accel/amdxdna: Fix notifier_wq lifetime race during device removal

amdxdna_remove() destroys notifier_wq. If amdxdna_gem_obj_free() is
called after device removal, it may attempt to flush notifier_wq,
resulting in a use-after-free.

Fix the race by allocating notifier_wq with
drmm_alloc_ordered_workqueue(), so its lifetime is managed by DRM and
remains valid until all managed resources are released.

Fixes: e486147c91 ("accel/amdxdna: Add BO import and export")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260611055150.3070216-2-lizhi.hou@amd.com
This commit is contained in:
Lizhi Hou
2026-06-10 22:51:49 -07:00
parent 1dbbc7f98c
commit 5c72124186

View File

@@ -392,9 +392,9 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (ret)
return ret;
xdna->notifier_wq = alloc_ordered_workqueue("notifier_wq", WQ_MEM_RECLAIM);
if (!xdna->notifier_wq) {
ret = -ENOMEM;
xdna->notifier_wq = drmm_alloc_ordered_workqueue(ddev, "notifier_wq", WQ_MEM_RECLAIM);
if (IS_ERR(xdna->notifier_wq)) {
ret = PTR_ERR(xdna->notifier_wq);
goto iommu_fini;
}
@@ -403,7 +403,7 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id)
mutex_unlock(&xdna->dev_lock);
if (ret) {
XDNA_ERR(xdna, "Hardware init failed, ret %d", ret);
goto destroy_notifier_wq;
goto iommu_fini;
}
ret = amdxdna_sysfs_init(xdna);
@@ -427,8 +427,6 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id)
mutex_lock(&xdna->dev_lock);
xdna->dev_info->ops->fini(xdna);
mutex_unlock(&xdna->dev_lock);
destroy_notifier_wq:
destroy_workqueue(xdna->notifier_wq);
iommu_fini:
amdxdna_iommu_fini(xdna);
return ret;
@@ -439,8 +437,6 @@ static void amdxdna_remove(struct pci_dev *pdev)
struct amdxdna_dev *xdna = pci_get_drvdata(pdev);
struct amdxdna_client *client;
destroy_workqueue(xdna->notifier_wq);
drm_dev_unplug(&xdna->ddev);
amdxdna_sysfs_fini(xdna);