Merge tag 'v7.0-rc4' into togreg

Linux 7.0-rc4

Required for the ds4422 series which is build upon;
5187e03b817c ("iio: dac: ds4424: reject -128 RAW value")

30 files changed, 287 insertions, 135 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index afe5ca81beec..db7858fe0c3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -641,6 +641,7 @@ static void aca_error_fini(struct aca_error *aerr)
 		aca_bank_error_remove(aerr, bank_error);
 
 out_unlock:
+	mutex_unlock(&aerr->lock);
 	mutex_destroy(&aerr->lock);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 06c1913d5a3f..29b400cdd6d5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1439,7 +1439,10 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
 		*process_info = info;
 	}
 
-	vm->process_info = *process_info;
+	if (cmpxchg(&vm->process_info, NULL, *process_info) != NULL) {
+		ret = -EINVAL;
+		goto already_acquired;
+	}
 
 	/* Validate page directory and attach eviction fence */
 	ret = amdgpu_bo_reserve(vm->root.bo, true);
@@ -1479,6 +1482,7 @@ validate_pd_fail:
 	amdgpu_bo_unreserve(vm->root.bo);
 reserve_pd_fail:
 	vm->process_info = NULL;
+already_acquired:
 	if (info) {
 		dma_fence_put(&info->eviction_fence->base);
 		*process_info = NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d9789e0b5201..d8296dfc5e8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2690,8 +2690,10 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 		break;
 	default:
 		r = amdgpu_discovery_set_ip_blocks(adev);
-		if (r)
+		if (r) {
+			adev->num_ip_blocks = 0;
 			return r;
+		}
 		break;
 	}
 
@@ -3247,6 +3249,8 @@ int amdgpu_device_set_cg_state(struct amdgpu_device *adev,
 		i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		if (!adev->ip_blocks[i].version)
+			continue;
 		/* skip CG for GFX, SDMA on S0ix */
 		if (adev->in_s0ix &&
 		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX ||
@@ -3286,6 +3290,8 @@ int amdgpu_device_set_pg_state(struct amdgpu_device *adev,
 		i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		if (!adev->ip_blocks[i].version)
+			continue;
 		/* skip PG for GFX, SDMA on S0ix */
 		if (adev->in_s0ix &&
 		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX ||
@@ -3493,6 +3499,8 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
 	int i, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].version)
+			continue;
 		if (!adev->ip_blocks[i].version->funcs->early_fini)
 			continue;
 
@@ -3570,6 +3578,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 		if (!adev->ip_blocks[i].status.sw)
 			continue;
 
+		if (!adev->ip_blocks[i].version)
+			continue;
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
 			amdgpu_ucode_free_bo(adev);
 			amdgpu_free_static_csa(&adev->virt.csa_obj);
@@ -3596,6 +3606,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		if (!adev->ip_blocks[i].version)
+			continue;
 		if (adev->ip_blocks[i].version->funcs->late_fini)
 			adev->ip_blocks[i].version->funcs->late_fini(&adev->ip_blocks[i]);
 		adev->ip_blocks[i].status.late_initialized = false;
@@ -7059,6 +7071,15 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	dev_info(adev->dev, "PCI error: slot reset callback!!\n");
 
 	memset(&reset_context, 0, sizeof(reset_context));
+	INIT_LIST_HEAD(&device_list);
+	hive = amdgpu_get_xgmi_hive(adev);
+	if (hive) {
+		mutex_lock(&hive->hive_lock);
+		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head)
+			list_add_tail(&tmp_adev->reset_list, &device_list);
+	} else {
+		list_add_tail(&adev->reset_list, &device_list);
+	}
 
 	if (adev->pcie_reset_ctx.swus)
 		link_dev = adev->pcie_reset_ctx.swus;
@@ -7099,19 +7120,13 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	reset_context.reset_req_dev = adev;
 	set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
 	set_bit(AMDGPU_SKIP_COREDUMP, &reset_context.flags);
-	INIT_LIST_HEAD(&device_list);
 
-	hive = amdgpu_get_xgmi_hive(adev);
 	if (hive) {
-		mutex_lock(&hive->hive_lock);
 		reset_context.hive = hive;
-		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head)
 			tmp_adev->pcie_reset_ctx.in_link_reset = true;
-			list_add_tail(&tmp_adev->reset_list, &device_list);
-		}
 	} else {
 		set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags);
-		list_add_tail(&adev->reset_list, &device_list);
 	}
 
 	r = amdgpu_device_asic_reset(adev, &device_list, &reset_context);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 77e2133de5cf..7f19554b9ad1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -83,7 +83,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
 {
 	struct amdgpu_device *adev = drm_to_adev(dev);
 
-	if (adev == NULL)
+	if (adev == NULL || !adev->num_ip_blocks)
 		return;
 
 	amdgpu_unregister_gpu_instance(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index dc8d2f52c7d6..e244c12ceb23 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -368,15 +368,15 @@ struct amdgpu_mode_info {
 
 	struct drm_property *plane_ctm_property;
 	/**
-	 * @shaper_lut_property: Plane property to set pre-blending shaper LUT
-	 * that converts color content before 3D LUT. If
-	 * plane_shaper_tf_property != Identity TF, AMD color module will
+	 * @plane_shaper_lut_property: Plane property to set pre-blending
+	 * shaper LUT that converts color content before 3D LUT.
+	 * If plane_shaper_tf_property != Identity TF, AMD color module will
 	 * combine the user LUT values with pre-defined TF into the LUT
 	 * parameters to be programmed.
 	 */
 	struct drm_property *plane_shaper_lut_property;
 	/**
-	 * @shaper_lut_size_property: Plane property for the size of
+	 * @plane_shaper_lut_size_property: Plane property for the size of
 	 * pre-blending shaper LUT as supported by the driver (read-only).
 	 */
 	struct drm_property *plane_shaper_lut_size_property;
@@ -400,10 +400,10 @@ struct amdgpu_mode_info {
 	 */
 	struct drm_property *plane_lut3d_property;
 	/**
-	 * @plane_degamma_lut_size_property: Plane property to define the max
-	 * size of 3D LUT as supported by the driver (read-only). The max size
-	 * is the max size of one dimension and, therefore, the max number of
-	 * entries for 3D LUT array is the 3D LUT size cubed;
+	 * @plane_lut3d_size_property: Plane property to define the max size
+	 * of 3D LUT as supported by the driver (read-only). The max size is
+	 * the max size of one dimension and, therefore, the max number of
+	 * entries for 3D LUT array is the 3D LUT size cubed.
 	 */
 	struct drm_property *plane_lut3d_size_property;
 	/**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 6e8aad91bcd3..0d3c18f04ac3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -332,13 +332,13 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 	if (!context || !context->initialized) {
 		dev_err(adev->dev, "TA is not initialized\n");
 		ret = -EINVAL;
-		goto err_free_shared_buf;
+		goto free_shared_buf;
 	}
 
