From: Jonathan Kim Date: Thu, 22 Aug 2024 14:44:39 +0000 (-0400) Subject: drm/amdkfd: fix missed queue reset on queue destroy X-Git-Tag: v6.12-rc1~126^2~1^2~18 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=101025e94b537e8b5426c73a985b26fc95c199cb;p=thirdparty%2Fkernel%2Flinux.git drm/amdkfd: fix missed queue reset on queue destroy If a queue is being destroyed but causes a HWS hang on removal, the KFD may issue an unnecessary gpu reset if the destroyed queue can be fixed by a queue reset. This is because the queue has been removed from the KFD's queue list prior to the preemption action on destroy so the reset call will fail to match the HQD PQ reset information against the KFD's queue record to do the actual reset. To fix this, deactivate the queue prior to preemption since it's being destroyed anyways and remove the queue from the KFD's queue list after preemption. Signed-off-by: Jonathan Kim Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- 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 577d121cc6d1a..71b465f8d83ee 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -2407,10 +2407,9 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, pdd->sdma_past_activity_counter += sdma_val; } - list_del(&q->list); - qpd->queue_count--; if (q->properties.is_active) { decrement_queue_count(dqm, qpd, q); + q->properties.is_active = false; if (!dqm->dev->kfd->shared_resources.enable_mes) { retval = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0, @@ -2421,6 +2420,8 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, retval = remove_queue_mes(dqm, q, qpd); } } + list_del(&q->list); + qpd->queue_count--; /* * Unconditionally decrement this counter, regardless of the queue's