, 0x7070, 0x7070, 0 },
+	{ 0x7171, 0x7171, 0x7171, 0 },
+	{ 0x7272, 0x7272, 0x7272, 0 },
+	{ 0x7373, 0x7373, 0x7373, 0 },
+	{ 0x7474, 0x7474, 0x7474, 0 },
+	{ 0x7575, 0x7575, 0x7575, 0 },
+	{ 0x7676, 0x7676, 0x7676, 0 },
+	{ 0x7777, 0x7777, 0x7777, 0 },
+	{ 0x7878, 0x7878, 0x7878, 0 },
+	{ 0x7979, 0x7979, 0x7979, 0 },
+	{ 0x7a7a, 0x7a7a, 0x7a7a, 0 },
+	{ 0x7b7b, 0x7b7b, 0x7b7b, 0 },
+	{ 0x7c7c, 0x7c7c, 0x7c7c, 0 },
+	{ 0x7d7d, 0x7d7d, 0x7d7d, 0 },
+	{ 0x7e7e, 0x7e7e, 0x7e7e, 0 },
+	{ 0x7f7f, 0x7f7f, 0x7f7f, 0 },
+	{ 0x8080, 0x8080, 0x8080, 0 },
+	{ 0x8181, 0x8181, 0x8181, 0 },
+	{ 0x8282, 0x8282, 0x8282, 0 },
+	{ 0x8383, 0x8383, 0x8383, 0 },
+	{ 0x8484, 0x8484, 0x8484, 0 },
+	{ 0x8585, 0x8585, 0x8585, 0 },
+	{ 0x8686, 0x8686, 0x8686, 0 },
+	{ 0x8787, 0x8787, 0x8787, 0 },
+	{ 0x8888, 0x8888, 0x8888, 0 },
+	{ 0x8989, 0x8989, 0x8989, 0 },
+	{ 0x8a8a, 0x8a8a, 0x8a8a, 0 },
+	{ 0x8b8b, 0x8b8b, 0x8b8b, 0 },
+	{ 0x8c8c, 0x8c8c, 0x8c8c, 0 },
+	{ 0x8d8d, 0x8d8d, 0x8d8d, 0 },
+	{ 0x8e8e, 0x8e8e, 0x8e8e, 0 },
+	{ 0x8f8f, 0x8f8f, 0x8f8f, 0 },
+	{ 0x9090, 0x9090, 0x9090, 0 },
+	{ 0x9191, 0x9191, 0x9191, 0 },
+	{ 0x9292, 0x9292, 0x9292, 0 },
+	{ 0x9393, 0x9393, 0x9393, 0 },
+	{ 0x9494, 0x9494, 0x9494, 0 },
+	{ 0x9595, 0x9595, 0x9595, 0 },
+	{ 0x9696, 0x9696, 0x9696, 0 },
+	{ 0x9797, 0x9797, 0x9797, 0 },
+	{ 0x9898, 0x9898, 0x9898, 0 },
+	{ 0x9999, 0x9999, 0x9999, 0 },
+	{ 0x9a9a, 0x9a9a, 0x9a9a, 0 },
+	{ 0x9b9b, 0x9b9b, 0x9b9b, 0 },
+	{ 0x9c9c, 0x9c9c, 0x9c9c, 0 },
+	{ 0x9d9d, 0x9d9d, 0x9d9d, 0 },
+	{ 0x9e9e, 0x9e9e, 0x9e9e, 0 },
+	{ 0x9f9f, 0x9f9f, 0x9f9f, 0 },
+	{ 0xa0a0, 0xa0a0, 0xa0a0, 0 },
+	{ 0xa1a1, 0xa1a1, 0xa1a1, 0 },
+	{ 0xa2a2, 0xa2a2, 0xa2a2, 0 },
+	{ 0xa3a3, 0xa3a3, 0xa3a3, 0 },
+	{ 0xa4a4, 0xa4a4, 0xa4a4, 0 },
+	{ 0xa5a5, 0xa5a5, 0xa5a5, 0 },
+	{ 0xa6a6, 0xa6a6, 0xa6a6, 0 },
+	{ 0xa7a7, 0xa7a7, 0xa7a7, 0 },
+	{ 0xa8a8, 0xa8a8, 0xa8a8, 0 },
+	{ 0xa9a9, 0xa9a9, 0xa9a9, 0 },
+	{ 0xaaaa, 0xaaaa, 0xaaaa, 0 },
+	{ 0xabab, 0xabab, 0xabab, 0 },
+	{ 0xacac, 0xacac, 0xacac, 0 },
+	{ 0xadad, 0xadad, 0xadad, 0 },
+	{ 0xaeae, 0xaeae, 0xaeae, 0 },
+	{ 0xafaf, 0xafaf, 0xafaf, 0 },
+	{ 0xb0b0, 0xb0b0, 0xb0b0, 0 },
+	{ 0xb1b1, 0xb1b1, 0xb1b1, 0 },
+	{ 0xb2b2, 0xb2b2, 0xb2b2, 0 },
+	{ 0xb3b3, 0xb3b3, 0xb3b3, 0 },
+	{ 0xb4b4, 0xb4b4, 0xb4b4, 0 },
+	{ 0xb5b5, 0xb5b5, 0xb5b5, 0 },
+	{ 0xb6b6, 0xb6b6, 0xb6b6, 0 },
+	{ 0xb7b7, 0xb7b7, 0xb7b7, 0 },
+	{ 0xb8b8, 0xb8b8, 0xb8b8, 0 },
+	{ 0xb9b9, 0xb9b9, 0xb9b9, 0 },
+	{ 0xbaba, 0xbaba, 0xbaba, 0 },
+	{ 0xbbbb, 0xbbbb, 0xbbbb, 0 },
+	{ 0xbcbc, 0xbcbc, 0xbcbc, 0 },
+	{ 0xbdbd, 0xbdbd, 0xbdbd, 0 },
+	{ 0xbebe, 0xbebe, 0xbebe, 0 },
+	{ 0xbfbf, 0xbfbf, 0xbfbf, 0 },
+	{ 0xc0c0, 0xc0c0, 0xc0c0, 0 },
+	{ 0xc1c1, 0xc1c1, 0xc1c1, 0 },
+	{ 0xc2c2, 0xc2c2, 0xc2c2, 0 },
+	{ 0xc3c3, 0xc3c3, 0xc3c3, 0 },
+	{ 0xc4c4, 0xc4c4, 0xc4c4, 0 },
+	{ 0xc5c5, 0xc5c5, 0xc5c5, 0 },
+	{ 0xc6c6, 0xc6c6, 0xc6c6, 0 },
+	{ 0xc7c7, 0xc7c7, 0xc7c7, 0 },
+	{ 0xc8c8, 0xc8c8, 0xc8c8, 0 },
+	{ 0xc9c9, 0xc9c9, 0xc9c9, 0 },
+	{ 0xcaca, 0xcaca, 0xcaca, 0 },
+	{ 0xcbcb, 0xcbcb, 0xcbcb, 0 },
+	{ 0xcccc, 0xcccc, 0xcccc, 0 },
+	{ 0xcdcd, 0xcdcd, 0xcdcd, 0 },
+	{ 0xcece, 0xcece, 0xcece, 0 },
+	{ 0xcfcf, 0xcfcf, 0xcfcf, 0 },
+	{ 0xd0d0, 0xd0d0, 0xd0d0, 0 },
+	{ 0xd1d1, 0xd1d1, 0xd1d1, 0 },
+	{ 0xd2d2, 0xd2d2, 0xd2d2, 0 },
