ASoc: simple-mux: Allow to specify an idle-state

Merge series from "Hendrik v. Raven" <h.v.raven@merzmedtech.de>:

This series adds support for the idle-state property from the mux
framework to the simple-mux audio variant. It allows to specify the state
of the mux when it is not in use.

139 files changed, 1266 insertions, 898 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index f85ace0384d2..7dd55ed57c1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -147,6 +147,7 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif,
 					   struct acpi_buffer *params)
 {
 	acpi_status status;
+	union acpi_object *obj;
 	union acpi_object atif_arg_elements[2];
 	struct acpi_object_list atif_arg;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -169,16 +170,24 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif,
 
 	status = acpi_evaluate_object(atif->handle, NULL, &atif_arg,
 				      &buffer);
+	obj = (union acpi_object *)buffer.pointer;
 
-	/* Fail only if calling the method fails and ATIF is supported */
-	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
+	/* Fail if calling the method fails */
+	if (ACPI_FAILURE(status)) {
 		DRM_DEBUG_DRIVER("failed to evaluate ATIF got %s\n",
 				 acpi_format_exception(status));
-		kfree(buffer.pointer);
+		kfree(obj);
 		return NULL;
 	}
 
-	return buffer.pointer;
+	if (obj->type != ACPI_TYPE_BUFFER) {
+		DRM_DEBUG_DRIVER("bad object returned from ATIF: %d\n",
+				 obj->type);
+		kfree(obj);
+		return NULL;
+	}
+
+	return obj;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index ce5ca304dba9..fa572ba7f9fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1439,8 +1439,8 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
 	list_add_tail(&vm->vm_list_node,
 			&(vm->process_info->vm_list_head));
 	vm->process_info->n_vms++;
-
-	*ef = dma_fence_get(&vm->process_info->eviction_fence->base);
+	if (ef)
+		*ef = dma_fence_get(&vm->process_info->eviction_fence->base);
 	mutex_unlock(&vm->process_info->lock);
 
 	return 0;
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_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index cbef720de779..9da4414de617 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -402,7 +402,7 @@ static ssize_t amdgpu_debugfs_gprwave_read(struct file *f, char __user *buf, siz
 	int r;
 	uint32_t *data, x;
 
-	if (size & 0x3 || *pos & 0x3)
+	if (size > 4096 || size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
@@ -1648,7 +1648,7 @@ int amdgpu_debugfs_regs_init(struct amdgpu_device *adev)
 
 	for (i = 0; i < ARRAY_SIZE(debugfs_regs); i++) {
 		ent = debugfs_create_file(debugfs_regs_names[i],
-					  S_IFREG | 0444, root,
+					  S_IFREG | 0400, root,
 					  adev, debugfs_regs[i]);
 		if (!i && !IS_ERR_OR_NULL(ent))
 			i_size_write(ent->d_inode, adev->rmmio_size);
@@ -2100,11 +2100,11 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 	amdgpu_securedisplay_debugfs_init(adev);
 	amdgpu_fw_attestation_debugfs_init(adev);
 
-	debugfs_create_file("amdgpu_evict_vram", 0444, root, adev,
+	debugfs_create_file("amdgpu_evict_vram", 0400, root, adev,
 			    &amdgpu_evict_vram_fops);
-	debugfs_create_file("amdgpu_evict_gtt", 0444, root, adev,
+	debugfs_create_file("amdgpu_evict_gtt", 0400, root, adev,
 			    &amdgpu_evict_gtt_fops);
-	debugfs_create_file("amdgpu_test_ib", 0444, root, adev,
+	debugfs_create_file("amdgpu_test_ib", 0400, root, adev,
 			    &amdgpu_debugfs_test_ib_fops);
 	debugfs_create_file("amdgpu_vm_info", 0444, root, adev,
 			    &amdgpu_debugfs_vm_info_fops);
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/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
index 5e8833e4fed2..ccfd2a4b4acc 100644
--- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
+++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
@@ -482,7 +482,7 @@ static bool __aqua_vanjaram_is_valid_mode(struct amdgpu_xcp_mgr *xcp_mgr,
 	case AMDGPU_SPX_PARTITION_MODE:
 		return adev->gmc.num_mem_partitions == 1 && num_xcc > 0;
 	case AMDGPU_DPX_PARTITION_MODE:
-		return adev->gmc.num_mem_partitions != 8 && (num_xcc % 4) == 0;
+		return adev->gmc.num_mem_partitions <= 2 && (num_xcc % 4) == 0;
 	case AMDGPU_TPX_PARTITION_MODE:
 		return (adev->gmc.num_mem_partitions == 1 ||
 			adev->gmc.num_mem_partitions == 3) &&
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/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
index a8763496aed3..9288f37a3cc5 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -51,6 +51,12 @@ MODULE_FIRMWARE("amdgpu/sdma_7_0_1.bin");
 #define SDMA0_HYP_DEC_REG_END 0x589a
 #define SDMA1_HYP_DEC_REG_OFFSET 0x20
 
+/*define for compression field for sdma7*/
+#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_offset 0
+#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_mask   0x00000001
+#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_shift  16
+#define SDMA_PKT_CONSTANT_FILL_HEADER_COMPRESS(x) (((x) & SDMA_PKT_CONSTANT_FILL_HEADER_compress_mask) << SDMA_PKT_CONSTANT_FILL_HEADER_compress_shift)
+
 static const struct amdgpu_hwip_reg_entry sdma_reg_list_7_0[] = {
 	SOC15_REG_ENTRY_STR(GC, 0, regSDMA0_STATUS_REG),
 	SOC15_REG_ENTRY_STR(GC, 0, regSDMA0_STATUS1_REG),
@@ -1724,7 +1730,8 @@ static void sdma_v7_0_emit_fill_buffer(struct amdgpu_ib *ib,
 				       uint64_t dst_offset,
 				       uint32_t byte_count)
 {
-	ib->ptr[ib->length_dw++] = SDMA_PKT_COPY_LINEAR_HEADER_OP(SDMA_OP_CONST_FILL);
+	ib->ptr[ib->length_dw++] = SDMA_PKT_CONSTANT_FILL_HEADER_OP(SDMA_OP_CONST_FILL) |
+		SDMA_PKT_CONSTANT_FILL_HEADER_COMPRESS(1);
 	ib->ptr[ib->length_dw++] = lower_32_bits(dst_offset);
 	ib->ptr[ib->length_dw++] = upper_32_bits(dst_offset);
 	ib->ptr[ib->length_dw++] = src_data;
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 d07acf1b2f93..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);
@@ -1702,12 +1702,15 @@ int kfd_process_device_init_vm(struct kfd_process_device *pdd,
 
 	ret = amdgpu_amdkfd_gpuvm_acquire_process_vm(dev->adev, avm,
 						     &p->kgd_process_info,
-						     &ef);
+						     p->ef ? NULL : &ef);
 	if (ret) {
 		dev_err(dev->adev->dev, "Failed to create process VM object\n");
 		return ret;
 	}
-	RCU_INIT_POINTER(p->ef, ef);
+
+	if (!p->ef)
+		RCU_INIT_POINTER(p->ef, ef);
+
 	pdd->drm_priv = drm_file->private_data;
 
 	ret = kfd_process_device_reserve_ib_mem(pdd);
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/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 60c617fcc97e..07e9ce99694f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2972,10 +2972,11 @@ static int dm_suspend(void *handle)
 
 	hpd_rx_irq_work_suspend(dm);
 
-	if (adev->dm.dc->caps.ips_support)
-		dc_allow_idle_optimizations(adev->dm.dc, true);
-
 	dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D3);
+
+	if (dm->dc->caps.ips_support && adev->in_s0ix)
+		dc_allow_idle_optimizations(dm->dc, true);
+
 	dc_dmub_srv_set_power_state(dm->dc->ctx->dmub_srv, DC_ACPI_CM_POWER_STATE_D3);
 
 	return 0;
@@ -8373,7 +8374,8 @@ static void manage_dm_interrupts(struct amdgpu_device *adev,
 		if (amdgpu_ip_version(adev, DCE_HWIP, 0) <
 		    IP_VERSION(3, 5, 0) ||
 		    acrtc_state->stream->link->psr_settings.psr_version <
-		    DC_PSR_VERSION_UNSUPPORTED) {
+		    DC_PSR_VERSION_UNSUPPORTED ||
+		    !(adev->flags & AMD_IS_APU)) {
 			timing = &acrtc_state->stream->timing;
 
 			/* at least 2 frames */
@@ -9427,6 +9429,7 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state,
 	bool mode_set_reset_required = false;
 	u32 i;
 	struct dc_commit_streams_params params = {dc_state->streams, dc_state->stream_count};
+	bool set_backlight_level = false;
 
 	/* Disable writeback */
 	for_each_old_connector_in_state(state, connector, old_con_state, i) {
@@ -9546,6 +9549,7 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state,
 			acrtc->hw_mode = new_crtc_state->mode;
 			crtc->hwmode = new_crtc_state->mode;
 			mode_set_reset_required = true;
+			set_backlight_level = true;
 		} else if (modereset_required(new_crtc_state)) {
 			drm_dbg_atomic(dev,
 				       "Atomic commit: RESET. crtc id %d:[%p]\n",
@@ -9597,6 +9601,19 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state,
 				acrtc->otg_inst = status->primary_otg_inst;
 		}
 	}
+
+	/* During boot up and resume the DC layer will reset the panel brightness
+	 * to fix a flicker issue.
+	 * It will cause the dm->actual_brightness is not the current panel brightness
+	 * level. (the dm->brightness is the correct panel level)
+	 * So we set the backlight level with dm->brightness value after set mode
+	 */
+	if (set_backlight_level) {
+		for (i = 0; i < dm->num_of_edps; i++) {
+			if (dm->backlight_dev[i])
+				amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]);
+		}
+	}
 }
 
 static void dm_set_writeback(struct amdgpu_display_manager *dm,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 069e0195e50a..eea317dcbe8c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -44,6 +44,7 @@
 
 #include "dm_helpers.h"
 #include "ddc_service_types.h"
+#include "clk_mgr.h"
 
 static u32 edid_extract_panel_id(struct edid *edid)
 {
@@ -1121,6 +1122,8 @@ bool dm_helpers_dp_handle_test_pattern_request(
 	struct pipe_ctx *pipe_ctx = NULL;
 	struct amdgpu_dm_connector *aconnector = link->priv;
 	struct drm_device *dev = aconnector->base.dev;
+	struct dc_state *dc_state = ctx->dc->current_state;
+	struct clk_mgr *clk_mgr = ctx->dc->clk_mgr;
 	int i;
 
 	for (i = 0; i < MAX_PIPES; i++) {
@@ -1221,6 +1224,16 @@ bool dm_helpers_dp_handle_test_pattern_request(
 	pipe_ctx->stream->test_pattern.type = test_pattern;
 	pipe_ctx->stream->test_pattern.color_space = test_pattern_color_space;
 
+	/* Temp W/A for compliance test failure */
+	dc_state->bw_ctx.bw.dcn.clk.p_state_change_support = false;
+	dc_state->bw_ctx.bw.dcn.clk.dramclk_khz = clk_mgr->dc_mode_softmax_enabled ?
+		clk_mgr->bw_params->dc_mode_softmax_memclk : clk_mgr->bw_params->max_memclk_mhz;
+	dc_state->bw_ctx.bw.dcn.clk.idle_dramclk_khz = dc_state->bw_ctx.bw.dcn.clk.dramclk_khz;
+	ctx->dc->clk_mgr->funcs->update_clocks(
+			ctx->dc->clk_mgr,
+			dc_state,
+			false);
+
 	dc_link_dp_set_test_pattern(
 		(struct dc_link *) link,
 		test_pattern,
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 0d8498ab9b23..be8fbb04ad98 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -3127,7 +3127,9 @@ static enum bp_result bios_parser_get_vram_info(
 	struct atom_data_revision revision;
 
 	// vram info moved to umc_info for DCN4x
-	if (info && DATA_TABLES(umc_info)) {
+	if (dcb->ctx->dce_version >= DCN_VERSION_4_01 &&
+		dcb->ctx->dce_version < DCN_VERSION_MAX &&
+		info && DATA_TABLES(umc_info)) {
 		header = GET_IMAGE(struct atom_common_table_header,
 					DATA_TABLES(umc_info));
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 5c39390ecbd5..a88f1b6ea64c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -5065,11 +5065,26 @@ static bool update_planes_and_stream_v3(struct dc *dc,
 	return true;
 }
 
+static void clear_update_flags(struct dc_surface_update *srf_updates,
+	int surface_count, struct dc_stream_state *stream)
+{
+	int i;
+
+	if (stream)
+		stream->update_flags.raw = 0;
+
+	for (i = 0; i < surface_count; i++)
+		if (srf_updates[i].surface)
+			srf_updates[i].surface->update_flags.raw = 0;
+}
+
 bool dc_update_planes_and_stream(struct dc *dc,
 		struct dc_surface_update *srf_updates, int surface_count,
 		struct dc_stream_state *stream,
 		struct dc_stream_update *stream_update)
 {
+	bool ret = false;
+
 	dc_exit_ips_for_hw_access(dc);
 	/*
 	 * update planes and stream version 3 separates FULL and FAST updates
@@ -5086,10 +5101,16 @@ bool dc_update_planes_and_stream(struct dc *dc,
 	 * features as they are now transparent to the new sequence.
 	 */
 	if (dc->ctx->dce_version >= DCN_VERSION_4_01)
-		return update_planes_and_stream_v3(dc, srf_updates,
+		ret = update_planes_and_stream_v3(dc, srf_updates,
 				surface_count, stream, stream_update);
-	return update_planes_and_stream_v2(dc, srf_updates,
+	else
+		ret = update_planes_and_stream_v2(dc, srf_updates,
 			surface_count, stream, stream_update);
+
+	if (ret)
+		clear_update_flags(srf_updates, surface_count, stream);
+
+	return ret;
 }
 
 void dc_commit_updates_for_stream(struct dc *dc,
@@ -5099,6 +5120,8 @@ void dc_commit_updates_for_stream(struct dc *dc,
 		struct dc_stream_update *stream_update,
 		struct dc_state *state)
 {
+	bool ret = false;
+
 	dc_exit_ips_for_hw_access(dc);
 	/* TODO: Since change commit sequence can have a huge impact,
 	 * we decided to only enable it for DCN3x. However, as soon as
@@ -5106,17 +5129,17 @@ void dc_commit_updates_for_stream(struct dc *dc,
 	 * the new sequence for all ASICs.
 	 */
 	if (dc->ctx->dce_version >= DCN_VERSION_4_01) {
-		update_planes_and_stream_v3(dc, srf_updates, surface_count,
+		ret = update_planes_and_stream_v3(dc, srf_updates, surface_count,
 				stream, stream_update);
-		return;
-	}
-	if (dc->ctx->dce_version >= DCN_VERSION_3_2) {
-		update_planes_and_stream_v2(dc, srf_updates, surface_count,
+	} else if (dc->ctx->dce_version >= DCN_VERSION_3_2) {
+		ret = update_planes_and_stream_v2(dc, srf_updates, surface_count,
 				stream, stream_update);
-		return;
-	}
-	update_planes_and_stream_v1(dc, srf_updates, surface_count, stream,
-			stream_update, state);
+	} else
+		ret = update_planes_and_stream_v1(dc, srf_updates, surface_count, stream,
+				stream_update, state);
+
+	if (ret)
+		clear_update_flags(srf_updates, surface_count, stream);
 }
 
 uint8_t dc_get_current_stream_count(struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_policy.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_policy.c
index 11c904ae2958..c4c52173ef22 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_policy.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_policy.c
@@ -303,6 +303,7 @@ void build_unoptimized_policy_settings(enum dml_project_id project, struct dml_m
 	if (project == dml_project_dcn35 ||
 		project == dml_project_dcn351) {
 		policy->DCCProgrammingAssumesScanDirectionUnknownFinal = false;
+		policy->EnhancedPrefetchScheduleAccelerationFinal = 0;
 		policy->AllowForPStateChangeOrStutterInVBlankFinal = dml_prefetch_support_uclk_fclk_and_stutter_if_possible; /*new*/
 		policy->UseOnlyMaxPrefetchModes = 1;
 	}
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index 3cd52e7a9c77..95838c7ab054 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -841,6 +841,8 @@ bool is_psr_su_specific_panel(struct dc_link *link)
 				isPSRSUSupported = false;
 			else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03)
 				isPSRSUSupported = false;
+			else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x01)
+				isPSRSUSupported = false;
 			else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1)
 				isPSRSUSupported = true;
 		}
diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h
index 9118fcddbf11..227bf0e84a13 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h
@@ -60,7 +60,7 @@ struct vi_dpm_level {
 
 struct vi_dpm_table {
 	uint32_t count;
-	struct vi_dpm_level dpm_level[] __counted_by(count);
+	struct vi_dpm_level dpm_level[];
 };
 
 #define PCIE_PERF_REQ_REMOVE_REGISTRY   0
@@ -91,7 +91,7 @@ struct phm_set_power_state_input {
 
 struct phm_clock_array {
 	uint32_t count;
-	uint32_t values[] __counted_by(count);
+	uint32_t values[];
 };
 
 struct phm_clock_voltage_dependency_record {
@@ -123,7 +123,7 @@ struct phm_acpclock_voltage_dependency_record {
 
 struct phm_clock_voltage_dependency_table {
 	uint32_t count;
-	struct phm_clock_voltage_dependency_record entries[] __counted_by(count);
+	struct phm_clock_voltage_dependency_record entries[];
 };
 
 struct phm_phase_shedding_limits_record {
@@ -140,7 +140,7 @@ struct phm_uvd_clock_voltage_dependency_record {
 
 struct phm_uvd_clock_voltage_dependency_table {
 	uint8_t count;
-	struct phm_uvd_clock_voltage_dependency_record entries[] __counted_by(count);
+	struct phm_uvd_clock_voltage_dependency_record entries[];
 };
 
 struct phm_acp_clock_voltage_dependency_record {
@@ -150,7 +150,7 @@ struct phm_acp_clock_voltage_dependency_record {
 
 struct phm_acp_clock_voltage_dependency_table {
 	uint32_t count;
-	struct phm_acp_clock_voltage_dependency_record entries[] __counted_by(count);
+	struct phm_acp_clock_voltage_dependency_record entries[];
 };
 
 struct phm_vce_clock_voltage_dependency_record {
@@ -161,32 +161,32 @@ struct phm_vce_clock_voltage_dependency_record {
 
 struct phm_phase_shedding_limits_table {
 	uint32_t count;
-	struct phm_phase_shedding_limits_record  entries[] __counted_by(count);
+	struct phm_phase_shedding_limits_record  entries[];
 };
 
 struct phm_vceclock_voltage_dependency_table {
 	uint8_t count;
-	struct phm_vceclock_voltage_dependency_record entries[] __counted_by(count);
+	struct phm_vceclock_voltage_dependency_record entries[];
 };
 
 struct phm_uvdclock_voltage_dependency_table {
 	uint8_t count;
-	struct phm_uvdclock_voltage_dependency_record entries[] __counted_by(count);
+	struct phm_uvdclock_voltage_dependency_record entries[];
 };
 
 struct phm_samuclock_voltage_dependency_table {
 	uint8_t count;
-	struct phm_samuclock_voltage_dependency_record entries[] __counted_by(count);
+	struct phm_samuclock_voltage_dependency_record entries[];
 };
 
 struct phm_acpclock_voltage_dependency_table {
 	uint32_t count;
-	struct phm_acpclock_voltage_dependency_record entries[] __counted_by(count);
+	struct phm_acpclock_voltage_dependency_record entries[];
 };
 
 struct phm_vce_clock_voltage_dependency_table {
 	uint8_t count;
-	struct phm_vce_clock_voltage_dependency_record entries[] __counted_by(count);
+	struct phm_vce_clock_voltage_dependency_record entries[];
 };
 
