diff options
author | H. Peter Anvin <hpa@zytor.com> | 2010-04-29 16:53:17 -0700 |
---|---|---|
committer | H. Peter Anvin <hpa@zytor.com> | 2010-04-29 16:53:17 -0700 |
commit | d9c5841e22231e4e49fd0a1004164e6fce59b7a6 (patch) | |
tree | e1f589c46b3ff79bbe7b1b2469f6362f94576da6 /net/ipv4/route.c | |
parent | x86: Fix LOCK_PREFIX_HERE for uniprocessor build (diff) | |
parent | x86-64: Reduce SMP locks table size (diff) | |
download | linux-dev-d9c5841e22231e4e49fd0a1004164e6fce59b7a6.tar.xz linux-dev-d9c5841e22231e4e49fd0a1004164e6fce59b7a6.zip |
Merge branch 'x86/asm' into x86/atomic
Merge reason:
Conflict between LOCK_PREFIX_HERE and relative alternatives
pointers
Resolved Conflicts:
arch/x86/include/asm/alternative.h
arch/x86/kernel/alternative.c
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Diffstat (limited to 'net/ipv4/route.c')
-rw-r--r-- | net/ipv4/route.c | 130 |
1 files changed, 86 insertions, 44 deletions
diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e446496f564f..cb562fdd9b9a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -90,6 +90,7 @@ #include <linux/jhash.h> #include <linux/rcupdate.h> #include <linux/times.h> +#include <linux/slab.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/protocol.h> @@ -146,7 +147,6 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu); static int rt_garbage_collect(struct dst_ops *ops); -static void rt_emergency_hash_rebuild(struct net *net); static struct dst_ops ipv4_dst_ops = { @@ -287,12 +287,12 @@ static struct rtable *rt_cache_get_first(struct seq_file *seq) if (!rt_hash_table[st->bucket].chain) continue; rcu_read_lock_bh(); - r = rcu_dereference(rt_hash_table[st->bucket].chain); + r = rcu_dereference_bh(rt_hash_table[st->bucket].chain); while (r) { if (dev_net(r->u.dst.dev) == seq_file_net(seq) && r->rt_genid == st->genid) return r; - r = rcu_dereference(r->u.dst.rt_next); + r = rcu_dereference_bh(r->u.dst.rt_next); } rcu_read_unlock_bh(); } @@ -314,7 +314,7 @@ static struct rtable *__rt_cache_get_next(struct seq_file *seq, rcu_read_lock_bh(); r = rt_hash_table[st->bucket].chain; } - return rcu_dereference(r); + return rcu_dereference_bh(r); } static struct rtable *rt_cache_get_next(struct seq_file *seq, @@ -586,7 +586,9 @@ static void __net_exit ip_rt_do_proc_exit(struct net *net) { remove_proc_entry("rt_cache", net->proc_net_stat); remove_proc_entry("rt_cache", net->proc_net); +#ifdef CONFIG_NET_CLS_ROUTE remove_proc_entry("rt_acct", net->proc_net); +#endif } static struct pernet_operations ip_rt_proc_ops __net_initdata = { @@ -778,11 +780,30 @@ static void rt_do_flush(int process_context) #define FRACT_BITS 3 #define ONE (1UL << FRACT_BITS) +/* + * Given a hash chain and an item in this hash chain, + * find if a previous entry has the same hash_inputs + * (but differs on tos, mark or oif) + * Returns 0 if an alias is found. + * Returns ONE if rth has no alias before itself. + */ +static int has_noalias(const struct rtable *head, const struct rtable *rth) +{ + const struct rtable *aux = head; + + while (aux != rth) { + if (compare_hash_inputs(&aux->fl, &rth->fl)) + return 0; + aux = aux->u.dst.rt_next; + } + return ONE; +} + static void rt_check_expire(void) { static unsigned int rover; unsigned int i = rover, goal; - struct rtable *rth, *aux, **rthp; + struct rtable *rth, **rthp; unsigned long samples = 0; unsigned long sum = 0, sum2 = 0; unsigned long delta; @@ -833,15 +854,7 @@ nofree: * attributes don't unfairly skew * the length computation */ - for (aux = rt_hash_table[i].chain;;) { - if (aux == rth) { - length += ONE; - break; - } - if (compare_hash_inputs(&aux->fl, &rth->fl)) - break; - aux = aux->u.dst.rt_next; - } + length += has_noalias(rt_hash_table[i].chain, rth); continue; } } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) @@ -920,10 +933,8 @@ static void rt_secret_rebuild_oneshot(struct net *net) { del_timer_sync(&net->ipv4.rt_secret_timer); rt_cache_invalidate(net); - if (ip_rt_secret_interval) { - net->ipv4.rt_secret_timer.expires += ip_rt_secret_interval; - add_timer(&net->ipv4.rt_secret_timer); - } + if (ip_rt_secret_interval) + mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval); } static void rt_emergency_hash_rebuild(struct net *net) @@ -1071,8 +1082,23 @@ work_done: out: return 0; } +/* + * Returns number of entries in a hash chain that have different hash_inputs + */ +static int slow_chain_length(const struct rtable *head) +{ + int length = 0; + const struct rtable *rth = head; + + while (rth) { + length += has_noalias(head, rth); + rth = rth->u.dst.rt_next; + } + return length >> FRACT_BITS; +} + static int rt_intern_hash(unsigned hash, struct rtable *rt, - struct rtable **rp, struct sk_buff *skb) + struct rtable **rp, struct sk_buff *skb, int ifindex) { struct rtable *rth, **rthp; unsigned long now; @@ -1183,14 +1209,20 @@ restart: rt_free(cand); } } else { - if (chain_length > rt_chain_length_max) { + if (chain_length > rt_chain_length_max && + slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) { struct net *net = dev_net(rt->u.dst.dev); int num = ++net->ipv4.current_rt_cache_rebuild_count; - if (!rt_caching(dev_net(rt->u.dst.dev))) { + if (!rt_caching(net)) { printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n", rt->u.dst.dev->name, num); } - rt_emergency_hash_rebuild(dev_net(rt->u.dst.dev)); + rt_emergency_hash_rebuild(net); + spin_unlock_bh(rt_hash_lock_addr(hash)); + + hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src, + ifindex, rt_genid(net)); + goto restart; } } @@ -1415,7 +1447,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, dev_hold(rt->u.dst.dev); if (rt->idev) in_dev_hold(rt->idev); - rt->u.dst.obsolete = 0; + rt->u.dst.obsolete = -1; rt->u.dst.lastuse = jiffies; rt->u.dst.path = &rt->u.dst; rt->u.dst.neighbour = NULL; @@ -1451,7 +1483,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, &netevent); rt_del(hash, rth); - if (!rt_intern_hash(hash, rt, &rt, NULL)) + if (!rt_intern_hash(hash, rt, &rt, NULL, rt->fl.oif)) ip_rt_put(rt); goto do_next; } @@ -1480,11 +1512,12 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) struct dst_entry *ret = dst; if (rt) { - if (dst->obsolete) { + if (dst->obsolete > 0) { ip_rt_put(rt); ret = NULL; } else if ((rt->rt_flags & RTCF_REDIRECTED) || - rt->u.dst.expires) { + (rt->u.dst.expires && + time_after_eq(jiffies, rt->u.dst.expires))) { unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src, rt->fl.oif, rt_genid(dev_net(dst->dev))); @@ -1700,7 +1733,9 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { - return NULL; + if (rt_is_expired((struct rtable *)dst)) + return NULL; + return dst; } static void ipv4_dst_destroy(struct dst_entry *dst) @@ -1862,7 +1897,8 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (!rth) goto e_nobufs; - rth->u.dst.output= ip_rt_bug; + rth->u.dst.output = ip_rt_bug; + rth->u.dst.obsolete = -1; atomic_set(&rth->u.dst.