Merge tag 'amd-drm-fixes-6.0-2022-08-31' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.0-2022-08-31:

amdgpu:
- FRU error message fix
- MES 11 updates
- DCN 3.2.x fixes
- DCN 3.1.4 fixes
- Fix possible use after free in CS IOCTL
- SMU 13.0.x fixes
- Fix iolink reporting on devices with direct connections to CPU
- GFX10 tap delay firmware fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220831212312.5921-1-alexander.deucher@amd.com

23 files changed, 234 insertions, 96 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f095a2513aff..1400abee9f40 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5524,7 +5524,8 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
 		~*peer_adev->dev->dma_mask : ~((1ULL << 32) - 1);
 	resource_size_t aper_limit =
 		adev->gmc.aper_base + adev->gmc.aper_size - 1;
-	bool p2p_access = !(pci_p2pdma_distance_many(adev->pdev,
+	bool p2p_access = !adev->gmc.xgmi.connected_to_cpu &&
+			  !(pci_p2pdma_distance_many(adev->pdev,
 					&peer_adev->dev, 1, true) < 0);
 
 	return pcie_p2p && p2p_access && (adev->gmc.visible_vram_size &&
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
index ecada5eadfe3..e325150879df 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
@@ -66,10 +66,15 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev)
 		return true;
 	case CHIP_SIENNA_CICHLID:
 		if (strnstr(atom_ctx->vbios_version, "D603",
+		    sizeof(atom_ctx->vbios_version))) {
+			if (strnstr(atom_ctx->vbios_version, "D603GLXE",
 			    sizeof(atom_ctx->vbios_version)))
-			return true;
-		else
+				return false;
+			else
+				return true;
+		} else {
 			return false;
+		}
 	default:
 		return false;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index b1099ee79c50..c2fd6f3076a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -159,7 +159,10 @@ void amdgpu_job_free(struct amdgpu_job *job)
 	amdgpu_sync_free(&job->sync);
 	amdgpu_sync_free(&job->sched_sync);
 
-	dma_fence_put(&job->hw_fence);
+	if (!job->hw_fence.ops)
+		kfree(job);
+	else
+		dma_fence_put(&job->hw_fence);
 }
 
 int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 1036446abc30..9f7a5e393f85 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2401,7 +2401,7 @@ static int psp_load_smu_fw(struct psp_context *psp)
 static bool fw_load_skip_check(struct psp_context *psp,
 			       struct amdgpu_firmware_info *ucode)
 {
-	if (!ucode->fw)
+	if (!ucode->fw || !ucode->ucode_size)
 		return true;
 
 	if (ucode->ucode_id == AMDGPU_UCODE_ID_SMC &&
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index a2a4dc1844c0..a3cd5c1e8529 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4274,35 +4274,45 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 
 		}
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS];
-		info->ucode_id = AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS;
-		info->fw = adev->gfx.rlc_fw;
-		adev->firmware.fw_size +=
-			ALIGN(adev->gfx.rlc.global_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		if (adev->gfx.rlc.global_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.global_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE0_TAP_DELAYS];
-		info->ucode_id = AMDGPU_UCODE_ID_SE0_TAP_DELAYS;
-		info->fw = adev->gfx.rlc_fw;
-		adev->firmware.fw_size +=
-			ALIGN(adev->gfx.rlc.se0_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		if (adev->gfx.rlc.se0_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE0_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_SE0_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.se0_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE1_TAP_DELAYS];
-		info->ucode_id = AMDGPU_UCODE_ID_SE1_TAP_DELAYS;
-		info->fw = adev->gfx.rlc_fw;
-		adev->firmware.fw_size +=
-			ALIGN(adev->gfx.rlc.se1_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		if (adev->gfx.rlc.se1_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE1_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_SE1_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.se1_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE2_TAP_DELAYS];
-		info->ucode_id = AMDGPU_UCODE_ID_SE2_TAP_DELAYS;
-		info->fw = adev->gfx.rlc_fw;
-		adev->firmware.fw_size +=
-			ALIGN(adev->gfx.rlc.se2_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		if (adev->gfx.rlc.se2_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE2_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_SE2_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.se2_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE3_TAP_DELAYS];
-		info->ucode_id = AMDGPU_UCODE_ID_SE3_TAP_DELAYS;
-		info->fw = adev->gfx.rlc_fw;
-		adev->firmware.fw_size +=
-			ALIGN(adev->gfx.rlc.se3_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		if (adev->gfx.rlc.se3_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE3_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_SE3_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.se3_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
 
