Merge tag 'amd-drm-next-6.18-2025-09-26' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.18-2025-09-26:

amdgpu:
- Misc fixes
- Misc cleanups
- SMU 13.x fixes
- MES fix
- VCN 5.0.1 reset fixes
- DCN 3.2 watermark fixes
- AVI infoframe fixes
- PSR fix
- Brightness fixes
- DCN 3.1.4 fixes
- DCN 3.1+ DTM fixes
- DCN powergating fixes
- DMUB fixes
- DCN/SMU cleanup
- DCN stutter fixes
- DCN 3.5 fixes
- GAMMA_LUT fixes
- Add UserQ documentation
- GC 9.4 reset fixes
- Enforce isolation cleanups
- UserQ fixes
- DC/non-DC common modes cleanup
- DCE6-10 fixes

amdkfd:
- Fix a race in sw_fini
- Switch partition fix

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250926143918.2030854-1-alexander.deucher@amd.com

39 files changed, 720 insertions, 243 deletions

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 7012b2c692b3..8e1622bf7a42 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -233,6 +233,7 @@ static int amdgpu_dm_encoder_init(struct drm_device *dev,
 
 static int amdgpu_dm_connector_get_modes(struct drm_connector *connector);
 
+static int amdgpu_dm_atomic_setup_commit(struct drm_atomic_state *state);
 static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state);
 
 static int amdgpu_dm_atomic_check(struct drm_device *dev,
@@ -417,8 +418,7 @@ static inline bool update_planes_and_stream_adapter(struct dc *dc,
 	/*
 	 * Previous frame finished and HW is ready for optimization.
 	 */
-	if (update_type == UPDATE_TYPE_FAST)
-		dc_post_update_surfaces_to_stream(dc);
+	dc_post_update_surfaces_to_stream(dc);
 
 	return dc_update_planes_and_stream(dc,
 					   array_of_surface_update,
@@ -3637,7 +3637,7 @@ static const struct drm_mode_config_funcs amdgpu_dm_mode_funcs = {
 
 static struct drm_mode_config_helper_funcs amdgpu_dm_mode_config_helperfuncs = {
 	.atomic_commit_tail = amdgpu_dm_atomic_commit_tail,
-	.atomic_commit_setup = drm_dp_mst_atomic_setup_commit,
+	.atomic_commit_setup = amdgpu_dm_atomic_setup_commit,
 };
 
 static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
@@ -4829,6 +4829,16 @@ static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *cap
 	if (!caps->data_points)
 		return;
 
+	/*
+	 * Handle the case where brightness is below the first data point
+	 * Interpolate between (0,0) and (first_signal, first_lum)
+	 */
+	if (brightness < caps->luminance_data[0].input_signal) {
+		lum = DIV_ROUND_CLOSEST(caps->luminance_data[0].luminance * brightness,
+					caps->luminance_data[0].input_signal);
+		goto scale;
+	}
+
 	left = 0;
 	right = caps->data_points - 1;
 	while (left <= right) {
@@ -8261,6 +8271,10 @@ static void amdgpu_dm_connector_add_common_modes(struct drm_encoder *encoder,
 		{"1920x1200", 1920, 1200}
 	};
 
+	if ((connector->connector_type != DRM_MODE_CONNECTOR_eDP) &&
+	    (connector->connector_type != DRM_MODE_CONNECTOR_LVDS))
+		return;
+
 	n = ARRAY_SIZE(common_modes);
 
 	for (i = 0; i < n; i++) {
@@ -10353,6 +10367,39 @@ static void amdgpu_dm_update_hdcp(struct drm_atomic_state *state)
 	}
 }
 
+static int amdgpu_dm_atomic_setup_commit(struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state;
+	int i, ret;
+
+	ret = drm_dp_mst_atomic_setup_commit(state);
+	if (ret)
+		return ret;
+
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
+		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
+		/*
+		 * Color management settings. We also update color properties
+		 * when a modeset is needed, to ensure it gets reprogrammed.
+		 */
+		if (dm_new_crtc_state->base.active && dm_new_crtc_state->stream &&
+		    (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) {
+				drm_dbg_atomic(state->dev, "Failed to update color state\n");
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
 /**
  * amdgpu_dm_atomic_commit_tail() - AMDgpu DM's commit tail implementation.
  * @state: The atomic state to commit
@@ -11167,7 +11214,7 @@ skip_modeset:
 	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);
+		ret = amdgpu_dm_check_crtc_color_mgmt(dm_new_crtc_state, true);
 		if (ret)
 			goto fail;
 	}
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 c41c0ee4687f..009f206226f0 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -1054,6 +1054,8 @@ 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_check_crtc_color_mgmt(struct dm_crtc_state *crtc,
+				    bool check_only);
 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);
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 c7387af725d6..a4ac6d442278 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
@@ -566,12 +566,11 @@ static int __set_output_tf(struct dc_transfer_func *func,
 	return res ? 0 : -ENOMEM;
 }
 
-static int amdgpu_dm_set_atomic_regamma(struct dc_stream_state *stream,
+static int amdgpu_dm_set_atomic_regamma(struct dc_transfer_func *out_tf,
 					const struct drm_color_lut *regamma_lut,
 					uint32_t regamma_size, bool has_rom,
 					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) {
@@ -821,7 +820,7 @@ int amdgpu_dm_verify_lut3d_size(struct amdgpu_device *adev,
 	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, dim_size = MAX_COLOR_3DLUT_SIZE;
-	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut;
+	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend;
 
 	/* shaper LUT is only available if 3D LUT color caps */
 	exp_size = has_3dlut ? MAX_COLOR_LUT_ENTRIES : 0;
@@ -885,33 +884,33 @@ int amdgpu_dm_verify_lut_sizes(const struct drm_crtc_state *crtc_state)
 }
 
 /**
- * amdgpu_dm_update_crtc_color_mgmt: Maps DRM color management to DC stream.
+ * amdgpu_dm_check_crtc_color_mgmt: Check if DRM color props are programmable by DC.
  * @crtc: amdgpu_dm crtc state
+ * @check_only: only check color state without update dc stream
  *
- * With no plane level color management properties we're free to use any
- * of the HW blocks as long as the CRTC CTM always comes before the
- * CRTC RGM and after the CRTC DGM.
- *
- * - The CRTC RGM block will be placed in the RGM LUT block if it is non-linear.
- * - The CRTC DGM block will be placed in the DGM LUT block if it is non-linear.
- * - The CRTC CTM will be placed in the gamut remap block if it is non-linear.
+ * This function just verifies CRTC LUT sizes, if there is enough space for
+ * output transfer function and if its parameters can be calculated by AMD
+ * color module. It also adjusts some settings for programming CRTC degamma at
+ * plane stage, using plane DGM block.
  *
  * The RGM block is typically more fully featured and accurate across
  * all ASICs - DCE can't support a custom non-linear CRTC DGM.
  *
  * For supporting both plane level color management and CRTC level color
- * management at once we have to either restrict the usage of CRTC properties
- * or blend adjustments together.
+ * management at once we have to either restrict the usage of some CRTC
+ * properties or blend adjustments together.
  *
  * Returns:
- * 0 on success. Error code if setup fails.
+ * 0 on success. Error code if validation fails.
  */
-int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
+
+int amdgpu_dm_check_crtc_color_mgmt(struct dm_crtc_state *crtc,
+				    bool check_only)
 {
 	struct dc_stream_state *stream = crtc->stream;
 	struct amdgpu_device *adev = drm_to_adev(crtc->base.state->dev);
 	bool has_rom = adev->asic_type <= CHIP_RAVEN;
-	struct drm_color_ctm *ctm = NULL;
+	struct dc_transfer_func *out_tf;
 	const struct drm_color_lut *degamma_lut, *regamma_lut;
 	uint32_t degamma_size, regamma_size;
 	bool has_regamma, has_degamma;
@@ -940,6 +939,14 @@ int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
 	crtc->cm_has_degamma = false;
 	crtc->cm_is_degamma_srgb = false;
 
+	if (check_only) {
+		out_tf = kvzalloc(sizeof(*out_tf), GFP_KERNEL);
+		if (!out_tf)
+			return -ENOMEM;
+	} else {
+		out_tf = &stream->out_transfer_func;
+	}
+
 	/* Setup regamma and degamma. */
 	if (is_legacy) {
 		/*
@@ -954,8 +961,8 @@ int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
 		 * inverse color ramp in legacy userspace.
 		 */
 		crtc->cm_is_degamma_srgb = true;
-		stream->out_transfer_func.type = TF_TYPE_DISTRIBUTED_POINTS;
-		stream->out_transfer_func.tf = TRANSFER_FUNCTION_SRGB;
+		out_tf->type = TF_TYPE_DISTRIBUTED_POINTS;
+		out_tf->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
@@ -963,16 +970,12 @@ int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
 		 *
 		 * See more in mod_color_calculate_regamma_params()
 		 */
-		r = __set_legacy_tf(&stream->out_transfer_func, regamma_lut,
+		r = __set_legacy_tf(out_tf, regamma_lut,
 				    regamma_size, has_rom);
-		if (r)
-			return r;
 	} else {
 		regamma_size = has_regamma ? regamma_size : 0;
-		r = amdgpu_dm_set_atomic_regamma(stream, regamma_lut,
+		r = amdgpu_dm_set_atomic_regamma(out_tf, regamma_lut,
 						 regamma_size, has_rom, tf);
-		if (r)
-			return r;
 	}
 
 	/*
@@ -981,6 +984,43 @@ int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
 	 * have to place the CTM in the OCSC in that case.
 	 */
 	crtc->cm_has_degamma = has_degamma;
+	if (check_only)
+		kvfree(out_tf);
+
+	return r;
+}
+
+/**
+ * amdgpu_dm_update_crtc_color_mgmt: Maps DRM color management to DC stream.
+ * @crtc: amdgpu_dm crtc state
+ *
+ * With no plane level color management properties we're free to use any
+ * of the HW blocks as long as the CRTC CTM always comes before the
+ * CRTC RGM and after the CRTC DGM.
+ *
+ * - The CRTC RGM block will be placed in the RGM LUT block if it is non-linear.
+ * - The CRTC DGM block will be placed in the DGM LUT block if it is non-linear.
+ * - The CRTC CTM will be placed in the gamut remap block if it is non-linear.
+ *
+ * The RGM block is typically more fully featured and accurate across
+ * all ASICs - DCE can't support a custom non-linear CRTC DGM.
+ *
+ * For supporting both plane level color management and CRTC level color
+ * management at once we have to either restrict the usage of CRTC properties
+ * or blend adjustments together.
+ *
+ * Returns:
+ * 0 on success. Error code if setup fails.
+ */
+int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
+{
+	struct dc_stream_state *stream = crtc->stream;
+	struct drm_color_ctm *ctm = NULL;
+	int ret;
+
+	ret = amdgpu_dm_check_crtc_color_mgmt(crtc, false);
+	if (ret)
+		return ret;
 
 	/* Setup CRTC CTM. */
 	if (crtc->base.ctm) {
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 466dccb355d7..1ec9d03ad747 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
@@ -218,8 +218,10 @@ static void amdgpu_dm_idle_worker(struct work_struct *work)
 			break;
 		}
 
-		if (idle_work->enable)
+		if (idle_work->enable) {
+			dc_post_update_surfaces_to_stream(idle_work->dm->dc);
 			dc_allow_idle_optimizations(idle_work->dm->dc, true);
+		}
 		mutex_unlock(&idle_work->dm->dc_lock);
 	}
 	idle_work->dm->idle_workqueue->running = false;
@@ -273,8 +275,10 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
 			vblank_work->acrtc->dm_irq_params.allow_sr_entry);
 	}
 
