[PATCH v3] net: sysctl for RA default route MTU

[Roman Gushchin]

This patch introduces new ipv6 sysctl: ra_default_route_mtu.
If it's set (> 0), it defines per-route MTU for any new default route
received by RA.

This sysctl will help in the following configuration: we want to use
jumbo-frames for internal networks and default ethernet frames for
default route. Per-route MTU can only lower per-link MTU, so link MTU
should be set to ~9000 (statically or via RA).

Due to dynamic nature of RA, setting MTU for default route will require
userspace agent, that will monitor changes of default route
and (re)configure it. Not simple. The suggested sysctl solves this
problem.

Signed-off-by: Roman Gushchin <klamm@xxxxxxxxxxxxxx>
Acked-by: Hannes Frederic Sowa <hannes@xxxxxxxxxxxxxxxxxxx>

---

Changes from v1: add forgotten brace.
Changes from v2: move RA-specific code from route.c to ndisc.c
---
 Documentation/networking/ip-sysctl.txt |  5 +++++
 include/linux/ipv6.h                   |  1 +
 include/uapi/linux/ipv6.h              |  1 +
 net/ipv6/addrconf.c                    | 10 ++++++++++
 net/ipv6/ndisc.c                       |  8 +++++++-
 5 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 071fb18..cf86729 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1349,6 +1349,11 @@ accept_ra_mtu - BOOLEAN
 	Functional default: enabled if accept_ra is enabled.
 			    disabled if accept_ra is disabled.
 
+ra_default_route_mtu - INTEGER
+	Define MTU for any new default route received by RA.
+
+	Functional default: disabled (0).
+
 accept_redirects - BOOLEAN
 	Accept Redirects.
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 82806c6..c7727b5 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -53,6 +53,7 @@ struct ipv6_devconf {
 	__s32           ndisc_notify;
 	__s32		suppress_frag_ndisc;
 	__s32		accept_ra_mtu;
+	__s32		ra_default_route_mtu;
 	struct ipv6_stable_secret {
 		bool initialized;
 		struct in6_addr secret;
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 5efa54a..1d31d70 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -170,6 +170,7 @@ enum {
 	DEVCONF_ACCEPT_RA_FROM_LOCAL,
 	DEVCONF_USE_OPTIMISTIC,
 	DEVCONF_ACCEPT_RA_MTU,
+	DEVCONF_RA_DEFAULT_ROUTE_MTU,
 	DEVCONF_STABLE_SECRET,
 	DEVCONF_MAX
 };
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2660263..15528f7 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -209,6 +209,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.accept_dad		= 1,
 	.suppress_frag_ndisc	= 1,
 	.accept_ra_mtu		= 1,
+	.ra_default_route_mtu	= 0,
 	.stable_secret		= {
 		.initialized = false,
 	}
@@ -250,6 +251,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.accept_dad		= 1,
 	.suppress_frag_ndisc	= 1,
 	.accept_ra_mtu		= 1,
+	.ra_default_route_mtu	= 0,
 	.stable_secret		= {
 		.initialized = false,
 	},
@@ -4583,6 +4585,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc;
 	array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local;
 	array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu;
+	array[DEVCONF_RA_DEFAULT_ROUTE_MTU] = cnf->ra_default_route_mtu;
 	/* we omit DEVCONF_STABLE_SECRET for now */
 }
 
@@ -5576,6 +5579,13 @@ static struct addrconf_sysctl_table
 			.proc_handler	= proc_dointvec,
 		},
 		{
+			.procname	= "ra_default_route_mtu",
+			.data		= &ipv6_devconf.ra_default_route_mtu,
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
+			.proc_handler	= proc_dointvec,
+		},
+		{
 			.procname	= "stable_secret",
 			.data		= &ipv6_devconf.stable_secret,
 			.maxlen		= IPV6_MAX_STRLEN,
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 247ad7c..2a3a564 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1208,6 +1208,11 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 				  "RA: %s failed to add default route\n",
 				  __func__);
 			return;
+		} else {
+			u32 mtu = in6_dev->cnf.ra_default_route_mtu;
+
+			if (mtu && mtu >= IPV6_MIN_MTU && mtu <= in6_dev->cnf.mtu6)
+				dst_metric_set(&rt->dst, RTAX_MTU, mtu);
 		}
 
 		neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr);
@@ -1370,7 +1375,8 @@ skip_routeinfo:
 		} else if (in6_dev->cnf.mtu6 != mtu) {
 			in6_dev->cnf.mtu6 = mtu;
 
-			if (rt)
+			if (rt && (!in6_dev->cnf.ra_default_route_mtu ||
+				   mtu < in6_dev->cnf.ra_default_route_mtu))
 				dst_metric_set(&rt->dst, RTAX_MTU, mtu);
 
 			rt6_mtu_change(skb->dev, mtu);
-- 
2.1.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/