Merge branch 'for-linus' into for-next

Pull remaining 6.18-devel changes.

Signed-off-by: Takashi Iwai <tiwai@suse.de>

59 files changed, 388 insertions, 127 deletions

diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 4b2f7d794275..da2565e6de71 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -245,7 +245,7 @@ always-$(CONFIG_DRM_HEADER_TEST) += \
 quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@)
       cmd_hdrtest = \
 		$(CC) $(c_flags) -fsyntax-only -x c /dev/null -include $< -include $<; \
-		 PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \
+		 PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \
 		touch $@
 
 $(obj)/%.hdrtest: $(src)/%.h FORCE
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index a2ca9acf8c4e..923f0fa7350c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1267,6 +1267,10 @@ static int unmap_bo_from_gpuvm(struct kgd_mem *mem,
 
 	(void)amdgpu_vm_bo_unmap(adev, bo_va, entry->va);
 
+	/* VM entity stopped if process killed, don't clear freed pt bo */
+	if (!amdgpu_vm_ready(vm))
+		return 0;
+
 	(void)amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
 
 	(void)amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index f5d5c45ddc0d..afedea02188d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -236,7 +236,7 @@ static int amdgpu_ctx_init_entity(struct amdgpu_ctx *ctx, u32 hw_ip,
 		r = amdgpu_xcp_select_scheds(adev, hw_ip, hw_prio, fpriv,
 						&num_scheds, &scheds);
 		if (r)
-			goto cleanup_entity;
+			goto error_free_entity;
 	}
 
 	/* disable load balance if the hw engine retains context among dependent jobs */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 3d032c4e2dce..2819aceaab74 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5243,10 +5243,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_release_full_gpu(adev, false);
 
-	r = amdgpu_dpm_notify_rlc_state(adev, false);
-	if (r)
-		return r;
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 8561ad7f6180..ed3bef1edfe4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -82,6 +82,18 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 
+	/*
+	 * Disable peer-to-peer access for DCC-enabled VRAM surfaces on GFX12+.
+	 * Such buffers cannot be safely accessed over P2P due to device-local
+	 * compression metadata. Fallback to system-memory path instead.
+	 * Device supports GFX12 (GC 12.x or newer)
+	 * BO was created with the AMDGPU_GEM_CREATE_GFX12_DCC flag
+	 *
+	 */
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(12, 0, 0) &&
+	    bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC)
+		attach->peer2peer = false;
+
 	if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) &&
 	    pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
 		attach->peer2peer = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 61268aa82df4..7333e19291cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2632,9 +2632,14 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+	int r;
 
-	if (amdgpu_acpi_should_gpu_reset(adev))
-		return amdgpu_asic_reset(adev);
+	if (amdgpu_acpi_should_gpu_reset(adev)) {
+		amdgpu_device_lock_reset_domain(adev->reset_domain);
+		r = amdgpu_asic_reset(adev);
+		amdgpu_device_unlock_reset_domain(adev->reset_domain);
+		return r;
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c
index 9cddbf50442a..37270c4dab8d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c
@@ -280,6 +280,8 @@ int isp_kernel_buffer_alloc(struct device *dev, u64 size,
 	if (ret)
 		return ret;
 
+	/* Ensure *bo is NULL so a new BO will be created */
+	*bo = NULL;
 	ret = amdgpu_bo_create_kernel(adev,
 				      size,
 				      ISP_MC_ADDR_ALIGN,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 8c0e5d03de50..aa7987d0806c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2355,8 +2355,11 @@ static int psp_securedisplay_initialize(struct psp_context *psp)
 	if (!ret && !psp->securedisplay_context.context.resp_status) {
 		psp->securedisplay_context.context.initialized = true;
 		mutex_init(&psp->securedisplay_context.mutex);
-	} else
+	} else {
+		/* don't try again */
+		psp->securedisplay_context.context.bin_desc.size_bytes = 0;
 		return ret;
+	}
 
 	mutex_lock(&psp->securedisplay_context.mutex);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index 761bad98da3e..4d0096d0baa9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -151,15 +151,16 @@ void amdgpu_userq_fence_driver_process(struct amdgpu_userq_fence_driver *fence_d
 {
 	struct amdgpu_userq_fence *userq_fence, *tmp;
 	struct dma_fence *fence;
+	unsigned long flags;
 	u64 rptr;
 	int i;
 
 	if (!fence_drv)
 		return;
 
+	spin_lock_irqsave(&fence_drv->fence_list_lock, flags);
 	rptr = amdgpu_userq_fence_read(fence_drv);
 
-	spin_lock(&fence_drv->fence_list_lock);
 	list_for_each_entry_safe(userq_fence, tmp, &fence_drv->fences, link) {
 		fence = &userq_fence->base;
 
@@ -174,7 +175,7 @@ void amdgpu_userq_fence_driver_process(struct amdgpu_userq_fence_driver *fence_d
 		list_del(&userq_fence->link);
 		dma_fence_put(fence);
 	}
-	spin_unlock(&fence_drv->fence_list_lock);
+	spin_unlock_irqrestore(&fence_drv->fence_list_lock, flags);
 }
 
 void amdgpu_userq_fence_driver_destroy(struct kref *ref)
diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
index 811124ff88a8..f9e2edf5260b 100644
--- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
+++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
@@ -407,7 +407,8 @@ static int aqua_vanjaram_switch_partition_mode(struct amdgpu_xcp_mgr *xcp_mgr,
 		return -EINVAL;
 	}
 
-	if (adev->kfd.init_complete && !amdgpu_in_reset(adev))
+	if (adev->kfd.init_complete && !amdgpu_in_reset(adev) &&
+		!adev->in_suspend)
 		flags |= AMDGPU_XCP_OPS_KFD;
 
 	if (flags & AMDGPU_XCP_OPS_KFD) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 7693b7953426..80565392313f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -3102,6 +3102,11 @@ static int gfx_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 5976ed55d9db..2b7aba22ecc1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4399,6 +4399,11 @@ static int gfx_v7_0_sw_init(struct amdgpu_ip_block *ip_block)
 
 	gfx_v7_0_gpu_early_init(adev);
 
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 0856ff65288c..8a81713d97aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -2023,6 +2023,11 @@ static int gfx_v8_0_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 77f9d5b9a556..c90cbe053ef3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -2292,7 +2292,9 @@ static int gfx_v9_4_3_cp_resume(struct amdgpu_device *adev)
 		r = amdgpu_xcp_init(adev->xcp_mgr, num_xcp, mode);
 
