Merge tag 'drm-fixes-2024-10-18' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Weekly fixes, msm and xe are the two main ones, with a bunch of
  scattered fixes including a largish revert in mgag200, then amdgpu,
  vmwgfx and scattering of other minor ones.

  All seems pretty regular.

  msm:
   - Display:
      - move CRTC resource assignment to atomic_check otherwise to make
        consecutive calls to atomic_check() consistent
      - fix rounding / sign-extension issues with pclk calculation in
        case of DSC
      - cleanups to drop incorrect null checks in dpu snapshots
      - fix to use kvzalloc in dpu snapshot to avoid allocation issues
        in heavily loaded system cases
      - Fix to not program merge_3d block if dual LM is not being used
      - Fix to not flush merge_3d block if its not enabled otherwise
        this leads to false timeouts
   - GPU:
      - a7xx: add a fence wait before SMMU table update

  xe:
   - New workaround to Xe2 (Aradhya)
   - Fix unbalanced rpm put (Matthew Auld)
   - Remove fragile lock optimization (Matthew Brost)
   - Fix job release, delegating it to the drm scheduler (Matthew Brost)
   - Fix timestamp bit width for Xe2 (Lucas)
   - Fix external BO's dma-resv usag (Matthew Brost)
   - Fix returning success for timeout in wait_token (Nirmoy)
   - Initialize fence to avoid it being detected as signaled (Matthew
     Auld)
   - Improve cache flush for BMG (Matthew Auld)
   - Don't allow hflip for tile4 framebuffer on Xe2 (Juha-Pekka)

  amdgpu:
   - SR-IOV fix
   - CS chunk handling fix
   - MES fixes
   - SMU13 fixes

  amdkfd:
   - VRAM usage reporting fix

  radeon:
   - Fix possible_clones handling

  i915:
   - Two DP bandwidth related MST fixes

  ast:
   - Clear EDID on unplugged connectors

  host1x:
   - Fix boot on Tegra186
   - Set DMA parameters

  mgag200:
   - Revert VBLANK support

  panel:
   - himax-hx83192: Adjust power and gamma

  qaic:
   - Sgtable loop fixes

  vmwgfx:
   - Limit display layout allocatino size
   - Handle allocation errors in connector checks
   - Clean up KMS code for 2d-only setup
   - Report surface-check errors correctly
   - Remove NULL test around kvfree()"

* tag 'drm-fixes-2024-10-18' of https://gitlab.freedesktop.org/drm/kernel: (45 commits)
  drm/ast: vga: Clear EDID if no display is connected
  drm/ast: sil164: Clear EDID if no display is connected
  Revert "drm/mgag200: Add vblank support"
  drm/amdgpu/swsmu: default to fullscreen 3D profile for dGPUs
  drm/i915/display: Don't allow tile4 framebuffer to do hflip on display20 or greater
  drm/xe/bmg: improve cache flushing behaviour
  drm/xe/xe_sync: initialise ufence.signalled
  drm/xe/ufence: ufence can be signaled right after wait_woken
  drm/xe: Use bookkeep slots for external BO's in exec IOCTL
  drm/xe/query: Increase timestamp width
  drm/xe: Don't free job in TDR
  drm/xe: Take job list lock in xe_sched_add_pending_job
  drm/xe: fix unbalanced rpm put() with declare_wedged()
  drm/xe: fix unbalanced rpm put() with fence_fini()
  drm/xe/xe2lpg: Extend Wa_15016589081 for xe2lpg
  drm/i915/dp_mst: Don't require DSC hblank quirk for a non-DSC compatible mode
  drm/i915/dp_mst: Handle error during DSC BW overhead/slice calculation
  drm/msm/a6xx+: Insert a fence wait before SMMU table update
  drm/msm/dpu: don't always program merge_3d block
  drm/msm/dpu: Don't always set merge_3d pending flush
  ...

61 files changed, 291 insertions, 388 deletions

diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c
index 9e8a8cbadf6b..d8bdab69f800 100644
--- a/drivers/accel/qaic/qaic_control.c
+++ b/drivers/accel/qaic/qaic_control.c
@@ -496,7 +496,7 @@ static int encode_addr_size_pairs(struct dma_xfer *xfer, struct wrapper_list *wr
 	nents = sgt->nents;
 	nents_dma = nents;
 	*size = QAIC_MANAGE_EXT_MSG_LENGTH - msg_hdr_len - sizeof(**out_trans);
-	for_each_sgtable_sg(sgt, sg, i) {
+	for_each_sgtable_dma_sg(sgt, sg, i) {
 		*size -= sizeof(*asp);
 		/* Save 1K for possible follow-up transactions. */
 		if (*size < SZ_1K) {
diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c
index e86e71c1cdd8..c20eb63750f5 100644
--- a/drivers/accel/qaic/qaic_data.c
+++ b/drivers/accel/qaic/qaic_data.c
@@ -184,7 +184,7 @@ static int clone_range_of_sgt_for_slice(struct qaic_device *qdev, struct sg_tabl
 	nents = 0;
 
 	size = size ? size : PAGE_SIZE;
-	for (sg = sgt_in->sgl; sg; sg = sg_next(sg)) {
+	for_each_sgtable_dma_sg(sgt_in, sg, j) {
 		len = sg_dma_len(sg);
 
 		if (!len)
@@ -221,7 +221,7 @@ static int clone_range_of_sgt_for_slice(struct qaic_device *qdev, struct sg_tabl
 
 	/* copy relevant sg node and fix page and length */
 	sgn = sgf;
-	for_each_sgtable_sg(sgt, sg, j) {
+	for_each_sgtable_dma_sg(sgt, sg, j) {
 		memcpy(sg, sgn, sizeof(*sg));
 		if (sgn == sgf) {
 			sg_dma_address(sg) += offf;
@@ -301,7 +301,7 @@ static int encode_reqs(struct qaic_device *qdev, struct bo_slice *slice,
 	 * fence.
 	 */
 	dev_addr = req->dev_addr;
-	for_each_sgtable_sg(slice->sgt, sg, i) {
+	for_each_sgtable_dma_sg(slice->sgt, sg, i) {
 		slice->reqs[i].cmd = cmd;
 		slice->reqs[i].src_addr = cpu_to_le64(slice->dir == DMA_TO_DEVICE ?
 						      sg_dma_address(sg) : dev_addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 1e475eb01417..d891ab779ca7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -265,7 +265,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p,
 
 			/* Only a single BO list is allowed to simplify handling. */
 			if (p->bo_list)
-				ret = -EINVAL;
+				goto free_partial_kdata;
 
 			ret = amdgpu_cs_p1_bo_handles(p, p->chunks[i].kdata);
 			if (ret)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 83e54697f0ee..f1ffab5a1eae 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1635,11 +1635,9 @@ int amdgpu_gfx_sysfs_isolation_shader_init(struct amdgpu_device *adev)
 {
 	int r;
 
-	if (!amdgpu_sriov_vf(adev)) {
-		r = device_create_file(adev->dev, &dev_attr_enforce_isolation);
-		if (r)
-			return r;
-	}
+	r = device_create_file(adev->dev, &dev_attr_enforce_isolation);
+	if (r)
+		return r;
 
 	r = device_create_file(adev->dev, &dev_attr_run_cleaner_shader);
 	if (r)
@@ -1650,8 +1648,7 @@ int amdgpu_gfx_sysfs_isolation_shader_init(struct amdgpu_device *adev)
 
 void amdgpu_gfx_sysfs_isolation_shader_fini(struct amdgpu_device *adev)
 {
-	if (!amdgpu_sriov_vf(adev))
-		device_remove_file(adev->dev, &dev_attr_enforce_isolation);
+	device_remove_file(adev->dev, &dev_attr_enforce_isolation);
 	device_remove_file(adev->dev, &dev_attr_run_cleaner_shader);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index 10b61ff63802..7d4b540340e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -1203,8 +1203,10 @@ int amdgpu_mes_add_ring(struct amdgpu_device *adev, int gang_id,
 
 	r = amdgpu_ring_init(adev, ring, 1024, NULL, 0,
 			     AMDGPU_RING_PRIO_DEFAULT, NULL);
-	if (r)
+	if (r) {
+		amdgpu_mes_unlock(&adev->mes);
 		goto clean_up_memory;
+	}
 
 	amdgpu_mes_ring_to_queue_props(adev, ring, &qprops);
 
@@ -1237,7 +1239,6 @@ clean_up_ring:
 	amdgpu_ring_fini(ring);
 clean_up_memory:
 	kfree(ring);
-	amdgpu_mes_unlock(&adev->mes);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 8d27421689c9..a37a6801c9ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -621,7 +621,7 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 
 	if (amdgpu_mes_log_enable) {
 		mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
-		mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr;
+		mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr + pipe * AMDGPU_MES_LOG_BUFFER_SIZE;
 	}
 
 	return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe,
@@ -1336,7 +1336,7 @@ static int mes_v12_0_sw_init(void *handle)
 	adev->mes.kiq_hw_fini = &mes_v12_0_kiq_hw_fini;
 	adev->mes.enable_legacy_queue_map = true;
 
-	adev->mes.event_log_size = AMDGPU_MES_LOG_BUFFER_SIZE;
+	adev->mes.event_log_size = adev->enable_uni_mes ? (AMDGPU_MAX_MES_PIPES * AMDGPU_MES_LOG_BUFFER_SIZE) : AMDGPU_MES_LOG_BUFFER_SIZE;
 
 	r = amdgpu_mes_init(adev);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 9044bdb38cf4..3e6b4736a7fe 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1148,7 +1148,7 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep,
 
 		if (flags & KFD_IOC_ALLOC_MEM_FLAGS_AQL_QUEUE_MEM)
 			size >>= 1;
-		WRITE_ONCE(pdd->vram_usage, pdd->vram_usage + PAGE_ALIGN(size));
+		atomic64_add(PAGE_ALIGN(size), &pdd->vram_usage);
 	}
 
 	mutex_unlock(&p->mutex);
@@ -1219,7 +1219,7 @@ static int kfd_ioctl_free_memory_of_gpu(struct file *filep,
 		kfd_process_device_remove_obj_handle(
 			pdd, GET_IDR_HANDLE(args->handle));
 
