Merge tag 'drm-next-2024-05-15' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "This is the main pull request for the drm subsystems for 6.10.

  In drivers the main thing is a new driver for ARM Mali firmware based
  GPUs, otherwise there are a lot of changes to amdgpu/xe/i915/msm and
  scattered changes to everything else.

  In the core a bunch of headers and Kconfig was refactored, along with
  the addition of a new panic handler which is meant to provide a user
  friendly message when a panic happens and graphical display is
  enabled.

  New drivers:
   - panthor: ARM Mali/Immortalis CSF-based GPU driver

  Core:
   - add a CONFIG_DRM_WERROR option
   - make more headers self-contained
   - grab resv lock in pin/unpin
   - fix vmap resv locking
   - EDID/eDP panel matching
   - Kconfig cleanups
   - DT sound bindings
   - Add SIZE_HINTS property for cursor planes
   - Add struct drm_edid_product_id and helpers.
   - Use drm device based logging in more drm functions.
   - drop seq_file.h from a bunch of places
   - use drm_edid driver conversions

  dp:
   - DP Tunnel documentation
   - MST read sideband cap
   - Adaptive sync SDP prep work

  ttm:
   - improve placement for TTM BOs in idle/busy handling

  panic:
   - Fixes for drm-panic, and option to test it.
   - Add drm panic to simpledrm, mgag200, imx, ast

  bridge:
   - improve init ordering
   - adv7511: allow GPIO pin sharing
   - tc358775: add tc358675 support

  panel:
   - AUO B120XAN01.0
   - Samsung s6e3fa7
   - BOE NT116WHM-N44
   - CMN N116BCA-EA1,
   - CrystalClear CMT430B19N00
   - Startek KD050HDFIA020-C020A
   - powertip PH128800T006-ZHC01
   - Innolux G121X1-L03
   - LG sw43408
   - Khadas TS050 V2
   - EDO RM69380 OLED
   - CSOT MNB601LS1-1

  amdgpu:
   - HDCP/ODM/RAS fixes
   - Devcoredump improvements
   - Expose VCN activity via sysfs
   - SMY 13.0.x updates
   - Enable fast updates on DCN 3.1.4
   - Add dclk and vclk reporting on additional devices
   - Add ACA RAS infrastructure
   - Implement TLB flush fence
   - EEPROM handling fixes
   - SMUIO 14.0.2 support
   - SMU 14.0.1 Updates
   - SMU 14.0.2 support
   - Sync page table freeing with TLB flushes
   - DML2 refactor
   - DC debug improvements
   - DCN 3.5.x Updates
   - GPU reset fixes
   - HDP fix for second GFX pipe on GC 10.x
   - Enable secondary GFX pipe on GC 10.3
   - Refactor and clean up BACO/BOCO/BAMACO handling
   - Remove invalid TTM resource start check
   - UAF fix in VA IOCTL
   - GPUVM page fault redirection to secondary IH rings for IH 6.x
   - Initial support for mapping kernel queues via MES
   - Fix VRAM memory accounting

  amdkfd:
   - MQD handling cleanup
   - Preemption handling fixes for XCDs
   - TLB flush fix for GC 9.4.2
   - Properly clean up workqueue during module unload
   - Fix memory leak process create failure
   - Range check CP bad op exception targets to avoid reporting invalid exceptions to userspace
   - Fix eviction fence handling
   - Fix leak in GPU memory allocation failure case
   - DMABuf import handling fix
   - Enable SQ watchpoint for gfx10

  i915:
   - Adding new DG2 PCI ID
   - add context hints for GT frequency
   - enable only one CCS for compute workloads
   - new workarounds
   - Fix UAF on destroy against retire race and remove two earlier partial fixes
   - Limit the reserved VM space to only the platforms that need it
   - Fix gt reset with GuC submission is disable
   - Add and use gt_to_guc() wrapper

  i915/xe display:
   - Lunar Lake display enabling, including cdclk and other refactors
   - BIOS/VBT/opregion related refactor
   - Digital port related refactor/clean-up
   - Fix 2s boot time regression on DP panel replay init
   - Remove duplication on audio enable/disable on SDVO and g4x+ DP
   - Disable AuxCCS framebuffers if built for Xe
   - Make crtc disable more atomic
   - Increase DP idle pattern wait timeout to 2ms
   - Start using container_of_const() for some extra const safety
   - Fix Jasper Lake boot freeze
   - Enable MST mode for 128b/132b single-stream sideband
   - Enable Adaptive Sync SDP Support for DP
   - Fix MTL supported DP rates - removal of UHBR13.5
   - PLL refactoring
   - Limit eDP MSO pipe only for display version 20
   - More display refactor towards independence from i915 dev_priv
   - Convert i915/xe fbdev to DRM client
   - More initial work to make display code more independent from i915

  xe:
   - improved error capture
   - clean up some uAPI leftovers
   - devcoredump update
   - Add BMG mocs table
   - Handle GSCCS ER interrupt
   - Implement xe2- and GuC workarounds
   - struct xe_device cleanup
   - Hwmon updates
   - Add LRC parsing for more GPU instruction
   - Increase VM_BIND number of per-ioctl Ops
   - drm/xe: Add XE_BO_GGTT_INVALIDATE flag
   - Initial development for SR-IOV support
   - Add new PCI IDs to DG2 platform
   - Move userptr over to start using hmm_range_fault

  msm:
   - Switched to generating register header files during build process
     instead of shipping pre-generated headers
   - Merged DPU and MDP4 format databases.
   - DP:
     - Stop using compat string to distinguish DP and eDP cases
     - Added support for X Elite platform (X1E80100)
     - Reworked DP aux/audio support
     - Added SM6350 DP to the bindings
   - GPU:
     - a7xx perfcntr reg fixes
     - MAINTAINERS updates
     - a750 devcoredump support

  radeon:
   - Silence UBSAN warnings related to flexible arrays

  nouveau:
   - move some uAPI objects to uapi headers

  omapdrm:
   - console fix

  ast:
   - add i2c polling

  qaic:
   - add debugfs entries

  exynos:
   - fix platform_driver .owner
   - drop cleanup code

  mediatek:
   - Use devm_platform_get_and_ioremap_resource() in mtk_hdmi_ddc_probe()
   - Add GAMMA 12-bit LUT support for MT8188
   - Rename mtk_drm_* to mtk_*
   - Drop driver owner initialization
   - Correct calculation formula of PHY Timing"

* tag 'drm-next-2024-05-15' of https://gitlab.freedesktop.org/drm/kernel: (1477 commits)
  drm/xe/ads: Use flexible-array
  drm/xe: Use ordered WQ for G2H handler
  drm/msm/gen_header: allow skipping the validation
  drm/msm/a6xx: Cleanup indexed regs const'ness
  drm/msm: Add devcoredump support for a750
  drm/msm: Adjust a7xx GBIF debugbus dumping
  drm/msm: Update a6xx registers XML
  drm/msm: Fix imported a750 snapshot header for upstream
  drm/msm: Import a750 snapshot registers from kgsl
  MAINTAINERS: Add Konrad Dybcio as a reviewer for the Adreno driver
  MAINTAINERS: Add a separate entry for Qualcomm Adreno GPU drivers
  drm/msm/a6xx: Avoid a nullptr dereference when speedbin setting fails
  drm/msm/adreno: fix CP cycles stat retrieval on a7xx
  drm/msm/a7xx: allow writing to CP_BV counter selection registers
  drm: zynqmp_dpsub: Always register bridge
  Revert "drm/bridge: ti-sn65dsi83: Fix enable error path"
  drm/fb_dma: Add checks in drm_fb_dma_get_scanout_buffer()
  drm/fbdev-generic: Do not set physical framebuffer address
  drm/panthor: Fix the FW reset logic
  drm/panthor: Make sure we handle 'unknown group state' case properly
  ...

21 files changed, 556 insertions, 243 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/Makefile b/drivers/gpu/drm/amd/display/dc/hwss/Makefile
index 9e8e9de51a92..cf8aa23b4415 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/hwss/Makefile
@@ -180,7 +180,7 @@ AMD_DISPLAY_FILES += $(AMD_DAL_HWSS_DCN35)
 
 ###############################################################################
 
-HWSS_DCN351 = dcn351_init.o
+HWSS_DCN351 = dcn351_hwseq.o dcn351_init.o
 
 AMD_DAL_HWSS_DCN351 = $(addprefix $(AMDDALPATH)/dc/hwss/dcn351/,$(HWSS_DCN351))
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 0ba1feaf96c0..0d3ea291eeee 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -249,7 +249,7 @@ static bool dce110_enable_display_power_gating(
 		return false;
 }
 
-static void build_prescale_params(struct ipp_prescale_params *prescale_params,
+static void dce110_prescale_params(struct ipp_prescale_params *prescale_params,
 		const struct dc_plane_state *plane_state)
 {
 	prescale_params->mode = IPP_PRESCALE_MODE_FIXED_UNSIGNED;
@@ -289,16 +289,14 @@ dce110_set_input_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 	if (ipp == NULL)
 		return false;
 
-	if (plane_state->in_transfer_func)
-		tf = plane_state->in_transfer_func;
+	tf = &plane_state->in_transfer_func;
 
-	build_prescale_params(&prescale_params, plane_state);
+	dce110_prescale_params(&prescale_params, plane_state);
 	ipp->funcs->ipp_program_prescale(ipp, &prescale_params);
 
-	if (plane_state->gamma_correction &&
-			!plane_state->gamma_correction->is_identity &&
+	if (!plane_state->gamma_correction.is_identity &&
 			dce_use_lut(plane_state->format))
-		ipp->funcs->ipp_program_input_lut(ipp, plane_state->gamma_correction);
+		ipp->funcs->ipp_program_input_lut(ipp, &plane_state->gamma_correction);
 
 	if (tf == NULL) {
 		/* Default case if no input transfer function specified */
@@ -614,11 +612,10 @@ dce110_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 	xfm->funcs->opp_power_on_regamma_lut(xfm, true);
 	xfm->regamma_params.hw_points_num = GAMMA_HW_POINTS_NUM;
 