 	} else {
-		if (amdgpu_xcp_query_partition_mode(adev->xcp_mgr,
+		if (adev->in_suspend)
+			amdgpu_xcp_restore_partition_mode(adev->xcp_mgr);
+		else if (amdgpu_xcp_query_partition_mode(adev->xcp_mgr,
 						    AMDGPU_XCP_FL_NONE) ==
 		    AMDGPU_UNKNOWN_COMPUTE_PARTITION_MODE)
 			r = amdgpu_xcp_switch_partition_mode(
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
index baf097d2e1ac..ab0bf880d3d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
@@ -878,6 +878,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_1_dec_ring_vm_funcs = {
 	.get_rptr = jpeg_v5_0_1_dec_ring_get_rptr,
 	.get_wptr = jpeg_v5_0_1_dec_ring_get_wptr,
 	.set_wptr = jpeg_v5_0_1_dec_ring_set_wptr,
+	.parse_cs = amdgpu_jpeg_dec_parse_cs,
 	.emit_frame_size =
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
 		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 64b240b51f1a..a9be7a505026 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -142,13 +142,37 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 	return err;
 }
 
-static int psp_v11_0_wait_for_bootloader(struct psp_context *psp)
+static int psp_v11_wait_for_tos_unload(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
+	uint32_t sol_reg1, sol_reg2;
+	int retry_loop;
 
+	/* Wait for the TOS to be unloaded */
+	for (retry_loop = 0; retry_loop < 20; retry_loop++) {
+		sol_reg1 = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+		usleep_range(1000, 2000);
+		sol_reg2 = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+		if (sol_reg1 == sol_reg2)
+			return 0;
+	}
+	dev_err(adev->dev, "TOS unload failed, C2PMSG_33: %x C2PMSG_81: %x",
+		RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_33),
+		RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81));
+
+	return -ETIME;
+}
+
+static int psp_v11_0_wait_for_bootloader(struct psp_context *psp)
+{
+	struct amdgpu_device *adev = psp->adev;
 	int ret;
 	int retry_loop;
 
+	/* For a reset done at the end of S3, only wait for TOS to be unloaded */
+	if (adev->in_s3 && !(adev->flags & AMD_IS_APU) && amdgpu_in_reset(adev))
+		return psp_v11_wait_for_tos_unload(psp);
+
 	for (retry_loop = 0; retry_loop < 20; retry_loop++) {
 		/* Wait for bootloader to signify that is
 		    ready having bit 31 of C2PMSG_35 set to 1 */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index a65c67cf56ff..f1e7583650c4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -297,16 +297,16 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
 		goto out_err_unreserve;
 	}
 
-	if (properties->ctx_save_restore_area_size != topo_dev->node_props.cwsr_size) {
-		pr_debug("queue cwsr size 0x%x not equal to node cwsr size 0x%x\n",
+	if (properties->ctx_save_restore_area_size < topo_dev->node_props.cwsr_size) {
+		pr_debug("queue cwsr size 0x%x not sufficient for node cwsr size 0x%x\n",
 			properties->ctx_save_restore_area_size,
 			topo_dev->node_props.cwsr_size);
 		err = -EINVAL;
 		goto out_err_unreserve;
 	}
 
-	total_cwsr_size = (topo_dev->node_props.cwsr_size + topo_dev->node_props.debug_memory_size)
-			  * NUM_XCC(pdd->dev->xcc_mask);
+	total_cwsr_size = (properties->ctx_save_restore_area_size +
+			   topo_dev->node_props.debug_memory_size) * NUM_XCC(pdd->dev->xcc_mask);
 	total_cwsr_size = ALIGN(total_cwsr_size, PAGE_SIZE);
 
 	err = kfd_queue_buffer_get(vm, (void *)properties->ctx_save_restore_area_address,
@@ -352,8 +352,8 @@ int kfd_queue_release_buffers(struct kfd_process_device *pdd, struct queue_prope
 	topo_dev = kfd_topology_device_by_id(pdd->dev->id);
 	if (!topo_dev)
 		return -EINVAL;
-	total_cwsr_size = (topo_dev->node_props.cwsr_size + topo_dev->node_props.debug_memory_size)
-			  * NUM_XCC(pdd->dev->xcc_mask);
+	total_cwsr_size = (properties->ctx_save_restore_area_size +
+			   topo_dev->node_props.debug_memory_size) * NUM_XCC(pdd->dev->xcc_mask);
 	total_cwsr_size = ALIGN(total_cwsr_size, PAGE_SIZE);
 
 	kfd_queue_buffer_svm_put(pdd, properties->ctx_save_restore_area_address, total_cwsr_size);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 9d72411c3379..74a1d3e1d52b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3687,6 +3687,8 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm,
 		svm_range_apply_attrs(p, prange, nattr, attrs, &update_mapping);
 		/* TODO: unmap ranges from GPU that lost access */
 	}
+	update_mapping |= !p->xnack_enabled && !list_empty(&remap_list);
+
 	list_for_each_entry_safe(prange, next, &remove_list, update_list) {
 		pr_debug("unlink old 0x%p prange 0x%p [0x%lx 0x%lx]\n",
 			 prange->svms, prange, prange->start,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index bfa3199591b6..91c0188a29b2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3563,6 +3563,7 @@ static int dm_resume(struct amdgpu_ip_block *ip_block)
 	/* Do mst topology probing after resuming cached state*/
 	drm_connector_list_iter_begin(ddev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
+		bool init = false;
 
 		if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
 			continue;
@@ -3572,7 +3573,14 @@ static int dm_resume(struct amdgpu_ip_block *ip_block)
 		    aconnector->mst_root)
 			continue;
 
-		drm_dp_mst_topology_queue_probe(&aconnector->mst_mgr);
+		scoped_guard(mutex, &aconnector->mst_mgr.lock) {
+			init = !aconnector->mst_mgr.mst_primary;
+		}
+		if (init)
+			dm_helpers_dp_mst_start_top_mgr(aconnector->dc_link->ctx,
+				aconnector->dc_link, false);
+		else
+			drm_dp_mst_topology_queue_probe(&aconnector->mst_mgr);
 	}
 	drm_connector_list_iter_end(&iter);
 
@@ -8030,7 +8038,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder,
 				       "mode %dx%d@%dHz is not native, enabling scaling\n",
 				       adjusted_mode->hdisplay, adjusted_mode->vdisplay,
 				       drm_mode_vrefresh(adjusted_mode));
-			dm_new_connector_state->scaling = RMX_FULL;
+			dm_new_connector_state->scaling = RMX_ASPECT;
 		}
 		return 0;
 	}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index f263e1a4537e..00dac862b665 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -1302,7 +1302,8 @@ static int odm_combine_segments_show(struct seq_file *m, void *unused)
 	if (connector->status != connector_status_connected)
 		return -ENODEV;
 
