diff options
author | Jiri Kosina <jkosina@suse.cz> | 2012-10-28 19:28:52 +0100 |
---|---|---|
committer | Jiri Kosina <jkosina@suse.cz> | 2012-10-28 19:29:19 +0100 |
commit | 3bd7bf1f0fe14f591c089ae61bbfa9bd356f178a (patch) | |
tree | 0058693cc9e70b7461dae551f8a19aff2efd13ca /net/netfilter | |
parent | f16f84937d769c893492160b1a8c3672e3992beb (diff) | |
parent | e657e078d3dfa9f96976db7a2b5fd7d7c9f1f1a6 (diff) |
Merge branch 'master' into for-next
Sync up with Linus' tree to be able to apply Cesar's patch
against newer version of the code.
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Diffstat (limited to 'net/netfilter')
68 files changed, 4624 insertions, 731 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index c19b214ffd5..fefa514b991 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -356,6 +356,55 @@ config NETFILTER_NETLINK_QUEUE_CT If this option is enabled, NFQUEUE can include Connection Tracking information together with the packet is the enqueued via NFNETLINK. +config NF_NAT + tristate + +config NF_NAT_NEEDED + bool + depends on NF_NAT + default y + +config NF_NAT_PROTO_DCCP + tristate + depends on NF_NAT && NF_CT_PROTO_DCCP + default NF_NAT && NF_CT_PROTO_DCCP + +config NF_NAT_PROTO_UDPLITE + tristate + depends on NF_NAT && NF_CT_PROTO_UDPLITE + default NF_NAT && NF_CT_PROTO_UDPLITE + +config NF_NAT_PROTO_SCTP + tristate + default NF_NAT && NF_CT_PROTO_SCTP + depends on NF_NAT && NF_CT_PROTO_SCTP + select LIBCRC32C + +config NF_NAT_AMANDA + tristate + depends on NF_CONNTRACK && NF_NAT + default NF_NAT && NF_CONNTRACK_AMANDA + +config NF_NAT_FTP + tristate + depends on NF_CONNTRACK && NF_NAT + default NF_NAT && NF_CONNTRACK_FTP + +config NF_NAT_IRC + tristate + depends on NF_CONNTRACK && NF_NAT + default NF_NAT && NF_CONNTRACK_IRC + +config NF_NAT_SIP + tristate + depends on NF_CONNTRACK && NF_NAT + default NF_NAT && NF_CONNTRACK_SIP + +config NF_NAT_TFTP + tristate + depends on NF_CONNTRACK && NF_NAT + default NF_NAT && NF_CONNTRACK_TFTP + endif # NF_CONNTRACK # transparent proxy support @@ -599,6 +648,16 @@ config NETFILTER_XT_TARGET_MARK (e.g. when running oldconfig). It selects CONFIG_NETFILTER_XT_MARK (combined mark/MARK module). +config NETFILTER_XT_TARGET_NETMAP + tristate '"NETMAP" target support' + depends on NF_NAT + ---help--- + NETMAP is an implementation of static 1:1 NAT mapping of network + addresses. It maps the network address part, while keeping the host + address part intact. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_TARGET_NFLOG tristate '"NFLOG" target support' default m if NETFILTER_ADVANCED=n @@ -621,19 +680,6 @@ config NETFILTER_XT_TARGET_NFQUEUE To compile it as a module, choose M here. If unsure, say N. -config NETFILTER_XT_TARGET_NOTRACK - tristate '"NOTRACK" target support' - depends on IP_NF_RAW || IP6_NF_RAW - depends on NF_CONNTRACK - help - The NOTRACK target allows a select rule to specify - which packets *not* to enter the conntrack/NAT - subsystem with all the consequences (no ICMP error tracking, - no protocol helpers for the selected packets). - - If you want to compile it as a module, say M here and read - <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. - config NETFILTER_XT_TARGET_RATEEST tristate '"RATEEST" target support' depends on NETFILTER_ADVANCED @@ -644,6 +690,17 @@ config NETFILTER_XT_TARGET_RATEEST To compile it as a module, choose M here. If unsure, say N. +config NETFILTER_XT_TARGET_REDIRECT + tristate "REDIRECT target support" + depends on NF_NAT + ---help--- + REDIRECT is a special case of NAT: all incoming connections are + mapped onto the incoming interface's address, causing the packets to + come to the local machine instead of passing through. This is + useful for transparent proxies. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_TARGET_TEE tristate '"TEE" - packet cloning to alternate destination' depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 1c5160f2278..32596978df1 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -43,6 +43,23 @@ obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o +nf_nat-y := nf_nat_core.o nf_nat_proto_unknown.o nf_nat_proto_common.o \ + nf_nat_proto_udp.o nf_nat_proto_tcp.o nf_nat_helper.o + +obj-$(CONFIG_NF_NAT) += nf_nat.o + +# NAT protocols (nf_nat) +obj-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o +obj-$(CONFIG_NF_NAT_PROTO_UDPLITE) += nf_nat_proto_udplite.o +obj-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o + +# NAT helpers +obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o +obj-$(CONFIG_NF_NAT_FTP) += nf_nat_ftp.o +obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o +obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o +obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o + # transparent proxy support obj-$(CONFIG_NETFILTER_TPROXY) += nf_tproxy_core.o @@ -53,6 +70,7 @@ obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o obj-$(CONFIG_NETFILTER_XT_SET) += xt_set.o +obj-$(CONFIG_NF_NAT) += xt_nat.o # targets obj-$(CONFIG_NETFILTER_XT_TARGET_AUDIT) += xt_AUDIT.o @@ -65,10 +83,11 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_HL) += xt_HL.o obj-$(CONFIG_NETFILTER_XT_TARGET_HMARK) += xt_HMARK.o obj-$(CONFIG_NETFILTER_XT_TARGET_LED) += xt_LED.o obj-$(CONFIG_NETFILTER_XT_TARGET_LOG) += xt_LOG.o +obj-$(CONFIG_NETFILTER_XT_TARGET_NETMAP) += xt_NETMAP.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o -obj-$(CONFIG_NETFILTER_XT_TARGET_NOTRACK) += xt_NOTRACK.o obj-$(CONFIG_NETFILTER_XT_TARGET_RATEEST) += xt_RATEEST.o +obj-$(CONFIG_NETFILTER_XT_TARGET_REDIRECT) += xt_REDIRECT.o obj-$(CONFIG_NETFILTER_XT_TARGET_SECMARK) += xt_SECMARK.o obj-$(CONFIG_NETFILTER_XT_TARGET_TPROXY) += xt_TPROXY.o obj-$(CONFIG_NETFILTER_XT_TARGET_TCPMSS) += xt_TCPMSS.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 0bc6b60db4d..68912dadf13 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -126,7 +126,7 @@ unsigned int nf_iterate(struct list_head *head, unsigned int hook, const struct net_device *indev, const struct net_device *outdev, - struct list_head **i, + struct nf_hook_ops **elemp, int (*okfn)(struct sk_buff *), int hook_thresh) { @@ -136,22 +136,20 @@ unsigned int nf_iterate(struct list_head *head, * The caller must not block between calls to this * function because of risk of continuing from deleted element. */ - list_for_each_continue_rcu(*i, head) { - struct nf_hook_ops *elem = (struct nf_hook_ops *)*i; - - if (hook_thresh > elem->priority) + list_for_each_entry_continue_rcu((*elemp), head, list) { + if (hook_thresh > (*elemp)->priority) continue; /* Optimization: we don't need to hold module reference here, since function can't sleep. --RR */ repeat: - verdict = elem->hook(hook, skb, indev, outdev, okfn); + verdict = (*elemp)->hook(hook, skb, indev, outdev, okfn); if (verdict != NF_ACCEPT) { #ifdef CONFIG_NETFILTER_DEBUG if (unlikely((verdict & NF_VERDICT_MASK) > NF_MAX_VERDICT)) { NFDEBUG("Evil return from %p(%u).\n", - elem->hook, hook); + (*elemp)->hook, hook); continue; } #endif @@ -172,14 +170,14 @@ int nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb, int (*okfn)(struct sk_buff *), int hook_thresh) { - struct list_head *elem; + struct nf_hook_ops *elem; unsigned int verdict; int ret = 0; /* We may already have this, but read-locks nest anyway */ rcu_read_lock(); - elem = &nf_hooks[pf][hook]; + elem = list_entry_rcu(&nf_hooks[pf][hook], struct nf_hook_ops, list); next_hook: verdict = nf_iterate(&nf_hooks[pf][hook], skb, hook, indev, outdev, &elem, okfn, hook_thresh); @@ -273,6 +271,11 @@ EXPORT_SYMBOL_GPL(nfq_ct_nat_hook); #endif /* CONFIG_NF_CONNTRACK */ +#ifdef CONFIG_NF_NAT_NEEDED +void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); +EXPORT_SYMBOL(nf_nat_decode_session_hook); +#endif + #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_net_netfilter; EXPORT_SYMBOL(proc_net_netfilter); diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index 7e1b061aeeb..4a92fd47bd4 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -27,9 +27,12 @@ #define IP_SET_BITMAP_TIMEOUT #include <linux/netfilter/ipset/ip_set_timeout.h> +#define REVISION_MIN 0 +#define REVISION_MAX 0 + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); -MODULE_DESCRIPTION("bitmap:ip type of IP sets"); +IP_SET_MODULE_DESC("bitmap:ip", REVISION_MIN, REVISION_MAX); MODULE_ALIAS("ip_set_bitmap:ip"); /* Type structure */ @@ -284,7 +287,7 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (cidr > 32) + if (!cidr || cidr > 32) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } else @@ -454,7 +457,8 @@ static int bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) { struct bitmap_ip *map; - u32 first_ip, last_ip, hosts, elements; + u32 first_ip, last_ip, hosts; + u64 elements; u8 netmask = 32; int ret; @@ -497,7 +501,7 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) if (netmask == 32) { hosts = 1; - elements = last_ip - first_ip + 1; + elements = (u64)last_ip - first_ip + 1; } else { u8 mask_bits; u32 mask; @@ -515,7 +519,8 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) if (elements > IPSET_BITMAP_MAX_RANGE + 1) return -IPSET_ERR_BITMAP_RANGE_SIZE; - pr_debug("hosts %u, elements %u\n", hosts, elements); + pr_debug("hosts %u, elements %llu\n", + hosts, (unsigned long long)elements); map = kzalloc(sizeof(*map), GFP_KERNEL); if (!map) @@ -554,8 +559,8 @@ static struct ip_set_type bitmap_ip_type __read_mostly = { .features = IPSET_TYPE_IP, .dimension = IPSET_DIM_ONE, .family = NFPROTO_IPV4, - .revision_min = 0, - .revision_max = 0, + .revision_min = REVISION_MIN, + .revision_max = REVISION_MAX, .create = bitmap_ip_create, .create_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index d7eaf10edb6..0f92dc24cb8 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -26,9 +26,12 @@ #include <linux/netfilter/ipset/ip_set_timeout.h> #include <linux/netfilter/ipset/ip_set_bitmap.h> +#define REVISION_MIN 0 +#define REVISION_MAX 0 + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); -MODULE_DESCRIPTION("bitmap:ip,mac type of IP sets"); +IP_SET_MODULE_DESC("bitmap:ip,mac", REVISION_MIN, REVISION_MAX); MODULE_ALIAS("ip_set_bitmap:ip,mac"); enum { @@ -320,11 +323,11 @@ bitmap_ipmac_tlist(const struct ip_set *set, (elem->match == MAC_FILLED && nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, elem->ether))) - goto nla_put_failure; + goto nla_put_failure; timeout = elem->match == MAC_UNSET ? elem->timeout : ip_set_timeout_get(elem->timeout); if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(timeout))) - goto nla_put_failure; + goto nla_put_failure; ipset_nest_end(skb, nested); } ipset_nest_end(skb, atd); @@ -557,7 +560,8 @@ static int bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[], u32 flags) { - u32 first_ip, last_ip, elements; + u32 first_ip, last_ip; + u64 elements; struct bitmap_ipmac *map; int ret; @@ -588,7 +592,7 @@ bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[], } else return -IPSET_ERR_PROTOCOL; - elements = last_ip - first_ip + 1; + elements = (u64)last_ip - first_ip + 1; if (elements > IPSET_BITMAP_MAX_RANGE + 1) return -IPSET_ERR_BITMAP_RANGE_SIZE; @@ -629,8 +633,8 @@ static struct ip_set_type bitmap_ipmac_type = { .features = IPSET_TYPE_IP | IPSET_TYPE_MAC, .dimension = IPSET_DIM_TWO, .family = NFPROTO_IPV4, - .revision_min = 0, - .revision_max = 0, + .revision_min = REVISION_MIN, + .revision_max = REVISION_MAX, .create = bitmap_ipmac_create, .create_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index b9f1fce7053..e6b2db76f4c 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -22,9 +22,12 @@ #define IP_SET_BITMAP_TIMEOUT #include <linux/netfilter/ipset/ip_set_timeout.h> +#define REVISION_MIN 0 +#define REVISION_MAX 0 + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); -MODULE_DESCRIPTION("bitmap:port type of IP sets"); +IP_SET_MODULE_DESC("bitmap:port", REVISION_MIN, REVISION_MAX); MODULE_ALIAS("ip_set_bitmap:port"); /* Type structure */ @@ -487,8 +490,8 @@ static struct ip_set_type bitmap_port_type = { .features = IPSET_TYPE_PORT, .dimension = IPSET_DIM_ONE, .family = NFPROTO_UNSPEC, - .revision_min = 0, - .revision_max = 0, + .revision_min = REVISION_MIN, + .revision_max = REVISION_MAX, .create = bitmap_port_create, .create_policy = { [IPSET_ATTR_PORT] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 9730882697a..778465f217f 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -69,7 +69,8 @@ find_set_type(const char *name, u8 family, u8 revision) list_for_each_entry_rcu(type, &ip_set_type_list, list) if (STREQ(type->name, name) && - (type->family == family || type->family == NFPROTO_UNSPEC) && + (type->family == family || + type->family == NFPROTO_UNSPEC) && revision >= type->revision_min && revision <= type->revision_max) return type; @@ -149,7 +150,8 @@ __find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max, rcu_read_lock(); list_for_each_entry_rcu(type, &ip_set_type_list, list) if (STREQ(type->name, name) && - (type->family == family || type->family == NFPROTO_UNSPEC)) { + (type->family == family || + type->family == NFPROTO_UNSPEC)) { found = true; if (type->revision_min < *min) *min = type->revision_min; @@ -368,6 +370,12 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, set->variant->kadt(set, skb, par, IPSET_ADD, opt); write_unlock_bh(&set->lock); ret = 1; + } else { + /* --return-nomatch: invert matched element */ + if ((opt->flags & IPSET_RETURN_NOMATCH) && + (set->type->features & IPSET_TYPE_NOMATCH) && + (ret > 0 || ret == -ENOTEMPTY)) + ret = -ret; } /* Convert error codes to nomatch */ @@ -563,13 +571,13 @@ flag_exist(const struct nlmsghdr *nlh) } static struct nlmsghdr * -start_msg(struct sk_buff *skb, u32 pid, u32 seq, unsigned int flags, +start_msg(struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags, enum ipset_cmd cmd) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - nlh = nlmsg_put(skb, pid, seq, cmd | (NFNL_SUBSYS_IPSET << 8), + nlh = nlmsg_put(skb, portid, seq, cmd | (NFNL_SUBSYS_IPSET << 8), sizeof(*nfmsg), flags); if (nlh == NULL) return NULL; @@ -721,7 +729,8 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, * by the nfnl mutex. Find the first free index in ip_set_list * and check clashing. */ - if ((ret = find_free_id(set->name, &index, &clash)) != 0) { + ret = find_free_id(set->name, &index, &clash); + if (ret != 0) { /* If this is the same set and requested, ignore error */ if (ret == -EEXIST && (flags & IPSET_FLAG_EXIST) && @@ -1045,7 +1054,7 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) ip_set_id_t index = IPSET_INVALID_ID, max; struct ip_set *set = NULL; struct nlmsghdr *nlh = NULL; - unsigned int flags = NETLINK_CB(cb->skb).pid ? NLM_F_MULTI : 0; + unsigned int flags = NETLINK_CB(cb->skb).portid ? NLM_F_MULTI : 0; u32 dump_type, dump_flags; int ret = 0; @@ -1093,7 +1102,7 @@ dump_last: pr_debug("reference set\n"); __ip_set_get(index); } - nlh = start_msg(skb, NETLINK_CB(cb->skb).pid, + nlh = start_msg(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, IPSET_CMD_LIST); if (!nlh) { @@ -1226,7 +1235,7 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, skb2 = nlmsg_new(payload, GFP_KERNEL); if (skb2 == NULL) return -ENOMEM; - rep = __nlmsg_put(skb2, NETLINK_CB(skb).pid, + rep = __nlmsg_put(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NLMSG_ERROR, payload, 0); errmsg = nlmsg_data(rep); errmsg->error = ret; @@ -1241,7 +1250,7 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, *errline = lineno; - netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); /* Signal netlink not to send its ACK/errmsg. */ return -EINTR; } @@ -1416,7 +1425,7 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb, if (skb2 == NULL) return -ENOMEM; - nlh2 = start_msg(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, + nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, IPSET_CMD_HEADER); if (!nlh2) goto nlmsg_failure; @@ -1428,7 +1437,7 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret < 0) return ret; @@ -1476,7 +1485,7 @@ ip_set_type(struct sock *ctnl, struct sk_buff *skb, if (skb2 == NULL) return -ENOMEM; - nlh2 = start_msg(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, + nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, IPSET_CMD_TYPE); if (!nlh2) goto nlmsg_failure; @@ -1489,7 +1498,7 @@ ip_set_type(struct sock *ctnl, struct sk_buff *skb, nlmsg_end(skb2, nlh2); pr_debug("Send TYPE, nlmsg_len: %u\n", nlh2->nlmsg_len); - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret < 0) return ret; @@ -1525,7 +1534,7 @@ ip_set_protocol(struct sock *ctnl, struct sk_buff *skb, if (skb2 == NULL) return -ENOMEM; - nlh2 = start_msg(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, + nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, IPSET_CMD_PROTOCOL); if (!nlh2) goto nlmsg_failure; @@ -1533,7 +1542,7 @@ ip_set_protocol(struct sock *ctnl, struct sk_buff *skb, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret < 0) return ret; diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index a68dbd4f1e4..ec3dba5dcd6 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -24,9 +24,12 @@ #include <linux/netfilter/ipset/ip_set_timeout.h> #include <linux/netfilter/ipset/ip_set_hash.h> +#define REVISION_MIN 0 +#define REVISION_MAX 0 + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); -MODULE_DESCRIPTION("hash:ip type of IP sets"); +IP_SET_MODULE_DESC("hash:ip", REVISION_MIN, REVISION_MAX); MODULE_ALIAS("ip_set_hash:ip"); /* Type specific function prefix */ @@ -114,7 +117,7 @@ nla_put_failure: static inline void hash_ip4_data_next(struct ip_set_hash *h, const struct hash_ip4_elem *d) { - h->next.ip = ntohl(d->ip); + h->next.ip = d->ip; } static int @@ -179,7 +182,7 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (cidr > 32) + if (!cidr || cidr > 32) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } else @@ -188,7 +191,7 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); if (retried) - ip = h->next.ip; + ip = ntohl(h->next.ip); for (; !before(ip_to, ip); ip += hosts) { nip = htonl(ip); if (nip == 0) @@ -452,8 +455,8 @@ static struct ip_set_type hash_ip_type __read_mostly = { .features = IPSET_TYPE_IP, .dimension = IPSET_DIM_ONE, .family = NFPROTO_UNSPEC, - .revision_min = 0, - .revision_max = 0, + .revision_min = REVISION_MIN, + .revision_max = REVISION_MAX, .create = hash_ip_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 92722bb82ee..0171f7502fa 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -25,9 +25,12 @@ #include <linux/netfilter/ipset/ip_set_getport.h> #include <linux/netfilter/ipset/ip_set_hash.h> +#define REVISION_MIN 0 +#define REVISION_MAX 1 /* SCTP and UDPLITE support added */ + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); -MODULE_DESCRIPTION("hash:ip,port type of IP sets"); +IP_SET_MODULE_DESC("hash:ip,port", REVISION_MIN, REVISION_MAX); MODULE_ALIAS("ip_set_hash:ip,port"); /* Type specific function prefix */ @@ -130,8 +133,8 @@ static inline void hash_ipport4_data_next(struct ip_set_hash *h, const struct hash_ipport4_elem *d) { - h->next.ip = ntohl(d->ip); - h->next.port = ntohs(d->port); + h->next.ip = d->ip; + h->next.port = d->port; } static int @@ -217,7 +220,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (cidr > 32) + if (!cidr || cidr > 32) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } else @@ -231,9 +234,10 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], } if (retried) - ip = h->next.ip; + ip = ntohl(h->next.ip); for (; !before(ip_to, ip); ip++) { - p = retried && ip == h->next.ip ? h->next.port : port; + p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) + : port; for (; p <= port_to; p++) { data.ip = htonl(ip); data.port = htons(p); @@ -349,7 +353,7 @@ static inline void hash_ipport6_data_next(struct ip_set_hash *h, const struct hash_ipport6_elem *d) { - h->next.port = ntohs(d->port); + h->next.port = d->port; } static int @@ -431,7 +435,7 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); if (retried) - port = h->next.port; + port = ntohs(h->next.port); for (; port <= port_to; port++) { data.port = htons(port); ret = adtfn(set, &data, timeout, flags); @@ -522,8 +526,8 @@ static struct ip_set_type hash_ipport_type __read_mostly = { .features = IPSET_TYPE_IP | IPSET_TYPE_PORT, .dimension = IPSET_DIM_TWO, .family = NFPROTO_UNSPEC, - .revision_min = 0, - .revision_max = 1, /* SCTP and UDPLITE support added */ + .revision_min = REVISION_MIN, + .revision_max = REVISION_MAX, .create = hash_ipport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 0637ce096de..6344ef551ec 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -25,9 +25,12 @@ #include <linux/netfilter/ipset/ip_set_getport.h> #include <linux/netfilter/ipset/ip_set_hash.h> +#define REVISION_MIN 0 +#define REVISION_MAX 1 /* SCTP and UDPLITE support added */ + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); -MODULE_DESCRIPTION("hash:ip,port,ip type of IP sets"); +IP_SET_MODULE_DESC("hash:ip,port,ip", REVISION_MIN, REVISION_MAX); MODULE_ALIAS("ip_set_hash:ip,port,ip"); /* Type specific function prefix */ @@ -133,8 +136,8 @@ static inline void hash_ipportip4_data_next(struct ip_set_hash *h, const struct hash_ipportip4_elem *d) { - h->next.ip = ntohl(d->ip); - h->next.port = ntohs(d->port); + h->next.ip = d->ip; + h->next.port = d->port; } static int @@ -225,7 +228,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (cidr > 32) + if (!cidr || cidr > 32) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } else @@ -239,9 +242,10 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], } if (retried) - ip = h->next.ip; + ip = ntohl(h->next.ip); for (; !before(ip_to, ip); ip++) { - p = retried && ip == h->next.ip ? h->next.port : port; + p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) + : port; for (; p <= port_to; p++) { data.ip = htonl(ip); data.port = htons(p); @@ -362,7 +366,7 @@ static inline void hash_ipportip6_data_next(struct ip_set_hash *h, const struct hash_ipportip6_elem *d) { - h->next.port = ntohs(d->port); + h->next.port = d->port; } static int @@ -449,7 +453,7 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); if (retried) - port = h->next.port; + port = ntohs(h->next.port); for (; port <= port_to; port++) { data.port = htons(port); ret = adtfn(set, &data, timeout, flags); @@ -540,8 +544,8 @@ static struct ip_set_type hash_ipportip_type __read_mostly = { .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2, .dimension = IPSET_DIM_THREE, .family = NFPROTO_UNSPEC, - .revision_min = 0, - .revision_max = 1, /* SCTP and UDPLITE support added */ + .revision_min = REVISION_MIN, + .revision_max = REVISION_MAX, .create = hash_ipportip_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 1ce21ca976e..cb71f9a774e 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -25,9 +25,14 @@ #include <linux/netfilter/ipset/ip_set_getport.h> #include <linux/netfilter/ipset/ip_set_hash.h> +#define REVISION_MIN 0 +/* 1 SCTP and UDPLITE support added */ +/* 2 Range as input support for IPv4 added */ +#define REVISION_MAX 3 /* nomatch flag support added */ + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); -MODULE_DESCRIPTION("hash:ip,port,net type of IP sets"); +IP_SET_MODULE_DESC("hash:ip,port,net", REVISION_MIN, REVISION_MAX); MODULE_ALIAS("ip_set_hash:ip,port,net"); /* Type specific function prefix */ @@ -99,10 +104,10 @@ hash_ipportnet4_data_flags(struct hash_ipportnet4_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } -static inline bool +static inline int hash_ipportnet4_data_match(const struct hash_ipportnet4_elem *elem) { - return !elem->nomatch; + return elem->nomatch ? -ENOTEMPTY : 1; } static inline void @@ -173,9 +178,9 @@ static inline void hash_ipportnet4_data_next(struct ip_set_hash *h, const struct hash_ipportnet4_elem *d) { - h->next.ip = ntohl(d->ip); - h->next.port = ntohs(d->port); - h->next.ip2 = ntohl(d->ip2); + h->next.ip = d->ip; + h->next.port = d->port; + h->next.ip2 = d->ip2; } static int @@ -290,7 +295,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (cidr > 32) + if (!cidr || cidr > 32) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } @@ -314,14 +319,17 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } if (retried) - ip = h->next.ip; + ip = ntohl(h->next.ip); for (; !before(ip_to, ip); ip++) { data.ip = htonl(ip); - p = retried && ip == h->next.ip ? h->next.port : port; + p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) + : port; for (; p <= port_to; p++) { data.port = htons(p); - ip2 = retried && ip == h->next.ip && p == h->next.port - ? h->next.ip2 : ip2_from; + ip2 = retried + && ip == ntohl(h->next.ip) + && p == ntohs(h->next.port) + ? ntohl(h->next.ip2) : ip2_from; while (!after(ip2, ip2_to)) { data.ip2 = htonl(ip2); ip2_last = ip_set_range_to_cidr(ip2, ip2_to, @@ -403,10 +411,10 @@ hash_ipportnet6_data_flags(struct hash_ipportnet6_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } -static inline bool +static inline int hash_ipportnet6_data_match(const struct hash_ipportnet6_elem *elem) { - return !elem->nomatch; + return elem->nomatch ? -ENOTEMPTY : 1; } static inline void @@ -486,7 +494,7 @@ static inline void hash_ipportnet6_data_next(struct ip_set_hash *h, const struct hash_ipportnet6_elem *d) { - h->next.port = ntohs(d->port); + h->next.port = d->port; } static int @@ -598,7 +606,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); if (retried) - port = h->next.port; + port = ntohs(h->next.port); for (; port <= port_to; port++) { data.port = htons(port); ret = adtfn(set, &data, timeout, flags); @@ -689,13 +697,12 @@ hash_ipportnet_create(struct ip_set *set, struct nlattr *tb[], u32 flags) static struct ip_set_type hash_ipportnet_type __read_mostly = { .name = "hash:ip,port,net", .protocol = IPSET_PROTOCOL, - .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2, + .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2 | + IPSET_TYPE_NOMATCH, .dimension = IPSET_DIM_THREE, .family = NFPROTO_UNSPEC, - .revision_min = 0, - /* 1 SCTP and UDPLITE support added */ - /* 2 Range as input support for IPv4 added */ - .revision_max = 3, /* nomatch flag support added */ + .revision_min = REVISION_MIN, + .revision_max = REVISION_MAX, .create = hash_ipportnet_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index c57a6a09906..29e94b981f3 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -23,9 +23,13 @@ #include <linux/netfilter/ipset/ip_set_timeout.h> #include <linux/netfilter/ipset/ip_set_hash.h> +#define REVISION_MIN 0 +/* 1 Range as input support for IPv4 added */ +#define REVISION_MAX 2 /* nomatch flag support added */ + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); -MODULE_DESCRIPTION("hash:net type of IP sets"); +IP_SET_MODULE_DESC("hash:net", REVISION_MIN, REVISION_MAX); MODULE_ALIAS("ip_set_hash:net"); /* Type specific function prefix */ @@ -86,10 +90,10 @@ hash_net4_data_flags(struct hash_net4_elem *dst, u32 flags) dst->nomatch = flags & IPSET_FLAG_NOMATCH; } -static inline bool +static inline int hash_net4_data_match(const struct hash_net4_elem *elem) { - return !elem->nomatch; + return elem->nomatch ? -ENOTEMPTY : 1; } static inline void @@ -152,7 +156,7 @@ static inline void hash_net4_data_next(struct ip_set_hash *h, const struct hash_net4_elem *d) { - h->next.ip = ntohl(d->ip); + h->next.ip = d->ip; } static int @@ -235,7 +239,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], return -IPSET_ERR_HASH_RANGE; } if (retried) - ip = h->next.ip; + ip = ntohl(h->next.ip); while (!after(ip, ip_to)) { data.ip = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &data.cidr); @@ -307,10 +311,10 @@ hash_net6_data_flags(struct hash_net6_elem *dst, u32 flags) dst->nomatch = flags & IPSET_FLAG_NOMATCH; } -static inline bool +static inline int hash_net6_data_match(const struct hash_net6_elem *elem) { - return !elem->nomatch; + return elem->nomatch ? -ENOTEMPTY : 1; } static inline void @@ -532,12 +536,11 @@ hash_net_create(struct ip_set *set, struct nlattr *tb[], u32 flags) static struct ip_set_type hash_net_type __read_mostly = { .name = "hash:net", .protocol = IPSET_PROTOCOL, - .features = IPSET_TYPE_IP, + .features = IPSET_TYPE_IP | IPSET_TYPE_NOMATCH, .dimension = IPSET_DIM_ONE, .family = NFPROTO_UNSPEC, - .revision_min = 0, - /* = 1 Range as input support for IPv4 added */ - .revision_max = 2, /* nomatch flag support added */ + .revision_min = REVISION_MIN, + .revision_max = REVISION_MAX, .create = hash_net_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index d5d3607ae7b..b9a63381e34 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -24,9 +24,13 @@ #include <linux/netfilter/ipset/ip_set_timeout.h> #include <linux/netfilter/ipset/ip_set_hash.h> +#define REVISION_MIN 0 +/* 1 nomatch flag support added */ +#define REVISION_MAX 2 /* /0 support added */ + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); -MODULE_DESCRIPTION("hash:net,iface type of IP sets"); +IP_SET_MODULE_DESC("hash:net,iface", REVISION_MIN, REVISION_MAX); MODULE_ALIAS("ip_set_hash:net,iface"); /* Interface name rbtree */ @@ -140,7 +144,7 @@ struct hash_netiface4_elem_hashed { u8 physdev; u8 cidr; u8 nomatch; - u8 padding; + u8 elem; }; #define HKEY_DATALEN sizeof(struct hash_netiface4_elem_hashed) @@ -151,7 +155,7 @@ struct hash_netiface4_elem { u8 physdev; u8 cidr; u8 nomatch; - u8 padding; + u8 elem; const char *iface; }; @@ -161,7 +165,7 @@ struct hash_netiface4_telem { u8 physdev; u8 cidr; u8 nomatch; - u8 padding; + u8 elem; const char *iface; unsigned long timeout; }; @@ -181,18 +185,14 @@ hash_netiface4_data_equal(const struct hash_netiface4_elem *ip1, static inline bool hash_netiface4_data_isnull(const struct hash_netiface4_elem *elem) { - return elem->cidr == 0; + return elem->elem == 0; } static inline void hash_netiface4_data_copy(struct hash_netiface4_elem *dst, const struct hash_netiface4_elem *src) { - dst->ip = src->ip; - dst->cidr = src->cidr; - dst->physdev = src->physdev; - dst->iface = src->iface; - dst->nomatch = src->nomatch; + memcpy(dst, src, sizeof(*dst)); } static inline void @@ -201,10 +201,10 @@ hash_netiface4_data_flags(struct hash_netiface4_elem *dst, u32 flags) dst->nomatch = flags & IPSET_FLAG_NOMATCH; } -static inline bool +static inline int hash_netiface4_data_match(const struct hash_netiface4_elem *elem) { - return !elem->nomatch; + return elem->nomatch ? -ENOTEMPTY : 1; } static inline void @@ -217,7 +217,7 @@ hash_netiface4_data_netmask(struct hash_netiface4_elem *elem, u8 cidr) static inline void hash_netiface4_data_zero_out(struct hash_netiface4_elem *elem) { - elem->cidr = 0; + elem->elem = 0; } static bool @@ -277,7 +277,7 @@ static inline void hash_netiface4_data_next(struct ip_set_hash *h, const struct hash_netiface4_elem *d) { - h->next.ip = ntohl(d->ip); + h->next.ip = d->ip; } static int @@ -288,7 +288,8 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface4_elem data = { - .