From 8fd8bae4cb99352d2d8ae29a9eb0551fb77b2b43 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Thu, 20 Feb 2025 16:02:13 -0500 Subject: [PATCH] drm/amdkfd: Fix pqm_destroy_queue race with GPU reset [ Upstream commit 7919b4cad5545ed93778f11881ceee72e4dbed66 ] If GPU in reset, destroy_queue return -EIO, pqm_destroy_queue should delete the queue from process_queue_list and free the resource. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 43c07ac2c6fce..cabe0012ab5b1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -384,7 +384,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) pr_err("Pasid 0x%x destroy queue %d failed, ret %d\n", pqm->process->pasid, pqn->q->properties.queue_id, retval); - if (retval != -ETIME) + if (retval != -ETIME && retval != -EIO) goto err_destroy_queue; } -- 2.47.3