qla2xxx: Fix TMR ABORT interaction issue between qla2xxx and TCM

During lun reset, TMR thread from TCM would issue abort
to qla driver.  At abort time, each command is in different
state.  Depending on the state, qla will use the TMR thread
to trigger a command free(cmd_kref--) if command is not
down at firmware.

Signed-off-by: Quinn Tran <quinn.tran@qlogic.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>

1 files changed, 70 insertions, 3 deletions

diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index faf0a126627f..3eecdd1bc6fb 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -298,6 +298,10 @@ static void tcm_qla2xxx_free_cmd(struct qla_tgt_cmd *cmd)
 {
 	cmd->vha->tgt_counters.core_qla_free_cmd++;
 	cmd->cmd_in_wq = 1;
+
+	BUG_ON(cmd->cmd_flags & BIT_20);
+	cmd->cmd_flags |= BIT_20;
+
 	INIT_WORK(&cmd->work, tcm_qla2xxx_complete_free);
 	queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work);
 }
@@ -374,6 +378,20 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
+
+	if (cmd->aborted) {
+		/* Cmd can loop during Q-full.  tcm_qla2xxx_aborted_task
+		 * can get ahead of this cmd. tcm_qla2xxx_aborted_task
+		 * already kick start the free.
+		 */
+		pr_debug("write_pending aborted cmd[%p] refcount %d "
+			"transport_state %x, t_state %x, se_cmd_flags %x\n",
+			cmd,cmd->se_cmd.cmd_kref.refcount.counter,
+			cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,
+			cmd->se_cmd.se_cmd_flags);
+		return 0;
+	}
 	cmd->cmd_flags |= BIT_3;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
@@ -405,7 +423,7 @@ static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd)
 	    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,
-					    3 * HZ);
+						50);
 		return 0;
 	}
 	spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
@@ -465,13 +483,25 @@ 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.
 	 * Otherwise return an exception via CHECK_CONDITION status.
 	 */
 	cmd->cmd_in_wq = 0;
-	cmd->cmd_flags |= BIT_11;
+
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	cmd->cmd_flags |= CMD_FLAG_DATA_WORK;
+	if (cmd->aborted) {
+		cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE;
+		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) {
 		/*
@@ -546,6 +576,20 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
 
+	if (cmd->aborted) {
+		/* Cmd can loop during Q-full.  tcm_qla2xxx_aborted_task
+		 * can get ahead of this cmd. tcm_qla2xxx_aborted_task
+		 * already kick start the free.
+		 */
+		pr_debug("queue_data_in aborted cmd[%p] refcount %d "
+			"transport_state %x, t_state %x, se_cmd_flags %x\n",
+			cmd,cmd->se_cmd.cmd_kref.refcount.counter,
+			cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,
+			cmd->se_cmd.se_cmd_flags);
+		return 0;
+	}
+
 	cmd->cmd_flags |= BIT_4;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
@@ -637,11 +681,34 @@ static void tcm_qla2xxx_queue_tm_rsp(struct se_cmd *se_cmd)
 	qlt_xmit_tm_rsp(mcmd);
 }
 
+
+#define DATA_WORK_NOT_FREE(_flags) \
+	(( _flags & (CMD_FLAG_DATA_WORK|CMD_FLAG_DATA_WORK_FREE)) == \
+	 CMD_FLAG_DATA_WORK)
 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);
-	qlt_abort_cmd(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_flags)) ) {
+
+		cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE;
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+		/* Cmd have not reached firmware.
+		 * 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 *,