From d7dedee184e775f77d321cfa1c660a7680cf6588 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 9 Jan 2018 16:40:25 +0200 Subject: ipv6: Calculate hash thresholds for IPv6 nexthops Before we convert IPv6 to use hash-threshold instead of modulo-N, we first need each nexthop to store its region boundary in the hash function's output space. The boundary is calculated by dividing the output space equally between the different active nexthops. That is, nexthops that are not dead or linkdown. The boundaries are rebalanced whenever a nexthop is added or removed to a multipath route and whenever a nexthop becomes active or inactive. Signed-off-by: Ido Schimmel Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 1 + include/net/ip6_route.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index ddf53dd1e948..97cd05d87780 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -149,6 +149,7 @@ struct rt6_info { */ struct list_head rt6i_siblings; unsigned int rt6i_nsiblings; + atomic_t rt6i_nh_upper_bound; atomic_t rt6i_ref; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 34cd3b0c6ded..27d23a65f3cd 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -66,6 +66,12 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } +static inline bool rt6_qualify_for_ecmp(const struct rt6_info *rt) +{ + return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) == + RTF_GATEWAY; +} + void ip6_route_input(struct sk_buff *skb); struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, @@ -171,6 +177,7 @@ void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); void rt6_sync_up(struct net_device *dev, unsigned int nh_flags); void rt6_disable_ip(struct net_device *dev, unsigned long event); void rt6_sync_down_dev(struct net_device *dev, unsigned long event); +void rt6_multipath_rebalance(struct rt6_info *rt); static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { -- cgit v1.2.3 From 398958ae48f44bb036d0fa9829cd489270bf1fc2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 9 Jan 2018 16:40:28 +0200 Subject: ipv6: Add support for non-equal-cost multipath The use of hash-threshold instead of modulo-N makes it trivial to add support for non-equal-cost multipath. Instead of dividing the multipath hash function's output space equally between the nexthops, each nexthop is assigned a region size which is proportional to its weight. Signed-off-by: Ido Schimmel Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 1 + net/ipv6/route.c | 11 +++++++---- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 97cd05d87780..34ec321d6a03 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -171,6 +171,7 @@ struct rt6_info { u32 rt6i_metric; u32 rt6i_pmtu; /* more non-fragment space at head required */ + int rt6i_nh_weight; unsigned short rt6i_nfheader_len; u8 rt6i_protocol; u8 exception_bucket_flushed:1, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7837b8c754a3..1076ae0ea9d5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2594,6 +2594,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, #endif rt->rt6i_metric = cfg->fc_metric; + rt->rt6i_nh_weight = 1; /* We cannot add true routes via loopback here, they would result in kernel looping; promote them to reject routes @@ -3507,11 +3508,11 @@ static int rt6_multipath_total_weight(const struct rt6_info *rt) int total = 0; if (!rt6_is_dead(rt)) - total++; + total += rt->rt6i_nh_weight; list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) { if (!rt6_is_dead(iter)) - total++; + total += iter->rt6i_nh_weight; } return total; @@ -3522,7 +3523,7 @@ static void rt6_upper_bound_set(struct rt6_info *rt, int *weight, int total) int upper_bound = -1; if (!rt6_is_dead(rt)) { - (*weight)++; + *weight += rt->rt6i_nh_weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31, total) - 1; } @@ -4024,6 +4025,8 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, goto cleanup; } + rt->rt6i_nh_weight = rtnh->rtnh_hops + 1; + err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg); if (err) { dst_release_immediate(&rt->dst); @@ -4246,7 +4249,7 @@ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt) if (!rtnh) goto nla_put_failure; - rtnh->rtnh_hops = 0; + rtnh->rtnh_hops = rt->rt6i_nh_weight - 1; rtnh->rtnh_ifindex = rt->dst.dev ? rt->dst.dev->ifindex : 0; if (rt6_nexthop_info(skb, rt, &flags, true) < 0) -- cgit v1.2.3