From 414938db7a335d0ba6579abf402cfaafdc98bae7 Mon Sep 17 00:00:00 2001
From: Peter Jung <admin@ptr1337.dev>
Date: Wed, 29 Nov 2023 19:55:12 +0100
Subject: [PATCH 1/7] amd-hdr

Signed-off-by: Peter Jung <admin@ptr1337.dev>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h      |  71 ++
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c |  34 +-
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h | 100 +++
 .../amd/display/amdgpu_dm/amdgpu_dm_color.c   | 805 ++++++++++++++++--
 .../amd/display/amdgpu_dm/amdgpu_dm_crtc.c    |  72 ++
 .../amd/display/amdgpu_dm/amdgpu_dm_plane.c   | 224 ++++-
 .../amd/display/dc/dcn10/dcn10_cm_common.c    |  95 ++-
 .../drm/amd/display/dc/dcn30/dcn30_hwseq.c    |  37 +
 .../drm/amd/display/dc/dcn30/dcn30_hwseq.h    |   3 +
 .../drm/amd/display/dc/dcn301/dcn301_init.c   |   2 +-
 .../gpu/drm/amd/display/include/fixed31_32.h  |  12 +
 drivers/gpu/drm/arm/malidp_crtc.c             |   2 +-
 drivers/gpu/drm/drm_atomic.c                  |   1 +
 drivers/gpu/drm/drm_atomic_state_helper.c     |   1 +
 drivers/gpu/drm/drm_property.c                |  49 ++
 include/drm/drm_mode_object.h                 |   2 +-
 include/drm/drm_plane.h                       |   7 +
 include/drm/drm_property.h                    |   6 +
 include/uapi/drm/drm_mode.h                   |   8 +
 19 files changed, 1441 insertions(+), 90 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index 32fe05c810c6f..84bf501b02f4c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -343,6 +343,77 @@ struct amdgpu_mode_info {
 	int			disp_priority;
 	const struct amdgpu_display_funcs *funcs;
 	const enum drm_plane_type *plane_type;
+
+	/* Driver-private color mgmt props */
+
+	/* @plane_degamma_lut_property: Plane property to set a degamma LUT to
+	 * convert input space before blending.
+	 */
+	struct drm_property *plane_degamma_lut_property;
+	/* @plane_degamma_lut_size_property: Plane property to define the max
+	 * size of degamma LUT as supported by the driver (read-only).
+	 */
+	struct drm_property *plane_degamma_lut_size_property;
+	/**
+	 * @plane_degamma_tf_property: Plane pre-defined transfer function to
+	 * to go from scanout/encoded values to linear values.
+	 */
+	struct drm_property *plane_degamma_tf_property;
+	/**
+	 * @plane_hdr_mult_property:
+	 */
+	struct drm_property *plane_hdr_mult_property;
+
+	struct drm_property *plane_ctm_property;
+	/**
+	 * @shaper_lut_property: Plane property to set pre-blending shaper LUT
+	 * that converts color content before 3D LUT.
+	 */
+	struct drm_property *plane_shaper_lut_property;
+	/**
+	 * @shaper_lut_size_property: Plane property for the size of
+	 * pre-blending shaper LUT as supported by the driver (read-only).
+	 */
+	struct drm_property *plane_shaper_lut_size_property;
+	/**
+	 * @plane_shaper_tf_property: Plane property to set a predefined
+	 * transfer function for pre-blending shaper (before applying 3D LUT)
+	 * with or without LUT.
+	 */
+	struct drm_property *plane_shaper_tf_property;
+	/**
+	 * @plane_lut3d_property: Plane property for gamma correction using a
+	 * 3D LUT (pre-blending).
+	 */
+	struct drm_property *plane_lut3d_property;
+	/**
+	 * @plane_degamma_lut_size_property: Plane property to define the max
+	 * size of 3D LUT as supported by the driver (read-only).
+	 */
+	struct drm_property *plane_lut3d_size_property;
+	/**
+	 * @plane_blend_lut_property: Plane property for output gamma before
+	 * blending. Userspace set a blend LUT to convert colors after 3D LUT
+	 * conversion. It works as a post-3D LUT 1D LUT, with shaper LUT, they
+	 * are sandwiching 3D LUT with two 1D LUT.
+	 */
+	struct drm_property *plane_blend_lut_property;
+	/**
+	 * @plane_blend_lut_size_property: Plane property to define the max
+	 * size of blend LUT as supported by the driver (read-only).
+	 */
+	struct drm_property *plane_blend_lut_size_property;
+	/**
+	 * @plane_blend_tf_property: Plane property to set a predefined
+	 * transfer function for pre-blending blend (before applying 3D LUT)
+	 * with or without LUT.
+	 */
+	struct drm_property *plane_blend_tf_property;
+	/* @regamma_tf_property: Transfer function for CRTC regamma
+	 * (post-blending). Possible values are defined by `enum
+	 * amdgpu_transfer_function`.
+	 */
+	struct drm_property *regamma_tf_property;
 };
 
 #define AMDGPU_MAX_BL_LEVEL 0xFF
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 deedcd9978459..572c71a54df42 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4022,6 +4022,11 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev)
 		return r;
 	}
 
+#ifdef AMD_PRIVATE_COLOR
+	if (amdgpu_dm_create_color_properties(adev))
+		return -ENOMEM;
+#endif
+
 	r = amdgpu_dm_audio_init(adev);
 	if (r) {
 		dc_release_state(state->context);
@@ -5094,7 +5099,9 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 	 * Always set input transfer function, since plane state is refreshed
 	 * every time.
 	 */
-	ret = amdgpu_dm_update_plane_color_mgmt(dm_crtc_state, dc_plane_state);
+	ret = amdgpu_dm_update_plane_color_mgmt(dm_crtc_state,
+						plane_state,
+						dc_plane_state);
 	if (ret)
 		return ret;
 
@@ -8117,6 +8124,10 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			bundle->surface_updates[planes_count].gamma = dc_plane->gamma_correction;
 			bundle->surface_updates[planes_count].in_transfer_func = dc_plane->in_transfer_func;
 			bundle->surface_updates[planes_count].gamut_remap_matrix = &dc_plane->gamut_remap_matrix;
+			bundle->surface_updates[planes_count].hdr_mult = dc_plane->hdr_mult;
+			bundle->surface_updates[planes_count].func_shaper = dc_plane->in_shaper_func;
+			bundle->surface_updates[planes_count].lut3d_func = dc_plane->lut3d_func;
+			bundle->surface_updates[planes_count].blend_tf = dc_plane->blend_tf;
 		}
 
 		amdgpu_dm_plane_fill_dc_scaling_info(dm->adev, new_plane_state,
@@ -8328,6 +8339,10 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				&acrtc_state->stream->csc_color_matrix;
 			bundle->stream_update.out_transfer_func =
 				acrtc_state->stream->out_transfer_func;
+			bundle->stream_update.lut3d_func =
+				(struct dc_3dlut *) acrtc_state->stream->lut3d_func;
+			bundle->stream_update.func_shaper =
+				(struct dc_transfer_func *) acrtc_state->stream->func_shaper;
 		}
 
 		acrtc_state->stream->abm_level = acrtc_state->abm_level;
@@ -9516,6 +9531,7 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm,
 	 * when a modeset is needed, to ensure it gets reprogrammed.
 	 */
 	if (dm_new_crtc_state->base.color_mgmt_changed ||
+	    dm_old_crtc_state->regamma_tf != dm_new_crtc_state->regamma_tf ||
 	    drm_atomic_crtc_needs_modeset(new_crtc_state)) {
 		ret = amdgpu_dm_update_crtc_color_mgmt(dm_new_crtc_state);
 		if (ret)
@@ -9583,6 +9599,10 @@ static bool should_reset_plane(struct drm_atomic_state *state,
 	 */
 	for_each_oldnew_plane_in_state(state, other, old_other_state, new_other_state, i) {
 		struct amdgpu_framebuffer *old_afb, *new_afb;
+		struct dm_plane_state *dm_new_other_state, *dm_old_other_state;
+
+		dm_new_other_state = to_dm_plane_state(new_other_state);
+		dm_old_other_state = to_dm_plane_state(old_other_state);
 
 		if (other->type == DRM_PLANE_TYPE_CURSOR)
 			continue;
@@ -9619,6 +9639,18 @@ static bool should_reset_plane(struct drm_atomic_state *state,
 		    old_other_state->color_encoding != new_other_state->color_encoding)
 			return true;
 
+		/* HDR/Transfer Function changes. */
+		if (dm_old_other_state->degamma_tf != dm_new_other_state->degamma_tf ||
+		    dm_old_other_state->degamma_lut != dm_new_other_state->degamma_lut ||
+		    dm_old_other_state->hdr_mult != dm_new_other_state->hdr_mult ||
+		    dm_old_other_state->ctm != dm_new_other_state->ctm ||
+		    dm_old_other_state->shaper_lut != dm_new_other_state->shaper_lut ||
+		    dm_old_other_state->shaper_tf != dm_new_other_state->shaper_tf ||
+		    dm_old_other_state->lut3d != dm_new_other_state->lut3d ||
+		    dm_old_other_state->blend_lut != dm_new_other_state->blend_lut ||
+		    dm_old_other_state->blend_tf != dm_new_other_state->blend_tf)
+			return true;
+
 		/* Framebuffer checks fall at the end. */
 		if (!old_other_state->fb || !new_other_state->fb)
 			continue;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 9e4cc5eeda767..24c87f425afbb 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -33,6 +33,8 @@
 #include <drm/drm_plane.h>
 #include "link_service_types.h"
 
+#define AMDGPU_HDR_MULT_DEFAULT (0x100000000LL)
+
 /*
  * This file contains the definition for amdgpu_display_manager
  * and its API for amdgpu driver's use.
@@ -716,9 +718,91 @@ static inline void amdgpu_dm_set_mst_status(uint8_t *status,
 
 extern const struct amdgpu_ip_block_version dm_ip_block;
 
