diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 660b3fbade41..0ef82b229754 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -282,8 +282,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 			p->pasid,
 			dev->id);
 
-	err = pqm_create_queue(&p->pqm, dev, filep, &q_properties,
-				0, q_properties.type, &queue_id);
+	err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id);
 	if (err != 0)
 		goto err_create_queue;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index 0aa021aa0aa1..c407f6bd9956 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -184,9 +184,10 @@ static int dbgdev_register_diq(struct kfd_dbgdev *dbgdev)
 	struct kernel_queue *kq = NULL;
 	int status;
 
+	properties.type = KFD_QUEUE_TYPE_DIQ;
+
 	status = pqm_create_queue(dbgdev->pqm, dbgdev->dev, NULL,
-				&properties, 0, KFD_QUEUE_TYPE_DIQ,
-				&qid);
+				&properties, &qid);
 
 	if (status) {
 		pr_err("Failed to create DIQ\n");
@@ -769,13 +770,8 @@ int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p)
 	union GRBM_GFX_INDEX_BITS reg_gfx_index;
 	struct kfd_process_device *pdd;
 	struct dbg_wave_control_info wac_info;
-	int temp;
-	int first_vmid_to_scan = 8;
-	int last_vmid_to_scan = 15;
-
-	first_vmid_to_scan = ffs(dev->shared_resources.compute_vmid_bitmap) - 1;
-	temp = dev->shared_resources.compute_vmid_bitmap >> first_vmid_to_scan;
-	last_vmid_to_scan = first_vmid_to_scan + ffz(temp);
+	int first_vmid_to_scan = dev->vm_info.first_vmid_kfd;
+	int last_vmid_to_scan = dev->vm_info.last_vmid_kfd;
 
 	reg_sq_cmd.u32All = 0;
 	status = 0;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 5df12b287201..46049f005b02 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -92,6 +92,8 @@ static int kfd_gtt_sa_init(struct kfd_dev *kfd, unsigned int buf_size,
 				unsigned int chunk_size);
 static void kfd_gtt_sa_fini(struct kfd_dev *kfd);
 
+static int kfd_resume(struct kfd_dev *kfd);
+
 static const struct kfd_device_info *lookup_device_info(unsigned short did)
 {
 	size_t i;
@@ -169,15 +171,8 @@ static bool device_iommu_pasid_init(struct kfd_dev *kfd)
 			(unsigned int)(1 << kfd->device_info->max_pasid_bits),
 			iommu_info.max_pasids);
 
-	err = amd_iommu_init_device(kfd->pdev, pasid_limit);
-	if (err < 0) {
-		dev_err(kfd_device, "error initializing iommu device\n");
-		return false;
-	}
-
 	if (!kfd_set_pasid_limit(pasid_limit)) {
 		dev_err(kfd_device, "error setting pasid limit\n");
-		amd_iommu_free_device(kfd->pdev);
 		return false;
 	}
 
@@ -189,7 +184,7 @@ static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid)
 	struct kfd_dev *dev = kfd_device_by_pci_dev(pdev);
 
 	if (dev)
-		kfd_unbind_process_from_device(dev, pasid);
+		kfd_process_iommu_unbind_callback(dev, pasid);
 }
 
 /*
@@ -224,6 +219,11 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 
 	kfd->shared_resources = *gpu_resources;
 
+	kfd->vm_info.first_vmid_kfd = ffs(gpu_resources->compute_vmid_bitmap)-1;
+	kfd->vm_info.last_vmid_kfd = fls(gpu_resources->compute_vmid_bitmap)-1;
+	kfd->vm_info.vmid_num_kfd = kfd->vm_info.last_vmid_kfd
+			- kfd->vm_info.first_vmid_kfd + 1;
+
 	/* calculate max size of mqds needed for queues */
 	size = max_num_of_queues_per_device *
 			kfd->device_info->mqd_size_aligned;
@@ -273,29 +273,22 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 		goto kfd_interrupt_error;
 	}
 
-	if (!device_iommu_pasid_init(kfd)) {
-		dev_err(kfd_device,
-			"Error initializing iommuv2 for device %x:%x\n",
-			kfd->pdev->vendor, kfd->pdev->device);
-		goto device_iommu_pasid_error;
-	}
-	amd_iommu_set_invalidate_ctx_cb(kfd->pdev,
-						iommu_pasid_shutdown_callback);
-	amd_iommu_set_invalid_ppr_cb(kfd->pdev, iommu_invalid_ppr_cb);
-
 	kfd->dqm = device_queue_manager_init(kfd);
 	if (!kfd->dqm) {
 		dev_err(kfd_device, "Error initializing queue manager\n");
 		goto device_queue_manager_error;
 	}
 
-	if (kfd->dqm->ops.start(kfd->dqm)) {
+	if (!device_iommu_pasid_init(kfd)) {
 		dev_err(kfd_device,
-			"Error starting queue manager for device %x:%x\n",
+			"Error initializing iommuv2 for device %x:%x\n",
 			kfd->pdev->vendor, kfd->pdev->device);
-		goto dqm_start_error;
+		goto device_iommu_pasid_error;
 	}
 
+	if (kfd_resume(kfd))
+		goto kfd_resume_error;
+
 	kfd->dbgmgr = NULL;
 
 	kfd->init_complete = true;
@@ -307,11 +300,10 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 
 	goto out;
 
-dqm_start_error:
+kfd_resume_error:
+device_iommu_pasid_error:
 	device_queue_manager_uninit(kfd->dqm);
 device_queue_manager_error:
-	amd_iommu_free_device(kfd->pdev);
-device_iommu_pasid_error:
 	kfd_interrupt_exit(kfd);
 kfd_interrupt_error:
 	kfd_topology_remove_device(kfd);
@@ -331,8 +323,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 void kgd2kfd_device_exit(struct kfd_dev *kfd)
 {
 	if (kfd->init_complete) {
+		kgd2kfd_suspend(kfd);
 		device_queue_manager_uninit(kfd->dqm);
-		amd_iommu_free_device(kfd->pdev);
 		kfd_interrupt_exit(kfd);
 		kfd_topology_remove_device(kfd);
 		kfd_doorbell_fini(kfd);
@@ -345,35 +337,59 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
 
 void kgd2kfd_suspend(struct kfd_dev *kfd)
 {
-	if (kfd->init_complete) {
-		kfd->dqm->ops.stop(kfd->dqm);
-		amd_iommu_set_invalidate_ctx_cb(kfd->pdev, NULL);
-		amd_iommu_set_invalid_ppr_cb(kfd->pdev, NULL);
-		amd_iommu_free_device(kfd->pdev);
-	}
+	if (!kfd->init_complete)
+		return;
+
+	kfd->dqm->ops.stop(kfd->dqm);
+
+	kfd_unbind_processes_from_device(kfd);
+
+	amd_iommu_set_invalidate_ctx_cb(kfd->pdev, NULL);
+	amd_iommu_set_invalid_ppr_cb(kfd->pdev, NULL);
+	amd_iommu_free_device(kfd->pdev);
 }
 
 int kgd2kfd_resume(struct kfd_dev *kfd)
 {
-	unsigned int pasid_limit;
-	int err;
+	if (!kfd->init_complete)
+		return 0;
 
-	pasid_limit = kfd_get_pasid_limit();
+	return kfd_resume(kfd);
 
-	if (kfd->init_complete) {
-		err = amd_iommu_init_device(kfd->pdev, pasid_limit);
-		if (err < 0) {
-			dev_err(kfd_device, "failed to initialize iommu\n");
-			return -ENXIO;
-		}
+}
 