 
@@ -393,7 +393,7 @@ union phm_cac_leakage_record {
 
 struct phm_cac_leakage_table {
 	uint32_t count;
-	union phm_cac_leakage_record entries[] __counted_by(count);
+	union phm_cac_leakage_record entries[];
 };
 
 struct phm_samu_clock_voltage_dependency_record {
@@ -404,7 +404,7 @@ struct phm_samu_clock_voltage_dependency_record {
 
 struct phm_samu_clock_voltage_dependency_table {
 	uint8_t count;
-	struct phm_samu_clock_voltage_dependency_record entries[] __counted_by(count);
+	struct phm_samu_clock_voltage_dependency_record entries[];
 };
 
 struct phm_cac_tdp_table {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index bb3bc68dfc39..ee1bcfaae3e3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1234,6 +1234,14 @@ static void smu_init_xgmi_plpd_mode(struct smu_context *smu)
 	}
 }
 
+static bool smu_is_workload_profile_available(struct smu_context *smu,
+					      u32 profile)
+{
+	if (profile >= PP_SMC_POWER_PROFILE_COUNT)
+		return false;
+	return smu->workload_map && smu->workload_map[profile].valid_mapping;
+}
+
 static int smu_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1251,21 +1259,33 @@ static int smu_sw_init(void *handle)
 	smu->watermarks_bitmap = 0;
 	smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
 	smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
+	smu->user_dpm_profile.user_workload_mask = 0;
 
 	atomic_set(&smu->smu_power.power_gate.vcn_gated, 1);
 	atomic_set(&smu->smu_power.power_gate.jpeg_gated, 1);
 	atomic_set(&smu->smu_power.power_gate.vpe_gated, 1);
 	atomic_set(&smu->smu_power.power_gate.umsch_mm_gated, 1);
 
-	smu->workload_prority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT] = 0;
-	smu->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D] = 1;
-	smu->workload_prority[PP_SMC_POWER_PROFILE_POWERSAVING] = 2;
-	smu->workload_prority[PP_SMC_POWER_PROFILE_VIDEO] = 3;
-	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];
+	smu->workload_priority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT] = 0;
+	smu->workload_priority[PP_SMC_POWER_PROFILE_FULLSCREEN3D] = 1;
+	smu->workload_priority[PP_SMC_POWER_PROFILE_POWERSAVING] = 2;
+	smu->workload_priority[PP_SMC_POWER_PROFILE_VIDEO] = 3;
+	smu->workload_priority[PP_SMC_POWER_PROFILE_VR] = 4;
+	smu->workload_priority[PP_SMC_POWER_PROFILE_COMPUTE] = 5;
+	smu->workload_priority[PP_SMC_POWER_PROFILE_CUSTOM] = 6;
+
+	if (smu->is_apu ||
+	    !smu_is_workload_profile_available(smu, PP_SMC_POWER_PROFILE_FULLSCREEN3D)) {
+		smu->driver_workload_mask =
+			1 << smu->workload_priority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT];
+	} else {
+		smu->driver_workload_mask =
+			1 << smu->workload_priority[PP_SMC_POWER_PROFILE_FULLSCREEN3D];
+		smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
+	}
 
+	smu->workload_mask = smu->driver_workload_mask |
+							smu->user_dpm_profile.user_workload_mask;
 	smu->workload_setting[0] = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
 	smu->workload_setting[1] = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
 	smu->workload_setting[2] = PP_SMC_POWER_PROFILE_POWERSAVING;
@@ -2226,7 +2246,7 @@ 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 +2275,7 @@ 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 +2292,7 @@ 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);
 	}
 
@@ -2335,17 +2355,20 @@ static int smu_switch_power_profile(void *handle,
 		return -EINVAL;
 
 	if (!en) {
-		smu->workload_mask &= ~(1 << smu->workload_prority[type]);
+		smu->driver_workload_mask &= ~(1 << smu->workload_priority[type]);
 		index = fls(smu->workload_mask);
 		index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
 		workload[0] = smu->workload_setting[index];
 	} else {
-		smu->workload_mask |= (1 << smu->workload_prority[type]);
+		smu->driver_workload_mask |= (1 << smu->workload_priority[type]);
 		index = fls(smu->workload_mask);
 		index = index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
 		workload[0] = smu->workload_setting[index];
 	}
 
+	smu->workload_mask = smu->driver_workload_mask |
+						 smu->user_dpm_profile.user_workload_mask;
+
 	if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL &&
 		smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM)
 		smu_bump_power_profile_mode(smu, workload, 0);
@@ -3036,12 +3059,23 @@ static int smu_set_power_profile_mode(void *handle,
 				      uint32_t param_size)
 {
 	struct smu_context *smu = handle;
+	int ret;
 
 	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled ||
 	    !smu->ppt_funcs->set_power_profile_mode)
 		return -EOPNOTSUPP;
 
-	return smu_bump_power_profile_mode(smu, param, param_size);
+	if (smu->user_dpm_profile.user_workload_mask &
+	   (1 << smu->workload_priority[param[param_size]]))
+	   return 0;
+
+	smu->user_dpm_profile.user_workload_mask =
+		(1 << smu->workload_priority[param[param_size]]);
+	smu->workload_mask = smu->user_dpm_profile.user_workload_mask |
+		smu->driver_workload_mask;
+	ret = smu_bump_power_profile_mode(smu, param, param_size);
+
+	return ret;
 }
 
 static int smu_get_fan_control_mode(void *handle, u32 *fan_mode)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index b44a185d07e8..d60d9a12a47e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -240,6 +240,7 @@ struct smu_user_dpm_profile {
 	/* user clock state information */
 	uint32_t clk_mask[SMU_CLK_COUNT];
 	uint32_t clk_dependency;
+	uint32_t user_workload_mask;
 };
 
 #define SMU_TABLE_INIT(tables, table_id, s, a, d)	\
@@ -557,7 +558,8 @@ struct smu_context {
 	bool disable_uclk_switch;
 
 	uint32_t workload_mask;
-	uint32_t workload_prority[WORKLOAD_POLICY_MAX];
+	uint32_t driver_workload_mask;
+	uint32_t workload_priority[WORKLOAD_POLICY_MAX];
 	uint32_t workload_setting[WORKLOAD_POLICY_MAX];
 	uint32_t power_profile_mode;
 	uint32_t default_power_profile_mode;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h
index ee457a6f0813..c2fd0a4a13e5 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h
@@ -25,7 +25,7 @@
 #define SMU14_DRIVER_IF_V14_0_H
 
 //Increment this version if SkuTable_t or BoardTable_t change
-#define PPTABLE_VERSION 0x18
+#define PPTABLE_VERSION 0x1B
 
 #define NUM_GFXCLK_DPM_LEVELS    16
 #define NUM_SOCCLK_DPM_LEVELS    8
@@ -145,7 +145,7 @@ typedef enum {
 } FEATURE_BTC_e;
 
 // Debug Overrides Bitmask
-#define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_VCN_FCLK      0x00000001
+#define DEBUG_OVERRIDE_NOT_USE      				   0x00000001
 #define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_DCN_FCLK      0x00000002
 #define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_MP0_FCLK      0x00000004
 #define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_VCN_DCFCLK    0x00000008
@@ -161,6 +161,7 @@ typedef enum {
 #define DEBUG_OVERRIDE_ENABLE_SOC_VF_BRINGUP_MODE      0x00002000
 #define DEBUG_OVERRIDE_ENABLE_PER_WGP_RESIENCY         0x00004000
 #define DEBUG_OVERRIDE_DISABLE_MEMORY_VOLTAGE_SCALING  0x00008000
+#define DEBUG_OVERRIDE_DFLL_BTC_FCW_LOG                0x00010000
 
 // VR Mapping Bit Defines
 #define VR_MAPPING_VR_SELECT_MASK  0x01
@@ -391,6 +392,21 @@ typedef struct {
   EccInfo_t  EccInfo[24];
 } EccInfoTable_t;
 
+#define EPCS_HIGH_POWER                  600
+#define EPCS_NORMAL_POWER                450
+#define EPCS_LOW_POWER                   300
+#define EPCS_SHORTED_POWER               150
+#define EPCS_NO_BOOTUP                   0
+
+typedef enum{
+  EPCS_SHORTED_LIMIT,
+  EPCS_LOW_POWER_LIMIT,
+  EPCS_NORMAL_POWER_LIMIT,
+  EPCS_HIGH_POWER_LIMIT,
+  EPCS_NOT_CONFIGURED,
+  EPCS_STATUS_COUNT,
+} EPCS_STATUS_e;
+
 //D3HOT sequences
 typedef enum {
   BACO_SEQUENCE,
@@ -662,7 +678,7 @@ typedef enum {
 } PP_GRTAVFS_FW_SEP_FUSE_e;
 
 #define PP_NUM_RTAVFS_PWL_ZONES 5
-
+#define PP_NUM_PSM_DIDT_PWL_ZONES 3
 
 // VBIOS or PPLIB configures telemetry slope and offset. Only slope expected to be set for SVI3
 // Slope Q1.7, Offset Q1.2
@@ -746,10 +762,10 @@ typedef struct {
   uint16_t               Padding;
 
   //Frequency changes
-  int16_t                GfxclkFmin;           // MHz
-  int16_t                GfxclkFmax;           // MHz
-  uint16_t               UclkFmin;             // MHz
-  uint16_t               UclkFmax;             // MHz
+  int16_t                GfxclkFoffset;
+  uint16_t               Padding1;
+  uint16_t               UclkFmin;
+  uint16_t               UclkFmax;
   uint16_t               FclkFmin;
   uint16_t               FclkFmax;
 
@@ -770,19 +786,23 @@ typedef struct {
   uint8_t                MaxOpTemp;
 
   uint8_t                AdvancedOdModeEnabled;
-  uint8_t                Padding1[3];
+  uint8_t                Padding2[3];
 
   uint16_t               GfxVoltageFullCtrlMode;
   uint16_t               SocVoltageFullCtrlMode;
   uint16_t               GfxclkFullCtrlMode;
   uint16_t               UclkFullCtrlMode;
   uint16_t               FclkFullCtrlMode;
-  uint16_t               Padding2;
+  uint16_t               Padding3;
 
   int16_t                GfxEdc;
   int16_t                GfxPccLimitControl;
 
-  uint32_t               Spare[10];
+  uint16_t               GfxclkFmaxVmax;
+  uint8_t                GfxclkFmaxVmaxTemperature;
+  uint8_t                Padding4[1];
+
+  uint32_t               Spare[9];
   uint32_t               MmHubPadding[8]; // SMU internal use. Adding here instead of external as a workaround
 } OverDriveTable_t;
 
@@ -802,8 +822,8 @@ typedef struct {
   uint16_t               VddSocVmax;
 
   //gfxclk
-  int16_t                GfxclkFmin;           // MHz
-  int16_t                GfxclkFmax;           // MHz
+  int16_t                GfxclkFoffset;
+  uint16_t               Padding;
   //uclk
   uint16_t               UclkFmin;             // MHz
   uint16_t               UclkFmax;             // MHz
@@ -828,7 +848,7 @@ typedef struct {
   uint8_t                FanZeroRpmEnable;
   //temperature
   uint8_t                MaxOpTemp;
-  uint8_t                Padding[2];
+  uint8_t                Padding1[2];
 
   //Full Ctrl
   uint16_t               GfxVoltageFullCtrlMode;
@@ -839,7 +859,7 @@ typedef struct {
   //EDC
   int16_t                GfxEdc;
   int16_t                GfxPccLimitControl;
-  int16_t                Padding1;
+  int16_t                Padding2;
 
   uint32_t               Spare[5];
 } OverDriveLimits_t;
@@ -987,8 +1007,9 @@ typedef struct {
   uint16_t BaseClockDc;
   uint16_t GameClockDc;
   uint16_t BoostClockDc;
-
-  uint32_t Reserved[4];
+  uint16_t MaxReportedClock;
+  uint16_t Padding;
+  uint32_t Reserved[3];
 } DriverReportedClocks_t;
 
 typedef struct {
@@ -1132,7 +1153,7 @@ typedef struct {
   uint32_t      DcModeMaxFreq     [PPCLK_COUNT            ];     // In MHz
 
   uint16_t      GfxclkAibFmax;
-  uint16_t      GfxclkFreqCap;
+  uint16_t      GfxDpmPadding;
 
   //GFX Idle Power Settings
   uint16_t      GfxclkFgfxoffEntry;   // Entry in RLC stage (PLL), in Mhz
@@ -1172,8 +1193,7 @@ typedef struct {
   uint32_t        DvoFmaxLowScaler; //Unitless float
 
   // GFX DCS
-  uint16_t      DcsGfxOffVoltage;     //Voltage in mV(Q2) applied to VDDGFX when entering DCS GFXOFF phase
-  uint16_t      PaddingDcs;
+  uint32_t      PaddingDcs;
 
   uint16_t      DcsMinGfxOffTime;     //Minimum amount of time PMFW shuts GFX OFF as part of GFX DCS phase
   uint16_t      DcsMaxGfxOffTime;      //Maximum amount of time PMFW can shut GFX OFF as part of GFX DCS phase at a stretch.
@@ -1205,8 +1225,7 @@ typedef struct {
   uint16_t      DalDcModeMaxUclkFreq;
   uint8_t       PaddingsMem[2];
   //FCLK Section
-  uint16_t      FclkDpmDisallowPstateFreq;  //Frequency which FW will target when indicated that display config cannot support P-state. Set to 0 use FW calculated value
-  uint16_t      PaddingFclk;
+  uint32_t      PaddingFclk;
 
   // Link DPM Settings
   uint8_t       PcieGenSpeed[NUM_LINK_LEVELS];           ///< 0:PciE-gen1 1:PciE-gen2 2:PciE-gen3 3:PciE-gen4 4:PciE-gen5
@@ -1215,12 +1234,19 @@ typedef struct {
 
   // SECTION: VDD_GFX AVFS
   uint8_t       OverrideGfxAvfsFuses;
-  uint8_t       GfxAvfsPadding[3];
+  uint8_t       GfxAvfsPadding[1];
+  uint16_t      DroopGBStDev;
 
   uint32_t      SocHwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT];   //new added for Soc domain
   uint32_t      GfxL2HwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT]; //see fusedoc for encoding
   //uint32_t      GfxSeHwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT];
-  uint32_t      spare_HwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT];
+
+  uint16_t      PsmDidt_Vcross[PP_NUM_PSM_DIDT_PWL_ZONES-1];
+  uint32_t      PsmDidt_StaticDroop_A[PP_NUM_PSM_DIDT_PWL_ZONES];
+  uint32_t      PsmDidt_StaticDroop_B[PP_NUM_PSM_DIDT_PWL_ZONES];
+  uint32_t      PsmDidt_DynDroop_A[PP_NUM_PSM_DIDT_PWL_ZONES];
+  uint32_t      PsmDidt_DynDroop_B[PP_NUM_PSM_DIDT_PWL_ZONES];
+  uint32_t      spare_HwRtAvfsFuses[19];
 
   uint32_t      SocCommonRtAvfs[PP_GRTAVFS_FW_COMMON_FUSE_COUNT];
   uint32_t      GfxCommonRtAvfs[PP_GRTAVFS_FW_COMMON_FUSE_COUNT];
@@ -1246,11 +1272,7 @@ typedef struct {
   uint32_t      dGbV_dT_vmin;
   uint32_t      dGbV_dT_vmax;
 
-  //Unused: PMFW-9370
-  uint32_t      V2F_vmin_range_low;
-  uint32_t      V2F_vmin_range_high;
-  uint32_t      V2F_vmax_range_low;
-  uint32_t      V2F_vmax_range_high;
+  uint32_t      PaddingV2F[4];
 
   AvfsDcBtcParams_t DcBtcGfxParams;
   QuadraticInt_t    SSCurve_GFX;
@@ -1327,18 +1349,18 @@ typedef struct {
   uint16_t        PsmDidtReleaseTimer;
   uint32_t        PsmDidtStallPattern; //Will be written to both pattern 1 and didt_static_level_prog
   // CAC EDC
-  uint32_t        Leakage_C0; // in IEEE float
-  uint32_t        Leakage_C1; // in IEEE float
-  uint32_t        Leakage_C2; // in IEEE float
-  uint32_t        Leakage_C3; // in IEEE float
-  uint32_t        Leakage_C4; // in IEEE float
-  uint32_t        Leakage_C5; // in IEEE float
-  uint32_t        GFX_CLK_SCALAR; // in IEEE float
-  uint32_t        GFX_CLK_INTERCEPT; // in IEEE float
-  uint32_t        GFX_CAC_M; // in IEEE float
-  uint32_t        GFX_CAC_B; // in IEEE float
-  uint32_t        VDD_GFX_CurrentLimitGuardband; // in IEEE float
-  uint32_t        DynToTotalCacScalar; // in IEEE
+  uint32_t        CacEdcCacLeakageC0;
+  uint32_t        CacEdcCacLeakageC1;
+  uint32_t        CacEdcCacLeakageC2;
+  uint32_t        CacEdcCacLeakageC3;
+  uint32_t        CacEdcCacLeakageC4;
+  uint32_t        CacEdcCacLeakageC5;
+  uint32_t        CacEdcGfxClkScalar;
+  uint32_t        CacEdcGfxClkIntercept;
+  uint32_t        CacEdcCac_m;
+  uint32_t        CacEdcCac_b;
+  uint32_t        CacEdcCurrLimitGuardband;
+  uint32_t        CacEdcDynToTotalCacRatio;
   // GFX EDC XVMIN
   uint32_t        XVmin_Gfx_EdcThreshScalar;
   uint32_t        XVmin_Gfx_EdcEnableFreq;
@@ -1467,7 +1489,7 @@ typedef struct {
   uint8_t      VddqOffEnabled;
   uint8_t      PaddingUmcFlags[2];
 
-  uint32_t    PostVoltageSetBacoDelay; // in microseconds. Amount of time FW will wait after power good is established or PSI0 command is issued
+  uint32_t    Paddign1;
   uint32_t    BacoEntryDelay; // in milliseconds. Amount of time FW will wait to trigger BACO entry after receiving entry notification from OS
 
   uint8_t     FuseWritePowerMuxPresent;
@@ -1530,7 +1552,7 @@ typedef struct {
   int16_t     FuzzyFan_ErrorSetDelta;
   int16_t     FuzzyFan_ErrorRateSetDelta;
   int16_t     FuzzyFan_PwmSetDelta;
-  uint16_t    FuzzyFan_Reserved;
+  uint16_t    FanPadding2;
 
   uint16_t    FwCtfLimit[TEMP_COUNT];
 
@@ -1547,9 +1569,10 @@ typedef struct {
   uint16_t    FanSpare[1];
   uint8_t     FanIntakeSensorSupport;
   uint8_t     FanIntakePadding;
-  uint32_t    FanAmbientPerfBoostThreshold;
   uint32_t    FanSpare2[12];
 
+  uint32_t ODFeatureCtrlMask;
+
   uint16_t TemperatureLimit_Hynix; // In degrees Celsius. Memory temperature limit associated with Hynix
   uint16_t TemperatureLimit_Micron; // In degrees Celsius. Memory temperature limit associated with Micron
   uint16_t TemperatureFwCtfLimit_Hynix;
@@ -1637,7 +1660,7 @@ typedef struct {
   uint16_t AverageDclk0Frequency  ;
   uint16_t AverageVclk1Frequency  ;
   uint16_t AverageDclk1Frequency  ;
-  uint16_t PCIeBusy               ;
+  uint16_t AveragePCIeBusy        ;
   uint16_t dGPU_W_MAX             ;
   uint16_t padding                ;
 
