Merge tag 'amd-drm-fixes-6.4-2023-04-26' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-fixes-6.4-2023-04-26:

amdgpu:
- SR-IOV fixes
- DCN 3.2 fixes
- DC mclk handling fixes
- eDP fixes
- SubVP fixes
- HDCP regression fix
- DSC fixes
- DC FP fixes
- DCN 3.x fixes
- Display flickering fix when switching between vram and gtt
- Z8 power saving fix
- Fix hang when skipping modeset

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230427033012.7668-1-alexander.deucher@amd.com

31 files changed, 300 insertions, 172 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a2292acf06d0..9b1eaba85bbd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2539,8 +2539,6 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	amdgpu_fru_get_product_info(adev);
 
 init_failed:
-	if (amdgpu_sriov_vf(adev))
-		amdgpu_virt_release_full_gpu(adev, true);
 
 	return r;
 }
@@ -3859,18 +3857,6 @@ fence_driver_init:
 
 	r = amdgpu_device_ip_init(adev);
 	if (r) {
-		/* failed in exclusive mode due to timeout */
-		if (amdgpu_sriov_vf(adev) &&
-		    !amdgpu_sriov_runtime(adev) &&
-		    amdgpu_virt_mmio_blocked(adev) &&
-		    !amdgpu_virt_wait_reset(adev)) {
-			dev_err(adev->dev, "VF exclusive mode timeout\n");
-			/* Don't send request since VF is inactive. */
-			adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME;
-			adev->virt.ops = NULL;
-			r = -EAGAIN;
-			goto release_ras_con;
-		}
 		dev_err(adev->dev, "amdgpu_device_ip_init failed\n");
 		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL, 0, 0);
 		goto release_ras_con;
@@ -3939,8 +3925,10 @@ fence_driver_init:
 				   msecs_to_jiffies(AMDGPU_RESUME_MS));
 	}
 
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev)) {
+		amdgpu_virt_release_full_gpu(adev, true);
 		flush_delayed_work(&adev->delayed_init_work);
+	}
 
 	r = sysfs_create_files(&adev->dev->kobj, amdgpu_dev_attributes);
 	if (r)
@@ -3980,6 +3968,20 @@ fence_driver_init:
 	return 0;
 
 release_ras_con:
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_release_full_gpu(adev, true);
+
+	/* failed in exclusive mode due to timeout */
+	if (amdgpu_sriov_vf(adev) &&
+		!amdgpu_sriov_runtime(adev) &&
+		amdgpu_virt_mmio_blocked(adev) &&
+		!amdgpu_virt_wait_reset(adev)) {
+		dev_err(adev->dev, "VF exclusive mode timeout\n");
+		/* Don't send request since VF is inactive. */
+		adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME;
+		adev->virt.ops = NULL;
+		r = -EAGAIN;
+	}
 	amdgpu_release_ras_context(adev);
 
 failed:
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index a6ad678fd507..77e1e64aa1d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -430,7 +430,7 @@ static int jpeg_v4_0_start_sriov(struct amdgpu_device *adev)
 		MMSCH_COMMAND__END;
 
 	header.version = MMSCH_VERSION;
-	header.total_size = sizeof(struct mmsch_v4_0_init_header) >> 2;
+	header.total_size = RREG32_SOC15(VCN, 0, regMMSCH_VF_CTX_SIZE);
 
 	header.jpegdec.init_status = 0;
 	header.jpegdec.table_offset = 0;
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 6cacb76f389e..8d17fd5a817e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3128,9 +3128,12 @@ void amdgpu_dm_update_connector_after_detect(
 						    aconnector->edid);
 		}
 
-		aconnector->timing_requested = kzalloc(sizeof(struct dc_crtc_timing), GFP_KERNEL);
-		if (!aconnector->timing_requested)
-			dm_error("%s: failed to create aconnector->requested_timing\n", __func__);
+		if (!aconnector->timing_requested) {
+			aconnector->timing_requested =
+				kzalloc(sizeof(struct dc_crtc_timing), GFP_KERNEL);
+			if (!aconnector->timing_requested)
+				dm_error("failed to create aconnector->requested_timing\n");
+		}
 
 		drm_connector_update_edid_property(connector, aconnector->edid);
 		amdgpu_dm_update_freesync_caps(connector, aconnector->edid);
@@ -7898,6 +7901,13 @@ static void amdgpu_dm_commit_cursors(struct drm_atomic_state *state)
 			amdgpu_dm_plane_handle_cursor_update(plane, old_plane_state);
 }
 
+static inline uint32_t get_mem_type(struct drm_framebuffer *fb)
+{
+	struct amdgpu_bo *abo = gem_to_amdgpu_bo(fb->obj[0]);
+
+	return abo->tbo.resource ? abo->tbo.resource->mem_type : 0;
+}
+
 static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				    struct dc_state *dc_state,
 				    struct drm_device *dev,
@@ -7972,6 +7982,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			continue;
 
 		dc_plane = dm_new_plane_state->dc_state;
+		if (!dc_plane)
+			continue;
 
 		bundle->surface_updates[planes_count].surface = dc_plane;
 		if (new_pcrtc_state->color_mgmt_changed) {
@@ -8038,11 +8050,13 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 
 		/*
 		 * Only allow immediate flips for fast updates that don't
-		 * change FB pitch, DCC state, rotation or mirroing.
+		 * change memory domain, FB pitch, DCC state, rotation or
+		 * mirroring.
 		 */
 		bundle->flip_addrs[planes_count].flip_immediate =
 			crtc->state->async_flip &&
-			acrtc_state->update_type == UPDATE_TYPE_FAST;
+			acrtc_state->update_type == UPDATE_TYPE_FAST &&
+			get_mem_type(old_plane_state->fb) == get_mem_type(fb);
 
 		timestamp_ns = ktime_get_ns();
 		bundle->flip_addrs[planes_count].flip_timestamp_in_us = div_u64(timestamp_ns, 1000);
@@ -8554,6 +8568,9 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc);
 		struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
 