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK, + .elem = 1, }; int ret; @@ -339,7 +340,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], { struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netiface4_elem data = { .cidr = HOST_MASK }; + struct hash_netiface4_elem data = { .cidr = HOST_MASK, .elem = 1 }; u32 ip = 0, ip_to, last; u32 timeout = h->timeout; char iface[IFNAMSIZ]; @@ -360,7 +361,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!data.cidr || data.cidr > HOST_MASK) + if (data.cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } @@ -389,7 +390,6 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_ADD && (cadt_flags & IPSET_FLAG_NOMATCH)) flags |= (cadt_flags << 16); } - if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { data.ip = htonl(ip & ip_set_hostmask(data.cidr)); ret = adtfn(set, &data, timeout, flags); @@ -409,7 +409,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], } if (retried) - ip = h->next.ip; + ip = ntohl(h->next.ip); while (!after(ip, ip_to)) { data.ip = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &data.cidr); @@ -442,7 +442,7 @@ struct hash_netiface6_elem_hashed { u8 physdev; u8 cidr; u8 nomatch; - u8 padding; + u8 elem; }; #define HKEY_DATALEN sizeof(struct hash_netiface6_elem_hashed) @@ -452,7 +452,7 @@ struct hash_netiface6_elem { u8 physdev; u8 cidr; u8 nomatch; - u8 padding; + u8 elem; const char *iface; }; @@ -461,7 +461,7 @@ struct hash_netiface6_telem { u8 physdev; u8 cidr; u8 nomatch; - u8 padding; + u8 elem; const char *iface; unsigned long timeout; }; @@ -481,7 +481,7 @@ hash_netiface6_data_equal(const struct hash_netiface6_elem *ip1, static inline bool hash_netiface6_data_isnull(const struct hash_netiface6_elem *elem) { - return elem->cidr == 0; + return elem->elem == 0; } static inline void @@ -497,16 +497,16 @@ hash_netiface6_data_flags(struct hash_netiface6_elem *dst, u32 flags) dst->nomatch = flags & IPSET_FLAG_NOMATCH; } -static inline bool +static inline int hash_netiface6_data_match(const struct hash_netiface6_elem *elem) { - return !elem->nomatch; + return elem->nomatch ? -ENOTEMPTY : 1; } static inline void hash_netiface6_data_zero_out(struct hash_netiface6_elem *elem) { - elem->cidr = 0; + elem->elem = 0; } static inline void @@ -590,7 +590,8 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface6_elem data = { - .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK, + .elem = 1, }; int ret; @@ -637,7 +638,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], { struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netiface6_elem data = { .cidr = HOST_MASK }; + struct hash_netiface6_elem data = { .cidr = HOST_MASK, .elem = 1 }; u32 timeout = h->timeout; char iface[IFNAMSIZ]; int ret; @@ -659,7 +660,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!data.cidr || data.cidr > HOST_MASK) + if (data.cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip6_netmask(&data.ip, data.cidr); @@ -773,11 +774,12 @@ hash_netiface_create(struct ip_set *set, struct nlattr *tb[], u32 flags) static struct ip_set_type hash_netiface_type __read_mostly = { .name = "hash:net,iface", .protocol = IPSET_PROTOCOL, - .features = IPSET_TYPE_IP | IPSET_TYPE_IFACE, + .features = IPSET_TYPE_IP | IPSET_TYPE_IFACE | + IPSET_TYPE_NOMATCH, .dimension = IPSET_DIM_TWO, .family = NFPROTO_UNSPEC, - .revision_min = 0, - .revision_max = 1, /* nomatch flag support added */ + .revision_min = REVISION_MIN, + .revision_max = REVISION_MAX, .create = hash_netiface_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index fc3143a2d41..7ef700de596 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -24,9 +24,14 @@ #include <linux/netfilter/ipset/ip_set_getport.h> #include <linux/netfilter/ipset/ip_set_hash.h> +#define REVISION_MIN 0 +/* 1 SCTP and UDPLITE support added */ +/* 2 Range as input support for IPv4 added */ +#define REVISION_MAX 3 /* nomatch flag support added */ + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); -MODULE_DESCRIPTION("hash:net,port type of IP sets"); +IP_SET_MODULE_DESC("hash:net,port", REVISION_MIN, REVISION_MAX); MODULE_ALIAS("ip_set_hash:net,port"); /* Type specific function prefix */ @@ -99,10 +104,10 @@ hash_netport4_data_flags(struct hash_netport4_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } -static inline bool +static inline int hash_netport4_data_match(const struct hash_netport4_elem *elem) { - return !elem->nomatch; + return elem->nomatch ? -ENOTEMPTY : 1; } static inline void @@ -171,8 +176,8 @@ static inline void hash_netport4_data_next(struct ip_set_hash *h, const struct hash_netport4_elem *d) { - h->next.ip = ntohl(d->ip); - h->next.port = ntohs(d->port); + h->next.ip = d->ip; + h->next.port = d->port; } static int @@ -289,12 +294,13 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], } if (retried) - ip = h->next.ip; + ip = ntohl(h->next.ip); while (!after(ip, ip_to)) { data.ip = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &cidr); data.cidr = cidr - 1; - p = retried && ip == h->next.ip ? h->next.port : port; + p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) + : port; for (; p <= port_to; p++) { data.port = htons(p); ret = adtfn(set, &data, timeout, flags); @@ -369,10 +375,10 @@ hash_netport6_data_flags(struct hash_netport6_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } -static inline bool +static inline int hash_netport6_data_match(const struct hash_netport6_elem *elem) { - return !elem->nomatch; + return elem->nomatch ? -ENOTEMPTY : 1; } static inline void @@ -450,7 +456,7 @@ static inline void hash_netport6_data_next(struct ip_set_hash *h, const struct hash_netport6_elem *d) { - h->next.port = ntohs(d->port); + h->next.port = d->port; } static int @@ -554,7 +560,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); if (retried) - port = h->next.port; + port = ntohs(h->next.port); for (; port <= port_to; port++) { data.port = htons(port); ret = adtfn(set, &data, timeout, flags); @@ -644,13 +650,11 @@ hash_netport_create(struct ip_set *set, struct nlattr *tb[], u32 flags) static struct ip_set_type hash_netport_type __read_mostly = { .name = "hash:net,port", .protocol = IPSET_PROTOCOL, - .features = IPSET_TYPE_IP | IPSET_TYPE_PORT, + .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_NOMATCH, .dimension = IPSET_DIM_TWO, .family = NFPROTO_UNSPEC, - .revision_min = 0, - /* 1 SCTP and UDPLITE support added */ - /* 2, Range as input support for IPv4 added */ - .revision_max = 3, /* nomatch flag support added */ + .revision_min = REVISION_MIN, + .revision_max = REVISION_MAX, .create = hash_netport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 6cb1225765f..8371c2bac2e 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -16,9 +16,12 @@ #include <linux/netfilter/ipset/ip_set_timeout.h> #include <linux/netfilter/ipset/ip_set_list.h> +#define REVISION_MIN 0 +#define REVISION_MAX 0 + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); -MODULE_DESCRIPTION("list:set type of IP sets"); +IP_SET_MODULE_DESC("list:set", REVISION_MIN, REVISION_MAX); MODULE_ALIAS("ip_set_list:set"); /* Member elements without and with timeout */ @@ -579,8 +582,8 @@ static struct ip_set_type list_set_type __read_mostly = { .features = IPSET_TYPE_NAME | IPSET_DUMP_LAST, .dimension = IPSET_DIM_ONE, .family = NFPROTO_UNSPEC, - .revision_min = 0, - .revision_max = 0, + .revision_min = REVISION_MIN, + .revision_max = REVISION_MAX, .create = list_set_create, .create_policy = { [IPSET_ATTR_SIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index f9871385a65..8b2cffdfdd9 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -250,7 +250,8 @@ comment 'IPVS application helper' config IP_VS_FTP tristate "FTP protocol helper" - depends on IP_VS_PROTO_TCP && NF_CONNTRACK && NF_NAT + depends on IP_VS_PROTO_TCP && NF_CONNTRACK && NF_NAT && \ + NF_CONNTRACK_FTP select IP_VS_NFCT ---help--- FTP is a protocol that transfers IP address and/or port number in diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 64f9e8f1320..9713e6e86d4 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -180,22 +180,38 @@ register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto, } -/* - * ip_vs_app registration routine - */ -int register_ip_vs_app(struct net *net, struct ip_vs_app *app) +/* Register application for netns */ +struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app) { struct netns_ipvs *ipvs = net_ipvs(net); - /* increase the module use count */ - ip_vs_use_count_inc(); + struct ip_vs_app *a; + int err = 0; + + if (!ipvs) + return ERR_PTR(-ENOENT); mutex_lock(&__ip_vs_app_mutex); - list_add(&app->a_list, &ipvs->app_list); + list_for_each_entry(a, &ipvs->app_list, a_list) { + if (!strcmp(app->name, a->name)) { + err = -EEXIST; + goto out_unlock; + } + } + a = kmemdup(app, sizeof(*app), GFP_KERNEL); + if (!a) { + err = -ENOMEM; + goto out_unlock; + } + INIT_LIST_HEAD(&a->incs_list); + list_add(&a->a_list, &ipvs->app_list); + /* increase the module use count */ + ip_vs_use_count_inc(); +out_unlock: mutex_unlock(&__ip_vs_app_mutex); - return 0; + return err ? ERR_PTR(err) : a; } @@ -205,20 +221,29 @@ int register_ip_vs_app(struct net *net, struct ip_vs_app *app) */ void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app) { - struct ip_vs_app *inc, *nxt; + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_app *a, *anxt, *inc, *nxt; + + if (!ipvs) + return; mutex_lock(&__ip_vs_app_mutex); - list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) { - ip_vs_app_inc_release(net, inc); - } + list_for_each_entry_safe(a, anxt, &ipvs->app_list, a_list) { + if (app && strcmp(app->name, a->name)) + continue; + list_for_each_entry_safe(inc, nxt, &a->incs_list, a_list) { + ip_vs_app_inc_release(net, inc); + } - list_del(&app->a_list); + list_del(&a->a_list); + kfree(a); - mutex_unlock(&__ip_vs_app_mutex); + /* decrease the module use count */ + ip_vs_use_count_dec(); + } - /* decrease the module use count */ - ip_vs_use_count_dec(); + mutex_unlock(&__ip_vs_app_mutex); } @@ -586,5 +611,6 @@ int __net_init ip_vs_app_net_init(struct net *net) void __net_exit ip_vs_app_net_cleanup(struct net *net) { + unregister_ip_vs_app(net, NULL /* all */); proc_net_remove(net, "ip_vs_app"); } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index b54eccef40b..58918e20f9d 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1303,7 +1303,8 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; - unsigned int offset, ihl, verdict; + unsigned int offset, offset2, ihl, verdict; + bool ipip; *related = 1; @@ -1345,6 +1346,21 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) net = skb_net(skb); + /* Special case for errors for IPIP packets */ + ipip = false; + if (cih->protocol == IPPROTO_IPIP) { + if (unlikely(cih->frag_off & htons(IP_OFFSET))) + return NF_ACCEPT; + /* Error for our IPIP must arrive at LOCAL_IN */ + if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) + return NF_ACCEPT; + offset += cih->ihl * 4; + cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); + if (cih == NULL) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + ipip = true; + } + pd = ip_vs_proto_data_get(net, cih->protocol); if (!pd) return NF_ACCEPT; @@ -1358,11 +1374,14 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking incoming ICMP for"); + offset2 = offset; offset += cih->ihl * 4; ip_vs_fill_iphdr(AF_INET, cih, &ciph); - /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, 1); + /* The embedded headers contain source and dest in reverse order. + * For IPIP this is error for request, not for reply. + */ + cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, ipip ? 0 : 1); if (!cp) return NF_ACCEPT; @@ -1376,6 +1395,57 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) goto out; } + if (ipip) { + __be32 info = ic->un.gateway; + + /* Update the MTU */ + if (ic->type == ICMP_DEST_UNREACH && + ic->code == ICMP_FRAG_NEEDED) { + struct ip_vs_dest *dest = cp->dest; + u32 mtu = ntohs(ic->un.frag.mtu); + + /* Strip outer IP and ICMP, go to IPIP header */ + __skb_pull(skb, ihl + sizeof(_icmph)); + offset2 -= ihl + sizeof(_icmph); + skb_reset_network_header(skb); + IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n", + &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); + rcu_read_lock(); + ipv4_update_pmtu(skb, dev_net(skb->dev), + mtu, 0, 0, 0, 0); + rcu_read_unlock(); + /* Client uses PMTUD? */ + if (!(cih->frag_off & htons(IP_DF))) + goto ignore_ipip; + /* Prefer the resulting PMTU */ + if (dest) { + spin_lock(&dest->dst_lock); + if (dest->dst_cache) + mtu = dst_mtu(dest->dst_cache); + spin_unlock(&dest->dst_lock); + } + if (mtu > 68 + sizeof(struct iphdr)) + mtu -= sizeof(struct iphdr); + info = htonl(mtu); + } + /* Strip outer IP, ICMP and IPIP, go to IP header of + * original request. + */ + __skb_pull(skb, offset2); + skb_reset_network_header(skb); + IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", + &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, + ic->type, ic->code, ntohl(info)); + icmp_send(skb, ic->type, ic->code, info); + /* ICMP can be shorter but anyways, account it */ + ip_vs_out_stats(cp, skb); + +ignore_ipip: + consume_skb(skb); + verdict = NF_STOLEN; + goto out; + } + /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index f51013c07b9..c4ee43710aa 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -539,8 +539,7 @@ static int ip_vs_rs_unhash(struct ip_vs_dest *dest) * Remove it from the rs_table table. */ if (!list_empty(&dest->d_list)) { - list_del(&dest->d_list); - INIT_LIST_HEAD(&dest->d_list); + list_del_init(&dest->d_list); } return 1; @@ -1803,6 +1802,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "pmtu_disc", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -2584,6 +2589,8 @@ __ip_vs_get_timeouts(struct net *net, struct ip_vs_timeout_user *u) struct ip_vs_proto_data *pd; #endif + memset(u, 0, sizeof (*u)); + #ifdef CONFIG_IP_VS_PROTO_TCP pd = ip_vs_proto_data_get(net, IPPROTO_TCP); u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ; @@ -2761,7 +2768,6 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { struct ip_vs_timeout_user t; - memset(&t, 0, sizeof(t)); __ip_vs_get_timeouts(net, &t); if (copy_to_user(user, &t, sizeof(t)) != 0) ret = -EFAULT; @@ -2933,7 +2939,7 @@ static int ip_vs_genl_dump_service(struct sk_buff *skb, { void *hdr; - hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &ip_vs_genl_family, NLM_F_MULTI, IPVS_CMD_NEW_SERVICE); if (!hdr) @@ -3122,7 +3128,7 @@ static int ip_vs_genl_dump_dest(struct sk_buff *skb, struct ip_vs_dest *dest, { void *hdr; - hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &ip_vs_genl_family, NLM_F_MULTI, IPVS_CMD_NEW_DEST); if (!hdr) @@ -3251,7 +3257,7 @@ static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __be32 state, struct netlink_callback *cb) { void *hdr; - hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &ip_vs_genl_family, NLM_F_MULTI, IPVS_CMD_NEW_DAEMON); if (!hdr) @@ -3678,7 +3684,7 @@ static void ip_vs_genl_unregister(void) * per netns intit/exit func. */ #ifdef CONFIG_SYSCTL -int __net_init ip_vs_control_net_init_sysctl(struct net *net) +static int __net_init ip_vs_control_net_init_sysctl(struct net *net) { int idx; struct netns_ipvs *ipvs = net_ipvs(net); @@ -3729,6 +3735,8 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net) ipvs->sysctl_sync_retries = clamp_t(int, DEFAULT_SYNC_RETRIES, 0, 3); tbl[idx++].data = &ipvs->sysctl_sync_retries; tbl[idx++].data = &ipvs->sysctl_nat_icmp_send; + ipvs->sysctl_pmtu_disc = 1; + tbl[idx++].data = &ipvs->sysctl_pmtu_disc; ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); @@ -3746,7 +3754,7 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net) return 0; } -void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) +static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -3757,8 +3765,8 @@ void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) #else -int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; } -void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { } +static int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; } +static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { } #endif diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index b20b29c903e..4f53a5f0443 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -268,6 +268,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, * packet. */ ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, + iph->ihl * 4, start-data, end-start, buf, buf_len); if (ret) { @@ -441,16 +442,10 @@ static int __net_init __ip_vs_ftp_init(struct net *net) if (!ipvs) return -ENOENT; - app = kmemdup(&ip_vs_ftp, sizeof(struct ip_vs_app), GFP_KERNEL); - if (!app) - return -ENOMEM; - INIT_LIST_HEAD(&app->a_list); - INIT_LIST_HEAD(&app->incs_list); - ipvs->ftp_app = app; - ret = register_ip_vs_app(net, app); - if (ret) - goto err_exit; + app = register_ip_vs_app(net, &ip_vs_ftp); + if (IS_ERR(app)) + return PTR_ERR(app); for (i = 0; i < ports_count; i++) { if (!ports[i]) @@ -464,9 +459,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net) return 0; err_unreg: - unregister_ip_vs_app(net, app); -err_exit: - kfree(ipvs->ftp_app); + unregister_ip_vs_app(net, &ip_vs_ftp); return ret; } /* @@ -474,10 +467,7 @@ err_exit: */ static void __ip_vs_ftp_exit(struct net *net) { - struct netns_ipvs *ipvs = net_ipvs(net); - - unregister_ip_vs_app(net, ipvs->ftp_app); - kfree(ipvs->ftp_app); + unregister_ip_vs_app(net, &ip_vs_ftp); } static struct pernet_operations ip_vs_ftp_ops = { diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 65b616ae171..cc4c8095681 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -49,6 +49,8 @@ enum { IP_VS_RT_MODE_RDR = 4, /* Allow redirect from remote daddr to * local */ + IP_VS_RT_MODE_CONNECT = 8, /* Always bind route to saddr */ + IP_VS_RT_MODE_KNOWN_NH = 16,/* Route via remote addr */ }; /* @@ -84,6 +86,60 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos) return dst; } +static inline bool +__mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu) +{ + if (IP6CB(skb)->frag_max_size) { + /* frag_max_size tell us that, this packet have been + * defragmented by netfilter IPv6 conntrack module. + */ + if (IP6CB(skb)->frag_max_size > mtu) + return true; /* largest fragment violate MTU */ + } + else if (skb->len > mtu && !skb_is_gso(skb)) { + return true; /* Packet size violate MTU size */ + } + return false; +} + +/* Get route to daddr, update *saddr, optionally bind route to saddr */ +static struct rtable *do_output_route4(struct net *net, __be32 daddr, + u32 rtos, int rt_mode, __be32 *saddr) +{ + struct flowi4 fl4; + struct rtable *rt; + int loop = 0; + + memset(&fl4, 0, sizeof(fl4)); + fl4.daddr = daddr; + fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0; + fl4.flowi4_tos = rtos; + fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ? + FLOWI_FLAG_KNOWN_NH : 0; + +retry: + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) { + /* Invalid saddr ? */ + if (PTR_ERR(rt) == -EINVAL && *saddr && + rt_mode & IP_VS_RT_MODE_CONNECT && !loop) { + *saddr = 0; + flowi4_update_output(&fl4, 0, rtos, daddr, 0); + goto retry; + } + IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr); + return NULL; + } else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) { + ip_rt_put(rt); + *saddr = fl4.saddr; + flowi4_update_output(&fl4, 0, rtos, daddr, fl4.saddr); + loop++; + goto retry; + } + *saddr = fl4.saddr; + return rt; +} + /* Get route to destination or remote server */ static struct rtable * __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, @@ -98,20 +154,13 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, spin_lock(&dest->dst_lock); if (!(rt = (struct rtable *) __ip_vs_dst_check(dest, rtos))) { - struct flowi4 fl4; - - memset(&fl4, 0, sizeof(fl4)); - fl4.daddr = dest->addr.ip; - fl4.flowi4_tos = rtos; - rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) { + rt = do_output_route4(net, dest->addr.ip, rtos, + rt_mode, &dest->dst_saddr.ip); + if (!rt) { spin_unlock(&dest->dst_lock); - IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", - &dest->addr.ip); return NULL; } __ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0); - dest->dst_saddr.ip = fl4.saddr; IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d, " "rtos=%X\n", &dest->addr.ip, &dest->dst_saddr.ip, @@ -122,19 +171,17 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, *ret_saddr = dest->dst_saddr.ip; spin_unlock(&dest->dst_lock); } else { - struct flowi4 fl4; + __be32 saddr = htonl(INADDR_ANY); - memset(&fl4, 0, sizeof(fl4)); - fl4.daddr = daddr; - fl4.flowi4_tos = rtos; - rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) { - IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", - &daddr); + /* For such unconfigured boxes avoid many route lookups + * for performance reasons because we do not remember saddr + */ + rt_mode &= ~IP_VS_RT_MODE_CONNECT; + rt = do_output_route4(net, daddr, rtos, rt_mode, &saddr); + if (!rt) return NULL; - } if (ret_saddr) - *ret_saddr = fl4.saddr; + *ret_saddr = saddr; } local = rt->rt_flags & RTCF_LOCAL; @@ -331,6 +378,7 @@ ip_vs_dst_reset(struct ip_vs_dest *dest) old_dst = dest->dst_cache; dest->dst_cache = NULL; dst_release(old_dst); + dest->dst_saddr.ip = 0; } #define IP_VS_XMIT_TUNNEL(skb, cp) \ @@ -462,7 +510,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if (skb->len > mtu && !skb_is_gso(skb)) { + if (__mtu_check_toobig_v6(skb, mtu)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -683,7 +731,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if (skb->len > mtu && !skb_is_gso(skb)) { + if (__mtu_check_toobig_v6(skb, mtu)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -766,12 +814,13 @@ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { + struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); struct rtable *rt; /* Route to the other host */ __be32 saddr; /* Source for tunnel */ struct net_device *tdev; /* Device to other host */ struct iphdr *old_iph = ip_hdr(skb); u8 tos = old_iph->tos; - __be16 df = old_iph->frag_off; + __be16 df; struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int mtu; @@ -781,7 +830,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(tos), IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL, + IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_CONNECT, &saddr))) goto tx_error_icmp; if (rt->rt_flags & RTCF_LOCAL) { @@ -796,13 +846,13 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__); goto tx_error_put; } - if (skb_dst(skb)) + if (rt_is_output_route(skb_rtable(skb))) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); - df |= (old_iph->frag_off & htons(IP_DF)); + /* Copy DF, reset fragment offset and MF */ + df = sysctl_pmtu_disc(ipvs) ? old_iph->frag_off & htons(IP_DF) : 0; - if ((old_iph->frag_off & htons(IP_DF) && - mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) { + if (df && mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb)) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; @@ -915,8 +965,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_dst(skb)) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); - if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) && - !skb_is_gso(skb)) { + /* MTU checking: Notice that 'mtu' have been adjusted before hand */ + if (__mtu_check_toobig_v6(skb, mtu)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -1014,7 +1064,8 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(iph->tos), IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL, NULL))) + IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_KNOWN_NH, NULL))) goto tx_error_icmp; if (rt->rt_flags & RTCF_LOCAL) { ip_rt_put(rt); @@ -1082,7 +1133,7 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if (skb->len > mtu) { + if (__mtu_check_toobig_v6(skb, mtu)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -1318,7 +1369,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if (skb->len > mtu && !skb_is_gso(skb)) { + if (__mtu_check_toobig_v6(skb, mtu)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index f2de8c55ac5..c514fe6033d 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -40,6 +40,7 @@ MODULE_PARM_DESC(ts_algo, "textsearch algorithm to use (default kmp)"); unsigned int (*nf_nat_amanda_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp) @@ -155,8 +156,8 @@ static int amanda_help(struct sk_buff *skb, nf_nat_amanda = rcu_dereference(nf_nat_amanda_hook); if (nf_nat_amanda && ct->status & IPS_NAT_MASK) - ret = nf_nat_amanda(skb, ctinfo, off - dataoff, - len, exp); + ret = nf_nat_amanda(skb, ctinfo, protoff, + off - dataoff, len, exp); else if (nf_ct_expect_related(exp) != 0) ret = NF_DROP; nf_ct_expect_put(exp); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 2ceec64b19f..0f241be28f9 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -55,6 +55,12 @@ int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct, const struct nlattr *attr) __read_mostly; EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook); +int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff); +EXPORT_SYMBOL_GPL(nf_nat_seq_adjust_hook); + DEFINE_SPINLOCK(nf_conntrack_lock); EXPORT_SYMBOL_GPL(nf_conntrack_lock); @@ -930,7 +936,6 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, enum ip_conntrack_info ctinfo; struct nf_conntrack_l3proto *l3proto; struct nf_conntrack_l4proto *l4proto; - struct nf_conn_timeout *timeout_ext; unsigned int *timeouts; unsigned int dataoff; u_int8_t protonum; @@ -997,11 +1002,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, NF_CT_ASSERT(skb->nfct); /* Decide what timeout policy we want to apply to this flow. */ - timeout_ext = nf_ct_timeout_find(ct); - if (timeout_ext) - timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext); - else - timeouts = l4proto->get_timeouts(net); + timeouts = nf_ct_timeout_lookup(net, ct, l4proto); ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum, timeouts); if (ret <= 0) { @@ -1223,6 +1224,8 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), spin_lock_bh(&nf_conntrack_lock); for (; *bucket < net->ct.htable_size; (*bucket)++) { hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) { + if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) + continue; ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) goto found; diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index e7be79e640d..de9781b6464 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -61,7 +61,7 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct) goto out_unlock; item.ct = ct; - item.pid = 0; + item.portid = 0; item.report = 0; ret = notify->fcn(events | missed, &item); diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 4bb771d1f57..1ce3befb7c8 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -48,6 +48,7 @@ module_param(loose, bool, 0600); unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, enum nf_ct_ftp_type type, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp); @@ -395,6 +396,12 @@ static int help(struct sk_buff *skb, /* Look up to see if we're just after a \n. */ if (!find_nl_seq(ntohl(th->seq), ct_ftp_info, dir)) { + /* We're picking up this, clear flags and let it continue */ + if (unlikely(ct_ftp_info->flags[dir] & NF_CT_FTP_SEQ_PICKUP)) { + ct_ftp_info->flags[dir] ^= NF_CT_FTP_SEQ_PICKUP; + goto skip_nl_seq; + } + /* Now if this ends in \n, update ftp info. */ pr_debug("nf_conntrack_ftp: wrong seq pos %s(%u) or %s(%u)\n", ct_ftp_info->seq_aft_nl_num[dir] > 0 ? "" : "(UNSET)", @@ -405,6 +412,7 @@ static int help(struct sk_buff *skb, goto out_update_nl; } +skip_nl_seq: /* Initialize IP/IPv6 addr to expected address (it's not mentioned in EPSV responses) */ cmd.l3num = nf_ct_l3num(ct); @@ -489,7 +497,7 @@ static int help(struct sk_buff *skb, nf_nat_ftp = rcu_dereference(nf_nat_ftp_hook); if (nf_nat_ftp && ct->status & IPS_NAT_MASK) ret = nf_nat_ftp(skb, ctinfo, search[dir][i].ftptype, - matchoff, matchlen, exp); + protoff, matchoff, matchlen, exp); else { /* Can't expect this? Best to drop packet now. */ if (nf_ct_expect_related(exp) != 0) @@ -511,6 +519,19 @@ out_update_nl: return ret; } +static int nf_ct_ftp_from_nlattr(struct nlattr *attr, struct nf_conn *ct) +{ + struct nf_ct_ftp_master *ftp = nfct_help_data(ct); + + /* This conntrack has been injected from user-space, always pick up + * sequence tracking. Otherwise, the first FTP command after the + * failover breaks. + */ + ftp->flags[IP_CT_DIR_ORIGINAL] |= NF_CT_FTP_SEQ_PICKUP; + ftp->flags[IP_CT_DIR_REPLY] |= NF_CT_FTP_SEQ_PICKUP; + return 0; +} + static struct nf_conntrack_helper ftp[MAX_PORTS][2] __read_mostly; static const struct nf_conntrack_expect_policy ftp_exp_policy = { @@ -560,6 +581,7 @@ static int __init nf_conntrack_ftp_init(void) ftp[i][j].expect_policy = &ftp_exp_policy; ftp[i][j].me = THIS_MODULE; ftp[i][j].help = help; + ftp[i][j].from_nlattr = nf_ct_ftp_from_nlattr; if (ports[i] == FTP_PORT) sprintf(ftp[i][j].name, "ftp"); else diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 4283b207e63..1b30b0dee70 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -49,12 +49,12 @@ MODULE_PARM_DESC(callforward_filter, "only create call forwarding expectations " "(determined by routing information)"); /* Hooks for NAT */ -int (*set_h245_addr_hook) (struct sk_buff *skb, +int (*set_h245_addr_hook) (struct sk_buff *skb, unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, union nf_inet_addr *addr, __be16 port) __read_mostly; -int (*set_h225_addr_hook) (struct sk_buff *skb, +int (*set_h225_addr_hook) (struct sk_buff *skb, unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, union nf_inet_addr *addr, __be16 