static int help(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
{
unsigned int dataoff;
const struct iphdr *iph;
const struct tcphdr *th;
struct tcphdr _tcph;
char *data, *data_limit, *ib_ptr;
int dir = CTINFO2DIR(ctinfo);
struct nf_conntrack_expect *exp;
struct nf_conntrack_tuple *tuple;
u_int32_t dcc_ip;
u_int16_t dcc_port;
__be16 port;
int i, ret = NF_ACCEPT;
char *addr_beg_p, *addr_end_p;
typeof(nf_nat_irc_hook) nf_nat_irc;
/* If packet is coming from IRC server */
if (dir == IP_CT_DIR_REPLY)
return NF_ACCEPT;
/* Until there's been traffic both ways, don't look in packets. */
if (ctinfo != IP_CT_ESTABLISHED &&
ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY)
return NF_ACCEPT;
/* Not a full tcp header? */
th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph);
if (th == NULL)
return NF_ACCEPT;
/* No data? */
dataoff = protoff + th->doff*4;
if (dataoff >= skb->len)
return NF_ACCEPT;
spin_lock_bh(&irc_buffer_lock);
ib_ptr = skb_header_pointer(skb, dataoff, skb->len - dataoff,
irc_buffer);
BUG_ON(ib_ptr == NULL);
data = ib_ptr;
data_limit = ib_ptr + skb->len - dataoff;
/* strlen("\1DCC SENT t AAAAAAAA P\1\n")=24
* 5+MINMATCHLEN+strlen("t AAAAAAAA P\1\n")=14 */
while (data < data_limit - (19 + MINMATCHLEN)) {
if (memcmp(data, "\1DCC ", 5)) {
data++;
continue;
}
data += 5;
/* we have at least (19+MINMATCHLEN)-5 bytes valid data left */
iph = ip_hdr(skb);
pr_debug("DCC found in master %pI4:%u %pI4:%u\n",
&iph->saddr, ntohs(th->source),
&iph->daddr, ntohs(th->dest));
for (i = 0; i < ARRAY_SIZE(dccprotos); i++) {
if (memcmp(data, dccprotos[i], strlen(dccprotos[i]))) {
/* no match */
continue;
}
data += strlen(dccprotos[i]);
pr_debug("DCC %s detected\n", dccprotos[i]);
/* we have at least
* (19+MINMATCHLEN)-5-dccprotos[i].matchlen bytes valid
* data left (== 14/13 bytes) */
if (parse_dcc((char *)data, data_limit, &dcc_ip,
&dcc_port, &addr_beg_p, &addr_end_p)) {
pr_debug("unable to parse dcc command\n");
continue;
}
pr_debug("DCC bound ip/port: %pI4:%u\n",
&dcc_ip, dcc_port);
/* dcc_ip can be the internal OR external (NAT'ed) IP */
tuple = &ct->tuplehash[dir].tuple;
if (tuple->src.u3.ip != htonl(dcc_ip) &&
tuple->dst.u3.ip != htonl(dcc_ip)) {
if (net_ratelimit())
printk(KERN_WARNING
"Forged DCC command from %pI4: %pI4:%u\n",
&tuple->src.u3.ip,
&dcc_ip, dcc_port);
continue;
}
exp = nf_conntrack_expect_alloc(ct);
if (exp == NULL) {
ret = NF_DROP;
goto out;
}
tuple = &ct->tuplehash[!dir].tuple;
port = htons(dcc_port);
nf_conntrack_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT,
tuple->src.l3num,
NULL, &tuple->dst.u3,
IPPROTO_TCP, NULL, &port);
nf_nat_irc = rcu_dereference(nf_nat_irc_hook);
if (nf_nat_irc && ct->status & IPS_NAT_MASK)
ret = nf_nat_irc(skb, ctinfo,
addr_beg_p - ib_ptr,
addr_end_p - addr_beg_p,
exp);
else if (nf_conntrack_expect_related(exp) != 0)
ret = NF_DROP;
nf_conntrack_expect_put(exp);
goto out;
}
}
out:
spin_unlock_bh(&irc_buffer_lock);
return ret;
}
struct sock*
xt_socket_get4_sk(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;
#ifdef XT_SOCKET_HAVE_CONNTRACK
struct nf_conn const *ct;
enum ip_conntrack_info ctinfo;
#endif
daddr = saddr = dport = sport = protocol = 0;
if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) {
hp = skb_header_pointer(skb, ip_hdrlen(skb),
sizeof(_hdr), &_hdr);
if (hp == NULL)
return NULL;
protocol = iph->protocol;
saddr = iph->saddr;
sport = hp->source;
daddr = iph->daddr;
dport = hp->dest;
} else if (iph->protocol == IPPROTO_ICMP) {
if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr,
&sport, &dport))
return NULL;
} else {
return NULL;
}
#ifdef XT_SOCKET_HAVE_CONNTRACK
/* Do the lookup with the original socket address in case this is a
* reply packet of an established SNAT-ted connection. */
ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct) &&
((iph->protocol != IPPROTO_ICMP &&
ctinfo == IP_CT_ESTABLISHED_REPLY) ||
(iph->protocol == IPPROTO_ICMP &&
ctinfo == IP_CT_RELATED_REPLY)) &&
(ct->status & IPS_SRC_NAT_DONE)) {
daddr = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip;
dport = (iph->protocol == IPPROTO_TCP) ?
ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port :
ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port;
}
#endif
sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol,
saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY);
pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n",
protocol, &saddr, ntohs(sport),
&daddr, ntohs(dport),
&iph->daddr, hp ? ntohs(hp->dest) : 0, sk);
return sk;
}
/* track caller id inside control connection, call expect_related */
static int
conntrack_pptp_help(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
{
int dir = CTINFO2DIR(ctinfo);
const struct nf_ct_pptp_master *info = &nfct_help(ct)->help.ct_pptp_info;
const struct tcphdr *tcph;
struct tcphdr _tcph;
const struct pptp_pkt_hdr *pptph;
struct pptp_pkt_hdr _pptph;
struct PptpControlHeader _ctlh, *ctlh;
union pptp_ctrl_union _pptpReq, *pptpReq;
unsigned int tcplen = skb->len - protoff;
unsigned int datalen, reqlen, nexthdr_off;
int oldsstate, oldcstate;
int ret;
u_int16_t msg;
#ifdef CONFIG_HTC_NET_MODIFY
if (info == NULL)
printk("[NET] info = NULL in %s\n", __func__);
#endif
/* don't do any tracking before tcp handshake complete */
if (ctinfo != IP_CT_ESTABLISHED &&
ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY)
return NF_ACCEPT;
nexthdr_off = protoff;
tcph = skb_header_pointer(skb, nexthdr_off, sizeof(_tcph), &_tcph);
BUG_ON(!tcph);
nexthdr_off += tcph->doff * 4;
datalen = tcplen - tcph->doff * 4;
pptph = skb_header_pointer(skb, nexthdr_off, sizeof(_pptph), &_pptph);
if (!pptph) {
pr_debug("no full PPTP header, can't track\n");
return NF_ACCEPT;
}
nexthdr_off += sizeof(_pptph);
datalen -= sizeof(_pptph);
/* if it's not a control message we can't do anything with it */
if (ntohs(pptph->packetType) != PPTP_PACKET_CONTROL ||
ntohl(pptph->magicCookie) != PPTP_MAGIC_COOKIE) {
pr_debug("not a control packet\n");
return NF_ACCEPT;
}
ctlh = skb_header_pointer(skb, nexthdr_off, sizeof(_ctlh), &_ctlh);
if (!ctlh)
return NF_ACCEPT;
nexthdr_off += sizeof(_ctlh);
datalen -= sizeof(_ctlh);
reqlen = datalen;
msg = ntohs(ctlh->messageType);
if (msg > 0 && msg <= PPTP_MSG_MAX && reqlen < pptp_msg_size[msg])
return NF_ACCEPT;
if (reqlen > sizeof(*pptpReq))
reqlen = sizeof(*pptpReq);
pptpReq = skb_header_pointer(skb, nexthdr_off, reqlen, &_pptpReq);
if (!pptpReq)
return NF_ACCEPT;
oldsstate = info->sstate;
oldcstate = info->cstate;
spin_lock_bh(&nf_pptp_lock);
/* FIXME: We just blindly assume that the control connection is always
* 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,
ctinfo);
else
/* server -> client (PAC -> PNS) */
ret = pptp_inbound_pkt(skb, ctlh, pptpReq, reqlen, ct,
ctinfo);
pr_debug("sstate: %d->%d, cstate: %d->%d\n",
oldsstate, info->sstate, oldcstate, info->cstate);
spin_unlock_bh(&nf_pptp_lock);
return ret;
}
/* Returns verdict for packet, or -1 for invalid. */
static int tcp_packet(struct nf_conn *conntrack,
const struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
int pf,
unsigned int hooknum)
{
enum tcp_conntrack new_state, old_state;
enum ip_conntrack_dir dir;
struct tcphdr *th, _tcph;
unsigned long timeout;
unsigned int index;
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
BUG_ON(th == NULL);
write_lock_bh(&tcp_lock);
old_state = conntrack->proto.tcp.state;
dir = CTINFO2DIR(ctinfo);
index = get_conntrack_index(th);
new_state = tcp_conntracks[dir][index][old_state];
switch (new_state) {
case TCP_CONNTRACK_IGNORE:
/* Ignored packets:
*
* a) SYN in ORIGINAL
* b) SYN/ACK in REPLY
* c) ACK in reply direction after initial SYN in original.
*/
if (index == TCP_SYNACK_SET
&& conntrack->proto.tcp.last_index == TCP_SYN_SET
&& conntrack->proto.tcp.last_dir != dir
&& ntohl(th->ack_seq) ==
conntrack->proto.tcp.last_end) {
/* This SYN/ACK acknowledges a SYN that we earlier
* ignored as invalid. This means that the client and
* the server are both in sync, while the firewall is
* not. We kill this session and block the SYN/ACK so
* that the client cannot but retransmit its SYN and
* thus initiate a clean new session.
*/
write_unlock_bh(&tcp_lock);
if (LOG_INVALID(IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: killing out of sync session ");
if (del_timer(&conntrack->timeout))
conntrack->timeout.function((unsigned long)
conntrack);
return -NF_DROP;
}
conntrack->proto.tcp.last_index = index;
conntrack->proto.tcp.last_dir = dir;
conntrack->proto.tcp.last_seq = ntohl(th->seq);
conntrack->proto.tcp.last_end =
segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th);
write_unlock_bh(&tcp_lock);
if (LOG_INVALID(IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid packed ignored ");
return NF_ACCEPT;
case TCP_CONNTRACK_MAX:
/* Invalid packet */
DEBUGP("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n",
dir, get_conntrack_index(th),
old_state);
write_unlock_bh(&tcp_lock);
if (LOG_INVALID(IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid state ");
return -NF_ACCEPT;
case TCP_CONNTRACK_SYN_SENT:
if (old_state < TCP_CONNTRACK_TIME_WAIT)
break;
if ((conntrack->proto.tcp.seen[dir].flags &
IP_CT_TCP_FLAG_CLOSE_INIT)
|| after(ntohl(th->seq),
conntrack->proto.tcp.seen[dir].td_end)) {
/* Attempt to reopen a closed connection.