-	if (pipe_ctx != NULL && pipe_ctx->stream_res.tg->funcs->get_odm_combine_segments)
+	if (pipe_ctx && pipe_ctx->stream_res.tg &&
+	    pipe_ctx->stream_res.tg->funcs->get_odm_combine_segments)
 		pipe_ctx->stream_res.tg->funcs->get_odm_combine_segments(pipe_ctx->stream_res.tg, &segments);
 
 	seq_printf(m, "%d\n", segments);
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
index 85303167a553..1173c53359b0 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
@@ -1141,6 +1141,7 @@ static bool detect_link_and_local_sink(struct dc_link *link,
 		    !sink->edid_caps.edid_hdmi)
 			sink->sink_signal = SIGNAL_TYPE_DVI_SINGLE_LINK;
 		else if (dc_is_dvi_signal(sink->sink_signal) &&
+			 dc_is_dvi_signal(link->connector_signal) &&
 			 aud_support->hdmi_audio_native &&
 			 sink->edid_caps.edid_hdmi)
 			sink->sink_signal = SIGNAL_TYPE_HDMI_TYPE_A;
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index ce421bcddcb0..1aae46d703ba 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -1260,6 +1260,17 @@ void mod_freesync_handle_v_update(struct mod_freesync *mod_freesync,
 		update_v_total_for_static_ramp(
 				core_freesync, stream, in_out_vrr);
 	}
+
+	/*
+	 * If VRR is inactive, set vtotal min and max to nominal vtotal
+	 */
+	 if (in_out_vrr->state == VRR_STATE_INACTIVE) {
+		in_out_vrr->adjust.v_total_min =
+			mod_freesync_calc_v_total_from_refresh(stream,
+				in_out_vrr->max_refresh_in_uhz);
+		in_out_vrr->adjust.v_total_max = in_out_vrr->adjust.v_total_min;
+		return;
+	}
 }
 
 unsigned long long mod_freesync_calc_nominal_field_rate(
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 518d07afc7df..bc29a923fa6e 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -195,24 +195,6 @@ int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 	return ret;
 }
 
-int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en)
-{
-	int ret = 0;
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-	if (pp_funcs && pp_funcs->notify_rlc_state) {
-		mutex_lock(&adev->pm.mutex);
-
-		ret = pp_funcs->notify_rlc_state(
-				adev->powerplay.pp_handle,
-				en);
-
-		mutex_unlock(&adev->pm.mutex);
-	}
-
-	return ret;
-}
-
 int amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev)
 {
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index b5fbb0fd1dc0..a7e6d7854b7b 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -4724,14 +4724,14 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 		ret = devm_device_add_group(adev->dev,
 					    &amdgpu_pm_policy_attr_group);
 		if (ret)
-			goto err_out0;
+			goto err_out1;
 	}
 
 	if (amdgpu_dpm_is_temp_metrics_supported(adev, SMU_TEMP_METRIC_GPUBOARD)) {
 		ret = devm_device_add_group(adev->dev,
 					    &amdgpu_board_attr_group);
 		if (ret)
-			goto err_out0;
+			goto err_out1;
 		if (amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MAXNODEPOWERLIMIT,
 						 (void *)&tmp) != -EOPNOTSUPP) {
 			sysfs_add_file_to_group(&adev->dev->kobj,
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index 65c1d98af26c..af48aead12f7 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -424,8 +424,6 @@ int amdgpu_dpm_mode1_reset(struct amdgpu_device *adev);
 int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 			     enum pp_mp1_state mp1_state);
 
-int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en);
-
 int amdgpu_dpm_set_gfx_power_up_by_imu(struct amdgpu_device *adev);
 
 int amdgpu_dpm_baco_exit(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index fb8086859857..244b8c364d45 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -2040,6 +2040,12 @@ static int smu_disable_dpms(struct smu_context *smu)
 	    smu->is_apu && (amdgpu_in_reset(adev) || adev->in_s0ix))
 		return 0;
 
+	/* vangogh s0ix */
+	if ((amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(11, 5, 0) ||
+	     amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(11, 5, 2)) &&
+	    adev->in_s0ix)
+		return 0;
+
 	/*
 	 * For gpu reset, runpm and hibernation through BACO,
 	 * BACO feature has to be kept enabled.
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 2c9869feba61..0708d0f0938b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -2217,6 +2217,9 @@ static int vangogh_post_smu_init(struct smu_context *smu)
 	uint32_t total_cu = adev->gfx.config.max_cu_per_sh *
 		adev->gfx.config.max_sh_per_se * adev->gfx.config.max_shader_engines;
 
+	if (adev->in_s0ix)
+		return 0;
+
 	/* allow message will be sent after enable message on Vangogh*/
 	if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_GFXCLK_BIT) &&
 			(adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
diff --git a/drivers/gpu/drm/clients/drm_client_setup.c b/drivers/gpu/drm/clients/drm_client_setup.c
index 72480db1f00d..515aceac22b1 100644
--- a/drivers/gpu/drm/clients/drm_client_setup.c
+++ b/drivers/gpu/drm/clients/drm_client_setup.c
@@ -13,8 +13,8 @@
 static char drm_client_default[16] = CONFIG_DRM_CLIENT_DEFAULT;
 module_param_string(active, drm_client_default, sizeof(drm_client_default), 0444);
 MODULE_PARM_DESC(active,
-		 "Choose which drm client to start, default is"
-		 CONFIG_DRM_CLIENT_DEFAULT "]");
+		 "Choose which drm client to start, default is "
+		 CONFIG_DRM_CLIENT_DEFAULT);
 
 /**
  * drm_client_setup() - Setup in-kernel DRM clients
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index e58c0c158b3a..b91575380708 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -413,7 +413,7 @@ obj-$(CONFIG_DRM_I915_GVT_KVMGT) += kvmgt.o
 #
 # Enable locally for CONFIG_DRM_I915_WERROR=y. See also scripts/Makefile.build
 ifdef CONFIG_DRM_I915_WERROR
-    cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none -Werror $<
+    cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none -Werror $<
 endif
 
 # header test
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 10eb93a34cf2..4619237f1346 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -585,6 +585,10 @@ static void _panel_replay_init_dpcd(struct intel_dp *intel_dp)
 	struct intel_display *display = to_intel_display(intel_dp);
 	int ret;
 
+	/* TODO: Enable Panel Replay on MST once it's properly implemented. */
+	if (intel_dp->mst_detect == DRM_DP_MST)
+		return;
+
 	ret = drm_dp_dpcd_read_data(&intel_dp->aux, DP_PANEL_REPLAY_CAP_SUPPORT,
 				    &intel_dp->pr_dpcd, sizeof(intel_dp->pr_dpcd));
 	if (ret < 0)
@@ -888,7 +892,8 @@ static bool is_dc5_dc6_blocked(struct intel_dp *intel_dp)
 {
 	struct intel_display *display = to_intel_display(intel_dp);
 	u32 current_dc_state = intel_display_power_get_current_dc_state(display);
-	struct drm_vblank_crtc *vblank = &display->drm->vblank[intel_dp->psr.pipe];
+	struct intel_crtc *crtc = intel_crtc_for_pipe(display, intel_dp->psr.pipe);
+	struct drm_vblank_crtc *vblank = drm_crtc_vblank_crtc(&crtc->base);
 
 	return (current_dc_state != DC_STATE_EN_UPTO_DC5 &&
 		current_dc_state != DC_STATE_EN_UPTO_DC6) ||
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
index 88b147fa5cb1..c90b35881a26 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
@@ -205,7 +205,7 @@ static u64 div_u64_roundup(u64 nom, u32 den)
 
