NFS client bugfixes for Linux 5.7

Highlights include:
 
 Stable fixes
 - fix handling of backchannel binding in BIND_CONN_TO_SESSION
 
 Bugfixes
 - Fix a credential use-after-free issue in pnfs_roc()
 - Fix potential posix_acl refcnt leak in nfs3_set_acl
 - defer slow parts of rpc_free_client() to a workqueue
 - Fix an Oopsable race in __nfs_list_for_each_server()
 - Fix trace point use-after-free race
 - Regression: the RDMA client no longer responds to server disconnect requests
 - Fix return values of xdr_stream_encode_item_{present, absent}
 - _pnfs_return_layout() must always wait for layoutreturn completion
 
 Cleanups
 - Remove unreachable error conditions
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEESQctxSBg8JpV8KqEZwvnipYKAPIFAl6tczsACgkQZwvnipYK
 APKHWg//QGx2Tolj5dh2jBHa47A5/SYnJxCZAA0/fWdwRtFkW3HyyGne1jU86do2
 SMAVpBpri1WJPt5d3DH66gu4l4UxG1h84s7QP4lGfSa85EmtLh+LoZQCZRqYoDOo
 JAMzWctELu1TUpaa1N5Dhg/qMtMy6ulRMWgzTLqB9a/pQa3onugTK6W7xiut2prj
 PBfFq7N9XXmPboSeGV9bR4L8XKSbTCLEt3U1F2zAGU7UUINvDfpjEXq7BHYCewKL
 ObPW6EWZksyna16H8i/xGWoKgE4JFVjMwQAP7UdDBi+FW9RI6UpTBoR6z9N748j0
 jEocDbI21wgnwmtrVTbzsYm6ttHl4D4egoNxn7m5zjxTU4Ba/RQG2aaHUGFOYpJj
 1FI1f6V1Y5v4mJajdsEH+pGW/4vK/4YMR+7YHJ/hYU/WiXjLf7onIIifdWt4SQdo
 lvZbGcx6IAHYUA4lI7hkcvrK4bbqAnPLFq28nlUWEID5q5D+nA1ZR9iN0FToviDy
 FYyhQzyfD1kt98SV1DjWUqvDDd6IB64iDZTXGmtWvj6c2nbezGiFffvtzUL5LFxY
 QfI8lkpmUyt1EiWlZWhtOh4zsiM5yMZkJB/3RJv3RMmswizSSAHdgCKWhdLpX0bl
 TG1L8yEmcTc5ANS37EhlpcBNbfYw7oIF/OXuReTSRoMQl5hxjfY=
 =w0zk
 -----END PGP SIGNATURE-----

Merge tag 'nfs-for-5.7-4' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:
 "Highlights include:

  Stable fixes:
   - fix handling of backchannel binding in BIND_CONN_TO_SESSION

  Bugfixes:
   - Fix a credential use-after-free issue in pnfs_roc()
   - Fix potential posix_acl refcnt leak in nfs3_set_acl
   - defer slow parts of rpc_free_client() to a workqueue
   - Fix an Oopsable race in __nfs_list_for_each_server()
   - Fix trace point use-after-free race
   - Regression: the RDMA client no longer responds to server disconnect
     requests
   - Fix return values of xdr_stream_encode_item_{present, absent}
   - _pnfs_return_layout() must always wait for layoutreturn completion

  Cleanups:
   - Remove unreachable error conditions"

* tag 'nfs-for-5.7-4' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  NFS: Fix a race in __nfs_list_for_each_server()
  NFSv4.1: fix handling of backchannel binding in BIND_CONN_TO_SESSION
  SUNRPC: defer slow parts of rpc_free_client() to a workqueue.
  NFSv4: Remove unreachable error condition due to rpc_run_task()
  SUNRPC: Remove unreachable error condition
  xprtrdma: Fix use of xdr_stream_encode_item_{present, absent}
  xprtrdma: Fix trace point use-after-free race
  xprtrdma: Restore wake-up-all to rpcrdma_cm_event_handler()
  nfs: Fix potential posix_acl refcnt leak in nfs3_set_acl
  NFS/pnfs: Fix a credential use-after-free issue in pnfs_roc()
  NFS/pnfs: Ensure that _pnfs_return_layout() waits for layoutreturn completion