-	if (stream->out_transfer_func &&
-	    stream->out_transfer_func->type == TF_TYPE_PREDEFINED &&
-	    stream->out_transfer_func->tf == TRANSFER_FUNCTION_SRGB) {
+	if (stream->out_transfer_func.type == TF_TYPE_PREDEFINED &&
+	    stream->out_transfer_func.tf == TRANSFER_FUNCTION_SRGB) {
 		xfm->funcs->opp_set_regamma_mode(xfm, OPP_REGAMMA_SRGB);
-	} else if (dce110_translate_regamma_to_hw_format(stream->out_transfer_func,
+	} else if (dce110_translate_regamma_to_hw_format(&stream->out_transfer_func,
 							 &xfm->regamma_params)) {
 		xfm->funcs->opp_program_regamma_pwl(xfm, &xfm->regamma_params);
 		xfm->funcs->opp_set_regamma_mode(xfm, OPP_REGAMMA_USER);
@@ -1192,16 +1189,6 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx)
 		dccg->funcs->disable_symclk_se(dccg, stream_enc->stream_enc_inst,
 					       link_enc->transmitter - TRANSMITTER_UNIPHY_A);
 	}
-
-	if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) {
-		/* TODO: This looks like a bug to me as we are disabling HPO IO when
-		 * we are just disabling a single HPO stream. Shouldn't we disable HPO
-		 * HW control only when HPOs for all streams are disabled?
-		 */
-		if (pipe_ctx->stream->ctx->dc->hwseq->funcs.setup_hpo_hw_control)
-			pipe_ctx->stream->ctx->dc->hwseq->funcs.setup_hpo_hw_control(
-					pipe_ctx->stream->ctx->dc->hwseq, false);
-	}
 }
 
 void dce110_unblank_stream(struct pipe_ctx *pipe_ctx,
@@ -1550,7 +1537,7 @@ enum dc_status dce110_apply_single_controller_ctx_to_hw(
 	}
 
 	if (pipe_ctx->stream_res.audio != NULL) {
-		struct audio_output audio_output;
+		struct audio_output audio_output = {0};
 
 		build_audio_output(context, pipe_ctx, &audio_output);
 
@@ -2201,7 +2188,7 @@ static void dce110_setup_audio_dto(
 		struct dc *dc,
 		struct dc_state *context)
 {
-	int i;
+	unsigned int i;
 
 	/* program audio wall clock. use HDMI as clock source if HDMI
 	 * audio active. Otherwise, use DP as clock source
@@ -2273,7 +2260,7 @@ static void dce110_setup_audio_dto(
 				continue;
 
 			if (pipe_ctx->stream_res.audio != NULL) {
-				struct audio_output audio_output;
+				struct audio_output audio_output = {0};
 
 				build_audio_output(context, pipe_ctx, &audio_output);
 
@@ -2288,6 +2275,19 @@ static void dce110_setup_audio_dto(
 	}
 }
 
+static bool dce110_is_hpo_enabled(struct dc_state *context)
+{
+	int i;
+
+	for (i = 0; i < MAX_HPO_DP2_ENCODERS; i++) {
+		if (context->res_ctx.is_hpo_dp_stream_enc_acquired[i]) {
+			return true;
+		}
+	}
+
+	return false;
+}
+
 enum dc_status dce110_apply_ctx_to_hw(
 		struct dc *dc,
 		struct dc_state *context)
@@ -2296,6 +2296,8 @@ enum dc_status dce110_apply_ctx_to_hw(
 	struct dc_bios *dcb = dc->ctx->dc_bios;
 	enum dc_status status;
 	int i;
+	bool was_hpo_enabled = dce110_is_hpo_enabled(dc->current_state);
+	bool is_hpo_enabled = dce110_is_hpo_enabled(context);
 
 	/* reset syncd pipes from disabled pipes */
 	if (dc->config.use_pipe_ctx_sync_logic)
@@ -2338,6 +2340,10 @@ enum dc_status dce110_apply_ctx_to_hw(
 
 	dce110_setup_audio_dto(dc, context);
 
+	if (dc->hwseq->funcs.setup_hpo_hw_control && was_hpo_enabled != is_hpo_enabled) {
+		dc->hwseq->funcs.setup_hpo_hw_control(dc->hwseq, is_hpo_enabled);
+	}
+
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx_old =
 					&dc->current_state->res_ctx.pipe_ctx[i];
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index 314798400b16..0c4aef8ffe2c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -367,7 +367,7 @@ static void dcn10_log_color_state(struct dc *dc,
 		 dc->caps.color.dpp.ocsc);
 
 	DTN_INFO("MPCC:  OPP  DPP  MPCCBOT  MODE  ALPHA_MODE  PREMULT  OVERLAP_ONLY  IDLE\n");
-	for (i = 0; i < pool->pipe_count; i++) {
+	for (i = 0; i < pool->mpcc_count; i++) {
 		struct mpcc_state s = {0};
 
 		pool->mpc->funcs->read_mpcc_state(pool->mpc, i, &s);
@@ -1366,6 +1366,7 @@ void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 	struct dce_hwseq *hws = dc->hwseq;
 	struct hubbub *hubbub = dc->res_pool->hubbub;
 	bool can_apply_seamless_boot = false;
+	bool tg_enabled[MAX_PIPES] = {false};
 
 	for (i = 0; i < context->stream_count; i++) {
 		if (context->streams[i]->apply_seamless_boot_optimization) {
@@ -1447,6 +1448,7 @@ void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 			// requesting data while in PSR.
 			tg->funcs->tg_init(tg);
 			hubp->power_gated = true;
+			tg_enabled[i] = true;
 			continue;
 		}
 
@@ -1488,6 +1490,20 @@ void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 		tg->funcs->tg_init(tg);
 	}
 
+	/* Clean up MPC tree */
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (tg_enabled[i]) {
+			if (dc->res_pool->opps[i]->mpc_tree_params.opp_list) {
+				if (dc->res_pool->opps[i]->mpc_tree_params.opp_list->mpcc_bot) {
+					int bot_id = dc->res_pool->opps[i]->mpc_tree_params.opp_list->mpcc_bot->mpcc_id;
+
+					if ((bot_id < MAX_MPCC) && (bot_id < MAX_PIPES) && (!tg_enabled[bot_id]))
+						dc->res_pool->opps[i]->mpc_tree_params.opp_list = NULL;
+				}
+			}
+		}
+	}
+
 	/* Power gate DSCs */
 	if (hws->funcs.dsc_pg_control != NULL) {
 		uint32_t num_opps = 0;
@@ -1813,14 +1829,12 @@ bool dcn10_set_input_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 	if (dpp_base == NULL)
 		return false;
 
-	if (plane_state->in_transfer_func)
-		tf = plane_state->in_transfer_func;
+	tf = &plane_state->in_transfer_func;
 
-	if (plane_state->gamma_correction &&
-		!dpp_base->ctx->dc->debug.always_use_regamma
-		&& !plane_state->gamma_correction->is_identity
+	if (!dpp_base->ctx->dc->debug.always_use_regamma
+		&& !plane_state->gamma_correction.is_identity
 			&& dce_use_lut(plane_state->format))
-		dpp_base->funcs->dpp_program_input_lut(dpp_base, plane_state->gamma_correction);
+		dpp_base->funcs->dpp_program_input_lut(dpp_base, &plane_state->gamma_correction);
 
 	if (tf == NULL)
 		dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_BYPASS);
@@ -1861,7 +1875,7 @@ bool dcn10_set_input_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 #define MAX_NUM_HW_POINTS 0x200
 
 static void log_tf(struct dc_context *ctx,
-				struct dc_transfer_func *tf, uint32_t hw_points_num)
+				const struct dc_transfer_func *tf, uint32_t hw_points_num)
 {
 	// DC_LOG_GAMMA is default logging of all hw points
 	// DC_LOG_ALL_GAMMA logs all points, not only hw points
@@ -1898,16 +1912,15 @@ bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 
 	dpp->regamma_params.hw_points_num = GAMMA_HW_POINTS_NUM;
 
-	if (stream->out_transfer_func &&
-	    stream->out_transfer_func->type == TF_TYPE_PREDEFINED &&
-	    stream->out_transfer_func->tf == TRANSFER_FUNCTION_SRGB)
+	if (stream->out_transfer_func.type == TF_TYPE_PREDEFINED &&
+	    stream->out_transfer_func.tf == TRANSFER_FUNCTION_SRGB)
 		dpp->funcs->dpp_program_regamma_pwl(dpp, NULL, OPP_REGAMMA_SRGB);
 
 	/* dcn10_translate_regamma_to_hw_format takes 750us, only do it when full
 	 * update.
 	 */
 	else if (cm_helper_translate_curve_to_hw_format(dc->ctx,
-			stream->out_transfer_func,
+			&stream->out_transfer_func,
 			&dpp->regamma_params, false)) {
 		dpp->funcs->dpp_program_regamma_pwl(
 				dpp,
@@ -1915,10 +1928,9 @@ bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 	} else
 		dpp->funcs->dpp_program_regamma_pwl(dpp, NULL, OPP_REGAMMA_BYPASS);
 
-	if (stream->ctx &&
-	    stream->out_transfer_func) {
+	if (stream->ctx) {
 		log_tf(stream->ctx,
-				stream->out_transfer_func,
+				&stream->out_transfer_func,
 				dpp->regamma_params.hw_points_num);
 	}
 
@@ -2173,7 +2185,7 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size,
 	struct dc_crtc_timing *hw_crtc_timing;
 	uint64_t phase[MAX_PIPES];
 	uint64_t modulo[MAX_PIPES];
-	unsigned int pclk;
+	unsigned int pclk = 0;
 
 	uint32_t embedded_pix_clk_100hz;
 	uint16_t embedded_h_total;
@@ -2264,7 +2276,7 @@ void dcn10_enable_vblanks_synchronization(
 	struct dc_context *dc_ctx = dc->ctx;
 	struct output_pixel_processor *opp;
 	struct timing_generator *tg;
-	int i, width, height, master;
+	int i, width = 0, height = 0, master;
 
