isci: Handle timed-out request terminations correctly

In the situation where a termination of an I/O times-out,
make sure that the linkage from the request to the task
is severed completely.  Also make sure that the selection
of tasks to terminate occurs under scic_lock.

Signed-off-by: Jeff Skirvin <jeffrey.d.skirvin@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c
index 5879e5f..433565c 100644
--- a/drivers/scsi/isci/request.c
+++ b/drivers/scsi/isci/request.c
@@ -2741,6 +2741,15 @@
 		spin_unlock(&request->state_lock);
 		break;
 
+	case dead:
+		/* This was a terminated request that timed-out during the
+		 * termination process.  There is no task to complete to
+		 * libsas.
+		 */
+		complete_to_host = isci_perform_normal_io_completion;
+		spin_unlock(&request->state_lock);
+		break;
+
 	default:
 
 		/* The request is done from an SCU HW perspective. */