fs/nfs/nfs3acl.c

@@ -253,37 +253,45 @@ int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 
 int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
-	struct posix_acl *alloc = NULL, *dfacl = NULL;
+	struct posix_acl *orig = acl, *dfacl = NULL, *alloc;
 	int status;
 
 	if (S_ISDIR(inode->i_mode)) {
 		switch(type) {
 		case ACL_TYPE_ACCESS:
-			alloc = dfacl = get_acl(inode, ACL_TYPE_DEFAULT);
+			alloc = get_acl(inode, ACL_TYPE_DEFAULT);
 			if (IS_ERR(alloc))
 				goto fail;
+			dfacl = alloc;
 			break;
 
 		case ACL_TYPE_DEFAULT:
-			dfacl = acl;
-			alloc = acl = get_acl(inode, ACL_TYPE_ACCESS);
+			alloc = get_acl(inode, ACL_TYPE_ACCESS);
 			if (IS_ERR(alloc))
 				goto fail;
+			dfacl = acl;
+			acl = alloc;
 			break;
 		}
 	}
 
 	if (acl == NULL) {
-		alloc = acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+		alloc = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
 		if (IS_ERR(alloc))
 			goto fail;
+		acl = alloc;
 	}
 	status = __nfs3_proc_setacls(inode, acl, dfacl);
-	posix_acl_release(alloc);
+out:
+	if (acl != orig)
+		posix_acl_release(acl);
+	if (dfacl != orig)
+		posix_acl_release(dfacl);
 	return status;
 
 fail:
-	return PTR_ERR(alloc);
+	status = PTR_ERR(alloc);
+	goto out;
 }
 
 const struct xattr_handler *nfs3_xattr_handlers[] = {

fs/nfs/nfs4proc.c

@@ -7891,6 +7891,7 @@ static void
 nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs41_bind_conn_to_session_args *args = task->tk_msg.rpc_argp;
+	struct nfs41_bind_conn_to_session_res *res = task->tk_msg.rpc_resp;
 	struct nfs_client *clp = args->client;
 
 	switch (task->tk_status) {
@@ -7899,6 +7900,12 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
 		nfs4_schedule_session_recovery(clp->cl_session,
 				task->tk_status);
 	}
+	if (args->dir == NFS4_CDFC4_FORE_OR_BOTH &&
+			res->dir != NFS4_CDFS4_BOTH) {
+		rpc_task_close_connection(task);
+		if (args->retries++ < MAX_BIND_CONN_TO_SESSION_RETRIES)
+			rpc_restart_call(task);
+	}
 }
 
 static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
@@ -7921,6 +7928,7 @@ int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt,
 	struct nfs41_bind_conn_to_session_args args = {
 		.client = clp,
 		.dir = NFS4_CDFC4_FORE_OR_BOTH,
+		.retries = 0,
 	};
 	struct nfs41_bind_conn_to_session_res res;
 	struct rpc_message msg = {
@@ -9191,8 +9199,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout)
 	nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0);
 
 	task = rpc_run_task(&task_setup_data);
-	if (IS_ERR(task))
-		return ERR_CAST(task);
+
 	status = rpc_wait_for_completion_task(task);
 	if (status != 0)
 		goto out;

fs/nfs/pnfs.c

@@ -1332,13 +1332,15 @@ _pnfs_return_layout(struct inode *ino)
 			!valid_layout) {
 		spin_unlock(&ino->i_lock);
 		dprintk("NFS: %s no layout segments to return\n", __func__);
-		goto out_put_layout_hdr;
+		goto out_wait_layoutreturn;
 	}
 
 	send = pnfs_prepare_layoutreturn(lo, &stateid, &cred, NULL);
 	spin_unlock(&ino->i_lock);
 	if (send)
 		status = pnfs_send_layoutreturn(lo, &stateid, &cred, IOMODE_ANY, true);
+out_wait_layoutreturn:
+	wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, TASK_UNINTERRUPTIBLE);
 out_put_layout_hdr:
 	pnfs_free_lseg_list(&tmp_list);
 	pnfs_put_layout_hdr(lo);
@@ -1456,18 +1458,15 @@ bool pnfs_roc(struct inode *ino,
 	/* lo ref dropped in pnfs_roc_release() */
 	layoutreturn = pnfs_prepare_layoutreturn(lo, &stateid, &lc_cred, &iomode);
 	/* If the creds don't match, we can't compound the layoutreturn */
-	if (!layoutreturn)
+	if (!layoutreturn || cred_fscmp(cred, lc_cred) != 0)
 		goto out_noroc;
-	if (cred_fscmp(cred, lc_cred) != 0)
-		goto out_noroc_put_cred;
 