-	if (dm->active_vblank_irq_count == 0)
+	if (dm->active_vblank_irq_count == 0) {
+		dc_post_update_surfaces_to_stream(dm->dc);
 		dc_allow_idle_optimizations(dm->dc, true);
+	}
 
 	mutex_unlock(&dm->dc_lock);
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index 58e084f52526..19038f336155 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -768,14 +768,18 @@ struct hdcp_workqueue *hdcp_create_workqueue(struct amdgpu_device *adev,
 		struct mod_hdcp_ddc_funcs *ddc_funcs = &config->ddc.funcs;
 
 		config->psp.handle = &adev->psp;
-		if (dc->ctx->dce_version == DCN_VERSION_3_1 ||
+		if (dc->ctx->dce_version == DCN_VERSION_3_1  ||
 		    dc->ctx->dce_version == DCN_VERSION_3_14 ||
 		    dc->ctx->dce_version == DCN_VERSION_3_15 ||
-		    dc->ctx->dce_version == DCN_VERSION_3_5 ||
+		    dc->ctx->dce_version == DCN_VERSION_3_16 ||
+		    dc->ctx->dce_version == DCN_VERSION_3_2  ||
+		    dc->ctx->dce_version == DCN_VERSION_3_21 ||
+		    dc->ctx->dce_version == DCN_VERSION_3_5  ||
 		    dc->ctx->dce_version == DCN_VERSION_3_51 ||
-		    dc->ctx->dce_version == DCN_VERSION_3_6 ||
-		    dc->ctx->dce_version == DCN_VERSION_3_16)
+		    dc->ctx->dce_version == DCN_VERSION_3_6  ||
+		    dc->ctx->dce_version == DCN_VERSION_4_01)
 			config->psp.caps.dtm_v3_supported = 1;
+
 		config->ddc.handle = dc_get_link_at_index(dc, i);
 
 		ddc_funcs->write_i2c = lp_write_i2c;
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 08f629c64df3..e027798ece03 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
@@ -1633,7 +1633,7 @@ dm_atomic_plane_attach_color_mgmt_properties(struct amdgpu_display_manager *dm,
 		drm_object_attach_property(&plane->base,
 					   dm->adev->mode_info.plane_ctm_property, 0);
 
-	if (dpp_color_caps.hw_3d_lut) {
+	if (dpp_color_caps.hw_3d_lut || dm->dc->caps.color.mpc.preblend) {
 		drm_object_attach_property(&plane->base,
 					   mode_info.plane_shaper_lut_property, 0);
 		drm_object_attach_property(&plane->base,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index 132de4071efd..8550d5e8b753 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -53,11 +53,11 @@ void dm_perf_trace_timestamp(const char *func_name, unsigned int line, struct dc
 				    func_name, line);
 }
 
-void dm_trace_smu_msg(uint32_t msg_id, uint32_t param_in, struct dc_context *ctx)
+void dm_trace_smu_enter(uint32_t msg_id, uint32_t param_in, unsigned int delay, struct dc_context *ctx)
 {
 }
 
-void dm_trace_smu_delay(uint32_t delay, struct dc_context *ctx)
+void dm_trace_smu_exit(bool success, uint32_t response, struct dc_context *ctx)
 {
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
index dbd6ef1b60a0..6131ede2db7a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
@@ -463,6 +463,9 @@ void dce_clk_mgr_construct(
 		clk_mgr->max_clks_state = DM_PP_CLOCKS_STATE_NOMINAL;
 	clk_mgr->cur_min_clks_state = DM_PP_CLOCKS_STATE_INVALID;
 
+	base->clks.max_supported_dispclk_khz =
+		clk_mgr->max_clks_by_state[DM_PP_CLOCKS_STATE_PERFORMANCE].display_clk_khz;
+
 	dce_clock_read_integrated_info(clk_mgr);
 	dce_clock_read_ss_info(clk_mgr);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
index a39641a0ff09..69dd80d9f738 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
@@ -147,6 +147,8 @@ void dce60_clk_mgr_construct(
 		struct dc_context *ctx,
 		struct clk_mgr_internal *clk_mgr)
 {
+	struct clk_mgr *base = &clk_mgr->base;
+
 	dce_clk_mgr_construct(ctx, clk_mgr);
 
 	memcpy(clk_mgr->max_clks_by_state,
@@ -157,5 +159,8 @@ void dce60_clk_mgr_construct(
 	clk_mgr->clk_mgr_shift = &disp_clk_shift;
 	clk_mgr->clk_mgr_mask = &disp_clk_mask;
 	clk_mgr->base.funcs = &dce60_funcs;
+
+	base->clks.max_supported_dispclk_khz =
+		clk_mgr->max_clks_by_state[DM_PP_CLOCKS_STATE_PERFORMANCE].display_clk_khz;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c
index 3253115a153d..827bc2431d5d 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c
@@ -69,7 +69,7 @@ static uint32_t dcn30_smu_wait_for_response(struct clk_mgr_internal *clk_mgr, un
 
 	/* handle DALSMC_Result_CmdRejectedBusy? */
 
-	TRACE_SMU_DELAY(delay_us * (initial_max_retries - max_retries), clk_mgr->base.ctx);
+	TRACE_SMU_MSG_DELAY(0, 0, delay_us * (initial_max_retries - max_retries), clk_mgr->base.ctx);
 
 	return reg;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
index 790bbd8235b1..9e63fa72101c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
@@ -77,6 +77,7 @@ static const struct IP_BASE CLK_BASE = { { { { 0x00016C00, 0x02401800, 0, 0, 0,
 #undef DC_LOGGER
 #define DC_LOGGER \
 	clk_mgr->base.base.ctx->logger
+
 #define regCLK1_CLK_PLL_REQ			0x0237
 #define regCLK1_CLK_PLL_REQ_BASE_IDX		0
 
@@ -87,8 +88,70 @@ static const struct IP_BASE CLK_BASE = { { { { 0x00016C00, 0x02401800, 0, 0, 0,
 #define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK	0x0000F000L
 #define CLK1_CLK_PLL_REQ__FbMult_frac_MASK	0xFFFF0000L
 
+#define regCLK1_CLK0_DFS_CNTL				0x0269
+#define regCLK1_CLK0_DFS_CNTL_BASE_IDX		0
+#define regCLK1_CLK1_DFS_CNTL				0x026c
+#define regCLK1_CLK1_DFS_CNTL_BASE_IDX		0
+#define regCLK1_CLK2_DFS_CNTL				0x026f
+#define regCLK1_CLK2_DFS_CNTL_BASE_IDX		0
+#define regCLK1_CLK3_DFS_CNTL				0x0272
+#define regCLK1_CLK3_DFS_CNTL_BASE_IDX		0
+#define regCLK1_CLK4_DFS_CNTL				0x0275
+#define regCLK1_CLK4_DFS_CNTL_BASE_IDX		0
+#define regCLK1_CLK5_DFS_CNTL				0x0278
+#define regCLK1_CLK5_DFS_CNTL_BASE_IDX		0
+
+#define regCLK1_CLK0_CURRENT_CNT			0x02fb
+#define regCLK1_CLK0_CURRENT_CNT_BASE_IDX	0
+#define regCLK1_CLK1_CURRENT_CNT			0x02fc
+#define regCLK1_CLK1_CURRENT_CNT_BASE_IDX	0
+#define regCLK1_CLK2_CURRENT_CNT			0x02fd
+#define regCLK1_CLK2_CURRENT_CNT_BASE_IDX	0
+#define regCLK1_CLK3_CURRENT_CNT			0x02fe
+#define regCLK1_CLK3_CURRENT_CNT_BASE_IDX	0
+#define regCLK1_CLK4_CURRENT_CNT			0x02ff
+#define regCLK1_CLK4_CURRENT_CNT_BASE_IDX	0
+#define regCLK1_CLK5_CURRENT_CNT			0x0300
+#define regCLK1_CLK5_CURRENT_CNT_BASE_IDX	0
+
+#define regCLK1_CLK0_BYPASS_CNTL			0x028a
+#define regCLK1_CLK0_BYPASS_CNTL_BASE_IDX	0
+#define regCLK1_CLK1_BYPASS_CNTL			0x0293
+#define regCLK1_CLK1_BYPASS_CNTL_BASE_IDX	0
 #define regCLK1_CLK2_BYPASS_CNTL			0x029c
 #define regCLK1_CLK2_BYPASS_CNTL_BASE_IDX	0
+#define regCLK1_CLK3_BYPASS_CNTL			0x02a5
+#define regCLK1_CLK3_BYPASS_CNTL_BASE_IDX	0
+#define regCLK1_CLK4_BYPASS_CNTL			0x02ae
+#define regCLK1_CLK4_BYPASS_CNTL_BASE_IDX	0
+#define regCLK1_CLK5_BYPASS_CNTL			0x02b7
+#define regCLK1_CLK5_BYPASS_CNTL_BASE_IDX	0
+
+#define regCLK1_CLK0_DS_CNTL				0x0283
+#define regCLK1_CLK0_DS_CNTL_BASE_IDX		0
+#define regCLK1_CLK1_DS_CNTL				0x028c
+#define regCLK1_CLK1_DS_CNTL_BASE_IDX		0
+#define regCLK1_CLK2_DS_CNTL				0x0295
+#define regCLK1_CLK2_DS_CNTL_BASE_IDX		0
+#define regCLK1_CLK3_DS_CNTL				0x029e
+#define regCLK1_CLK3_DS_CNTL_BASE_IDX		0
+#define regCLK1_CLK4_DS_CNTL				0x02a7
+#define regCLK1_CLK4_DS_CNTL_BASE_IDX		0
+#define regCLK1_CLK5_DS_CNTL				0x02b0
+#define regCLK1_CLK5_DS_CNTL_BASE_IDX		0
+
+#define regCLK1_CLK0_ALLOW_DS				0x0284
+#define regCLK1_CLK0_ALLOW_DS_BASE_IDX		0
+#define regCLK1_CLK1_ALLOW_DS				0x028d
+#define regCLK1_CLK1_ALLOW_DS_BASE_IDX		0
+#define regCLK1_CLK2_ALLOW_DS				0x0296
+#define regCLK1_CLK2_ALLOW_DS_BASE_IDX		0
+#define regCLK1_CLK3_ALLOW_DS				0x029f
+#define regCLK1_CLK3_ALLOW_DS_BASE_IDX		0
+#define regCLK1_CLK4_ALLOW_DS				0x02a8
+#define regCLK1_CLK4_ALLOW_DS_BASE_IDX		0
+#define regCLK1_CLK5_ALLOW_DS				0x02b1
+#define regCLK1_CLK5_ALLOW_DS_BASE_IDX		0
 
 #define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL__SHIFT	0x0
 #define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV__SHIFT	0x10
@@ -185,6 +248,8 @@ void dcn314_init_clocks(struct clk_mgr *clk_mgr)
 {
 	struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
 	uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz;
+	struct clk_mgr_dcn314 *clk_mgr_dcn314 = TO_CLK_MGR_DCN314(clk_mgr_int);
+	struct clk_log_info log_info = {0};
 
 	memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
 	// Assumption is that boot state always supports pstate
@@ -200,6 +265,9 @@ void dcn314_init_clocks(struct clk_mgr *clk_mgr)
 			dce_adjust_dp_ref_freq_for_ss(clk_mgr_int, clk_mgr->dprefclk_khz);
 	else
 		clk_mgr->dp_dto_source_clock_in_khz = clk_mgr->dprefclk_khz;
+
+	dcn314_dump_clk_registers(&clk_mgr->boot_snapshot, &clk_mgr_dcn314->base.base, &log_info);
+	clk_mgr->clks.dispclk_khz =  clk_mgr->boot_snapshot.dispclk * 1000;
 }
 
 void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
@@ -218,6 +286,8 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 	if (dc->work_arounds.skip_clock_update)
 		return;
 
