3 files changed, 29 insertions, 58 deletions

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 6c5c7c1bf5ed..6e7bc983fc0b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1209,6 +1209,15 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 	pr_debug_ratelimited("Evicting process pid %d queues\n",
 			    pdd->process->lead_thread->pid);
 
+	if (dqm->dev->kfd->shared_resources.enable_mes) {
+		pdd->last_evict_timestamp = get_jiffies_64();
+		retval = suspend_all_queues_mes(dqm);
+		if (retval) {
+			dev_err(dev, "Suspending all queues failed");
+			goto out;
+		}
+	}
+
 	/* Mark all queues as evicted. Deactivate all active queues on
 	 * the qpd.
 	 */
@@ -1221,23 +1230,27 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 		decrement_queue_count(dqm, qpd, q);
 
 		if (dqm->dev->kfd->shared_resources.enable_mes) {
-			int err;
-
-			err = remove_queue_mes(dqm, q, qpd);
-			if (err) {
+			retval = remove_queue_mes(dqm, q, qpd);
+			if (retval) {
 				dev_err(dev, "Failed to evict queue %d\n",
 					q->properties.queue_id);
-				retval = err;
+				goto out;
 			}
 		}
 	}
-	pdd->last_evict_timestamp = get_jiffies_64();
-	if (!dqm->dev->kfd->shared_resources.enable_mes)
+
+	if (!dqm->dev->kfd->shared_resources.enable_mes) {
+		pdd->last_evict_timestamp = get_jiffies_64();
 		retval = execute_queues_cpsch(dqm,
 					      qpd->is_debug ?
 					      KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES :
 					      KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0,
 					      USE_DEFAULT_GRACE_PERIOD);
+	} else {
+		retval = resume_all_queues_mes(dqm);
+		if (retval)
+			dev_err(dev, "Resuming all queues failed");
+	}
 
 out:
 	dqm_unlock(dqm);
@@ -3098,61 +3111,17 @@ out:
 	return ret;
 }
 
-static int kfd_dqm_evict_pasid_mes(struct device_queue_manager *dqm,
-				   struct qcm_process_device *qpd)
-{
-	struct device *dev = dqm->dev->adev->dev;
-	int ret = 0;
-
-	/* Check if process is already evicted */
-	dqm_lock(dqm);
-	if (qpd->evicted) {
-		/* Increment the evicted count to make sure the
-		 * process stays evicted before its terminated.
-		 */
-		qpd->evicted++;
-		dqm_unlock(dqm);
-		goto out;
-	}
-	dqm_unlock(dqm);
-
-	ret = suspend_all_queues_mes(dqm);
-	if (ret) {
-		dev_err(dev, "Suspending all queues failed");
-		goto out;
-	}
-
-	ret = dqm->ops.evict_process_queues(dqm, qpd);
-	if (ret) {
-		dev_err(dev, "Evicting process queues failed");
-		goto out;
-	}
-
-	ret = resume_all_queues_mes(dqm);
-	if (ret)
-		dev_err(dev, "Resuming all queues failed");
-
-out:
-	return ret;
-}
-
 int kfd_evict_process_device(struct kfd_process_device *pdd)
 {
 	struct device_queue_manager *dqm;
 	struct kfd_process *p;
-	int ret = 0;
 
 	p = pdd->process;
 	dqm = pdd->dev->dqm;
 
 	WARN(debug_evictions, "Evicting pid %d", p->lead_thread->pid);
 
-	if (dqm->dev->kfd->shared_resources.enable_mes)
-		ret = kfd_dqm_evict_pasid_mes(dqm, &pdd->qpd);
-	else
-		ret = dqm->ops.evict_process_queues(dqm, &pdd->qpd);
-
-	return ret;
+	return dqm->ops.evict_process_queues(dqm, &pdd->qpd);
 }
 
 int reserve_debug_trap_vmid(struct device_queue_manager *dqm,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index a65c67cf56ff..f1e7583650c4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -297,16 +297,16 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
 		goto out_err_unreserve;
 	}
 
-	if (properties->ctx_save_restore_area_size != topo_dev->node_props.cwsr_size) {
-		pr_debug("queue cwsr size 0x%x not equal to node cwsr size 0x%x\n",
+	if (properties->ctx_save_restore_area_size < topo_dev->node_props.cwsr_size) {
+		pr_debug("queue cwsr size 0x%x not sufficient for node cwsr size 0x%x\n",
 			properties->ctx_save_restore_area_size,
 			topo_dev->node_props.cwsr_size);
 		err = -EINVAL;
 		goto out_err_unreserve;
 	}
 
-	total_cwsr_size = (topo_dev->node_props.cwsr_size + topo_dev->node_props.debug_memory_size)
-			  * NUM_XCC(pdd->dev->xcc_mask);
+	total_cwsr_size = (properties->ctx_save_restore_area_size +
+			   topo_dev->node_props.debug_memory_size) * NUM_XCC(pdd->dev->xcc_mask);
 	total_cwsr_size = ALIGN(total_cwsr_size, PAGE_SIZE);
 
 	err = kfd_queue_buffer_get(vm, (void *)properties->ctx_save_restore_area_address,
@@ -352,8 +352,8 @@ int kfd_queue_release_buffers(struct kfd_process_device *pdd, struct queue_prope
 	topo_dev = kfd_topology_device_by_id(pdd->dev->id);
 	if (!topo_dev)
 		return -EINVAL;
-	total_cwsr_size = (topo_dev->node_props.cwsr_size + topo_dev->node_props.debug_memory_size)
-			  * NUM_XCC(pdd->dev->xcc_mask);
+	total_cwsr_size = (properties->ctx_save_restore_area_size +
+			   topo_dev->node_props.debug_memory_size) * NUM_XCC(pdd->dev->xcc_mask);
 	total_cwsr_size = ALIGN(total_cwsr_size, PAGE_SIZE);
 
 	kfd_queue_buffer_svm_put(pdd, properties->ctx_save_restore_area_address, total_cwsr_size);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 9d72411c3379..74a1d3e1d52b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3687,6 +3687,8 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm,
 		svm_range_apply_attrs(p, prange, nattr, attrs, &update_mapping);
 		/* TODO: unmap ranges from GPU that lost access */
 	}
+	update_mapping |= !p->xnack_enabled && !list_empty(&remap_list);
+
 	list_for_each_entry_safe(prange, next, &remove_list, update_list) {
 		pr_debug("unlink old 0x%p prange 0x%p [0x%lx 0x%lx]\n",
 			 prange->svms, prange, prange->start,