@@ -1665,12 +1688,12 @@ typedef struct {
 
   uint16_t AverageGfxActivity    ;
   uint16_t AverageUclkActivity   ;
-  uint16_t Vcn0ActivityPercentage  ;
+  uint16_t AverageVcn0ActivityPercentage;
   uint16_t Vcn1ActivityPercentage  ;
 
   uint32_t EnergyAccumulator;
   uint16_t AverageSocketPower;
-  uint16_t MovingAverageTotalBoardPower;
+  uint16_t AverageTotalBoardPower;
 
   uint16_t AvgTemperature[TEMP_COUNT];
   uint16_t AvgTemperatureFanIntake;
@@ -1684,7 +1707,8 @@ typedef struct {
 
 
   uint8_t  ThrottlingPercentage[THROTTLER_COUNT];
-  uint8_t  padding1[3];
+  uint8_t  VmaxThrottlingPercentage;
+  uint8_t  padding1[2];
 
   //metrics for D3hot entry/exit and driver ARM msgs
   uint32_t D3HotEntryCountPerMode[D3HOT_SEQUENCE_COUNT];
@@ -1693,7 +1717,7 @@ typedef struct {
 
   uint16_t ApuSTAPMSmartShiftLimit;
   uint16_t ApuSTAPMLimit;
-  uint16_t MovingAvgApuSocketPower;
+  uint16_t AvgApuSocketPower;
 
   uint16_t AverageUclkActivity_MAX;
 
@@ -1823,6 +1847,17 @@ typedef struct {
 #define TABLE_TRANSFER_FAILED     0xFF
 #define TABLE_TRANSFER_PENDING    0xAB
 
+#define TABLE_PPT_FAILED                          0x100
+#define TABLE_TDC_FAILED                          0x200
+#define TABLE_TEMP_FAILED                         0x400
+#define TABLE_FAN_TARGET_TEMP_FAILED              0x800
+#define TABLE_FAN_STOP_TEMP_FAILED               0x1000
+#define TABLE_FAN_START_TEMP_FAILED              0x2000
+#define TABLE_FAN_PWM_MIN_FAILED                 0x4000
+#define TABLE_ACOUSTIC_TARGET_RPM_FAILED         0x8000
+#define TABLE_ACOUSTIC_LIMIT_RPM_FAILED         0x10000
+#define TABLE_MGPU_ACOUSTIC_TARGET_RPM_FAILED   0x20000
+
 // Table types
 #define TABLE_PPTABLE            0
 #define TABLE_COMBO_PPTABLE           1
@@ -1849,5 +1884,6 @@ typedef struct {
 #define IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING  0x7
 #define IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL        0x8
 #define IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY        0x9
+#define IH_INTERRUPT_CONTEXT_ID_DYNAMIC_TABLE       0xA
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
index 46b456590a08..727d5b405435 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
@@ -28,7 +28,7 @@
 #define SMU14_DRIVER_IF_VERSION_INV 0xFFFFFFFF
 #define SMU14_DRIVER_IF_VERSION_SMU_V14_0_0 0x7
 #define SMU14_DRIVER_IF_VERSION_SMU_V14_0_1 0x6
-#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x26
+#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x2E
 
 #define FEATURE_MASK(feature) (1ULL << feature)
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index c0f6b59369b7..31fe512028f4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -1455,7 +1455,6 @@ static int arcturus_set_power_profile_mode(struct smu_context *smu,
 		return -EINVAL;
 	}
 
-
 	if ((profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) &&
 	     (smu->smc_fw_version >= 0x360d00)) {
 		if (size != 10)
@@ -1523,14 +1522,14 @@ static int arcturus_set_power_profile_mode(struct smu_context *smu,
 
 	ret = smu_cmn_send_smc_msg_with_param(smu,
 					  SMU_MSG_SetWorkloadMask,
-					  1 << workload_type,
+					  smu->workload_mask,
 					  NULL);
 	if (ret) {
 		dev_err(smu->adev->dev, "Fail to set workload type %d\n", workload_type);
 		return ret;
 	}
 
-	smu->power_profile_mode = profile_mode;
+	smu_cmn_assign_power_profile(smu);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 16af1a329621..12223f507977 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -2081,10 +2081,13 @@ static int navi10_set_power_profile_mode(struct smu_context *smu, long *input, u
 						       smu->power_profile_mode);
 	if (workload_type < 0)
 		return -EINVAL;
+
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask,
-				    1 << workload_type, NULL);
+				    smu->workload_mask, NULL);
 	if (ret)
 		dev_err(smu->adev->dev, "[%s] Failed to set work load mask!", __func__);
+	else
+		smu_cmn_assign_power_profile(smu);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 9c3c48297cba..3b7b2ec8319a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -1786,10 +1786,13 @@ static int sienna_cichlid_set_power_profile_mode(struct smu_context *smu, long *
 						       smu->power_profile_mode);
 	if (workload_type < 0)
 		return -EINVAL;
+
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask,
-				    1 << workload_type, NULL);
+				    smu->workload_mask, NULL);
 	if (ret)
 		dev_err(smu->adev->dev, "[%s] Failed to set work load mask!", __func__);
+	else
+		smu_cmn_assign_power_profile(smu);
 
 	return ret;
 }
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 22737b11b1bf..952ee22cbc90 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -242,7 +242,9 @@ static int vangogh_tables_init(struct smu_context *smu)
 		goto err0_out;
 	smu_table->metrics_time = 0;
 
-	smu_table->gpu_metrics_table_size = max(sizeof(struct gpu_metrics_v2_3), sizeof(struct gpu_metrics_v2_2));
+	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_2);
+	smu_table->gpu_metrics_table_size = max(smu_table->gpu_metrics_table_size, sizeof(struct gpu_metrics_v2_3));
+	smu_table->gpu_metrics_table_size = max(smu_table->gpu_metrics_table_size, sizeof(struct gpu_metrics_v2_4));
 	smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
 	if (!smu_table->gpu_metrics_table)
 		goto err1_out;
@@ -1077,7 +1079,7 @@ static int vangogh_set_power_profile_mode(struct smu_context *smu, long *input,
 	}
 
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ActiveProcessNotify,
-				    1 << workload_type,
+				    smu->workload_mask,
 				    NULL);
 	if (ret) {
 		dev_err_once(smu->adev->dev, "Fail to set workload type %d\n",
@@ -1085,7 +1087,7 @@ static int vangogh_set_power_profile_mode(struct smu_context *smu, long *input,
 		return ret;
 	}
 
-	smu->power_profile_mode = profile_mode;
+	smu_cmn_assign_power_profile(smu);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index cc0504b063fa..62316a6707ef 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -890,14 +890,14 @@ static int renoir_set_power_profile_mode(struct smu_context *smu, long *input, u
 	}
 
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ActiveProcessNotify,
-				    1 << workload_type,
+				    smu->workload_mask,
 				    NULL);
 	if (ret) {
 		dev_err_once(smu->adev->dev, "Fail to set workload type %d\n", workload_type);
 		return ret;
 	}
 
-	smu->power_profile_mode = profile_mode;
+	smu_cmn_assign_power_profile(smu);
 
 	return 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..5dd7ceca64fe 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
@@ -2555,26 +2555,34 @@ 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;
 	}
 
+	smu->workload_mask |= workload_mask;
 	ret = smu_cmn_send_smc_msg_with_param(smu,
 					       SMU_MSG_SetWorkloadMask,
-					       workload_mask,
+					       smu->workload_mask,
 					       NULL);
-	if (!ret)
-		smu->workload_mask = workload_mask;
+	if (!ret) {
+		smu_cmn_assign_power_profile(smu);
+		if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_POWERSAVING) {
+			workload_type = smu_cmn_to_asic_specific_index(smu,
+							       CMN2ASIC_MAPPING_WORKLOAD,
+							       PP_SMC_POWER_PROFILE_FULLSCREEN3D);
+			smu->power_profile_mode = smu->workload_mask & (1 << workload_type)
+										? PP_SMC_POWER_PROFILE_FULLSCREEN3D
+										: PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
+		}
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index b891a5e0a396..9d0b19419de0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2499,13 +2499,14 @@ static int smu_v13_0_7_set_power_profile_mode(struct smu_context *smu, long *inp
 						       smu->power_profile_mode);
 	if (workload_type < 0)
 		return -EINVAL;
+
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask,
-				    1 << workload_type, NULL);
+				    smu->workload_mask, NULL);
 
 	if (ret)
 		dev_err(smu->adev->dev, "[%s] Failed to set work load mask!", __func__);
 	else
-		smu->workload_mask = (1 << workload_type);
+		smu_cmn_assign_power_profile(smu);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 5899d01fa73d..1aa13d32ceb2 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -367,54 +367,6 @@ static int smu_v14_0_2_store_powerplay_table(struct smu_context *smu)
 	return 0;
 }
 
-#ifndef atom_smc_dpm_info_table_14_0_0
-struct atom_smc_dpm_info_table_14_0_0 {
-	struct atom_common_table_header table_header;
-	BoardTable_t BoardTable;
-};
-#endif
-
-static int smu_v14_0_2_append_powerplay_table(struct smu_context *smu)
-{
-	struct smu_table_context *table_context = &smu->smu_table;
-	PPTable_t *smc_pptable = table_context->driver_pptable;
-	struct atom_smc_dpm_info_table_14_0_0 *smc_dpm_table;
-	BoardTable_t *BoardTable = &smc_pptable->BoardTable;
-	int index, ret;
-
-	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
-					    smc_dpm_info);
-
-	ret = amdgpu_atombios_get_data_table(smu->adev, index, NULL, NULL, NULL,
-					     (uint8_t **)&smc_dpm_table);
-	if (ret)
-		return ret;
-
-	memcpy(BoardTable, &smc_dpm_table->BoardTable, sizeof(BoardTable_t));
-
-	return 0;
-}
-
-#if 0
-static int smu_v14_0_2_get_pptable_from_pmfw(struct smu_context *smu,
-					     void **table,
-					     uint32_t *size)
-{
-	struct smu_table_context *smu_table = &smu->smu_table;
-	void *combo_pptable = smu_table->combo_pptable;
-	int ret = 0;
-
-	ret = smu_cmn_get_combo_pptable(smu);
-	if (ret)
-		return ret;
-
-	*table = combo_pptable;
-	*size = sizeof(struct smu_14_0_powerplay_table);
-
-	return 0;
-}
-#endif
-
 static int smu_v14_0_2_get_pptable_from_pmfw(struct smu_context *smu,
 					     void **table,
 					     uint32_t *size)
@@ -436,16 +388,12 @@ static int smu_v14_0_2_get_pptable_from_pmfw(struct smu_context *smu,
 static int smu_v14_0_2_setup_pptable(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 
 	if (amdgpu_sriov_vf(smu->adev))
 		return 0;
 
-	if (!adev->scpm_enabled)
-		ret = smu_v14_0_setup_pptable(smu);
-	else
-		ret = smu_v14_0_2_get_pptable_from_pmfw(smu,
+	ret = smu_v14_0_2_get_pptable_from_pmfw(smu,
 							&smu_table->power_play_table,
 							&smu_table->power_play_table_size);
 	if (ret)
@@ -455,16 +403,6 @@ static int smu_v14_0_2_setup_pptable(struct smu_context *smu)
 	if (ret)
 		return ret;
 
-	/*
-	 * With SCPM enabled, the operation below will be handled
-	 * by PSP. Driver involvment is unnecessary and useless.
-	 */
-	if (!adev->scpm_enabled) {
-		ret = smu_v14_0_2_append_powerplay_table(smu);
-		if (ret)
-			return ret;
-	}
-
 	ret = smu_v14_0_2_check_powerplay_table(smu);
 	if (ret)
 		return ret;
@@ -1077,12 +1015,9 @@ static void smu_v14_0_2_get_od_setting_limits(struct smu_context *smu,
 
 	switch (od_feature_bit) {
 	case PP_OD_FEATURE_GFXCLK_FMIN:
-		od_min_setting = overdrive_lowerlimits->GfxclkFmin;
-		od_max_setting = overdrive_upperlimits->GfxclkFmin;
-		break;
 	case PP_OD_FEATURE_GFXCLK_FMAX:
-		od_min_setting = overdrive_lowerlimits->GfxclkFmax;
-		od_max_setting = overdrive_upperlimits->GfxclkFmax;
+		od_min_setting = overdrive_lowerlimits->GfxclkFoffset;
+		od_max_setting = overdrive_upperlimits->GfxclkFoffset;
 		break;
 	case PP_OD_FEATURE_UCLK_FMIN:
 		od_min_setting = overdrive_lowerlimits->UclkFmin;
@@ -1269,10 +1204,16 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
 							 PP_OD_FEATURE_GFXCLK_BIT))
 			break;
 
-		size += sysfs_emit_at(buf, size, "OD_SCLK:\n");
-		size += sysfs_emit_at(buf, size, "0: %uMhz\n1: %uMhz\n",
-					od_table->OverDriveTable.GfxclkFmin,
-					od_table->OverDriveTable.GfxclkFmax);
+		PPTable_t *pptable = smu->smu_table.driver_pptable;
+		const OverDriveLimits_t * const overdrive_upperlimits =
+					&pptable->SkuTable.OverDriveLimitsBasicMax;
+		const OverDriveLimits_t * const overdrive_lowerlimits =
+					&pptable->SkuTable.OverDriveLimitsBasicMin;
+
+		size += sysfs_emit_at(buf, size, "OD_SCLK_OFFSET:\n");
+		size += sysfs_emit_at(buf, size, "0: %dMhz\n1: %uMhz\n",
+					overdrive_lowerlimits->GfxclkFoffset,
+					overdrive_upperlimits->GfxclkFoffset);
 		break;
 
 	case SMU_OD_MCLK:
@@ -1414,7 +1355,7 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
 							  PP_OD_FEATURE_GFXCLK_FMAX,
 							  NULL,
 							  &max_value);
-			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "SCLK_OFFSET: %7dMhz %10uMhz\n",
 					      min_value, max_value);
 		}
 
@@ -1796,7 +1737,7 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu,
 	DpmActivityMonitorCoeffInt_t *activity_monitor =
 		&(activity_monitor_external.DpmActivityMonitorCoeffInt);
 	int workload_type, ret = 0;
-
+	uint32_t current_profile_mode = smu->power_profile_mode;
 	smu->power_profile_mode = input[size];
 
 	if (smu->power_profile_mode >= PP_SMC_POWER_PROFILE_COUNT) {
@@ -1854,6 +1795,11 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu,
 		}
 	}
 
+	if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE)
+		smu_v14_0_deep_sleep_control(smu, false);
+	else if (current_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE)
+		smu_v14_0_deep_sleep_control(smu, true);
+
 	/* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */
 	workload_type = smu_cmn_to_asic_specific_index(smu,
 						       CMN2ASIC_MAPPING_WORKLOAD,
@@ -1861,12 +1807,11 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu,
 	if (workload_type < 0)
 		return -EINVAL;
 
-	ret = smu_cmn_send_smc_msg_with_param(smu,
-					       SMU_MSG_SetWorkloadMask,
-					       1 << workload_type,
-					       NULL);
+	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask,
+										  smu->workload_mask, NULL);
+
 	if (!ret)
-		smu->workload_mask = 1 << workload_type;
+		smu_cmn_assign_power_profile(smu);
 
 	return ret;
 }
@@ -2158,7 +2103,7 @@ static ssize_t smu_v14_0_2_get_gpu_metrics(struct smu_context *smu,
 
 	gpu_metrics->average_gfx_activity = metrics->AverageGfxActivity;
 	gpu_metrics->average_umc_activity = metrics->AverageUclkActivity;
-	gpu_metrics->average_mm_activity = max(metrics->Vcn0ActivityPercentage,
+	gpu_metrics->average_mm_activity = max(metrics->AverageVcn0ActivityPercentage,
 					       metrics->Vcn1ActivityPercentage);
 
 	gpu_metrics->average_socket_power = metrics->AverageSocketPower;
@@ -2217,8 +2162,7 @@ static void smu_v14_0_2_dump_od_table(struct smu_context *smu,
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	dev_dbg(adev->dev, "OD: Gfxclk: (%d, %d)\n", od_table->OverDriveTable.GfxclkFmin,
-						     od_table->OverDriveTable.GfxclkFmax);
+	dev_dbg(adev->dev, "OD: Gfxclk offset: (%d)\n", od_table->OverDriveTable.GfxclkFoffset);
 	dev_dbg(adev->dev, "OD: Uclk: (%d, %d)\n", od_table->OverDriveTable.UclkFmin,
 						   od_table->OverDriveTable.UclkFmax);
 }
@@ -2309,10 +2253,8 @@ static int smu_v14_0_2_set_default_od_settings(struct smu_context *smu)
 		memcpy(user_od_table,
 		       boot_od_table,
 		       sizeof(OverDriveTableExternal_t));
-		user_od_table->OverDriveTable.GfxclkFmin =
-				user_od_table_bak.OverDriveTable.GfxclkFmin;
-		user_od_table->OverDriveTable.GfxclkFmax =
-				user_od_table_bak.OverDriveTable.GfxclkFmax;
+		user_od_table->OverDriveTable.GfxclkFoffset =
+				user_od_table_bak.OverDriveTable.GfxclkFoffset;
 		user_od_table->OverDriveTable.UclkFmin =
 				user_od_table_bak.OverDriveTable.UclkFmin;
 		user_od_table->OverDriveTable.UclkFmax =
@@ -2441,22 +2383,6 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
 			}
 
 			switch (input[i]) {
-			case 0:
-				smu_v14_0_2_get_od_setting_limits(smu,
-								  PP_OD_FEATURE_GFXCLK_FMIN,
-								  &minimum,
-								  &maximum);
-				if (input[i + 1] < minimum ||
-				    input[i + 1] > maximum) {
-					dev_info(adev->dev, "GfxclkFmin (%ld) must be within [%u, %u]!\n",
-						input[i + 1], minimum, maximum);
-					return -EINVAL;
-				}
-
-				od_table->OverDriveTable.GfxclkFmin = input[i + 1];
-				od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT;
-				break;
-
 			case 1:
 				smu_v14_0_2_get_od_setting_limits(smu,
 								  PP_OD_FEATURE_GFXCLK_FMAX,
@@ -2469,7 +2395,7 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
 					return -EINVAL;
 				}
 
-				od_table->OverDriveTable.GfxclkFmax = input[i + 1];
+				od_table->OverDriveTable.GfxclkFoffset = input[i + 1];
 				od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT;
 				break;
 
@@ -2480,13 +2406,6 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
 			}
 		}
 
-		if (od_table->OverDriveTable.GfxclkFmin > od_table->OverDriveTable.GfxclkFmax) {
-			dev_err(adev->dev,
-				"Invalid setting: GfxclkFmin(%u) is bigger than GfxclkFmax(%u)\n",
-				(uint32_t)od_table->OverDriveTable.GfxclkFmin,
-				(uint32_t)od_table->OverDriveTable.GfxclkFmax);
-			return -EINVAL;
-		}
 		break;
 
 	case PP_OD_EDIT_MCLK_VDDC_TABLE:
@@ -2817,7 +2736,6 @@ static const struct pptable_funcs smu_v14_0_2_ppt_funcs = {
 	.check_fw_status = smu_v14_0_check_fw_status,
 	.setup_pptable = smu_v14_0_2_setup_pptable,
 	.check_fw_version = smu_v14_0_check_fw_version,
-	.write_pptable = smu_cmn_write_pptable,
 	.set_driver_table_location = smu_v14_0_set_driver_table_location,
 	.system_features_control = smu_v14_0_system_features_control,
 	.set_allowed_mask = smu_v14_0_set_allowed_mask,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 91ad434bcdae..bdfc5e617333 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -1138,6 +1138,14 @@ int smu_cmn_set_mp1_state(struct smu_context *smu,
 	return ret;
 }
 
