Commit a6db4494 authored by David Ahern's avatar David Ahern Committed by David S. Miller
Browse files

net: ipv4: Consider failed nexthops in multipath routes 



Multipath route lookups should consider knowledge about next hops and not
select a hop that is known to be failed.

Example:

                     [h2]                   [h3]   15.0.0.5
                      |                      |
                     3|                     3|
                    [SP1]                  [SP2]--+
                     1  2                   1     2
                     |  |     /-------------+     |
                     |   \   /                    |
                     |     X                      |
                     |    / \                     |
                     |   /   \---------------\    |
                     1  2                     1   2
         12.0.0.2  [TOR1] 3-----------------3 [TOR2] 12.0.0.3
                     4                         4
                      \                       /
                        \                    /
                         \                  /
                          -------|   |-----/
                                 1   2
                                [TOR3]
                                  3|
                                   |
                                  [h1]  12.0.0.1

host h1 with IP 12.0.0.1 has 2 paths to host h3 at 15.0.0.5:

    root@h1:~# ip ro ls
    ...
    12.0.0.0/24 dev swp1  proto kernel  scope link  src 12.0.0.1
    15.0.0.0/16
            nexthop via 12.0.0.2  dev swp1 weight 1
            nexthop via 12.0.0.3  dev swp1 weight 1
    ...

If the link between tor3 and tor1 is down and the link between tor1
and tor2 then tor1 is effectively cut-off from h1. Yet the route lookups
in h1 are alternating between the 2 routes: ping 15.0.0.5 gets one and
ssh 15.0.0.5 gets the other. Connections that attempt to use the
12.0.0.2 nexthop fail since that neighbor is not reachable:

    root@h1:~# ip neigh show
    ...
    12.0.0.3 dev swp1 lladdr 00:02:00:00:00:1b REACHABLE
    12.0.0.2 dev swp1  FAILED
    ...

The failed path can be avoided by considering known neighbor information
when selecting next hops. If the neighbor lookup fails we have no
knowledge about the nexthop, so give it a shot. If there is an entry
then only select the nexthop if the state is sane. This is similar to
what fib_detect_death does.

To maintain backward compatibility use of the neighbor information is
based on a new sysctl, fib_multipath_use_neigh.

Signed-off-by: default avatarDavid Ahern <dsa@cumulusnetworks.com>
Reviewed-by: default avatarJulian Anastasov <ja@ssi.bg>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 0b0e30c6

Documentation/networking/ip-sysctl.txt

+10 −0
Original line number Diff line number Diff line
@@ -63,6 +63,16 @@ fwmark_reflect - BOOLEAN 
	fwmark of the packet they are replying to.

	Default: 0



fib_multipath_use_neigh - BOOLEAN

	Use status of existing neighbor entry when determining nexthop for

	multipath routes. If disabled, neighbor information is not used and

	packets could be directed to a failed nexthop. Only valid for kernels

	built with CONFIG_IP_ROUTE_MULTIPATH enabled.

	Default: 0 (disabled)

	Possible values:

	0 - disabled

	1 - enabled



route/max_size - INTEGER

	Maximum number of routes allowed in the kernel.  Increase

	this when using large numbers of interfaces and/or routes.

include/net/netns/ipv4.h

+3 −0
Original line number Diff line number Diff line
@@ -132,6 +132,9 @@ struct netns_ipv4 { 
	struct list_head	mr_tables;

	struct fib_rules_ops	*mr_rules_ops;

#endif

#endif

#ifdef CONFIG_IP_ROUTE_MULTIPATH

	int sysctl_fib_multipath_use_neigh;

#endif

	atomic_t	rt_genid;

};

net/ipv4/fib_semantics.c

+29 −5
Original line number Diff line number Diff line
@@ -1559,21 +1559,45 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags) 
}



#ifdef CONFIG_IP_ROUTE_MULTIPATH

static bool fib_good_nh(const struct fib_nh *nh)

{

	int state = NUD_REACHABLE;



	if (nh->nh_scope == RT_SCOPE_LINK) {

		struct neighbour *n;



		rcu_read_lock_bh();



		n = __ipv4_neigh_lookup_noref(nh->nh_dev, nh->nh_gw);

		if (n)

			state = n->nud_state;



		rcu_read_unlock_bh();

	}



	return !!(state & NUD_VALID);

}



void fib_select_multipath(struct fib_result *res, int hash)

{

	struct fib_info *fi = res->fi;

	struct net *net = fi->fib_net;

	bool first = false;



	for_nexthops(fi) {

		if (hash > atomic_read(&nh->nh_upper_bound))

			continue;



		if (!net->ipv4.sysctl_fib_multipath_use_neigh ||

		    fib_good_nh(nh)) {

			res->nh_sel = nhsel;

			return;

		}

		if (!first) {

			res->nh_sel = nhsel;

			first = true;

		}

	} endfor_nexthops(fi);



	/* Race condition: route has just become dead. */

	res->nh_sel = 0;

}

#endif

net/ipv4/sysctl_net_ipv4.c

+11 −0
Original line number Diff line number Diff line
@@ -960,6 +960,17 @@ static struct ctl_table ipv4_net_table[] = { 
		.mode		= 0644,

		.proc_handler	= proc_dointvec,

	},

#ifdef CONFIG_IP_ROUTE_MULTIPATH

	{

		.procname	= "fib_multipath_use_neigh",

		.data		= &init_net.ipv4.sysctl_fib_multipath_use_neigh,

		.maxlen		= sizeof(int),

		.mode		= 0644,

		.proc_handler	= proc_dointvec_minmax,

		.extra1		= &zero,

		.extra2		= &one,

	},

#endif

	{ }

};

CRA Git | Maintained and supported by SUSTech CRA and CCSE