Merge tag 'drm-fixes-2024-05-03' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Weekly fixes, mostly made up from amdgpu and some panel changes.

  Otherwise xe, nouveau, vmwgfx and a couple of others, all seems pretty
  on track.

  amdgpu:
   - Fix VRAM memory accounting
   - DCN 3.1 fixes
   - DCN 2.0 fix
   - DCN 3.1.5 fix
   - DCN 3.5 fix
   - DCN 3.2.1 fix
   - DP fixes
   - Seamless boot fix
   - Fix call order in amdgpu_ttm_move()
   - Fix doorbell regression
   - Disable panel replay temporarily

  amdkfd:
   - Flush wq before creating kfd process

  xe:
   - Fix UAF on rebind worker
   - Fix ADL-N display integration

  imagination:
   - fix page-count macro

  nouveau:
   - avoid page-table allocation failures
   - fix firmware memory allocation

  panel:
   - ili9341: avoid OF for device properties; respect deferred probe;
     fix usage of errno codes

  ttm:
   - fix status output

  vmwgfx:
   - fix legacy display unit
   - fix read length in fence signalling"

* tag 'drm-fixes-2024-05-03' of https://gitlab.freedesktop.org/drm/kernel: (25 commits)
  drm/xe/display: Fix ADL-N detection
  drm/panel: ili9341: Use predefined error codes
  drm/panel: ili9341: Respect deferred probe
  drm/panel: ili9341: Correct use of device property APIs
  drm/xe/vm: prevent UAF in rebind_work_func()
  drm/amd/display: Disable panel replay by default for now
  drm/amdgpu: fix doorbell regression
  drm/amdkfd: Flush the process wq before creating a kfd_process
  drm/amd/display: Disable seamless boot on 128b/132b encoding
  drm/amd/display: Fix DC mode screen flickering on DCN321
  drm/amd/display: Add VCO speed parameter for DCN31 FPU
  drm/amdgpu: once more fix the call oder in amdgpu_ttm_move() v2
  drm/amd/display: Allocate zero bw after bw alloc enable
  drm/amd/display: Fix incorrect DSC instance for MST
  drm/amd/display: Atom Integrated System Info v2_2 for DCN35
  drm/amd/display: Add dtbclk access to dcn315
  drm/amd/display: Ensure that dmcub support flag is set for DCN20
  drm/amd/display: Handle Y carry-over in VCP X.Y calculation
  drm/amdgpu: Fix VRAM memory accounting
  drm/vmwgfx: Fix invalid reads in fence signaled events
  ...

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

@@ -220,7 +220,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 	    (kfd_mem_limit.ttm_mem_used + ttm_mem_needed >
 	     kfd_mem_limit.max_ttm_mem_limit) ||
 	    (adev && xcp_id >= 0 && adev->kfd.vram_used[xcp_id] + vram_needed >
-	     vram_size - reserved_for_pt)) {
+	     vram_size - reserved_for_pt - atomic64_read(&adev->vram_pin_size))) {
 		ret = -ENOMEM;
 		goto release;
 	}

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

@@ -1243,14 +1243,18 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
  * amdgpu_bo_move_notify - notification about a memory move
  * @bo: pointer to a buffer object
  * @evict: if this move is evicting the buffer from the graphics address space
+ * @new_mem: new resource for backing the BO
  *
  * Marks the corresponding &amdgpu_bo buffer object as invalid, also performs
  * bookkeeping.
  * TTM driver callback which is called when ttm moves a buffer.
  */
-void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict)
+void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
+			   bool evict,
+			   struct ttm_resource *new_mem)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
+	struct ttm_resource *old_mem = bo->resource;
 	struct amdgpu_bo *abo;
 
 	if (!amdgpu_bo_is_amdgpu_bo(bo))
@@ -1262,12 +1266,12 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict)
 	amdgpu_bo_kunmap(abo);
 
 	if (abo->tbo.base.dma_buf && !abo->tbo.base.import_attach &&
-	    bo->resource->mem_type != TTM_PL_SYSTEM)
+	    old_mem && old_mem->mem_type != TTM_PL_SYSTEM)
 		dma_buf_move_notify(abo->tbo.base.dma_buf);
 
