Received-SPF: pass (google.com: domain of linux-nfs-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
From:   "NeilBrown" <neilb@suse.de>
To:     "Steve Dickson" <steved@redhat.com>
Cc:     "Linux NFS Mailing List" <linux-nfs@vger.kernel.org>
Subject: [PATCH nfs-utils - v2] nfsd: allow server scope to be set with config
 or command line.
In-reply-to: <166848711530.4614.10805714091203567578@noble.neil.brown.name>
References: <166813011417.19313.12216066495338584736@noble.neil.brown.name>,
 <166848711530.4614.10805714091203567578@noble.neil.brown.name>
Date:   Tue, 15 Nov 2022 15:40:01 +1100
Message-id: <166848720192.4614.15106591314080263893@noble.neil.brown.name>
Precedence: bulk


NFSv4.1 and later require the server to report a "scope".  Servers with
the same scope are expected to understand each other's state ids etc,
though may not accept them - this ensure there can be no
misunderstanding.  This is helpful for migration.

Servers with different scope are known to be different and if a server
appears to change scope on a restart, lock recovery must not be
attempted.

It is important for fail-over configurations to have the same scope for
all server instances.  Linux NFSD sets scope to host name.  It is common
for fail-over configurations to use different host names on different
server nodes.  So the default is not good for these configurations and
must be over-ridden.

As discussed in
  https://github.com/ClusterLabs/resource-agents/issues/1644
some HA management tools attempt to address this with calls to "unshare"
and "hostname" before running "rpc.nfsd".  This is unnecessarily
cumbersome.

This patch adds a "-S" command-line option and nfsd.scope config value
so that the scope can be set easily for nfsd.

Signed-off-by: NeilBrown <neilb@suse.de>
---
 systemd/nfs.conf.man |  1 +
 utils/nfsd/nfsd.c    | 17 ++++++++++++++++-
 utils/nfsd/nfsd.man  | 13 ++++++++++++-
 3 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/systemd/nfs.conf.man b/systemd/nfs.conf.man
index b95c05a68759..bfd3380ff081 100644
--- a/systemd/nfs.conf.man
+++ b/systemd/nfs.conf.man
@@ -172,6 +172,7 @@ for details.
 Recognized values:
 .BR threads ,
 .BR host ,
+.BR scope ,
 .BR port ,
 .BR grace-time ,
 .BR lease-time ,
diff --git a/utils/nfsd/nfsd.c b/utils/nfsd/nfsd.c
index 4016a761293b..249df00b448d 100644
--- a/utils/nfsd/nfsd.c
+++ b/utils/nfsd/nfsd.c
@@ -23,6 +23,7 @@
 #include <sys/socket.h>
 #include <netinet/in.h>
 #include <arpa/inet.h>
+#include <sched.h>
=20
 #include "conffile.h"
 #include "nfslib.h"
@@ -39,6 +40,7 @@ static void	usage(const char *);
 static struct option longopts[] =3D
 {
 	{ "host", 1, 0, 'H' },
+	{ "scope", 1, 0, 'S'},
 	{ "help", 0, 0, 'h' },
 	{ "no-nfs-version", 1, 0, 'N' },
 	{ "nfs-version", 1, 0, 'V' },
@@ -69,6 +71,7 @@ main(int argc, char **argv)
 	int	count =3D NFSD_NPROC, c, i, error =3D 0, portnum, fd, found_one;
 	char *p, *progname, *port, *rdma_port =3D NULL;
 	char **haddr =3D NULL;
+	char *scope =3D NULL;
 	int hcounter =3D 0;
 	struct conf_list *hosts;
 	int	socket_up =3D 0;
@@ -168,8 +171,9 @@ main(int argc, char **argv)
 			hcounter++;
 		}
 	}
+	scope =3D conf_get_str("nfsd", "scope");
=20
-	while ((c =3D getopt_long(argc, argv, "dH:hN:V:p:P:stTuUrG:L:", longopts, N=
ULL)) !=3D EOF) {
+	while ((c =3D getopt_long(argc, argv, "dH:S:hN:V:p:P:stTuUrG:L:", longopts,=
 NULL)) !=3D EOF) {
 		switch(c) {
 		case 'd':
 			xlog_config(D_ALL, 1);
@@ -190,6 +194,9 @@ main(int argc, char **argv)
 			haddr[hcounter] =3D optarg;
 			hcounter++;
 			break;
+		case 'S':
+			scope =3D optarg;
+			break;
 		case 'P':	/* XXX for nfs-server compatibility */
 		case 'p':
 			/* only the last -p option has any effect */
@@ -367,6 +374,14 @@ main(int argc, char **argv)
 	if (lease  > 0)
 		nfssvc_set_time("lease", lease);
=20
+	if (scope) {
+		if (unshare(CLONE_NEWUTS) < 0 ||
+		    sethostname(scope, strlen(scope)) < 0) {
+			xlog(L_ERROR, "Unable to set server scope: %m");
+			error =3D -1;
+			goto out;
+		}
+	}
 	i =3D 0;
 	do {
 		error =3D nfssvc_set_sockets(protobits, haddr[i], port);
diff --git a/utils/nfsd/nfsd.man b/utils/nfsd/nfsd.man
index bb99fe2b1d89..dc05f3623465 100644
--- a/utils/nfsd/nfsd.man
+++ b/utils/nfsd/nfsd.man
@@ -35,9 +35,17 @@ Note that
 .B lockd
 (which performs file locking services for NFS) may still accept
 request on all known network addresses.  This may change in future
-releases of the Linux Kernel. This option can be used multiple time=20
+releases of the Linux Kernel. This option can be used multiple times
 to listen to more than one interface.
 .TP
+.B \S " or " \-\-scope scope
+NFSv4.1 and later require the server to report a "scope" which is used
+by the clients to detect if two connections are to the same server.
+By default Linux NFSD uses the host name as the scope.
+.sp
+It is particularly important for high-availablity configurations to ensure
+that all potential server nodes report the same server scope.
+.TP
 .B \-p " or " \-\-port  port
 specify a different port to listen on for NFS requests. By default,
 .B rpc.nfsd
@@ -134,6 +142,9 @@ will listen on.  Use of the
 .B --host
 option replaces all host names listed here.
 .TP
+.B scope
+Set the server scope.
+.TP
 .B grace-time
 The grace time, for both NFSv4 and NLM, in seconds.
 .TP
--=20
2.38.1