From: Alexandra Winter Date: Tue, 21 Sep 2021 16:52:16 +0200 Subject: s390/qeth: Fix deadlock in remove_discipline Git-commit: ee909d0b1dac8632eeb78cbf17661d6c7674bbd0 Patch-mainline: v5.15-rc3 References: git-fixes Problem: qeth_close_dev_handler is a worker that tries to acquire card->discipline_mutex via drv->set_offline() in ccwgroup_set_offline(). Since commit b41b554c1ee7 ("s390/qeth: fix locking for discipline setup / removal") qeth_remove_discipline() is called under card->discipline_mutex and cancels the work and waits for it to finish. STOPLAN reception with reason code IPA_RC_VEPA_TO_VEB_TRANSITION is the only situation that schedules close_dev_work. In that situation scheduling qeth recovery will also result in an offline interface, when resetting the isolation mode fails, if the external switch is still set to VEB. And since commit 0b9902c1fcc5 ("s390/qeth: fix deadlock during recovery") qeth recovery does not aquire card->discipline_mutex anymore. So we accept the longer pathlength of qeth_schedule_recovery in this error situation and re-use the existing function. As a side-benefit this changes the hwtrap to behave like during recovery instead of like during a user-triggered set_offline. Fixes: b41b554c1ee7 ("s390/qeth: fix locking for discipline setup / removal") Signed-off-by: Alexandra Winter Acked-by: Julian Wiedmann Signed-off-by: Julian Wiedmann Signed-off-by: Jakub Kicinski Acked-by: Petr Tesarik --- drivers/s390/net/qeth_core.h | 1 - drivers/s390/net/qeth_core_main.c | 16 ++++------------ drivers/s390/net/qeth_l2_main.c | 1 - drivers/s390/net/qeth_l3_main.c | 1 - 4 files changed, 4 insertions(+), 15 deletions(-) --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -857,7 +857,6 @@ struct qeth_card { struct napi_struct napi; struct qeth_rx rx; struct delayed_work buffer_reclaim_work; - struct work_struct close_dev_work; }; static inline bool qeth_card_hw_is_reachable(struct qeth_card *card) --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -73,15 +73,6 @@ static void qeth_notify_skbs(struct qeth enum iucv_tx_notify notification); static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int); -static void qeth_close_dev_handler(struct work_struct *work) -{ - struct qeth_card *card; - - card = container_of(work, struct qeth_card, close_dev_work); - QETH_CARD_TEXT(card, 2, "cldevhdl"); - ccwgroup_set_offline(card->gdev); -} - static const char *qeth_get_cardname(struct qeth_card *card) { if (IS_VM_NIC(card)) { @@ -888,10 +888,12 @@ static struct qeth_ipa_cmd *qeth_check_i case IPA_CMD_STOPLAN: if (cmd->hdr.return_code == IPA_RC_VEPA_TO_VEB_TRANSITION) { dev_err(&card->gdev->dev, - "Interface %s is down because the adjacent port is no longer in reflective relay mode\n", + "Adjacent port of interface %s is no longer in reflective relay mode, trigger recovery\n", netdev_name(card->dev)); - schedule_work(&card->close_dev_work); + /* Set offline, then probably fail to set online: */ + qeth_schedule_recovery(card); } else { + /* stay online for subsequent STARTLAN */ dev_warn(&card->gdev->dev, "The link for interface %s on CHPID 0x%X failed\n", netdev_name(card->dev), card->info.chpid); @@ -1627,7 +1629,6 @@ static void qeth_setup_card(struct qeth_ INIT_LIST_HEAD(&card->ipato.entries); qeth_init_qdio_info(card); INIT_DELAYED_WORK(&card->buffer_reclaim_work, qeth_buffer_reclaim_work); - INIT_WORK(&card->close_dev_work, qeth_close_dev_handler); hash_init(card->rx_mode_addrs); hash_init(card->local_addrs4); hash_init(card->local_addrs6); static void qeth_core_sl_print(struct seq_file *m, struct service_level *slr) --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -2207,7 +2207,6 @@ static void qeth_l2_remove_device(struct if (gdev->state == CCWGROUP_ONLINE) qeth_set_offline(card, card->discipline, false); - cancel_work_sync(&card->close_dev_work); if (card->dev->reg_state == NETREG_REGISTERED) unregister_netdev(card->dev); } --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1976,7 +1976,6 @@ static void qeth_l3_remove_device(struct if (cgdev->state == CCWGROUP_ONLINE) qeth_set_offline(card, card->discipline, false); - cancel_work_sync(&card->close_dev_work); if (card->dev->reg_state == NETREG_REGISTERED) unregister_netdev(card->dev);