niansa-misc/linux
1
0
Fork 0
mirror of synced 2025-03-06 20:59:54 +01:00
Code Issues Projects Releases Packages Wiki Activity

xprtrdma: Fix recursion into rpcrdma_xprt_disconnect()

Browse source 
Both Dan and I have observed two processes invoking
rpcrdma_xprt_disconnect() concurrently. In my case:

1. The connect worker invokes rpcrdma_xprt_disconnect(), which
   drains the QP and waits for the final completion
2. This causes the newly posted Receive to flush and invoke
   xprt_force_disconnect()
3. xprt_force_disconnect() sets CLOSE_WAIT and wakes up the RPC task
   that is holding the transport lock
4. The RPC task invokes xprt_connect(), which calls ->ops->close
5. xprt_rdma_close() invokes rpcrdma_xprt_disconnect(), which tries
   to destroy the QP.

Deadlock.

To prevent xprt_force_disconnect() from waking anything, handle the
clean up after a failed connection attempt in the xprt's sndtask.

The retry loop is removed from rpcrdma_xprt_connect() to ensure
that the newly allocated ep and id are properly released before
a REJECTED connection attempt can be retried.

Reported-by: Dan Aloni <dan@kernelim.com>
Fixes: e28ce90083 ("xprtrdma: kmalloc rpcrdma_ep separate from rpcrdma_xprt")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
This commit is contained in:
Chuck Lever 2020-06-27 12:35:09 -04:00 • committed by Anna Schumaker
parent 85bfd71bc3
commit 4cf44be6f1
2 changed files with 7 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
net/sunrpc/xprtrdma/transport.c
View file

@ -249,6 +249,11 @@ xprt_rdma_connect_worker(struct work_struct *work)
xprt->stat.connect_start; xprt->stat.connect_start;
xprt_set_connected(xprt); xprt_set_connected(xprt);
rc = -EAGAIN; rc = -EAGAIN;
} else {
/* Force a call to xprt_rdma_close to clean up */
spin_lock(&xprt->transport_lock);
set_bit(XPRT_CLOSE_WAIT, &xprt->state);
spin_unlock(&xprt->transport_lock);
} }
xprt_wake_pending_tasks(xprt, rc); xprt_wake_pending_tasks(xprt, rc);
} }

10
net/sunrpc/xprtrdma/verbs.c
View file

@ -290,7 +290,7 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
sap, rdma_reject_msg(id, event->status)); sap, rdma_reject_msg(id, event->status));
ep->re_connect_status = -ECONNREFUSED; ep->re_connect_status = -ECONNREFUSED;
if (event->status == IB_CM_REJ_STALE_CONN) if (event->status == IB_CM_REJ_STALE_CONN)
ep->re_connect_status = -EAGAIN; ep->re_connect_status = -ENOTCONN;
goto disconnected; goto disconnected;
case RDMA_CM_EVENT_DISCONNECTED: case RDMA_CM_EVENT_DISCONNECTED:
ep->re_connect_status = -ECONNABORTED; ep->re_connect_status = -ECONNABORTED;
@ -521,8 +521,6 @@ int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt)
struct rpcrdma_ep *ep; struct rpcrdma_ep *ep;
int rc; int rc;
retry:
rpcrdma_xprt_disconnect(r_xprt);
rc = rpcrdma_ep_create(r_xprt); rc = rpcrdma_ep_create(r_xprt);
if (rc) if (rc)
return rc; return rc;
@ -550,17 +548,13 @@ retry:
wait_event_interruptible(ep->re_connect_wait, wait_event_interruptible(ep->re_connect_wait,
ep->re_connect_status != 0); ep->re_connect_status != 0);
if (ep->re_connect_status <= 0) { if (ep->re_connect_status <= 0) {
if (ep->re_connect_status == -EAGAIN)
goto retry;
rc = ep->re_connect_status; rc = ep->re_connect_status;
goto out; goto out;
} }
rc = rpcrdma_reqs_setup(r_xprt); rc = rpcrdma_reqs_setup(r_xprt);
if (rc) { if (rc)
rpcrdma_xprt_disconnect(r_xprt);
goto out; goto out;
}
rpcrdma_mrs_create(r_xprt); rpcrdma_mrs_create(r_xprt);
out: out: