Merge tag 'drm-fixes-2025-05-17' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Weekly drm fixes, I'll be honest and say I think this is larger than
  I'd prefer at this point, the main blow out point is that xe has two
  larger fixes.

  One is a fix for active context utilisation reporting, it's for a
  reported regression and will end up in stable anyways, so I don't see
  any point in holding it up.

  The second is a fix for mixed cpu/gpu atomics, which are currently
  broken, but are also not something your average desktop/laptop user is
  going to hit in normal operation, and having them fixed now is better
  than threading them through stable later.

  Other than those, it's mostly the usual, a bunch of amdgpu randoms and
  a few other minor fixes.

  dma-buf:
   - Avoid memory reordering in fence handling

  meson:
   - Avoid integer overflow in mode-clock calculations

  panel-mipi-dbi:
   - Fix output with drm_client_setup_with_fourcc()

  amdgpu:
   - Fix CSA unmap
   - Fix MALL size reporting on GFX11.5
   - AUX fix
   - DCN 3.5 fix
   - VRR fix
   - DP MST fix
   - DML 2.1 fixes
   - Silence DP AUX spam
   - DCN 4.0.1 cursor fix
   - VCN 4.0.5 fix

  ivpu:
   - Fix buffer size in debugfs code

  gpuvm:
   - Add timeslicing and allocation restriction for SVM

  xe:
   - Fix shrinker debugfs name
   - Add HW workaround to Xe2
   - Fix SVM when mixing GPU and CPU atomics
   - Fix per client engine utilization due to active contexts not saving
     timestamp with lite restore enabled"

* tag 'drm-fixes-2025-05-17' of https://gitlab.freedesktop.org/drm/kernel: (24 commits)
  drm/xe: Add WA BB to capture active context utilization
  drm/xe: Save the gt pointer in lrc and drop the tile
  drm/xe: Save CTX_TIMESTAMP mmio value instead of LRC value
  drm/xe: Timeslice GPU on atomic SVM fault
  drm/gpusvm: Add timeslicing support to GPU SVM
  drm/xe: Strict migration policy for atomic SVM faults
  drm/gpusvm: Introduce devmem_only flag for allocation
  drm/xe/xe2hpg: Add Wa_22021007897
  drm/amdgpu: read back register after written for VCN v4.0.5
  Revert "drm/amd/display: Hardware cursor changes color when switched to software cursor"
  dma-buf: insert memory barrier before updating num_fences
  drm/xe: Fix the gem shrinker name
  drm/amd/display: Avoid flooding unnecessary info messages
  drm/amd/display: Fix null check of pipe_ctx->plane_state for update_dchubp_dpp
  drm/amd/display: check stream id dml21 wrapper to get plane_id
  drm/amd/display: fix link_set_dpms_off multi-display MST corner case
  drm/amd/display: Defer BW-optimization-blocked DRR adjustments
  Revert: "drm/amd/display: Enable urgent latency adjustment on DCN35"
  drm/amd/display: Correct the reply value when AUX write incomplete
  drm/amdgpu: fix incorrect MALL size for GFX1151
  ...

Author: torvalds

drivers/accel/ivpu/ivpu_debugfs.c

@@ -455,7 +455,7 @@ priority_bands_fops_write(struct file *file, const char __user *user_buf, size_t
 	if (ret < 0)
 		return ret;
 
-	buf[size] = '\0';
+	buf[ret] = '\0';
 	ret = sscanf(buf, "%u %u %u %u", &band, &grace_period, &process_grace_period,
 		     &process_quantum);
 	if (ret != 4)

drivers/dma-buf/dma-resv.c

@@ -320,8 +320,9 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,
 	count++;
 
 	dma_resv_list_set(fobj, i, fence, usage);
-	/* pointer update must be visible before we extend the num_fences */
-	smp_store_mb(fobj->num_fences, count);
+	/* fence update must be visible before we extend the num_fences */
+	smp_wmb();
+	fobj->num_fences = count;
 }
 EXPORT_SYMBOL(dma_resv_add_fence);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c

@@ -109,7 +109,7 @@ int amdgpu_unmap_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	struct drm_exec exec;
 	int r;
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
+	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = amdgpu_vm_lock_pd(vm, &exec, 0);
 		if (likely(!r))

drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c

@@ -752,6 +752,18 @@ static int gmc_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 	adev->gmc.vram_type = vram_type;
 	adev->gmc.vram_vendor = vram_vendor;
 