 	if (!psp->ta_funcs || !psp->ta_funcs->fn_ta_invoke) {
 		dev_err(adev->dev, "Unsupported function to invoke TA\n");
 		ret = -EOPNOTSUPP;
-		goto err_free_shared_buf;
+		goto free_shared_buf;
 	}
 
 	context->session_id = ta_id;
@@ -346,7 +346,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 	mutex_lock(&psp->ras_context.mutex);
 	ret = prep_ta_mem_context(&context->mem_context, shared_buf, shared_buf_len);
 	if (ret)
-		goto err_free_shared_buf;
+		goto unlock;
 
 	ret = psp_fn_ta_invoke(psp, cmd_id);
 	if (ret || context->resp_status) {
@@ -354,15 +354,17 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 			ret, context->resp_status);
 		if (!ret) {
 			ret = -EINVAL;
-			goto err_free_shared_buf;
+			goto unlock;
 		}
 	}
 
 	if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len))
 		ret = -EFAULT;
 
-err_free_shared_buf:
+unlock:
 	mutex_unlock(&psp->ras_context.mutex);
+
+free_shared_buf:
 	kfree(shared_buf);
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 9d67b770bcc2..7c450350847d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -446,8 +446,7 @@ static int amdgpu_userq_wait_for_last_fence(struct amdgpu_usermode_queue *queue)
 	return ret;
 }
 
-static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue,
-				 int queue_id)
+static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue)
 {
 	struct amdgpu_userq_mgr *uq_mgr = queue->userq_mgr;
 	struct amdgpu_device *adev = uq_mgr->adev;
@@ -461,7 +460,6 @@ static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue,
 	uq_funcs->mqd_destroy(queue);
 	amdgpu_userq_fence_driver_free(queue);
 	/* Use interrupt-safe locking since IRQ handlers may access these XArrays */
-	xa_erase_irq(&uq_mgr->userq_xa, (unsigned long)queue_id);
 	xa_erase_irq(&adev->userq_doorbell_xa, queue->doorbell_index);
 	queue->userq_mgr = NULL;
 	list_del(&queue->userq_va_list);
@@ -470,12 +468,6 @@ static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue,
 	up_read(&adev->reset_domain->sem);
 }
 
-static struct amdgpu_usermode_queue *
-amdgpu_userq_find(struct amdgpu_userq_mgr *uq_mgr, int qid)
-{
-	return xa_load(&uq_mgr->userq_xa, qid);
-}
-
 void
 amdgpu_userq_ensure_ev_fence(struct amdgpu_userq_mgr *uq_mgr,
 			     struct amdgpu_eviction_fence_mgr *evf_mgr)
@@ -625,22 +617,13 @@ unref_bo:
 }
 
 static int
-amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
+amdgpu_userq_destroy(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_queue *queue)
 {
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
-	struct amdgpu_userq_mgr *uq_mgr = &fpriv->userq_mgr;
 	struct amdgpu_device *adev = uq_mgr->adev;
-	struct amdgpu_usermode_queue *queue;
 	int r = 0;
 
 	cancel_delayed_work_sync(&uq_mgr->resume_work);
 	mutex_lock(&uq_mgr->userq_mutex);
-	queue = amdgpu_userq_find(uq_mgr, queue_id);
-	if (!queue) {
-		drm_dbg_driver(adev_to_drm(uq_mgr->adev), "Invalid queue id to destroy\n");
-		mutex_unlock(&uq_mgr->userq_mutex);
-		return -EINVAL;
-	}
 	amdgpu_userq_wait_for_last_fence(queue);
 	/* Cancel any pending hang detection work and cleanup */
 	if (queue->hang_detect_fence) {
@@ -672,7 +655,7 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
 		drm_warn(adev_to_drm(uq_mgr->adev), "trying to destroy a HW mapping userq\n");
 		queue->state = AMDGPU_USERQ_STATE_HUNG;
 	}
-	amdgpu_userq_cleanup(queue, queue_id);
+	amdgpu_userq_cleanup(queue);
 	mutex_unlock(&uq_mgr->userq_mutex);
 
 	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
@@ -680,6 +663,37 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
 	return r;
 }
 
+static void amdgpu_userq_kref_destroy(struct kref *kref)
+{
+	int r;
+	struct amdgpu_usermode_queue *queue =
+		container_of(kref, struct amdgpu_usermode_queue, refcount);
+	struct amdgpu_userq_mgr *uq_mgr = queue->userq_mgr;
+
+	r = amdgpu_userq_destroy(uq_mgr, queue);
+	if (r)
+		drm_file_err(uq_mgr->file, "Failed to destroy usermode queue %d\n", r);
+}
+
+struct amdgpu_usermode_queue *amdgpu_userq_get(struct amdgpu_userq_mgr *uq_mgr, u32 qid)
+{
+	struct amdgpu_usermode_queue *queue;
+
+	xa_lock(&uq_mgr->userq_xa);
+	queue = xa_load(&uq_mgr->userq_xa, qid);
+	if (queue)
+		kref_get(&queue->refcount);
+	xa_unlock(&uq_mgr->userq_xa);
+
+	return queue;
+}
+
+void amdgpu_userq_put(struct amdgpu_usermode_queue *queue)
+{
+	if (queue)
+		kref_put(&queue->refcount, amdgpu_userq_kref_destroy);
+}
+
 static int amdgpu_userq_priority_permit(struct drm_file *filp,
 					int priority)
 {
@@ -834,6 +848,9 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 		goto unlock;
 	}
 