 	DC_LOGGER_INIT(dc_ctx->logger);
 
@@ -2330,7 +2342,7 @@ void dcn10_enable_timing_synchronization(
 	struct dc_context *dc_ctx = dc->ctx;
 	struct output_pixel_processor *opp;
 	struct timing_generator *tg;
-	int i, width, height;
+	int i, width = 0, height = 0;
 
 	DC_LOGGER_INIT(dc_ctx->logger);
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index 8b3536c380b8..7d833fa6dd77 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -155,7 +155,7 @@ void dcn20_log_color_state(struct dc *dc,
 	DTN_INFO("MPCC:  OPP  DPP  MPCCBOT  MODE  ALPHA_MODE  PREMULT  OVERLAP_ONLY  IDLE"
 		 "  OGAM mode\n");
 
-	for (i = 0; i < pool->pipe_count; i++) {
+	for (i = 0; i < pool->mpcc_count; i++) {
 		struct mpcc_state s = {0};
 
 		pool->mpc->funcs->read_mpcc_state(pool->mpc, i, &s);
@@ -403,7 +403,7 @@ void dcn20_init_blank(
 	struct output_pixel_processor *opp = NULL;
 	struct output_pixel_processor *bottom_opp = NULL;
 	uint32_t num_opps, opp_id_src0, opp_id_src1;
-	uint32_t otg_active_width, otg_active_height;
+	uint32_t otg_active_width = 0, otg_active_height = 0;
 
 	/* program opp dpg blank color */
 	color_space = COLOR_SPACE_SRGB;
@@ -873,6 +873,22 @@ enum dc_status dcn20_enable_stream_timing(
 		return DC_ERROR_UNEXPECTED;
 	}
 
+	if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) {
+		struct dccg *dccg = dc->res_pool->dccg;
+		struct timing_generator *tg = pipe_ctx->stream_res.tg;
+		struct dtbclk_dto_params dto_params = {0};
+
+		if (dccg->funcs->set_dtbclk_p_src)
+			dccg->funcs->set_dtbclk_p_src(dccg, DTBCLK0, tg->inst);
+
+		dto_params.otg_inst = tg->inst;
+		dto_params.pixclk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10;
+		dto_params.num_odm_segments = get_odm_segment_count(pipe_ctx);
+		dto_params.timing = &pipe_ctx->stream->timing;
+		dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr);
+		dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
+	}
+
 	if (dc_is_hdmi_tmds_signal(stream->signal)) {
 		stream->link->phy_state.symclk_ref_cnts.otg = 1;
 		if (stream->link->phy_state.symclk_state == SYMCLK_OFF_TX_OFF)
@@ -959,22 +975,6 @@ enum dc_status dcn20_enable_stream_timing(
 			pipe_ctx->stream_res.tg->funcs->phantom_crtc_post_enable(pipe_ctx->stream_res.tg);
 	}
 
-	if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) {
-		struct dccg *dccg = dc->res_pool->dccg;
-		struct timing_generator *tg = pipe_ctx->stream_res.tg;
-		struct dtbclk_dto_params dto_params = {0};
-
-		if (dccg->funcs->set_dtbclk_p_src)
-			dccg->funcs->set_dtbclk_p_src(dccg, DTBCLK0, tg->inst);
-
-		dto_params.otg_inst = tg->inst;
-		dto_params.pixclk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10;
-		dto_params.num_odm_segments = get_odm_segment_count(pipe_ctx);
-		dto_params.timing = &pipe_ctx->stream->timing;
-		dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr);
-		dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
-	}
-
 	return DC_OK;
 }
 
@@ -1011,7 +1011,7 @@ bool dcn20_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 {
 	int mpcc_id = pipe_ctx->plane_res.hubp->inst;
 	struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc;
-	struct pwl_params *params = NULL;
+	const struct pwl_params *params = NULL;
 	/*
 	 * program OGAM only for the top pipe
 	 * if there is a pipe split then fix diagnostic is required:
@@ -1022,19 +1022,19 @@ bool dcn20_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 	if (mpc->funcs->power_on_mpc_mem_pwr)
 		mpc->funcs->power_on_mpc_mem_pwr(mpc, mpcc_id, true);
 	if (pipe_ctx->top_pipe == NULL
-			&& mpc->funcs->set_output_gamma && stream->out_transfer_func) {
-		if (stream->out_transfer_func->type == TF_TYPE_HWPWL)
-			params = &stream->out_transfer_func->pwl;
-		else if (pipe_ctx->stream->out_transfer_func->type ==
+			&& mpc->funcs->set_output_gamma) {
+		if (stream->out_transfer_func.type == TF_TYPE_HWPWL)
+			params = &stream->out_transfer_func.pwl;
+		else if (pipe_ctx->stream->out_transfer_func.type ==
 			TF_TYPE_DISTRIBUTED_POINTS &&
 			cm_helper_translate_curve_to_hw_format(dc->ctx,
-			stream->out_transfer_func,
+			&stream->out_transfer_func,
 			&mpc->blender_params, false))
 			params = &mpc->blender_params;
 		/*
 		 * there is no ROM
 		 */
-		if (stream->out_transfer_func->type == TF_TYPE_PREDEFINED)
+		if (stream->out_transfer_func.type == TF_TYPE_PREDEFINED)
 			BREAK_TO_DEBUGGER();
 	}
 	/*
@@ -1050,17 +1050,15 @@ bool dcn20_set_blend_lut(
 {
 	struct dpp *dpp_base = pipe_ctx->plane_res.dpp;
 	bool result = true;
-	struct pwl_params *blend_lut = NULL;
-
-	if (plane_state->blend_tf) {
-		if (plane_state->blend_tf->type == TF_TYPE_HWPWL)
-			blend_lut = &plane_state->blend_tf->pwl;
-		else if (plane_state->blend_tf->type == TF_TYPE_DISTRIBUTED_POINTS) {
-			cm_helper_translate_curve_to_hw_format(plane_state->ctx,
-					plane_state->blend_tf,
-					&dpp_base->regamma_params, false);
-			blend_lut = &dpp_base->regamma_params;
-		}
+	const struct pwl_params *blend_lut = NULL;
+
+	if (plane_state->blend_tf.type == TF_TYPE_HWPWL)
+		blend_lut = &plane_state->blend_tf.pwl;
+	else if (plane_state->blend_tf.type == TF_TYPE_DISTRIBUTED_POINTS) {
+		cm_helper_translate_curve_to_hw_format(plane_state->ctx,
+				&plane_state->blend_tf,
+				&dpp_base->regamma_params, false);
+		blend_lut = &dpp_base->regamma_params;
 	}
 	result = dpp_base->funcs->dpp_program_blnd_lut(dpp_base, blend_lut);
 
@@ -1072,24 +1070,21 @@ bool dcn20_set_shaper_3dlut(
 {
 	struct dpp *dpp_base = pipe_ctx->plane_res.dpp;
 	bool result = true;
-	struct pwl_params *shaper_lut = NULL;
-
-	if (plane_state->in_shaper_func) {
-		if (plane_state->in_shaper_func->type == TF_TYPE_HWPWL)
-			shaper_lut = &plane_state->in_shaper_func->pwl;
-		else if (plane_state->in_shaper_func->type == TF_TYPE_DISTRIBUTED_POINTS) {
-			cm_helper_translate_curve_to_hw_format(plane_state->ctx,
-					plane_state->in_shaper_func,
-					&dpp_base->shaper_params, true);
-			shaper_lut = &dpp_base->shaper_params;
-		}
+	const struct pwl_params *shaper_lut = NULL;
+
+	if (plane_state->in_shaper_func.type == TF_TYPE_HWPWL)
+		shaper_lut = &plane_state->in_shaper_func.pwl;
+	else if (plane_state->in_shaper_func.type == TF_TYPE_DISTRIBUTED_POINTS) {
+		cm_helper_translate_curve_to_hw_format(plane_state->ctx,
+				&plane_state->in_shaper_func,
+				&dpp_base->shaper_params, true);
+		shaper_lut = &dpp_base->shaper_params;
 	}
 
 	result = dpp_base->funcs->dpp_program_shaper_lut(dpp_base, shaper_lut);
-	if (plane_state->lut3d_func &&
-		plane_state->lut3d_func->state.bits.initialized == 1)
+	if (plane_state->lut3d_func.state.bits.initialized == 1)
 		result = dpp_base->funcs->dpp_program_3dlut(dpp_base,
-								&plane_state->lut3d_func->lut_3d);
+								&plane_state->lut3d_func.lut_3d);
 	else
 		result = dpp_base->funcs->dpp_program_3dlut(dpp_base, NULL);
 
@@ -1112,15 +1107,7 @@ bool dcn20_set_input_transfer_func(struct dc *dc,
 	hws->funcs.set_shaper_3dlut(pipe_ctx, plane_state);
 	hws->funcs.set_blend_lut(pipe_ctx, plane_state);
 
-	if (plane_state->in_transfer_func)
-		tf = plane_state->in_transfer_func;
-
-
-	if (tf == NULL) {
-		dpp_base->funcs->dpp_set_degamma(dpp_base,
-				IPP_DEGAMMA_MODE_BYPASS);
-		return true;
-	}
+	tf = &plane_state->in_transfer_func;
 
 	if (tf->type == TF_TYPE_HWPWL || tf->type == TF_TYPE_DISTRIBUTED_POINTS)
 		use_degamma_ram = true;
@@ -1917,9 +1904,11 @@ static void dcn20_program_pipe(
 			dc->res_pool->hubbub->funcs->force_wm_propagate_to_pipes(dc->res_pool->hubbub);
 	}
 