+	/* The mall_size is already calculated as mall_size_per_umc * num_umc.
+	 * However, for gfx1151, which features a 2-to-1 UMC mapping,
+	 * the result must be multiplied by 2 to determine the actual mall size.
+	 */
+	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+	case IP_VERSION(11, 5, 1):
+		adev->gmc.mall_size *= 2;
+		break;
+	default:
+		break;
+	}
+
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(11, 0, 0):
 	case IP_VERSION(11, 0, 1):

drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c

@@ -1023,6 +1023,10 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 			ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
 			VCN_RB1_DB_CTRL__EN_MASK);
 
+	/* Keeping one read-back to ensure all register writes are done, otherwise
+	 * it may introduce race conditions */
+	RREG32_SOC15(VCN, inst_idx, regVCN_RB1_DB_CTRL);
+
 	return 0;
 }
 
@@ -1205,6 +1209,10 @@ static int vcn_v4_0_5_start(struct amdgpu_vcn_inst *vinst)
 	WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
 	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
 
+	/* Keeping one read-back to ensure all register writes are done, otherwise
+	 * it may introduce race conditions */
+	RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
+
 	return 0;
 }
 

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -372,6 +372,8 @@ get_crtc_by_otg_inst(struct amdgpu_device *adev,
 static inline bool is_dc_timing_adjust_needed(struct dm_crtc_state *old_state,
 					      struct dm_crtc_state *new_state)
 {
+	if (new_state->stream->adjust.timing_adjust_pending)
+		return true;
 	if (new_state->freesync_config.state ==  VRR_STATE_ACTIVE_FIXED)
 		return true;
 	else if (amdgpu_dm_crtc_vrr_active(old_state) != amdgpu_dm_crtc_vrr_active(new_state))
@@ -12763,7 +12765,8 @@ int amdgpu_dm_process_dmub_aux_transfer_sync(
 		/* The reply is stored in the top nibble of the command. */
 		payload->reply[0] = (adev->dm.dmub_notify->aux_reply.command >> 4) & 0xF;
 
-	if (!payload->write && p_notify->aux_reply.length)
+	/*write req may receive a byte indicating partially written number as well*/
+	if (p_notify->aux_reply.length)
 		memcpy(payload->data, p_notify->aux_reply.data,
 				p_notify->aux_reply.length);
 

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c

@@ -62,6 +62,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	enum aux_return_code_type operation_result;
 	struct amdgpu_device *adev;
 	struct ddc_service *ddc;
+	uint8_t copy[16];
 
 	if (WARN_ON(msg->size > 16))
 		return -E2BIG;
@@ -77,6 +78,11 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 			(msg->request & DP_AUX_I2C_WRITE_STATUS_UPDATE) != 0;
 	payload.defer_delay = 0;
 
+	if (payload.write) {
+		memcpy(copy, msg->buffer, msg->size);
+		payload.data = copy;
+	}
+
 	result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload,
 				      &operation_result);
 
@@ -100,9 +106,9 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	 */
 	if (payload.write && result >= 0) {
 		if (result) {
-			/*one byte indicating partially written bytes. Force 0 to retry*/
-			drm_info(adev_to_drm(adev), "amdgpu: AUX partially written\n");
-			result = 0;
+			/*one byte indicating partially written bytes*/
+			drm_dbg_dp(adev_to_drm(adev), "amdgpu: AUX partially written\n");
+			result = payload.data[0];
 		} else if (!payload.reply[0])
 			/*I2C_ACK|AUX_ACK*/
 			result = msg->size;
@@ -127,11 +133,11 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 			break;
 		}
 
-		drm_info(adev_to_drm(adev), "amdgpu: DP AUX transfer fail:%d\n", operation_result);
+		drm_dbg_dp(adev_to_drm(adev), "amdgpu: DP AUX transfer fail:%d\n", operation_result);
 	}
 
 	if (payload.reply[0])
-		drm_info(adev_to_drm(adev), "amdgpu: AUX reply command not ACK: 0x%02x.",
+		drm_dbg_dp(adev_to_drm(adev), "amdgpu: AUX reply command not ACK: 0x%02x.",
 			payload.reply[0]);
 
 	return result;

drivers/gpu/drm/amd/display/dc/core/dc.c

@@ -439,9 +439,12 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 	 * Don't adjust DRR while there's bandwidth optimizations pending to
 	 * avoid conflicting with firmware updates.
 	 */
-	if (dc->ctx->dce_version > DCE_VERSION_MAX)
-		if (dc->optimized_required || dc->wm_optimized_required)
+	if (dc->ctx->dce_version > DCE_VERSION_MAX) {
+		if (dc->optimized_required || dc->wm_optimized_required) {
+			stream->adjust.timing_adjust_pending = true;
 			return false;
+		}
+	}
 
 	dc_exit_ips_for_hw_access(dc);
 