+	display_count = dcn314_get_active_display_cnt_wa(dc, context);
+
 	/*
 	 * if it is safe to lower, but we are already in the lower state, we don't have to do anything
 	 * also if safe to lower is false, we just go in the higher state
@@ -236,7 +306,6 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 		}
 		/* check that we're not already in lower */
 		if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_LOW_POWER) {
-			display_count = dcn314_get_active_display_cnt_wa(dc, context);
 			/* if we can go lower, go lower */
 			if (display_count == 0) {
 				union display_idle_optimization_u idle_info = { 0 };
@@ -293,11 +362,19 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 		update_dppclk = true;
 	}
 
-	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz) &&
+	    (new_clocks->dispclk_khz > 0 || (safe_to_lower && display_count == 0))) {
+		int requested_dispclk_khz = new_clocks->dispclk_khz;
+
 		dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true);
 
+		/* Clamp the requested clock to PMFW based on their limit. */
+		if (dc->debug.min_disp_clk_khz > 0 && requested_dispclk_khz < dc->debug.min_disp_clk_khz)
+			requested_dispclk_khz = dc->debug.min_disp_clk_khz;
+
+		dcn314_smu_set_dispclk(clk_mgr, requested_dispclk_khz);
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
-		dcn314_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
+
 		dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false);
 
 		update_dispclk = true;
@@ -385,10 +462,65 @@ bool dcn314_are_clock_states_equal(struct dc_clocks *a,
 	return true;
 }
 
-static void dcn314_dump_clk_registers(struct clk_state_registers_and_bypass *regs_and_bypass,
+
+static void dcn314_dump_clk_registers_internal(struct dcn35_clk_internal *internal, struct clk_mgr *clk_mgr_base)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+
+	// read dtbclk
+	internal->CLK1_CLK4_CURRENT_CNT = REG_READ(CLK1_CLK4_CURRENT_CNT);
+	internal->CLK1_CLK4_BYPASS_CNTL = REG_READ(CLK1_CLK4_BYPASS_CNTL);
+
+	// read dcfclk
+	internal->CLK1_CLK3_CURRENT_CNT = REG_READ(CLK1_CLK3_CURRENT_CNT);
+	internal->CLK1_CLK3_BYPASS_CNTL = REG_READ(CLK1_CLK3_BYPASS_CNTL);
+
+	// read dcf deep sleep divider
+	internal->CLK1_CLK3_DS_CNTL = REG_READ(CLK1_CLK3_DS_CNTL);
+	internal->CLK1_CLK3_ALLOW_DS = REG_READ(CLK1_CLK3_ALLOW_DS);
+
+	// read dppclk
+	internal->CLK1_CLK1_CURRENT_CNT = REG_READ(CLK1_CLK1_CURRENT_CNT);
+	internal->CLK1_CLK1_BYPASS_CNTL = REG_READ(CLK1_CLK1_BYPASS_CNTL);
+
+	// read dprefclk
+	internal->CLK1_CLK2_CURRENT_CNT = REG_READ(CLK1_CLK2_CURRENT_CNT);
+	internal->CLK1_CLK2_BYPASS_CNTL = REG_READ(CLK1_CLK2_BYPASS_CNTL);
+
+	// read dispclk
+	internal->CLK1_CLK0_CURRENT_CNT = REG_READ(CLK1_CLK0_CURRENT_CNT);
+	internal->CLK1_CLK0_BYPASS_CNTL = REG_READ(CLK1_CLK0_BYPASS_CNTL);
+}
+
+void dcn314_dump_clk_registers(struct clk_state_registers_and_bypass *regs_and_bypass,
 		struct clk_mgr *clk_mgr_base, struct clk_log_info *log_info)
 {
-	return;
+
+	struct dcn35_clk_internal internal = {0};
+
+	dcn314_dump_clk_registers_internal(&internal, clk_mgr_base);
+
+	regs_and_bypass->dcfclk = internal.CLK1_CLK3_CURRENT_CNT / 10;
+	regs_and_bypass->dcf_deep_sleep_divider = internal.CLK1_CLK3_DS_CNTL / 10;
+	regs_and_bypass->dcf_deep_sleep_allow = internal.CLK1_CLK3_ALLOW_DS;
+	regs_and_bypass->dprefclk = internal.CLK1_CLK2_CURRENT_CNT / 10;
+	regs_and_bypass->dispclk = internal.CLK1_CLK0_CURRENT_CNT / 10;
+	regs_and_bypass->dppclk = internal.CLK1_CLK1_CURRENT_CNT / 10;
+	regs_and_bypass->dtbclk = internal.CLK1_CLK4_CURRENT_CNT / 10;
+
+	regs_and_bypass->dppclk_bypass = internal.CLK1_CLK1_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dppclk_bypass < 0 || regs_and_bypass->dppclk_bypass > 4)
+		regs_and_bypass->dppclk_bypass = 0;
+	regs_and_bypass->dcfclk_bypass = internal.CLK1_CLK3_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dcfclk_bypass < 0 || regs_and_bypass->dcfclk_bypass > 4)
+		regs_and_bypass->dcfclk_bypass = 0;
+	regs_and_bypass->dispclk_bypass = internal.CLK1_CLK0_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dispclk_bypass < 0 || regs_and_bypass->dispclk_bypass > 4)
+		regs_and_bypass->dispclk_bypass = 0;
+	regs_and_bypass->dprefclk_bypass = internal.CLK1_CLK2_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dprefclk_bypass < 0 || regs_and_bypass->dprefclk_bypass > 4)
+		regs_and_bypass->dprefclk_bypass = 0;
+
 }
 
 static struct clk_bw_params dcn314_bw_params = {
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
index 002c28e80720..0577eb527bc3 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
@@ -65,4 +65,9 @@ void dcn314_clk_mgr_construct(struct dc_context *ctx,
 
 void dcn314_clk_mgr_destroy(struct clk_mgr_internal *clk_mgr_int);
 
+
+void dcn314_dump_clk_registers(struct clk_state_registers_and_bypass *regs_and_bypass,
+		struct clk_mgr *clk_mgr_base, struct clk_log_info *log_info);
+
+
 #endif //__DCN314_CLK_MGR_H__
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr_smu_msg.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr_smu_msg.c
index cf2d35363e8b..5d80fdf63ffc 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr_smu_msg.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr_smu_msg.c
@@ -63,7 +63,8 @@ static uint32_t dcn32_smu_wait_for_response(struct clk_mgr_internal *clk_mgr, un
 			udelay(delay_us);
 	} while (max_retries--);
 
-	TRACE_SMU_DELAY(delay_us * (initial_max_retries - max_retries), clk_mgr->base.ctx);
+	TRACE_SMU_MSG_DELAY(0, 0, delay_us * (initial_max_retries - max_retries), clk_mgr->base.ctx);
+
 
 	return reg;
 }
@@ -120,7 +121,7 @@ static uint32_t dcn32_smu_wait_for_response_delay(struct clk_mgr_internal *clk_m
 		*total_delay_us += delay_us;
 	} while (max_retries--);
 
-	TRACE_SMU_DELAY(*total_delay_us, clk_mgr->base.ctx);
+	TRACE_SMU_MSG_DELAY(0, 0, *total_delay_us, clk_mgr->base.ctx);
 
 	return reg;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 86edf11b8c5a..b11383fba35f 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -587,9 +587,118 @@ bool dcn35_are_clock_states_equal(struct dc_clocks *a,
 	return true;
 }
 
-static void dcn35_dump_clk_registers(struct clk_state_registers_and_bypass *regs_and_bypass,
+static void dcn35_save_clk_registers_internal(struct dcn35_clk_internal *internal, struct clk_mgr *clk_mgr_base)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+
+	// read dtbclk
+	internal->CLK1_CLK4_CURRENT_CNT = REG_READ(CLK1_CLK4_CURRENT_CNT);
+	internal->CLK1_CLK4_BYPASS_CNTL = REG_READ(CLK1_CLK4_BYPASS_CNTL);
+
+	// read dcfclk
+	internal->CLK1_CLK3_CURRENT_CNT = REG_READ(CLK1_CLK3_CURRENT_CNT);
+	internal->CLK1_CLK3_BYPASS_CNTL = REG_READ(CLK1_CLK3_BYPASS_CNTL);
+
+	// read dcf deep sleep divider
+	internal->CLK1_CLK3_DS_CNTL = REG_READ(CLK1_CLK3_DS_CNTL);
+	internal->CLK1_CLK3_ALLOW_DS = REG_READ(CLK1_CLK3_ALLOW_DS);
+
+	// read dppclk
+	internal->CLK1_CLK1_CURRENT_CNT = REG_READ(CLK1_CLK1_CURRENT_CNT);
+	internal->CLK1_CLK1_BYPASS_CNTL = REG_READ(CLK1_CLK1_BYPASS_CNTL);
+
+	// read dprefclk
+	internal->CLK1_CLK2_CURRENT_CNT = REG_READ(CLK1_CLK2_CURRENT_CNT);
+	internal->CLK1_CLK2_BYPASS_CNTL = REG_READ(CLK1_CLK2_BYPASS_CNTL);
+
+	// read dispclk
+	internal->CLK1_CLK0_CURRENT_CNT = REG_READ(CLK1_CLK0_CURRENT_CNT);
+	internal->CLK1_CLK0_BYPASS_CNTL = REG_READ(CLK1_CLK0_BYPASS_CNTL);
+}
+
+static void dcn35_save_clk_registers(struct clk_state_registers_and_bypass *regs_and_bypass,
 		struct clk_mgr_dcn35 *clk_mgr)
 {
+	struct dcn35_clk_internal internal = {0};
+	char *bypass_clks[5] = {"0x0 DFS", "0x1 REFCLK", "0x2 ERROR", "0x3 400 FCH", "0x4 600 FCH"};
+
+	dcn35_save_clk_registers_internal(&internal, &clk_mgr->base.base);
+
+	regs_and_bypass->dcfclk = internal.CLK1_CLK3_CURRENT_CNT / 10;
+	regs_and_bypass->dcf_deep_sleep_divider = internal.CLK1_CLK3_DS_CNTL / 10;
+	regs_and_bypass->dcf_deep_sleep_allow = internal.CLK1_CLK3_ALLOW_DS;
+	regs_and_bypass->dprefclk = internal.CLK1_CLK2_CURRENT_CNT / 10;
+	regs_and_bypass->dispclk = internal.CLK1_CLK0_CURRENT_CNT / 10;
+	regs_and_bypass->dppclk = internal.CLK1_CLK1_CURRENT_CNT / 10;
+	regs_and_bypass->dtbclk = internal.CLK1_CLK4_CURRENT_CNT / 10;
+
+	regs_and_bypass->dppclk_bypass = internal.CLK1_CLK1_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dppclk_bypass < 0 || regs_and_bypass->dppclk_bypass > 4)
+		regs_and_bypass->dppclk_bypass = 0;
+	regs_and_bypass->dcfclk_bypass = internal.CLK1_CLK3_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dcfclk_bypass < 0 || regs_and_bypass->dcfclk_bypass > 4)
+		regs_and_bypass->dcfclk_bypass = 0;
+	regs_and_bypass->dispclk_bypass = internal.CLK1_CLK0_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dispclk_bypass < 0 || regs_and_bypass->dispclk_bypass > 4)
+		regs_and_bypass->dispclk_bypass = 0;
+	regs_and_bypass->dprefclk_bypass = internal.CLK1_CLK2_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dprefclk_bypass < 0 || regs_and_bypass->dprefclk_bypass > 4)
+		regs_and_bypass->dprefclk_bypass = 0;
+
+	if (clk_mgr->base.base.ctx->dc->debug.pstate_enabled) {
+		DC_LOG_SMU("clk_type,clk_value,deepsleep_cntl,deepsleep_allow,bypass\n");
+
+		DC_LOG_SMU("dcfclk,%d,%d,%d,%s\n",
+				   regs_and_bypass->dcfclk,
+				   regs_and_bypass->dcf_deep_sleep_divider,
+				   regs_and_bypass->dcf_deep_sleep_allow,
+				   bypass_clks[(int) regs_and_bypass->dcfclk_bypass]);
+
+		DC_LOG_SMU("dprefclk,%d,N/A,N/A,%s\n",
+			regs_and_bypass->dprefclk,
+			bypass_clks[(int) regs_and_bypass->dprefclk_bypass]);
+
+		DC_LOG_SMU("dispclk,%d,N/A,N/A,%s\n",
+			regs_and_bypass->dispclk,
+			bypass_clks[(int) regs_and_bypass->dispclk_bypass]);
+
+		// REGISTER VALUES
+		DC_LOG_SMU("reg_name,value,clk_type");
+
+		DC_LOG_SMU("CLK1_CLK3_CURRENT_CNT,%d,dcfclk",
+				internal.CLK1_CLK3_CURRENT_CNT);
+
+		DC_LOG_SMU("CLK1_CLK4_CURRENT_CNT,%d,dtbclk",
+					internal.CLK1_CLK4_CURRENT_CNT);
+
+		DC_LOG_SMU("CLK1_CLK3_DS_CNTL,%d,dcf_deep_sleep_divider",
+					internal.CLK1_CLK3_DS_CNTL);
+
+		DC_LOG_SMU("CLK1_CLK3_ALLOW_DS,%d,dcf_deep_sleep_allow",
+					internal.CLK1_CLK3_ALLOW_DS);
+
+		DC_LOG_SMU("CLK1_CLK2_CURRENT_CNT,%d,dprefclk",
+					internal.CLK1_CLK2_CURRENT_CNT);
+
+		DC_LOG_SMU("CLK1_CLK0_CURRENT_CNT,%d,dispclk",
+					internal.CLK1_CLK0_CURRENT_CNT);
+
+		DC_LOG_SMU("CLK1_CLK1_CURRENT_CNT,%d,dppclk",
+					internal.CLK1_CLK1_CURRENT_CNT);
+
+		DC_LOG_SMU("CLK1_CLK3_BYPASS_CNTL,%d,dcfclk_bypass",
+					internal.CLK1_CLK3_BYPASS_CNTL);
+
+		DC_LOG_SMU("CLK1_CLK2_BYPASS_CNTL,%d,dprefclk_bypass",
+					internal.CLK1_CLK2_BYPASS_CNTL);
+
+		DC_LOG_SMU("CLK1_CLK0_BYPASS_CNTL,%d,dispclk_bypass",
+					internal.CLK1_CLK0_BYPASS_CNTL);
+
+		DC_LOG_SMU("CLK1_CLK1_BYPASS_CNTL,%d,dppclk_bypass",
+					internal.CLK1_CLK1_BYPASS_CNTL);
+
+	}
 }
 