 		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1];
 		info->ucode_id = AMDGPU_UCODE_ID_CP_MEC1;
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 120ea294abef..cc3fdbbcd314 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -183,6 +183,7 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes,
 	mes_add_queue_pkt.trap_handler_addr = input->tba_addr;
 	mes_add_queue_pkt.tma_addr = input->tma_addr;
 	mes_add_queue_pkt.is_kfd_process = input->is_kfd_process;
+	mes_add_queue_pkt.trap_en = 1;
 
 	return mes_v11_0_submit_pkt_and_poll_completion(mes,
 			&mes_add_queue_pkt, sizeof(mes_add_queue_pkt),
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index aeecca68dea7..fb22c3d70528 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1094,7 +1094,8 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 				dc->current_state->stream_count != context->stream_count)
 			should_disable = true;
 
-		if (old_stream && !dc->current_state->res_ctx.pipe_ctx[i].top_pipe) {
+		if (old_stream && !dc->current_state->res_ctx.pipe_ctx[i].top_pipe &&
+				!dc->current_state->res_ctx.pipe_ctx[i].prev_odm_pipe) {
 			struct pipe_ctx *old_pipe, *new_pipe;
 
 			old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c
index a788d160953b..ab70ebd8f223 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c
@@ -104,6 +104,9 @@ static bool has_query_dp_alt(struct link_encoder *enc)
 {
 	struct dc_dmub_srv *dc_dmub_srv = enc->ctx->dmub_srv;
 
+	if (enc->ctx->dce_version >= DCN_VERSION_3_15)
+		return true;
+
 	/* Supports development firmware and firmware >= 4.0.11 */
 	return dc_dmub_srv &&
 	       !(dc_dmub_srv->dmub->fw_version >= DMUB_FW_VERSION(4, 0, 0) &&
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c
index b384f30395d3..e3351ddc566c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c
@@ -317,6 +317,7 @@ static void enc314_stream_encoder_dp_unblank(
 	/* switch DP encoder to CRTC data, but reset it the fifo first. It may happen
 	 * that it overflows during mode transition, and sometimes doesn't recover.
 	 */
+	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7);
 	REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 1);
 	udelay(10);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c
index 0c7980266b85..38aa28ec6b13 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c
@@ -98,7 +98,8 @@ static void optc314_set_odm_combine(struct timing_generator *optc, int *opp_id,
 	REG_UPDATE(OPTC_WIDTH_CONTROL,
 			OPTC_SEGMENT_WIDTH, mpcc_hactive);
 
-	REG_SET(OTG_H_TIMING_CNTL, 0, OTG_H_TIMING_DIV_MODE, opp_cnt - 1);
+	REG_UPDATE(OTG_H_TIMING_CNTL,
+			OTG_H_TIMING_DIV_MODE, opp_cnt - 1);
 	optc1->opp_count = opp_cnt;
 }
 
