From 0132ba7ff0f613915d332a30fcf14cf66e317f98 Mon Sep 17 00:00:00 2001 From: "Jesse.Zhang" Date: Thu, 15 May 2025 15:02:13 +0800 Subject: [PATCH] drm/amdgpu: Fix eviction fence worker race during fd close MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit The current cleanup order during file descriptor close can lead to a race condition where the eviction fence worker attempts to access a destroyed mutex from the user queue manager: [ 517.294055] DEBUG_LOCKS_WARN_ON(lock->magic != lock) [ 517.294060] WARNING: CPU: 8 PID: 2030 at kernel/locking/mutex.c:564 [ 517.294094] Workqueue: events amdgpu_eviction_fence_suspend_worker [amdgpu] The issue occurs because: 1. We destroy the user queue manager (including its mutex) first 2. Then try to destroy eviction fences which may have pending work 3. The eviction fence worker may try to access the already-destroyed mutex Fix this by reordering the cleanup to: 1. First mark the fd as closing and destroy eviction fences, which flushes any pending work 2. Then safely destroy the user queue manager after we're certain no more fence work will be executed The copy in amdgpu_driver_postclose_kms() needs to be removed (Christian) Reviewed-by: Christian König Reviewed-by: Prike Liang Reviewed-by: Arvind Yadav Signed-off-by: Jesse Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 5 ----- 2 files changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 4ddd08ce8885..4db92e0a60da 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2913,8 +2913,8 @@ static int amdgpu_drm_release(struct inode *inode, struct file *filp) if (fpriv) { fpriv->evf_mgr.fd_closing = true; - amdgpu_userq_mgr_fini(&fpriv->userq_mgr); amdgpu_eviction_fence_destroy(&fpriv->evf_mgr); + amdgpu_userq_mgr_fini(&fpriv->userq_mgr); } return drm_release(inode, filp); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 9fbb04aee97b..d2ce7d86dbc8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -1502,11 +1502,6 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev, amdgpu_bo_unreserve(pd); } - if (!fpriv->evf_mgr.fd_closing) { - fpriv->evf_mgr.fd_closing = true; - amdgpu_userq_mgr_fini(&fpriv->userq_mgr); - amdgpu_eviction_fence_destroy(&fpriv->evf_mgr); - } amdgpu_ctx_mgr_fini(&fpriv->ctx_mgr); amdgpu_vm_fini(adev, &fpriv->vm); -- 2.47.2