+	{ 0xd3d3, 0xd3d3, 0xd3d3, 0 },
+	{ 0xd4d4, 0xd4d4, 0xd4d4, 0 },
+	{ 0xd5d5, 0xd5d5, 0xd5d5, 0 },
+	{ 0xd6d6, 0xd6d6, 0xd6d6, 0 },
+	{ 0xd7d7, 0xd7d7, 0xd7d7, 0 },
+	{ 0xd8d8, 0xd8d8, 0xd8d8, 0 },
+	{ 0xd9d9, 0xd9d9, 0xd9d9, 0 },
+	{ 0xdada, 0xdada, 0xdada, 0 },
+	{ 0xdbdb, 0xdbdb, 0xdbdb, 0 },
+	{ 0xdcdc, 0xdcdc, 0xdcdc, 0 },
+	{ 0xdddd, 0xdddd, 0xdddd, 0 },
+	{ 0xdede, 0xdede, 0xdede, 0 },
+	{ 0xdfdf, 0xdfdf, 0xdfdf, 0 },
+	{ 0xe0e0, 0xe0e0, 0xe0e0, 0 },
+	{ 0xe1e1, 0xe1e1, 0xe1e1, 0 },
+	{ 0xe2e2, 0xe2e2, 0xe2e2, 0 },
+	{ 0xe3e3, 0xe3e3, 0xe3e3, 0 },
+	{ 0xe4e4, 0xe4e4, 0xe4e4, 0 },
+	{ 0xe5e5, 0xe5e5, 0xe5e5, 0 },
+	{ 0xe6e6, 0xe6e6, 0xe6e6, 0 },
+	{ 0xe7e7, 0xe7e7, 0xe7e7, 0 },
+	{ 0xe8e8, 0xe8e8, 0xe8e8, 0 },
+	{ 0xe9e9, 0xe9e9, 0xe9e9, 0 },
+	{ 0xeaea, 0xeaea, 0xeaea, 0 },
+	{ 0xebeb, 0xebeb, 0xebeb, 0 },
+	{ 0xecec, 0xecec, 0xecec, 0 },
+	{ 0xeded, 0xeded, 0xeded, 0 },
+	{ 0xeeee, 0xeeee, 0xeeee, 0 },
+	{ 0xefef, 0xefef, 0xefef, 0 },
+	{ 0xf0f0, 0xf0f0, 0xf0f0, 0 },
+	{ 0xf1f1, 0xf1f1, 0xf1f1, 0 },
+	{ 0xf2f2, 0xf2f2, 0xf2f2, 0 },
+	{ 0xf3f3, 0xf3f3, 0xf3f3, 0 },
+	{ 0xf4f4, 0xf4f4, 0xf4f4, 0 },
+	{ 0xf5f5, 0xf5f5, 0xf5f5, 0 },
+	{ 0xf6f6, 0xf6f6, 0xf6f6, 0 },
+	{ 0xf7f7, 0xf7f7, 0xf7f7, 0 },
+	{ 0xf8f8, 0xf8f8, 0xf8f8, 0 },
+	{ 0xf9f9, 0xf9f9, 0xf9f9, 0 },
+	{ 0xfafa, 0xfafa, 0xfafa, 0 },
+	{ 0xfbfb, 0xfbfb, 0xfbfb, 0 },
+	{ 0xfcfc, 0xfcfc, 0xfcfc, 0 },
+	{ 0xfdfd, 0xfdfd, 0xfdfd, 0 },
+	{ 0xfefe, 0xfefe, 0xfefe, 0 },
+	{ 0xffff, 0xffff, 0xffff, 0 },
+};
+
+const struct vkms_color_lut linear_eotf = {
+	.base = linear_array,
+	.lut_length = LUT_SIZE,
+	.channel_value2index_ratio = 0xff00ffll
+};
+EXPORT_SYMBOL(linear_eotf);
+
+static struct drm_color_lut srgb_array[LUT_SIZE] = {
+	{ 0x0, 0x0, 0x0, 0 },
+	{ 0x13, 0x13, 0x13, 0 },
+	{ 0x27, 0x27, 0x27, 0 },
+	{ 0x3b, 0x3b, 0x3b, 0 },
+	{ 0x4f, 0x4f, 0x4f, 0 },
+	{ 0x63, 0x63, 0x63, 0 },
+	{ 0x77, 0x77, 0x77, 0 },
+	{ 0x8b, 0x8b, 0x8b, 0 },
+	{ 0x9f, 0x9f, 0x9f, 0 },
+	{ 0xb3, 0xb3, 0xb3, 0 },
+	{ 0xc6, 0xc6, 0xc6, 0 },
+	{ 0xdb, 0xdb, 0xdb, 0 },
+	{ 0xf0, 0xf0, 0xf0, 0 },
+	{ 0x107, 0x107, 0x107, 0 },
+	{ 0x11f, 0x11f, 0x11f, 0 },
+	{ 0x139, 0x139, 0x139, 0 },
+	{ 0x153, 0x153, 0x153, 0 },
+	{ 0x16f, 0x16f, 0x16f, 0 },
+	{ 0x18c, 0x18c, 0x18c, 0 },
+	{ 0x1aa, 0x1aa, 0x1aa, 0 },
+	{ 0x1ca, 0x1ca, 0x1ca, 0 },
+	{ 0x1eb, 0x1eb, 0x1eb, 0 },
+	{ 0x20d, 0x20d, 0x20d, 0 },
+	{ 0x231, 0x231, 0x231, 0 },
+	{ 0x256, 0x256, 0x256, 0 },
+	{ 0x27d, 0x27d, 0x27d, 0 },
+	{ 0x2a4, 0x2a4, 0x2a4, 0 },
+	{ 0x2ce, 0x2ce, 0x2ce, 0 },
+	{ 0x2f9, 0x2f9, 0x2f9, 0 },
+	{ 0x325, 0x325, 0x325, 0 },
+	{ 0x352, 0x352, 0x352, 0 },
+	{ 0x381, 0x381, 0x381, 0 },
+	{ 0x3b2, 0x3b2, 0x3b2, 0 },
+	{ 0x3e4, 0x3e4, 0x3e4, 0 },
+	{ 0x418, 0x418, 0x418, 0 },
+	{ 0x44d, 0x44d, 0x44d, 0 },
+	{ 0x484, 0x484, 0x484, 0 },
+	{ 0x4bc, 0x4bc, 0x4bc, 0 },
+	{ 0x4f6, 0x4f6, 0x4f6, 0 },
+	{ 0x531, 0x531, 0x531, 0 },
+	{ 0x56e, 0x56e, 0x56e, 0 },
+	{ 0x5ad, 0x5ad, 0x5ad, 0 },
+	{ 0x5ed, 0x5ed, 0x5ed, 0 },
+	{ 0x62f, 0x62f, 0x62f, 0 },
+	{ 0x672, 0x672, 0x672, 0 },
+	{ 0x6b7, 0x6b7, 0x6b7, 0 },
+	{ 0x6fe, 0x6fe, 0x6fe, 0 },
+	{ 0x746, 0x746, 0x746, 0 },
+	{ 0x791, 0x791, 0x791, 0 },
+	{ 0x7dc, 0x7dc, 0x7dc, 0 },
+	{ 0x82a, 0x82a, 0x82a, 0 },
+	{ 0x879, 0x879, 0x879, 0 },
+	{ 0x8ca, 0x8ca, 0x8ca, 0 },