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 3a9e3870b3a9..2a2a4a9cc117 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
@@ -454,6 +454,7 @@ static const struct dcn31_hpo_dp_stream_encoder_registers hpo_dp_stream_enc_regs
 	hpo_dp_stream_encoder_reg_list(0),
 	hpo_dp_stream_encoder_reg_list(1),
 	hpo_dp_stream_encoder_reg_list(2),
+	hpo_dp_stream_encoder_reg_list(3)
 };
 
 static const struct dcn31_hpo_dp_stream_encoder_shift hpo_dp_se_shift = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
index a31c64b50410..0d5e8a441512 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
@@ -225,19 +225,19 @@ void dccg32_set_dpstreamclk(
 	case 0:
 		REG_UPDATE_2(DPSTREAMCLK_CNTL,
 			     DPSTREAMCLK0_EN,
-			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK0_SRC_SEL, 0);
+			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK0_SRC_SEL, otg_inst);
 		break;
 	case 1:
 		REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK1_EN,
-			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK1_SRC_SEL, 1);
+			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK1_SRC_SEL, otg_inst);
 		break;
 	case 2:
 		REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK2_EN,
-			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK2_SRC_SEL, 2);
+			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK2_SRC_SEL, otg_inst);
 		break;
 	case 3:
 		REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK3_EN,
-			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK3_SRC_SEL, 3);
+			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK3_SRC_SEL, otg_inst);
 		break;
 	default:
 		BREAK_TO_DEBUGGER();
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c
index 26648ce772da..38a48983f663 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c
@@ -310,6 +310,11 @@ static void enc32_stream_encoder_dp_unblank(
 	// TODO: Confirm if we need to wait for DIG_SYMCLK_FE_ON
 	REG_WAIT(DIG_FE_CNTL, DIG_SYMCLK_FE_ON, 1, 10, 5000);
 
+	/* read start level = 0 will bring underflow / overflow and DIG_FIFO_ERROR = 1
+	 * so set it to 1/2 full = 7 before reset as suggested by hardware team.
+	 */
+	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7);
+
 	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1);
 
 	REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 1, 10, 5000);
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 ebd3945c71f1..8d9d96c39808 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
@@ -295,24 +295,38 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 		}
 
 		// Include cursor size for CAB allocation
-		if (stream->cursor_position.enable && plane->address.grph.cursor_cache_addr.quad_part) {
-			cursor_size = dc->caps.max_cursor_size * dc->caps.max_cursor_size;
-			switch (stream->cursor_attributes.color_format) {
-			case CURSOR_MODE_MONO:
-				cursor_size /= 2;
-				break;
-			case CURSOR_MODE_COLOR_1BIT_AND:
-			case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA:
-			case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA:
-				cursor_size *= 4;
-				break;
+		for (j = 0; j < dc->res_pool->pipe_count; j++) {
+			struct pipe_ctx *pipe = &ctx->res_ctx.pipe_ctx[j];
+			struct hubp *hubp = pipe->plane_res.hubp;
 
-			case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED:
-			case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED:
-				cursor_size *= 8;
-				break;
-			}
-			cache_lines_used += dcn32_cache_lines_for_surface(dc, surface_size,
+			if (pipe->stream && pipe->plane_state && hubp)
+				/* Find the cursor plane and use the exact size instead of
+				 * using the max for calculation
+				 */
+				if (hubp->curs_attr.width > 0) {
+					cursor_size = hubp->curs_attr.width * hubp->curs_attr.height;
+					break;
+				}
+		}
+
+		switch (stream->cursor_attributes.color_format) {
+		case CURSOR_MODE_MONO:
+			cursor_size /= 2;
+			break;
+		case CURSOR_MODE_COLOR_1BIT_AND:
+		case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA:
+		case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA:
+			cursor_size *= 4;
+			break;
+
+		case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED:
+		case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED:
+			cursor_size *= 8;
+			break;
+		}
+
+		if (stream->cursor_position.enable && plane->address.grph.cursor_cache_addr.quad_part) {
+			cache_lines_used += dcn32_cache_lines_for_surface(dc, cursor_size,
 					plane->address.grph.cursor_cache_addr.quad_part);
 		}
 	}
@@ -325,6 +339,26 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 	if (cache_lines_used % lines_per_way > 0)
 		num_ways++;
 
