Merge tag 'nfs-for-5.8-3' of git://git.linux-nfs.org/projects/anna/linux-nfs into master

Pull NFS client fixes from Anna Schumaker:
 "A few more NFS client bugfixes for Linux 5.8:

  NFS:
   - Fix interrupted slots by using the SEQUENCE operation

  SUNRPC:
   - revert d03727b248d0 to fix unkillable IOs

  xprtrdma:
   - Fix double-free in rpcrdma_ep_create()
   - Fix recursion into rpcrdma_xprt_disconnect()
   - Fix return code from rpcrdma_xprt_connect()
   - Fix handling of connect errors
   - Fix incorrect header size calculations"

* tag 'nfs-for-5.8-3' of git://git.linux-nfs.org/projects/anna/linux-nfs:
  SUNRPC reverting d03727b248d0 ("NFSv4 fix CLOSE not waiting for direct IO compeletion")
  xprtrdma: fix incorrect header size calculations
  NFS: Fix interrupted slots by sending a solo SEQUENCE operation
  xprtrdma: Fix handling of connect errors
  xprtrdma: Fix return code from rpcrdma_xprt_connect()
  xprtrdma: Fix recursion into rpcrdma_xprt_disconnect()
  xprtrdma: Fix double-free in rpcrdma_ep_create()

6 files changed, 45 insertions, 33 deletions

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 3d113cf8908ac9..1b79dd5cf66160 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -267,6 +267,8 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)
 {
 	struct inode *inode = dreq->inode;
 
+	inode_dio_end(inode);
+
 	if (dreq->iocb) {
 		long res = (long) dreq->error;
 		if (dreq->count != 0) {
@@ -278,10 +280,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)
 
 	complete(&dreq->completion);
 
-	igrab(inode);
 	nfs_direct_req_release(dreq);
-	inode_dio_end(inode);
-	iput(inode);
 }
 
 static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
@@ -411,10 +410,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 	 * generic layer handle the completion.
 	 */
 	if (requested_bytes == 0) {
-		igrab(inode);
-		nfs_direct_req_release(dreq);
 		inode_dio_end(inode);
-		iput(inode);
+		nfs_direct_req_release(dreq);
 		return result < 0 ? result : -EIO;
 	}
 
@@ -867,10 +864,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 	 * generic layer handle the completion.
 	 */
 	if (requested_bytes == 0) {
-		igrab(inode);
-		nfs_direct_req_release(dreq);
 		inode_dio_end(inode);
-		iput(inode);
+		nfs_direct_req_release(dreq);
 		return result < 0 ? result : -EIO;
 	}
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index ccd6c1637b270b..f96367a2463e37 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -83,7 +83,6 @@ nfs_file_release(struct inode *inode, struct file *filp)
 	dprintk("NFS: release(%pD2)\n", filp);
 
 	nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
-	inode_dio_wait(inode);
 	nfs_file_clear_open_context(filp);
 	return 0;
 }
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e32717fd1169a9..2e2dac29a9e915 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -774,6 +774,14 @@ static void nfs4_slot_sequence_acked(struct nfs4_slot *slot,
 	slot->seq_nr_last_acked = seqnr;
 }
 
+static void nfs4_probe_sequence(struct nfs_client *client, const struct cred *cred,
+				struct nfs4_slot *slot)
+{
+	struct rpc_task *task = _nfs41_proc_sequence(client, cred, slot, true);
+	if (!IS_ERR(task))
+		rpc_put_task_async(task);
+}
+
 static int nfs41_sequence_process(struct rpc_task *task,
 		struct nfs4_sequence_res *res)
 {
@@ -790,6 +798,7 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		goto out;
 
 	session = slot->table->session;
+	clp = session->clp;
 
 	trace_nfs4_sequence_done(session, res);
 
@@ -804,7 +813,6 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		nfs4_slot_sequence_acked(slot, slot->seq_nr);
 		/* Update the slot's sequence and clientid lease timer */
 		slot->seq_done = 1;
-		clp = session->clp;
 		do_renew_lease(clp, res->sr_timestamp);
 		/* Check sequence flags */
 		nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags,
@@ -852,10 +860,18 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		/*
 		 * Were one or more calls using this slot interrupted?
 		 * If the server never received the request, then our
-		 * transmitted slot sequence number may be too high.
+		 * transmitted slot sequence number may be too high. However,
+		 * if the server did receive the request then it might
+		 * accidentally give us a reply with a mismatched operation.
+		 * We can sort this out by sending a lone sequence operation
+		 * to the server on the same slot.
 		 */
 		if ((s32)(slot->seq_nr - slot->seq_nr_last_acked) > 1) {
 			slot->seq_nr--;
+			if (task->tk_msg.rpc_proc != &nfs4_procedures[NFSPROC4_CLNT_SEQUENCE]) {
+				nfs4_probe_sequence(clp, task->tk_msg.rpc_cred, slot);
+				res->sr_slot = NULL;
+			}
 			goto retry_nowait;
 		}
 		/*
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 935bbef2f7bef1..453bacc9990783 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -71,7 +71,7 @@ static unsigned int rpcrdma_max_call_header_size(unsigned int maxsegs)
 	size = RPCRDMA_HDRLEN_MIN;
 
