From b0c110ca8e89f2c9cd52ec7fb1b98c5b7aa78496 Mon Sep 17 00:00:00 2001 From: jamal Date: Sun, 18 Oct 2009 02:12:33 +0000 Subject: net: Fix RPF to work with policy routing Policy routing is not looked up by mark on reverse path filtering. This fixes it. Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 5 ++++- net/ipv4/route.c | 8 ++++---- 2 files changed, 8 insertions(+), 5 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index e2f950592566..aa00398be80e 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -229,14 +229,17 @@ unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, */ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, - struct net_device *dev, __be32 *spec_dst, u32 *itag) + struct net_device *dev, __be32 *spec_dst, + u32 *itag, u32 mark) { struct in_device *in_dev; struct flowi fl = { .nl_u = { .ip4_u = { .daddr = src, .saddr = dst, .tos = tos } }, + .mark = mark, .iif = oif }; + struct fib_result res; int no_addr, rpf; int ret; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bb4199252026..5b1050a5d874 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1854,7 +1854,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto e_inval; spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK); } else if (fib_validate_source(saddr, 0, tos, 0, - dev, &spec_dst, &itag) < 0) + dev, &spec_dst, &itag, 0) < 0) goto e_inval; rth = dst_alloc(&ipv4_dst_ops); @@ -1967,7 +1967,7 @@ static int __mkroute_input(struct sk_buff *skb, err = fib_validate_source(saddr, daddr, tos, FIB_RES_OIF(*res), - in_dev->dev, &spec_dst, &itag); + in_dev->dev, &spec_dst, &itag, skb->mark); if (err < 0) { ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr, saddr); @@ -2141,7 +2141,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, int result; result = fib_validate_source(saddr, daddr, tos, net->loopback_dev->ifindex, - dev, &spec_dst, &itag); + dev, &spec_dst, &itag, skb->mark); if (result < 0) goto martian_source; if (result) @@ -2170,7 +2170,7 @@ brd_input: spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK); else { err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst, - &itag); + &itag, skb->mark); if (err < 0) goto martian_source; if (err) -- cgit v1.2.3 From 9d410c796067686b1e032d54ce475b7055537138 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 30 Oct 2009 05:03:53 +0000 Subject: net: fix sk_forward_alloc corruption On UDP sockets, we must call skb_free_datagram() with socket locked, or risk sk_forward_alloc corruption. This requirement is not respected in SUNRPC. Add a convenient helper, skb_free_datagram_locked() and use it in SUNRPC Reported-by: Francis Moreau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ net/core/datagram.c | 10 +++++++++- net/ipv4/udp.c | 4 +--- net/ipv6/udp.c | 4 +--- net/sunrpc/svcsock.c | 10 +++++----- 5 files changed, 18 insertions(+), 12 deletions(-) (limited to 'net/ipv4') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6aebfceca3eb..bcdd6606f468 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1757,6 +1757,8 @@ extern int skb_copy_datagram_const_iovec(const struct sk_buff *from, int to_offset, int size); extern void skb_free_datagram(struct sock *sk, struct sk_buff *skb); +extern void skb_free_datagram_locked(struct sock *sk, + struct sk_buff *skb); extern int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); extern __wsum skb_checksum(const struct sk_buff *skb, int offset, diff --git a/net/core/datagram.c b/net/core/datagram.c index 1c6cf3a1a4f6..4ade3011bb3c 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -224,6 +224,15 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb) consume_skb(skb); sk_mem_reclaim_partial(sk); } +EXPORT_SYMBOL(skb_free_datagram); + +void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) +{ + lock_sock(sk); + skb_free_datagram(sk, skb); + release_sock(sk); +} +EXPORT_SYMBOL(skb_free_datagram_locked); /** * skb_kill_datagram - Free a datagram skbuff forcibly @@ -752,5 +761,4 