-	/* remember the eviction */
-	if (evict)
-		atomic64_inc(&adev->num_evictions);
+	/* move_notify is called before move happens */
+	trace_amdgpu_bo_move(abo, new_mem ? new_mem->mem_type : -1,
+			     old_mem ? old_mem->mem_type : -1);
 }
 
 void amdgpu_bo_get_memory(struct amdgpu_bo *bo,

drivers/gpu/drm/amd/amdgpu/amdgpu_object.h

@@ -328,7 +328,9 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
 int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 			   size_t buffer_size, uint32_t *metadata_size,
 			   uint64_t *flags);
-void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict);
+void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
+			   bool evict,
+			   struct ttm_resource *new_mem);
 void amdgpu_bo_release_notify(struct ttm_buffer_object *bo);
 vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
 void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,

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

@@ -419,7 +419,7 @@ bool amdgpu_res_cpu_visible(struct amdgpu_device *adev,
 		return false;
 
 	if (res->mem_type == TTM_PL_SYSTEM || res->mem_type == TTM_PL_TT ||
-	    res->mem_type == AMDGPU_PL_PREEMPT)
+	    res->mem_type == AMDGPU_PL_PREEMPT || res->mem_type == AMDGPU_PL_DOORBELL)
 		return true;
 
 	if (res->mem_type != TTM_PL_VRAM)
@@ -481,14 +481,16 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 
 	if (!old_mem || (old_mem->mem_type == TTM_PL_SYSTEM &&
 			 bo->ttm == NULL)) {
+		amdgpu_bo_move_notify(bo, evict, new_mem);
 		ttm_bo_move_null(bo, new_mem);
-		goto out;
+		return 0;
 	}
 	if (old_mem->mem_type == TTM_PL_SYSTEM &&
 	    (new_mem->mem_type == TTM_PL_TT ||
 	     new_mem->mem_type == AMDGPU_PL_PREEMPT)) {
+		amdgpu_bo_move_notify(bo, evict, new_mem);
 		ttm_bo_move_null(bo, new_mem);
-		goto out;
+		return 0;
 	}
 	if ((old_mem->mem_type == TTM_PL_TT ||
 	     old_mem->mem_type == AMDGPU_PL_PREEMPT) &&
@@ -498,9 +500,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			return r;
 
 		amdgpu_ttm_backend_unbind(bo->bdev, bo->ttm);
+		amdgpu_bo_move_notify(bo, evict, new_mem);
 		ttm_resource_free(bo, &bo->resource);
 		ttm_bo_assign_mem(bo, new_mem);
-		goto out;
+		return 0;
 	}
 
 	if (old_mem->mem_type == AMDGPU_PL_GDS ||
@@ -512,8 +515,9 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 	    new_mem->mem_type == AMDGPU_PL_OA ||
 	    new_mem->mem_type == AMDGPU_PL_DOORBELL) {
 		/* Nothing to save here */
+		amdgpu_bo_move_notify(bo, evict, new_mem);
 		ttm_bo_move_null(bo, new_mem);
-		goto out;
+		return 0;
 	}
 
 	if (bo->type == ttm_bo_type_device &&
@@ -525,8 +529,8 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 		abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
 	}
 
-	if (adev->mman.buffer_funcs_enabled) {
-		if (((old_mem->mem_type == TTM_PL_SYSTEM &&
+	if (adev->mman.buffer_funcs_enabled &&
+	    ((old_mem->mem_type == TTM_PL_SYSTEM &&
 	      new_mem->mem_type == TTM_PL_VRAM) ||
 	     (old_mem->mem_type == TTM_PL_VRAM &&
 	      new_mem->mem_type == TTM_PL_SYSTEM))) {
@@ -537,10 +541,11 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 		return -EMULTIHOP;
 	}
 