-		amd_iommu_set_invalidate_ctx_cb(kfd->pdev,
-						iommu_pasid_shutdown_callback);
-		amd_iommu_set_invalid_ppr_cb(kfd->pdev, iommu_invalid_ppr_cb);
-		kfd->dqm->ops.start(kfd->dqm);
+static int kfd_resume(struct kfd_dev *kfd)
+{
+	int err = 0;
+	unsigned int pasid_limit = kfd_get_pasid_limit();
+
+	err = amd_iommu_init_device(kfd->pdev, pasid_limit);
+	if (err)
+		return -ENXIO;
+	amd_iommu_set_invalidate_ctx_cb(kfd->pdev,
+					iommu_pasid_shutdown_callback);
+	amd_iommu_set_invalid_ppr_cb(kfd->pdev,
+				     iommu_invalid_ppr_cb);
+
+	err = kfd_bind_processes_to_device(kfd);
+	if (err)
+		goto processes_bind_error;
+
+	err = kfd->dqm->ops.start(kfd->dqm);
+	if (err) {
+		dev_err(kfd_device,
+			"Error starting queue manager for device %x:%x\n",
+			kfd->pdev->vendor, kfd->pdev->device);
+		goto dqm_start_error;
 	}
 
-	return 0;
+	return err;
+
+dqm_start_error:
+processes_bind_error:
+	amd_iommu_free_device(kfd->pdev);
+
+	return err;
 }
 
 /* This is called directly from KGD at ISR. */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 53a66e821624..da3b74315acf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -44,9 +44,14 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 					struct queue *q,
 					struct qcm_process_device *qpd);
 
-static int execute_queues_cpsch(struct device_queue_manager *dqm, bool lock);
-static int destroy_queues_cpsch(struct device_queue_manager *dqm,
-				bool preempt_static_queues, bool lock);
+static int execute_queues_cpsch(struct device_queue_manager *dqm,
+				enum kfd_unmap_queues_filter filter,
+				uint32_t filter_param);
+static int unmap_queues_cpsch(struct device_queue_manager *dqm,
+				enum kfd_unmap_queues_filter filter,
+				uint32_t filter_param);
+
+static int map_queues_cpsch(struct device_queue_manager *dqm);
 
 static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 					struct queue *q,
@@ -113,11 +118,11 @@ static int allocate_vmid(struct device_queue_manager *dqm,
 	if (dqm->vmid_bitmap == 0)
 		return -ENOMEM;
 
-	bit = find_first_bit((unsigned long *)&dqm->vmid_bitmap, CIK_VMID_NUM);
+	bit = find_first_bit((unsigned long *)&dqm->vmid_bitmap,
+				dqm->dev->vm_info.vmid_num_kfd);
 	clear_bit(bit, (unsigned long *)&dqm->vmid_bitmap);
 
-	/* Kaveri kfd vmid's starts from vmid 8 */
-	allocated_vmid = bit + KFD_VMID_START_OFFSET;
+	allocated_vmid = bit + dqm->dev->vm_info.first_vmid_kfd;
 	pr_debug("vmid allocation %d\n", allocated_vmid);
 	qpd->vmid = allocated_vmid;
 	q->properties.vmid = allocated_vmid;
@@ -132,7 +137,7 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
 				struct qcm_process_device *qpd,
 				struct queue *q)
 {
-	int bit = qpd->vmid - KFD_VMID_START_OFFSET;
+	int bit = qpd->vmid - dqm->dev->vm_info.first_vmid_kfd;
 
 	/* Release the vmid mapping */
 	set_pasid_vmid_mapping(dqm, 0, qpd->vmid);
@@ -184,6 +189,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 	}
 
 	list_add(&q->list, &qpd->queues_list);
+	qpd->queue_count++;
 	if (q->properties.is_active)
 		dqm->queue_count++;
 
@@ -273,6 +279,9 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 	dqm->dev->kfd2kgd->set_scratch_backing_va(
 			dqm->dev->kgd, qpd->sh_hidden_private_base, qpd->vmid);
 
+	if (!q->properties.is_active)
+		return 0;
+
 	retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue, &q->properties,
 			       q->process->mm);
 	if (retval)
@@ -288,65 +297,74 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 	return retval;
 }
 
-static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
+/* Access to DQM has to be locked before calling destroy_queue_nocpsch_locked
+ * to avoid asynchronized access
+ */
+static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
 				struct qcm_process_device *qpd,
 				struct queue *q)
 {
 	int retval;
 	struct mqd_manager *mqd;
 
-	retval = 0;
-
-	mutex_lock(&dqm->lock);
+	mqd = dqm->ops.get_mqd_manager(dqm,
+		get_mqd_type_from_queue_type(q->properties.type));
+	if (!mqd)
+		return -ENOMEM;
 
 	if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE) {
-		mqd = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE);
-		if (mqd == NULL) {
-			retval = -ENOMEM;
-			goto out;
-		}
 		deallocate_hqd(dqm, q);
 	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
-		mqd = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_SDMA);
-		if (mqd == NULL) {
-			retval = -ENOMEM;
-			goto out;
-		}
 		dqm->sdma_queue_count--;
 		deallocate_sdma_queue(dqm, q->sdma_id);
 	} else {
 		pr_debug("q->properties.type %d is invalid\n",
 				q->properties.type);
-		retval = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
+	dqm->total_queue_count--;
 
 	retval = mqd->destroy_mqd(mqd, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
-				QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS,
+				KFD_UNMAP_LATENCY_MS,
 				q->pipe, q->queue);
-
-	if (retval)
-		goto out;
+	if (retval == -ETIME)
+		qpd->reset_wavefronts = true;
 
 	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
 
 	list_del(&q->list);
-	if (list_empty(&qpd->queues_list))
+	if (list_empty(&qpd->queues_list)) {
+		if (qpd->reset_wavefronts) {
+			pr_warn("Resetting wave fronts (nocpsch) on dev %p\n",
+					dqm->dev);
+			/* dbgdev_wave_reset_wavefronts has to be called before
+			 * deallocate_vmid(), i.e. when vmid is still in use.
+			 */
+			dbgdev_wave_reset_wavefronts(dqm->dev,
+					qpd->pqm->process);
+			qpd->reset_wavefronts = false;
+		}
+
 		deallocate_vmid(dqm, qpd, q);
+	}
+	qpd->queue_count--;
 	if (q->properties.is_active)
 		dqm->queue_count--;
 
-	/*
-	 * Unconditionally decrement this counter, regardless of the queue's
-	 * type
-	 */
-	dqm->total_queue_count--;
-	pr_debug("Total of %d queues are accountable so far\n",
-			dqm->total_queue_count);
+	return retval;
+}
 
-out:
+static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
+				struct qcm_process_device *qpd,
+				struct queue *q)
+{
+	int retval;
+
+	mutex_lock(&dqm->lock);
+	retval = destroy_queue_nocpsch_locked(dqm, qpd, q);
 	mutex_unlock(&dqm->lock);
+
 	return retval;
 }
 
@@ -364,29 +382,56 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		goto out_unlock;
 	}
 
-	if (q->properties.is_active)
-		prev_active = true;
+	/* Save previous activity state for counters */
+	prev_active = q->properties.is_active;
+
+	/* Make sure the queue is unmapped before updating the MQD */
+	if (sched_policy != KFD_SCHED_POLICY_NO_HWS) {
+		retval = unmap_queues_cpsch(dqm,
+				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
+		if (retval != 0) {
+			pr_err("unmap queue failed\n");
+			goto out_unlock;
+		}
+	} else if (sched_policy == KFD_SCHED_POLICY_NO_HWS &&
+		   prev_active &&
+		   (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
+		    q->properties.type == KFD_QUEUE_TYPE_SDMA)) {
+		retval = mqd->destroy_mqd(mqd, q->mqd,
+				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
+				KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
+		if (retval) {
+			pr_err("destroy mqd failed\n");
+			goto out_unlock;
+		}
+	}
+
+	retval = mqd->update_mqd(mqd, q->mqd, &q->properties);
+
+	if (sched_policy != KFD_SCHED_POLICY_NO_HWS)
+		retval = map_queues_cpsch(dqm);
+	else if (sched_policy == KFD_SCHED_POLICY_NO_HWS &&
+		 q->properties.is_active &&
+		 (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
+		  q->properties.type == KFD_QUEUE_TYPE_SDMA))
+		retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue,
+				       &q->properties, q->process->mm);
 