+		if (!adev->dm.hdcp_workqueue)
+			continue;
+
 		pr_debug("[HDCP_DM] -------------- i : %x ----------\n", i);
 
 		if (!connector)
@@ -8602,6 +8619,9 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc);
 		struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
 
+		if (!adev->dm.hdcp_workqueue)
+			continue;
+
 		new_crtc_state = NULL;
 		old_crtc_state = NULL;
 
@@ -9620,8 +9640,9 @@ static int dm_update_plane_state(struct dc *dc,
 			return -EINVAL;
 		}
 
+		if (dm_old_plane_state->dc_state)
+			dc_plane_state_release(dm_old_plane_state->dc_state);
 
-		dc_plane_state_release(dm_old_plane_state->dc_state);
 		dm_new_plane_state->dc_state = NULL;
 
 		*lock_and_validation_needed = true;
@@ -10158,6 +10179,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 		ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
 		if (ret) {
 			DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
+			ret = -EINVAL;
 			goto fail;
 		}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 330ab036c830..c6ce2b7123b7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -687,7 +687,6 @@ static void apply_synaptics_fifo_reset_wa(struct drm_dp_aux *aux)
 		return;
 
 	data[0] |= (1 << 1); // set bit 1 to 1
-		return;
 
 	if (!execute_synaptics_rc_command(aux, false, 0x31, 4, 0x221198, data))
 		return;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 994ba426ca66..810ab682f424 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -379,13 +379,17 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 		if (aconnector->dc_sink && connector->state) {
 			struct drm_device *dev = connector->dev;
 			struct amdgpu_device *adev = drm_to_adev(dev);
-			struct hdcp_workqueue *hdcp_work = adev->dm.hdcp_workqueue;
-			struct hdcp_workqueue *hdcp_w = &hdcp_work[aconnector->dc_link->link_index];
 
-			connector->state->hdcp_content_type =
-			hdcp_w->hdcp_content_type[connector->index];
-			connector->state->content_protection =
-			hdcp_w->content_protection[connector->index];
+			if (adev->dm.hdcp_workqueue) {
+				struct hdcp_workqueue *hdcp_work = adev->dm.hdcp_workqueue;
+				struct hdcp_workqueue *hdcp_w =
+					&hdcp_work[aconnector->dc_link->link_index];
+
+				connector->state->hdcp_content_type =
+				hdcp_w->hdcp_content_type[connector->index];
+				connector->state->content_protection =
+				hdcp_w->content_protection[connector->index];
+			}
 		}
 
 		if (aconnector->dc_sink) {
@@ -1406,6 +1410,7 @@ int pre_validate_dsc(struct drm_atomic_state *state,
 	ret = pre_compute_mst_dsc_configs_for_state(state, local_dc_state, vars);
 	if (ret != 0) {
 		DRM_INFO_ONCE("pre_compute_mst_dsc_configs_for_state() failed\n");
+		ret = -EINVAL;
 		goto clean_exit;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
index 1743ca0a3641..c42aa947c969 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
@@ -89,6 +89,7 @@ void dc_fpu_begin(const char *function_name, const int line)
 
 	if (*pcpu == 1) {
 #if defined(CONFIG_X86)
+		migrate_disable();
 		kernel_fpu_begin();
 #elif defined(CONFIG_PPC64)
 		if (cpu_has_feature(CPU_FTR_VSX_COMP)) {
@@ -129,6 +130,7 @@ void dc_fpu_end(const char *function_name, const int line)
 	if (*pcpu <= 0) {
 #if defined(CONFIG_X86)
 		kernel_fpu_end();
+		migrate_enable();
 #elif defined(CONFIG_PPC64)
 		if (cpu_has_feature(CPU_FTR_VSX_COMP)) {
 			disable_kernel_vsx();
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
index ea753f8fa175..8d9444db092a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
@@ -878,6 +878,8 @@ void dcn32_clk_mgr_construct(
 		struct pp_smu_funcs *pp_smu,
 		struct dccg *dccg)
 {
+	struct clk_log_info log_info = {0};
+
 	clk_mgr->base.ctx = ctx;
 	clk_mgr->base.funcs = &dcn32_funcs;
 	if (ASICREV_IS_GC_11_0_2(clk_mgr->base.ctx->asic_id.hw_internal_rev)) {
@@ -911,6 +913,7 @@ void dcn32_clk_mgr_construct(
 			clk_mgr->base.clks.ref_dtbclk_khz = 268750;
 	}
 
+
 	/* integer part is now VCO frequency in kHz */
 	clk_mgr->base.dentist_vco_freq_khz = dcn32_get_vco_frequency_from_reg(clk_mgr);
 
@@ -918,6 +921,8 @@ void dcn32_clk_mgr_construct(
 	if (clk_mgr->base.dentist_vco_freq_khz == 0)
 		clk_mgr->base.dentist_vco_freq_khz = 4300000; /* Updated as per HW docs */
 
+	dcn32_dump_clk_registers(&clk_mgr->base.boot_snapshot, &clk_mgr->base, &log_info);
+
 	if (ctx->dc->debug.disable_dtb_ref_clk_switch &&
 			clk_mgr->base.clks.ref_dtbclk_khz != clk_mgr->base.boot_snapshot.dtbclk) {
 		clk_mgr->base.clks.ref_dtbclk_khz = clk_mgr->base.boot_snapshot.dtbclk;
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 85d54bfb595c..117d80cb36fb 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1707,6 +1707,9 @@ bool dc_remove_plane_from_context(
 	struct dc_stream_status *stream_status = NULL;
 	struct resource_pool *pool = dc->res_pool;
 