+void smu_cmn_assign_power_profile(struct smu_context *smu)
+{
+	uint32_t index;
+	index = fls(smu->workload_mask);
+	index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
+	smu->power_profile_mode = smu->workload_setting[index];
+}
+
 bool smu_cmn_is_audio_func_enabled(struct amdgpu_device *adev)
 {
 	struct pci_dev *p = NULL;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index 1de685defe85..8a801e389659 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -130,6 +130,8 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev);
 int smu_cmn_set_mp1_state(struct smu_context *smu,
 			  enum pp_mp1_state mp1_state);
 
+void smu_cmn_assign_power_profile(struct smu_context *smu);
+
 /*
  * Helper function to make sysfs_emit_at() happy. Align buf to
  * the current page boundary and record the offset.
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/bridge/aux-bridge.c b/drivers/gpu/drm/bridge/aux-bridge.c
index b29980f95379..295e9d031e2d 100644
--- a/drivers/gpu/drm/bridge/aux-bridge.c
+++ b/drivers/gpu/drm/bridge/aux-bridge.c
@@ -58,9 +58,10 @@ int drm_aux_bridge_register(struct device *parent)
 	adev->id = ret;
 	adev->name = "aux_bridge";
 	adev->dev.parent = parent;
-	adev->dev.of_node = of_node_get(parent->of_node);
 	adev->dev.release = drm_aux_bridge_release;
 
+	device_set_of_node_from_dev(&adev->dev, parent);
+
 	ret = auxiliary_device_init(adev);
 	if (ret) {
 		ida_free(&drm_aux_bridge_ida, adev->id);
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 290e2532fab1..f3afdab55c11 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -2391,6 +2391,7 @@ static int tc_probe_bridge_endpoint(struct tc_data *tc)
 			if (tc->pre_emphasis[0] < 0 || tc->pre_emphasis[0] > 2 ||
 			    tc->pre_emphasis[1] < 0 || tc->pre_emphasis[1] > 2) {
 				dev_err(dev, "Incorrect Pre-Emphasis setting, use either 0=0dB 1=3.5dB 2=6dB\n");
+				of_node_put(node);
 				return -EINVAL;
 			}
 		}
diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c
index b0602c4f3628..51c2d742d199 100644
--- a/drivers/gpu/drm/drm_fbdev_dma.c
+++ b/drivers/gpu/drm/drm_fbdev_dma.c
@@ -50,7 +50,8 @@ static void drm_fbdev_dma_fb_destroy(struct fb_info *info)
 	if (!fb_helper->dev)
 		return;
 
-	fb_deferred_io_cleanup(info);
+	if (info->fbdefio)
+		fb_deferred_io_cleanup(info);
 	drm_fb_helper_fini(fb_helper);
 
 	drm_client_buffer_vunmap(fb_helper->buffer);
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index 0830cae9a4d0..2d84d7ea1ab7 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -403,7 +403,6 @@ static const struct dmi_system_id orientation_data[] = {
 	}, {	/* Lenovo Yoga Tab 3 X90F */
 		.matches = {
 		 DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
-		 DMI_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"),
 		 DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"),
 		},
 		.driver_data = (void *)&lcd1600x2560_rightside_up,
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index faa253b27664..14ac351fd76d 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -123,9 +123,8 @@ config DRM_I915_USERPTR
 config DRM_I915_GVT_KVMGT
 	tristate "Enable KVM host support Intel GVT-g graphics virtualization"
 	depends on DRM_I915
-	depends on X86
+	depends on KVM_X86
 	depends on 64BIT
-	depends on KVM
 	depends on VFIO
 	select DRM_I915_GVT
 	select KVM_EXTERNAL_WRITE_TRACKING
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/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index 6980b98792c2..377939de0ff4 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -1094,7 +1094,8 @@ static void intel_hdcp_update_value(struct intel_connector *connector,
 	hdcp->value = value;
 	if (update_property) {
 		drm_connector_get(&connector->base);
-		queue_work(i915->unordered_wq, &hdcp->prop_work);
+		if (!queue_work(i915->unordered_wq, &hdcp->prop_work))
+			drm_connector_put(&connector->base);
 	}
 }
 
@@ -2524,7 +2525,8 @@ void intel_hdcp_update_pipe(struct intel_atomic_state *state,
 		mutex_lock(&hdcp->mutex);
 		hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED;
 		drm_connector_get(&connector->base);
-		queue_work(i915->unordered_wq, &hdcp->prop_work);
+		if (!queue_work(i915->unordered_wq, &hdcp->prop_work))
+			drm_connector_put(&connector->base);
 		mutex_unlock(&hdcp->mutex);
 	}
 
@@ -2541,7 +2543,9 @@ void intel_hdcp_update_pipe(struct intel_atomic_state *state,
 		 */
 		if (!desired_and_not_enabled && !content_protection_type_changed) {
 			drm_connector_get(&connector->base);
-			queue_work(i915->unordered_wq, &hdcp->prop_work);
+			if (!queue_work(i915->unordered_wq, &hdcp->prop_work))
+				drm_connector_put(&connector->base);
+
 		}
 	}
 
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/imagination/pvr_context.c b/drivers/gpu/drm/imagination/pvr_context.c
index eded5e955cc0..4cb3494c0bb2 100644
--- a/drivers/gpu/drm/imagination/pvr_context.c
+++ b/drivers/gpu/drm/imagination/pvr_context.c
@@ -17,10 +17,14 @@
 
 #include <drm/drm_auth.h>
 #include <drm/drm_managed.h>
+
+#include <linux/bug.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
+#include <linux/list.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/xarray.h>
@@ -354,6 +358,10 @@ int pvr_context_create(struct pvr_file *pvr_file, struct drm_pvr_ioctl_create_co
 		return err;
 	}
 
+	spin_lock(&pvr_dev->ctx_list_lock);
+	list_add_tail(&ctx->file_link, &pvr_file->contexts);
+	spin_unlock(&pvr_dev->ctx_list_lock);
+
 	return 0;
 
 err_destroy_fw_obj:
@@ -380,6 +388,11 @@ pvr_context_release(struct kref *ref_count)
 		container_of(ref_count, struct pvr_context, ref_count);
 	struct pvr_device *pvr_dev = ctx->pvr_dev;
 
+	WARN_ON(in_interrupt());
+	spin_lock(&pvr_dev->ctx_list_lock);
+	list_del(&ctx->file_link);
+	spin_unlock(&pvr_dev->ctx_list_lock);
+
 	xa_erase(&pvr_dev->ctx_ids, ctx->ctx_id);
 	pvr_context_destroy_queues(ctx);
 	pvr_fw_object_destroy(ctx->fw_obj);
@@ -437,11 +450,30 @@ pvr_context_destroy(struct pvr_file *pvr_file, u32 handle)
  */
 void pvr_destroy_contexts_for_file(struct pvr_file *pvr_file)
 {
+	struct pvr_device *pvr_dev = pvr_file->pvr_dev;
 	struct pvr_context *ctx;
 	unsigned long handle;
 
 	xa_for_each(&pvr_file->ctx_handles, handle, ctx)
 		pvr_context_destroy(pvr_file, handle);
+
+	spin_lock(&pvr_dev->ctx_list_lock);
+	ctx = list_first_entry(&pvr_file->contexts, struct pvr_context, file_link);
+
+	while (!list_entry_is_head(ctx, &pvr_file->contexts, file_link)) {
+		list_del_init(&ctx->file_link);
+
+		if (pvr_context_get_if_referenced(ctx)) {
+			spin_unlock(&pvr_dev->ctx_list_lock);
+
+			pvr_vm_unmap_all(ctx->vm_ctx);
+
+			pvr_context_put(ctx);
+			spin_lock(&pvr_dev->ctx_list_lock);
+		}
+		ctx = list_first_entry(&pvr_file->contexts, struct pvr_context, file_link);
+	}
+	spin_unlock(&pvr_dev->ctx_list_lock);
 }
 
 /**
@@ -451,6 +483,7 @@ void pvr_destroy_contexts_for_file(struct pvr_file *pvr_file)
 void pvr_context_device_init(struct pvr_device *pvr_dev)
 {
 	xa_init_flags(&pvr_dev->ctx_ids, XA_FLAGS_ALLOC1);
+	spin_lock_init(&pvr_dev->ctx_list_lock);
 }
 
 /**
diff --git a/drivers/gpu/drm/imagination/pvr_context.h b/drivers/gpu/drm/imagination/pvr_context.h
index 0c7b97dfa6ba..07afa179cdf4 100644
--- a/drivers/gpu/drm/imagination/pvr_context.h
+++ b/drivers/gpu/drm/imagination/pvr_context.h
@@ -85,6 +85,9 @@ struct pvr_context {
 		/** @compute: Transfer queue. */
 		struct pvr_queue *transfer;
 	} queues;
+
+	/** @file_link: pvr_file PVR context list link. */
+	struct list_head file_link;
 };
 
 static __always_inline struct pvr_queue *
@@ -124,6 +127,24 @@ pvr_context_get(struct pvr_context *ctx)
 }
 
 /**
+ * pvr_context_get_if_referenced() - Take an additional reference on a still
+ * referenced context.
+ * @ctx: Context pointer.
+ *
+ * Call pvr_context_put() to release.
+ *
+ * Returns:
+ *  * True on success, or
+ *  * false if no context pointer passed, or the context wasn't still
+ *  * referenced.
+ */
+static __always_inline bool
+pvr_context_get_if_referenced(struct pvr_context *ctx)
+{
+	return ctx != NULL && kref_get_unless_zero(&ctx->ref_count) != 0;
+}
+
+/**
  * pvr_context_lookup() - Lookup context pointer from handle and file.
  * @pvr_file: Pointer to pvr_file structure.
  * @handle: Context handle.
diff --git a/drivers/gpu/drm/imagination/pvr_device.h b/drivers/gpu/drm/imagination/pvr_device.h
index b574e23d484b..6d0dfacb677b 100644
--- a/drivers/gpu/drm/imagination/pvr_device.h
+++ b/drivers/gpu/drm/imagination/pvr_device.h
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/math.h>
 #include <linux/mutex.h>
+#include <linux/spinlock_types.h>
 #include <linux/timer.h>
 #include <linux/types.h>
 #include <linux/wait.h>
@@ -293,6 +294,12 @@ struct pvr_device {
 
 	/** @sched_wq: Workqueue for schedulers. */
 	struct workqueue_struct *sched_wq;
+
+	/**
+	 * @ctx_list_lock: Lock to be held when accessing the context list in
+	 *  struct pvr_file.
+	 */
+	spinlock_t ctx_list_lock;
 };
 
 /**
@@ -344,6 +351,9 @@ struct pvr_file {
 	 * This array is used to allocate handles returned to userspace.
 	 */
 	struct xarray vm_ctx_handles;
+
+	/** @contexts: PVR context list. */
+	struct list_head contexts;
 };
 
 /**
diff --git a/drivers/gpu/drm/imagination/pvr_drv.c b/drivers/gpu/drm/imagination/pvr_drv.c
index 1a0cb7aa9cea..fb17196e05f4 100644
--- a/drivers/gpu/drm/imagination/pvr_drv.c
+++ b/drivers/gpu/drm/imagination/pvr_drv.c
@@ -28,6 +28,7 @@
 #include <linux/export.h>
 #include <linux/fs.h>
 #include <linux/kernel.h>
+#include <linux/list.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -1326,6 +1327,8 @@ pvr_drm_driver_open(struct drm_device *drm_dev, struct drm_file *file)
 	 */
 	pvr_file->pvr_dev = pvr_dev;
 
+	INIT_LIST_HEAD(&pvr_file->contexts);
+
 	xa_init_flags(&pvr_file->ctx_handles, XA_FLAGS_ALLOC1);
 	xa_init_flags(&pvr_file->free_list_handles, XA_FLAGS_ALLOC1);
 	xa_init_flags(&pvr_file->hwrt_handles, XA_FLAGS_ALLOC1);
diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c
index 97c0f772ed65..7bd6ba4c6e8a 100644
--- a/drivers/gpu/drm/imagination/pvr_vm.c
+++ b/drivers/gpu/drm/imagination/pvr_vm.c
@@ -14,6 +14,7 @@
 #include <drm/drm_gem.h>
 #include <drm/drm_gpuvm.h>
 
+#include <linux/bug.h>
 #include <linux/container_of.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -597,12 +598,26 @@ err_free:
 }
 
 /**
- * pvr_vm_context_release() - Teardown a VM context.
- * @ref_count: Pointer to reference counter of the VM context.
+ * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context.
+ * @vm_ctx: Target VM context.
  *
  * This function ensures that no mappings are left dangling by unmapping them
  * all in order of ascending device-virtual address.
  */
+void
+pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx)
+{
+	WARN_ON(pvr_vm_unmap(vm_ctx, vm_ctx->gpuvm_mgr.mm_start,
+			     vm_ctx->gpuvm_mgr.mm_range));
+}
+
+/**
+ * pvr_vm_context_release() - Teardown a VM context.
+ * @ref_count: Pointer to reference counter of the VM context.
+ *
+ * This function also ensures that no mappings are left dangling by calling
+ * pvr_vm_unmap_all.
+ */
 static void
 pvr_vm_context_release(struct kref *ref_count)
 {
@@ -612,8 +627,7 @@ pvr_vm_context_release(struct kref *ref_count)
 	if (vm_ctx->fw_mem_ctx_obj)
 		pvr_fw_object_destroy(vm_ctx->fw_mem_ctx_obj);
 
-	WARN_ON(pvr_vm_unmap(vm_ctx, vm_ctx->gpuvm_mgr.mm_start,
-			     vm_ctx->gpuvm_mgr.mm_range));
+	pvr_vm_unmap_all(vm_ctx);
 
 	pvr_mmu_context_destroy(vm_ctx->mmu_ctx);
 	drm_gem_private_object_fini(&vm_ctx->dummy_gem);
diff --git a/drivers/gpu/drm/imagination/pvr_vm.h b/drivers/gpu/drm/imagination/pvr_vm.h
index f2a6463f2b05..79406243617c 100644
--- a/drivers/gpu/drm/imagination/pvr_vm.h
+++ b/drivers/gpu/drm/imagination/pvr_vm.h
@@ -39,6 +39,7 @@ int pvr_vm_map(struct pvr_vm_context *vm_ctx,
 	       struct pvr_gem_object *pvr_obj, u64 pvr_obj_offset,
 	       u64 device_addr, u64 size);
 int pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size);
+void pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx);
 
 dma_addr_t pvr_vm_get_page_table_root_addr(struct pvr_vm_context *vm_ctx);
 struct dma_resv *pvr_vm_get_dma_resv(struct pvr_vm_context *vm_ctx);
diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c
index 175b00e5a253..eb0e1233ad04 100644
--- a/drivers/gpu/drm/mediatek/mtk_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_crtc.c
@@ -127,9 +127,8 @@ static void mtk_crtc_destroy(struct drm_crtc *crtc)
 
 	mtk_mutex_put(mtk_crtc->mutex);
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
-	cmdq_pkt_destroy(&mtk_crtc->cmdq_client, &mtk_crtc->cmdq_handle);
-
 	if (mtk_crtc->cmdq_client.chan) {
+		cmdq_pkt_destroy(&mtk_crtc->cmdq_client, &mtk_crtc->cmdq_handle);
 		mbox_free_channel(mtk_crtc->cmdq_client.chan);
 		mtk_crtc->cmdq_client.chan = NULL;
 	}
@@ -913,6 +912,7 @@ static int mtk_crtc_init_comp_planes(struct drm_device *drm_dev,
 				BIT(pipe),
 				mtk_crtc_plane_type(mtk_crtc->layer_nr, num_planes),
 				mtk_ddp_comp_supported_rotations(comp),
+				mtk_ddp_comp_get_blend_modes(comp),
 				mtk_ddp_comp_get_formats(comp),
 				mtk_ddp_comp_get_num_formats(comp), i);
 		if (ret)
diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
index be66d94be361..edc6417639e6 100644
--- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
@@ -363,6 +363,7 @@ static const struct mtk_ddp_comp_funcs ddp_ovl = {
 	.layer_config = mtk_ovl_layer_config,
 	.bgclr_in_on = mtk_ovl_bgclr_in_on,
 	.bgclr_in_off = mtk_ovl_bgclr_in_off,
+	.get_blend_modes = mtk_ovl_get_blend_modes,
 	.get_formats = mtk_ovl_get_formats,
 	.get_num_formats = mtk_ovl_get_num_formats,
 };
@@ -416,6 +417,7 @@ static const struct mtk_ddp_comp_funcs ddp_ovl_adaptor = {
 	.disconnect = mtk_ovl_adaptor_disconnect,
 	.add = mtk_ovl_adaptor_add_comp,
 	.remove = mtk_ovl_adaptor_remove_comp,
+	.get_blend_modes = mtk_ovl_adaptor_get_blend_modes,
 	.get_formats = mtk_ovl_adaptor_get_formats,
 	.get_num_formats = mtk_ovl_adaptor_get_num_formats,
 	.mode_valid = mtk_ovl_adaptor_mode_valid,
diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
index ecf6dc283cd7..39720b27f4e9 100644
--- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
@@ -80,6 +80,7 @@ struct mtk_ddp_comp_funcs {
 	void (*ctm_set)(struct device *dev,
 			struct drm_crtc_state *state);
 	struct device * (*dma_dev_get)(struct device *dev);
+	u32 (*get_blend_modes)(struct device *dev);
 	const u32 *(*get_formats)(struct device *dev);
 	size_t (*get_num_formats)(struct device *dev);
 	void (*connect)(struct device *dev, struct device *mmsys_dev, unsigned int next);
@@ -267,6 +268,15 @@ static inline struct device *mtk_ddp_comp_dma_dev_get(struct mtk_ddp_comp *comp)
 }
 
 static inline
+u32 mtk_ddp_comp_get_blend_modes(struct mtk_ddp_comp *comp)
+{
+	if (comp->funcs && comp->funcs->get_blend_modes)
+		return comp->funcs->get_blend_modes(comp->dev);
+
+	return 0;
+}
+
+static inline
 const u32 *mtk_ddp_comp_get_formats(struct mtk_ddp_comp *comp)
 {
 	if (comp->funcs && comp->funcs->get_formats)
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_drv.h b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
index 082ac18fe04a..04154db9085c 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_drv.h
+++ b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
@@ -103,6 +103,7 @@ void mtk_ovl_register_vblank_cb(struct device *dev,
 void mtk_ovl_unregister_vblank_cb(struct device *dev);
 void mtk_ovl_enable_vblank(struct device *dev);
 void mtk_ovl_disable_vblank(struct device *dev);
+u32 mtk_ovl_get_blend_modes(struct device *dev);
 const u32 *mtk_ovl_get_formats(struct device *dev);
 size_t mtk_ovl_get_num_formats(struct device *dev);
 