-	WRITE_ONCE(pdd->vram_usage, pdd->vram_usage - size);
+	atomic64_sub(size, &pdd->vram_usage);
 
 err_unlock:
 err_pdd:
@@ -2347,7 +2347,7 @@ static int criu_restore_memory_of_gpu(struct kfd_process_device *pdd,
 	} else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) {
 		bo_bucket->restored_offset = offset;
 		/* Update the VRAM usage count */
-		WRITE_ONCE(pdd->vram_usage, pdd->vram_usage + bo_bucket->size);
+		atomic64_add(bo_bucket->size, &pdd->vram_usage);
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index d6530febabad..26e48fdc8728 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -775,7 +775,7 @@ struct kfd_process_device {
 	enum kfd_pdd_bound bound;
 
 	/* VRAM usage */
-	uint64_t vram_usage;
+	atomic64_t vram_usage;
 	struct attribute attr_vram;
 	char vram_filename[MAX_SYSFS_FILENAME_LEN];
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index d665ecdcd12f..d4aa843aacfd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -332,7 +332,7 @@ static ssize_t kfd_procfs_show(struct kobject *kobj, struct attribute *attr,
 	} else if (strncmp(attr->name, "vram_", 5) == 0) {
 		struct kfd_process_device *pdd = container_of(attr, struct kfd_process_device,
 							      attr_vram);
-		return snprintf(buffer, PAGE_SIZE, "%llu\n", READ_ONCE(pdd->vram_usage));
+		return snprintf(buffer, PAGE_SIZE, "%llu\n", atomic64_read(&pdd->vram_usage));
 	} else if (strncmp(attr->name, "sdma_", 5) == 0) {
 		struct kfd_process_device *pdd = container_of(attr, struct kfd_process_device,
 							      attr_sdma);
@@ -1625,7 +1625,7 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_node *dev,
 	pdd->bound = PDD_UNBOUND;
 	pdd->already_dequeued = false;
 	pdd->runtime_inuse = false;
-	pdd->vram_usage = 0;
+	atomic64_set(&pdd->vram_usage, 0);
 	pdd->sdma_past_activity_counter = 0;
 	pdd->user_gpu_id = dev->id;
 	atomic64_set(&pdd->evict_duration_counter, 0);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 04e746923697..1893c27746a5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -405,6 +405,27 @@ static void svm_range_bo_release(struct kref *kref)
 		spin_lock(&svm_bo->list_lock);
 	}
 	spin_unlock(&svm_bo->list_lock);
+
+	if (mmget_not_zero(svm_bo->eviction_fence->mm)) {
+		struct kfd_process_device *pdd;
+		struct kfd_process *p;
+		struct mm_struct *mm;
+
+		mm = svm_bo->eviction_fence->mm;
+		/*
+		 * The forked child process takes svm_bo device pages ref, svm_bo could be
+		 * released after parent process is gone.
+		 */
+		p = kfd_lookup_process_by_mm(mm);
+		if (p) {
+			pdd = kfd_get_process_device_data(svm_bo->node, p);
+			if (pdd)
+				atomic64_sub(amdgpu_bo_size(svm_bo->bo), &pdd->vram_usage);
+			kfd_unref_process(p);
+		}
+		mmput(mm);
+	}
+
 	if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base))
 		/* We're not in the eviction worker. Signal the fence. */
 		dma_fence_signal(&svm_bo->eviction_fence->base);
@@ -532,6 +553,7 @@ int
 svm_range_vram_node_new(struct kfd_node *node, struct svm_range *prange,
 			bool clear)
 {
+	struct kfd_process_device *pdd;
 	struct amdgpu_bo_param bp;
 	struct svm_range_bo *svm_bo;
 	struct amdgpu_bo_user *ubo;
@@ -623,6 +645,10 @@ svm_range_vram_node_new(struct kfd_node *node, struct svm_range *prange,
 	list_add(&prange->svm_bo_list, &svm_bo->range_list);
 	spin_unlock(&svm_bo->list_lock);
 
+	pdd = svm_range_get_pdd_by_node(prange, node);
+	if (pdd)
+		atomic64_add(amdgpu_bo_size(bo), &pdd->vram_usage);
+
 	return 0;
 
 reserve_bo_failed:
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index bb3bc68dfc39..9ad9cf7a9c98 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1264,7 +1264,11 @@ static int smu_sw_init(void *handle)
 	smu->workload_prority[PP_SMC_POWER_PROFILE_VR] = 4;
 	smu->workload_prority[PP_SMC_POWER_PROFILE_COMPUTE] = 5;
 	smu->workload_prority[PP_SMC_POWER_PROFILE_CUSTOM] = 6;
-	smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT];
+
+	if (smu->is_apu)
+		smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT];
+	else
+		smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D];
 
 	smu->workload_setting[0] = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
 	smu->workload_setting[1] = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
@@ -2226,7 +2230,7 @@ static int smu_bump_power_profile_mode(struct smu_context *smu,
 static int smu_adjust_power_state_dynamic(struct smu_context *smu,
 					  enum amd_dpm_forced_level level,
 					  bool skip_display_settings,
-					  bool force_update)
+					  bool init)
 {
 	int ret = 0;
 	int index = 0;
@@ -2255,7 +2259,7 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu,
 		}
 	}
 
-	if (force_update || smu_dpm_ctx->dpm_level != level) {
+	if (smu_dpm_ctx->dpm_level != level) {
 		ret = smu_asic_set_performance_level(smu, level);
 		if (ret) {
 			dev_err(smu->adev->dev, "Failed to set performance level!");
@@ -2272,7 +2276,7 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu,
 		index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
 		workload[0] = smu->workload_setting[index];
 
-		if (force_update || smu->power_profile_mode != workload[0])
+		if (init || smu->power_profile_mode != workload[0])
 			smu_bump_power_profile_mode(smu, workload, 0);
 	}
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 1d024b122b0c..cb923e33fd6f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2555,18 +2555,16 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu,
 	workload_mask = 1 << workload_type;
 
 	/* Add optimizations for SMU13.0.0/10.  Reuse the power saving profile */
-	if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE) {
-		if ((amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 0) &&
-			((smu->adev->pm.fw_version == 0x004e6601) ||
-			(smu->adev->pm.fw_version >= 0x004e7300))) ||
-			(amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) &&
-			 smu->adev->pm.fw_version >= 0x00504500)) {
-			workload_type = smu_cmn_to_asic_specific_index(smu,
-								CMN2ASIC_MAPPING_WORKLOAD,
-								PP_SMC_POWER_PROFILE_POWERSAVING);
-			if (workload_type >= 0)
-				workload_mask |= 1 << workload_type;
-		}
+	if ((amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 0) &&
+	     ((smu->adev->pm.fw_version == 0x004e6601) ||
+	      (smu->adev->pm.fw_version >= 0x004e7300))) ||
+	    (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) &&
+	     smu->adev->pm.fw_version >= 0x00504500)) {
+		workload_type = smu_cmn_to_asic_specific_index(smu,
+							       CMN2ASIC_MAPPING_WORKLOAD,
+							       PP_SMC_POWER_PROFILE_POWERSAVING);
+		if (workload_type >= 0)
+			workload_mask |= 1 << workload_type;
 	}
 
 	ret = smu_cmn_send_smc_msg_with_param(smu,
diff --git a/drivers/gpu/drm/ast/ast_sil164.c b/drivers/gpu/drm/ast/ast_sil164.c
index 496c7120e515..c231389936bd 100644
--- a/drivers/gpu/drm/ast/ast_sil164.c
+++ b/drivers/gpu/drm/ast/ast_sil164.c
@@ -29,6 +29,8 @@ static int ast_sil164_connector_helper_get_modes(struct drm_connector *connector
 	if (ast_connector->physical_status == connector_status_connected) {
 		count = drm_connector_helper_get_modes(connector);
 	} else {
+		drm_edid_connector_update(connector, NULL);
+
 		/*
 		 * There's no EDID data without a connected monitor. Set BMC-
 		 * compatible modes in this case. The XGA default resolution
diff --git a/drivers/gpu/drm/ast/ast_vga.c b/drivers/gpu/drm/ast/ast_vga.c
index 3e815da43fbd..dd389a0a8f4a 100644
--- a/drivers/gpu/drm/ast/ast_vga.c
+++ b/drivers/gpu/drm/ast/ast_vga.c
@@ -29,6 +29,8 @@ static int ast_vga_connector_helper_get_modes(struct drm_connector *connector)
 	if (ast_connector->physical_status == connector_status_connected) {
 		count = drm_connector_helper_get_modes(connector);
 	} else {
+		drm_edid_connector_update(connector, NULL);
+
 		/*
 		 * There's no EDID data without a connected monitor. Set BMC-
 		 * compatible modes in this case. The XGA default resolution
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 15541932b809..eeaedd979354 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -89,25 +89,19 @@ static int intel_dp_mst_max_dpt_bpp(const struct intel_crtc_state *crtc_state,
 
 static int intel_dp_mst_bw_overhead(const struct intel_crtc_state *crtc_state,
 				    const struct intel_connector *connector,
-				    bool ssc, bool dsc, int bpp_x16)
+				    bool ssc, int dsc_slice_count, int bpp_x16)
 {
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->hw.adjusted_mode;
 	unsigned long flags = DRM_DP_BW_OVERHEAD_MST;
-	int dsc_slice_count = 0;
 	int overhead;
 
 	flags |= intel_dp_is_uhbr(crtc_state) ? DRM_DP_BW_OVERHEAD_UHBR : 0;
 	flags |= ssc ? DRM_DP_BW_OVERHEAD_SSC_REF_CLK : 0;
 	flags |= crtc_state->fec_enable ? DRM_DP_BW_OVERHEAD_FEC : 0;
 
-	if (dsc) {
+	if (dsc_slice_count)
 		flags |= DRM_DP_BW_OVERHEAD_DSC;
-		dsc_slice_count = intel_dp_dsc_get_slice_count(connector,
-							       adjusted_mode->clock,
-							       adjusted_mode->hdisplay,
-							       crtc_state->joiner_pipes);
-	}
 
 	overhead = drm_dp_bw_overhead(crtc_state->lane_count,
 				      adjusted_mode->hdisplay,
@@ -153,6 +147,19 @@ static int intel_dp_mst_calc_pbn(int pixel_clock, int bpp_x16, int bw_overhead)
 	return DIV_ROUND_UP(effective_data_rate * 64, 54 * 1000);
 }
 
