From 38fe73cc2c96fbc9942b07220f2a4f1bab37392d Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Wed, 10 Oct 2018 03:23:10 +0000 Subject: [PATCH] scsi: target: Fix target_wait_for_sess_cmds breakage with active signals With the addition of commit 00d909a10710 ("scsi: target: Make the session shutdown code also wait for commands that are being aborted") in v4.19-rc, it incorrectly assumes no signals will be pending for task_struct executing the normal session shutdown and I/O quiesce code-path. For example, iscsi-target and iser-target issue SIGINT to all kthreads as part of session shutdown. This has been the behaviour since day one. As-is when signals are pending with se_cmds active in se_sess->sess_cmd_list, wait_event_interruptible_lock_irq_timeout() returns a negative number and immediately kills the machine because of the do while (ret <= 0) loop that was added in commit 00d909a107 to spin while backend I/O is taking any amount of extended time (say 30 seconds) to complete. Here's what it looks like in action with debug plus delayed backend I/O completion: [ 4951.909951] se_sess: 000000003e7e08fa before target_wait_for_sess_cmds [ 4951.914600] target_wait_for_sess_cmds: signal_pending: 1 [ 4951.918015] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 0 [ 4951.921639] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 1 [ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 2 [ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 3 [ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 4 [ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 5 [ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 6 [ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 7 [ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 8 [ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 9 ... followed by the usual RCU CPU stalls and deadlock. There was never a case pre commit 00d909a107 where wait_for_complete(&se_cmd->cmd_wait_comp) was able to be interrupted, so to address this for v4.19+ moving forward go ahead and use wait_event_lock_irq_timeout() instead so new code works with all fabric drivers. Also for commit 00d909a107, fix a minor regression in target_release_cmd_kref() to only wake_up the new se_sess->cmd_list_wq only when shutdown has actually been triggered via se_sess->sess_tearing_down. Fixes: 00d909a10710 ("scsi: target: Make the session shutdown code also wait for commands that are being aborted") Cc: # v4.19+ Cc: Bart Van Assche Cc: Mike Christie Cc: Hannes Reinecke Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: Bryant G. Ly Tested-by: Nicholas Bellinger Signed-off-by: Nicholas Bellinger Reviewed-by: Bryant G. Ly Signed-off-by: Martin K. Petersen --- drivers/target/target_core_transport.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 86c0156e6c88..fc3093d21b96 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -2754,7 +2754,7 @@ static void target_release_cmd_kref(struct kref *kref) if (se_sess) { spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); list_del_init(&se_cmd->se_cmd_list); - if (list_empty(&se_sess->sess_cmd_list)) + if (se_sess->sess_tearing_down && list_empty(&se_sess->sess_cmd_list)) wake_up(&se_sess->cmd_list_wq); spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); } @@ -2907,7 +2907,7 @@ void target_wait_for_sess_cmds(struct se_session *se_sess) spin_lock_irq(&se_sess->sess_cmd_lock); do { - ret = wait_event_interruptible_lock_irq_timeout( + ret = wait_event_lock_irq_timeout( se_sess->cmd_list_wq, list_empty(&se_sess->sess_cmd_list), se_sess->sess_cmd_lock, 180 * HZ);