+enum amdgpu_transfer_function {
+	AMDGPU_TRANSFER_FUNCTION_DEFAULT,
+	AMDGPU_TRANSFER_FUNCTION_SRGB_EOTF,
+	AMDGPU_TRANSFER_FUNCTION_BT709_EOTF,
+	AMDGPU_TRANSFER_FUNCTION_PQ_EOTF,
+	AMDGPU_TRANSFER_FUNCTION_LINEAR,
+	AMDGPU_TRANSFER_FUNCTION_UNITY,
+	AMDGPU_TRANSFER_FUNCTION_GAMMA22_EOTF,
+	AMDGPU_TRANSFER_FUNCTION_GAMMA24_EOTF,
+	AMDGPU_TRANSFER_FUNCTION_GAMMA26_EOTF,
+	AMDGPU_TRANSFER_FUNCTION_SRGB_INV_EOTF,
+	AMDGPU_TRANSFER_FUNCTION_BT709_INV_EOTF,
+	AMDGPU_TRANSFER_FUNCTION_PQ_INV_EOTF,
+	AMDGPU_TRANSFER_FUNCTION_GAMMA22_INV_EOTF,
+	AMDGPU_TRANSFER_FUNCTION_GAMMA24_INV_EOTF,
+	AMDGPU_TRANSFER_FUNCTION_GAMMA26_INV_EOTF,
+        AMDGPU_TRANSFER_FUNCTION_COUNT
+};
+
 struct dm_plane_state {
 	struct drm_plane_state base;
 	struct dc_plane_state *dc_state;
+
+	/* Plane color mgmt */
+	/**
+	 * @degamma_lut:
+	 *
+	 * 1D LUT for mapping framebuffer/plane pixel data before sampling or
+	 * blending operations. It's usually applied to linearize input space.
+	 * The blob (if not NULL) is an array of &struct drm_color_lut.
+	 */
+	struct drm_property_blob *degamma_lut;
+	/**
+	 * @degamma_tf:
+	 *
+	 * Predefined transfer function to tell DC driver the input space to
+	 * linearize.
+	 */
+	enum amdgpu_transfer_function degamma_tf;
+	/**
+	 * @hdr_mult:
+	 *
+	 * Multiplier to 'gain' the plane.  When PQ is decoded using the fixed
+	 * func transfer function to the internal FP16 fb, 1.0 -> 80 nits (on
+	 * AMD at least). When sRGB is decoded, 1.0 -> 1.0, obviously.
+	 * Therefore, 1.0 multiplier = 80 nits for SDR content.  So if you
+	 * want, 203 nits for SDR content, pass in (203.0 / 80.0).  Format is
+	 * S31.32 sign-magnitude.
+	 */
+	__u64 hdr_mult;
+	/**
+	 * @ctm:
+	 *
+	 * Color transformation matrix. See drm_crtc_enable_color_mgmt(). The
+	 * blob (if not NULL) is a &struct drm_color_ctm.
+	 */
+	struct drm_property_blob *ctm;
+	/**
+	 * @shaper_lut: shaper lookup table blob. The blob (if not NULL) is an
+	 * array of &struct drm_color_lut.
+	 */
+	struct drm_property_blob *shaper_lut;
+	/**
+	 * @shaper_tf:
+	 *
+	 * Predefined transfer function to delinearize color space.
+	 */
+	enum amdgpu_transfer_function shaper_tf;
+	/**
+	 * @lut3d: 3D lookup table blob. The blob (if not NULL) is an array of
+	 * &struct drm_color_lut.
+	 */
+	struct drm_property_blob *lut3d;
+	/**
+	 * @blend_lut: blend lut lookup table blob. The blob (if not NULL) is an
+	 * array of &struct drm_color_lut.
+	 */
+	struct drm_property_blob *blend_lut;
+	/**
+	 * @blend_tf:
+	 *
+	 * Pre-defined transfer function for converting plane pixel data before
+	 * applying blend LUT.
+	 */
+	enum amdgpu_transfer_function blend_tf;
 };
 
 struct dm_crtc_state {
@@ -743,6 +827,14 @@ struct dm_crtc_state {
 	struct dc_info_packet vrr_infopacket;
 
 	int abm_level;
+
+        /**
+	 * @regamma_tf:
+	 *
+	 * Pre-defined transfer function for converting internal FB -> wire
+	 * encoding.
+	 */
+	enum amdgpu_transfer_function regamma_tf;
 };
 
 #define to_dm_crtc_state(x) container_of(x, struct dm_crtc_state, base)
@@ -804,14 +896,22 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector,
 
 void amdgpu_dm_trigger_timing_sync(struct drm_device *dev);
 
+/* 3D LUT max size is 17x17x17 */
+#define MAX_COLOR_3DLUT_ENTRIES 4913
+#define MAX_COLOR_3DLUT_BITDEPTH 12
+int amdgpu_dm_verify_lut3d_size(struct amdgpu_device *adev,
+				struct drm_plane_state *plane_state);
+/* 1D LUT size */
 #define MAX_COLOR_LUT_ENTRIES 4096
 /* Legacy gamm LUT users such as X doesn't like large LUT sizes */
 #define MAX_COLOR_LEGACY_LUT_ENTRIES 256
 
 void amdgpu_dm_init_color_mod(void);
+int amdgpu_dm_create_color_properties(struct amdgpu_device *adev);
 int amdgpu_dm_verify_lut_sizes(const struct drm_crtc_state *crtc_state);
 int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc);
 int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
+				      struct drm_plane_state *plane_state,
 				      struct dc_plane_state *dc_plane_state);
 
 void amdgpu_dm_update_connector_after_detect(
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 a4cb23d059bd6..0442eeaa97637 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
@@ -72,6 +72,7 @@
  */
 
 #define MAX_DRM_LUT_VALUE 0xFFFF
+#define SDR_WHITE_LEVEL_INIT_VALUE 80
 
 /**
  * amdgpu_dm_init_color_mod - Initialize the color module.
@@ -84,6 +85,213 @@ void amdgpu_dm_init_color_mod(void)
 	setup_x_points_distribution();
 }
 
+#ifdef AMD_PRIVATE_COLOR
+/* Pre-defined Transfer Functions (TF)
+ *
+ * AMD driver supports pre-defined mathematical functions for transferring
+ * between encoded values and optical/linear space. Depending on HW color caps,
+ * ROMs and curves built by the AMD color module support these transforms.
+ *
+ * The driver-specific color implementation exposes properties for pre-blending
+ * degamma TF, shaper TF (before 3D LUT), and blend(dpp.ogam) TF and
+ * post-blending regamma (mpc.ogam) TF. However, only pre-blending degamma
+ * supports ROM curves. AMD color module uses pre-defined coefficients to build
+ * curves for the other blocks. What can be done by each color block is
+ * described by struct dpp_color_capsand struct mpc_color_caps.
+ *
+ * AMD driver-specific color API exposes the following pre-defined transfer
+ * functions:
+ *
+ * - Linear/Unity: linear/identity relationship between pixel value and
+ *   luminance value;
+ * - Gamma 2.2, Gamma 2.4, Gamma 2.6: pure gamma functions;
+ * - sRGB: 2.4 gamma with small initial linear section as standardized by IEC
+ *   61966-2-1:1999;
+ * - BT.709 (BT.1886): 2.4 gamma with differences in the dark end of the scale.
+ *   Used in HD-TV and standardized by ITU-R BT.1886;
+ * - PQ (Perceptual Quantizer): used for HDR display, allows luminance range
+ *   capability of 0 to 10,000 nits; standardized by SMPTE ST 2084.
+ *
+ * In the driver-specific API, color block names attached to TF properties
+ * suggest the intention regarding non-linear encoding pixel's luminance
+ * values. As some newer encodings don't use gamma curve, we make encoding and
+ * decoding explicit by defining an enum list of transfer functions supported
+ * in terms of EOTF and inverse EOTF, where:
+ *
+ * - EOTF (electro-optical transfer function): is the transfer function to go
+ *   from the encoded value to an optical (linear) value. De-gamma functions
+ *   traditionally do this.
+ * - Inverse EOTF (simply the inverse of the EOTF): is usually intended to go
+ *   from an optical/linear space (which might have been used for blending)
+ *   back to the encoded values. Gamma functions traditionally do this.
+ */
+static const char * const
+amdgpu_transfer_function_names[] = {
+	[AMDGPU_TRANSFER_FUNCTION_DEFAULT]		= "Default",
+	[AMDGPU_TRANSFER_FUNCTION_LINEAR]		= "Linear",
+	[AMDGPU_TRANSFER_FUNCTION_UNITY]		= "Unity",
+	[AMDGPU_TRANSFER_FUNCTION_SRGB_EOTF]		= "sRGB EOTF",
+	[AMDGPU_TRANSFER_FUNCTION_BT709_EOTF]		= "BT.709 EOTF",
+	[AMDGPU_TRANSFER_FUNCTION_PQ_EOTF]		= "PQ EOTF",
+	[AMDGPU_TRANSFER_FUNCTION_GAMMA22_EOTF]		= "Gamma 2.2 EOTF",
+	[AMDGPU_TRANSFER_FUNCTION_GAMMA24_EOTF]		= "Gamma 2.4 EOTF",
+	[AMDGPU_TRANSFER_FUNCTION_GAMMA26_EOTF]		= "Gamma 2.6 EOTF",
+	[AMDGPU_TRANSFER_FUNCTION_SRGB_INV_EOTF]	= "sRGB inv_EOTF",
+	[AMDGPU_TRANSFER_FUNCTION_BT709_INV_EOTF]	= "BT.709 inv_EOTF",
+	[AMDGPU_TRANSFER_FUNCTION_PQ_INV_EOTF]		= "PQ inv_EOTF",
+	[AMDGPU_TRANSFER_FUNCTION_GAMMA22_INV_EOTF]	= "Gamma 2.2 inv_EOTF",
+	[AMDGPU_TRANSFER_FUNCTION_GAMMA24_INV_EOTF]	= "Gamma 2.4 inv_EOTF",
+	[AMDGPU_TRANSFER_FUNCTION_GAMMA26_INV_EOTF]	= "Gamma 2.6 inv_EOTF",
+};
+
+static const u32 amdgpu_eotf =
+	BIT(AMDGPU_TRANSFER_FUNCTION_SRGB_EOTF) |
+	BIT(AMDGPU_TRANSFER_FUNCTION_BT709_EOTF) |
+	BIT(AMDGPU_TRANSFER_FUNCTION_PQ_EOTF) |
+	BIT(AMDGPU_TRANSFER_FUNCTION_GAMMA22_EOTF) |
+	BIT(AMDGPU_TRANSFER_FUNCTION_GAMMA24_EOTF) |
+	BIT(AMDGPU_TRANSFER_FUNCTION_GAMMA26_EOTF);
+
+static const u32 amdgpu_inv_eotf =
+	BIT(AMDGPU_TRANSFER_FUNCTION_SRGB_INV_EOTF) |
+	BIT(AMDGPU_TRANSFER_FUNCTION_BT709_INV_EOTF) |
+	BIT(AMDGPU_TRANSFER_FUNCTION_PQ_INV_EOTF) |
+	BIT(AMDGPU_TRANSFER_FUNCTION_GAMMA22_INV_EOTF) |
+	BIT(AMDGPU_TRANSFER_FUNCTION_GAMMA24_INV_EOTF) |
+	BIT(AMDGPU_TRANSFER_FUNCTION_GAMMA26_INV_EOTF);
+
+static struct drm_property *
+amdgpu_create_tf_property(struct drm_device *dev,
+			  const char *name,
+			  u32 supported_tf)
+{
+	u32 transfer_functions = supported_tf |
+				 BIT(AMDGPU_TRANSFER_FUNCTION_DEFAULT) |
+				 BIT(AMDGPU_TRANSFER_FUNCTION_LINEAR) |
+				 BIT(AMDGPU_TRANSFER_FUNCTION_UNITY);
+	struct drm_prop_enum_list enum_list[AMDGPU_TRANSFER_FUNCTION_COUNT];
+	int i, len;
+
+	len = 0;
+	for (i = 0; i < AMDGPU_TRANSFER_FUNCTION_COUNT; i++) {
+		if ((transfer_functions & BIT(i)) == 0)
+			continue;
+
+		enum_list[len].type = i;
+		enum_list[len].name = amdgpu_transfer_function_names[i];
+		len++;
+	}
+
+	return drm_property_create_enum(dev, DRM_MODE_PROP_ENUM,
+					name, enum_list, len);
+}
+
+int
+amdgpu_dm_create_color_properties(struct amdgpu_device *adev)
+{
+	struct drm_property *prop;
+
+	prop = drm_property_create(adev_to_drm(adev),
+				   DRM_MODE_PROP_BLOB,
+				   "AMD_PLANE_DEGAMMA_LUT", 0);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_degamma_lut_property = prop;
+
+	prop = drm_property_create_range(adev_to_drm(adev),
+					 DRM_MODE_PROP_IMMUTABLE,
+					 "AMD_PLANE_DEGAMMA_LUT_SIZE", 0, UINT_MAX);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_degamma_lut_size_property = prop;
+
+	prop = amdgpu_create_tf_property(adev_to_drm(adev),
+					 "AMD_PLANE_DEGAMMA_TF",
+					 amdgpu_eotf);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_degamma_tf_property = prop;
+
+	prop = drm_property_create_range(adev_to_drm(adev),
+					 0, "AMD_PLANE_HDR_MULT", 0, U64_MAX);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_hdr_mult_property = prop;
+
+	prop = drm_property_create(adev_to_drm(adev),
+				   DRM_MODE_PROP_BLOB,
+				   "AMD_PLANE_CTM", 0);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_ctm_property = prop;
+
+	prop = drm_property_create(adev_to_drm(adev),
+				   DRM_MODE_PROP_BLOB,
+				   "AMD_PLANE_SHAPER_LUT", 0);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_shaper_lut_property = prop;
+
+	prop = drm_property_create_range(adev_to_drm(adev),
+					 DRM_MODE_PROP_IMMUTABLE,
+					 "AMD_PLANE_SHAPER_LUT_SIZE", 0, UINT_MAX);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_shaper_lut_size_property = prop;
+
+	prop = amdgpu_create_tf_property(adev_to_drm(adev),
+					 "AMD_PLANE_SHAPER_TF",
+					 amdgpu_inv_eotf);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_shaper_tf_property = prop;
+
+	prop = drm_property_create(adev_to_drm(adev),
+				   DRM_MODE_PROP_BLOB,
+				   "AMD_PLANE_LUT3D", 0);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_lut3d_property = prop;
+
+	prop = drm_property_create_range(adev_to_drm(adev),
+					 DRM_MODE_PROP_IMMUTABLE,
+					 "AMD_PLANE_LUT3D_SIZE", 0, UINT_MAX);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_lut3d_size_property = prop;
+
+	prop = drm_property_create(adev_to_drm(adev),
+				   DRM_MODE_PROP_BLOB,
+				   "AMD_PLANE_BLEND_LUT", 0);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_blend_lut_property = prop;
+
+	prop = drm_property_create_range(adev_to_drm(adev),
+					 DRM_MODE_PROP_IMMUTABLE,
+					 "AMD_PLANE_BLEND_LUT_SIZE", 0, UINT_MAX);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_blend_lut_size_property = prop;
+
+	prop = amdgpu_create_tf_property(adev_to_drm(adev),
+					 "AMD_PLANE_BLEND_TF",
+					 amdgpu_eotf);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.plane_blend_tf_property = prop;
+
+	prop = amdgpu_create_tf_property(adev_to_drm(adev),
+					 "AMD_CRTC_REGAMMA_TF",
+					 amdgpu_inv_eotf);
+	if (!prop)
+		return -ENOMEM;
+	adev->mode_info.regamma_tf_property = prop;
+
+	return 0;
+}
+#endif
+
 /**
  * __extract_blob_lut - Extracts the DRM lut and lut size from a blob.
  * @blob: DRM color mgmt property blob
@@ -182,7 +390,6 @@ static void __drm_lut_to_dc_gamma(const struct drm_color_lut *lut,
 static void __drm_ctm_to_dc_matrix(const struct drm_color_ctm *ctm,
 				   struct fixed31_32 *matrix)
 {
-	int64_t val;
 	int i;
 