* Delete this connection and look up again. */
write_unlock_bh(&tcp_lock);
if (del_timer(&conntrack->timeout))
conntrack->timeout.function((unsigned long)
conntrack);
return -NF_REPEAT;
} else {
write_unlock_bh(&tcp_lock);
if (LOG_INVALID(IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL,
NULL, "nf_ct_tcp: invalid SYN");
return -NF_ACCEPT;
}
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
&& ((test_bit(IPS_SEEN_REPLY_BIT, &conntrack->status)
&& conntrack->proto.tcp.last_index == TCP_SYN_SET)
|| (!test_bit(IPS_ASSURED_BIT, &conntrack->status)
&& conntrack->proto.tcp.last_index == TCP_ACK_SET))
&& ntohl(th->ack_seq) == conntrack->proto.tcp.last_end) {
/* RST sent to invalid SYN or ACK we had let through
* at a) and c) above:
*
* a) SYN was in window then
* c) we hold a half-open connection.
*
* Delete our connection entry.
* We skip window checking, because packet might ACK
* segments we ignored. */
goto in_window;
}
/* Just fall through */
default:
/* Keep compilers happy. */
break;
}
if (!tcp_in_window(&conntrack->proto.tcp, dir, index,
skb, dataoff, th, pf)) {
write_unlock_bh(&tcp_lock);
return -NF_ACCEPT;
}
in_window:
/* From now on we have got in-window packets */
conntrack->proto.tcp.last_index = index;
DEBUGP("tcp_conntracks: src=%u.%u.%u.%u:%hu dst=%u.%u.%u.%u:%hu "
"syn=%i ack=%i fin=%i rst=%i old=%i new=%i\n",
NIPQUAD(iph->saddr), ntohs(th->source),
NIPQUAD(iph->daddr), ntohs(th->dest),
(th->syn ? 1 : 0), (th->ack ? 1 : 0),
(th->fin ? 1 : 0), (th->rst ? 1 : 0),
old_state, new_state);
conntrack->proto.tcp.state = new_state;
if (old_state != new_state
&& (new_state == TCP_CONNTRACK_FIN_WAIT
|| new_state == TCP_CONNTRACK_CLOSE))
conntrack->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT;
timeout = conntrack->proto.tcp.retrans >= nf_ct_tcp_max_retrans
&& *tcp_timeouts[new_state] > nf_ct_tcp_timeout_max_retrans
? nf_ct_tcp_timeout_max_retrans : *tcp_timeouts[new_state];
write_unlock_bh(&tcp_lock);
nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, skb);
if (new_state != old_state)
nf_conntrack_event_cache(IPCT_PROTOINFO, skb);
if (!test_bit(IPS_SEEN_REPLY_BIT, &conntrack->status)) {
/* If only reply is a RST, we can consider ourselves not to
have an established connection: this is a fairly common
problem case, so we can delete the conntrack
immediately. --RR */
if (th->rst) {
if (del_timer(&conntrack->timeout))
conntrack->timeout.function((unsigned long)
conntrack);
return NF_ACCEPT;
}
} else if (!test_bit(IPS_ASSURED_BIT, &conntrack->status)
&& (old_state == TCP_CONNTRACK_SYN_RECV
|| old_state == TCP_CONNTRACK_ESTABLISHED)
&& new_state == TCP_CONNTRACK_ESTABLISHED) {
/* Set ASSURED if we see see valid ack in ESTABLISHED
after SYN_RECV or a valid answer for a picked up
connection. */
set_bit(IPS_ASSURED_BIT, &conntrack->status);
nf_conntrack_event_cache(IPCT_STATUS, skb);
}
nf_ct_refresh_acct(conntrack, ctinfo, skb, timeout);
return NF_ACCEPT;
}
static unsigned int ipv6_synproxy_hook(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct synproxy_net *snet = synproxy_pernet(dev_net(in ? : out));
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
struct nf_conn_synproxy *synproxy;
struct synproxy_options opts = {};
const struct ip_ct_tcp *state;
struct tcphdr *th, _th;
__be16 frag_off;
u8 nexthdr;
int thoff;
ct = nf_ct_get(skb, &ctinfo);
if (ct == NULL)
return NF_ACCEPT;
synproxy = nfct_synproxy(ct);
if (synproxy == NULL)
return NF_ACCEPT;
if (nf_is_loopback_packet(skb))
return NF_ACCEPT;
nexthdr = ipv6_hdr(skb)->nexthdr;
thoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
&frag_off);
if (thoff < 0)
return NF_ACCEPT;
th = skb_header_pointer(skb, thoff, sizeof(_th), &_th);
if (th == NULL)
return NF_DROP;
state = &ct->proto.tcp;
switch (state->state) {
case TCP_CONNTRACK_CLOSE:
if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
nf_ct_seqadj_init(ct, ctinfo, synproxy->isn -
ntohl(th->seq) + 1);
break;
}
if (!th->syn || th->ack ||
CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
break;
/* Reopened connection - reset the sequence number and timestamp
* adjustments, they will get initialized once the connection is
* reestablished.
*/
nf_ct_seqadj_init(ct, ctinfo, 0);
synproxy->tsoff = 0;
this_cpu_inc(snet->stats->conn_reopened);
/* fall through */
case TCP_CONNTRACK_SYN_SENT:
if (!synproxy_parse_options(skb, thoff, th, &opts))
return NF_DROP;
if (!th->syn && th->ack &&
CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
/* Keep-Alives are sent with SEG.SEQ = SND.NXT-1,
* therefore we need to add 1 to make the SYN sequence
* number match the one of first SYN.
*/
if (synproxy_recv_client_ack(snet, skb, th, &opts,
ntohl(th->seq) + 1))
this_cpu_inc(snet->stats->cookie_retrans);
return NF_DROP;
}
synproxy->isn = ntohl(th->ack_seq);
if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy->its = opts.tsecr;
break;
case TCP_CONNTRACK_SYN_RECV:
if (!th->syn || !th->ack)
break;
if (!synproxy_parse_options(skb, thoff, th, &opts))
return NF_DROP;
if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy->tsoff = opts.tsval - synproxy->its;
opts.options &= ~(XT_SYNPROXY_OPT_MSS |
XT_SYNPROXY_OPT_WSCALE |
XT_SYNPROXY_OPT_SACK_PERM);
swap(opts.tsval, opts.tsecr);
synproxy_send_server_ack(snet, state, skb, th, &opts);
nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq));
swap(opts.tsval, opts.tsecr);
synproxy_send_client_ack(snet, skb, th, &opts);
consume_skb(skb);
return NF_STOLEN;
default:
break;
}
synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy);
return NF_ACCEPT;
}
static int dump_tcp_header(struct sbuff *m, const struct sk_buff *skb,
u8 proto, int fragment, unsigned int offset,
unsigned int logflags)
{
struct tcphdr _tcph;
const struct tcphdr *th;
/* Max length: 10 "PROTO=TCP " */
sb_add(m, "PROTO=TCP ");
if (fragment)
return 0;
/* Max length: 25 "INCOMPLETE [65535 bytes] " */
th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
if (th == NULL) {
sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset);
return 1;
}
/* Max length: 20 "SPT=65535 DPT=65535 " */
sb_add(m, "SPT=%u DPT=%u ", ntohs(th->source), ntohs(th->dest));
/* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */
if (logflags & XT_LOG_TCPSEQ)
sb_add(m, "SEQ=%u ACK=%u ", ntohl(th->seq), ntohl(th->ack_seq));
/* Max length: 13 "WINDOW=65535 " */
sb_add(m, "WINDOW=%u ", ntohs(th->window));
/* Max length: 9 "RES=0x3C " */
sb_add(m, "RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) &
TCP_RESERVED_BITS) >> 22));
/* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */
if (th->cwr)
sb_add(m, "CWR ");
if (th->ece)
sb_add(m, "ECE ");
if (th->urg)
sb_add(m, "URG ");
if (th->ack)
sb_add(m, "ACK ");
if (th->psh)
sb_add(m, "PSH ");
if (th->rst)
sb_add(m, "RST ");
if (th->syn)
sb_add(m, "SYN ");
if (th->fin)
sb_add(m, "FIN ");
/* Max length: 11 "URGP=65535 " */
sb_add(m, "URGP=%u ", ntohs(th->urg_ptr));
if ((logflags & XT_LOG_TCPOPT) && th->doff*4 > sizeof(struct tcphdr)) {
u_int8_t _opt[60 - sizeof(struct tcphdr)];
const u_int8_t *op;
unsigned int i;
unsigned int optsize = th->doff*4 - sizeof(struct tcphdr);
op = skb_header_pointer(skb, offset + sizeof(struct tcphdr),
optsize, _opt);
if (op == NULL) {
sb_add(m, "OPT (TRUNCATED)");
return 1;
}
/* Max length: 127 "OPT (" 15*4*2chars ") " */
sb_add(m, "OPT (");
for (i = 0; i < optsize; i++)
sb_add(m, "%02X", op[i]);
sb_add(m, ") ");
}
return 0;
}
/* Called when a new connection for this protocol found. */
static int tcp_new(struct nf_conn *conntrack,
const struct sk_buff *skb,
unsigned int dataoff)
{
enum tcp_conntrack new_state;
struct tcphdr *th, _tcph;
#ifdef DEBUGP_VARS
struct ip_ct_tcp_state *sender = &conntrack->proto.tcp.seen[0];
struct ip_ct_tcp_state *receiver = &conntrack->proto.tcp.seen[1];
#endif
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
BUG_ON(th == NULL);
/* Don't need lock here: this conntrack not in circulation yet */
new_state
= tcp_conntracks[0][get_conntrack_index(th)]
[TCP_CONNTRACK_NONE];
/* Invalid: delete conntrack */
if (new_state >= TCP_CONNTRACK_MAX) {
DEBUGP("nf_ct_tcp: invalid new deleting.\n");
return 0;
}
if (new_state == TCP_CONNTRACK_SYN_SENT) {
/* SYN packet */
conntrack->proto.tcp.seen[0].td_end =
segment_seq_plus_len(ntohl(th->seq), skb->len,
dataoff, th);
conntrack->proto.tcp.seen[0].td_maxwin = ntohs(th->window);
if (conntrack->proto.tcp.seen[0].td_maxwin == 0)
conntrack->proto.tcp.seen[0].td_maxwin = 1;
conntrack->proto.tcp.seen[0].td_maxend =
conntrack->proto.tcp.seen[0].td_end;
tcp_options(skb, dataoff, th, &conntrack->proto.tcp.seen[0]);
conntrack->proto.tcp.seen[1].flags = 0;
} else if (nf_ct_tcp_loose == 0) {
/* Don't try to pick up connections. */
return 0;
} else {
/*
* We are in the middle of a connection,
* its history is lost for us.
