From 556699341efa98243e08e34401b3f601da91f5a3 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Thu, 3 Sep 2020 14:28:54 -0400 Subject: [PATCH] tg3: Fix soft lockup when tg3_reset_task() fails. If tg3_reset_task() fails, the device state is left in an inconsistent state with IFF_RUNNING still set but NAPI state not enabled. A subsequent operation, such as ifdown or AER error can cause it to soft lock up when it tries to disable NAPI state. Fix it by bringing down the device to !IFF_RUNNING state when tg3_reset_task() fails. tg3_reset_task() running from workqueue will now call tg3_close() when the reset fails. We need to modify tg3_reset_task_cancel() slightly to avoid tg3_close() calling cancel_work_sync() to cancel tg3_reset_task(). Otherwise cancel_work_sync() will wait forever for tg3_reset_task() to finish. Reported-by: David Christensen Reported-by: Baptiste Covolato Fixes: db2199737990 ("tg3: Schedule at most one tg3_reset_task run") Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/tg3.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index ebff1fc0d8ce..4515804d1ce4 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -7221,8 +7221,8 @@ static inline void tg3_reset_task_schedule(struct tg3 *tp) static inline void tg3_reset_task_cancel(struct tg3 *tp) { - cancel_work_sync(&tp->reset_task); - tg3_flag_clear(tp, RESET_TASK_PENDING); + if (test_and_clear_bit(TG3_FLAG_RESET_TASK_PENDING, tp->tg3_flags)) + cancel_work_sync(&tp->reset_task); tg3_flag_clear(tp, TX_RECOVERY_PENDING); } @@ -11209,18 +11209,27 @@ static void tg3_reset_task(struct work_struct *work) tg3_halt(tp, RESET_KIND_SHUTDOWN, 0); err = tg3_init_hw(tp, true); - if (err) + if (err) { + tg3_full_unlock(tp); + tp->irq_sync = 0; + tg3_napi_enable(tp); + /* Clear this flag so that tg3_reset_task_cancel() will not + * call cancel_work_sync() and wait forever. + */ + tg3_flag_clear(tp, RESET_TASK_PENDING); + dev_close(tp->dev); goto out; + } tg3_netif_start(tp); -out: tg3_full_unlock(tp); if (!err) tg3_phy_start(tp); tg3_flag_clear(tp, RESET_TASK_PENDING); +out: rtnl_unlock(); }