 	/*
@@ -201,12 +408,33 @@ static void __drm_ctm_to_dc_matrix(const struct drm_color_ctm *ctm,
 		}
 
 		/* gamut_remap_matrix[i] = ctm[i - floor(i/4)] */
-		val = ctm->matrix[i - (i / 4)];
-		/* If negative, convert to 2's complement. */
-		if (val & (1ULL << 63))
-			val = -(val & ~(1ULL << 63));
+		matrix[i] = dc_fixpt_from_s3132(ctm->matrix[i - (i / 4)]);
+	}
+}
 
-		matrix[i].value = val;
+/**
+ * __drm_ctm2_to_dc_matrix - converts a DRM CTM2 to a DC CSC float matrix
+ * @ctm: DRM color transformation matrix
+ * @matrix: DC CSC float matrix
+ *
+ * The matrix needs to be a 3x4 (12 entry) matrix.
+ */
+static void __drm_ctm2_to_dc_matrix(const struct drm_color_ctm2 *ctm,
+				   struct fixed31_32 *matrix)
+{
+	int i;
+
+	/*
+	 * DRM gives a 3x3 matrix, but DC wants 3x4. Assuming we're operating
+	 * with homogeneous coordinates, augment the matrix with 0's.
+	 *
+	 * The format provided is S31.32, using signed-magnitude representation.
+	 * Our fixed31_32 is also S31.32, but is using 2's complement. We have
+	 * to convert from signed-magnitude to 2's complement.
+	 */
+	for (i = 0; i < 12; i++) {
+		/* gamut_remap_matrix[i] = ctm[i - floor(i/4)] */
+		matrix[i] = dc_fixpt_from_s3132(ctm->matrix[i]);
 	}
 }
 
@@ -268,16 +496,18 @@ static int __set_output_tf(struct dc_transfer_func *func,
 	struct calculate_buffer cal_buffer = {0};
 	bool res;
 
-	ASSERT(lut && lut_size == MAX_COLOR_LUT_ENTRIES);
-
 	cal_buffer.buffer_index = -1;
 
-	gamma = dc_create_gamma();
-	if (!gamma)
-		return -ENOMEM;
+	if (lut_size) {
+		ASSERT(lut && lut_size == MAX_COLOR_LUT_ENTRIES);
 
-	gamma->num_entries = lut_size;
-	__drm_lut_to_dc_gamma(lut, gamma, false);
+		gamma = dc_create_gamma();
+		if (!gamma)
+			return -ENOMEM;
+
+		gamma->num_entries = lut_size;
+		__drm_lut_to_dc_gamma(lut, gamma, false);
+	}
 
 	if (func->tf == TRANSFER_FUNCTION_LINEAR) {
 		/*
@@ -285,27 +515,63 @@ static int __set_output_tf(struct dc_transfer_func *func,
 		 * on top of a linear input. But degamma params can be used
 		 * instead to simulate this.
 		 */
-		gamma->type = GAMMA_CUSTOM;
+		if (gamma)
+			gamma->type = GAMMA_CUSTOM;
 		res = mod_color_calculate_degamma_params(NULL, func,
-							gamma, true);
+							 gamma, gamma != NULL);
 	} else {
 		/*
 		 * Assume sRGB. The actual mapping will depend on whether the
 		 * input was legacy or not.
 		 */
-		gamma->type = GAMMA_CS_TFM_1D;
-		res = mod_color_calculate_regamma_params(func, gamma, false,
+		if (gamma)
+			gamma->type = GAMMA_CS_TFM_1D;
+		res = mod_color_calculate_regamma_params(func, gamma, gamma != NULL,
 							 has_rom, NULL, &cal_buffer);
 	}
 
-	dc_gamma_release(&gamma);
+	if (gamma)
+		dc_gamma_release(&gamma);
 
 	return res ? 0 : -ENOMEM;
 }
 
+static int amdgpu_dm_set_atomic_regamma(struct dc_stream_state *stream,
+					const struct drm_color_lut *regamma_lut,
+					uint32_t regamma_size, bool has_rom,
+					enum dc_transfer_func_predefined tf)
+{
+	struct dc_transfer_func *out_tf = stream->out_transfer_func;
+	int ret = 0;
+
+	if (regamma_size || tf != TRANSFER_FUNCTION_LINEAR) {
+		/* CRTC RGM goes into RGM LUT.
+		 *
+		 * Note: there is no implicit sRGB regamma here. We are using
+		 * degamma calculation from color module to calculate the curve
+		 * from a linear base.
+		 */
+		out_tf->type = TF_TYPE_DISTRIBUTED_POINTS;
+		out_tf->tf = tf;
+		out_tf->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE;
+
+		ret = __set_output_tf(out_tf, regamma_lut, regamma_size, has_rom);
+	} else {
+		/*
+		 * No CRTC RGM means we can just put the block into bypass
+		 * since we don't have any plane level adjustments using it.
+		 */
+		out_tf->type = TF_TYPE_BYPASS;
+		out_tf->tf = TRANSFER_FUNCTION_LINEAR;
+	}
+
+	return ret;
+}
+
 /**
  * __set_input_tf - 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.
@@ -313,27 +579,249 @@ static int __set_output_tf(struct dc_transfer_func *func,
  * Returns:
  * 0 in case of success. -ENOMEM if fails.
  */
-static int __set_input_tf(struct dc_transfer_func *func,
+static int __set_input_tf(struct dc_color_caps *caps, struct dc_transfer_func *func,
 			  const struct drm_color_lut *lut, uint32_t lut_size)
 {
 	struct dc_gamma *gamma = NULL;
 	bool res;
 
-	gamma = dc_create_gamma();
-	if (!gamma)
-		return -ENOMEM;
+	if (lut_size) {
+		gamma = dc_create_gamma();
+		if (!gamma)
+			return -ENOMEM;
 
-	gamma->type = GAMMA_CUSTOM;
-	gamma->num_entries = lut_size;
+		gamma->type = GAMMA_CUSTOM;
+		gamma->num_entries = lut_size;
 
-	__drm_lut_to_dc_gamma(lut, gamma, false);
+		__drm_lut_to_dc_gamma(lut, gamma, false);
+	}
 