+	{ 0x91d, 0x91d, 0x91d, 0 },
+	{ 0x971, 0x971, 0x971, 0 },
+	{ 0x9c7, 0x9c7, 0x9c7, 0 },
+	{ 0xa1f, 0xa1f, 0xa1f, 0 },
+	{ 0xa79, 0xa79, 0xa79, 0 },
+	{ 0xad4, 0xad4, 0xad4, 0 },
+	{ 0xb32, 0xb32, 0xb32, 0 },
+	{ 0xb91, 0xb91, 0xb91, 0 },
+	{ 0xbf2, 0xbf2, 0xbf2, 0 },
+	{ 0xc54, 0xc54, 0xc54, 0 },
+	{ 0xcb9, 0xcb9, 0xcb9, 0 },
+	{ 0xd1f, 0xd1f, 0xd1f, 0 },
+	{ 0xd88, 0xd88, 0xd88, 0 },
+	{ 0xdf2, 0xdf2, 0xdf2, 0 },
+	{ 0xe5e, 0xe5e, 0xe5e, 0 },
+	{ 0xecc, 0xecc, 0xecc, 0 },
+	{ 0xf3c, 0xf3c, 0xf3c, 0 },
+	{ 0xfad, 0xfad, 0xfad, 0 },
+	{ 0x1021, 0x1021, 0x1021, 0 },
+	{ 0x1096, 0x1096, 0x1096, 0 },
+	{ 0x110e, 0x110e, 0x110e, 0 },
+	{ 0x1187, 0x1187, 0x1187, 0 },
+	{ 0x1203, 0x1203, 0x1203, 0 },
+	{ 0x1280, 0x1280, 0x1280, 0 },
+	{ 0x12ff, 0x12ff, 0x12ff, 0 },
+	{ 0x1380, 0x1380, 0x1380, 0 },
+	{ 0x1404, 0x1404, 0x1404, 0 },
+	{ 0x1489, 0x1489, 0x1489, 0 },
+	{ 0x1510, 0x1510, 0x1510, 0 },
+	{ 0x1599, 0x1599, 0x1599, 0 },
+	{ 0x1624, 0x1624, 0x1624, 0 },
+	{ 0x16b2, 0x16b2, 0x16b2, 0 },
+	{ 0x1741, 0x1741, 0x1741, 0 },
+	{ 0x17d2, 0x17d2, 0x17d2, 0 },
+	{ 0x1865, 0x1865, 0x1865, 0 },
+	{ 0x18fb, 0x18fb, 0x18fb, 0 },
+	{ 0x1992, 0x1992, 0x1992, 0 },
+	{ 0x1a2c, 0x1a2c, 0x1a2c, 0 },
+	{ 0x1ac8, 0x1ac8, 0x1ac8, 0 },
+	{ 0x1b65, 0x1b65, 0x1b65, 0 },
+	{ 0x1c05, 0x1c05, 0x1c05, 0 },
+	{ 0x1ca7, 0x1ca7, 0x1ca7, 0 },
+	{ 0x1d4b, 0x1d4b, 0x1d4b, 0 },
+	{ 0x1df1, 0x1df1, 0x1df1, 0 },
+	{ 0x1e99, 0x1e99, 0x1e99, 0 },
+	{ 0x1f44, 0x1f44, 0x1f44, 0 },
+	{ 0x1ff0, 0x1ff0, 0x1ff0, 0 },
+	{ 0x209f, 0x209f, 0x209f, 0 },
+	{ 0x2150, 0x2150, 0x2150, 0 },
+	{ 0x2203, 0x2203, 0x2203, 0 },
+	{ 0x22b8, 0x22b8, 0x22b8, 0 },
+	{ 0x2370, 0x2370, 0x2370, 0 },
+	{ 0x2429, 0x2429, 0x2429, 0 },
+	{ 0x24e5, 0x24e5, 0x24e5, 0 },
+	{ 0x25a3, 0x25a3, 0x25a3, 0 },
+	{ 0x2663, 0x2663, 0x2663, 0 },
+	{ 0x2726, 0x2726, 0x2726, 0 },
+	{ 0x27ea, 0x27ea, 0x27ea, 0 },
+	{ 0x28b1, 0x28b1, 0x28b1, 0 },
+	{ 0x297a, 0x297a, 0x297a, 0 },
+	{ 0x2a45, 0x2a45, 0x2a45, 0 },
+	{ 0x2b13, 0x2b13, 0x2b13, 0 },
+	{ 0x2be3, 0x2be3, 0x2be3, 0 },
+	{ 0x2cb5, 0x2cb5, 0x2cb5, 0 },
+	{ 0x2d89, 0x2d89, 0x2d89, 0 },
+	{ 0x2e60, 0x2e60, 0x2e60, 0 },
+	{ 0x2f39, 0x2f39, 0x2f39, 0 },
+	{ 0x3014, 0x3014, 0x3014, 0 },
+	{ 0x30f2, 0x30f2, 0x30f2, 0 },
+	{ 0x31d2, 0x31d2, 0x31d2, 0 },
+	{ 0x32b4, 0x32b4, 0x32b4, 0 },
+	{ 0x3398, 0x3398, 0x3398, 0 },
+	{ 0x347f, 0x347f, 0x347f, 0 },
+	{ 0x3569, 0x3569, 0x3569, 0 },
+	{ 0x3654, 0x3654, 0x3654, 0 },
+	{ 0x3742, 0x3742, 0x3742, 0 },
+	{ 0x3832, 0x3832, 0x3832, 0 },
+	{ 0x3925, 0x3925, 0x3925, 0 },
+	{ 0x3a1a, 0x3a1a, 0x3a1a, 0 },
+	{ 0x3b11, 0x3b11, 0x3b11, 0 },
+	{ 0x3c0b, 0x3c0b, 0x3c0b, 0 },
+	{ 0x3d07, 0x3d07, 0x3d07, 0 },
+	{ 0x3e05, 0x3e05, 0x3e05, 0 },
+	{ 0x3f06, 0x3f06, 0x3f06, 0 },
+	{ 0x400a, 0x400a, 0x400a, 0 },
+	{ 0x410f, 0x410f, 0x410f, 0 },
+	{ 0x4218, 0x4218, 0x4218, 0 },
+	{ 0x4322, 0x4322, 0x4322, 0 },
+	{ 0x442f, 0x442f, 0x442f, 0 },
+	{ 0x453f, 0x453f, 0x453f, 0 },
+	{ 0x4650, 0x4650, 0x4650, 0 },
+	{ 0x4765, 0x4765, 0x4765, 0 },
+	{ 0x487c, 0x487c, 0x487c, 0 },
+	{ 0x4995, 0x4995, 0x4995, 0 },
+	{ 0x4ab1, 0x4ab1, 0x4ab1, 0 },
+	{ 0x4bcf, 0x4bcf, 0x4bcf, 0 },
+	{ 0x4cf0, 0x4cf0, 0x4cf0, 0 },
+	{ 0x4e13, 0x4e13, 0x4e13, 0 },
+	{ 0x4f39, 0x4f39, 0x4f39, 0 },
+	{ 0x5061, 0x5061, 0x5061, 0 },