 u64 intel_gt_clock_interval_to_ns(const struct intel_gt *gt, u64 count)
 {
-	return div_u64_roundup(count * NSEC_PER_SEC, gt->clock_frequency);
+	return mul_u64_u32_div(count, NSEC_PER_SEC, gt->clock_frequency);
 }
 
 u64 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u64 count)
@@ -215,7 +215,7 @@ u64 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u64 count)
 
 u64 intel_gt_ns_to_clock_interval(const struct intel_gt *gt, u64 ns)
 {
-	return div_u64_roundup(gt->clock_frequency * ns, NSEC_PER_SEC);
+	return mul_u64_u32_div(ns, gt->clock_frequency, NSEC_PER_SEC);
 }
 
 u64 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u64 ns)
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 25e97031d76e..30d5889fc809 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -1595,8 +1595,20 @@ err_unlock:
 err_vma_res:
 	i915_vma_resource_free(vma_res);
 err_fence:
-	if (work)
-		dma_fence_work_commit_imm(&work->base);
+	if (work) {
+		/*
+		 * When pinning VMA to GGTT on CHV or BXT with VTD enabled,
+		 * commit VMA binding asynchronously to avoid risk of lock
+		 * inversion among reservation_ww locks held here and
+		 * cpu_hotplug_lock acquired from stop_machine(), which we
+		 * wrap around GGTT updates when running in those environments.
+		 */
+		if (i915_vma_is_ggtt(vma) &&
+		    intel_vm_no_concurrent_access_wa(vma->vm->i915))
+			dma_fence_work_commit(&work->base);
+		else
+			dma_fence_work_commit_imm(&work->base);
+	}
 err_rpm:
 	intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);
 
diff --git a/drivers/gpu/drm/imagination/Kconfig b/drivers/gpu/drm/imagination/Kconfig
index 682dd2633d0c..0482bfcefdde 100644
--- a/drivers/gpu/drm/imagination/Kconfig
+++ b/drivers/gpu/drm/imagination/Kconfig
@@ -7,6 +7,7 @@ config DRM_POWERVR
 	depends on DRM
 	depends on MMU
 	depends on PM
+	depends on POWER_SEQUENCING || !POWER_SEQUENCING
 	select DRM_EXEC
 	select DRM_GEM_SHMEM_HELPER
 	select DRM_SCHED
diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c
index bc7527542fdc..c4c6d0249df5 100644
--- a/drivers/gpu/drm/mediatek/mtk_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_crtc.c
@@ -283,6 +283,10 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg)
 	unsigned int i;
 	unsigned long flags;
 
+	/* release GCE HW usage and start autosuspend */
+	pm_runtime_mark_last_busy(cmdq_cl->chan->mbox->dev);
+	pm_runtime_put_autosuspend(cmdq_cl->chan->mbox->dev);
+
 	if (data->sta < 0)
 		return;
 
@@ -618,6 +622,9 @@ static void mtk_crtc_update_config(struct mtk_crtc *mtk_crtc, bool needs_vblank)
 		mtk_crtc->config_updating = false;
 		spin_unlock_irqrestore(&mtk_crtc->config_lock, flags);
 
+		if (pm_runtime_resume_and_get(mtk_crtc->cmdq_client.chan->mbox->dev) < 0)
+			goto update_config_out;
+
 		mbox_send_message(mtk_crtc->cmdq_client.chan, cmdq_handle);
 		mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0);
 		goto update_config_out;
diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c
index 02349bd44001..788b52c1d10c 100644
--- a/drivers/gpu/drm/mediatek/mtk_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_plane.c
@@ -21,9 +21,6 @@
 
 static const u64 modifiers[] = {
 	DRM_FORMAT_MOD_LINEAR,
-	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
-				AFBC_FORMAT_MOD_SPLIT |
-				AFBC_FORMAT_MOD_SPARSE),
 	DRM_FORMAT_MOD_INVALID,
 };
 
@@ -71,26 +68,7 @@ static bool mtk_plane_format_mod_supported(struct drm_plane *plane,
 					   uint32_t format,
 					   uint64_t modifier)
 {
-	if (modifier == DRM_FORMAT_MOD_LINEAR)
-		return true;
-
-	if (modifier != DRM_FORMAT_MOD_ARM_AFBC(
-				AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
-				AFBC_FORMAT_MOD_SPLIT |
-				AFBC_FORMAT_MOD_SPARSE))
-		return false;
-
-	if (format != DRM_FORMAT_XRGB8888 &&
-	    format != DRM_FORMAT_ARGB8888 &&
-	    format != DRM_FORMAT_BGRX8888 &&
-	    format != DRM_FORMAT_BGRA8888 &&
-	    format != DRM_FORMAT_ABGR8888 &&
-	    format != DRM_FORMAT_XBGR8888 &&
-	    format != DRM_FORMAT_RGB888 &&
-	    format != DRM_FORMAT_BGR888)
-		return false;
-
-	return true;
+	return modifier == DRM_FORMAT_MOD_LINEAR;
 }
 
 static void mtk_plane_destroy_state(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index e97e39abf3a2..12b1dba8e05d 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2867,7 +2867,9 @@ nv50_display_create(struct drm_device *dev)
 	}
 
 	/* Assign the correct format modifiers */
-	if (disp->disp->object.oclass >= TU102_DISP)
+	if (disp->disp->object.oclass >= GB202_DISP)
+		nouveau_display(dev)->format_modifiers = wndwca7e_modifiers;
+	else if (disp->disp->object.oclass >= TU102_DISP)
 		nouveau_display(dev)->format_modifiers = wndwc57e_modifiers;
 	else
 	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_FERMI)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h
index 15f9242b72ac..5d998f0319dc 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h
@@ -104,4 +104,5 @@ struct nouveau_encoder *nv50_real_outp(struct drm_encoder *encoder);
 extern const u64 disp50xx_modifiers[];
 extern const u64 disp90xx_modifiers[];
 extern const u64 wndwc57e_modifiers[];
+extern const u64 wndwca7e_modifiers[];
 #endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index e2c55f4b9c5a..ef9e410babbf 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -786,13 +786,14 @@ nv50_wndw_destroy(struct drm_plane *plane)
 }
 
 /* This function assumes the format has already been validated against the plane
- * and the modifier was validated against the device-wides modifier list at FB
+ * and the modifier was validated against the device-wide modifier list at FB
  * creation time.
  */
 static bool nv50_plane_format_mod_supported(struct drm_plane *plane,
 					    u32 format, u64 modifier)
 {
 	struct nouveau_drm *drm = nouveau_drm(plane->dev);
+	const struct drm_format_info *info = drm_format_info(format);
 	uint8_t i;
 