-	res = mod_color_calculate_degamma_params(NULL, func, gamma, true);
-	dc_gamma_release(&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)
+{
+	switch (tf)
+	{
+	default:
+	case AMDGPU_TRANSFER_FUNCTION_DEFAULT:
+	case AMDGPU_TRANSFER_FUNCTION_LINEAR:
+		return TRANSFER_FUNCTION_LINEAR;
+	case AMDGPU_TRANSFER_FUNCTION_SRGB_EOTF:
+	case AMDGPU_TRANSFER_FUNCTION_SRGB_INV_EOTF:
+		return TRANSFER_FUNCTION_SRGB;
+	case AMDGPU_TRANSFER_FUNCTION_BT709_EOTF:
+	case AMDGPU_TRANSFER_FUNCTION_BT709_INV_EOTF:
+		return TRANSFER_FUNCTION_BT709;
+	case AMDGPU_TRANSFER_FUNCTION_PQ_EOTF:
+	case AMDGPU_TRANSFER_FUNCTION_PQ_INV_EOTF:
+		return TRANSFER_FUNCTION_PQ;
+	case AMDGPU_TRANSFER_FUNCTION_UNITY:
+		return TRANSFER_FUNCTION_UNITY;
+	case AMDGPU_TRANSFER_FUNCTION_GAMMA22_EOTF:
+	case AMDGPU_TRANSFER_FUNCTION_GAMMA22_INV_EOTF:
+		return TRANSFER_FUNCTION_GAMMA22;
+	case AMDGPU_TRANSFER_FUNCTION_GAMMA24_EOTF:
+	case AMDGPU_TRANSFER_FUNCTION_GAMMA24_INV_EOTF:
+		return TRANSFER_FUNCTION_GAMMA24;
+	case AMDGPU_TRANSFER_FUNCTION_GAMMA26_EOTF:
+	case AMDGPU_TRANSFER_FUNCTION_GAMMA26_INV_EOTF:
+		return TRANSFER_FUNCTION_GAMMA26;
+	}
+}
+
+static void __to_dc_lut3d_color(struct dc_rgb *rgb,
+				const struct drm_color_lut lut,
+				int bit_precision)
+{
+	rgb->red = drm_color_lut_extract(lut.red, bit_precision);
+	rgb->green = drm_color_lut_extract(lut.green, bit_precision);
+	rgb->blue  = drm_color_lut_extract(lut.blue, bit_precision);
+}
+
+static void __drm_3dlut_to_dc_3dlut(const struct drm_color_lut *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 3dlut 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_color(&lut0[lut_i], lut[i], bit_depth);
+		__to_dc_lut3d_color(&lut1[lut_i], lut[i + 1], bit_depth);
+		__to_dc_lut3d_color(&lut2[lut_i], lut[i + 2], bit_depth);
+		__to_dc_lut3d_color(&lut3[lut_i], lut[i + 3], bit_depth);
+	}
+	/* lut0 has 1229 points (lut_size/4 + 1) */
+	__to_dc_lut3d_color(&lut0[lut_i], lut[i], bit_depth);
+}
+
+/* amdgpu_dm_atomic_lut3d - set DRM 3D LUT to DC stream
+ * @drm_lut3d: DRM CRTC (user) 3D LUT
+ * @drm_lut3d_size: size of 3D LUT
+ * @lut3d: DC 3D LUT
+ *
+ * Map DRM CRTC 3D LUT to DC 3D LUT and all necessary bits to program it
+ * on DCN MPC accordingly.
+ */
+static void amdgpu_dm_atomic_lut3d(const struct drm_color_lut *drm_lut,
+				   uint32_t drm_lut3d_size,
+				   struct dc_3dlut *lut)
+{
+	if (!drm_lut3d_size) {
+		lut->state.bits.initialized = 0;
+	} else {
+		/* Stride and bit depth are not programmable by API yet.
+		 * Therefore, only supports 17x17x17 3D LUT (12-bit).
+		 */
+		lut->lut_3d.use_tetrahedral_9 = false;
+		lut->lut_3d.use_12bits = true;
+		lut->state.bits.initialized = 1;
+		__drm_3dlut_to_dc_3dlut(drm_lut, drm_lut3d_size, &lut->lut_3d,
+					lut->lut_3d.use_tetrahedral_9,
+					MAX_COLOR_3DLUT_BITDEPTH);
+	}
+}
+
+static int amdgpu_dm_atomic_shaper_lut(const struct drm_color_lut *shaper_lut,
+				       bool has_rom,
+				       enum dc_transfer_func_predefined tf,
+				       uint32_t shaper_size,
+				       struct dc_transfer_func *func_shaper)
+{
+	int ret = 0;
+
+	if (shaper_size || tf != TRANSFER_FUNCTION_LINEAR) {
+		/* If DRM shaper LUT is set, we assume a linear color space
+		 * (linearized by DRM degamma 1D LUT or not)
+		 */
+		func_shaper->type = TF_TYPE_DISTRIBUTED_POINTS;
+		func_shaper->tf = tf;
+		func_shaper->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE;
+
+		ret = __set_output_tf(func_shaper, shaper_lut, shaper_size, has_rom);
+	} else {
+		func_shaper->type = TF_TYPE_BYPASS;
+		func_shaper->tf = TRANSFER_FUNCTION_LINEAR;
+	}
+
+	return ret;
+}
+
+static int amdgpu_dm_atomic_blend_lut(const struct drm_color_lut *blend_lut,
+				       bool has_rom,
+				       enum dc_transfer_func_predefined tf,
+				       uint32_t blend_size,
+				       struct dc_transfer_func *func_blend)
+{
+	int ret = 0;
+
+	if (blend_size || tf != TRANSFER_FUNCTION_LINEAR) {
+		/* DRM plane gamma LUT or TF means we are linearizing color
+		 * space before blending (similar to degamma programming). As
+		 * we don't have hardcoded curve support, or we use AMD color
+		 * module to fill the parameters that will be translated to HW
+		 * points.
+		 */
+		func_blend->type = TF_TYPE_DISTRIBUTED_POINTS;
+		func_blend->tf = tf;
+		func_blend->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE;
+
+		ret = __set_input_tf(NULL, func_blend, blend_lut, blend_size);
+	} else {
+		func_blend->type = TF_TYPE_BYPASS;
+		func_blend->tf = TRANSFER_FUNCTION_LINEAR;
+	}
+
+	return ret;
+}
+
+/* amdgpu_dm_lut3d_size - get expected size according to hw color caps
+ * @adev: amdgpu device
+ * @lut_size: default size
+ *
+ * Return:
+ * lut_size if DC 3D LUT is supported, zero otherwise.
+ */
+static uint32_t amdgpu_dm_get_lut3d_size(struct amdgpu_device *adev,
+					 uint32_t lut_size)
+{
+	return adev->dm.dc->caps.color.dpp.hw_3d_lut ? lut_size : 0;
+}
+
+/**
+ * amdgpu_dm_verify_lut3d_size - verifies if 3D LUT is supported and if DRM 3D
+ * LUT matches the hw supported size
+ * @adev: amdgpu device
+ * @crtc_state: the DRM CRTC state
+ *
+ * Verifies if post-blending (MPC) 3D LUT is supported by the HW (DCN 3.0 or
+ * newer) and if the DRM 3D LUT matches the supported size.
+ *
+ * Returns:
+ * 0 on success. -EINVAL if lut size are invalid.
+ */
+int amdgpu_dm_verify_lut3d_size(struct amdgpu_device *adev,
+				struct drm_plane_state *plane_state)
+{
+	struct dm_plane_state *dm_plane_state = to_dm_plane_state(plane_state);
+	const struct drm_color_lut *shaper = NULL, *lut3d = NULL;
+	uint32_t exp_size, size;
+
+	/* shaper LUT is only available if 3D LUT color caps*/
+	exp_size = amdgpu_dm_get_lut3d_size(adev, MAX_COLOR_LUT_ENTRIES);
+	shaper = __extract_blob_lut(dm_plane_state->shaper_lut, &size);
+
+	if (shaper && size != exp_size) {
+		drm_dbg(&adev->ddev,
+			"Invalid Shaper LUT size. Should be %u but got %u.\n",
+			exp_size, size);
+	}
+
+	exp_size = amdgpu_dm_get_lut3d_size(adev, MAX_COLOR_3DLUT_ENTRIES);
+	lut3d = __extract_blob_lut(dm_plane_state->lut3d, &size);
+
+	if (lut3d && size != exp_size) {
+		drm_dbg(&adev->ddev, "Invalid 3D LUT size. Should be %u but got %u.\n",
+			exp_size, size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
  * amdgpu_dm_verify_lut_sizes - verifies if DRM luts match the hw supported sizes
  * @crtc_state: the DRM CRTC state
@@ -401,9 +889,12 @@ int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
 	const struct drm_color_lut *degamma_lut, *regamma_lut;
 	uint32_t degamma_size, regamma_size;
 	bool has_regamma, has_degamma;
+	enum dc_transfer_func_predefined tf = TRANSFER_FUNCTION_LINEAR;
 	bool is_legacy;
 	int r;
 
+	tf = amdgpu_tf_to_dc_tf(crtc->regamma_tf);
+
 	r = amdgpu_dm_verify_lut_sizes(&crtc->base);
 	if (r)
 		return r;
@@ -440,26 +931,22 @@ int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
 		stream->out_transfer_func->type = TF_TYPE_DISTRIBUTED_POINTS;
 		stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
 
+		/* Note: although we pass has_rom as parameter here, we never
+		 * actually use ROM because the color module only takes the ROM
+		 * path if transfer_func->type == PREDEFINED.
+		 *
+		 * See more in mod_color_calculate_regamma_params()
+		 */
 		r = __set_legacy_tf(stream->out_transfer_func, regamma_lut,
 				    regamma_size, has_rom);
 		if (r)
 			return r;
-	} else if (has_regamma) {
-		/* If atomic regamma, CRTC RGM goes into RGM LUT. */
-		stream->out_transfer_func->type = TF_TYPE_DISTRIBUTED_POINTS;
-		stream->out_transfer_func->tf = TRANSFER_FUNCTION_LINEAR;
-
-		r = __set_output_tf(stream->out_transfer_func, regamma_lut,
-				    regamma_size, has_rom);
+	} else {
+		regamma_size = has_regamma ? regamma_size : 0;
+		r = amdgpu_dm_set_atomic_regamma(stream, regamma_lut,
+						 regamma_size, has_rom, tf);
 		if (r)
 			return r;
-	} else {
-		/*
-		 * No CRTC RGM means we can just put the block into bypass
-		 * since we don't have any plane level adjustments using it.
-		 */
-		stream->out_transfer_func->type = TF_TYPE_BYPASS;
-		stream->out_transfer_func->tf = TRANSFER_FUNCTION_LINEAR;
 	}
 