+	/* drop this refcount during queue destroy */
+	kref_init(&queue->refcount);
+
 	/* Wait for mode-1 reset to complete */
 	down_read(&adev->reset_domain->sem);
 	r = xa_err(xa_store_irq(&adev->userq_doorbell_xa, index, queue, GFP_KERNEL));
@@ -985,7 +1002,9 @@ int amdgpu_userq_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *filp)
 {
 	union drm_amdgpu_userq *args = data;
-	int r;
+	struct amdgpu_fpriv *fpriv = filp->driver_priv;
+	struct amdgpu_usermode_queue *queue;
+	int r = 0;
 
 	if (!amdgpu_userq_enabled(dev))
 		return -ENOTSUPP;
@@ -1000,11 +1019,16 @@ int amdgpu_userq_ioctl(struct drm_device *dev, void *data,
 			drm_file_err(filp, "Failed to create usermode queue\n");
 		break;
 
-	case AMDGPU_USERQ_OP_FREE:
-		r = amdgpu_userq_destroy(filp, args->in.queue_id);
-		if (r)
-			drm_file_err(filp, "Failed to destroy usermode queue\n");
+	case AMDGPU_USERQ_OP_FREE: {
+		xa_lock(&fpriv->userq_mgr.userq_xa);
+		queue = __xa_erase(&fpriv->userq_mgr.userq_xa, args->in.queue_id);
+		xa_unlock(&fpriv->userq_mgr.userq_xa);
+		if (!queue)
+			return -ENOENT;
+
+		amdgpu_userq_put(queue);
 		break;
+	}
 
 	default:
 		drm_dbg_driver(dev, "Invalid user queue op specified: %d\n", args->in.op);
@@ -1023,16 +1047,23 @@ amdgpu_userq_restore_all(struct amdgpu_userq_mgr *uq_mgr)
 
 	/* Resume all the queues for this process */
 	xa_for_each(&uq_mgr->userq_xa, queue_id, queue) {
+		queue = amdgpu_userq_get(uq_mgr, queue_id);
+		if (!queue)
+			continue;
+
 		if (!amdgpu_userq_buffer_vas_mapped(queue)) {
 			drm_file_err(uq_mgr->file,
 				     "trying restore queue without va mapping\n");
 			queue->state = AMDGPU_USERQ_STATE_INVALID_VA;
+			amdgpu_userq_put(queue);
 			continue;
 		}
 
 		r = amdgpu_userq_restore_helper(queue);
 		if (r)
 			ret = r;
+
+		amdgpu_userq_put(queue);
 	}
 
 	if (ret)
@@ -1266,9 +1297,13 @@ amdgpu_userq_evict_all(struct amdgpu_userq_mgr *uq_mgr)
 	amdgpu_userq_detect_and_reset_queues(uq_mgr);
 	/* Try to unmap all the queues in this process ctx */
 	xa_for_each(&uq_mgr->userq_xa, queue_id, queue) {
+		queue = amdgpu_userq_get(uq_mgr, queue_id);
+		if (!queue)
+			continue;
 		r = amdgpu_userq_preempt_helper(queue);
 		if (r)
 			ret = r;
+		amdgpu_userq_put(queue);
 	}
 
 	if (ret)
@@ -1301,16 +1336,24 @@ amdgpu_userq_wait_for_signal(struct amdgpu_userq_mgr *uq_mgr)
 	int ret;
 
 	xa_for_each(&uq_mgr->userq_xa, queue_id, queue) {
+		queue = amdgpu_userq_get(uq_mgr, queue_id);
+		if (!queue)
+			continue;
+
 		struct dma_fence *f = queue->last_fence;
 
-		if (!f || dma_fence_is_signaled(f))
+		if (!f || dma_fence_is_signaled(f)) {
+			amdgpu_userq_put(queue);
 			continue;
+		}
 		ret = dma_fence_wait_timeout(f, true, msecs_to_jiffies(100));
 		if (ret <= 0) {
 			drm_file_err(uq_mgr->file, "Timed out waiting for fence=%llu:%llu\n",
 				     f->context, f->seqno);
+			amdgpu_userq_put(queue);
 			return -ETIMEDOUT;
 		}
+		amdgpu_userq_put(queue);
 	}
 
 	return 0;
@@ -1361,20 +1404,23 @@ int amdgpu_userq_mgr_init(struct amdgpu_userq_mgr *userq_mgr, struct drm_file *f
 void amdgpu_userq_mgr_fini(struct amdgpu_userq_mgr *userq_mgr)
 {
 	struct amdgpu_usermode_queue *queue;
-	unsigned long queue_id;
+	unsigned long queue_id = 0;
+
+	for (;;) {
+		xa_lock(&userq_mgr->userq_xa);
+		queue = xa_find(&userq_mgr->userq_xa, &queue_id, ULONG_MAX,
+				XA_PRESENT);
+		if (queue)
+			__xa_erase(&userq_mgr->userq_xa, queue_id);
+		xa_unlock(&userq_mgr->userq_xa);
 
-	cancel_delayed_work_sync(&userq_mgr->resume_work);
+		if (!queue)
+			break;
 
-	mutex_lock(&userq_mgr->userq_mutex);
-	amdgpu_userq_detect_and_reset_queues(userq_mgr);
-	xa_for_each(&userq_mgr->userq_xa, queue_id, queue) {
-		amdgpu_userq_wait_for_last_fence(queue);
-		amdgpu_userq_unmap_helper(queue);
-		amdgpu_userq_cleanup(queue, queue_id);
+		amdgpu_userq_put(queue);
 	}
 
 	xa_destroy(&userq_mgr->userq_xa);
-	mutex_unlock(&userq_mgr->userq_mutex);
 	mutex_destroy(&userq_mgr->userq_mutex);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
index 5845d8959034..736c1d38297c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
@@ -74,6 +74,7 @@ struct amdgpu_usermode_queue {
 	struct dentry		*debugfs_queue;
 	struct delayed_work hang_detect_work;
 	struct dma_fence *hang_detect_fence;
+	struct kref		refcount;
 
 	struct list_head	userq_va_list;
 };
@@ -112,6 +113,9 @@ struct amdgpu_db_info {
 	struct amdgpu_userq_obj	*db_obj;
 };
 