-	if (dc->res_pool->hubbub->funcs->program_det_size && pipe_ctx->update_flags.bits.det_size)
-		dc->res_pool->hubbub->funcs->program_det_size(
-			dc->res_pool->hubbub, pipe_ctx->plane_res.hubp->inst, pipe_ctx->det_buffer_size_kb);
+	if (pipe_ctx->update_flags.bits.det_size) {
+		if (dc->res_pool->hubbub->funcs->program_det_size)
+			dc->res_pool->hubbub->funcs->program_det_size(
+				dc->res_pool->hubbub, pipe_ctx->plane_res.hubp->inst, pipe_ctx->det_buffer_size_kb);
+	}
 
 	if (pipe_ctx->update_flags.raw || pipe_ctx->plane_state->update_flags.raw || pipe_ctx->stream->update_flags.raw)
 		dcn20_update_dchubp_dpp(dc, pipe_ctx, context);
@@ -2080,9 +2069,11 @@ void dcn20_program_front_end_for_ctx(
 			 * turned on (i.e. in an MCLK switch) which can come in too late and cause issues with
 			 * DET allocation.
 			 */
-			if (hubbub->funcs->program_det_size && (context->res_ctx.pipe_ctx[i].update_flags.bits.disable ||
-					(context->res_ctx.pipe_ctx[i].plane_state && dc_state_get_pipe_subvp_type(context, &context->res_ctx.pipe_ctx[i]) == SUBVP_PHANTOM)))
-				hubbub->funcs->program_det_size(hubbub, dc->current_state->res_ctx.pipe_ctx[i].plane_res.hubp->inst, 0);
+			if ((context->res_ctx.pipe_ctx[i].update_flags.bits.disable ||
+					(context->res_ctx.pipe_ctx[i].plane_state && dc_state_get_pipe_subvp_type(context, &context->res_ctx.pipe_ctx[i]) == SUBVP_PHANTOM))) {
+				if (hubbub->funcs->program_det_size)
+					hubbub->funcs->program_det_size(hubbub, dc->current_state->res_ctx.pipe_ctx[i].plane_res.hubp->inst, 0);
+			}
 			hws->funcs.plane_atomic_disconnect(dc, dc->current_state, &dc->current_state->res_ctx.pipe_ctx[i]);
 			DC_LOG_DC("Reset mpcc for pipe %d\n", dc->current_state->res_ctx.pipe_ctx[i].pipe_idx);
 		}
@@ -2893,11 +2884,6 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 	struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc;
 
 	if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) {
-		if (dc->hwseq->funcs.setup_hpo_hw_control)
-			dc->hwseq->funcs.setup_hpo_hw_control(dc->hwseq, true);
-	}
-
-	if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) {
 		dto_params.otg_inst = tg->inst;
 		dto_params.pixclk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10;
 		dto_params.num_odm_segments = get_odm_segment_count(pipe_ctx);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_init.c
index 884e3e323338..ef6488165b8f 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_init.c
@@ -67,6 +67,7 @@ static const struct hw_sequencer_funcs dcn20_funcs = {
 	.setup_stereo = dcn10_setup_stereo,
 	.set_avmute = dce110_set_avmute,
 	.log_hw_state = dcn10_log_hw_state,
+	.log_color_state = dcn20_log_color_state,
 	.get_hw_state = dcn10_get_hw_state,
 	.clear_status_bits = dcn10_clear_status_bits,
 	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn201/dcn201_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn201/dcn201_hwseq.c
index d5769f38874f..6be846635a79 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn201/dcn201_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn201/dcn201_hwseq.c
@@ -167,7 +167,7 @@ void dcn201_init_blank(
 	struct tg_color black_color = {0};
 	struct output_pixel_processor *opp = NULL;
 	uint32_t num_opps, opp_id_src0, opp_id_src1;
-	uint32_t otg_active_width, otg_active_height;
+	uint32_t otg_active_width = 0, otg_active_height = 0;
 
 	/* program opp dpg blank color */
 	color_space = COLOR_SPACE_SRGB;
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
index 7252f5f781f0..804be977ea47 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
@@ -66,7 +66,7 @@ static void mmhub_update_page_table_config(struct dcn_hubbub_phys_addr_config *c
 
 int dcn21_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_phy_addr_space_config *pa_config)
 {
-	struct dcn_hubbub_phys_addr_config config;
+	struct dcn_hubbub_phys_addr_config config = {0};
 
 	config.system_aperture.fb_top = pa_config->system_aperture.fb_top;
 	config.system_aperture.fb_offset = pa_config->system_aperture.fb_offset;
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
index 8bc3d01537bb..ed9141a67db3 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
@@ -166,7 +166,7 @@ void dcn30_log_color_state(struct dc *dc,
 		 "C21        C22        C23        C24        "
 		 "C31        C32        C33        C34        \n");
 
-	for (i = 0; i < pool->pipe_count; i++) {
+	for (i = 0; i < pool->mpcc_count; i++) {
 		struct mpcc_state s = {0};
 
 		pool->mpc->funcs->read_mpcc_state(pool->mpc, i, &s);
@@ -223,16 +223,14 @@ bool dcn30_set_blend_lut(
 {
 	struct dpp *dpp_base = pipe_ctx->plane_res.dpp;
 	bool result = true;
-	struct pwl_params *blend_lut = NULL;
-
-	if (plane_state->blend_tf) {
-		if (plane_state->blend_tf->type == TF_TYPE_HWPWL)
-			blend_lut = &plane_state->blend_tf->pwl;
-		else if (plane_state->blend_tf->type == TF_TYPE_DISTRIBUTED_POINTS) {
-			cm3_helper_translate_curve_to_hw_format(
-					plane_state->blend_tf, &dpp_base->regamma_params, false);
-			blend_lut = &dpp_base->regamma_params;
-		}
+	const struct pwl_params *blend_lut = NULL;
+
+	if (plane_state->blend_tf.type == TF_TYPE_HWPWL)
+		blend_lut = &plane_state->blend_tf.pwl;
+	else if (plane_state->blend_tf.type == TF_TYPE_DISTRIBUTED_POINTS) {
+		cm3_helper_translate_curve_to_hw_format(
+				&plane_state->blend_tf, &dpp_base->regamma_params, false);
+		blend_lut = &dpp_base->regamma_params;
 	}
 	result = dpp_base->funcs->dpp_program_blnd_lut(dpp_base, blend_lut);
 
@@ -300,27 +298,24 @@ bool dcn30_set_input_transfer_func(struct dc *dc,
 	struct dpp *dpp_base = pipe_ctx->plane_res.dpp;
 	enum dc_transfer_func_predefined tf;
 	bool result = true;
-	struct pwl_params *params = NULL;
+	const struct pwl_params *params = NULL;
 
 	if (dpp_base == NULL || plane_state == NULL)
 		return false;
 
 	tf = TRANSFER_FUNCTION_UNITY;
 
-	if (plane_state->in_transfer_func &&
-		plane_state->in_transfer_func->type == TF_TYPE_PREDEFINED)
-		tf = plane_state->in_transfer_func->tf;
+	if (plane_state->in_transfer_func.type == TF_TYPE_PREDEFINED)
+		tf = plane_state->in_transfer_func.tf;
 
 	dpp_base->funcs->dpp_set_pre_degam(dpp_base, tf);
 
-	if (plane_state->in_transfer_func) {
-		if (plane_state->in_transfer_func->type == TF_TYPE_HWPWL)
-			params = &plane_state->in_transfer_func->pwl;
-		else if (plane_state->in_transfer_func->type == TF_TYPE_DISTRIBUTED_POINTS &&
-			cm3_helper_translate_curve_to_hw_format(plane_state->in_transfer_func,
-					&dpp_base->degamma_params, false))
-			params = &dpp_base->degamma_params;
-	}
+	if (plane_state->in_transfer_func.type == TF_TYPE_HWPWL)
+		params = &plane_state->in_transfer_func.pwl;
+	else if (plane_state->in_transfer_func.type == TF_TYPE_DISTRIBUTED_POINTS &&
+		cm3_helper_translate_curve_to_hw_format(&plane_state->in_transfer_func,
+				&dpp_base->degamma_params, false))
+		params = &dpp_base->degamma_params;
 
 	result = dpp_base->funcs->dpp_program_gamcor_lut(dpp_base, params);
 
@@ -378,24 +373,24 @@ bool dcn30_set_output_transfer_func(struct dc *dc,
 {
 	int mpcc_id = pipe_ctx->plane_res.hubp->inst;
 	struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc;
-	struct pwl_params *params = NULL;
+	const struct pwl_params *params = NULL;
 	bool ret = false;
 
 	/* program OGAM or 3DLUT only for the top pipe*/
 	if (pipe_ctx->top_pipe == NULL) {
 		/*program rmu shaper and 3dlut in MPC*/
 		ret = dcn30_set_mpc_shaper_3dlut(pipe_ctx, stream);
-		if (ret == false && mpc->funcs->set_output_gamma && stream->out_transfer_func) {
-			if (stream->out_transfer_func->type == TF_TYPE_HWPWL)
-				params = &stream->out_transfer_func->pwl;
-			else if (pipe_ctx->stream->out_transfer_func->type ==
+		if (ret == false && mpc->funcs->set_output_gamma) {
+			if (stream->out_transfer_func.type == TF_TYPE_HWPWL)
+				params = &stream->out_transfer_func.pwl;
+			else if (pipe_ctx->stream->out_transfer_func.type ==
 					TF_TYPE_DISTRIBUTED_POINTS &&
 					cm3_helper_translate_curve_to_hw_format(
-					stream->out_transfer_func,
+					&stream->out_transfer_func,
 					&mpc->blender_params, false))
 				params = &mpc->blender_params;
 			 /* there are no ROM LUTs in OUTGAM */
-			if (stream->out_transfer_func->type == TF_TYPE_PREDEFINED)
+			if (stream->out_transfer_func.type == TF_TYPE_PREDEFINED)
 				BREAK_TO_DEBUGGER();
 		}
 	}
@@ -804,7 +799,7 @@ void dcn30_init_hw(struct dc *dc)
 	// Get DMCUB capabilities
 	dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv);
 	dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr;
-	dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch;
+	dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch_ver;
 }
 
 void dcn30_set_avmute(struct pipe_ctx *pipe_ctx, bool enable)
@@ -818,7 +813,7 @@ void dcn30_set_avmute(struct pipe_ctx *pipe_ctx, bool enable)
 				enable);
 