* Let's try to use the data from the packet.
*/
conntrack->proto.tcp.seen[0].td_end =
segment_seq_plus_len(ntohl(th->seq), skb->len,
dataoff, th);
conntrack->proto.tcp.seen[0].td_maxwin = ntohs(th->window);
if (conntrack->proto.tcp.seen[0].td_maxwin == 0)
conntrack->proto.tcp.seen[0].td_maxwin = 1;
conntrack->proto.tcp.seen[0].td_maxend =
conntrack->proto.tcp.seen[0].td_end +
conntrack->proto.tcp.seen[0].td_maxwin;
conntrack->proto.tcp.seen[0].td_scale = 0;
/* We assume SACK and liberal window checking to handle
* window scaling */
conntrack->proto.tcp.seen[0].flags =
conntrack->proto.tcp.seen[1].flags = IP_CT_TCP_FLAG_SACK_PERM |
IP_CT_TCP_FLAG_BE_LIBERAL;
}
conntrack->proto.tcp.seen[1].td_end = 0;
conntrack->proto.tcp.seen[1].td_maxend = 0;
conntrack->proto.tcp.seen[1].td_maxwin = 1;
conntrack->proto.tcp.seen[1].td_scale = 0;
/* tcp_packet will set them */
conntrack->proto.tcp.state = TCP_CONNTRACK_NONE;
conntrack->proto.tcp.last_index = TCP_NONE_SET;
DEBUGP("tcp_new: sender end=%u maxend=%u maxwin=%u scale=%i "
"receiver end=%u maxend=%u maxwin=%u scale=%i\n",
sender->td_end, sender->td_maxend, sender->td_maxwin,
sender->td_scale,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
return 1;
}
int
ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rt6_info *rt; /* Route to the other host */
int mtu;
int local;
EnterFunction(10);
/* check if it is a connection of no-client-port */
if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
__be16 _pt, *p;
p = skb_header_pointer(skb, sizeof(struct ipv6hdr),
sizeof(_pt), &_pt);
if (p == NULL)
goto tx_error;
ip_vs_conn_fill_cport(cp, *p);
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
}
if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
0, (IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR))))
goto tx_error_icmp;
local = __ip_vs_is_local_route6(rt);
/*
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct)) {
IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to local address");
goto tx_error_put;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) {
IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to loopback address");
goto tx_error_put;
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if (skb->len > mtu && !skb_is_gso(skb)) {
if (!skb->dev) {
struct net *net = dev_net(skb_dst(skb)->dev);
skb->dev = net->loopback_dev;
}
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP_VS_DBG_RL_PKT(0, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): frag needed for");
goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, sizeof(struct ipv6hdr)))
goto tx_error_put;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
/* mangle the packet */
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
goto tx_error;
ipv6_hdr(skb)->daddr = cp->daddr.in6;
if (!local || !skb->dev) {
/* drop the old route when skb is not shared */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
/* destined to loopback, do we need to change route? */
dst_release(&rt->dst);
}
IP_VS_DBG_PKT(10, AF_INET6, pp, skb, 0, "After DNAT");
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
MTU problem. */
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp, local);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
LeaveFunction(10);
kfree_skb(skb);
return NF_STOLEN;
tx_error_put:
dst_release(&rt->dst);
goto tx_error;
}
static int get_tpkt_data(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo,
unsigned char **data, int *datalen, int *dataoff)
{
struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
int dir = CTINFO2DIR(ctinfo);
const struct tcphdr *th;
struct tcphdr _tcph;
int tcpdatalen;
int tcpdataoff;
unsigned char *tpkt;
int tpktlen;
int tpktoff;
#ifdef CONFIG_HTC_NETWORK_MODIFY
if (IS_ERR(info) || (!info))
printk(KERN_ERR "[NET] info is NULL in %s!\n", __func__);
#endif
th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph);
if (th == NULL)
return 0;
tcpdataoff = protoff + th->doff * 4;
tcpdatalen = skb->len - tcpdataoff;
if (tcpdatalen <= 0)
goto clear_out;
if (*data == NULL) {
tpkt = skb_header_pointer(skb, tcpdataoff, tcpdatalen,
h323_buffer);
BUG_ON(tpkt == NULL);
if (tcpdatalen < 4 || tpkt[0] != 0x03 || tpkt[1] != 0) {
if (info->tpkt_len[dir] > 0) {
pr_debug("nf_ct_h323: previous packet "
"indicated separate TPKT data of %hu "
"bytes\n", info->tpkt_len[dir]);
if (info->tpkt_len[dir] <= tcpdatalen) {
*data = tpkt;
*datalen = info->tpkt_len[dir];
*dataoff = 0;
goto out;
}
pr_debug("nf_ct_h323: fragmented TPKT\n");
goto clear_out;
}
return 0;
}
tpktoff = 0;
} else {
tpktoff = *dataoff + *datalen;
tcpdatalen -= tpktoff;
if (tcpdatalen <= 4)
goto clear_out;
tpkt = *data + *datalen;
if (tpkt[0] != 0x03 || tpkt[1] != 0)
goto clear_out;
}
tpktlen = tpkt[2] * 256 + tpkt[3];
if (tpktlen < 4)
goto clear_out;
if (tpktlen > tcpdatalen) {
if (tcpdatalen == 4) {
pr_debug("nf_ct_h323: separate TPKT header indicates "
"there will be TPKT data of %hu bytes\n",
tpktlen - 4);
info->tpkt_len[dir] = tpktlen - 4;
return 0;
}
pr_debug("nf_ct_h323: incomplete TPKT (fragmented?)\n");
goto clear_out;
}
*data = tpkt + 4;
*datalen = tpktlen - 4;
*dataoff = tpktoff + 4;
out:
info->tpkt_len[dir] = 0;
return 1;
clear_out:
info->tpkt_len[dir] = 0;
return 0;
}
static bool
ipv6header_mt6(const struct sk_buff *skb, const struct net_device *in,
const struct net_device *out, const struct xt_match *match,
const void *matchinfo, int offset, unsigned int protoff,
bool *hotdrop)
{
const struct ip6t_ipv6header_info *info = matchinfo;
unsigned int temp;
int len;
u8 nexthdr;
unsigned int ptr;
/* Make sure this isn't an evil packet */
/* type of the 1st exthdr */
nexthdr = ipv6_hdr(skb)->nexthdr;
/* pointer to the 1st exthdr */
ptr = sizeof(struct ipv6hdr);
/* available length */
len = skb->len - ptr;
temp = 0;
while (ip6t_ext_hdr(nexthdr)) {
struct ipv6_opt_hdr _hdr, *hp;
int hdrlen;
/* Is there enough space for the next ext header? */
if (len < (int)sizeof(struct ipv6_opt_hdr))
return false;
/* No more exthdr -> evaluate */
if (nexthdr == NEXTHDR_NONE) {
temp |= MASK_NONE;
break;
}
/* ESP -> evaluate */
if (nexthdr == NEXTHDR_ESP) {
temp |= MASK_ESP;
break;
}
hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr);
BUG_ON(hp == NULL);
/* Calculate the header length */
if (nexthdr == NEXTHDR_FRAGMENT)
hdrlen = 8;
else if (nexthdr == NEXTHDR_AUTH)
hdrlen = (hp->hdrlen + 2) << 2;
else
hdrlen = ipv6_optlen(hp);
/* set the flag */
switch (nexthdr) {
case NEXTHDR_HOP:
temp |= MASK_HOPOPTS;
break;
case NEXTHDR_ROUTING:
temp |= MASK_ROUTING;
break;
case NEXTHDR_FRAGMENT:
temp |= MASK_FRAGMENT;
break;
case NEXTHDR_AUTH:
temp |= MASK_AH;
break;
case NEXTHDR_DEST:
temp |= MASK_DSTOPTS;
break;
default:
return false;
break;
}
nexthdr = hp->nexthdr;
len -= hdrlen;
ptr += hdrlen;
if (ptr > skb->len)
break;
}
if (nexthdr != NEXTHDR_NONE && nexthdr != NEXTHDR_ESP)
temp |= MASK_PROTO;
if (info->modeflag)
return !((temp ^ info->matchflags ^ info->invflags)
& info->matchflags);
else {
if (info->invflags)
return temp != info->matchflags;
else
return temp == info->matchflags;
}
}
/*
* NAT transmitter (only for outside-to-inside nat forwarding)
* Not used for related ICMP
*/
int
ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rtable *rt; /* Route to the other host */
int mtu;
struct iphdr *iph = ip_hdr(skb);
int local;
EnterFunction(10);
/* check if it is a connection of no-client-port */
if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
__be16 _pt, *p;
p = skb_header_pointer(skb, iph->ihl*4, sizeof(_pt), &_pt);
if (p == NULL)
goto tx_error;
ip_vs_conn_fill_cport(cp, *p);
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
}
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 |
IP_VS_RT_MODE_RDR, NULL)))
goto tx_error_icmp;
local = rt->rt_flags & RTCF_LOCAL;
/*
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct)) {
IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0,
"ip_vs_nat_xmit(): "
"stopping DNAT to local address");
goto tx_error_put;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && ipv4_is_loopback(cp->daddr.ip) &&
rt_is_input_route(skb_rtable(skb))) {
IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): "
"stopping DNAT to loopback address");
goto tx_error_put;
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) &&
!skb_is_gso(skb)) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0,
"ip_vs_nat_xmit(): frag needed for");
goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, sizeof(struct iphdr)))
goto tx_error_put;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
/* mangle the packet */
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
goto tx_error_put;
ip_hdr(skb)->daddr = cp->daddr.ip;
ip_send_check(ip_hdr(skb));
if (!local) {
/* drop old route */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
ip_rt_put(rt);
/*
* Some IPv4 replies get local address from routes,
* not from iph, so while we DNAT after routing
* we need this second input/output route.
