Merge tag 'nfs-for-5.15-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "New Features:
   - Better client responsiveness when server isn't replying
   - Use refcount_t in sunrpc rpc_client refcount tracking
   - Add srcaddr and dst_port to the sunrpc sysfs info files
   - Add basic support for connection sharing between servers with multiple NICs`

  Bugfixes and Cleanups:
   - Sunrpc tracepoint cleanups
   - Disconnect after ib_post_send() errors to avoid deadlocks
   - Fix for tearing down rpcrdma_reps
   - Fix a potential pNFS layoutget livelock loop
   - pNFS layout barrier fixes
   - Fix a potential memory corruption in rpc_wake_up_queued_task_set_status()
   - Fix reconnection locking
   - Fix return value of get_srcport()
   - Remove rpcrdma_post_sends()
   - Remove pNFS dead code
   - Remove copy size restriction for inter-server copies
   - Overhaul the NFS callback service
   - Clean up sunrpc TCP socket shutdowns
   - Always provide aligned buffers to RPC read layers"

* tag 'nfs-for-5.15-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (39 commits)
  NFS: Always provide aligned buffers to the RPC read layers
  NFSv4.1 add network transport when session trunking is detected
  SUNRPC enforce creation of no more than max_connect xprts
  NFSv4 introduce max_connect mount options
  SUNRPC add xps_nunique_destaddr_xprts to xprt_switch_info in sysfs
  SUNRPC keep track of number of transports to unique addresses
  NFSv3: Delete duplicate judgement in nfs3_async_handle_jukebox
  SUNRPC: Tweak TCP socket shutdown in the RPC client
  SUNRPC: Simplify socket shutdown when not reusing TCP ports
  NFSv4.2: remove restriction of copy size for inter-server copy.
  NFS: Clean up the synopsis of callback process_op()
  NFS: Extract the xdr_init_encode/decode() calls from decode_compound
  NFS: Remove unused callback void decoder
  NFS: Add a private local dispatcher for NFSv4 callback operations
  SUNRPC: Eliminate the RQ_AUTHERR flag
  SUNRPC: Set rq_auth_stat in the pg_authenticate() callout
  SUNRPC: Add svc_rqst::rq_auth_stat
  SUNRPC: Add dst_port to the sysfs xprt info file
  SUNRPC: Add srcaddr as a file in sysfs
  sunrpc: Fix return value of get_srcport()
  ...

5 files changed, 28 insertions, 31 deletions

diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index 1151efd09b27..17f174d6ea3b 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -115,7 +115,7 @@ int xprt_rdma_bc_send_reply(struct rpc_rqst *rqst)
 	if (rc < 0)
 		goto failed_marshal;
 
-	if (rpcrdma_post_sends(r_xprt, req))
+	if (frwr_send(r_xprt, req))
 		goto drop_connection;
 	return 0;
 
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 229fcc9a9064..f700b34a5bfd 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -394,6 +394,7 @@ int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	struct rpcrdma_ep *ep = r_xprt->rx_ep;
 	struct rpcrdma_mr *mr;
 	unsigned int num_wrs;
+	int ret;
 
 	num_wrs = 1;
 	post_wr = send_wr;
@@ -420,7 +421,10 @@ int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	}
 
 	trace_xprtrdma_post_send(req);
-	return ib_post_send(ep->re_id->qp, post_wr, NULL);
+	ret = ib_post_send(ep->re_id->qp, post_wr, NULL);
+	if (ret)
+		trace_xprtrdma_post_send_err(r_xprt, req, ret);
+	return ret;
 }
 
 /**
@@ -557,6 +561,10 @@ 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 +661,8 @@ 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);
 }
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 9c2ffc67c0fd..16e5696314a4 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -250,12 +250,9 @@ xprt_rdma_connect_worker(struct work_struct *work)
 					   xprt->stat.connect_start;
 		xprt_set_connected(xprt);
 		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);
-	}
+	} else
+		rpcrdma_xprt_disconnect(r_xprt);
+	xprt_unlock_connect(xprt, r_xprt);
 	xprt_wake_pending_tasks(xprt, rc);
 }
 
@@ -489,6 +486,8 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 	struct rpcrdma_ep *ep = r_xprt->rx_ep;
 	unsigned long delay;
 
+	WARN_ON_ONCE(!xprt_lock_connect(xprt, task, r_xprt));
+
 	delay = 0;
 	if (ep && ep->re_connect_status != 0) {
 		delay = xprt_reconnect_delay(xprt);
@@ -661,7 +660,7 @@ xprt_rdma_send_request(struct rpc_rqst *rqst)
 		goto drop_connection;
 	rqst->rq_xtime = ktime_get();
 
-	if (rpcrdma_post_sends(r_xprt, req))
+	if (frwr_send(r_xprt, req))
 		goto drop_connection;
 
 	rqst->rq_xmit_bytes_sent += rqst->rq_snd_buf.len;
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 649c23518ec0..aaec3c9be8db 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -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);
@@ -1350,21 +1350,6 @@ static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb)
 }
 
 /**
- * rpcrdma_post_sends - Post WRs to a transport's Send Queue
- * @r_xprt: controlling transport instance
- * @req: rpcrdma_req containing the Send WR to post
- *
- * Returns 0 if the post was successful, otherwise -ENOTCONN
- * is returned.
- */
-int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
-{
-	if (frwr_send(r_xprt, req))
-		return -ENOTCONN;
-	return 0;
-}
-
-/**
  * rpcrdma_post_recvs - Refill the Receive Queue
  * @r_xprt: controlling transport instance
  * @needed: current credit grant
@@ -1416,12 +1401,8 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp)
 
 	rc = ib_post_recv(ep->re_id->qp, wr,
 			  (const struct ib_recv_wr **)&bad_wr);
-	if (atomic_dec_return(&ep->re_receiving) > 0)
-		complete(&ep->re_done);
-
-out:
-	trace_xprtrdma_post_recvs(r_xprt, count, rc);
 	if (rc) {
+		trace_xprtrdma_post_recvs_err(r_xprt, rc);
 		for (wr = bad_wr; wr;) {
 			struct rpcrdma_rep *rep;
 
@@ -1431,6 +1412,11 @@ out:
 			--count;
 		}
 	}
+	if (atomic_dec_return(&ep->re_receiving) > 0)
+		complete(&ep->re_done);
+
+out:
+	trace_xprtrdma_post_recvs(r_xprt, count);
 	ep->re_receive_count += count;
 	return;
 }
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 5d231d94e944..d91f54eae00b 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -454,11 +454,11 @@ 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);
 
-int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req);
 void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp);
 
 /*