diff options
Diffstat (limited to 'net/ipv4')
58 files changed, 426 insertions, 512 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 864009643675..5750a2b2a0d6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1007,7 +1007,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, sk->sk_protocol, - inet->sport, inet->dport, sk); + inet->sport, inet->dport, sk, 0); if (err) return err; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 7b068a891953..0072d79f0c2a 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -49,7 +49,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) err = ip_route_connect(&rt, usin->sin_addr.s_addr, saddr, RT_CONN_FLAGS(sk), oif, sk->sk_protocol, - inet->sport, usin->sin_port, sk); + inet->sport, usin->sin_port, sk, 1); if (err) return err; if ((rt->rt_flags & RTCF_BROADCAST) && !sock_flag(sk, SOCK_BROADCAST)) { diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 480ace9819f6..c40203640966 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1140,7 +1140,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, nlh = nlmsg_put(skb, pid, seq, event, sizeof(*ifm), flags); if (nlh == NULL) - return -ENOBUFS; + return -EMSGSIZE; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; @@ -1167,7 +1167,8 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, return nlmsg_end(skb, nlh); nla_put_failure: - return nlmsg_cancel(skb, nlh); + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) @@ -1225,9 +1226,12 @@ static void rtmsg_ifa(int event, struct in_ifaddr* ifa, struct nlmsghdr *nlh, goto errout; err = inet_fill_ifaddr(skb, ifa, pid, seq, event, 0); - /* failure implies BUG in inet_nlmsg_size() */ - BUG_ON(err < 0); - + if (err < 0) { + /* -EMSGSIZE implies BUG in inet_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } err = rtnl_notify(skb, pid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); errout: if (err < 0) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e63b8a98fb4d..be1028c9933e 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -314,9 +314,12 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, err = fib_dump_info(skb, info->pid, seq, event, tb_id, fa->fa_type, fa->fa_scope, key, dst_len, fa->fa_tos, fa->fa_info, 0); - /* failure implies BUG in fib_nlmsg_size() */ - BUG_ON(err < 0); - + if (err < 0) { + /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } err = rtnl_notify(skb, info->pid, RTNLGRP_IPV4_ROUTE, info->nlh, GFP_KERNEL); errout: @@ -960,7 +963,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, nlh = nlmsg_put(skb, pid, seq, event, sizeof(*rtm), flags); if (nlh == NULL) - return -ENOBUFS; + return -EMSGSIZE; rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET; @@ -1031,7 +1034,8 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, return nlmsg_end(skb, nlh); nla_put_failure: - return nlmsg_cancel(skb, nlh); + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } /* diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 0017ccb01d6d..024ae56cab25 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -455,6 +455,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, skb = add_grhead(skb, pmc, type, &pgr); first = 0; } + if (!skb) + return NULL; psrc = (__be32 *)skb_put(skb, sizeof(__be32)); *psrc = psf->sf_inaddr; scount++; stotal++; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 77761ac4f7bb..8aa7d51e6881 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -153,7 +153,7 @@ static int inet_csk_diag_fill(struct sock *sk, rtattr_failure: nlmsg_failure: skb_trim(skb, b - skb->data); - return -1; + return -EMSGSIZE; } static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, @@ -209,7 +209,7 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, return skb->len; nlmsg_failure: skb_trim(skb, previous_tail - skb->data); - return -1; + return -EMSGSIZE; } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, @@ -274,11 +274,14 @@ static int inet_diag_get_exact(struct sk_buff *in_skb, if (!rep) goto out; - if (sk_diag_fill(sk, rep, req->idiag_ext, - NETLINK_CB(in_skb).pid, - nlh->nlmsg_seq, 0, nlh) <= 0) - BUG(); - + err = sk_diag_fill(sk, rep, req->idiag_ext, + NETLINK_CB(in_skb).pid, + nlh->nlmsg_seq, 0, nlh); + if (err < 0) { + WARN_ON(err == -EMSGSIZE); + kfree_skb(rep); + goto out; + } err = netlink_unicast(idiagnl, rep, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); if (err > 0) @@ -775,7 +778,7 @@ next_normal: struct inet_timewait_sock *tw; inet_twsk_for_each(tw, node, - &hashinfo->ehash[i + hashinfo->ehash_size].chain) { + &head->twchain) { if (num < s_num) goto next_dying; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 8c79c8a4ea5c..150ace18dc75 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -212,7 +212,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, write_lock(&head->lock); /* Check TIME-WAIT sockets first. */ - sk_for_each(sk2, node, &(head + hinfo->ehash_size)->chain) { + sk_for_each(sk2, node, &head->twchain) { tw = inet_twsk(sk2); if (INET_TW_MATCH(sk2, hash, acookie, saddr, daddr, ports, dif)) { diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 9f414e35c488..a73cf93cee36 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -78,8 +78,8 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, if (__sk_del_node_init(sk)) sock_prot_dec_use(sk->sk_prot); - /* Step 3: Hash TW into TIMEWAIT half of established hash table. */ - inet_twsk_add_node(tw, &(ehead + hashinfo->ehash_size)->chain); + /* Step 3: Hash TW into TIMEWAIT chain. */ + inet_twsk_add_node(tw, &ehead->twchain); atomic_inc(&tw->tw_refcnt); write_unlock(&ehead->lock); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 476cb6084c75..51c83500790f 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1008,7 +1008,8 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) goto done; dev = t->dev; } - err = unregister_netdevice(dev); + unregister_netdevice(dev); + err = 0; break; default: diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 9d719d664e5b..da8bbd20c7ed 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -754,7 +754,8 @@ ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) goto done; dev = t->dev; } - err = unregister_netdevice(dev); + unregister_netdevice(dev); + err = 0; break; default: diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 47bd3ad18b71..9b08e7ad71bc 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -361,32 +361,6 @@ config IP_NF_TARGET_ULOG To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_TCPMSS - tristate "TCPMSS target support" - depends on IP_NF_IPTABLES - ---help--- - This option adds a `TCPMSS' target, which allows you to alter the - MSS value of TCP SYN packets, to control the maximum size for that - connection (usually limiting it to your outgoing interface's MTU - minus 40). - - This is used to overcome criminally braindead ISPs or servers which - block ICMP Fragmentation Needed packets. The symptoms of this - problem are that everything works fine from your Linux - firewall/router, but machines behind it can never exchange large - packets: - 1) Web browsers connect, then hang with no data received. - 2) Small mail works fine, but large emails hang. - 3) ssh works fine, but scp hangs after initial handshaking. - - Workaround: activate this option and add a rule to your firewall - configuration like: - - iptables -A FORWARD -p tcp --tcp-flags SYN,RST SYN \ - -j TCPMSS --clamp-mss-to-pmtu - - To compile it as a module, choose M here. If unsure, say N. - # NAT + specific targets: ip_conntrack config IP_NF_NAT tristate "Full NAT" diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 16d177b71bf8..6625ec68180c 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -103,7 +103,6 @@ obj-$(CONFIG_IP_NF_TARGET_SAME) += ipt_SAME.o obj-$(CONFIG_IP_NF_NAT_SNMP_BASIC) += ip_nat_snmp_basic.o obj-$(CONFIG_IP_NF_TARGET_LOG) += ipt_LOG.o obj-$(CONFIG_IP_NF_TARGET_ULOG) += ipt_ULOG.o -obj-$(CONFIG_IP_NF_TARGET_TCPMSS) += ipt_TCPMSS.o obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o obj-$(CONFIG_IP_NF_TARGET_TTL) += ipt_TTL.o diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c index 06e4e8a6dd9f..c34f48fe5478 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c @@ -50,12 +50,9 @@ static DEFINE_RWLOCK(tcp_lock); If it's non-zero, we mark only out of window RST segments as INVALID. */ int ip_ct_tcp_be_liberal __read_mostly = 0; -/* When connection is picked up from the middle, how many packets are required - to pass in each direction when we assume we are in sync - if any side uses - window scaling, we lost the game. - If it is set to zero, we disable picking up already established +/* If it is set to zero, we disable picking up already established connections. */ -int ip_ct_tcp_loose __read_mostly = 3; +int ip_ct_tcp_loose __read_mostly = 1; /* Max number of the retransmitted packets without receiving an (acceptable) ACK from the destination. If this number is reached, a shorter timer @@ -694,11 +691,10 @@ static int tcp_in_window(struct ip_ct_tcp *state, before(sack, receiver->td_end + 1), after(ack, receiver->td_end - MAXACKWINDOW(sender))); - if (sender->loose || receiver->loose || - (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)))) { + if (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))) { /* * Take into account window scaling (RFC 1323). */ @@ -743,15 +739,13 @@ static int tcp_in_window(struct ip_ct_tcp *state, state->retrans = 0; } } - /* - * Close the window of disabled window tracking :-) - */ - if (sender->loose) - sender->loose--; - res = 1; } else { - if (LOG_INVALID(IPPROTO_TCP)) + res = 0; + if (sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL || + ip_ct_tcp_be_liberal) + res = 1; + if (!res && LOG_INVALID(IPPROTO_TCP)) nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_tcp: %s ", before(seq, sender->td_maxend + 1) ? @@ -762,8 +756,6 @@ static int tcp_in_window(struct ip_ct_tcp *state, : "ACK is over the upper bound (ACKed data not seen yet)" : "SEQ is under the lower bound (already ACKed data retransmitted)" : "SEQ is over the upper bound (over the window of the receiver)"); - - res = ip_ct_tcp_be_liberal; } DEBUGP("tcp_in_window: res=%i sender end=%u maxend=%u maxwin=%u " @@ -1105,8 +1097,6 @@ static int tcp_new(struct ip_conntrack *conntrack, tcp_options(skb, iph, th, &conntrack->proto.tcp.seen[0]); conntrack->proto.tcp.seen[1].flags = 0; - conntrack->proto.tcp.seen[0].loose = - conntrack->proto.tcp.seen[1].loose = 0; } else if (ip_ct_tcp_loose == 0) { /* Don't try to pick up connections. */ return 0; @@ -1127,11 +1117,11 @@ static int tcp_new(struct ip_conntrack *conntrack, conntrack->proto.tcp.seen[0].td_maxwin; conntrack->proto.tcp.seen[0].td_scale = 0; - /* We assume SACK. Should we assume window scaling too? */ + /* We assume SACK and liberal window checking to handle + * window scaling */ conntrack->proto.tcp.seen[0].flags = - conntrack->proto.tcp.seen[1].flags = IP_CT_TCP_FLAG_SACK_PERM; - conntrack->proto.tcp.seen[0].loose = - conntrack->proto.tcp.seen[1].loose = ip_ct_tcp_loose; + conntrack->proto.tcp.seen[1].flags = IP_CT_TCP_FLAG_SACK_PERM | + IP_CT_TCP_FLAG_BE_LIBERAL; } conntrack->proto.tcp.seen[1].td_end = 0; diff --git a/net/ipv4/netfilter/ip_nat_core.c b/net/ipv4/netfilter/ip_nat_core.c index 9d1a5175dcd4..5e08c2bf887d 100644 --- a/net/ipv4/netfilter/ip_nat_core.c +++ b/net/ipv4/netfilter/ip_nat_core.c @@ -246,8 +246,9 @@ get_unique_tuple(struct ip_conntrack_tuple *tuple, if (maniptype == IP_NAT_MANIP_SRC) { if (find_appropriate_src(orig_tuple, tuple, range)) { DEBUGP("get_unique_tuple: Found current src map\n"); - if (!ip_nat_used_tuple(tuple, conntrack)) - return; + if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) + if (!ip_nat_used_tuple(tuple, conntrack)) + return; } } @@ -261,6 +262,13 @@ get_unique_tuple(struct ip_conntrack_tuple *tuple, proto = ip_nat_proto_find_get(orig_tuple->dst.protonum); + /* Change protocol info to have some randomization */ + if (range->flags & IP_NAT_RANGE_PROTO_RANDOM) { + proto->unique_tuple(tuple, range, maniptype, conntrack); + ip_nat_proto_put(proto); + return; + } + /* Only bother mapping if it's not already in range and unique */ if ((!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) || proto->in_range(tuple, maniptype, &range->min, &range->max)) diff --git a/net/ipv4/netfilter/ip_nat_helper.c b/net/ipv4/netfilter/ip_nat_helper.c index ee80feb4b2a9..2e5c4bc52a60 100644 --- a/net/ipv4/netfilter/ip_nat_helper.c +++ b/net/ipv4/netfilter/ip_nat_helper.c @@ -183,7 +183,7 @@ ip_nat_mangle_tcp_packet(struct sk_buff **pskb, datalen = (*pskb)->len - iph->ihl*4; if ((*pskb)->ip_summed != CHECKSUM_PARTIAL) { tcph->check = 0; - tcph->check = tcp_v4_check(tcph, datalen, + tcph->check = tcp_v4_check(datalen, iph->saddr, iph->daddr, csum_partial((char *)tcph, datalen, 0)); diff --git a/net/ipv4/netfilter/ip_nat_proto_tcp.c b/net/ipv4/netfilter/ip_nat_proto_tcp.c index b586d18b3fb3..14ff24f53a7a 100644 --- a/net/ipv4/netfilter/ip_nat_proto_tcp.c +++ b/net/ipv4/netfilter/ip_nat_proto_tcp.c @@ -8,6 +8,7 @@ #include <linux/types.h> #include <linux/init.h> +#include <linux/random.h> #include <linux/netfilter.h> #include <linux/ip.h> #include <linux/tcp.h> @@ -75,6 +76,10 @@ tcp_unique_tuple(struct ip_conntrack_tuple *tuple, range_size = ntohs(range->max.tcp.port) - min + 1; } + /* Start from random port to avoid prediction */ + if (range->flags & IP_NAT_RANGE_PROTO_RANDOM) + port = net_random(); + for (i = 0; i < range_size; i++, port++) { *portptr = htons(min + port % range_size); if (!ip_nat_used_tuple(tuple, conntrack)) { diff --git a/net/ipv4/netfilter/ip_nat_proto_udp.c b/net/ipv4/netfilter/ip_nat_proto_udp.c index 5ced0877b32f..dfd521672891 100644 --- a/net/ipv4/netfilter/ip_nat_proto_udp.c +++ b/net/ipv4/netfilter/ip_nat_proto_udp.c @@ -8,6 +8,7 @@ #include <linux/types.h> #include <linux/init.h> +#include <linux/random.h> #include <linux/netfilter.h> #include <linux/ip.h> #include <linux/udp.h> @@ -74,6 +75,10 @@ udp_unique_tuple(struct ip_conntrack_tuple *tuple, range_size = ntohs(range->max.udp.port) - min + 1; } + /* Start from random port to avoid prediction */ + if (range->flags & IP_NAT_RANGE_PROTO_RANDOM) + port = net_random(); + for (i = 0; i < range_size; i++, port++) { *portptr = htons(min + port % range_size); if (!ip_nat_used_tuple(tuple, conntrack)) diff --git a/net/ipv4/netfilter/ip_nat_rule.c b/net/ipv4/netfilter/ip_nat_rule.c index a176aa3031e0..e1c8a05f3dc6 100644 --- a/net/ipv4/netfilter/ip_nat_rule.c +++ b/net/ipv4/netfilter/ip_nat_rule.c @@ -86,7 +86,7 @@ static struct } }; -static struct ipt_table nat_table = { +static struct xt_table nat_table = { .name = "nat", .valid_hooks = NAT_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, @@ -99,7 +99,7 @@ static unsigned int ipt_snat_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, - const struct ipt_target *target, + const struct xt_target *target, const void *targinfo) { struct ip_conntrack *ct; @@ -141,7 +141,7 @@ static unsigned int ipt_dnat_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, - const struct ipt_target *target, + const struct xt_target *target, const void *targinfo) { struct ip_conntrack *ct; @@ -166,7 +166,7 @@ static unsigned int ipt_dnat_target(struct sk_buff **pskb, static int ipt_snat_checkentry(const char *tablename, const void *entry, - const struct ipt_target *target, + const struct xt_target *target, void *targinfo, unsigned int hook_mask) { @@ -182,7 +182,7 @@ static int ipt_snat_checkentry(const char *tablename, static int ipt_dnat_checkentry(const char *tablename, const void *entry, - const struct ipt_target *target, + const struct xt_target *target, void *targinfo, unsigned int hook_mask) { @@ -193,6 +193,10 @@ static int ipt_dnat_checkentry(const char *tablename, printk("DNAT: multiple ranges no longer supported\n"); return 0; } + if (mr->range[0].flags & IP_NAT_RANGE_PROTO_RANDOM) { + printk("DNAT: port randomization not supported\n"); + return 0; + } return 1; } @@ -257,8 +261,9 @@ int ip_nat_rule_find(struct sk_buff **pskb, return ret; } -static struct ipt_target ipt_snat_reg = { +static struct xt_target ipt_snat_reg = { .name = "SNAT", + .family = AF_INET, .target = ipt_snat_target, .targetsize = sizeof(struct ip_nat_multi_range_compat), .table = "nat", @@ -266,8 +271,9 @@ static struct ipt_target ipt_snat_reg = { .checkentry = ipt_snat_checkentry, }; -static struct ipt_target ipt_dnat_reg = { +static struct xt_target ipt_dnat_reg = { .name = "DNAT", + .family = AF_INET, .target = ipt_dnat_target, .targetsize = sizeof(struct ip_nat_multi_range_compat), .table = "nat", @@ -282,27 +288,27 @@ int __init ip_nat_rule_init(void) ret = ipt_register_table(&nat_table, &nat_initial_table.repl); if (ret != 0) return ret; - ret = ipt_register_target(&ipt_snat_reg); + ret = xt_register_target(&ipt_snat_reg); if (ret != 0) goto unregister_table; - ret = ipt_register_target(&ipt_dnat_reg); + ret = xt_register_target(&ipt_dnat_reg); if (ret != 0) goto unregister_snat; return ret; unregister_snat: - ipt_unregister_target(&ipt_snat_reg); + xt_unregister_target(&ipt_snat_reg); unregister_table: - ipt_unregister_table(&nat_table); + xt_unregister_table(&nat_table); return ret; } void ip_nat_rule_cleanup(void) { - ipt_unregister_target(&ipt_dnat_reg); - ipt_unregister_target(&ipt_snat_reg); + xt_unregister_target(&ipt_dnat_reg); + xt_unregister_target(&ipt_snat_reg); ipt_unregister_table(&nat_table); } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index fc1f153c86ba..5a7b3a341389 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -216,7 +216,7 @@ ipt_do_table(struct sk_buff **pskb, unsigned int hook, const struct net_device *in, const struct net_device *out, - struct ipt_table *table) + struct xt_table *table) { static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); u_int16_t offset; @@ -507,7 +507,7 @@ check_entry(struct ipt_entry *e, const char *name) static inline int check_match(struct ipt_entry_match *m, const char *name, const struct ipt_ip *ip, unsigned int hookmask) { - struct ipt_match *match; + struct xt_match *match; int ret; match = m->u.kernel.match; @@ -531,7 +531,7 @@ find_check_match(struct ipt_entry_match *m, unsigned int hookmask, unsigned int *i) { - struct ipt_match *match; + struct xt_match *match; int ret; match = try_then_request_module(xt_find_match(AF_INET, m->u.user.name, @@ -557,7 +557,7 @@ err: static inline int check_target(struct ipt_entry *e, const char *name) { struct ipt_entry_target *t; - struct ipt_target *target; + struct xt_target *target; int ret; t = ipt_get_target(e); @@ -580,7 +580,7 @@ find_check_entry(struct ipt_entry *e, const char *name, unsigned int size, unsigned int *i) { struct ipt_entry_target *t; - struct ipt_target *target; + struct xt_target *target; int ret; unsigned int j; @@ -818,7 +818,7 @@ get_counters(const struct xt_table_info *t, } } -static inline struct xt_counters * alloc_counters(struct ipt_table *table) +static inline struct xt_counters * alloc_counters(struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; @@ -843,7 +843,7 @@ static inline struct xt_counters * alloc_counters(struct ipt_table *table) static int copy_entries_to_user(unsigned int total_size, - struct ipt_table *table, + struct xt_table *table, void __user *userptr) { unsigned int off, num; @@ -1046,7 +1046,7 @@ static int compat_table_info(struct xt_table_info *info, static int get_info(void __user *user, int *len, int compat) { char name[IPT_TABLE_MAXNAMELEN]; - struct ipt_table *t; + struct xt_table *t; int ret; if (*len != sizeof(struct ipt_getinfo)) { @@ -1107,7 +1107,7 @@ get_entries(struct ipt_get_entries __user *uptr, int *len) { int ret; struct ipt_get_entries get; - struct ipt_table *t; + struct xt_table *t; if (*len < sizeof(get)) { duprintf("get_entries: %u < %d\n", *len, @@ -1151,7 +1151,7 @@ __do_replace(const char *name, unsigned int valid_hooks, void __user *counters_ptr) { int ret; - struct ipt_table *t; + struct xt_table *t; struct xt_table_info *oldinfo; struct xt_counters *counters; void *loc_cpu_old_entry; @@ -1302,7 +1302,7 @@ do_add_counters(void __user *user, unsigned int len, int compat) char *name; int size; void *ptmp; - struct ipt_table *t; + struct xt_table *t; struct xt_table_info *private; int ret = 0; void *loc_cpu_entry; @@ -1437,7 +1437,7 @@ compat_check_calc_match(struct ipt_entry_match *m, unsigned int hookmask, int *size, int *i) { - struct ipt_match *match; + struct xt_match *match; match = try_then_request_module(xt_find_match(AF_INET, m->u.user.name, m->u.user.revision), @@ -1466,7 +1466,7 @@ check_compat_entry_size_and_hooks(struct ipt_entry *e, const char *name) { struct ipt_entry_target *t; - struct ipt_target *target; + struct xt_target *target; unsigned int entry_offset; int ret, off, h, j; @@ -1550,7 +1550,7 @@ static int compat_copy_entry_from_user(struct ipt_entry *e, void **dstptr, struct xt_table_info *newinfo, unsigned char *base) { struct ipt_entry_target *t; - struct ipt_target *target; + struct xt_target *target; struct ipt_entry *de; unsigned int origsize; int ret, h; @@ -1795,7 +1795,7 @@ struct compat_ipt_get_entries }; static int compat_copy_entries_to_user(unsigned int total_size, - struct ipt_table *table, void __user *userptr) + struct xt_table *table, void __user *userptr) { unsigned int off, num; struct compat_ipt_entry e; @@ -1869,7 +1869,7 @@ compat_get_entries(struct compat_ipt_get_entries __user *uptr, int *len) { int ret; struct compat_ipt_get_entries get; - struct ipt_table *t; + struct xt_table *t; if (*len < sizeof(get)) { @@ -2052,7 +2052,7 @@ int ipt_register_table(struct xt_table *table, const struct ipt_replace *repl) return 0; } -void ipt_unregister_table(struct ipt_table *table) +void ipt_unregister_table(struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; @@ -2124,7 +2124,7 @@ icmp_checkentry(const char *tablename, } /* The built-in targets: standard (NULL) and error. */ -static struct ipt_target ipt_standard_target = { +static struct xt_target ipt_standard_target = { .name = IPT_STANDARD_TARGET, .targetsize = sizeof(int), .family = AF_INET, @@ -2135,7 +2135,7 @@ static struct ipt_target ipt_standard_target = { #endif }; -static struct ipt_target ipt_error_target = { +static struct xt_target ipt_error_target = { .name = IPT_ERROR_TARGET, .target = ipt_error, .targetsize = IPT_FUNCTION_MAXNAMELEN, @@ -2158,7 +2158,7 @@ static struct nf_sockopt_ops ipt_sockopts = { #endif }; -static struct ipt_match icmp_matchstruct = { +static struct xt_match icmp_matchstruct = { .name = "icmp", .match = icmp_match, .matchsize = sizeof(struct ipt_icmp), diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index b1c11160b9de..343c2abdc1a0 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -26,6 +26,7 @@ #include <linux/netfilter_arp.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv4/ipt_CLUSTERIP.h> #include <net/netfilter/nf_conntrack_compat.h> @@ -247,6 +248,7 @@ clusterip_hashfn(struct sk_buff *skb, struct clusterip_config *config) switch (iph->protocol) { case IPPROTO_TCP: case IPPROTO_UDP: + case IPPROTO_UDPLITE: case IPPROTO_SCTP: case IPPROTO_DCCP: case IPPROTO_ICMP: @@ -329,7 +331,7 @@ target(struct sk_buff **pskb, if ((*pskb)->nh.iph->protocol == IPPROTO_ICMP && (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED+IP_CT_IS_REPLY)) - return IPT_CONTINUE; + return XT_CONTINUE; /* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO, * TIMESTAMP, INFO_REQUEST or ADDRESS type icmp packets from here @@ -367,7 +369,7 @@ target(struct sk_buff **pskb, * actually a unicast IP packet. TCP doesn't like PACKET_MULTICAST */ (*pskb)->pkt_type = PACKET_HOST; - return IPT_CONTINUE; + return XT_CONTINUE; } static int @@ -470,8 +472,9 @@ static void destroy(const struct xt_target *target, void *targinfo) nf_ct_l3proto_module_put(target->family); } -static struct ipt_target clusterip_tgt = { +static struct xt_target clusterip_tgt = { .name = "CLUSTERIP", + .family = AF_INET, .target = target, .targetsize = sizeof(struct ipt_clusterip_tgt_info), .checkentry = checkentry, @@ -727,7 +730,7 @@ static int __init ipt_clusterip_init(void) { int ret; - ret = ipt_register_target(&clusterip_tgt); + ret = xt_register_target(&clusterip_tgt); if (ret < 0) return ret; @@ -753,7 +756,7 @@ cleanup_hook: nf_unregister_hook(&cip_arp_ops); #endif /* CONFIG_PROC_FS */ cleanup_target: - ipt_unregister_target(&clusterip_tgt); + xt_unregister_target(&clusterip_tgt); return ret; } @@ -765,7 +768,7 @@ static void __exit ipt_clusterip_fini(void) remove_proc_entry(clusterip_procdir->name, clusterip_procdir->parent); #endif nf_unregister_hook(&cip_arp_ops); - ipt_unregister_target(&clusterip_tgt); + xt_unregister_target(&clusterip_tgt); } module_init(ipt_clusterip_init); diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index b55d670a24df..b5ca5938d1fe 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -9,12 +9,14 @@ * ipt_ECN.c,v 1.5 2002/08/18 19:36:51 laforge Exp */ +#include <linux/in.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/tcp.h> #include <net/checksum.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv4/ipt_ECN.h> @@ -95,7 +97,7 @@ target(struct sk_buff **pskb, if (!set_ect_tcp(pskb, einfo)) return NF_DROP; - return IPT_CONTINUE; + return XT_CONTINUE; } static int @@ -119,7 +121,7 @@ checkentry(const char *tablename, return 0; } if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) - && (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & IPT_INV_PROTO))) { + && (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) { printk(KERN_WARNING "ECN: cannot use TCP operations on a " "non-tcp rule\n"); return 0; @@ -127,8 +129,9 @@ checkentry(const char *tablename, return 1; } -static struct ipt_target ipt_ecn_reg = { +static struct xt_target ipt_ecn_reg = { .name = "ECN", + .family = AF_INET, .target = target, .targetsize = sizeof(struct ipt_ECN_info), .table = "mangle", @@ -138,12 +141,12 @@ static struct ipt_target ipt_ecn_reg = { static int __init ipt_ecn_init(void) { - return ipt_register_target(&ipt_ecn_reg); + return xt_register_target(&ipt_ecn_reg); } static void __exit ipt_ecn_fini(void) { - ipt_unregister_target(&ipt_ecn_reg); + xt_unregister_target(&ipt_ecn_reg); } module_init(ipt_ecn_init); diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index c96de16fefae..f68370ffb43f 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -20,7 +20,7 @@ #include <net/route.h> #include <linux/netfilter.