diff options
Diffstat (limited to 'net/ipv4/route.c')
-rw-r--r-- | net/ipv4/route.c | 48 |
1 files changed, 30 insertions, 18 deletions
diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6ee5354c9aa..2ea6dcc3e2c 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -282,6 +282,8 @@ static struct rtable *rt_cache_get_first(struct seq_file *seq) struct rtable *r = NULL; for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) { + if (!rt_hash_table[st->bucket].chain) + continue; rcu_read_lock_bh(); r = rcu_dereference(rt_hash_table[st->bucket].chain); while (r) { @@ -299,11 +301,14 @@ static struct rtable *__rt_cache_get_next(struct seq_file *seq, struct rtable *r) { struct rt_cache_iter_state *st = seq->private; + r = r->u.dst.rt_next; while (!r) { rcu_read_unlock_bh(); - if (--st->bucket < 0) - break; + do { + if (--st->bucket < 0) + return NULL; + } while (!rt_hash_table[st->bucket].chain); rcu_read_lock_bh(); r = rt_hash_table[st->bucket].chain; } @@ -1104,7 +1109,12 @@ restart: printk("\n"); } #endif - rt_hash_table[hash].chain = rt; + /* + * Since lookup is lockfree, we must make sure + * previous writes to rt are comitted to memory + * before making rt visible to other CPUS. + */ + rcu_assign_pointer(rt_hash_table[hash].chain, rt); spin_unlock_bh(rt_hash_lock_addr(hash)); *rp = rt; return 0; @@ -2356,11 +2366,6 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, ipv4_is_zeronet(oldflp->fl4_src)) goto out; - /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ - dev_out = ip_dev_find(net, oldflp->fl4_src); - if (dev_out == NULL) - goto out; - /* I removed check for oif == dev_out->oif here. It was wrong for two reasons: 1. ip_dev_find(net, saddr) can return wrong iface, if saddr @@ -2372,6 +2377,11 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, if (oldflp->oif == 0 && (ipv4_is_multicast(oldflp->fl4_dst) || oldflp->fl4_dst == htonl(0xFFFFFFFF))) { + /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ + dev_out = ip_dev_find(net, oldflp->fl4_src); + if (dev_out == NULL) + goto out; + /* Special hack: user can direct multicasts and limited broadcast via necessary interface without fiddling with IP_MULTICAST_IF or IP_PKTINFO. @@ -2390,9 +2400,15 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, fl.oif = dev_out->ifindex; goto make_route; } - if (dev_out) + + if (!(oldflp->flags & FLOWI_FLAG_ANYSRC)) { + /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ + dev_out = ip_dev_find(net, oldflp->fl4_src); + if (dev_out == NULL) + goto out; dev_put(dev_out); - dev_out = NULL; + dev_out = NULL; + } } @@ -2840,7 +2856,9 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) if (s_h < 0) s_h = 0; s_idx = idx = cb->args[1]; - for (h = s_h; h <= rt_hash_mask; h++) { + for (h = s_h; h <= rt_hash_mask; h++, s_idx = 0) { + 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++) { @@ -2859,7 +2877,6 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) dst_release(xchg(&skb->dst, NULL)); } rcu_read_unlock_bh(); - s_idx = 0; } done: @@ -2896,8 +2913,6 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, } static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table, - int __user *name, - int nlen, void __user *oldval, size_t __user *oldlenp, void __user *newval, @@ -2960,16 +2975,13 @@ static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write, } static int ipv4_sysctl_rt_secret_interval_strategy(ctl_table *table, - int __user *name, - int nlen, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen) { int old = ip_rt_secret_interval; - int ret = sysctl_jiffies(table, name, nlen, oldval, oldlenp, newval, - newlen); + int ret = sysctl_jiffies(table, oldval, oldlenp, newval, newlen); rt_secret_reschedule(old); |