 	/*
-	 *
 	 * check active state vs. the previous state
 	 * and modify counter accordingly
 	 */
-	retval = mqd->update_mqd(mqd, q->mqd, &q->properties);
-	if ((q->properties.is_active) && (!prev_active))
+	if (q->properties.is_active && !prev_active)
 		dqm->queue_count++;
 	else if (!q->properties.is_active && prev_active)
 		dqm->queue_count--;
 
-	if (sched_policy != KFD_SCHED_POLICY_NO_HWS)
-		retval = execute_queues_cpsch(dqm, false);
-
 out_unlock:
 	mutex_unlock(&dqm->lock);
 	return retval;
 }
 
-static struct mqd_manager *get_mqd_manager_nocpsch(
+static struct mqd_manager *get_mqd_manager(
 		struct device_queue_manager *dqm, enum KFD_MQD_TYPE type)
 {
 	struct mqd_manager *mqd;
@@ -407,7 +452,7 @@ static struct mqd_manager *get_mqd_manager_nocpsch(
 	return mqd;
 }
 
-static int register_process_nocpsch(struct device_queue_manager *dqm,
+static int register_process(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
 	struct device_process_node *n;
@@ -431,7 +476,7 @@ static int register_process_nocpsch(struct device_queue_manager *dqm,
 	return retval;
 }
 
-static int unregister_process_nocpsch(struct device_queue_manager *dqm,
+static int unregister_process(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
 	int retval;
@@ -507,13 +552,13 @@ static int initialize_nocpsch(struct device_queue_manager *dqm)
 				dqm->allocated_queues[pipe] |= 1 << queue;
 	}
 
-	dqm->vmid_bitmap = (1 << VMID_PER_DEVICE) - 1;
+	dqm->vmid_bitmap = (1 << dqm->dev->vm_info.vmid_num_kfd) - 1;
 	dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
 
 	return 0;
 }
 
-static void uninitialize_nocpsch(struct device_queue_manager *dqm)
+static void uninitialize(struct device_queue_manager *dqm)
 {
 	int i;
 
@@ -577,8 +622,8 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 	if (retval)
 		return retval;
 
-	q->properties.sdma_queue_id = q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
-	q->properties.sdma_engine_id = q->sdma_id / CIK_SDMA_ENGINE_NUM;
+	q->properties.sdma_queue_id = q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
+	q->properties.sdma_engine_id = q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
 
 	pr_debug("SDMA id is:    %d\n", q->sdma_id);
 	pr_debug("SDMA queue id: %d\n", q->properties.sdma_queue_id);
@@ -613,8 +658,7 @@ static int set_sched_resources(struct device_queue_manager *dqm)
 	int i, mec;
 	struct scheduling_resources res;
 
-	res.vmid_mask = (1 << VMID_PER_DEVICE) - 1;
-	res.vmid_mask <<= KFD_VMID_START_OFFSET;
+	res.vmid_mask = dqm->dev->shared_resources.compute_vmid_bitmap;
 
 	res.queue_mask = 0;
 	for (i = 0; i < KGD_MAX_QUEUES; ++i) {
@@ -661,6 +705,7 @@ static int initialize_cpsch(struct device_queue_manager *dqm)
 	dqm->queue_count = dqm->processes_count = 0;
 	dqm->sdma_queue_count = 0;
 	dqm->active_runlist = false;
+	dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
 	retval = dqm->ops_asic_specific.initialize(dqm);
 	if (retval)
 		mutex_destroy(&dqm->lock);
@@ -670,7 +715,6 @@ static int initialize_cpsch(struct device_queue_manager *dqm)
 
 static int start_cpsch(struct device_queue_manager *dqm)
 {
-	struct device_process_node *node;
 	int retval;
 
 	retval = 0;
@@ -697,12 +741,9 @@ static int start_cpsch(struct device_queue_manager *dqm)
 
 	init_interrupts(dqm);
 
-	list_for_each_entry(node, &dqm->queues, list)
-		if (node->qpd->pqm->process && dqm->dev)
-			kfd_bind_process_to_device(dqm->dev,
-						node->qpd->pqm->process);
-
-	execute_queues_cpsch(dqm, true);
+	mutex_lock(&dqm->lock);
+	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
+	mutex_unlock(&dqm->lock);
 
 	return 0;
 fail_allocate_vidmem:
@@ -714,15 +755,10 @@ static int start_cpsch(struct device_queue_manager *dqm)
 
 static int stop_cpsch(struct device_queue_manager *dqm)
 {
-	struct device_process_node *node;
-	struct kfd_process_device *pdd;
+	mutex_lock(&dqm->lock);
+	unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
+	mutex_unlock(&dqm->lock);
 
-	destroy_queues_cpsch(dqm, true, true);
-
-	list_for_each_entry(node, &dqm->queues, list) {
-		pdd = qpd_to_pdd(node->qpd);
-		pdd->bound = false;
-	}
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
 	pm_uninit(&dqm->packets);
 
@@ -752,7 +788,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
 	list_add(&kq->list, &qpd->priv_queue_list);
 	dqm->queue_count++;
 	qpd->is_debug = true;
-	execute_queues_cpsch(dqm, false);
+	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 	mutex_unlock(&dqm->lock);
 
 	return 0;
@@ -763,12 +799,10 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
 	mutex_lock(&dqm->lock);
-	/* here we actually preempt the DIQ */
-	destroy_queues_cpsch(dqm, true, false);
 	list_del(&kq->list);
 	dqm->queue_count--;
 	qpd->is_debug = false;
-	execute_queues_cpsch(dqm, false);
+	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
 	/*
 	 * Unconditionally decrement this counter, regardless of the queue's
 	 * type.
@@ -779,14 +813,6 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 	mutex_unlock(&dqm->lock);
 }
 
-static void select_sdma_engine_id(struct queue *q)
-{
-	static int sdma_id;
-
-	q->sdma_id = sdma_id;
-	sdma_id = (sdma_id + 1) % 2;
-}
-
 static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 			struct qcm_process_device *qpd, int *allocate_vmid)
 {
@@ -807,9 +833,15 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		goto out;
 	}
 
-	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
-		select_sdma_engine_id(q);
-
+	if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
+		retval = allocate_sdma_queue(dqm, &q->sdma_id);
+		if (retval != 0)
+			goto out;
+		q->properties.sdma_queue_id =
+			q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
+		q->properties.sdma_engine_id =
+			q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
+	}
 	mqd = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
 
@@ -825,9 +857,11 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		goto out;
 
 	list_add(&q->list, &qpd->queues_list);
+	qpd->queue_count++;
 	if (q->properties.is_active) {
 		dqm->queue_count++;
-		retval = execute_queues_cpsch(dqm, false);
+		retval = execute_queues_cpsch(dqm,
+				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 	}
 
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
@@ -848,12 +882,12 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 
 int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
 				unsigned int fence_value,
-				unsigned long timeout)
+				unsigned int timeout_ms)
 {
-	timeout += jiffies;
+	unsigned long end_jiffies = msecs_to_jiffies(timeout_ms) + jiffies;
 
 	while (*fence_addr != fence_value) {
-		if (time_after(jiffies, timeout)) {
+		if (time_after(jiffies, end_jiffies)) {
 			pr_err("qcm fence wait loop timeout expired\n");
 			return -ETIME;
 		}
@@ -863,44 +897,57 @@ int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
 	return 0;
 }
 