@@ -131,6 +132,7 @@ void mtk_ovl_adaptor_start(struct device *dev);
 void mtk_ovl_adaptor_stop(struct device *dev);
 unsigned int mtk_ovl_adaptor_layer_nr(struct device *dev);
 struct device *mtk_ovl_adaptor_dma_dev_get(struct device *dev);
+u32 mtk_ovl_adaptor_get_blend_modes(struct device *dev);
 const u32 *mtk_ovl_adaptor_get_formats(struct device *dev);
 size_t mtk_ovl_adaptor_get_num_formats(struct device *dev);
 enum drm_mode_status mtk_ovl_adaptor_mode_valid(struct device *dev,
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 89b439dcf3a6..e0c0bb01f65a 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -65,8 +65,8 @@
 #define OVL_CON_CLRFMT_RGB	(1 << 12)
 #define OVL_CON_CLRFMT_ARGB8888	(2 << 12)
 #define OVL_CON_CLRFMT_RGBA8888	(3 << 12)
-#define OVL_CON_CLRFMT_ABGR8888	(OVL_CON_CLRFMT_RGBA8888 | OVL_CON_BYTE_SWAP)
-#define OVL_CON_CLRFMT_BGRA8888	(OVL_CON_CLRFMT_ARGB8888 | OVL_CON_BYTE_SWAP)
+#define OVL_CON_CLRFMT_ABGR8888	(OVL_CON_CLRFMT_ARGB8888 | OVL_CON_BYTE_SWAP)
+#define OVL_CON_CLRFMT_BGRA8888	(OVL_CON_CLRFMT_RGBA8888 | OVL_CON_BYTE_SWAP)
 #define OVL_CON_CLRFMT_UYVY	(4 << 12)
 #define OVL_CON_CLRFMT_YUYV	(5 << 12)
 #define OVL_CON_MTX_YUV_TO_RGB	(6 << 16)
@@ -146,6 +146,7 @@ struct mtk_disp_ovl_data {
 	bool fmt_rgb565_is_0;
 	bool smi_id_en;
 	bool supports_afbc;
+	const u32 blend_modes;
 	const u32 *formats;
 	size_t num_formats;
 	bool supports_clrfmt_ext;
@@ -214,6 +215,13 @@ void mtk_ovl_disable_vblank(struct device *dev)
 	writel_relaxed(0x0, ovl->regs + DISP_REG_OVL_INTEN);
 }
 
+u32 mtk_ovl_get_blend_modes(struct device *dev)
+{
+	struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
+
+	return ovl->data->blend_modes;
+}
+
 const u32 *mtk_ovl_get_formats(struct device *dev)
 {
 	struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
@@ -386,14 +394,27 @@ void mtk_ovl_layer_off(struct device *dev, unsigned int idx,
 		      DISP_REG_OVL_RDMA_CTRL(idx));
 }
 
-static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt,
-				    unsigned int blend_mode)
+static unsigned int mtk_ovl_fmt_convert(struct mtk_disp_ovl *ovl,
+					struct mtk_plane_state *state)
 {
-	/* The return value in switch "MEM_MODE_INPUT_FORMAT_XXX"
-	 * is defined in mediatek HW data sheet.
-	 * The alphabet order in XXX is no relation to data
-	 * arrangement in memory.
+	unsigned int fmt = state->pending.format;
+	unsigned int blend_mode = DRM_MODE_BLEND_COVERAGE;
+
+	/*
+	 * For the platforms where OVL_CON_CLRFMT_MAN is defined in the hardware data sheet
+	 * and supports premultiplied color formats, such as OVL_CON_CLRFMT_PARGB8888.
+	 *
+	 * Check blend_modes in the driver data to see if premultiplied mode is supported.
+	 * If not, use coverage mode instead to set it to the supported color formats.
+	 *
+	 * Current DRM assumption is that alpha is default premultiplied, so the bitmask of
+	 * blend_modes must include BIT(DRM_MODE_BLEND_PREMULTI). Otherwise, mtk_plane_init()
+	 * will get an error return from drm_plane_create_blend_mode_property() and
+	 * state->base.pixel_blend_mode should not be used.
 	 */
+	if (ovl->data->blend_modes & BIT(DRM_MODE_BLEND_PREMULTI))
+		blend_mode = state->base.pixel_blend_mode;
+
 	switch (fmt) {
 	default:
 	case DRM_FORMAT_RGB565:
@@ -471,20 +492,26 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx,
 		return;
 	}
 
-	con = ovl_fmt_convert(ovl, fmt, blend_mode);
+	con = mtk_ovl_fmt_convert(ovl, state);
 	if (state->base.fb) {
-		con |= OVL_CON_AEN;
 		con |= state->base.alpha & OVL_CON_ALPHA;
-	}
 
-	/* CONST_BLD must be enabled for XRGB formats although the alpha channel
-	 * can be ignored, or OVL will still read the value from memory.
-	 * For RGB888 related formats, whether CONST_BLD is enabled or not won't
-	 * affect the result. Therefore we use !has_alpha as the condition.
-	 */
-	if ((state->base.fb && !state->base.fb->format->has_alpha) ||
-	    blend_mode == DRM_MODE_BLEND_PIXEL_NONE)
-		ignore_pixel_alpha = OVL_CONST_BLEND;
+		/*
+		 * For blend_modes supported SoCs, always enable alpha blending.
+		 * For blend_modes unsupported SoCs, enable alpha blending when has_alpha is set.
+		 */
+		if (blend_mode || state->base.fb->format->has_alpha)
+			con |= OVL_CON_AEN;
+
+		/*
+		 * Although the alpha channel can be ignored, CONST_BLD must be enabled
+		 * for XRGB format, otherwise OVL will still read the value from memory.
+		 * For RGB888 related formats, whether CONST_BLD is enabled or not won't
+		 * affect the result. Therefore we use !has_alpha as the condition.
+		 */
+		if (blend_mode == DRM_MODE_BLEND_PIXEL_NONE || !state->base.fb->format->has_alpha)
+			ignore_pixel_alpha = OVL_CONST_BLEND;
+	}
 
 	if (pending->rotation & DRM_MODE_REFLECT_Y) {
 		con |= OVL_CON_VIRT_FLIP;
@@ -663,6 +690,9 @@ static const struct mtk_disp_ovl_data mt8192_ovl_driver_data = {
 	.layer_nr = 4,
 	.fmt_rgb565_is_0 = true,
 	.smi_id_en = true,
+	.blend_modes = BIT(DRM_MODE_BLEND_PREMULTI) |
+		       BIT(DRM_MODE_BLEND_COVERAGE) |
+		       BIT(DRM_MODE_BLEND_PIXEL_NONE),
 	.formats = mt8173_formats,
 	.num_formats = ARRAY_SIZE(mt8173_formats),
 };
@@ -673,6 +703,9 @@ static const struct mtk_disp_ovl_data mt8192_ovl_2l_driver_data = {
 	.layer_nr = 2,
 	.fmt_rgb565_is_0 = true,
 	.smi_id_en = true,
+	.blend_modes = BIT(DRM_MODE_BLEND_PREMULTI) |
+		       BIT(DRM_MODE_BLEND_COVERAGE) |
+		       BIT(DRM_MODE_BLEND_PIXEL_NONE),
 	.formats = mt8173_formats,
 	.num_formats = ARRAY_SIZE(mt8173_formats),
 };
@@ -684,6 +717,9 @@ static const struct mtk_disp_ovl_data mt8195_ovl_driver_data = {
 	.fmt_rgb565_is_0 = true,
 	.smi_id_en = true,
 	.supports_afbc = true,
+	.blend_modes = BIT(DRM_MODE_BLEND_PREMULTI) |
+		       BIT(DRM_MODE_BLEND_COVERAGE) |
+		       BIT(DRM_MODE_BLEND_PIXEL_NONE),
 	.formats = mt8195_formats,
 	.num_formats = ARRAY_SIZE(mt8195_formats),
 	.supports_clrfmt_ext = true,
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c
index c6768210b08b..bf2546c4681a 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c
@@ -400,6 +400,13 @@ void mtk_ovl_adaptor_disable_vblank(struct device *dev)
 	mtk_ethdr_disable_vblank(ovl_adaptor->ovl_adaptor_comp[OVL_ADAPTOR_ETHDR0]);
 }
 
+u32 mtk_ovl_adaptor_get_blend_modes(struct device *dev)
+{
+	struct mtk_disp_ovl_adaptor *ovl_adaptor = dev_get_drvdata(dev);
+
+	return mtk_ethdr_get_blend_modes(ovl_adaptor->ovl_adaptor_comp[OVL_ADAPTOR_ETHDR0]);
+}
+
 const u32 *mtk_ovl_adaptor_get_formats(struct device *dev)
 {
 	struct mtk_disp_ovl_adaptor *ovl_adaptor = dev_get_drvdata(dev);
diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c
index d8796a904eca..f2bee617f063 100644
--- a/drivers/gpu/drm/mediatek/mtk_dp.c
+++ b/drivers/gpu/drm/mediatek/mtk_dp.c
@@ -145,6 +145,89 @@ struct mtk_dp_data {
 	u16 audio_m_div2_bit;
 };
 
+static const struct mtk_dp_efuse_fmt mt8188_dp_efuse_fmt[MTK_DP_CAL_MAX] = {
+	[MTK_DP_CAL_GLB_BIAS_TRIM] = {
+		.idx = 0,
+		.shift = 10,
+		.mask = 0x1f,
+		.min_val = 1,
+		.max_val = 0x1e,
+		.default_val = 0xf,
+	},
+	[MTK_DP_CAL_CLKTX_IMPSE] = {
+		.idx = 0,
+		.shift = 15,
+		.mask = 0xf,
+		.min_val = 1,
+		.max_val = 0xe,
+		.default_val = 0x8,
+	},
+	[MTK_DP_CAL_LN_TX_IMPSEL_PMOS_0] = {
+		.idx = 1,
+		.shift = 0,
+		.mask = 0xf,
+		.min_val = 1,
+		.max_val = 0xe,
+		.default_val = 0x8,
+	},
+	[MTK_DP_CAL_LN_TX_IMPSEL_PMOS_1] = {
+		.idx = 1,
+		.shift = 8,
+		.mask = 0xf,
+		.min_val = 1,
+		.max_val = 0xe,
+		.default_val = 0x8,
+	},
+	[MTK_DP_CAL_LN_TX_IMPSEL_PMOS_2] = {
+		.idx = 1,
+		.shift = 16,
+		.mask = 0xf,
+		.min_val = 1,
+		.max_val = 0xe,
+		.default_val = 0x8,
+	},
+	[MTK_DP_CAL_LN_TX_IMPSEL_PMOS_3] = {
+		.idx = 1,
+		.shift = 24,
+		.mask = 0xf,
+		.min_val = 1,
+		.max_val = 0xe,
+		.default_val = 0x8,
+	},
+	[MTK_DP_CAL_LN_TX_IMPSEL_NMOS_0] = {
+		.idx = 1,
+		.shift = 4,
+		.mask = 0xf,
+		.min_val = 1,
+		.max_val = 0xe,
+		.default_val = 0x8,
+	},
+	[MTK_DP_CAL_LN_TX_IMPSEL_NMOS_1] = {
+		.idx = 1,
+		.shift = 12,
+		.mask = 0xf,
+		.min_val = 1,
+		.max_val = 0xe,
+		.default_val = 0x8,
+	},
+	[MTK_DP_CAL_LN_TX_IMPSEL_NMOS_2] = {
+		.idx = 1,
+		.shift = 20,
+		.mask = 0xf,
+		.min_val = 1,
+		.max_val = 0xe,
+		.default_val = 0x8,
+	},
+	[MTK_DP_CAL_LN_TX_IMPSEL_NMOS_3] = {
+		.idx = 1,
+		.shift = 28,
+		.mask = 0xf,
+		.min_val = 1,
+		.max_val = 0xe,
+		.default_val = 0x8,
+	},
+};
+
 static const struct mtk_dp_efuse_fmt mt8195_edp_efuse_fmt[MTK_DP_CAL_MAX] = {
 	[MTK_DP_CAL_GLB_BIAS_TRIM] = {
 		.idx = 3,
@@ -2771,7 +2854,7 @@ static SIMPLE_DEV_PM_OPS(mtk_dp_pm_ops, mtk_dp_suspend, mtk_dp_resume);
 static const struct mtk_dp_data mt8188_dp_data = {
 	.bridge_type = DRM_MODE_CONNECTOR_DisplayPort,
 	.smc_cmd = MTK_DP_SIP_ATF_VIDEO_UNMUTE,
-	.efuse_fmt = mt8195_dp_efuse_fmt,
+	.efuse_fmt = mt8188_dp_efuse_fmt,
 	.audio_supported = true,
 	.audio_pkt_in_hblank_area = true,
 	.audio_m_div2_bit = MT8188_AUDIO_M_CODE_MULT_DIV_SEL_DP_ENC0_P0_DIV_2,
diff --git a/drivers/gpu/drm/mediatek/mtk_ethdr.c b/drivers/gpu/drm/mediatek/mtk_ethdr.c
index d1d9cf8b10e1..0f22e7d337cb 100644
--- a/drivers/gpu/drm/mediatek/mtk_ethdr.c
+++ b/drivers/gpu/drm/mediatek/mtk_ethdr.c
@@ -145,6 +145,13 @@ static irqreturn_t mtk_ethdr_irq_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+u32 mtk_ethdr_get_blend_modes(struct device *dev)
+{
+	return BIT(DRM_MODE_BLEND_PREMULTI) |
+	       BIT(DRM_MODE_BLEND_COVERAGE) |
+	       BIT(DRM_MODE_BLEND_PIXEL_NONE);
+}
+
 void mtk_ethdr_layer_config(struct device *dev, unsigned int idx,
 			    struct mtk_plane_state *state,
 			    struct cmdq_pkt *cmdq_pkt)
diff --git a/drivers/gpu/drm/mediatek/mtk_ethdr.h b/drivers/gpu/drm/mediatek/mtk_ethdr.h
index 81af9edea3f7..a72aeee46829 100644
--- a/drivers/gpu/drm/mediatek/mtk_ethdr.h
+++ b/drivers/gpu/drm/mediatek/mtk_ethdr.h
@@ -13,6 +13,7 @@ void mtk_ethdr_clk_disable(struct device *dev);
 void mtk_ethdr_config(struct device *dev, unsigned int w,
 		      unsigned int h, unsigned int vrefresh,
 		      unsigned int bpc, struct cmdq_pkt *cmdq_pkt);
+u32 mtk_ethdr_get_blend_modes(struct device *dev);
 void mtk_ethdr_layer_config(struct device *dev, unsigned int idx,
 			    struct mtk_plane_state *state,
 			    struct cmdq_pkt *cmdq_pkt);
diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c
index 7d2cb4e0fafa..8a48b3b0a956 100644
--- a/drivers/gpu/drm/mediatek/mtk_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_plane.c
@@ -320,8 +320,8 @@ static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = {
 
 int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
 		   unsigned long possible_crtcs, enum drm_plane_type type,
-		   unsigned int supported_rotations, const u32 *formats,
-		   size_t num_formats, unsigned int plane_idx)
+		   unsigned int supported_rotations, const u32 blend_modes,
+		   const u32 *formats, size_t num_formats, unsigned int plane_idx)
 {
 	int err;
 
@@ -366,12 +366,11 @@ int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
 	if (err)
 		DRM_ERROR("failed to create property: alpha\n");
 
-	err = drm_plane_create_blend_mode_property(plane,
-						   BIT(DRM_MODE_BLEND_PREMULTI) |
-						   BIT(DRM_MODE_BLEND_COVERAGE) |
-						   BIT(DRM_MODE_BLEND_PIXEL_NONE));
-	if (err)
-		DRM_ERROR("failed to create property: blend_mode\n");
+	if (blend_modes) {
+		err = drm_plane_create_blend_mode_property(plane, blend_modes);
+		if (err)
+			DRM_ERROR("failed to create property: blend_mode\n");
+	}
 
 	drm_plane_helper_add(plane, &mtk_plane_helper_funcs);
 
diff --git a/drivers/gpu/drm/mediatek/mtk_plane.h b/drivers/gpu/drm/mediatek/mtk_plane.h
index 5b177eac67b7..3b13b89989c7 100644
--- a/drivers/gpu/drm/mediatek/mtk_plane.h
+++ b/drivers/gpu/drm/mediatek/mtk_plane.h
@@ -48,6 +48,6 @@ to_mtk_plane_state(struct drm_plane_state *state)
 
 int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
 		   unsigned long possible_crtcs, enum drm_plane_type type,
-		   unsigned int supported_rotations, const u32 *formats,
-		   size_t num_formats, unsigned int plane_idx);
+		   unsigned int supported_rotations, const u32 blend_modes,
+		   const u32 *formats, size_t num_formats, unsigned int plane_idx);
 #endif
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/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index 9e6f39912368..a2055f2a014a 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -210,7 +210,7 @@ struct nvkm_gsp {
 	} *rm;
 
 	struct {
-		struct mutex mutex;;
+		struct mutex mutex;
 		struct idr idr;
 	} client_id;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 1f2d649f4b96..1a072568cef6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -193,7 +193,7 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
 	if (!spage || !(src & MIGRATE_PFN_MIGRATE))
 		goto done;
 
-	dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address);
+	dpage = alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vmf->vma, vmf->address);
 	if (!dpage)
 		goto done;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index f6e78dba594f..34985771b2a2 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -331,7 +331,7 @@ nouveau_accel_ce_init(struct nouveau_drm *drm)
 		return;
 	}
 
-	ret = nouveau_channel_new(&drm->client, false, runm, NvDmaFB, NvDmaTT, &drm->cechan);
+	ret = nouveau_channel_new(&drm->client, true, runm, NvDmaFB, NvDmaTT, &drm->cechan);
 	if (ret)
 		NV_ERROR(drm, "failed to create ce channel, %d\n", ret);
 }
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/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c
index 4082c8f2951d..6fbff516c1c1 100644
--- a/drivers/gpu/drm/panthor/panthor_device.c
+++ b/drivers/gpu/drm/panthor/panthor_device.c
@@ -390,11 +390,15 @@ int panthor_device_mmap_io(struct panthor_device *ptdev, struct vm_area_struct *
 {
 	u64 offset = (u64)vma->vm_pgoff << PAGE_SHIFT;
 
+	if ((vma->vm_flags & VM_SHARED) == 0)
+		return -EINVAL;
+
 	switch (offset) {
 	case DRM_PANTHOR_USER_FLUSH_ID_MMIO_OFFSET:
 		if (vma->vm_end - vma->vm_start != PAGE_SIZE ||
 		    (vma->vm_flags & (VM_WRITE | VM_EXEC)))
 			return -EINVAL;
+		vm_flags_clear(vma, VM_MAYWRITE);
 
 		break;
 
diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c
index ef232c0c2049..4e2d3a02ea06 100644
--- a/drivers/gpu/drm/panthor/panthor_fw.c
+++ b/drivers/gpu/drm/panthor/panthor_fw.c
@@ -487,6 +487,7 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev,
 					 struct panthor_fw_binary_iter *iter,
 					 u32 ehdr)
 {
+	ssize_t vm_pgsz = panthor_vm_page_size(ptdev->fw->vm);
 	struct panthor_fw_binary_section_entry_hdr hdr;
 	struct panthor_fw_section *section;
 	u32 section_size;
@@ -515,8 +516,7 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev,
 		return -EINVAL;
 	}
 
-	if ((hdr.va.start & ~PAGE_MASK) != 0 ||
-	    (hdr.va.end & ~PAGE_MASK) != 0) {
+	if (!IS_ALIGNED(hdr.va.start, vm_pgsz) || !IS_ALIGNED(hdr.va.end, vm_pgsz)) {
 		drm_err(&ptdev->base, "Firmware corrupted, virtual addresses not page aligned: 0x%x-0x%x\n",
 			hdr.va.start, hdr.va.end);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c
index 38f560864879..be97d56bc011 100644
--- a/drivers/gpu/drm/panthor/panthor_gem.c
+++ b/drivers/gpu/drm/panthor/panthor_gem.c
@@ -44,8 +44,7 @@ void panthor_kernel_bo_destroy(struct panthor_kernel_bo *bo)
 			to_panthor_bo(bo->obj)->exclusive_vm_root_gem != panthor_vm_root_gem(vm)))
 		goto out_free_bo;
 