 	/* All chipsets can display all formats in linear layout */
@@ -800,13 +801,32 @@ static bool nv50_plane_format_mod_supported(struct drm_plane *plane,
 		return true;
 
 	if (drm->client.device.info.chipset < 0xc0) {
-		const struct drm_format_info *info = drm_format_info(format);
 		const uint8_t kind = (modifier >> 12) & 0xff;
 
 		if (!format) return false;
 
 		for (i = 0; i < info->num_planes; i++)
 			if ((info->cpp[i] != 4) && kind != 0x70) return false;
+	} else if (drm->client.device.info.chipset >= 0x1b2) {
+		const uint8_t slayout = ((modifier >> 22) & 0x1) |
+			((modifier >> 25) & 0x6);
+
+		if (!format)
+			return false;
+
+		/*
+		 * Note in practice this implies only formats where cpp is equal
+		 * for each plane, or >= 4 for all planes, are supported.
+		 */
+		for (i = 0; i < info->num_planes; i++) {
+			if (((info->cpp[i] == 2) && slayout != 3) ||
+			    ((info->cpp[i] == 1) && slayout != 2) ||
+			    ((info->cpp[i] >= 4) && slayout != 1))
+				return false;
+
+			/* 24-bit not supported. It has yet another layout */
+			WARN_ON(info->cpp[i] == 3);
+		}
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c
index 0d8e9a9d1a57..2cec8cfbd546 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c
@@ -179,6 +179,39 @@ wndwca7e_ntfy_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 	return 0;
 }
 
+/****************************************************************
+ *            Log2(block height) ----------------------------+  *
+ *            Page Kind ----------------------------------+  |  *
+ *            Gob Height/Page Kind Generation ------+     |  |  *
+ *                          Sector layout -------+  |     |  |  *
+ *                          Compression ------+  |  |     |  |  */
+const u64 wndwca7e_modifiers[] = { /*         |  |  |     |  |  */
+	/* 4cpp+ modifiers */
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 0),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 1),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 2),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 3),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 4),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 5),
+	/* 1cpp/8bpp modifiers */
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 0),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 1),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 2),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 3),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 4),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 5),
+	/* 2cpp/16bpp modifiers */
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 0),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 1),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 2),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 3),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 4),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 5),
+	/* All formats support linear */
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID
+};
+
 static const struct nv50_wndw_func
 wndwca7e = {
 	.acquire = wndwc37e_acquire,
diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c
index 156c7a0b62a2..3f43686f0195 100644
--- a/drivers/gpu/drm/panthor/panthor_gem.c
+++ b/drivers/gpu/drm/panthor/panthor_gem.c
@@ -288,6 +288,23 @@ panthor_gem_create_with_handle(struct drm_file *file,
 
 	panthor_gem_debugfs_set_usage_flags(bo, 0);
 
+	/* If this is a write-combine mapping, we query the sgt to force a CPU
+	 * cache flush (dma_map_sgtable() is called when the sgt is created).
+	 * This ensures the zero-ing is visible to any uncached mapping created
+	 * by vmap/mmap.
+	 * FIXME: Ideally this should be done when pages are allocated, not at
+	 * BO creation time.
+	 */
+	if (shmem->map_wc) {
+		struct sg_table *sgt;
+
+		sgt = drm_gem_shmem_get_pages_sgt(shmem);
+		if (IS_ERR(sgt)) {
+			ret = PTR_ERR(sgt);
+			goto out_put_gem;
+		}
+	}
+
 	/*
 	 * Allocate an id of idr table where the obj is registered
 	 * and handle has the id what user can see.
@@ -296,6 +313,7 @@ panthor_gem_create_with_handle(struct drm_file *file,
 	if (!ret)
 		*size = bo->base.base.size;
 
+out_put_gem:
 	/* drop reference from allocate - handle holds it now. */
 	drm_gem_object_put(&shmem->base);
 
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index c8e949f4a568..fe174a4857be 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -173,26 +173,15 @@ int drm_sched_entity_error(struct drm_sched_entity *entity)
 }
 EXPORT_SYMBOL(drm_sched_entity_error);
 
+static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
+					  struct dma_fence_cb *cb);
+
 static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk)
 {
 	struct drm_sched_job *job = container_of(wrk, typeof(*job), work);
-
-	drm_sched_fence_scheduled(job->s_fence, NULL);
-	drm_sched_fence_finished(job->s_fence, -ESRCH);
-	WARN_ON(job->s_fence->parent);
-	job->sched->ops->free_job(job);
-}
-
-/* Signal the scheduler finished fence when the entity in question is killed. */
-static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
-					  struct dma_fence_cb *cb)
-{
-	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
-						 finish_cb);
+	struct dma_fence *f;
 	unsigned long index;
 
-	dma_fence_put(f);
-
 	/* Wait for all dependencies to avoid data corruptions */
 	xa_for_each(&job->dependencies, index, f) {
 		struct drm_sched_fence *s_fence = to_drm_sched_fence(f);
@@ -220,6 +209,21 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 		dma_fence_put(f);
 	}
 
+	drm_sched_fence_scheduled(job->s_fence, NULL);
+	drm_sched_fence_finished(job->s_fence, -ESRCH);
+	WARN_ON(job->s_fence->parent);
+	job->sched->ops->free_job(job);
+}
+
+/* Signal the scheduler finished fence when the entity in question is killed. */
+static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
+					  struct dma_fence_cb *cb)
+{
+	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
+						 finish_cb);
+
+	dma_fence_put(f);
+
 	INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work);
 	schedule_work(&job->work);
 }
diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index 7d9e85e932d7..f0e72d4b6a47 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -85,6 +85,7 @@ config DRM_PANEL_MIPI_DBI
 config DRM_PIXPAPER
         tristate "DRM support for PIXPAPER display panels"
         depends on DRM && SPI
+        depends on MMU
         select DRM_CLIENT_SELECTION
         select DRM_GEM_SHMEM_HELPER
         select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c
index 718832b08d96..c46f17ba7236 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c
@@ -100,8 +100,10 @@ vmw_cursor_update_type(struct vmw_private *vmw, struct vmw_plane_state *vps)
 	if (vmw->has_mob) {
 		if ((vmw->capabilities2 & SVGA_CAP2_CURSOR_MOB) != 0)
 			return VMW_CURSOR_UPDATE_MOB;
+		else
+			return VMW_CURSOR_UPDATE_GB_ONLY;
 	}
-
+	drm_warn_once(&vmw->drm, "Unknown Cursor Type!\n");
 	return VMW_CURSOR_UPDATE_NONE;
 }
 