port) @@ -62,16 +62,17 @@ int (*set_h225_addr_hook) (struct sk_buff *skb, int (*set_sig_addr_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int count) __read_mostly; int (*set_ras_addr_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int count) __read_mostly; int (*nat_rtp_rtcp_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, __be16 port, __be16 rtp_port, @@ -80,24 +81,28 @@ int (*nat_rtp_rtcp_hook) (struct sk_buff *skb, int (*nat_t120_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp) __read_mostly; int (*nat_h245_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp) __read_mostly; int (*nat_callforwarding_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp) __read_mostly; int (*nat_q931_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int idx, __be16 port, struct nf_conntrack_expect *exp) __read_mostly; @@ -251,6 +256,7 @@ static int get_h245_addr(struct nf_conn *ct, const unsigned char *data, /****************************************************************************/ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr) { @@ -295,9 +301,10 @@ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.dst.u3, sizeof(ct->tuplehash[dir].tuple.src.u3)) && (nat_rtp_rtcp = rcu_dereference(nat_rtp_rtcp_hook)) && + nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { /* NAT needed */ - ret = nat_rtp_rtcp(skb, ct, ctinfo, data, dataoff, + ret = nat_rtp_rtcp(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, rtp_port, rtp_exp, rtcp_exp); } else { /* Conntrack only */ if (nf_ct_expect_related(rtp_exp) == 0) { @@ -324,6 +331,7 @@ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, static int expect_t120(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr) { @@ -353,9 +361,10 @@ static int expect_t120(struct sk_buff *skb, &ct->tuplehash[!dir].tuple.dst.u3, sizeof(ct->tuplehash[dir].tuple.src.u3)) && (nat_t120 = rcu_dereference(nat_t120_hook)) && + nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { /* NAT needed */ - ret = nat_t120(skb, ct, ctinfo, data, dataoff, taddr, + ret = nat_t120(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ if (nf_ct_expect_related(exp) == 0) { @@ -374,6 +383,7 @@ static int expect_t120(struct sk_buff *skb, static int process_h245_channel(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, H2250LogicalChannelParameters *channel) { @@ -381,7 +391,7 @@ static int process_h245_channel(struct sk_buff *skb, if (channel->options & eH2250LogicalChannelParameters_mediaChannel) { /* RTP */ - ret = expect_rtp_rtcp(skb, ct, ctinfo, data, dataoff, + ret = expect_rtp_rtcp(skb, ct, ctinfo, protoff, data, dataoff, &channel->mediaChannel); if (ret < 0) return -1; @@ -390,7 +400,7 @@ static int process_h245_channel(struct sk_buff *skb, if (channel-> options & eH2250LogicalChannelParameters_mediaControlChannel) { /* RTCP */ - ret = expect_rtp_rtcp(skb, ct, ctinfo, data, dataoff, + ret = expect_rtp_rtcp(skb, ct, ctinfo, protoff, data, dataoff, &channel->mediaControlChannel); if (ret < 0) return -1; @@ -402,6 +412,7 @@ static int process_h245_channel(struct sk_buff *skb, /****************************************************************************/ static int process_olc(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, OpenLogicalChannel *olc) { @@ -412,7 +423,8 @@ static int process_olc(struct sk_buff *skb, struct nf_conn *ct, if (olc->forwardLogicalChannelParameters.multiplexParameters.choice == eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters) { - ret = process_h245_channel(skb, ct, ctinfo, data, dataoff, + ret = process_h245_channel(skb, ct, ctinfo, + protoff, data, dataoff, &olc-> forwardLogicalChannelParameters. multiplexParameters. @@ -430,7 +442,8 @@ static int process_olc(struct sk_buff *skb, struct nf_conn *ct, eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters)) { ret = - process_h245_channel(skb, ct, ctinfo, data, dataoff, + process_h245_channel(skb, ct, ctinfo, + protoff, data, dataoff, &olc-> reverseLogicalChannelParameters. multiplexParameters. @@ -448,7 +461,7 @@ static int process_olc(struct sk_buff *skb, struct nf_conn *ct, t120.choice == eDataProtocolCapability_separateLANStack && olc->separateStack.networkAddress.choice == eNetworkAccessParameters_networkAddress_localAreaAddress) { - ret = expect_t120(skb, ct, ctinfo, data, dataoff, + ret = expect_t120(skb, ct, ctinfo, protoff, data, dataoff, &olc->separateStack.networkAddress. localAreaAddress); if (ret < 0) @@ -461,7 +474,7 @@ static int process_olc(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_olca(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, + unsigned int protoff, unsigned char **data, int dataoff, OpenLogicalChannelAck *olca) { H2250LogicalChannelAckParameters *ack; @@ -477,7 +490,8 @@ static int process_olca(struct sk_buff *skb, struct nf_conn *ct, choice == eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters)) { - ret = process_h245_channel(skb, ct, ctinfo, data, dataoff, + ret = process_h245_channel(skb, ct, ctinfo, + protoff, data, dataoff, &olca-> reverseLogicalChannelParameters. multiplexParameters. @@ -496,7 +510,8 @@ static int process_olca(struct sk_buff *skb, struct nf_conn *ct, if (ack->options & eH2250LogicalChannelAckParameters_mediaChannel) { /* RTP */ - ret = expect_rtp_rtcp(skb, ct, ctinfo, data, dataoff, + ret = expect_rtp_rtcp(skb, ct, ctinfo, + protoff, data, dataoff, &ack->mediaChannel); if (ret < 0) return -1; @@ -505,7 +520,8 @@ static int process_olca(struct sk_buff *skb, struct nf_conn *ct, if (ack->options & eH2250LogicalChannelAckParameters_mediaControlChannel) { /* RTCP */ - ret = expect_rtp_rtcp(skb, ct, ctinfo, data, dataoff, + ret = expect_rtp_rtcp(skb, ct, ctinfo, + protoff, data, dataoff, &ack->mediaControlChannel); if (ret < 0) return -1; @@ -515,7 +531,7 @@ static int process_olca(struct sk_buff *skb, struct nf_conn *ct, if ((olca->options & eOpenLogicalChannelAck_separateStack) && olca->separateStack.networkAddress.choice == eNetworkAccessParameters_networkAddress_localAreaAddress) { - ret = expect_t120(skb, ct, ctinfo, data, dataoff, + ret = expect_t120(skb, ct, ctinfo, protoff, data, dataoff, &olca->separateStack.networkAddress. localAreaAddress); if (ret < 0) @@ -528,14 +544,15 @@ static int process_olca(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_h245(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, + unsigned int protoff, unsigned char **data, int dataoff, MultimediaSystemControlMessage *mscm) { switch (mscm->choice) { case eMultimediaSystemControlMessage_request: if (mscm->request.choice == eRequestMessage_openLogicalChannel) { - return process_olc(skb, ct, ctinfo, data, dataoff, + return process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &mscm->request.openLogicalChannel); } pr_debug("nf_ct_h323: H.245 Request %d\n", @@ -544,7 +561,8 @@ static int process_h245(struct sk_buff *skb, struct nf_conn *ct, case eMultimediaSystemControlMessage_response: if (mscm->response.choice == eResponseMessage_openLogicalChannelAck) { - return process_olca(skb, ct, ctinfo, data, dataoff, + return process_olca(skb, ct, ctinfo, + protoff, data, dataoff, &mscm->response. openLogicalChannelAck); } @@ -595,7 +613,8 @@ static int h245_help(struct sk_buff *skb, unsigned int protoff, } /* Process H.245 signal */ - if (process_h245(skb, ct, ctinfo, &data, dataoff, &mscm) < 0) + if (process_h245(skb, ct, ctinfo, protoff, + &data, dataoff, &mscm) < 0) goto drop; } @@ -659,7 +678,7 @@ int get_h225_addr(struct nf_conn *ct, unsigned char *data, /****************************************************************************/ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr) { int dir = CTINFO2DIR(ctinfo); @@ -688,9 +707,10 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.dst.u3, sizeof(ct->tuplehash[dir].tuple.src.u3)) && (nat_h245 = rcu_dereference(nat_h245_hook)) && + nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { /* NAT needed */ - ret = nat_h245(skb, ct, ctinfo, data, dataoff, taddr, + ret = nat_h245(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ if (nf_ct_expect_related(exp) == 0) { @@ -776,6 +796,7 @@ static int callforward_do_filter(const union nf_inet_addr *src, static int expect_callforwarding(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr) { @@ -811,9 +832,11 @@ static int expect_callforwarding(struct sk_buff *skb, &ct->tuplehash[!dir].tuple.dst.u3, sizeof(ct->tuplehash[dir].tuple.src.u3)) && (nat_callforwarding = rcu_dereference(nat_callforwarding_hook)) && + nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { /* Need NAT */ - ret = nat_callforwarding(skb, ct, ctinfo, data, dataoff, + ret = nat_callforwarding(skb, ct, ctinfo, + protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ if (nf_ct_expect_related(exp) == 0) { @@ -831,6 +854,7 @@ static int expect_callforwarding(struct sk_buff *skb, /****************************************************************************/ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, Setup_UUIE *setup) { @@ -844,7 +868,7 @@ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_q931: Setup\n"); if (setup->options & eSetup_UUIE_h245Address) { - ret = expect_h245(skb, ct, ctinfo, data, dataoff, + ret = expect_h245(skb, ct, ctinfo, protoff, data, dataoff, &setup->h245Address); if (ret < 0) return -1; @@ -852,14 +876,15 @@ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, set_h225_addr = rcu_dereference(set_h225_addr_hook); if ((setup->options & eSetup_UUIE_destCallSignalAddress) && - (set_h225_addr) && ct->status & IPS_NAT_MASK && + (set_h225_addr) && nf_ct_l3num(ct) == NFPROTO_IPV4 && + ct->status & IPS_NAT_MASK && get_h225_addr(ct, *data, &setup->destCallSignalAddress, &addr, &port) && memcmp(&addr, &ct->tuplehash[!dir].tuple.src.u3, sizeof(addr))) { pr_debug("nf_ct_q931: set destCallSignalAddress %pI6:%hu->%pI6:%hu\n", &addr, ntohs(port), &ct->tuplehash[!dir].tuple.src.u3, ntohs(ct->tuplehash[!dir].tuple.src.u.tcp.port)); - ret = set_h225_addr(skb, data, dataoff, + ret = set_h225_addr(skb, protoff, data, dataoff, &setup->destCallSignalAddress, &ct->tuplehash[!dir].tuple.src.u3, ct->tuplehash[!dir].tuple.src.u.tcp.port); @@ -868,14 +893,15 @@ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, } if ((setup->options & eSetup_UUIE_sourceCallSignalAddress) && - (set_h225_addr) && ct->status & IPS_NAT_MASK && + (set_h225_addr) && nf_ct_l3num(ct) == NFPROTO_IPV4 && + ct->status & IPS_NAT_MASK && get_h225_addr(ct, *data, &setup->sourceCallSignalAddress, &addr, &port) && memcmp(&addr, &ct->tuplehash[!dir].tuple.dst.u3, sizeof(addr))) { pr_debug("nf_ct_q931: set sourceCallSignalAddress %pI6:%hu->%pI6:%hu\n", &addr, ntohs(port), &ct->tuplehash[!dir].tuple.dst.u3, ntohs(ct->tuplehash[!dir].tuple.dst.u.tcp.port)); - ret = set_h225_addr(skb, data, dataoff, + ret = set_h225_addr(skb, protoff, data, dataoff, &setup->sourceCallSignalAddress, &ct->tuplehash[!dir].tuple.dst.u3, ct->tuplehash[!dir].tuple.dst.u.tcp.port); @@ -885,7 +911,8 @@ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, if (setup->options & eSetup_UUIE_fastStart) { for (i = 0; i < setup->fastStart.count; i++) { - ret = process_olc(skb, ct, ctinfo, data, dataoff, + ret = process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &setup->fastStart.item[i]); if (ret < 0) return -1; @@ -899,6 +926,7 @@ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, static int process_callproceeding(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, CallProceeding_UUIE *callproc) { @@ -908,7 +936,7 @@ static int process_callproceeding(struct sk_buff *skb, pr_debug("nf_ct_q931: CallProceeding\n"); if (callproc->options & eCallProceeding_UUIE_h245Address) { - ret = expect_h245(skb, ct, ctinfo, data, dataoff, + ret = expect_h245(skb, ct, ctinfo, protoff, data, dataoff, &callproc->h245Address); if (ret < 0) return -1; @@ -916,7 +944,8 @@ static int process_callproceeding(struct sk_buff *skb, if (callproc->options & eCallProceeding_UUIE_fastStart) { for (i = 0; i < callproc->fastStart.count; i++) { - ret = process_olc(skb, ct, ctinfo, data, dataoff, + ret = process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &callproc->fastStart.item[i]); if (ret < 0) return -1; @@ -929,6 +958,7 @@ static int process_callproceeding(struct sk_buff *skb, /****************************************************************************/ static int process_connect(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, Connect_UUIE *connect) { @@ -938,7 +968,7 @@ static int process_connect(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_q931: Connect\n"); if (connect->options & eConnect_UUIE_h245Address) { - ret = expect_h245(skb, ct, ctinfo, data, dataoff, + ret = expect_h245(skb, ct, ctinfo, protoff, data, dataoff, &connect->h245Address); if (ret < 0) return -1; @@ -946,7 +976,8 @@ static int process_connect(struct sk_buff *skb, struct nf_conn *ct, if (connect->options & eConnect_UUIE_fastStart) { for (i = 0; i < connect->fastStart.count; i++) { - ret = process_olc(skb, ct, ctinfo, data, dataoff, + ret = process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &connect->fastStart.item[i]); if (ret < 0) return -1; @@ -959,6 +990,7 @@ static int process_connect(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_alerting(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, Alerting_UUIE *alert) { @@ -968,7 +1000,7 @@ static int process_alerting(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_q931: Alerting\n"); if (alert->options & eAlerting_UUIE_h245Address) { - ret = expect_h245(skb, ct, ctinfo, data, dataoff, + ret = expect_h245(skb, ct, ctinfo, protoff, data, dataoff, &alert->h245Address); if (ret < 0) return -1; @@ -976,7 +1008,8 @@ static int process_alerting(struct sk_buff *skb, struct nf_conn *ct, if (alert->options & eAlerting_UUIE_fastStart) { for (i = 0; i < alert->fastStart.count; i++) { - ret = process_olc(skb, ct, ctinfo, data, dataoff, + ret = process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &alert->fastStart.item[i]); if (ret < 0) return -1; @@ -989,6 +1022,7 @@ static int process_alerting(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_facility(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, Facility_UUIE *facility) { @@ -999,15 +1033,15 @@ static int process_facility(struct sk_buff *skb, struct nf_conn *ct, if (facility->reason.choice == eFacilityReason_callForwarded) { if (facility->options & eFacility_UUIE_alternativeAddress) - return expect_callforwarding(skb, ct, ctinfo, data, - dataoff, + return expect_callforwarding(skb, ct, ctinfo, + protoff, data, dataoff, &facility-> alternativeAddress); return 0; } if (facility->options & eFacility_UUIE_h245Address) { - ret = expect_h245(skb, ct, ctinfo, data, dataoff, + ret = expect_h245(skb, ct, ctinfo, protoff, data, dataoff, &facility->h245Address); if (ret < 0) return -1; @@ -1015,7 +1049,8 @@ static int process_facility(struct sk_buff *skb, struct nf_conn *ct, if (facility->options & eFacility_UUIE_fastStart) { for (i = 0; i < facility->fastStart.count; i++) { - ret = process_olc(skb, ct, ctinfo, data, dataoff, + ret = process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &facility->fastStart.item[i]); if (ret < 0) return -1; @@ -1028,6 +1063,7 @@ static int process_facility(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_progress(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, Progress_UUIE *progress) { @@ -1037,7 +1073,7 @@ static int process_progress(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_q931: Progress\n"); if (progress->options & eProgress_UUIE_h245Address) { - ret = expect_h245(skb, ct, ctinfo, data, dataoff, + ret = expect_h245(skb, ct, ctinfo, protoff, data, dataoff, &progress->h245Address); if (ret < 0) return -1; @@ -1045,7 +1081,8 @@ static int process_progress(struct sk_buff *skb, struct nf_conn *ct, if (progress->options & eProgress_UUIE_fastStart) { for (i = 0; i < progress->fastStart.count; i++) { - ret = process_olc(skb, ct, ctinfo, data, dataoff, + ret = process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &progress->fastStart.item[i]); if (ret < 0) return -1; @@ -1058,7 +1095,8 @@ static int process_progress(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_q931(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, Q931 *q931) + unsigned int protoff, unsigned char **data, int dataoff, + Q931 *q931) { H323_UU_PDU *pdu = &q931->UUIE.h323_uu_pdu; int i; @@ -1066,28 +1104,29 @@ static int process_q931(struct sk_buff *skb, struct nf_conn *ct, switch (pdu->h323_message_body.choice) { case eH323_UU_PDU_h323_message_body_setup: - ret = process_setup(skb, ct, ctinfo, data, dataoff, + ret = process_setup(skb, ct, ctinfo, protoff, data, dataoff, &pdu->h323_message_body.setup); break; case eH323_UU_PDU_h323_message_body_callProceeding: - ret = process_callproceeding(skb, ct, ctinfo, data, dataoff, + ret = process_callproceeding(skb, ct, ctinfo, + protoff, data, dataoff, &pdu->h323_message_body. callProceeding); break; case eH323_UU_PDU_h323_message_body_connect: - ret = process_connect(skb, ct, ctinfo, data, dataoff, + ret = process_connect(skb, ct, ctinfo, protoff, data, dataoff, &pdu->h323_message_body.connect); break; case eH323_UU_PDU_h323_message_body_alerting: - ret = process_alerting(skb, ct, ctinfo, data, dataoff, + ret = process_alerting(skb, ct, ctinfo, protoff, data, dataoff, &pdu->h323_message_body.alerting); break; case eH323_UU_PDU_h323_message_body_facility: - ret = process_facility(skb, ct, ctinfo, data, dataoff, + ret = process_facility(skb, ct, ctinfo, protoff, data, dataoff, &pdu->h323_message_body.facility); break; case eH323_UU_PDU_h323_message_body_progress: - ret = process_progress(skb, ct, ctinfo, data, dataoff, + ret = process_progress(skb, ct, ctinfo, protoff, data, dataoff, &pdu->h323_message_body.progress); break; default: @@ -1101,7 +1140,8 @@ static int process_q931(struct sk_buff *skb, struct nf_conn *ct, if (pdu->options & eH323_UU_PDU_h245Control) { for (i = 0; i < pdu->h245Control.count; i++) { - ret = process_h245(skb, ct, ctinfo, data, dataoff, + ret = process_h245(skb, ct, ctinfo, + protoff, data, dataoff, &pdu->h245Control.item[i]); if (ret < 0) return -1; @@ -1146,7 +1186,8 @@ static int q931_help(struct sk_buff *skb, unsigned int protoff, } /* Process Q.931 signal */ - if (process_q931(skb, ct, ctinfo, &data, dataoff, &q931) < 0) + if (process_q931(skb, ct, ctinfo, protoff, + &data, dataoff, &q931) < 0) goto drop; } @@ -1243,7 +1284,7 @@ static int set_expect_timeout(struct nf_conntrack_expect *exp, /****************************************************************************/ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int count) { struct nf_ct_h323_master *info = nfct_help_data(ct); @@ -1278,8 +1319,10 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, exp->flags = NF_CT_EXPECT_PERMANENT; /* Accept multiple calls */ nat_q931 = rcu_dereference(nat_q931_hook); - if (nat_q931 && ct->status & IPS_NAT_MASK) { /* Need NAT */ - ret = nat_q931(skb, ct, ctinfo, data, taddr, i, port, exp); + if (nat_q931 && nf_ct_l3num(ct) == NFPROTO_IPV4 && + ct->status & IPS_NAT_MASK) { /* Need NAT */ + ret = nat_q931(skb, ct, ctinfo, protoff, data, + taddr, i, port, exp); } else { /* Conntrack only */ if (nf_ct_expect_related(exp) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); @@ -1299,6 +1342,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_grq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, GatekeeperRequest *grq) { typeof(set_ras_addr_hook) set_ras_addr; @@ -1306,8 +1350,9 @@ static int process_grq(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_ras: GRQ\n"); set_ras_addr = rcu_dereference(set_ras_addr_hook); - if (set_ras_addr && ct->status & IPS_NAT_MASK) /* NATed */ - return set_ras_addr(skb, ct, ctinfo, data, + if (set_ras_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && + ct->status & IPS_NAT_MASK) /* NATed */ + return set_ras_addr(skb, ct, ctinfo, protoff, data, &grq->rasAddress, 1); return 0; } @@ -1315,6 +1360,7 @@ static int process_grq(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, GatekeeperConfirm *gcf) { int dir = CTINFO2DIR(ctinfo); @@ -1359,6 +1405,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_rrq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, RegistrationRequest *rrq) { struct nf_ct_h323_master *info = nfct_help_data(ct); @@ -1367,15 +1414,16 @@ static int process_rrq(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_ras: RRQ\n"); - ret = expect_q931(skb, ct, ctinfo, data, + ret = expect_q931(skb, ct, ctinfo, protoff, data, rrq->callSignalAddress.item, rrq->callSignalAddress.count); if (ret < 0) return -1; set_ras_addr = rcu_dereference(set_ras_addr_hook); - if (set_ras_addr && ct->status & IPS_NAT_MASK) { - ret = set_ras_addr(skb, ct, ctinfo, data, + if (set_ras_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && + ct->status & IPS_NAT_MASK) { + ret = set_ras_addr(skb, ct, ctinfo, protoff, data, rrq->rasAddress.item, rrq->rasAddress.count); if (ret < 0) @@ -1394,6 +1442,7 @@ static int process_rrq(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, RegistrationConfirm *rcf) { struct nf_ct_h323_master *info = nfct_help_data(ct); @@ -1405,8 +1454,9 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_ras: RCF\n"); set_sig_addr = rcu_dereference(set_sig_addr_hook); - if (set_sig_addr && ct->status & IPS_NAT_MASK) { - ret = set_sig_addr(skb, ct, ctinfo, data, + if (set_sig_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && + ct->status & IPS_NAT_MASK) { + ret = set_sig_addr(skb, ct, ctinfo, protoff, data, rcf->callSignalAddress.item, rcf->callSignalAddress.count); if (ret < 0) @@ -1443,6 +1493,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_urq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, UnregistrationRequest *urq) { struct nf_ct_h323_master *info = nfct_help_data(ct); @@ -1453,8 +1504,9 @@ static int process_urq(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_ras: URQ\n"); set_sig_addr = rcu_dereference(set_sig_addr_hook); - if (set_sig_addr && ct->status & IPS_NAT_MASK) { - ret = set_sig_addr(skb, ct, ctinfo, data, + if (set_sig_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && + ct->status & IPS_NAT_MASK) { + ret = set_sig_addr(skb, ct, ctinfo, protoff, data, urq->callSignalAddress.item, urq->callSignalAddress.count); if (ret < 0) @@ -1475,6 +1527,7 @@ static int process_urq(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_arq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, AdmissionRequest *arq) { const struct nf_ct_h323_master *info = nfct_help_data(ct); @@ -1491,9 +1544,10 @@ static int process_arq(struct sk_buff *skb, struct nf_conn *ct, &addr, &port) && !memcmp(&addr, &ct->tuplehash[dir].tuple.src.u3, sizeof(addr)) && port == info->sig_port[dir] && + nf_ct_l3num(ct) == NFPROTO_IPV4 && set_h225_addr && ct->status & IPS_NAT_MASK) { /* Answering ARQ */ - return set_h225_addr(skb, data, 0, + return set_h225_addr(skb, protoff, data, 0, &arq->destCallSignalAddress, &ct->tuplehash[!dir].tuple.dst.u3, info->sig_port[!dir]); @@ -1503,9 +1557,10 @@ static int process_arq(struct sk_buff *skb, struct nf_conn *ct, get_h225_addr(ct, *data, &arq->srcCallSignalAddress, &addr, &port) && !memcmp(&addr, &ct->tuplehash[dir].tuple.src.u3, sizeof(addr)) && - set_h225_addr && ct->status & IPS_NAT_MASK) { + set_h225_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && + ct->status & IPS_NAT_MASK) { /* Calling ARQ */ - return set_h225_addr(skb, data, 0, + return set_h225_addr(skb, protoff, data, 0, &arq->srcCallSignalAddress, &ct->tuplehash[!dir].tuple.dst.u3, port); @@ -1517,6 +1572,7 @@ static int process_arq(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, AdmissionConfirm *acf) { int dir = CTINFO2DIR(ctinfo); @@ -1535,8 +1591,9 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, if (!memcmp(&addr, &ct->tuplehash[dir].tuple.dst.u3, sizeof(addr))) { /* Answering ACF */ set_sig_addr = rcu_dereference(set_sig_addr_hook); - if (set_sig_addr && ct->status & IPS_NAT_MASK) - return set_sig_addr(skb, ct, ctinfo, data, + if (set_sig_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && + ct->status & IPS_NAT_MASK) + return set_sig_addr(skb, ct, ctinfo, protoff, data, &acf->destCallSignalAddress, 1); return 0; } @@ -1564,6 +1621,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_lrq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, LocationRequest *lrq) { typeof(set_ras_addr_hook) set_ras_addr; @@ -1571,8 +1629,9 @@ static int process_lrq(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_ras: LRQ\n"); set_ras_addr = rcu_dereference(set_ras_addr_hook); - if (set_ras_addr && ct->status & IPS_NAT_MASK) - return set_ras_addr(skb, ct, ctinfo, data, + if (set_ras_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && + ct->status & IPS_NAT_MASK) + return set_ras_addr(skb, ct, ctinfo, protoff, data, &lrq->replyAddress, 1); return 0; } @@ -1580,6 +1639,7 @@ static int process_lrq(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, LocationConfirm *lcf) { int dir = CTINFO2DIR(ctinfo); @@ -1619,6 +1679,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_irr(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, InfoRequestResponse *irr) { int ret; @@ -1628,16 +1689,18 @@ static int process_irr(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_ras: IRR\n"); set_ras_addr = rcu_dereference(set_ras_addr_hook); - if (set_ras_addr && ct->status & IPS_NAT_MASK) { - ret = set_ras_addr(skb, ct, ctinfo, data, + if (set_ras_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && + ct->status & IPS_NAT_MASK) { + ret = set_ras_addr(skb, ct, ctinfo, protoff, data, &irr->rasAddress, 1); if (ret < 0) return -1; } set_sig_addr = rcu_dereference(set_sig_addr_hook); - if (set_sig_addr && ct->status & IPS_NAT_MASK) { - ret = set_sig_addr(skb, ct, ctinfo, data, + if (set_sig_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && + ct->status & IPS_NAT_MASK) { + ret = set_sig_addr(skb, ct, ctinfo, protoff, data, irr->callSignalAddress.item, irr->callSignalAddress.count); if (ret < 0) @@ -1650,38 +1713,39 @@ static int process_irr(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_ras(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, RasMessage *ras) { switch (ras->choice) { case eRasMessage_gatekeeperRequest: - return process_grq(skb, ct, ctinfo, data, + return process_grq(skb, ct, ctinfo, protoff, data, &ras->gatekeeperRequest); case eRasMessage_gatekeeperConfirm: - return process_gcf(skb, ct, ctinfo, data, + return process_gcf(skb, ct, ctinfo, protoff, data, &ras->gatekeeperConfirm); case eRasMessage_registrationRequest: - return process_rrq(skb, ct, ctinfo, data, + return process_rrq(skb, ct, ctinfo, protoff, data, &ras->registrationRequest); case eRasMessage_registrationConfirm: - return process_rcf(skb, ct, ctinfo, data, + return process_rcf(skb, ct, ctinfo, protoff, data, &ras->registrationConfirm); case eRasMessage_unregistrationRequest: - return process_urq(skb, ct, ctinfo, data, + return process_urq(skb, ct, ctinfo, protoff, data, &ras->unregistrationRequest); case eRasMessage_admissionRequest: - return process_arq(skb, ct, ctinfo, data, + return process_arq(skb, ct, ctinfo, protoff, data, &ras->admissionRequest); case eRasMessage_admissionConfirm: - return process_acf(skb, ct, ctinfo, data, + return process_acf(skb, ct, ctinfo, protoff, data, &ras->admissionConfirm); case eRasMessage_locationRequest: - return process_lrq(skb, ct, ctinfo, data, + return process_lrq(skb, ct, ctinfo, protoff, data, &ras->locationRequest); case eRasMessage_locationConfirm: - return process_lcf(skb, ct, ctinfo, data, + return process_lcf(skb, ct, ctinfo, protoff, data, &ras->locationConfirm); case eRasMessage_infoRequestResponse: - return process_irr(skb, ct, ctinfo, data, + return process_irr(skb, ct, ctinfo, protoff, data, &ras->infoRequestResponse); default: pr_debug("nf_ct_ras: RAS message %d\n", ras->choice); @@ -1721,7 +1785,7 @@ static int ras_help(struct sk_buff *skb, unsigned int protoff, } /* Process RAS message */ - if (process_ras(skb, ct, ctinfo, &data, &ras) < 0) + if (process_ras(skb, ct, ctinfo, protoff, &data, &ras) < 0) goto drop; accept: diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 009c52cfd1e..3b20aa77cfc 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -33,6 +33,7 @@ static DEFINE_SPINLOCK(irc_buffer_lock); unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp) __read_mostly; @@ -205,7 +206,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, nf_nat_irc = rcu_dereference(nf_nat_irc_hook); if (nf_nat_irc && ct->status & IPS_NAT_MASK) - ret = nf_nat_irc(skb, ctinfo, + ret = nf_nat_irc(skb, ctinfo, protoff, addr_beg_p - ib_ptr, addr_end_p - addr_beg_p, exp); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 9807f3278fc..7bbfb3deea3 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -45,7 +45,7 @@ #include <net/netfilter/nf_conntrack_timestamp.