-	ret = panthor_vm_unmap_range(vm, bo->va_node.start,
-				     panthor_kernel_bo_size(bo));
+	ret = panthor_vm_unmap_range(vm, bo->va_node.start, bo->va_node.size);
 	if (ret)
 		goto out_free_bo;
 
@@ -95,10 +94,16 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm,
 	}
 
 	bo = to_panthor_bo(&obj->base);
-	size = obj->base.size;
 	kbo->obj = &obj->base;
 	bo->flags = bo_flags;
 
+	/* The system and GPU MMU page size might differ, which becomes a
+	 * problem for FW sections that need to be mapped at explicit address
+	 * since our PAGE_SIZE alignment might cover a VA range that's
+	 * expected to be used for another section.
+	 * Make sure we never map more than we need.
+	 */
+	size = ALIGN(size, panthor_vm_page_size(vm));
 	ret = panthor_vm_alloc_va(vm, gpu_va, size, &kbo->va_node);
 	if (ret)
 		goto err_put_obj;
diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c
index 3cd2bce59edc..7db2edb3374c 100644
--- a/drivers/gpu/drm/panthor/panthor_mmu.c
+++ b/drivers/gpu/drm/panthor/panthor_mmu.c
@@ -826,6 +826,14 @@ void panthor_vm_idle(struct panthor_vm *vm)
 	mutex_unlock(&ptdev->mmu->as.slots_lock);
 }
 
+u32 panthor_vm_page_size(struct panthor_vm *vm)
+{
+	const struct io_pgtable *pgt = io_pgtable_ops_to_pgtable(vm->pgtbl_ops);
+	u32 pg_shift = ffs(pgt->cfg.pgsize_bitmap) - 1;
+
+	return 1u << pg_shift;
+}
+
 static void panthor_vm_stop(struct panthor_vm *vm)
 {
 	drm_sched_stop(&vm->sched, NULL);
@@ -1025,12 +1033,13 @@ int
 panthor_vm_alloc_va(struct panthor_vm *vm, u64 va, u64 size,
 		    struct drm_mm_node *va_node)
 {
+	ssize_t vm_pgsz = panthor_vm_page_size(vm);
 	int ret;
 
-	if (!size || (size & ~PAGE_MASK))
+	if (!size || !IS_ALIGNED(size, vm_pgsz))
 		return -EINVAL;
 
-	if (va != PANTHOR_VM_KERNEL_AUTO_VA && (va & ~PAGE_MASK))
+	if (va != PANTHOR_VM_KERNEL_AUTO_VA && !IS_ALIGNED(va, vm_pgsz))
 		return -EINVAL;
 
 	mutex_lock(&vm->mm_lock);
@@ -1571,7 +1580,9 @@ panthor_vm_pool_get_vm(struct panthor_vm_pool *pool, u32 handle)
 {
 	struct panthor_vm *vm;
 
+	xa_lock(&pool->xa);
 	vm = panthor_vm_get(xa_load(&pool->xa, handle));
+	xa_unlock(&pool->xa);
 
 	return vm;
 }
@@ -2366,11 +2377,12 @@ panthor_vm_bind_prepare_op_ctx(struct drm_file *file,
 			       const struct drm_panthor_vm_bind_op *op,
 			       struct panthor_vm_op_ctx *op_ctx)
 {
+	ssize_t vm_pgsz = panthor_vm_page_size(vm);
 	struct drm_gem_object *gem;
 	int ret;
 
 	/* Aligned on page size. */
-	if ((op->va | op->size) & ~PAGE_MASK)
+	if (!IS_ALIGNED(op->va | op->size, vm_pgsz))
 		return -EINVAL;
 
 	switch (op->flags & DRM_PANTHOR_VM_BIND_OP_TYPE_MASK) {
diff --git a/drivers/gpu/drm/panthor/panthor_mmu.h b/drivers/gpu/drm/panthor/panthor_mmu.h
index 6788771071e3..8d21e83d8aba 100644
--- a/drivers/gpu/drm/panthor/panthor_mmu.h
+++ b/drivers/gpu/drm/panthor/panthor_mmu.h
@@ -30,6 +30,7 @@ panthor_vm_get_bo_for_va(struct panthor_vm *vm, u64 va, u64 *bo_offset);
 
 int panthor_vm_active(struct panthor_vm *vm);
 void panthor_vm_idle(struct panthor_vm *vm);
+u32 panthor_vm_page_size(struct panthor_vm *vm);
 int panthor_vm_as(struct panthor_vm *vm);
 int panthor_vm_flush_all(struct panthor_vm *vm);
 
diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
index aee362abb710..9929e22f4d8d 100644
--- a/drivers/gpu/drm/panthor/panthor_sched.c
+++ b/drivers/gpu/drm/panthor/panthor_sched.c
@@ -589,10 +589,11 @@ struct panthor_group {
 	 * @timedout: True when a timeout occurred on any of the queues owned by
 	 * this group.
 	 *
-	 * Timeouts can be reported by drm_sched or by the FW. In any case, any
-	 * timeout situation is unrecoverable, and the group becomes useless.
-	 * We simply wait for all references to be dropped so we can release the
-	 * group object.
+	 * Timeouts can be reported by drm_sched or by the FW. If a reset is required,
+	 * and the group can't be suspended, this also leads to a timeout. In any case,
+	 * any timeout situation is unrecoverable, and the group becomes useless. We
+	 * simply wait for all references to be dropped so we can release the group
+	 * object.
 	 */
 	bool timedout;
 
@@ -2640,6 +2641,12 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 		csgs_upd_ctx_init(&upd_ctx);
 		while (slot_mask) {
 			u32 csg_id = ffs(slot_mask) - 1;
+			struct panthor_csg_slot *csg_slot = &sched->csg_slots[csg_id];
+
+			/* We consider group suspension failures as fatal and flag the
+			 * group as unusable by setting timedout=true.
+			 */
+			csg_slot->group->timedout = true;
 
 			csgs_upd_ctx_queue_reqs(ptdev, &upd_ctx, csg_id,
 						CSG_STATE_TERMINATE,
@@ -3409,6 +3416,11 @@ panthor_job_create(struct panthor_file *pfile,
 		goto err_put_job;
 	}
 
+	if (!group_can_run(job->group)) {
+		ret = -EINVAL;
+		goto err_put_job;
+	}
+
 	if (job->queue_idx >= job->group->queue_count ||
 	    !job->group->queues[job->queue_idx]) {
 		ret = -EINVAL;
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index fca8b08535a5..6328627b7c34 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -228,10 +228,8 @@ void radeon_dp_aux_init(struct radeon_connector *radeon_connector)
 {
 	struct drm_device *dev = radeon_connector->base.dev;
 	struct radeon_device *rdev = dev->dev_private;
-	int ret;
 
 	radeon_connector->ddc_bus->rec.hpd = radeon_connector->hpd.hpd;
-	radeon_connector->ddc_bus->aux.dev = radeon_connector->base.kdev;
 	radeon_connector->ddc_bus->aux.drm_dev = radeon_connector->base.dev;
 	if (ASIC_IS_DCE5(rdev)) {
 		if (radeon_auxch)
@@ -242,11 +240,8 @@ void radeon_dp_aux_init(struct radeon_connector *radeon_connector)
 		radeon_connector->ddc_bus->aux.transfer = radeon_dp_aux_transfer_atom;
 	}
 
-	ret = drm_dp_aux_register(&radeon_connector->ddc_bus->aux);
-	if (!ret)
-		radeon_connector->ddc_bus->has_aux = true;
-
-	WARN(ret, "drm_dp_aux_register() failed with error %d\n", ret);
+	drm_dp_aux_init(&radeon_connector->ddc_bus->aux);
+	radeon_connector->ddc_bus->has_aux = true;
 }
 
 /***** general DP utility functions *****/
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 528a8f3677c2..f9c73c55f04f 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1786,6 +1786,20 @@ static enum drm_mode_status radeon_dp_mode_valid(struct drm_connector *connector
 	return MODE_OK;
 }
 
+static int
+radeon_connector_late_register(struct drm_connector *connector)
+{
+	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+	int r = 0;
+
+	if (radeon_connector->ddc_bus->has_aux) {
+		radeon_connector->ddc_bus->aux.dev = radeon_connector->base.kdev;
+		r = drm_dp_aux_register(&radeon_connector->ddc_bus->aux);
+	}
+
+	return r;
+}
+
 static const struct drm_connector_helper_funcs radeon_dp_connector_helper_funcs = {
 	.get_modes = radeon_dp_get_modes,
 	.mode_valid = radeon_dp_mode_valid,
@@ -1800,6 +1814,7 @@ static const struct drm_connector_funcs radeon_dp_connector_funcs = {
 	.early_unregister = radeon_connector_unregister,
 	.destroy = radeon_connector_destroy,
 	.force = radeon_dvi_force,
+	.late_register = radeon_connector_late_register,
 };
 
 static const struct drm_connector_funcs radeon_edp_connector_funcs = {
@@ -1810,6 +1825,7 @@ static const struct drm_connector_funcs radeon_edp_connector_funcs = {
 	.early_unregister = radeon_connector_unregister,
 	.destroy = radeon_connector_destroy,
 	.force = radeon_dvi_force,
+	.late_register = radeon_connector_late_register,
 };
 
 static const struct drm_connector_funcs radeon_lvds_bridge_connector_funcs = {
@@ -1820,6 +1836,7 @@ static const struct drm_connector_funcs radeon_lvds_bridge_connector_funcs = {
 	.early_unregister = radeon_connector_unregister,
 	.destroy = radeon_connector_destroy,
 	.force = radeon_dvi_force,
+	.late_register = radeon_connector_late_register,
 };
 
 void
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/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 9735f4968b86..bf2d4b16dc2a 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -44,8 +44,6 @@ struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj);
 int radeon_gem_prime_pin(struct drm_gem_object *obj);
 void radeon_gem_prime_unpin(struct drm_gem_object *obj);
 
-const struct drm_gem_object_funcs radeon_gem_object_funcs;
-
 static vm_fault_t radeon_gem_fault(struct vm_fault *vmf)
 {
 	struct ttm_buffer_object *bo = vmf->vma->vm_private_data;
@@ -132,7 +130,6 @@ retry:
 		return r;
 	}
 	*obj = &robj->tbo.base;
-	(*obj)->funcs = &radeon_gem_object_funcs;
 	robj->pid = task_pid_nr(current);
 
 	mutex_lock(&rdev->gem.mutex);
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index d0e4b43d155c..7672404fdb29 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -151,6 +151,7 @@ int radeon_bo_create(struct radeon_device *rdev,
 	if (bo == NULL)
 		return -ENOMEM;
 	drm_gem_private_object_init(rdev_to_drm(rdev), &bo->tbo.base, size);
+	bo->tbo.base.funcs = &radeon_gem_object_funcs;
 	bo->rdev = rdev;
 	bo->surface_reg = -1;
 	INIT_LIST_HEAD(&bo->list);
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 6f27cab0b76d..e97c6c60bc96 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -87,6 +87,12 @@
 #define CREATE_TRACE_POINTS
 #include "gpu_scheduler_trace.h"
 
+#ifdef CONFIG_LOCKDEP
+static struct lockdep_map drm_sched_lockdep_map = {
+	.name = "drm_sched_lockdep_map"
+};
+#endif
+
 #define to_drm_sched_job(sched_job)		\
 		container_of((sched_job), struct drm_sched_job, queue_node)
 
@@ -1269,7 +1275,13 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 		sched->submit_wq = submit_wq;
 		sched->own_submit_wq = false;
 	} else {
-		sched->submit_wq = alloc_ordered_workqueue(name, 0);
+#ifdef CONFIG_LOCKDEP
+		sched->submit_wq = alloc_ordered_workqueue_lockdep_map(name,
+								       WQ_MEM_RECLAIM,
+								       &drm_sched_lockdep_map);
+#else
+		sched->submit_wq = alloc_ordered_workqueue(name, WQ_MEM_RECLAIM);
+#endif
 		if (!sched->submit_wq)
 			return -ENOMEM;
 
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index c9eb329665ec..34d22ba210b0 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -1153,8 +1153,8 @@ static int host1x_drm_probe(struct host1x_device *dev)
 
 	if (host1x_drm_wants_iommu(dev) && device_iommu_mapped(dma_dev)) {
 		tegra->domain = iommu_paging_domain_alloc(dma_dev);
-		if (!tegra->domain) {
-			err = -ENOMEM;
+		if (IS_ERR(tegra->domain)) {
+			err = PTR_ERR(tegra->domain);
 			goto free;
 		}
 
diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c
index 4de1ea0fc7c0..00c8564520e7 100644
--- a/drivers/gpu/drm/tegra/gr3d.c
+++ b/drivers/gpu/drm/tegra/gr3d.c
@@ -46,7 +46,6 @@ struct gr3d {
 	unsigned int nclocks;
 	struct reset_control_bulk_data resets[RST_GR3D_MAX];
 	unsigned int nresets;
-	struct dev_pm_domain_list *pd_list;
 
 	DECLARE_BITMAP(addr_regs, GR3D_NUM_REGS);
 };
@@ -370,12 +369,18 @@ static int gr3d_power_up_legacy_domain(struct device *dev, const char *name,
 	return 0;
 }
 
+static void gr3d_del_link(void *link)
+{
+	device_link_del(link);
+}
+
 static int gr3d_init_power(struct device *dev, struct gr3d *gr3d)
 {
-	struct dev_pm_domain_attach_data pd_data = {
-		.pd_names = (const char *[]) { "3d0", "3d1" },
-		.num_pd_names = 2,
-	};
+	static const char * const opp_genpd_names[] = { "3d0", "3d1", NULL };
+	const u32 link_flags = DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME;
+	struct device **opp_virt_devs, *pd_dev;
+	struct device_link *link;
+	unsigned int i;
 	int err;
 
 	err = of_count_phandle_with_args(dev->of_node, "power-domains",
@@ -409,10 +414,29 @@ static int gr3d_init_power(struct device *dev, struct gr3d *gr3d)
 	if (dev->pm_domain)
 		return 0;
 
-	err = dev_pm_domain_attach_list(dev, &pd_data, &gr3d->pd_list);
-	if (err < 0)
+	err = devm_pm_opp_attach_genpd(dev, opp_genpd_names, &opp_virt_devs);
+	if (err)
 		return err;
 
+	for (i = 0; opp_genpd_names[i]; i++) {
+		pd_dev = opp_virt_devs[i];
+		if (!pd_dev) {
+			dev_err(dev, "failed to get %s power domain\n",
+				opp_genpd_names[i]);
+			return -EINVAL;
+		}
+
+		link = device_link_add(dev, pd_dev, link_flags);
+		if (!link) {
+			dev_err(dev, "failed to link to %s\n", dev_name(pd_dev));
+			return -EINVAL;
+		}
+
+		err = devm_add_action_or_reset(dev, gr3d_del_link, link);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
@@ -503,13 +527,13 @@ static int gr3d_probe(struct platform_device *pdev)
 
 	err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
 	if (err)
-		goto err;
+		return err;
 
 	err = host1x_client_register(&gr3d->client.base);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to register host1x client: %d\n",
 			err);
-		goto err;
+		return err;
 	}
 
 	/* initialize address register map */
@@ -517,9 +541,6 @@ static int gr3d_probe(struct platform_device *pdev)
 		set_bit(gr3d_addr_regs[i], gr3d->addr_regs);
 
 	return 0;
-err:
-	dev_pm_domain_detach_list(gr3d->pd_list);
-	return err;
 }
 
 static void gr3d_remove(struct platform_device *pdev)
@@ -528,7 +549,6 @@ static void gr3d_remove(struct platform_device *pdev)
 
 	pm_runtime_disable(&pdev->dev);
 	host1x_client_unregister(&gr3d->client.base);
-	dev_pm_domain_detach_list(gr3d->pd_list);
 }
 
 static int __maybe_unused gr3d_runtime_suspend(struct device *dev)
diff --git a/drivers/gpu/drm/tests/drm_connector_test.c b/drivers/gpu/drm/tests/drm_connector_test.c
index 15e36a8db685..6bba97d0be88 100644
--- a/drivers/gpu/drm/tests/drm_connector_test.c
+++ b/drivers/gpu/drm/tests/drm_connector_test.c
@@ -996,7 +996,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb(struct kunit *test)
 	unsigned long long rate;
 	struct drm_device *drm = &priv->drm;
 
-	mode = drm_display_mode_from_cea_vic(drm, 16);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);
@@ -1017,7 +1017,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_10bpc(struct kunit *test)
 	unsigned long long rate;
 	struct drm_device *drm = &priv->drm;
 
-	mode = drm_display_mode_from_cea_vic(drm, 16);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);
@@ -1038,7 +1038,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_10bpc_vic_1(struct kunit *t
 	unsigned long long rate;
 	struct drm_device *drm = &priv->drm;
 
-	mode = drm_display_mode_from_cea_vic(drm, 1);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	rate = drm_hdmi_compute_mode_clock(mode, 10, HDMI_COLORSPACE_RGB);
@@ -1056,7 +1056,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_12bpc(struct kunit *test)
 	unsigned long long rate;
 	struct drm_device *drm = &priv->drm;
 
-	mode = drm_display_mode_from_cea_vic(drm, 16);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);
@@ -1077,7 +1077,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_12bpc_vic_1(struct kunit *t
 	unsigned long long rate;
 	struct drm_device *drm = &priv->drm;
 
-	mode = drm_display_mode_from_cea_vic(drm, 1);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	rate = drm_hdmi_compute_mode_clock(mode, 12, HDMI_COLORSPACE_RGB);
@@ -1095,7 +1095,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_double(struct kunit *test)
 	unsigned long long rate;
 	struct drm_device *drm = &priv->drm;
 
-	mode = drm_display_mode_from_cea_vic(drm, 6);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 6);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_TRUE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);
@@ -1118,7 +1118,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv420_valid(struct kunit
 	unsigned long long rate;
 	unsigned int vic = *(unsigned int *)test->param_value;
 
-	mode = drm_display_mode_from_cea_vic(drm, vic);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, vic);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);
@@ -1155,7 +1155,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv420_10_bpc(struct kuni
 		drm_hdmi_compute_mode_clock_yuv420_vic_valid_tests[0];
 	unsigned long long rate;
 
-	mode = drm_display_mode_from_cea_vic(drm, vic);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, vic);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);
@@ -1180,7 +1180,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv420_12_bpc(struct kuni
 		drm_hdmi_compute_mode_clock_yuv420_vic_valid_tests[0];
 	unsigned long long rate;
 
-	mode = drm_display_mode_from_cea_vic(drm, vic);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, vic);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);
@@ -1203,7 +1203,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv422_8_bpc(struct kunit
 	struct drm_device *drm = &priv->drm;
 	unsigned long long rate;
 
-	mode = drm_display_mode_from_cea_vic(drm, 16);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);
@@ -1225,7 +1225,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv422_10_bpc(struct kuni
 	struct drm_device *drm = &priv->drm;
 	unsigned long long rate;
 
-	mode = drm_display_mode_from_cea_vic(drm, 16);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);
@@ -1247,7 +1247,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv422_12_bpc(struct kuni
 	struct drm_device *drm = &priv->drm;
 	unsigned long long rate;
 