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ipt_LOG.h> MODULE_LICENSE("GPL"); @@ -432,7 +432,7 @@ ipt_log_target(struct sk_buff **pskb, ipt_log_packet(PF_INET, hooknum, *pskb, in, out, &li, loginfo->prefix); - return IPT_CONTINUE; + return XT_CONTINUE; } static int ipt_log_checkentry(const char *tablename, @@ -455,8 +455,9 @@ static int ipt_log_checkentry(const char *tablename, return 1; } -static struct ipt_target ipt_log_reg = { +static struct xt_target ipt_log_reg = { .name = "LOG", + .family = AF_INET, .target = ipt_log_target, .targetsize = sizeof(struct ipt_log_info), .checkentry = ipt_log_checkentry, @@ -471,8 +472,11 @@ static struct nf_logger ipt_log_logger ={ static int __init ipt_log_init(void) { - if (ipt_register_target(&ipt_log_reg)) - return -EINVAL; + int ret; + + ret = xt_register_target(&ipt_log_reg); + if (ret < 0) + return ret; if (nf_log_register(PF_INET, &ipt_log_logger) < 0) { printk(KERN_WARNING "ipt_LOG: not logging via system console " "since somebody else already registered for PF_INET\n"); @@ -486,7 +490,7 @@ static int __init ipt_log_init(void) static void __exit ipt_log_fini(void) { nf_log_unregister_logger(&ipt_log_logger); - ipt_unregister_target(&ipt_log_reg); + xt_unregister_target(&ipt_log_reg); } module_init(ipt_log_init); diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index d669685afd04..91c42efcd533 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -25,7 +25,7 @@ #else #include <linux/netfilter_ipv4/ip_nat_rule.h> #endif -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); @@ -190,8 +190,9 @@ static struct notifier_block masq_inet_notifier = { .notifier_call = masq_inet_event, }; -static struct ipt_target masquerade = { +static struct xt_target masquerade = { .name = "MASQUERADE", + .family = AF_INET, .target = masquerade_target, .targetsize = sizeof(struct ip_nat_multi_range_compat), .table = "nat", @@ -204,7 +205,7 @@ static int __init ipt_masquerade_init(void) { int ret; - ret = ipt_register_target(&masquerade); + ret = xt_register_target(&masquerade); if (ret == 0) { /* Register for device down reports */ @@ -218,7 +219,7 @@ static int __init ipt_masquerade_init(void) static void __exit ipt_masquerade_fini(void) { - ipt_unregister_target(&masquerade); + xt_unregister_target(&masquerade); unregister_netdevice_notifier(&masq_dev_notifier); unregister_inetaddr_notifier(&masq_inet_notifier); } diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c index 9390e90f2b25..b4acc241d898 100644 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ b/net/ipv4/netfilter/ipt_NETMAP.c @@ -15,6 +15,7 @@ #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> +#include <linux/netfilter/x_tables.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_rule.h> #else @@ -88,8 +89,9 @@ target(struct sk_buff **pskb, return ip_nat_setup_info(ct, &newrange, hooknum); } -static struct ipt_target target_module = { +static struct xt_target target_module = { .name = MODULENAME, + .family = AF_INET, .target = target, .targetsize = sizeof(struct ip_nat_multi_range_compat), .table = "nat", @@ -101,12 +103,12 @@ static struct ipt_target target_module = { static int __init ipt_netmap_init(void) { - return ipt_register_target(&target_module); + return xt_register_target(&target_module); } static void __exit ipt_netmap_fini(void) { - ipt_unregister_target(&target_module); + xt_unregister_target(&target_module); } module_init(ipt_netmap_init); diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c index 462eceb3a1b1..54cd021aa5a8 100644 --- a/net/ipv4/netfilter/ipt_REDIRECT.c +++ b/net/ipv4/netfilter/ipt_REDIRECT.c @@ -18,6 +18,7 @@ #include <net/protocol.h> #include <net/checksum.h> #include <linux/netfilter_ipv4.h> +#include <linux/netfilter/x_tables.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_rule.h> #else @@ -104,8 +105,9 @@ redirect_target(struct sk_buff **pskb, return ip_nat_setup_info(ct, &newrange, hooknum); } -static struct ipt_target redirect_reg = { +static struct xt_target redirect_reg = { .name = "REDIRECT", + .family = AF_INET, .target = redirect_target, .targetsize = sizeof(struct ip_nat_multi_range_compat), .table = "nat", @@ -116,12 +118,12 @@ static struct ipt_target redirect_reg = { static int __init ipt_redirect_init(void) { - return ipt_register_target(&redirect_reg); + return xt_register_target(&redirect_reg); } static void __exit ipt_redirect_fini(void) { - ipt_unregister_target(&redirect_reg); + xt_unregister_target(&redirect_reg); } module_init(ipt_redirect_init); diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index f0319e5ee437..e4a1ddb386a7 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -22,6 +22,7 @@ #include <net/tcp.h> #include <net/route.h> #include <net/dst.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv4/ipt_REJECT.h> #ifdef CONFIG_BRIDGE_NETFILTER @@ -116,7 +117,7 @@ static void send_reset(struct sk_buff *oldskb, int hook) /* Adjust TCP checksum */ tcph->check = 0; - tcph->check = tcp_v4_check(tcph, sizeof(struct tcphdr), + tcph->check = tcp_v4_check(sizeof(struct tcphdr), nskb->nh.iph->saddr, nskb->nh.iph->daddr, csum_partial((char *)tcph, @@ -230,7 +231,7 @@ static int check(const char *tablename, } else if (rejinfo->with == IPT_TCP_RESET) { /* Must specify that it's a TCP packet */ if (e->ip.proto != IPPROTO_TCP - || (e->ip.invflags & IPT_INV_PROTO)) { + || (e->ip.invflags & XT_INV_PROTO)) { DEBUGP("REJECT: TCP_RESET invalid for non-tcp\n"); return 0; } @@ -238,8 +239,9 @@ static int check(const char *tablename, return 1; } -static struct ipt_target ipt_reject_reg = { +static struct xt_target ipt_reject_reg = { .name = "REJECT", + .family = AF_INET, .target = reject, .targetsize = sizeof(struct ipt_reject_info), .table = "filter", @@ -251,12 +253,12 @@ static struct ipt_target ipt_reject_reg = { static int __init ipt_reject_init(void) { - return ipt_register_target(&ipt_reject_reg); + return xt_register_target(&ipt_reject_reg); } static void __exit ipt_reject_fini(void) { - ipt_unregister_target(&ipt_reject_reg); + xt_unregister_target(&ipt_reject_reg); } module_init(ipt_reject_init); diff --git a/net/ipv4/netfilter/ipt_SAME.c b/net/ipv4/netfilter/ipt_SAME.c index 3dcf29411337..a1cdd1262de2 100644 --- a/net/ipv4/netfilter/ipt_SAME.c +++ b/net/ipv4/netfilter/ipt_SAME.c @@ -34,6 +34,7 @@ #include <net/protocol.h> #include <net/checksum.h> #include <linux/netfilter_ipv4.h> +#include <linux/netfilter/x_tables.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_rule.h> #else @@ -186,8 +187,9 @@ same_target(struct sk_buff **pskb, return ip_nat_setup_info(ct, &newrange, hooknum); } -static struct ipt_target same_reg = { +static struct xt_target same_reg = { .name = "SAME", + .family = AF_INET, .target = same_target, .targetsize = sizeof(struct ipt_same_info), .table = "nat", @@ -199,12 +201,12 @@ static struct ipt_target same_reg = { static int __init ipt_same_init(void) { - return ipt_register_target(&same_reg); + return xt_register_target(&same_reg); } static void __exit ipt_same_fini(void) { - ipt_unregister_target(&same_reg); + xt_unregister_target(&same_reg); } module_init(ipt_same_init); diff --git a/net/ipv4/netfilter/ipt_TCPMSS.c b/net/ipv4/netfilter/ipt_TCPMSS.c deleted file mode 100644 index 93eb5c3c1884..000000000000 --- a/net/ipv4/netfilter/ipt_TCPMSS.c +++ /dev/null @@ -1,207 +0,0 @@ -/* - * This is a module which is used for setting the MSS option in TCP packets. - * - * Copyright (C) 2000 Marc Boucher <marc@mbsi.ca> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/ip.h> -#include <net/tcp.h> - -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_TCPMSS.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); -MODULE_DESCRIPTION("iptables TCP MSS modification module"); - -static inline unsigned int -optlen(const u_int8_t *opt, unsigned int offset) -{ - /* Beware zero-length options: make finite progress */ - if (opt[offset] <= TCPOPT_NOP || opt[offset+1] == 0) - return 1; - else - return opt[offset+1]; -} - -static unsigned int -ipt_tcpmss_target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const struct xt_target *target, - const void *targinfo) -{ - const struct ipt_tcpmss_info *tcpmssinfo = targinfo; - struct tcphdr *tcph; - struct iphdr *iph; - u_int16_t tcplen, newmss; - __be16 newtotlen, oldval; - unsigned int i; - u_int8_t *opt; - - if (!skb_make_writable(pskb, (*pskb)->len)) - return NF_DROP; - - iph = (*pskb)->nh.iph; - tcplen = (*pskb)->len - iph->ihl*4; - tcph = (void *)iph + iph->ihl*4; - - /* Since it passed flags test in tcp match, we know it is is - not a fragment, and has data >= tcp header length. SYN - packets should not contain data: if they did, then we risk - running over MTU, sending Frag Needed and breaking things - badly. --RR */ - if (tcplen != tcph->doff*4) { - if (net_ratelimit()) - printk(KERN_ERR - "ipt_tcpmss_target: bad length (%d bytes)\n", - (*pskb)->len); - return NF_DROP; - } - - if (tcpmssinfo->mss == IPT_TCPMSS_CLAMP_PMTU) { - if (dst_mtu((*pskb)->dst) <= sizeof(struct iphdr) + - sizeof(struct tcphdr)) { - if (net_ratelimit()) - printk(KERN_ERR "ipt_tcpmss_target: " - "unknown or invalid path-MTU (%d)\n", - dst_mtu((*pskb)->dst)); - return NF_DROP; /* or IPT_CONTINUE ?? */ - } - - newmss = dst_mtu((*pskb)->dst) - sizeof(struct iphdr) - - sizeof(struct tcphdr); - } else - newmss = tcpmssinfo->mss; - - opt = (u_int8_t *)tcph; - for (i = sizeof(struct tcphdr); i < tcph->doff*4; i += optlen(opt, i)) { - if (opt[i] == TCPOPT_MSS && tcph->doff*4 - i >= TCPOLEN_MSS && - opt[i+1] == TCPOLEN_MSS) { - u_int16_t oldmss; - - oldmss = (opt[i+2] << 8) | opt[i+3]; - - if (tcpmssinfo->mss == IPT_TCPMSS_CLAMP_PMTU && - oldmss <= newmss) - return IPT_CONTINUE; - - opt[i+2] = (newmss & 0xff00) >> 8; - opt[i+3] = (newmss & 0x00ff); - - nf_proto_csum_replace2(&tcph->check, *pskb, - htons(oldmss), htons(newmss), 0); - return IPT_CONTINUE; - } - } - - /* - * MSS Option not found ?! add it.. - */ - if (skb_tailroom((*pskb)) < TCPOLEN_MSS) { - struct sk_buff *newskb; - - newskb = skb_copy_expand(*pskb, skb_headroom(*pskb), - TCPOLEN_MSS, GFP_ATOMIC); - if (!newskb) - return NF_DROP; - kfree_skb(*pskb); - *pskb = newskb; - iph = (*pskb)->nh.iph; - tcph = (void *)iph + iph->ihl*4; - } - - skb_put((*pskb), TCPOLEN_MSS); - - opt = (u_int8_t *)tcph + sizeof(struct tcphdr); - memmove(opt + TCPOLEN_MSS, opt, tcplen - sizeof(struct tcphdr)); - - nf_proto_csum_replace2(&tcph->check, *pskb, - htons(tcplen), htons(tcplen + TCPOLEN_MSS), 1); - opt[0] = TCPOPT_MSS; - opt[1] = TCPOLEN_MSS; - opt[2] = (newmss & 0xff00) >> 8; - opt[3] = (newmss & 0x00ff); - - nf_proto_csum_replace4(&tcph->check, *pskb, 0, *((__be32 *)opt), 0); - - oldval = ((__be16 *)tcph)[6]; - tcph->doff += TCPOLEN_MSS/4; - nf_proto_csum_replace2(&tcph->check, *pskb, - oldval, ((__be16 *)tcph)[6], 0); - - newtotlen = htons(ntohs(iph->tot_len) + TCPOLEN_MSS); - nf_csum_replace2(&iph->check, iph->tot_len, newtotlen); - iph->tot_len = newtotlen; - return IPT_CONTINUE; -} - -#define TH_SYN 0x02 - -static inline int find_syn_match(const struct ipt_entry_match *m) -{ - const struct ipt_tcp *tcpinfo = (const struct ipt_tcp *)m->data; - - if (strcmp(m->u.kernel.match->name, "tcp") == 0 && - tcpinfo->flg_cmp & TH_SYN && - !