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_core.h> -#include <net/netfilter/nf_nat_protocol.h> +#include <net/netfilter/nf_nat_l4proto.h> #include <net/netfilter/nf_nat_helper.h> #endif @@ -418,16 +418,16 @@ nla_put_failure: } static int -ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, +ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct nf_conn *ct) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct nlattr *nest_parms; - unsigned int flags = pid ? NLM_F_MULTI : 0, event; + unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_NEW); - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -604,7 +604,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) goto errout; type |= NFNL_SUBSYS_CTNETLINK << 8; - nlh = nlmsg_put(skb, item->pid, 0, type, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -680,7 +680,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) rcu_read_unlock(); nlmsg_end(skb, nlh); - err = nfnetlink_send(skb, net, item->pid, group, item->report, + err = nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); if (err == -ENOBUFS || err == -EAGAIN) return -ENOBUFS; @@ -757,7 +757,7 @@ restart: #endif rcu_read_lock(); res = - ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, + ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct); @@ -961,7 +961,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, else { /* Flush the whole table */ nf_conntrack_flush_report(net, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, nlmsg_report(nlh)); return 0; } @@ -985,7 +985,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, if (del_timer(&ct->timeout)) { if (nf_conntrack_event_report(IPCT_DESTROY, ct, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, nlmsg_report(nlh)) < 0) { nf_ct_delete_from_lists(ct); /* we failed to report the event, try later */ @@ -1069,14 +1069,14 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, } rcu_read_lock(); - err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, + err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), ct); rcu_read_unlock(); nf_ct_put(ct); if (err <= 0) goto free; - err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (err < 0) goto out; @@ -1096,13 +1096,14 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, const struct nlattr *attr) { typeof(nfnetlink_parse_nat_setup_hook) parse_nat_setup; + int err; parse_nat_setup = rcu_dereference(nfnetlink_parse_nat_setup_hook); if (!parse_nat_setup) { #ifdef CONFIG_MODULES rcu_read_unlock(); nfnl_unlock(); - if (request_module("nf-nat-ipv4") < 0) { + if (request_module("nf-nat") < 0) { nfnl_lock(); rcu_read_lock(); return -EOPNOTSUPP; @@ -1115,7 +1116,23 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, return -EOPNOTSUPP; } - return parse_nat_setup(ct, manip, attr); + err = parse_nat_setup(ct, manip, attr); + if (err == -EAGAIN) { +#ifdef CONFIG_MODULES + rcu_read_unlock(); + nfnl_unlock(); + if (request_module("nf-nat-%u", nf_ct_l3num(ct)) < 0) { + nfnl_lock(); + rcu_read_lock(); + return -EOPNOTSUPP; + } + nfnl_lock(); + rcu_read_lock(); +#else + err = -EOPNOTSUPP; +#endif + } + return err; } #endif @@ -1221,7 +1238,7 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) if (help) { if (help->helper == helper) { /* update private helper data if allowed. */ - if (helper->from_nlattr && helpinfo) + if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); return 0; } else @@ -1450,7 +1467,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, goto err2; } /* set private helper data if allowed. */ - if (helper->from_nlattr && helpinfo) + if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); /* not in hash table yet so not strictly necessary */ @@ -1596,7 +1613,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, (1 << IPCT_PROTOINFO) | (1 << IPCT_NATSEQADJ) | (1 << IPCT_MARK) | events, - ct, NETLINK_CB(skb).pid, + ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_put(ct); } @@ -1618,7 +1635,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, (1 << IPCT_PROTOINFO) | (1 << IPCT_NATSEQADJ) | (1 << IPCT_MARK), - ct, NETLINK_CB(skb).pid, + ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); } } @@ -1628,15 +1645,15 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, } static int -ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 pid, u32 seq, +ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, __u16 cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0, event; + unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_GET_STATS_CPU); - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -1688,7 +1705,7 @@ ctnetlink_ct_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) st = per_cpu_ptr(net->ct.stat, cpu); if (ctnetlink_ct_stat_cpu_fill_info(skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cpu, st) < 0) break; @@ -1714,16 +1731,16 @@ ctnetlink_stat_ct_cpu(struct sock *ctnl, struct sk_buff *skb, } static int -ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, +ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct net *net) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0, event; + unsigned int flags = portid ? NLM_F_MULTI : 0, event; unsigned int nr_conntracks = atomic_read(&net->ct.count); event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_GET_STATS); - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -1756,14 +1773,14 @@ ctnetlink_stat_ct(struct sock *ctnl, struct sk_buff *skb, if (skb2 == NULL) return -ENOMEM; - err = ctnetlink_stat_ct_fill_info(skb2, NETLINK_CB(skb).pid, + err = ctnetlink_stat_ct_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), sock_net(skb->sk)); if (err <= 0) goto free; - err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (err < 0) goto out; @@ -1979,6 +1996,8 @@ nla_put_failure: return -1; } +static const union nf_inet_addr any_addr; + static int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) @@ -2005,7 +2024,8 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, goto nla_put_failure; #ifdef CONFIG_NF_NAT_NEEDED - if (exp->saved_ip || exp->saved_proto.all) { + if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) || + exp->saved_proto.all) { nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; @@ -2014,7 +2034,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, goto nla_put_failure; nat_tuple.src.l3num = nf_ct_l3num(master); - nat_tuple.src.u3.ip = exp->saved_ip; + nat_tuple.src.u3 = exp->saved_addr; nat_tuple.dst.protonum = nf_ct_protonum(master); nat_tuple.src.u = exp->saved_proto; @@ -2050,15 +2070,15 @@ nla_put_failure: } static int -ctnetlink_exp_fill_info(struct sk_buff *skb, u32 pid, u32 seq, +ctnetlink_exp_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int event, const struct nf_conntrack_expect *exp) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0; + unsigned int flags = portid ? NLM_F_MULTI : 0; event |= NFNL_SUBSYS_CTNETLINK_EXP << 8; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -2109,7 +2129,7 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) goto errout; type |= NFNL_SUBSYS_CTNETLINK_EXP << 8; - nlh = nlmsg_put(skb, item->pid, 0, type, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -2124,7 +2144,7 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) rcu_read_unlock(); nlmsg_end(skb, nlh); - nfnetlink_send(skb, net, item->pid, group, item->report, GFP_ATOMIC); + nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); return 0; nla_put_failure: @@ -2167,7 +2187,7 @@ restart: cb->args[1] = 0; } if (ctnetlink_exp_fill_info(skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { @@ -2260,14 +2280,14 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, } rcu_read_lock(); - err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).pid, + err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp); rcu_read_unlock(); nf_ct_expect_put(exp); if (err <= 0) goto free; - err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (err < 0) goto out; @@ -2321,7 +2341,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, /* after list removal, usage count == 1 */ spin_lock_bh(&nf_conntrack_lock); if (del_timer(&exp->timeout)) { - nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).pid, + nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_expect_put(exp); } @@ -2343,7 +2363,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, if (!strcmp(m_help->helper->name, name) && del_timer(&exp->timeout)) { nf_ct_unlink_expect_report(exp, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_expect_put(exp); } @@ -2359,7 +2379,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, hnode) { if (del_timer(&exp->timeout)) { nf_ct_unlink_expect_report(exp, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_expect_put(exp); } @@ -2410,7 +2430,7 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr, if (err < 0) return err; - exp->saved_ip = nat_tuple.src.u3.ip; + exp->saved_addr = nat_tuple.src.u3; exp->saved_proto = nat_tuple.src.u; exp->dir = ntohl(nla_get_be32(tb[CTA_EXPECT_NAT_DIR])); @@ -2424,7 +2444,7 @@ static int ctnetlink_create_expect(struct net *net, u16 zone, const struct nlattr * const cda[], u_int8_t u3, - u32 pid, int report) + u32 portid, int report) { struct nf_conntrack_tuple tuple, mask, master_tuple; struct nf_conntrack_tuple_hash *h = NULL; @@ -2537,7 +2557,7 @@ ctnetlink_create_expect(struct net *net, u16 zone, if (err < 0) goto err_out; } - err = nf_ct_expect_related_report(exp, pid, report); + err = nf_ct_expect_related_report(exp, portid, report); err_out: nf_ct_expect_put(exp); out: @@ -2580,7 +2600,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_CREATE) { err = ctnetlink_create_expect(net, zone, cda, u3, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, nlmsg_report(nlh)); } return err; @@ -2595,15 +2615,15 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, } static int -ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int cpu, +ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0, event; + unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_EXP_GET_STATS_CPU); - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -2642,7 +2662,7 @@ ctnetlink_exp_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; st = per_cpu_ptr(net->ct.stat, cpu); - if (ctnetlink_exp_stat_fill_info(skb, NETLINK_CB(cb->skb).pid, + if (ctnetlink_exp_stat_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cpu, st) < 0) break; diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 6fed9ec3524..cc7669ef0b9 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -45,14 +45,14 @@ static DEFINE_SPINLOCK(nf_pptp_lock); int (*nf_nat_pptp_hook_outbound)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - struct PptpControlHeader *ctlh, + unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_outbound); int (*nf_nat_pptp_hook_inbound)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - struct PptpControlHeader *ctlh, + unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_inbound); @@ -262,7 +262,7 @@ out_unexpect_orig: } static inline int -pptp_inbound_pkt(struct sk_buff *skb, +pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq, unsigned int reqlen, @@ -376,7 +376,8 @@ pptp_inbound_pkt(struct sk_buff *skb, nf_nat_pptp_inbound = rcu_dereference(nf_nat_pptp_hook_inbound); if (nf_nat_pptp_inbound && ct->status & IPS_NAT_MASK) - return nf_nat_pptp_inbound(skb, ct, ctinfo, ctlh, pptpReq); + return nf_nat_pptp_inbound(skb, ct, ctinfo, + protoff, ctlh, pptpReq); return NF_ACCEPT; invalid: @@ -389,7 +390,7 @@ invalid: } static inline int -pptp_outbound_pkt(struct sk_buff *skb, +pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq, unsigned int reqlen, @@ -471,7 +472,8 @@ pptp_outbound_pkt(struct sk_buff *skb, nf_nat_pptp_outbound = rcu_dereference(nf_nat_pptp_hook_outbound); if (nf_nat_pptp_outbound && ct->status & IPS_NAT_MASK) - return nf_nat_pptp_outbound(skb, ct, ctinfo, ctlh, pptpReq); + return nf_nat_pptp_outbound(skb, ct, ctinfo, + protoff, ctlh, pptpReq); return NF_ACCEPT; invalid: @@ -570,11 +572,11 @@ conntrack_pptp_help(struct sk_buff *skb, unsigned int protoff, * established from PNS->PAC. However, RFC makes no guarantee */ if (dir == IP_CT_DIR_ORIGINAL) /* client -> server (PNS -> PAC) */ - ret = pptp_outbound_pkt(skb, ctlh, pptpReq, reqlen, ct, + ret = pptp_outbound_pkt(skb, protoff, ctlh, pptpReq, reqlen, ct, ctinfo); else /* server -> client (PAC -> PNS) */ - ret = pptp_inbound_pkt(skb, ctlh, pptpReq, reqlen, ct, + ret = pptp_inbound_pkt(skb, protoff, ctlh, pptpReq, reqlen, ct, ctinfo); pr_debug("sstate: %d->%d, cstate: %d->%d\n", oldsstate, info->sstate, oldcstate, info->cstate); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 0dc63854390..51e928db48c 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -21,7 +21,6 @@ #include <linux/notifier.h> #include <linux/kernel.h> #include <linux/netdevice.h> -#include <linux/rtnetlink.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l3proto.h> @@ -294,9 +293,7 @@ void nf_conntrack_l3proto_unregister(struct net *net, nf_ct_l3proto_unregister_sysctl(net, proto); /* Remove all contrack entries for this protocol */ - rtnl_lock(); nf_ct_iterate_cleanup(net, kill_l3proto, proto); - rtnl_unlock(); } EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_unregister); @@ -502,9 +499,7 @@ void nf_conntrack_l4proto_unregister(struct net *net, nf_ct_l4proto_unregister_sysctl(net, pn, l4proto); /* Remove all contrack entries for this protocol */ - rtnl_lock(); nf_ct_iterate_cleanup(net, kill_l4proto, l4proto); - rtnl_unlock(); } EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_unregister); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index e046b3756aa..61f9285111d 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -502,10 +502,10 @@ static inline s16 nat_offset(const struct nf_conn *ct, 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) +#define NAT_OFFSET(ct, dir, seq) \ + (nat_offset(ct, dir, seq)) #else -#define NAT_OFFSET(pf, ct, dir, seq) 0 +#define NAT_OFFSET(ct, dir, seq) 0 #endif static bool tcp_in_window(const struct nf_conn *ct, @@ -538,7 +538,7 @@ static bool tcp_in_window(const struct nf_conn *ct, tcp_sack(skb, dataoff, tcph, &sack); /* Take into account NAT sequence number mangling */ - receiver_offset = NAT_OFFSET(pf, ct, !dir, ack - 1); + receiver_offset = NAT_OFFSET(ct, !dir, ack - 1); ack -= receiver_offset; sack -= receiver_offset; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 5c0a112aeee..df8f4f28448 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -52,15 +52,17 @@ module_param(sip_direct_media, int, 0600); MODULE_PARM_DESC(sip_direct_media, "Expect Media streams between signalling " "endpoints only (default 1)"); -unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, unsigned int dataoff, - const char **dptr, +unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sip_hook); -void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, s16 off) __read_mostly; +void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, unsigned int protoff, + s16 off) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sip_seq_adjust_hook); unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, @@ -69,7 +71,8 @@ unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, unsigned int matchlen) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sip_expect_hook); -unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, unsigned int dataoff, +unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int sdpoff, @@ -79,7 +82,8 @@ unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, unsigned int dataoff, __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sdp_addr_hook); -unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, unsigned int dataoff, +unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int matchoff, @@ -88,6 +92,7 @@ unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, unsigned int dataoff, EXPORT_SYMBOL_GPL(nf_nat_sdp_port_hook); unsigned int (*nf_nat_sdp_session_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, @@ -96,7 +101,8 @@ unsigned int (*nf_nat_sdp_session_hook)(struct sk_buff *skb, __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sdp_session_hook); -unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb, unsigned int dataoff, +unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, struct nf_conntrack_expect *rtp_exp, @@ -737,13 +743,18 @@ static int sdp_addr_len(const struct nf_conn *ct, const char *dptr, * be tolerant and also accept records terminated with a single newline * character". We handle both cases. */ -static const struct sip_header ct_sdp_hdrs[] = { - [SDP_HDR_VERSION] = SDP_HDR("v=", NULL, digits_len), - [SDP_HDR_OWNER_IP4] = SDP_HDR("o=", "IN IP4 ", sdp_addr_len), - [SDP_HDR_CONNECTION_IP4] = SDP_HDR("c=", "IN IP4 ", sdp_addr_len), - [SDP_HDR_OWNER_IP6] = SDP_HDR("o=", "IN IP6 ", sdp_addr_len), - [SDP_HDR_CONNECTION_IP6] = SDP_HDR("c=", "IN IP6 ", sdp_addr_len), - [SDP_HDR_MEDIA] = SDP_HDR("m=", NULL, media_len), +static const struct sip_header ct_sdp_hdrs_v4[] = { + [SDP_HDR_VERSION] = SDP_HDR("v=", NULL, digits_len), + [SDP_HDR_OWNER] = SDP_HDR("o=", "IN IP4 ", sdp_addr_len), + [SDP_HDR_CONNECTION] = SDP_HDR("c=", "IN IP4 ", sdp_addr_len), + [SDP_HDR_MEDIA] = SDP_HDR("m=", NULL, media_len), +}; + +static const struct sip_header ct_sdp_hdrs_v6[] = { + [SDP_HDR_VERSION] = SDP_HDR("v=", NULL, digits_len), + [SDP_HDR_OWNER] = SDP_HDR("o=", "IN IP6 ", sdp_addr_len), + [SDP_HDR_CONNECTION] = SDP_HDR("c=", "IN IP6 ", sdp_addr_len), + [SDP_HDR_MEDIA] = SDP_HDR("m=", NULL, media_len), }; /* Linear string search within SDP header values */ @@ -769,11 +780,14 @@ int ct_sip_get_sdp_header(const struct nf_conn *ct, const char *dptr, enum sdp_header_types term, unsigned int *matchoff, unsigned int *matchlen) { - const struct sip_header *hdr = &ct_sdp_hdrs[type]; - const struct sip_header *thdr = &ct_sdp_hdrs[term]; + const struct sip_header *hdrs, *hdr, *thdr; const char *start = dptr, *limit = dptr + datalen; int shift = 0; + hdrs = nf_ct_l3num(ct) == NFPROTO_IPV4 ? ct_sdp_hdrs_v4 : ct_sdp_hdrs_v6; + hdr = &hdrs[type]; + thdr = &hdrs[term]; + for (dptr += dataoff; dptr < limit; dptr++) { /* Find beginning of line */ if (*dptr != '\r' && *dptr != '\n') @@ -883,7 +897,8 @@ static void flush_expectations(struct nf_conn *ct, bool media) spin_unlock_bh(&nf_conntrack_lock); } -static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int dataoff, +static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, union nf_inet_addr *daddr, __be16 port, enum sip_expectation_classes class, @@ -939,12 +954,12 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int dataoff, exp->class != class) break; #ifdef CONFIG_NF_NAT_NEEDED - if (exp->tuple.src.l3num == AF_INET && !direct_rtp && - (exp->saved_ip != exp->tuple.dst.u3.ip || + if (!direct_rtp && + (!nf_inet_addr_cmp(&exp->saved_addr, &exp->tuple.dst.u3) || exp->saved_proto.udp.port != exp->tuple.dst.u.udp.port) && ct->status & IPS_NAT_MASK) { - daddr->ip = exp->saved_ip; - tuple.dst.u3.ip = exp->saved_ip; + *daddr = exp->saved_addr; + tuple.dst.u3 = exp->saved_addr; tuple.dst.u.udp.port = exp->saved_proto.udp.port; direct_rtp = 1; } else @@ -960,7 +975,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int dataoff, if (direct_rtp) { nf_nat_sdp_port = rcu_dereference(nf_nat_sdp_port_hook); if (nf_nat_sdp_port && - !nf_nat_sdp_port(skb, dataoff, dptr, datalen, + !nf_nat_sdp_port(skb, protoff, dataoff, dptr, datalen, mediaoff, medialen, ntohs(rtp_port))) goto err1; } @@ -982,7 +997,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int dataoff, nf_nat_sdp_media = rcu_dereference(nf_nat_sdp_media_hook); if (nf_nat_sdp_media && ct->status & IPS_NAT_MASK && !direct_rtp) - ret = nf_nat_sdp_media(skb, dataoff, dptr, datalen, + ret = nf_nat_sdp_media(skb, protoff, dataoff, dptr, datalen, rtp_exp, rtcp_exp, mediaoff, medialen, daddr); else { @@ -1023,7 +1038,8 @@ static const struct sdp_media_type *sdp_media_type(const char *dptr, return NULL; } -static int process_sdp(struct sk_buff *skb, unsigned int dataoff, +static int process_sdp(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq) { @@ -1036,15 +1052,12 @@ static int process_sdp(struct sk_buff *skb, unsigned int dataoff, unsigned int i; union nf_inet_addr caddr, maddr, rtp_addr; unsigned int port; - enum sdp_header_types c_hdr; const struct sdp_media_type *t; int ret = NF_ACCEPT; typeof(nf_nat_sdp_addr_hook) nf_nat_sdp_addr; typeof(nf_nat_sdp_session_hook) nf_nat_sdp_session; nf_nat_sdp_addr = rcu_dereference(nf_nat_sdp_addr_hook); - c_hdr = nf_ct_l3num(ct) == AF_INET ? SDP_HDR_CONNECTION_IP4 : - SDP_HDR_CONNECTION_IP6; /* Find beginning of session description */ if (ct_sip_get_sdp_header(ct, *dptr, 0, *datalen, @@ -1058,7 +1071,7 @@ static int process_sdp(struct sk_buff *skb, unsigned int dataoff, * the end of the session description. */ caddr_len = 0; if (ct_sip_parse_sdp_addr(ct, *dptr, sdpoff, *datalen, - c_hdr, SDP_HDR_MEDIA, + SDP_HDR_CONNECTION, SDP_HDR_MEDIA, &matchoff, &matchlen, &caddr) > 0) caddr_len = matchlen; @@ -1088,7 +1101,7 @@ static int process_sdp(struct sk_buff *skb, unsigned int dataoff, /* The media description overrides the session description. */ maddr_len = 0; if (ct_sip_parse_sdp_addr(ct, *dptr, mediaoff, *datalen, - c_hdr, SDP_HDR_MEDIA, + SDP_HDR_CONNECTION, SDP_HDR_MEDIA, &matchoff, &matchlen, &maddr) > 0) { maddr_len = matchlen; memcpy(&rtp_addr, &maddr, sizeof(rtp_addr)); @@ -1097,7 +1110,8 @@ static int process_sdp(struct sk_buff *skb, unsigned int dataoff, else return NF_DROP; - ret = set_expected_rtp_rtcp(skb, dataoff, dptr, datalen, + ret = set_expected_rtp_rtcp(skb, protoff, dataoff, + dptr, datalen, &rtp_addr, htons(port), t->class, mediaoff, medialen); if (ret != NF_ACCEPT) @@ -1105,8 +1119,9 @@ static int process_sdp(struct sk_buff *skb, unsigned int dataoff, /* Update media connection address if present */ if (maddr_len && nf_nat_sdp_addr && ct->status & IPS_NAT_MASK) { - ret = nf_nat_sdp_addr(skb, dataoff, dptr, datalen, - mediaoff, c_hdr, SDP_HDR_MEDIA, + ret = nf_nat_sdp_addr(skb, protoff, dataoff, + dptr, datalen, mediaoff, + SDP_HDR_CONNECTION, SDP_HDR_MEDIA, &rtp_addr); if (ret != NF_ACCEPT) return ret; @@ -1117,12 +1132,13 @@ static int process_sdp(struct sk_buff *skb, unsigned int dataoff, /* Update session connection and owner addresses */ nf_nat_sdp_session = rcu_dereference(nf_nat_sdp_session_hook); if (nf_nat_sdp_session && ct->status & IPS_NAT_MASK) - ret = nf_nat_sdp_session(skb, dataoff, dptr, datalen, sdpoff, - &rtp_addr); + ret = nf_nat_sdp_session(skb, protoff, dataoff, + dptr, datalen, sdpoff, &rtp_addr); return ret; } -static int process_invite_response(struct sk_buff *skb, unsigned int dataoff, +static int process_invite_response(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code) { @@ -1132,13 +1148,14 @@ static int process_invite_response(struct sk_buff *skb, unsigned int dataoff, if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) - return process_sdp(skb, dataoff, dptr, datalen, cseq); + return process_sdp(skb, protoff, dataoff, dptr, datalen, cseq); else if (ct_sip_info->invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } -static int process_update_response(struct sk_buff *skb, unsigned int dataoff, +static int process_update_response(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code) { @@ -1148,13 +1165,14 @@ static int process_update_response(struct sk_buff *skb, unsigned int dataoff, if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) - return process_sdp(skb, dataoff, dptr, datalen, cseq); + return process_sdp(skb, protoff, dataoff, dptr, datalen, cseq); else if (ct_sip_info->invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } -static int process_prack_response(struct sk_buff *skb, unsigned int dataoff, +static int process_prack_response(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code) { @@ -1164,13 +1182,14 @@ static int process_prack_response(struct sk_buff *skb, unsigned int dataoff, if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) - return process_sdp(skb, dataoff, dptr, datalen, cseq); + return process_sdp(skb, protoff, dataoff, dptr, datalen, cseq); else if (ct_sip_info->invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } -static int process_invite_request(struct sk_buff *skb, unsigned int dataoff, +static int process_invite_request(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq) { @@ -1180,13 +1199,14 @@ static int process_invite_request(struct sk_buff *skb, unsigned int dataoff, unsigned int ret; flush_expectations(ct, true); - ret = process_sdp(skb, dataoff, dptr, datalen, cseq); + ret = process_sdp(skb, protoff, dataoff, dptr, datalen, cseq); if (ret == NF_ACCEPT) ct_sip_info->invite_cseq = cseq; return ret; } -static int process_bye_request(struct sk_buff *skb, unsigned int dataoff, +static int process_bye_request(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq) { @@ -1201,7 +1221,8 @@ static int process_bye_request(struct sk_buff *skb, unsigned int dataoff, * signalling connections. The expectation is marked inactive and is activated * when receiving a response indicating success from the registrar. */ -static int process_register_request(struct sk_buff *skb, unsigned int dataoff, +static int process_register_request(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq) { @@ -1276,8 +1297,8 @@ static int process_register_request(struct sk_buff *skb, unsigned int dataoff, nf_nat_sip_expect = rcu_dereference(nf_nat_sip_expect_hook); if (nf_nat_sip_expect && ct->status & IPS_NAT_MASK) - ret = nf_nat_sip_expect(skb, dataoff, dptr, datalen, exp, - matchoff, matchlen); + ret = nf_nat_sip_expect(skb, protoff, dataoff, dptr, datalen, + exp, matchoff, matchlen); else { if (nf_ct_expect_related(exp) != 0) ret = NF_DROP; @@ -1292,7 +1313,8 @@ store_cseq: return ret; } -static int process_register_response(struct sk_buff *skb, unsigned int dataoff, +static int process_register_response(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code) { @@ -1374,7 +1396,8 @@ static const struct sip_handler sip_handlers[] = { SIP_HANDLER("REGISTER", process_register_request, process_register_response), }; -static int process_sip_response(struct sk_buff *skb, unsigned int dataoff, +static int process_sip_response(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen) { enum ip_conntrack_info ctinfo; @@ -1405,13 +1428,14 @@ static int process_sip_response(struct sk_buff *skb, unsigned int dataoff, if (*datalen < matchend + handler->len || strnicmp(*dptr + matchend, handler->method, handler->len)) continue; - return handler->response(skb, dataoff, dptr, datalen, + return handler->response(skb, protoff, dataoff, dptr, datalen, cseq, code); } return NF_ACCEPT; } -static int process_sip_request(struct sk_buff *skb, unsigned int dataoff, +static int process_sip_request(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen) { enum ip_conntrack_info ctinfo; @@ -1436,26 +1460,28 @@ static int process_sip_request(struct sk_buff *skb, unsigned int dataoff, if (!cseq) return NF_DROP; - return handler->request(skb, dataoff, dptr, datalen, cseq); + return handler->request(skb, protoff, dataoff, dptr, datalen, + cseq); } return NF_ACCEPT; } static int process_sip_msg(struct sk_buff *skb, struct nf_conn *ct, - unsigned int dataoff, const char **dptr, - unsigned int *datalen) + unsigned int protoff, unsigned int dataoff, + const char **dptr, unsigned int *datalen) { typeof(nf_nat_sip_hook) nf_nat_sip; int ret; if (strnicmp(*dptr, "SIP/2.0 ", strlen("SIP/2.0 ")) != 0) - ret = process_sip_request(skb, dataoff, dptr, datalen); + ret = process_sip_request(skb, protoff, dataoff, dptr, datalen); else - ret = process_sip_response(skb, dataoff, dptr, datalen); + ret = process_sip_response(skb, protoff, dataoff, dptr, datalen); if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) { nf_nat_sip = rcu_dereference(nf_nat_sip_hook); - if (nf_nat_sip && !nf_nat_sip(skb, dataoff, dptr, datalen)) + if (nf_nat_sip && !nf_nat_sip(skb, protoff, dataoff, + dptr, datalen)) ret = NF_DROP; } @@ -1523,7 +1549,8 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, if (msglen > datalen) return NF_DROP; - ret = process_sip_msg(skb, ct, dataoff, &dptr, &msglen); + ret = process_sip_msg(skb, ct, protoff, dataoff, + &dptr, &msglen); if (ret != NF_ACCEPT) break; diff = msglen - origlen; @@ -1537,7 +1564,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) { nf_nat_sip_seq_adjust = rcu_dereference(nf_nat_sip_seq_adjust_hook); if (nf_nat_sip_seq_adjust) - nf_nat_sip_seq_adjust(skb, tdiff); + nf_nat_sip_seq_adjust(skb, protoff, tdiff); } return ret; @@ -1564,7 +1591,7 @@ static int sip_help_udp(struct sk_buff *skb, unsigned int protoff, if (datalen < strlen("SIP/2.0 200")) return NF_ACCEPT; - return process_sip_msg(skb, ct, dataoff, &dptr, &datalen); + return process_sip_msg(skb, ct, protoff, dataoff, &dptr, &datalen); } static struct nf_conntrack_helper sip[MAX_PORTS][4] __read_mostly; diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index 770f76432ad..3deec997be8 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -18,13 +18,13 @@ extern unsigned int nf_iterate(struct list_head *head, unsigned int hook, const struct net_device *indev, const struct net_device *outdev, - struct list_head **i, + struct nf_hook_ops **elemp, int (*okfn)(struct sk_buff *), int hook_thresh); /* nf_queue.c */ extern int nf_queue(struct sk_buff *skb, - struct list_head *elem, + struct nf_hook_ops *elem, u_int8_t pf, unsigned int hook, struct net_device *indev, struct net_device *outdev, diff --git a/net/netfilter/nf_nat_amanda.c b/net/netfilter/nf_nat_amanda.c new file mode 100644 index 00000000000..42d33788117 --- /dev/null +++ b/net/netfilter/nf_nat_amanda.c @@ -0,0 +1,85 @@ +/* Amanda extension for TCP NAT alteration. + * (C) 2002 by Brian J. Murrell <netfilter@interlinx.bc.ca> + * based on a copy of HW's ip_nat_irc.c as well as other modules + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/udp.h> + +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_expect.h> +#include <net/netfilter/nf_nat_helper.h> +#include <linux/netfilter/nf_conntrack_amanda.h> + +MODULE_AUTHOR("Brian J. Murrell <netfilter@interlinx.bc.ca>"); +MODULE_DESCRIPTION("Amanda NAT helper"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ip_nat_amanda"); + +static unsigned int help(struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned int matchoff, + unsigned int matchlen, + struct nf_conntrack_expect *exp) +{ + char buffer[sizeof("65535")]; + u_int16_t port; + unsigned int ret; + + /* Connection comes from client. */ + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; + exp->dir = IP_CT_DIR_ORIGINAL; + + /* When you see the packet, we need to NAT it the same as the + * this one (ie. same IP: it will be TCP and master is UDP). */ + exp->expectfn = nf_nat_follow_master; + + /* Try to get same port: if not, try to change it. */ + for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { + int res; + + exp->tuple.dst.u.tcp.port = htons(port); + res = nf_ct_expect_related(exp); + if (res == 0) + break; + else if (res != -EBUSY) { + port = 0; + break; + } + } + + if (port == 0) + return NF_DROP; + + sprintf(buffer, "%u", port); + ret = nf_nat_mangle_udp_packet(skb, exp->master, ctinfo, + protoff, matchoff, matchlen, + buffer, strlen(buffer)); + if (ret != NF_ACCEPT) + nf_ct_unexpect_related(exp); + return ret; +} + +static void __exit nf_nat_amanda_fini(void) +{ + RCU_INIT_POINTER(nf_nat_amanda_hook, NULL); + synchronize_rcu(); +} + +static int __init nf_nat_amanda_init(void) +{ + BUG_ON(nf_nat_amanda_hook != NULL); + RCU_INIT_POINTER(nf_nat_amanda_hook, help); + return 0; +} + +module_init(nf_nat_amanda_init); +module_exit(nf_nat_amanda_fini); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c new file mode 100644 index 00000000000..5f2f9109f46 --- /dev/null +++ b/net/netfilter/nf_nat_core.c @@ -0,0 +1,856 @@ +/* + * (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2011 Patrick McHardy <kaber@trash.net> + * + * 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/types.h> +#include <linux/timer.h> +#include <linux/skbuff.h> +#include <linux/gfp.h> +#include <net/xfrm.h> +#include <linux/jhash.h> +#include <linux/rtnetlink.