+	{ 0x518b, 0x518b, 0x518b, 0 },
+	{ 0x52b9, 0x52b9, 0x52b9, 0 },
+	{ 0x53e8, 0x53e8, 0x53e8, 0 },
+	{ 0x551b, 0x551b, 0x551b, 0 },
+	{ 0x5650, 0x5650, 0x5650, 0 },
+	{ 0x5787, 0x5787, 0x5787, 0 },
+	{ 0x58c1, 0x58c1, 0x58c1, 0 },
+	{ 0x59fd, 0x59fd, 0x59fd, 0 },
+	{ 0x5b3c, 0x5b3c, 0x5b3c, 0 },
+	{ 0x5c7e, 0x5c7e, 0x5c7e, 0 },
+	{ 0x5dc2, 0x5dc2, 0x5dc2, 0 },
+	{ 0x5f09, 0x5f09, 0x5f09, 0 },
+	{ 0x6052, 0x6052, 0x6052, 0 },
+	{ 0x619e, 0x619e, 0x619e, 0 },
+	{ 0x62ec, 0x62ec, 0x62ec, 0 },
+	{ 0x643d, 0x643d, 0x643d, 0 },
+	{ 0x6591, 0x6591, 0x6591, 0 },
+	{ 0x66e7, 0x66e7, 0x66e7, 0 },
+	{ 0x6840, 0x6840, 0x6840, 0 },
+	{ 0x699b, 0x699b, 0x699b, 0 },
+	{ 0x6afa, 0x6afa, 0x6afa, 0 },
+	{ 0x6c5a, 0x6c5a, 0x6c5a, 0 },
+	{ 0x6dbe, 0x6dbe, 0x6dbe, 0 },
+	{ 0x6f24, 0x6f24, 0x6f24, 0 },
+	{ 0x708c, 0x708c, 0x708c, 0 },
+	{ 0x71f8, 0x71f8, 0x71f8, 0 },
+	{ 0x7366, 0x7366, 0x7366, 0 },
+	{ 0x74d6, 0x74d6, 0x74d6, 0 },
+	{ 0x764a, 0x764a, 0x764a, 0 },
+	{ 0x77c0, 0x77c0, 0x77c0, 0 },
+	{ 0x7938, 0x7938, 0x7938, 0 },
+	{ 0x7ab4, 0x7ab4, 0x7ab4, 0 },
+	{ 0x7c32, 0x7c32, 0x7c32, 0 },
+	{ 0x7db3, 0x7db3, 0x7db3, 0 },
+	{ 0x7f36, 0x7f36, 0x7f36, 0 },
+	{ 0x80bc, 0x80bc, 0x80bc, 0 },
+	{ 0x8245, 0x8245, 0x8245, 0 },
+	{ 0x83d1, 0x83d1, 0x83d1, 0 },
+	{ 0x855f, 0x855f, 0x855f, 0 },
+	{ 0x86f0, 0x86f0, 0x86f0, 0 },
+	{ 0x8884, 0x8884, 0x8884, 0 },
+	{ 0x8a1a, 0x8a1a, 0x8a1a, 0 },
+	{ 0x8bb4, 0x8bb4, 0x8bb4, 0 },
+	{ 0x8d50, 0x8d50, 0x8d50, 0 },
+	{ 0x8eee, 0x8eee, 0x8eee, 0 },
+	{ 0x9090, 0x9090, 0x9090, 0 },
+	{ 0x9234, 0x9234, 0x9234, 0 },
+	{ 0x93db, 0x93db, 0x93db, 0 },
+	{ 0x9585, 0x9585, 0x9585, 0 },
+	{ 0x9732, 0x9732, 0x9732, 0 },
+	{ 0x98e1, 0x98e1, 0x98e1, 0 },
+	{ 0x9a93, 0x9a93, 0x9a93, 0 },
+	{ 0x9c48, 0x9c48, 0x9c48, 0 },
+	{ 0x9e00, 0x9e00, 0x9e00, 0 },
+	{ 0x9fbb, 0x9fbb, 0x9fbb, 0 },
+	{ 0xa178, 0xa178, 0xa178, 0 },
+	{ 0xa338, 0xa338, 0xa338, 0 },
+	{ 0xa4fb, 0xa4fb, 0xa4fb, 0 },
+	{ 0xa6c1, 0xa6c1, 0xa6c1, 0 },
+	{ 0xa88a, 0xa88a, 0xa88a, 0 },
+	{ 0xaa56, 0xaa56, 0xaa56, 0 },
+	{ 0xac24, 0xac24, 0xac24, 0 },
+	{ 0xadf5, 0xadf5, 0xadf5, 0 },
+	{ 0xafc9, 0xafc9, 0xafc9, 0 },
+	{ 0xb1a0, 0xb1a0, 0xb1a0, 0 },
+	{ 0xb37a, 0xb37a, 0xb37a, 0 },
+	{ 0xb557, 0xb557, 0xb557, 0 },
+	{ 0xb736, 0xb736, 0xb736, 0 },
+	{ 0xb919, 0xb919, 0xb919, 0 },
+	{ 0xbafe, 0xbafe, 0xbafe, 0 },
+	{ 0xbce6, 0xbce6, 0xbce6, 0 },
+	{ 0xbed2, 0xbed2, 0xbed2, 0 },
+	{ 0xc0c0, 0xc0c0, 0xc0c0, 0 },
+	{ 0xc2b0, 0xc2b0, 0xc2b0, 0 },
+	{ 0xc4a4, 0xc4a4, 0xc4a4, 0 },
+	{ 0xc69b, 0xc69b, 0xc69b, 0 },
+	{ 0xc895, 0xc895, 0xc895, 0 },
+	{ 0xca91, 0xca91, 0xca91, 0 },
+	{ 0xcc91, 0xcc91, 0xcc91, 0 },
+	{ 0xce93, 0xce93, 0xce93, 0 },
+	{ 0xd098, 0xd098, 0xd098, 0 },
+	{ 0xd2a1, 0xd2a1, 0xd2a1, 0 },
+	{ 0xd4ac, 0xd4ac, 0xd4ac, 0 },
+	{ 0xd6ba, 0xd6ba, 0xd6ba, 0 },
+	{ 0xd8cb, 0xd8cb, 0xd8cb, 0 },
+	{ 0xdadf, 0xdadf, 0xdadf, 0 },
+	{ 0xdcf7, 0xdcf7, 0xdcf7, 0 },
+	{ 0xdf11, 0xdf11, 0xdf11, 0 },
+	{ 0xe12e, 0xe12e, 0xe12e, 0 },
+	{ 0xe34e, 0xe34e, 0xe34e, 0 },
+	{ 0xe571, 0xe571, 0xe571, 0 },
+	{ 0xe796, 0xe796, 0xe796, 0 },
+	{ 0xe9bf, 0xe9bf, 0xe9bf, 0 },
+	{ 0xebeb, 0xebeb, 0xebeb, 0 },
+	{ 0xee1a, 0xee1a, 0xee1a, 0 },
+	{ 0xf04c, 0xf04c, 0xf04c, 0 },
+	{ 0xf281, 0xf281, 0xf281, 0 },
+	{ 0xf4b9, 0xf4b9, 0xf4b9, 0 },
+	{ 0xf6f4, 0xf6f4, 0xf6f4, 0 },