@@ -139,6 +141,7 @@ static u32 vmw_cursor_mob_size(enum vmw_cursor_update_type update_type,
 {
 	switch (update_type) {
 	case VMW_CURSOR_UPDATE_LEGACY:
+	case VMW_CURSOR_UPDATE_GB_ONLY:
 	case VMW_CURSOR_UPDATE_NONE:
 		return 0;
 	case VMW_CURSOR_UPDATE_MOB:
@@ -623,6 +626,7 @@ int vmw_cursor_plane_prepare_fb(struct drm_plane *plane,
 		if (!surface || vps->cursor.legacy.id == surface->snooper.id)
 			vps->cursor.update_type = VMW_CURSOR_UPDATE_NONE;
 		break;
+	case VMW_CURSOR_UPDATE_GB_ONLY:
 	case VMW_CURSOR_UPDATE_MOB: {
 		bo = vmw_user_object_buffer(&vps->uo);
 		if (bo) {
@@ -737,6 +741,7 @@ void
 vmw_cursor_plane_atomic_update(struct drm_plane *plane,
 			       struct drm_atomic_state *state)
 {
+	struct vmw_bo *bo;
 	struct drm_plane_state *new_state =
 		drm_atomic_get_new_plane_state(state, plane);
 	struct drm_plane_state *old_state =
@@ -762,6 +767,15 @@ vmw_cursor_plane_atomic_update(struct drm_plane *plane,
 	case VMW_CURSOR_UPDATE_MOB:
 		vmw_cursor_update_mob(dev_priv, vps);
 		break;
+	case VMW_CURSOR_UPDATE_GB_ONLY:
+		bo = vmw_user_object_buffer(&vps->uo);
+		if (bo)
+			vmw_send_define_cursor_cmd(dev_priv, bo->map.virtual,
+						   vps->base.crtc_w,
+						   vps->base.crtc_h,
+						   vps->base.hotspot_x,
+						   vps->base.hotspot_y);
+		break;
 	case VMW_CURSOR_UPDATE_NONE:
 		/* do nothing */
 		break;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.h b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.h
index 40694925a70e..0c2cc0699b0d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.h
@@ -33,6 +33,7 @@ static const u32 __maybe_unused vmw_cursor_plane_formats[] = {
 enum vmw_cursor_update_type {
 	VMW_CURSOR_UPDATE_NONE = 0,
 	VMW_CURSOR_UPDATE_LEGACY,
+	VMW_CURSOR_UPDATE_GB_ONLY,
 	VMW_CURSOR_UPDATE_MOB,
 };
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index d539f25b5fbe..3057f8baa7d2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -3668,6 +3668,11 @@ static int vmw_cmd_check(struct vmw_private *dev_priv,
 
 
 	cmd_id = header->id;
+	if (header->size > SVGA_CMD_MAX_DATASIZE) {
+		VMW_DEBUG_USER("SVGA3D command: %d is too big.\n",
+			       cmd_id + SVGA_3D_CMD_BASE);
+		return -E2BIG;
+	}
 	*size = header->size + sizeof(SVGA3dCmdHeader);
 
 	cmd_id -= SVGA_3D_CMD_BASE;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
index 7de20e56082c..fd4e76486f2d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
@@ -32,22 +32,22 @@ enum vmw_bo_dirty_method {
 
 /**
  * struct vmw_bo_dirty - Dirty information for buffer objects
+ * @ref_count: Reference count for this structure. Must be first member!
  * @start: First currently dirty bit
  * @end: Last currently dirty bit + 1
  * @method: The currently used dirty method
  * @change_count: Number of consecutive method change triggers
- * @ref_count: Reference count for this structure
  * @bitmap_size: The size of the bitmap in bits. Typically equal to the
  * nuber of pages in the bo.
  * @bitmap: A bitmap where each bit represents a page. A set bit means a
  * dirty page.
  */
 struct vmw_bo_dirty {
+	struct   kref ref_count;
 	unsigned long start;
 	unsigned long end;
 	enum vmw_bo_dirty_method method;
 	unsigned int change_count;
-	unsigned int ref_count;
 	unsigned long bitmap_size;
 	unsigned long bitmap[];
 };
@@ -221,7 +221,7 @@ int vmw_bo_dirty_add(struct vmw_bo *vbo)
 	int ret;
 
 	if (dirty) {
-		dirty->ref_count++;
+		kref_get(&dirty->ref_count);
 		return 0;
 	}
 
@@ -235,7 +235,7 @@ int vmw_bo_dirty_add(struct vmw_bo *vbo)
 	dirty->bitmap_size = num_pages;
 	dirty->start = dirty->bitmap_size;
 	dirty->end = 0;
-	dirty->ref_count = 1;
+	kref_init(&dirty->ref_count);
 	if (num_pages < PAGE_SIZE / sizeof(pte_t)) {
 		dirty->method = VMW_BO_DIRTY_PAGETABLE;
 	} else {
@@ -274,10 +274,8 @@ void vmw_bo_dirty_release(struct vmw_bo *vbo)
 {
 	struct vmw_bo_dirty *dirty = vbo->dirty;
 
-	if (dirty && --dirty->ref_count == 0) {
-		kvfree(dirty);
+	if (dirty && kref_put(&dirty->ref_count, (void *)kvfree))
 		vbo->dirty = NULL;
-	}
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index 51f2a03847f9..f680c8b8f258 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -168,6 +168,7 @@
 
 #define XEHP_SLICE_COMMON_ECO_CHICKEN1		XE_REG_MCR(0x731c, XE_REG_OPTION_MASKED)
 #define   MSC_MSAA_REODER_BUF_BYPASS_DISABLE	REG_BIT(14)
+#define   FAST_CLEAR_VALIGN_FIX			REG_BIT(13)
 
 #define XE2LPM_CCCHKNREG1			XE_REG(0x82a8)
 
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 34d33965eac2..456899238377 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -988,16 +988,16 @@ void xe_device_shutdown(struct xe_device *xe)
 
 	drm_dbg(&xe->drm, "Shutting down device\n");
 
-	if (xe_driver_flr_disabled(xe)) {
-		xe_display_pm_shutdown(xe);
+	xe_display_pm_shutdown(xe);
 
-		xe_irq_suspend(xe);
+	xe_irq_suspend(xe);
 
-		for_each_gt(gt, xe, id)
-			xe_gt_shutdown(gt);
+	for_each_gt(gt, xe, id)
+		xe_gt_shutdown(gt);
 
-		xe_display_pm_shutdown_late(xe);
-	} else {
+	xe_display_pm_shutdown_late(xe);
+
+	if (!xe_driver_flr_disabled(xe)) {
 		/* BOOM! */
 		__xe_driver_flr(xe);
 	}
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 7715e74bb945..a8ab363a8046 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -165,7 +165,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 	for (num_syncs = 0; num_syncs < args->num_syncs; num_syncs++) {
 		err = xe_sync_entry_parse(xe, xef, &syncs[num_syncs],
-					  &syncs_user[num_syncs], SYNC_PARSE_FLAG_EXEC |
+					  &syncs_user[num_syncs], NULL, 0,
+					  SYNC_PARSE_FLAG_EXEC |
 					  (xe_vm_in_lr_mode(vm) ?
 					   SYNC_PARSE_FLAG_LR_MODE : 0));
 		if (err)
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 37b2b93b73d6..cb5f204c08ed 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -10,6 +10,7 @@
 #include <drm/drm_device.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
+#include <drm/drm_syncobj.h>
 #include <uapi/drm/xe_drm.h>
 
 #include "xe_dep_scheduler.h"
@@ -324,6 +325,16 @@ struct xe_exec_queue *xe_exec_queue_create_bind(struct xe_device *xe,
 	}
 	xe_vm_put(migrate_vm);
 