+	if (!plane_state)
+		return true;
+
 	for (i = 0; i < context->stream_count; i++)
 		if (context->streams[i] == stream) {
 			stream_status = &context->stream_status[i];
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 23ee63b98dcd..30f0ba05a6e6 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1454,6 +1454,7 @@ struct dc_link {
 
 	struct ddc_service *ddc;
 
+	enum dp_panel_mode panel_mode;
 	bool aux_mode;
 
 	/* Private to DC core */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index 181a3408cc61..25284006019c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -144,7 +144,7 @@ struct test_pattern {
 	unsigned int cust_pattern_size;
 };
 
-#define SUBVP_DRR_MARGIN_US 600 // 600us for DRR margin (SubVP + DRR)
+#define SUBVP_DRR_MARGIN_US 100 // 100us for DRR margin (SubVP + DRR)
 
 enum mall_stream_type {
 	SUBVP_NONE, // subvp not in use
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 9fe0ce91db00..8d2460d06bce 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -3031,10 +3031,12 @@ void dce110_enable_dp_link_output(
 	const struct link_hwss *link_hwss = get_link_hwss(link, link_res);
 	unsigned int i;
 
-
+	/*
+	 * Add the logic to extract BOTH power up and power down sequences
+	 * from enable/disable link output and only call edp panel control
+	 * in enable_link_dp and disable_link_dp once.
+	 */
 	if (link->connector_signal == SIGNAL_TYPE_EDP) {
-		if (!link->dc->config.edp_no_power_sequencing)
-			link->dc->hwss.edp_power_control(link, true);
 		link->dc->hwss.edp_wait_for_hpd_ready(link, true);
 	}
 
@@ -3096,11 +3098,12 @@ void dce110_disable_link_output(struct dc_link *link,
 
 	link_hwss->disable_link_output(link, link_res, signal);
 	link->phy_state.symclk_state = SYMCLK_OFF_TX_OFF;
-
-	if (signal == SIGNAL_TYPE_EDP &&
-			link->dc->hwss.edp_backlight_control)
-		link->dc->hwss.edp_power_control(link, false);
-	else if (dmcu != NULL && dmcu->funcs->lock_phy)
+	/*
+	 * Add the logic to extract BOTH power up and power down sequences
+	 * from enable/disable link output and only call edp panel control
+	 * in enable_link_dp and disable_link_dp once.
+	 */
+	if (dmcu != NULL && dmcu->funcs->lock_phy)
 		dmcu->funcs->unlock_phy(dmcu);
 	dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 5403e9399a46..422fbf79da64 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -2113,6 +2113,15 @@ void dcn20_optimize_bandwidth(
 	if (hubbub->funcs->program_compbuf_size)
 		hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true);
 
+	if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) {
+		dc_dmub_srv_p_state_delegate(dc,
+			true, context);
+		context->bw_ctx.bw.dcn.clk.p_state_change_support = true;
+		dc->clk_mgr->clks.fw_based_mclk_switching = true;
+	} else {
+		dc->clk_mgr->clks.fw_based_mclk_switching = false;
+	}
+
 	dc->clk_mgr->funcs->update_clocks(
 			dc->clk_mgr,
 			context,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index 0e071fbc9154..8263a07f265f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -983,13 +983,36 @@ void dcn30_set_disp_pattern_generator(const struct dc *dc,
 }
 
 void dcn30_prepare_bandwidth(struct dc *dc,
- 	struct dc_state *context)
+	struct dc_state *context)
 {
+	bool p_state_change_support = context->bw_ctx.bw.dcn.clk.p_state_change_support;
+	/* Any transition into an FPO config should disable MCLK switching first to avoid
+	 * driver and FW P-State synchronization issues.
+	 */
+	if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dc->clk_mgr->clks.fw_based_mclk_switching) {
+		dc->optimized_required = true;
+		context->bw_ctx.bw.dcn.clk.p_state_change_support = false;
+	}
+
 	if (dc->clk_mgr->dc_mode_softmax_enabled)
 		if (dc->clk_mgr->clks.dramclk_khz <= dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000 &&
 				context->bw_ctx.bw.dcn.clk.dramclk_khz > dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000)
 			dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz);
 
 	dcn20_prepare_bandwidth(dc, context);
+	/*
+	 * enabled -> enabled: do not disable
+	 * enabled -> disabled: disable
+	 * disabled -> enabled: don't care
+	 * disabled -> disabled: don't care
+	 */
+	if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching)
+		dc_dmub_srv_p_state_delegate(dc, false, context);
+
+	if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dc->clk_mgr->clks.fw_based_mclk_switching) {
+		/* After disabling P-State, restore the original value to ensure we get the correct P-State
+		 * on the next optimize. */
+		context->bw_ctx.bw.dcn.clk.p_state_change_support = p_state_change_support;
+	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
index 965f5ceb33f7..67a34cda3774 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -701,7 +701,9 @@ static const struct dc_plane_cap plane_cap = {
 			.argb8888 = 167,
 			.nv12 = 167,
 			.fp16 = 167
-	}
+	},
+	16,
+	16
 };
 
 static const struct dc_debug_options debug_defaults_drv = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
index 7ac6e69cff37..62ce36c75c4d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@@ -295,6 +295,10 @@ void dcn31_init_hw(struct dc *dc)
 	if (dc->res_pool->hubbub->funcs->init_crb)
 		dc->res_pool->hubbub->funcs->init_crb(dc->res_pool->hubbub);
 #endif
+
+	// Get DMCUB capabilities
+	dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv->dmub);
+	dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr;
 }
 
 void dcn31_dsc_pg_control(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c
index 6f879265ad9c..de7bfba2c179 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c
@@ -274,7 +274,7 @@ static void dccg314_set_dpstreamclk(
 	}
 }
 