+struct amdgpu_usermode_queue *amdgpu_userq_get(struct amdgpu_userq_mgr *uq_mgr, u32 qid);
+void amdgpu_userq_put(struct amdgpu_usermode_queue *queue);
+
 int amdgpu_userq_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
 
 int amdgpu_userq_mgr_init(struct amdgpu_userq_mgr *userq_mgr, struct drm_file *file_priv,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index 8013260e29dc..5239b06b9ab0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -35,6 +35,8 @@
 static const struct dma_fence_ops amdgpu_userq_fence_ops;
 static struct kmem_cache *amdgpu_userq_fence_slab;
 
+#define AMDGPU_USERQ_MAX_HANDLES	(1U << 16)
+
 int amdgpu_userq_fence_slab_init(void)
 {
 	amdgpu_userq_fence_slab = kmem_cache_create("amdgpu_userq_fence",
@@ -464,7 +466,7 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 	struct drm_amdgpu_userq_signal *args = data;
 	struct drm_gem_object **gobj_write = NULL;
 	struct drm_gem_object **gobj_read = NULL;
-	struct amdgpu_usermode_queue *queue;
+	struct amdgpu_usermode_queue *queue = NULL;
 	struct amdgpu_userq_fence *userq_fence;
 	struct drm_syncobj **syncobj = NULL;
 	u32 *bo_handles_write, num_write_bo_handles;
@@ -478,6 +480,11 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 	if (!amdgpu_userq_enabled(dev))
 		return -ENOTSUPP;
 
+	if (args->num_syncobj_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    args->num_bo_write_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    args->num_bo_read_handles > AMDGPU_USERQ_MAX_HANDLES)
+		return -EINVAL;
+
 	num_syncobj_handles = args->num_syncobj_handles;
 	syncobj_handles = memdup_user(u64_to_user_ptr(args->syncobj_handles),
 				      size_mul(sizeof(u32), num_syncobj_handles));
@@ -546,7 +553,7 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 	}
 
 	/* Retrieve the user queue */
-	queue = xa_load(&userq_mgr->userq_xa, args->queue_id);
+	queue = amdgpu_userq_get(userq_mgr, args->queue_id);
 	if (!queue) {
 		r = -ENOENT;
 		goto put_gobj_write;
@@ -641,6 +648,9 @@ free_syncobj:
 free_syncobj_handles:
 	kfree(syncobj_handles);
 
+	if (queue)
+		amdgpu_userq_put(queue);
+
 	return r;
 }
 
@@ -653,7 +663,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 	struct drm_amdgpu_userq_wait *wait_info = data;
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	struct amdgpu_userq_mgr *userq_mgr = &fpriv->userq_mgr;
-	struct amdgpu_usermode_queue *waitq;
+	struct amdgpu_usermode_queue *waitq = NULL;
 	struct drm_gem_object **gobj_write;
 	struct drm_gem_object **gobj_read;
 	struct dma_fence **fences = NULL;
@@ -664,6 +674,11 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 	if (!amdgpu_userq_enabled(dev))
 		return -ENOTSUPP;
 
+	if (wait_info->num_syncobj_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    wait_info->num_bo_write_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    wait_info->num_bo_read_handles > AMDGPU_USERQ_MAX_HANDLES)
+		return -EINVAL;
+
 	num_read_bo_handles = wait_info->num_bo_read_handles;
 	bo_handles_read = memdup_user(u64_to_user_ptr(wait_info->bo_read_handles),
 				      size_mul(sizeof(u32), num_read_bo_handles));
@@ -833,7 +848,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 
 			dma_resv_for_each_fence(&resv_cursor, gobj_read[i]->resv,
 						DMA_RESV_USAGE_READ, fence) {
-				if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+				if (num_fences >= wait_info->num_fences) {
 					r = -EINVAL;
 					goto free_fences;
 				}
@@ -850,7 +865,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 
 			dma_resv_for_each_fence(&resv_cursor, gobj_write[i]->resv,
 						DMA_RESV_USAGE_WRITE, fence) {
-				if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+				if (num_fences >= wait_info->num_fences) {
 					r = -EINVAL;
 					goto free_fences;
 				}
@@ -874,8 +889,9 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 					goto free_fences;
 
 				dma_fence_unwrap_for_each(f, &iter, fence) {
-					if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+					if (num_fences >= wait_info->num_fences) {
 						r = -EINVAL;
+						dma_fence_put(fence);
 						goto free_fences;
 					}
 
@@ -898,8 +914,9 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 			if (r)
 				goto free_fences;
 
-			if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+			if (num_fences >= wait_info->num_fences) {
 				r = -EINVAL;
+				dma_fence_put(fence);
 				goto free_fences;
 			}
 
@@ -912,7 +929,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 		 */
 		num_fences = dma_fence_dedup_array(fences, num_fences);
 
-		waitq = xa_load(&userq_mgr->userq_xa, wait_info->waitq_id);
+		waitq = amdgpu_userq_get(userq_mgr, wait_info->waitq_id);
 		if (!waitq) {
 			r = -EINVAL;
 			goto free_fences;
@@ -969,32 +986,14 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 			r = -EFAULT;
 			goto free_fences;
 		}
-
-		kfree(fences);
-		kfree(fence_info);
 	}
 