 	/*
@@ -495,20 +982,10 @@ int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
 	return 0;
 }
 
-/**
- * amdgpu_dm_update_plane_color_mgmt: Maps DRM color management to DC plane.
- * @crtc: amdgpu_dm crtc state
- * @dc_plane_state: target DC surface
- *
- * Update the underlying dc_stream_state's input transfer function (ITF) in
- * preparation for hardware commit. The transfer function used depends on
- * the preparation done on the stream for color management.
- *
- * Returns:
- * 0 on success. -ENOMEM if mem allocation fails.
- */
-int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
-				      struct dc_plane_state *dc_plane_state)
+static int
+map_crtc_degamma_to_dc_plane(struct dm_crtc_state *crtc,
+			     struct dc_plane_state *dc_plane_state,
+			     struct dc_color_caps *caps)
 {
 	const struct drm_color_lut *degamma_lut;
 	enum dc_transfer_func_predefined tf = TRANSFER_FUNCTION_SRGB;
@@ -531,8 +1008,7 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 						 &degamma_size);
 		ASSERT(degamma_size == MAX_COLOR_LUT_ENTRIES);
 
-		dc_plane_state->in_transfer_func->type =
-			TF_TYPE_DISTRIBUTED_POINTS;
+		dc_plane_state->in_transfer_func->type = TF_TYPE_DISTRIBUTED_POINTS;
 
 		/*
 		 * This case isn't fully correct, but also fairly
@@ -564,11 +1040,11 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 			dc_plane_state->in_transfer_func->tf =
 				TRANSFER_FUNCTION_LINEAR;
 
-		r = __set_input_tf(dc_plane_state->in_transfer_func,
+		r = __set_input_tf(caps, dc_plane_state->in_transfer_func,
 				   degamma_lut, degamma_size);
 		if (r)
 			return r;
-	} else if (crtc->cm_is_degamma_srgb) {
+	} else {
 		/*
 		 * For legacy gamma support we need the regamma input
 		 * in linear space. Assume that the input is sRGB.
@@ -577,14 +1053,213 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 		dc_plane_state->in_transfer_func->tf = tf;
 
 		if (tf != TRANSFER_FUNCTION_SRGB &&
-		    !mod_color_calculate_degamma_params(NULL,
-			    dc_plane_state->in_transfer_func, NULL, false))
+		    !mod_color_calculate_degamma_params(caps,
+							dc_plane_state->in_transfer_func,
+							NULL, false))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int
+__set_dm_plane_degamma(struct drm_plane_state *plane_state,
+		       struct dc_plane_state *dc_plane_state,
+		       struct dc_color_caps *color_caps)
+{
+	struct dm_plane_state *dm_plane_state = to_dm_plane_state(plane_state);
+	const struct drm_color_lut *degamma_lut;
+	enum amdgpu_transfer_function tf = AMDGPU_TRANSFER_FUNCTION_DEFAULT;
+	uint32_t degamma_size;
+	bool has_degamma_lut;
+	int ret;
+
+	degamma_lut = __extract_blob_lut(dm_plane_state->degamma_lut,
+					 &degamma_size);
+
+	has_degamma_lut = degamma_lut &&
+			  !__is_lut_linear(degamma_lut, degamma_size);
+
+	tf = dm_plane_state->degamma_tf;
+
+	/* If we don't have plane degamma LUT nor TF to set on DC, we have
+	 * nothing to do here, return.
+	 */
+	if (!has_degamma_lut && tf == AMDGPU_TRANSFER_FUNCTION_DEFAULT)
+		return -EINVAL;
+
+	dc_plane_state->in_transfer_func->tf = amdgpu_tf_to_dc_tf(tf);
+
+	if (has_degamma_lut) {
+		ASSERT(degamma_size == MAX_COLOR_LUT_ENTRIES);
+
+		dc_plane_state->in_transfer_func->type =
+			TF_TYPE_DISTRIBUTED_POINTS;
+
+		ret = __set_input_tf(color_caps, dc_plane_state->in_transfer_func,
+				     degamma_lut, degamma_size);
+		if (ret)
+			return ret;
+       } else {
+		dc_plane_state->in_transfer_func->type =
+			TF_TYPE_PREDEFINED;
+
+		if (!mod_color_calculate_degamma_params(color_caps,
+		    dc_plane_state->in_transfer_func, NULL, false))
 			return -ENOMEM;
-	} else {
-		/* ...Otherwise we can just bypass the DGM block. */
-		dc_plane_state->in_transfer_func->type = TF_TYPE_BYPASS;
-		dc_plane_state->in_transfer_func->tf = TRANSFER_FUNCTION_LINEAR;
+	}
+	return 0;
+}
+
+static int
+amdgpu_dm_plane_set_color_properties(struct drm_plane_state *plane_state,
+				     struct dc_plane_state *dc_plane_state,
+				     struct dc_color_caps *color_caps)
+{
+	struct dm_plane_state *dm_plane_state = to_dm_plane_state(plane_state);
+	enum amdgpu_transfer_function shaper_tf = AMDGPU_TRANSFER_FUNCTION_DEFAULT;
+	enum amdgpu_transfer_function blend_tf = AMDGPU_TRANSFER_FUNCTION_DEFAULT;
+	const struct drm_color_lut *shaper_lut, *lut3d, *blend_lut;
+	uint32_t shaper_size, lut3d_size, blend_size;
+	int ret;
+
+	/* We have nothing to do here, return */
+	if (!plane_state->color_mgmt_changed)
+		return 0;
+
+	dc_plane_state->hdr_mult = dc_fixpt_from_s3132(dm_plane_state->hdr_mult);
+
+	shaper_lut = __extract_blob_lut(dm_plane_state->shaper_lut, &shaper_size);
+	shaper_size = shaper_lut != NULL ? shaper_size : 0;
+	shaper_tf = dm_plane_state->shaper_tf;
+	lut3d = __extract_blob_lut(dm_plane_state->lut3d, &lut3d_size);
+	lut3d_size = lut3d != NULL ? lut3d_size : 0;
+
+	amdgpu_dm_atomic_lut3d(lut3d, lut3d_size, dc_plane_state->lut3d_func);
+	ret = amdgpu_dm_atomic_shaper_lut(shaper_lut, false,
+					  amdgpu_tf_to_dc_tf(shaper_tf),
+					  shaper_size,
+					  dc_plane_state->in_shaper_func);
+	if (ret) {
+		drm_dbg_kms(plane_state->plane->dev,
+			    "setting plane %d shaper LUT failed.\n",
+			    plane_state->plane->index);
+
+		return ret;
+	}
+
+	blend_tf = dm_plane_state->blend_tf;
+	blend_lut = __extract_blob_lut(dm_plane_state->blend_lut, &blend_size);
+	blend_size = blend_lut != NULL ? blend_size : 0;
+
+	ret = amdgpu_dm_atomic_blend_lut(blend_lut, false,
+					 amdgpu_tf_to_dc_tf(blend_tf),
+					 blend_size, dc_plane_state->blend_tf);
+	if (ret) {
+		drm_dbg_kms(plane_state->plane->dev,
+			    "setting plane %d gamma lut failed.\n",
+			    plane_state->plane->index);
+
+		return ret;
 	}
 
 	return 0;
 }
+
+/**
+ * amdgpu_dm_update_plane_color_mgmt: Maps DRM color management to DC plane.
+ * @crtc: amdgpu_dm crtc state
+ * @plane_state: DRM plane state
+ * @dc_plane_state: target DC surface
+ *
+ * Update the underlying dc_stream_state's input transfer function (ITF) in
+ * preparation for hardware commit. The transfer function used depends on
+ * the preparation done on the stream for color management.
+ *
+ * Returns:
+ * 0 on success. -ENOMEM if mem allocation fails.
+ */
+int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
+				      struct drm_plane_state *plane_state,
+				      struct dc_plane_state *dc_plane_state)
+{
+	struct amdgpu_device *adev = drm_to_adev(crtc->base.state->dev);
+	struct dm_plane_state *dm_plane_state = to_dm_plane_state(plane_state);
+	struct drm_color_ctm2 *ctm = NULL;
+	struct dc_color_caps *color_caps = NULL;
+	bool has_crtc_cm_degamma;
+	int ret;
+
+	ret = amdgpu_dm_verify_lut3d_size(adev, plane_state);
+	if (ret) {
+		drm_dbg_driver(&adev->ddev, "amdgpu_dm_verify_lut3d_size() failed\n");
+		return ret;
+	}
+
+	if (dc_plane_state->ctx && dc_plane_state->ctx->dc)
+		color_caps = &dc_plane_state->ctx->dc->caps.color;
+
+	/* Initially, we can just bypass the DGM block. */
+	dc_plane_state->in_transfer_func->type = TF_TYPE_BYPASS;
+	dc_plane_state->in_transfer_func->tf = TRANSFER_FUNCTION_LINEAR;
+
+	/* After, we start to update values according to color props */
+	has_crtc_cm_degamma = (crtc->cm_has_degamma || crtc->cm_is_degamma_srgb);
+
+	ret = __set_dm_plane_degamma(plane_state, dc_plane_state, color_caps);
+	if (ret == -ENOMEM)
+		return ret;
+
+	/* We only have one degamma block available (pre-blending) for the
+	 * whole color correction pipeline, so that we can't actually perform
+	 * plane and CRTC degamma at the same time. Explicitly reject atomic
+	 * updates when userspace sets both plane and CRTC degamma properties.
+	 */
+	if (has_crtc_cm_degamma && ret != -EINVAL){
+		drm_dbg_kms(crtc->base.crtc->dev,
+			    "doesn't support plane and CRTC degamma at the same time\n");
+			return -EINVAL;
+	}
+
+	/* If we are here, it means we don't have plane degamma settings, check
+	 * if we have CRTC degamma waiting for mapping to pre-blending degamma
+	 * block
+	 */
+	if (has_crtc_cm_degamma) {
+		/* AMD HW doesn't have post-blending degamma caps. When DRM
+		 * CRTC atomic degamma is set, we maps it to DPP degamma block
+		 * (pre-blending) or, on legacy gamma, we use DPP degamma to
+		 * linearize (implicit degamma) from sRGB/BT709 according to
+		 * the input space.
+		 */
+		ret = map_crtc_degamma_to_dc_plane(crtc, dc_plane_state, color_caps);
+		if (ret)
+			return ret;
+	}
+
+	/* Setup CRTC CTM. */
+	if (dm_plane_state->ctm) {
+		ctm = (struct drm_color_ctm2 *)dm_plane_state->ctm->data;
+
+		/*
+		 * So far, if we have both plane and CRTC CTM, plane CTM takes
+		 * the priority and we discard data for CRTC CTM, as
+		 * implemented in dcn10_program_gamut_remap().  However, we
+		 * have MPC gamut_remap_matrix from DCN3 family, therefore we
+		 * can remap MPC programing of the matrix to MPC block and
+		 * provide support for both DPP and MPC matrix at the same
+		 * time.
+		 */
+		__drm_ctm2_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 {
+		/* Bypass CTM. */
+		dc_plane_state->gamut_remap_matrix.enable_remap = false;
+		dc_plane_state->input_csc_color_matrix.enable_adjustment = false;
+	}
+
+	return amdgpu_dm_plane_set_color_properties(plane_state,
+						    dc_plane_state, color_caps);
+}
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 97b7a0b8a1c26..a05c210754d44 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
@@ -260,6 +260,7 @@ static struct drm_crtc_state *dm_crtc_duplicate_state(struct drm_crtc *crtc)
 	state->freesync_config = cur->freesync_config;
 	state->cm_has_degamma = cur->cm_has_degamma;
 	state->cm_is_degamma_srgb = cur->cm_is_degamma_srgb;
+	state->regamma_tf = cur->regamma_tf;
 	state->crc_skip_count = cur->crc_skip_count;
 	state->mpo_requested = cur->mpo_requested;
 	/* TODO Duplicate dc_stream after objects are stream object is flattened */
@@ -296,6 +297,70 @@ static int amdgpu_dm_crtc_late_register(struct drm_crtc *crtc)
 }
 #endif
 