-	mode = drm_display_mode_from_cea_vic(drm, 16);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);
diff --git a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c
index 34ee95d41f29..294773342e71 100644
--- a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c
+++ b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c
@@ -441,7 +441,7 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode_vic_1(struct kunit *test)
 	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
 
-	mode = drm_display_mode_from_cea_vic(drm, 1);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	drm = &priv->drm;
@@ -555,7 +555,7 @@ static void drm_test_check_broadcast_rgb_full_cea_mode_vic_1(struct kunit *test)
 	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
 
-	mode = drm_display_mode_from_cea_vic(drm, 1);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	drm = &priv->drm;
@@ -671,7 +671,7 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode_vic_1(struct kunit *te
 	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
 
-	mode = drm_display_mode_from_cea_vic(drm, 1);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	drm = &priv->drm;
@@ -1263,7 +1263,7 @@ static void drm_test_check_output_bpc_format_vic_1(struct kunit *test)
 	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
 
-	mode = drm_display_mode_from_cea_vic(drm, 1);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	/*
diff --git a/drivers/gpu/drm/tests/drm_kunit_helpers.c b/drivers/gpu/drm/tests/drm_kunit_helpers.c
index aa62719dab0e..04a6b8cc62ac 100644
--- a/drivers/gpu/drm/tests/drm_kunit_helpers.c
+++ b/drivers/gpu/drm/tests/drm_kunit_helpers.c
@@ -3,6 +3,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_drv.h>
+#include <drm/drm_edid.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_kunit_helpers.h>
 #include <drm/drm_managed.h>
@@ -311,6 +312,47 @@ drm_kunit_helper_create_crtc(struct kunit *test,
 }
 EXPORT_SYMBOL_GPL(drm_kunit_helper_create_crtc);
 
+static void kunit_action_drm_mode_destroy(void *ptr)
+{
+	struct drm_display_mode *mode = ptr;
+
+	drm_mode_destroy(NULL, mode);
+}
+
+/**
+ * drm_kunit_display_mode_from_cea_vic() - return a mode for CEA VIC
+					   for a KUnit test
+ * @test: The test context object
+ * @dev: DRM device
+ * @video_code: CEA VIC of the mode
+ *
+ * Creates a new mode matching the specified CEA VIC for a KUnit test.
+ *
+ * Resources will be cleaned up automatically.
+ *
+ * Returns: A new drm_display_mode on success or NULL on failure
+ */
+struct drm_display_mode *
+drm_kunit_display_mode_from_cea_vic(struct kunit *test, struct drm_device *dev,
+				    u8 video_code)
+{
+	struct drm_display_mode *mode;
+	int ret;
+
+	mode = drm_display_mode_from_cea_vic(dev, video_code);
+	if (!mode)
+		return NULL;
+
+	ret = kunit_add_action_or_reset(test,
+					kunit_action_drm_mode_destroy,
+					mode);
+	if (ret)
+		return NULL;
+
+	return mode;
+}
+EXPORT_SYMBOL_GPL(drm_kunit_display_mode_from_cea_vic);
+
 MODULE_AUTHOR("Maxime Ripard <maxime@cerno.tech>");
 MODULE_DESCRIPTION("KUnit test suite helper functions");
 MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/v3d/v3d_perfmon.c b/drivers/gpu/drm/v3d/v3d_perfmon.c
index cd7f1eedf17f..00cd081d7873 100644
--- a/drivers/gpu/drm/v3d/v3d_perfmon.c
+++ b/drivers/gpu/drm/v3d/v3d_perfmon.c
@@ -306,6 +306,11 @@ void v3d_perfmon_open_file(struct v3d_file_priv *v3d_priv)
 static int v3d_perfmon_idr_del(int id, void *elem, void *data)
 {
 	struct v3d_perfmon *perfmon = elem;
+	struct v3d_dev *v3d = (struct v3d_dev *)data;
+
+	/* If the active perfmon is being destroyed, stop it first */
+	if (perfmon == v3d->active_perfmon)
+		v3d_perfmon_stop(v3d, perfmon, false);
 
 	v3d_perfmon_put(perfmon);
 
@@ -314,8 +319,10 @@ static int v3d_perfmon_idr_del(int id, void *elem, void *data)
 
 void v3d_perfmon_close_file(struct v3d_file_priv *v3d_priv)
 {
+	struct v3d_dev *v3d = v3d_priv->v3d;
+
 	mutex_lock(&v3d_priv->perfmon.lock);
-	idr_for_each(&v3d_priv->perfmon.idr, v3d_perfmon_idr_del, NULL);
+	idr_for_each(&v3d_priv->perfmon.idr, v3d_perfmon_idr_del, v3d);
 	idr_destroy(&v3d_priv->perfmon.idr);
 	mutex_unlock(&v3d_priv->perfmon.lock);
 	mutex_destroy(&v3d_priv->perfmon.lock);
diff --git a/drivers/gpu/drm/vc4/vc4_perfmon.c b/drivers/gpu/drm/vc4/vc4_perfmon.c
index c4ac2c946238..c00a5cc2316d 100644
--- a/drivers/gpu/drm/vc4/vc4_perfmon.c
+++ b/drivers/gpu/drm/vc4/vc4_perfmon.c
@@ -116,6 +116,11 @@ void vc4_perfmon_open_file(struct vc4_file *vc4file)
 static int vc4_perfmon_idr_del(int id, void *elem, void *data)
 {
 	struct vc4_perfmon *perfmon = elem;
+	struct vc4_dev *vc4 = (struct vc4_dev *)data;
+
+	/* If the active perfmon is being destroyed, stop it first */
+	if (perfmon == vc4->active_perfmon)
+		vc4_perfmon_stop(vc4, perfmon, false);
 
 	vc4_perfmon_put(perfmon);
 
@@ -130,7 +135,7 @@ void vc4_perfmon_close_file(struct vc4_file *vc4file)
 		return;
 
 	mutex_lock(&vc4file->perfmon.lock);
-	idr_for_each(&vc4file->perfmon.idr, vc4_perfmon_idr_del, NULL);
+	idr_for_each(&vc4file->perfmon.idr, vc4_perfmon_idr_del, vc4);
 	idr_destroy(&vc4file->perfmon.idr);
 	mutex_unlock(&vc4file->perfmon.lock);
 	mutex_destroy(&vc4file->perfmon.lock);
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/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c
index 75736faf2a80..c6e0c8d77a70 100644
--- a/drivers/gpu/drm/xe/display/xe_display.c
+++ b/drivers/gpu/drm/xe/display/xe_display.c
@@ -309,18 +309,7 @@ static void xe_display_flush_cleanup_work(struct xe_device *xe)
 }
 
 /* TODO: System and runtime suspend/resume sequences will be sanitized as a follow-up. */
-void xe_display_pm_runtime_suspend(struct xe_device *xe)
-{
-	if (!xe->info.probe_display)
-		return;
-
-	if (xe->d3cold.allowed)
-		xe_display_pm_suspend(xe, true);
-
-	intel_hpd_poll_enable(xe);
-}
-
-void xe_display_pm_suspend(struct xe_device *xe, bool runtime)
+static void __xe_display_pm_suspend(struct xe_device *xe, bool runtime)
 {
 	struct intel_display *display = &xe->display;
 	bool s2idle = suspend_to_idle();
@@ -353,28 +342,38 @@ void xe_display_pm_suspend(struct xe_device *xe, bool runtime)
 	intel_opregion_suspend(display, s2idle ? PCI_D1 : PCI_D3cold);
 
 	intel_dmc_suspend(xe);
+
+	if (runtime && has_display(xe))
+		intel_hpd_poll_enable(xe);
 }
 
-void xe_display_pm_suspend_late(struct xe_device *xe)
+void xe_display_pm_suspend(struct xe_device *xe)
+{
+	__xe_display_pm_suspend(xe, false);
+}
+
+void xe_display_pm_runtime_suspend(struct xe_device *xe)
 {
-	bool s2idle = suspend_to_idle();
 	if (!xe->info.probe_display)
 		return;
 
-	intel_power_domains_suspend(xe, s2idle);
+	if (xe->d3cold.allowed) {
+		__xe_display_pm_suspend(xe, true);
+		return;
+	}
 
-	intel_display_power_suspend_late(xe);
+	intel_hpd_poll_enable(xe);
 }
 
-void xe_display_pm_runtime_resume(struct xe_device *xe)
+void xe_display_pm_suspend_late(struct xe_device *xe)
 {
+	bool s2idle = suspend_to_idle();
 	if (!xe->info.probe_display)
 		return;
 
-	intel_hpd_poll_disable(xe);
+	intel_power_domains_suspend(xe, s2idle);
 
-	if (xe->d3cold.allowed)
-		xe_display_pm_resume(xe, true);
+	intel_display_power_suspend_late(xe);
 }
 
 void xe_display_pm_resume_early(struct xe_device *xe)
@@ -387,7 +386,7 @@ void xe_display_pm_resume_early(struct xe_device *xe)
 	intel_power_domains_resume(xe);
 }
 
-void xe_display_pm_resume(struct xe_device *xe, bool runtime)
+static void __xe_display_pm_resume(struct xe_device *xe, bool runtime)
 {
 	struct intel_display *display = &xe->display;
 
@@ -411,9 +410,11 @@ void xe_display_pm_resume(struct xe_device *xe, bool runtime)
 		intel_display_driver_resume(xe);
 		drm_kms_helper_poll_enable(&xe->drm);
 		intel_display_driver_enable_user_access(xe);
-		intel_hpd_poll_disable(xe);
 	}
 
+	if (has_display(xe))
+		intel_hpd_poll_disable(xe);
+
 	intel_opregion_resume(display);
 
 	intel_fbdev_set_suspend(&xe->drm, FBINFO_STATE_RUNNING, false);
@@ -421,6 +422,26 @@ void xe_display_pm_resume(struct xe_device *xe, bool runtime)
 	intel_power_domains_enable(xe);
 }
 
+void xe_display_pm_resume(struct xe_device *xe)
+{
+	__xe_display_pm_resume(xe, false);
+}
+
+void xe_display_pm_runtime_resume(struct xe_device *xe)
+{
+	if (!xe->info.probe_display)
+		return;
+
+	if (xe->d3cold.allowed) {
+		__xe_display_pm_resume(xe, true);
+		return;
+	}
+
+	intel_hpd_init(xe);
+	intel_hpd_poll_disable(xe);
+}
+
+
 static void display_device_remove(struct drm_device *dev, void *arg)
 {
 	struct xe_device *xe = arg;
diff --git a/drivers/gpu/drm/xe/display/xe_display.h b/drivers/gpu/drm/xe/display/xe_display.h
index 53d727fd792b..bed55fd26f30 100644
--- a/drivers/gpu/drm/xe/display/xe_display.h
+++ b/drivers/gpu/drm/xe/display/xe_display.h
@@ -34,10 +34,10 @@ void xe_display_irq_enable(struct xe_device *xe, u32 gu_misc_iir);
 void xe_display_irq_reset(struct xe_device *xe);
 void xe_display_irq_postinstall(struct xe_device *xe, struct xe_gt *gt);
 
-void xe_display_pm_suspend(struct xe_device *xe, bool runtime);
+void xe_display_pm_suspend(struct xe_device *xe);
 void xe_display_pm_suspend_late(struct xe_device *xe);
 void xe_display_pm_resume_early(struct xe_device *xe);
-void xe_display_pm_resume(struct xe_device *xe, bool runtime);
+void xe_display_pm_resume(struct xe_device *xe);
 void xe_display_pm_runtime_suspend(struct xe_device *xe);
 void xe_display_pm_runtime_resume(struct xe_device *xe);
 
@@ -65,10 +65,10 @@ static inline void xe_display_irq_enable(struct xe_device *xe, u32 gu_misc_iir)
 static inline void xe_display_irq_reset(struct xe_device *xe) {}
 static inline void xe_display_irq_postinstall(struct xe_device *xe, struct xe_gt *gt) {}
 
-static inline void xe_display_pm_suspend(struct xe_device *xe, bool runtime) {}
+static inline void xe_display_pm_suspend(struct xe_device *xe) {}
 static inline void xe_display_pm_suspend_late(struct xe_device *xe) {}
 static inline void xe_display_pm_resume_early(struct xe_device *xe) {}
-static inline void xe_display_pm_resume(struct xe_device *xe, bool runtime) {}
+static inline void xe_display_pm_resume(struct xe_device *xe) {}
 static inline void xe_display_pm_runtime_suspend(struct xe_device *xe) {}
 static inline void xe_display_pm_runtime_resume(struct xe_device *xe) {}
 
diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index ac9c437e103d..bd604b9f08e4 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)
@@ -520,7 +517,7 @@
  *   [4-6]     RSVD
  *   [7]       Disabled
  */
-#define CCS_MODE				XE_REG(0x14804)
+#define CCS_MODE				XE_REG(0x14804, XE_REG_OPTION_MASKED)
 #define   CCS_MODE_CSLICE_0_3_MASK		REG_GENMASK(11, 0) /* 3 bits per cslice */
 #define   CCS_MODE_CSLICE_MASK			0x7 /* CCS0-3 + rsvd */
 #define   CCS_MODE_CSLICE_WIDTH			ilog2(CCS_MODE_CSLICE_MASK + 1)
diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
index 668615c6b172..fe4319eb13fd 100644
--- a/drivers/gpu/drm/xe/xe_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_debugfs.c
@@ -187,7 +187,7 @@ void xe_debugfs_register(struct xe_device *xe)
 	debugfs_create_file("forcewake_all", 0400, root, xe,
 			    &forcewake_all_fops);
 
-	debugfs_create_file("wedged_mode", 0400, root, xe,
+	debugfs_create_file("wedged_mode", 0600, root, xe,
 			    &wedged_mode_fops);
 
 	for (mem_type = XE_PL_VRAM0; mem_type <= XE_PL_VRAM1; ++mem_type) {
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 5a63d135ba96..a1987b554a8d 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -87,10 +87,6 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file)
 	mutex_init(&xef->exec_queue.lock);
 	xa_init_flags(&xef->exec_queue.xa, XA_FLAGS_ALLOC1);
 
-	spin_lock(&xe->clients.lock);
-	xe->clients.count++;
-	spin_unlock(&xe->clients.lock);
-
 	file->driver_priv = xef;
 	kref_init(&xef->refcount);
 
@@ -107,17 +103,12 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file)
 static void xe_file_destroy(struct kref *ref)
 {
 	struct xe_file *xef = container_of(ref, struct xe_file, refcount);
-	struct xe_device *xe = xef->xe;
 
 	xa_destroy(&xef->exec_queue.xa);
 	mutex_destroy(&xef->exec_queue.lock);
 	xa_destroy(&xef->vm.xa);
 	mutex_destroy(&xef->vm.lock);
 
-	spin_lock(&xe->clients.lock);
-	xe->clients.count--;
-	spin_unlock(&xe->clients.lock);
-
 	xe_drm_client_put(xef->client);
 	kfree(xef->process_name);
 	kfree(xef);
@@ -333,7 +324,6 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
 	xe->info.force_execlist = xe_modparam.force_execlist;
 
 	spin_lock_init(&xe->irq.lock);
-	spin_lock_init(&xe->clients.lock);
 
 	init_waitqueue_head(&xe->ufence_wq);
 
@@ -890,7 +880,7 @@ void xe_device_l2_flush(struct xe_device *xe)
 	spin_lock(&gt->global_invl_lock);
 	xe_mmio_write32(gt, XE2_GLOBAL_INVAL, 0x1);
 
-	if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 150, NULL, true))
+	if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 500, NULL, true))
 		xe_gt_err_once(gt, "Global invalidation timeout\n");
 	spin_unlock(&gt->global_invl_lock);
 
@@ -980,13 +970,13 @@ 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_device.h b/drivers/gpu/drm/xe/xe_device.h
index 894f04770454..34620ef855c0 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -178,4 +178,18 @@ void xe_device_declare_wedged(struct xe_device *xe);
 struct xe_file *xe_file_get(struct xe_file *xef);
 void xe_file_put(struct xe_file *xef);
 
+/*
+ * Occasionally it is seen that the G2H worker starts running after a delay of more than
+ * a second even after being queued and activated by the Linux workqueue subsystem. This
+ * leads to G2H timeout error. The root cause of issue lies with scheduling latency of
+ * Lunarlake Hybrid CPU. Issue disappears if we disable Lunarlake atom cores from BIOS
+ * and this is beyond xe kmd.
+ *
+ * TODO: Drop this change once workqueue scheduling delay issue is fixed on LNL Hybrid CPU.
+ */
+#define LNL_FLUSH_WORKQUEUE(wq__) \
+	flush_workqueue(wq__)
+#define LNL_FLUSH_WORK(wrk__) \
+	flush_work(wrk__)
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 09d731a9125c..687f3a9039bb 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -353,15 +353,6 @@ struct xe_device {
 		struct workqueue_struct *wq;
 	} sriov;
 
-	/** @clients: drm clients info */
-	struct {
-		/** @clients.lock: Protects drm clients info */
-		spinlock_t lock;
-
-		/** @clients.count: number of drm clients */
-		u64 count;
-	} clients;
-
 	/** @usm: unified memory state */
 	struct {
 		/** @usm.asid: convert a ASID to VM */
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 7b38485817dc..756b492f13b0 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).
@@ -137,12 +132,16 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	if (XE_IOCTL_DBG(xe, !q))
 		return -ENOENT;
 
-	if (XE_IOCTL_DBG(xe, q->flags & EXEC_QUEUE_FLAG_VM))
-		return -EINVAL;
+	if (XE_IOCTL_DBG(xe, q->flags & EXEC_QUEUE_FLAG_VM)) {
+		err = -EINVAL;
+		goto err_exec_queue;
+	}
 
 	if (XE_IOCTL_DBG(xe, args->num_batch_buffer &&
-			 q->width != args->num_batch_buffer))
-		return -EINVAL;
+			 q->width != args->num_batch_buffer)) {
+		err = -EINVAL;
+		goto err_exec_queue;
+	}
 
 	if (XE_IOCTL_DBG(xe, q->ops->reset_status(q))) {
 		err = -ECANCELED;
@@ -225,6 +224,7 @@ retry:
 			fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm);
 			if (IS_ERR(fence)) {
 				err = PTR_ERR(fence);
+				xe_vm_unlock(vm);
 				goto err_unlock_list;
 			}
 			for (i = 0; i < num_syncs; i++)
@@ -304,7 +304,8 @@ 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_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index d098d2dd1b2d..fd0f3b3c9101 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -260,8 +260,14 @@ void xe_exec_queue_fini(struct xe_exec_queue *q)
 {
 	int i;
 