-static int destroy_sdma_queues(struct device_queue_manager *dqm,
+static int unmap_sdma_queues(struct device_queue_manager *dqm,
 				unsigned int sdma_engine)
 {
 	return pm_send_unmap_queue(&dqm->packets, KFD_QUEUE_TYPE_SDMA,
-			KFD_PREEMPT_TYPE_FILTER_DYNAMIC_QUEUES, 0, false,
+			KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0, false,
 			sdma_engine);
 }
 
-static int destroy_queues_cpsch(struct device_queue_manager *dqm,
-				bool preempt_static_queues, bool lock)
+/* dqm->lock mutex has to be locked before calling this function */
+static int map_queues_cpsch(struct device_queue_manager *dqm)
 {
 	int retval;
-	enum kfd_preempt_type_filter preempt_type;
-	struct kfd_process_device *pdd;
 
-	retval = 0;
+	if (dqm->queue_count <= 0 || dqm->processes_count <= 0)
+		return 0;
+
+	if (dqm->active_runlist)
+		return 0;
+
+	retval = pm_send_runlist(&dqm->packets, &dqm->queues);
+	if (retval) {
+		pr_err("failed to execute runlist\n");
+		return retval;
+	}
+	dqm->active_runlist = true;
+
+	return retval;
+}
+
+/* dqm->lock mutex has to be locked before calling this function */
+static int unmap_queues_cpsch(struct device_queue_manager *dqm,
+				enum kfd_unmap_queues_filter filter,
+				uint32_t filter_param)
+{
+	int retval = 0;
 
-	if (lock)
-		mutex_lock(&dqm->lock);
 	if (!dqm->active_runlist)
-		goto out;
+		return retval;
 
 	pr_debug("Before destroying queues, sdma queue count is : %u\n",
 		dqm->sdma_queue_count);
 
 	if (dqm->sdma_queue_count > 0) {
-		destroy_sdma_queues(dqm, 0);
-		destroy_sdma_queues(dqm, 1);
+		unmap_sdma_queues(dqm, 0);
+		unmap_sdma_queues(dqm, 1);
 	}
 
-	preempt_type = preempt_static_queues ?
-			KFD_PREEMPT_TYPE_FILTER_ALL_QUEUES :
-			KFD_PREEMPT_TYPE_FILTER_DYNAMIC_QUEUES;
-
 	retval = pm_send_unmap_queue(&dqm->packets, KFD_QUEUE_TYPE_COMPUTE,
-			preempt_type, 0, false, 0);
+			filter, filter_param, false, 0);
 	if (retval)
-		goto out;
+		return retval;
 
 	*dqm->fence_addr = KFD_FENCE_INIT;
 	pm_send_query_status(&dqm->packets, dqm->fence_gpu_addr,
@@ -908,55 +955,29 @@ static int destroy_queues_cpsch(struct device_queue_manager *dqm,
 	/* should be timed out */
 	retval = amdkfd_fence_wait_timeout(dqm->fence_addr, KFD_FENCE_COMPLETED,
 				QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS);
-	if (retval) {
-		pdd = kfd_get_process_device_data(dqm->dev,
-				kfd_get_process(current));
-		pdd->reset_wavefronts = true;
-		goto out;
-	}
+	if (retval)
+		return retval;
+
 	pm_release_ib(&dqm->packets);
 	dqm->active_runlist = false;
 
-out:
-	if (lock)
-		mutex_unlock(&dqm->lock);
 	return retval;
 }
 
-static int execute_queues_cpsch(struct device_queue_manager *dqm, bool lock)
+/* dqm->lock mutex has to be locked before calling this function */
+static int execute_queues_cpsch(struct device_queue_manager *dqm,
+				enum kfd_unmap_queues_filter filter,
+				uint32_t filter_param)
 {
 	int retval;
 
-	if (lock)
-		mutex_lock(&dqm->lock);
-
-	retval = destroy_queues_cpsch(dqm, false, false);
+	retval = unmap_queues_cpsch(dqm, filter, filter_param);
 	if (retval) {
-		pr_err("The cp might be in an unrecoverable state due to an unsuccessful queues preemption");
-		goto out;
+		pr_err("The cp might be in an unrecoverable state due to an unsuccessful queues preemption\n");
+		return retval;
 	}
 
-	if (dqm->queue_count <= 0 || dqm->processes_count <= 0) {
-		retval = 0;
-		goto out;
-	}
-
-	if (dqm->active_runlist) {
-		retval = 0;
-		goto out;
-	}
-
-	retval = pm_send_runlist(&dqm->packets, &dqm->queues);
-	if (retval) {
-		pr_err("failed to execute runlist");
-		goto out;
-	}
-	dqm->active_runlist = true;
-
-out:
-	if (lock)
-		mutex_unlock(&dqm->lock);
-	return retval;
+	return map_queues_cpsch(dqm);
 }
 
 static int destroy_queue_cpsch(struct device_queue_manager *dqm,
@@ -991,14 +1012,20 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 		goto failed;
 	}
 
-	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
+	if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
 		dqm->sdma_queue_count--;
+		deallocate_sdma_queue(dqm, q->sdma_id);
+	}
 
 	list_del(&q->list);
+	qpd->queue_count--;
 	if (q->properties.is_active)
 		dqm->queue_count--;
 
-	execute_queues_cpsch(dqm, false);
+	retval = execute_queues_cpsch(dqm,
+				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
+	if (retval == -ETIME)
+		qpd->reset_wavefronts = true;
 
 	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
 
@@ -1088,6 +1115,109 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm,
 	return retval;
 }
 