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_helper.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_l3proto.h> +#include <net/netfilter/nf_conntrack_zones.h> +#include <linux/netfilter/nf_nat.h> + +static DEFINE_SPINLOCK(nf_nat_lock); + +static DEFINE_MUTEX(nf_nat_proto_mutex); +static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO] + __read_mostly; +static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO] + __read_mostly; + + +inline const struct nf_nat_l3proto * +__nf_nat_l3proto_find(u8 family) +{ + return rcu_dereference(nf_nat_l3protos[family]); +} + +inline const struct nf_nat_l4proto * +__nf_nat_l4proto_find(u8 family, u8 protonum) +{ + return rcu_dereference(nf_nat_l4protos[family][protonum]); +} +EXPORT_SYMBOL_GPL(__nf_nat_l4proto_find); + +#ifdef CONFIG_XFRM +static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl) +{ + const struct nf_nat_l3proto *l3proto; + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + enum ip_conntrack_dir dir; + unsigned long statusbit; + u8 family; + + ct = nf_ct_get(skb, &ctinfo); + if (ct == NULL) + return; + + family = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num; + rcu_read_lock(); + l3proto = __nf_nat_l3proto_find(family); + if (l3proto == NULL) + goto out; + + dir = CTINFO2DIR(ctinfo); + if (dir == IP_CT_DIR_ORIGINAL) + statusbit = IPS_DST_NAT; + else + statusbit = IPS_SRC_NAT; + + l3proto->decode_session(skb, ct, dir, statusbit, fl); +out: + rcu_read_unlock(); +} + +int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family) +{ + struct flowi fl; + unsigned int hh_len; + struct dst_entry *dst; + + if (xfrm_decode_session(skb, &fl, family) < 0) + return -1; + + dst = skb_dst(skb); + if (dst->xfrm) + dst = ((struct xfrm_dst *)dst)->route; + dst_hold(dst); + + dst = xfrm_lookup(dev_net(dst->dev), dst, &fl, skb->sk, 0); + if (IS_ERR(dst)) + return -1; + + skb_dst_drop(skb); + skb_dst_set(skb, dst); + + /* Change in oif may mean change in hh_len. */ + hh_len = skb_dst(skb)->dev->hard_header_len; + if (skb_headroom(skb) < hh_len && + pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) + return -1; + return 0; +} +EXPORT_SYMBOL(nf_xfrm_me_harder); +#endif /* CONFIG_XFRM */ + +/* We keep an extra hash for each conntrack, for fast searching. */ +static inline unsigned int +hash_by_src(const struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple) +{ + unsigned int hash; + + /* Original src, to ensure we map it consistently if poss. */ + hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32), + tuple->dst.protonum ^ zone ^ nf_conntrack_hash_rnd); + return ((u64)hash * net->ct.nat_htable_size) >> 32; +} + +/* Is this tuple already taken? (not by us) */ +int +nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, + const struct nf_conn *ignored_conntrack) +{ + /* Conntrack tracking doesn't keep track of outgoing tuples; only + * incoming ones. NAT means they don't have a fixed mapping, + * so we invert the tuple and look for the incoming reply. + * + * We could keep a separate hash if this proves too slow. + */ + struct nf_conntrack_tuple reply; + + nf_ct_invert_tuplepr(&reply, tuple); + return nf_conntrack_tuple_taken(&reply, ignored_conntrack); +} +EXPORT_SYMBOL(nf_nat_used_tuple); + +/* If we source map this tuple so reply looks like reply_tuple, will + * that meet the constraints of range. + */ +static int in_range(const struct nf_nat_l3proto *l3proto, + const struct nf_nat_l4proto *l4proto, + const struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range) +{ + /* If we are supposed to map IPs, then we must be in the + * range specified, otherwise let this drag us onto a new src IP. + */ + if (range->flags & NF_NAT_RANGE_MAP_IPS && + !l3proto->in_range(tuple, range)) + return 0; + + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) || + l4proto->in_range(tuple, NF_NAT_MANIP_SRC, + &range->min_proto, &range->max_proto)) + return 1; + + return 0; +} + +static inline int +same_src(const struct nf_conn *ct, + const struct nf_conntrack_tuple *tuple) +{ + const struct nf_conntrack_tuple *t; + + t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + return (t->dst.protonum == tuple->dst.protonum && + nf_inet_addr_cmp(&t->src.u3, &tuple->src.u3) && + t->src.u.all == tuple->src.u.all); +} + +/* Only called for SRC manip */ +static int +find_appropriate_src(struct net *net, u16 zone, + const struct nf_nat_l3proto *l3proto, + const struct nf_nat_l4proto *l4proto, + const struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple *result, + const struct nf_nat_range *range) +{ + unsigned int h = hash_by_src(net, zone, tuple); + const struct nf_conn_nat *nat; + const struct nf_conn *ct; + const struct hlist_node *n; + + hlist_for_each_entry_rcu(nat, n, &net->ct.nat_bysource[h], bysource) { + ct = nat->ct; + if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) { + /* Copy source part from reply tuple. */ + nf_ct_invert_tuplepr(result, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + result->dst = tuple->dst; + + if (in_range(l3proto, l4proto, result, range)) + return 1; + } + } + return 0; +} + +/* For [FUTURE] fragmentation handling, we want the least-used + * src-ip/dst-ip/proto triple. Fairness doesn't come into it. Thus + * if the range specifies 1.2.3.4 ports 10000-10005 and 1.2.3.5 ports + * 1-65535, we don't do pro-rata allocation based on ports; we choose + * the ip with the lowest src-ip/dst-ip/proto usage. + */ +static void +find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + const struct nf_conn *ct, + enum nf_nat_manip_type maniptype) +{ + union nf_inet_addr *var_ipp; + unsigned int i, max; + /* Host order */ + u32 minip, maxip, j, dist; + bool full_range; + + /* No IP mapping? Do nothing. */ + if (!(range->flags & NF_NAT_RANGE_MAP_IPS)) + return; + + if (maniptype == NF_NAT_MANIP_SRC) + var_ipp = &tuple->src.u3; + else + var_ipp = &tuple->dst.u3; + + /* Fast path: only one choice. */ + if (nf_inet_addr_cmp(&range->min_addr, &range->max_addr)) { + *var_ipp = range->min_addr; + return; + } + + if (nf_ct_l3num(ct) == NFPROTO_IPV4) + max = sizeof(var_ipp->ip) / sizeof(u32) - 1; + else + max = sizeof(var_ipp->ip6) / sizeof(u32) - 1; + + /* Hashing source and destination IPs gives a fairly even + * spread in practice (if there are a small number of IPs + * involved, there usually aren't that many connections + * anyway). The consistency means that servers see the same + * client coming from the same IP (some Internet Banking sites + * like this), even across reboots. + */ + j = jhash2((u32 *)&tuple->src.u3, sizeof(tuple->src.u3) / sizeof(u32), + range->flags & NF_NAT_RANGE_PERSISTENT ? + 0 : (__force u32)tuple->dst.u3.all[max] ^ zone); + + full_range = false; + for (i = 0; i <= max; i++) { + /* If first bytes of the address are at the maximum, use the + * distance. Otherwise use the full range. + */ + if (!full_range) { + minip = ntohl((__force __be32)range->min_addr.all[i]); + maxip = ntohl((__force __be32)range->max_addr.all[i]); + dist = maxip - minip + 1; + } else { + minip = 0; + dist = ~0; + } + + var_ipp->all[i] = (__force __u32) + htonl(minip + (((u64)j * dist) >> 32)); + if (var_ipp->all[i] != range->max_addr.all[i]) + full_range = true; + + if (!(range->flags & NF_NAT_RANGE_PERSISTENT)) + j ^= (__force u32)tuple->dst.u3.all[i]; + } +} + +/* Manipulate the tuple into the range given. For NF_INET_POST_ROUTING, + * we change the source to map into the range. For NF_INET_PRE_ROUTING + * and NF_INET_LOCAL_OUT, we change the destination to map into the + * range. It might not be possible to get a unique tuple, but we try. + * At worst (or if we race), we will end up with a final duplicate in + * __ip_conntrack_confirm and drop the packet. */ +static void +get_unique_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig_tuple, + const struct nf_nat_range *range, + struct nf_conn *ct, + enum nf_nat_manip_type maniptype) +{ + const struct nf_nat_l3proto *l3proto; + const struct nf_nat_l4proto *l4proto; + struct net *net = nf_ct_net(ct); + u16 zone = nf_ct_zone(ct); + + rcu_read_lock(); + l3proto = __nf_nat_l3proto_find(orig_tuple->src.l3num); + l4proto = __nf_nat_l4proto_find(orig_tuple->src.l3num, + orig_tuple->dst.protonum); + + /* 1) If this srcip/proto/src-proto-part is currently mapped, + * and that same mapping gives a unique tuple within the given + * range, use that. + * + * This is only required for source (ie. NAT/masq) mappings. + * So far, we don't do local source mappings, so multiple + * manips not an issue. + */ + if (maniptype == NF_NAT_MANIP_SRC && + !(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) { + /* try the original tuple first */ + if (in_range(l3proto, l4proto, orig_tuple, range)) { + if (!nf_nat_used_tuple(orig_tuple, ct)) { + *tuple = *orig_tuple; + goto out; + } + } else if (find_appropriate_src(net, zone, l3proto, l4proto, + orig_tuple, tuple, range)) { + pr_debug("get_unique_tuple: Found current src map\n"); + if (!nf_nat_used_tuple(tuple, ct)) + goto out; + } + } + + /* 2) Select the least-used IP/proto combination in the given range */ + *tuple = *orig_tuple; + find_best_ips_proto(zone, tuple, range, ct, maniptype); + + /* 3) The per-protocol part of the manip is made to map into + * the range to make a unique tuple. + */ + + /* Only bother mapping if it's not already in range and unique */ + if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) { + if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { + if (l4proto->in_range(tuple, maniptype, + &range->min_proto, + &range->max_proto) && + (range->min_proto.all == range->max_proto.all || + !nf_nat_used_tuple(tuple, ct))) + goto out; + } else if (!nf_nat_used_tuple(tuple, ct)) { + goto out; + } + } + + /* Last change: get protocol to try to obtain unique tuple. */ + l4proto->unique_tuple(l3proto, tuple, range, maniptype, ct); +out: + rcu_read_unlock(); +} + +unsigned int +nf_nat_setup_info(struct nf_conn *ct, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype) +{ + struct net *net = nf_ct_net(ct); + struct nf_conntrack_tuple curr_tuple, new_tuple; + struct nf_conn_nat *nat; + + /* nat helper or nfctnetlink also setup binding */ + nat = nfct_nat(ct); + if (!nat) { + nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); + if (nat == NULL) { + pr_debug("failed to add NAT extension\n"); + return NF_ACCEPT; + } + } + + NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC || + maniptype == NF_NAT_MANIP_DST); + BUG_ON(nf_nat_initialized(ct, maniptype)); + + /* What we've got will look like inverse of reply. Normally + * this is what is in the conntrack, except for prior + * manipulations (future optimization: if num_manips == 0, + * orig_tp = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple) + */ + nf_ct_invert_tuplepr(&curr_tuple, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + + get_unique_tuple(&new_tuple, &curr_tuple, range, ct, maniptype); + + if (!nf_ct_tuple_equal(&new_tuple, &curr_tuple)) { + struct nf_conntrack_tuple reply; + + /* Alter conntrack table so will recognize replies. */ + nf_ct_invert_tuplepr(&reply, &new_tuple); + nf_conntrack_alter_reply(ct, &reply); + + /* Non-atomic: we own this at the moment. */ + if (maniptype == NF_NAT_MANIP_SRC) + ct->status |= IPS_SRC_NAT; + else + ct->status |= IPS_DST_NAT; + } + + if (maniptype == NF_NAT_MANIP_SRC) { + unsigned int srchash; + + srchash = hash_by_src(net, nf_ct_zone(ct), + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + spin_lock_bh(&nf_nat_lock); + /* nf_conntrack_alter_reply might re-allocate extension aera */ + nat = nfct_nat(ct); + nat->ct = ct; + hlist_add_head_rcu(&nat->bysource, + &net->ct.nat_bysource[srchash]); + spin_unlock_bh(&nf_nat_lock); + } + + /* It's done. */ + if (maniptype == NF_NAT_MANIP_DST) + ct->status |= IPS_DST_NAT_DONE; + else + ct->status |= IPS_SRC_NAT_DONE; + + return NF_ACCEPT; +} +EXPORT_SYMBOL(nf_nat_setup_info); + +/* Do packet manipulations according to nf_nat_setup_info. */ +unsigned int nf_nat_packet(struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int hooknum, + struct sk_buff *skb) +{ + const struct nf_nat_l3proto *l3proto; + const struct nf_nat_l4proto *l4proto; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + unsigned long statusbit; + enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum); + + if (mtype == NF_NAT_MANIP_SRC) + statusbit = IPS_SRC_NAT; + else + statusbit = IPS_DST_NAT; + + /* Invert if this is reply dir. */ + if (dir == IP_CT_DIR_REPLY) + statusbit ^= IPS_NAT_MASK; + + /* Non-atomic: these bits don't change. */ + if (ct->status & statusbit) { + struct nf_conntrack_tuple target; + + /* We are aiming to look like inverse of other direction. */ + nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + + l3proto = __nf_nat_l3proto_find(target.src.l3num); + l4proto = __nf_nat_l4proto_find(target.src.l3num, + target.dst.protonum); + if (!l3proto->manip_pkt(skb, 0, l4proto, &target, mtype)) + return NF_DROP; + } + return NF_ACCEPT; +} +EXPORT_SYMBOL_GPL(nf_nat_packet); + +struct nf_nat_proto_clean { + u8 l3proto; + u8 l4proto; + bool hash; +}; + +/* Clear NAT section of all conntracks, in case we're loaded again. */ +static int nf_nat_proto_clean(struct nf_conn *i, void *data) +{ + const struct nf_nat_proto_clean *clean = data; + struct nf_conn_nat *nat = nfct_nat(i); + + if (!nat) + return 0; + if (!(i->status & IPS_SRC_NAT_DONE)) + return 0; + if ((clean->l3proto && nf_ct_l3num(i) != clean->l3proto) || + (clean->l4proto && nf_ct_protonum(i) != clean->l4proto)) + return 0; + + if (clean->hash) { + spin_lock_bh(&nf_nat_lock); + hlist_del_rcu(&nat->bysource); + spin_unlock_bh(&nf_nat_lock); + } else { + memset(nat, 0, sizeof(*nat)); + i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK | + IPS_SEQ_ADJUST); + } + return 0; +} + +static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) +{ + struct nf_nat_proto_clean clean = { + .l3proto = l3proto, + .l4proto = l4proto, + }; + struct net *net; + + rtnl_lock(); + /* Step 1 - remove from bysource hash */ + clean.hash = true; + for_each_net(net) + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + synchronize_rcu(); + + /* Step 2 - clean NAT section */ + clean.hash = false; + for_each_net(net) + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + rtnl_unlock(); +} + +static void nf_nat_l3proto_clean(u8 l3proto) +{ + struct nf_nat_proto_clean clean = { + .l3proto = l3proto, + }; + struct net *net; + + rtnl_lock(); + /* Step 1 - remove from bysource hash */ + clean.hash = true; + for_each_net(net) + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + synchronize_rcu(); + + /* Step 2 - clean NAT section */ + clean.hash = false; + for_each_net(net) + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + rtnl_unlock(); +} + +/* Protocol registration. */ +int nf_nat_l4proto_register(u8 l3proto, const struct nf_nat_l4proto *l4proto) +{ + const struct nf_nat_l4proto **l4protos; + unsigned int i; + int ret = 0; + + mutex_lock(&nf_nat_proto_mutex); + if (nf_nat_l4protos[l3proto] == NULL) { + l4protos = kmalloc(IPPROTO_MAX * sizeof(struct nf_nat_l4proto *), + GFP_KERNEL); + if (l4protos == NULL) { + ret = -ENOMEM; + goto out; + } + + for (i = 0; i < IPPROTO_MAX; i++) + RCU_INIT_POINTER(l4protos[i], &nf_nat_l4proto_unknown); + + /* Before making proto_array visible to lockless readers, + * we must make sure its content is committed to memory. + */ + smp_wmb(); + + nf_nat_l4protos[l3proto] = l4protos; + } + + if (rcu_dereference_protected( + nf_nat_l4protos[l3proto][l4proto->l4proto], + lockdep_is_held(&nf_nat_proto_mutex) + ) != &nf_nat_l4proto_unknown) { + ret = -EBUSY; + goto out; + } + RCU_INIT_POINTER(nf_nat_l4protos[l3proto][l4proto->l4proto], l4proto); + out: + mutex_unlock(&nf_nat_proto_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_register); + +/* No one stores the protocol anywhere; simply delete it. */ +void nf_nat_l4proto_unregister(u8 l3proto, const struct nf_nat_l4proto *l4proto) +{ + mutex_lock(&nf_nat_proto_mutex); + RCU_INIT_POINTER(nf_nat_l4protos[l3proto][l4proto->l4proto], + &nf_nat_l4proto_unknown); + mutex_unlock(&nf_nat_proto_mutex); + synchronize_rcu(); + + nf_nat_l4proto_clean(l3proto, l4proto->l4proto); +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_unregister); + +int nf_nat_l3proto_register(const struct nf_nat_l3proto *l3proto) +{ + int err; + + err = nf_ct_l3proto_try_module_get(l3proto->l3proto); + if (err < 0) + return err; + + mutex_lock(&nf_nat_proto_mutex); + RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_TCP], + &nf_nat_l4proto_tcp); + RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_UDP], + &nf_nat_l4proto_udp); + mutex_unlock(&nf_nat_proto_mutex); + + RCU_INIT_POINTER(nf_nat_l3protos[l3proto->l3proto], l3proto); + return 0; +} +EXPORT_SYMBOL_GPL(nf_nat_l3proto_register); + +void nf_nat_l3proto_unregister(const struct nf_nat_l3proto *l3proto) +{ + mutex_lock(&nf_nat_proto_mutex); + RCU_INIT_POINTER(nf_nat_l3protos[l3proto->l3proto], NULL); + mutex_unlock(&nf_nat_proto_mutex); + synchronize_rcu(); + + nf_nat_l3proto_clean(l3proto->l3proto); + nf_ct_l3proto_module_put(l3proto->l3proto); +} +EXPORT_SYMBOL_GPL(nf_nat_l3proto_unregister); + +/* No one using conntrack by the time this called. */ +static void nf_nat_cleanup_conntrack(struct nf_conn *ct) +{ + struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT); + + if (nat == NULL || nat->ct == NULL) + return; + + NF_CT_ASSERT(nat->ct->status & IPS_SRC_NAT_DONE); + + spin_lock_bh(&nf_nat_lock); + hlist_del_rcu(&nat->bysource); + spin_unlock_bh(&nf_nat_lock); +} + +static void nf_nat_move_storage(void *new, void *old) +{ + struct nf_conn_nat *new_nat = new; + struct nf_conn_nat *old_nat = old; + struct nf_conn *ct = old_nat->ct; + + if (!ct || !(ct->status & IPS_SRC_NAT_DONE)) + return; + + spin_lock_bh(&nf_nat_lock); + hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); + spin_unlock_bh(&nf_nat_lock); +} + +static struct nf_ct_ext_type nat_extend __read_mostly = { + .len = sizeof(struct nf_conn_nat), + .align = __alignof__(struct nf_conn_nat), + .destroy = nf_nat_cleanup_conntrack, + .move = nf_nat_move_storage, + .id = NF_CT_EXT_NAT, + .flags = NF_CT_EXT_F_PREALLOC, +}; + +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> + +static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = { + [CTA_PROTONAT_PORT_MIN] = { .type = NLA_U16 }, + [CTA_PROTONAT_PORT_MAX] = { .type = NLA_U16 }, +}; + +static int nfnetlink_parse_nat_proto(struct nlattr *attr, + const struct nf_conn *ct, + struct nf_nat_range *range) +{ + struct nlattr *tb[CTA_PROTONAT_MAX+1]; + const struct nf_nat_l4proto *l4proto; + int err; + + err = nla_parse_nested(tb, CTA_PROTONAT_MAX, attr, protonat_nla_policy); + if (err < 0) + return err; + + l4proto = __nf_nat_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); + if (l4proto->nlattr_to_range) + err = l4proto->nlattr_to_range(tb, range); + + return err; +} + +static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { + [CTA_NAT_V4_MINIP] = { .type = NLA_U32 }, + [CTA_NAT_V4_MAXIP] = { .type = NLA_U32 }, + [CTA_NAT_V6_MINIP] = { .len = sizeof(struct in6_addr) }, + [CTA_NAT_V6_MAXIP] = { .len = sizeof(struct in6_addr) }, + [CTA_NAT_PROTO] = { .type = NLA_NESTED }, +}; + +static int +nfnetlink_parse_nat(const struct nlattr *nat, + const struct nf_conn *ct, struct nf_nat_range *range) +{ + const struct nf_nat_l3proto *l3proto; + struct nlattr *tb[CTA_NAT_MAX+1]; + int err; + + memset(range, 0, sizeof(*range)); + + err = nla_parse_nested(tb, CTA_NAT_MAX, nat, nat_nla_policy); + if (err < 0) + return err; + + rcu_read_lock(); + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + if (l3proto == NULL) { + err = -EAGAIN; + goto out; + } + err = l3proto->nlattr_to_range(tb, range); + if (err < 0) + goto out; + + if (!tb[CTA_NAT_PROTO]) + goto out; + + err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); +out: + rcu_read_unlock(); + return err; +} + +static int +nfnetlink_parse_nat_setup(struct nf_conn *ct, + enum nf_nat_manip_type manip, + const struct nlattr *attr) +{ + struct nf_nat_range range; + int err; + + err = nfnetlink_parse_nat(attr, ct, &range); + if (err < 0) + return err; + if (nf_nat_initialized(ct, manip)) + return -EEXIST; + + return nf_nat_setup_info(ct, &range, manip); +} +#else +static int +nfnetlink_parse_nat_setup(struct nf_conn *ct, + enum nf_nat_manip_type manip, + const struct nlattr *attr) +{ + return -EOPNOTSUPP; +} +#endif + +static int __net_init nf_nat_net_init(struct net *net) +{ + /* Leave them the same for the moment. */ + net->ct.nat_htable_size = net->ct.htable_size; + net->ct.nat_bysource = nf_ct_alloc_hashtable(&net->ct.nat_htable_size, 0); + if (!net->ct.nat_bysource) + return -ENOMEM; + return 0; +} + +static void __net_exit nf_nat_net_exit(struct net *net) +{ + struct nf_nat_proto_clean clean = {}; + + nf_ct_iterate_cleanup(net, &nf_nat_proto_clean, &clean); + synchronize_rcu(); + nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size); +} + +static struct pernet_operations nf_nat_net_ops = { + .init = nf_nat_net_init, + .exit = nf_nat_net_exit, +}; + +static struct nf_ct_helper_expectfn follow_master_nat = { + .name = "nat-follow-master", + .expectfn = nf_nat_follow_master, +}; + +static struct nfq_ct_nat_hook nfq_ct_nat = { + .seq_adjust = nf_nat_tcp_seq_adjust, +}; + +static int __init nf_nat_init(void) +{ + int ret; + + ret = nf_ct_extend_register(&nat_extend); + if (ret < 0) { + printk(KERN_ERR "nf_nat_core: Unable to register extension\n"); + return ret; + } + + ret = register_pernet_subsys(&nf_nat_net_ops); + if (ret < 0) + goto cleanup_extend; + + nf_ct_helper_expectfn_register(&follow_master_nat); + + /* Initialize fake conntrack so that NAT will skip it */ + nf_ct_untracked_status_or(IPS_NAT_DONE_MASK); + + BUG_ON(nf_nat_seq_adjust_hook != NULL); + RCU_INIT_POINTER(nf_nat_seq_adjust_hook, nf_nat_seq_adjust); + BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); + RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, + nfnetlink_parse_nat_setup); + BUG_ON(nf_ct_nat_offset != NULL); + RCU_INIT_POINTER(nf_ct_nat_offset, nf_nat_get_offset); + RCU_INIT_POINTER(nfq_ct_nat_hook, &nfq_ct_nat); +#ifdef CONFIG_XFRM + BUG_ON(nf_nat_decode_session_hook != NULL); + RCU_INIT_POINTER(nf_nat_decode_session_hook, __nf_nat_decode_session); +#endif + return 0; + + cleanup_extend: + nf_ct_extend_unregister(&nat_extend); + return ret; +} + +static void __exit nf_nat_cleanup(void) +{ + unsigned int i; + + unregister_pernet_subsys(&nf_nat_net_ops); + nf_ct_extend_unregister(&nat_extend); + nf_ct_helper_expectfn_unregister(&follow_master_nat); + RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL); + RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); + RCU_INIT_POINTER(nf_ct_nat_offset, NULL); + RCU_INIT_POINTER(nfq_ct_nat_hook, NULL); +#ifdef CONFIG_XFRM + RCU_INIT_POINTER(nf_nat_decode_session_hook, NULL); +#endif + for (i = 0; i < NFPROTO_NUMPROTO; i++) + kfree(nf_nat_l4protos[i]); + synchronize_net(); +} + +MODULE_LICENSE("GPL"); + +module_init(nf_nat_init); +module_exit(nf_nat_cleanup); diff --git a/net/netfilter/nf_nat_ftp.c b/net/netfilter/nf_nat_ftp.c new file mode 100644 index 00000000000..e839b97b286 --- /dev/null +++ b/net/netfilter/nf_nat_ftp.c @@ -0,0 +1,143 @@ +/* FTP extension for TCP NAT alteration. */ + +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * + * 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/moduleparam.h> +#include <linux/inet.h> +#include <linux/tcp.h> +#include <linux/netfilter_ipv4.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_helper.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_expect.h> +#include <linux/netfilter/nf_conntrack_ftp.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>"); +MODULE_DESCRIPTION("ftp NAT helper"); +MODULE_ALIAS("ip_nat_ftp"); + +/* FIXME: Time out? --RR */ + +static int nf_nat_ftp_fmt_cmd(struct nf_conn *ct, enum nf_ct_ftp_type type, + char *buffer, size_t buflen, + union nf_inet_addr *addr, u16 port) +{ + switch (type) { + case NF_CT_FTP_PORT: + case NF_CT_FTP_PASV: + return snprintf(buffer, buflen, "%u,%u,%u,%u,%u,%u", + ((unsigned char *)&addr->ip)[0], + ((unsigned char *)&addr->ip)[1], + ((unsigned char *)&addr->ip)[2], + ((unsigned char *)&addr->ip)[3], + port >> 8, + port & 0xFF); + case NF_CT_FTP_EPRT: + if (nf_ct_l3num(ct) == NFPROTO_IPV4) + return snprintf(buffer, buflen, "|1|%pI4|%u|", + &addr->ip, port); + else + return snprintf(buffer, buflen, "|2|%pI6|%u|", + &addr->ip6, port); + case NF_CT_FTP_EPSV: + return snprintf(buffer, buflen, "|||%u|", port); + } + + return 0; +} + +/* So, this packet has hit the connection tracking matching code. + Mangle it, and change the expectation to match the new version. */ +static unsigned int nf_nat_ftp(struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + enum nf_ct_ftp_type type, + unsigned int protoff, + unsigned int matchoff, + unsigned int matchlen, + struct nf_conntrack_expect *exp) +{ + union nf_inet_addr newaddr; + u_int16_t port; + int dir = CTINFO2DIR(ctinfo); + struct nf_conn *ct = exp->master; + char buffer[sizeof("|1||65535|") + INET6_ADDRSTRLEN]; + unsigned int buflen; + + pr_debug("FTP_NAT: type %i, off %u len %u\n", type, matchoff, matchlen); + + /* Connection will come from wherever this packet goes, hence !dir */ + newaddr = ct->tuplehash[!dir].tuple.dst.u3; + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; + exp->dir = !dir; + + /* When you see the packet, we need to NAT it the same as the + * this one. */ + exp->expectfn = nf_nat_follow_master; + + /* Try to get same port: if not, try to change it. */ + for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { + int ret; + + exp->tuple.dst.u.tcp.port = htons(port); + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; + break; + } + } + + if (port == 0) + return NF_DROP; + + buflen = nf_nat_ftp_fmt_cmd(ct, type, buffer, sizeof(buffer), + &newaddr, port); + if (!buflen) + goto out; + + pr_debug("calling nf_nat_mangle_tcp_packet\n"); + + if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff, + matchlen, buffer, buflen)) + goto out; + + return NF_ACCEPT; + +out: + nf_ct_unexpect_related(exp); + return NF_DROP; +} + +static void __exit nf_nat_ftp_fini(void) +{ + RCU_INIT_POINTER(nf_nat_ftp_hook, NULL); + synchronize_rcu(); +} + +static int __init nf_nat_ftp_init(void) +{ + BUG_ON(nf_nat_ftp_hook != NULL); + RCU_INIT_POINTER(nf_nat_ftp_hook, nf_nat_ftp); + return 0; +} + +/* Prior to 2.6.11, we had a ports param. No longer, but don't break users. */ +static int warn_set(const char *val, struct kernel_param *kp) +{ + printk(KERN_INFO KBUILD_MODNAME + ": kernel >= 2.6.10 only uses 'ports' for conntrack modules\n"); + return 0; +} +module_param_call(ports, warn_set, NULL, NULL, 0); + +module_init(nf_nat_ftp_init); +module_exit(nf_nat_ftp_fini); diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c new file mode 100644 index 00000000000..23c2b38676a --- /dev/null +++ b/net/netfilter/nf_nat_helper.c @@ -0,0 +1,435 @@ +/* nf_nat_helper.c - generic support functions for NAT helpers + * + * (C) 2000-2002 Harald Welte <laforge@netfilter.org> + * (C) 2003-2006 Netfilter Core Team <coreteam@netfilter.org> + * + * 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/gfp.h> +#include <linux/types.h> +#include <linux/skbuff.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <net/tcp.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_ecache.h> +#include <net/netfilter/nf_conntrack_expect.