SUNRPC: Fix backchannel RPC soft lockups

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@hammerspace.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Cc: <stable@vger.kernel.org> # v4.20+

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index c3b11a715082914c2bfee7be0d27a507be967fdd..5cf91322de0fc57f895d857d2c37ec436b6b862d 100644 (file)
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1312,6 +1312,7 @@ nfsd4_run_cb_work(struct work_struct *work)
                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 *work)
        }
 
        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);
 }
 

diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index e27e3532ec7567a9b4e3dd07f158c26f58aafb64..92f2c08c67a5b7eed2e58a8ce0980991521a7438 100644 (file)
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -1040,6 +1040,8 @@ static void svc_delete_xprt(struct svc_xprt *xprt)
 
        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);

diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index d510a3a15d4be9d169598da0a06db896357190a0..af7eb8d202ae70fceffe554d184e27f9348dcc05 100644 (file)
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -244,6 +244,8 @@ 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;
 }
 

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 0bda8a73e8a86ea99ff5c04192a4624752d8a067..845d0be805ece18da98e87886c08595d18252d65 100644 (file)
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2584,6 +2584,7 @@ static int bc_send_request(struct rpc_rqst *req)
 
 static void bc_close(struct rpc_xprt *xprt)
 {
+       xprt_disconnect_done(xprt);
 }
 
 /*