+	{ 0xf932, 0xf932, 0xf932, 0 },
+	{ 0xfb73, 0xfb73, 0xfb73, 0 },
+	{ 0xfdb7, 0xfdb7, 0xfdb7, 0 },
+	{ 0xffff, 0xffff, 0xffff, 0 },
+};
+
+const struct vkms_color_lut srgb_eotf = {
+	.base = srgb_array,
+	.lut_length = LUT_SIZE,
+	.channel_value2index_ratio = 0xff00ffll
+};
+EXPORT_SYMBOL(srgb_eotf);
+
+static struct drm_color_lut srgb_inv_array[LUT_SIZE] = {
+	{ 0x0, 0x0, 0x0, 0 },
+	{ 0xcc2, 0xcc2, 0xcc2, 0 },
+	{ 0x15be, 0x15be, 0x15be, 0 },
+	{ 0x1c56, 0x1c56, 0x1c56, 0 },
+	{ 0x21bd, 0x21bd, 0x21bd, 0 },
+	{ 0x2666, 0x2666, 0x2666, 0 },
+	{ 0x2a8a, 0x2a8a, 0x2a8a, 0 },
+	{ 0x2e4c, 0x2e4c, 0x2e4c, 0 },
+	{ 0x31c0, 0x31c0, 0x31c0, 0 },
+	{ 0x34f6, 0x34f6, 0x34f6, 0 },
+	{ 0x37f9, 0x37f9, 0x37f9, 0 },
+	{ 0x3acf, 0x3acf, 0x3acf, 0 },
+	{ 0x3d80, 0x3d80, 0x3d80, 0 },
+	{ 0x4010, 0x4010, 0x4010, 0 },
+	{ 0x4284, 0x4284, 0x4284, 0 },
+	{ 0x44dd, 0x44dd, 0x44dd, 0 },
+	{ 0x4720, 0x4720, 0x4720, 0 },
+	{ 0x494e, 0x494e, 0x494e, 0 },
+	{ 0x4b69, 0x4b69, 0x4b69, 0 },
+	{ 0x4d73, 0x4d73, 0x4d73, 0 },
+	{ 0x4f6e, 0x4f6e, 0x4f6e, 0 },
+	{ 0x5159, 0x5159, 0x5159, 0 },
+	{ 0x5337, 0x5337, 0x5337, 0 },
+	{ 0x5509, 0x5509, 0x5509, 0 },
+	{ 0x56cf, 0x56cf, 0x56cf, 0 },
+	{ 0x588a, 0x588a, 0x588a, 0 },
+	{ 0x5a3b, 0x5a3b, 0x5a3b, 0 },
+	{ 0x5be2, 0x5be2, 0x5be2, 0 },
+	{ 0x5d80, 0x5d80, 0x5d80, 0 },
+	{ 0x5f16, 0x5f16, 0x5f16, 0 },
+	{ 0x60a4, 0x60a4, 0x60a4, 0 },
+	{ 0x6229, 0x6229, 0x6229, 0 },
+	{ 0x63a8, 0x63a8, 0x63a8, 0 },
+	{ 0x6520, 0x6520, 0x6520, 0 },
+	{ 0x6691, 0x6691, 0x6691, 0 },
+	{ 0x67fc, 0x67fc, 0x67fc, 0 },
+	{ 0x6961, 0x6961, 0x6961, 0 },
+	{ 0x6ac0, 0x6ac0, 0x6ac0, 0 },
+	{ 0x6c19, 0x6c19, 0x6c19, 0 },
+	{ 0x6d6e, 0x6d6e, 0x6d6e, 0 },
+	{ 0x6ebd, 0x6ebd, 0x6ebd, 0 },
+	{ 0x7008, 0x7008, 0x7008, 0 },
+	{ 0x714d, 0x714d, 0x714d, 0 },
+	{ 0x728f, 0x728f, 0x728f, 0 },
+	{ 0x73cc, 0x73cc, 0x73cc, 0 },
+	{ 0x7504, 0x7504, 0x7504, 0 },
+	{ 0x7639, 0x7639, 0x7639, 0 },
+	{ 0x776a, 0x776a, 0x776a, 0 },
+	{ 0x7897, 0x7897, 0x7897, 0 },
+	{ 0x79c1, 0x79c1, 0x79c1, 0 },
+	{ 0x7ae7, 0x7ae7, 0x7ae7, 0 },
+	{ 0x7c09, 0x7c09, 0x7c09, 0 },
+	{ 0x7d28, 0x7d28, 0x7d28, 0 },
+	{ 0x7e44, 0x7e44, 0x7e44, 0 },
+	{ 0x7f5d, 0x7f5d, 0x7f5d, 0 },
+	{ 0x8073, 0x8073, 0x8073, 0 },
+	{ 0x8186, 0x8186, 0x8186, 0 },
+	{ 0x8296, 0x8296, 0x8296, 0 },
+	{ 0x83a4, 0x83a4, 0x83a4, 0 },
+	{ 0x84ae, 0x84ae, 0x84ae, 0 },
+	{ 0x85b6, 0x85b6, 0x85b6, 0 },
+	{ 0x86bc, 0x86bc, 0x86bc, 0 },
+	{ 0x87bf, 0x87bf, 0x87bf, 0 },
+	{ 0x88bf, 0x88bf, 0x88bf, 0 },
+	{ 0x89be, 0x89be, 0x89be, 0 },
+	{ 0x8ab9, 0x8ab9, 0x8ab9, 0 },
+	{ 0x8bb3, 0x8bb3, 0x8bb3, 0 },
+	{ 0x8cab, 0x8cab, 0x8cab, 0 },
+	{ 0x8da0, 0x8da0, 0x8da0, 0 },
+	{ 0x8e93, 0x8e93, 0x8e93, 0 },
+	{ 0x8f84, 0x8f84, 0x8f84, 0 },
+	{ 0x9073, 0x9073, 0x9073, 0 },
+	{ 0x9161, 0x9161, 0x9161, 0 },
+	{ 0x924c, 0x924c, 0x924c, 0 },
+	{ 0x9335, 0x9335, 0x9335, 0 },
+	{ 0x941d, 0x941d, 0x941d, 0 },
+	{ 0x9503, 0x9503, 0x9503, 0 },
+	{ 0x95e7, 0x95e7, 0x95e7, 0 },
+	{ 0x96c9, 0x96c9, 0x96c9, 0 },
+	{ 0x97aa, 0x97aa, 0x97aa, 0 },
+	{ 0x9889, 0x9889, 0x9889, 0 },
+	{ 0x9966, 0x9966, 0x9966, 0 },
+	{ 0x9a42, 0x9a42, 0x9a42, 0 },
+	{ 0x9b1c, 0x9b1c, 0x9b1c, 0 },
+	{ 0x9bf5, 0x9bf5, 0x9bf5, 0 },
+	{ 0x9ccc, 0x9ccc, 0x9ccc, 0 },
+	{ 0x9da1, 0x9da1, 0x9da1, 0 },
+	{ 0x9e76, 0x9e76, 0x9e76, 0 },