 	roc = layoutreturn;
 	pnfs_init_layoutreturn_args(args, lo, &stateid, iomode);
 	res->lrs_present = 0;
 	layoutreturn = false;
-
-out_noroc_put_cred:
 	put_cred(lc_cred);
+
 out_noroc:
 	spin_unlock(&ino->i_lock);
 	rcu_read_unlock();

fs/nfs/super.c

@@ -185,7 +185,7 @@ static int __nfs_list_for_each_server(struct list_head *head,
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(server, head, client_link) {
-		if (!nfs_sb_active(server->super))
+		if (!(server->super && nfs_sb_active(server->super)))
 			continue;
 		rcu_read_unlock();
 		if (last)

include/linux/nfs_xdr.h

@@ -1317,11 +1317,13 @@ struct nfs41_impl_id {
 	struct nfstime4			date;
 };
 
+#define MAX_BIND_CONN_TO_SESSION_RETRIES 3
 struct nfs41_bind_conn_to_session_args {
 	struct nfs_client		*client;
 	struct nfs4_sessionid		sessionid;
 	u32				dir;
 	bool				use_conn_in_rdma_mode;
+	int				retries;
 };
 
 struct nfs41_bind_conn_to_session_res {

include/linux/sunrpc/clnt.h

@@ -71,7 +71,13 @@ struct rpc_clnt {
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	struct dentry		*cl_debugfs;	/* debugfs directory */
 #endif
+	/* cl_work is only needed after cl_xpi is no longer used,
+	 * and that are of similar size
+	 */
+	union {
 		struct rpc_xprt_iter	cl_xpi;
+		struct work_struct	cl_work;
+	};
 	const struct cred	*cl_cred;
 };
 
@@ -236,4 +242,9 @@ static inline int rpc_reply_expected(struct rpc_task *task)
 		(task->tk_msg.rpc_proc->p_decode != NULL);
 }
 
+static inline void rpc_task_close_connection(struct rpc_task *task)
+{
+	if (task->tk_xprt)
+		xprt_force_disconnect(task->tk_xprt);
+}
 #endif /* _LINUX_SUNRPC_CLNT_H */

include/trace/events/rpcrdma.h

@@ -692,11 +692,10 @@ TRACE_EVENT(xprtrdma_prepsend_failed,
 
 TRACE_EVENT(xprtrdma_post_send,
 	TP_PROTO(
-		const struct rpcrdma_req *req,
-		int status
+		const struct rpcrdma_req *req
 	),
 
-	TP_ARGS(req, status),
+	TP_ARGS(req),
 
 	TP_STRUCT__entry(
 		__field(const void *, req)
@@ -705,7 +704,6 @@ TRACE_EVENT(xprtrdma_post_send,
 		__field(unsigned int, client_id)
 		__field(int, num_sge)
 		__field(int, signaled)
-		__field(int, status)
 	),
 
 	TP_fast_assign(
@@ -718,15 +716,13 @@ TRACE_EVENT(xprtrdma_post_send,
 		__entry->sc = req->rl_sendctx;
 		__entry->num_sge = req->rl_wr.num_sge;
 		__entry->signaled = req->rl_wr.send_flags & IB_SEND_SIGNALED;
-		__entry->status = status;
 	),
 
