iavf: Fix a locking bug in an error path

If the netdev lock has been obtained, unlock it before returning.
This bug has been detected by the Clang thread-safety analyzer.

Fixes: afc664987ab3 ("eth: iavf: extend the netdev_lock usage")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20250206175114.1974171-28-bvanassche@acm.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 2d7a18fcc3be436ac263f7cb13109756a48db3fa..852e5b62f0a5dc038c0e5c0f76541870e69384ac 100644 (file)
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2903,8 +2903,8 @@ static void iavf_watchdog_task(struct work_struct *work)
        }
 
        mutex_unlock(&adapter->crit_lock);
-       netdev_unlock(netdev);
 restart_watchdog:
+       netdev_unlock(netdev);
        if (adapter->state >= __IAVF_DOWN)
                queue_work(adapter->wq, &adapter->adminq_task);
        if (adapter->aq_required)