libiscsi: fix locking in iscsi_eh_device_reset

We must be using the bh spin locking functions in
iscsi_eh_device_reset becuase the session lock interacts with
a thread and softirq.

This patch also fixes up a bogus comment and check in fail_command,
because no one drops the lock (bnx2i did but it is not going
upstream yet and there were other refcount changes for that).

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 5aa0db1..801c7cf 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -404,11 +404,6 @@
 		conn->session->queued_cmdsn--;
 	else
 		conn->session->tt->cleanup_task(conn, task);
-	/*
-	 * Check if cleanup_task dropped the lock and the command completed,
-	 */
-	if (!task->sc)
-		return;
 
 	sc->result = err;
 	if (!scsi_bidi_cmnd(sc))
@@ -1829,10 +1824,10 @@
 
 	iscsi_suspend_tx(conn);
 
-	spin_lock(&session->lock);
+	spin_lock_bh(&session->lock);
 	fail_all_commands(conn, sc->device->lun, DID_ERROR);
 	conn->tmf_state = TMF_INITIAL;
-	spin_unlock(&session->lock);
+	spin_unlock_bh(&session->lock);
 
 	iscsi_start_tx(conn);
 	goto done;