+#ifdef AMD_PRIVATE_COLOR
+/**
+ * drm_crtc_additional_color_mgmt - enable additional color properties
+ * @crtc: DRM CRTC
+ *
+ * This function lets the driver enable post-blending CRTC regamma transfer
+ * function property in addition to DRM CRTC gamma LUT. Default value means
+ * linear transfer function, which is the default CRTC gamma LUT behaviour
+ * without this property.
+ */
+static void
+dm_crtc_additional_color_mgmt(struct drm_crtc *crtc)
+{
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
+
+	if(adev->dm.dc->caps.color.mpc.ogam_ram)
+		drm_object_attach_property(&crtc->base,
+					   adev->mode_info.regamma_tf_property,
+					   AMDGPU_TRANSFER_FUNCTION_DEFAULT);
+}
+
+static int
+amdgpu_dm_atomic_crtc_set_property(struct drm_crtc *crtc,
+				   struct drm_crtc_state *state,
+				   struct drm_property *property,
+				   uint64_t val)
+{
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
+	struct dm_crtc_state *acrtc_state = to_dm_crtc_state(state);
+
+	if (property == adev->mode_info.regamma_tf_property) {
+		if (acrtc_state->regamma_tf != val) {
+			acrtc_state->regamma_tf = val;
+			acrtc_state->base.color_mgmt_changed |= 1;
+		}
+	} else {
+		drm_dbg_atomic(crtc->dev,
+			       "[CRTC:%d:%s] unknown property [PROP:%d:%s]]\n",
+			       crtc->base.id, crtc->name,
+			       property->base.id, property->name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+amdgpu_dm_atomic_crtc_get_property(struct drm_crtc *crtc,
+				   const struct drm_crtc_state *state,
+				   struct drm_property *property,
+				   uint64_t *val)
+{
+	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
+	struct dm_crtc_state *acrtc_state = to_dm_crtc_state(state);
+
+	if (property == adev->mode_info.regamma_tf_property)
+		*val = acrtc_state->regamma_tf;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+#endif
+
 /* Implemented only the options currently available for the driver */
 static const struct drm_crtc_funcs amdgpu_dm_crtc_funcs = {
 	.reset = dm_crtc_reset_state,
@@ -314,6 +379,10 @@ static const struct drm_crtc_funcs amdgpu_dm_crtc_funcs = {
 #if defined(CONFIG_DEBUG_FS)
 	.late_register = amdgpu_dm_crtc_late_register,
 #endif
+#ifdef AMD_PRIVATE_COLOR
+	.atomic_set_property = amdgpu_dm_atomic_crtc_set_property,
+	.atomic_get_property = amdgpu_dm_atomic_crtc_get_property,
+#endif
 };
 
 static void dm_crtc_helper_disable(struct drm_crtc *crtc)
@@ -489,6 +558,9 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
 
 	drm_mode_crtc_set_gamma_size(&acrtc->base, MAX_COLOR_LEGACY_LUT_ENTRIES);
 
+#ifdef AMD_PRIVATE_COLOR
+	dm_crtc_additional_color_mgmt(&acrtc->base);
+#endif
 	return 0;
 
 fail:
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 cc74dd69acf2b..17719e15cbe58 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
@@ -1333,8 +1333,14 @@ static void dm_drm_plane_reset(struct drm_plane *plane)
 	amdgpu_state = kzalloc(sizeof(*amdgpu_state), GFP_KERNEL);
 	WARN_ON(amdgpu_state == NULL);
 
-	if (amdgpu_state)
-		__drm_atomic_helper_plane_reset(plane, &amdgpu_state->base);
+	if (!amdgpu_state)
+		return;
+
+	__drm_atomic_helper_plane_reset(plane, &amdgpu_state->base);
+	amdgpu_state->degamma_tf = AMDGPU_TRANSFER_FUNCTION_DEFAULT;
+	amdgpu_state->hdr_mult = AMDGPU_HDR_MULT_DEFAULT;
+	amdgpu_state->shaper_tf = AMDGPU_TRANSFER_FUNCTION_DEFAULT;
+	amdgpu_state->blend_tf = AMDGPU_TRANSFER_FUNCTION_DEFAULT;
 }
 
 static struct drm_plane_state *
@@ -1354,6 +1360,22 @@ dm_drm_plane_duplicate_state(struct drm_plane *plane)
 		dc_plane_state_retain(dm_plane_state->dc_state);
 	}
 
+	if (dm_plane_state->degamma_lut)
+		drm_property_blob_get(dm_plane_state->degamma_lut);
+	if (dm_plane_state->ctm)
+		drm_property_blob_get(dm_plane_state->ctm);
+	if (dm_plane_state->shaper_lut)
+		drm_property_blob_get(dm_plane_state->shaper_lut);
+	if (dm_plane_state->lut3d)
+		drm_property_blob_get(dm_plane_state->lut3d);
+	if (dm_plane_state->blend_lut)
+		drm_property_blob_get(dm_plane_state->blend_lut);
+
+	dm_plane_state->degamma_tf = old_dm_plane_state->degamma_tf;
+	dm_plane_state->hdr_mult = old_dm_plane_state->hdr_mult;
+	dm_plane_state->shaper_tf = old_dm_plane_state->shaper_tf;
+	dm_plane_state->blend_tf = old_dm_plane_state->blend_tf;
+
 	return &dm_plane_state->base;
 }
 
@@ -1421,12 +1443,203 @@ static void dm_drm_plane_destroy_state(struct drm_plane *plane,
 {
 	struct dm_plane_state *dm_plane_state = to_dm_plane_state(state);
 
+	if (dm_plane_state->degamma_lut)
+		drm_property_blob_put(dm_plane_state->degamma_lut);
+	if (dm_plane_state->ctm)
+		drm_property_blob_put(dm_plane_state->ctm);
+	if (dm_plane_state->lut3d)
+		drm_property_blob_put(dm_plane_state->lut3d);
+	if (dm_plane_state->shaper_lut)
+		drm_property_blob_put(dm_plane_state->shaper_lut);
+	if (dm_plane_state->blend_lut)
+		drm_property_blob_put(dm_plane_state->blend_lut);
+
 	if (dm_plane_state->dc_state)
 		dc_plane_state_release(dm_plane_state->dc_state);
 