(tcpinfo->invflags & IPT_TCP_INV_FLAGS)) - return 1; - - return 0; -} - -/* Must specify -p tcp --syn/--tcp-flags SYN */ -static int -ipt_tcpmss_checkentry(const char *tablename, - const void *e_void, - const struct xt_target *target, - void *targinfo, - unsigned int hook_mask) -{ - const struct ipt_tcpmss_info *tcpmssinfo = targinfo; - const struct ipt_entry *e = e_void; - - if (tcpmssinfo->mss == IPT_TCPMSS_CLAMP_PMTU && - (hook_mask & ~((1 << NF_IP_FORWARD) | - (1 << NF_IP_LOCAL_OUT) | - (1 << NF_IP_POST_ROUTING))) != 0) { - printk("TCPMSS: path-MTU clamping only supported in " - "FORWARD, OUTPUT and POSTROUTING hooks\n"); - return 0; - } - - if (IPT_MATCH_ITERATE(e, find_syn_match)) - return 1; - printk("TCPMSS: Only works on TCP SYN packets\n"); - return 0; -} - -static struct ipt_target ipt_tcpmss_reg = { - .name = "TCPMSS", - .target = ipt_tcpmss_target, - .targetsize = sizeof(struct ipt_tcpmss_info), - .proto = IPPROTO_TCP, - .checkentry = ipt_tcpmss_checkentry, - .me = THIS_MODULE, -}; - -static int __init ipt_tcpmss_init(void) -{ - return ipt_register_target(&ipt_tcpmss_reg); -} - -static void __exit ipt_tcpmss_fini(void) -{ - ipt_unregister_target(&ipt_tcpmss_reg); -} - -module_init(ipt_tcpmss_init); -module_exit(ipt_tcpmss_fini); diff --git a/net/ipv4/netfilter/ipt_TOS.c b/net/ipv4/netfilter/ipt_TOS.c index 18e74ac4d425..29b05a6bd108 100644 --- a/net/ipv4/netfilter/ipt_TOS.c +++ b/net/ipv4/netfilter/ipt_TOS.c @@ -13,7 +13,7 @@ #include <linux/ip.h> #include <net/checksum.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ipt_TOS.h> MODULE_LICENSE("GPL"); @@ -40,7 +40,7 @@ target(struct sk_buff **pskb, iph->tos = (iph->tos & IPTOS_PREC_MASK) | tosinfo->tos; nf_csum_replace2(&iph->check, htons(oldtos), htons(iph->tos)); } - return IPT_CONTINUE; + return XT_CONTINUE; } static int @@ -63,8 +63,9 @@ checkentry(const char *tablename, return 1; } -static struct ipt_target ipt_tos_reg = { +static struct xt_target ipt_tos_reg = { .name = "TOS", + .family = AF_INET, .target = target, .targetsize = sizeof(struct ipt_tos_target_info), .table = "mangle", @@ -74,12 +75,12 @@ static struct ipt_target ipt_tos_reg = { static int __init ipt_tos_init(void) { - return ipt_register_target(&ipt_tos_reg); + return xt_register_target(&ipt_tos_reg); } static void __exit ipt_tos_fini(void) { - ipt_unregister_target(&ipt_tos_reg); + xt_unregister_target(&ipt_tos_reg); } module_init(ipt_tos_init); diff --git a/net/ipv4/netfilter/ipt_TTL.c b/net/ipv4/netfilter/ipt_TTL.c index fffe5ca82e91..d2b6fa3f9dcd 100644 --- a/net/ipv4/netfilter/ipt_TTL.c +++ b/net/ipv4/netfilter/ipt_TTL.c @@ -12,7 +12,7 @@ #include <linux/ip.h> #include <net/checksum.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ipt_TTL.h> MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); @@ -59,7 +59,7 @@ ipt_ttl_target(struct sk_buff **pskb, iph->ttl = new_ttl; } - return IPT_CONTINUE; + return XT_CONTINUE; } static int ipt_ttl_checkentry(const char *tablename, @@ -80,8 +80,9 @@ static int ipt_ttl_checkentry(const char *tablename, return 1; } -static struct ipt_target ipt_TTL = { +static struct xt_target ipt_TTL = { .name = "TTL", + .family = AF_INET, .target = ipt_ttl_target, .targetsize = sizeof(struct ipt_TTL_info), .table = "mangle", @@ -91,12 +92,12 @@ static struct ipt_target ipt_TTL = { static int __init ipt_ttl_init(void) { - return ipt_register_target(&ipt_TTL); + return xt_register_target(&ipt_TTL); } static void __exit ipt_ttl_fini(void) { - ipt_unregister_target(&ipt_TTL); + xt_unregister_target(&ipt_TTL); } module_init(ipt_ttl_init); diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index dbd34783a64d..7af57a3a1f36 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -57,7 +57,7 @@ #include <linux/mm.h> #include <linux/moduleparam.h> #include <linux/netfilter.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ipt_ULOG.h> #include <net/sock.h> #include <linux/bitops.h> @@ -132,7 +132,6 @@ static void ulog_send(unsigned int nlgroupnum) ub->qlen = 0; ub->skb = NULL; ub->lastnlh = NULL; - } @@ -314,7 +313,7 @@ static unsigned int ipt_ulog_target(struct sk_buff **pskb, ipt_ulog_packet(hooknum, *pskb, in, out, loginfo, NULL); - return IPT_CONTINUE; + return XT_CONTINUE; } static void ipt_logfn(unsigned int pf, @@ -363,8 +362,9 @@ static int ipt_ulog_checkentry(const char *tablename, return 1; } -static struct ipt_target ipt_ulog_reg = { +static struct xt_target ipt_ulog_reg = { .name = "ULOG", + .family = AF_INET, .target = ipt_ulog_target, .targetsize = sizeof(struct ipt_ulog_info), .checkentry = ipt_ulog_checkentry, @@ -379,7 +379,7 @@ static struct nf_logger ipt_ulog_logger = { static int __init ipt_ulog_init(void) { - int i; + int ret, i; DEBUGP("ipt_ULOG: init module\n"); @@ -400,9 +400,10 @@ static int __init ipt_ulog_init(void) if (!nflognl) return -ENOMEM; - if (ipt_register_target(&ipt_ulog_reg) != 0) { + ret = xt_register_target(&ipt_ulog_reg); + if (ret < 0) { sock_release(nflognl->sk_socket); - return -EINVAL; + return ret; } if (nflog) nf_log_register(PF_INET, &ipt_ulog_logger); @@ -419,7 +420,7 @@ static void __exit ipt_ulog_fini(void) if (nflog) nf_log_unregister_logger(&ipt_ulog_logger); - ipt_unregister_target(&ipt_ulog_reg); + xt_unregister_target(&ipt_ulog_reg); sock_release(nflognl->sk_socket); /* remove pending timers and free allocated skb's */ @@ -435,7 +436,6 @@ static void __exit ipt_ulog_fini(void) ub->skb = NULL; } } - } module_init(ipt_ulog_init); diff --git a/net/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c index 7b60eb74788b..648f555c4d16 100644 --- a/net/ipv4/netfilter/ipt_addrtype.c +++ b/net/ipv4/netfilter/ipt_addrtype.c @@ -16,7 +16,7 @@ #include <net/route.h> #include <linux/netfilter_ipv4/ipt_addrtype.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); @@ -44,8 +44,9 @@ static int match(const struct sk_buff *skb, return ret; } -static struct ipt_match addrtype_match = { +static struct xt_match addrtype_match = { .name = "addrtype", + .family = AF_INET, .match = match, .matchsize = sizeof(struct ipt_addrtype_info), .me = THIS_MODULE @@ -53,12 +54,12 @@ static struct ipt_match addrtype_match = { static int __init ipt_addrtype_init(void) { - return ipt_register_match(&addrtype_match); + return xt_register_match(&addrtype_match); } static void __exit ipt_addrtype_fini(void) { - ipt_unregister_match(&addrtype_match); + xt_unregister_match(&addrtype_match); } module_init(ipt_addrtype_init); diff --git a/net/ipv4/netfilter/ipt_ah.c b/net/ipv4/netfilter/ipt_ah.c index 1798f86bc534..42f41224a43a 100644 --- a/net/ipv4/netfilter/ipt_ah.c +++ b/net/ipv4/netfilter/ipt_ah.c @@ -6,12 +6,13 @@ * published by the Free Software Foundation. */ +#include <linux/in.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/netfilter_ipv4/ipt_ah.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Yon Uriarte <yon@astaro.de>"); @@ -86,8 +87,9 @@ checkentry(const char *tablename, return 1; } -static struct ipt_match ah_match = { +static struct xt_match ah_match = { .name = "ah", + .family = AF_INET, .match = match, .matchsize = sizeof(struct ipt_ah), .proto = IPPROTO_AH, @@ -97,12 +99,12 @@ static struct ipt_match ah_match = { static int __init ipt_ah_init(void) { - return ipt_register_match(&ah_match); + return xt_register_match(&ah_match); } static void __exit ipt_ah_fini(void) { - ipt_unregister_match(&ah_match); + xt_unregister_match(&ah_match); } module_init(ipt_ah_init); diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index dafbdec0efc0..37508b2cfea6 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -9,10 +9,13 @@ * published by the Free Software Foundation. */ +#include <linux/in.h> +#include <linux/ip.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/tcp.