From 22d9e071e5028815accf26956ed0b9634a4c0b8d Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Wed, 15 Oct 2025 15:17:54 -0400 Subject: [PATCH] drm/amdkfd: Dequeue user queues when process mm released Move dequeue user queues and destroy user queues from kfd_process_wq_release to mmu notifier release callback, to ensure no system memory access from GPU because the process memory is going to free from CPU after mmu release notifier callback returns. Destroy queue releases the svm prange queue_refcount, this also removes fake flase positive warning message "Freeing queue vital buffer" message if application crash or killed. Suggested-by: Felix Kuehling Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index ddfe30c13e9d6..f5d173f1ca3b5 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1162,9 +1162,6 @@ static void kfd_process_wq_release(struct work_struct *work) release_work); struct dma_fence *ef; - kfd_process_dequeue_from_all_devices(p); - pqm_uninit(&p->pqm); - /* * If GPU in reset, user queues may still running, wait for reset complete. */ @@ -1226,6 +1223,14 @@ static void kfd_process_notifier_release_internal(struct kfd_process *p) cancel_delayed_work_sync(&p->eviction_work); cancel_delayed_work_sync(&p->restore_work); + /* + * Dequeue and destroy user queues, it is not safe for GPU to access + * system memory after mmu release notifier callback returns because + * exit_mmap free process memory afterwards. + */ + kfd_process_dequeue_from_all_devices(p); + pqm_uninit(&p->pqm); + for (i = 0; i < p->n_pdds; i++) { struct kfd_process_device *pdd = p->pdds[i]; -- 2.47.3