 		/* Wait for two frame to make sure AV mute is sent out */
-		if (enable) {
+		if (enable && pipe_ctx->stream_res.tg->funcs->is_tg_enabled(pipe_ctx->stream_res.tg)) {
 			pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE);
 			pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK);
 			pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE);
@@ -890,7 +885,7 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable)
 {
 	union dmub_rb_cmd cmd;
 	uint32_t tmr_delay = 0, tmr_scale = 0;
-	struct dc_cursor_attributes cursor_attr;
+	struct dc_cursor_attributes cursor_attr = {0};
 	bool cursor_cache_enable = false;
 	struct dc_stream_state *stream = NULL;
 	struct dc_plane_state *plane = NULL;
@@ -946,7 +941,8 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable)
 					plane->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB8888 &&
 					plane->address.page_table_base.quad_part == 0 &&
 					dc->hwss.does_plane_fit_in_mall &&
-					dc->hwss.does_plane_fit_in_mall(dc, plane,
+					dc->hwss.does_plane_fit_in_mall(dc, plane->plane_size.surface_pitch,
+							plane->plane_size.surface_size.height, plane->format,
 							cursor_cache_enable ? &cursor_attr : NULL)) {
 				unsigned int v_total = stream->adjust.v_total_max ?
 						stream->adjust.v_total_max : stream->timing.v_total;
@@ -1076,11 +1072,15 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable)
 	return true;
 }
 
-bool dcn30_does_plane_fit_in_mall(struct dc *dc, struct dc_plane_state *plane, struct dc_cursor_attributes *cursor_attr)
+bool dcn30_does_plane_fit_in_mall(struct dc *dc,
+		unsigned int pitch,
+		unsigned int height,
+		enum surface_pixel_format format,
+		struct dc_cursor_attributes *cursor_attr)
 {
 	// add meta size?
-	unsigned int surface_size = plane->plane_size.surface_pitch * plane->plane_size.surface_size.height *
-			(plane->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4);
+	unsigned int surface_size = pitch * height *
+			(format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4);
 	unsigned int mall_size = dc->caps.mall_size_total;
 	unsigned int cursor_size = 0;
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.h
index 638f018a3cb5..76b16839486a 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.h
@@ -71,7 +71,10 @@ void dcn30_set_avmute(struct pipe_ctx *pipe_ctx, bool enable);
 void dcn30_update_info_frame(struct pipe_ctx *pipe_ctx);
 void dcn30_program_dmdata_engine(struct pipe_ctx *pipe_ctx);
 
-bool dcn30_does_plane_fit_in_mall(struct dc *dc, struct dc_plane_state *plane,
+bool dcn30_does_plane_fit_in_mall(struct dc *dc,
+		unsigned int pitch,
+		unsigned int height,
+		enum surface_pixel_format format,
 		struct dc_cursor_attributes *cursor_attr);
 
 bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c
index a760f0c6fe98..1c8abb417b6e 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c
@@ -273,7 +273,7 @@ void dcn31_init_hw(struct dc *dc)
 	// Get DMCUB capabilities
 	dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv);
 	dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr;
-	dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch;
+	dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch_ver;
 }
 
 void dcn31_dsc_pg_control(
@@ -479,7 +479,7 @@ void dcn31_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool p
 
 int dcn31_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_phy_addr_space_config *pa_config)
 {
-	struct dcn_hubbub_phys_addr_config config;
+	struct dcn_hubbub_phys_addr_config config = {0};
 
 	config.system_aperture.fb_top = pa_config->system_aperture.fb_top;
 	config.system_aperture.fb_offset = pa_config->system_aperture.fb_offset;
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
index 093f4387553c..0d8a05cf8b1a 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
@@ -82,7 +82,7 @@ static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 
 	if (enable) {
 		struct dsc_config dsc_cfg;
-		struct dsc_optc_config dsc_optc_cfg;
+		struct dsc_optc_config dsc_optc_cfg = {0};
 		enum optc_dsc_mode optc_dsc_mode;
 
 		/* Enable DSC hw block */
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index 7668229438da..b8e884368dc6 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -239,8 +239,10 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 	// Convert number of cache lines required to number of ways
 	if (dc->debug.force_mall_ss_num_ways > 0) {
 		num_ways = dc->debug.force_mall_ss_num_ways;
+	} else if (dc->res_pool->funcs->calculate_mall_ways_from_bytes) {
+		num_ways = dc->res_pool->funcs->calculate_mall_ways_from_bytes(dc, mall_ss_size_bytes);
 	} else {
-		num_ways = dcn32_helper_mall_bytes_to_ways(dc, mall_ss_size_bytes);
+		num_ways = 0;
 	}
 
 	return num_ways;
@@ -261,7 +263,9 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable)
 	for (i = 0; i < dc->current_state->stream_count; i++) {
 		/* MALL SS messaging is not supported with PSR at this time */
 		if (dc->current_state->streams[i] != NULL &&
-				dc->current_state->streams[i]->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED)
+				dc->current_state->streams[i]->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED &&
+				(dc->current_state->stream_count > 1 || (!dc->current_state->streams[i]->dpms_off &&
+						dc->current_state->stream_status[i].plane_count > 0)))
 			return false;
 	}
 
@@ -475,39 +479,35 @@ bool dcn32_set_mcm_luts(
 	int mpcc_id = pipe_ctx->plane_res.hubp->inst;
 	struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc;
 	bool result = true;
-	struct pwl_params *lut_params = NULL;
+	const struct pwl_params *lut_params = NULL;
 
 	// 1D LUT
-	if (plane_state->blend_tf) {
-		if (plane_state->blend_tf->type == TF_TYPE_HWPWL)
-			lut_params = &plane_state->blend_tf->pwl;
-		else if (plane_state->blend_tf->type == TF_TYPE_DISTRIBUTED_POINTS) {
-			cm3_helper_translate_curve_to_hw_format(plane_state->blend_tf,
-					&dpp_base->regamma_params, false);
-			lut_params = &dpp_base->regamma_params;
-		}
+	if (plane_state->blend_tf.type == TF_TYPE_HWPWL)
+		lut_params = &plane_state->blend_tf.pwl;
+	else if (plane_state->blend_tf.type == TF_TYPE_DISTRIBUTED_POINTS) {
+		cm3_helper_translate_curve_to_hw_format(&plane_state->blend_tf,
+				&dpp_base->regamma_params, false);
+		lut_params = &dpp_base->regamma_params;
 	}
 	result = mpc->funcs->program_1dlut(mpc, lut_params, mpcc_id);
 	lut_params = NULL;
 
 	// Shaper
-	if (plane_state->in_shaper_func) {
-		if (plane_state->in_shaper_func->type == TF_TYPE_HWPWL)
-			lut_params = &plane_state->in_shaper_func->pwl;
-		else if (plane_state->in_shaper_func->type == TF_TYPE_DISTRIBUTED_POINTS) {
-			// TODO: dpp_base replace
-			ASSERT(false);
-			cm3_helper_translate_curve_to_hw_format(plane_state->in_shaper_func,
-					&dpp_base->shaper_params, true);
-			lut_params = &dpp_base->shaper_params;
-		}
+	if (plane_state->in_shaper_func.type == TF_TYPE_HWPWL)
+		lut_params = &plane_state->in_shaper_func.pwl;
+	else if (plane_state->in_shaper_func.type == TF_TYPE_DISTRIBUTED_POINTS) {
+		// TODO: dpp_base replace
+		ASSERT(false);
+		cm3_helper_translate_curve_to_hw_format(&plane_state->in_shaper_func,
+				&dpp_base->shaper_params, true);
+		lut_params = &dpp_base->shaper_params;
 	}
 
 	result = mpc->funcs->program_shaper(mpc, lut_params, mpcc_id);
 
 	// 3D
-	if (plane_state->lut3d_func && plane_state->lut3d_func->state.bits.initialized == 1)
-		result = mpc->funcs->program_3dlut(mpc, &plane_state->lut3d_func->lut_3d, mpcc_id);
+	if (plane_state->lut3d_func.state.bits.initialized == 1)
+		result = mpc->funcs->program_3dlut(mpc, &plane_state->lut3d_func.lut_3d, mpcc_id);
 	else
 		result = mpc->funcs->program_3dlut(mpc, NULL, mpcc_id);
 
@@ -524,27 +524,24 @@ bool dcn32_set_input_transfer_func(struct dc *dc,
 
 	enum dc_transfer_func_predefined tf;
 	bool result = true;
-	struct pwl_params *params = NULL;
+	const struct pwl_params *params = NULL;
 
 	if (mpc == NULL || plane_state == NULL)
 		return false;
 
 	tf = TRANSFER_FUNCTION_UNITY;
 
-	if (plane_state->in_transfer_func &&
-		plane_state->in_transfer_func->type == TF_TYPE_PREDEFINED)
-		tf = plane_state->in_transfer_func->tf;
+	if (plane_state->in_transfer_func.type == TF_TYPE_PREDEFINED)
+		tf = plane_state->in_transfer_func.tf;
 
 	dpp_base->funcs->dpp_set_pre_degam(dpp_base, tf);
 
-	if (plane_state->in_transfer_func) {
-		if (plane_state->in_transfer_func->type == TF_TYPE_HWPWL)
-			params = &plane_state->in_transfer_func->pwl;
-		else if (plane_state->in_transfer_func->type == TF_TYPE_DISTRIBUTED_POINTS &&
-			cm3_helper_translate_curve_to_hw_format(plane_state->in_transfer_func,
-					&dpp_base->degamma_params, false))
-			params = &dpp_base->degamma_params;
-	}
+	if (plane_state->in_transfer_func.type == TF_TYPE_HWPWL)
+		params = &plane_state->in_transfer_func.pwl;
+	else if (plane_state->in_transfer_func.type == TF_TYPE_DISTRIBUTED_POINTS &&
+		cm3_helper_translate_curve_to_hw_format(&plane_state->in_transfer_func,
+				&dpp_base->degamma_params, false))
+		params = &dpp_base->degamma_params;
 
 	dpp_base->funcs->dpp_program_gamcor_lut(dpp_base, params);
 