+	for (i = 0; i < ctx->stream_count; i++) {
+		stream = ctx->streams[i];
+		for (j = 0; j < ctx->stream_status[i].plane_count; j++) {
+			plane = ctx->stream_status[i].plane_states[j];
+
+			if (stream->cursor_position.enable && plane &&
+				!plane->address.grph.cursor_cache_addr.quad_part &&
+				cursor_size > 16384) {
+				/* Cursor caching is not supported since it won't be on the same line.
+				 * So we need an extra line to accommodate it. With large cursors and a single 4k monitor
+				 * this case triggers corruption. If we're at the edge, then dont trigger display refresh
+				 * from MALL. We only need to cache cursor if its greater that 64x64 at 4 bpp.
+				 */
+				num_ways++;
+				/* We only expect one cursor plane */
+				break;
+			}
+		}
+	}
+
 	return num_ways;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
index 955f52e6064d..ab918fe38f6a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
@@ -144,7 +144,7 @@ bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc,
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 
 		if (!pipe->stream)
-			continue;
+			return false;
 
 		if (!pipe->plane_state)
 			return false;
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 8118cfc5b405..8e4c9d0887ce 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
@@ -1014,6 +1014,15 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
 	    dc->debug.force_subvp_mclk_switch)) {
 
 		dcn32_merge_pipes_for_subvp(dc, context);
+		// to re-initialize viewport after the pipe merge
+		for (int i = 0; i < dc->res_pool->pipe_count; i++) {
+			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+			if (!pipe_ctx->plane_state || !pipe_ctx->stream)
+				continue;
+
+			resource_build_scaling_params(pipe_ctx);
+		}
 
 		while (!found_supported_config && dcn32_enough_pipes_for_subvp(dc, context) &&
 			dcn32_assign_subvp_pipe(dc, context, &dc_pipe_idx)) {
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c b/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c
index db7b0b155374..226af06278ce 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c
@@ -116,7 +116,7 @@ static void setup_hpo_dp_stream_encoder(struct pipe_ctx *pipe_ctx)
 	dto_params.timing = &pipe_ctx->stream->timing;
 	dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr);
 
-	dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, link_enc->inst);
+	dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, stream_enc->inst);
 	dccg->funcs->enable_symclk32_se(dccg, stream_enc->inst, phyd32clk);
 	dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 	stream_enc->funcs->enable_stream(stream_enc);
@@ -137,7 +137,7 @@ static void reset_hpo_dp_stream_encoder(struct pipe_ctx *pipe_ctx)
 	stream_enc->funcs->disable(stream_enc);
 	dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 	dccg->funcs->disable_symclk32_se(dccg, stream_enc->inst);
-	dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst,  pipe_ctx->link_res.hpo_dp_link_enc->inst);
+	dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, stream_enc->inst);
 }
 
 static void setup_hpo_dp_stream_attribute(struct pipe_ctx *pipe_ctx)
diff --git a/drivers/gpu/drm/amd/include/mes_v11_api_def.h b/drivers/gpu/drm/amd/include/mes_v11_api_def.h
index 80dab1146439..50bfa513cb35 100644
--- a/drivers/gpu/drm/amd/include/mes_v11_api_def.h
+++ b/drivers/gpu/drm/amd/include/mes_v11_api_def.h
@@ -268,7 +268,8 @@ union MESAPI__ADD_QUEUE {
 			uint32_t is_tmz_queue		: 1;
 			uint32_t map_kiq_utility_queue  : 1;
 			uint32_t is_kfd_process		: 1;
-			uint32_t reserved		: 22;
+			uint32_t trap_en		: 1;
+			uint32_t reserved		: 21;
 		};
 		struct MES_API_STATUS		api_status;
 		uint64_t                        tma_addr;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
index f745cd8f1ab7..063f4a737605 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
@@ -25,7 +25,7 @@
 #define SMU13_DRIVER_IF_V13_0_0_H
 