*/
if (!__ip_vs_reroute_locally(skb))
goto tx_error;
}
IP_VS_DBG_PKT(10, AF_INET, pp, skb, 0, "After DNAT");
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
MTU problem. */
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_put:
ip_rt_put(rt);
goto tx_error;
}
/* Send RST reply */
static void send_reset(struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
const struct iphdr *oiph;
struct iphdr *niph;
const struct tcphdr *oth;
struct tcphdr _otcph, *tcph;
/* IP header checks: fragment. */
if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
return;
oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
sizeof(_otcph), &_otcph);
if (oth == NULL)
return;
/* No RST for RST. */
if (oth->rst)
return;
if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
return;
/* Check checksum */
if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
return;
oiph = ip_hdr(oldskb);
nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
LL_MAX_HEADER, GFP_ATOMIC);
if (!nskb)
return;
skb_reserve(nskb, LL_MAX_HEADER);
skb_reset_network_header(nskb);
niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
niph->version = 4;
niph->ihl = sizeof(struct iphdr) / 4;
niph->tos = 0;
niph->id = 0;
niph->frag_off = htons(IP_DF);
niph->protocol = IPPROTO_TCP;
niph->check = 0;
niph->saddr = oiph->daddr;
niph->daddr = oiph->saddr;
skb_reset_transport_header(nskb);
tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
memset(tcph, 0, sizeof(*tcph));
tcph->source = oth->dest;
tcph->dest = oth->source;
tcph->doff = sizeof(struct tcphdr) / 4;
if (oth->ack)
tcph->seq = oth->ack_seq;
else {
tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
oldskb->len - ip_hdrlen(oldskb) -
(oth->doff << 2));
tcph->ack = 1;
}
tcph->rst = 1;
tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
niph->daddr, 0);
nskb->ip_summed = CHECKSUM_PARTIAL;
nskb->csum_start = (unsigned char *)tcph - nskb->head;
nskb->csum_offset = offsetof(struct tcphdr, check);
/* ip_route_me_harder expects skb->dst to be set */
skb_dst_set_noref(nskb, skb_dst(oldskb));
nskb->protocol = htons(ETH_P_IP);
if (ip_route_me_harder(nskb, RTN_UNSPEC))
goto free_nskb;
niph->ttl = ip4_dst_hoplimit(skb_dst(nskb));
/* "Never happens" */
if (nskb->len > dst_mtu(skb_dst(nskb)))
goto free_nskb;
nf_ct_attach(nskb, oldskb);
ip_local_out(nskb);
return;
free_nskb:
kfree_skb(nskb);
}
static int
tcp_match(const struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
const struct xt_match *match,
const void *matchinfo,
int offset,
unsigned int protoff,
int *hotdrop)
{
struct tcphdr _tcph, *th;
const struct xt_tcp *tcpinfo = matchinfo;
if (offset) {
/* To quote Alan:
Don't allow a fragment of TCP 8 bytes in. Nobody normal
causes this. Its a cracker trying to break in by doing a
flag overwrite to pass the direction checks.
*/
if (offset == 1) {
duprintf("Dropping evil TCP offset=1 frag.\n");
*hotdrop = 1;
}
/* Must not be a fragment. */
return 0;
}
#define FWINVTCP(bool,invflg) ((bool) ^ !!(tcpinfo->invflags & invflg))
th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph);
if (th == NULL) {
/* We've been asked to examine this packet, and we
can't. Hence, no choice but to drop. */
duprintf("Dropping evil TCP offset=0 tinygram.\n");
*hotdrop = 1;
return 0;
}
if (!port_match(tcpinfo->spts[0], tcpinfo->spts[1],
ntohs(th->source),
!!(tcpinfo->invflags & XT_TCP_INV_SRCPT)))
return 0;
if (!port_match(tcpinfo->dpts[0], tcpinfo->dpts[1],
ntohs(th->dest),
!!(tcpinfo->invflags & XT_TCP_INV_DSTPT)))
return 0;
if (!FWINVTCP((((unsigned char *)th)[13] & tcpinfo->flg_mask)
== tcpinfo->flg_cmp,
XT_TCP_INV_FLAGS))
return 0;
if (tcpinfo->option) {
if (th->doff * 4 < sizeof(_tcph)) {
*hotdrop = 1;
return 0;
}
if (!tcp_find_option(tcpinfo->option, skb, protoff,
th->doff*4 - sizeof(_tcph),
tcpinfo->invflags & XT_TCP_INV_OPTION,
hotdrop))
return 0;
}
return 1;
}
bool
synproxy_parse_options(const struct sk_buff *skb, unsigned int doff,
const struct tcphdr *th, struct synproxy_options *opts)
{
int length = (th->doff * 4) - sizeof(*th);
u8 buf[40], *ptr;
ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf);
if (ptr == NULL)
return false;
opts->options = 0;
while (length > 0) {
int opcode = *ptr++;
int opsize;
switch (opcode) {
case TCPOPT_EOL:
return true;
case TCPOPT_NOP:
length--;
continue;
default:
opsize = *ptr++;
if (opsize < 2)
return true;
if (opsize > length)
return true;
switch (opcode) {
case TCPOPT_MSS:
if (opsize == TCPOLEN_MSS) {
opts->mss = get_unaligned_be16(ptr);
opts->options |= XT_SYNPROXY_OPT_MSS;
}
break;
case TCPOPT_WINDOW:
if (opsize == TCPOLEN_WINDOW) {
opts->wscale = *ptr;
if (opts->wscale > 14)
opts->wscale = 14;
opts->options |= XT_SYNPROXY_OPT_WSCALE;
}
break;
case TCPOPT_TIMESTAMP:
if (opsize == TCPOLEN_TIMESTAMP) {
opts->tsval = get_unaligned_be32(ptr);
opts->tsecr = get_unaligned_be32(ptr + 4);
opts->options |= XT_SYNPROXY_OPT_TIMESTAMP;
}
break;
case TCPOPT_SACK_PERM:
if (opsize == TCPOLEN_SACK_PERM)
opts->options |= XT_SYNPROXY_OPT_SACK_PERM;
break;
}
ptr += opsize - 2;
length -= opsize;
}
}
return true;
}
/* One level of recursion won't kill us */
static void dump_ipv4_packet(struct sbuff *m,
const struct nf_loginfo *info,
const struct sk_buff *skb,
unsigned int iphoff)
{
struct iphdr _iph;
const struct iphdr *ih;
unsigned int logflags;
if (info->type == NF_LOG_TYPE_LOG)
logflags = info->u.log.logflags;
else
logflags = NF_LOG_MASK;
ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph);
if (ih == NULL) {
sb_add(m, "TRUNCATED");
return;
}
/* Important fields:
* TOS, len, DF/MF, fragment offset, TTL, src, dst, options. */
/* Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " */
sb_add(m, "SRC=%pI4 DST=%pI4 ",
&ih->saddr, &ih->daddr);
/* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */
sb_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ",
ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK,
ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id));
/* Max length: 6 "CE DF MF " */
if (ntohs(ih->frag_off) & IP_CE)
sb_add(m, "CE ");
if (ntohs(ih->frag_off) & IP_DF)
sb_add(m, "DF ");
if (ntohs(ih->frag_off) & IP_MF)
sb_add(m, "MF ");
/* Max length: 11 "FRAG:65535 " */
if (ntohs(ih->frag_off) & IP_OFFSET)
sb_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET);
if ((logflags & XT_LOG_IPOPT) &&
ih->ihl * 4 > sizeof(struct iphdr)) {
const unsigned char *op;
unsigned char _opt[4 * 15 - sizeof(struct iphdr)];
unsigned int i, optsize;
optsize = ih->ihl * 4 - sizeof(struct iphdr);
op = skb_header_pointer(skb, iphoff+sizeof(_iph),
optsize, _opt);
if (op == NULL) {
sb_add(m, "TRUNCATED");
return;
}
/* Max length: 127 "OPT (" 15*4*2chars ") " */
sb_add(m, "OPT (");
for (i = 0; i < optsize; i++)
sb_add(m, "%02X", op[i]);
sb_add(m, ") ");
}
switch (ih->protocol) {
case IPPROTO_TCP:
if (dump_tcp_header(m, skb, ih->protocol,
ntohs(ih->frag_off) & IP_OFFSET,
iphoff+ih->ihl*4, logflags))
return;
break;
case IPPROTO_UDP:
case IPPROTO_UDPLITE:
if (dump_udp_header(m, skb, ih->protocol,
ntohs(ih->frag_off) & IP_OFFSET,
iphoff+ih->ihl*4))
return;
break;
case IPPROTO_ICMP: {
struct icmphdr _icmph;
const struct icmphdr *ich;
static const size_t required_len[NR_ICMP_TYPES+1]
= { [ICMP_ECHOREPLY] = 4,
[ICMP_DEST_UNREACH]
= 8 + sizeof(struct iphdr),
[ICMP_SOURCE_QUENCH]
= 8 + sizeof(struct iphdr),
[ICMP_REDIRECT]
= 8 + sizeof(struct iphdr),
[ICMP_ECHO] = 4,
[ICMP_TIME_EXCEEDED]
= 8 + sizeof(struct iphdr),
[ICMP_PARAMETERPROB]
= 8 + sizeof(struct iphdr),
[ICMP_TIMESTAMP] = 20,
[ICMP_TIMESTAMPREPLY] = 20,
[ICMP_ADDRESS] = 12,
[ICMP_ADDRESSREPLY] = 12 };
/* Max length: 11 "PROTO=ICMP " */
sb_add(m, "PROTO=ICMP ");
if (ntohs(ih->frag_off) & IP_OFFSET)
break;
/* Max length: 25 "INCOMPLETE [65535 bytes] " */
ich = skb_header_pointer(skb, iphoff + ih->ihl * 4,
sizeof(_icmph), &_icmph);
if (ich == NULL) {
sb_add(m, "INCOMPLETE [%u bytes] ",
skb->len - iphoff - ih->ihl*4);
break;
}
/* Max length: 18 "TYPE=255 CODE=255 " */
sb_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code);
/* Max length: 25 "INCOMPLETE [65535 bytes] " */
if (ich->type <= NR_ICMP_TYPES &&
required_len[ich->type] &&
skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) {