@@ -562,24 +559,24 @@ bool dcn32_set_output_transfer_func(struct dc *dc,
 {
 	int mpcc_id = pipe_ctx->plane_res.hubp->inst;
 	struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc;
-	struct pwl_params *params = NULL;
+	const struct pwl_params *params = NULL;
 	bool ret = false;
 
 	/* program OGAM or 3DLUT only for the top pipe*/
 	if (resource_is_pipe_type(pipe_ctx, OPP_HEAD)) {
 		/*program shaper and 3dlut in MPC*/
 		ret = dcn32_set_mpc_shaper_3dlut(pipe_ctx, stream);
-		if (ret == false && mpc->funcs->set_output_gamma && stream->out_transfer_func) {
-			if (stream->out_transfer_func->type == TF_TYPE_HWPWL)
-				params = &stream->out_transfer_func->pwl;
-			else if (pipe_ctx->stream->out_transfer_func->type ==
+		if (ret == false && mpc->funcs->set_output_gamma) {
+			if (stream->out_transfer_func.type == TF_TYPE_HWPWL)
+				params = &stream->out_transfer_func.pwl;
+			else if (pipe_ctx->stream->out_transfer_func.type ==
 					TF_TYPE_DISTRIBUTED_POINTS &&
 					cm3_helper_translate_curve_to_hw_format(
-					stream->out_transfer_func,
+					&stream->out_transfer_func,
 					&mpc->blender_params, false))
 				params = &mpc->blender_params;
 			/* there are no ROM LUTs in OUTGAM */
-			if (stream->out_transfer_func->type == TF_TYPE_PREDEFINED)
+			if (stream->out_transfer_func.type == TF_TYPE_PREDEFINED)
 				BREAK_TO_DEBUGGER();
 		}
 	}
@@ -956,10 +953,10 @@ void dcn32_init_hw(struct dc *dc)
 		dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr;
 		dc->caps.dmub_caps.subvp_psr = dc->ctx->dmub_srv->dmub->feature_caps.subvp_psr_support;
 		dc->caps.dmub_caps.gecc_enable = dc->ctx->dmub_srv->dmub->feature_caps.gecc_enable;
-		dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch;
+		dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch_ver;
 
 		if (dc->ctx->dmub_srv->dmub->fw_version <
-		    DMUB_FW_VERSION(7, 0, 35)) {
+				DMUB_FW_VERSION(7, 0, 35)) {
 			dc->debug.force_disable_subvp = true;
 			dc->debug.disable_fpo_optimizations = true;
 		}
@@ -992,7 +989,7 @@ static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 
 	if (enable) {
 		struct dsc_config dsc_cfg;
-		struct dsc_optc_config dsc_optc_cfg;
+		struct dsc_optc_config dsc_optc_cfg = {0};
 		enum optc_dsc_mode optc_dsc_mode;
 
 		/* Enable DSC hw block */
@@ -1545,7 +1542,7 @@ void dcn32_init_blank(
 	struct output_pixel_processor *opp = NULL;
 	struct output_pixel_processor *bottom_opp = NULL;
 	uint32_t num_opps, opp_id_src0, opp_id_src1;
-	uint32_t otg_active_width, otg_active_height;
+	uint32_t otg_active_width = 0, otg_active_height = 0;
 	uint32_t i;
 
 	/* program opp dpg blank color */
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index 9067ca78f851..5295f52e4fc8 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -349,7 +349,7 @@ void dcn35_init_hw(struct dc *dc)
 	if (dc->ctx->dmub_srv) {
 		dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv);
 		dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr;
-		dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch;
+		dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch_ver;
 	}
 
 	if (dc->res_pool->pg_cntl) {
@@ -373,7 +373,7 @@ static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 
 	if (enable) {
 		struct dsc_config dsc_cfg;
-		struct dsc_optc_config dsc_optc_cfg;
+		struct dsc_optc_config dsc_optc_cfg = {0};
 		enum optc_dsc_mode optc_dsc_mode;
 
 		/* Enable DSC hw block */
@@ -495,6 +495,17 @@ void dcn35_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst,
 	}
 }
 
+void dcn35_dpstream_root_clock_control(struct dce_hwseq *hws, unsigned int dp_hpo_inst, bool clock_on)
+{
+	if (!hws->ctx->dc->debug.root_clock_optimization.bits.dpstream)
+		return;
+
+	if (hws->ctx->dc->res_pool->dccg->funcs->set_dpstreamclk_root_clock_gating) {
+		hws->ctx->dc->res_pool->dccg->funcs->set_dpstreamclk_root_clock_gating(
+			hws->ctx->dc->res_pool->dccg, dp_hpo_inst, clock_on);
+	}
+}
+
 void dcn35_dsc_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int dsc_inst,
@@ -700,6 +711,7 @@ void dcn35_init_pipes(struct dc *dc, struct dc_state *context)
 	struct hubbub *hubbub = dc->res_pool->hubbub;
 	struct pg_cntl *pg_cntl = dc->res_pool->pg_cntl;
 	bool can_apply_seamless_boot = false;
+	bool tg_enabled[MAX_PIPES] = {false};
 
 	for (i = 0; i < context->stream_count; i++) {
 		if (context->streams[i]->apply_seamless_boot_optimization) {
@@ -781,6 +793,7 @@ void dcn35_init_pipes(struct dc *dc, struct dc_state *context)
 			// requesting data while in PSR.
 			tg->funcs->tg_init(tg);
 			hubp->power_gated = true;
+			tg_enabled[i] = true;
 			continue;
 		}
 
@@ -822,6 +835,20 @@ void dcn35_init_pipes(struct dc *dc, struct dc_state *context)
 		tg->funcs->tg_init(tg);
 	}
 
+	/* Clean up MPC tree */
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (tg_enabled[i]) {
+			if (dc->res_pool->opps[i]->mpc_tree_params.opp_list) {
+				if (dc->res_pool->opps[i]->mpc_tree_params.opp_list->mpcc_bot) {
+					int bot_id = dc->res_pool->opps[i]->mpc_tree_params.opp_list->mpcc_bot->mpcc_id;
+
+					if ((bot_id < MAX_MPCC) && (bot_id < MAX_PIPES) && (!tg_enabled[bot_id]))
+						dc->res_pool->opps[i]->mpc_tree_params.opp_list = NULL;
+				}
+			}
+		}
+	}
+
 	if (pg_cntl != NULL) {
 		if (pg_cntl->funcs->dsc_pg_control != NULL) {
 			uint32_t num_opps = 0;
@@ -982,6 +1009,9 @@ void dcn35_calc_blocks_to_gate(struct dc *dc, struct dc_state *context,
 	if (!hpo_frl_stream_enc_acquired && !hpo_dp_stream_enc_acquired)
 		update_state->pg_res_update[PG_HPO] = true;
 
+	if (hpo_frl_stream_enc_acquired)
+		update_state->pg_pipe_res_update[PG_HDMISTREAM][0] = true;
+
 	update_state->pg_res_update[PG_DWB] = true;
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
@@ -999,8 +1029,7 @@ void dcn35_calc_blocks_to_gate(struct dc *dc, struct dc_state *context,
 		if (pipe_ctx->plane_res.dpp)
 			update_state->pg_pipe_res_update[PG_DPP][pipe_ctx->plane_res.hubp->inst] = false;
 
-		if ((pipe_ctx->plane_res.dpp || pipe_ctx->stream_res.opp) &&
-			pipe_ctx->plane_res.mpcc_inst >= 0)
+		if (pipe_ctx->plane_res.dpp || pipe_ctx->stream_res.opp)
 			update_state->pg_pipe_res_update[PG_MPCC][pipe_ctx->plane_res.mpcc_inst] = false;
 
 		if (pipe_ctx->stream_res.dsc)
@@ -1008,6 +1037,9 @@ void dcn35_calc_blocks_to_gate(struct dc *dc, struct dc_state *context,
 
 		if (pipe_ctx->stream_res.opp)
 			update_state->pg_pipe_res_update[PG_OPP][pipe_ctx->stream_res.opp->inst] = false;
+
+		if (pipe_ctx->stream_res.hpo_dp_stream_enc)
+			update_state->pg_pipe_res_update[PG_DPSTREAM][pipe_ctx->stream_res.hpo_dp_stream_enc->inst] = false;
 	}
 	/*domain24 controls all the otg, mpc, opp, as long as one otg is still up, avoid enabling OTG PG*/
 	for (i = 0; i < dc->res_pool->timing_generator_count; i++) {
@@ -1065,6 +1097,9 @@ void dcn35_calc_blocks_to_ungate(struct dc *dc, struct dc_state *context,
 
 				if (j == PG_OPTC && new_pipe->stream_res.tg)
 					update_state->pg_pipe_res_update[j][new_pipe->stream_res.tg->inst] = true;
+
+				if (j == PG_DPSTREAM && new_pipe->stream_res.hpo_dp_stream_enc)
+					update_state->pg_pipe_res_update[j][new_pipe->stream_res.hpo_dp_stream_enc->inst] = true;
 			}
 		} else if (cur_pipe->plane_state == new_pipe->plane_state ||
 				cur_pipe == new_pipe) {
@@ -1094,6 +1129,11 @@ void dcn35_calc_blocks_to_ungate(struct dc *dc, struct dc_state *context,
 					cur_pipe->stream_res.tg != new_pipe->stream_res.tg &&
 					new_pipe->stream_res.tg)
 					update_state->pg_pipe_res_update[j][new_pipe->stream_res.tg->inst] = true;
+
+				if (j == PG_DPSTREAM &&
+					cur_pipe->stream_res.hpo_dp_stream_enc != new_pipe->stream_res.hpo_dp_stream_enc &&
+					new_pipe->stream_res.hpo_dp_stream_enc)
+					update_state->pg_pipe_res_update[j][new_pipe->stream_res.hpo_dp_stream_enc->inst] = true;
 			}
 		}
 	}
@@ -1109,6 +1149,9 @@ void dcn35_calc_blocks_to_ungate(struct dc *dc, struct dc_state *context,
 	if (hpo_frl_stream_enc_acquired || hpo_dp_stream_enc_acquired)
 		update_state->pg_res_update[PG_HPO] = true;
 