 static bool dcn35_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base)
@@ -623,6 +732,7 @@ static void init_clk_states(struct clk_mgr *clk_mgr)
 void dcn35_init_clocks(struct clk_mgr *clk_mgr)
 {
 	struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
+	struct clk_mgr_dcn35 *clk_mgr_dcn35 = TO_CLK_MGR_DCN35(clk_mgr_int);
 
 	init_clk_states(clk_mgr);
 
@@ -633,6 +743,13 @@ void dcn35_init_clocks(struct clk_mgr *clk_mgr)
 	else
 		clk_mgr->dp_dto_source_clock_in_khz = clk_mgr->dprefclk_khz;
 
+	dcn35_save_clk_registers(&clk_mgr->boot_snapshot, clk_mgr_dcn35);
+
+	clk_mgr->clks.ref_dtbclk_khz =  clk_mgr->boot_snapshot.dtbclk * 10;
+	if (clk_mgr->boot_snapshot.dtbclk > 59000) {
+		/*dtbclk enabled based on */
+		clk_mgr->clks.dtbclk_en = true;
+	}
 }
 static struct clk_bw_params dcn35_bw_params = {
 	.vram_type = Ddr4MemType,
@@ -1323,7 +1440,7 @@ void dcn35_clk_mgr_construct(
 		dcn35_bw_params.wm_table = ddr5_wm_table;
 	}
 	/* Saved clocks configured at boot for debug purposes */
-	dcn35_dump_clk_registers(&clk_mgr->base.base.boot_snapshot, clk_mgr);
+	dcn35_save_clk_registers(&clk_mgr->base.base.boot_snapshot, clk_mgr);
 
 	clk_mgr->base.base.dprefclk_khz = dcn35_smu_get_dprefclk(&clk_mgr->base);
 	clk_mgr->base.base.clks.ref_dtbclk_khz = 600000;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c
index 47461f249e83..306016c1f109 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c
@@ -162,7 +162,7 @@ static void dcn401_init_single_clock(struct clk_mgr_internal *clk_mgr, PPCLK_e c
 	unsigned int i;
 	char *entry_i = (char *)entry_0;
 
-	uint32_t ret = dcn30_smu_get_dpm_freq_by_index(clk_mgr, clk, 0xFF);
+	uint32_t ret = dcn401_smu_get_dpm_freq_by_index(clk_mgr, clk, 0xFF);
 
 	if (ret & (1 << 31))
 		/* fine-grained, only min and max */
@@ -174,7 +174,7 @@ static void dcn401_init_single_clock(struct clk_mgr_internal *clk_mgr, PPCLK_e c
 
 	/* if the initial message failed, num_levels will be 0 */
 	for (i = 0; i < *num_levels && i < ARRAY_SIZE(clk_mgr->base.bw_params->clk_table.entries); i++) {
-		*((unsigned int *)entry_i) = (dcn30_smu_get_dpm_freq_by_index(clk_mgr, clk, i) & 0xFFFF);
+		*((unsigned int *)entry_i) = (dcn401_smu_get_dpm_freq_by_index(clk_mgr, clk, i) & 0xFFFF);
 		entry_i += sizeof(clk_mgr->base.bw_params->clk_table.entries[0]);
 	}
 }
@@ -231,20 +231,20 @@ void dcn401_init_clocks(struct clk_mgr *clk_mgr_base)
 	clk_mgr->smu_present = false;
 	clk_mgr->dpm_present = false;
 
-	if (!clk_mgr_base->force_smu_not_present && dcn30_smu_get_smu_version(clk_mgr, &clk_mgr->smu_ver))
+	if (!clk_mgr_base->force_smu_not_present && dcn401_smu_get_smu_version(clk_mgr, &clk_mgr->smu_ver))
 		clk_mgr->smu_present = true;
 
 	if (!clk_mgr->smu_present)
 		return;
 
-	dcn30_smu_check_driver_if_version(clk_mgr);
-	dcn30_smu_check_msg_header_version(clk_mgr);
+	dcn401_smu_check_driver_if_version(clk_mgr);
+	dcn401_smu_check_msg_header_version(clk_mgr);
 
 	/* DCFCLK */
 	dcn401_init_single_clock(clk_mgr, PPCLK_DCFCLK,
 			&clk_mgr_base->bw_params->clk_table.entries[0].dcfclk_mhz,
 			&num_entries_per_clk->num_dcfclk_levels);
-	clk_mgr_base->bw_params->dc_mode_limit.dcfclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DCFCLK);
+	clk_mgr_base->bw_params->dc_mode_limit.dcfclk_mhz = dcn401_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DCFCLK);
 	if (num_entries_per_clk->num_dcfclk_levels && clk_mgr_base->bw_params->dc_mode_limit.dcfclk_mhz ==
 			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_dcfclk_levels - 1].dcfclk_mhz)
 		clk_mgr_base->bw_params->dc_mode_limit.dcfclk_mhz = 0;
@@ -253,7 +253,7 @@ void dcn401_init_clocks(struct clk_mgr *clk_mgr_base)
 	dcn401_init_single_clock(clk_mgr, PPCLK_SOCCLK,
 					&clk_mgr_base->bw_params->clk_table.entries[0].socclk_mhz,
 					&num_entries_per_clk->num_socclk_levels);
-	clk_mgr_base->bw_params->dc_mode_limit.socclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_SOCCLK);
+	clk_mgr_base->bw_params->dc_mode_limit.socclk_mhz = dcn401_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_SOCCLK);
 	if (num_entries_per_clk->num_socclk_levels && clk_mgr_base->bw_params->dc_mode_limit.socclk_mhz ==
 			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_socclk_levels - 1].socclk_mhz)
 		clk_mgr_base->bw_params->dc_mode_limit.socclk_mhz = 0;
@@ -263,7 +263,7 @@ void dcn401_init_clocks(struct clk_mgr *clk_mgr_base)
 		dcn401_init_single_clock(clk_mgr, PPCLK_DTBCLK,
 				&clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz,
 				&num_entries_per_clk->num_dtbclk_levels);
-		clk_mgr_base->bw_params->dc_mode_limit.dtbclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DTBCLK);
+		clk_mgr_base->bw_params->dc_mode_limit.dtbclk_mhz = dcn401_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DTBCLK);
 		if (num_entries_per_clk->num_dtbclk_levels && clk_mgr_base->bw_params->dc_mode_limit.dtbclk_mhz ==
 				clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_dtbclk_levels - 1].dtbclk_mhz)
 			clk_mgr_base->bw_params->dc_mode_limit.dtbclk_mhz = 0;
@@ -273,7 +273,7 @@ void dcn401_init_clocks(struct clk_mgr *clk_mgr_base)
 	dcn401_init_single_clock(clk_mgr, PPCLK_DISPCLK,
 			&clk_mgr_base->bw_params->clk_table.entries[0].dispclk_mhz,
 			&num_entries_per_clk->num_dispclk_levels);
-	clk_mgr_base->bw_params->dc_mode_limit.dispclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DISPCLK);
+	clk_mgr_base->bw_params->dc_mode_limit.dispclk_mhz = dcn401_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DISPCLK);
 	if (num_entries_per_clk->num_dispclk_levels && clk_mgr_base->bw_params->dc_mode_limit.dispclk_mhz ==
 			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_dispclk_levels - 1].dispclk_mhz)
 		clk_mgr_base->bw_params->dc_mode_limit.dispclk_mhz = 0;
@@ -1318,8 +1318,8 @@ static void dcn401_notify_wm_ranges(struct clk_mgr *clk_mgr_base)
 			table->Watermarks.WatermarkRow[i].WmSetting = i;
 			table->Watermarks.WatermarkRow[i].Flags = clk_mgr->base.bw_params->wm_table.nv_entries[i].pmfw_breakdown.wm_type;
 		}
-	dcn30_smu_set_dram_addr_high(clk_mgr, clk_mgr->wm_range_table_addr >> 32);
-	dcn30_smu_set_dram_addr_low(clk_mgr, clk_mgr->wm_range_table_addr & 0xFFFFFFFF);
+	dcn401_smu_set_dram_addr_high(clk_mgr, clk_mgr->wm_range_table_addr >> 32);
+	dcn401_smu_set_dram_addr_low(clk_mgr, clk_mgr->wm_range_table_addr & 0xFFFFFFFF);
 	dcn401_smu_transfer_wm_table_dram_2_smu(clk_mgr);
 }
 