+static int process_termination_nocpsch(struct device_queue_manager *dqm,
+		struct qcm_process_device *qpd)
+{
+	struct queue *q, *next;
+	struct device_process_node *cur, *next_dpn;
+	int retval = 0;
+
+	mutex_lock(&dqm->lock);
+
+	/* Clear all user mode queues */
+	list_for_each_entry_safe(q, next, &qpd->queues_list, list) {
+		int ret;
+
+		ret = destroy_queue_nocpsch_locked(dqm, qpd, q);
+		if (ret)
+			retval = ret;
+	}
+
+	/* Unregister process */
+	list_for_each_entry_safe(cur, next_dpn, &dqm->queues, list) {
+		if (qpd == cur->qpd) {
+			list_del(&cur->list);
+			kfree(cur);
+			dqm->processes_count--;
+			break;
+		}
+	}
+
+	mutex_unlock(&dqm->lock);
+	return retval;
+}
+
+
+static int process_termination_cpsch(struct device_queue_manager *dqm,
+		struct qcm_process_device *qpd)
+{
+	int retval;
+	struct queue *q, *next;
+	struct kernel_queue *kq, *kq_next;
+	struct mqd_manager *mqd;
+	struct device_process_node *cur, *next_dpn;
+	enum kfd_unmap_queues_filter filter =
+		KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES;
+
+	retval = 0;
+
+	mutex_lock(&dqm->lock);
+
+	/* Clean all kernel queues */
+	list_for_each_entry_safe(kq, kq_next, &qpd->priv_queue_list, list) {
+		list_del(&kq->list);
+		dqm->queue_count--;
+		qpd->is_debug = false;
+		dqm->total_queue_count--;
+		filter = KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES;
+	}
+
+	/* Clear all user mode queues */
+	list_for_each_entry(q, &qpd->queues_list, list) {
+		if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
+			dqm->sdma_queue_count--;
+
+		if (q->properties.is_active)
+			dqm->queue_count--;
+
+		dqm->total_queue_count--;
+	}
+
+	/* Unregister process */
+	list_for_each_entry_safe(cur, next_dpn, &dqm->queues, list) {
+		if (qpd == cur->qpd) {
+			list_del(&cur->list);
+			kfree(cur);
+			dqm->processes_count--;
+			break;
+		}
+	}
+
+	retval = execute_queues_cpsch(dqm, filter, 0);
+	if (retval || qpd->reset_wavefronts) {
+		pr_warn("Resetting wave fronts (cpsch) on dev %p\n", dqm->dev);
+		dbgdev_wave_reset_wavefronts(dqm->dev, qpd->pqm->process);
+		qpd->reset_wavefronts = false;
+	}
+
+	/* lastly, free mqd resources */
+	list_for_each_entry_safe(q, next, &qpd->queues_list, list) {
+		mqd = dqm->ops.get_mqd_manager(dqm,
+			get_mqd_type_from_queue_type(q->properties.type));
+		if (!mqd) {
+			retval = -ENOMEM;
+			goto out;
+		}
+		list_del(&q->list);
+		qpd->queue_count--;
+		mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	}
+
+out:
+	mutex_unlock(&dqm->lock);
+	return retval;
+}
+
 struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 {
 	struct device_queue_manager *dqm;
@@ -1109,13 +1239,14 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 		dqm->ops.stop = stop_cpsch;
 		dqm->ops.destroy_queue = destroy_queue_cpsch;
 		dqm->ops.update_queue = update_queue;
-		dqm->ops.get_mqd_manager = get_mqd_manager_nocpsch;
-		dqm->ops.register_process = register_process_nocpsch;
-		dqm->ops.unregister_process = unregister_process_nocpsch;
-		dqm->ops.uninitialize = uninitialize_nocpsch;
+		dqm->ops.get_mqd_manager = get_mqd_manager;
+		dqm->ops.register_process = register_process;
+		dqm->ops.unregister_process = unregister_process;
+		dqm->ops.uninitialize = uninitialize;
 		dqm->ops.create_kernel_queue = create_kernel_queue_cpsch;
 		dqm->ops.destroy_kernel_queue = destroy_kernel_queue_cpsch;
 		dqm->ops.set_cache_memory_policy = set_cache_memory_policy;
+		dqm->ops.process_termination = process_termination_cpsch;
 		break;
 	case KFD_SCHED_POLICY_NO_HWS:
 		/* initialize dqm for no cp scheduling */
@@ -1124,12 +1255,13 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 		dqm->ops.create_queue = create_queue_nocpsch;
 		dqm->ops.destroy_queue = destroy_queue_nocpsch;
 		dqm->ops.update_queue = update_queue;
-		dqm->ops.get_mqd_manager = get_mqd_manager_nocpsch;
-		dqm->ops.register_process = register_process_nocpsch;
-		dqm->ops.unregister_process = unregister_process_nocpsch;
+		dqm->ops.get_mqd_manager = get_mqd_manager;
+		dqm->ops.register_process = register_process;
+		dqm->ops.unregister_process = unregister_process;
 		dqm->ops.initialize = initialize_nocpsch;
-		dqm->ops.uninitialize = uninitialize_nocpsch;
+		dqm->ops.uninitialize = uninitialize;
 		dqm->ops.set_cache_memory_policy = set_cache_memory_policy;
+		dqm->ops.process_termination = process_termination_nocpsch;
 		break;
 	default:
 		pr_err("Invalid scheduling policy %d\n", sched_policy);
@@ -1144,6 +1276,10 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 	case CHIP_KAVERI:
 		device_queue_manager_init_cik(&dqm->ops_asic_specific);
 		break;
+	default:
+		WARN(1, "Unexpected ASIC family %u",
+		     dev->device_info->asic_family);
+		goto out_free;
 	}
 
 	if (!dqm->ops.initialize(dqm))
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index faf820a06400..31c2b1f9d320 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -29,11 +29,9 @@
 #include "kfd_priv.h"
 #include "kfd_mqd_manager.h"
 
-#define QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS	(500)
-#define CIK_VMID_NUM				(8)
-#define KFD_VMID_START_OFFSET			(8)
-#define VMID_PER_DEVICE				CIK_VMID_NUM
-#define KFD_DQM_FIRST_PIPE			(0)
+#define KFD_UNMAP_LATENCY_MS			(4000)
+#define QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS (2 * KFD_UNMAP_LATENCY_MS + 1000)
+
 #define CIK_SDMA_QUEUES				(4)
 #define CIK_SDMA_QUEUES_PER_ENGINE		(2)
 #define CIK_SDMA_ENGINE_NUM			(2)
@@ -79,6 +77,8 @@ struct device_process_node {
  * @set_cache_memory_policy: Sets memory policy (cached/ non cached) for the
  * memory apertures.
  *
+ * @process_termination: Clears all process queues belongs to that device.
+ *
  */
 
 struct device_queue_manager_ops {
@@ -122,6 +122,9 @@ struct device_queue_manager_ops {
 					   enum cache_policy alternate_policy,
 					   void __user *alternate_aperture_base,
 					   uint64_t alternate_aperture_size);
+
+	int (*process_termination)(struct device_queue_manager *dqm,
+			struct qcm_process_device *qpd);
 };
 
 struct device_queue_manager_asic_ops {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index ed71ad40e8f7..8b0c0645d7c0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -185,7 +185,7 @@ static void uninitialize(struct kernel_queue *kq)
 		kq->mqd->destroy_mqd(kq->mqd,
 					kq->queue->mqd,
 					KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
-					QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS,
+					KFD_UNMAP_LATENCY_MS,
 					kq->queue->pipe,
 					kq->queue->queue);
 	else if (kq->queue->properties.type == KFD_QUEUE_TYPE_DIQ)
@@ -303,14 +303,20 @@ struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 	case CHIP_KAVERI:
 		kernel_queue_init_cik(&kq->ops_asic_specific);
 		break;
+	default:
+		WARN(1, "Unexpected ASIC family %u",
+		     dev->device_info->asic_family);
+		goto out_free;
 	}
 
-	if (!kq->ops.initialize(kq, dev, type, KFD_KERNEL_QUEUE_SIZE)) {
-		pr_err("Failed to init kernel queue\n");
-		kfree(kq);
-		return NULL;
-	}
-	return kq;
+	if (kq->ops.initialize(kq, dev, type, KFD_KERNEL_QUEUE_SIZE))
+		return kq;
+
+	pr_err("Failed to init kernel queue\n");
+
+out_free:
+	kfree(kq);
+	return NULL;
 }
 
 void kernel_queue_uninit(struct kernel_queue *kq)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index b1ef1368c3bb..dfd260ef81ff 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -31,6 +31,9 @@ struct mqd_manager *mqd_manager_init(enum KFD_MQD_TYPE type,
 		return mqd_manager_init_cik(type, dev);
 	case CHIP_CARRIZO:
 		return mqd_manager_init_vi(type, dev);
+	default:
+		WARN(1, "Unexpected ASIC family %u",
+		     dev->device_info->asic_family);
 	}
 
 	return NULL;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index 1d312603de9f..16da8ad02d8b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -140,8 +140,6 @@ static int pm_create_map_process(struct packet_manager *pm, uint32_t *buffer,
 				struct qcm_process_device *qpd)
 {
 	struct pm4_mes_map_process *packet;
-	struct queue *cur;
-	uint32_t num_queues;
 
 	packet = (struct pm4_mes_map_process *)buffer;
 