+	if (hpo_frl_stream_enc_acquired)
+		update_state->pg_pipe_res_update[PG_HDMISTREAM][0] = true;
+
 }
 
 /**
@@ -1233,14 +1276,19 @@ void dcn35_root_clock_control(struct dc *dc,
 	if (!pg_cntl)
 		return;
 	/*enable root clock first when power up*/
-	if (power_on)
+	if (power_on) {
 		for (i = 0; i < dc->res_pool->pipe_count; i++) {
 			if (update_state->pg_pipe_res_update[PG_HUBP][i] &&
 				update_state->pg_pipe_res_update[PG_DPP][i]) {
 				if (dc->hwseq->funcs.dpp_root_clock_control)
 					dc->hwseq->funcs.dpp_root_clock_control(dc->hwseq, i, power_on);
 			}
+			if (update_state->pg_pipe_res_update[PG_DPSTREAM][i])
+				if (dc->hwseq->funcs.dpstream_root_clock_control)
+					dc->hwseq->funcs.dpstream_root_clock_control(dc->hwseq, i, power_on);
 		}
+
+	}
 	for (i = 0; i < dc->res_pool->res_cap->num_dsc; i++) {
 		if (update_state->pg_pipe_res_update[PG_DSC][i]) {
 			if (power_on) {
@@ -1253,14 +1301,19 @@ void dcn35_root_clock_control(struct dc *dc,
 		}
 	}
 	/*disable root clock first when power down*/
-	if (!power_on)
+	if (!power_on) {
 		for (i = 0; i < dc->res_pool->pipe_count; i++) {
 			if (update_state->pg_pipe_res_update[PG_HUBP][i] &&
 				update_state->pg_pipe_res_update[PG_DPP][i]) {
 				if (dc->hwseq->funcs.dpp_root_clock_control)
 					dc->hwseq->funcs.dpp_root_clock_control(dc->hwseq, i, power_on);
 			}
+			if (update_state->pg_pipe_res_update[PG_DPSTREAM][i])
+				if (dc->hwseq->funcs.dpstream_root_clock_control)
+					dc->hwseq->funcs.dpstream_root_clock_control(dc->hwseq, i, power_on);
 		}
+
+	}
 }
 
 void dcn35_prepare_bandwidth(
@@ -1301,22 +1354,6 @@ void dcn35_optimize_bandwidth(
 	}
 }
 
-void dcn35_set_idle_state(const struct dc *dc, bool allow_idle)
-{
-	// TODO: Find a more suitable communcation
-	if (dc->clk_mgr->funcs->set_idle_state)
-		dc->clk_mgr->funcs->set_idle_state(dc->clk_mgr, allow_idle);
-}
-
-uint32_t dcn35_get_idle_state(const struct dc *dc)
-{
-	// TODO: Find a more suitable communcation
-	if (dc->clk_mgr->funcs->get_idle_state)
-		return dc->clk_mgr->funcs->get_idle_state(dc->clk_mgr);
-
-	return 0;
-}
-
 void dcn35_set_drr(struct pipe_ctx **pipe_ctx,
 		int num_pipes, struct dc_crtc_timing_adjust adjust)
 {
@@ -1374,3 +1411,31 @@ void dcn35_set_static_screen_control(struct pipe_ctx **pipe_ctx,
 			set_static_screen_control(pipe_ctx[i]->stream_res.tg,
 					triggers, params->num_frames);
 }
+
+void dcn35_set_long_vblank(struct pipe_ctx **pipe_ctx,
+		int num_pipes, uint32_t v_total_min, uint32_t v_total_max)
+{
+	int i = 0;
+	struct long_vtotal_params params = {0};
+
+	params.vertical_total_max = v_total_max;
+	params.vertical_total_min = v_total_min;
+
+	for (i = 0; i < num_pipes; i++) {
+		if (!pipe_ctx[i])
+			continue;
+
+		if (pipe_ctx[i]->stream) {
+			struct dc_crtc_timing *timing = &pipe_ctx[i]->stream->timing;
+
+			if (timing)
+				params.vertical_blank_start = timing->v_total - timing->v_front_porch;
+			else
+				params.vertical_blank_start = 0;
+
+			if ((pipe_ctx[i]->stream_res.tg != NULL) && pipe_ctx[i]->stream_res.tg->funcs &&
+				pipe_ctx[i]->stream_res.tg->funcs->set_long_vtotal)
+				pipe_ctx[i]->stream_res.tg->funcs->set_long_vtotal(pipe_ctx[i]->stream_res.tg, &params);
+		}
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h
index c354efa6c1b2..a731c8880d60 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h
@@ -37,6 +37,8 @@ void dcn35_dsc_pg_control(struct dce_hwseq *hws, unsigned int dsc_inst, bool pow
 
 void dcn35_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool clock_on);
 
+void dcn35_dpstream_root_clock_control(struct dce_hwseq *hws, unsigned int dp_hpo_inst, bool clock_on);
+
 void dcn35_enable_power_gating_plane(struct dce_hwseq *hws, bool enable);
 
 void dcn35_set_dmu_fgcg(struct dce_hwseq *hws, bool enable);
@@ -84,13 +86,13 @@ void dcn35_dsc_pg_control(
 		unsigned int dsc_inst,
 		bool power_on);
 
-void dcn35_set_idle_state(const struct dc *dc, bool allow_idle);
-uint32_t dcn35_get_idle_state(const struct dc *dc);
-
 void dcn35_set_drr(struct pipe_ctx **pipe_ctx,
 		int num_pipes, struct dc_crtc_timing_adjust adjust);
 
 void dcn35_set_static_screen_control(struct pipe_ctx **pipe_ctx,
 		int num_pipes, const struct dc_static_screen_params *params);
 
+void dcn35_set_long_vblank(struct pipe_ctx **pipe_ctx,
+		int num_pipes, uint32_t v_total_min, uint32_t v_total_max);
+
 #endif /* __DC_HWSS_DCN35_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
index a93073055e7b..df3bf77f3fb4 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
@@ -121,8 +121,7 @@ static const struct hw_sequencer_funcs dcn35_funcs = {
 	.hw_block_power_up = dcn35_hw_block_power_up,
 	.hw_block_power_down = dcn35_hw_block_power_down,
 	.root_clock_control = dcn35_root_clock_control,
-	.set_idle_state = dcn35_set_idle_state,
-	.get_idle_state = dcn35_get_idle_state
+	.set_long_vtotal = dcn35_set_long_vblank,
 };
 
 static const struct hwseq_private_funcs dcn35_private_funcs = {
@@ -148,6 +147,7 @@ static const struct hwseq_private_funcs dcn35_private_funcs = {
 	//.hubp_pg_control = dcn35_hubp_pg_control,
 	.enable_power_gating_plane = dcn35_enable_power_gating_plane,
 	.dpp_root_clock_control = dcn35_dpp_root_clock_control,
+	.dpstream_root_clock_control = dcn35_dpstream_root_clock_control,
 	.program_all_writeback_pipes_in_tree = dcn30_program_all_writeback_pipes_in_tree,
 	.update_odm = dcn35_update_odm,
 	.set_hdr_multiplier = dcn10_set_hdr_multiplier,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/Makefile b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/Makefile
index b24ad27fe6ef..a4b3c1e99ec6 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/Makefile
@@ -1,16 +1,27 @@
 #
-# (c) Copyright 2022 Advanced Micro Devices, Inc. All the rights reserved
+# Copyright (c) 2022-2024 Advanced Micro Devices, Inc.
 #
-#  All rights reserved.  This notice is intended as a precaution against
-#  inadvertent publication and does not imply publication or any waiver
-#  of confidentiality.  The year included in the foregoing notice is the
-#  year of creation of the work.
+# 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:
 #
-#  Authors: AMD
+# 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.
 #
 # Makefile for DCN351.
 
