Merge tag 'drm-fixes-2022-09-02' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Regular fixes pull. One core dma-buf fix, then two weeks of i915
  fixes, a lot of amdgpu fixes mostly for new IP, and a bunch of msm
  fixes, mostly modesetting ones.

  Nothing seems too bad at this point.

  dma-buf/dma-resv:
   - Fence-handling fix

  i915:
   - GVT fixes including fix for a CommetLake regression in mmio table
     and misc doc and typo fixes
   - Fix CCS handling
   - Fix for guc requests after reset
   - Display DSI related fixes
   - Display backlight related fixes
   - Fix for a null pointer dereference
   - HDMI related quirk for ECS Liva Q2 with GLK graphics
   - Skip wm/ddb readout for disabled pipes

  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

  msm:
   - Fix for inconsistent indenting in msm_dsi_dphy_timing_calc_v3().
   - Fix to make eDP the first connector in the connected list.
   - Fix to populate intf_cfg correctly before calling reset_intf_cfg().
   - Specify the correct number of DSI regulators for SDM660.
   - Specify the correct number of DSI regulators for MSM8996.
   - Fix for removing DP_RECOVERED_CLOCK_OUT_EN bit for tps4 link training
   - Fix probe-deferral crash in gpu devfreq
   - Fix gpu debugfs deadlock"

* tag 'drm-fixes-2022-09-02' of git://anongit.freedesktop.org/drm/drm: (51 commits)
  drm/amd/amdgpu: skip ucode loading if ucode_size == 0
  drm/amdgpu: only init tap_delay ucode when it's included in ucode binary
  drm/amd/display: Fix black flash when switching from ODM2to1 to ODMBypass
  drm/amd/display: Fix check for stream and plane
  drm/amd/display: Re-initialize viewport after pipe merge
  drm/amd/display: Use correct plane for CAB cursor size allocation
  drm/amdgpu: ensure no PCIe peer access for CPU XGMI iolinks
  drm/amd/pm: bump SMU 13.0.0 driver_if header version
  drm/amd/pm: use vbios carried pptable for all SMU13.0.7 SKUs
  drm/amd/pm: use vbios carried pptable for those supported SKUs
  drm/amd/display: fix wrong register access
  drm/amd/display: use actual cursor size instead of max for CAB allocation
  drm/amd/display: disable display fresh from MALL on an edge case for DCN321
  drm/amd/display: Fix CAB cursor size allocation for DCN32/321
  drm/amd/display: Missing HPO instance added
  drm/amd/display: set dig fifo read start level to 7 before dig fifo reset
  drm/amdgpu: Fix use-after-free in amdgpu_cs_ioctl
  drm/amd/display: Fix OTG H timing reset for dcn314
  drm/amd/display: Fix DCN32 DPSTREAMCLK_CNTL programming
  drm/amdgpu: Update mes_v11_api_def.h
  ...

46 files changed, 348 insertions, 162 deletions

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 205acb2c744d..e3885c90a3ac 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -295,7 +295,8 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,
 		enum dma_resv_usage old_usage;
 
 		dma_resv_list_entry(fobj, i, obj, &old, &old_usage);
-		if ((old->context == fence->context && old_usage >= usage) ||
+		if ((old->context == fence->context && old_usage >= usage &&
+		     dma_fence_is_later(fence, old)) ||
 		    dma_fence_is_signaled(old)) {
 			dma_resv_list_set(fobj, i, fence, usage);
 			dma_fence_put(old);
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