+	amdgpu_bo_move_notify(bo, evict, new_mem);
+	if (adev->mman.buffer_funcs_enabled)
 		r = amdgpu_move_blit(bo, evict, new_mem, old_mem);
-	} else {
+	else
 		r = -ENODEV;
-	}
 
 	if (r) {
 		/* Check that all memory is CPU accessible */
@@ -555,11 +560,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			return r;
 	}
 
-	trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
-out:
-	/* update statistics */
+	/* update statistics after the move */
+	if (evict)
+		atomic64_inc(&adev->num_evictions);
 	atomic64_add(bo->base.size, &adev->num_bytes_moved);
-	amdgpu_bo_move_notify(bo, evict);
 	return 0;
 }
 
@@ -1559,7 +1563,7 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo,
 static void
 amdgpu_bo_delete_mem_notify(struct ttm_buffer_object *bo)
 {
-	amdgpu_bo_move_notify(bo, false);
+	amdgpu_bo_move_notify(bo, false, NULL);
 }
 
 static struct ttm_device_funcs amdgpu_bo_driver = {

drivers/gpu/drm/amd/amdkfd/kfd_process.c

@@ -829,6 +829,14 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
 	if (process) {
 		pr_debug("Process already found\n");
 	} else {
+		/* If the process just called exec(3), it is possible that the
+		 * cleanup of the kfd_process (following the release of the mm
+		 * of the old process image) is still in the cleanup work queue.
+		 * Make sure to drain any job before trying to recreate any
+		 * resource for this process.
+		 */
+		flush_workqueue(kfd_process_wq);
+
 		process = create_process(thread);
 		if (IS_ERR(process))
 			goto out;

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

@@ -4537,15 +4537,18 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 	/* Determine whether to enable Replay support by default. */
 	if (!(amdgpu_dc_debug_mask & DC_DISABLE_REPLAY)) {
 		switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) {
-		case IP_VERSION(3, 1, 4):
-		case IP_VERSION(3, 1, 5):
-		case IP_VERSION(3, 1, 6):
-		case IP_VERSION(3, 2, 0):
-		case IP_VERSION(3, 2, 1):
-		case IP_VERSION(3, 5, 0):
-		case IP_VERSION(3, 5, 1):
-			replay_feature_enabled = true;
-			break;
+/*
+ * Disabled by default due to https://gitlab.freedesktop.org/drm/amd/-/issues/3344
+ *		case IP_VERSION(3, 1, 4):
+ *		case IP_VERSION(3, 1, 5):
+ *		case IP_VERSION(3, 1, 6):
+ *		case IP_VERSION(3, 2, 0):
+ *		case IP_VERSION(3, 2, 1):
+ *		case IP_VERSION(3, 5, 0):
+ *		case IP_VERSION(3, 5, 1):
+ *			replay_feature_enabled = true;
+ *			break;
+ */
 		default:
 			replay_feature_enabled = amdgpu_dc_feature_mask & DC_REPLAY_MASK;
 			break;

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

@@ -1495,7 +1495,9 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -1596,7 +1598,9 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -1681,7 +1685,9 @@ static ssize_t dp_dsc_slice_width_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -1780,7 +1786,9 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -1865,7 +1873,9 @@ static ssize_t dp_dsc_slice_height_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -1964,7 +1974,9 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -2045,7 +2057,9 @@ static ssize_t dp_dsc_bits_per_pixel_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -2141,7 +2155,9 @@ static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *bu
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -2220,7 +2236,9 @@ static ssize_t dp_dsc_pic_width_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -2276,7 +2294,9 @@ static ssize_t dp_dsc_pic_height_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -2347,7 +2367,9 @@ static ssize_t dp_dsc_chunk_size_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -2418,7 +2440,9 @@ static ssize_t dp_dsc_slice_bpg_offset_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 

drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c

@@ -2948,6 +2948,7 @@ static enum bp_result construct_integrated_info(
 				result = get_integrated_info_v2_1(bp, info);
 				break;
 			case 2:
+			case 3:
 				result = get_integrated_info_v2_2(bp, info);
 				break;
 			default:

drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c

@@ -145,6 +145,10 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base,
 	 */
 	clk_mgr_base->clks.zstate_support = new_clocks->zstate_support;
 	if (safe_to_lower) {
+		if (clk_mgr_base->clks.dtbclk_en && !new_clocks->dtbclk_en) {
+			dcn315_smu_set_dtbclk(clk_mgr, false);
+			clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en;
+		}
 		/* check that we're not already in lower */
 		if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_LOW_POWER) {
 			display_count = dcn315_get_active_display_cnt_wa(dc, context);
@@ -160,6 +164,10 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base,
 			}
 		}
 	} else {
+		if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) {
+			dcn315_smu_set_dtbclk(clk_mgr, true);
+			clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en;
+		}
 		/* check that we're not already in D0 */
 		if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_MISSION_MODE) {
 			union display_idle_optimization_u idle_info = { 0 };

drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c

@@ -712,6 +712,10 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base,
 					 * since we calculate mode support based on softmax being the max UCLK
 					 * frequency.
 					 */
+					if (dc->debug.disable_dc_mode_overwrite) {
+						dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz);
+						dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz);
+					} else
 						dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK,
 								dc->clk_mgr->bw_params->dc_mode_softmax_memclk);
 				} else {
@@ -746,8 +750,13 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base,
 		/* set UCLK to requested value if P-State switching is supported, or to re-enable P-State switching */
 		if (clk_mgr_base->clks.p_state_change_support &&
 				(update_uclk || !clk_mgr_base->clks.prev_p_state_change_support) &&
-				!dc->work_arounds.clock_update_disable_mask.uclk)
+				!dc->work_arounds.clock_update_disable_mask.uclk) {
+			if (dc->clk_mgr->dc_mode_softmax_enabled && dc->debug.disable_dc_mode_overwrite)
+				dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK,
+						max((int)dc->clk_mgr->bw_params->dc_mode_softmax_memclk, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz)));
+
 			dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz));
+		}
 
 		if (clk_mgr_base->clks.num_ways != new_clocks->num_ways &&
 				clk_mgr_base->clks.num_ways > new_clocks->num_ways) {

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

@@ -1801,6 +1801,9 @@ bool dc_validate_boot_timing(const struct dc *dc,
 		return false;
 	}
 
+	if (link->dpcd_caps.channel_coding_cap.bits.DP_128b_132b_SUPPORTED)
+		return false;
+
 	if (dc->link_srv->edp_is_ilr_optimization_required(link, crtc_timing)) {
 		DC_LOG_EVENT_LINK_TRAINING("Seamless boot disabled to optimize eDP link rate\n");
 		return false;

drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c

@@ -395,6 +395,12 @@ void dcn31_hpo_dp_link_enc_set_throttled_vcp_size(
 				x),
 			25));
 
+	// If y rounds up to integer, carry it over to x.
+	if (y >> 25) {
+		x += 1;
+		y = 0;
+	}
+
 	switch (stream_encoder_inst) {
 	case 0:
 		REG_SET_2(DP_DPHY_SYM32_VC_RATE_CNTL0, 0,

drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c

@@ -291,6 +291,7 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = {
 	.do_urgent_latency_adjustment = false,
 	.urgent_latency_adjustment_fabric_clock_component_us = 0,
 	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+	.dispclk_dppclk_vco_speed_mhz = 2400.0,
 	.num_chans = 4,
 	.dummy_pstate_latency_us = 10.0
 };
@@ -438,6 +439,7 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_16_soc = {
 	.do_urgent_latency_adjustment = false,
 	.urgent_latency_adjustment_fabric_clock_component_us = 0,
 	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+	.dispclk_dppclk_vco_speed_mhz = 2500.0,
 };
 
 void dcn31_zero_pipe_dcc_fraction(display_e2e_pipe_params_st *pipes,

drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c

@@ -270,7 +270,7 @@ static void set_usb4_req_bw_req(struct dc_link *link, int req_bw)
 