sb_add(m, "INCOMPLETE [%u bytes] ",
skb->len - iphoff - ih->ihl*4);
break;
}
switch (ich->type) {
case ICMP_ECHOREPLY:
case ICMP_ECHO:
/* Max length: 19 "ID=65535 SEQ=65535 " */
sb_add(m, "ID=%u SEQ=%u ",
ntohs(ich->un.echo.id),
ntohs(ich->un.echo.sequence));
break;
case ICMP_PARAMETERPROB:
/* Max length: 14 "PARAMETER=255 " */
sb_add(m, "PARAMETER=%u ",
ntohl(ich->un.gateway) >> 24);
break;
case ICMP_REDIRECT:
/* Max length: 24 "GATEWAY=255.255.255.255 " */
sb_add(m, "GATEWAY=%pI4 ", &ich->un.gateway);
/* Fall through */
case ICMP_DEST_UNREACH:
case ICMP_SOURCE_QUENCH:
case ICMP_TIME_EXCEEDED:
/* Max length: 3+maxlen */
if (!iphoff) { /* Only recurse once. */
sb_add(m, "[");
dump_ipv4_packet(m, info, skb,
iphoff + ih->ihl*4+sizeof(_icmph));
sb_add(m, "] ");
}
/* Max length: 10 "MTU=65535 " */
if (ich->type == ICMP_DEST_UNREACH &&
ich->code == ICMP_FRAG_NEEDED)
sb_add(m, "MTU=%u ", ntohs(ich->un.frag.mtu));
}
break;
}
/* Max Length */
case IPPROTO_AH: {
struct ip_auth_hdr _ahdr;
const struct ip_auth_hdr *ah;
if (ntohs(ih->frag_off) & IP_OFFSET)
break;
/* Max length: 9 "PROTO=AH " */
sb_add(m, "PROTO=AH ");
/* Max length: 25 "INCOMPLETE [65535 bytes] " */
ah = skb_header_pointer(skb, iphoff+ih->ihl*4,
sizeof(_ahdr), &_ahdr);
if (ah == NULL) {
sb_add(m, "INCOMPLETE [%u bytes] ",
skb->len - iphoff - ih->ihl*4);
break;
}
/* Length: 15 "SPI=0xF1234567 " */
sb_add(m, "SPI=0x%x ", ntohl(ah->spi));
break;
}
case IPPROTO_ESP: {
struct ip_esp_hdr _esph;
const struct ip_esp_hdr *eh;
/* Max length: 10 "PROTO=ESP " */
sb_add(m, "PROTO=ESP ");
if (ntohs(ih->frag_off) & IP_OFFSET)
break;
/* Max length: 25 "INCOMPLETE [65535 bytes] " */
eh = skb_header_pointer(skb, iphoff+ih->ihl*4,
sizeof(_esph), &_esph);
if (eh == NULL) {
sb_add(m, "INCOMPLETE [%u bytes] ",
skb->len - iphoff - ih->ihl*4);
break;
}
/* Length: 15 "SPI=0xF1234567 " */
sb_add(m, "SPI=0x%x ", ntohl(eh->spi));
break;
}
/* Max length: 10 "PROTO 255 " */
default:
sb_add(m, "PROTO=%u ", ih->protocol);
}
/* Max length: 15 "UID=4294967295 " */
if ((logflags & XT_LOG_UID) && !iphoff)
dump_sk_uid_gid(m, skb->sk);
/* Max length: 16 "MARK=0xFFFFFFFF " */
if (!iphoff && skb->mark)
sb_add(m, "MARK=0x%x ", skb->mark);
/* Proto Max log string length */
/* IP: 40+46+6+11+127 = 230 */
/* TCP: 10+max(25,20+30+13+9+32+11+127) = 252 */
/* UDP: 10+max(25,20) = 35 */
/* UDPLITE: 14+max(25,20) = 39 */
/* ICMP: 11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */
/* ESP: 10+max(25)+15 = 50 */
/* AH: 9+max(25)+15 = 49 */
/* unknown: 10 */
/* (ICMP allows recursion one level deep) */
/* maxlen = IP + ICMP + IP + max(TCP,UDP,ICMP,unknown) */
/* maxlen = 230+ 91 + 230 + 252 = 803 */
}
static bool
ebt_arp_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct ebt_arp_info *info = par->matchinfo;
const struct arphdr *ah;
struct arphdr _arph;
ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
if (ah == NULL)
return false;
if (info->bitmask & EBT_ARP_OPCODE && FWINV(info->opcode !=
ah->ar_op, EBT_ARP_OPCODE))
return false;
if (info->bitmask & EBT_ARP_HTYPE && FWINV(info->htype !=
ah->ar_hrd, EBT_ARP_HTYPE))
return false;
if (info->bitmask & EBT_ARP_PTYPE && FWINV(info->ptype !=
ah->ar_pro, EBT_ARP_PTYPE))
return false;
if (info->bitmask & (EBT_ARP_SRC_IP | EBT_ARP_DST_IP | EBT_ARP_GRAT)) {
const __be32 *sap, *dap;
__be32 saddr, daddr;
if (ah->ar_pln != sizeof(__be32) || ah->ar_pro != htons(ETH_P_IP))
return false;
sap = skb_header_pointer(skb, sizeof(struct arphdr) +
ah->ar_hln, sizeof(saddr),
&saddr);
if (sap == NULL)
return false;
dap = skb_header_pointer(skb, sizeof(struct arphdr) +
2*ah->ar_hln+sizeof(saddr),
sizeof(daddr), &daddr);
if (dap == NULL)
return false;
if (info->bitmask & EBT_ARP_SRC_IP &&
FWINV(info->saddr != (*sap & info->smsk), EBT_ARP_SRC_IP))
return false;
if (info->bitmask & EBT_ARP_DST_IP &&
FWINV(info->daddr != (*dap & info->dmsk), EBT_ARP_DST_IP))
return false;
if (info->bitmask & EBT_ARP_GRAT &&
FWINV(*dap != *sap, EBT_ARP_GRAT))
return false;
}
if (info->bitmask & (EBT_ARP_SRC_MAC | EBT_ARP_DST_MAC)) {
const unsigned char *mp;
unsigned char _mac[ETH_ALEN];
uint8_t verdict, i;
if (ah->ar_hln != ETH_ALEN || ah->ar_hrd != htons(ARPHRD_ETHER))
return false;
if (info->bitmask & EBT_ARP_SRC_MAC) {
mp = skb_header_pointer(skb, sizeof(struct arphdr),
sizeof(_mac), &_mac);
if (mp == NULL)
return false;
verdict = 0;
for (i = 0; i < 6; i++)
verdict |= (mp[i] ^ info->smaddr[i]) &
info->smmsk[i];
if (FWINV(verdict != 0, EBT_ARP_SRC_MAC))
return false;
}
if (info->bitmask & EBT_ARP_DST_MAC) {
mp = skb_header_pointer(skb, sizeof(struct arphdr) +
ah->ar_hln + ah->ar_pln,
sizeof(_mac), &_mac);
if (mp == NULL)
return false;
verdict = 0;
for (i = 0; i < 6; i++)
verdict |= (mp[i] ^ info->dmaddr[i]) &
info->dmmsk[i];
if (FWINV(verdict != 0, EBT_ARP_DST_MAC))
return false;
}
}
return true;
}
/* One level of recursion won't kill us */
static void dump_ipv6_packet(struct sbuff *m,
const struct nf_loginfo *info,
const struct sk_buff *skb, unsigned int ip6hoff,
int recurse)
{
u_int8_t currenthdr;
int fragment;
struct ipv6hdr _ip6h;
const struct ipv6hdr *ih;
unsigned int ptr;
unsigned int hdrlen = 0;
unsigned int logflags;
if (info->type == NF_LOG_TYPE_LOG)
logflags = info->u.log.logflags;
else
logflags = NF_LOG_MASK;
ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h);
if (ih == NULL) {
sb_add(m, "TRUNCATED");
return;
}
/* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */
sb_add(m, "SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr);
/* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */
sb_add(m, "LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ",
ntohs(ih->payload_len) + sizeof(struct ipv6hdr),
(ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20,
ih->hop_limit,
(ntohl(*(__be32 *)ih) & 0x000fffff));
fragment = 0;
ptr = ip6hoff + sizeof(struct ipv6hdr);
currenthdr = ih->nexthdr;
while (currenthdr != NEXTHDR_NONE && ip6t_ext_hdr(currenthdr)) {
struct ipv6_opt_hdr _hdr;
const struct ipv6_opt_hdr *hp;
hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr);
if (hp == NULL) {
sb_add(m, "TRUNCATED");
return;
}
/* Max length: 48 "OPT (...) " */
if (logflags & XT_LOG_IPOPT)
sb_add(m, "OPT ( ");
switch (currenthdr) {
case IPPROTO_FRAGMENT: {
struct frag_hdr _fhdr;
const struct frag_hdr *fh;
sb_add(m, "FRAG:");
fh = skb_header_pointer(skb, ptr, sizeof(_fhdr),
&_fhdr);
if (fh == NULL) {
sb_add(m, "TRUNCATED ");
return;
}
/* Max length: 6 "65535 " */
sb_add(m, "%u ", ntohs(fh->frag_off) & 0xFFF8);
/* Max length: 11 "INCOMPLETE " */
if (fh->frag_off & htons(0x0001))
sb_add(m, "INCOMPLETE ");
sb_add(m, "ID:%08x ", ntohl(fh->identification));
if (ntohs(fh->frag_off) & 0xFFF8)
fragment = 1;
hdrlen = 8;
break;
}
case IPPROTO_DSTOPTS:
case IPPROTO_ROUTING:
case IPPROTO_HOPOPTS:
if (fragment) {
if (logflags & XT_LOG_IPOPT)
sb_add(m, ")");
return;
}
hdrlen = ipv6_optlen(hp);
break;
/* Max Length */
case IPPROTO_AH:
if (logflags & XT_LOG_IPOPT) {
struct ip_auth_hdr _ahdr;
const struct ip_auth_hdr *ah;
/* Max length: 3 "AH " */
sb_add(m, "AH ");
if (fragment) {
sb_add(m, ")");
return;
}
ah = skb_header_pointer(skb, ptr, sizeof(_ahdr),
&_ahdr);
if (ah == NULL) {
/*
* Max length: 26 "INCOMPLETE [65535
* bytes] )"
*/
sb_add(m, "INCOMPLETE [%u bytes] )",
skb->len - ptr);
return;
}
/* Length: 15 "SPI=0xF1234567 */
sb_add(m, "SPI=0x%x ", ntohl(ah->spi));
}
hdrlen = (hp->hdrlen+2)<<2;
break;
case IPPROTO_ESP:
if (logflags & XT_LOG_IPOPT) {
struct ip_esp_hdr _esph;
const struct ip_esp_hdr *eh;
/* Max length: 4 "ESP " */
sb_add(m, "ESP ");
if (fragment) {
sb_add(m, ")");
return;
}
/*
* Max length: 26 "INCOMPLETE [65535 bytes] )"
*/
eh = skb_header_pointer(skb, ptr, sizeof(_esph),
&_esph);
if (eh == NULL) {
sb_add(m, "INCOMPLETE [%u bytes] )",
skb->len - ptr);
return;
}
/* Length: 16 "SPI=0xF1234567 )" */
sb_add(m, "SPI=0x%x )", ntohl(eh->spi));
}
return;
default:
/* Max length: 20 "Unknown Ext Hdr 255" */
sb_add(m, "Unknown Ext Hdr %u", currenthdr);
return;
}
if (logflags & XT_LOG_IPOPT)
sb_add(m, ") ");
currenthdr = hp->nexthdr;
ptr += hdrlen;
}
switch (currenthdr) {
case IPPROTO_TCP:
if (dump_tcp_header(m, skb, currenthdr, fragment, ptr,