+	{ 0x9f49, 0x9f49, 0x9f49, 0 },
+	{ 0xa01a, 0xa01a, 0xa01a, 0 },
+	{ 0xa0ea, 0xa0ea, 0xa0ea, 0 },
+	{ 0xa1b9, 0xa1b9, 0xa1b9, 0 },
+	{ 0xa286, 0xa286, 0xa286, 0 },
+	{ 0xa352, 0xa352, 0xa352, 0 },
+	{ 0xa41d, 0xa41d, 0xa41d, 0 },
+	{ 0xa4e7, 0xa4e7, 0xa4e7, 0 },
+	{ 0xa5af, 0xa5af, 0xa5af, 0 },
+	{ 0xa676, 0xa676, 0xa676, 0 },
+	{ 0xa73c, 0xa73c, 0xa73c, 0 },
+	{ 0xa801, 0xa801, 0xa801, 0 },
+	{ 0xa8c5, 0xa8c5, 0xa8c5, 0 },
+	{ 0xa987, 0xa987, 0xa987, 0 },
+	{ 0xaa48, 0xaa48, 0xaa48, 0 },
+	{ 0xab09, 0xab09, 0xab09, 0 },
+	{ 0xabc8, 0xabc8, 0xabc8, 0 },
+	{ 0xac86, 0xac86, 0xac86, 0 },
+	{ 0xad43, 0xad43, 0xad43, 0 },
+	{ 0xadff, 0xadff, 0xadff, 0 },
+	{ 0xaeba, 0xaeba, 0xaeba, 0 },
+	{ 0xaf74, 0xaf74, 0xaf74, 0 },
+	{ 0xb02d, 0xb02d, 0xb02d, 0 },
+	{ 0xb0e5, 0xb0e5, 0xb0e5, 0 },
+	{ 0xb19c, 0xb19c, 0xb19c, 0 },
+	{ 0xb252, 0xb252, 0xb252, 0 },
+	{ 0xb307, 0xb307, 0xb307, 0 },
+	{ 0xb3bb, 0xb3bb, 0xb3bb, 0 },
+	{ 0xb46f, 0xb46f, 0xb46f, 0 },
+	{ 0xb521, 0xb521, 0xb521, 0 },
+	{ 0xb5d3, 0xb5d3, 0xb5d3, 0 },
+	{ 0xb683, 0xb683, 0xb683, 0 },
+	{ 0xb733, 0xb733, 0xb733, 0 },
+	{ 0xb7e2, 0xb7e2, 0xb7e2, 0 },
+	{ 0xb890, 0xb890, 0xb890, 0 },
+	{ 0xb93d, 0xb93d, 0xb93d, 0 },
+	{ 0xb9ea, 0xb9ea, 0xb9ea, 0 },
+	{ 0xba96, 0xba96, 0xba96, 0 },
+	{ 0xbb40, 0xbb40, 0xbb40, 0 },
+	{ 0xbbea, 0xbbea, 0xbbea, 0 },
+	{ 0xbc94, 0xbc94, 0xbc94, 0 },
+	{ 0xbd3c, 0xbd3c, 0xbd3c, 0 },
+	{ 0xbde4, 0xbde4, 0xbde4, 0 },
+	{ 0xbe8b, 0xbe8b, 0xbe8b, 0 },
+	{ 0xbf31, 0xbf31, 0xbf31, 0 },
+	{ 0xbfd7, 0xbfd7, 0xbfd7, 0 },
+	{ 0xc07b, 0xc07b, 0xc07b, 0 },
+	{ 0xc120, 0xc120, 0xc120, 0 },
+	{ 0xc1c3, 0xc1c3, 0xc1c3, 0 },
+	{ 0xc266, 0xc266, 0xc266, 0 },
+	{ 0xc308, 0xc308, 0xc308, 0 },
+	{ 0xc3a9, 0xc3a9, 0xc3a9, 0 },
+	{ 0xc449, 0xc449, 0xc449, 0 },
+	{ 0xc4e9, 0xc4e9, 0xc4e9, 0 },
+	{ 0xc589, 0xc589, 0xc589, 0 },
+	{ 0xc627, 0xc627, 0xc627, 0 },
+	{ 0xc6c5, 0xc6c5, 0xc6c5, 0 },
+	{ 0xc763, 0xc763, 0xc763, 0 },
+	{ 0xc7ff, 0xc7ff, 0xc7ff, 0 },
+	{ 0xc89b, 0xc89b, 0xc89b, 0 },
+	{ 0xc937, 0xc937, 0xc937, 0 },
+	{ 0xc9d2, 0xc9d2, 0xc9d2, 0 },
+	{ 0xca6c, 0xca6c, 0xca6c, 0 },
+	{ 0xcb06, 0xcb06, 0xcb06, 0 },
+	{ 0xcb9f, 0xcb9f, 0xcb9f, 0 },
+	{ 0xcc37, 0xcc37, 0xcc37, 0 },
+	{ 0xcccf, 0xcccf, 0xcccf, 0 },
+	{ 0xcd66, 0xcd66, 0xcd66, 0 },
+	{ 0xcdfd, 0xcdfd, 0xcdfd, 0 },
+	{ 0xce93, 0xce93, 0xce93, 0 },
+	{ 0xcf29, 0xcf29, 0xcf29, 0 },
+	{ 0xcfbe, 0xcfbe, 0xcfbe, 0 },
+	{ 0xd053, 0xd053, 0xd053, 0 },
+	{ 0xd0e7, 0xd0e7, 0xd0e7, 0 },
+	{ 0xd17a, 0xd17a, 0xd17a, 0 },
+	{ 0xd20d, 0xd20d, 0xd20d, 0 },
+	{ 0xd2a0, 0xd2a0, 0xd2a0, 0 },
+	{ 0xd331, 0xd331, 0xd331, 0 },
+	{ 0xd3c3, 0xd3c3, 0xd3c3, 0 },
+	{ 0xd454, 0xd454, 0xd454, 0 },
+	{ 0xd4e4, 0xd4e4, 0xd4e4, 0 },
+	{ 0xd574, 0xd574, 0xd574, 0 },
+	{ 0xd603, 0xd603, 0xd603, 0 },
+	{ 0xd692, 0xd692, 0xd692, 0 },
+	{ 0xd720, 0xd720, 0xd720, 0 },
+	{ 0xd7ae, 0xd7ae, 0xd7ae, 0 },
+	{ 0xd83c, 0xd83c, 0xd83c, 0 },
+	{ 0xd8c9, 0xd8c9, 0xd8c9, 0 },
+	{ 0xd955, 0xd955, 0xd955, 0 },
+	{ 0xd9e1, 0xd9e1, 0xd9e1, 0 },
+	{ 0xda6d, 0xda6d, 0xda6d, 0 },
+	{ 0xdaf8, 0xdaf8, 0xdaf8, 0 },
+	{ 0xdb83, 0xdb83, 0xdb83, 0 },
+	{ 0xdc0d, 0xdc0d, 0xdc0d, 0 },
+	{ 0xdc97, 0xdc97, 0xdc97, 0 },
+	{ 0xdd20, 0xdd20, 0xdd20, 0 },
+	{ 0xdda9, 0xdda9, 0xdda9, 0 },
+	{ 0xde31, 0xde31, 0xde31, 0 },
+	{ 0xdeb9, 0xdeb9, 0xdeb9, 0 },
