From: Chuck Lever <chuck.lever@xxxxxxxxxx>
commit 6221f1d9b63fed6260273e59a2b89ab30537a811 upstream.
Currently, after the forward channel connection goes away,
backchannel operations are causing soft lockups on the server
because call_transmit_status's SOFTCONN logic ignores ENOTCONN.
Such backchannel Calls are aggressively retried until the client
reconnects.
Backchannel Calls should use RPC_TASK_NOCONNECT rather than
RPC_TASK_SOFTCONN. If there is no forward connection, the server is
not capable of establishing a connection back to the client, thus
that backchannel request should fail before the server attempts to
send it. Commit 58255a4e3ce5 ("NFSD: NFSv4 callback client should
use RPC_TASK_SOFTCONN") was merged several years before
RPC_TASK_NOCONNECT was available.
Because setup_callback_client() explicitly sets NOPING, the NFSv4.0
callback connection depends on the first callback RPC to initiate
a connection to the client. Thus NFSv4.0 needs to continue to use
RPC_TASK_SOFTCONN.
Suggested-by: Trond Myklebust <trondmy@xxxxxxxxxxxxxxx>
Signed-off-by: Chuck Lever <chuck.lever@xxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> # v4.20+
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
fs/nfsd/nfs4callback.c | 4 +++-
net/sunrpc/svc_xprt.c | 2 ++
net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 2 ++
net/sunrpc/xprtsock.c | 1 +
4 files changed, 8 insertions(+), 1 deletion(-)
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1312,6 +1312,7 @@ nfsd4_run_cb_work(struct work_struct *wo
container_of(work, struct nfsd4_callback, cb_work);
struct nfs4_client *clp = cb->cb_clp;
struct rpc_clnt *clnt;
+ int flags;
if (cb->cb_need_restart) {
cb->cb_need_restart = false;
@@ -1340,7 +1341,8 @@ nfsd4_run_cb_work(struct work_struct *wo
}
cb->cb_msg.rpc_cred = clp->cl_cb_cred;
- rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN,
+ flags = clp->cl_minorversion ? RPC_TASK_NOCONNECT : RPC_TASK_SOFTCONN;
+ rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | flags,
cb->cb_ops ? &nfsd4_cb_ops : &nfsd4_cb_probe_ops, cb);
}
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -1028,6 +1028,8 @@ static void svc_delete_xprt(struct svc_x
dprintk("svc: svc_delete_xprt(%p)\n", xprt);
xprt->xpt_ops->xpo_detach(xprt);
+ if (xprt->xpt_bc_xprt)
+ xprt->xpt_bc_xprt->ops->close(xprt->xpt_bc_xprt);
spin_lock_bh(&serv->sv_lock);
list_del_init(&xprt->xpt_list);
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -242,6 +242,8 @@ static void
xprt_rdma_bc_close(struct rpc_xprt *xprt)
{
dprintk("svcrdma: %s: xprt %p\n", __func__, xprt);
+
+ xprt_disconnect_done(xprt);
xprt->cwnd = RPC_CWNDSHIFT;
}
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2714,6 +2714,7 @@ static int bc_send_request(struct rpc_rq
static void bc_close(struct rpc_xprt *xprt)
{
+ xprt_disconnect_done(xprt);
}
/*