+static int intel_dp_mst_dsc_get_slice_count(const struct intel_connector *connector,
+					    const struct intel_crtc_state *crtc_state)
+{
+	const struct drm_display_mode *adjusted_mode =
+		&crtc_state->hw.adjusted_mode;
+	int num_joined_pipes = crtc_state->joiner_pipes;
+
+	return intel_dp_dsc_get_slice_count(connector,
+					    adjusted_mode->clock,
+					    adjusted_mode->hdisplay,
+					    num_joined_pipes);
+}
+
 static int intel_dp_mst_find_vcpi_slots_for_bpp(struct intel_encoder *encoder,
 						struct intel_crtc_state *crtc_state,
 						int max_bpp,
@@ -172,6 +179,7 @@ static int intel_dp_mst_find_vcpi_slots_for_bpp(struct intel_encoder *encoder,
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->hw.adjusted_mode;
 	int bpp, slots = -EINVAL;
+	int dsc_slice_count = 0;
 	int max_dpt_bpp;
 	int ret = 0;
 
@@ -203,6 +211,15 @@ static int intel_dp_mst_find_vcpi_slots_for_bpp(struct intel_encoder *encoder,
 	drm_dbg_kms(&i915->drm, "Looking for slots in range min bpp %d max bpp %d\n",
 		    min_bpp, max_bpp);
 
+	if (dsc) {
+		dsc_slice_count = intel_dp_mst_dsc_get_slice_count(connector, crtc_state);
+		if (!dsc_slice_count) {
+			drm_dbg_kms(&i915->drm, "Can't get valid DSC slice count\n");
+
+			return -ENOSPC;
+		}
+	}
+
 	for (bpp = max_bpp; bpp >= min_bpp; bpp -= step) {
 		int local_bw_overhead;
 		int remote_bw_overhead;
@@ -216,9 +233,9 @@ static int intel_dp_mst_find_vcpi_slots_for_bpp(struct intel_encoder *encoder,
 					       intel_dp_output_bpp(crtc_state->output_format, bpp));
 
 		local_bw_overhead = intel_dp_mst_bw_overhead(crtc_state, connector,
-							     false, dsc, link_bpp_x16);
+							     false, dsc_slice_count, link_bpp_x16);
 		remote_bw_overhead = intel_dp_mst_bw_overhead(crtc_state, connector,
-							      true, dsc, link_bpp_x16);
+							      true, dsc_slice_count, link_bpp_x16);
 
 		intel_dp_mst_compute_m_n(crtc_state, connector,
 					 local_bw_overhead,
@@ -449,6 +466,9 @@ hblank_expansion_quirk_needs_dsc(const struct intel_connector *connector,
 	if (mode_hblank_period_ns(adjusted_mode) > hblank_limit)
 		return false;
 
+	if (!intel_dp_mst_dsc_get_slice_count(connector, crtc_state))
+		return false;
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c
index 5be7bb43e2e0..35557d98d7a7 100644
--- a/drivers/gpu/drm/i915/display/intel_fb.c
+++ b/drivers/gpu/drm/i915/display/intel_fb.c
@@ -438,6 +438,19 @@ bool intel_fb_needs_64k_phys(u64 modifier)
 				      INTEL_PLANE_CAP_NEED64K_PHYS);
 }
 
+/**
+ * intel_fb_is_tile4_modifier: Check if a modifier is a tile4 modifier type
+ * @modifier: Modifier to check
+ *
+ * Returns:
+ * Returns %true if @modifier is a tile4 modifier.
+ */
+bool intel_fb_is_tile4_modifier(u64 modifier)
+{
+	return plane_caps_contain_any(lookup_modifier(modifier)->plane_caps,
+				      INTEL_PLANE_CAP_TILING_4);
+}
+
 static bool check_modifier_display_ver_range(const struct intel_modifier_desc *md,
 					     u8 display_ver_from, u8 display_ver_until)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_fb.h b/drivers/gpu/drm/i915/display/intel_fb.h
index 10de437e8ef8..827be3f7934c 100644
--- a/drivers/gpu/drm/i915/display/intel_fb.h
+++ b/drivers/gpu/drm/i915/display/intel_fb.h
@@ -35,6 +35,7 @@ bool intel_fb_is_ccs_modifier(u64 modifier);
 bool intel_fb_is_rc_ccs_cc_modifier(u64 modifier);
 bool intel_fb_is_mc_ccs_modifier(u64 modifier);
 bool intel_fb_needs_64k_phys(u64 modifier);
+bool intel_fb_is_tile4_modifier(u64 modifier);
 
 bool intel_fb_is_ccs_aux_plane(const struct drm_framebuffer *fb, int color_plane);
 int intel_fb_rc_ccs_cc_plane(const struct drm_framebuffer *fb);
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index 17d4c880ecc4..c8720d31d101 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -1591,6 +1591,17 @@ static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state,
 		return -EINVAL;
 	}
 
+	/*
+	 * Display20 onward tile4 hflip is not supported
+	 */
+	if (rotation & DRM_MODE_REFLECT_X &&
+	    intel_fb_is_tile4_modifier(fb->modifier) &&
+	    DISPLAY_VER(dev_priv) >= 20) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "horizontal flip is not supported with tile4 surface formats\n");
+		return -EINVAL;
+	}
+
 	if (drm_rotation_90_or_270(rotation)) {
 		if (!intel_fb_supports_90_270_rotation(to_intel_framebuffer(fb))) {
 			drm_dbg_kms(&dev_priv->drm,
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index 6623ee4e3277..9f5925693686 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -18,7 +18,6 @@
 #include <drm/drm_managed.h>
 #include <drm/drm_module.h>
 #include <drm/drm_pciids.h>
-#include <drm/drm_vblank.h>
 
 #include "mgag200_drv.h"
 
@@ -85,34 +84,6 @@ resource_size_t mgag200_probe_vram(void __iomem *mem, resource_size_t size)
 	return offset - 65536;
 }
 
-static irqreturn_t mgag200_irq_handler(int irq, void *arg)
-{
-	struct drm_device *dev = arg;
-	struct mga_device *mdev = to_mga_device(dev);
-	struct drm_crtc *crtc;
-	u32 status, ien;
-
-	status = RREG32(MGAREG_STATUS);
-
-	if (status & MGAREG_STATUS_VLINEPEN) {
-		ien = RREG32(MGAREG_IEN);
-		if (!(ien & MGAREG_IEN_VLINEIEN))
-			goto out;
-
-		crtc = drm_crtc_from_index(dev, 0);
-		if (WARN_ON_ONCE(!crtc))
-			goto out;
-		drm_crtc_handle_vblank(crtc);
-
-		WREG32(MGAREG_ICLEAR, MGAREG_ICLEAR_VLINEICLR);
-
-		return IRQ_HANDLED;
-	}
-
-out:
-	return IRQ_NONE;
-}
-
 /*
  * DRM driver
  */
@@ -196,7 +167,6 @@ int mgag200_device_init(struct mga_device *mdev,
 			const struct mgag200_device_funcs *funcs)
 {
 	struct drm_device *dev = &mdev->base;
-	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	u8 crtcext3, misc;
 	int ret;
 
@@ -223,14 +193,6 @@ int mgag200_device_init(struct mga_device *mdev,
 	mutex_unlock(&mdev->rmmio_lock);
 
 	WREG32(MGAREG_IEN, 0);
-	WREG32(MGAREG_ICLEAR, MGAREG_ICLEAR_VLINEICLR);
-
-	ret = devm_request_irq(&pdev->dev, pdev->irq, mgag200_irq_handler, IRQF_SHARED,
-			       dev->driver->name, dev);
-	if (ret) {
-		drm_err(dev, "Failed to acquire interrupt, error %d\n", ret);
-		return ret;
-	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index 4760ba92871b..988967eafbf2 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -391,24 +391,17 @@ int mgag200_crtc_helper_atomic_check(struct drm_crtc *crtc, struct drm_atomic_st
 void mgag200_crtc_helper_atomic_flush(struct drm_crtc *crtc, struct drm_atomic_state *old_state);
 void mgag200_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_atomic_state *old_state);
 void mgag200_crtc_helper_atomic_disable(struct drm_crtc *crtc, struct drm_atomic_state *old_state);
-bool mgag200_crtc_helper_get_scanout_position(struct drm_crtc *crtc, bool in_vblank_irq,
-					      int *vpos, int *hpos,
-					      ktime_t *stime, ktime_t *etime,
-					      const struct drm_display_mode *mode);
 
 #define MGAG200_CRTC_HELPER_FUNCS \
 	.mode_valid = mgag200_crtc_helper_mode_valid, \
 	.atomic_check = mgag200_crtc_helper_atomic_check, \
 	.atomic_flush = mgag200_crtc_helper_atomic_flush, \
 	.atomic_enable = mgag200_crtc_helper_atomic_enable, \
-	.atomic_disable = mgag200_crtc_helper_atomic_disable, \
-	.get_scanout_position = mgag200_crtc_helper_get_scanout_position
+	.atomic_disable = mgag200_crtc_helper_atomic_disable
 
 void mgag200_crtc_reset(struct drm_crtc *crtc);
 struct drm_crtc_state *mgag200_crtc_atomic_duplicate_state(struct drm_crtc *crtc);
 void mgag200_crtc_atomic_destroy_state(struct drm_crtc *crtc, struct drm_crtc_state *crtc_state);
-int mgag200_crtc_enable_vblank(struct drm_crtc *crtc);
-void mgag200_crtc_disable_vblank(struct drm_crtc *crtc);
 
 #define MGAG200_CRTC_FUNCS \
 	.reset = mgag200_crtc_reset, \
@@ -416,10 +409,7 @@ void mgag200_crtc_disable_vblank(struct drm_crtc *crtc);
 	.set_config = drm_atomic_helper_set_config, \
 	.page_flip = drm_atomic_helper_page_flip, \
 	.atomic_duplicate_state = mgag200_crtc_atomic_duplicate_state, \
-	.atomic_destroy_state = mgag200_crtc_atomic_destroy_state, \
-	.enable_vblank = mgag200_crtc_enable_vblank, \
-	.disable_vblank = mgag200_crtc_disable_vblank, \
-	.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp
+	.atomic_destroy_state = mgag200_crtc_atomic_destroy_state
 
 void mgag200_set_mode_regs(struct mga_device *mdev, const struct drm_display_mode *mode,
 			   bool set_vidrst);
diff --git a/drivers/gpu/drm/mgag200/mgag200_g200.c b/drivers/gpu/drm/mgag200/mgag200_g200.c
index 77ce8d36cef0..f874e2949840 100644
--- a/drivers/gpu/drm/mgag200/mgag200_g200.c
+++ b/drivers/gpu/drm/mgag200/mgag200_g200.c
@@ -8,7 +8,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_probe_helper.h>
-#include <drm/drm_vblank.h>
 
 #include "mgag200_drv.h"
 
@@ -404,9 +403,5 @@ struct mga_device *mgag200_g200_device_create(struct pci_dev *pdev, const struct
 	drm_mode_config_reset(dev);
 	drm_kms_helper_poll_init(dev);
 
