IB/srp: Avoid that writing into "add_target" hangs due to a cable pull

If a cable is pulled while srp_connect_target() is in progress
that can result in that function never to return. That makes the
process, e.g. srp_daemon, that invoked this function unkillable.
Avoid this by letting srp_connect_target() finish if the event
IB_CM_TIMEWAIT_EXIT is received. This patch fixes a hang with the
following call trace:

 [<ffffffff814eae85>] schedule_timeout+0x215/0x2e0
 [<ffffffff814eab03>] wait_for_common+0x123/0x180
 [<ffffffff814eac1d>] wait_for_completion+0x1d/0x20
 [<ffffffffa03b398c>] srp_connect_target+0x1dc/0x410 [ib_srp]
 [<ffffffffa03b5809>] srp_create_target+0xba9/0xe70 [ib_srp]
 [<ffffffff8133e590>] dev_attr_store+0x20/0x30
 [<ffffffff811eb8f5>] sysfs_write_file+0xe5/0x170
 [<ffffffff811767c8>] vfs_write+0xb8/0x1a0
 [<ffffffff811770c1>] sys_write+0x51/0x90
 [<ffffffff8100b072>] system_call_fastpath+0x16/0x1b

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Roland Dreier <roland@purestorage.com>
This commit is contained in:
Bart Van Assche 2014-03-14 13:53:40 +01:00 committed by Roland Dreier
parent a702adceec
commit ac72d766a8

View File

@ -1871,6 +1871,7 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
case IB_CM_TIMEWAIT_EXIT:
shost_printk(KERN_ERR, target->scsi_host,
PFX "connection closed\n");
comp = 1;
target->status = 0;
break;