Re: [PATCH v2] net: sysctl for RA default route MTU

[Denis Kirjanov <kda@linux-powerpc.org>]

On 3/25/15, Roman Gushchin <klamm@yandex-team.ru> wrote:
> 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@yandex-team.ru>

It's net-next material

> ---
>
> Changes from v1: add forgotten brace.
> ---
>  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                       |  3 ++-
>  net/ipv6/route.c                       |  8 ++++++++
>  6 files changed, 27 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/networking/ip-sysctl.txt
> b/Documentation/networking/ip-sysctl.txt
> index 1b8c964..c013dda 100644
> --- a/Documentation/networking/ip-sysctl.txt
> +++ b/Documentation/networking/ip-sysctl.txt
> @@ -1316,6 +1316,11 @@ 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 4d5169f..b310c9f 100644
> --- a/include/linux/ipv6.h
> +++ b/include/linux/ipv6.h
> @@ -40,6 +40,7 @@ struct ipv6_devconf {
>  	__s32		proxy_ndp;
>  	__s32		accept_source_route;
>  	__s32		accept_ra_from_local;
> +	__s32		ra_default_route_mtu;
>  #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
>  	__s32		optimistic_dad;
>  	__s32		use_optimistic;
> diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
> index 437a6a4..4539c31 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_MAX
>  };
>
> diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
> index b603002..322dd733 100644
> --- a/net/ipv6/addrconf.c
> +++ b/net/ipv6/addrconf.c
> @@ -189,6 +189,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly =
> {
>  	.accept_ra_defrtr	= 1,
>  	.accept_ra_from_local	= 0,
>  	.accept_ra_pinfo	= 1,
> +	.ra_default_route_mtu	= 0,
>  #ifdef CONFIG_IPV6_ROUTER_PREF
>  	.accept_ra_rtr_pref	= 1,
>  	.rtr_probe_interval	= 60 * HZ,
> @@ -240,6 +241,7 @@ 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,
>  };
>
>  /* Check if a valid qdisc is available */
> @@ -4398,6 +4400,7 @@ 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;
>  }
>
>  static inline size_t inet6_ifla6_size(void)
> @@ -5315,6 +5318,13 @@ 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,
> +		},
> +		{
>  			/* sentinel */
>  		}
>  	},
> diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
> index 471ed24..c70ab44 100644
> --- a/net/ipv6/ndisc.c
> +++ b/net/ipv6/ndisc.c
> @@ -1362,7 +1362,8 @@ 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);
> diff --git a/net/ipv6/route.c b/net/ipv6/route.c
> index 4688bd4..6394adf 100644
> --- a/net/ipv6/route.c
> +++ b/net/ipv6/route.c
> @@ -1714,6 +1714,14 @@ int ip6_route_add(struct fib6_config *cfg)
>
>  	rt->rt6i_flags = cfg->fc_flags;
>
> +	if ((cfg->fc_flags & (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)) ==
> +	    (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)) {
> +		u32 mtu = idev->cnf.ra_default_route_mtu;
> +
> +		if (mtu && mtu >= IPV6_MIN_MTU && mtu <= idev->cnf.mtu6)
> +			dst_metric_set(&rt->dst, RTAX_MTU, mtu);
> +	}
> +
>  install_route:
>  	rt->dst.dev = dev;
>  	rt->rt6i_idev = idev;
> --
> 2.1.0
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>