-	ret = drm_vblank_init(dev, 1);
-	if (ret)
-		return ERR_PTR(ret);
-
 	return mdev;
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_g200eh.c b/drivers/gpu/drm/mgag200/mgag200_g200eh.c
index 09ced65c1d2f..e2305f8e00f8 100644
--- a/drivers/gpu/drm/mgag200/mgag200_g200eh.c
+++ b/drivers/gpu/drm/mgag200/mgag200_g200eh.c
@@ -8,7 +8,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_probe_helper.h>
-#include <drm/drm_vblank.h>
 
 #include "mgag200_drv.h"
 
@@ -276,9 +275,5 @@ struct mga_device *mgag200_g200eh_device_create(struct pci_dev *pdev, const stru
 	drm_mode_config_reset(dev);
 	drm_kms_helper_poll_init(dev);
 
-	ret = drm_vblank_init(dev, 1);
-	if (ret)
-		return ERR_PTR(ret);
-
 	return mdev;
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_g200eh3.c b/drivers/gpu/drm/mgag200/mgag200_g200eh3.c
index 5daa469137bd..11ae76eb081d 100644
--- a/drivers/gpu/drm/mgag200/mgag200_g200eh3.c
+++ b/drivers/gpu/drm/mgag200/mgag200_g200eh3.c
@@ -7,7 +7,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_probe_helper.h>
-#include <drm/drm_vblank.h>
 
 #include "mgag200_drv.h"
 
@@ -181,9 +180,5 @@ struct mga_device *mgag200_g200eh3_device_create(struct pci_dev *pdev,
 	drm_mode_config_reset(dev);
 	drm_kms_helper_poll_init(dev);
 
-	ret = drm_vblank_init(dev, 1);
-	if (ret)
-		return ERR_PTR(ret);
-
 	return mdev;
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_g200er.c b/drivers/gpu/drm/mgag200/mgag200_g200er.c
index 09cfffafe130..c20ed0ab50ec 100644
--- a/drivers/gpu/drm/mgag200/mgag200_g200er.c
+++ b/drivers/gpu/drm/mgag200/mgag200_g200er.c
@@ -8,7 +8,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_probe_helper.h>
-#include <drm/drm_vblank.h>
 
 #include "mgag200_drv.h"
 
@@ -206,8 +205,6 @@ static void mgag200_g200er_crtc_helper_atomic_enable(struct drm_crtc *crtc,
 		mgag200_crtc_set_gamma_linear(mdev, format);
 
 	mgag200_enable_display(mdev);
-
-	drm_crtc_vblank_on(crtc);
 }
 
 static const struct drm_crtc_helper_funcs mgag200_g200er_crtc_helper_funcs = {
@@ -215,8 +212,7 @@ static const struct drm_crtc_helper_funcs mgag200_g200er_crtc_helper_funcs = {
 	.atomic_check = mgag200_crtc_helper_atomic_check,
 	.atomic_flush = mgag200_crtc_helper_atomic_flush,
 	.atomic_enable = mgag200_g200er_crtc_helper_atomic_enable,
-	.atomic_disable = mgag200_crtc_helper_atomic_disable,
-	.get_scanout_position = mgag200_crtc_helper_get_scanout_position,
+	.atomic_disable = mgag200_crtc_helper_atomic_disable
 };
 
 static const struct drm_crtc_funcs mgag200_g200er_crtc_funcs = {
@@ -312,9 +308,5 @@ struct mga_device *mgag200_g200er_device_create(struct pci_dev *pdev, const stru
 	drm_mode_config_reset(dev);
 	drm_kms_helper_poll_init(dev);
 
-	ret = drm_vblank_init(dev, 1);
-	if (ret)
-		return ERR_PTR(ret);
-
 	return mdev;
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_g200ev.c b/drivers/gpu/drm/mgag200/mgag200_g200ev.c
index 3d48baa91d8b..78be964eb97c 100644
--- a/drivers/gpu/drm/mgag200/mgag200_g200ev.c
+++ b/drivers/gpu/drm/mgag200/mgag200_g200ev.c
@@ -8,7 +8,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_probe_helper.h>
-#include <drm/drm_vblank.h>
 
 #include "mgag200_drv.h"
 
@@ -207,8 +206,6 @@ static void mgag200_g200ev_crtc_helper_atomic_enable(struct drm_crtc *crtc,
 		mgag200_crtc_set_gamma_linear(mdev, format);
 
 	mgag200_enable_display(mdev);
-
-	drm_crtc_vblank_on(crtc);
 }
 
 static const struct drm_crtc_helper_funcs mgag200_g200ev_crtc_helper_funcs = {
@@ -216,8 +213,7 @@ static const struct drm_crtc_helper_funcs mgag200_g200ev_crtc_helper_funcs = {
 	.atomic_check = mgag200_crtc_helper_atomic_check,
 	.atomic_flush = mgag200_crtc_helper_atomic_flush,
 	.atomic_enable = mgag200_g200ev_crtc_helper_atomic_enable,
-	.atomic_disable = mgag200_crtc_helper_atomic_disable,
-	.get_scanout_position = mgag200_crtc_helper_get_scanout_position,
+	.atomic_disable = mgag200_crtc_helper_atomic_disable
 };
 
 static const struct drm_crtc_funcs mgag200_g200ev_crtc_funcs = {
@@ -317,9 +313,5 @@ struct mga_device *mgag200_g200ev_device_create(struct pci_dev *pdev, const stru
 	drm_mode_config_reset(dev);
 	drm_kms_helper_poll_init(dev);
 
-	ret = drm_vblank_init(dev, 1);
-	if (ret)
-		return ERR_PTR(ret);
-
 	return mdev;
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_g200ew3.c b/drivers/gpu/drm/mgag200/mgag200_g200ew3.c
index dabc778e64e8..31624c9ab7b7 100644
--- a/drivers/gpu/drm/mgag200/mgag200_g200ew3.c
+++ b/drivers/gpu/drm/mgag200/mgag200_g200ew3.c
@@ -7,7 +7,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_probe_helper.h>
-#include <drm/drm_vblank.h>
 
 #include "mgag200_drv.h"
 
@@ -199,9 +198,5 @@ struct mga_device *mgag200_g200ew3_device_create(struct pci_dev *pdev,
 	drm_mode_config_reset(dev);
 	drm_kms_helper_poll_init(dev);
 
-	ret = drm_vblank_init(dev, 1);
-	if (ret)
-		return ERR_PTR(ret);
-
 	return mdev;
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_g200se.c b/drivers/gpu/drm/mgag200/mgag200_g200se.c
index 9dcbe8304271..7a32d3b1d226 100644
--- a/drivers/gpu/drm/mgag200/mgag200_g200se.c
+++ b/drivers/gpu/drm/mgag200/mgag200_g200se.c
@@ -8,7 +8,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_probe_helper.h>
-#include <drm/drm_vblank.h>
 
 #include "mgag200_drv.h"
 
@@ -338,8 +337,6 @@ static void mgag200_g200se_crtc_helper_atomic_enable(struct drm_crtc *crtc,
 		mgag200_crtc_set_gamma_linear(mdev, format);
 
 	mgag200_enable_display(mdev);
-
-	drm_crtc_vblank_on(crtc);
 }
 
 static const struct drm_crtc_helper_funcs mgag200_g200se_crtc_helper_funcs = {
@@ -347,8 +344,7 @@ static const struct drm_crtc_helper_funcs mgag200_g200se_crtc_helper_funcs = {
 	.atomic_check = mgag200_crtc_helper_atomic_check,
 	.atomic_flush = mgag200_crtc_helper_atomic_flush,
 	.atomic_enable = mgag200_g200se_crtc_helper_atomic_enable,
-	.atomic_disable = mgag200_crtc_helper_atomic_disable,
-	.get_scanout_position = mgag200_crtc_helper_get_scanout_position,
+	.atomic_disable = mgag200_crtc_helper_atomic_disable
 };
 
 static const struct drm_crtc_funcs mgag200_g200se_crtc_funcs = {
@@ -517,9 +513,5 @@ struct mga_device *mgag200_g200se_device_create(struct pci_dev *pdev, const stru
 	drm_mode_config_reset(dev);
 	drm_kms_helper_poll_init(dev);
 
-	ret = drm_vblank_init(dev, 1);
-	if (ret)
-		return ERR_PTR(ret);
-
 	return mdev;
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_g200wb.c b/drivers/gpu/drm/mgag200/mgag200_g200wb.c
index 83a24aedbf2f..a0e7b9ad46cd 100644
--- a/drivers/gpu/drm/mgag200/mgag200_g200wb.c
+++ b/drivers/gpu/drm/mgag200/mgag200_g200wb.c
@@ -8,7 +8,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_probe_helper.h>
-#include <drm/drm_vblank.h>
 
 #include "mgag200_drv.h"
 
@@ -323,9 +322,5 @@ struct mga_device *mgag200_g200wb_device_create(struct pci_dev *pdev, const stru
 	drm_mode_config_reset(dev);
 	drm_kms_helper_poll_init(dev);
 
-	ret = drm_vblank_init(dev, 1);
-	if (ret)
-		return ERR_PTR(ret);
-
 	return mdev;
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 7159909aca1e..fb71658c3117 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -22,7 +22,6 @@
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_panic.h>
 #include <drm/drm_print.h>
-#include <drm/drm_vblank.h>
 
 #include "mgag200_ddc.h"
 #include "mgag200_drv.h"
@@ -227,14 +226,7 @@ void mgag200_set_mode_regs(struct mga_device *mdev, const struct drm_display_mod
 	vblkstr = mode->crtc_vblank_start;
 	vblkend = vtotal + 1;
 
-	/*
-	 * There's no VBLANK interrupt on Matrox chipsets, so we use
-	 * the VLINE interrupt instead. It triggers when the current
-	 * <linecomp> has been reached. For VBLANK, this is the first
-	 * non-visible line at the bottom of the screen. Therefore,
-	 * keep <linecomp> in sync with <vblkstr>.
-	 */
-	linecomp = vblkstr;
+	linecomp = vdispend;
 
 	misc = RREG8(MGA_MISC_IN);
 