logflags))
return;
break;
case IPPROTO_UDP:
case IPPROTO_UDPLITE:
if (dump_udp_header(m, skb, currenthdr, fragment, ptr))
return;
break;
case IPPROTO_ICMPV6: {
struct icmp6hdr _icmp6h;
const struct icmp6hdr *ic;
/* Max length: 13 "PROTO=ICMPv6 " */
sb_add(m, "PROTO=ICMPv6 ");
if (fragment)
break;
/* Max length: 25 "INCOMPLETE [65535 bytes] " */
ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h);
if (ic == NULL) {
sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr);
return;
}
/* Max length: 18 "TYPE=255 CODE=255 " */
sb_add(m, "TYPE=%u CODE=%u ", ic->icmp6_type, ic->icmp6_code);
switch (ic->icmp6_type) {
case ICMPV6_ECHO_REQUEST:
case ICMPV6_ECHO_REPLY:
/* Max length: 19 "ID=65535 SEQ=65535 " */
sb_add(m, "ID=%u SEQ=%u ",
ntohs(ic->icmp6_identifier),
ntohs(ic->icmp6_sequence));
break;
case ICMPV6_MGM_QUERY:
case ICMPV6_MGM_REPORT:
case ICMPV6_MGM_REDUCTION:
break;
case ICMPV6_PARAMPROB:
/* Max length: 17 "POINTER=ffffffff " */
sb_add(m, "POINTER=%08x ", ntohl(ic->icmp6_pointer));
/* Fall through */
case ICMPV6_DEST_UNREACH:
case ICMPV6_PKT_TOOBIG:
case ICMPV6_TIME_EXCEED:
/* Max length: 3+maxlen */
if (recurse) {
sb_add(m, "[");
dump_ipv6_packet(m, info, skb,
ptr + sizeof(_icmp6h), 0);
sb_add(m, "] ");
}
/* Max length: 10 "MTU=65535 " */
if (ic->icmp6_type == ICMPV6_PKT_TOOBIG)
sb_add(m, "MTU=%u ", ntohl(ic->icmp6_mtu));
}
break;
}
/* Max length: 10 "PROTO=255 " */
default:
sb_add(m, "PROTO=%u ", currenthdr);
}
/* Max length: 15 "UID=4294967295 " */
if ((logflags & XT_LOG_UID) && recurse)
dump_sk_uid_gid(m, skb->sk);
/* Max length: 16 "MARK=0xFFFFFFFF " */
if (!recurse && skb->mark)
sb_add(m, "MARK=0x%x ", skb->mark);
}
/* Send RST reply */
static void send_reset(struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
const struct iphdr *oiph;
struct iphdr *niph;
const struct tcphdr *oth;
struct tcphdr _otcph, *tcph;
unsigned int addr_type;
/* IP header checks: fragment. */
if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
return;
oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
sizeof(_otcph), &_otcph);
if (oth == NULL)
return;
/* No RST for RST. */
if (oth->rst)
return;
/* Check checksum */
if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
return;
oiph = ip_hdr(oldskb);
nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
LL_MAX_HEADER, GFP_ATOMIC);
if (!nskb)
return;
skb_reserve(nskb, LL_MAX_HEADER);
skb_reset_network_header(nskb);
niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
niph->version = 4;
niph->ihl = sizeof(struct iphdr) / 4;
niph->tos = 0;
niph->id = 0;
niph->frag_off = htons(IP_DF);
niph->protocol = IPPROTO_TCP;
niph->check = 0;
niph->saddr = oiph->daddr;
niph->daddr = oiph->saddr;
tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
memset(tcph, 0, sizeof(*tcph));
tcph->source = oth->dest;
tcph->dest = oth->source;
tcph->doff = sizeof(struct tcphdr) / 4;
if (oth->ack)
tcph->seq = oth->ack_seq;
else {
tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
oldskb->len - ip_hdrlen(oldskb) -
(oth->doff << 2));
tcph->ack = 1;
}
tcph->rst = 1;
tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
niph->daddr, 0);
nskb->ip_summed = CHECKSUM_PARTIAL;
nskb->csum_start = (unsigned char *)tcph - nskb->head;
nskb->csum_offset = offsetof(struct tcphdr, check);
addr_type = RTN_UNSPEC;
if (hook != NF_INET_FORWARD
#ifdef CONFIG_BRIDGE_NETFILTER
|| (nskb->nf_bridge && nskb->nf_bridge->mask & BRNF_BRIDGED)
#endif
)
addr_type = RTN_LOCAL;
/* ip_route_me_harder expects skb->dst to be set */
skb_dst_set_noref(nskb, skb_dst(oldskb));
if (ip_route_me_harder(nskb, addr_type))
goto free_nskb;
niph->ttl = dst_metric(skb_dst(nskb), RTAX_HOPLIMIT);
/* "Never happens" */
if (nskb->len > dst_mtu(skb_dst(nskb)))
goto free_nskb;
nf_ct_attach(nskb, oldskb);
ip_local_out(nskb);
return;
free_nskb:
kfree_skb(nskb);
}
static int help(struct sk_buff *skb,
unsigned int protoff,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo)
{
unsigned int dataoff, datalen;
const struct tcphdr *th;
struct tcphdr _tcph;
void *sb_ptr;
int ret = NF_ACCEPT;
int dir = CTINFO2DIR(ctinfo);
struct nf_ct_sane_master *ct_sane_info;
struct nf_conntrack_expect *exp;
struct nf_conntrack_tuple *tuple;
struct sane_request *req;
struct sane_reply_net_start *reply;
ct_sane_info = &nfct_help(ct)->help.ct_sane_info;
/* Until there's been traffic both ways, don't look in packets. */
if (ctinfo != IP_CT_ESTABLISHED &&
ctinfo != IP_CT_ESTABLISHED_REPLY)
return NF_ACCEPT;
/* Not a full tcp header? */
th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph);
if (th == NULL)
return NF_ACCEPT;
/* No data? */
dataoff = protoff + th->doff * 4;
if (dataoff >= skb->len)
return NF_ACCEPT;
datalen = skb->len - dataoff;
spin_lock_bh(&nf_sane_lock);
sb_ptr = skb_header_pointer(skb, dataoff, datalen, sane_buffer);
BUG_ON(sb_ptr == NULL);
if (dir == IP_CT_DIR_ORIGINAL) {
if (datalen != sizeof(struct sane_request))
goto out;
req = sb_ptr;
if (req->RPC_code != htonl(SANE_NET_START)) {
/* Not an interesting command */
ct_sane_info->state = SANE_STATE_NORMAL;
goto out;
}
/* We're interested in the next reply */
ct_sane_info->state = SANE_STATE_START_REQUESTED;
goto out;
}
/* Is it a reply to an uninteresting command? */
if (ct_sane_info->state != SANE_STATE_START_REQUESTED)
goto out;
/* It's a reply to SANE_NET_START. */
ct_sane_info->state = SANE_STATE_NORMAL;
if (datalen < sizeof(struct sane_reply_net_start)) {
pr_debug("nf_ct_sane: NET_START reply too short\n");
goto out;
}
reply = sb_ptr;
if (reply->status != htonl(SANE_STATUS_SUCCESS)) {
/* saned refused the command */
pr_debug("nf_ct_sane: unsuccessful SANE_STATUS = %u\n",
ntohl(reply->status));
goto out;
}
/* Invalid saned reply? Ignore it. */
if (reply->zero != 0)
goto out;
exp = nf_ct_expect_alloc(ct);
if (exp == NULL) {
ret = NF_DROP;
goto out;
}
tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&tuple->src.u3, &tuple->dst.u3,
IPPROTO_TCP, NULL, &reply->port);
pr_debug("nf_ct_sane: expect: ");
nf_ct_dump_tuple(&exp->tuple);
/* Can't expect this? Best to drop packet now. */
if (nf_ct_expect_related(exp) != 0)
ret = NF_DROP;
nf_ct_expect_put(exp);
out:
spin_unlock_bh(&nf_sane_lock);
return ret;
}
/* Returns verdict for packet, or -1 for invalid. */
static int tcp_packet(struct nf_conn *ct,
const struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
int pf,
unsigned int hooknum)
{
struct nf_conntrack_tuple *tuple;
enum tcp_conntrack new_state, old_state;
enum ip_conntrack_dir dir;
const struct tcphdr *th;
struct tcphdr _tcph;
unsigned long timeout;
unsigned int index;
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
BUG_ON(th == NULL);
write_lock_bh(&tcp_lock);
old_state = ct->proto.tcp.state;
dir = CTINFO2DIR(ctinfo);
index = get_conntrack_index(th);
new_state = tcp_conntracks[dir][index][old_state];
tuple = &ct->tuplehash[dir].tuple;
switch (new_state) {
case TCP_CONNTRACK_SYN_SENT:
if (old_state < TCP_CONNTRACK_TIME_WAIT)
break;
/* RFC 1122: "When a connection is closed actively,
* it MUST linger in TIME-WAIT state for a time 2xMSL
* (Maximum Segment Lifetime). However, it MAY accept
* a new SYN from the remote TCP to reopen the connection
* directly from TIME-WAIT state, if..."
* We ignore the conditions because we are in the
* TIME-WAIT state anyway.
*
* Handle aborted connections: we and the server
* think there is an existing connection but the client
* aborts it and starts a new one.
*/
if (((ct->proto.tcp.seen[dir].flags
| ct->proto.tcp.seen[!dir].flags)
& IP_CT_TCP_FLAG_CLOSE_INIT)
|| (ct->proto.tcp.last_dir == dir
&& ct->proto.tcp.last_index == TCP_RST_SET)) {
/* Attempt to reopen a closed/aborted connection.
* Delete this connection and look up again. */
write_unlock_bh(&tcp_lock);
if (del_timer(&ct->timeout))
ct->timeout.function((unsigned long)ct);
return -NF_REPEAT;
}
/* Fall through */
case TCP_CONNTRACK_IGNORE:
/* Ignored packets:
*
* Our connection entry may be out of sync, so ignore
* packets which may signal the real connection between
* the client and the server.
*
* a) SYN in ORIGINAL
* b) SYN/ACK in REPLY
* c) ACK in reply direction after initial SYN in original.