 	/* Maximum Read list size */
-	size = maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32);
+	size += maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32);
 
 	/* Minimal Read chunk size */
 	size += sizeof(__be32);	/* segment count */
@@ -94,7 +94,7 @@ static unsigned int rpcrdma_max_reply_header_size(unsigned int maxsegs)
 	size = RPCRDMA_HDRLEN_MIN;
 
 	/* Maximum Write list size */
-	size = sizeof(__be32);		/* segment count */
+	size += sizeof(__be32);		/* segment count */
 	size += maxsegs * rpcrdma_segment_maxsz * sizeof(__be32);
 	size += sizeof(__be32);	/* list discriminator */
 
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 14165b673b2068..053c8ab1265a70 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -249,6 +249,11 @@ 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);
 	}
 	xprt_wake_pending_tasks(xprt, rc);
 }
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 2198c8ec8dff62..75c646743df3ef 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -281,17 +281,19 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 		break;
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 		ep->re_connect_status = -ENOTCONN;
-		goto disconnected;
+		goto wake_connect_worker;
 	case RDMA_CM_EVENT_UNREACHABLE:
 		ep->re_connect_status = -ENETUNREACH;
-		goto disconnected;
+		goto wake_connect_worker;
 	case RDMA_CM_EVENT_REJECTED:
 		dprintk("rpcrdma: connection to %pISpc rejected: %s\n",
 			sap, rdma_reject_msg(id, event->status));
 		ep->re_connect_status = -ECONNREFUSED;
 		if (event->status == IB_CM_REJ_STALE_CONN)
-			ep->re_connect_status = -EAGAIN;
-		goto disconnected;
+			ep->re_connect_status = -ENOTCONN;
+wake_connect_worker:
+		wake_up_all(&ep->re_connect_wait);
+		return 0;
 	case RDMA_CM_EVENT_DISCONNECTED:
 		ep->re_connect_status = -ECONNABORTED;
 disconnected:
@@ -400,14 +402,14 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt)
 
 	ep = kzalloc(sizeof(*ep), GFP_NOFS);
 	if (!ep)
-		return -EAGAIN;
+		return -ENOTCONN;
 	ep->re_xprt = &r_xprt->rx_xprt;
 	kref_init(&ep->re_kref);
 
 	id = rpcrdma_create_id(r_xprt, ep);
 	if (IS_ERR(id)) {
-		rc = PTR_ERR(id);
-		goto out_free;
+		kfree(ep);
+		return PTR_ERR(id);
 	}
 	__module_get(THIS_MODULE);
 	device = id->device;
@@ -506,9 +508,6 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt)
 out_destroy:
 	rpcrdma_ep_put(ep);
 	rdma_destroy_id(id);
-out_free:
-	kfree(ep);
-	r_xprt->rx_ep = NULL;
 	return rc;
 }
 
@@ -524,8 +523,6 @@ int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt)
 	struct rpcrdma_ep *ep;
 	int rc;
 
-retry:
-	rpcrdma_xprt_disconnect(r_xprt);
 	rc = rpcrdma_ep_create(r_xprt);
 	if (rc)
 		return rc;
@@ -540,10 +537,6 @@ retry:
 	rpcrdma_ep_get(ep);
 	rpcrdma_post_recvs(r_xprt, true);
 
-	rc = rpcrdma_sendctxs_create(r_xprt);
-	if (rc)
-		goto out;
-
 	rc = rdma_connect(ep->re_id, &ep->re_remote_cma);
 	if (rc)
 		goto out;
@@ -553,15 +546,19 @@ retry:
 	wait_event_interruptible(ep->re_connect_wait,
 				 ep->re_connect_status != 0);
 	if (ep->re_connect_status <= 0) {
-		if (ep->re_connect_status == -EAGAIN)
-			goto retry;
 		rc = ep->re_connect_status;
 		goto out;
 	}
 
+	rc = rpcrdma_sendctxs_create(r_xprt);
+	if (rc) {
+		rc = -ENOTCONN;
+		goto out;
+	}
+
 	rc = rpcrdma_reqs_setup(r_xprt);
 	if (rc) {
-		rpcrdma_xprt_disconnect(r_xprt);
+		rc = -ENOTCONN;
 		goto out;
 	}
 	rpcrdma_mrs_create(r_xprt);