-	TP_printk("task:%u@%u req=%p sc=%p (%d SGE%s) %sstatus=%d",
+	TP_printk("task:%u@%u req=%p sc=%p (%d SGE%s) %s",
 		__entry->task_id, __entry->client_id,
 		__entry->req, __entry->sc, __entry->num_sge,
 		(__entry->num_sge == 1 ? "" : "s"),
-		(__entry->signaled ? "signaled " : ""),
-		__entry->status
+		(__entry->signaled ? "signaled" : "")
 	)
 );
 

net/sunrpc/clnt.c

@@ -880,6 +880,20 @@ EXPORT_SYMBOL_GPL(rpc_shutdown_client);
 /*
  * Free an RPC client
  */
+static void rpc_free_client_work(struct work_struct *work)
+{
+	struct rpc_clnt *clnt = container_of(work, struct rpc_clnt, cl_work);
+
+	/* These might block on processes that might allocate memory,
+	 * so they cannot be called in rpciod, so they are handled separately
+	 * here.
+	 */
+	rpc_clnt_debugfs_unregister(clnt);
+	rpc_clnt_remove_pipedir(clnt);
+
+	kfree(clnt);
+	rpciod_down();
+}
 static struct rpc_clnt *
 rpc_free_client(struct rpc_clnt *clnt)
 {
@@ -890,17 +904,16 @@ rpc_free_client(struct rpc_clnt *clnt)
 			rcu_dereference(clnt->cl_xprt)->servername);
 	if (clnt->cl_parent != clnt)
 		parent = clnt->cl_parent;
-	rpc_clnt_debugfs_unregister(clnt);
-	rpc_clnt_remove_pipedir(clnt);
 	rpc_unregister_client(clnt);
 	rpc_free_iostats(clnt->cl_metrics);
 	clnt->cl_metrics = NULL;
 	xprt_put(rcu_dereference_raw(clnt->cl_xprt));
 	xprt_iter_destroy(&clnt->cl_xpi);
-	rpciod_down();
 	put_cred(clnt->cl_cred);
 	rpc_free_clid(clnt);
-	kfree(clnt);
+
+	INIT_WORK(&clnt->cl_work, rpc_free_client_work);
+	schedule_work(&clnt->cl_work);
 	return parent;
 }
 
@@ -2808,8 +2821,7 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt,
 	task = rpc_call_null_helper(clnt, xprt, NULL,
 			RPC_TASK_SOFT|RPC_TASK_SOFTCONN|RPC_TASK_ASYNC|RPC_TASK_NULLCREDS,
 			&rpc_cb_add_xprt_call_ops, data);
-	if (IS_ERR(task))
-		return PTR_ERR(task);
+
 	rpc_put_task(task);
 success:
 	return 1;

net/sunrpc/xprtrdma/rpc_rdma.c

@@ -388,7 +388,9 @@ static int rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
 	} while (nsegs);
 
 done:
-	return xdr_stream_encode_item_absent(xdr);
+	if (xdr_stream_encode_item_absent(xdr) < 0)
+		return -EMSGSIZE;
+	return 0;
 }
 
 /* Register and XDR encode the Write list. Supports encoding a list
@@ -454,7 +456,9 @@ static int rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt,
 	*segcount = cpu_to_be32(nchunks);
 
 done:
-	return xdr_stream_encode_item_absent(xdr);
+	if (xdr_stream_encode_item_absent(xdr) < 0)
+		return -EMSGSIZE;
+	return 0;
 }
 
 /* Register and XDR encode the Reply chunk. Supports encoding an array
@@ -480,8 +484,11 @@ static int rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 	int nsegs, nchunks;
 	__be32 *segcount;
 
-	if (wtype != rpcrdma_replych)
-		return xdr_stream_encode_item_absent(xdr);
+	if (wtype != rpcrdma_replych) {
+		if (xdr_stream_encode_item_absent(xdr) < 0)
+			return -EMSGSIZE;
+		return 0;
+	}
 
 	seg = req->rl_segments;
 	nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_rcv_buf, 0, wtype, seg);

net/sunrpc/xprtrdma/verbs.c

@@ -289,6 +289,7 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 	case RDMA_CM_EVENT_DISCONNECTED:
 		ep->re_connect_status = -ECONNABORTED;
 disconnected:
+		xprt_force_disconnect(xprt);
 		return rpcrdma_ep_destroy(ep);
 	default:
 		break;
@@ -1355,8 +1356,8 @@ int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 		--ep->re_send_count;
 	}
 
+	trace_xprtrdma_post_send(req);
 	rc = frwr_send(r_xprt, req);
-	trace_xprtrdma_post_send(req, rc);
 	if (rc)
 		return -ENOTCONN;
 	return 0;