 	/* Error check whether requested and allocated are equal */
 	req_bw = requested_bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity);
-	if (req_bw == link->dpia_bw_alloc_config.allocated_bw) {
+	if (req_bw && (req_bw == link->dpia_bw_alloc_config.allocated_bw)) {
 		DC_LOG_ERROR("%s: Request bw equals to allocated bw for link(%d)\n",
 			__func__, link->link_index);
 	}
@@ -341,6 +341,14 @@ bool link_dp_dpia_set_dptx_usb4_bw_alloc_support(struct dc_link *link)
 			ret = true;
 			init_usb4_bw_struct(link);
 			link->dpia_bw_alloc_config.bw_alloc_enabled = true;
+
+			/*
+			 * During DP tunnel creation, CM preallocates BW and reduces estimated BW of other
+			 * DPIA. CM release preallocation only when allocation is complete. Do zero alloc
+			 * to make the CM to release preallocation and update estimated BW correctly for
+			 * all DPIAs per host router
+			 */
+			link_dp_dpia_allocate_usb4_bandwidth_for_stream(link, 0);
 		}
 	}
 

drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c

@@ -2449,6 +2449,7 @@ static bool dcn20_resource_construct(
 	dc->caps.post_blend_color_processing = true;
 	dc->caps.force_dp_tps4_for_cp2520 = true;
 	dc->caps.extended_aux_timeout_support = true;
+	dc->caps.dmcub_support = true;
 
 	/* Color pipeline capabilities */
 	dc->caps.color.dpp.dcn_arch = 1;

drivers/gpu/drm/imagination/pvr_fw_mips.h

@@ -7,13 +7,14 @@
 #include "pvr_rogue_mips.h"
 
 #include <asm/page.h>
+#include <linux/math.h>
 #include <linux/types.h>
 
 /* Forward declaration from pvr_gem.h. */
 struct pvr_gem_object;
 
-#define PVR_MIPS_PT_PAGE_COUNT ((ROGUE_MIPSFW_MAX_NUM_PAGETABLE_PAGES * ROGUE_MIPSFW_PAGE_SIZE_4K) \
-				>> PAGE_SHIFT)
+#define PVR_MIPS_PT_PAGE_COUNT DIV_ROUND_UP(ROGUE_MIPSFW_MAX_NUM_PAGETABLE_PAGES * ROGUE_MIPSFW_PAGE_SIZE_4K, PAGE_SIZE)
+
 /**
  * struct pvr_fw_mips_data - MIPS-specific data
  */

drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h

@@ -15,7 +15,9 @@ struct nvkm_gsp_mem {
 };
 
 struct nvkm_gsp_radix3 {
-	struct nvkm_gsp_mem mem[3];
+	struct nvkm_gsp_mem lvl0;
+	struct nvkm_gsp_mem lvl1;
+	struct sg_table lvl2;
 };
 
 int nvkm_gsp_sg(struct nvkm_device *, u64 size, struct sg_table *);

drivers/gpu/drm/nouveau/nvkm/core/firmware.c

@@ -205,7 +205,9 @@ nvkm_firmware_dtor(struct nvkm_firmware *fw)
 		break;
 	case NVKM_FIRMWARE_IMG_DMA:
 		nvkm_memory_unref(&memory);
-		dma_free_coherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), fw->img, fw->phys);
+		dma_unmap_single(fw->device->dev, fw->phys, sg_dma_len(&fw->mem.sgl),
+				 DMA_TO_DEVICE);
+		kfree(fw->img);
 		break;
 	case NVKM_FIRMWARE_IMG_SGT:
 		nvkm_memory_unref(&memory);
@@ -235,14 +237,17 @@ nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name,
 		fw->img = kmemdup(src, fw->len, GFP_KERNEL);
 		break;
 	case NVKM_FIRMWARE_IMG_DMA: {
-		dma_addr_t addr;
-
 		len = ALIGN(fw->len, PAGE_SIZE);
 