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_helper.h> + +#define DUMP_OFFSET(x) \ + pr_debug("offset_before=%d, offset_after=%d, correction_pos=%u\n", \ + x->offset_before, x->offset_after, x->correction_pos); + +static DEFINE_SPINLOCK(nf_nat_seqofs_lock); + +/* Setup TCP sequence correction given this change at this sequence */ +static inline void +adjust_tcp_sequence(u32 seq, + int sizediff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way = &nat->seq[dir]; + + pr_debug("adjust_tcp_sequence: seq = %u, sizediff = %d\n", + seq, sizediff); + + pr_debug("adjust_tcp_sequence: Seq_offset before: "); + DUMP_OFFSET(this_way); + + spin_lock_bh(&nf_nat_seqofs_lock); + + /* SYN adjust. If it's uninitialized, or this is after last + * correction, record it: we don't handle more than one + * adjustment in the window, but do deal with common case of a + * retransmit */ + if (this_way->offset_before == this_way->offset_after || + before(this_way->correction_pos, seq)) { + this_way->correction_pos = seq; + this_way->offset_before = this_way->offset_after; + this_way->offset_after += sizediff; + } + spin_unlock_bh(&nf_nat_seqofs_lock); + + pr_debug("adjust_tcp_sequence: Seq_offset after: "); + 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; +} + +/* Frobs data inside this packet, which is linear. */ +static void mangle_contents(struct sk_buff *skb, + unsigned int dataoff, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len) +{ + unsigned char *data; + + BUG_ON(skb_is_nonlinear(skb)); + data = skb_network_header(skb) + dataoff; + + /* move post-replacement */ + memmove(data + match_offset + rep_len, + data + match_offset + match_len, + skb->tail - (skb->network_header + dataoff + + match_offset + match_len)); + + /* insert data from buffer */ + memcpy(data + match_offset, rep_buffer, rep_len); + + /* update skb info */ + if (rep_len > match_len) { + pr_debug("nf_nat_mangle_packet: Extending packet by " + "%u from %u bytes\n", rep_len - match_len, skb->len); + skb_put(skb, rep_len - match_len); + } else { + pr_debug("nf_nat_mangle_packet: Shrinking packet from " + "%u from %u bytes\n", match_len - rep_len, skb->len); + __skb_trim(skb, skb->len + rep_len - match_len); + } + + if (nf_ct_l3num((struct nf_conn *)skb->nfct) == NFPROTO_IPV4) { + /* fix IP hdr checksum information */ + ip_hdr(skb)->tot_len = htons(skb->len); + ip_send_check(ip_hdr(skb)); + } else + ipv6_hdr(skb)->payload_len = + htons(skb->len - sizeof(struct ipv6hdr)); +} + +/* Unusual, but possible case. */ +static int enlarge_skb(struct sk_buff *skb, unsigned int extra) +{ + if (skb->len + extra > 65535) + return 0; + + if (pskb_expand_head(skb, 0, extra - skb_tailroom(skb), GFP_ATOMIC)) + return 0; + + return 1; +} + +void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, + __be32 seq, s16 off) +{ + if (!off) + return; + set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); + adjust_tcp_sequence(ntohl(seq), off, ct, ctinfo); + nf_conntrack_event_cache(IPCT_NATSEQADJ, ct); +} +EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust); + +void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, + u32 ctinfo, int off) +{ + const struct tcphdr *th; + + if (nf_ct_protonum(ct) != IPPROTO_TCP) + return; + + th = (struct tcphdr *)(skb_network_header(skb)+ ip_hdrlen(skb)); + nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off); +} +EXPORT_SYMBOL_GPL(nf_nat_tcp_seq_adjust); + +/* Generic function for mangling variable-length address changes inside + * NATed TCP connections (like the PORT XXX,XXX,XXX,XXX,XXX,XXX + * command in FTP). + * + * Takes care about all the nasty sequence number changes, checksumming, + * skb enlargement, ... + * + * */ +int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len, bool adjust) +{ + const struct nf_nat_l3proto *l3proto; + struct tcphdr *tcph; + int oldlen, datalen; + + if (!skb_make_writable(skb, skb->len)) + return 0; + + if (rep_len > match_len && + rep_len - match_len > skb_tailroom(skb) && + !enlarge_skb(skb, rep_len - match_len)) + return 0; + + SKB_LINEAR_ASSERT(skb); + + tcph = (void *)skb->data + protoff; + + oldlen = skb->len - protoff; + mangle_contents(skb, protoff + tcph->doff*4, + match_offset, match_len, rep_buffer, rep_len); + + datalen = skb->len - protoff; + + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + l3proto->csum_recalc(skb, IPPROTO_TCP, tcph, &tcph->check, + datalen, oldlen); + + if (adjust && rep_len != match_len) + nf_nat_set_seq_adjust(ct, ctinfo, tcph->seq, + (int)rep_len - (int)match_len); + + return 1; +} +EXPORT_SYMBOL(__nf_nat_mangle_tcp_packet); + +/* Generic function for mangling variable-length address changes inside + * NATed UDP connections (like the CONNECT DATA XXXXX MESG XXXXX INDEX XXXXX + * command in the Amanda protocol) + * + * Takes care about all the nasty sequence number changes, checksumming, + * skb enlargement, ... + * + * XXX - This function could be merged with nf_nat_mangle_tcp_packet which + * should be fairly easy to do. + */ +int +nf_nat_mangle_udp_packet(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len) +{ + const struct nf_nat_l3proto *l3proto; + struct udphdr *udph; + int datalen, oldlen; + + if (!skb_make_writable(skb, skb->len)) + return 0; + + if (rep_len > match_len && + rep_len - match_len > skb_tailroom(skb) && + !enlarge_skb(skb, rep_len - match_len)) + return 0; + + udph = (void *)skb->data + protoff; + + oldlen = skb->len - protoff; + mangle_contents(skb, protoff + sizeof(*udph), + match_offset, match_len, rep_buffer, rep_len); + + /* update the length of the UDP packet */ + datalen = skb->len - protoff; + udph->len = htons(datalen); + + /* fix udp checksum if udp checksum was previously calculated */ + if (!udph->check && skb->ip_summed != CHECKSUM_PARTIAL) + return 1; + + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + l3proto->csum_recalc(skb, IPPROTO_UDP, udph, &udph->check, + datalen, oldlen); + + return 1; +} +EXPORT_SYMBOL(nf_nat_mangle_udp_packet); + +/* Adjust one found SACK option including checksum correction */ +static void +sack_adjust(struct sk_buff *skb, + struct tcphdr *tcph, + unsigned int sackoff, + unsigned int sackend, + struct nf_nat_seq *natseq) +{ + while (sackoff < sackend) { + struct tcp_sack_block_wire *sack; + __be32 new_start_seq, new_end_seq; + + sack = (void *)skb->data + sackoff; + if (after(ntohl(sack->start_seq) - natseq->offset_before, + natseq->correction_pos)) + new_start_seq = htonl(ntohl(sack->start_seq) + - natseq->offset_after); + else + new_start_seq = htonl(ntohl(sack->start_seq) + - natseq->offset_before); + + if (after(ntohl(sack->end_seq) - natseq->offset_before, + natseq->correction_pos)) + new_end_seq = htonl(ntohl(sack->end_seq) + - natseq->offset_after); + else + new_end_seq = htonl(ntohl(sack->end_seq) + - natseq->offset_before); + + pr_debug("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n", + ntohl(sack->start_seq), new_start_seq, + ntohl(sack->end_seq), new_end_seq); + + inet_proto_csum_replace4(&tcph->check, skb, + sack->start_seq, new_start_seq, 0); + inet_proto_csum_replace4(&tcph->check, skb, + sack->end_seq, new_end_seq, 0); + sack->start_seq = new_start_seq; + sack->end_seq = new_end_seq; + sackoff += sizeof(*sack); + } +} + +/* TCP SACK sequence number adjustment */ +static inline unsigned int +nf_nat_sack_adjust(struct sk_buff *skb, + unsigned int protoff, + struct tcphdr *tcph, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + unsigned int dir, optoff, optend; + struct nf_conn_nat *nat = nfct_nat(ct); + + optoff = protoff + sizeof(struct tcphdr); + optend = protoff + tcph->doff * 4; + + if (!skb_make_writable(skb, optend)) + return 0; + + dir = CTINFO2DIR(ctinfo); + + while (optoff < optend) { + /* Usually: option, length. */ + unsigned char *op = skb->data + optoff; + + switch (op[0]) { + case TCPOPT_EOL: + return 1; + case TCPOPT_NOP: + optoff++; + continue; + default: + /* no partial options */ + if (optoff + 1 == optend || + optoff + op[1] > optend || + op[1] < 2) + return 0; + if (op[0] == TCPOPT_SACK && + op[1] >= 2+TCPOLEN_SACK_PERBLOCK && + ((op[1] - 2) % TCPOLEN_SACK_PERBLOCK) == 0) + sack_adjust(skb, tcph, optoff+2, + optoff+op[1], &nat->seq[!dir]); + optoff += op[1]; + } + } + return 1; +} + +/* TCP sequence number adjustment. Returns 1 on success, 0 on failure */ +int +nf_nat_seq_adjust(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff) +{ + struct tcphdr *tcph; + int dir; + __be32 newseq, newack; + s16 seqoff, ackoff; + struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way, *other_way; + + dir = CTINFO2DIR(ctinfo); + + this_way = &nat->seq[dir]; + other_way = &nat->seq[!dir]; + + if (!skb_make_writable(skb, protoff + sizeof(*tcph))) + return 0; + + tcph = (void *)skb->data + protoff; + if (after(ntohl(tcph->seq), this_way->correction_pos)) + seqoff = this_way->offset_after; + else + seqoff = this_way->offset_before; + + if (after(ntohl(tcph->ack_seq) - other_way->offset_before, + other_way->correction_pos)) + ackoff = other_way->offset_after; + else + ackoff = other_way->offset_before; + + newseq = htonl(ntohl(tcph->seq) + seqoff); + newack = htonl(ntohl(tcph->ack_seq) - ackoff); + + inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0); + inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0); + + pr_debug("Adjusting sequence number from %u->%u, ack from %u->%u\n", + ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq), + ntohl(newack)); + + tcph->seq = newseq; + tcph->ack_seq = newack; + + return nf_nat_sack_adjust(skb, protoff, tcph, ct, ctinfo); +} + +/* Setup NAT on this expected conntrack so it follows master. */ +/* If we fail to get a free NAT slot, we'll get dropped on confirm */ +void nf_nat_follow_master(struct nf_conn *ct, + struct nf_conntrack_expect *exp) +{ + struct nf_nat_range range; + + /* This must be a fresh one. */ + BUG_ON(ct->status & IPS_NAT_DONE_MASK); + + /* Change src to where master sends to */ + range.flags = NF_NAT_RANGE_MAP_IPS; + range.min_addr = range.max_addr + = ct->master->tuplehash[!exp->dir].tuple.dst.u3; + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); + + /* For DST manip, map port here to where it's expected. */ + range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); + range.min_proto = range.max_proto = exp->saved_proto; + range.min_addr = range.max_addr + = ct->master->tuplehash[!exp->dir].tuple.src.u3; + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); +} +EXPORT_SYMBOL(nf_nat_follow_master); diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c new file mode 100644 index 00000000000..1fedee6e7fb --- /dev/null +++ b/net/netfilter/nf_nat_irc.c @@ -0,0 +1,93 @@ +/* IRC extension for TCP NAT alteration. + * + * (C) 2000-2001 by Harald Welte <laforge@gnumonks.org> + * (C) 2004 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation + * based on a copy of RR's ip_nat_ftp.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/tcp.h> +#include <linux/kernel.h> + +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_helper.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_expect.h> +#include <linux/netfilter/nf_conntrack_irc.h> + +MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>"); +MODULE_DESCRIPTION("IRC (DCC) NAT helper"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ip_nat_irc"); + +static unsigned int help(struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned int matchoff, + unsigned int matchlen, + struct nf_conntrack_expect *exp) +{ + char buffer[sizeof("4294967296 65635")]; + u_int16_t port; + unsigned int ret; + + /* Reply comes from server. */ + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; + exp->dir = IP_CT_DIR_REPLY; + exp->expectfn = nf_nat_follow_master; + + /* Try to get same port: if not, try to change it. */ + for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { + int ret; + + exp->tuple.dst.u.tcp.port = htons(port); + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; + break; + } + } + + if (port == 0) + return NF_DROP; + + ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo, + protoff, matchoff, matchlen, buffer, + strlen(buffer)); + if (ret != NF_ACCEPT) + nf_ct_unexpect_related(exp); + return ret; +} + +static void __exit nf_nat_irc_fini(void) +{ + RCU_INIT_POINTER(nf_nat_irc_hook, NULL); + synchronize_rcu(); +} + +static int __init nf_nat_irc_init(void) +{ + BUG_ON(nf_nat_irc_hook != NULL); + RCU_INIT_POINTER(nf_nat_irc_hook, help); + return 0; +} + +/* Prior to 2.6.11, we had a ports param. No longer, but don't break users. */ +static int warn_set(const char *val, struct kernel_param *kp) +{ + printk(KERN_INFO KBUILD_MODNAME + ": kernel >= 2.6.10 only uses 'ports' for conntrack modules\n"); + return 0; +} +module_param_call(ports, warn_set, NULL, NULL, 0); + +module_init(nf_nat_irc_init); +module_exit(nf_nat_irc_fini); diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c new file mode 100644 index 00000000000..9baaf734c14 --- /dev/null +++ b/net/netfilter/nf_nat_proto_common.c @@ -0,0 +1,112 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2008 Patrick McHardy <kaber@trash.net> + * + * 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/types.h> +#include <linux/random.h> +#include <linux/netfilter.h> +#include <linux/export.h> + +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> + +bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype, + const union nf_conntrack_man_proto *min, + const union nf_conntrack_man_proto *max) +{ + __be16 port; + + if (maniptype == NF_NAT_MANIP_SRC) + port = tuple->src.u.all; + else + port = tuple->dst.u.all; + + return ntohs(port) >= ntohs(min->all) && + ntohs(port) <= ntohs(max->all); +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_in_range); + +void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct, + u16 *rover) +{ + unsigned int range_size, min, i; + __be16 *portptr; + u_int16_t off; + + if (maniptype == NF_NAT_MANIP_SRC) + portptr = &tuple->src.u.all; + else + portptr = &tuple->dst.u.all; + + /* If no range specified... */ + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { + /* If it's dst rewrite, can't change port */ + if (maniptype == NF_NAT_MANIP_DST) + return; + + if (ntohs(*portptr) < 1024) { + /* Loose convention: >> 512 is credential passing */ + if (ntohs(*portptr) < 512) { + min = 1; + range_size = 511 - min + 1; + } else { + min = 600; + range_size = 1023 - min + 1; + } + } else { + min = 1024; + range_size = 65535 - 1024 + 1; + } + } else { + min = ntohs(range->min_proto.all); + range_size = ntohs(range->max_proto.all) - min + 1; + } + + if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) + off = l3proto->secure_port(tuple, maniptype == NF_NAT_MANIP_SRC + ? tuple->dst.u.all + : tuple->src.u.all); + else + off = *rover; + + for (i = 0; ; ++off) { + *portptr = htons(min + off % range_size); + if (++i != range_size && nf_nat_used_tuple(tuple, ct)) + continue; + if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) + *rover = off; + return; + } + return; +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple); + +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[], + struct nf_nat_range *range) +{ + if (tb[CTA_PROTONAT_PORT_MIN]) { + range->min_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]); + range->max_proto.all = range->min_proto.all; + range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; + } + if (tb[CTA_PROTONAT_PORT_MAX]) { + range->max_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MAX]); + range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; + } + return 0; +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_nlattr_to_range); +#endif diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c new file mode 100644 index 00000000000..c8be2cdac0b --- /dev/null +++ b/net/netfilter/nf_nat_proto_dccp.c @@ -0,0 +1,116 @@ +/* + * DCCP NAT protocol helper + * + * Copyright (c) 2005, 2006, 2008 Patrick McHardy <kaber@trash.net> + * + * 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/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/skbuff.h> +#include <linux/dccp.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> + +static u_int16_t dccp_port_rover; + +static void +dccp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &dccp_port_rover); +} + +static bool +dccp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct dccp_hdr *hdr; + __be16 *portptr, oldport, newport; + int hdrsize = 8; /* DCCP connection tracking guarantees this much */ + + if (skb->len >= hdroff + sizeof(struct dccp_hdr)) + hdrsize = sizeof(struct dccp_hdr); + + if (!skb_make_writable(skb, hdroff + hdrsize)) + return false; + + hdr = (struct dccp_hdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + newport = tuple->src.u.dccp.port; + portptr = &hdr->dccph_sport; + } else { + newport = tuple->dst.u.dccp.port; + portptr = &hdr->dccph_dport; + } + + oldport = *portptr; + *portptr = newport; + + if (hdrsize < sizeof(*hdr)) + return true; + + l3proto->csum_update(skb, iphdroff, &hdr->dccph_checksum, + tuple, maniptype); + inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport, + 0); + return true; +} + +static const struct nf_nat_l4proto nf_nat_l4proto_dccp = { + .l4proto = IPPROTO_DCCP, + .manip_pkt = dccp_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = dccp_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; + +static int __init nf_nat_proto_dccp_init(void) +{ + int err; + + err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_dccp); + if (err < 0) + goto err1; + err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_dccp); + if (err < 0) + goto err2; + return 0; + +err2: + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_dccp); +err1: + return err; +} + +static void __exit nf_nat_proto_dccp_fini(void) +{ + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_dccp); + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_dccp); + +} + +module_init(nf_nat_proto_dccp_init); +module_exit(nf_nat_proto_dccp_fini); + +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("DCCP NAT protocol helper"); +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c new file mode 100644 index 00000000000..e64faa5ca89 --- /dev/null +++ b/net/netfilter/nf_nat_proto_sctp.c @@ -0,0 +1,103 @@ +/* + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * + * 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/types.h> +#include <linux/init.h> +#include <linux/sctp.h> +#include <linux/module.h> +#include <net/sctp/checksum.h> + +#include <net/netfilter/nf_nat_l4proto.h> + +static u_int16_t nf_sctp_port_rover; + +static void +sctp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &nf_sctp_port_rover); +} + +static bool +sctp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct sk_buff *frag; + sctp_sctphdr_t *hdr; + __be32 crc32; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + + hdr = (struct sctphdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + /* Get rid of src port */ + hdr->source = tuple->src.u.sctp.port; + } else { + /* Get rid of dst port */ + hdr->dest = tuple->dst.u.sctp.port; + } + + crc32 = sctp_start_cksum((u8 *)hdr, skb_headlen(skb) - hdroff); + skb_walk_frags(skb, frag) + crc32 = sctp_update_cksum((u8 *)frag->data, skb_headlen(frag), + crc32); + crc32 = sctp_end_cksum(crc32); + hdr->checksum = crc32; + + return true; +} + +static const struct nf_nat_l4proto nf_nat_l4proto_sctp = { + .l4proto = IPPROTO_SCTP, + .manip_pkt = sctp_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = sctp_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; + +static int __init nf_nat_proto_sctp_init(void) +{ + int err; + + err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_sctp); + if (err < 0) + goto err1; + err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_sctp); + if (err < 0) + goto err2; + return 0; + +err2: + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_sctp); +err1: + return err; +} + +static void __exit nf_nat_proto_sctp_exit(void) +{ + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_sctp); + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_sctp); +} + +module_init(nf_nat_proto_sctp_init); +module_exit(nf_nat_proto_sctp_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SCTP NAT protocol helper"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c new file mode 100644 index 00000000000..83ec8a6e4c3 --- /dev/null +++ b/net/netfilter/nf_nat_proto_tcp.c @@ -0,0 +1,85 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * + * 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/types.h> +#include <linux/init.h> +#include <linux/export.h> +#include <linux/tcp.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/nfnetlink_conntrack.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> +#include <net/netfilter/nf_nat_core.h> + +static u16 tcp_port_rover; + +static void +tcp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &tcp_port_rover); +} + +static bool +tcp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct tcphdr *hdr; + __be16 *portptr, newport, oldport; + int hdrsize = 8; /* TCP connection tracking guarantees this much */ + + /* this could be a inner header returned in icmp packet; in such + cases we cannot update the checksum field since it is outside of + the 8 bytes of transport layer headers we are guaranteed */ + if (skb->len >= hdroff + sizeof(struct tcphdr)) + hdrsize = sizeof(struct tcphdr); + + if (!skb_make_writable(skb, hdroff + hdrsize)) + return false; + + hdr = (struct tcphdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + /* Get rid of src port */ + newport = tuple->src.u.tcp.port; + portptr = &hdr->source; + } else { + /* Get rid of dst port */ + newport = tuple->dst.u.tcp.port; + portptr = &hdr->dest; + } + + oldport = *portptr; + *portptr = newport; + + if (hdrsize < sizeof(*hdr)) + return true; + + l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); + inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, 0); + return true; +} + +const struct nf_nat_l4proto nf_nat_l4proto_tcp = { + .l4proto = IPPROTO_TCP, + .manip_pkt = tcp_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = tcp_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c new file mode 100644 index 00000000000..7df613fb34a --- /dev/null +++ b/net/netfilter/nf_nat_proto_udp.c @@ -0,0 +1,76 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * + * 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/types.h> +#include <linux/export.h> +#include <linux/init.h> +#include <linux/udp.h> + +#include <linux/netfilter.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> + +static u16 udp_port_rover; + +static void +udp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &udp_port_rover); +} + +static bool +udp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct udphdr *hdr; + __be16 *portptr, newport; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + hdr = (struct udphdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + /* Get rid of src port */ + newport = tuple->src.u.udp.port; + portptr = &hdr->source; + } else { + /* Get rid of dst port */ + newport = tuple->dst.u.udp.port; + portptr = &hdr->dest; + } + if (hdr->check || skb->ip_summed == CHECKSUM_PARTIAL) { + l3proto->csum_update(skb, iphdroff, &hdr->check, + tuple, maniptype); + inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, + 0); + if (!hdr->check) + hdr->check = CSUM_MANGLED_0; + } + *portptr = newport; + return true; +} + +const struct nf_nat_l4proto nf_nat_l4proto_udp = { + .l4proto = IPPROTO_UDP, + .manip_pkt = udp_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = udp_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; diff --git a/net/netfilter/nf_nat_proto_udplite.c b/net/netfilter/nf_nat_proto_udplite.c new file mode 100644 index 00000000000..776a0d1317b --- /dev/null +++ b/net/netfilter/nf_nat_proto_udplite.c @@ -0,0 +1,106 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2008 Patrick McHardy <kaber@trash.net> + * + * 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/types.h> +#include <linux/init.h> +#include <linux/udp.h> + +#include <linux/netfilter.h> +#include <linux/module.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> + +static u16 udplite_port_rover; + +static void +udplite_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &udplite_port_rover); +} + +static bool +udplite_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct udphdr *hdr; + __be16 *portptr, newport; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + + hdr = (struct udphdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + /* Get rid of source port */ + newport = tuple->src.u.udp.port; + portptr = &hdr->source; + } else { + /* Get rid of dst port */ + newport = tuple->dst.u.udp.port; + portptr = &hdr->dest; + } + + l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); + inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, 0); + if (!hdr->check) + hdr->check = CSUM_MANGLED_0; + + *portptr = newport; + return true; +} + +static const struct nf_nat_l4proto nf_nat_l4proto_udplite = { + .l4proto = IPPROTO_UDPLITE, + .manip_pkt = udplite_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = udplite_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; + +static int __init nf_nat_proto_udplite_init(void) +{ + int err; + + err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_udplite); + if (err < 0) + goto err1; + err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_udplite); + if (err < 0) + goto err2; + return 0; + +err2: + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_udplite); +err1: + return err; +} + +static void __exit nf_nat_proto_udplite_fini(void) +{ + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_udplite); + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_udplite); +} + +module_init(nf_nat_proto_udplite_init); +module_exit(nf_nat_proto_udplite_fini); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("UDP-Lite NAT protocol helper"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); diff --git a/net/netfilter/nf_nat_proto_unknown.c b/net/netfilter/nf_nat_proto_unknown.c new file mode 100644 index 00000000000..6e494d58441 --- /dev/null +++ b/net/netfilter/nf_nat_proto_unknown.c @@ -0,0 +1,54 @@ +/* The "unknown" protocol. This is what is used for protocols we + * don't understand. It's returned by ip_ct_find_proto(). + */ + +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * + * 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/types.h> +#include <linux/init.h> + +#include <linux/netfilter.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_l4proto.h> + +static bool unknown_in_range(const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type manip_type, + const union nf_conntrack_man_proto *min, + const union nf_conntrack_man_proto *max) +{ + return true; +} + +static void unknown_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + /* Sorry: we can't help you; if it's not unique, we can't frob + * anything. + */ + return; +} + +static bool +unknown_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + return true; +} + +const struct nf_nat_l4proto nf_nat_l4proto_unknown = { + .manip_pkt = unknown_manip_pkt, + .in_range = unknown_in_range, + .unique_tuple = unknown_unique_tuple, +}; diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c new file mode 100644 index 00000000000..16303c75221 --- /dev/null +++ b/net/netfilter/nf_nat_sip.c @@ -0,0 +1,612 @@ +/* SIP extension for NAT alteration. + * + * (C) 2005 by Christian Hentschel <chentschel@arnet.com.ar> + * based on RR's ip_nat_ftp.c and other modules. + * (C) 2007 United Security Providers + * (C) 2007, 2008, 2011, 2012 Patrick McHardy <kaber@trash.net> + * + * 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/inet.h> +#include <linux/udp.h> +#include <linux/tcp.h> + +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_helper.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_expect.h> +#include <linux/netfilter/nf_conntrack_sip.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Christian Hentschel <chentschel@arnet.com.ar>"); +MODULE_DESCRIPTION("SIP NAT helper"); +MODULE_ALIAS("ip_nat_sip"); + + +static unsigned int mangle_packet(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int matchoff, unsigned int matchlen, + const char *buffer, unsigned int buflen) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + struct tcphdr *th; + unsigned int baseoff; + + if (nf_ct_protonum(ct) == IPPROTO_TCP) { + th = (struct tcphdr *)(skb->data + protoff); + baseoff = protoff + th->doff * 4; + matchoff += dataoff - baseoff; + + if (!