+	{ 0xdf41, 0xdf41, 0xdf41, 0 },
+	{ 0xdfc8, 0xdfc8, 0xdfc8, 0 },
+	{ 0xe04f, 0xe04f, 0xe04f, 0 },
+	{ 0xe0d5, 0xe0d5, 0xe0d5, 0 },
+	{ 0xe15b, 0xe15b, 0xe15b, 0 },
+	{ 0xe1e0, 0xe1e0, 0xe1e0, 0 },
+	{ 0xe266, 0xe266, 0xe266, 0 },
+	{ 0xe2ea, 0xe2ea, 0xe2ea, 0 },
+	{ 0xe36f, 0xe36f, 0xe36f, 0 },
+	{ 0xe3f3, 0xe3f3, 0xe3f3, 0 },
+	{ 0xe476, 0xe476, 0xe476, 0 },
+	{ 0xe4f9, 0xe4f9, 0xe4f9, 0 },
+	{ 0xe57c, 0xe57c, 0xe57c, 0 },
+	{ 0xe5fe, 0xe5fe, 0xe5fe, 0 },
+	{ 0xe680, 0xe680, 0xe680, 0 },
+	{ 0xe702, 0xe702, 0xe702, 0 },
+	{ 0xe783, 0xe783, 0xe783, 0 },
+	{ 0xe804, 0xe804, 0xe804, 0 },
+	{ 0xe884, 0xe884, 0xe884, 0 },
+	{ 0xe905, 0xe905, 0xe905, 0 },
+	{ 0xe984, 0xe984, 0xe984, 0 },
+	{ 0xea04, 0xea04, 0xea04, 0 },
+	{ 0xea83, 0xea83, 0xea83, 0 },
+	{ 0xeb02, 0xeb02, 0xeb02, 0 },
+	{ 0xeb80, 0xeb80, 0xeb80, 0 },
+	{ 0xebfe, 0xebfe, 0xebfe, 0 },
+	{ 0xec7b, 0xec7b, 0xec7b, 0 },
+	{ 0xecf9, 0xecf9, 0xecf9, 0 },
+	{ 0xed76, 0xed76, 0xed76, 0 },
+	{ 0xedf2, 0xedf2, 0xedf2, 0 },
+	{ 0xee6f, 0xee6f, 0xee6f, 0 },
+	{ 0xeeeb, 0xeeeb, 0xeeeb, 0 },
+	{ 0xef66, 0xef66, 0xef66, 0 },
+	{ 0xefe2, 0xefe2, 0xefe2, 0 },
+	{ 0xf05d, 0xf05d, 0xf05d, 0 },
+	{ 0xf0d7, 0xf0d7, 0xf0d7, 0 },
+	{ 0xf152, 0xf152, 0xf152, 0 },
+	{ 0xf1cc, 0xf1cc, 0xf1cc, 0 },
+	{ 0xf245, 0xf245, 0xf245, 0 },
+	{ 0xf2bf, 0xf2bf, 0xf2bf, 0 },
+	{ 0xf338, 0xf338, 0xf338, 0 },
+	{ 0xf3b0, 0xf3b0, 0xf3b0, 0 },
+	{ 0xf429, 0xf429, 0xf429, 0 },
+	{ 0xf4a1, 0xf4a1, 0xf4a1, 0 },
+	{ 0xf519, 0xf519, 0xf519, 0 },
+	{ 0xf590, 0xf590, 0xf590, 0 },
+	{ 0xf608, 0xf608, 0xf608, 0 },
+	{ 0xf67e, 0xf67e, 0xf67e, 0 },
+	{ 0xf6f5, 0xf6f5, 0xf6f5, 0 },
+	{ 0xf76b, 0xf76b, 0xf76b, 0 },
+	{ 0xf7e1, 0xf7e1, 0xf7e1, 0 },
+	{ 0xf857, 0xf857, 0xf857, 0 },
+	{ 0xf8cd, 0xf8cd, 0xf8cd, 0 },
+	{ 0xf942, 0xf942, 0xf942, 0 },
+	{ 0xf9b7, 0xf9b7, 0xf9b7, 0 },
+	{ 0xfa2b, 0xfa2b, 0xfa2b, 0 },
+	{ 0xfaa0, 0xfaa0, 0xfaa0, 0 },
+	{ 0xfb14, 0xfb14, 0xfb14, 0 },
+	{ 0xfb88, 0xfb88, 0xfb88, 0 },
+	{ 0xfbfb, 0xfbfb, 0xfbfb, 0 },
+	{ 0xfc6e, 0xfc6e, 0xfc6e, 0 },
+	{ 0xfce1, 0xfce1, 0xfce1, 0 },
+	{ 0xfd54, 0xfd54, 0xfd54, 0 },
+	{ 0xfdc6, 0xfdc6, 0xfdc6, 0 },
+	{ 0xfe39, 0xfe39, 0xfe39, 0 },
+	{ 0xfeaa, 0xfeaa, 0xfeaa, 0 },
+	{ 0xff1c, 0xff1c, 0xff1c, 0 },
+	{ 0xff8d, 0xff8d, 0xff8d, 0 },
+	{ 0xffff, 0xffff, 0xffff, 0 },
+};
+
+const struct vkms_color_lut srgb_inv_eotf = {
+	.base = srgb_inv_array,
+	.lut_length = LUT_SIZE,
+	.channel_value2index_ratio = 0xff00ffll
+};
+EXPORT_SYMBOL(srgb_inv_eotf);
diff --git a/drivers/gpu/drm/vkms/vkms_luts.h b/drivers/gpu/drm/vkms/vkms_luts.h
new file mode 100644
index 000000000000..925a4a7b84e2
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_luts.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _VKMS_LUTS_H_
+#define _VKMS_LUTS_H_
+
+#define LUT_SIZE 256
+
+extern const struct vkms_color_lut linear_eotf;
+extern const struct vkms_color_lut srgb_eotf;
+extern const struct vkms_color_lut srgb_inv_eotf;
+
+#endif /* _VKMS_LUTS_H_ */
diff --git a/drivers/gpu/drm/vkms/vkms_output.c b/drivers/gpu/drm/vkms/vkms_output.c
index 81d17b7dc0eb..86ce07a617f5 100644
--- a/drivers/gpu/drm/vkms/vkms_output.c
+++ b/drivers/gpu/drm/vkms/vkms_output.c
@@ -20,11 +20,7 @@ int vkms_output_init(struct vkms_device *vkmsdev)
 		return -EINVAL;
 
 	vkms_config_for_each_plane(vkmsdev->config, plane_cfg) {
-		enum drm_plane_type type;
-
-		type = vkms_config_plane_get_type(plane_cfg);
-
-		plane_cfg->plane = vkms_plane_init(vkmsdev, type);
+		plane_cfg->plane = vkms_plane_init(vkmsdev, plane_cfg);
 		if (IS_ERR(plane_cfg->plane)) {
 			DRM_DEV_ERROR(dev->dev, "Failed to init vkms plane\n");
 			return PTR_ERR(plane_cfg->plane);
diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c
index 89a9fc91e059..19fe6acad306 100644
--- a/drivers/gpu/drm/vkms/vkms_plane.c
+++ b/drivers/gpu/drm/vkms/vkms_plane.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0+
 
+#include "vkms_config.h"
 #include <linux/iosys-map.h>
 
 #include <drm/drm_atomic.h>
@@ -218,7 +219,7 @@ static const struct drm_plane_helper_funcs vkms_plane_helper_funcs = {
 };
 
 struct vkms_plane *vkms_plane_init(struct vkms_device *vkmsdev,
-				   enum drm_plane_type type)
+				   struct vkms_config_plane *plane_cfg)
 {
 	struct drm_device *dev = &vkmsdev->drm;
 	struct vkms_plane *plane;
@@ -226,7 +227,8 @@ struct vkms_plane *vkms_plane_init(struct vkms_device *vkmsdev,
 	plane = drmm_universal_plane_alloc(dev, struct vkms_plane, base, 0,
 					   &vkms_plane_funcs,
 					   vkms_formats, ARRAY_SIZE(vkms_formats),
-					   NULL, type, NULL);
+					   NULL, vkms_config_plane_get_type(plane_cfg),
+					   NULL);
 	if (IS_ERR(plane))
 		return plane;
 
@@ -244,5 +246,8 @@ struct vkms_plane *vkms_plane_init(struct vkms_device *vkmsdev,
 					  DRM_COLOR_YCBCR_BT601,
 					  DRM_COLOR_YCBCR_FULL_RANGE);
 
+	if (vkms_config_plane_get_default_pipeline(plane_cfg))
+		vkms_initialize_colorops(&plane->base);
+
 	return plane;
 }
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index e365df6af353..3f475f0e6545 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -71,6 +71,15 @@ u32 host1x_sync_readl(struct host1x *host1x, u32 r)
 	return readl(sync_regs + r);
 }
 
+#ifdef CONFIG_64BIT
+u64 host1x_sync_readq(struct host1x *host1x, u32 r)
+{
+	void __iomem *sync_regs = host1x->regs + host1x->info->sync_offset;
+
+	return readq(sync_regs + r);
+}
+#endif
+
 void host1x_ch_writel(struct host1x_channel *ch, u32 v, u32 r)
 {
 	writel(v, ch->regs + r);
diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h
index d3855a1c6b47..ef44618ed88a 100644
--- a/drivers/gpu/host1x/dev.h
+++ b/drivers/gpu/host1x/dev.h
@@ -179,6 +179,9 @@ void host1x_hypervisor_writel(struct host1x *host1x, u32 v, u32 r);
 u32 host1x_hypervisor_readl(struct host1x *host1x, u32 r);
 void host1x_sync_writel(struct host1x *host1x, u32 v, u32 r);
 u32 host1x_sync_readl(struct host1x *host1x, u32 r);
+#ifdef CONFIG_64BIT
+u64 host1x_sync_readq(struct host1x *host1x, u32 r);
+#endif
 void host1x_ch_writel(struct host1x_channel *ch, u32 v, u32 r);
 u32 host1x_ch_readl(struct host1x_channel *ch, u32 r);
 
diff --git a/drivers/gpu/host1x/hw/intr_hw.c b/drivers/gpu/host1x/hw/intr_hw.c
index 415f8d7e4202..bd5b5ef62f35 100644
--- a/drivers/gpu/host1x/hw/intr_hw.c
+++ b/drivers/gpu/host1x/hw/intr_hw.c
@@ -11,26 +11,64 @@
 #include "../intr.h"
 #include "../dev.h"
 
+static void process_32_syncpts(struct host1x *host, unsigned long val, u32 reg_offset)
+{
+	unsigned int id;
+
+	if (!val)
+		return;
+
+	host1x_sync_writel(host, val, HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(reg_offset));
+	host1x_sync_writel(host, val, HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(reg_offset));
+
+	for_each_set_bit(id, &val, 32)
+		host1x_intr_handle_interrupt(host, reg_offset * 32 + id);
+}
+
 static irqreturn_t syncpt_thresh_isr(int irq, void *dev_id)
 {
 	struct host1x_intr_irq_data *irq_data = dev_id;
 	struct host1x *host = irq_data->host;
 	unsigned long reg;
-	unsigned int i, id;
+	unsigned int i;
 
+#if !defined(CONFIG_64BIT)
 	for (i = irq_data->offset; i < DIV_ROUND_UP(host->info->nb_pts, 32);
 	     i += host->num_syncpt_irqs) {
 		reg = host1x_sync_readl(host,
 			HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(i));
 
-		host1x_sync_writel(host, reg,
-			HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(i));
-		host1x_sync_writel(host, reg,
+		process_32_syncpts(host, reg, i);
+	}
+#elif HOST1X_HW == 6 || HOST1X_HW == 7
+	/*
+	 * Tegra186 and Tegra194 have the first INT_STATUS register not 64-bit aligned,
+	 * and only have one interrupt line.
+	 */
+	reg = host1x_sync_readl(host, HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(0));
+	process_32_syncpts(host, reg, 0);
+
+	for (i = 1; i < (host->info->nb_pts / 32) - 1; i += 2) {
+		reg = host1x_sync_readq(host,
 			HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(i));
 
-		for_each_set_bit(id, &reg, 32)
-			host1x_intr_handle_interrupt(host, i * 32 + id);
+		process_32_syncpts(host, lower_32_bits(reg), i);
+		process_32_syncpts(host, upper_32_bits(reg), i + 1);
+	}
+
+	reg = host1x_sync_readl(host, HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(i));
+	process_32_syncpts(host, reg, i);
+#else
+	/* All 64-bit capable SoCs have number of syncpoints divisible by 64 */
+	for (i = irq_data->offset; i < DIV_ROUND_UP(host->info->nb_pts, 64);
+	     i += host->num_syncpt_irqs) {
+		reg = host1x_sync_readq(host,
+			HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(i * 2));
+
+		process_32_syncpts(host, lower_32_bits(reg), i * 2 + 0);
+		process_32_syncpts(host, upper_32_bits(reg), i * 2 + 1);
 	}
+#endif
 
 	return IRQ_HANDLED;
 }
@@ -68,12 +106,12 @@ host1x_intr_init_host_sync(struct host1x *host, u32 cpm)
 
 	/*
 	 * Program threshold interrupt destination among 8 lines per VM,
-	 * per syncpoint. For each group of 32 syncpoints (corresponding to one
-	 * interrupt status register), direct to one interrupt line, going
+	 * per syncpoint. For each group of 64 syncpoints (corresponding to two
+	 * interrupt status registers), direct to one interrupt line, going
 	 * around in a round robin fashion.
 	 */
 	for (id = 0; id < host->info->nb_pts; id++) {
-		u32 reg_offset = id / 32;
+		u32 reg_offset = id / 64;
 		u32 irq_index = reg_offset % host->num_syncpt_irqs;
 
 		host1x_sync_writel(host, irq_index, HOST1X_SYNC_SYNCPT_INTR_DEST(id));