From f9dd09c7f7199685601d75882447a6598be8a3e0 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 6 Nov 2009 00:43:42 -0800 Subject: netfilter: nf_nat: fix NAT issue in 2.6.30.4+ Vitezslav Samel discovered that since 2.6.30.4+ active FTP can not work over NAT. The "cause" of the problem was a fix of unacknowledged data detection with NAT (commit a3a9f79e361e864f0e9d75ebe2a0cb43d17c4272). However, actually, that fix uncovered a long standing bug in TCP conntrack: when NAT was enabled, we simply updated the max of the right edge of the segments we have seen (td_end), by the offset NAT produced with changing IP/port in the data. However, we did not update the other parameter (td_maxend) which is affected by the NAT offset. Thus that could drift away from the correct value and thus resulted breaking active FTP. The patch below fixes the issue by *not* updating the conntrack parameters from NAT, but instead taking into account the NAT offsets in conntrack in a consistent way. (Updating from NAT would be more harder and expensive because it'd need to re-calculate parameters we already calculated in conntrack.) Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/nf_conntrack_core.c | 8 +++++ net/netfilter/nf_conntrack_proto_tcp.c | 64 ++++++++++++++-------------------- 2 files changed, 34 insertions(+), 38 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 7c9ec3dee96..0cdfb388a19 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1350,6 +1350,11 @@ err_stat: return ret; } +s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq); +EXPORT_SYMBOL_GPL(nf_ct_nat_offset); + int nf_conntrack_init(struct net *net) { int ret; @@ -1367,6 +1372,9 @@ int nf_conntrack_init(struct net *net) /* For use by REJECT target */ rcu_assign_pointer(ip_ct_attach, nf_conntrack_attach); rcu_assign_pointer(nf_ct_destroy, destroy_conntrack); + + /* Howto get NAT offsets */ + rcu_assign_pointer(nf_ct_nat_offset, NULL); } return 0; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 97a82ba7537..ba2b7693728 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -492,6 +492,21 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, } } +#ifdef CONFIG_NF_NAT_NEEDED +static inline s16 nat_offset(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq) +{ + typeof(nf_ct_nat_offset) get_offset = rcu_dereference(nf_ct_nat_offset); + + return get_offset != NULL ? get_offset(ct, dir, seq) : 0; +} +#define NAT_OFFSET(pf, ct, dir, seq) \ + (pf == NFPROTO_IPV4 ? nat_offset(ct, dir, seq) : 0) +#else +#define NAT_OFFSET(pf, ct, dir, seq) 0 +#endif + static bool tcp_in_window(const struct nf_conn *ct, struct ip_ct_tcp *state, enum ip_conntrack_dir dir, @@ -506,6 +521,7 @@ static bool tcp_in_window(const struct nf_conn *ct, struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; __u32 seq, ack, sack, end, win, swin; + s16 receiver_offset; bool res; /* @@ -519,11 +535,16 @@ static bool tcp_in_window(const struct nf_conn *ct, if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM) tcp_sack(skb, dataoff, tcph, &sack); + /* Take into account NAT sequence number mangling */ + receiver_offset = NAT_OFFSET(pf, ct, !dir, ack - 1); + ack -= receiver_offset; + sack -= receiver_offset; + pr_debug("tcp_in_window: START\n"); pr_debug("tcp_in_window: "); nf_ct_dump_tuple(tuple); - pr_debug("seq=%u ack=%u sack=%u win=%u end=%u\n", - seq, ack, sack, win, end); + pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n", + seq, ack, receiver_offset, sack, receiver_offset, win, end); pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i " "receiver end=%u maxend=%u maxwin=%u scale=%i\n", sender->td_end, sender->td_maxend, sender->td_maxwin, @@ -613,8 +634,8 @@ static bool tcp_in_window(const struct nf_conn *ct, pr_debug("tcp_in_window: "); nf_ct_dump_tuple(tuple); - pr_debug("seq=%u ack=%u sack =%u win=%u