@@ -3168,7 +3171,8 @@ static void copy_stream_update_to_stream(struct dc *dc,
 
 	if (update->crtc_timing_adjust) {
 		if (stream->adjust.v_total_min != update->crtc_timing_adjust->v_total_min ||
-			stream->adjust.v_total_max != update->crtc_timing_adjust->v_total_max)
+			stream->adjust.v_total_max != update->crtc_timing_adjust->v_total_max ||
+			stream->adjust.timing_adjust_pending)
 			update->crtc_timing_adjust->timing_adjust_pending = true;
 		stream->adjust = *update->crtc_timing_adjust;
 		update->crtc_timing_adjust->timing_adjust_pending = false;

drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c

@@ -195,9 +195,9 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 	.dcn_downspread_percent = 0.5,
 	.gpuvm_min_page_size_bytes = 4096,
 	.hostvm_min_page_size_bytes = 4096,
-	.do_urgent_latency_adjustment = 1,
+	.do_urgent_latency_adjustment = 0,
 	.urgent_latency_adjustment_fabric_clock_component_us = 0,
-	.urgent_latency_adjustment_fabric_clock_reference_mhz = 3000,
+	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
 };
 
 void dcn35_build_wm_range_table_fpu(struct clk_mgr *clk_mgr)

drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c

@@ -910,18 +910,20 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm
 }
 
 //TODO : Could be possibly moved to a common helper layer.
-static bool dml21_wrapper_get_plane_id(const struct dc_state *context, const struct dc_plane_state *plane, unsigned int *plane_id)
+static bool dml21_wrapper_get_plane_id(const struct dc_state *context, unsigned int stream_id, const struct dc_plane_state *plane, unsigned int *plane_id)
 {
 	int i, j;
 
 	if (!plane_id)
 		return false;
 
 	for (i = 0; i < context->stream_count; i++) {
-		for (j = 0; j < context->stream_status[i].plane_count; j++) {
-			if (context->stream_status[i].plane_states[j] == plane) {
-				*plane_id = (i << 16) | j;
-				return true;
+		if (context->streams[i]->stream_id == stream_id) {
+			for (j = 0; j < context->stream_status[i].plane_count; j++) {
+				if (context->stream_status[i].plane_states[j] == plane) {
+					*plane_id = (i << 16) | j;
+					return true;
+				}
 			}
 		}
 	}
@@ -944,14 +946,14 @@ static unsigned int map_stream_to_dml21_display_cfg(const struct dml2_context *d
 	return location;
 }
 
-static unsigned int map_plane_to_dml21_display_cfg(const struct dml2_context *dml_ctx,
+static unsigned int map_plane_to_dml21_display_cfg(const struct dml2_context *dml_ctx, unsigned int stream_id,
 		const struct dc_plane_state *plane, const struct dc_state *context)
 {
 	unsigned int plane_id;
 	int i = 0;
 	int location = -1;
 
-	if (!dml21_wrapper_get_plane_id(context, plane, &plane_id)) {
+	if (!dml21_wrapper_get_plane_id(context, stream_id, plane, &plane_id)) {
 		ASSERT(false);
 		return -1;
 	}
@@ -1037,7 +1039,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s
 			dml_dispcfg->plane_descriptors[disp_cfg_plane_location].stream_index = disp_cfg_stream_location;
 		} else {
 			for (plane_index = 0; plane_index < context->stream_status[stream_index].plane_count; plane_index++) {
-				disp_cfg_plane_location = map_plane_to_dml21_display_cfg(dml_ctx, context->stream_status[stream_index].plane_states[plane_index], context);
+				disp_cfg_plane_location = map_plane_to_dml21_display_cfg(dml_ctx, context->streams[stream_index]->stream_id, context->stream_status[stream_index].plane_states[plane_index], context);
 
 				if (disp_cfg_plane_location < 0)
 					disp_cfg_plane_location = dml_dispcfg->num_planes++;
@@ -1048,7 +1050,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s
 				populate_dml21_plane_config_from_plane_state(dml_ctx, &dml_dispcfg->plane_descriptors[disp_cfg_plane_location], context->stream_status[stream_index].plane_states[plane_index], context, stream_index);
 				dml_dispcfg->plane_descriptors[disp_cfg_plane_location].stream_index = disp_cfg_stream_location;
 
-				if (dml21_wrapper_get_plane_id(context, context->stream_status[stream_index].plane_states[plane_index], &dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[disp_cfg_plane_location]))
+				if (dml21_wrapper_get_plane_id(context, context->streams[stream_index]->stream_id, context->stream_status[stream_index].plane_states[plane_index], &dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[disp_cfg_plane_location]))
 					dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id_valid[disp_cfg_plane_location] = true;
 
 				/* apply forced pstate policy */