-void dccg314_init(struct dccg *dccg)
+static void dccg314_init(struct dccg *dccg)
 {
 	int otg_inst;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
index 50ed7e09d5ba..2f7df8d34a91 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
@@ -885,7 +885,7 @@ static const struct dc_plane_cap plane_cap = {
 static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = false,
 	.enable_z9_disable_interface = true,
-	.minimum_z8_residency_time = 3080,
+	.minimum_z8_residency_time = 2000,
 	.psr_skip_crtc_disable = true,
 	.disable_dmcu = true,
 	.force_abm_enable = false,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
index db0974fe58ab..1f5ee5cde6e1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
@@ -948,6 +948,7 @@ void dcn32_init_hw(struct dc *dc)
 	if (dc->ctx->dmub_srv) {
 		dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv->dmub);
 		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;
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index e30d1f60695d..a876e6eb6cd8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -324,7 +324,6 @@ static const struct dcn10_link_enc_shift le_shift = {
 
 static const struct dcn10_link_enc_mask le_mask = {
 	LINK_ENCODER_MASK_SH_LIST_DCN31(_MASK), \
-
 	//DPCS_DCN31_MASK_SH_LIST(_MASK)
 };
 
@@ -2024,7 +2023,7 @@ int dcn32_populate_dml_pipes_from_context(
 	// In general cases we want to keep the dram clock change requirement
 	// (prefer configs that support MCLK switch). Only override to false
 	// for SubVP
-	if (subvp_in_use)
+	if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || subvp_in_use)
 		context->bw_ctx.dml.soc.dram_clock_change_requirement_final = false;
 	else
 		context->bw_ctx.dml.soc.dram_clock_change_requirement_final = true;
@@ -2093,27 +2092,28 @@ static bool dcn32_resource_construct(
 	uint32_t pipe_fuses = 0;
 	uint32_t num_pipes  = 4;
 
-	#undef REG_STRUCT
-	#define REG_STRUCT bios_regs
-		bios_regs_init();
-
-	#undef REG_STRUCT
-	#define REG_STRUCT clk_src_regs
-		clk_src_regs_init(0, A),
-		clk_src_regs_init(1, B),
-		clk_src_regs_init(2, C),
-		clk_src_regs_init(3, D),
-		clk_src_regs_init(4, E);
-	#undef REG_STRUCT
-	#define REG_STRUCT abm_regs
-		abm_regs_init(0),
-		abm_regs_init(1),
-		abm_regs_init(2),
-		abm_regs_init(3);
-
-	#undef REG_STRUCT
-	#define REG_STRUCT dccg_regs
-		dccg_regs_init();
+#undef REG_STRUCT
+#define REG_STRUCT bios_regs
+	bios_regs_init();
+
+#undef REG_STRUCT
+#define REG_STRUCT clk_src_regs
+	clk_src_regs_init(0, A),
+	clk_src_regs_init(1, B),
+	clk_src_regs_init(2, C),
+	clk_src_regs_init(3, D),
+	clk_src_regs_init(4, E);
+
+#undef REG_STRUCT
+#define REG_STRUCT abm_regs
+	abm_regs_init(0),
+	abm_regs_init(1),
+	abm_regs_init(2),
+	abm_regs_init(3);
+
+#undef REG_STRUCT
+#define REG_STRUCT dccg_regs
+	dccg_regs_init();
 
 	DC_FP_START();
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index 38d1f2be8cf3..f1c1a4b5fcac 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -917,19 +917,19 @@ void dcn20_populate_dml_writeback_from_context(struct dc *dc,
 }
 
 void dcn20_fpu_set_wb_arb_params(struct mcif_arb_params *wb_arb_params,
-                                struct dc_state *context,
-                                display_e2e_pipe_params_st *pipes,
-                                int pipe_cnt, int i)
+				 struct dc_state *context,
+				 display_e2e_pipe_params_st *pipes,
+				 int pipe_cnt, int i)
 {
-       int k;
+	int k;
 
-       dc_assert_fp_enabled();
+	dc_assert_fp_enabled();
 
-       for (k = 0; k < sizeof(wb_arb_params->cli_watermark)/sizeof(wb_arb_params->cli_watermark[0]); k++) {
-               wb_arb_params->cli_watermark[k] = get_wm_writeback_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-               wb_arb_params->pstate_watermark[k] = get_wm_writeback_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-       }
-       wb_arb_params->time_per_pixel = 16.0 * 1000 / (context->res_ctx.pipe_ctx[i].stream->phy_pix_clk / 1000); /* 4 bit fraction, ms */
+	for (k = 0; k < sizeof(wb_arb_params->cli_watermark)/sizeof(wb_arb_params->cli_watermark[0]); k++) {
+		wb_arb_params->cli_watermark[k] = get_wm_writeback_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+		wb_arb_params->pstate_watermark[k] = get_wm_writeback_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	}
+	wb_arb_params->time_per_pixel = 16.0 * 1000 / (context->res_ctx.pipe_ctx[i].stream->phy_pix_clk / 1000); /* 4 bit fraction, ms */
 }
 
 static bool is_dtbclk_required(struct dc *dc, struct dc_state *context)
@@ -1037,11 +1037,11 @@ static void dcn20_adjust_freesync_v_startup(
 	*vstartup_start = ((newVstartup > *vstartup_start) ? newVstartup : *vstartup_start);
 }
 