@@ -645,8 +637,6 @@ void mgag200_crtc_helper_atomic_flush(struct drm_crtc *crtc, struct drm_atomic_s
 	struct mgag200_crtc_state *mgag200_crtc_state = to_mgag200_crtc_state(crtc_state);
 	struct drm_device *dev = crtc->dev;
 	struct mga_device *mdev = to_mga_device(dev);
-	struct drm_pending_vblank_event *event;
-	unsigned long flags;
 
 	if (crtc_state->enable && crtc_state->color_mgmt_changed) {
 		const struct drm_format_info *format = mgag200_crtc_state->format;
@@ -656,18 +646,6 @@ void mgag200_crtc_helper_atomic_flush(struct drm_crtc *crtc, struct drm_atomic_s
 		else
 			mgag200_crtc_set_gamma_linear(mdev, format);
 	}
-
-	event = crtc->state->event;
-	if (event) {
-		crtc->state->event = NULL;
-
-		spin_lock_irqsave(&dev->event_lock, flags);
-		if (drm_crtc_vblank_get(crtc) != 0)
-			drm_crtc_send_vblank_event(crtc, event);
-		else
-			drm_crtc_arm_vblank_event(crtc, event);
-		spin_unlock_irqrestore(&dev->event_lock, flags);
-	}
 }
 
 void mgag200_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_atomic_state *old_state)
@@ -692,44 +670,15 @@ void mgag200_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_atomic_
 		mgag200_crtc_set_gamma_linear(mdev, format);
 
 	mgag200_enable_display(mdev);
-
-	drm_crtc_vblank_on(crtc);
 }
 
 void mgag200_crtc_helper_atomic_disable(struct drm_crtc *crtc, struct drm_atomic_state *old_state)
 {
 	struct mga_device *mdev = to_mga_device(crtc->dev);
 
-	drm_crtc_vblank_off(crtc);
-
 	mgag200_disable_display(mdev);
 }
 
-bool mgag200_crtc_helper_get_scanout_position(struct drm_crtc *crtc, bool in_vblank_irq,
-					      int *vpos, int *hpos,
-					      ktime_t *stime, ktime_t *etime,
-					      const struct drm_display_mode *mode)
-{
-	struct mga_device *mdev = to_mga_device(crtc->dev);
-	u32 vcount;
-
-	if (stime)
-		*stime = ktime_get();
-
-	if (vpos) {
-		vcount = RREG32(MGAREG_VCOUNT);
-		*vpos = vcount & GENMASK(11, 0);
-	}
-
-	if (hpos)
-		*hpos = mode->htotal >> 1; // near middle of scanline on average
-
-	if (etime)
-		*etime = ktime_get();
-
-	return true;
-}
-
 void mgag200_crtc_reset(struct drm_crtc *crtc)
 {
 	struct mgag200_crtc_state *mgag200_crtc_state;
@@ -774,30 +723,6 @@ void mgag200_crtc_atomic_destroy_state(struct drm_crtc *crtc, struct drm_crtc_st
 	kfree(mgag200_crtc_state);
 }
 
-int mgag200_crtc_enable_vblank(struct drm_crtc *crtc)
-{
-	struct mga_device *mdev = to_mga_device(crtc->dev);
-	u32 ien;
-
-	WREG32(MGAREG_ICLEAR, MGAREG_ICLEAR_VLINEICLR);
-
-	ien = RREG32(MGAREG_IEN);
-	ien |= MGAREG_IEN_VLINEIEN;
-	WREG32(MGAREG_IEN, ien);
-
-	return 0;
-}
-
-void mgag200_crtc_disable_vblank(struct drm_crtc *crtc)
-{
-	struct mga_device *mdev = to_mga_device(crtc->dev);
-	u32 ien;
-
-	ien = RREG32(MGAREG_IEN);
-	ien &= ~(MGAREG_IEN_VLINEIEN);
-	WREG32(MGAREG_IEN, ien);
-}
-
 /*
  * Mode config
  */
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 06cab2c6fd66..702b8d4b3497 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -101,9 +101,10 @@ static void get_stats_counter(struct msm_ringbuffer *ring, u32 counter,
 }
 
 static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
-		struct msm_ringbuffer *ring, struct msm_file_private *ctx)
+		struct msm_ringbuffer *ring, struct msm_gem_submit *submit)
 {
 	bool sysprof = refcount_read(&a6xx_gpu->base.base.sysprof_active) > 1;
+	struct msm_file_private *ctx = submit->queue->ctx;
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	phys_addr_t ttbr;
 	u32 asid;
@@ -115,6 +116,15 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 	if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid))
 		return;
 
+	if (adreno_gpu->info->family >= ADRENO_7XX_GEN1) {
+		/* Wait for previous submit to complete before continuing: */
+		OUT_PKT7(ring, CP_WAIT_TIMESTAMP, 4);
+		OUT_RING(ring, 0);
+		OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence)));
+		OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence)));
+		OUT_RING(ring, submit->seqno - 1);
+	}
+
 	if (!sysprof) {
 		if (!adreno_is_a7xx(adreno_gpu)) {
 			/* Turn off protected mode to write to special registers */
@@ -193,7 +203,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned int i, ibs = 0;
 
-	a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx);
+	a6xx_set_pagetable(a6xx_gpu, ring, submit);
 
 	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0),
 		rbmemptr_stats(ring, index, cpcycles_start));
@@ -283,7 +293,7 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
 	OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BR);
 
-	a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx);
+	a6xx_set_pagetable(a6xx_gpu, ring, submit);
 
 	get_stats_counter(ring, REG_A7XX_RBBM_PERFCTR_CP(0),
 		rbmemptr_stats(ring, index, cpcycles_start));
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index 4c1be2f0555f..db6c57900781 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -711,12 +711,13 @@ void dpu_crtc_complete_commit(struct drm_crtc *crtc)
 	_dpu_crtc_complete_flip(crtc);
 }
 
-static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc,
+static int _dpu_crtc_check_and_setup_lm_bounds(struct drm_crtc *crtc,
 		struct drm_crtc_state *state)
 {
 	struct dpu_crtc_state *cstate = to_dpu_crtc_state(state);
 	struct drm_display_mode *adj_mode = &state->adjusted_mode;
 	u32 crtc_split_width = adj_mode->hdisplay / cstate->num_mixers;
+	struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc);
 	int i;
 
 	for (i = 0; i < cstate->num_mixers; i++) {
@@ -727,7 +728,12 @@ static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc,
 		r->y2 = adj_mode->vdisplay;
 
 		trace_dpu_crtc_setup_lm_bounds(DRMID(crtc), i, r);
+
+		if (drm_rect_width(r) > dpu_kms->catalog->caps->max_mixer_width)
+			return -E2BIG;
 	}
+
+	return 0;
 }
 
 static void _dpu_crtc_get_pcc_coeff(struct drm_crtc_state *state,
@@ -803,7 +809,7 @@ static void dpu_crtc_atomic_begin(struct drm_crtc *crtc,
 
 	DRM_DEBUG_ATOMIC("crtc%d\n", crtc->base.id);
 
-	_dpu_crtc_setup_lm_bounds(crtc, crtc->state);
+	_dpu_crtc_check_and_setup_lm_bounds(crtc, crtc->state);
 
 	/* encoder will trigger pending mask now */
 	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
@@ -1091,9 +1097,6 @@ static void dpu_crtc_disable(struct drm_crtc *crtc,
 
 	dpu_core_perf_crtc_update(crtc, 0);
 
-	memset(cstate->mixers, 0, sizeof(cstate->mixers));
-	cstate->num_mixers = 0;
-
 	/* disable clk & bw control until clk & bw properties are set */
 	cstate->bw_control = false;
 	cstate->bw_split_vote = false;
@@ -1192,8 +1195,11 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
 	if (crtc_state->active_changed)
 		crtc_state->mode_changed = true;
 
-	if (cstate->num_mixers)
-		_dpu_crtc_setup_lm_bounds(crtc, crtc_state);
+	if (cstate->num_mixers) {
+		rc = _dpu_crtc_check_and_setup_lm_bounds(crtc, crtc_state);
+		if (rc)
+			return rc;
+	}
 
 	/* FIXME: move this to dpu_plane_atomic_check? */
 	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 3b171bf227d1..bd3698bf0cf7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -624,6 +624,40 @@ static struct msm_display_topology dpu_encoder_get_topology(
 	return topology;
 }
 
+static void dpu_encoder_assign_crtc_resources(struct dpu_kms *dpu_kms,
+					      struct drm_encoder *drm_enc,
+					      struct dpu_global_state *global_state,
+					      struct drm_crtc_state *crtc_state)
+{
+	struct dpu_crtc_state *cstate;
+	struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC];
+	struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC];
+	struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_ENC];
+	int num_lm, num_ctl, num_dspp, i;
+
+	cstate = to_dpu_crtc_state(crtc_state);
+
+	memset(cstate->mixers, 0, sizeof(cstate->mixers));
+
+	num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+		drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl));
+	num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+		drm_enc->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm));
+	num_dspp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+		drm_enc->base.id, DPU_HW_BLK_DSPP, hw_dspp,
+		ARRAY_SIZE(hw_dspp));
+
+	for (i = 0; i < num_lm; i++) {
+		int ctl_idx = (i < num_ctl) ? i : (num_ctl-1);
+
+		cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]);
+		cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]);
+		cstate->mixers[i].hw_dspp = i < num_dspp ? to_dpu_hw_dspp(hw_dspp[i]) : NULL;
+	}
+
+	cstate->num_mixers = num_lm;
+}
+
 static int dpu_encoder_virt_atomic_check(
 		struct drm_encoder *drm_enc,
 		struct drm_crtc_state *crtc_state,
@@ -692,6 +726,9 @@ static int dpu_encoder_virt_atomic_check(
 		if (!crtc_state->active_changed || crtc_state->enable)
 			ret = dpu_rm_reserve(&dpu_kms->rm, global_state,
 					drm_enc, crtc_state, topology);
+		if (!ret)
+			dpu_encoder_assign_crtc_resources(dpu_kms, drm_enc,
+							  global_state, crtc_state);
 	}
 
 	trace_dpu_enc_atomic_check_flags(DRMID(drm_enc), adj_mode->flags);
@@ -1093,14 +1130,11 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
 	struct dpu_encoder_virt *dpu_enc;
 	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
-	struct dpu_crtc_state *cstate;
 	struct dpu_global_state *global_state;
 	struct dpu_hw_blk *hw_pp[MAX_CHANNELS_PER_ENC];
 	struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC];
-	struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC];
-	struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_ENC] = { NULL };
 	struct dpu_hw_blk *hw_dsc[MAX_CHANNELS_PER_ENC];
-	int num_lm, num_ctl, num_pp, num_dsc;
+	int num_ctl, num_pp, num_dsc;
 	unsigned int dsc_mask = 0;
 	int i;
 