-DCN351 = dcn351_init.o
+DCN351 = dcn351_hwseq.o dcn351_init.o
 
 AMD_DAL_DCN351 = $(addprefix $(AMDDALPATH)/dc/dcn351/,$(DCN351))
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_hwseq.c
new file mode 100644
index 000000000000..93fe5b262a3d
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_hwseq.c
@@ -0,0 +1,182 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2024 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 "core_types.h"
+#include "resource.h"
+#include "dcn351_hwseq.h"
+#include "dcn35/dcn35_hwseq.h"
+
+#define DC_LOGGER_INIT(logger) \
+	struct dal_logger *dc_logger = logger
+
+#define DC_LOGGER \
+	dc_logger
+
+void dcn351_calc_blocks_to_gate(struct dc *dc, struct dc_state *context,
+	struct pg_block_update *update_state)
+{
+	int i, j;
+
+	dcn35_calc_blocks_to_gate(dc, context, update_state);
+
+	for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) {
+		if (!update_state->pg_pipe_res_update[PG_HUBP][i] &&
+			!update_state->pg_pipe_res_update[PG_DPP][i]) {
+			for (j = i - 1; j >= 0; j--) {
+				update_state->pg_pipe_res_update[PG_HUBP][j] = false;
+				update_state->pg_pipe_res_update[PG_DPP][j] = false;
+			}
+
+			break;
+		}
+	}
+}
+
+void dcn351_calc_blocks_to_ungate(struct dc *dc, struct dc_state *context,
+	struct pg_block_update *update_state)
+{
+	int i, j;
+
+	dcn35_calc_blocks_to_ungate(dc, context, update_state);
+
+	for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) {
+		if (update_state->pg_pipe_res_update[PG_HUBP][i] &&
+			update_state->pg_pipe_res_update[PG_DPP][i]) {
+			for (j = i - 1; j >= 0; j--) {
+				update_state->pg_pipe_res_update[PG_HUBP][j] = true;
+				update_state->pg_pipe_res_update[PG_DPP][j] = true;
+			}
+
+			break;
+		}
+	}
+}
+
+/**
+ * dcn351_hw_block_power_down() - power down sequence
+ *
+ * The following sequence describes the ON-OFF (ONO) for power down:
+ *
+ *	ONO Region 11, DCPG 19: dsc3
+ *	ONO Region 10, DCPG 3: dchubp3, dpp3
+ *	ONO Region 9, DCPG 18: dsc2
+ *	ONO Region 8, DCPG 2: dchubp2, dpp2
+ *	ONO Region 7, DCPG 17: dsc1
+ *	ONO Region 6, DCPG 1: dchubp1, dpp1
+ *	ONO Region 5, DCPG 16: dsc0
+ *	ONO Region 4, DCPG 0: dchubp0, dpp0
+ *	ONO Region 3, DCPG 25: hpo - SKIPPED. Should be kept on
+ *	ONO Region 2, DCPG 24: mpc opp optc dwb
+ *	ONO Region 1, DCPG 23: dchubbub dchvm dchubbubmem - SKIPPED. PMFW will pwr dwn at IPS2 entry
+ *	ONO Region 0, DCPG 22: dccg dio dcio - SKIPPED. will be pwr dwn after lono timer is armed
+ *
+ * @dc: Current DC state
+ * @update_state: update PG sequence states for HW block
+ */
+void dcn351_hw_block_power_down(struct dc *dc,
+	struct pg_block_update *update_state)
+{
+	int i = 0;
+	struct pg_cntl *pg_cntl = dc->res_pool->pg_cntl;
+
+	if (!pg_cntl || dc->debug.ignore_pg)
+		return;
+
+	for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) {
+		if (update_state->pg_pipe_res_update[PG_DSC][i]) {
+			if (pg_cntl->funcs->dsc_pg_control)
+				pg_cntl->funcs->dsc_pg_control(pg_cntl, i, false);
+		}
+
+		if (update_state->pg_pipe_res_update[PG_HUBP][i] &&
+			update_state->pg_pipe_res_update[PG_DPP][i]) {
+			if (pg_cntl->funcs->hubp_dpp_pg_control)
+				pg_cntl->funcs->hubp_dpp_pg_control(pg_cntl, i, false);
+		}
+	}
+
+	// domain25 currently always on.
+
+	/* this will need all the clients to unregister optc interrupts, let dmubfw handle this */
+	if (pg_cntl->funcs->plane_otg_pg_control)
+		pg_cntl->funcs->plane_otg_pg_control(pg_cntl, false);
+
+	// domain23 currently always on.
+	// domain22 currently always on.
+}
+
+/**
+ * dcn351_hw_block_power_up() - power up sequence
+ *
+ * The following sequence describes the ON-OFF (ONO) for power up:
+ *
+ *	ONO Region 0, DCPG 22: dccg dio dcio - SKIPPED
+ *	ONO Region 1, DCPG 23: dchubbub dchvm dchubbubmem - SKIPPED. PMFW will power up at IPS2 exit
+ *	ONO Region 2, DCPG 24: mpc opp optc dwb
+ *	ONO Region 3, DCPG 25: hpo - SKIPPED
+ *	ONO Region 4, DCPG 0: dchubp0, dpp0
+ *	ONO Region 5, DCPG 16: dsc0
+ *	ONO Region 6, DCPG 1: dchubp1, dpp1
+ *	ONO Region 7, DCPG 17: dsc1
+ *	ONO Region 8, DCPG 2: dchubp2, dpp2
+ *	ONO Region 9, DCPG 18: dsc2
+ *	ONO Region 10, DCPG 3: dchubp3, dpp3
+ *	ONO Region 11, DCPG 19: dsc3
+ *
+ * @dc: Current DC state
+ * @update_state: update PG sequence states for HW block
+ */
+void dcn351_hw_block_power_up(struct dc *dc,
+	struct pg_block_update *update_state)
+{
+	int i = 0;
+	struct pg_cntl *pg_cntl = dc->res_pool->pg_cntl;
+
+	if (!pg_cntl || dc->debug.ignore_pg)
+		return;
+
+	// domain22 currently always on.
+	// domain23 currently always on.
+
+	/* this will need all the clients to unregister optc interrupts, let dmubfw handle this */
+	if (pg_cntl->funcs->plane_otg_pg_control)
+		pg_cntl->funcs->plane_otg_pg_control(pg_cntl, true);
+
+	// domain25 currently always on.
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (update_state->pg_pipe_res_update[PG_HUBP][i] &&
+			update_state->pg_pipe_res_update[PG_DPP][i]) {
+			if (pg_cntl->funcs->hubp_dpp_pg_control)
+				pg_cntl->funcs->hubp_dpp_pg_control(pg_cntl, i, true);
+		}
+
+		if (update_state->pg_pipe_res_update[PG_DSC][i]) {
+			if (pg_cntl->funcs->dsc_pg_control)
+				pg_cntl->funcs->dsc_pg_control(pg_cntl, i, true);
+		}
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_hwseq.h
new file mode 100644
index 000000000000..6d8f3bfb668e
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_hwseq.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2024 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 __DC_HWSS_DCN351_H__
+#define __DC_HWSS_DCN351_H__
+
+#include "hw_sequencer_private.h"
+
+void dcn351_calc_blocks_to_gate(struct dc *dc, struct dc_state *context,
+	struct pg_block_update *update_state);
+void dcn351_calc_blocks_to_ungate(struct dc *dc, struct dc_state *context,
+	struct pg_block_update *update_state);
+void dcn351_hw_block_power_up(struct dc *dc,
+	struct pg_block_update *update_state);
+void dcn351_hw_block_power_down(struct dc *dc,
+	struct pg_block_update *update_state);
+
+#endif /* __DC_HWSS_DCN351_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
index 670255c9bc82..a53092cd619b 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
@@ -32,6 +32,7 @@
 #include "dcn31/dcn31_hwseq.h"
 #include "dcn32/dcn32_hwseq.h"
 #include "dcn35/dcn35_hwseq.h"
+#include "dcn351/dcn351_hwseq.h"
 
 #include "dcn351_init.h"
 
@@ -120,8 +121,6 @@ static const struct hw_sequencer_funcs dcn351_funcs = {
 	.hw_block_power_up = dcn35_hw_block_power_up,
 	.hw_block_power_down = dcn35_hw_block_power_down,
 	.root_clock_control = dcn35_root_clock_control,
-	.set_idle_state = dcn35_set_idle_state,
-	.get_idle_state = dcn35_get_idle_state
 };
 
 static const struct hwseq_private_funcs dcn351_private_funcs = {
@@ -147,6 +146,7 @@ static const struct hwseq_private_funcs dcn351_private_funcs = {
 	//.hubp_pg_control = dcn35_hubp_pg_control,
 	.enable_power_gating_plane = dcn35_enable_power_gating_plane,
 	.dpp_root_clock_control = dcn35_dpp_root_clock_control,
+	.dpstream_root_clock_control = dcn35_dpstream_root_clock_control,
 	.program_all_writeback_pipes_in_tree = dcn30_program_all_writeback_pipes_in_tree,
 	.update_odm = dcn35_update_odm,
 	.set_hdr_multiplier = dcn10_set_hdr_multiplier,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
index f89f205e42a1..7c339e7e7117 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
@@ -377,7 +377,10 @@ struct hw_sequencer_funcs {
 	/* Idle Optimization Related */
 	bool (*apply_idle_power_optimizations)(struct dc *dc, bool enable);
 
-	bool (*does_plane_fit_in_mall)(struct dc *dc, struct dc_plane_state *plane,
+	bool (*does_plane_fit_in_mall)(struct dc *dc,
+			unsigned int pitch,
+			unsigned int height,
+			enum surface_pixel_format format,
 			struct dc_cursor_attributes *cursor_attr);
 	void (*commit_subvp_config)(struct dc *dc, struct dc_state *context);
 	void (*enable_phantom_streams)(struct dc *dc, struct dc_state *context);
@@ -424,11 +427,10 @@ struct hw_sequencer_funcs {
 		struct pg_block_update *update_state);
 	void (*root_clock_control)(struct dc *dc,
 		struct pg_block_update *update_state, bool power_on);
-	void (*set_idle_state)(const struct dc *dc, bool allow_idle);
-	uint32_t (*get_idle_state)(const struct dc *dc);
 	bool (*is_pipe_topology_transition_seamless)(struct dc *dc,
 			const struct dc_state *cur_ctx,
 			const struct dc_state *new_ctx);
+	void (*set_long_vtotal)(struct pipe_ctx **pipe_ctx, int num_pipes, uint32_t v_total_min, uint32_t v_total_max);
 };
 
 void color_space_to_black_color(
@@ -478,9 +480,10 @@ void hwss_build_fast_sequence(struct dc *dc,
 		struct dc_dmub_cmd *dc_dmub_cmd,
 		unsigned int dmub_cmd_count,
 		struct block_sequence block_sequence[],
-		int *num_steps,
+		unsigned int *num_steps,
 		struct pipe_ctx *pipe_ctx,
-		struct dc_stream_status *stream_status);
+		struct dc_stream_status *stream_status,
+		struct dc_state *context);
 
 void hwss_send_dmcub_cmd(union block_sequence_params *params);
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
index 554cfab5ab24..341219cf4144 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
@@ -120,6 +120,10 @@ struct hwseq_private_funcs {
 			struct dce_hwseq *hws,
 			unsigned int dpp_inst,
 			bool clock_on);
+	void (*dpstream_root_clock_control)(
+			struct dce_hwseq *hws,
+			unsigned int dpp_inst,
+			bool clock_on);
 	void (*dpp_pg_control)(struct dce_hwseq *hws,
 			unsigned int dpp_inst,
 			bool power_on);