-void dcn20_calculate_dlg_params(
-		struct dc *dc, struct dc_state *context,
-		display_e2e_pipe_params_st *pipes,
-		int pipe_cnt,
-		int vlevel)
+void dcn20_calculate_dlg_params(struct dc *dc,
+				struct dc_state *context,
+				display_e2e_pipe_params_st *pipes,
+				int pipe_cnt,
+				int vlevel)
 {
 	int i, pipe_idx;
 
@@ -1083,6 +1083,7 @@ void dcn20_calculate_dlg_params(
 		pipes[pipe_idx].pipe.dest.vupdate_offset = get_vupdate_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
 		pipes[pipe_idx].pipe.dest.vupdate_width = get_vupdate_width(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
 		pipes[pipe_idx].pipe.dest.vready_offset = get_vready_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
+
 		if (context->res_ctx.pipe_ctx[i].stream->mall_stream_config.type == SUBVP_PHANTOM) {
 			// Phantom pipe requires that DET_SIZE = 0 and no unbounded requests
 			context->res_ctx.pipe_ctx[i].det_buffer_size_kb = 0;
@@ -1091,6 +1092,7 @@ void dcn20_calculate_dlg_params(
 			context->res_ctx.pipe_ctx[i].det_buffer_size_kb = context->bw_ctx.dml.ip.det_buffer_size_kbytes;
 			context->res_ctx.pipe_ctx[i].unbounded_req = pipes[pipe_idx].pipe.src.unbounded_req_mode;
 		}
+
 		if (context->bw_ctx.bw.dcn.clk.dppclk_khz < pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000)
 			context->bw_ctx.bw.dcn.clk.dppclk_khz = pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000;
 		context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz =
@@ -1118,6 +1120,7 @@ void dcn20_calculate_dlg_params(
 		if (!context->res_ctx.pipe_ctx[i].stream)
 			continue;
 
+		/* cstate disabled on 201 */
 		if (dc->ctx->dce_version == DCN_VERSION_2_01)
 			cstate_en = false;
 
@@ -1201,11 +1204,10 @@ static void swizzle_to_dml_params(
 	}
 }
 
-int dcn20_populate_dml_pipes_from_context(
-		struct dc *dc,
-		struct dc_state *context,
-		display_e2e_pipe_params_st *pipes,
-		bool fast_validate)
+int dcn20_populate_dml_pipes_from_context(struct dc *dc,
+					  struct dc_state *context,
+					  display_e2e_pipe_params_st *pipes,
+					  bool fast_validate)
 {
 	int pipe_cnt, i;
 	bool synchronized_vblank = true;
@@ -1257,6 +1259,8 @@ int dcn20_populate_dml_pipes_from_context(
 
 		pipes[pipe_cnt].clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0;
 
+		pipes[pipe_cnt].pipe.dest.use_maximum_vstartup = dc->ctx->dce_version == DCN_VERSION_2_01;
+
 		pipes[pipe_cnt].dout.dsc_enable = res_ctx->pipe_ctx[i].stream->timing.flags.DSC;
 		/* todo: rotation?*/
 		pipes[pipe_cnt].dout.dsc_slices = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.num_slices_h;
@@ -1296,8 +1300,7 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].pipe.dest.pixel_rate_mhz *= 2;
 		pipes[pipe_cnt].pipe.dest.otg_inst = res_ctx->pipe_ctx[i].stream_res.tg->inst;
 		pipes[pipe_cnt].dout.dp_lanes = 4;
-		if (res_ctx->pipe_ctx[i].stream->link)
-			pipes[pipe_cnt].dout.dp_rate = dm_dp_rate_na;
+		pipes[pipe_cnt].dout.dp_rate = dm_dp_rate_na;
 		pipes[pipe_cnt].dout.is_virtual = 0;
 		pipes[pipe_cnt].pipe.dest.vtotal_min = res_ctx->pipe_ctx[i].stream->adjust.v_total_min;
 		pipes[pipe_cnt].pipe.dest.vtotal_max = res_ctx->pipe_ctx[i].stream->adjust.v_total_max;
@@ -1357,7 +1360,6 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].dout.is_virtual = 1;
 			pipes[pipe_cnt].dout.output_type = dm_dp;
 			pipes[pipe_cnt].dout.dp_lanes = 4;
-			pipes[pipe_cnt].dout.dp_rate = dm_dp_rate_hbr2;
 		}
 
 		switch (res_ctx->pipe_ctx[i].stream->timing.display_color_depth) {
@@ -1507,6 +1509,7 @@ int dcn20_populate_dml_pipes_from_context(
 			default:
 				break;
 			}
+
 			pipes[pipe_cnt].pipe.src.viewport_y_y = scl->viewport.y;
 			pipes[pipe_cnt].pipe.src.viewport_y_c = scl->viewport_c.y;
 			pipes[pipe_cnt].pipe.src.viewport_x_y = scl->viewport.x;
@@ -1615,13 +1618,12 @@ int dcn20_populate_dml_pipes_from_context(
 	return pipe_cnt;
 }
 
-void dcn20_calculate_wm(
-		struct dc *dc, struct dc_state *context,
-		display_e2e_pipe_params_st *pipes,
-		int *out_pipe_cnt,
-		int *pipe_split_from,
-		int vlevel,
-		bool fast_validate)
+void dcn20_calculate_wm(struct dc *dc, struct dc_state *context,
+			display_e2e_pipe_params_st *pipes,
+			int *out_pipe_cnt,
+			int *pipe_split_from,
+			int vlevel,
+			bool fast_validate)
 {
 	int pipe_cnt, i, pipe_idx;
 