__nf_nat_mangle_tcp_packet(skb, ct, ctinfo, + protoff, matchoff, matchlen, + buffer, buflen, false)) + return 0; + } else { + baseoff = protoff + sizeof(struct udphdr); + matchoff += dataoff - baseoff; + + if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo, + protoff, matchoff, matchlen, + buffer, buflen)) + return 0; + } + + /* Reload data pointer and adjust datalen value */ + *dptr = skb->data + dataoff; + *datalen += buflen - matchlen; + return 1; +} + +static int sip_sprintf_addr(const struct nf_conn *ct, char *buffer, + const union nf_inet_addr *addr, bool delim) +{ + if (nf_ct_l3num(ct) == NFPROTO_IPV4) + return sprintf(buffer, "%pI4", &addr->ip); + else { + if (delim) + return sprintf(buffer, "[%pI6c]", &addr->ip6); + else + return sprintf(buffer, "%pI6c", &addr->ip6); + } +} + +static int sip_sprintf_addr_port(const struct nf_conn *ct, char *buffer, + const union nf_inet_addr *addr, u16 port) +{ + if (nf_ct_l3num(ct) == NFPROTO_IPV4) + return sprintf(buffer, "%pI4:%u", &addr->ip, port); + else + return sprintf(buffer, "[%pI6c]:%u", &addr->ip6, port); +} + +static int map_addr(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int matchoff, unsigned int matchlen, + union nf_inet_addr *addr, __be16 port) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")]; + unsigned int buflen; + union nf_inet_addr newaddr; + __be16 newport; + + if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, addr) && + ct->tuplehash[dir].tuple.src.u.udp.port == port) { + newaddr = ct->tuplehash[!dir].tuple.dst.u3; + newport = ct->tuplehash[!dir].tuple.dst.u.udp.port; + } else if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, addr) && + ct->tuplehash[dir].tuple.dst.u.udp.port == port) { + newaddr = ct->tuplehash[!dir].tuple.src.u3; + newport = ct->tuplehash[!dir].tuple.src.u.udp.port; + } else + return 1; + + if (nf_inet_addr_cmp(&newaddr, addr) && newport == port) + return 1; + + buflen = sip_sprintf_addr_port(ct, buffer, &newaddr, ntohs(newport)); + return mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen); +} + +static int map_sip_addr(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + enum sip_header_types type) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + unsigned int matchlen, matchoff; + union nf_inet_addr addr; + __be16 port; + + if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, type, NULL, + &matchoff, &matchlen, &addr, &port) <= 0) + return 1; + return map_addr(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, &addr, port); +} + +static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + unsigned int coff, matchoff, matchlen; + enum sip_header_types hdr; + union nf_inet_addr addr; + __be16 port; + int request, in_header; + + /* Basic rules: requests and responses. */ + if (strnicmp(*dptr, "SIP/2.0", strlen("SIP/2.0")) != 0) { + if (ct_sip_parse_request(ct, *dptr, *datalen, + &matchoff, &matchlen, + &addr, &port) > 0 && + !map_addr(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, &addr, port)) + return NF_DROP; + request = 1; + } else + request = 0; + + if (nf_ct_protonum(ct) == IPPROTO_TCP) + hdr = SIP_HDR_VIA_TCP; + else + hdr = SIP_HDR_VIA_UDP; + + /* Translate topmost Via header and parameters */ + if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, + hdr, NULL, &matchoff, &matchlen, + &addr, &port) > 0) { + unsigned int olen, matchend, poff, plen, buflen, n; + char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")]; + + /* We're only interested in headers related to this + * connection */ + if (request) { + if (!nf_inet_addr_cmp(&addr, + &ct->tuplehash[dir].tuple.src.u3) || + port != ct->tuplehash[dir].tuple.src.u.udp.port) + goto next; + } else { + if (!nf_inet_addr_cmp(&addr, + &ct->tuplehash[dir].tuple.dst.u3) || + port != ct->tuplehash[dir].tuple.dst.u.udp.port) + goto next; + } + + olen = *datalen; + if (!map_addr(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, &addr, port)) + return NF_DROP; + + matchend = matchoff + matchlen + *datalen - olen; + + /* The maddr= parameter (RFC 2361) specifies where to send + * the reply. */ + if (ct_sip_parse_address_param(ct, *dptr, matchend, *datalen, + "maddr=", &poff, &plen, + &addr, true) > 0 && + nf_inet_addr_cmp(&addr, &ct->tuplehash[dir].tuple.src.u3) && + !nf_inet_addr_cmp(&addr, &ct->tuplehash[!dir].tuple.dst.u3)) { + buflen = sip_sprintf_addr(ct, buffer, + &ct->tuplehash[!dir].tuple.dst.u3, + true); + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, + poff, plen, buffer, buflen)) + return NF_DROP; + } + + /* The received= parameter (RFC 2361) contains the address + * from which the server received the request. */ + if (ct_sip_parse_address_param(ct, *dptr, matchend, *datalen, + "received=", &poff, &plen, + &addr, false) > 0 && + nf_inet_addr_cmp(&addr, &ct->tuplehash[dir].tuple.dst.u3) && + !nf_inet_addr_cmp(&addr, &ct->tuplehash[!dir].tuple.src.u3)) { + buflen = sip_sprintf_addr(ct, buffer, + &ct->tuplehash[!dir].tuple.src.u3, + false); + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, + poff, plen, buffer, buflen)) + return NF_DROP; + } + + /* The rport= parameter (RFC 3581) contains the port number + * from which the server received the request. */ + if (ct_sip_parse_numerical_param(ct, *dptr, matchend, *datalen, + "rport=", &poff, &plen, + &n) > 0 && + htons(n) == ct->tuplehash[dir].tuple.dst.u.udp.port && + htons(n) != ct->tuplehash[!dir].tuple.src.u.udp.port) { + __be16 p = ct->tuplehash[!dir].tuple.src.u.udp.port; + buflen = sprintf(buffer, "%u", ntohs(p)); + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, + poff, plen, buffer, buflen)) + return NF_DROP; + } + } + +next: + /* Translate Contact headers */ + coff = 0; + in_header = 0; + while (ct_sip_parse_header_uri(ct, *dptr, &coff, *datalen, + SIP_HDR_CONTACT, &in_header, + &matchoff, &matchlen, + &addr, &port) > 0) { + if (!map_addr(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, + &addr, port)) + return NF_DROP; + } + + if (!map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_FROM) || + !map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_TO)) + return NF_DROP; + + return NF_ACCEPT; +} + +static void nf_nat_sip_seq_adjust(struct sk_buff *skb, unsigned int protoff, + s16 off) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + const struct tcphdr *th; + + if (nf_ct_protonum(ct) != IPPROTO_TCP || off == 0) + return; + + th = (struct tcphdr *)(skb->data + protoff); + nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off); +} + +/* Handles expected signalling connections and media streams */ +static void nf_nat_sip_expected(struct nf_conn *ct, + struct nf_conntrack_expect *exp) +{ + struct nf_nat_range range; + + /* This must be a fresh one. */ + BUG_ON(ct->status & IPS_NAT_DONE_MASK); + + /* For DST manip, map port here to where it's expected. */ + range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); + range.min_proto = range.max_proto = exp->saved_proto; + range.min_addr = range.max_addr = exp->saved_addr; + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); + + /* Change src to where master sends to, but only if the connection + * actually came from the same source. */ + if (nf_inet_addr_cmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3, + &ct->master->tuplehash[exp->dir].tuple.src.u3)) { + range.flags = NF_NAT_RANGE_MAP_IPS; + range.min_addr = range.max_addr + = ct->master->tuplehash[!exp->dir].tuple.dst.u3; + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); + } +} + +static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + struct nf_conntrack_expect *exp, + unsigned int matchoff, + unsigned int matchlen) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + union nf_inet_addr newaddr; + u_int16_t port; + char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")]; + unsigned int buflen; + + /* Connection will come from reply */ + if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, + &ct->tuplehash[!dir].tuple.dst.u3)) + newaddr = exp->tuple.dst.u3; + else + newaddr = ct->tuplehash[!dir].tuple.dst.u3; + + /* If the signalling port matches the connection's source port in the + * original direction, try to use the destination port in the opposite + * direction. */ + if (exp->tuple.dst.u.udp.port == + ct->tuplehash[dir].tuple.src.u.udp.port) + port = ntohs(ct->tuplehash[!dir].tuple.dst.u.udp.port); + else + port = ntohs(exp->tuple.dst.u.udp.port); + + exp->saved_addr = exp->tuple.dst.u3; + exp->tuple.dst.u3 = newaddr; + exp->saved_proto.udp.port = exp->tuple.dst.u.udp.port; + exp->dir = !dir; + exp->expectfn = nf_nat_sip_expected; + + for (; port != 0; port++) { + int ret; + + exp->tuple.dst.u.udp.port = htons(port); + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; + break; + } + } + + if (port == 0) + return NF_DROP; + + if (!nf_inet_addr_cmp(&exp->tuple.dst.u3, &exp->saved_addr) || + exp->tuple.dst.u.udp.port != exp->saved_proto.udp.port) { + buflen = sip_sprintf_addr_port(ct, buffer, &newaddr, port); + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen)) + goto err; + } + return NF_ACCEPT; + +err: + nf_ct_unexpect_related(exp); + return NF_DROP; +} + +static int mangle_content_len(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + unsigned int matchoff, matchlen; + char buffer[sizeof("65536")]; + int buflen, c_len; + + /* Get actual SDP length */ + if (ct_sip_get_sdp_header(ct, *dptr, 0, *datalen, + SDP_HDR_VERSION, SDP_HDR_UNSPEC, + &matchoff, &matchlen) <= 0) + return 0; + c_len = *datalen - matchoff + strlen("v="); + + /* Now, update SDP length */ + if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_CONTENT_LENGTH, + &matchoff, &matchlen) <= 0) + return 0; + + buflen = sprintf(buffer, "%u", c_len); + return mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen); +} + +static int mangle_sdp_packet(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int sdpoff, + enum sdp_header_types type, + enum sdp_header_types term, + char *buffer, int buflen) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + unsigned int matchlen, matchoff; + + if (ct_sip_get_sdp_header(ct, *dptr, sdpoff, *datalen, type, term, + &matchoff, &matchlen) <= 0) + return -ENOENT; + return mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen) ? 0 : -EINVAL; +} + +static unsigned int nf_nat_sdp_addr(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int sdpoff, + enum sdp_header_types type, + enum sdp_header_types term, + const union nf_inet_addr *addr) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + char buffer[INET6_ADDRSTRLEN]; + unsigned int buflen; + + buflen = sip_sprintf_addr(ct, buffer, addr, false); + if (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, + sdpoff, type, term, buffer, buflen)) + return 0; + + return mangle_content_len(skb, protoff, dataoff, dptr, datalen); +} + +static unsigned int nf_nat_sdp_port(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int matchoff, + unsigned int matchlen, + u_int16_t port) +{ + char buffer[sizeof("nnnnn")]; + unsigned int buflen; + + buflen = sprintf(buffer, "%u", port); + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen)) + return 0; + + return mangle_content_len(skb, protoff, dataoff, dptr, datalen); +} + +static unsigned int nf_nat_sdp_session(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int sdpoff, + const union nf_inet_addr *addr) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + char buffer[INET6_ADDRSTRLEN]; + unsigned int buflen; + + /* Mangle session description owner and contact addresses */ + buflen = sip_sprintf_addr(ct, buffer, addr, false); + if (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, sdpoff, + SDP_HDR_OWNER, SDP_HDR_MEDIA, buffer, buflen)) + return 0; + + switch (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, sdpoff, + SDP_HDR_CONNECTION, SDP_HDR_MEDIA, + buffer, buflen)) { + case 0: + /* + * RFC 2327: + * + * Session description + * + * c=* (connection information - not required if included in all media) + */ + case -ENOENT: + break; + default: + return 0; + } + + return mangle_content_len(skb, protoff, dataoff, dptr, datalen); +} + +/* So, this packet has hit the connection tracking matching code. + Mangle it, and change the expectation to match the new version. */ +static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + struct nf_conntrack_expect *rtp_exp, + struct nf_conntrack_expect *rtcp_exp, + unsigned int mediaoff, + unsigned int medialen, + union nf_inet_addr *rtp_addr) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + u_int16_t port; + + /* Connection will come from reply */ + if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, + &ct->tuplehash[!dir].tuple.dst.u3)) + *rtp_addr = rtp_exp->tuple.dst.u3; + else + *rtp_addr = ct->tuplehash[!dir].tuple.dst.u3; + + rtp_exp->saved_addr = rtp_exp->tuple.dst.u3; + rtp_exp->tuple.dst.u3 = *rtp_addr; + rtp_exp->saved_proto.udp.port = rtp_exp->tuple.dst.u.udp.port; + rtp_exp->dir = !dir; + rtp_exp->expectfn = nf_nat_sip_expected; + + rtcp_exp->saved_addr = rtcp_exp->tuple.dst.u3; + rtcp_exp->tuple.dst.u3 = *rtp_addr; + rtcp_exp->saved_proto.udp.port = rtcp_exp->tuple.dst.u.udp.port; + rtcp_exp->dir = !dir; + rtcp_exp->expectfn = nf_nat_sip_expected; + + /* Try to get same pair of ports: if not, try to change them. */ + for (port = ntohs(rtp_exp->tuple.dst.u.udp.port); + port != 0; port += 2) { + int ret; + + rtp_exp->tuple.dst.u.udp.port = htons(port); + ret = nf_ct_expect_related(rtp_exp); + if (ret == -EBUSY) + continue; + else if (ret < 0) { + port = 0; + break; + } + rtcp_exp->tuple.dst.u.udp.port = htons(port + 1); + ret = nf_ct_expect_related(rtcp_exp); + if (ret == 0) + break; + else if (ret == -EBUSY) { + nf_ct_unexpect_related(rtp_exp); + continue; + } else if (ret < 0) { + nf_ct_unexpect_related(rtp_exp); + port = 0; + break; + } + } + + if (port == 0) + goto err1; + + /* Update media port. */ + if (rtp_exp->tuple.dst.u.udp.port != rtp_exp->saved_proto.udp.port && + !nf_nat_sdp_port(skb, protoff, dataoff, dptr, datalen, + mediaoff, medialen, port)) + goto err2; + + return NF_ACCEPT; + +err2: + nf_ct_unexpect_related(rtp_exp); + nf_ct_unexpect_related(rtcp_exp); +err1: + return NF_DROP; +} + +static struct nf_ct_helper_expectfn sip_nat = { + .name = "sip", + .expectfn = nf_nat_sip_expected, +}; + +static void __exit nf_nat_sip_fini(void) +{ + RCU_INIT_POINTER(nf_nat_sip_hook, NULL); + RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, NULL); + RCU_INIT_POINTER(nf_nat_sip_expect_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_addr_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_port_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_session_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_media_hook, NULL); + nf_ct_helper_expectfn_unregister(&sip_nat); + synchronize_rcu(); +} + +static int __init nf_nat_sip_init(void) +{ + BUG_ON(nf_nat_sip_hook != NULL); + BUG_ON(nf_nat_sip_seq_adjust_hook != NULL); + BUG_ON(nf_nat_sip_expect_hook != NULL); + BUG_ON(nf_nat_sdp_addr_hook != NULL); + BUG_ON(nf_nat_sdp_port_hook != NULL); + BUG_ON(nf_nat_sdp_session_hook != NULL); + BUG_ON(nf_nat_sdp_media_hook != NULL); + RCU_INIT_POINTER(nf_nat_sip_hook, nf_nat_sip); + RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, nf_nat_sip_seq_adjust); + RCU_INIT_POINTER(nf_nat_sip_expect_hook, nf_nat_sip_expect); + RCU_INIT_POINTER(nf_nat_sdp_addr_hook, nf_nat_sdp_addr); + RCU_INIT_POINTER(nf_nat_sdp_port_hook, nf_nat_sdp_port); + RCU_INIT_POINTER(nf_nat_sdp_session_hook, nf_nat_sdp_session); + RCU_INIT_POINTER(nf_nat_sdp_media_hook, nf_nat_sdp_media); + nf_ct_helper_expectfn_register(&sip_nat); + return 0; +} + +module_init(nf_nat_sip_init); +module_exit(nf_nat_sip_fini); diff --git a/net/netfilter/nf_nat_tftp.c b/net/netfilter/nf_nat_tftp.c new file mode 100644 index 00000000000..ccabbda71a3 --- /dev/null +++ b/net/netfilter/nf_nat_tftp.c @@ -0,0 +1,50 @@ +/* (C) 2001-2002 Magnus Boden <mb@ozaba.mine.nu> + * + * 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/udp.h> + +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_expect.h> +#include <net/netfilter/nf_nat_helper.h> +#include <linux/netfilter/nf_conntrack_tftp.h> + +MODULE_AUTHOR("Magnus Boden <mb@ozaba.mine.nu>"); +MODULE_DESCRIPTION("TFTP NAT helper"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ip_nat_tftp"); + +static unsigned int help(struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + struct nf_conntrack_expect *exp) +{ + const struct nf_conn *ct = exp->master; + + exp->saved_proto.udp.port + = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port; + exp->dir = IP_CT_DIR_REPLY; + exp->expectfn = nf_nat_follow_master; + if (nf_ct_expect_related(exp) != 0) + return NF_DROP; + return NF_ACCEPT; +} + +static void __exit nf_nat_tftp_fini(void) +{ + RCU_INIT_POINTER(nf_nat_tftp_hook, NULL); + synchronize_rcu(); +} + +static int __init nf_nat_tftp_init(void) +{ + BUG_ON(nf_nat_tftp_hook != NULL); + RCU_INIT_POINTER(nf_nat_tftp_hook, help); + return 0; +} + +module_init(nf_nat_tftp_init); +module_exit(nf_nat_tftp_fini); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index ce60cf0f6c1..8d2cf9ec37a 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -118,7 +118,7 @@ static void nf_queue_entry_release_refs(struct nf_queue_entry *entry) * through nf_reinject(). */ static int __nf_queue(struct sk_buff *skb, - struct list_head *elem, + struct nf_hook_ops *elem, u_int8_t pf, unsigned int hook, struct net_device *indev, struct net_device *outdev, @@ -155,7 +155,7 @@ static int __nf_queue(struct sk_buff *skb, *entry = (struct nf_queue_entry) { .skb = skb, - .elem = list_entry(elem, struct nf_hook_ops, list), + .elem = elem, .pf = pf, .hook = hook, .indev = indev, @@ -225,7 +225,7 @@ static void nf_bridge_adjust_segmented_data(struct sk_buff *skb) #endif int nf_queue(struct sk_buff *skb, - struct list_head *elem, + struct nf_hook_ops *elem, u_int8_t pf, unsigned int hook, struct net_device *indev, struct net_device *outdev, @@ -287,7 +287,7 @@ int nf_queue(struct sk_buff *skb, void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) { struct sk_buff *skb = entry->skb; - struct list_head *elem = &entry->elem->list; + struct nf_hook_ops *elem = entry->elem; const struct nf_afinfo *afinfo; int err; @@ -297,7 +297,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) /* Continue traversal iff userspace said ok... */ if (verdict == NF_REPEAT) { - elem = elem->prev; + elem = list_entry(elem->list.prev, struct nf_hook_ops, list); verdict = NF_ACCEPT; } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index a26503342e7..ffb92c03a35 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -241,7 +241,7 @@ static int __net_init nfnetlink_net_init(struct net *net) #endif }; - nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, THIS_MODULE, &cfg); + nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, &cfg); if (!nfnl) return -ENOMEM; net->nfnl_stash = nfnl; diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index b2e7310ca0b..589d686f0b4 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -79,11 +79,11 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, if (tb[NFACCT_BYTES]) { atomic64_set(&nfacct->bytes, - be64_to_cpu(nla_get_u64(tb[NFACCT_BYTES]))); + be64_to_cpu(nla_get_be64(tb[NFACCT_BYTES]))); } if (tb[NFACCT_PKTS]) { atomic64_set(&nfacct->pkts, - be64_to_cpu(nla_get_u64(tb[NFACCT_PKTS]))); + be64_to_cpu(nla_get_be64(tb[NFACCT_PKTS]))); } atomic_set(&nfacct->refcnt, 1); list_add_tail_rcu(&nfacct->head, &nfnl_acct_list); @@ -91,16 +91,16 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, } static int -nfnl_acct_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, +nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct nf_acct *acct) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0; + unsigned int flags = portid ? NLM_F_MULTI : 0; u64 pkts, bytes; event |= NFNL_SUBSYS_ACCT << 8; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -150,7 +150,7 @@ nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb) if (last && cur != last) continue; - if (nfnl_acct_fill_info(skb, NETLINK_CB(cb->skb).pid, + if (nfnl_acct_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), NFNL_MSG_ACCT_NEW, cur) < 0) { @@ -195,7 +195,7 @@ nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb, break; } - ret = nfnl_acct_fill_info(skb2, NETLINK_CB(skb).pid, + ret = nfnl_acct_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), NFNL_MSG_ACCT_NEW, cur); @@ -203,7 +203,7 @@ nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb, kfree_skb(skb2); break; } - ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).pid, + ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret > 0) ret = 0; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index d6836193d47..945950a8b1f 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -74,7 +74,7 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple, if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM]) return -EINVAL; - tuple->src.l3num = ntohs(nla_get_u16(tb[NFCTH_TUPLE_L3PROTONUM])); + tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM])); tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]); return 0; @@ -85,6 +85,9 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct) { const struct nf_conn_help *help = nfct_help(ct); + if (attr == NULL) + return -EINVAL; + if (help->helper->data_len == 0) return -EINVAL; @@ -395,16 +398,16 @@ nla_put_failure: } static int -nfnl_cthelper_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, +nfnl_cthelper_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct nf_conntrack_helper *helper) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0; + unsigned int flags = portid ? NLM_F_MULTI : 0; int status; event |= NFNL_SUBSYS_CTHELPER << 8; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -468,7 +471,7 @@ restart: cb->args[1] = 0; } if (nfnl_cthelper_fill_info(skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), NFNL_MSG_CTHELPER_NEW, cur) < 0) { @@ -538,7 +541,7 @@ nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb, break; } - ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).pid, + ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), NFNL_MSG_CTHELPER_NEW, cur); @@ -547,7 +550,7 @@ nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb, break; } - ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).pid, + ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret > 0) ret = 0; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index cdecbc8fe96..8847b4d8be0 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -155,16 +155,16 @@ err_proto_put: } static int -ctnl_timeout_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, +ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct ctnl_timeout *timeout) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0; + unsigned int flags = portid ? NLM_F_MULTI : 0; struct nf_conntrack_l4proto *l4proto = timeout->l4proto; event |= NFNL_SUBSYS_CTNETLINK_TIMEOUT << 8; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -222,7 +222,7 @@ ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) if (last && cur != last) continue; - if (ctnl_timeout_fill_info(skb, NETLINK_CB(cb->skb).pid, + if (ctnl_timeout_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_NEW, cur) < 0) { @@ -268,7 +268,7 @@ cttimeout_get_timeout(struct sock *ctnl, struct sk_buff *skb, break; } - ret = ctnl_timeout_fill_info(skb2, NETLINK_CB(skb).pid, + ret = ctnl_timeout_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_NEW, cur); @@ -276,7 +276,7 @@ cttimeout_get_timeout(struct sock *ctnl, struct sk_buff *skb, kfree_skb(skb2); break; } - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret > 0) ret = 0; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 5cfb5bedb2b..9f199f2e31f 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -55,7 +55,8 @@ struct nfulnl_instance { unsigned int qlen; /* number of nlmsgs in skb */ struct sk_buff *skb; /* pre-allocatd skb */ struct timer_list timer; - int peer_pid; /* PID of the peer process */ + struct user_namespace *peer_user_ns; /* User namespace of the peer process */ + int peer_portid; /* PORTID of the peer process */ /* configurable parameters */ unsigned int flushtimeout; /* timeout until queue flush */ @@ -132,7 +133,7 @@ instance_put(struct nfulnl_instance *inst) static void nfulnl_timer(unsigned long data); static struct nfulnl_instance * -instance_create(u_int16_t group_num, int pid) +instance_create(u_int16_t group_num, int portid, struct user_namespace *user_ns) { struct nfulnl_instance *inst; int err; @@ -162,7 +163,8 @@ instance_create(u_int16_t group_num, int pid) setup_timer(&inst->timer, nfulnl_timer, (unsigned long)inst); - inst->peer_pid = pid; + inst->peer_user_ns = user_ns; + inst->peer_portid = portid; inst->group_num = group_num; inst->qthreshold = NFULNL_QTHRESH_DEFAULT; @@ -334,7 +336,7 @@ __nfulnl_send(struct nfulnl_instance *inst) if (!nlh) goto out; } - status = nfnetlink_unicast(inst->skb, &init_net, inst->peer_pid, + status = nfnetlink_unicast(inst->skb, &init_net, inst->peer_portid, MSG_DONTWAIT); inst->qlen = 0; @@ -505,8 +507,10 @@ __build_packet_message(struct nfulnl_instance *inst, read_lock_bh(&sk->sk_callback_lock); if (sk->sk_socket && sk->sk_socket->file) { struct file *file = sk->sk_socket->file; - __be32 uid = htonl(file->f_cred->fsuid); - __be32 gid = htonl(file->f_cred->fsgid); + const struct cred *cred = file->f_cred; + struct user_namespace *user_ns = inst->peer_user_ns; + __be32 uid = htonl(from_kuid_munged(user_ns, cred->fsuid)); + __be32 gid = htonl(from_kgid_munged(user_ns, cred->fsgid)); read_unlock_bh(&sk->sk_callback_lock); if (nla_put_be32(inst->skb, NFULA_UID, uid) || nla_put_be32(inst->skb, NFULA_GID, gid)) @@ -700,7 +704,7 @@ nfulnl_rcv_nl_event(struct notifier_block *this, if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) { int i; - /* destroy all instances for this pid */ + /* destroy all instances for this portid */ spin_lock_bh(&instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct hlist_node *tmp, *t2; @@ -709,7 +713,7 @@ nfulnl_rcv_nl_event(struct notifier_block *this, hlist_for_each_entry_safe(inst, tmp, t2, head, hlist) { if ((net_eq(n->net, &init_net)) && - (n->pid == inst->peer_pid)) + (n->portid == inst->peer_portid)) __instance_destroy(inst); } } @@ -771,7 +775,7 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, } inst = instance_lookup_get(group_num); - if (inst && inst->peer_pid != NETLINK_CB(skb).pid) { + if (inst && inst->peer_portid != NETLINK_CB(skb).portid) { ret = -EPERM; goto out_put; } @@ -785,7 +789,8 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, } inst = instance_create(group_num, - NETLINK_CB(skb).pid); + NETLINK_CB(skb).portid, + sk_user_ns(NETLINK_CB(skb).ssk)); if (IS_ERR(inst)) { ret = PTR_ERR(inst); goto out; @@ -943,7 +948,7 @@ static int seq_show(struct seq_file *s, void *v) return seq_printf(s, "%5d %6d %5d %1d %5d %6d %2d\n", inst->group_num, - inst->peer_pid, inst->qlen, + inst->peer_portid, inst->qlen, inst->copy_mode, inst->copy_range, inst->flushtimeout, atomic_read(&inst->use)); } diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index c0496a55ad0..e12d44e75b2 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -44,7 +44,7 @@ struct nfqnl_instance { struct hlist_node hlist; /* global list of queues */ struct rcu_head rcu; - int peer_pid; + int peer_portid; unsigned int queue_maxlen; unsigned int copy_range; unsigned int queue_dropped; @@ -92,7 +92,7 @@ instance_lookup(u_int16_t queue_num) } static struct nfqnl_instance * -instance_create(u_int16_t queue_num, int pid) +instance_create(u_int16_t queue_num, int portid) { struct nfqnl_instance *inst; unsigned int h; @@ -111,7 +111,7 @@ instance_create(u_int16_t queue_num, int pid) } inst->queue_num = queue_num; - inst->peer_pid = pid; + inst->peer_portid = portid; inst->queue_maxlen = NFQNL_QMAX_DEFAULT; inst->copy_range = 0xfffff; inst->copy_mode = NFQNL_COPY_NONE; @@ -225,7 +225,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, { sk_buff_data_t old_tail; size_t size; - size_t data_len = 0; + size_t data_len = 0, cap_len = 0; struct sk_buff *skb; struct nlattr *nla; struct nfqnl_msg_packet_hdr *pmsg; @@ -247,7 +247,8 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, #endif + nla_total_size(sizeof(u_int32_t)) /* mark */ + nla_total_size(sizeof(struct nfqnl_msg_packet_hw)) - + nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp)); + + nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp) + + nla_total_size(sizeof(u_int32_t))); /* cap_len */ outdev = entry->outdev; @@ -266,6 +267,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, data_len = entskb->len; size += nla_total_size(data_len); + cap_len = entskb->len; break; } @@ -402,12 +404,14 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0) goto nla_put_failure; + if (cap_len > 0 && nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len))) + goto nla_put_failure; + nlh->nlmsg_len = skb->tail - old_tail; return skb; nla_put_failure: - if (skb) - kfree_skb(skb); + kfree_skb(skb); net_err_ratelimited("nf_queue: error creating packet message\n"); return NULL; } @@ -440,7 +444,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) } spin_lock_bh(&queue->lock); - if (!queue->peer_pid) { + if (!queue->peer_portid) { err = -EINVAL; goto err_out_free_nskb; } @@ -459,7 +463,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) *packet_id_ptr = htonl(entry->id); /* nfnetlink_unicast will either free the nskb or add it to a socket */ - err = nfnetlink_unicast(nskb, &init_net, queue->peer_pid, MSG_DONTWAIT); + err = nfnetlink_unicast(nskb, &init_net, queue->peer_portid, MSG_DONTWAIT); if (err < 0) { queue->queue_user_dropped++; goto err_out_unlock; @@ -527,9 +531,13 @@ nfqnl_set_mode(struct nfqnl_instance *queue, case NFQNL_COPY_PACKET: queue->copy_mode = mode; - /* we're using struct nlattr which has 16bit nla_len */ - if (range > 0xffff) - queue->copy_range = 0xffff; + /* We're using struct nlattr which has 16bit nla_len. Note that + * nla_len includes the header length. Thus, the maximum packet + * length that we support is 65531 bytes. We send truncated + * packets if the specified length is larger than that. + */ + if (range > 0xffff - NLA_HDRLEN) + queue->copy_range = 0xffff - NLA_HDRLEN; else queue->copy_range = range; break; @@ -616,7 +624,7 @@ nfqnl_rcv_nl_event(struct notifier_block *this, if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) { int i; - /* destroy all instances for this pid */ + /* destroy all instances for this portid */ spin_lock(&instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct hlist_node *tmp, *t2; @@ -625,7 +633,7 @@ nfqnl_rcv_nl_event(struct notifier_block *this, hlist_for_each_entry_safe(inst, tmp, t2, head, hlist) { if ((n->net == &init_net) && - (n->pid == inst->peer_pid)) + (n->portid == inst->peer_portid)) __instance_destroy(inst); } } @@ -650,7 +658,7 @@ static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { [NFQA_MARK] = { .type = NLA_U32 }, }; -static struct nfqnl_instance *verdict_instance_lookup(u16 queue_num, int nlpid) +static struct nfqnl_instance *verdict_instance_lookup(u16 queue_num, int nlportid) { struct nfqnl_instance *queue; @@ -658,7 +666,7 @@ static struct nfqnl_instance *verdict_instance_lookup(u16 queue_num, int nlpid) if (!queue) return ERR_PTR(-ENODEV); - if (queue->peer_pid != nlpid) + if (queue->peer_portid != nlportid) return ERR_PTR(-EPERM); return queue; @@ -698,7 +706,7 @@ nfqnl_recv_verdict_batch(struct sock *ctnl, struct sk_buff *skb, LIST_HEAD(batch_list); u16 queue_num = ntohs(nfmsg->res_id); - queue = verdict_instance_lookup(queue_num, NETLINK_CB(skb).pid); + queue = verdict_instance_lookup(queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); @@ -749,7 +757,7 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, queue = instance_lookup(queue_num); if (!queue) - queue = verdict_instance_lookup(queue_num, NETLINK_CB(skb).pid); + queue = verdict_instance_lookup(queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); @@ -832,7 +840,7 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, rcu_read_lock(); queue = instance_lookup(queue_num); - if (queue && queue->peer_pid != NETLINK_CB(skb).pid) { + if (queue && queue->peer_portid != NETLINK_CB(skb).portid) { ret = -EPERM; goto err_out_unlock; } @@ -844,7 +852,7 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, ret = -EBUSY; goto err_out_unlock; } - queue = instance_create(queue_num, NETLINK_CB(skb).pid); + queue = instance_create(queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) { ret = PTR_ERR(queue); goto err_out_unlock; @@ -1016,7 +1024,7 @@ static int seq_show(struct seq_file *s, void *v) return seq_printf(s, "%5d %6d %5d %1d %5d %5d %5d %8d %2d\n", inst->queue_num, - inst->peer_pid, inst->queue_total, + inst->peer_portid, inst->queue_total, inst->copy_mode, inst->copy_range, inst->queue_dropped, inst->queue_user_dropped, inst->id_sequence, 1); diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 116018560c6..ae7f5daeee4 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -72,14 +72,44 @@ static u8 xt_ct_find_proto(const struct xt_tgchk_param *par) return 0; } +static int +xt_ct_set_helper(struct nf_conn *ct, const char *helper_name, + const struct xt_tgchk_param *par) +{ + struct nf_conntrack_helper *helper; + struct nf_conn_help *help; + u8 proto; + + proto = xt_ct_find_proto(par); + if (!proto) { + pr_info("You must specify a L4 protocol, and not use " + "inversions on it.