*
* If the ignored packet is invalid, the receiver will send
* a RST we'll catch below.
*/
if (index == TCP_SYNACK_SET
&& ct->proto.tcp.last_index == TCP_SYN_SET
&& ct->proto.tcp.last_dir != dir
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
/* b) This SYN/ACK acknowledges a SYN that we earlier
* ignored as invalid. This means that the client and
* the server are both in sync, while the firewall is
* not. We kill this session and block the SYN/ACK so
* that the client cannot but retransmit its SYN and
* thus initiate a clean new session.
*/
write_unlock_bh(&tcp_lock);
if (LOG_INVALID(IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: killing out of sync session ");
if (del_timer(&ct->timeout))
ct->timeout.function((unsigned long)ct);
return -NF_DROP;
}
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
ct->proto.tcp.last_seq = ntohl(th->seq);
ct->proto.tcp.last_end =
segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th);
write_unlock_bh(&tcp_lock);
if (LOG_INVALID(IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid packet ignored ");
return NF_ACCEPT;
case TCP_CONNTRACK_MAX:
/* Invalid packet */
pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n",
dir, get_conntrack_index(th), old_state);
write_unlock_bh(&tcp_lock);
if (LOG_INVALID(IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid state ");
return -NF_ACCEPT;
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
&& ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_SYN_SET)
|| (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_ACK_SET))
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
/* RST sent to invalid SYN or ACK we had let through
* at a) and c) above:
*
* a) SYN was in window then
* c) we hold a half-open connection.
*
* Delete our connection entry.
* We skip window checking, because packet might ACK
* segments we ignored. */
goto in_window;
}
/* Just fall through */
default:
/* Keep compilers happy. */
break;
}
if (!tcp_in_window(ct, &ct->proto.tcp, dir, index,
skb, dataoff, th, pf)) {
write_unlock_bh(&tcp_lock);
return -NF_ACCEPT;
}
in_window:
/* From now on we have got in-window packets */
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
pr_debug("tcp_conntracks: ");
NF_CT_DUMP_TUPLE(tuple);
pr_debug("syn=%i ack=%i fin=%i rst=%i old=%i new=%i\n",
(th->syn ? 1 : 0), (th->ack ? 1 : 0),
(th->fin ? 1 : 0), (th->rst ? 1 : 0),
old_state, new_state);
ct->proto.tcp.state = new_state;
if (old_state != new_state
&& new_state == TCP_CONNTRACK_FIN_WAIT)
ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT;
timeout = ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans
&& tcp_timeouts[new_state] > nf_ct_tcp_timeout_max_retrans
? nf_ct_tcp_timeout_max_retrans : tcp_timeouts[new_state];
write_unlock_bh(&tcp_lock);
nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, skb);
if (new_state != old_state)
nf_conntrack_event_cache(IPCT_PROTOINFO, skb);
if (!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
/* If only reply is a RST, we can consider ourselves not to
have an established connection: this is a fairly common
problem case, so we can delete the conntrack
immediately. --RR */
if (th->rst) {
if (del_timer(&ct->timeout))
ct->timeout.function((unsigned long)ct);
return NF_ACCEPT;
}
} else if (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& (old_state == TCP_CONNTRACK_SYN_RECV
|| old_state == TCP_CONNTRACK_ESTABLISHED)
&& new_state == TCP_CONNTRACK_ESTABLISHED) {
/* Set ASSURED if we see see valid ack in ESTABLISHED
after SYN_RECV or a valid answer for a picked up
connection. */
set_bit(IPS_ASSURED_BIT, &ct->status);
nf_conntrack_event_cache(IPCT_STATUS, skb);
}
nf_ct_refresh_acct(ct, ctinfo, skb, timeout);
return NF_ACCEPT;
}
static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff,
struct tcphdr *tcph, __u32 *sack)
{
unsigned char buff[(15 * 4) - sizeof(struct tcphdr)];
unsigned char *ptr;
int length = (tcph->doff*4) - sizeof(struct tcphdr);
__u32 tmp;
if (!length)
return;
ptr = skb_header_pointer(skb, dataoff + sizeof(struct tcphdr),
length, buff);
BUG_ON(ptr == NULL);
/* Fast path for timestamp-only option */
if (length == TCPOLEN_TSTAMP_ALIGNED*4
&& *(__be32 *)ptr ==
__constant_htonl((TCPOPT_NOP << 24)
| (TCPOPT_NOP << 16)
| (TCPOPT_TIMESTAMP << 8)
| TCPOLEN_TIMESTAMP))
return;
while (length > 0) {
int opcode = *ptr++;
int opsize, i;
switch (opcode) {
case TCPOPT_EOL:
return;
case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */
length--;
continue;
default:
opsize = *ptr++;
if (opsize < 2) /* "silly options" */
return;
if (opsize > length)
break; /* don't parse partial options */
if (opcode == TCPOPT_SACK
&& opsize >= (TCPOLEN_SACK_BASE
+ TCPOLEN_SACK_PERBLOCK)
&& !((opsize - TCPOLEN_SACK_BASE)
% TCPOLEN_SACK_PERBLOCK)) {
for (i = 0;
i < (opsize - TCPOLEN_SACK_BASE);
i += TCPOLEN_SACK_PERBLOCK) {
tmp = ntohl(*((__be32 *)(ptr+i)+1));
if (after(tmp, *sack))
*sack = tmp;
}
return;
}
ptr += opsize - 2;
length -= opsize;
}
}
}
static int help(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
{
unsigned int dataoff;
const struct iphdr *iph;
const struct tcphdr *th;
struct tcphdr _tcph;
const char *data_limit;
char *data, *ib_ptr;
int dir = CTINFO2DIR(ctinfo);
struct nf_conntrack_expect *exp;
struct nf_conntrack_tuple *tuple;
__be32 dcc_ip;
u_int16_t dcc_port;
__be16 port;
int i, ret = NF_ACCEPT;
char *addr_beg_p, *addr_end_p;
typeof(nf_nat_irc_hook) nf_nat_irc;
if (dir == IP_CT_DIR_REPLY)
return NF_ACCEPT;
if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY)
return NF_ACCEPT;
th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph);
if (th == NULL)
return NF_ACCEPT;
dataoff = protoff + th->doff*4;
if (dataoff >= skb->len)
return NF_ACCEPT;
spin_lock_bh(&irc_buffer_lock);
ib_ptr = skb_header_pointer(skb, dataoff, skb->len - dataoff,
irc_buffer);
BUG_ON(ib_ptr == NULL);
data = ib_ptr;
data_limit = ib_ptr + skb->len - dataoff;
while (data < data_limit - (19 + MINMATCHLEN)) {
if (memcmp(data, "\1DCC ", 5)) {
data++;
continue;
}
data += 5;
iph = ip_hdr(skb);
pr_debug("DCC found in master %pI4:%u %pI4:%u\n",
&iph->saddr, ntohs(th->source),
&iph->daddr, ntohs(th->dest));
for (i = 0; i < ARRAY_SIZE(dccprotos); i++) {
if (memcmp(data, dccprotos[i], strlen(dccprotos[i]))) {
continue;
}
data += strlen(dccprotos[i]);
pr_debug("DCC %s detected\n", dccprotos[i]);
if (parse_dcc(data, data_limit, &dcc_ip,
&dcc_port, &addr_beg_p, &addr_end_p)) {
pr_debug("unable to parse dcc command\n");
continue;
}
pr_debug("DCC bound ip/port: %pI4:%u\n",
&dcc_ip, dcc_port);
tuple = &ct->tuplehash[dir].tuple;
if (tuple->src.u3.ip != dcc_ip &&
tuple->dst.u3.ip != dcc_ip) {
if (net_ratelimit())
printk(KERN_WARNING
"Forged DCC command from %pI4: %pI4:%u\n",
&tuple->src.u3.ip,
&dcc_ip, dcc_port);
continue;
}
exp = nf_ct_expect_alloc(ct);
if (exp == NULL) {
ret = NF_DROP;
goto out;
}
tuple = &ct->tuplehash[!dir].tuple;
port = htons(dcc_port);
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT,
tuple->src.l3num,
NULL, &tuple->dst.u3,
IPPROTO_TCP, NULL, &port);
nf_nat_irc = rcu_dereference(nf_nat_irc_hook);
if (nf_nat_irc && ct->status & IPS_NAT_MASK)
ret = nf_nat_irc(skb, ctinfo,
addr_beg_p - ib_ptr,
addr_end_p - addr_beg_p,
exp);
else if (nf_ct_expect_related(exp) != 0)
ret = NF_DROP;
nf_ct_expect_put(exp);
goto out;
}
}
out:
spin_unlock_bh(&irc_buffer_lock);
return ret;
}
static int help(struct sk_buff *skb,
unsigned int protoff,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo)
{
unsigned int dataoff, datalen;
const struct tcphdr *th;
struct tcphdr _tcph;
void *sb_ptr;
int ret = NF_ACCEPT;
int dir = CTINFO2DIR(ctinfo);
struct nf_ct_sane_master *ct_sane_info;
struct nf_conntrack_expect *exp;
struct nf_conntrack_tuple *tuple;
struct sane_request *req;
struct sane_reply_net_start *reply;
ct_sane_info = &nfct_help(ct)->help.ct_sane_info;
if (ctinfo != IP_CT_ESTABLISHED &&
ctinfo != IP_CT_ESTABLISHED+IP_CT_IS_REPLY)
return NF_ACCEPT;
th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph);
if (th == NULL)
return NF_ACCEPT;
dataoff = protoff + th->doff * 4;
if (dataoff >= skb->len)
return NF_ACCEPT;
datalen = skb->len - dataoff;
spin_lock_bh(&nf_sane_lock);
sb_ptr = skb_header_pointer(skb, dataoff, datalen, sane_buffer);
BUG_ON(sb_ptr == NULL);
if (dir == IP_CT_DIR_ORIGINAL) {
if (datalen != sizeof(struct sane_request))
goto out;
req = sb_ptr;
if (req->RPC_code != htonl(SANE_NET_START)) {
ct_sane_info->state = SANE_STATE_NORMAL;
goto out;
}
ct_sane_info->state = SANE_STATE_START_REQUESTED;
goto out;
}
if (ct_sane_info->state != SANE_STATE_START_REQUESTED)
goto out;
ct_sane_info->state = SANE_STATE_NORMAL;
if (datalen < sizeof(struct sane_reply_net_start)) {
pr_debug("nf_ct_sane: NET_START reply too short\n");
goto out;
}
reply = sb_ptr;
if (reply->status != htonl(SANE_STATUS_SUCCESS)) {
pr_debug("nf_ct_sane: unsuccessful SANE_STATUS = %u\n",
ntohl(reply->status));
goto out;
}
if (reply->zero != 0)
goto out;
exp = nf_ct_expect_alloc(ct);
if (exp == NULL) {
ret = NF_DROP;
goto out;
}
tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&tuple->src.u3, &tuple->dst.u3,
IPPROTO_TCP, NULL, &reply->port);
pr_debug("nf_ct_sane: expect: ");
nf_ct_dump_tuple(&exp->tuple);
if (nf_ct_expect_related(exp) != 0)
ret = NF_DROP;
nf_ct_expect_put(exp);
out:
spin_unlock_bh(&nf_sane_lock);
return ret;
}
/* Returns verdict for packet, or -1 for invalid. */
static int tcp_packet(struct nf_conn *ct,
const struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
u_int8_t pf,
unsigned int hooknum)
{
struct net *net = nf_ct_net(ct);
struct nf_conntrack_tuple *tuple;
enum tcp_conntrack new_state, old_state;
enum ip_conntrack_dir dir;
const struct tcphdr *th;
struct tcphdr _tcph;
unsigned long timeout;
unsigned int index;
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
BUG_ON(th == NULL);
spin_lock_bh(&ct->lock);
old_state = ct->proto.tcp.state;
dir = CTINFO2DIR(ctinfo);
index = get_conntrack_index(th);
new_state = tcp_conntracks[dir][index][old_state];
tuple = &ct->tuplehash[dir].tuple;
switch (new_state) {
case TCP_CONNTRACK_SYN_SENT:
if (old_state < TCP_CONNTRACK_TIME_WAIT)
break;
/* RFC 1122: "When a connection is closed actively,
* it MUST linger in TIME-WAIT state for a time 2xMSL
* (Maximum Segment Lifetime). However, it MAY accept
* a new SYN from the remote TCP to reopen the connection
* directly from TIME-WAIT state, if..."