+	if (!IS_ERR(q)) {
+		int err = drm_syncobj_create(&q->ufence_syncobj,
+					     DRM_SYNCOBJ_CREATE_SIGNALED,
+					     NULL);
+		if (err) {
+			xe_exec_queue_put(q);
+			return ERR_PTR(err);
+		}
+	}
+
 	return q;
 }
 ALLOW_ERROR_INJECTION(xe_exec_queue_create_bind, ERRNO);
@@ -333,6 +344,9 @@ void xe_exec_queue_destroy(struct kref *ref)
 	struct xe_exec_queue *q = container_of(ref, struct xe_exec_queue, refcount);
 	struct xe_exec_queue *eq, *next;
 
+	if (q->ufence_syncobj)
+		drm_syncobj_put(q->ufence_syncobj);
+
 	if (xe_exec_queue_uses_pxp(q))
 		xe_pxp_exec_queue_remove(gt_to_xe(q->gt)->pxp, q);
 
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 27b76cf9da89..df1c69dc81f1 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -15,6 +15,7 @@
 #include "xe_hw_fence_types.h"
 #include "xe_lrc_types.h"
 
+struct drm_syncobj;
 struct xe_execlist_exec_queue;
 struct xe_gt;
 struct xe_guc_exec_queue;
@@ -155,6 +156,12 @@ struct xe_exec_queue {
 		struct list_head link;
 	} pxp;
 
+	/** @ufence_syncobj: User fence syncobj */
+	struct drm_syncobj *ufence_syncobj;
+
+	/** @ufence_timeline_value: User fence timeline value */
+	u64 ufence_timeline_value;
+
 	/** @ops: submission backend exec queue operations */
 	const struct xe_exec_queue_ops *ops;
 
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 18f6327bf552..283d846c3512 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -200,6 +200,9 @@ static void guc_ct_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc_ct *ct = arg;
 
+#if IS_ENABLED(CONFIG_DRM_XE_DEBUG)
+	cancel_work_sync(&ct->dead.worker);
+#endif
 	ct_exit_safe_mode(ct);
 	destroy_workqueue(ct->g2h_wq);
 	xa_destroy(&ct->fence_lookup);
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index a4894eb0d7f3..125698a9ecf1 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -10,6 +10,7 @@
 
 #include <drm/drm_drv.h>
 #include <drm/drm_managed.h>
+#include <drm/drm_syncobj.h>
 #include <uapi/drm/xe_drm.h>
 
 #include <generated/xe_wa_oob.h>
@@ -1389,7 +1390,9 @@ static int xe_oa_user_extensions(struct xe_oa *oa, enum xe_oa_user_extn_from fro
 	return 0;
 }
 
-static int xe_oa_parse_syncs(struct xe_oa *oa, struct xe_oa_open_param *param)
+static int xe_oa_parse_syncs(struct xe_oa *oa,
+			     struct xe_oa_stream *stream,
+			     struct xe_oa_open_param *param)
 {
 	int ret, num_syncs, num_ufence = 0;
 
@@ -1409,7 +1412,9 @@ static int xe_oa_parse_syncs(struct xe_oa *oa, struct xe_oa_open_param *param)
 
 	for (num_syncs = 0; num_syncs < param->num_syncs; num_syncs++) {
 		ret = xe_sync_entry_parse(oa->xe, param->xef, &param->syncs[num_syncs],
-					  &param->syncs_user[num_syncs], 0);
+					  &param->syncs_user[num_syncs],
+					  stream->ufence_syncobj,
+					  ++stream->ufence_timeline_value, 0);
 		if (ret)
 			goto err_syncs;
 
@@ -1539,7 +1544,7 @@ static long xe_oa_config_locked(struct xe_oa_stream *stream, u64 arg)
 		return -ENODEV;
 
 	param.xef = stream->xef;
-	err = xe_oa_parse_syncs(stream->oa, &param);
+	err = xe_oa_parse_syncs(stream->oa, stream, &param);
 	if (err)
 		goto err_config_put;
 
@@ -1635,6 +1640,7 @@ static void xe_oa_destroy_locked(struct xe_oa_stream *stream)
 	if (stream->exec_q)
 		xe_exec_queue_put(stream->exec_q);
 
+	drm_syncobj_put(stream->ufence_syncobj);
 	kfree(stream);
 }
 
@@ -1826,6 +1832,7 @@ static int xe_oa_stream_open_ioctl_locked(struct xe_oa *oa,
 					  struct xe_oa_open_param *param)
 {
 	struct xe_oa_stream *stream;
+	struct drm_syncobj *ufence_syncobj;
 	int stream_fd;
 	int ret;
 
@@ -1836,17 +1843,31 @@ static int xe_oa_stream_open_ioctl_locked(struct xe_oa *oa,
 		goto exit;
 	}
 
+	ret = drm_syncobj_create(&ufence_syncobj, DRM_SYNCOBJ_CREATE_SIGNALED,
+				 NULL);
+	if (ret)
+		goto exit;
+
 	stream = kzalloc(sizeof(*stream), GFP_KERNEL);
 	if (!stream) {
 		ret = -ENOMEM;
-		goto exit;
+		goto err_syncobj;
 	}
-
+	stream->ufence_syncobj = ufence_syncobj;
 	stream->oa = oa;
-	ret = xe_oa_stream_init(stream, param);
+
+	ret = xe_oa_parse_syncs(oa, stream, param);
 	if (ret)
 		goto err_free;
 
+	ret = xe_oa_stream_init(stream, param);
+	if (ret) {
+		while (param->num_syncs--)
+			xe_sync_entry_cleanup(&param->syncs[param->num_syncs]);
+		kfree(param->syncs);
+		goto err_free;
+	}
+
 	if (!param->disabled) {
 		ret = xe_oa_enable_locked(stream);
 		if (ret)
@@ -1870,6 +1891,8 @@ err_destroy:
 	xe_oa_stream_destroy(stream);
 err_free:
 	kfree(stream);
+err_syncobj:
+	drm_syncobj_put(ufence_syncobj);
 exit:
 	return ret;
 }
@@ -2083,22 +2106,14 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 		goto err_exec_q;
 	}
 
-	ret = xe_oa_parse_syncs(oa, &param);
-	if (ret)
-		goto err_exec_q;
-
 	mutex_lock(&param.hwe->gt->oa.gt_lock);
 	ret = xe_oa_stream_open_ioctl_locked(oa, &param);
 	mutex_unlock(&param.hwe->gt->oa.gt_lock);
 	if (ret < 0)
-		goto err_sync_cleanup;
+		goto err_exec_q;
 
 	return ret;
 
-err_sync_cleanup:
-	while (param.num_syncs--)
-		xe_sync_entry_cleanup(&param.syncs[param.num_syncs]);
-	kfree(param.syncs);
 err_exec_q:
 	if (param.exec_q)
 		xe_exec_queue_put(param.exec_q);
diff --git a/drivers/gpu/drm/xe/xe_oa_types.h b/drivers/gpu/drm/xe/xe_oa_types.h
index 2628f78c4e8d..daf701b5d48b 100644
--- a/drivers/gpu/drm/xe/xe_oa_types.h
+++ b/drivers/gpu/drm/xe/xe_oa_types.h
@@ -15,6 +15,8 @@
 #include "regs/xe_reg_defs.h"
 #include "xe_hw_engine_types.h"
 