 	drm_atomic_helper_plane_destroy_state(plane, state);
 }
 
+#ifdef AMD_PRIVATE_COLOR
+static void
+dm_atomic_plane_attach_color_mgmt_properties(struct amdgpu_display_manager *dm,
+					     struct drm_plane *plane)
+{
+	struct amdgpu_mode_info mode_info = dm->adev->mode_info;
+	struct dpp_color_caps dpp_color_caps = dm->dc->caps.color.dpp;
+
+	/* Check HW color pipeline capabilities for DPP (pre-blending) before expose*/
+	if (dpp_color_caps.dgam_ram || dpp_color_caps.gamma_corr) {
+		drm_object_attach_property(&plane->base,
+					   mode_info.plane_degamma_lut_property, 0);
+		drm_object_attach_property(&plane->base,
+					   mode_info.plane_degamma_lut_size_property,
+					   MAX_COLOR_LUT_ENTRIES);
+		drm_object_attach_property(&plane->base,
+					   dm->adev->mode_info.plane_degamma_tf_property,
+					   AMDGPU_TRANSFER_FUNCTION_DEFAULT);
+	}
+	/* HDR MULT is always available */
+	drm_object_attach_property(&plane->base,
+				   dm->adev->mode_info.plane_hdr_mult_property,
+				   AMDGPU_HDR_MULT_DEFAULT);
+
+	/* Only enable plane CTM if both DPP and MPC gamut remap is available. */
+	if (dm->dc->caps.color.mpc.gamut_remap)
+		drm_object_attach_property(&plane->base,
+					   dm->adev->mode_info.plane_ctm_property, 0);
+
+	if (dpp_color_caps.hw_3d_lut) {
+		drm_object_attach_property(&plane->base,
+					   mode_info.plane_shaper_lut_property, 0);
+		drm_object_attach_property(&plane->base,
+					   mode_info.plane_shaper_lut_size_property,
+					   MAX_COLOR_LUT_ENTRIES);
+		drm_object_attach_property(&plane->base,
+					   mode_info.plane_shaper_tf_property,
+					   AMDGPU_TRANSFER_FUNCTION_DEFAULT);
+		drm_object_attach_property(&plane->base,
+					   mode_info.plane_lut3d_property, 0);
+		drm_object_attach_property(&plane->base,
+					   mode_info.plane_lut3d_size_property,
+					   MAX_COLOR_3DLUT_ENTRIES);
+	}
+
+	if (dpp_color_caps.ogam_ram) {
+		drm_object_attach_property(&plane->base,
+					   mode_info.plane_blend_lut_property, 0);
+		drm_object_attach_property(&plane->base,
+					   mode_info.plane_blend_lut_size_property,
+					   MAX_COLOR_LUT_ENTRIES);
+		drm_object_attach_property(&plane->base,
+					   mode_info.plane_blend_tf_property,
+					   AMDGPU_TRANSFER_FUNCTION_DEFAULT);
+	}
+}
+
+static int
+dm_atomic_plane_set_property(struct drm_plane *plane,
+			     struct drm_plane_state *state,
+			     struct drm_property *property,
+			     uint64_t val)
+{
+	struct dm_plane_state *dm_plane_state = to_dm_plane_state(state);
+	struct amdgpu_device *adev = drm_to_adev(plane->dev);
+	bool replaced = false;
+	int ret;
+
+	if (property == adev->mode_info.plane_degamma_lut_property) {
+		ret = drm_property_replace_blob_from_id(plane->dev,
+							&dm_plane_state->degamma_lut,
+							val,
+							-1, sizeof(struct drm_color_lut),
+							&replaced);
+		dm_plane_state->base.color_mgmt_changed |= replaced;
+		return ret;
+	} else if (property == adev->mode_info.plane_degamma_tf_property) {
+		if (dm_plane_state->degamma_tf != val) {
+			dm_plane_state->degamma_tf = val;
+			dm_plane_state->base.color_mgmt_changed = 1;
+		}
+	} else if (property == adev->mode_info.plane_hdr_mult_property) {
+		if (dm_plane_state->hdr_mult != val) {
+			dm_plane_state->hdr_mult = val;
+			dm_plane_state->base.color_mgmt_changed = 1;
+		}
+	} else if (property == adev->mode_info.plane_ctm_property) {
+		ret = drm_property_replace_blob_from_id(plane->dev,
+							&dm_plane_state->ctm,
+							val,
+							sizeof(struct drm_color_ctm2), -1,
+							&replaced);
+		dm_plane_state->base.color_mgmt_changed |= replaced;
+		return ret;
+	} else if (property == adev->mode_info.plane_shaper_lut_property) {
+		ret = drm_property_replace_blob_from_id(plane->dev,
+							&dm_plane_state->shaper_lut,
+							val, -1,
+							sizeof(struct drm_color_lut),
+							&replaced);
+		dm_plane_state->base.color_mgmt_changed |= replaced;
+		return ret;
+	} else if (property == adev->mode_info.plane_shaper_tf_property) {
+		if (dm_plane_state->shaper_tf != val) {
+			dm_plane_state->shaper_tf = val;
+			dm_plane_state->base.color_mgmt_changed = 1;
+		}
+	} else if (property == adev->mode_info.plane_lut3d_property) {
+		ret = drm_property_replace_blob_from_id(plane->dev,
+							&dm_plane_state->lut3d,
+							val, -1,
+							sizeof(struct drm_color_lut),
+							&replaced);
+		dm_plane_state->base.color_mgmt_changed |= replaced;
+		return ret;
+	} else if (property == adev->mode_info.plane_blend_lut_property) {
+		ret = drm_property_replace_blob_from_id(plane->dev,
+							&dm_plane_state->blend_lut,
+							val, -1,
+							sizeof(struct drm_color_lut),
+							&replaced);
+		dm_plane_state->base.color_mgmt_changed |= replaced;
+		return ret;
+	} else if (property == adev->mode_info.plane_blend_tf_property) {
+		if (dm_plane_state->blend_tf != val) {
+			dm_plane_state->blend_tf = val;
+			dm_plane_state->base.color_mgmt_changed = 1;
+		}
+	} else {
+		drm_dbg_atomic(plane->dev,
+			       "[PLANE:%d:%s] unknown property [PROP:%d:%s]]\n",
+			       plane->base.id, plane->name,
+			       property->base.id, property->name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+dm_atomic_plane_get_property(struct drm_plane *plane,
+			     const struct drm_plane_state *state,
+			     struct drm_property *property,
+			     uint64_t *val)
+{
+	struct dm_plane_state *dm_plane_state = to_dm_plane_state(state);
+	struct amdgpu_device *adev = drm_to_adev(plane->dev);
+
+	if (property == adev->mode_info.plane_degamma_lut_property) {
+		*val = (dm_plane_state->degamma_lut) ?
+			dm_plane_state->degamma_lut->base.id : 0;
+	} else if (property == adev->mode_info.plane_degamma_tf_property) {
+		*val = dm_plane_state->degamma_tf;
+	} else if (property == adev->mode_info.plane_hdr_mult_property) {
+		*val = dm_plane_state->hdr_mult;
+	} else if (property == adev->mode_info.plane_ctm_property) {
+		*val = (dm_plane_state->ctm) ?
+			dm_plane_state->ctm->base.id : 0;
+	} else 	if (property == adev->mode_info.plane_shaper_lut_property) {
+		*val = (dm_plane_state->shaper_lut) ?
+			dm_plane_state->shaper_lut->base.id : 0;
+	} else if (property == adev->mode_info.plane_shaper_tf_property) {
+		*val = dm_plane_state->shaper_tf;
+	} else 	if (property == adev->mode_info.plane_lut3d_property) {
+		*val = (dm_plane_state->lut3d) ?
+			dm_plane_state->lut3d->base.id : 0;
+	} else 	if (property == adev->mode_info.plane_blend_lut_property) {
+		*val = (dm_plane_state->blend_lut) ?
+			dm_plane_state->blend_lut->base.id : 0;
+	} else if (property == adev->mode_info.plane_blend_tf_property) {
+		*val = dm_plane_state->blend_tf;
+
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+#endif
+
 static const struct drm_plane_funcs dm_plane_funcs = {
 	.update_plane	= drm_atomic_helper_update_plane,
 	.disable_plane	= drm_atomic_helper_disable_plane,
@@ -1435,6 +1648,10 @@ static const struct drm_plane_funcs dm_plane_funcs = {
 	.atomic_duplicate_state = dm_drm_plane_duplicate_state,
 	.atomic_destroy_state = dm_drm_plane_destroy_state,
 	.format_mod_supported = dm_plane_format_mod_supported,
+#ifdef AMD_PRIVATE_COLOR
+	.atomic_set_property = dm_atomic_plane_set_property,
+	.atomic_get_property = dm_atomic_plane_get_property,
+#endif
 };
 
 int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm,
@@ -1514,6 +1731,9 @@ int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm,
 
 	drm_plane_helper_add(plane, &dm_plane_helper_funcs);
 
+#ifdef AMD_PRIVATE_COLOR
+	dm_atomic_plane_attach_color_mgmt_properties(dm, plane);
+#endif
 	/* Create (reset) the plane state */
 	if (plane->funcs->reset)
 		plane->funcs->reset(plane);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
index 3538973bd0c6c..04b2e04b68f33 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
@@ -349,20 +349,37 @@ bool cm_helper_translate_curve_to_hw_format(struct dc_context *ctx,
 		 * segment is from 2^-10 to 2^1
 		 * There are less than 256 points, for optimization
 		 */
-		seg_distr[0] = 3;
-		seg_distr[1] = 4;
-		seg_distr[2] = 4;
-		seg_distr[3] = 4;
-		seg_distr[4] = 4;
-		seg_distr[5] = 4;
-		seg_distr[6] = 4;
-		seg_distr[7] = 4;
-		seg_distr[8] = 4;
-		seg_distr[9] = 4;
-		seg_distr[10] = 1;
-
-		region_start = -10;
-		region_end = 1;
+		if (output_tf->tf == TRANSFER_FUNCTION_LINEAR) {
+			seg_distr[0] = 0; /* 2 */
+			seg_distr[1] = 1; /* 4 */
+			seg_distr[2] = 2; /* 4 */
+			seg_distr[3] = 3; /* 8 */
+			seg_distr[4] = 4; /* 16 */
+			seg_distr[5] = 5; /* 32 */
+			seg_distr[6] = 6; /* 64 */
+			seg_distr[7] = 7; /* 128 */
+
+			region_start = -8;
+			region_end = 1;
+		} else {
+			seg_distr[0] = 3; /* 8 */
+			seg_distr[1] = 4; /* 16 */
+			seg_distr[2] = 4;
+			seg_distr[3] = 4;
+			seg_distr[4] = 4;
+			seg_distr[5] = 4;
+			seg_distr[6] = 4;
+			seg_distr[7] = 4;
+			seg_distr[8] = 4;
+			seg_distr[9] = 4;
+			seg_distr[10] = 1; /* 2 */
+			/* total = 8*16 + 8 + 64 + 2 = */
+
+			region_start = -10;
+			region_end = 1;
+		}
+
+
 	}
 
 	for (i = region_end - region_start; i < MAX_REGIONS_NUMBER ; i++)
@@ -375,16 +392,56 @@ bool cm_helper_translate_curve_to_hw_format(struct dc_context *ctx,
 
 	j = 0;
 	for (k = 0; k < (region_end - region_start); k++) {
-		increment = NUMBER_SW_SEGMENTS / (1 << seg_distr[k]);
+		/*
+		 * We're using an ugly-ish hack here. Our HW allows for
+		 * 256 segments per region but SW_SEGMENTS is 16.
+		 * SW_SEGMENTS has some undocumented relationship to
+		 * the number of points in the tf_pts struct, which
+		 * is 512, unlike what's suggested TRANSFER_FUNC_POINTS.
+		 *
+		 * In order to work past this dilemma we'll scale our
+		 * increment by (1 << 4) and then do the inverse (1 >> 4)
+		 * when accessing the elements in tf_pts.
+		 *
+		 * TODO: find a better way using SW_SEGMENTS and
+		 *       TRANSFER_FUNC_POINTS definitions
+		 */
+		increment = (NUMBER_SW_SEGMENTS << 4) / (1 << seg_distr[k]);
 		start_index = (region_start + k + MAX_LOW_POINT) *
 				NUMBER_SW_SEGMENTS;
-		for (i = start_index; i < start_index + NUMBER_SW_SEGMENTS;
+		for (i = (start_index << 4); i < (start_index << 4) + (NUMBER_SW_SEGMENTS << 4);
 				i += increment) {
+			struct fixed31_32 in_plus_one, in;
+			struct fixed31_32 value, red_value, green_value, blue_value;
+			uint32_t t = i & 0xf;
+
 			if (j == hw_points - 1)
 				break;
-			rgb_resulted[j].red = output_tf->tf_pts.red[i];
-			rgb_resulted[j].green = output_tf->tf_pts.green[i];
-			rgb_resulted[j].blue = output_tf->tf_pts.blue[i];
+
+			in_plus_one = output_tf->tf_pts.red[(i >> 4) + 1];
+			in = output_tf->tf_pts.red[i >> 4];
+			value = dc_fixpt_sub(in_plus_one, in);
+			value = dc_fixpt_shr(dc_fixpt_mul_int(value, t),  4);
+			value = dc_fixpt_add(in, value);
+			red_value = value;
+
+			in_plus_one = output_tf->tf_pts.green[(i >> 4) + 1];
+			in = output_tf->tf_pts.green[i >> 4];
+			value = dc_fixpt_sub(in_plus_one, in);
+			value = dc_fixpt_shr(dc_fixpt_mul_int(value, t),  4);
+			value = dc_fixpt_add(in, value);
+			green_value = value;
+
+			in_plus_one = output_tf->tf_pts.blue[(i >> 4) + 1];
+			in = output_tf->tf_pts.blue[i >> 4];
+			value = dc_fixpt_sub(in_plus_one, in);
+			value = dc_fixpt_shr(dc_fixpt_mul_int(value, t),  4);
+			value = dc_fixpt_add(in, value);
+			blue_value = value;
+
+			rgb_resulted[j].red = red_value;
+			rgb_resulted[j].green = green_value;
+			rgb_resulted[j].blue = blue_value;
 			j++;
 		}
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index 255713ec29bb0..fce9b33c0f881 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -186,6 +186,43 @@ bool dcn30_set_input_transfer_func(struct dc *dc,
 	return result;
 }
 
