diff options
author | David S. Miller <davem@davemloft.net> | 2012-07-26 11:14:38 +0000 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2012-07-26 15:50:39 -0700 |
commit | c6cffba4ffa26a8ffacd0bb9f3144e34f20da7de (patch) | |
tree | b67532a74343d42bcf8784b8e32d7cf6d69313db /net/ipv4/route.c | |
parent | 4487e64de63b8e42efe5a5543871c42c5a5859d9 (diff) | |
download | op-kernel-dev-c6cffba4ffa26a8ffacd0bb9f3144e34f20da7de.zip op-kernel-dev-c6cffba4ffa26a8ffacd0bb9f3144e34f20da7de.tar.gz |
ipv4: Fix input route performance regression.
With the routing cache removal we lost the "noref" code paths on
input, and this can kill some routing workloads.
Reinstate the noref path when we hit a cached route in the FIB
nexthops.
With help from Eric Dumazet.
Reported-by: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/route.c')
-rw-r--r-- | net/ipv4/route.c | 48 |
1 files changed, 22 insertions, 26 deletions
diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3f7bb71..fc1a81c 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1199,10 +1199,9 @@ restart: fnhe->fnhe_stamp = jiffies; } -static inline void rt_release_rcu(struct rcu_head *head) +static inline void rt_free(struct rtable *rt) { - struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); - dst_release(dst); + call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); } static void rt_cache_route(struct fib_nh *nh, struct rtable *rt) @@ -1216,9 +1215,15 @@ static void rt_cache_route(struct fib_nh *nh, struct rtable *rt) prev = cmpxchg(p, orig, rt); if (prev == orig) { - dst_clone(&rt->dst); if (orig) - call_rcu_bh(&orig->dst.rcu_head, rt_release_rcu); + rt_free(orig); + } else { + /* Routes we intend to cache in the FIB nexthop have + * the DST_NOCACHE bit clear. However, if we are + * unsuccessful at storing this route into the cache + * we really need to set it. + */ + rt->dst.flags |= DST_NOCACHE; } } @@ -1245,7 +1250,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif - if (!(rt->dst.flags & DST_HOST)) + if (!(rt->dst.flags & DST_NOCACHE)) rt_cache_route(nh, rt); } @@ -1261,7 +1266,7 @@ static struct rtable *rt_dst_alloc(struct net_device *dev, bool nopolicy, bool noxfrm, bool will_cache) { return dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, - (will_cache ? 0 : DST_HOST) | DST_NOCACHE | + (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | (nopolicy ? DST_NOPOLICY : 0) | (noxfrm ? DST_NOXFRM : 0)); } @@ -1366,8 +1371,7 @@ static void ip_handle_martian_source(struct net_device *dev, static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, struct in_device *in_dev, - __be32 daddr, __be32 saddr, u32 tos, - struct rtable **result) + __be32 daddr, __be32 saddr, u32 tos) { struct rtable *rth; int err; @@ -1418,7 +1422,7 @@ static int __mkroute_input(struct sk_buff *skb, if (!itag) { rth = FIB_RES_NH(*res).nh_rth_input; if (rt_cache_valid(rth)) { - dst_hold(&rth->dst); + skb_dst_set_noref(skb, &rth->dst); goto out; } do_cache = true; @@ -1445,8 +1449,8 @@ static int __mkroute_input(struct sk_buff *skb, rth->dst.output = ip_output; rt_set_nexthop(rth, daddr, res, NULL, res->fi, res->type, itag); + skb_dst_set(skb, &rth->dst); out: - *result = rth; err = 0; cleanup: return err; @@ -1458,21 +1462,13 @@ static int ip_mkroute_input(struct sk_buff *skb, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos) { - struct rtable *rth = NULL; - int err; - #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && res->fi->fib_nhs > 1) fib_select_multipath(res); #endif /* create a routing cache entry */ - err = __mkroute_input(skb, res, in_dev, daddr, saddr, tos, &rth); - if (err) - return err; - - skb_dst_set(skb, &rth->dst); - return 0; + return __mkroute_input(skb, res, in_dev, daddr, saddr, tos); } /* @@ -1588,8 +1584,9 @@ local_input: if (!itag) { rth = FIB_RES_NH(res).nh_rth_input; if (rt_cache_valid(rth)) { - dst_hold(&rth->dst); - goto set_and_out; + skb_dst_set_noref(skb, &rth->dst); + err = 0; + goto out; } do_cache = true; } @@ -1620,7 +1617,6 @@ local_input: } if (do_cache) rt_cache_route(&FIB_RES_NH(res), rth); -set_and_out: skb_dst_set(skb, &rth->dst); err = 0; goto out; @@ -1658,8 +1654,8 @@ martian_source_keep_err: goto out; } -int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev) +int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev) { int res; @@ -1702,7 +1698,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, rcu_read_unlock(); return res; } -EXPORT_SYMBOL(ip_route_input); +EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, |