-	drm_exec_fini(&exec);
-	for (i = 0; i < num_read_bo_handles; i++)
-		drm_gem_object_put(gobj_read[i]);
-	kfree(gobj_read);
-
-	for (i = 0; i < num_write_bo_handles; i++)
-		drm_gem_object_put(gobj_write[i]);
-	kfree(gobj_write);
-
-	kfree(timeline_points);
-	kfree(timeline_handles);
-	kfree(syncobj_handles);
-	kfree(bo_handles_write);
-	kfree(bo_handles_read);
-
-	return 0;
-
 free_fences:
-	while (num_fences-- > 0)
-		dma_fence_put(fences[num_fences]);
-	kfree(fences);
+	if (fences) {
+		while (num_fences-- > 0)
+			dma_fence_put(fences[num_fences]);
+		kfree(fences);
+	}
 free_fence_info:
 	kfree(fence_info);
 exec_fini:
@@ -1018,5 +1017,8 @@ free_bo_handles_write:
 free_bo_handles_read:
 	kfree(bo_handles_read);
 
+	if (waitq)
+		amdgpu_userq_put(waitq);
+
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 09ebb13ca5e8..a926a330700e 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -720,11 +720,6 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes)
 	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
 	mes_set_hw_res_pkt.oversubscription_timer = 50;
-	if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x7f)
-		mes_set_hw_res_pkt.enable_lr_compute_wa = 1;
-	else
-		dev_info_once(mes->adev->dev,
-			      "MES FW version must be >= 0x7f to enable LR compute workaround.\n");
 
 	if (amdgpu_mes_log_enable) {
 		mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index b1c864dc79a8..023c7345ea54 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -731,6 +731,9 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 	int i;
 	struct amdgpu_device *adev = mes->adev;
 	union MESAPI_SET_HW_RESOURCES mes_set_hw_res_pkt;
+	uint32_t mes_rev = (pipe == AMDGPU_MES_SCHED_PIPE) ?
+		(mes->sched_version & AMDGPU_MES_VERSION_MASK) :
+		(mes->kiq_version & AMDGPU_MES_VERSION_MASK);
 
 	memset(&mes_set_hw_res_pkt, 0, sizeof(mes_set_hw_res_pkt));
 
@@ -779,18 +782,13 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 	mes_set_hw_res_pkt.use_different_vmid_compute = 1;
 	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
-	if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x82)
-		mes_set_hw_res_pkt.enable_lr_compute_wa = 1;
-	else
-		dev_info_once(adev->dev,
-			      "MES FW version must be >= 0x82 to enable LR compute workaround.\n");
 
 	/*
 	 * Keep oversubscribe timer for sdma . When we have unmapped doorbell
 	 * handling support, other queue will not use the oversubscribe timer.
 	 * handling  mode - 0: disabled; 1: basic version; 2: basic+ version
 	 */
-	mes_set_hw_res_pkt.oversubscription_timer = 50;
+	mes_set_hw_res_pkt.oversubscription_timer = mes_rev < 0x8b ? 0 : 50;
 	mes_set_hw_res_pkt.unmapped_doorbell_handling = 1;
 
 	if (amdgpu_mes_log_enable) {
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c
index 723ddae17644..73a709773e85 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c
@@ -69,12 +69,12 @@ static int psp_v15_0_0_ring_stop(struct psp_context *psp,
 				   0x80000000, 0x80000000, false);
 	} else {
 		/* Write the ring destroy command*/
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_64,
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64,
 			     GFX_CTRL_CMD_ID_DESTROY_RINGS);
 		/* there might be handshake issue with hardware which needs delay */
 		mdelay(20);
 		/* Wait for response flag (bit 31) */
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_64),
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64),
 				   0x80000000, 0x80000000, false);
 	}
 
@@ -116,7 +116,7 @@ static int psp_v15_0_0_ring_create(struct psp_context *psp,
 
 	} else {
 		/* Wait for sOS ready for ring creation */
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_64),
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64),
 				   0x80000000, 0x80000000, false);
 		if (ret) {
 			DRM_ERROR("Failed to wait for trust OS ready for ring creation\n");
@@ -125,23 +125,23 @@ static int psp_v15_0_0_ring_create(struct psp_context *psp,
 
 		/* Write low address of the ring to C2PMSG_69 */
 		psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr);
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_69, psp_ring_reg);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_69, psp_ring_reg);
 		/* Write high address of the ring to C2PMSG_70 */
 		psp_ring_reg = upper_32_bits(ring->ring_mem_mc_addr);
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_70, psp_ring_reg);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_70, psp_ring_reg);
 		/* Write size of ring to C2PMSG_71 */
 		psp_ring_reg = ring->ring_size;
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_71, psp_ring_reg);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_71, psp_ring_reg);
 		/* Write the ring initialization command to C2PMSG_64 */
 		psp_ring_reg = ring_type;
 		psp_ring_reg = psp_ring_reg << 16;
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_64, psp_ring_reg);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64, psp_ring_reg);
 
 		/* there might be handshake issue with hardware which needs delay */
 		mdelay(20);
 
 		/* Wait for response flag (bit 31) in C2PMSG_64 */
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_64),
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64),
 				   0x80000000, 0x8000FFFF, false);
 	}
 
@@ -174,7 +174,7 @@ static uint32_t psp_v15_0_0_ring_get_wptr(struct psp_context *psp)
 	if (amdgpu_sriov_vf(adev))
 		data = RREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_102);
 	else
-		data = RREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_67);
+		data = RREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_67);
 
 	return data;
 }
@@ -188,7 +188,7 @@ static void psp_v15_0_0_ring_set_wptr(struct psp_context *psp, uint32_t value)
 		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_101,
 			     GFX_CTRL_CMD_ID_CONSUME_CMD);
 	} else
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_67, value);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_67, value);
 }
 
 static const struct psp_funcs psp_v15_0_0_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 8122a5cacf07..a0ad1f8a76f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -858,7 +858,9 @@ static int soc21_common_early_init(struct amdgpu_ip_block *ip_block)
 			AMD_CG_SUPPORT_IH_CG |
 			AMD_CG_SUPPORT_BIF_MGCG |
 			AMD_CG_SUPPORT_BIF_LS;
-		adev->pg_flags = AMD_PG_SUPPORT_VCN |
+		adev->pg_flags = AMD_PG_SUPPORT_VCN_DPG |
+			AMD_PG_SUPPORT_VCN |
+			AMD_PG_SUPPORT_JPEG_DPG |
 			AMD_PG_SUPPORT_JPEG |
 			AMD_PG_SUPPORT_GFX_PG;
 		adev->external_rev_id = adev->rev_id + 0x1;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index 0202df5db1e1..6109124f852e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -174,6 +174,10 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 		fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
 		fw_shared->sq.is_enabled = 1;
 