@@ -156,10 +154,7 @@ static int pm_create_map_process(struct packet_manager *pm, uint32_t *buffer,
 	packet->bitfields10.gds_size = qpd->gds_size;
 	packet->bitfields10.num_gws = qpd->num_gws;
 	packet->bitfields10.num_oac = qpd->num_oac;
-	num_queues = 0;
-	list_for_each_entry(cur, &qpd->queues_list, list)
-		num_queues++;
-	packet->bitfields10.num_queues = (qpd->is_debug) ? 0 : num_queues;
+	packet->bitfields10.num_queues = (qpd->is_debug) ? 0 : qpd->queue_count;
 
 	packet->sh_mem_config = qpd->sh_mem_config;
 	packet->sh_mem_bases = qpd->sh_mem_bases;
@@ -208,7 +203,7 @@ static int pm_create_map_queue(struct packet_manager *pm, uint32_t *buffer,
 			queue_type__mes_map_queues__debug_interface_queue_vi;
 		break;
 	case KFD_QUEUE_TYPE_SDMA:
-		packet->bitfields2.engine_sel =
+		packet->bitfields2.engine_sel = q->properties.sdma_engine_id +
 				engine_sel__mes_map_queues__sdma0_vi;
 		use_static = false; /* no static queues under SDMA */
 		break;
@@ -376,7 +371,7 @@ int pm_send_set_resources(struct packet_manager *pm,
 	packet->bitfields2.queue_type =
 			queue_type__mes_set_resources__hsa_interface_queue_hiq;
 	packet->bitfields2.vmid_mask = res->vmid_mask;
-	packet->bitfields2.unmap_latency = KFD_UNMAP_LATENCY;
+	packet->bitfields2.unmap_latency = KFD_UNMAP_LATENCY_MS / 100;
 	packet->bitfields7.oac_mask = res->oac_mask;
 	packet->bitfields8.gds_heap_base = res->gds_heap_base;
 	packet->bitfields8.gds_heap_size = res->gds_heap_size;
@@ -476,7 +471,7 @@ int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
 }
 
 int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
-			enum kfd_preempt_type_filter mode,
+			enum kfd_unmap_queues_filter filter,
 			uint32_t filter_param, bool reset,
 			unsigned int sdma_engine)
 {
@@ -494,8 +489,8 @@ int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
 
 	packet = (struct pm4_mes_unmap_queues *)buffer;
 	memset(buffer, 0, sizeof(struct pm4_mes_unmap_queues));
-	pr_debug("static_queue: unmapping queues: mode is %d , reset is %d , type is %d\n",
-		mode, reset, type);
+	pr_debug("static_queue: unmapping queues: filter is %d , reset is %d , type is %d\n",
+		filter, reset, type);
 	packet->header.u32All = build_pm4_header(IT_UNMAP_QUEUES,
 					sizeof(struct pm4_mes_unmap_queues));
 	switch (type) {
@@ -521,29 +516,29 @@ int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
 		packet->bitfields2.action =
 				action__mes_unmap_queues__preempt_queues;
 
-	switch (mode) {
-	case KFD_PREEMPT_TYPE_FILTER_SINGLE_QUEUE:
+	switch (filter) {
+	case KFD_UNMAP_QUEUES_FILTER_SINGLE_QUEUE:
 		packet->bitfields2.queue_sel =
 				queue_sel__mes_unmap_queues__perform_request_on_specified_queues;
 		packet->bitfields2.num_queues = 1;
 		packet->bitfields3b.doorbell_offset0 = filter_param;
 		break;
-	case KFD_PREEMPT_TYPE_FILTER_BY_PASID:
+	case KFD_UNMAP_QUEUES_FILTER_BY_PASID:
 		packet->bitfields2.queue_sel =
 				queue_sel__mes_unmap_queues__perform_request_on_pasid_queues;
 		packet->bitfields3a.pasid = filter_param;
 		break;
-	case KFD_PREEMPT_TYPE_FILTER_ALL_QUEUES:
+	case KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES:
 		packet->bitfields2.queue_sel =
 				queue_sel__mes_unmap_queues__unmap_all_queues;
 		break;
-	case KFD_PREEMPT_TYPE_FILTER_DYNAMIC_QUEUES:
+	case KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES:
 		/* in this case, we do not preempt static queues */
 		packet->bitfields2.queue_sel =
 				queue_sel__mes_unmap_queues__unmap_all_non_static_queues;
 		break;
 	default:
-		WARN(1, "filter %d", mode);
+		WARN(1, "filter %d", filter);
 		retval = -EINVAL;
 		goto err_invalid;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 634083e340d1..7d86ec9790d3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -33,6 +33,8 @@
 #include <linux/kfd_ioctl.h>
 #include <kgd_kfd_interface.h>
 
+#include "amd_shared.h"
+
 #define KFD_SYSFS_FILE_MODE 0444
 
 #define KFD_MMAP_DOORBELL_MASK 0x8000000000000
@@ -112,11 +114,6 @@ enum cache_policy {
 	cache_policy_noncoherent
 };
 
-enum asic_family_type {
-	CHIP_KAVERI = 0,
-	CHIP_CARRIZO
-};
-
 struct kfd_event_interrupt_class {
 	bool (*interrupt_isr)(struct kfd_dev *dev,
 				const uint32_t *ih_ring_entry);
@@ -125,7 +122,7 @@ struct kfd_event_interrupt_class {
 };
 
 struct kfd_device_info {
-	unsigned int asic_family;
+	enum amd_asic_type asic_family;
 	const struct kfd_event_interrupt_class *event_interrupt_class;
 	unsigned int max_pasid_bits;
 	unsigned int max_no_of_hqd;
@@ -141,6 +138,12 @@ struct kfd_mem_obj {
 	uint32_t *cpu_ptr;
 };
 
+struct kfd_vmid_info {
+	uint32_t first_vmid_kfd;
+	uint32_t last_vmid_kfd;
+	uint32_t vmid_num_kfd;
+};
+
 struct kfd_dev {
 	struct kgd_dev *kgd;
 
@@ -162,6 +165,7 @@ struct kfd_dev {
 					   */
 
 	struct kgd2kfd_shared_resources shared_resources;
+	struct kfd_vmid_info vm_info;
 
 	const struct kfd2kgd_calls *kfd2kgd;
 	struct mutex doorbell_mutex;
@@ -218,22 +222,22 @@ void kfd_chardev_exit(void);
 struct device *kfd_chardev(void);
 
 /**
- * enum kfd_preempt_type_filter
+ * enum kfd_unmap_queues_filter
  *
- * @KFD_PREEMPT_TYPE_FILTER_SINGLE_QUEUE: Preempts single queue.
+ * @KFD_UNMAP_QUEUES_FILTER_SINGLE_QUEUE: Preempts single queue.
  *
- * @KFD_PRERMPT_TYPE_FILTER_ALL_QUEUES: Preempts all queues in the
+ * @KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES: Preempts all queues in the
  *						running queues list.
  *
- * @KFD_PRERMPT_TYPE_FILTER_BY_PASID: Preempts queues that belongs to
+ * @KFD_UNMAP_QUEUES_FILTER_BY_PASID: Preempts queues that belongs to
  *						specific process.
  *
  */
-enum kfd_preempt_type_filter {
-	KFD_PREEMPT_TYPE_FILTER_SINGLE_QUEUE,
-	KFD_PREEMPT_TYPE_FILTER_ALL_QUEUES,
-	KFD_PREEMPT_TYPE_FILTER_DYNAMIC_QUEUES,
-	KFD_PREEMPT_TYPE_FILTER_BY_PASID
+enum kfd_unmap_queues_filter {
+	KFD_UNMAP_QUEUES_FILTER_SINGLE_QUEUE,
+	KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES,
+	KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES,
+	KFD_UNMAP_QUEUES_FILTER_BY_PASID
 };
 
 /**
@@ -401,7 +405,6 @@ struct scheduling_resources {
 struct process_queue_manager {
 	/* data */
 	struct kfd_process	*process;
-	unsigned int		num_concurrent_processes;
 	struct list_head	queues;
 	unsigned long		*queue_slot_bitmap;
 };
@@ -417,6 +420,12 @@ struct qcm_process_device {
 	unsigned int queue_count;
 	unsigned int vmid;
 	bool is_debug;
+
+	/* This flag tells if we should reset all wavefronts on
+	 * process termination
+	 */
+	bool reset_wavefronts;
+
 	/*
 	 * All the memory management data should be here too
 	 */
@@ -432,6 +441,13 @@ struct qcm_process_device {
 	uint32_t sh_hidden_private_base;
 };
 