+void dcn30_program_gamut_remap(struct pipe_ctx *pipe_ctx)
+{
+	int i = 0;
+	struct dpp_grph_csc_adjustment dpp_adjust;
+	struct mpc_grph_gamut_adjustment mpc_adjust;
+	int mpcc_id = pipe_ctx->plane_res.hubp->inst;
+	struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc;
+
+	memset(&dpp_adjust, 0, sizeof(dpp_adjust));
+	dpp_adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_BYPASS;
+
+	if (pipe_ctx->plane_state &&
+	    pipe_ctx->plane_state->gamut_remap_matrix.enable_remap == true) {
+		dpp_adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_SW;
+		for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++)
+			dpp_adjust.temperature_matrix[i] =
+				pipe_ctx->plane_state->gamut_remap_matrix.matrix[i];
+	}
+
+	pipe_ctx->plane_res.dpp->funcs->dpp_set_gamut_remap(pipe_ctx->plane_res.dpp,
+							    &dpp_adjust);
+
+	memset(&mpc_adjust, 0, sizeof(mpc_adjust));
+	mpc_adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_BYPASS;
+
+	if (pipe_ctx->top_pipe == NULL) {
+		if (pipe_ctx->stream->gamut_remap_matrix.enable_remap == true) {
+			mpc_adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_SW;
+			for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++)
+				mpc_adjust.temperature_matrix[i] =
+					pipe_ctx->stream->gamut_remap_matrix.matrix[i];
+		}
+	}
+
+	mpc->funcs->set_gamut_remap(mpc, mpcc_id, &mpc_adjust);
+}
+
 bool dcn30_set_output_transfer_func(struct dc *dc,
 				struct pipe_ctx *pipe_ctx,
 				const struct dc_stream_state *stream)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h
index ce19c54097f8b..e557e2b986187 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h
@@ -58,6 +58,9 @@ bool dcn30_set_blend_lut(struct pipe_ctx *pipe_ctx,
 bool dcn30_set_input_transfer_func(struct dc *dc,
 				struct pipe_ctx *pipe_ctx,
 				const struct dc_plane_state *plane_state);
+
+void dcn30_program_gamut_remap(struct pipe_ctx *pipe_ctx);
+
 bool dcn30_set_output_transfer_func(struct dc *dc,
 				struct pipe_ctx *pipe_ctx,
 				const struct dc_stream_state *stream);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c
index 61205cdbe2d5a..fdbe3d42cd7b6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c
@@ -33,7 +33,7 @@
 #include "dcn301_init.h"
 
 static const struct hw_sequencer_funcs dcn301_funcs = {
-	.program_gamut_remap = dcn10_program_gamut_remap,
+	.program_gamut_remap = dcn30_program_gamut_remap,
 	.init_hw = dcn10_init_hw,
 	.power_down_on_boot = dcn10_power_down_on_boot,
 	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
diff --git a/drivers/gpu/drm/amd/display/include/fixed31_32.h b/drivers/gpu/drm/amd/display/include/fixed31_32.h
index d4cf7ead1d877..84da1dd34efd1 100644
--- a/drivers/gpu/drm/amd/display/include/fixed31_32.h
+++ b/drivers/gpu/drm/amd/display/include/fixed31_32.h
@@ -69,6 +69,18 @@ static const struct fixed31_32 dc_fixpt_epsilon = { 1LL };
 static const struct fixed31_32 dc_fixpt_half = { 0x80000000LL };
 static const struct fixed31_32 dc_fixpt_one = { 0x100000000LL };
 
+static inline struct fixed31_32 dc_fixpt_from_s3132(__u64 x)
+{
+	struct fixed31_32 val;
+
+	/* If negative, convert to 2's complement. */
+	if (x & (1ULL << 63))
+		x = -(x & ~(1ULL << 63));
+
+	val.value = x;
+	return val;
+}
+
 /*
  * @brief
  * Initialization routines
diff --git a/drivers/gpu/drm/arm/malidp_crtc.c b/drivers/gpu/drm/arm/malidp_crtc.c
index dc01c43f61930..d72c22dcf6855 100644
--- a/drivers/gpu/drm/arm/malidp_crtc.c
+++ b/drivers/gpu/drm/arm/malidp_crtc.c
@@ -221,7 +221,7 @@ static int malidp_crtc_atomic_check_ctm(struct drm_crtc *crtc,
 
 	/*
 	 * The size of the ctm is checked in
-	 * drm_atomic_replace_property_blob_from_id.
+	 * drm_property_replace_blob_from_id.
 	 */
 	ctm = (struct drm_color_ctm *)state->ctm->data;
 	for (i = 0; i < ARRAY_SIZE(ctm->matrix); ++i) {
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index c277b198fa3fa..c3df45f901456 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -733,6 +733,7 @@ static void drm_atomic_plane_print_state(struct drm_printer *p,
 		   drm_get_color_encoding_name(state->color_encoding));
 	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);
 
 	if (plane->funcs->atomic_print_state)
 		plane->funcs->atomic_print_state(p, state);
diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c
index 784e63d70a421..25bb0859fda74 100644
--- a/drivers/gpu/drm/drm_atomic_state_helper.c
+++ b/drivers/gpu/drm/drm_atomic_state_helper.c
@@ -338,6 +338,7 @@ void __drm_atomic_helper_plane_duplicate_state(struct drm_plane *plane,
 	state->fence = NULL;
 	state->commit = NULL;
 	state->fb_damage_clips = NULL;
+	state->color_mgmt_changed = false;
 }
 EXPORT_SYMBOL(__drm_atomic_helper_plane_duplicate_state);
 
diff --git a/drivers/gpu/drm/drm_property.c b/drivers/gpu/drm/drm_property.c
index dfec479830e49..f72ef6493340a 100644
--- a/drivers/gpu/drm/drm_property.c
+++ b/drivers/gpu/drm/drm_property.c
@@ -751,6 +751,55 @@ bool drm_property_replace_blob(struct drm_property_blob **blob,
 }
 EXPORT_SYMBOL(drm_property_replace_blob);
 
+/**
+ * drm_property_replace_blob_from_id - replace a blob property taking a reference
+ * @dev: DRM device
+ * @blob: a pointer to the member blob to be replaced
+ * @blob_id: the id of the new blob to replace with
+ * @expected_size: expected size of the blob property
+ * @expected_elem_size: expected size of an element in the blob property
+ * @replaced: if the blob was in fact replaced
+ *
+ * Look up the new blob from id, take its reference, check expected sizes of
+ * the blob and its element and replace the old blob by the new one. Advertise
+ * if the replacement operation was successful.
+ *
+ * Return: true if the blob was in fact replaced. -EINVAL if the new blob was
+ * not found or sizes don't match.
+ */
+int drm_property_replace_blob_from_id(struct drm_device *dev,
+					 struct drm_property_blob **blob,
+					 uint64_t blob_id,
+					 ssize_t expected_size,
+					 ssize_t expected_elem_size,
+					 bool *replaced)
+{
+	struct drm_property_blob *new_blob = NULL;
+
+	if (blob_id != 0) {
+		new_blob = drm_property_lookup_blob(dev, blob_id);
+		if (new_blob == NULL)
+			return -EINVAL;
+
+		if (expected_size > 0 &&
+		    new_blob->length != expected_size) {
+			drm_property_blob_put(new_blob);
+			return -EINVAL;
+		}
+		if (expected_elem_size > 0 &&
+		    new_blob->length % expected_elem_size != 0) {
+			drm_property_blob_put(new_blob);
+			return -EINVAL;
+		}
+	}
+
+	*replaced |= drm_property_replace_blob(blob, new_blob);
+	drm_property_blob_put(new_blob);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_property_replace_blob_from_id);
+
 int drm_mode_getblob_ioctl(struct drm_device *dev,
 			   void *data, struct drm_file *file_priv)
 {
diff --git a/include/drm/drm_mode_object.h b/include/drm/drm_mode_object.h
index 912f1e4156853..08d7a7f0188fe 100644
--- a/include/drm/drm_mode_object.h
+++ b/include/drm/drm_mode_object.h
@@ -60,7 +60,7 @@ struct drm_mode_object {
 	void (*free_cb)(struct kref *kref);
 };
 
-#define DRM_OBJECT_MAX_PROPERTY 24
+#define DRM_OBJECT_MAX_PROPERTY 64
 /**
  * struct drm_object_properties - property tracking for &drm_mode_object
  */
diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h
index 79d62856defbf..4f87803b3ea12 100644
--- a/include/drm/drm_plane.h
+++ b/include/drm/drm_plane.h
@@ -237,6 +237,13 @@ struct drm_plane_state {
 
 	/** @state: backpointer to global drm_atomic_state */
 	struct drm_atomic_state *state;
+
+	/**
+	 * @color_mgmt_changed: Color management properties have changed. Used
+	 * by the atomic helpers and drivers to steer the atomic commit control
+	 * flow.
+	 */
+	bool color_mgmt_changed : 1;
 };
 
 static inline struct drm_rect
diff --git a/include/drm/drm_property.h b/include/drm/drm_property.h
index 65bc9710a4702..082f29156b3e3 100644
--- a/include/drm/drm_property.h
+++ b/include/drm/drm_property.h
@@ -279,6 +279,12 @@ struct drm_property_blob *drm_property_create_blob(struct drm_device *dev,
 						   const void *data);
 struct drm_property_blob *drm_property_lookup_blob(struct drm_device *dev,
 						   uint32_t id);
+int drm_property_replace_blob_from_id(struct drm_device *dev,
+				      struct drm_property_blob **blob,
+				      uint64_t blob_id,
+				      ssize_t expected_size,
+				      ssize_t expected_elem_size,
+				      bool *replaced);
 int drm_property_replace_global_blob(struct drm_device *dev,
 				     struct drm_property_blob **replace,
 				     size_t length,
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index ea1b639bcb288..cea5653e4020b 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -846,6 +846,14 @@ struct drm_color_ctm {
 	__u64 matrix[9];
 };
 
+struct drm_color_ctm2 {
+	/*
+	 * Conversion matrix in S31.32 sign-magnitude
+	 * (not two's complement!) format.
+	 */
+	__u64 matrix[12];
+};
+
 struct drm_color_lut {
 	/*
 	 * Values are mapped linearly to 0.0 - 1.0 range, with 0x0 == 0.0 and
-- 
2.43.0