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, EXPORT_SYMBOL(datagram_poll); EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec); EXPORT_SYMBOL(skb_copy_datagram_iovec); -EXPORT_SYMBOL(skb_free_datagram); EXPORT_SYMBOL(skb_recv_datagram); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d0d436d6216c..0fa9f70e4b19 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -999,9 +999,7 @@ try_again: err = ulen; out_free: - lock_sock(sk); - skb_free_datagram(sk, skb); - release_sock(sk); + skb_free_datagram_locked(sk, skb); out: return err; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3a60f12b34ed..cf538ed5ef6a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -288,9 +288,7 @@ try_again: err = ulen; out_free: - lock_sock(sk); - skb_free_datagram(sk, skb); - release_sock(sk); + skb_free_datagram_locked(sk, skb); out: return err; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index ccc5e83cae5d..1c246a4f491e 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -111,7 +111,7 @@ static void svc_release_skb(struct svc_rqst *rqstp) rqstp->rq_xprt_ctxt = NULL; dprintk("svc: service %p, releasing skb %p\n", rqstp, skb); - skb_free_datagram(svsk->sk_sk, skb); + skb_free_datagram_locked(svsk->sk_sk, skb); } } @@ -578,7 +578,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) "svc: received unknown control message %d/%d; " "dropping RPC reply datagram\n", cmh->cmsg_level, cmh->cmsg_type); - skb_free_datagram(svsk->sk_sk, skb); + skb_free_datagram_locked(svsk->sk_sk, skb); return 0; } @@ -588,18 +588,18 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb)) { local_bh_enable(); /* checksum error */ - skb_free_datagram(svsk->sk_sk, skb); + skb_free_datagram_locked(svsk->sk_sk, skb); return 0; } local_bh_enable(); - skb_free_datagram(svsk->sk_sk, skb); + skb_free_datagram_locked(svsk->sk_sk, skb); } else { /* we can use it in-place */ rqstp->rq_arg.head[0].iov_base = skb->data + sizeof(struct udphdr); rqstp->rq_arg.head[0].iov_len = len; if (skb_checksum_complete(skb)) { - skb_free_datagram(svsk->sk_sk, skb); + skb_free_datagram_locked(svsk->sk_sk, skb); return 0; } rqstp->rq_xprt_ctxt = skb; -- cgit v1.2.3 From 2e9526b352061ee0fd2a1580a2e3a5af960dabc4 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 30 Oct 2009 05:51:48 +0000 Subject: gre: Fix dev_addr clobbering for gretap Nathan Neulinger noticed that gretap devices get their MAC address from the local IP address, which results in invalid MAC addresses half of the time. This is because gretap is still using the tunnel netdev ops rather than the correct tap netdev ops struct. This patch also fixes changelink to not clobber the MAC address for the gretap case. Signed-off-by: Herbert Xu Acked-by: Stephen Hemminger Tested-by: Nathan Neulinger Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 41ada9904d31..143333852624 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1464,7 +1464,7 @@ static void ipgre_tap_setup(struct net_device *dev) ether_setup(dev); - dev->netdev_ops = &ipgre_netdev_ops; + dev->netdev_ops = &ipgre_tap_netdev_ops; dev->destructor = free_netdev; dev->iflink = 0; @@ -1525,25 +1525,29 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], if (t->dev != dev) return -EEXIST; } else { - unsigned nflags = 0; - t = nt; - if (ipv4_is_multicast(p.iph.daddr)) - nflags = IFF_BROADCAST; - else if (p.iph.daddr) - nflags = IFF_POINTOPOINT; + if (dev->type != ARPHRD_ETHER) { + unsigned nflags = 0; - if ((dev->flags ^ nflags) & - (IFF_POINTOPOINT | IFF_BROADCAST)) - return -EINVAL; + if (ipv4_is_multicast(p.iph.daddr)) + nflags = IFF_BROADCAST; + else if (p.iph.daddr) + nflags = IFF_POINTOPOINT; + + if ((dev->flags ^ nflags) & + (IFF_POINTOPOINT | IFF_BROADCAST)) + return -EINVAL; + } ipgre_tunnel_unlink(ign, t); t->parms.iph.saddr = p.iph.saddr; t->parms.iph.daddr = p.iph.daddr; t->parms.i_key = p.i_key; - memcpy(dev->dev_addr, &p.iph.saddr, 4); - memcpy(dev->broadcast, &p.iph.daddr, 4); + if (dev->type != ARPHRD_ETHER) { + memcpy(dev->dev_addr, &p.iph.saddr, 4); + memcpy(dev->broadcast, &p.iph.daddr, 4); + } ipgre_tunnel_link(ign, t); netdev_state_change(dev); } -- cgit