+		fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_SMU_DPM_INTERFACE_FLAG);
+		fw_shared->smu_dpm_interface.smu_interface_type = (adev->flags & AMD_IS_APU) ?
+			AMDGPU_VCN_SMU_DPM_INTERFACE_APU : AMDGPU_VCN_SMU_DPM_INTERFACE_DGPU;
+
 		if (amdgpu_vcnfw_log)
 			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 8ea31699d38b..f5d2847e1cbb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -593,6 +593,7 @@ int pqm_update_queue_properties(struct process_queue_manager *pqm,
 					 p->queue_size)) {
 			pr_debug("ring buf 0x%llx size 0x%llx not mapped on GPU\n",
 				 p->queue_address, p->queue_size);
+			amdgpu_bo_unreserve(vm->root.bo);
 			return -EFAULT;
 		}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index 2ba98f384685..cd1e58b8defc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -1706,6 +1706,7 @@ __set_dm_plane_colorop_3dlut(struct drm_plane_state *plane_state,
 	struct dc_transfer_func *tf = &dc_plane_state->in_shaper_func;
 	struct drm_atomic_state *state = plane_state->state;
 	const struct amdgpu_device *adev = drm_to_adev(colorop->dev);
+	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend;
 	const struct drm_device *dev = colorop->dev;
 	const struct drm_color_lut32 *lut3d;
 	uint32_t lut3d_size;
@@ -1722,7 +1723,7 @@ __set_dm_plane_colorop_3dlut(struct drm_plane_state *plane_state,
 	}
 
 	if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_3D_LUT) {
-		if (!adev->dm.dc->caps.color.dpp.hw_3d_lut) {
+		if (!has_3dlut) {
 			drm_dbg(dev, "3D LUT is not supported by hardware\n");
 			return -EINVAL;
 		}
@@ -1875,6 +1876,7 @@ amdgpu_dm_plane_set_colorop_properties(struct drm_plane_state *plane_state,
 	struct drm_colorop *colorop = plane_state->color_pipeline;
 	struct drm_device *dev = plane_state->plane->dev;
 	struct amdgpu_device *adev = drm_to_adev(dev);
+	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend;
 	int ret;
 
 	/* 1D Curve - DEGAM TF */
@@ -1907,7 +1909,7 @@ amdgpu_dm_plane_set_colorop_properties(struct drm_plane_state *plane_state,
 	if (ret)
 		return ret;
 
-	if (adev->dm.dc->caps.color.dpp.hw_3d_lut) {
+	if (has_3dlut) {
 		/* 1D Curve & LUT - SHAPER TF & LUT */
 		colorop = colorop->next;
 		if (!colorop) {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
index f25c0ede7199..d59ba82d3d7c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
@@ -60,6 +60,7 @@ int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_pr
 	struct drm_colorop *ops[MAX_COLOR_PIPELINE_OPS];
 	struct drm_device *dev = plane->dev;
 	struct amdgpu_device *adev = drm_to_adev(dev);
+	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend;
 	int ret;
 	int i = 0;
 
@@ -112,7 +113,7 @@ int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_pr
 
 	i++;
 
-	if (adev->dm.dc->caps.color.dpp.hw_3d_lut) {
+	if (has_3dlut) {
 		/* 1D curve - SHAPER TF */
 		ops[i] = kzalloc_obj(*ops[0]);
 		if (!ops[i]) {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 130190e8a1b2..304437c2284d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -765,15 +765,15 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
 	dm->adev->mode_info.crtcs[crtc_index] = acrtc;
 
 	/* Don't enable DRM CRTC degamma property for
-	 * 1. Degamma is replaced by color pipeline.
-	 * 2. DCE since it doesn't support programmable degamma anywhere.
-	 * 3. DCN401 since pre-blending degamma LUT doesn't apply to cursor.
+	 * 1. DCE since it doesn't support programmable degamma anywhere.
+	 * 2. DCN401 since pre-blending degamma LUT doesn't apply to cursor.
+	 * Note: DEGAMMA properties are created even if the primary plane has the
+	 * COLOR_PIPELINE property. User space can use either the DEGAMMA properties
+	 * or the COLOR_PIPELINE property. An atomic commit which attempts to enable
+	 * both is rejected.
 	 */
-	if (plane->color_pipeline_property)
-		has_degamma = false;
-	else
-		has_degamma = dm->adev->dm.dc->caps.color.dpp.dcn_arch &&
-			      dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01;
+	has_degamma = dm->adev->dm.dc->caps.color.dpp.dcn_arch &&
+		      dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01;
 
 	drm_crtc_enable_color_mgmt(&acrtc->base, has_degamma ? MAX_COLOR_LUT_ENTRIES : 0,
 				   true, MAX_COLOR_LUT_ENTRIES);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index 70587e5a8d46..127207e18dcb 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -1256,6 +1256,14 @@ static int amdgpu_dm_plane_atomic_check(struct drm_plane *plane,
 	if (ret)
 		return ret;
 
+	/* Reject commits that attempt to use both COLOR_PIPELINE and CRTC DEGAMMA_LUT */
+	if (new_plane_state->color_pipeline && new_crtc_state->degamma_lut) {
+		drm_dbg_atomic(plane->dev,
+			       "[PLANE:%d:%s] COLOR_PIPELINE and CRTC DEGAMMA_LUT cannot be enabled simultaneously\n",
+			       plane->base.id, plane->name);
+		return -EINVAL;
+	}
+
 	ret = amdgpu_dm_plane_fill_dc_scaling_info(adev, new_plane_state, &scaling_info);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 246893d80f1f..baf820e6eae8 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -170,11 +170,11 @@ struct dc_stream_state *dc_create_stream_for_sink(
 	if (sink == NULL)
 		goto fail;
 
