diff options
| author | Nicolas Dichtel <nicolas.dichtel@6wind.com> | 2012-10-22 03:42:09 +0000 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2012-10-23 02:38:32 -0400 |
| commit | 51ebd3181572af8d5076808dab2682d800f6da5d (patch) | |
| tree | 41bce53f5ed82791ea5975f6ce708f54729659b4 /net/ipv6/ip6_fib.c | |
| parent | d94ce9b283736a876b2e6dec665c68e5e8b5d55e (diff) | |
ipv6: add support of equal cost multipath (ECMP)
Each nexthop is added like a single route in the routing table. All routes
that have the same metric/weight and destination but not the same gateway
are considering as ECMP routes. They are linked together, through a list called
rt6i_siblings.
ECMP routes can be added in one shot, with RTA_MULTIPATH attribute or one after
the other (in both case, the flag NLM_F_EXCL should not be set).
The patch is based on a previous work from
Luc Saillard <luc.saillard@6wind.com>.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv6/ip6_fib.c')
| -rw-r--r-- | net/ipv6/ip6_fib.c | 57 |
1 files changed, 57 insertions, 0 deletions
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 24995a93ef8c..710cafd2e1a9 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -672,6 +672,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, iter->rt6i_idev == rt->rt6i_idev && ipv6_addr_equal(&iter->rt6i_gateway, &rt->rt6i_gateway)) { + if (rt->rt6i_nsiblings) + rt->rt6i_nsiblings = 0; if (!(iter->rt6i_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->rt6i_flags & RTF_EXPIRES)) @@ -680,6 +682,21 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, rt6_set_expires(iter, rt->dst.expires); return -EEXIST; } + /* If we have the same destination and the same metric, + * but not the same gateway, then the route we try to + * add is sibling to this route, increment our counter + * of siblings, and later we will add our route to the + * list. + * Only static routes (which don't have flag + * RTF_EXPIRES) are used for ECMPv6. + * + * To avoid long list, we only had siblings if the + * route have a gateway. + */ + if (rt->rt6i_flags & RTF_GATEWAY && + !(rt->rt6i_flags & RTF_EXPIRES) && + !(iter->rt6i_flags & RTF_EXPIRES)) + rt->rt6i_nsiblings++; } if (iter->rt6i_metric > rt->rt6i_metric) @@ -692,6 +709,35 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, if (ins == &fn->leaf) fn->rr_ptr = NULL; + /* Link this route to others same route. */ + if (rt->rt6i_nsiblings) { + unsigned int rt6i_nsiblings; + struct rt6_info *sibling, *temp_sibling; + + /* Find the first route that have the same metric */ + sibling = fn->leaf; + while (sibling) { + if (sibling->rt6i_metric == rt->rt6i_metric) { + list_add_tail(&rt->rt6i_siblings, + &sibling->rt6i_siblings); + break; + } + sibling = sibling->dst.rt6_next; + } + /* For each sibling in the list, increment the counter of + * siblings. BUG() if counters does not match, list of siblings + * is broken! + */ + rt6i_nsiblings = 0; + list_for_each_entry_safe(sibling, temp_sibling, + &rt->rt6i_siblings, rt6i_siblings) { + sibling->rt6i_nsiblings++; + BUG_ON(sibling->rt6i_nsiblings != rt->rt6i_nsiblings); + rt6i_nsiblings++; + } + BUG_ON(rt6i_nsiblings != rt->rt6i_nsiblings); + } + /* * insert node */ @@ -1193,6 +1239,17 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, if (fn->rr_ptr == rt) fn->rr_ptr = NULL; + /* Remove this entry from other siblings */ + if (rt->rt6i_nsiblings) { + struct rt6_info *sibling, *next_sibling; + + list_for_each_entry_safe(sibling, next_sibling, + &rt->rt6i_siblings, rt6i_siblings) + sibling->rt6i_nsiblings--; + rt->rt6i_nsiblings = 0; + list_del_init(&rt->rt6i_siblings); + } + /* Adjust walkers */ read_lock(&fib6_walker_lock); FOR_WALKERS(w) { |