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv4/ipt_ecn.h> @@ -109,8 +112,9 @@ static int checkentry(const char *tablename, const void *ip_void, return 1; } -static struct ipt_match ecn_match = { +static struct xt_match ecn_match = { .name = "ecn", + .family = AF_INET, .match = match, .matchsize = sizeof(struct ipt_ecn_info), .checkentry = checkentry, @@ -119,12 +123,12 @@ static struct ipt_match ecn_match = { static int __init ipt_ecn_init(void) { - return ipt_register_match(&ecn_match); + return xt_register_match(&ecn_match); } static void __exit ipt_ecn_fini(void) { - ipt_unregister_match(&ecn_match); + xt_unregister_match(&ecn_match); } module_init(ipt_ecn_init); diff --git a/net/ipv4/netfilter/ipt_iprange.c b/net/ipv4/netfilter/ipt_iprange.c index 5202edd8d333..05de593be94c 100644 --- a/net/ipv4/netfilter/ipt_iprange.c +++ b/net/ipv4/netfilter/ipt_iprange.c @@ -10,7 +10,7 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ip.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ipt_iprange.h> MODULE_LICENSE("GPL"); @@ -63,22 +63,22 @@ match(const struct sk_buff *skb, return 1; } -static struct ipt_match iprange_match = { +static struct xt_match iprange_match = { .name = "iprange", + .family = AF_INET, .match = match, .matchsize = sizeof(struct ipt_iprange_info), - .destroy = NULL, .me = THIS_MODULE }; static int __init ipt_iprange_init(void) { - return ipt_register_match(&iprange_match); + return xt_register_match(&iprange_match); } static void __exit ipt_iprange_fini(void) { - ipt_unregister_match(&iprange_match); + xt_unregister_match(&iprange_match); } module_init(ipt_iprange_init); diff --git a/net/ipv4/netfilter/ipt_owner.c b/net/ipv4/netfilter/ipt_owner.c index 78c336f12a9e..9f496ac834b5 100644 --- a/net/ipv4/netfilter/ipt_owner.c +++ b/net/ipv4/netfilter/ipt_owner.c @@ -15,7 +15,7 @@ #include <net/sock.h> #include <linux/netfilter_ipv4/ipt_owner.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); @@ -68,8 +68,9 @@ checkentry(const char *tablename, return 1; } -static struct ipt_match owner_match = { +static struct xt_match owner_match = { .name = "owner", + .family = AF_INET, .match = match, .matchsize = sizeof(struct ipt_owner_info), .hooks = (1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_POST_ROUTING), @@ -79,12 +80,12 @@ static struct ipt_match owner_match = { static int __init ipt_owner_init(void) { - return ipt_register_match(&owner_match); + return xt_register_match(&owner_match); } static void __exit ipt_owner_fini(void) { - ipt_unregister_match(&owner_match); + xt_unregister_match(&owner_match); } module_init(ipt_owner_init); diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c index 4db0e73c56f1..6b97b6796173 100644 --- a/net/ipv4/netfilter/ipt_recent.c +++ b/net/ipv4/netfilter/ipt_recent.c @@ -12,6 +12,7 @@ * Copyright 2002-2003, Stephen Frost, 2.5.x port by laforge@netfilter.org */ #include <linux/init.h> +#include <linux/ip.h> #include <linux/moduleparam.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -24,7 +25,7 @@ #include <linux/skbuff.h> #include <linux/inet.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ipt_recent.h> MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); @@ -462,8 +463,9 @@ static struct file_operations recent_fops = { }; #endif /* CONFIG_PROC_FS */ -static struct ipt_match recent_match = { +static struct xt_match recent_match = { .name = "recent", + .family = AF_INET, .match = ipt_recent_match, .matchsize = sizeof(struct ipt_recent_info), .checkentry = ipt_recent_checkentry, @@ -479,13 +481,13 @@ static int __init ipt_recent_init(void) return -EINVAL; ip_list_hash_size = 1 << fls(ip_list_tot); - err = ipt_register_match(&recent_match); + err = xt_register_match(&recent_match); #ifdef CONFIG_PROC_FS if (err) return err; proc_dir = proc_mkdir("ipt_recent", proc_net); if (proc_dir == NULL) { - ipt_unregister_match(&recent_match); + xt_unregister_match(&recent_match); err = -ENOMEM; } #endif @@ -495,7 +497,7 @@ static int __init ipt_recent_init(void) static void __exit ipt_recent_exit(void) { BUG_ON(!list_empty(&tables)); - ipt_unregister_match(&recent_match); + xt_unregister_match(&recent_match); #ifdef CONFIG_PROC_FS remove_proc_entry("ipt_recent", proc_net); #endif diff --git a/net/ipv4/netfilter/ipt_tos.c b/net/ipv4/netfilter/ipt_tos.c index 5549c39c7851..5d33b51d49d8 100644 --- a/net/ipv4/netfilter/ipt_tos.c +++ b/net/ipv4/netfilter/ipt_tos.c @@ -8,11 +8,12 @@ * published by the Free Software Foundation. */ +#include <linux/ip.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter_ipv4/ipt_tos.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("iptables TOS match module"); @@ -32,8 +33,9 @@ match(const struct sk_buff *skb, return (skb->nh.iph->tos == info->tos) ^ info->invert; } -static struct ipt_match tos_match = { +static struct xt_match tos_match = { .name = "tos", + .family = AF_INET, .match = match, .matchsize = sizeof(struct ipt_tos_info), .me = THIS_MODULE, @@ -41,12 +43,12 @@ static struct ipt_match tos_match = { static int __init ipt_multiport_init(void) { - return ipt_register_match(&tos_match); + return xt_register_match(&tos_match); } static void __exit ipt_multiport_fini(void) { - ipt_unregister_match(&tos_match); + xt_unregister_match(&tos_match); } module_init(ipt_multiport_init); diff --git a/net/ipv4/netfilter/ipt_ttl.c b/net/ipv4/netfilter/ipt_ttl.c index a5243bdb87d7..d5cd984e5ed2 100644 --- a/net/ipv4/netfilter/ipt_ttl.c +++ b/net/ipv4/netfilter/ipt_ttl.c @@ -9,11 +9,12 @@ * published by the Free Software Foundation. */ +#include <linux/ip.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter_ipv4/ipt_ttl.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("IP tables TTL matching module"); @@ -48,8 +49,9 @@ static int match(const struct sk_buff *skb, return 0; } -static struct ipt_match ttl_match = { +static struct xt_match ttl_match = { .name = "ttl", + .family = AF_INET, .match = match, .matchsize = sizeof(struct ipt_ttl_info), .me = THIS_MODULE, @@ -57,13 +59,12 @@ static struct ipt_match ttl_match = { static int __init ipt_ttl_init(void) { - return ipt_register_match(&ttl_match); + return xt_register_match(&ttl_match); } static void __exit ipt_ttl_fini(void) { - ipt_unregister_match(&ttl_match); - + xt_unregister_match(&ttl_match); } module_init(ipt_ttl_init); diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index e2e7dd8d7903..51053cb42f43 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -74,7 +74,7 @@ static struct } }; -static struct ipt_table packet_filter = { +static struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index af2939889444..a532e4d84332 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -103,7 +103,7 @@ static struct } }; -static struct ipt_table packet_mangler = { +static struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index bcbeb4aeacd9..5277550fa6b5 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -79,7 +79,7 @@ static struct } }; -static struct ipt_table packet_raw = { +static struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 86a92272b053..998b2557692c 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -254,8 +254,9 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, if (maniptype == IP_NAT_MANIP_SRC) { if (find_appropriate_src(orig_tuple, tuple, range)) { DEBUGP("get_unique_tuple: Found current src map\n"); - if (!nf_nat_used_tuple(tuple, ct)) - return; + if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) + if (!nf_nat_used_tuple(tuple, ct)) + return; } } @@ -269,6 +270,13 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, proto = nf_nat_proto_find_get(orig_tuple->dst.protonum); + /* Change protocol info to have some randomization */ + if (range->flags & IP_NAT_RANGE_PROTO_RANDOM) { + proto->unique_tuple(tuple, range, maniptype, ct); + nf_nat_proto_put(proto); + return; + } + /* Only bother mapping if it's not already in range and unique */ if ((!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) || proto->in_range(tuple, maniptype, &range->min, &range->max)) && diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 98fbfc84d183..dc6738bdfab7 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -176,7 +176,7 @@ nf_nat_mangle_tcp_packet(struct sk_buff **pskb, datalen = (*pskb)->len - iph->ihl*4; if ((*pskb)->ip_summed != CHECKSUM_PARTIAL) { tcph->check = 0; - tcph->check = tcp_v4_check(tcph, datalen, + tcph->check = tcp_v4_check(datalen, iph->saddr, iph->daddr, csum_partial((char *)tcph, datalen, 0)); diff --git a/net/ipv4/netfilter/nf_nat_proto_tcp.c b/net/ipv4/netfilter/nf_nat_proto_tcp.c index 7e26a7e9bee1..439164c7a626 100644 --- a/net/ipv4/netfilter/nf_nat_proto_tcp.c +++ b/net/ipv4/netfilter/nf_nat_proto_tcp.c @@ -8,6 +8,7 @@ #include <linux/types.h> #include <linux/init.h> +#include <linux/random.h> #include <linux/ip.h> #include <linux/tcp.h> @@ -75,6 +76,9 @@ tcp_unique_tuple(struct nf_conntrack_tuple *tuple, range_size = ntohs(range->max.tcp.port) - min + 1; } + if (range->flags & IP_NAT_RANGE_PROTO_RANDOM) + port = net_random(); + for (i = 0; i < range_size; i++, port++) { *portptr = htons(min + port % range_size); if (!nf_nat_used_tuple(tuple, ct)) diff --git a/net/ipv4/netfilter/nf_nat_proto_udp.c b/net/ipv4/netfilter/nf_nat_proto_udp.c index ab0ce4c8699f..8cae6e063bb6 100644 --- a/net/ipv4/netfilter/nf_nat_proto_udp.c +++ b/net/ipv4/netfilter/nf_nat_proto_udp.c @@ -8,6 +8,7 @@ #include <linux/types.h> #include <linux/init.h> +#include <linux/random.h> #include <linux/ip.h> #include <linux/udp.h> @@ -73,6 +74,9 @@ udp_unique_tuple(struct nf_conntrack_tuple *tuple, range_size = ntohs(range->max.udp.port) - min + 1; } + if (range->flags & IP_NAT_RANGE_PROTO_RANDOM) + port = net_random(); + for (i = 0; i < range_size; i++, port++) { *portptr = htons(min + port % range_size); if (!nf_nat_used_tuple(tuple, ct)) diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index b868ee0195d4..7f95b4e2eb31 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -119,7 +119,7 @@ static struct } }; -static struct ipt_table nat_table = { +static struct xt_table nat_table = { .name = "nat", .valid_hooks = NAT_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, @@ -226,6 +226,10 @@ static int ipt_dnat_checkentry(const char *tablename, printk("DNAT: multiple ranges no longer supported\n"); return 0; } + if (mr->range[0].flags & IP_NAT_RANGE_PROTO_RANDOM) { + printk("DNAT: port randomization not supported\n"); + return 0; + } return 1; } @@ -290,7 +294,7 @@ int nf_nat_rule_find(struct sk_buff **pskb, return ret; } -static struct ipt_target ipt_snat_reg = { +static struct xt_target ipt_snat_reg = { .name = "SNAT", .target = ipt_snat_target, .targetsize = sizeof(struct nf_nat_multi_range_compat), diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index 00d6dea9f7f3..5a964a167c13 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -32,12 +32,6 @@ #define DEBUGP(format, args...) #endif -#define HOOKNAME(hooknum) ((hooknum) == NF_IP_POST_ROUTING ? "POST_ROUTING" \ - : ((hooknum) == NF_IP_PRE_ROUTING ? "PRE_ROUTING" \ - : ((hooknum) == NF_IP_LOCAL_OUT ? "LOCAL_OUT" \ - : ((hooknum) == NF_IP_LOCAL_IN ? "LOCAL_IN" \ - : "*ERROR*"))) - #ifdef CONFIG_XFRM static void nat_decode_session(struct sk_buff *skb, struct flowi *fl) { diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a6c63bbd9ddb..fed6a1e7af9e 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -489,7 +489,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } security_sk_classify_flow(sk, &fl); - err = ip_route_output_flow(&rt, &fl, sk, !(msg->msg_flags&MSG_DONTWAIT)); + err = ip_route_output_flow(&rt, &fl, sk, 1); } if (err) goto done; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 2daa0dc19d33..baee304a3cb7 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2635,7 +2635,7 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags); if (nlh == NULL) - return -ENOBUFS; + return -EMSGSIZE; r = nlmsg_data(nlh); r->rtm_family = AF_INET; @@ -2718,7 +2718,8 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, return nlmsg_end(skb, nlh); nla_put_failure: - return nlmsg_cancel(skb, nlh); + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b67e0dd743be..5bd43d7294fd 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2415,10 +2415,11 @@ void __init tcp_init(void) &tcp_hashinfo.ehash_size, NULL, 0); - tcp_hashinfo.ehash_size = (1 << tcp_hashinfo.ehash_size) >> 1; - for (i = 0; i < (tcp_hashinfo.ehash_size << 1); i++) { + tcp_hashinfo.ehash_size = 1 << tcp_hashinfo.ehash_size; + for (i = 0; i < tcp_hashinfo.ehash_size; i++) { rwlock_init(&tcp_hashinfo.ehash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].chain); + INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].twchain); } tcp_hashinfo.bhash = @@ -2475,7 +2476,7 @@ void __init tcp_init(void) printk(KERN_INFO "TCP: Hash tables configured " "(established %d bind %d)\n", - tcp_hashinfo.ehash_size << 1, tcp_hashinfo.bhash_size); + tcp_hashinfo.ehash_size, tcp_hashinfo.bhash_size); tcp_register_congestion_control(&tcp_reno); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c26076fb890e..c6109895bb5e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -936,28 +936,58 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ struct tcp_sock *tp = tcp_sk(sk); unsigned char *ptr = ack_skb->h.raw + TCP_SKB_CB(ack_skb)->sacked; struct tcp_sack_block_wire *sp = (struct tcp_sack_block_wire *)(ptr+2); + struct sk_buff *cached_skb; int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3; int reord = tp->packets_out; int prior_fackets; u32 lost_retrans = 0; int flag = 0; int dup_sack = 0; + int cached_fack_count; int i; + int first_sack_index; if (!tp->sacked_out) tp->fackets_out = 0; prior_fackets = tp->fackets_out; + /* Check for D-SACK. */ + if (before(ntohl(sp[0].start_seq), TCP_SKB_CB(ack_skb)->ack_seq)) { + dup_sack = 1; + tp->rx_opt.sack_ok |= 4; + NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV); + } else if (num_sacks > 1 && + !after(ntohl(sp[0].end_seq), ntohl(sp[1].end_seq)) && + !before(ntohl(sp[0].start_seq), ntohl(sp[1].start_seq))) { + dup_sack = 1; + tp->rx_opt.sack_ok |= 4; + NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV); + } + + /* D-SACK for already forgotten data... + * Do dumb counting. */ + if (dup_sack && + !after(ntohl(sp[0].end_seq), prior_snd_una) && + after(ntohl(sp[0].end_seq), tp->undo_marker)) + tp->undo_retrans--; + + /* Eliminate too old ACKs, but take into + * account more or less fresh ones, they can + * contain valid SACK info. + */ + if (before(TCP_SKB_CB(ack_skb)->ack_seq, prior_snd_una - tp->max_window)) + return 0; + /* SACK fastpath: * if the only SACK change is the increase of the end_seq of * the first block then only apply that SACK block * and use retrans queue hinting otherwise slowpath */ flag = 1; - for (i = 0; i< num_sacks; i++) { - __u32 start_seq = ntohl(sp[i].start_seq); - __u32 end_seq = ntohl(sp[i].end_seq); + for (i = 0; i < num_sacks; i++) { + __be32 start_seq = sp[i].start_seq; + __be32 end_seq = sp[i].end_seq; - if (i == 0){ + if (i == 0) { if (tp->recv_sack_cache[i].start_seq != start_seq) flag = 0; } else { @@ -967,39 +997,14 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ } tp->recv_sack_cache[i].start_seq = start_seq; tp->recv_sack_cache[i].end_seq = end_seq; - - /* Check for D-SACK. */ - if (i == 0) { - u32 ack = TCP_SKB_CB(ack_skb)->ack_seq; - - if (before(start_seq, ack)) { - dup_sack = 1; - tp->rx_opt.sack_ok |= 4; - NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV); - } else if (num_sacks > 1 && - !after(end_seq, ntohl(sp[1].end_seq)) && - !before(start_seq, ntohl(sp[1].start_seq))) { - dup_sack = 1; - tp->rx_opt.sack_ok |= 4; - NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV); - } - - /* D-SACK for already forgotten data... - * Do dumb counting. */ - if (dup_sack && - !after(end_seq, prior_snd_una) && - after(end_seq, tp->undo_marker)) - tp->undo_retrans--; - - /* Eliminate too old ACKs, but take into - * account more or less fresh ones, they can - * contain valid SACK info. - */ - if (before(ack, prior_snd_una - tp->max_window)) - return 0; - } + } + /* Clear the rest of the cache sack blocks so they won't match mistakenly. */ + for (; i < ARRAY_SIZE(tp->recv_sack_cache); i++) { + tp->recv_sack_cache[i].start_seq = 0; + tp->recv_sack_cache[i].end_seq = 0; } + first_sack_index = 0; if (flag) num_sacks = 1; else { @@ -1016,6 +1021,10 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ tmp = sp[j]; sp[j] = sp[j+1]; sp[j+1] = tmp; + + /* Track where the first SACK block goes to */ + if (j == first_sack_index) + first_sack_index = j+1; } } @@ -1025,20 +1034,22 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ /* clear flag as used for different purpose in following code */ flag = 0; + /* Use SACK fastpath hint if valid */ + cached_skb = tp->fastpath_skb_hint; + cached_fack_count = tp->fastpath_cnt_hint; + if (!cached_skb) { + cached_skb = sk->sk_write_queue.next; + cached_fack_count = 0; + } + for (i=0; i<num_sacks; i++, sp++) { struct sk_buff *skb; __u32 start_seq = ntohl(sp->start_seq); __u32 end_seq = ntohl(sp->end_seq); int fack_count; - /* Use SACK fastpath hint if valid */ - if (tp->fastpath_skb_hint) { - skb = tp->fastpath_skb_hint; - fack_count = tp->fastpath_cnt_hint; - } else { - skb = sk->sk_write_queue.next; - fack_count = 0; - } + skb = cached_skb; + fack_count = cached_fack_count; /* Event "B" in the comment above. */ if (after(end_seq, tp->high_seq)) @@ -1048,8 +1059,12 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ int in_sack, pcount; u8 sacked; - tp->fastpath_skb_hint = skb; - tp->fastpath_cnt_hint = fack_count; + cached_skb = skb; + cached_fack_count = fack_count; + if (i == first_sack_index) { + tp->fastpath_skb_hint = skb; + tp->fastpath_cnt_hint = fack_count; + } /* The retransmission queue is always in order, so * we can short-circuit the walk early. diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 12de90a5047c..f51d6404c61c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -191,7 +191,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tmp = ip_route_connect(&rt, nexthop, inet->saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_TCP, - inet->sport, usin->sin_port, sk); + inet->sport, usin->sin_port, sk, 1); if (tmp < 0) return tmp; @@ -502,11 +502,11 @@ void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) struct tcphdr *th = skb->h.th; if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v4_check(th, len, - inet->saddr, inet->daddr, 0); + th->check = ~tcp_v4_check(len, inet->saddr, + inet->daddr, 0); skb->csum_offset = offsetof(struct tcphdr, check); } else { - th->check = tcp_v4_check(th, len, inet->saddr, inet->daddr, + th->check = tcp_v4_check(len, inet->saddr, inet->daddr, csum_partial((char *)th, th->doff << 2, skb->csum)); @@ -525,7 +525,7 @@ int tcp_v4_gso_send_check(struct sk_buff *skb) th = skb->h.th; th->check = 0; - th->check = ~tcp_v4_check(th, skb->len, iph->saddr, iph->daddr, 0); + th->check = ~tcp_v4_check(skb->len, iph->saddr, iph->daddr, 0); skb->csum_offset = offsetof(struct tcphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; return 0; @@ -747,7 +747,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req, if (skb) { struct tcphdr *th = skb->h.th; - th->check = tcp_v4_check(th, skb->len, + th->check = tcp_v4_check(skb->len, ireq->loc_addr, ireq->rmt_addr, csum_partial((char *)th, skb->len, @@ -1514,7 +1514,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) static __sum16 tcp_v4_checksum_init(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_COMPLETE) { - if (!tcp_v4_check(skb->h.th, skb->len, skb->nh.iph->saddr, + if (!tcp_v4_check(skb->len, skb->nh.iph->saddr, skb->nh.iph->daddr, skb->csum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; return 0; @@ -2051,7 +2051,7 @@ static void *established_get_first(struct seq_file *seq) } st->state = TCP_SEQ_STATE_TIME_WAIT; inet_twsk_for_each(tw, node, - &tcp_hashinfo.ehash[st->bucket + tcp_hashinfo.ehash_size].chain) { + &tcp_hashinfo.ehash[st->bucket].twchain) { if (tw->tw_family != st->family) { continue; } @@ -2107,7 +2107,7 @@ get_tw: } st->state = TCP_SEQ_STATE_TIME_WAIT; - tw = tw_head(&tcp_hashinfo.ehash[st->bucket + tcp_hashinfo.ehash_size].chain); + tw = tw_head(&tcp_hashinfo.ehash[st->bucket].twchain); goto get_tw; found: cur = sk; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 975f4472af29..58b7111523f4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -965,7 +965,8 @@ static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, struct sk_buff *sk u32 in_flight, cwnd; /* Don't be strict about the congestion window for the final FIN. */ - if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) + if ((TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) && + tcp_skb_pcount(skb) == 1) return 1; in_flight = tcp_packets_in_flight(tp); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index cfff930f2baf..8b54c68a0d12 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -629,7 +629,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, { .sport = inet->sport, .dport = dport } } }; security_sk_classify_flow(sk, &fl); - err = ip_route_output_flow(&rt, &fl, sk, !(msg->msg_flags&MSG_DONTWAIT)); + err = ip_route_output_flow(&rt, &fl, sk, 1); if (err) goto out; diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index e23c21d31a53..e54c5494c88f 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -23,6 +23,12 @@ static inline void ipip_ecn_decapsulate(struct sk_buff *skb) IP_ECN_set_ce(inner_iph); } +static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb) +{ + if (INET_ECN_is_ce(iph->tos)) + IP6_ECN_set_ce(skb->nh.ipv6h); +} + /* Add encapsulation header. * * The top IP header will be constructed per RFC 2401. The following fields @@ -36,6 +42,7 @@ static inline void ipip_ecn_decapsulate(struct sk_buff *skb) static int xfrm4_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { struct dst_entry *dst = skb->dst; + struct xfrm_dst *xdst = (struct xfrm_dst*)dst; struct iphdr *iph, *top_iph; int flags; @@ -48,15 +55,27 @@ static int xfrm4_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->ihl = 5; top_iph->version = 4; + flags = x->props.flags; + /* DS disclosed */ - top_iph->tos = INET_ECN_encapsulate(iph->tos, iph->tos); + if (xdst->route->ops->family == AF_INET) { + top_iph->protocol = IPPROTO_IPIP; + top_iph->tos = INET_ECN_encapsulate(iph->tos, iph->tos); + top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? + 0 : (iph->frag_off & htons(IP_DF)); + } +#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) + else { + struct ipv6hdr *ipv6h = (struct ipv6hdr*)iph; + top_iph->protocol = IPPROTO_IPV6; + top_iph->tos = INET_ECN_encapsulate(iph->tos, ipv6_get_dsfield(ipv6h)); + top_iph->frag_off = 0; + } +#endif - flags = x->props.flags; if (flags & XFRM_STATE_NOECN) IP_ECN_clear(top_iph); - top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? - 0 : (iph->frag_off & htons(IP_DF)); if (!top_iph->frag_off) __ip_select_ident(top_iph, dst->child, 0); @@ -64,7 +83,6 @@ static int xfrm4_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; - top_iph->protocol = IPPROTO_IPIP; memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options)); return 0; @@ -75,8 +93,16 @@ static int xfrm4_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) struct iphdr *iph = skb->nh.iph; int err = -EINVAL; - if (iph->protocol != IPPROTO_IPIP) - goto out; + switch(iph->protocol){ + case IPPROTO_IPIP: +#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) + case IPPROTO_IPV6: + break; +#endif + default: + goto out; + } + if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; @@ -84,10 +110,19 @@ static int xfrm4_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) goto out; - if (x->props.flags & XFRM_STATE_DECAP_DSCP) - ipv4_copy_dscp(iph, skb->h.ipiph); - if (!(x->props.flags & XFRM_STATE_NOECN)) - ipip_ecn_decapsulate(skb); + if (iph->protocol == IPPROTO_IPIP) { + if (x->props.flags & XFRM_STATE_DECAP_DSCP) + ipv4_copy_dscp(iph, skb->h.ipiph); + if (!(x->props.flags & XFRM_STATE_NOECN)) + ipip_ecn_decapsulate(skb); + } +#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) + else { + if (!(x->props.flags & XFRM_STATE_NOECN)) + ipip6_ecn_decapsulate(iph, skb); + skb->protocol = htons(ETH_P_IPV6); + } +#endif skb->mac.raw = memmove(skb->data - skb->mac_len, skb->mac.raw, skb->mac_len); skb->nh.raw = skb->data; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index fb9f69c616f5..699f27ce62ad 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -72,13 +72,11 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int struct dst_entry *dst, *dst_prev; struct rtable *rt0 = (struct rtable*)(*dst_p); struct rtable *rt = rt0; - __be32 remote = fl->fl4_dst; - __be32 local = fl->fl4_src; struct flowi fl_tunnel = { .nl_u = { .ip4_u = { - .saddr = local, - .daddr = remote, + .saddr = fl->fl4_src, + .daddr = fl->fl4_dst, .tos = fl->fl4_tos } } @@ -94,7 +92,6 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int for (i = 0; i < nx; i++) { struct dst_entry *dst1 = dst_alloc(&xfrm4_dst_ops); struct xfrm_dst *xdst; - int tunnel = 0; if (unlikely(dst1 == NULL)) { err = -ENOBUFS; @@ -116,19 +113,28 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int dst1->next = dst_prev; dst_prev = dst1; - if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { - remote = xfrm[i]->id.daddr.a4; - local = xfrm[i]->props.saddr.a4; - tunnel = 1; - } + header_len += xfrm[i]->props.header_len; trailer_len += xfrm[i]->props.trailer_len; - if (tunnel) { - fl_tunnel.fl4_src = local; - fl_tunnel.fl4_dst = remote; + if (xfrm[i]->props.mode == XFRM_MODE_TUNNEL) { + unsigned short encap_family = xfrm[i]->props.family; + switch(encap_family) { + case AF_INET: + fl_tunnel.fl4_dst = xfrm[i]->id.daddr.a4; + fl_tunnel.fl4_src = xfrm[i]->props.saddr.a4; + break; +#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) + case AF_INET6: + ipv6_addr_copy(&fl_tunnel.fl6_dst, (struct in6_addr*)&xfrm[i]->id.daddr.a6); + ipv6_addr_copy(&fl_tunnel.fl6_src, (struct in6_addr*)&xfrm[i]->props.saddr.a6); + break; +#endif + default: + BUG_ON(1); + } err = xfrm_dst_lookup((struct xfrm_dst **)&rt, - &fl_tunnel, AF_INET); + &fl_tunnel, encap_family); if (err) goto error; } else @@ -145,6 +151,7 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int i = 0; for (; dst_prev != &rt->u.dst; dst_prev = dst_prev->child) { struct xfrm_dst *x = (struct xfrm_dst*)dst_prev; + struct xfrm_state_afinfo *afinfo; x->u.rt.fl = *fl; dst_prev->xfrm = xfrm[i++]; @@ -162,8 +169,18 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int /* Copy neighbout for reachability confirmation */ dst_prev->neighbour = neigh_clone(rt->u.dst.neighbour); dst_prev->input = rt->u.dst.input; - dst_prev->output = xfrm4_output; - if (rt->peer) + /* XXX: When IPv6 module can be unloaded, we should manage reference + * to xfrm6_output in afinfo->output. Miyazawa + * */ + afinfo = xfrm_state_get_afinfo(dst_prev->xfrm->props.family); + if (!afinfo) { + dst = *dst_p; + err = -EAFNOSUPPORT; + goto error; + } + dst_prev->output = afinfo->output; + xfrm_state_put_afinfo(afinfo); + if (dst_prev->xfrm->props.family == AF_INET && rt->peer) atomic_inc(&rt->peer->refcnt); x->u.rt.peer = rt->peer; /* Sheit... I remember I did this right. Apparently, @@ -274,7 +291,7 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt.idev)) in_dev_put(xdst->u.rt.idev); - if (likely(xdst->u.rt.peer)) + if (dst->xfrm->props.family == AF_INET && likely(xdst->u.rt.peer)) inet_putpeer(xdst->u.rt.peer); xfrm_dst_destroy(xdst); } diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 3cc3df0c6ece..93e2c061cdda 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -51,6 +51,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = { .family = AF_INET, .init_flags = xfrm4_init_flags, .init_tempsel = __xfrm4_init_tempsel, + .output = xfrm4_output, }; void __init xfrm4_state_init(void) |