@@ -1733,8 +1735,11 @@ void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 }
 
-void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb,
-		struct pp_smu_nv_clock_table *max_clocks, unsigned int *uclk_states, unsigned int num_states)
+void dcn20_update_bounding_box(struct dc *dc,
+			       struct _vcs_dpi_soc_bounding_box_st *bb,
+			       struct pp_smu_nv_clock_table *max_clocks,
+			       unsigned int *uclk_states,
+			       unsigned int num_states)
 {
 	int num_calculated_states = 0;
 	int min_dcfclk = 0;
@@ -1796,9 +1801,8 @@ void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s
 	bb->clock_limits[num_calculated_states].state = bb->num_states;
 }
 
-void dcn20_cap_soc_clocks(
-		struct _vcs_dpi_soc_bounding_box_st *bb,
-		struct pp_smu_nv_clock_table max_clocks)
+void dcn20_cap_soc_clocks(struct _vcs_dpi_soc_bounding_box_st *bb,
+			  struct pp_smu_nv_clock_table max_clocks)
 {
 	int i;
 
@@ -1954,80 +1958,80 @@ validate_out:
 }
 
 bool dcn20_validate_bandwidth_fp(struct dc *dc,
-                                struct dc_state *context,
-                                bool fast_validate)
+				 struct dc_state *context,
+				 bool fast_validate)
 {
-       bool voltage_supported = false;
-       bool full_pstate_supported = false;
-       bool dummy_pstate_supported = false;
-       double p_state_latency_us;
+	bool voltage_supported = false;
+	bool full_pstate_supported = false;
+	bool dummy_pstate_supported = false;
+	double p_state_latency_us;
 
-       dc_assert_fp_enabled();
+	dc_assert_fp_enabled();
 
-       p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us;
-       context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support =
-               dc->debug.disable_dram_clock_change_vactive_support;
-       context->bw_ctx.dml.soc.allow_dram_clock_one_display_vactive =
-               dc->debug.enable_dram_clock_change_one_display_vactive;
+	p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us;
+	context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support =
+		dc->debug.disable_dram_clock_change_vactive_support;
+	context->bw_ctx.dml.soc.allow_dram_clock_one_display_vactive =
+		dc->debug.enable_dram_clock_change_one_display_vactive;
 
-       /*Unsafe due to current pipe merge and split logic*/
-       ASSERT(context != dc->current_state);
+	/*Unsafe due to current pipe merge and split logic*/
+	ASSERT(context != dc->current_state);
 
-       if (fast_validate) {
-               return dcn20_validate_bandwidth_internal(dc, context, true);
-       }
+	if (fast_validate) {
+		return dcn20_validate_bandwidth_internal(dc, context, true);
+	}
 
-       // Best case, we support full UCLK switch latency
-       voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false);
-       full_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support;
+	// Best case, we support full UCLK switch latency
+	voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false);
+	full_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support;
 
-       if (context->bw_ctx.dml.soc.dummy_pstate_latency_us == 0 ||
-               (voltage_supported && full_pstate_supported)) {
-               context->bw_ctx.bw.dcn.clk.p_state_change_support = full_pstate_supported;
-               goto restore_dml_state;
-       }
+	if (context->bw_ctx.dml.soc.dummy_pstate_latency_us == 0 ||
+		(voltage_supported && full_pstate_supported)) {
+		context->bw_ctx.bw.dcn.clk.p_state_change_support = full_pstate_supported;
+		goto restore_dml_state;
+	}
 
-       // Fallback: Try to only support G6 temperature read latency
-       context->bw_ctx.dml.soc.dram_clock_change_latency_us = context->bw_ctx.dml.soc.dummy_pstate_latency_us;
+	// Fallback: Try to only support G6 temperature read latency
+	context->bw_ctx.dml.soc.dram_clock_change_latency_us = context->bw_ctx.dml.soc.dummy_pstate_latency_us;
 
-       voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false);
-       dummy_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support;
+	voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false);
+	dummy_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support;
 
-       if (voltage_supported && (dummy_pstate_supported || !(context->stream_count))) {
-               context->bw_ctx.bw.dcn.clk.p_state_change_support = false;
-               goto restore_dml_state;
-       }
+	if (voltage_supported && (dummy_pstate_supported || !(context->stream_count))) {
+		context->bw_ctx.bw.dcn.clk.p_state_change_support = false;
+		goto restore_dml_state;
+	}
 
-       // ERROR: fallback is supposed to always work.
-       ASSERT(false);
+	// ERROR: fallback is supposed to always work.
+	ASSERT(false);
 
 restore_dml_state:
-       context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us;
-       return voltage_supported;
+	context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us;
+	return voltage_supported;
 }
 
 void dcn20_fpu_set_wm_ranges(int i,
-                            struct pp_smu_wm_range_sets *ranges,
-                            struct _vcs_dpi_soc_bounding_box_st *loaded_bb)
+			     struct pp_smu_wm_range_sets *ranges,
+			     struct _vcs_dpi_soc_bounding_box_st *loaded_bb)
 {
-       dc_assert_fp_enabled();
+	dc_assert_fp_enabled();
 
-       ranges->reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
-       ranges->reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
+	ranges->reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
+	ranges->reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
 }
 
 void dcn20_fpu_adjust_dppclk(struct vba_vars_st *v,
-                            int vlevel,
-                            int max_mpc_comb,
-                            int pipe_idx,
-                            bool is_validating_bw)
+			     int vlevel,
+			     int max_mpc_comb,
+			     int pipe_idx,
+			     bool is_validating_bw)
 {
-       dc_assert_fp_enabled();
+	dc_assert_fp_enabled();
 