-	stream = kzalloc_obj(struct dc_stream_state);
+	stream = kzalloc_obj(struct dc_stream_state, GFP_ATOMIC);
 	if (stream == NULL)
 		goto fail;
 
-	stream->update_scratch = kzalloc((int32_t) dc_update_scratch_space_size(), GFP_KERNEL);
+	stream->update_scratch = kzalloc((int32_t) dc_update_scratch_space_size(), GFP_ATOMIC);
 	if (stream->update_scratch == NULL)
 		goto fail;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h
index 3711d400773a..4c4e61bc91b5 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h
@@ -38,7 +38,11 @@
 	DCCG_SRII(PIXEL_RATE_CNTL, OTG, 0),\
 	DCCG_SRII(PIXEL_RATE_CNTL, OTG, 1),\
 	SR(DISPCLK_FREQ_CHANGE_CNTL),\
-	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL)
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV),\
+	SR(MILLISECOND_TIME_BASE_DIV),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
+	SR(DCCG_GATE_DISABLE_CNTL2)
 
 #define DCCG_REG_LIST_DCN2() \
 	DCCG_COMMON_REG_LIST_DCN_BASE(),\
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c
index 75c69348027e..c4d4eea140f3 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c
@@ -96,6 +96,25 @@ static void dccg21_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppcl
 	dccg->pipe_dppclk_khz[dpp_inst] = req_dppclk;
 }
 
+/*
+ * On DCN21 S0i3 resume, BIOS programs MICROSECOND_TIME_BASE_DIV to
+ * 0x00120464 as a marker that golden init has already been done.
+ * dcn21_s0i3_golden_init_wa() reads this marker later in bios_golden_init()
+ * to decide whether to skip golden init.
+ *
+ * dccg2_init() unconditionally overwrites MICROSECOND_TIME_BASE_DIV to
+ * 0x00120264, destroying the marker before it can be read.
+ *
+ * Guard the call: if the S0i3 marker is present, skip dccg2_init() so the
+ * WA can function correctly. bios_golden_init() will handle init in that case.
+ */
+static void dccg21_init(struct dccg *dccg)
+{
+	if (dccg2_is_s0i3_golden_init_wa_done(dccg))
+		return;
+
+	dccg2_init(dccg);
+}
 
 static const struct dccg_funcs dccg21_funcs = {
 	.update_dpp_dto = dccg21_update_dpp_dto,
@@ -103,7 +122,7 @@ static const struct dccg_funcs dccg21_funcs = {
 	.set_fifo_errdet_ovr_en = dccg2_set_fifo_errdet_ovr_en,
 	.otg_add_pixel = dccg2_otg_add_pixel,
 	.otg_drop_pixel = dccg2_otg_drop_pixel,
-	.dccg_init = dccg2_init,
+	.dccg_init = dccg21_init,
 	.refclk_setup = dccg2_refclk_setup, /* Deprecated - for backward compatibility only */
 	.allow_clock_gating = dccg2_allow_clock_gating,
 	.enable_memory_low_power = dccg2_enable_memory_low_power,
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h
index 067e49cb238e..e2381ca0be0b 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h
@@ -34,7 +34,13 @@
 	DCCG_SRII(DTO_PARAM, DPPCLK, 1),\
 	DCCG_SRII(DTO_PARAM, DPPCLK, 2),\
 	DCCG_SRII(DTO_PARAM, DPPCLK, 3),\
-	SR(REFCLK_CNTL)
+	SR(REFCLK_CNTL),\
+	SR(DISPCLK_FREQ_CHANGE_CNTL),\
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV),\
+	SR(MILLISECOND_TIME_BASE_DIV),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
+	SR(DCCG_GATE_DISABLE_CNTL2)
 
 #define DCCG_MASK_SH_LIST_DCN301(mask_sh) \
 	DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 0, mask_sh),\
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h
index bf659920d4cc..b5e3849ef12a 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h
@@ -64,9 +64,12 @@
 	SR(DSCCLK1_DTO_PARAM),\
 	SR(DSCCLK2_DTO_PARAM),\
 	SR(DSCCLK_DTO_CTRL),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
 	SR(DCCG_GATE_DISABLE_CNTL2),\
 	SR(DCCG_GATE_DISABLE_CNTL3),\
-	SR(HDMISTREAMCLK0_DTO_PARAM)
+	SR(HDMISTREAMCLK0_DTO_PARAM),\
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV)
 
 
 #define DCCG_MASK_SH_LIST_DCN31(mask_sh) \
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h
index a609635f35db..ecbdc05f7c45 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h
@@ -70,11 +70,14 @@
 	SR(DSCCLK2_DTO_PARAM),\
 	SR(DSCCLK3_DTO_PARAM),\
 	SR(DSCCLK_DTO_CTRL),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
 	SR(DCCG_GATE_DISABLE_CNTL2),\
 	SR(DCCG_GATE_DISABLE_CNTL3),\
 	SR(HDMISTREAMCLK0_DTO_PARAM),\
 	SR(OTG_PIXEL_RATE_DIV),\
-	SR(DTBCLK_P_CNTL)
+	SR(DTBCLK_P_CNTL),\
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV)
 
