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. */