v1.2.3 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 --- include/net/netfilter/nf_conntrack.h | 8 ++--- include/net/netfilter/nf_nat_helper.h | 4 +++ net/ipv4/netfilter/nf_nat_core.c | 3 ++ net/ipv4/netfilter/nf_nat_helper.c | 34 ++++++++++++------ net/netfilter/nf_conntrack_core.c | 8 +++++ net/netfilter/nf_conntrack_proto_tcp.c | 64 ++++++++++++++-------------------- 6 files changed, 67 insertions(+), 54 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index cbdd6284996d..5cf7270e3ffc 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -255,11 +255,9 @@ static inline bool nf_ct_kill(struct nf_conn *ct) } /* These are for NAT. Icky. */ -/* Update TCP window tracking data when NAT mangles the packet */ -extern void nf_conntrack_tcp_update(const struct sk_buff *skb, - unsigned int dataoff, - struct nf_conn *ct, int dir, - s16 offset); +extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq); /* Fake conntrack entry for untracked connections */ extern struct nf_conn nf_conntrack_untracked; diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h index 237a961f40e1..4222220920a5 100644 --- a/include/net/netfilter/nf_nat_helper.h +++ b/include/net/netfilter/nf_nat_helper.h @@ -32,4 +32,8 @@ extern int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, * to port ct->master->saved_proto. */ extern void nf_nat_follow_master(struct nf_conn *ct, struct nf_conntrack_expect *this); + +extern s16 nf_nat_get_offset(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq); #endif diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 68afc6ecd343..fe1a64479dd0 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -750,6 +750,8 @@ static int __init nf_nat_init(void) BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); rcu_assign_pointer(nfnetlink_parse_nat_setup_hook, nfnetlink_parse_nat_setup); + BUG_ON(nf_ct_nat_offset != NULL); + rcu_assign_pointer(nf_ct_nat_offset, nf_nat_get_offset); return 0; cleanup_extend: @@ -764,6 +766,7 @@ static void __exit nf_nat_cleanup(void) nf_ct_extend_unregister(&nat_extend); rcu_assign_pointer(nf_nat_seq_adjust_hook, NULL); rcu_assign_pointer(nfnetlink_parse_nat_setup_hook, NULL); + rcu_assign_pointer(nf_ct_nat_offset, NULL); synchronize_net(); } diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 09172a65d9b6..f9520fa3aba9 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -73,6 +73,28 @@ adjust_tcp_sequence(u32 seq, DUMP_OFFSET(this_way); } +/* Get the offset value, for conntrack */ +s16 nf_nat_get_offset(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq) +{ + struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way; + s16 offset; + + if (!nat) + return 0; + + this_way = &nat->seq[dir]; + spin_lock_bh(&nf_nat_seqofs_lock); + offset = after(seq, this_way->correction_pos) + ? this_way->offset_after : this_way->offset_before; + spin_unlock_bh(&nf_nat_seqofs_lock); + + return offset; +} +EXPORT_SYMBOL_GPL(nf_nat_get_offset); + /* Frobs data inside this packet, which is linear. */ static void mangle_contents(struct sk_buff *skb, unsigned int dataoff, @@ -189,11 +211,6 @@ nf_nat_mangle_tcp_packet(struct sk_buff *skb, adjust_tcp_sequence(ntohl(tcph->seq), (int)rep_len - (int)match_len, ct, ctinfo); - /* Tell TCP window tracking about seq change */ - nf_conntrack_tcp_update(skb, ip_hdrlen(skb), - ct, CTINFO2DIR(ctinfo), - (int)rep_len - (int)match_len); - nf_conntrack_event_cache(IPCT_NATSEQADJ, ct); } return 1; @@ -415,12 +432,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, tcph->seq = newseq; tcph->ack_seq = newack; - if (!nf_nat_sack_adjust(skb, tcph, ct, ctinfo)) - return 0; - - nf_conntrack_tcp_update(skb, ip_hdrlen(skb), ct, dir, seqoff); - - return 1; + return nf_nat_sack_adjust(skb, tcph, ct, ctinfo); } /* Setup NAT on this expected conntrack so it follows master. */ diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 7c9ec3dee96e..0cdfb388a191 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 97a82ba75376..ba2b76937283 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 v1.2.3