 //Increment this version if SkuTable_t or BoardTable_t change
-#define PPTABLE_VERSION 0x22
+#define PPTABLE_VERSION 0x24
 
 #define NUM_GFXCLK_DPM_LEVELS    16
 #define NUM_SOCCLK_DPM_LEVELS    8
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 ac308e72241a..f442bf085a31 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
@@ -30,7 +30,7 @@
 #define SMU13_DRIVER_IF_VERSION_ALDE 0x08
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x05
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x2E
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x30
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C
 
 #define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500  //500ms
@@ -291,5 +291,11 @@ int smu_v13_0_set_default_dpm_tables(struct smu_context *smu);
 void smu_v13_0_set_smu_mailbox_registers(struct smu_context *smu);
 
 int smu_v13_0_mode1_reset(struct smu_context *smu);
+
+int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu,
+					void **table,
+					uint32_t *size,
+					uint32_t pptable_id);
+
 #endif
 #endif
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 18ee3b5e64c5..24488f4cb78c 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
@@ -84,9 +84,6 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_7.bin");
 static const int link_width[] = {0, 1, 2, 4, 8, 12, 16};
 static const int link_speed[] = {25, 50, 80, 160};
 
-static int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu, void **table, uint32_t *size,
-					       uint32_t pptable_id);
-
 int smu_v13_0_init_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
@@ -224,23 +221,19 @@ int smu_v13_0_init_pptable_microcode(struct smu_context *smu)
 
 		/*
 		 * Temporary solution for SMU V13.0.0 with SCPM enabled:
-		 *   - use 36831 signed pptable when pp_table_id is 3683
-		 *   - use 37151 signed pptable when pp_table_id is 3715
-		 *   - use 36641 signed pptable when pp_table_id is 3664 or 0
-		 * TODO: drop these when the pptable carried in vbios is ready.
+		 *   - use vbios carried pptable when pptable_id is 3664, 3715 or 3795
+		 *   - use 36831 soft pptable when pptable_id is 3683
 		 */
 		if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)) {
 			switch (pptable_id) {
-			case 0:
 			case 3664:
-				pptable_id = 36641;
+			case 3715:
+			case 3795:
+				pptable_id = 0;
 				break;
 			case 3683:
 				pptable_id = 36831;
 				break;
-			case 3715:
-				pptable_id = 37151;
-				break;
 			default:
 				dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id);
 				return -EINVAL;
@@ -425,8 +418,10 @@ static int smu_v13_0_get_pptable_from_vbios(struct smu_context *smu, void **tabl
 	return 0;
 }
 
-static int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu, void **table, uint32_t *size,
-					       uint32_t pptable_id)
+int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu,
+					void **table,
+					uint32_t *size,
+					uint32_t pptable_id)
 {
 	const struct smc_firmware_header_v1_0 *hdr;
 	struct amdgpu_device *adev = smu->adev;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index df4a47acd724..7db2fd9ea74a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -388,11 +388,29 @@ static int smu_v13_0_0_append_powerplay_table(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_v13_0_0_setup_pptable(struct smu_context *smu)
+static int smu_v13_0_0_get_pptable_from_pmfw(struct smu_context *smu,
+					     void **table,
+					     uint32_t *size)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	void *combo_pptable = smu_table->combo_pptable;
+	int ret = 0;
+
+	ret = smu_cmn_get_combo_pptable(smu);
+	if (ret)
+		return ret;
+
+	*table = combo_pptable;
+	*size = sizeof(struct smu_13_0_0_powerplay_table);
+
+	return 0;
+}
+
+static int smu_v13_0_0_setup_pptable(struct smu_context *smu)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
 	struct amdgpu_device *adev = smu->adev;
+	uint32_t pptable_id;
 	int ret = 0;
 
