The system may crash when a malformed request is received and
the error is detected by the responder.
NodeA: $ ibv_rc_pingpong -g 0 -d rxe0 -i 1 -n 1 -s 50000
NodeB: $ ibv_rc_pingpong -g 0 -d rxe0 -i 1 -n 1 -s 1024 <NodeA_ip>
The responder generates a receive error on node B since the incoming
SEND is oversized. If the client tears down the QP before the responder
or the completer finish running, a page fault may occur.
The fix makes the destroy operation spin until the tasks complete, which
appears to be original intent of the design.
Signed-off-by: Andrew Boyer <andrew.boyer@xxxxxxxx>
---
drivers/infiniband/sw/rxe/rxe_task.c | 19 +++++++++++++++++++
drivers/infiniband/sw/rxe/rxe_task.h | 1 +
2 files changed, 20 insertions(+)
diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c
index 1e19bf8..1e9a28f 100644
--- a/drivers/infiniband/sw/rxe/rxe_task.c
+++ b/drivers/infiniband/sw/rxe/rxe_task.c
@@ -121,6 +121,7 @@ int rxe_init_task(void *obj, struct rxe_task *task,
task->arg = arg;
task->func = func;
snprintf(task->name, sizeof(task->name), "%s", name);
+ task->destroyed = false;
tasklet_init(&task->tasklet, rxe_do_task, (unsigned long)task);
@@ -132,11 +133,29 @@ int rxe_init_task(void *obj, struct rxe_task *task,
void rxe_cleanup_task(struct rxe_task *task)
{
+ unsigned long flags;
+ bool idle = false;
+
+ /*
+ * Mark the task, then wait for it to finish. It might be
+ * running in a non-tasklet (direct call) context.
+ */
+ task->destroyed = true;
+
+ do {
+ spin_lock_irqsave(&task->state_lock, flags);
+ idle = (task->state == TASK_STATE_START);
+ spin_unlock_irqrestore(&task->state_lock, flags);
+ } while (!idle);
+
tasklet_kill(&task->tasklet);
}
void rxe_run_task(struct rxe_task *task, int sched)
{
+ if (task->destroyed)
+ return;
+
if (sched)
tasklet_schedule(&task->tasklet);
else
diff --git a/drivers/infiniband/sw/rxe/rxe_task.h b/drivers/infiniband/sw/rxe/rxe_task.h
index d14aa6d..08ff42d 100644
--- a/drivers/infiniband/sw/rxe/rxe_task.h
+++ b/drivers/infiniband/sw/rxe/rxe_task.h
@@ -54,6 +54,7 @@ struct rxe_task {
int (*func)(void *arg);
int ret;
char name[16];
+ bool destroyed;
};
/*
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