@@ -1390,7 +1390,7 @@ static void dcn401_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base)
 				clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_memclk_levels - 1].memclk_mhz;
 	}
 
-	clk_mgr_base->bw_params->dc_mode_limit.memclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_UCLK);
+	clk_mgr_base->bw_params->dc_mode_limit.memclk_mhz = dcn401_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_UCLK);
 	if (num_entries_per_clk->num_memclk_levels && clk_mgr_base->bw_params->dc_mode_limit.memclk_mhz ==
 			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_memclk_levels - 1].memclk_mhz)
 		clk_mgr_base->bw_params->dc_mode_limit.memclk_mhz = 0;
@@ -1399,7 +1399,7 @@ static void dcn401_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base)
 	dcn401_init_single_clock(clk_mgr, PPCLK_FCLK,
 			&clk_mgr_base->bw_params->clk_table.entries[0].fclk_mhz,
 			&num_entries_per_clk->num_fclk_levels);
-	clk_mgr_base->bw_params->dc_mode_limit.fclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_FCLK);
+	clk_mgr_base->bw_params->dc_mode_limit.fclk_mhz = dcn401_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_FCLK);
 	if (num_entries_per_clk->num_fclk_levels && clk_mgr_base->bw_params->dc_mode_limit.fclk_mhz ==
 			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_fclk_levels - 1].fclk_mhz)
 		clk_mgr_base->bw_params->dc_mode_limit.fclk_mhz = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.c
index 21c35528f61f..3a263840893e 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.c
@@ -57,6 +57,8 @@ static bool dcn401_smu_send_msg_with_param(struct clk_mgr_internal *clk_mgr, uin
 	/* Wait for response register to be ready */
 	dcn401_smu_wait_for_response(clk_mgr, 10, 200000);
 
+	TRACE_SMU_MSG_ENTER(msg_id, param_in, clk_mgr->base.ctx);
+
 	/* Clear response register */
 	REG_WRITE(DAL_RESP_REG, 0);
 
@@ -71,9 +73,11 @@ static bool dcn401_smu_send_msg_with_param(struct clk_mgr_internal *clk_mgr, uin
 		if (param_out)
 			*param_out = REG_READ(DAL_ARG_REG);
 
+		TRACE_SMU_MSG_EXIT(true, param_out ? *param_out : 0, clk_mgr->base.ctx);
 		return true;
 	}
 
+	TRACE_SMU_MSG_EXIT(false, 0, clk_mgr->base.ctx);
 	return false;
 }
 
@@ -102,8 +106,6 @@ static uint32_t dcn401_smu_wait_for_response_delay(struct clk_mgr_internal *clk_
 		*total_delay_us += delay_us;
 	} while (max_retries--);
 
-	TRACE_SMU_DELAY(*total_delay_us, clk_mgr->base.ctx);
-
 	return reg;
 }
 
@@ -115,6 +117,8 @@ static bool dcn401_smu_send_msg_with_param_delay(struct clk_mgr_internal *clk_mg
 	/* Wait for response register to be ready */
 	dcn401_smu_wait_for_response_delay(clk_mgr, 10, 200000, &delay1_us);
 
+	TRACE_SMU_MSG_ENTER(msg_id, param_in, clk_mgr->base.ctx);
+
 	/* Clear response register */
 	REG_WRITE(DAL_RESP_REG, 0);
 
@@ -124,18 +128,71 @@ static bool dcn401_smu_send_msg_with_param_delay(struct clk_mgr_internal *clk_mg
 	/* Trigger the message transaction by writing the message ID */
 	REG_WRITE(DAL_MSG_REG, msg_id);
 
-	TRACE_SMU_MSG(msg_id, param_in, clk_mgr->base.ctx);
-
 	/* Wait for response */
 	if (dcn401_smu_wait_for_response_delay(clk_mgr, 10, 200000, &delay2_us) == DALSMC_Result_OK) {
 		if (param_out)
 			*param_out = REG_READ(DAL_ARG_REG);
 
 		*total_delay_us = delay1_us + delay2_us;
+		TRACE_SMU_MSG_EXIT(true, param_out ? *param_out : 0, clk_mgr->base.ctx);
 		return true;
 	}
 
 	*total_delay_us = delay1_us + 2000000;
+	TRACE_SMU_MSG_EXIT(false, 0, clk_mgr->base.ctx);
+	return false;
+}
+
+bool dcn401_smu_get_smu_version(struct clk_mgr_internal *clk_mgr, unsigned int *version)
+{
+	smu_print("SMU Get SMU version\n");
+
+	if (dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_GetSmuVersion, 0, version)) {
+
+		smu_print("SMU version: %d\n", *version);
+
+		return true;
+	}
+
+	return false;
+}
+
+/* Message output should match SMU11_DRIVER_IF_VERSION in smu11_driver_if.h */
+bool dcn401_smu_check_driver_if_version(struct clk_mgr_internal *clk_mgr)
+{
+	uint32_t response = 0;
+
+	smu_print("SMU Check driver if version\n");
+
+	if (dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_GetDriverIfVersion, 0, &response)) {
+
+		smu_print("SMU driver if version: %d\n", response);
+
+		if (response == SMU14_DRIVER_IF_VERSION)
+			return true;
+	}
+
+	return false;
+}
+
+/* Message output should match DALSMC_VERSION in dalsmc.h */
+bool dcn401_smu_check_msg_header_version(struct clk_mgr_internal *clk_mgr)
+{
+	uint32_t response = 0;
+
+	smu_print("SMU Check msg header version\n");
+
+	if (dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_GetMsgHeaderVersion, 0, &response)) {
+
+		smu_print("SMU msg header version: %d\n", response);
+
+		if (response == DALSMC_VERSION)
+			return true;
+	}
+
 	return false;
 }
 
@@ -163,6 +220,22 @@ void dcn401_smu_send_cab_for_uclk_message(struct clk_mgr_internal *clk_mgr, unsi
 	smu_print("Numways for SubVP : %d\n", num_ways);
 }
 
+void dcn401_smu_set_dram_addr_high(struct clk_mgr_internal *clk_mgr, uint32_t addr_high)
+{
+	smu_print("SMU Set DRAM addr high: %d\n", addr_high);
+
+	dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_SetDalDramAddrHigh, addr_high, NULL);
+}
+
+void dcn401_smu_set_dram_addr_low(struct clk_mgr_internal *clk_mgr, uint32_t addr_low)
+{
+	smu_print("SMU Set DRAM addr low: %d\n", addr_low);
+
+	dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_SetDalDramAddrLow, addr_low, NULL);
+}
+
 void dcn401_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr)
 {
 	smu_print("SMU Transfer WM table DRAM 2 SMU\n");
@@ -348,3 +421,52 @@ unsigned int dcn401_smu_get_num_of_umc_channels(struct clk_mgr_internal *clk_mgr
 
 	return response;
 }
+
+/*
+ * Frequency in MHz returned in lower 16 bits for valid DPM level
+ *
+ * Call with dpm_level = 0xFF to query features, return value will be:
+ *     Bits 7:0 - number of DPM levels
+ *     Bit   28 - 1 = auto DPM on
+ *     Bit   29 - 1 = sweep DPM on
+ *     Bit   30 - 1 = forced DPM on
+ *     Bit   31 - 0 = discrete, 1 = fine-grained
+ *
+ * With fine-grained DPM, only min and max frequencies will be reported
+ *
+ * Returns 0 on failure
+ */
+unsigned int dcn401_smu_get_dpm_freq_by_index(struct clk_mgr_internal *clk_mgr, uint32_t clk, uint8_t dpm_level)
+{
+	uint32_t response = 0;
+
+	/* bits 23:16 for clock type, lower 8 bits for DPM level */
+	uint32_t param = (clk << 16) | dpm_level;
+
+	smu_print("SMU Get dpm freq by index: clk = %d, dpm_level = %d\n", clk, dpm_level);
+
+	dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_GetDpmFreqByIndex, param, &response);
+
+	smu_print("SMU dpm freq: %d MHz\n", response);
+
+	return response;
+}
+
+/* Returns the max DPM frequency in DC mode in MHz, 0 on failure */
+unsigned int dcn401_smu_get_dc_mode_max_dpm_freq(struct clk_mgr_internal *clk_mgr, uint32_t clk)
+{
+	uint32_t response = 0;
+
+	/* bits 23:16 for clock type */
+	uint32_t param = clk << 16;
+
+	smu_print("SMU Get DC mode max DPM freq: clk = %d\n", clk);
+
+	dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_GetDcModeMaxDpmFreq, param, &response);
+
+	smu_print("SMU DC mode max DMP freq: %d MHz\n", response);
+
+	return response;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.h
index e02eb1294b37..4f5ac603e822 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.h
@@ -7,11 +7,17 @@
 
 #include "os_types.h"
 #include "core_types.h"
-#include "dcn32/dcn32_clk_mgr_smu_msg.h"
 
+struct clk_mgr_internal;
+
+bool dcn401_smu_get_smu_version(struct clk_mgr_internal *clk_mgr, unsigned int *version);
+bool dcn401_smu_check_driver_if_version(struct clk_mgr_internal *clk_mgr);
+bool dcn401_smu_check_msg_header_version(struct clk_mgr_internal *clk_mgr);
 void dcn401_smu_send_fclk_pstate_message(struct clk_mgr_internal *clk_mgr, bool support);
 void dcn401_smu_send_uclk_pstate_message(struct clk_mgr_internal *clk_mgr, bool support);
 void dcn401_smu_send_cab_for_uclk_message(struct clk_mgr_internal *clk_mgr, unsigned int num_ways);
+void dcn401_smu_set_dram_addr_high(struct clk_mgr_internal *clk_mgr, uint32_t addr_high);
+void dcn401_smu_set_dram_addr_low(struct clk_mgr_internal *clk_mgr, uint32_t addr_low);
 void dcn401_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr);
 void dcn401_smu_set_pme_workaround(struct clk_mgr_internal *clk_mgr);
 unsigned int dcn401_smu_set_hard_min_by_freq(struct clk_mgr_internal *clk_mgr, uint32_t clk, uint16_t freq_mhz);
@@ -29,5 +35,7 @@ bool dcn401_smu_set_subvp_uclk_fclk_hardmin(struct clk_mgr_internal *clk_mgr,
 void dcn401_smu_set_min_deep_sleep_dcef_clk(struct clk_mgr_internal *clk_mgr, uint32_t freq_mhz);
 void dcn401_smu_set_num_of_displays(struct clk_mgr_internal *clk_mgr, uint32_t num_displays);
 unsigned int dcn401_smu_get_num_of_umc_channels(struct clk_mgr_internal *clk_mgr);
+unsigned int dcn401_smu_get_dc_mode_max_dpm_freq(struct clk_mgr_internal *clk_mgr, uint32_t clk);
+unsigned int dcn401_smu_get_dpm_freq_by_index(struct clk_mgr_internal *clk_mgr, uint32_t clk, uint8_t dpm_level);
 
