qla2xxx: Fix incorrect tcm_qla2xxx_free_cmd use during TMR ABORT

This patch drops two incorrect usages of tcm_qla2xxx_free_cmd()
during TMR ABORT within tcm_qla2xxx_handle_data_work() and
tcm_qla2xxx_aborted_task(), which where attempting to dispatch
into workqueue context to do tcm_qla2xxx_complete_free() and
subsequently invoke transport_generic_free_cmd().

This is incorrect because during TMR ABORT target-core will
drop the outstanding se_cmd->cmd_kref references once it has
quiesced the se_cmd via transport_wait_for_tasks(), and in
the case of qla2xxx it should not attempt to do it's own
transport_generic_free_cmd() once the abort has occured.

As reported by Pascal, this was originally manifesting as a
BUG_ON(cmd->cmd_in_wq) in qlt_free_cmd() during TMR ABORT,
with a LIO backend that had sufficently high enough WRITE
latency to trigger a host side TMR ABORT_TASK.

In addition, for the case in tcm_qla2xxx_write_pending_status()
and tcm_qla2xxx_handle_data_work() that waits for outstanding
FCP WRITE data transfer to complete before preceeding with a
TMR ABORT, avoid se_cmd->t_transport_stop_comp that is already
used by transport_wait_for_tasks() and use a qla2xxx internal
struct completion instead.
Reported-by: Pascal de Bruijn <p.debruijn@unilogic.nl>
Tested-by: Pascal de Bruijn <p.debruijn@unilogic.nl>
Acked-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Cc: Quinn Tran <quinn.tran@cavium.com>
Cc: <stable@vger.kernel.org> # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>

drivers/scsi/qla2xxx/qla_target.c

@@ -4079,6 +4079,8 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha,
 	cmd = &((struct qla_tgt_cmd *)se_sess->sess_cmd_map)[tag];
 	memset(cmd, 0, sizeof(struct qla_tgt_cmd));
 
+	init_completion(&cmd->write_pending_abort_comp);
+
 	memcpy(&cmd->atio, atio, sizeof(*atio));
 	cmd->state = QLA_TGT_STATE_NEW;
 	cmd->tgt = vha->vha_tgt.qla_tgt;
@@ -5083,6 +5085,8 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
 
 	qlt_incr_num_pend_cmds(vha);
 	INIT_LIST_HEAD(&cmd->cmd_list);
+	init_completion(&cmd->write_pending_abort_comp);
+
 	memcpy(&cmd->atio, atio, sizeof(*atio));
 
 	cmd->tgt = vha->vha_tgt.qla_tgt;

drivers/scsi/qla2xxx/qla_target.h

@@ -868,6 +868,7 @@ struct qla_tgt_cmd {
 	unsigned char sense_buffer[TRANSPORT_SENSE_BUFFER];
 
 	spinlock_t cmd_lock;
+	struct completion write_pending_abort_comp;
 	/* to save extra sess dereferences */
 	unsigned int conf_compl_supported:1;
 	unsigned int sg_mapped:1;

drivers/scsi/qla2xxx/tcm_qla2xxx.c

@@ -415,6 +415,7 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd)
 
 static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd)
 {
+	struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd);
 	unsigned long flags;
 	/*
 	 * Check for WRITE_PENDING status to determine if we need to wait for
@@ -424,8 +425,7 @@ static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd)
 	if (se_cmd->t_state == TRANSPORT_WRITE_PENDING ||
 	    se_cmd->t_state == TRANSPORT_COMPLETE_QF_WP) {
 		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
-		wait_for_completion_timeout(&se_cmd->t_transport_stop_comp,
-						50);
+		wait_for_completion(&cmd->write_pending_abort_comp);
 		return 0;
 	}
 	spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
@@ -501,7 +501,6 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
 static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
 {
 	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
-	unsigned long flags;
 
 	/*
 	 * Ensure that the complete FCP WRITE payload has been received.
@@ -509,17 +508,6 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
 	 */
 	cmd->cmd_in_wq = 0;
 
-	spin_lock_irqsave(&cmd->cmd_lock, flags);
-	cmd->data_work = 1;
-	if (cmd->aborted) {
-		cmd->data_work_free = 1;
-		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
-
-		tcm_qla2xxx_free_cmd(cmd);
-		return;
-	}
-	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
-
 	cmd->vha->tgt_counters.qla_core_ret_ctio++;
 	if (!cmd->write_data_transferred) {
 		/*
@@ -527,7 +515,7 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
 		 * waiting upon completion in tcm_qla2xxx_write_pending_status()
 		 */
 		if (cmd->se_cmd.transport_state & CMD_T_ABORTED) {
-			complete(&cmd->se_cmd.t_transport_stop_comp);
+			complete(&cmd->write_pending_abort_comp);
 			return;
 		}
 
@@ -753,31 +741,13 @@ static void tcm_qla2xxx_queue_tm_rsp(struct se_cmd *se_cmd)
 	qlt_xmit_tm_rsp(mcmd);
 }
 
-#define DATA_WORK_NOT_FREE(_cmd) (_cmd->data_work && !_cmd->data_work_free)
 static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-	unsigned long flags;
 
 	if (qlt_abort_cmd(cmd))
 		return;
-
-	spin_lock_irqsave(&cmd->cmd_lock, flags);
-	if ((cmd->state == QLA_TGT_STATE_NEW)||
-	    ((cmd->state == QLA_TGT_STATE_DATA_IN) &&
-		DATA_WORK_NOT_FREE(cmd))) {
-		cmd->data_work_free = 1;
-		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
-		/*
-		 * cmd has not reached fw, Use this trigger to free it.
-		 */
-		tcm_qla2xxx_free_cmd(cmd);
-		return;
-	}
-	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
-	return;
-
 }
 
 static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *,