scsi: qedi: Fix list_del corruption while removing active I/O

[ Upstream commit 28b35d17 ]

While aborting the I/O, the firmware cleanup task timed out and driver
deleted the I/O from active command list. Some time later the firmware
sent the cleanup task response and driver again deleted the I/O from
active command list causing firmware to send completion for non-existent
I/O and list_del corruption of active command list.

Add fix to check if I/O is present before deleting it from the active
command list to ensure firmware sends valid I/O completion and protect
against list_del corruption.

Link: https://lore.kernel.org/r/20200908095657.26821-4-mrangankar@marvell.comSigned-off-by: NNilesh Javali <njavali@marvell.com>
Signed-off-by: NManish Rangankar <mrangankar@marvell.com>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NSasha Levin <sashal@kernel.org>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

drivers/scsi/qedi/qedi_fw.c

@@ -837,8 +837,11 @@ static void qedi_process_cmd_cleanup_resp(struct qedi_ctx *qedi,
 			qedi_clear_task_idx(qedi_conn->qedi, rtid);
 
 			spin_lock(&qedi_conn->list_lock);
+			if (likely(dbg_cmd->io_cmd_in_list)) {
+				dbg_cmd->io_cmd_in_list = false;
 				list_del_init(&dbg_cmd->io_cmd);
 				qedi_conn->active_cmd_count--;
+			}
 			spin_unlock(&qedi_conn->list_lock);
 			qedi_cmd->state = CLEANUP_RECV;
 			wake_up_interruptible(&qedi_conn->wait_queue);
@@ -1257,6 +1260,7 @@ int qedi_cleanup_all_io(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn,
 		qedi_conn->cmd_cleanup_req++;
 		qedi_iscsi_cleanup_task(ctask, true);
 
+		cmd->io_cmd_in_list = false;
 		list_del_init(&cmd->io_cmd);
 		qedi_conn->active_cmd_count--;
 		QEDI_WARN(&qedi->dbg_ctx,
@@ -1470,8 +1474,11 @@ static void qedi_tmf_work(struct work_struct *work)
 	spin_unlock_bh(&qedi_conn->tmf_work_lock);
 
 	spin_lock(&qedi_conn->list_lock);
+	if (likely(cmd->io_cmd_in_list)) {
+		cmd->io_cmd_in_list = false;
 		list_del_init(&cmd->io_cmd);
 		qedi_conn->active_cmd_count--;
+	}
 	spin_unlock(&qedi_conn->list_lock);
 
 	clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);