@@ -557,6 +557,10 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
/* On error, the MRs get destroyed once the QP has drained. */
trace_xprtrdma_post_linv_err(req, rc);
+
+ /* Force a connection loss to ensure complete recovery.
+ */
+ rpcrdma_force_disconnect(ep);
}
/**
@@ -653,4 +657,8 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
* retransmission.
*/
rpcrdma_unpin_rqst(req->rl_reply);
+
+ /* Force a connection loss to ensure complete recovery.
+ */
+ rpcrdma_force_disconnect(ep);
}
@@ -124,7 +124,7 @@ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt)
* connection is closed or lost. (The important thing is it needs
* to be invoked "at least" once).
*/
-static void rpcrdma_force_disconnect(struct rpcrdma_ep *ep)
+void rpcrdma_force_disconnect(struct rpcrdma_ep *ep)
{
if (atomic_add_unless(&ep->re_force_disconnect, 1, 1))
xprt_force_disconnect(ep->re_xprt);
@@ -454,6 +454,7 @@ extern unsigned int xprt_rdma_memreg_strategy;
/*
* Endpoint calls - xprtrdma/verbs.c
*/
+void rpcrdma_force_disconnect(struct rpcrdma_ep *ep);
void rpcrdma_flush_disconnect(struct rpcrdma_xprt *r_xprt, struct ib_wc *wc);
int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt);
void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt);
ib_post_send() does not disconnect the QP when it returns an immediate error. Thus, the code that posts LocalInv has to explicitly disconnect after an immediate error. This is just like the frwr_send() callers handle it. If a disconnect isn't done here, the transport deadlocks. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> --- net/sunrpc/xprtrdma/frwr_ops.c | 8 ++++++++ net/sunrpc/xprtrdma/verbs.c | 2 +- net/sunrpc/xprtrdma/xprt_rdma.h | 1 + 3 files changed, 10 insertions(+), 1 deletion(-)