@@ -1129,11 +1163,6 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
 		ARRAY_SIZE(hw_pp));
 	num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
 		drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl));
-	num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
-		drm_enc->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm));
-	dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
-		drm_enc->base.id, DPU_HW_BLK_DSPP, hw_dspp,
-		ARRAY_SIZE(hw_dspp));
 
 	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++)
 		dpu_enc->hw_pp[i] = i < num_pp ? to_dpu_hw_pingpong(hw_pp[i])
@@ -1159,36 +1188,23 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
 		dpu_enc->cur_master->hw_cdm = hw_cdm ? to_dpu_hw_cdm(hw_cdm) : NULL;
 	}
 
-	cstate = to_dpu_crtc_state(crtc_state);
-
-	for (i = 0; i < num_lm; i++) {
-		int ctl_idx = (i < num_ctl) ? i : (num_ctl-1);
-
-		cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]);
-		cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]);
-		cstate->mixers[i].hw_dspp = to_dpu_hw_dspp(hw_dspp[i]);
-	}
-
-	cstate->num_mixers = num_lm;
-
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (!dpu_enc->hw_pp[i]) {
+		phys->hw_pp = dpu_enc->hw_pp[i];
+		if (!phys->hw_pp) {
 			DPU_ERROR_ENC(dpu_enc,
 				"no pp block assigned at idx: %d\n", i);
 			return;
 		}
 
-		if (!hw_ctl[i]) {
+		phys->hw_ctl = i < num_ctl ? to_dpu_hw_ctl(hw_ctl[i]) : NULL;
+		if (!phys->hw_ctl) {
 			DPU_ERROR_ENC(dpu_enc,
 				"no ctl block assigned at idx: %d\n", i);
 			return;
 		}
 
-		phys->hw_pp = dpu_enc->hw_pp[i];
-		phys->hw_ctl = to_dpu_hw_ctl(hw_ctl[i]);
-
 		phys->cached_mode = crtc_state->adjusted_mode;
 		if (phys->ops.atomic_mode_set)
 			phys->ops.atomic_mode_set(phys, crtc_state, conn_state);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
index ba8878d21cf0..d8a2edebfe8c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -302,7 +302,7 @@ static void dpu_encoder_phys_vid_setup_timing_engine(
 	intf_cfg.stream_sel = 0; /* Don't care value for video mode */
 	intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
 	intf_cfg.dsc = dpu_encoder_helper_get_dsc(phys_enc);
-	if (phys_enc->hw_pp->merge_3d)
+	if (intf_cfg.mode_3d && phys_enc->hw_pp->merge_3d)
 		intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
 
 	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
@@ -440,10 +440,12 @@ static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc)
 	struct dpu_hw_ctl *ctl;
 	const struct msm_format *fmt;
 	u32 fmt_fourcc;
+	u32 mode_3d;
 
 	ctl = phys_enc->hw_ctl;
 	fmt_fourcc = dpu_encoder_get_drm_fmt(phys_enc);
 	fmt = mdp_get_format(&phys_enc->dpu_kms->base, fmt_fourcc, 0);
+	mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
 
 	DPU_DEBUG_VIDENC(phys_enc, "\n");
 
@@ -466,7 +468,8 @@ static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc)
 		goto skip_flush;
 
 	ctl->ops.update_pending_flush_intf(ctl, phys_enc->hw_intf->idx);
-	if (ctl->ops.update_pending_flush_merge_3d && phys_enc->hw_pp->merge_3d)
+	if (mode_3d && ctl->ops.update_pending_flush_merge_3d &&
+	    phys_enc->hw_pp->merge_3d)
 		ctl->ops.update_pending_flush_merge_3d(ctl, phys_enc->hw_pp->merge_3d->idx);
 
 	if (ctl->ops.update_pending_flush_cdm && phys_enc->hw_cdm)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
index 882c717859ce..07035ab77b79 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
@@ -275,6 +275,7 @@ static void _dpu_encoder_phys_wb_update_flush(struct dpu_encoder_phys *phys_enc)
 	struct dpu_hw_pingpong *hw_pp;
 	struct dpu_hw_cdm *hw_cdm;
 	u32 pending_flush = 0;
+	u32 mode_3d;
 
 	if (!phys_enc)
 		return;
@@ -283,6 +284,7 @@ static void _dpu_encoder_phys_wb_update_flush(struct dpu_encoder_phys *phys_enc)
 	hw_pp = phys_enc->hw_pp;
 	hw_ctl = phys_enc->hw_ctl;
 	hw_cdm = phys_enc->hw_cdm;
+	mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
 
 	DPU_DEBUG("[wb:%d]\n", hw_wb->idx - WB_0);
 
@@ -294,7 +296,8 @@ static void _dpu_encoder_phys_wb_update_flush(struct dpu_encoder_phys *phys_enc)
 	if (hw_ctl->ops.update_pending_flush_wb)
 		hw_ctl->ops.update_pending_flush_wb(hw_ctl, hw_wb->idx);
 
-	if (hw_ctl->ops.update_pending_flush_merge_3d && hw_pp && hw_pp->merge_3d)
+	if (mode_3d && hw_ctl->ops.update_pending_flush_merge_3d &&
+	    hw_pp && hw_pp->merge_3d)
 		hw_ctl->ops.update_pending_flush_merge_3d(hw_ctl,
 				hw_pp->merge_3d->idx);
 
diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c
index add72bbc28b1..4d55e3cf570f 100644
--- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c
+++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c
@@ -26,7 +26,7 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b
 	end_addr = base_addr + aligned_len;
 
 	if (!(*reg))
-		*reg = kzalloc(len_padded, GFP_KERNEL);
+		*reg = kvzalloc(len_padded, GFP_KERNEL);
 
 	if (*reg)
 		dump_addr = *reg;
@@ -48,20 +48,21 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b
 	}
 }
 
-static void msm_disp_state_print_regs(u32 **reg, u32 len, void __iomem *base_addr,
-		struct drm_printer *p)
+static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len,
+		void __iomem *base_addr, struct drm_printer *p)
 {
 	int i;
-	u32 *dump_addr = NULL;
 	void __iomem *addr;
 	u32 num_rows;
 
+	if (!dump_addr) {
+		drm_printf(p, "Registers not stored\n");
+		return;
+	}
+
 	addr = base_addr;
 	num_rows = len / REG_DUMP_ALIGN;
 
-	if (*reg)
-		dump_addr = *reg;
-
 	for (i = 0; i < num_rows; i++) {
 		drm_printf(p, "0x%lx : %08x %08x %08x %08x\n",
 				(unsigned long)(addr - base_addr),
@@ -89,7 +90,7 @@ void msm_disp_state_print(struct msm_disp_state *state, struct drm_printer *p)
 
 	list_for_each_entry_safe(block, tmp, &state->blocks, node) {
 		drm_printf(p, "====================%s================\n", block->name);
-		msm_disp_state_print_regs(&block->state, block->size, block->base_addr, p);
+		msm_disp_state_print_regs(block->state, block->size, block->base_addr, p);
 	}
 
 	drm_printf(p, "===================dpu drm state================\n");
@@ -161,7 +162,7 @@ void msm_disp_state_free(void *data)
 
 	list_for_each_entry_safe(block, tmp, &disp_state->blocks, node) {
 		list_del(&block->node);
-		kfree(block->state);
+		kvfree(block->state);
 		kfree(block);
 	}
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 185d7de0bf37..a98d24b7cb00 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -542,7 +542,7 @@ static unsigned long dsi_adjust_pclk_for_compression(const struct drm_display_mo
 
 	int new_htotal = mode->htotal - mode->hdisplay + new_hdisplay;
 
-	return new_htotal * mode->vtotal * drm_mode_vrefresh(mode);
+	return mult_frac(mode->clock * 1000u, new_htotal, mode->htotal);
 }
 
 static unsigned long dsi_get_pclk_rate(const struct drm_display_mode *mode,
@@ -550,7 +550,7 @@ static unsigned long dsi_get_pclk_rate(const struct drm_display_mode *mode,
 {
 	unsigned long pclk_rate;
 
-	pclk_rate = mode->clock * 1000;
+	pclk_rate = mode->clock * 1000u;
 
 	if (dsc)
 		pclk_rate = dsi_adjust_pclk_for_compression(mode, dsc);
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c
index 0e3a2b16a2ce..e6ffaf92d26d 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c
@@ -153,15 +153,6 @@ static inline u32 pll_get_pll_cmp(u64 fdata, unsigned long ref_clk)
 	return dividend - 1;
 }
 
-static inline u64 pll_cmp_to_fdata(u32 pll_cmp, unsigned long ref_clk)
-{
-	u64 fdata = ((u64)pll_cmp) * ref_clk * 10;
-
-	do_div(fdata, HDMI_PLL_CMP_CNT);
-
-	return fdata;
-}
-
 #define HDMI_REF_CLOCK_HZ ((u64)19200000)
 #define HDMI_MHZ_TO_HZ ((u64)1000000)
 static int pll_get_post_div(struct hdmi_8998_post_divider *pd, u64 bclk)
diff --git a/drivers/gpu/drm/panel/panel-himax-hx83102.c b/drivers/gpu/drm/panel/panel-himax-hx83102.c
index 6e4b7e4644ce..8b48bba18131 100644
--- a/drivers/gpu/drm/panel/panel-himax-hx83102.c
+++ b/drivers/gpu/drm/panel/panel-himax-hx83102.c
@@ -298,7 +298,7 @@ static int ivo_t109nw41_init(struct hx83102 *ctx)
 	msleep(60);
 
 	hx83102_enable_extended_cmds(&dsi_ctx, true);
-	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, HX83102_SETPOWER, 0x2c, 0xed, 0xed, 0x0f, 0xcf, 0x42,
+	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, HX83102_SETPOWER, 0x2c, 0xed, 0xed, 0x27, 0xe7, 0x52,
 				     0xf5, 0x39, 0x36, 0x36, 0x36, 0x36, 0x32, 0x8b, 0x11, 0x65, 0x00, 0x88,
 				     0xfa, 0xff, 0xff, 0x8f, 0xff, 0x08, 0xd6, 0x33);
 	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, HX83102_SETDISP, 0x00, 0x47, 0xb0, 0x80, 0x00, 0x12,
@@ -343,11 +343,11 @@ static int ivo_t109nw41_init(struct hx83102 *ctx)
 				     0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xa0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 				     0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 				     0x00, 0x00, 0x00, 0x00, 0x00, 0x00);
-	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, HX83102_SETGMA, 0x04, 0x04, 0x06, 0x0a, 0x0a, 0x05,
-				     0x12, 0x14, 0x17, 0x13, 0x2c, 0x33, 0x39, 0x4b, 0x4c, 0x56, 0x61, 0x78,
-				     0x7a, 0x41, 0x50, 0x68, 0x73, 0x04, 0x04, 0x06, 0x0a, 0x0a, 0x05, 0x12,
-				     0x14, 0x17, 0x13, 0x2c, 0x33, 0x39, 0x4b, 0x4c, 0x56, 0x61, 0x78, 0x7a,
-				     0x41, 0x50, 0x68, 0x73);
+	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, HX83102_SETGMA, 0x00, 0x07, 0x10, 0x17, 0x1c, 0x33,
+				     0x48, 0x50, 0x57, 0x50, 0x68, 0x6e, 0x71, 0x7f, 0x81, 0x8a, 0x8e, 0x9b,
+				     0x9c, 0x4d, 0x56, 0x5d, 0x73, 0x00, 0x07, 0x10, 0x17, 0x1c, 0x33, 0x48,
+				     0x50, 0x57, 0x50, 0x68, 0x6e, 0x71, 0x7f, 0x81, 0x8a, 0x8e, 0x9b, 0x9c,
+				     0x4d, 0x56, 0x5d, 0x73);
 	mipi_dsi_dcs_write_seq_multi(&dsi_ctx, HX83102_SETTP1, 0x07, 0x10, 0x10, 0x1a, 0x26, 0x9e,
 				     0x00, 0x4f, 0xa0, 0x14, 0x14, 0x00, 0x00, 0x00, 0x00, 0x12, 0x0a, 0x02,
 				     0x02, 0x00, 0x33, 0x02, 0x04, 0x18, 0x01);
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index 0f723292409e..fafed331e0a0 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -43,7 +43,7 @@ static uint32_t radeon_encoder_clones(struct drm_encoder *encoder)
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct drm_encoder *clone_encoder;
-	uint32_t index_mask = 0;
+	uint32_t index_mask = drm_encoder_mask(encoder);
 	int count;
 
 	/* DIG routing gets problematic */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
index 890a66a2361f..64bd7d74854e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
@@ -635,10 +635,8 @@ out:
 		kunmap_atomic(d.src_addr);
 	if (d.dst_addr)
 		kunmap_atomic(d.dst_addr);
-	if (src_pages)
-		kvfree(src_pages);
-	if (dst_pages)
-		kvfree(dst_pages);
+	kvfree(src_pages);
+	kvfree(dst_pages);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 3f4719b3c268..4e2807f5f94c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -62,7 +62,7 @@
 #define VMWGFX_DRIVER_MINOR 20
 #define VMWGFX_DRIVER_PATCHLEVEL 0
 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024)
-#define VMWGFX_MAX_DISPLAYS 16
+#define VMWGFX_NUM_DISPLAY_UNITS 8
 #define VMWGFX_CMD_BOUNCE_INIT_SIZE 32768
 
 #define VMWGFX_MIN_INITIAL_WIDTH 1280
@@ -82,7 +82,7 @@
 #define VMWGFX_NUM_GB_CONTEXT 256
 #define VMWGFX_NUM_GB_SHADER 20000
 #define VMWGFX_NUM_GB_SURFACE 32768
-#define VMWGFX_NUM_GB_SCREEN_TARGET VMWGFX_MAX_DISPLAYS
+#define VMWGFX_NUM_GB_SCREEN_TARGET VMWGFX_NUM_DISPLAY_UNITS
 #define VMWGFX_NUM_DXCONTEXT 256
 #define VMWGFX_NUM_DXQUERY 512
 #define VMWGFX_NUM_MOB (VMWGFX_NUM_GB_CONTEXT +\
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 288ed0bb75cb..63b8d7591253 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1283,7 +1283,6 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
 {
 	struct drm_device *dev = &dev_priv->drm;
 	struct vmw_framebuffer_surface *vfbs;
-	enum SVGA3dSurfaceFormat format;
 	struct vmw_surface *surface;
 	int ret;
 
@@ -1320,34 +1319,6 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
 		return -EINVAL;
 	}
 
-	switch (mode_cmd->pixel_format) {
-	case DRM_FORMAT_ARGB8888:
-		format = SVGA3D_A8R8G8B8;
-		break;
-	case DRM_FORMAT_XRGB8888:
-		format = SVGA3D_X8R8G8B8;
-		break;
-	case DRM_FORMAT_RGB565:
-		format = SVGA3D_R5G6B5;
-		break;
-	case DRM_FORMAT_XRGB1555:
-		format = SVGA3D_A1R5G5B5;
-		break;
-	default:
-		DRM_ERROR("Invalid pixel format: %p4cc\n",
-			  &mode_cmd->pixel_format);
-		return -EINVAL;
-	}
-
-	/*
-	 * For DX, surface format validation is done when surface->scanout
-	 * is set.
-	 */
-	if (!has_sm4_context(dev_priv) && format != surface->metadata.format) {
-		DRM_ERROR("Invalid surface format for requested mode.\n");
-		return -EINVAL;
-	}
-
 	vfbs = kzalloc(sizeof(*vfbs), GFP_KERNEL);
 	if (!vfbs) {
 		ret = -ENOMEM;
@@ -1539,6 +1510,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 		DRM_ERROR("Surface size cannot exceed %dx%d\n",
 			dev_priv->texture_max_width,
 			dev_priv->texture_max_height);
+		ret = -EINVAL;
 		goto err_out;
 	}
 
@@ -2225,7 +2197,7 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_vmw_update_layout_arg *arg =
 		(struct drm_vmw_update_layout_arg *)data;
-	void __user *user_rects;
+	const void __user *user_rects;
 	struct drm_vmw_rect *rects;
 	struct drm_rect *drm_rects;
 	unsigned rects_size;
@@ -2237,6 +2209,8 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 					    VMWGFX_MIN_INITIAL_HEIGHT};
 		vmw_du_update_layout(dev_priv, 1, &def_rect);
 		return 0;
+	} else if (arg->num_outputs > VMWGFX_NUM_DISPLAY_UNITS) {
+		return -E2BIG;
 	}
 
 	rects_size = arg->num_outputs * sizeof(struct drm_vmw_rect);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index 6141fadf81ef..2a6c6d6581e0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -199,9 +199,6 @@ struct vmw_kms_dirty {
 	s32 unit_y2;
 };
 
-#define VMWGFX_NUM_DISPLAY_UNITS 8
-
-
 #define vmw_framebuffer_to_vfb(x) \
 	container_of(x, struct vmw_framebuffer, base)
 #define vmw_framebuffer_to_vfbs(x) \
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index fab155a68054..82d18b88f4a7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -886,6 +886,10 @@ static int vmw_stdu_connector_atomic_check(struct drm_connector *conn,
 	struct drm_crtc_state *new_crtc_state;
 
 	conn_state = drm_atomic_get_connector_state(state, conn);
+
+	if (IS_ERR(conn_state))
+		return PTR_ERR(conn_state);
+
 	du = vmw_connector_to_stdu(conn);
 
 	if (!conn_state->crtc)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 1625b30d9970..5721c74da3e0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -2276,9 +2276,12 @@ int vmw_dumb_create(struct drm_file *file_priv,
 	const struct SVGA3dSurfaceDesc *desc = vmw_surface_get_desc(format);
 	SVGA3dSurfaceAllFlags flags = SVGA3D_SURFACE_HINT_TEXTURE |
 				      SVGA3D_SURFACE_HINT_RENDERTARGET |
-				      SVGA3D_SURFACE_SCREENTARGET |
-				      SVGA3D_SURFACE_BIND_SHADER_RESOURCE |
-				      SVGA3D_SURFACE_BIND_RENDER_TARGET;
+				      SVGA3D_SURFACE_SCREENTARGET;
+
+	if (vmw_surface_is_dx_screen_target_format(format)) {
+		flags |= SVGA3D_SURFACE_BIND_SHADER_RESOURCE |
+			 SVGA3D_SURFACE_BIND_RENDER_TARGET;
+	}
 
 	/*
 	 * Without mob support we're just going to use raw memory buffer
diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index ac9c437e103d..00ad34ed73a5 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -393,9 +393,6 @@
 
 #define XE2_GLOBAL_INVAL			XE_REG(0xb404)
 
-#define SCRATCH1LPFC				XE_REG(0xb474)
-#define   EN_L3_RW_CCS_CACHE_FLUSH		REG_BIT(0)
-
 #define XE2LPM_L3SQCREG2			XE_REG_MCR(0xb604)
 
 #define XE2LPM_L3SQCREG3			XE_REG_MCR(0xb608)
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 5a63d135ba96..0a9ffc19e92f 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -980,13 +980,13 @@ void xe_device_declare_wedged(struct xe_device *xe)
 		return;
 	}
 
+	xe_pm_runtime_get_noresume(xe);
+
 	if (drmm_add_action_or_reset(&xe->drm, xe_device_wedged_fini, xe)) {
 		drm_err(&xe->drm, "Failed to register xe_device_wedged_fini clean-up. Although device is wedged.\n");
 		return;
 	}
 