+struct drm_syncobj;
+
 #define DEFAULT_XE_OA_BUFFER_SIZE SZ_16M
 
 enum xe_oa_report_header {
@@ -248,6 +250,12 @@ struct xe_oa_stream {
 	/** @xef: xe_file with which the stream was opened */
 	struct xe_file *xef;
 
+	/** @ufence_syncobj: User fence syncobj */
+	struct drm_syncobj *ufence_syncobj;
+
+	/** @ufence_timeline_value: User fence timeline value */
+	u64 ufence_timeline_value;
+
 	/** @last_fence: fence to use in stream destroy when needed */
 	struct dma_fence *last_fence;
 
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index 82872a51f098..d48ab7b32ca5 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -113,6 +113,8 @@ static void user_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 			struct xe_sync_entry *sync,
 			struct drm_xe_sync __user *sync_user,
+			struct drm_syncobj *ufence_syncobj,
+			u64 ufence_timeline_value,
 			unsigned int flags)
 {
 	struct drm_xe_sync sync_in;
@@ -192,10 +194,15 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 		if (exec) {
 			sync->addr = sync_in.addr;
 		} else {
+			sync->ufence_timeline_value = ufence_timeline_value;
 			sync->ufence = user_fence_create(xe, sync_in.addr,
 							 sync_in.timeline_value);
 			if (XE_IOCTL_DBG(xe, IS_ERR(sync->ufence)))
 				return PTR_ERR(sync->ufence);
+			sync->ufence_chain_fence = dma_fence_chain_alloc();
+			if (!sync->ufence_chain_fence)
+				return -ENOMEM;
+			sync->ufence_syncobj = ufence_syncobj;
 		}
 
 		break;
@@ -239,7 +246,12 @@ void xe_sync_entry_signal(struct xe_sync_entry *sync, struct dma_fence *fence)
 	} else if (sync->ufence) {
 		int err;
 
-		dma_fence_get(fence);
+		drm_syncobj_add_point(sync->ufence_syncobj,
+				      sync->ufence_chain_fence,
+				      fence, sync->ufence_timeline_value);
+		sync->ufence_chain_fence = NULL;
+
+		fence = drm_syncobj_fence_get(sync->ufence_syncobj);
 		user_fence_get(sync->ufence);
 		err = dma_fence_add_callback(fence, &sync->ufence->cb,
 					     user_fence_cb);
@@ -259,7 +271,8 @@ void xe_sync_entry_cleanup(struct xe_sync_entry *sync)
 		drm_syncobj_put(sync->syncobj);
 	dma_fence_put(sync->fence);
 	dma_fence_chain_free(sync->chain_fence);
-	if (sync->ufence)
+	dma_fence_chain_free(sync->ufence_chain_fence);
+	if (!IS_ERR_OR_NULL(sync->ufence))
 		user_fence_put(sync->ufence);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_sync.h b/drivers/gpu/drm/xe/xe_sync.h
index 256ffc1e54dc..51f2d803e977 100644
--- a/drivers/gpu/drm/xe/xe_sync.h
+++ b/drivers/gpu/drm/xe/xe_sync.h
@@ -8,6 +8,7 @@
 
 #include "xe_sync_types.h"
 
+struct drm_syncobj;
 struct xe_device;
 struct xe_exec_queue;
 struct xe_file;
@@ -21,6 +22,8 @@ struct xe_vm;
 int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 			struct xe_sync_entry *sync,
 			struct drm_xe_sync __user *sync_user,
+			struct drm_syncobj *ufence_syncobj,
+			u64 ufence_timeline_value,
 			unsigned int flags);
 int xe_sync_entry_add_deps(struct xe_sync_entry *sync,
 			   struct xe_sched_job *job);
diff --git a/drivers/gpu/drm/xe/xe_sync_types.h b/drivers/gpu/drm/xe/xe_sync_types.h
index 30ac3f51993b..b88f1833e28c 100644
--- a/drivers/gpu/drm/xe/xe_sync_types.h
+++ b/drivers/gpu/drm/xe/xe_sync_types.h
@@ -18,9 +18,12 @@ struct xe_sync_entry {
 	struct drm_syncobj *syncobj;
 	struct dma_fence *fence;
 	struct dma_fence_chain *chain_fence;
+	struct dma_fence_chain *ufence_chain_fence;
+	struct drm_syncobj *ufence_syncobj;
 	struct xe_user_fence *ufence;
 	u64 addr;
 	u64 timeline_value;
+	u64 ufence_timeline_value;
 	u32 type;
 	u32 flags;
 };
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 63c65e3d207b..ccb09ef4ec9e 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3606,8 +3606,12 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 	syncs_user = u64_to_user_ptr(args->syncs);
 	for (num_syncs = 0; num_syncs < args->num_syncs; num_syncs++) {
+		struct xe_exec_queue *__q = q ?: vm->q[0];
+
 		err = xe_sync_entry_parse(xe, xef, &syncs[num_syncs],
 					  &syncs_user[num_syncs],
+					  __q->ufence_syncobj,
+					  ++__q->ufence_timeline_value,
 					  (xe_vm_in_lr_mode(vm) ?
 					   SYNC_PARSE_FLAG_LR_MODE : 0) |
 					  (!args->num_binds ?
diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index cd03891654a1..3cf30718b200 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -679,6 +679,8 @@ static const struct xe_rtp_entry_sr engine_was[] = {
 	},
 	{ XE_RTP_NAME("14023061436"),
 	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3001),
+		       FUNC(xe_rtp_match_first_render_or_compute), OR,
+		       GRAPHICS_VERSION_RANGE(3003, 3005),
 		       FUNC(xe_rtp_match_first_render_or_compute)),
 	  XE_RTP_ACTIONS(SET(TDL_CHICKEN, QID_WAIT_FOR_THREAD_NOT_RUN_DISABLE))
 	},
@@ -916,6 +918,15 @@ static const struct xe_rtp_entry_sr lrc_was[] = {
 	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3003), ENGINE_CLASS(RENDER)),
 	  XE_RTP_ACTIONS(SET(COMMON_SLICE_CHICKEN4, SBE_PUSH_CONSTANT_BEHIND_FIX_ENABLE))
 	},
+	{ XE_RTP_NAME("14024681466"),
+	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3005), ENGINE_CLASS(RENDER)),
+	  XE_RTP_ACTIONS(SET(XEHP_SLICE_COMMON_ECO_CHICKEN1, FAST_CLEAR_VALIGN_FIX))
+	},
+	{ XE_RTP_NAME("15016589081"),
+	  XE_RTP_RULES(GRAPHICS_VERSION(3000), GRAPHICS_STEP(A0, B0),
+		       ENGINE_CLASS(RENDER)),
+	  XE_RTP_ACTIONS(SET(CHICKEN_RASTER_1, DIS_CLIP_NEGATIVE_BOUNDING_BOX))
+	},
 };
 
 static __maybe_unused const struct xe_rtp_entry oob_was[] = {