 #endif /* __DCN401_CLK_MGR_SMU_MSG_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index c4dd52ed377d..5f2d5638c819 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -460,7 +460,7 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 	 * avoid conflicting with firmware updates.
 	 */
 	if (dc->ctx->dce_version > DCE_VERSION_MAX) {
-		if ((dc->optimized_required || dc->wm_optimized_required) &&
+		if (dc->optimized_required &&
 			(stream->adjust.v_total_max != adjust->v_total_max ||
 			stream->adjust.v_total_min != adjust->v_total_min)) {
 			stream->adjust.timing_adjust_pending = true;
@@ -2577,7 +2577,6 @@ void dc_post_update_surfaces_to_stream(struct dc *dc)
 	}
 
 	dc->optimized_required = false;
-	dc->wm_optimized_required = false;
 }
 
 bool dc_set_generic_gpio_for_stereo(bool enable,
@@ -3056,8 +3055,6 @@ enum surface_update_type dc_check_update_surfaces_for_stream(
 		} else if (memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0) {
 			dc->optimized_required = true;
 		}
-
-		dc->optimized_required |= dc->wm_optimized_required;
 	}
 
 	return type;
@@ -3313,6 +3310,9 @@ static void copy_stream_update_to_stream(struct dc *dc,
 	if (update->adaptive_sync_infopacket)
 		stream->adaptive_sync_infopacket = *update->adaptive_sync_infopacket;
 
+	if (update->avi_infopacket)
+		stream->avi_infopacket = *update->avi_infopacket;
+
 	if (update->dither_option)
 		stream->dither_option = *update->dither_option;
 
@@ -3607,7 +3607,8 @@ static void commit_planes_do_stream_update(struct dc *dc,
 					stream_update->vsp_infopacket ||
 					stream_update->hfvsif_infopacket ||
 					stream_update->adaptive_sync_infopacket ||
-					stream_update->vtem_infopacket) {
+					stream_update->vtem_infopacket ||
+					stream_update->avi_infopacket) {
 				resource_build_info_frame(pipe_ctx);
 				dc->hwss.update_info_frame(pipe_ctx);
 
@@ -5079,6 +5080,7 @@ static bool full_update_required(struct dc *dc,
 			stream_update->hfvsif_infopacket ||
 			stream_update->vtem_infopacket ||
 			stream_update->adaptive_sync_infopacket ||
+			stream_update->avi_infopacket ||
 			stream_update->dpms_off ||
 			stream_update->allow_freesync ||
 			stream_update->vrr_active_variable ||
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index cbca3c67f439..bc5dedf5f60c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -4410,8 +4410,14 @@ static void set_avi_info_frame(
 	unsigned int fr_ind = pipe_ctx->stream->timing.fr_index;
 	enum dc_timing_3d_format format;
 
+	if (stream->avi_infopacket.valid) {
+		*info_packet = stream->avi_infopacket;
+		return;
+	}
+
 	memset(&hdmi_info, 0, sizeof(union hdmi_info_packet));
 
+
 	color_space = pipe_ctx->stream->output_color_space;
 	if (color_space == COLOR_SPACE_UNKNOWN)
 		color_space = (stream->timing.pixel_encoding == PIXEL_ENCODING_RGB) ?
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 9d15ba591772..98f0b6b3c213 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -55,7 +55,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.350"
+#define DC_VER "3.2.351"
 
 /**
  * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC
@@ -1163,6 +1163,7 @@ struct dc_debug_options {
 	unsigned int auxless_alpm_lfps_silence_ns;
 	unsigned int auxless_alpm_lfps_t1t2_us;
 	short auxless_alpm_lfps_t1t2_offset_us;
+	bool disable_stutter_for_wm_program;
 };
 
 
@@ -1391,7 +1392,6 @@ union surface_update_flags {
 		uint32_t in_transfer_func_change:1;
 		uint32_t input_csc_change:1;
 		uint32_t coeff_reduction_change:1;
-		uint32_t output_tf_change:1;
 		uint32_t pixel_format_change:1;
 		uint32_t plane_size_change:1;
 		uint32_t gamut_remap_change:1;
@@ -1735,7 +1735,6 @@ struct dc {
 
 	/* Require to optimize clocks and bandwidth for added/removed planes */
 	bool optimized_required;
-	bool wm_optimized_required;
 	bool idle_optimizations_allowed;
 	bool enable_c20_dtm_b0;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index 5fc6fea211de..76cf9fdedab0 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -203,6 +203,7 @@ struct dc_stream_state {
 	struct dc_info_packet hfvsif_infopacket;
 	struct dc_info_packet vtem_infopacket;
 	struct dc_info_packet adaptive_sync_infopacket;
+	struct dc_info_packet avi_infopacket;
 	uint8_t dsc_packed_pps[128];
 	struct rect src; /* composition area */
 	struct rect dst; /* stream addressable area */
@@ -335,6 +336,8 @@ struct dc_stream_update {
 	struct dc_info_packet *hfvsif_infopacket;
 	struct dc_info_packet *vtem_infopacket;
 	struct dc_info_packet *adaptive_sync_infopacket;
+	struct dc_info_packet *avi_infopacket;
+
 	bool *dpms_off;
 	bool integer_scaling_update;
 	bool *allow_freesync;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 619834a328a3..b5aa03a3e39c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -1217,6 +1217,7 @@ struct dc_panel_config {
 		bool rc_disable;
 		bool rc_allow_static_screen;
 		bool rc_allow_fullscreen_VPB;
+		bool read_psrcap_again;
 		unsigned int replay_enable_option;
 	} psr;
 	/* ABM */
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c
index 0ce9489ac6b7..de6d62401362 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c
@@ -39,6 +39,7 @@
 
 #define CTX \
 	dccg_dcn->base.ctx
+#include "logger_types.h"
 #define DC_LOGGER \
 	dccg->ctx->logger
 
@@ -1136,7 +1137,7 @@ static void dcn35_set_dppclk_enable(struct dccg *dccg,
 	default:
 		break;
 	}
-	//DC_LOG_DEBUG("%s: dpp_inst(%d) DPPCLK_EN = %d\n", __func__, dpp_inst, enable);
+	DC_LOG_DEBUG("%s: dpp_inst(%d) DPPCLK_EN = %d\n", __func__, dpp_inst, enable);
 
 }
 
@@ -1406,6 +1407,10 @@ static void dccg35_set_dtbclk_dto(
 		 * PIPEx_DTO_SRC_SEL should not be programmed during DTBCLK update since OTG may still be on, and the
 		 * programming is handled in program_pix_clk() regardless, so it can be removed from here.
 		 */
+		DC_LOG_DEBUG("%s: OTG%d DTBCLK DTO enabled: pixclk_khz=%d, ref_dtbclk_khz=%d, req_dtbclk_khz=%d, phase=%d, modulo=%d\n",
+				__func__, params->otg_inst, params->pixclk_khz,
+				params->ref_dtbclk_khz, req_dtbclk_khz, phase, modulo);
+
 	} else {
 		switch (params->otg_inst) {
 		case 0:
@@ -1431,6 +1436,8 @@ static void dccg35_set_dtbclk_dto(
 
 		REG_WRITE(DTBCLK_DTO_MODULO[params->otg_inst], 0);
 		REG_WRITE(DTBCLK_DTO_PHASE[params->otg_inst], 0);
+
+		DC_LOG_DEBUG("%s: OTG%d DTBCLK DTO disabled\n", __func__, params->otg_inst);
 	}
 }
 
@@ -1475,6 +1482,8 @@ static void dccg35_set_dpstreamclk(
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+	DC_LOG_DEBUG("%s: dp_hpo_inst(%d) DPSTREAMCLK_EN = %d, DPSTREAMCLK_SRC_SEL = %d\n",
+			__func__, dp_hpo_inst, (src == REFCLK) ? 0 : 1, otg_inst);
 }
 
 
@@ -1514,6 +1523,8 @@ static void dccg35_set_dpstreamclk_root_clock_gating(
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+	DC_LOG_DEBUG("%s: dp_hpo_inst(%d) DPSTREAMCLK_ROOT_GATE_DISABLE = %d\n",
+			__func__, dp_hpo_inst, enable ? 1 : 0);
 }
 
 
@@ -1553,7 +1564,7 @@ static void dccg35_set_physymclk_root_clock_gating(
 		BREAK_TO_DEBUGGER();
 		return;
 	}
-	//DC_LOG_DEBUG("%s: dpp_inst(%d) PHYESYMCLK_ROOT_GATE_DISABLE:\n", __func__, phy_inst, enable ? 0 : 1);
+	DC_LOG_DEBUG("%s: dpp_inst(%d) PHYESYMCLK_ROOT_GATE_DISABLE: %d\n", __func__, phy_inst, enable ? 0 : 1);
 
 }
 
@@ -1626,6 +1637,8 @@ static void dccg35_set_physymclk(
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+	DC_LOG_DEBUG("%s: phy_inst(%d) PHYxSYMCLK_EN = %d, PHYxSYMCLK_SRC_SEL = %d\n",
+			__func__, phy_inst, force_enable ? 1 : 0, clk_src);
 }
 
 static void dccg35_set_valid_pixel_rate(
@@ -1673,6 +1686,7 @@ static void dccg35_dpp_root_clock_control(
 	}
 
 	dccg->dpp_clock_gated[dpp_inst] = !clock_on;
+	DC_LOG_DEBUG("%s: dpp_inst(%d) clock_on = %d\n", __func__, dpp_inst, clock_on);
 }
 
 static void dccg35_disable_symclk32_se(
@@ -1731,6 +1745,7 @@ static void dccg35_disable_symclk32_se(
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+
 }
 
 static void dccg35_init_cb(struct dccg *dccg)
@@ -1738,7 +1753,6 @@ static void dccg35_init_cb(struct dccg *dccg)
 	(void)dccg;
 	/* Any RCG should be done when driver enter low power mode*/
 }
-
 void dccg35_init(struct dccg *dccg)
 {
 	int otg_inst;
@@ -1753,6 +1767,8 @@ void dccg35_init(struct dccg *dccg)
 		for (otg_inst = 0; otg_inst < 2; otg_inst++) {
 			dccg31_disable_symclk32_le(dccg, otg_inst);
 			dccg31_set_symclk32_le_root_clock_gating(dccg, otg_inst, false);
+			DC_LOG_DEBUG("%s: OTG%d SYMCLK32_LE disabled and root clock gating disabled\n",
+					__func__, otg_inst);
 		}
 
 //	if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
@@ -1765,6 +1781,8 @@ void dccg35_init(struct dccg *dccg)
 			dccg35_set_dpstreamclk(dccg, REFCLK, otg_inst,
 						otg_inst);
 			dccg35_set_dpstreamclk_root_clock_gating(dccg, otg_inst, false);
+			DC_LOG_DEBUG("%s: OTG%d DPSTREAMCLK disabled and root clock gating disabled\n",
+					__func__, otg_inst);
 		}
 
