3 files changed, 34 insertions, 11 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index bdc01ca9609a..5c8d81bfce7a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -509,10 +509,19 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 	start = start_mgr << PAGE_SHIFT;
 	end = (last_mgr + 1) << PAGE_SHIFT;
 
+	r = amdgpu_amdkfd_reserve_mem_limit(node->adev,
+					prange->npages * PAGE_SIZE,
+					KFD_IOC_ALLOC_MEM_FLAGS_VRAM,
+					node->xcp ? node->xcp->id : 0);
+	if (r) {
+		dev_dbg(node->adev->dev, "failed to reserve VRAM, r: %ld\n", r);
+		return -ENOSPC;
+	}
+
 	r = svm_range_vram_node_new(node, prange, true);
 	if (r) {
 		dev_dbg(node->adev->dev, "fail %ld to alloc vram\n", r);
-		return r;
+		goto out;
 	}
 	ttm_res_offset = (start_mgr - prange->start + prange->offset) << PAGE_SHIFT;
 
@@ -545,6 +554,11 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 		svm_range_vram_node_free(prange);
 	}
 
+out:
+	amdgpu_amdkfd_unreserve_mem_limit(node->adev,
+					prange->npages * PAGE_SIZE,
+					KFD_IOC_ALLOC_MEM_FLAGS_VRAM,
+					node->xcp ? node->xcp->id : 0);
 	return r < 0 ? r : 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 717a60d7a4ea..451bb058cc62 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -819,9 +819,9 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
 	mutex_lock(&kfd_processes_mutex);
 
 	if (kfd_is_locked()) {
-		mutex_unlock(&kfd_processes_mutex);
 		pr_debug("KFD is locked! Cannot create process");
-		return ERR_PTR(-EINVAL);
+		process = ERR_PTR(-EINVAL);
+		goto out;
 	}
 
 	/* A prior open of /dev/kfd could have already created the process. */
@@ -829,6 +829,14 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
 	if (process) {
 		pr_debug("Process already found\n");
 	} else {
+		/* If the process just called exec(3), it is possible that the
+		 * cleanup of the kfd_process (following the release of the mm
+		 * of the old process image) is still in the cleanup work queue.
+		 * Make sure to drain any job before trying to recreate any
+		 * resource for this process.
+		 */
+		flush_workqueue(kfd_process_wq);
+
 		process = create_process(thread);
 		if (IS_ERR(process))
 			goto out;
@@ -1922,6 +1930,8 @@ static int signal_eviction_fence(struct kfd_process *p)
 	rcu_read_lock();
 	ef = dma_fence_get_rcu_safe(&p->ef);
 	rcu_read_unlock();
+	if (!ef)
+		return -EINVAL;
 
 	ret = dma_fence_signal(ef);
 	dma_fence_put(ef);
@@ -1949,10 +1959,9 @@ static void evict_process_worker(struct work_struct *work)
 		 * they are responsible stopping the queues and scheduling
 		 * the restore work.
 		 */
-		if (!signal_eviction_fence(p))
-			queue_delayed_work(kfd_restore_wq, &p->restore_work,
-				msecs_to_jiffies(PROCESS_RESTORE_TIME_MS));
-		else
+		if (signal_eviction_fence(p) ||
+		    mod_delayed_work(kfd_restore_wq, &p->restore_work,
+				     msecs_to_jiffies(PROCESS_RESTORE_TIME_MS)))
 			kfd_process_restore_queues(p);
 
 		pr_debug("Finished evicting pasid 0x%x\n", p->pasid);
@@ -2011,9 +2020,9 @@ static void restore_process_worker(struct work_struct *work)
 	if (ret) {
 		pr_debug("Failed to restore BOs of pasid 0x%x, retry after %d ms\n",
 			 p->pasid, PROCESS_BACK_OFF_TIME_MS);
-		ret = queue_delayed_work(kfd_restore_wq, &p->restore_work,
-				msecs_to_jiffies(PROCESS_BACK_OFF_TIME_MS));
-		WARN(!ret, "reschedule restore work failed\n");
+		if (mod_delayed_work(kfd_restore_wq, &p->restore_work,
+				     msecs_to_jiffies(PROCESS_RESTORE_TIME_MS)))
+			kfd_process_restore_queues(p);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index f0f7f48af413..386875e6eb96 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3426,7 +3426,7 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
 				mm, KFD_MIGRATE_TRIGGER_PREFETCH);
 	*migrated = !r;
 
-	return r;
+	return 0;
 }
 
 int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)