-		fw->img = dma_alloc_coherent(fw->device->dev, len, &addr, GFP_KERNEL);
-		if (fw->img) {
+		fw->img = kmalloc(len, GFP_KERNEL);
+		if (!fw->img)
+			return -ENOMEM;
+
 		memcpy(fw->img, src, fw->len);
-			fw->phys = addr;
+		fw->phys = dma_map_single(fw->device->dev, fw->img, len, DMA_TO_DEVICE);
+		if (dma_mapping_error(fw->device->dev, fw->phys)) {
+			kfree(fw->img);
+			return -EFAULT;
 		}
 
 		sg_init_one(&fw->mem.sgl, fw->img, len);

drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c

@@ -1624,7 +1624,7 @@ r535_gsp_wpr_meta_init(struct nvkm_gsp *gsp)
 	meta->magic = GSP_FW_WPR_META_MAGIC;
 	meta->revision = GSP_FW_WPR_META_REVISION;
 
-	meta->sysmemAddrOfRadix3Elf = gsp->radix3.mem[0].addr;
+	meta->sysmemAddrOfRadix3Elf = gsp->radix3.lvl0.addr;
 	meta->sizeOfRadix3Elf = gsp->fb.wpr2.elf.size;
 
 	meta->sysmemAddrOfBootloader = gsp->boot.fw.addr;
@@ -1919,8 +1919,9 @@ nvkm_gsp_sg(struct nvkm_device *device, u64 size, struct sg_table *sgt)
 static void
 nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
 {
-	for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--)
-		nvkm_gsp_mem_dtor(gsp, &rx3->mem[i]);
+	nvkm_gsp_sg_free(gsp->subdev.device, &rx3->lvl2);
+	nvkm_gsp_mem_dtor(gsp, &rx3->lvl1);
+	nvkm_gsp_mem_dtor(gsp, &rx3->lvl0);
 }
 
 /**
@@ -1960,36 +1961,60 @@ static int
 nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size,
 		   struct nvkm_gsp_radix3 *rx3)
 {
-	u64 addr;
-
-	for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) {
-		u64 *ptes;
+	struct sg_dma_page_iter sg_dma_iter;
+	struct scatterlist *sg;
 	size_t bufsize;
-		int ret, idx;
+	u64 *pte;
+	int ret, i, page_idx = 0;
 
-		bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
-		ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]);
+	ret = nvkm_gsp_mem_ctor(gsp, GSP_PAGE_SIZE, &rx3->lvl0);
 	if (ret)
 		return ret;
 
-		ptes = rx3->mem[i].data;
-		if (i == 2) {
-			struct scatterlist *sgl;
+	ret = nvkm_gsp_mem_ctor(gsp, GSP_PAGE_SIZE, &rx3->lvl1);
+	if (ret)
+		goto lvl1_fail;
+
+	// Allocate level 2
+	bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
+	ret = nvkm_gsp_sg(gsp->subdev.device, bufsize, &rx3->lvl2);
+	if (ret)
+		goto lvl2_fail;
+
+	// Write the bus address of level 1 to level 0
+	pte = rx3->lvl0.data;
+	*pte = rx3->lvl1.addr;
+
+	// Write the bus address of each page in level 2 to level 1
+	pte = rx3->lvl1.data;
+	for_each_sgtable_dma_page(&rx3->lvl2, &sg_dma_iter, 0)
+		*pte++ = sg_page_iter_dma_address(&sg_dma_iter);
 