 #define DCCG_MASK_SH_LIST_DCN314_COMMON(mask_sh) \
 	DCCG_SFI(DPPCLK_DTO_CTRL, DTO_DB_EN, DPPCLK, 0, mask_sh),\
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
index b91517b9fedc..eb198d52a115 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
@@ -72,7 +72,11 @@ void dcn401_initialize_min_clocks(struct dc *dc)
 		 * audio corruption. Read current DISPCLK from DENTIST and request the same
 		 * freq to ensure that the timing is valid and unchanged.
 		 */
-		clocks->dispclk_khz = dc->clk_mgr->funcs->get_dispclk_from_dentist(dc->clk_mgr);
+		if (dc->clk_mgr->funcs->get_dispclk_from_dentist) {
+			clocks->dispclk_khz = dc->clk_mgr->funcs->get_dispclk_from_dentist(dc->clk_mgr);
+		} else {
+			clocks->dispclk_khz = dc->clk_mgr->boot_snapshot.dispclk * 1000;
+		}
 	}
 	clocks->ref_dtbclk_khz = dc->clk_mgr->bw_params->clk_table.entries[0].dtbclk_mhz * 1000;
 	clocks->fclk_p_state_change_support = true;
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h
index 0e4c195297a4..fe97943b9b97 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h
@@ -82,6 +82,24 @@
 #define regMPASP_SMN_IH_SW_INT_CTRL                                                                     0x0142
 #define regMPASP_SMN_IH_SW_INT_CTRL_BASE_IDX                                                            0
 
+// addressBlock: mp_SmuMpASPPub_PcruDec
+// base address: 0x3800000
+#define regMPASP_PCRU1_MPASP_C2PMSG_64                                                   0x4280
+#define regMPASP_PCRU1_MPASP_C2PMSG_64_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_65                                                   0x4281
+#define regMPASP_PCRU1_MPASP_C2PMSG_65_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_66                                                   0x4282
+#define regMPASP_PCRU1_MPASP_C2PMSG_66_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_67                                                   0x4283
+#define regMPASP_PCRU1_MPASP_C2PMSG_67_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_68                                                   0x4284
+#define regMPASP_PCRU1_MPASP_C2PMSG_68_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_69                                                   0x4285
+#define regMPASP_PCRU1_MPASP_C2PMSG_69_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_70                                                   0x4286
+#define regMPASP_PCRU1_MPASP_C2PMSG_70_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_71                                                   0x4287
+#define regMPASP_PCRU1_MPASP_C2PMSG_71_BASE_IDX                                          3
 
 // addressBlock: mp_SmuMp1_SmnDec
 // base address: 0x0
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 e030f1e186cb..a8d63d4d1f6e 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
@@ -2034,6 +2034,7 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu,
 			smu, SMU_DRIVER_TABLE_GPU_METRICS);
 	SmuMetricsExternal_t metrics_ext;
 	SmuMetrics_t *metrics = &metrics_ext.SmuMetrics;
+	uint32_t mp1_ver = amdgpu_ip_version(smu->adev, MP1_HWIP, 0);
 	int ret = 0;
 
 	ret = smu_cmn_get_metrics_table(smu,
@@ -2058,7 +2059,12 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu,
 					       metrics->Vcn1ActivityPercentage);
 
 	gpu_metrics->average_socket_power = metrics->AverageSocketPower;
-	gpu_metrics->energy_accumulator = metrics->EnergyAccumulator;
+
+	if ((mp1_ver == IP_VERSION(13, 0, 0) && smu->smc_fw_version <= 0x004e1e00) ||
+	    (mp1_ver == IP_VERSION(13, 0, 10) && smu->smc_fw_version <= 0x00500800))
+		gpu_metrics->energy_accumulator = metrics->EnergyAccumulator;
+	else
+		gpu_metrics->energy_accumulator = UINT_MAX;
 
 	if (metrics->AverageGfxActivity <= SMU_13_0_0_BUSY_THRESHOLD)
 		gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs;
@@ -2216,7 +2222,8 @@ static int smu_v13_0_0_restore_user_od_settings(struct smu_context *smu)
 	user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) |
 							BIT(PP_OD_FEATURE_UCLK_BIT) |
 							BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) |
-							BIT(PP_OD_FEATURE_FAN_CURVE_BIT);
+							BIT(PP_OD_FEATURE_FAN_CURVE_BIT) |
+							BIT(PP_OD_FEATURE_ZERO_FAN_BIT);
 	res = smu_v13_0_0_upload_overdrive_table(smu, user_od_table);
 	user_od_table->OverDriveTable.FeatureCtrlMask = 0;
 	if (res == 0)
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 af0482c9caa7..5500a0f12f0e 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
@@ -2065,7 +2065,8 @@ static ssize_t smu_v13_0_7_get_gpu_metrics(struct smu_context *smu,
 					       metrics->Vcn1ActivityPercentage);
 
 	gpu_metrics->average_socket_power = metrics->AverageSocketPower;
-	gpu_metrics->energy_accumulator = metrics->EnergyAccumulator;
+	gpu_metrics->energy_accumulator = smu->smc_fw_version <= 0x00521400 ?
+		metrics->EnergyAccumulator : UINT_MAX;
 
 	if (metrics->AverageGfxActivity <= SMU_13_0_7_BUSY_THRESHOLD)
 		gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs;
@@ -2223,7 +2224,8 @@ static int smu_v13_0_7_restore_user_od_settings(struct smu_context *smu)
 	user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) |
 							BIT(PP_OD_FEATURE_UCLK_BIT) |
 							BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) |
-							BIT(PP_OD_FEATURE_FAN_CURVE_BIT);
+							BIT(PP_OD_FEATURE_FAN_CURVE_BIT) |
+							BIT(PP_OD_FEATURE_ZERO_FAN_BIT);
 	res = smu_v13_0_7_upload_overdrive_table(smu, user_od_table);
 	user_od_table->OverDriveTable.FeatureCtrlMask = 0;
 	if (res == 0)
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 9994d4369da8..73762d9b5969 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
@@ -2311,7 +2311,8 @@ static int smu_v14_0_2_restore_user_od_settings(struct smu_context *smu)
 	user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) |
 							BIT(PP_OD_FEATURE_UCLK_BIT) |
 							BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) |
-							BIT(PP_OD_FEATURE_FAN_CURVE_BIT);
+							BIT(PP_OD_FEATURE_FAN_CURVE_BIT) |
+							BIT(PP_OD_FEATURE_ZERO_FAN_BIT);
 	res = smu_v14_0_2_upload_overdrive_table(smu, user_od_table);
 	user_od_table->OverDriveTable.FeatureCtrlMask = 0;
 	if (res == 0)