 /*
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
index 9e2a473a8852..f9542edff14b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
@@ -169,6 +169,7 @@ static bool dmub_replay_copy_settings(struct dmub_replay *dmub,
 	copy_settings_data->max_deviation_line			= link->dpcd_caps.pr_info.max_deviation_line;
 	copy_settings_data->smu_optimizations_en		= link->replay_settings.replay_smu_opt_enable;
 	copy_settings_data->replay_timing_sync_supported = link->replay_settings.config.replay_timing_sync_supported;
+	copy_settings_data->replay_support_fast_resync_in_ultra_sleep_mode = link->replay_settings.config.replay_support_fast_resync_in_ultra_sleep_mode;
 
 	copy_settings_data->debug.bitfields.enable_ips_visual_confirm = dc->dc->debug.enable_ips_visual_confirm;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services.h b/drivers/gpu/drm/amd/display/dc/dm_services.h
index 7b398d4f4439..fbbf9c757b3c 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services.h
@@ -277,12 +277,13 @@ void dm_perf_trace_timestamp(const char *func_name, unsigned int line, struct dc
 /*
  * SMU message tracing
  */
-void dm_trace_smu_msg(uint32_t msg_id, uint32_t param_in, struct dc_context *ctx);
-void dm_trace_smu_delay(uint32_t delay, struct dc_context *ctx);
-
-#define TRACE_SMU_MSG(msg_id, param_in, ctx)	dm_trace_smu_msg(msg_id, param_in, ctx)
-#define TRACE_SMU_DELAY(response_delay, ctx)	dm_trace_smu_delay(response_delay, ctx)
+void dm_trace_smu_enter(uint32_t msg_id, uint32_t param_in, unsigned int delay, struct dc_context *ctx);
+void dm_trace_smu_exit(bool success, uint32_t response, struct dc_context *ctx);
 
+#define TRACE_SMU_MSG_DELAY(msg_id, param_in, delay, ctx)	dm_trace_smu_enter(msg_id, param_in, delay, ctx)
+#define TRACE_SMU_MSG(msg_id, param_in, ctx)	dm_trace_smu_enter(msg_id, param_in, 0, ctx)
+#define TRACE_SMU_MSG_ENTER(msg_id, param_in, ctx)	dm_trace_smu_enter(msg_id, param_in, 0, ctx)
+#define TRACE_SMU_MSG_EXIT(success, response, ctx)	dm_trace_smu_exit(success, response, ctx)
 
 /*
  * DMUB Interfaces
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn3.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn3.c
index e763c8e45da8..1b9579a32ff2 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn3.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn3.c
@@ -48,18 +48,19 @@ static void set_reserved_time_on_all_planes_with_stream_index(struct display_con
 
 static void remove_duplicates(double *list_a, int *list_a_size)
 {
-	int cur_element = 0;
-	// For all elements b[i] in list_b[]
-	while (cur_element < *list_a_size - 1) {
-		if (list_a[cur_element] == list_a[cur_element + 1]) {
-			for (int j = cur_element + 1; j < *list_a_size - 1; j++) {
-				list_a[j] = list_a[j + 1];
-			}
-			*list_a_size = *list_a_size - 1;
-		} else {
-			cur_element++;
+	int j = 0;
+
+	if (*list_a_size == 0)
+		return;
+
+	for (int i = 1; i < *list_a_size; i++) {
+		if (list_a[j] != list_a[i]) {
+			j++;
+			list_a[j] = list_a[i];
 		}
 	}
+
+	*list_a_size = j + 1;
 }
 
 static bool increase_mpc_combine_factor(unsigned int *mpc_combine_factor, unsigned int limit)
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
index 92957398ac0a..4d4ca6d77bbd 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
@@ -28,6 +28,7 @@
 #include "dcn32_hubbub.h"
 #include "dm_services.h"
 #include "reg_helper.h"
+#include "dal_asic_id.h"
 
 
 #define CTX \
@@ -72,6 +73,14 @@ static void dcn32_init_crb(struct hubbub *hubbub)
 	REG_UPDATE(DCHUBBUB_DEBUG_CTRL_0, DET_DEPTH, 0x47F);
 }
 
+static void hubbub32_set_sdp_control(struct hubbub *hubbub, bool dc_control)
+{
+	struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub);
+
+	REG_UPDATE(DCHUBBUB_SDPIF_CFG0,
+			SDPIF_PORT_CONTROL, dc_control);
+}
+
 void hubbub32_set_request_limit(struct hubbub *hubbub, int memory_channel_count, int words_per_channel)
 {
 	struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub);
@@ -754,8 +763,18 @@ static bool hubbub32_program_watermarks(
 		unsigned int refclk_mhz,
 		bool safe_to_lower)
 {
+	struct dc *dc = hubbub->ctx->dc;
 	bool wm_pending = false;
 
+	if (!safe_to_lower && dc->debug.disable_stutter_for_wm_program &&
+			(ASICREV_IS_GC_11_0_0(dc->ctx->asic_id.hw_internal_rev) ||
+			ASICREV_IS_GC_11_0_3(dc->ctx->asic_id.hw_internal_rev))) {
+		/* before raising watermarks, SDP control give to DF, stutter must be disabled */
+		wm_pending = true;
+		hubbub32_set_sdp_control(hubbub, false);
+		hubbub1_allow_self_refresh_control(hubbub, false);
+	}
+
 	if (hubbub32_program_urgent_watermarks(hubbub, watermarks, refclk_mhz, safe_to_lower))
 		wm_pending = true;
 
@@ -786,10 +805,20 @@ static bool hubbub32_program_watermarks(
 	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND,
 			DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 0x1FF);*/
 
-	if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter)
-		hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
+	if (safe_to_lower) {
+		/* after lowering watermarks, stutter setting is restored, SDP control given to DC */
+		hubbub1_allow_self_refresh_control(hubbub, !dc->debug.disable_stutter);
+
+		if (dc->debug.disable_stutter_for_wm_program &&
+				(ASICREV_IS_GC_11_0_0(dc->ctx->asic_id.hw_internal_rev) ||
+				ASICREV_IS_GC_11_0_3(dc->ctx->asic_id.hw_internal_rev))) {
+			hubbub32_set_sdp_control(hubbub, true);
+		}
+	} else if (dc->debug.disable_stutter) {
+		hubbub1_allow_self_refresh_control(hubbub, !dc->debug.disable_stutter);
+	}
 
-	hubbub32_force_usr_retraining_allow(hubbub, hubbub->ctx->dc->debug.force_usr_allow);
+	hubbub32_force_usr_retraining_allow(hubbub, dc->debug.force_usr_allow);
 
 	return wm_pending;
 }
@@ -974,8 +1003,7 @@ void hubbub32_init(struct hubbub *hubbub)
 	ignore the "df_pre_cstate_req" from the SDP port control.
 	only the DCN will determine when to connect the SDP port
 	*/
-	REG_UPDATE(DCHUBBUB_SDPIF_CFG0,
-			SDPIF_PORT_CONTROL, 1);
+	hubbub32_set_sdp_control(hubbub, true);
 	/*Set SDP's max outstanding request to 512
 	must set the register back to 0 (max outstanding = 256) in zero frame buffer mode*/
 	REG_UPDATE(DCHUBBUB_SDPIF_CFG1,
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 74f5e05f9cb4..e9fe97f0c4ea 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
@@ -3347,7 +3347,7 @@ void dcn10_prepare_bandwidth(
 			context,
 			false);
 
-	dc->wm_optimized_required = hubbub->funcs->program_watermarks(hubbub,
+	dc->optimized_required = hubbub->funcs->program_watermarks(hubbub,
 			&context->bw_ctx.bw.dcn.watermarks,
 			dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 			true);
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 417f2679723e..9477c9f9e196 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
@@ -1982,10 +1982,8 @@ static void dcn20_program_pipe(
 	 * updating on slave planes
 	 */
 	if (pipe_ctx->update_flags.bits.enable ||
-		pipe_ctx->update_flags.bits.plane_changed ||
-		pipe_ctx->stream->update_flags.bits.out_tf ||
-		(pipe_ctx->plane_state &&
-			pipe_ctx->plane_state->update_flags.bits.output_tf_change))
+	    pipe_ctx->update_flags.bits.plane_changed ||
+	    pipe_ctx->stream->update_flags.bits.out_tf)
 		hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream);
 
 	/* If the pipe has been enabled or has a different opp, we
@@ -2390,10 +2388,10 @@ void dcn20_prepare_bandwidth(
 	}
 
 	/* program dchubbub watermarks:
-	 * For assigning wm_optimized_required, use |= operator since we don't want
+	 * For assigning optimized_required, use |= operator since we don't want
 	 * to clear the value if the optimize has not happened yet
 	 */
-	dc->wm_optimized_required |= hubbub->funcs->program_watermarks(hubbub,
+	dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub,
 					&context->bw_ctx.bw.dcn.watermarks,
 					dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 					false);
@@ -2406,10 +2404,10 @@ void dcn20_prepare_bandwidth(
 	if (hubbub->funcs->program_compbuf_size) {
 		if (context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes) {
 			compbuf_size_kb = context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes;
-			dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes);
+			dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes);
 		} else {
 			compbuf_size_kb = context->bw_ctx.bw.dcn.compbuf_size_kb;
-			dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb);
+			dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb);
 		}
 
 		hubbub->funcs->program_compbuf_size(hubbub, compbuf_size_kb, false);
@@ -3131,7 +3129,8 @@ void dcn20_fpga_init_hw(struct dc *dc)
 		res_pool->dccg->funcs->dccg_init(res_pool->dccg);
 
 	//Enable ability to power gate / don't force power on permanently
-	hws->funcs.enable_power_gating_plane(hws, true);
+	if (hws->funcs.enable_power_gating_plane)
+		hws->funcs.enable_power_gating_plane(hws, true);
 
 	// Specific to FPGA dccg and registers
 	REG_WRITE(RBBMIF_TIMEOUT_DIS, 0xFFFFFFFF);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
index 1b0b772fc5dd..7c276c319086 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
@@ -1383,22 +1383,22 @@ void dcn401_prepare_bandwidth(struct dc *dc,
 			false);
 
 	/* program dchubbub watermarks:
-	 * For assigning wm_optimized_required, use |= operator since we don't want
+	 * For assigning optimized_required, use |= operator since we don't want
 	 * to clear the value if the optimize has not happened yet
 	 */
-	dc->wm_optimized_required |= hubbub->funcs->program_watermarks(hubbub,
+	dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub,
 					&context->bw_ctx.bw.dcn.watermarks,
 					dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 					false);
 	/* update timeout thresholds */
 	if (hubbub->funcs->program_arbiter) {
-		dc->wm_optimized_required |= hubbub->funcs->program_arbiter(hubbub, &context->bw_ctx.bw.dcn.arb_regs, false);
+		dc->optimized_required |= hubbub->funcs->program_arbiter(hubbub, &context->bw_ctx.bw.dcn.arb_regs, false);
 	}
 
 	/* decrease compbuf size */
 	if (hubbub->funcs->program_compbuf_segments) {
 		compbuf_size = context->bw_ctx.bw.dcn.arb_regs.compbuf_size;
-		dc->wm_optimized_required |= (compbuf_size != dc->current_state->bw_ctx.bw.dcn.arb_regs.compbuf_size);
+		dc->optimized_required |= (compbuf_size != dc->current_state->bw_ctx.bw.dcn.arb_regs.compbuf_size);
 
 		hubbub->funcs->program_compbuf_segments(hubbub, compbuf_size, false);
 	}
@@ -2032,10 +2032,8 @@ void dcn401_program_pipe(
 	 * updating on slave planes
 	 */
 	if (pipe_ctx->update_flags.bits.enable ||
-		pipe_ctx->update_flags.bits.plane_changed ||
-		pipe_ctx->stream->update_flags.bits.out_tf ||
-		(pipe_ctx->plane_state &&
-			pipe_ctx->plane_state->update_flags.bits.output_tf_change))
+	    pipe_ctx->update_flags.bits.plane_changed ||
+	    pipe_ctx->stream->update_flags.bits.out_tf)
 		hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream);
 
 	/* If the pipe has been enabled or has a different opp, we
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index 8b7b87b21c2e..5e806edbb9f6 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -703,6 +703,20 @@ bool edp_setup_psr(struct dc_link *link,
 	if (!link)
 		return false;
 