__refcnt, 1); rth->u.dst.flags= DST_HOST; @@ -1901,7 +1937,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, in_dev_put(in_dev); hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev))); - return rt_intern_hash(hash, rth, NULL, skb); + return rt_intern_hash(hash, rth, NULL, skb, dev->ifindex); e_nobufs: in_dev_put(in_dev); @@ -1988,8 +2024,13 @@ static int __mkroute_input(struct sk_buff *skb, if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is * invalid for proxy arp. DNAT routes are always valid. + * + * Proxy arp feature have been extended to allow, ARP + * replies back to the same interface, to support + * Private VLAN switch technologies. See arp.c. */ - if (out_dev == in_dev) { + if (out_dev == in_dev && + IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) { err = -EINVAL; goto cleanup; } @@ -2023,6 +2064,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->fl.oif = 0; rth->rt_spec_dst= spec_dst; + rth->u.dst.obsolete = -1; rth->u.dst.input = ip_forward; rth->u.dst.output = ip_output; rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev)); @@ -2062,7 +2104,7 @@ static int ip_mkroute_input(struct sk_buff *skb, /* put it into the cache */ hash = rt_hash(daddr, saddr, fl->iif, rt_genid(dev_net(rth->u.dst.dev))); - return rt_intern_hash(hash, rth, NULL, skb); + return rt_intern_hash(hash, rth, NULL, skb, fl->iif); } /* @@ -2187,6 +2229,7 @@ local_input: goto e_nobufs; rth->u.dst.output= ip_rt_bug; + rth->u.dst.obsolete = -1; rth->rt_genid = rt_genid(net); atomic_set(&rth->u.dst.__refcnt, 1); @@ -2218,7 +2261,7 @@ local_input: } rth->rt_type = res.type; hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net)); - err = rt_intern_hash(hash, rth, NULL, skb); + err = rt_intern_hash(hash, rth, NULL, skb, fl.iif); goto done; no_route: @@ -2413,6 +2456,7 @@ static int __mkroute_output(struct rtable **result, rth->rt_spec_dst= fl->fl4_src; rth->u.dst.output=ip_output; + rth->u.dst.obsolete = -1; rth->rt_genid = rt_genid(dev_net(dev_out)); RT_CACHE_STAT_INC(out_slow_tot); @@ -2464,7 +2508,7 @@ static int ip_mkroute_output(struct rtable **rp, if (err == 0) { hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif, rt_genid(dev_net(dev_out))); - err = rt_intern_hash(hash, rth, rp, NULL); + err = rt_intern_hash(hash, rth, rp, NULL, oldflp->oif); } return err; @@ -2687,8 +2731,8 @@ int __ip_route_output_key(struct net *net, struct rtable **rp, hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif, rt_genid(net)); rcu_read_lock_bh(); - for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; - rth = rcu_dereference(rth->u.dst.rt_next)) { + for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth; + rth = rcu_dereference_bh(rth->u.dst.rt_next)) { if (rth->fl.fl4_dst == flp->fl4_dst && rth->fl.fl4_src == flp->fl4_src && rth->fl.iif == 0 && @@ -3006,8 +3050,8 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!rt_hash_table[h].chain) continue; rcu_read_lock_bh(); - for (rt = rcu_dereference(rt_hash_table[h].chain), idx = 0; rt; - rt = rcu_dereference(rt->u.dst.rt_next), idx++) { + for (rt = rcu_dereference_bh(rt_hash_table[h].chain), idx = 0; rt; + rt = rcu_dereference_bh(rt->u.dst.rt_next), idx++) { if (!net_eq(dev_net(rt->u.dst.dev), net) || idx < s_idx) continue; if (rt_is_expired(rt)) @@ -3070,22 +3114,20 @@ static void rt_secret_reschedule(int old) rtnl_lock(); for_each_net(net) { int deleted = del_timer_sync(&net->ipv4.rt_secret_timer); + long time; if (!new) continue; if (deleted) { - long time = net->ipv4.rt_secret_timer.expires - jiffies; + time = net->ipv4.rt_secret_timer.expires - jiffies; if (time <= 0 || (time += diff) <= 0) time = 0; - - net->ipv4.rt_secret_timer.expires = time; } else - net->ipv4.rt_secret_timer.expires = new; + time = new; - net->ipv4.rt_secret_timer.expires += jiffies; - add_timer(&net->ipv4.rt_secret_timer); + mod_timer(&net->ipv4.rt_secret_timer, jiffies + time); } rtnl_unlock(); } @@ -3327,7 +3369,7 @@ static __net_initdata struct pernet_operations rt_secret_timer_ops = { #ifdef CONFIG_NET_CLS_ROUTE -struct ip_rt_acct *ip_rt_acct __read_mostly; +struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; #endif /* CONFIG_NET_CLS_ROUTE */ static __initdata unsigned long rhash_entries; |