From d7e8ddc392a3659206e7973e75c47849f2c8b72a Mon Sep 17 00:00:00 2001 From: Harish Kasiviswanathan Date: Tue, 26 Mar 2024 15:32:46 -0400 Subject: [PATCH] drm/amdkfd: Reset GPU on queue preemption failure Currently, with F32 HWS GPU reset is only when unmap queue fails. However, if compute queue doesn't repond to preemption request in time unmap will return without any error. In this case, only preemption error is logged and Reset is not triggered. Call GPU reset in this case also. Reviewed-by: Alex Deucher Signed-off-by: Harish Kasiviswanathan Reviewed-by: Mukul Joshi Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 1 + 1 file changed, 1 insertion(+) 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 151fabf84040..c08b6ee25289 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -2000,6 +2000,7 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, if (mqd_mgr->check_preemption_failed(mqd_mgr, dqm->packet_mgr.priv_queue->queue->mqd)) { while (halt_if_hws_hang) schedule(); + kfd_hws_hang(dqm); return -ETIME; } -- 2.49.0