+	/* This is a workaround: some vendors require the source to
+	 * read the PSR cap; otherwise, the vendor's PSR feature will
+	 * fall back to its default behavior, causing a misconfiguration
+	 * of this feature.
+	 */
+	if (link->panel_config.psr.read_psrcap_again) {
+		dm_helpers_dp_read_dpcd(
+			link->ctx,
+			link,
+			DP_PSR_SUPPORT,
+			&link->dpcd_caps.psr_info.psr_version,
+			sizeof(link->dpcd_caps.psr_info.psr_version));
+	}
+
 	//Clear PSR cfg
 	memset(&psr_configuration, 0, sizeof(psr_configuration));
 	dm_helpers_dp_write_dpcd(
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c
index 3a51be63f020..c4b4dc3ad8c9 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c
@@ -29,6 +29,7 @@
 #include "stream_encoder.h"
 
 #include "resource.h"
+#include "clk_mgr.h"
 #include "include/irq_service_interface.h"
 #include "virtual/virtual_stream_encoder.h"
 #include "dce110/dce110_resource.h"
@@ -836,17 +837,24 @@ static enum dc_status build_mapped_resource(
 	return DC_OK;
 }
 
-static enum dc_status dce100_validate_bandwidth(
+enum dc_status dce100_validate_bandwidth(
 	struct dc  *dc,
 	struct dc_state *context,
 	enum dc_validate_mode validate_mode)
 {
 	int i;
 	bool at_least_one_pipe = false;
+	struct dc_stream_state *stream = NULL;
+	const uint32_t max_pix_clk_khz = max(dc->clk_mgr->clks.max_supported_dispclk_khz, 400000);
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (context->res_ctx.pipe_ctx[i].stream)
+		stream = context->res_ctx.pipe_ctx[i].stream;
+		if (stream) {
 			at_least_one_pipe = true;
+
+			if (stream->timing.pix_clk_100hz >= max_pix_clk_khz * 10)
+				return DC_FAIL_BANDWIDTH_VALIDATE;
+		}
 	}
 
 	if (at_least_one_pipe) {
@@ -854,7 +862,16 @@ static enum dc_status dce100_validate_bandwidth(
 		context->bw_ctx.bw.dce.dispclk_khz = 681000;
 		context->bw_ctx.bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER_CZ;
 	} else {
-		context->bw_ctx.bw.dce.dispclk_khz = 0;
+		/* On DCE 6.0 and 6.4 the PLL0 is both the display engine clock and
+		 * the DP clock, and shouldn't be turned off. Just select the display
+		 * clock value from its low power mode.
+		 */
+		if (dc->ctx->dce_version == DCE_VERSION_6_0 ||
+			dc->ctx->dce_version == DCE_VERSION_6_4)
+			context->bw_ctx.bw.dce.dispclk_khz = 352000;
+		else
+			context->bw_ctx.bw.dce.dispclk_khz = 0;
+
 		context->bw_ctx.bw.dce.yclk_khz = 0;
 	}
 
@@ -881,7 +898,7 @@ static bool dce100_validate_surface_sets(
 	return true;
 }
 
-static enum dc_status dce100_validate_global(
+enum dc_status dce100_validate_global(
 		struct dc  *dc,
 		struct dc_state *context)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.h
index fecab7c560f5..dd150a4b4610 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.h
@@ -41,6 +41,15 @@ struct resource_pool *dce100_create_resource_pool(
 
 enum dc_status dce100_validate_plane(const struct dc_plane_state *plane_state, struct dc_caps *caps);
 
+enum dc_status dce100_validate_global(
+		struct dc  *dc,
+		struct dc_state *context);
+
+enum dc_status dce100_validate_bandwidth(
+		struct dc  *dc,
+		struct dc_state *context,
+		enum dc_validate_mode validate_mode);
+
 enum dc_status dce100_add_stream_to_ctx(
 		struct dc *dc,
 		struct dc_state *new_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c
index c164d2500c2a..53c67ebe779f 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c
@@ -34,6 +34,7 @@
 #include "stream_encoder.h"
 
 #include "resource.h"
+#include "clk_mgr.h"
 #include "include/irq_service_interface.h"
 #include "irq/dce60/irq_service_dce60.h"
 #include "dce110/dce110_timing_generator.h"
@@ -863,70 +864,6 @@ static void dce60_resource_destruct(struct dce110_resource_pool *pool)
 	}
 }
 
-static enum dc_status dce60_validate_bandwidth(
-	struct dc *dc,
-	struct dc_state *context,
-	enum dc_validate_mode validate_mode)
-{
-	int i;
-	bool at_least_one_pipe = false;
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (context->res_ctx.pipe_ctx[i].stream)
-			at_least_one_pipe = true;
-	}
-
-	if (at_least_one_pipe) {
-		/* TODO implement when needed but for now hardcode max value*/
-		context->bw_ctx.bw.dce.dispclk_khz = 681000;
-		context->bw_ctx.bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER_CZ;
-	} else {
-		/* On DCE 6.0 and 6.4 the PLL0 is both the display engine clock and
-		 * the DP clock, and shouldn't be turned off. Just select the display
-		 * clock value from its low power mode.
-		 */
-		if (dc->ctx->dce_version == DCE_VERSION_6_0 ||
-			dc->ctx->dce_version == DCE_VERSION_6_4)
-			context->bw_ctx.bw.dce.dispclk_khz = 352000;
-		else
-			context->bw_ctx.bw.dce.dispclk_khz = 0;
-
-		context->bw_ctx.bw.dce.yclk_khz = 0;
-	}
-
-	return DC_OK;
-}
-
-static bool dce60_validate_surface_sets(
-		struct dc_state *context)
-{
-	int i;
-
-	for (i = 0; i < context->stream_count; i++) {
-		if (context->stream_status[i].plane_count == 0)
-			continue;
-
-		if (context->stream_status[i].plane_count > 1)
-			return false;
-
-		if (context->stream_status[i].plane_states[0]->format
-				>= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN)
-			return false;
-	}
-
-	return true;
-}
-
-static enum dc_status dce60_validate_global(
-		struct dc *dc,
-		struct dc_state *context)
-{
-	if (!dce60_validate_surface_sets(context))
-		return DC_FAIL_SURFACE_VALIDATE;
-
-	return DC_OK;
-}
-
 static void dce60_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
@@ -940,10 +877,10 @@ static const struct resource_funcs dce60_res_pool_funcs = {
 	.destroy = dce60_destroy_resource_pool,
 	.link_enc_create = dce60_link_encoder_create,
 	.panel_cntl_create = dce60_panel_cntl_create,
-	.validate_bandwidth = dce60_validate_bandwidth,
+	.validate_bandwidth = dce100_validate_bandwidth,
 	.validate_plane = dce100_validate_plane,
 	.add_stream_to_ctx = dce100_add_stream_to_ctx,
-	.validate_global = dce60_validate_global,
+	.validate_global = dce100_validate_global,
 	.find_first_free_match_stream_enc_for_link = dce100_find_first_free_match_stream_enc_for_link
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c
index 3e8b0ac11d90..5b7769745202 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c
@@ -32,6 +32,7 @@
 #include "stream_encoder.h"
 
 #include "resource.h"
+#include "clk_mgr.h"
 #include "include/irq_service_interface.h"
 #include "irq/dce80/irq_service_dce80.h"
 #include "dce110/dce110_timing_generator.h"
@@ -869,61 +870,6 @@ static void dce80_resource_destruct(struct dce110_resource_pool *pool)
 	}
 }
 
-static enum dc_status dce80_validate_bandwidth(
-	struct dc *dc,
-	struct dc_state *context,
-	enum dc_validate_mode validate_mode)
-{
-	int i;
-	bool at_least_one_pipe = false;
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (context->res_ctx.pipe_ctx[i].stream)
-			at_least_one_pipe = true;
-	}
-
-	if (at_least_one_pipe) {
-		/* TODO implement when needed but for now hardcode max value*/
-		context->bw_ctx.bw.dce.dispclk_khz = 681000;
-		context->bw_ctx.bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER_CZ;
-	} else {
-		context->bw_ctx.bw.dce.dispclk_khz = 0;
-		context->bw_ctx.bw.dce.yclk_khz = 0;
-	}
-
-	return DC_OK;
-}
-
-static bool dce80_validate_surface_sets(
-		struct dc_state *context)
-{
-	int i;
-
-	for (i = 0; i < context->stream_count; i++) {
-		if (context->stream_status[i].plane_count == 0)
-			continue;
-
-		if (context->stream_status[i].plane_count > 1)
-			return false;
-
-		if (context->stream_status[i].plane_states[0]->format
-				>= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN)
-			return false;
-	}
-
-	return true;
-}
-
-static enum dc_status dce80_validate_global(
-		struct dc *dc,
-		struct dc_state *context)
-{
-	if (!dce80_validate_surface_sets(context))
-		return DC_FAIL_SURFACE_VALIDATE;
-
-	return DC_OK;
-}
-
 static void dce80_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
@@ -937,10 +883,10 @@ static const struct resource_funcs dce80_res_pool_funcs = {
 	.destroy = dce80_destroy_resource_pool,
 	.link_enc_create = dce80_link_encoder_create,
 	.panel_cntl_create = dce80_panel_cntl_create,
-	.validate_bandwidth = dce80_validate_bandwidth,
+	.validate_bandwidth = dce100_validate_bandwidth,
 	.validate_plane = dce100_validate_plane,
 	.add_stream_to_ctx = dce100_add_stream_to_ctx,
-	.validate_global = dce80_validate_global,
+	.validate_global = dce100_validate_global,
 	.find_first_free_match_stream_enc_for_link = dce100_find_first_free_match_stream_enc_for_link
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
index 663c49cce4aa..d4917a35b991 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
@@ -927,6 +927,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.enable_legacy_fast_update = true,
 	.using_dml2 = false,
 	.disable_dsc_power_gate = true,
+	.min_disp_clk_khz = 100000,
 };
 
 static const struct dc_panel_config panel_config_defaults = {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index 8f80ccb846d7..3965a7f1b64b 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -739,6 +739,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.fpo_vactive_min_active_margin_us = 200,
 	.fpo_vactive_max_blank_us = 1000,
 	.enable_legacy_fast_update = false,
+	.disable_stutter_for_wm_program = true
 };
 
 static struct dce_aux *dcn32_aux_engine_create(
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
index 20d714596021..99f0432288b4 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
@@ -1230,7 +1230,8 @@ unsigned int dcn32_get_max_hw_cursor_size(const struct dc *dc,
       SR(DCHUBBUB_ARB_MALL_CNTL),                                              \
       SR(DCN_VM_FAULT_ADDR_MSB), SR(DCN_VM_FAULT_ADDR_LSB),                    \
       SR(DCN_VM_FAULT_CNTL), SR(DCN_VM_FAULT_STATUS),                          \
-      SR(SDPIF_REQUEST_RATE_LIMIT)
+      SR(SDPIF_REQUEST_RATE_LIMIT),                                            \
+      SR(DCHUBBUB_SDPIF_CFG0)
 
 /* DCCG */
 
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index e65747f7f12f..92248224b713 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -4143,9 +4143,13 @@ struct dmub_cmd_replay_copy_settings_data {
 	 */
 	uint8_t hpo_link_enc_inst;
 	/**
+	 * Determines if fast resync in ultra sleep mode is enabled/disabled.
+	 */
+	uint8_t replay_support_fast_resync_in_ultra_sleep_mode;
+	/**
 	 * @pad: Align structure to 4 byte boundary.
 	 */
-	uint8_t pad[2];
+	uint8_t pad[1];
 };