 	/*
@@ -401,17 +419,51 @@ static int smu_v13_0_0_setup_pptable(struct smu_context *smu)
 	 * rely on the combo pptable(and its revelant SMU message).
 	 */
 	if (adev->scpm_enabled) {
-		ret = smu_cmn_get_combo_pptable(smu);
-		if (ret)
-			return ret;
-
-		smu->smu_table.power_play_table = combo_pptable;
-		smu->smu_table.power_play_table_size = sizeof(struct smu_13_0_0_powerplay_table);
+		ret = smu_v13_0_0_get_pptable_from_pmfw(smu,
+							&smu_table->power_play_table,
+							&smu_table->power_play_table_size);
 	} else {
-		ret = smu_v13_0_setup_pptable(smu);
-		if (ret)
-			return ret;
+		/* override pptable_id from driver parameter */
+		if (amdgpu_smu_pptable_id >= 0) {
+			pptable_id = amdgpu_smu_pptable_id;
+			dev_info(adev->dev, "override pptable id %d\n", pptable_id);
+		} else {
+			pptable_id = smu_table->boot_values.pp_table_id;
+		}
+
+		/*
+		 * Temporary solution for SMU V13.0.0 with SCPM disabled:
+		 *   - use vbios carried pptable when pptable_id is 3664, 3715 or 3795
+		 *   - use soft pptable when pptable_id is 3683
+		 */
+		if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)) {
+			switch (pptable_id) {
+			case 3664:
+			case 3715:
+			case 3795:
+				pptable_id = 0;
+				break;
+			case 3683:
+				break;
+			default:
+				dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id);
+				return -EINVAL;
+			}
+		}
+
+		/* force using vbios pptable in sriov mode */
+		if ((amdgpu_sriov_vf(adev) || !pptable_id) && (amdgpu_emu_mode != 1))
+			ret = smu_v13_0_0_get_pptable_from_pmfw(smu,
+								&smu_table->power_play_table,
+								&smu_table->power_play_table_size);
+		else
+			ret = smu_v13_0_get_pptable_from_firmware(smu,
+								  &smu_table->power_play_table,
+								  &smu_table->power_play_table_size,
+								  pptable_id);
 	}
+	if (ret)
+		return ret;
 
 	ret = smu_v13_0_0_store_powerplay_table(smu);
 	if (ret)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index 1016d1c216d8..fcf24c540859 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -400,11 +400,27 @@ static int smu_v13_0_7_append_powerplay_table(struct smu_context *smu)
 	return 0;
 }
 
+static int smu_v13_0_7_get_pptable_from_pmfw(struct smu_context *smu,
+					     void **table,
+					     uint32_t *size)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	void *combo_pptable = smu_table->combo_pptable;
+	int ret = 0;
+
+	ret = smu_cmn_get_combo_pptable(smu);
+	if (ret)
+		return ret;
+
+	*table = combo_pptable;
+	*size = sizeof(struct smu_13_0_7_powerplay_table);
+
+	return 0;
+}
 
 static int smu_v13_0_7_setup_pptable(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	void *combo_pptable = smu_table->combo_pptable;
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 
@@ -413,18 +429,11 @@ static int smu_v13_0_7_setup_pptable(struct smu_context *smu)
 	 * be used directly by driver. To get the raw pptable, we need to
 	 * rely on the combo pptable(and its revelant SMU message).
 	 */
-	if (adev->scpm_enabled) {
-		ret = smu_cmn_get_combo_pptable(smu);
-		if (ret)
-			return ret;
-
-		smu->smu_table.power_play_table = combo_pptable;
-		smu->smu_table.power_play_table_size = sizeof(struct smu_13_0_7_powerplay_table);
-	} else {
-		ret = smu_v13_0_setup_pptable(smu);
-		if (ret)
-			return ret;
-	}
+	ret = smu_v13_0_7_get_pptable_from_pmfw(smu,
+						&smu_table->power_play_table,
+						&smu_table->power_play_table_size);
+	if (ret)
+		return ret;
 
 	ret = smu_v13_0_7_store_powerplay_table(smu);
 	if (ret)