-			for_each_sgtable_dma_sg(sgt, sgl, idx) {
-				for (int j = 0; j < sg_dma_len(sgl) / GSP_PAGE_SIZE; j++)
-					*ptes++ = sg_dma_address(sgl) + (GSP_PAGE_SIZE * j);
+	// Finally, write the bus address of each page in sgt to level 2
+	for_each_sgtable_sg(&rx3->lvl2, sg, i) {
+		void *sgl_end;
+
+		pte = sg_virt(sg);
+		sgl_end = (void *)pte + sg->length;
+
+		for_each_sgtable_dma_page(sgt, &sg_dma_iter, page_idx) {
+			*pte++ = sg_page_iter_dma_address(&sg_dma_iter);
+			page_idx++;
+
+			// Go to the next scatterlist for level 2 if we've reached the end
+			if ((void *)pte >= sgl_end)
+				break;
 		}
-		} else {
-			for (int j = 0; j < size / GSP_PAGE_SIZE; j++)
-				*ptes++ = addr + GSP_PAGE_SIZE * j;
 	}
 
-		size = rx3->mem[i].size;
-		addr = rx3->mem[i].addr;
+	if (ret) {
+lvl2_fail:
+		nvkm_gsp_mem_dtor(gsp, &rx3->lvl1);
+lvl1_fail:
+		nvkm_gsp_mem_dtor(gsp, &rx3->lvl0);
 	}
 
-	return 0;
+	return ret;
 }
 
 int
@@ -2021,7 +2046,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend)
 		sr = gsp->sr.meta.data;
 		sr->magic = GSP_FW_SR_META_MAGIC;
 		sr->revision = GSP_FW_SR_META_REVISION;
-		sr->sysmemAddrOfSuspendResumeData = gsp->sr.radix3.mem[0].addr;
+		sr->sysmemAddrOfSuspendResumeData = gsp->sr.radix3.lvl0.addr;
 		sr->sizeOfSuspendResumeData = len;
 
 		mbox0 = lower_32_bits(gsp->sr.meta.addr);

drivers/gpu/drm/panel/Kconfig

@@ -177,7 +177,7 @@ config DRM_PANEL_ILITEK_IL9322
 
 config DRM_PANEL_ILITEK_ILI9341
 	tristate "Ilitek ILI9341 240x320 QVGA panels"
-	depends on OF && SPI
+	depends on SPI
 	select DRM_KMS_HELPER
 	select DRM_GEM_DMA_HELPER
 	depends on BACKLIGHT_CLASS_DEVICE

drivers/gpu/drm/panel/panel-ilitek-ili9341.c

@@ -22,8 +22,9 @@
 #include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of.h>
+#include <linux/property.h>
 #include <linux/regulator/consumer.h>
 #include <linux/spi/spi.h>
 
@@ -421,7 +422,7 @@ static int ili9341_dpi_prepare(struct drm_panel *panel)
 
 	ili9341_dpi_init(ili);
 
-	return ret;
+	return 0;
 }
 
 static int ili9341_dpi_enable(struct drm_panel *panel)
@@ -691,7 +692,7 @@ static int ili9341_dpi_probe(struct spi_device *spi, struct gpio_desc *dc,
 	 * Every new incarnation of this display must have a unique
 	 * data entry for the system in this driver.
 	 */
-	ili->conf = of_device_get_match_data(dev);
+	ili->conf = device_get_match_data(dev);
 	if (!ili->conf) {
 		dev_err(dev, "missing device configuration\n");
 		return -ENODEV;
@@ -714,18 +715,18 @@ static int ili9341_probe(struct spi_device *spi)
 
 	reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(reset))
-		dev_err(dev, "Failed to get gpio 'reset'\n");
+		return dev_err_probe(dev, PTR_ERR(reset), "Failed to get gpio 'reset'\n");
 
 	dc = devm_gpiod_get_optional(dev, "dc", GPIOD_OUT_LOW);
 	if (IS_ERR(dc))
-		dev_err(dev, "Failed to get gpio 'dc'\n");
+		return dev_err_probe(dev, PTR_ERR(dc), "Failed to get gpio 'dc'\n");
 
 	if (!strcmp(id->name, "sf-tc240t-9370-t"))
 		return ili9341_dpi_probe(spi, dc, reset);
 	else if (!strcmp(id->name, "yx240qv29"))
 		return ili9341_dbi_probe(spi, dc, reset);
 