+	/*
+	 * Before releasing our ref to lrc and xef, accumulate our run ticks
+	 */
+	xe_exec_queue_update_run_ticks(q);
+
 	for (i = 0; i < q->width; ++i)
 		xe_lrc_put(q->lrc[i]);
+
 	__xe_exec_queue_free(q);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_force_wake.c b/drivers/gpu/drm/xe/xe_force_wake.c
index b263fff15273..7d9fc489dcb8 100644
--- a/drivers/gpu/drm/xe/xe_force_wake.c
+++ b/drivers/gpu/drm/xe/xe_force_wake.c
@@ -115,9 +115,15 @@ static int __domain_wait(struct xe_gt *gt, struct xe_force_wake_domain *domain,
 			     XE_FORCE_WAKE_ACK_TIMEOUT_MS * USEC_PER_MSEC,
 			     &value, true);
 	if (ret)
-		xe_gt_notice(gt, "Force wake domain %d failed to ack %s (%pe) reg[%#x] = %#x\n",
-			     domain->id, str_wake_sleep(wake), ERR_PTR(ret),
-			     domain->reg_ack.addr, value);
+		xe_gt_err(gt, "Force wake domain %d failed to ack %s (%pe) reg[%#x] = %#x\n",
+			  domain->id, str_wake_sleep(wake), ERR_PTR(ret),
+			  domain->reg_ack.addr, value);
+	if (value == ~0) {
+		xe_gt_err(gt,
+			  "Force wake domain %d: %s. MMIO unreliable (forcewake register returns 0xFFFFFFFF)!\n",
+			  domain->id, str_wake_sleep(wake));
+		ret = -EIO;
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 2895f154654c..ff19eca5d358 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -397,6 +397,16 @@ static void ggtt_invalidate_gt_tlb(struct xe_gt *gt)
 
 static void xe_ggtt_invalidate(struct xe_ggtt *ggtt)
 {
+	struct xe_device *xe = tile_to_xe(ggtt->tile);
+
+	/*
+	 * XXX: Barrier for GGTT pages. Unsure exactly why this required but
+	 * without this LNL is having issues with the GuC reading scratch page
+	 * vs. correct GGTT page. Not particularly a hot code path so blindly
+	 * do a mmio read here which results in GuC reading correct GGTT page.
+	 */
+	xe_mmio_read32(xe_root_mmio_gt(xe), VF_CAP_REG);
+
 	/* Each GT in a tile has its own TLB to cache GGTT lookups */
 	ggtt_invalidate_gt_tlb(ggtt->tile->primary_gt);
 	ggtt_invalidate_gt_tlb(ggtt->tile->media_gt);
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 f0dc2bf24c7b..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);
@@ -874,7 +873,9 @@ int xe_gt_sanitize_freq(struct xe_gt *gt)
 	int ret = 0;
 
 	if ((!xe_uc_fw_is_available(&gt->uc.gsc.fw) ||
-	     xe_uc_fw_is_loaded(&gt->uc.gsc.fw)) && XE_WA(gt, 22019338487))
+	     xe_uc_fw_is_loaded(&gt->uc.gsc.fw) ||
+	     xe_uc_fw_is_in_error_state(&gt->uc.gsc.fw)) &&
+	    XE_WA(gt, 22019338487))
 		ret = xe_guc_pc_restore_stashed_freq(&gt->uc.guc.pc);
 
 	return ret;
diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
index d2e4dc3aaf61..ffcbd05671fc 100644
--- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
+++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
@@ -68,6 +68,12 @@ static void __xe_gt_apply_ccs_mode(struct xe_gt *gt, u32 num_engines)
 		}
 	}
 
+	/*
+	 * Mask bits need to be set for the register. Though only Xe2+
+	 * platforms require setting of mask bits, it won't harm for older
+	 * platforms as these bits are unused there.
+	 */
+	mode |= CCS_MODE_CSLICE_0_3_MASK << 16;
 	xe_mmio_write32(gt, CCS_MODE, mode);
 
 	xe_gt_dbg(gt, "CCS_MODE=%x config:%08x, num_engines:%d, num_slices:%d\n",
@@ -133,9 +139,10 @@ ccs_mode_store(struct device *kdev, struct device_attribute *attr,
 	}
 
 	/* CCS mode can only be updated when there are no drm clients */
-	spin_lock(&xe->clients.lock);
-	if (xe->clients.count) {
-		spin_unlock(&xe->clients.lock);
+	mutex_lock(&xe->drm.filelist_mutex);
+	if (!list_empty(&xe->drm.filelist)) {
+		mutex_unlock(&xe->drm.filelist_mutex);
+		xe_gt_dbg(gt, "Rejecting compute mode change as there are active drm clients\n");
 		return -EBUSY;
 	}
 
@@ -146,7 +153,7 @@ ccs_mode_store(struct device *kdev, struct device_attribute *attr,
 		xe_gt_reset_async(gt);
 	}
 
-	spin_unlock(&xe->clients.lock);
+	mutex_unlock(&xe->drm.filelist_mutex);
 
 	return count;
 }
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index 8250ef71e685..afdb477ecf83 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -387,6 +387,8 @@ static void pf_release_ggtt(struct xe_tile *tile, struct xe_ggtt_node *node)
 		 * the xe_ggtt_clear() called by below xe_ggtt_remove_node().
 		 */
 		xe_ggtt_node_remove(node, false);
+	} else {
+		xe_ggtt_node_fini(node);
 	}
 }
 
@@ -442,7 +444,7 @@ static int pf_provision_vf_ggtt(struct xe_gt *gt, unsigned int vfid, u64 size)
 	config->ggtt_region = node;
 	return 0;
 err:
-	xe_ggtt_node_fini(node);
+	pf_release_ggtt(tile, node);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index cca9cf536f76..9d82ea30f4df 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)
 {
@@ -63,6 +72,8 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
 	struct xe_device *xe = gt_to_xe(gt);
 	struct xe_gt_tlb_invalidation_fence *fence, *next;
 
+	LNL_FLUSH_WORK(&gt->uc.guc.ct.g2h_worker);
+
 	spin_lock_irq(&gt->tlb_invalidation.pending_lock);
 	list_for_each_entry_safe(fence, next,
 				 &gt->tlb_invalidation.pending_fences, link) {
@@ -204,7 +215,7 @@ 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 +278,8 @@ 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 +505,8 @@ 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 +526,3 @@ 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_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index f24dd5223926..9c505d3517cd 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -667,16 +667,12 @@ static int __guc_ct_send_locked(struct xe_guc_ct *ct, const u32 *action,
 		num_g2h = 1;
 
 		if (g2h_fence_needs_alloc(g2h_fence)) {
-			void *ptr;
-
 			g2h_fence->seqno = next_ct_seqno(ct, true);
-			ptr = xa_store(&ct->fence_lookup,
-				       g2h_fence->seqno,
-				       g2h_fence, GFP_ATOMIC);
-			if (IS_ERR(ptr)) {
-				ret = PTR_ERR(ptr);
+			ret = xa_err(xa_store(&ct->fence_lookup,
+					      g2h_fence->seqno, g2h_fence,
+					      GFP_ATOMIC));
+			if (ret)
 				goto out;
-			}
 		}
 
 		seqno = g2h_fence->seqno;
@@ -879,14 +875,11 @@ retry:
 retry_same_fence:
 	ret = guc_ct_send(ct, action, len, 0, 0, &g2h_fence);
 	if (unlikely(ret == -ENOMEM)) {
-		void *ptr;
-
 		/* Retry allocation /w GFP_KERNEL */
-		ptr = xa_store(&ct->fence_lookup,
-			       g2h_fence.seqno,
-			       &g2h_fence, GFP_KERNEL);
-		if (IS_ERR(ptr))
-			return PTR_ERR(ptr);
+		ret = xa_err(xa_store(&ct->fence_lookup, g2h_fence.seqno,
+				      &g2h_fence, GFP_KERNEL));
+		if (ret)
+			return ret;
 
 		goto retry_same_fence;
 	} else if (unlikely(ret)) {
@@ -903,16 +896,35 @@ retry_same_fence:
 	}
 
 	ret = wait_event_timeout(ct->g2h_fence_wq, g2h_fence.done, HZ);
+
 	if (!ret) {
-		xe_gt_err(gt, "Timed out wait for G2H, fence %u, action %04x",
-			  g2h_fence.seqno, action[0]);
+		LNL_FLUSH_WORK(&ct->g2h_worker);
+		if (g2h_fence.done) {
+			xe_gt_warn(gt, "G2H fence %u, action %04x, done\n",
+				   g2h_fence.seqno, action[0]);
+			ret = 1;
+		}
+	}
+
+	/*
+	 * Ensure we serialize with completion side to prevent UAF with fence going out of scope on
+	 * the stack, since we have no clue if it will fire after the timeout before we can erase
+	 * from the xa. Also we have some dependent loads and stores below for which we need the
+	 * correct ordering, and we lack the needed barriers.
+	 */
+	mutex_lock(&ct->lock);
+	if (!ret) {
+		xe_gt_err(gt, "Timed out wait for G2H, fence %u, action %04x, done %s",
+			  g2h_fence.seqno, action[0], str_yes_no(g2h_fence.done));
 		xa_erase_irq(&ct->fence_lookup, g2h_fence.seqno);
+		mutex_unlock(&ct->lock);
 		return -ETIME;
 	}
 
 	if (g2h_fence.retry) {
 		xe_gt_dbg(gt, "H2G action %#x retrying: reason %#x\n",
 			  action[0], g2h_fence.reason);
+		mutex_unlock(&ct->lock);
 		goto retry;
 	}
 	if (g2h_fence.fail) {
@@ -921,7 +933,12 @@ retry_same_fence:
 		ret = -EIO;
 	}
 
-	return ret > 0 ? response_buffer ? g2h_fence.response_len : g2h_fence.response_data : ret;
+	if (ret > 0)
+		ret = response_buffer ? g2h_fence.response_len : g2h_fence.response_data;
+
+	mutex_unlock(&ct->lock);
+
+	return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 80062e1d3f66..4f5d00aea716 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -224,80 +224,11 @@ static bool exec_queue_killed_or_banned_or_wedged(struct xe_exec_queue *q)
 		 EXEC_QUEUE_STATE_BANNED));
 }
 
-#ifdef CONFIG_PROVE_LOCKING
-static int alloc_submit_wq(struct xe_guc *guc)
-{
-	int i;
-
-	for (i = 0; i < NUM_SUBMIT_WQ; ++i) {
-		guc->submission_state.submit_wq_pool[i] =
-			alloc_ordered_workqueue("submit_wq", 0);
-		if (!guc->submission_state.submit_wq_pool[i])
-			goto err_free;
-	}
-
-	return 0;
-
-err_free:
-	while (i)
-		destroy_workqueue(guc->submission_state.submit_wq_pool[--i]);
-
-	return -ENOMEM;
-}
-
-static void free_submit_wq(struct xe_guc *guc)
-{
-	int i;
-
-	for (i = 0; i < NUM_SUBMIT_WQ; ++i)
-		destroy_workqueue(guc->submission_state.submit_wq_pool[i]);
-}
-
-static struct workqueue_struct *get_submit_wq(struct xe_guc *guc)
-{
-	int idx = guc->submission_state.submit_wq_idx++ % NUM_SUBMIT_WQ;
-
-	return guc->submission_state.submit_wq_pool[idx];
-}
-#else
-static int alloc_submit_wq(struct xe_guc *guc)
-{
-	return 0;
-}
-
-static void free_submit_wq(struct xe_guc *guc)
-{
-
-}
-
-static struct workqueue_struct *get_submit_wq(struct xe_guc *guc)
-{
-	return NULL;
-}
-#endif
-
-static void xe_guc_submit_fini(struct xe_guc *guc)
-{
-	struct xe_device *xe = guc_to_xe(guc);
-	struct xe_gt *gt = guc_to_gt(guc);
-	int ret;
-
-	ret = wait_event_timeout(guc->submission_state.fini_wq,
-				 xa_empty(&guc->submission_state.exec_queue_lookup),
-				 HZ * 5);
-
-	drain_workqueue(xe->destroy_wq);
-
-	xe_gt_assert(gt, ret);
-}
-
 static void guc_submit_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc *guc = arg;
 
-	xe_guc_submit_fini(guc);
 	xa_destroy(&guc->submission_state.exec_queue_lookup);
-	free_submit_wq(guc);
 }
 
 static void guc_submit_wedged_fini(void *arg)
@@ -359,10 +290,6 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids)
 	if (err)
 		return err;
 
-	err = alloc_submit_wq(guc);
-	if (err)
-		return err;
-
 	gt->exec_queue_ops = &guc_exec_queue_ops;
 
 	xa_init(&guc->submission_state.exec_queue_lookup);
@@ -393,7 +320,6 @@ static void __release_guc_id(struct xe_guc *guc, struct xe_exec_queue *q, u32 xa
 static int alloc_guc_id(struct xe_guc *guc, struct xe_exec_queue *q)
 {
 	int ret;
-	void *ptr;
 	int i;
 
 	/*
@@ -413,12 +339,10 @@ static int alloc_guc_id(struct xe_guc *guc, struct xe_exec_queue *q)
 	q->guc->id = ret;
 
 	for (i = 0; i < q->width; ++i) {
-		ptr = xa_store(&guc->submission_state.exec_queue_lookup,
-			       q->guc->id + i, q, GFP_NOWAIT);
-		if (IS_ERR(ptr)) {
-			ret = PTR_ERR(ptr);
+		ret = xa_err(xa_store(&guc->submission_state.exec_queue_lookup,
+				      q->guc->id + i, q, GFP_NOWAIT));
+		if (ret)
 			goto err_release;
-		}
 	}
 
 	return 0;
@@ -821,8 +745,6 @@ static void guc_exec_queue_free_job(struct drm_sched_job *drm_job)
 {
 	struct xe_sched_job *job = to_xe_sched_job(drm_job);
 
-	xe_exec_queue_update_run_ticks(job->q);
-
 	trace_xe_sched_job_free(job);
 	xe_sched_job_put(job);
 }
@@ -992,12 +914,22 @@ static void xe_guc_exec_queue_lr_cleanup(struct work_struct *w)
 static bool check_timeout(struct xe_exec_queue *q, struct xe_sched_job *job)
 {
 	struct xe_gt *gt = guc_to_gt(exec_queue_to_guc(q));
-	u32 ctx_timestamp = xe_lrc_ctx_timestamp(q->lrc[0]);
-	u32 ctx_job_timestamp = xe_lrc_ctx_job_timestamp(q->lrc[0]);
+	u32 ctx_timestamp, ctx_job_timestamp;
 	u32 timeout_ms = q->sched_props.job_timeout_ms;
 	u32 diff;
 	u64 running_time_ms;
 
+	if (!xe_sched_job_started(job)) {
+		xe_gt_warn(gt, "Check job timeout: seqno=%u, lrc_seqno=%u, guc_id=%d, not started",
+			   xe_sched_job_seqno(job), xe_sched_job_lrc_seqno(job),
+			   q->guc->id);
+
+		return xe_sched_invalidate_job(job, 2);
+	}
+
+	ctx_timestamp = xe_lrc_ctx_timestamp(q->lrc[0]);
+	ctx_job_timestamp = xe_lrc_ctx_job_timestamp(q->lrc[0]);
+
 	/*
 	 * Counter wraps at ~223s at the usual 19.2MHz, be paranoid catch
 	 * possible overflows with a high timeout.
@@ -1106,10 +1038,13 @@ 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;
 	}
@@ -1122,10 +1057,6 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 		exec_queue_killed_or_banned_or_wedged(q) ||
 		exec_queue_destroyed(q);
 
-	/* Job hasn't started, can't be timed out */
-	if (!skip_timeout_check && !xe_sched_job_started(job))
-		goto rearm;
-
 	/*
 	 * XXX: Sampling timeout doesn't work in wedged mode as we have to
 	 * modify scheduling state to read timestamp. We could read the
@@ -1482,8 +1413,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 	timeout = (q->vm && xe_vm_in_lr_mode(q->vm)) ? MAX_SCHEDULE_TIMEOUT :
 		  msecs_to_jiffies(q->sched_props.job_timeout_ms);
 	err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops,
-			    get_submit_wq(guc),
-			    q->lrc[0]->ring.size / MAX_JOB_SIZE_BYTES, 64,
+			    NULL, q->lrc[0]->ring.size / MAX_JOB_SIZE_BYTES, 64,
 			    timeout, guc_to_gt(guc)->ordered_wq, NULL,
 			    q->name, gt_to_xe(q->gt)->drm.dev);
 	if (err)
@@ -1800,8 +1730,13 @@ void xe_guc_submit_stop(struct xe_guc *guc)
 
 	mutex_lock(&guc->submission_state.lock);
 
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		/* Prevent redundant attempts to stop parallel queues */
+		if (q->guc->id != index)
+			continue;
+
 		guc_exec_queue_stop(guc, q);
+	}
 
 	mutex_unlock(&guc->submission_state.lock);
 
@@ -1839,8 +1774,13 @@ int xe_guc_submit_start(struct xe_guc *guc)
 
 	mutex_lock(&guc->submission_state.lock);
 	atomic_dec(&guc->submission_state.stopped);
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		/* Prevent redundant attempts to start parallel queues */
+		if (q->guc->id != index)
+			continue;
+
 		guc_exec_queue_start(q);
+	}
 	mutex_unlock(&guc->submission_state.lock);
 
 	wake_up_all(&guc->ct.wq);
diff --git a/drivers/gpu/drm/xe/xe_guc_types.h b/drivers/gpu/drm/xe/xe_guc_types.h
index 69046f698271..ed150fc09ad0 100644
--- a/drivers/gpu/drm/xe/xe_guc_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_types.h
@@ -72,13 +72,6 @@ struct xe_guc {
 		atomic_t stopped;
 		/** @submission_state.lock: protects submission state */
 		struct mutex lock;
-#ifdef CONFIG_PROVE_LOCKING
-#define NUM_SUBMIT_WQ	256
-		/** @submission_state.submit_wq_pool: submission ordered workqueues pool */
-		struct workqueue_struct *submit_wq_pool[NUM_SUBMIT_WQ];
-		/** @submission_state.submit_wq_idx: submission ordered workqueue index */
-		int submit_wq_idx;
-#endif
 		/** @submission_state.enabled: submission is enabled */
 		bool enabled;
 		/** @submission_state.fini_wq: submit fini wait queue */
diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index 7cf2160fe040..33eb039053e4 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -123,7 +123,7 @@ int xe_pm_suspend(struct xe_device *xe)
 	for_each_gt(gt, xe, id)
 		xe_gt_suspend_prepare(gt);
 
-	xe_display_pm_suspend(xe, false);
+	xe_display_pm_suspend(xe);
 
 	/* FIXME: Super racey... */
 	err = xe_bo_evict_all(xe);
@@ -133,7 +133,7 @@ int xe_pm_suspend(struct xe_device *xe)
 	for_each_gt(gt, xe, id) {
 		err = xe_gt_suspend(gt);
 		if (err) {
-			xe_display_pm_resume(xe, false);
+			xe_display_pm_resume(xe);
 			goto err;
 		}
 	}
@@ -187,7 +187,7 @@ int xe_pm_resume(struct xe_device *xe)
 	for_each_gt(gt, xe, id)
 		xe_gt_resume(gt);
 
-	xe_display_pm_resume(xe, false);
+	xe_display_pm_resume(xe);
 
 	err = xe_bo_restore_user(xe);
 	if (err)
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..2e72c06fd40d 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -54,11 +54,12 @@ static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr,
 {
 	struct xe_user_fence *ufence;
 	u64 __user *ptr = u64_to_user_ptr(addr);
+	u64 __maybe_unused prefetch_val;
 
-	if (!access_ok(ptr, sizeof(*ptr)))
+	if (get_user(prefetch_val, 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..5b4264ea38bd 100644
--- a/drivers/gpu/drm/xe/xe_wait_user_fence.c
+++ b/drivers/gpu/drm/xe/xe_wait_user_fence.c
@@ -155,6 +155,13 @@ int xe_wait_user_fence_ioctl(struct drm_device *dev, void *data,
 		}
 
 		if (!timeout) {
+			LNL_FLUSH_WORKQUEUE(xe->ordered_wq);
+			err = do_compare(addr, args->value, args->mask,
+					 args->op);
+			if (err <= 0) {
+				drm_dbg(&xe->drm, "LNL_FLUSH_WORKQUEUE resolved ufence timeout\n");
+				break;
+			}
 			err = -ETIME;
 			break;
 		}
@@ -169,9 +176,6 @@ 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);