+
+enum kfd_pdd_bound {
+	PDD_UNBOUND = 0,
+	PDD_BOUND,
+	PDD_BOUND_SUSPENDED,
+};
+
 /* Data that is per-process-per device. */
 struct kfd_process_device {
 	/*
@@ -443,6 +459,8 @@ struct kfd_process_device {
 	/* The device that owns this data. */
 	struct kfd_dev *dev;
 
+	/* The process that owns this kfd_process_device. */
+	struct kfd_process *process;
 
 	/* per-process-per device QCM data structure */
 	struct qcm_process_device qpd;
@@ -456,12 +474,14 @@ struct kfd_process_device {
 	uint64_t scratch_limit;
 
 	/* Is this process/pasid bound to this device? (amd_iommu_bind_pasid) */
-	bool bound;
+	enum kfd_pdd_bound bound;
 
-	/* This flag tells if we should reset all
-	 * wavefronts on process termination
+	/* Flag used to tell the pdd has dequeued from the dqm.
+	 * This is used to prevent dev->dqm->ops.process_termination() from
+	 * being called twice when it is already called in IOMMU callback
+	 * function.
 	 */
-	bool reset_wavefronts;
+	bool already_dequeued;
 };
 
 #define qpd_to_pdd(x) container_of(x, struct kfd_process_device, qpd)
@@ -547,8 +567,10 @@ struct kfd_process *kfd_get_process(const struct task_struct *);
 struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid);
 
 struct kfd_process_device *kfd_bind_process_to_device(struct kfd_dev *dev,
-							struct kfd_process *p);
-void kfd_unbind_process_from_device(struct kfd_dev *dev, unsigned int pasid);
+						struct kfd_process *p);
+int kfd_bind_processes_to_device(struct kfd_dev *dev);
+void kfd_unbind_processes_from_device(struct kfd_dev *dev);
+void kfd_process_iommu_unbind_callback(struct kfd_dev *dev, unsigned int pasid);
 struct kfd_process_device *kfd_get_process_device_data(struct kfd_dev *dev,
 							struct kfd_process *p);
 struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
@@ -646,14 +668,14 @@ struct process_queue_node {
 	struct list_head process_queue_list;
 };
 
+void kfd_process_dequeue_from_device(struct kfd_process_device *pdd);
+void kfd_process_dequeue_from_all_devices(struct kfd_process *p);
 int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p);
 void pqm_uninit(struct process_queue_manager *pqm);
 int pqm_create_queue(struct process_queue_manager *pqm,
 			    struct kfd_dev *dev,
 			    struct file *f,
 			    struct queue_properties *properties,
-			    unsigned int flags,
-			    enum kfd_queue_type type,
 			    unsigned int *qid);
 int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid);
 int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
@@ -663,15 +685,12 @@ struct kernel_queue *pqm_get_kernel_queue(struct process_queue_manager *pqm,
 
 int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
 				unsigned int fence_value,
-				unsigned long timeout);
+				unsigned int timeout_ms);
 
 /* Packet Manager */
 
-#define KFD_HIQ_TIMEOUT (500)
-
 #define KFD_FENCE_COMPLETED (100)
 #define KFD_FENCE_INIT   (10)
-#define KFD_UNMAP_LATENCY (150)
 
 struct packet_manager {
 	struct device_queue_manager *dqm;
@@ -690,7 +709,7 @@ int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
 				uint32_t fence_value);
 
 int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
-			enum kfd_preempt_type_filter mode,
+			enum kfd_unmap_queues_filter mode,
 			uint32_t filter_param, bool reset,
 			unsigned int sdma_engine);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 9e65ce3c1967..3ccb3b53216e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -171,12 +171,10 @@ static void kfd_process_wq_release(struct work_struct *work)
 		pr_debug("Releasing pdd (topology id %d) for process (pasid %d) in workqueue\n",
 				pdd->dev->id, p->pasid);
 
-		if (pdd->reset_wavefronts)
-			dbgdev_wave_reset_wavefronts(pdd->dev, p);
+		if (pdd->bound == PDD_BOUND)
+			amd_iommu_unbind_pasid(pdd->dev->pdev, p->pasid);
 
-		amd_iommu_unbind_pasid(pdd->dev->pdev, p->pasid);
 		list_del(&pdd->per_device_list);
-
 		kfree(pdd);
 	}
 
@@ -236,24 +234,17 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
 
 	mutex_lock(&p->mutex);
 
-	/* In case our notifier is called before IOMMU notifier */
+	kfd_process_dequeue_from_all_devices(p);
 	pqm_uninit(&p->pqm);
 
 	/* Iterate over all process device data structure and check
-	 * if we should delete debug managers and reset all wavefronts
+	 * if we should delete debug managers
 	 */
-	list_for_each_entry(pdd, &p->per_device_data, per_device_list) {
+	list_for_each_entry(pdd, &p->per_device_data, per_device_list)
 		if ((pdd->dev->dbgmgr) &&
 				(pdd->dev->dbgmgr->pasid == p->pasid))
 			kfd_dbgmgr_destroy(pdd->dev->dbgmgr);
 
-		if (pdd->reset_wavefronts) {
-			pr_warn("Resetting all wave fronts\n");
-			dbgdev_wave_reset_wavefronts(pdd->dev, p);
-			pdd->reset_wavefronts = false;
-		}
-	}
-
 	mutex_unlock(&p->mutex);
 
 	/*
@@ -351,9 +342,9 @@ struct kfd_process_device *kfd_get_process_device_data(struct kfd_dev *dev,
 
 	list_for_each_entry(pdd, &p->per_device_data, per_device_list)
 		if (pdd->dev == dev)
-			break;
+			return pdd;
 
-	return pdd;
+	return NULL;
 }
 
 struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
@@ -367,7 +358,9 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
 		INIT_LIST_HEAD(&pdd->qpd.queues_list);
 		INIT_LIST_HEAD(&pdd->qpd.priv_queue_list);
 		pdd->qpd.dqm = dev->dqm;
-		pdd->reset_wavefronts = false;
+		pdd->process = p;
+		pdd->bound = PDD_UNBOUND;
+		pdd->already_dequeued = false;
 		list_add(&pdd->per_device_list, &p->per_device_data);
 	}
 
@@ -393,19 +386,91 @@ struct kfd_process_device *kfd_bind_process_to_device(struct kfd_dev *dev,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	if (pdd->bound)
+	if (pdd->bound == PDD_BOUND) {
 		return pdd;
+	} else if (unlikely(pdd->bound == PDD_BOUND_SUSPENDED)) {
+		pr_err("Binding PDD_BOUND_SUSPENDED pdd is unexpected!\n");
+		return ERR_PTR(-EINVAL);
+	}
 
 	err = amd_iommu_bind_pasid(dev->pdev, p->pasid, p->lead_thread);
 	if (err < 0)
 		return ERR_PTR(err);
 