-	return -1;
+	return -ENODEV;
 }
 
 static void ili9341_remove(struct spi_device *spi)

drivers/gpu/drm/ttm/ttm_tt.c

@@ -92,7 +92,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc)
 	 */
 	if (bdev->pool.use_dma_alloc && cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
 		page_flags |= TTM_TT_FLAG_DECRYPTED;
-		drm_info(ddev, "TT memory decryption enabled.");
+		drm_info_once(ddev, "TT memory decryption enabled.");
 	}
 
 	bo->ttm = bdev->funcs->ttm_tt_create(bo, page_flags);

drivers/gpu/drm/vmwgfx/vmwgfx_bo.c

@@ -204,6 +204,7 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv,
 			     VMW_BO_DOMAIN_VRAM,
 			     VMW_BO_DOMAIN_VRAM);
 	buf->places[0].lpfn = PFN_UP(bo->resource->size);
+	buf->busy_places[0].lpfn = PFN_UP(bo->resource->size);
 	ret = ttm_bo_validate(bo, &buf->placement, &ctx);
 
 	/* For some reason we didn't end up at the start of vram */

drivers/gpu/drm/vmwgfx/vmwgfx_fence.c

@@ -991,7 +991,7 @@ static int vmw_event_fence_action_create(struct drm_file *file_priv,
 	}
 
 	event->event.base.type = DRM_VMW_EVENT_FENCE_SIGNALED;
-	event->event.base.length = sizeof(*event);
+	event->event.base.length = sizeof(event->event);
 	event->event.user_data = user_data;
 
 	ret = drm_event_reserve_init(dev, file_priv, &event->base, &event->event.base);

drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h

@@ -84,7 +84,8 @@ static inline struct drm_i915_private *kdev_to_i915(struct device *kdev)
 #define IS_ROCKETLAKE(dev_priv)	IS_PLATFORM(dev_priv, XE_ROCKETLAKE)
 #define IS_DG1(dev_priv)        IS_PLATFORM(dev_priv, XE_DG1)
 #define IS_ALDERLAKE_S(dev_priv) IS_PLATFORM(dev_priv, XE_ALDERLAKE_S)
-#define IS_ALDERLAKE_P(dev_priv) IS_PLATFORM(dev_priv, XE_ALDERLAKE_P)
+#define IS_ALDERLAKE_P(dev_priv) (IS_PLATFORM(dev_priv, XE_ALDERLAKE_P) || \
+				  IS_PLATFORM(dev_priv, XE_ALDERLAKE_N))
 #define IS_XEHPSDV(dev_priv) (dev_priv && 0)
 #define IS_DG2(dev_priv)	IS_PLATFORM(dev_priv, XE_DG2)
 #define IS_PONTEVECCHIO(dev_priv) IS_PLATFORM(dev_priv, XE_PVC)

drivers/gpu/drm/xe/xe_vm.c

@@ -1606,6 +1606,9 @@ static void vm_destroy_work_func(struct work_struct *w)
 	/* xe_vm_close_and_put was not called? */
 	xe_assert(xe, !vm->size);
 
+	if (xe_vm_in_preempt_fence_mode(vm))
+		flush_work(&vm->preempt.rebind_work);
+
 	mutex_destroy(&vm->snap_mutex);
 
 	if (!(vm->flags & XE_VM_FLAG_MIGRATION))