-       if (is_validating_bw)
-               v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] *= 2;
-       else
-               v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] /= 2;
+	if (is_validating_bw)
+		v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] *= 2;
+	else
+		v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] /= 2;
 }
 
 int dcn21_populate_dml_pipes_from_context(struct dc *dc,
@@ -2329,7 +2333,7 @@ void dcn21_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 		k++;
 	}
 
-	memcpy(dcn2_1_soc.clock_limits, s, sizeof(dcn2_1_soc.clock_limits));
+	memcpy(&dcn2_1_soc.clock_limits, s, sizeof(dcn2_1_soc.clock_limits));
 
 	if (clk_table->num_entries) {
 		dcn2_1_soc.num_states = clk_table->num_entries + 1;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c
index 80972ee5e55b..a352c703e258 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c
@@ -368,7 +368,9 @@ void dcn30_fpu_update_soc_for_wm_a(struct dc *dc, struct dc_state *context)
 	dc_assert_fp_enabled();
 
 	if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].valid) {
-		context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us;
+		if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching ||
+				context->bw_ctx.dml.soc.dram_clock_change_latency_us == 0)
+			context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us;
 		context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_enter_plus_exit_time_us;
 		context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_exit_time_us;
 	}
@@ -563,6 +565,20 @@ void dcn30_fpu_calculate_wm_and_dlg(
 		pipe_idx++;
 	}
 
+	// WA: restrict FPO to use first non-strobe mode (NV24 BW issue)
+	if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching &&
+			dc->dml.soc.num_chans <= 4 &&
+			context->bw_ctx.dml.vba.DRAMSpeed <= 1700 &&
+			context->bw_ctx.dml.vba.DRAMSpeed >= 1500) {
+
+		for (i = 0; i < dc->dml.soc.num_states; i++) {
+			if (dc->dml.soc.clock_limits[i].dram_speed_mts > 1700) {
+				context->bw_ctx.dml.vba.DRAMSpeed = dc->dml.soc.clock_limits[i].dram_speed_mts;
+				break;
+			}
+		}
+	}
+
 	dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);
 
 	if (!pstate_en)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 4548320217fc..47beb4ea779d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -109,7 +109,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = {
 		{
 			.state = 0,
 			.dcfclk_mhz = 1564.0,
-			.fabricclk_mhz = 400.0,
+			.fabricclk_mhz = 2500.0,
 			.dispclk_mhz = 2150.0,
 			.dppclk_mhz = 2150.0,
 			.phyclk_mhz = 810.0,
@@ -117,7 +117,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = {
 			.phyclk_d32_mhz = 625.0,
 			.socclk_mhz = 1200.0,
 			.dscclk_mhz = 716.667,
-			.dram_speed_mts = 16000.0,
+			.dram_speed_mts = 18000.0,
 			.dtbclk_mhz = 1564.0,
 		},
 	},
@@ -148,7 +148,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = {
 	.max_avg_fabric_bw_use_normal_percent = 60.0,
 	.max_avg_dram_bw_use_normal_strobe_percent = 50.0,
 	.max_avg_dram_bw_use_normal_percent = 15.0,
-	.num_chans = 8,
+	.num_chans = 24,
 	.dram_channel_width_bytes = 2,
 	.fabric_datapath_to_dcn_data_return_bytes = 64,
 	.return_bus_width_bytes = 64,
@@ -1331,6 +1331,11 @@ static void dcn32_calculate_dlg_params(struct dc *dc, struct dc_state *context,
 			context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb]
 					!= dm_dram_clock_change_unsupported;
 
+	/* Pstate change might not be supported by hardware, but it might be
+	 * possible with firmware driven vertical blank stretching.
+	 */
+	context->bw_ctx.bw.dcn.clk.p_state_change_support |= context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching;
+
 	context->bw_ctx.bw.dcn.clk.dppclk_khz = 0;
 	context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context);
 	context->bw_ctx.bw.dcn.clk.ref_dtbclk_khz = context->bw_ctx.dml.vba.DTBCLKPerState[vlevel] * 1000;
@@ -2871,3 +2876,9 @@ bool dcn32_find_vactive_pipe(struct dc *dc, const struct dc_state *context, uint
 	}
 	return vactive_found;
 }
+
+void dcn32_set_clock_limits(const struct _vcs_dpi_soc_bounding_box_st *soc_bb)
+{
+	dc_assert_fp_enabled();
+	dcn3_2_soc.clock_limits[0].dcfclk_mhz = 1200.0;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
index 9a0806a0e2ef..dcf512cd3072 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
@@ -80,4 +80,6 @@ void dcn32_assign_fpo_vactive_candidate(struct dc *dc, const struct dc_state *co
 
 bool dcn32_find_vactive_pipe(struct dc *dc, const struct dc_state *context, uint32_t vactive_margin_req);
 