-	pdd->bound = true;
+	pdd->bound = PDD_BOUND;
 
 	return pdd;
 }
 
-void kfd_unbind_process_from_device(struct kfd_dev *dev, unsigned int pasid)
+/*
+ * Bind processes do the device that have been temporarily unbound
+ * (PDD_BOUND_SUSPENDED) in kfd_unbind_processes_from_device.
+ */
+int kfd_bind_processes_to_device(struct kfd_dev *dev)
+{
+	struct kfd_process_device *pdd;
+	struct kfd_process *p;
+	unsigned int temp;
+	int err = 0;
+
+	int idx = srcu_read_lock(&kfd_processes_srcu);
+
+	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
+		mutex_lock(&p->mutex);
+		pdd = kfd_get_process_device_data(dev, p);
+		if (pdd->bound != PDD_BOUND_SUSPENDED) {
+			mutex_unlock(&p->mutex);
+			continue;
+		}
+
+		err = amd_iommu_bind_pasid(dev->pdev, p->pasid,
+				p->lead_thread);
+		if (err < 0) {
+			pr_err("unexpected pasid %d binding failure\n",
+					p->pasid);
+			mutex_unlock(&p->mutex);
+			break;
+		}
+
+		pdd->bound = PDD_BOUND;
+		mutex_unlock(&p->mutex);
+	}
+
+	srcu_read_unlock(&kfd_processes_srcu, idx);
+
+	return err;
+}
+
+/*
+ * Temporarily unbind currently bound processes from the device and
+ * mark them as PDD_BOUND_SUSPENDED. These processes will be restored
+ * to PDD_BOUND state in kfd_bind_processes_to_device.
+ */
+void kfd_unbind_processes_from_device(struct kfd_dev *dev)
+{
+	struct kfd_process_device *pdd;
+	struct kfd_process *p;
+	unsigned int temp, temp_bound, temp_pasid;
+
+	int idx = srcu_read_lock(&kfd_processes_srcu);
+
+	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
+		mutex_lock(&p->mutex);
+		pdd = kfd_get_process_device_data(dev, p);
+		temp_bound = pdd->bound;
+		temp_pasid = p->pasid;
+		if (pdd->bound == PDD_BOUND)
+			pdd->bound = PDD_BOUND_SUSPENDED;
+		mutex_unlock(&p->mutex);
+
+		if (temp_bound == PDD_BOUND)
+			amd_iommu_unbind_pasid(dev->pdev, temp_pasid);
+	}
+
+	srcu_read_unlock(&kfd_processes_srcu, idx);
+}
+
+void kfd_process_iommu_unbind_callback(struct kfd_dev *dev, unsigned int pasid)
 {
 	struct kfd_process *p;
 	struct kfd_process_device *pdd;
@@ -424,28 +489,12 @@ void kfd_unbind_process_from_device(struct kfd_dev *dev, unsigned int pasid)
 	if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid))
 		kfd_dbgmgr_destroy(dev->dbgmgr);
 
-	pqm_uninit(&p->pqm);
-
 	pdd = kfd_get_process_device_data(dev, p);
-
-	if (!pdd) {
-		mutex_unlock(&p->mutex);
-		return;
-	}
-
-	if (pdd->reset_wavefronts) {
-		dbgdev_wave_reset_wavefronts(pdd->dev, p);
-		pdd->reset_wavefronts = false;
-	}
-
-	/*
-	 * Just mark pdd as unbound, because we still need it
-	 * to call amd_iommu_unbind_pasid() in when the
-	 * process exits.
-	 * We don't call amd_iommu_unbind_pasid() here
-	 * because the IOMMU called us.
-	 */
-	pdd->bound = false;
+	if (pdd)
+		/* For GPU relying on IOMMU, we need to dequeue here
+		 * when PASID is still bound.
+		 */
+		kfd_process_dequeue_from_device(pdd);
 
 	mutex_unlock(&p->mutex);
 }
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 03bec765b03d..5129dc139219 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -63,6 +63,25 @@ static int find_available_queue_slot(struct process_queue_manager *pqm,
 	return 0;
 }
 
+void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
+{
+	struct kfd_dev *dev = pdd->dev;
+
+	if (pdd->already_dequeued)
+		return;
+
+	dev->dqm->ops.process_termination(dev->dqm, &pdd->qpd);
+	pdd->already_dequeued = true;
+}
+
+void kfd_process_dequeue_from_all_devices(struct kfd_process *p)
+{
+	struct kfd_process_device *pdd;
+
+	list_for_each_entry(pdd, &p->per_device_data, per_device_list)
+		kfd_process_dequeue_from_device(pdd);
+}
+
 int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p)
 {
 	INIT_LIST_HEAD(&pqm->queues);
@@ -78,21 +97,14 @@ int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p)
 
 void pqm_uninit(struct process_queue_manager *pqm)
 {
-	int retval;
 	struct process_queue_node *pqn, *next;
 
 	list_for_each_entry_safe(pqn, next, &pqm->queues, process_queue_list) {
-		retval = pqm_destroy_queue(
-				pqm,
-				(pqn->q != NULL) ?
-					pqn->q->properties.queue_id :
-					pqn->kq->queue->properties.queue_id);
-
-		if (retval != 0) {
-			pr_err("failed to destroy queue\n");
-			return;
-		}
+		uninit_queue(pqn->q);
+		list_del(&pqn->process_queue_list);
+		kfree(pqn);
 	}
+
 	kfree(pqm->queue_slot_bitmap);
 	pqm->queue_slot_bitmap = NULL;
 }
@@ -130,20 +142,16 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			    struct kfd_dev *dev,
 			    struct file *f,
 			    struct queue_properties *properties,
-			    unsigned int flags,
-			    enum kfd_queue_type type,
 			    unsigned int *qid)
 {
 	int retval;
 	struct kfd_process_device *pdd;
-	struct queue_properties q_properties;
 	struct queue *q;
 	struct process_queue_node *pqn;
 	struct kernel_queue *kq;
-	int num_queues = 0;
-	struct queue *cur;
+	enum kfd_queue_type type = properties->type;
+	unsigned int max_queues = 127; /* HWS limit */
 
-	memcpy(&q_properties, properties, sizeof(struct queue_properties));
 	q = NULL;
 	kq = NULL;
 
@@ -159,13 +167,11 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 	 * If we are just about to create DIQ, the is_debug flag is not set yet
 	 * Hence we also check the type as well
 	 */
-	if ((pdd->qpd.is_debug) ||
-		(type == KFD_QUEUE_TYPE_DIQ)) {
-		list_for_each_entry(cur, &pdd->qpd.queues_list, list)
-			num_queues++;
-		if (num_queues >= dev->device_info->max_no_of_hqd/2)
-			return -ENOSPC;
-	}
+	if ((pdd->qpd.is_debug) || (type == KFD_QUEUE_TYPE_DIQ))
+		max_queues = dev->device_info->max_no_of_hqd/2;
+
+	if (pdd->qpd.queue_count >= max_queues)
+		return -ENOSPC;
 
 	retval = find_available_queue_slot(pqm, qid);
 	if (retval != 0)
@@ -187,14 +193,14 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 	case KFD_QUEUE_TYPE_COMPUTE:
 		/* check if there is over subscription */
 		if ((sched_policy == KFD_SCHED_POLICY_HWS_NO_OVERSUBSCRIPTION) &&
-		((dev->dqm->processes_count >= VMID_PER_DEVICE) ||
+		((dev->dqm->processes_count >= dev->vm_info.vmid_num_kfd) ||
 		(dev->dqm->queue_count >= get_queues_num(dev->dqm)))) {
 			pr_err("Over-subscription is not allowed in radeon_kfd.sched_policy == 1\n");
 			retval = -EPERM;
 			goto err_create_queue;
 		}
 
-		retval = create_cp_queue(pqm, dev, &q, &q_properties, f, *qid);
+		retval = create_cp_queue(pqm, dev, &q, properties, f, *qid);
 		if (retval != 0)
 			goto err_create_queue;
 		pqn->q = q;
@@ -231,9 +237,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 	list_add(&pqn->process_queue_list, &pqm->queues);
 
 	if (q) {
-		*properties = q->properties;
 		pr_debug("PQM done creating queue\n");
-		print_queue_properties(properties);
+		print_queue_properties(&q->properties);
 	}
 
 	return retval;
@@ -290,9 +295,6 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 	if (pqn->q) {
 		dqm = pqn->q->device->dqm;
 		retval = dqm->ops.destroy_queue(dqm, &pdd->qpd, pqn->q);
-		if (retval != 0)
-			return retval;
-
 		uninit_queue(pqn->q);
 	}