-	xe_pm_runtime_get_noresume(xe);
-
 	if (!atomic_xchg(&xe->wedged.flag, 1)) {
 		xe->needs_flr_on_fini = true;
 		drm_err(&xe->drm,
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 7b38485817dc..f23ac1e2ed88 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -41,11 +41,6 @@
  * user knows an exec writes to a BO and reads from the BO in the next exec, it
  * is the user's responsibility to pass in / out fence between the two execs).
  *
- * Implicit dependencies for external BOs are handled by using the dma-buf
- * implicit dependency uAPI (TODO: add link). To make this works each exec must
- * install the job's fence into the DMA_RESV_USAGE_WRITE slot of every external
- * BO mapped in the VM.
- *
  * We do not allow a user to trigger a bind at exec time rather we have a VM
  * bind IOCTL which uses the same in / out fence interface as exec. In that
  * sense, a VM bind is basically the same operation as an exec from the user
@@ -59,8 +54,8 @@
  * behind any pending kernel operations on any external BOs in VM or any BOs
  * private to the VM. This is accomplished by the rebinds waiting on BOs
  * DMA_RESV_USAGE_KERNEL slot (kernel ops) and kernel ops waiting on all BOs
- * slots (inflight execs are in the DMA_RESV_USAGE_BOOKING for private BOs and
- * in DMA_RESV_USAGE_WRITE for external BOs).
+ * slots (inflight execs are in the DMA_RESV_USAGE_BOOKKEEP for private BOs and
+ * for external BOs).
  *
  * Rebinds / dma-resv usage applies to non-compute mode VMs only as for compute
  * mode VMs we use preempt fences and a rebind worker (TODO: add link).
@@ -304,7 +299,8 @@ retry:
 	xe_sched_job_arm(job);
 	if (!xe_vm_in_lr_mode(vm))
 		drm_gpuvm_resv_add_fence(&vm->gpuvm, exec, &job->drm.s_fence->finished,
-					 DMA_RESV_USAGE_BOOKKEEP, DMA_RESV_USAGE_WRITE);
+					 DMA_RESV_USAGE_BOOKKEEP,
+					 DMA_RESV_USAGE_BOOKKEEP);
 
 	for (i = 0; i < num_syncs; i++) {
 		xe_sync_entry_signal(&syncs[i], &job->drm.s_fence->finished);
diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.h b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
index 5ad5629a6c60..64b2ae6839db 100644
--- a/drivers/gpu/drm/xe/xe_gpu_scheduler.h
+++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
@@ -63,7 +63,9 @@ xe_sched_invalidate_job(struct xe_sched_job *job, int threshold)
 static inline void xe_sched_add_pending_job(struct xe_gpu_scheduler *sched,
 					    struct xe_sched_job *job)
 {
+	spin_lock(&sched->base.job_list_lock);
 	list_add(&job->drm.list, &sched->base.pending_list);
+	spin_unlock(&sched->base.job_list_lock);
 }
 
 static inline
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index ea65cf59372c..d5fd6a089b7c 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -108,7 +108,6 @@ static void xe_gt_enable_host_l2_vram(struct xe_gt *gt)
 		return;
 
 	if (!xe_gt_is_media_type(gt)) {
-		xe_mmio_write32(gt, SCRATCH1LPFC, EN_L3_RW_CCS_CACHE_FLUSH);
 		reg = xe_gt_mcr_unicast_read_any(gt, XE2_GAMREQSTRM_CTRL);
 		reg |= CG_DIS_CNTLBUS;
 		xe_gt_mcr_multicast_write(gt, XE2_GAMREQSTRM_CTRL, reg);
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index cca9cf536f76..bbb9e411d21f 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -37,6 +37,15 @@ static long tlb_timeout_jiffies(struct xe_gt *gt)
 	return hw_tlb_timeout + 2 * delay;
 }
 
+static void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence)
+{
+	if (WARN_ON_ONCE(!fence->gt))
+		return;
+
+	xe_pm_runtime_put(gt_to_xe(fence->gt));
+	fence->gt = NULL; /* fini() should be called once */
+}
+
 static void
 __invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence)
 {
@@ -204,7 +213,7 @@ static int send_tlb_invalidation(struct xe_guc *guc,
 						   tlb_timeout_jiffies(gt));
 		}
 		spin_unlock_irq(&gt->tlb_invalidation.pending_lock);
-	} else if (ret < 0) {
+	} else {
 		__invalidation_fence_signal(xe, fence);
 	}
 	if (!ret) {
@@ -267,10 +276,8 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
 
 		xe_gt_tlb_invalidation_fence_init(gt, &fence, true);
 		ret = xe_gt_tlb_invalidation_guc(gt, &fence);
-		if (ret < 0) {
-			xe_gt_tlb_invalidation_fence_fini(&fence);
+		if (ret)
 			return ret;
-		}
 
 		xe_gt_tlb_invalidation_fence_wait(&fence);
 	} else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) {
@@ -496,7 +503,8 @@ static const struct dma_fence_ops invalidation_fence_ops = {
  * @stack: fence is stack variable
  *
  * Initialize TLB invalidation fence for use. xe_gt_tlb_invalidation_fence_fini
- * must be called if fence is not signaled.
+ * will be automatically called when fence is signalled (all fences must signal),
+ * even on error.
  */
 void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
 				       struct xe_gt_tlb_invalidation_fence *fence,
@@ -516,14 +524,3 @@ void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
 		dma_fence_get(&fence->base);
 	fence->gt = gt;
 }
-
-/**
- * xe_gt_tlb_invalidation_fence_fini - Finalize TLB invalidation fence
- * @fence: TLB invalidation fence to finalize
- *
- * Drop PM ref which fence took durinig init.
- */
-void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence)
-{
-	xe_pm_runtime_put(gt_to_xe(fence->gt));
-}
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
index a84065fa324c..f430d5797af7 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
@@ -28,7 +28,6 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
 void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
 				       struct xe_gt_tlb_invalidation_fence *fence,
 				       bool stack);
-void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence);
 
 static inline void
 xe_gt_tlb_invalidation_fence_wait(struct xe_gt_tlb_invalidation_fence *fence)
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 63495007f336..8a9254e5af6e 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1030,10 +1030,13 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 
 	/*
 	 * TDR has fired before free job worker. Common if exec queue
-	 * immediately closed after last fence signaled.
+	 * immediately closed after last fence signaled. Add back to pending
+	 * list so job can be freed and kick scheduler ensuring free job is not
+	 * lost.
 	 */
 	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &job->fence->flags)) {
-		guc_exec_queue_free_job(drm_job);
+		xe_sched_add_pending_job(sched, job);
+		xe_sched_submission_start(sched);
 
 		return DRM_GPU_SCHED_STAT_NOMINAL;
 	}
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 28d9bb3b825d..848da8e68c7a 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -161,7 +161,11 @@ query_engine_cycles(struct xe_device *xe,
 			  cpu_clock);
 
 	xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL);
-	resp.width = 36;
+
+	if (GRAPHICS_VER(xe) >= 20)
+		resp.width = 64;
+	else
+		resp.width = 36;
 
 	/* Only write to the output fields of user query */
 	if (put_user(resp.cpu_timestamp, &query_ptr->cpu_timestamp))
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index bb3c2a830362..c6cf227ead40 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -58,7 +58,7 @@ static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr,
 	if (!access_ok(ptr, sizeof(*ptr)))
 		return ERR_PTR(-EFAULT);
 
-	ufence = kmalloc(sizeof(*ufence), GFP_KERNEL);
+	ufence = kzalloc(sizeof(*ufence), GFP_KERNEL);
 	if (!ufence)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index ce9dca4d4e87..c99380271de6 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3199,10 +3199,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 
 			ret = xe_gt_tlb_invalidation_vma(tile->primary_gt,
 							 &fence[fence_id], vma);
-			if (ret < 0) {
-				xe_gt_tlb_invalidation_fence_fini(&fence[fence_id]);
+			if (ret)
 				goto wait;
-			}
 			++fence_id;
 
 			if (!tile->media_gt)
@@ -3214,10 +3212,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 
 			ret = xe_gt_tlb_invalidation_vma(tile->media_gt,
 							 &fence[fence_id], vma);
-			if (ret < 0) {
-				xe_gt_tlb_invalidation_fence_fini(&fence[fence_id]);
+			if (ret)
 				goto wait;
-			}
 			++fence_id;
 		}
 	}
diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index d424992514a4..353936a0f877 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -710,6 +710,10 @@ static const struct xe_rtp_entry_sr lrc_was[] = {
 			     DIS_PARTIAL_AUTOSTRIP |
 			     DIS_AUTOSTRIP))
 	},
+	{ XE_RTP_NAME("15016589081"),
+	  XE_RTP_RULES(GRAPHICS_VERSION(2004), ENGINE_CLASS(RENDER)),
+	  XE_RTP_ACTIONS(SET(CHICKEN_RASTER_1, DIS_CLIP_NEGATIVE_BOUNDING_BOX))
+	},
 
 	/* Xe2_HPG */
 	{ XE_RTP_NAME("15010599737"),
diff --git a/drivers/gpu/drm/xe/xe_wait_user_fence.c b/drivers/gpu/drm/xe/xe_wait_user_fence.c
index d46fa8374980..f5deb81eba01 100644
--- a/drivers/gpu/drm/xe/xe_wait_user_fence.c
+++ b/drivers/gpu/drm/xe/xe_wait_user_fence.c
@@ -169,9 +169,6 @@ int xe_wait_user_fence_ioctl(struct drm_device *dev, void *data,
 			args->timeout = 0;
 	}
 
-	if (!timeout && !(err < 0))
-		err = -ETIME;
-
 	if (q)
 		xe_exec_queue_put(q);
 
diff --git a/drivers/gpu/host1x/context.c b/drivers/gpu/host1x/context.c
index 955c971c528d..a6f6779662a3 100644
--- a/drivers/gpu/host1x/context.c
+++ b/drivers/gpu/host1x/context.c
@@ -58,6 +58,7 @@ int host1x_memory_context_list_init(struct host1x *host1x)
 		ctx->dev.parent = host1x->dev;
 		ctx->dev.release = host1x_memory_context_release;
 
+		ctx->dev.dma_parms = &ctx->dma_parms;
 		dma_set_max_seg_size(&ctx->dev, UINT_MAX);
 
 		err = device_add(&ctx->dev);
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index b62e4f0e8130..e98528777faa 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -625,12 +625,6 @@ static int host1x_probe(struct platform_device *pdev)
 		goto free_contexts;
 	}
 
-	err = host1x_intr_init(host);
-	if (err) {
-		dev_err(&pdev->dev, "failed to initialize interrupts\n");
-		goto deinit_syncpt;
-	}
-
 	pm_runtime_enable(&pdev->dev);
 
 	err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
@@ -642,6 +636,12 @@ static int host1x_probe(struct platform_device *pdev)
 	if (err)
 		goto pm_disable;
 
+	err = host1x_intr_init(host);
+	if (err) {
+		dev_err(&pdev->dev, "failed to initialize interrupts\n");
+		goto pm_put;
+	}
+
 	host1x_debug_init(host);
 
 	err = host1x_register(host);
@@ -658,13 +658,11 @@ unregister:
 	host1x_unregister(host);
 deinit_debugfs:
 	host1x_debug_deinit(host);
-
+	host1x_intr_deinit(host);
+pm_put:
 	pm_runtime_put_sync_suspend(&pdev->dev);
 pm_disable:
 	pm_runtime_disable(&pdev->dev);
-
-	host1x_intr_deinit(host);
-deinit_syncpt:
 	host1x_syncpt_deinit(host);
 free_contexts:
 	host1x_memory_context_list_free(&host->context_list);
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index 9c8119ed13a4..c4dde3aafcac 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -466,6 +466,7 @@ struct host1x_memory_context {
 	refcount_t ref;
 	struct pid *owner;
 
+	struct device_dma_parameters dma_parms;
 	struct device dev;
 	u64 dma_mask;
 	u32 stream_id;