+void dcn32_set_clock_limits(const struct _vcs_dpi_soc_bounding_box_st *soc_bb);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
index 57b9bd896678..342a1bcb4927 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
@@ -106,16 +106,16 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = {
 	.clock_limits = {
 		{
 			.state = 0,
-			.dcfclk_mhz = 1564.0,
-			.fabricclk_mhz = 400.0,
-			.dispclk_mhz = 2150.0,
-			.dppclk_mhz = 2150.0,
+			.dcfclk_mhz = 1434.0,
+			.fabricclk_mhz = 2250.0,
+			.dispclk_mhz = 1720.0,
+			.dppclk_mhz = 1720.0,
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
-			.phyclk_d32_mhz = 625.0,
+			.phyclk_d32_mhz = 313.0,
 			.socclk_mhz = 1200.0,
-			.dscclk_mhz = 716.667,
-			.dram_speed_mts = 1600.0,
+			.dscclk_mhz = 573.333,
+			.dram_speed_mts = 16000.0,
 			.dtbclk_mhz = 1564.0,
 		},
 	},
@@ -125,14 +125,14 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = {
 	.sr_exit_z8_time_us = 285.0,
 	.sr_enter_plus_exit_z8_time_us = 320,
 	.writeback_latency_us = 12.0,
-	.round_trip_ping_latency_dcfclk_cycles = 263,
+	.round_trip_ping_latency_dcfclk_cycles = 207,
 	.urgent_latency_pixel_data_only_us = 4,
 	.urgent_latency_pixel_mixed_with_vm_data_us = 4,
 	.urgent_latency_vm_data_only_us = 4,
-	.fclk_change_latency_us = 20,
-	.usr_retraining_latency_us = 2,
-	.smn_latency_us = 2,
-	.mall_allocated_for_dcn_mbytes = 64,
+	.fclk_change_latency_us = 7,
+	.usr_retraining_latency_us = 0,
+	.smn_latency_us = 0,
+	.mall_allocated_for_dcn_mbytes = 32,
 	.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
 	.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
 	.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index 027ad1f0144d..2267fb097830 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -1927,6 +1927,11 @@ static void disable_link_dp(struct dc_link *link,
 
 	dp_disable_link_phy(link, link_res, signal);
 
+	if (link->connector_signal == SIGNAL_TYPE_EDP) {
+		if (!link->dc->config.edp_no_power_sequencing)
+			link->dc->hwss.edp_power_control(link, false);
+	}
+
 	if (signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 		/* set the sink to SST mode after disabling the link */
 		enable_mst_on_sink(link, false);
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
index 170f33835930..579fa222810d 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
@@ -1596,7 +1596,10 @@ bool perform_link_training_with_retries(
 				 * Report and continue with eDP panel mode to
 				 * perform eDP link training with right settings
 				 */
-				cp_psp->funcs.enable_assr(cp_psp->handle, link);
+				bool result;
+				result = cp_psp->funcs.enable_assr(cp_psp->handle, link);
+				if (!result && link->panel_mode != DP_PANEL_MODE_EDP)
+					panel_mode = DP_PANEL_MODE_DEFAULT;
 			}
 		}
 
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 d895046787bc..8d1df863659c 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
@@ -83,6 +83,7 @@ void dp_set_panel_mode(struct dc_link *link, enum dp_panel_mode panel_mode)
 			ASSERT(result == DC_OK);
 		}
 	}
+	link->panel_mode = panel_mode;
 	DC_LOG_DETECTION_DP_CAPS("Link: %d eDP panel mode supported: %d "
 		 "eDP panel mode enabled: %d \n",
 		 link->link_index,
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c
index a76da0131add..9c20516be066 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c
@@ -130,12 +130,13 @@ void dmub_dcn32_reset(struct dmub_srv *dmub)
 	REG_WRITE(DMCUB_INBOX1_WPTR, 0);
 	REG_WRITE(DMCUB_OUTBOX1_RPTR, 0);
 	REG_WRITE(DMCUB_OUTBOX1_WPTR, 0);
+	REG_WRITE(DMCUB_OUTBOX0_RPTR, 0);
+	REG_WRITE(DMCUB_OUTBOX0_WPTR, 0);
 	REG_WRITE(DMCUB_SCRATCH0, 0);
 }
 
 void dmub_dcn32_reset_release(struct dmub_srv *dmub)
 {
-	REG_WRITE(DMCUB_GPINT_DATAIN1, 0);
 	REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 0);
 	REG_WRITE(DMCUB_SCRATCH15, dmub->psp_version & 0x001100FF);
 	REG_UPDATE_2(DMCUB_CNTL, DMCUB_ENABLE, 1, DMCUB_TRACEPORT_EN, 1);
diff --git a/drivers/gpu/drm/amd/display/include/signal_types.h b/drivers/gpu/drm/amd/display/include/signal_types.h
index beed70179bb5..23a308c3eccb 100644
--- a/drivers/gpu/drm/amd/display/include/signal_types.h
+++ b/drivers/gpu/drm/amd/display/include/signal_types.h
@@ -104,6 +104,7 @@ static inline bool dc_is_audio_capable_signal(enum signal_type signal)
 {
 	return (signal == SIGNAL_TYPE_DISPLAY_PORT ||
 		signal == SIGNAL_TYPE_DISPLAY_PORT_MST ||
+		signal == SIGNAL_TYPE_VIRTUAL ||
 		dc_is_hdmi_signal(signal));
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
index 7944ce80e5c3..df3baaab0037 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
@@ -62,8 +62,8 @@
 #define CTF_OFFSET_HOTSPOT		5
 #define CTF_OFFSET_MEM			5
 
-static const int pmfw_decoded_link_speed[5] = {1, 2, 3, 4, 5};
-static const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16};
+extern const int pmfw_decoded_link_speed[5];
+extern const int pmfw_decoded_link_width[7];
 
 #define DECODE_GEN_SPEED(gen_speed_idx)		(pmfw_decoded_link_speed[gen_speed_idx])
 #define DECODE_LANE_WIDTH(lane_width_idx)	(pmfw_decoded_link_width[lane_width_idx])
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index 73175c993da9..393c6a7b9609 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -85,6 +85,9 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_10.bin");
 static const int link_width[] = {0, 1, 2, 4, 8, 12, 16};
 static const int link_speed[] = {25, 50, 80, 160};
 
+const int pmfw_decoded_link_speed[5] = {1, 2, 3, 4, 5};
+const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16};
+
 int smu_v13_0_init_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;