end=%u\n", - seq, ack, sack, win, end); + pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n", + seq, ack, receiver_offset, sack, receiver_offset, win, end); pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i " "receiver end=%u maxend=%u maxwin=%u scale=%i\n", sender->td_end, sender->td_maxend, sender->td_maxwin, @@ -700,7 +721,7 @@ static bool tcp_in_window(const struct nf_conn *ct, before(seq, sender->td_maxend + 1) ? after(end, sender->td_end - receiver->td_maxwin - 1) ? before(sack, receiver->td_end + 1) ? - after(ack, receiver->td_end - MAXACKWINDOW(sender)) ? "BUG" + after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1) ? "BUG" : "ACK is under the lower bound (possible overly delayed ACK)" : "ACK is over the upper bound (ACKed data not seen yet)" : "SEQ is under the lower bound (already ACKed data retransmitted)" @@ -715,39 +736,6 @@ static bool tcp_in_window(const struct nf_conn *ct, return res; } -#ifdef CONFIG_NF_NAT_NEEDED -/* Update sender->td_end after NAT successfully mangled the packet */ -/* Caller must linearize skb at tcp header. */ -void nf_conntrack_tcp_update(const struct sk_buff *skb, - unsigned int dataoff, - struct nf_conn *ct, int dir, - s16 offset) -{ - const struct tcphdr *tcph = (const void *)skb->data + dataoff; - const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[dir]; - const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[!dir]; - __u32 end; - - end = segment_seq_plus_len(ntohl(tcph->seq), skb->len, dataoff, tcph); - - spin_lock_bh(&ct->lock); - /* - * We have to worry for the ack in the reply packet only... - */ - if (ct->proto.tcp.seen[dir].td_end + offset == end) - ct->proto.tcp.seen[dir].td_end = end; - ct->proto.tcp.last_end = end; - spin_unlock_bh(&ct->lock); - pr_debug("tcp_update: sender end=%u maxend=%u maxwin=%u scale=%i " - "receiver end=%u maxend=%u maxwin=%u scale=%i\n", - sender->td_end, sender->td_maxend, sender->td_maxwin, - sender->td_scale, - receiver->td_end, receiver->td_maxend, receiver->td_maxwin, - receiver->td_scale); -} -EXPORT_SYMBOL_GPL(nf_conntrack_tcp_update); -#endif - #define TH_FIN 0x01 #define TH_SYN 0x02 #define TH_RST 0x04 -- cgit v1.2.2 From 539054a8fa5141c9a4e9ac6a86d249e3f2bdef45 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Fri, 6 Nov 2009 18:08:32 -0800 Subject: netfilter: xt_connlimit: fix regression caused by zero family value Commit v2.6.28-rc1~717^2~109^2~2 was slightly incomplete; not all instances of par->match->family were changed to par->family. References: http://bugzilla.netfilter.org/show_bug.cgi?id=610 Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/xt_connlimit.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 68098095439..38f03f75a63 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -103,7 +103,7 @@ static int count_them(struct xt_connlimit_data *data, const struct nf_conntrack_tuple *tuple, const union nf_inet_addr *addr, const union nf_inet_addr *mask, - const struct xt_match *match) + u_int8_t family) { const struct nf_conntrack_tuple_hash *found; struct xt_connlimit_conn *conn; @@ -113,8 +113,7 @@ static int count_them(struct xt_connlimit_data *data, bool addit = true; int matches = 0; - - if (match->family == NFPROTO_IPV6) + if (family == NFPROTO_IPV6) hash = &data->iphash[connlimit_iphash6(addr, mask)]; else hash = &data->iphash[connlimit_iphash(addr->ip & mask->ip)]; @@ -157,8 +156,7 @@ static int count_them(struct xt_connlimit_data *data, continue; } - if (same_source_net(addr, mask, &conn->tuple.src.u3, - match->family)) + if (same_source_net(addr, mask, &conn->tuple.src.u3, family)) /* same source network -> be counted! */ ++matches; nf_ct_put(found_ct); @@ -207,7 +205,7 @@ connlimit_mt(const struct sk_buff *skb, const struct xt_match_param *par) spin_lock_bh(&info->data->lock); connections = count_them(info->data, tuple_ptr, &addr, - &info->mask, par->match); + &info->mask, par->family); spin_unlock_bh(&info->data->lock); if (connections < 0) { -- cgit v1.2.2