drm/amdgpu: Fix NULL dereference in amdgpu_userq_restore_worker

Switch cancel_delayed_work() to cancel_delayed_work_sync() to ensure
the delayed work has finished executing before proceeding with
resource cleanup. This prevents a potential use-after-free or
NULL dereference if the resume_work is still running during finalization.

BUG: kernel NULL pointer dereference, address: 0000000000000140
[  +0.000050] #PF: supervisor read access in kernel mode
[  +0.000019] #PF: error_code(0x0000) - not-present page
[  +0.000021] PGD 0 P4D 0
[  +0.000015] Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
[  +0.000021] CPU: 17 UID: 0 PID: 196299 Comm: kworker/17:0 Tainted: G     U             6.14.0-org-staging #1
[  +0.000032] Tainted: [U]=USER
[  +0.000015] Hardware name: Gigabyte Technology Co., Ltd. X570 AORUS ELITE/X570 AORUS ELITE, BIOS F39 03/22/2024
[  +0.000029] Workqueue: events amdgpu_userq_restore_worker [amdgpu]
[  +0.000426] RIP: 0010:drm_exec_lock_obj+0x32/0x210 [drm_exec]
[  +0.000025] Code: e5 41 57 41 56 41 55 49 89 f5 41 54 49 89 fc 48 83 ec 08 4c 8b 77 30 4d 85 f6 0f 85 c0 00 00 00 4c 8d 7f 08 48 39 77 38 74 54 <49> 8b bd f8 00 00 00 4c 89 fe 41 f6 04 24 01 75 3c e8 08 50 bc e0
[  +0.000046] RSP: 0018:ffffab1b04da3ce8 EFLAGS: 00010297
[  +0.000020] RAX: 0000000000000001 RBX: ffff930cc60e4bc0 RCX: 0000000000000000
[  +0.000025] RDX: 0000000000000004 RSI: 0000000000000048 RDI: ffffab1b04da3d88
[  +0.000028] RBP: ffffab1b04da3d10 R08: ffff930cc60e4000 R09: 0000000000000000
[  +0.000022] R10: ffffab1b04da3d18 R11: 0000000000000001 R12: ffffab1b04da3d88
[  +0.000023] R13: 0000000000000048 R14: 0000000000000000 R15: ffffab1b04da3d90
[  +0.000023] FS:  0000000000000000(0000) GS:ffff9313dea80000(0000) knlGS:0000000000000000
[  +0.000024] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  +0.000021] CR2: 0000000000000140 CR3: 000000018351a000 CR4: 0000000000350ef0
[  +0.000025] Call Trace:
[  +0.000018]  <TASK>
[  +0.000015]  ? show_regs+0x69/0x80
[  +0.000022]  ? __die+0x25/0x70
[  +0.000019]  ? page_fault_oops+0x15d/0x510
[  +0.000024]  ? do_user_addr_fault+0x312/0x690
[  +0.000024]  ? sched_clock_cpu+0x10/0x1a0
[  +0.000028]  ? exc_page_fault+0x78/0x1b0
[  +0.000025]  ? asm_exc_page_fault+0x27/0x30
[  +0.000024]  ? drm_exec_lock_obj+0x32/0x210 [drm_exec]
[  +0.000024]  drm_exec_prepare_obj+0x21/0x60 [drm_exec]
[  +0.000021]  amdgpu_vm_lock_pd+0x22/0x30 [amdgpu]
[  +0.000266]  amdgpu_userq_validate_bos+0x6c/0x320 [amdgpu]
[  +0.000333]  amdgpu_userq_restore_worker+0x4a/0x120 [amdgpu]
[  +0.000316]  process_one_work+0x189/0x3c0
[  +0.000021]  worker_thread+0x2a4/0x3b0
[  +0.000022]  kthread+0x109/0x220
[  +0.000018]  ? __pfx_worker_thread+0x10/0x10
[  +0.000779]  ? _raw_spin_unlock_irq+0x1f/0x40
[  +0.000560]  ? __pfx_kthread+0x10/0x10
[  +0.000543]  ret_from_fork+0x3c/0x60
[  +0.000507]  ? __pfx_kthread+0x10/0x10
[  +0.000515]  ret_from_fork_asm+0x1a/0x30
[  +0.000515]  </TASK>

v2: Replace cancel_delayed_work() to cancel_delayed_work_sync()
    in amdgpu_userq_destroy() and amdgpu_userq_evict().

Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Arvind Yadav <arvind.yadav@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 394b036be1d9e59e91a08c8d5588f549b94191d9..ac3ab4cc8e5a43e75f1a09585917c417ef0345b3 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -301,7 +301,7 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
        struct amdgpu_usermode_queue *queue;
        int r = 0;
 
-       cancel_delayed_work(&uq_mgr->resume_work);
+       cancel_delayed_work_sync(&uq_mgr->resume_work);
        mutex_lock(&uq_mgr->userq_mutex);
 
        queue = amdgpu_userq_find(uq_mgr, queue_id);
@@ -746,7 +746,7 @@ amdgpu_userq_evict(struct amdgpu_userq_mgr *uq_mgr,
        amdgpu_eviction_fence_signal(evf_mgr, ev_fence);
 
        if (evf_mgr->fd_closing) {
-               cancel_delayed_work(&uq_mgr->resume_work);
+               cancel_delayed_work_sync(&uq_mgr->resume_work);
                return;
        }
 
@@ -777,7 +777,7 @@ void amdgpu_userq_mgr_fini(struct amdgpu_userq_mgr *userq_mgr)
        struct amdgpu_userq_mgr *uqm, *tmp;
        uint32_t queue_id;
 
-       cancel_delayed_work(&userq_mgr->resume_work);
+       cancel_delayed_work_sync(&userq_mgr->resume_work);
 
        mutex_lock(&userq_mgr->userq_mutex);
        idr_for_each_entry(&userq_mgr->userq_idr, queue, queue_id) {