\n"); + return -ENOENT; + } + + helper = nf_conntrack_helper_try_module_get(helper_name, par->family, + proto); + if (helper == NULL) { + pr_info("No such helper \"%s\"\n", helper_name); + return -ENOENT; + } + + help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL); + if (help == NULL) { + module_put(helper->me); + return -ENOMEM; + } + + help->helper = helper; + return 0; +} + static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) { struct xt_ct_target_info *info = par->targinfo; struct nf_conntrack_tuple t; - struct nf_conn_help *help; struct nf_conn *ct; - int ret = 0; - u8 proto; + int ret; if (info->flags & ~XT_CT_NOTRACK) return -EINVAL; @@ -112,31 +142,9 @@ static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) goto err3; if (info->helper[0]) { - struct nf_conntrack_helper *helper; - - ret = -ENOENT; - proto = xt_ct_find_proto(par); - if (!proto) { - pr_info("You must specify a L4 protocol, " - "and not use inversions on it.\n"); - goto err3; - } - - ret = -ENOENT; - helper = nf_conntrack_helper_try_module_get(info->helper, - par->family, - proto); - if (helper == NULL) { - pr_info("No such helper \"%s\"\n", info->helper); - goto err3; - } - - ret = -ENOMEM; - help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL); - if (help == NULL) + ret = xt_ct_set_helper(ct, info->helper, par); + if (ret < 0) goto err3; - - help->helper = helper; } __set_bit(IPS_TEMPLATE_BIT, &ct->status); @@ -164,17 +172,79 @@ static void __xt_ct_tg_timeout_put(struct ctnl_timeout *timeout) } #endif +static int +xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, + const char *timeout_name) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + typeof(nf_ct_timeout_find_get_hook) timeout_find_get; + struct ctnl_timeout *timeout; + struct nf_conn_timeout *timeout_ext; + struct nf_conntrack_l4proto *l4proto; + int ret = 0; + u8 proto; + + rcu_read_lock(); + timeout_find_get = rcu_dereference(nf_ct_timeout_find_get_hook); + if (timeout_find_get == NULL) { + ret = -ENOENT; + pr_info("Timeout policy base is empty\n"); + goto out; + } + + proto = xt_ct_find_proto(par); + if (!proto) { + ret = -EINVAL; + pr_info("You must specify a L4 protocol, and not use " + "inversions on it.\n"); + goto out; + } + + timeout = timeout_find_get(timeout_name); + if (timeout == NULL) { + ret = -ENOENT; + pr_info("No such timeout policy \"%s\"\n", timeout_name); + goto out; + } + + if (timeout->l3num != par->family) { + ret = -EINVAL; + pr_info("Timeout policy `%s' can only be used by L3 protocol " + "number %d\n", timeout_name, timeout->l3num); + goto err_put_timeout; + } + /* Make sure the timeout policy matches any existing protocol tracker, + * otherwise default to generic. + */ + l4proto = __nf_ct_l4proto_find(par->family, proto); + if (timeout->l4proto->l4proto != l4proto->l4proto) { + ret = -EINVAL; + pr_info("Timeout policy `%s' can only be used by L4 protocol " + "number %d\n", + timeout_name, timeout->l4proto->l4proto); + goto err_put_timeout; + } + timeout_ext = nf_ct_timeout_ext_add(ct, timeout, GFP_ATOMIC); + if (timeout_ext == NULL) + ret = -ENOMEM; + +err_put_timeout: + __xt_ct_tg_timeout_put(timeout); +out: + rcu_read_unlock(); + return ret; +#else + return -EOPNOTSUPP; +#endif +} + static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) { struct xt_ct_target_info_v1 *info = par->targinfo; struct nf_conntrack_tuple t; - struct nf_conn_help *help; struct nf_conn *ct; - int ret = 0; - u8 proto; -#ifdef CONFIG_NF_CONNTRACK_TIMEOUT - struct ctnl_timeout *timeout; -#endif + int ret; + if (info->flags & ~XT_CT_NOTRACK) return -EINVAL; @@ -206,93 +276,16 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) goto err3; if (info->helper[0]) { - struct nf_conntrack_helper *helper; - - ret = -ENOENT; - proto = xt_ct_find_proto(par); - if (!proto) { - pr_info("You must specify a L4 protocol, " - "and not use inversions on it.\n"); - goto err3; - } - - ret = -ENOENT; - helper = nf_conntrack_helper_try_module_get(info->helper, - par->family, - proto); - if (helper == NULL) { - pr_info("No such helper \"%s\"\n", info->helper); + ret = xt_ct_set_helper(ct, info->helper, par); + if (ret < 0) goto err3; - } - - ret = -ENOMEM; - help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL); - if (help == NULL) - goto err3; - - help->helper = helper; } -#ifdef CONFIG_NF_CONNTRACK_TIMEOUT if (info->timeout[0]) { - typeof(nf_ct_timeout_find_get_hook) timeout_find_get; - struct nf_conn_timeout *timeout_ext; - - rcu_read_lock(); - timeout_find_get = - rcu_dereference(nf_ct_timeout_find_get_hook); - - if (timeout_find_get) { - const struct ipt_entry *e = par->entryinfo; - struct nf_conntrack_l4proto *l4proto; - - if (e->ip.invflags & IPT_INV_PROTO) { - ret = -EINVAL; - pr_info("You cannot use inversion on " - "L4 protocol\n"); - goto err4; - } - timeout = timeout_find_get(info->timeout); - if (timeout == NULL) { - ret = -ENOENT; - pr_info("No such timeout policy \"%s\"\n", - info->timeout); - goto err4; - } - if (timeout->l3num != par->family) { - ret = -EINVAL; - pr_info("Timeout policy `%s' can only be " - "used by L3 protocol number %d\n", - info->timeout, timeout->l3num); - goto err5; - } - /* Make sure the timeout policy matches any existing - * protocol tracker, otherwise default to generic. - */ - l4proto = __nf_ct_l4proto_find(par->family, - e->ip.proto); - if (timeout->l4proto->l4proto != l4proto->l4proto) { - ret = -EINVAL; - pr_info("Timeout policy `%s' can only be " - "used by L4 protocol number %d\n", - info->timeout, - timeout->l4proto->l4proto); - goto err5; - } - timeout_ext = nf_ct_timeout_ext_add(ct, timeout, - GFP_ATOMIC); - if (timeout_ext == NULL) { - ret = -ENOMEM; - goto err5; - } - } else { - ret = -ENOENT; - pr_info("Timeout policy base is empty\n"); - goto err4; - } - rcu_read_unlock(); + ret = xt_ct_set_timeout(ct, par, info->timeout); + if (ret < 0) + goto err3; } -#endif __set_bit(IPS_TEMPLATE_BIT, &ct->status); __set_bit(IPS_CONFIRMED_BIT, &ct->status); @@ -300,12 +293,6 @@ out: info->ct = ct; return 0; -#ifdef CONFIG_NF_CONNTRACK_TIMEOUT -err5: - __xt_ct_tg_timeout_put(timeout); -err4: - rcu_read_unlock(); -#endif err3: nf_conntrack_free(ct); err2: @@ -330,15 +317,30 @@ static void xt_ct_tg_destroy_v0(const struct xt_tgdtor_param *par) nf_ct_put(info->ct); } -static void xt_ct_tg_destroy_v1(const struct xt_tgdtor_param *par) +static void xt_ct_destroy_timeout(struct nf_conn *ct) { - struct xt_ct_target_info_v1 *info = par->targinfo; - struct nf_conn *ct = info->ct; - struct nf_conn_help *help; #ifdef CONFIG_NF_CONNTRACK_TIMEOUT struct nf_conn_timeout *timeout_ext; typeof(nf_ct_timeout_put_hook) timeout_put; + + rcu_read_lock(); + timeout_put = rcu_dereference(nf_ct_timeout_put_hook); + + if (timeout_put) { + timeout_ext = nf_ct_timeout_find(ct); + if (timeout_ext) + timeout_put(timeout_ext->timeout); + } + rcu_read_unlock(); #endif +} + +static void xt_ct_tg_destroy_v1(const struct xt_tgdtor_param *par) +{ + struct xt_ct_target_info_v1 *info = par->targinfo; + struct nf_conn *ct = info->ct; + struct nf_conn_help *help; + if (!nf_ct_is_untracked(ct)) { help = nfct_help(ct); if (help) @@ -346,17 +348,7 @@ static void xt_ct_tg_destroy_v1(const struct xt_tgdtor_param *par) nf_ct_l3proto_module_put(par->family); -#ifdef CONFIG_NF_CONNTRACK_TIMEOUT - rcu_read_lock(); - timeout_put = rcu_dereference(nf_ct_timeout_put_hook); - - if (timeout_put) { - timeout_ext = nf_ct_timeout_find(ct); - if (timeout_ext) - timeout_put(timeout_ext->timeout); - } - rcu_read_unlock(); -#endif + xt_ct_destroy_timeout(ct); } nf_ct_put(info->ct); } diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c index 91e9af4d1f4..fa40096940a 100644 --- a/net/netfilter/xt_LOG.c +++ b/net/netfilter/xt_LOG.c @@ -151,10 +151,12 @@ static void dump_sk_uid_gid(struct sbuff *m, struct sock *sk) return; read_lock_bh(&sk->sk_callback_lock); - if (sk->sk_socket && sk->sk_socket->file) + if (sk->sk_socket && sk->sk_socket->file) { + const struct cred *cred = sk->sk_socket->file->f_cred; sb_add(m, "UID=%u GID=%u ", - sk->sk_socket->file->f_cred->fsuid, - sk->sk_socket->file->f_cred->fsgid); + from_kuid_munged(&init_user_ns, cred->fsuid), + from_kgid_munged(&init_user_ns, cred->fsgid)); + } read_unlock_bh(&sk->sk_callback_lock); } diff --git a/net/netfilter/xt_NETMAP.c b/net/netfilter/xt_NETMAP.c new file mode 100644 index 00000000000..b253e07cb1c --- /dev/null +++ b/net/netfilter/xt_NETMAP.c @@ -0,0 +1,165 @@ +/* + * (C) 2000-2001 Svenning Soerensen <svenning@post5.tele.dk> + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * + * 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/ip.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/ipv6.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter/x_tables.h> +#include <net/netfilter/nf_nat.h> + +static unsigned int +netmap_tg6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + struct nf_nat_range newrange; + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + union nf_inet_addr new_addr, netmask; + unsigned int i; + + ct = nf_ct_get(skb, &ctinfo); + for (i = 0; i < ARRAY_SIZE(range->min_addr.ip6); i++) + netmask.ip6[i] = ~(range->min_addr.ip6[i] ^ + range->max_addr.ip6[i]); + + if (par->hooknum == NF_INET_PRE_ROUTING || + par->hooknum == NF_INET_LOCAL_OUT) + new_addr.in6 = ipv6_hdr(skb)->daddr; + else + new_addr.in6 = ipv6_hdr(skb)->saddr; + + for (i = 0; i < ARRAY_SIZE(new_addr.ip6); i++) { + new_addr.ip6[i] &= ~netmask.ip6[i]; + new_addr.ip6[i] |= range->min_addr.ip6[i] & + netmask.ip6[i]; + } + + newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr = new_addr; + newrange.max_addr = new_addr; + newrange.min_proto = range->min_proto; + newrange.max_proto = range->max_proto; + + return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(par->hooknum)); +} + +static int netmap_tg6_checkentry(const struct xt_tgchk_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + + if (!(range->flags & NF_NAT_RANGE_MAP_IPS)) + return -EINVAL; + return 0; +} + +static unsigned int +netmap_tg4(struct sk_buff *skb, const struct xt_action_param *par) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + __be32 new_ip, netmask; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + struct nf_nat_range newrange; + + NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING || + par->hooknum == NF_INET_POST_ROUTING || + par->hooknum == NF_INET_LOCAL_OUT || + par->hooknum == NF_INET_LOCAL_IN); + ct = nf_ct_get(skb, &ctinfo); + + netmask = ~(mr->range[0].min_ip ^ mr->range[0].max_ip); + + if (par->hooknum == NF_INET_PRE_ROUTING || + par->hooknum == NF_INET_LOCAL_OUT) + new_ip = ip_hdr(skb)->daddr & ~netmask; + else + new_ip = ip_hdr(skb)->saddr & ~netmask; + new_ip |= mr->range[0].min_ip & netmask; + + memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); + memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); + newrange.flags = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.ip = new_ip; + newrange.max_addr.ip = new_ip; + newrange.min_proto = mr->range[0].min; + newrange.max_proto = mr->range[0].max; + + /* Hand modified range to generic setup. */ + return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(par->hooknum)); +} + +static int netmap_tg4_check(const struct xt_tgchk_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + + if (!(mr->range[0].flags & NF_NAT_RANGE_MAP_IPS)) { + pr_debug("bad MAP_IPS.\n"); + return -EINVAL; + } + if (mr->rangesize != 1) { + pr_debug("bad rangesize %u.\n", mr->rangesize); + return -EINVAL; + } + return 0; +} + +static struct xt_target netmap_tg_reg[] __read_mostly = { + { + .name = "NETMAP", + .family = NFPROTO_IPV6, + .revision = 0, + .target = netmap_tg6, + .targetsize = sizeof(struct nf_nat_range), + .table = "nat", + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_LOCAL_IN), + .checkentry = netmap_tg6_checkentry, + .me = THIS_MODULE, + }, + { + .name = "NETMAP", + .family = NFPROTO_IPV4, + .revision = 0, + .target = netmap_tg4, + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), + .table = "nat", + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_LOCAL_IN), + .checkentry = netmap_tg4_check, + .me = THIS_MODULE, + }, +}; + +static int __init netmap_tg_init(void) +{ + return xt_register_targets(netmap_tg_reg, ARRAY_SIZE(netmap_tg_reg)); +} + +static void netmap_tg_exit(void) +{ + xt_unregister_targets(netmap_tg_reg, ARRAY_SIZE(netmap_tg_reg)); +} + +module_init(netmap_tg_init); +module_exit(netmap_tg_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Xtables: 1:1 NAT mapping of subnets"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS("ip6t_NETMAP"); +MODULE_ALIAS("ipt_NETMAP"); diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index 7babe7d6871..817f9e9f2b1 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -43,7 +43,7 @@ static u32 hash_v4(const struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); /* packets in either direction go into same queue */ - if (iph->saddr < iph->daddr) + if ((__force u32)iph->saddr < (__force u32)iph->daddr) return jhash_3words((__force u32)iph->saddr, (__force u32)iph->daddr, iph->protocol, jhash_initval); @@ -57,7 +57,8 @@ static u32 hash_v6(const struct sk_buff *skb) const struct ipv6hdr *ip6h = ipv6_hdr(skb); u32 a, b, c; - if (ip6h->saddr.s6_addr32[3] < ip6h->daddr.s6_addr32[3]) { + if ((__force u32)ip6h->saddr.s6_addr32[3] < + (__force u32)ip6h->daddr.s6_addr32[3]) { a = (__force u32) ip6h->saddr.s6_addr32[3]; b = (__force u32) ip6h->daddr.s6_addr32[3]; } else { @@ -65,7 +66,8 @@ static u32 hash_v6(const struct sk_buff *skb) a = (__force u32) ip6h->daddr.s6_addr32[3]; } - if (ip6h->saddr.s6_addr32[1] < ip6h->daddr.s6_addr32[1]) + if ((__force u32)ip6h->saddr.s6_addr32[1] < + (__force u32)ip6h->daddr.s6_addr32[1]) c = (__force u32) ip6h->saddr.s6_addr32[1]; else c = (__force u32) ip6h->daddr.s6_addr32[1]; diff --git a/net/netfilter/xt_NOTRACK.c b/net/netfilter/xt_NOTRACK.c deleted file mode 100644 index 9d782181b6c..00000000000 --- a/net/netfilter/xt_NOTRACK.c +++ /dev/null @@ -1,53 +0,0 @@ -/* This is a module which is used for setting up fake conntracks - * on packets so that they are not seen by the conntrack/NAT code. - */ -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter/x_tables.h> -#include <net/netfilter/nf_conntrack.h> - -MODULE_DESCRIPTION("Xtables: Disabling connection tracking for packets"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("ipt_NOTRACK"); -MODULE_ALIAS("ip6t_NOTRACK"); - -static unsigned int -notrack_tg(struct sk_buff *skb, const struct xt_action_param *par) -{ - /* Previously seen (loopback)? Ignore. */ - if (skb->nfct != NULL) - return XT_CONTINUE; - - /* Attach fake conntrack entry. - If there is a real ct entry correspondig to this packet, - it'll hang aroun till timing out. We don't deal with it - for performance reasons. JK */ - skb->nfct = &nf_ct_untracked_get()->ct_general; - skb->nfctinfo = IP_CT_NEW; - nf_conntrack_get(skb->nfct); - - return XT_CONTINUE; -} - -static struct xt_target notrack_tg_reg __read_mostly = { - .name = "NOTRACK", - .revision = 0, - .family = NFPROTO_UNSPEC, - .target = notrack_tg, - .table = "raw", - .me = THIS_MODULE, -}; - -static int __init notrack_tg_init(void) -{ - return xt_register_target(¬rack_tg_reg); -} - -static void __exit notrack_tg_exit(void) -{ - xt_unregister_target(¬rack_tg_reg); -} - -module_init(notrack_tg_init); -module_exit(notrack_tg_exit); diff --git a/net/netfilter/xt_REDIRECT.c b/net/netfilter/xt_REDIRECT.c new file mode 100644 index 00000000000..22a10309297 --- /dev/null +++ b/net/netfilter/xt_REDIRECT.c @@ -0,0 +1,190 @@ +/* + * (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * + * 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. + * + * Based on Rusty Russell's IPv4 REDIRECT target. Development of IPv6 + * NAT funded by Astaro. + */ + +#include <linux/if.h> +#include <linux/inetdevice.h> +#include <linux/ip.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/netfilter.h> +#include <linux/types.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter/x_tables.h> +#include <net/addrconf.h> +#include <net/checksum.h> +#include <net/protocol.h> +#include <net/netfilter/nf_nat.h> + +static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT; + +static unsigned int +redirect_tg6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + struct nf_nat_range newrange; + struct in6_addr newdst; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + if (par->hooknum == NF_INET_LOCAL_OUT) + newdst = loopback_addr; + else { + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + bool addr = false; + + rcu_read_lock(); + idev = __in6_dev_get(skb->dev); + if (idev != NULL) { + list_for_each_entry(ifa, &idev->addr_list, if_list) { + newdst = ifa->addr; + addr = true; + break; + } + } + rcu_read_unlock(); + + if (!addr) + return NF_DROP; + } + + newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.in6 = newdst; + newrange.max_addr.in6 = newdst; + newrange.min_proto = range->min_proto; + newrange.max_proto = range->max_proto; + + return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST); +} + +static int redirect_tg6_checkentry(const struct xt_tgchk_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + + if (range->flags & NF_NAT_RANGE_MAP_IPS) + return -EINVAL; + return 0; +} + +/* FIXME: Take multiple ranges --RR */ +static int redirect_tg4_check(const struct xt_tgchk_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + + if (mr->range[0].flags & NF_NAT_RANGE_MAP_IPS) { + pr_debug("bad MAP_IPS.\n"); + return -EINVAL; + } + if (mr->rangesize != 1) { + pr_debug("bad rangesize %u.\n", mr->rangesize); + return -EINVAL; + } + return 0; +} + +static unsigned int +redirect_tg4(struct sk_buff *skb, const struct xt_action_param *par) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + __be32 newdst; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + struct nf_nat_range newrange; + + NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING || + par->hooknum == NF_INET_LOCAL_OUT); + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); + + /* Local packets: make them go to loopback */ + if (par->hooknum == NF_INET_LOCAL_OUT) + newdst = htonl(0x7F000001); + else { + struct in_device *indev; + struct in_ifaddr *ifa; + + newdst = 0; + + rcu_read_lock(); + indev = __in_dev_get_rcu(skb->dev); + if (indev && (ifa = indev->ifa_list)) + newdst = ifa->ifa_local; + rcu_read_unlock(); + + if (!newdst) + return NF_DROP; + } + + /* Transfer from original range. */ + memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); + memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); + newrange.flags = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.ip = newdst; + newrange.max_addr.ip = newdst; + newrange.min_proto = mr->range[0].min; + newrange.max_proto = mr->range[0].max; + + /* Hand modified range to generic setup. */ + return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST); +} + +static struct xt_target redirect_tg_reg[] __read_mostly = { + { + .name = "REDIRECT", + .family = NFPROTO_IPV6, + .revision = 0, + .table = "nat", + .checkentry = redirect_tg6_checkentry, + .target = redirect_tg6, + .targetsize = sizeof(struct nf_nat_range), + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, + { + .name = "REDIRECT", + .family = NFPROTO_IPV4, + .revision = 0, + .table = "nat", + .target = redirect_tg4, + .checkentry = redirect_tg4_check, + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, +}; + +static int __init redirect_tg_init(void) +{ + return xt_register_targets(redirect_tg_reg, + ARRAY_SIZE(redirect_tg_reg)); +} + +static void __exit redirect_tg_exit(void) +{ + xt_unregister_targets(redirect_tg_reg, ARRAY_SIZE(redirect_tg_reg)); +} + +module_init(redirect_tg_init); +module_exit(redirect_tg_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("Xtables: Connection redirection to localhost"); +MODULE_ALIAS("ip6t_REDIRECT"); +MODULE_ALIAS("ipt_REDIRECT"); diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index ee2e5bc5a8c..bd93e51d30a 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -70,6 +70,7 @@ tee_tg_route4(struct sk_buff *skb, const struct xt_tee_tginfo *info) fl4.daddr = info->gw.ip; fl4.flowi4_tos = RT_TOS(iph->tos); fl4.flowi4_scope = RT_SCOPE_UNIVERSE; + fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH; rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) return false; diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c new file mode 100644 index 00000000000..bea7464cc43 --- /dev/null +++ b/net/netfilter/xt_nat.c @@ -0,0 +1,170 @@ +/* + * (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2011 Patrick McHardy <kaber@trash.net> + * + * 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/netfilter.h> +#include <linux/netfilter/x_tables.h> +#include <net/netfilter/nf_nat_core.h> + +static int xt_nat_checkentry_v0(const struct xt_tgchk_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + + if (mr->rangesize != 1) { + pr_info("%s: multiple ranges no longer supported\n", + par->target->name); + return -EINVAL; + } + return 0; +} + +static void xt_nat_convert_range(struct nf_nat_range *dst, + const struct nf_nat_ipv4_range *src) +{ + memset(&dst->min_addr, 0, sizeof(dst->min_addr)); + memset(&dst->max_addr, 0, sizeof(dst->max_addr)); + + dst->flags = src->flags; + dst->min_addr.ip = src->min_ip; + dst->max_addr.ip = src->max_ip; + dst->min_proto = src->min; + dst->max_proto = src->max; +} + +static unsigned int +xt_snat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + struct nf_nat_range range; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY)); + + xt_nat_convert_range(&range, &mr->range[0]); + return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); +} + +static unsigned int +xt_dnat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + struct nf_nat_range range; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); + + xt_nat_convert_range(&range, &mr->range[0]); + return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); +} + +static unsigned int +xt_snat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY)); + + return nf_nat_setup_info(ct, range, NF_NAT_MANIP_SRC); +} + +static unsigned int +xt_dnat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); + + return nf_nat_setup_info(ct, range, NF_NAT_MANIP_DST); +} + +static struct xt_target xt_nat_target_reg[] __read_mostly = { + { + .name = "SNAT", + .revision = 0, + .checkentry = xt_nat_checkentry_v0, + .target = xt_snat_target_v0, + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), + .family = NFPROTO_IPV4, + .table = "nat", + .hooks = (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, + { + .name = "DNAT", + .revision = 0, + .checkentry = xt_nat_checkentry_v0, + .target = xt_dnat_target_v0, + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), + .family = NFPROTO_IPV4, + .table = "nat", + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, + { + .name = "SNAT", + .revision = 1, + .target = xt_snat_target_v1, + .targetsize = sizeof(struct nf_nat_range), + .table = "nat", + .hooks = (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, + { + .name = "DNAT", + .revision = 1, + .target = xt_dnat_target_v1, + .targetsize = sizeof(struct nf_nat_range), + .table = "nat", + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, +}; + +static int __init xt_nat_init(void) +{ + return xt_register_targets(xt_nat_target_reg, + ARRAY_SIZE(xt_nat_target_reg)); +} + +static void __exit xt_nat_exit(void) +{ + xt_unregister_targets(xt_nat_target_reg, ARRAY_SIZE(xt_nat_target_reg)); +} + +module_init(xt_nat_init); +module_exit(xt_nat_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS("ipt_SNAT"); +MODULE_ALIAS("ipt_DNAT"); +MODULE_ALIAS("ip6t_SNAT"); +MODULE_ALIAS("ip6t_DNAT"); diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 846f895cb65..a5e673d32bd 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -269,7 +269,7 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) mss <<= 8; mss |= optp[2]; - mss = ntohs(mss); + mss = ntohs((__force __be16)mss); break; case OSFOPT_TS: loop_cont = 1; diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index 772d7389b33..ca2e577ed8a 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -17,6 +17,17 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_owner.h> +static int owner_check(const struct xt_mtchk_param *par) +{ + struct xt_owner_match_info *info = par->matchinfo; + + /* For now only allow adding matches from the initial user namespace */ + if ((info->match & (XT_OWNER_UID|XT_OWNER_GID)) && + (current_user_ns() != &init_user_ns)) + return -EINVAL; + return 0; +} + static bool owner_mt(const struct sk_buff *skb, struct xt_action_param *par) { @@ -37,17 +48,23 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) return ((info->match ^ info->invert) & (XT_OWNER_UID | XT_OWNER_GID)) == 0; - if (info->match & XT_OWNER_UID) - if ((filp->f_cred->fsuid >= info->uid_min && - filp->f_cred->fsuid <= info->uid_max) ^ + if (info->match & XT_OWNER_UID) { + kuid_t uid_min = make_kuid(&init_user_ns, info->uid_min); + kuid_t uid_max = make_kuid(&init_user_ns, info->uid_max); + if ((uid_gte(filp->f_cred->fsuid, uid_min) && + uid_lte(filp->f_cred->fsuid, uid_max)) ^ !(info->invert & XT_OWNER_UID)) return false; + } - if (info->match & XT_OWNER_GID) - if ((filp->f_cred->fsgid >= info->gid_min && - filp->f_cred->fsgid <= info->gid_max) ^ + if (info->match & XT_OWNER_GID) { + kgid_t gid_min = make_kgid(&init_user_ns, info->gid_min); + kgid_t gid_max = make_kgid(&init_user_ns, info->gid_max); + if ((gid_gte(filp->f_cred->fsgid, gid_min) && + gid_lte(filp->f_cred->fsgid, gid_max)) ^ !(info->invert & XT_OWNER_GID)) return false; + } return true; } @@ -56,6 +73,7 @@ static struct xt_match owner_mt_reg __read_mostly = { .name = "owner", .revision = 1, .family = NFPROTO_UNSPEC, + .checkentry = owner_check, .match = owner_mt, .matchsize = sizeof(struct xt_owner_match_info), .hooks = (1 << NF_INET_LOCAL_OUT) | diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index ae2ad1eec8d..4635c9b0045 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -317,6 +317,8 @@ static int recent_mt_check(const struct xt_mtchk_param *par, struct recent_table *t; #ifdef CONFIG_PROC_FS struct proc_dir_entry *pde; + kuid_t uid; + kgid_t gid; #endif unsigned int i; int ret = -EINVAL; @@ -372,6 +374,13 @@ static int recent_mt_check(const struct xt_mtchk_param *par, for (i = 0; i < ip_list_hash_size; i++) INIT_LIST_HEAD(&t->iphash[i]); #ifdef CONFIG_PROC_FS + uid = make_kuid(&init_user_ns, ip_list_uid); + gid = make_kgid(&init_user_ns, ip_list_gid); + if (!uid_valid(uid) || !gid_valid(gid)) { + kfree(t); + ret = -EINVAL; + goto out; + } pde = proc_create_data(t->name, ip_list_perms, recent_net->xt_recent, &recent_mt_fops, t); if (pde == NULL) { @@ -379,8 +388,8 @@ static int recent_mt_check(const struct xt_mtchk_param *par, ret = -ENOMEM; goto out; } - pde->uid = ip_list_uid; - pde->gid = ip_list_gid; + pde->uid = uid; + pde->gid = gid; #endif spin_lock_bh(&recent_lock); list_add_tail(&t->list, &recent_net->tables); diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index c6f7db720d8..865a9e54f3a 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -356,6 +356,27 @@ static struct xt_match set_matches[] __read_mostly = { .destroy = set_match_v1_destroy, .me = THIS_MODULE }, + /* --return-nomatch flag support */ + { + .name = "set", + .family = NFPROTO_IPV4, + .revision = 2, + .match = set_match_v1, + .matchsize = sizeof(struct xt_set_info_match_v1), + .checkentry = set_match_v1_checkentry, + .destroy = set_match_v1_destroy, + .me = THIS_MODULE + }, + { + .name = "set", + .family = NFPROTO_IPV6, + .revision = 2, + .match = set_match_v1, + .matchsize = sizeof(struct xt_set_info_match_v1), + .checkentry = set_match_v1_checkentry, + .destroy = set_match_v1_destroy, + .me = THIS_MODULE + }, }; static struct xt_target set_targets[] __read_mostly = { @@ -389,6 +410,7 @@ static struct xt_target set_targets[] __read_mostly = { .destroy = set_target_v1_destroy, .me = THIS_MODULE }, + /* --timeout and --exist flags support */ { .name = "SET", .revision = 2, diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 9ea482d08cf..63b2bdb59e9 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -108,9 +108,9 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, const struct iphdr *iph = ip_hdr(skb); struct udphdr _hdr, *hp = NULL; struct sock *sk; - __be32 daddr, saddr; - __be16 dport, sport; - u8 protocol; + __be32 uninitialized_var(daddr), uninitialized_var(saddr); + __be16 uninitialized_var(dport), uninitialized_var(sport); + u8 uninitialized_var(protocol); #ifdef XT_SOCKET_HAVE_CONNTRACK struct nf_conn const *ct; enum ip_conntrack_info ctinfo; @@ -261,9 +261,9 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) struct ipv6hdr *iph = ipv6_hdr(skb); struct udphdr _hdr, *hp = NULL; struct sock *sk; - struct in6_addr *daddr, *saddr; - __be16 dport, sport; - int thoff = 0, tproto; + struct in6_addr *daddr = NULL, *saddr = NULL; + __be16 uninitialized_var(dport), uninitialized_var(sport); + int thoff = 0, uninitialized_var(tproto); const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c index c48975ff8ea..0ae55a36f49 100644 --- a/net/netfilter/xt_time.c +++ b/net/netfilter/xt_time.c @@ -42,6 +42,7 @@ static const u_int16_t days_since_leapyear[] = { */ enum { DSE_FIRST = 2039, + SECONDS_PER_DAY = 86400, }; static const u_int16_t days_since_epoch[] = { /* 2039 - 2030 */ @@ -78,7 +79,7 @@ static inline unsigned int localtime_1(struct xtm *r, time_t time) unsigned int v, w; /* Each day has 86400s, so finding the hour/minute is actually easy. */ - v = time % 86400; + v = time % SECONDS_PER_DAY; r->second = v % 60; w = v / 60; r->minute = w % 60; @@ -199,6 +200,18 @@ time_mt(const struct sk_buff *skb, struct xt_action_param *par) if (packet_time < info->daytime_start && packet_time > info->daytime_stop) return false; + + /** if user asked to ignore 'next day', then e.g. + * '1 PM Wed, August 1st' should be treated + * like 'Tue 1 PM July 31st'. + * + * This also causes + * 'Monday, "23:00 to 01:00", to match for 2 hours, starting + * Monday 23:00 to Tuesday 01:00. + */ + if ((info->flags & XT_TIME_CONTIGUOUS) && + packet_time <= info->daytime_stop) + stamp -= SECONDS_PER_DAY; } localtime_2(¤t_time, stamp); @@ -227,6 +240,15 @@ static int time_mt_check(const struct xt_mtchk_param *par) return -EDOM; } + if (info->flags & ~XT_TIME_ALL_FLAGS) { + pr_info("unknown flags 0x%x\n", info->flags & ~XT_TIME_ALL_FLAGS); + return -EINVAL; + } + + if ((info->flags & XT_TIME_CONTIGUOUS) && + info->daytime_start < info->daytime_stop) + return -EINVAL; + return 0; } |