* We ignore the conditions because we are in the
* TIME-WAIT state anyway.
*
* Handle aborted connections: we and the server
* think there is an existing connection but the client
* aborts it and starts a new one.
*/
if (((ct->proto.tcp.seen[dir].flags
| ct->proto.tcp.seen[!dir].flags)
& IP_CT_TCP_FLAG_CLOSE_INIT)
|| (ct->proto.tcp.last_dir == dir
&& ct->proto.tcp.last_index == TCP_RST_SET)) {
/* Attempt to reopen a closed/aborted connection.
* Delete this connection and look up again. */
spin_unlock_bh(&ct->lock);
/* Only repeat if we can actually remove the timer.
* Destruction may already be in progress in process
* context and we must give it a chance to terminate.
*/
if (nf_ct_kill(ct))
return -NF_REPEAT;
return NF_DROP;
}
/* Fall through */
case TCP_CONNTRACK_IGNORE:
/* Ignored packets:
*
* Our connection entry may be out of sync, so ignore
* packets which may signal the real connection between
* the client and the server.
*
* a) SYN in ORIGINAL
* b) SYN/ACK in REPLY
* c) ACK in reply direction after initial SYN in original.
*
* If the ignored packet is invalid, the receiver will send
* a RST we'll catch below.
*/
if (index == TCP_SYNACK_SET
&& ct->proto.tcp.last_index == TCP_SYN_SET
&& ct->proto.tcp.last_dir != dir
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
/* b) This SYN/ACK acknowledges a SYN that we earlier
* ignored as invalid. This means that the client and
* the server are both in sync, while the firewall is
* not. We get in sync from the previously annotated
* values.
*/
old_state = TCP_CONNTRACK_SYN_SENT;
new_state = TCP_CONNTRACK_SYN_RECV;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_end =
ct->proto.tcp.last_end;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxend =
ct->proto.tcp.last_end;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxwin =
ct->proto.tcp.last_win == 0 ?
1 : ct->proto.tcp.last_win;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale =
ct->proto.tcp.last_wscale;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags =
ct->proto.tcp.last_flags;
memset(&ct->proto.tcp.seen[dir], 0,
sizeof(struct ip_ct_tcp_state));
break;
}
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
ct->proto.tcp.last_seq = ntohl(th->seq);
ct->proto.tcp.last_end =
segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th);
ct->proto.tcp.last_win = ntohs(th->window);
/* a) This is a SYN in ORIGINAL. The client and the server
* may be in sync but we are not. In that case, we annotate
* the TCP options and let the packet go through. If it is a
* valid SYN packet, the server will reply with a SYN/ACK, and
* then we'll get in sync. Otherwise, the server ignores it. */
if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) {
struct ip_ct_tcp_state seen = {};
ct->proto.tcp.last_flags =
ct->proto.tcp.last_wscale = 0;
tcp_options(skb, dataoff, th, &seen);
if (seen.flags & IP_CT_TCP_FLAG_WINDOW_SCALE) {
ct->proto.tcp.last_flags |=
IP_CT_TCP_FLAG_WINDOW_SCALE;
ct->proto.tcp.last_wscale = seen.td_scale;
}
if (seen.flags & IP_CT_TCP_FLAG_SACK_PERM) {
ct->proto.tcp.last_flags |=
IP_CT_TCP_FLAG_SACK_PERM;
}
}
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid packet ignored ");
return NF_ACCEPT;
case TCP_CONNTRACK_MAX:
/* Invalid packet */
pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n",
dir, get_conntrack_index(th), old_state);
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid state ");
return -NF_ACCEPT;
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
&& (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
&& before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) {
/* Invalid RST */
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid RST ");
return -NF_ACCEPT;
}
if (index == TCP_RST_SET
&& ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_SYN_SET)
|| (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_ACK_SET))
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
/* RST sent to invalid SYN or ACK we had let through
* at a) and c) above:
*
* a) SYN was in window then
* c) we hold a half-open connection.
*
* Delete our connection entry.
* We skip window checking, because packet might ACK
* segments we ignored. */
goto in_window;
}
/* Just fall through */
default:
/* Keep compilers happy. */
break;
}
if (!tcp_in_window(ct, &ct->proto.tcp, dir, index,
skb, dataoff, th, pf)) {
spin_unlock_bh(&ct->lock);
return -NF_ACCEPT;
}
in_window:
/* From now on we have got in-window packets */
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
pr_debug("tcp_conntracks: ");
nf_ct_dump_tuple(tuple);
pr_debug("syn=%i ack=%i fin=%i rst=%i old=%i new=%i\n",
(th->syn ? 1 : 0), (th->ack ? 1 : 0),
(th->fin ? 1 : 0), (th->rst ? 1 : 0),
old_state, new_state);
ct->proto.tcp.state = new_state;
if (old_state != new_state
&& new_state == TCP_CONNTRACK_FIN_WAIT)
ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT;
if (ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans &&
tcp_timeouts[new_state] > nf_ct_tcp_timeout_max_retrans)
timeout = nf_ct_tcp_timeout_max_retrans;
else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) &
IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED &&
tcp_timeouts[new_state] > nf_ct_tcp_timeout_unacknowledged)
timeout = nf_ct_tcp_timeout_unacknowledged;
else
timeout = tcp_timeouts[new_state];
spin_unlock_bh(&ct->lock);
if (new_state != old_state)
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
if (!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
/* If only reply is a RST, we can consider ourselves not to
have an established connection: this is a fairly common
problem case, so we can delete the conntrack
immediately. --RR */
if (th->rst) {
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
} else if (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& (old_state == TCP_CONNTRACK_SYN_RECV
|| old_state == TCP_CONNTRACK_ESTABLISHED)
&& new_state == TCP_CONNTRACK_ESTABLISHED) {
/* Set ASSURED if we see see valid ack in ESTABLISHED
after SYN_RECV or a valid answer for a picked up
connection. */
set_bit(IPS_ASSURED_BIT, &ct->status);
nf_conntrack_event_cache(IPCT_ASSURED, ct);
}
nf_ct_refresh_acct(ct, ctinfo, skb, timeout);
return NF_ACCEPT;
}
static bool
match(const struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
const struct xt_match *match,
const void *matchinfo,
int offset,
unsigned int protoff,
bool *hotdrop)
{
struct ipv6_rt_hdr _route;
const struct ipv6_rt_hdr *rh;
const struct ip6t_rt *rtinfo = matchinfo;
unsigned int temp;
unsigned int ptr;
unsigned int hdrlen = 0;
bool ret = false;
struct in6_addr _addr;
const struct in6_addr *ap;
int err;
err = ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL);
if (err < 0) {
if (err != -ENOENT)
*hotdrop = true;
return false;
}
rh = skb_header_pointer(skb, ptr, sizeof(_route), &_route);
if (rh == NULL) {
*hotdrop = true;
return false;
}
hdrlen = ipv6_optlen(rh);
if (skb->len - ptr < hdrlen) {
/* Pcket smaller than its length field */
return false;
}
DEBUGP("IPv6 RT LEN %u %u ", hdrlen, rh->hdrlen);
DEBUGP("TYPE %04X ", rh->type);
DEBUGP("SGS_LEFT %u %02X\n", rh->segments_left, rh->segments_left);
DEBUGP("IPv6 RT segsleft %02X ",
(segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1],
rh->segments_left,
!!(rtinfo->invflags & IP6T_RT_INV_SGS))));
DEBUGP("type %02X %02X %02X ",
rtinfo->rt_type, rh->type,
(!(rtinfo->flags & IP6T_RT_TYP) ||
((rtinfo->rt_type == rh->type) ^
!!(rtinfo->invflags & IP6T_RT_INV_TYP))));
DEBUGP("len %02X %04X %02X ",
rtinfo->hdrlen, hdrlen,
(!(rtinfo->flags & IP6T_RT_LEN) ||
((rtinfo->hdrlen == hdrlen) ^
!!(rtinfo->invflags & IP6T_RT_INV_LEN))));
DEBUGP("res %02X %02X %02X ",
(rtinfo->flags & IP6T_RT_RES),
((const struct rt0_hdr *)rh)->reserved,
!((rtinfo->flags & IP6T_RT_RES) &&
(((const struct rt0_hdr *)rh)->reserved)));
ret = (rh != NULL)
&&
(segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1],
rh->segments_left,
!!(rtinfo->invflags & IP6T_RT_INV_SGS)))
&&
(!(rtinfo->flags & IP6T_RT_LEN) ||
((rtinfo->hdrlen == hdrlen) ^
!!(rtinfo->invflags & IP6T_RT_INV_LEN)))
&&
(!(rtinfo->flags & IP6T_RT_TYP) ||
((rtinfo->rt_type == rh->type) ^
!!(rtinfo->invflags & IP6T_RT_INV_TYP)));
if (ret && (rtinfo->flags & IP6T_RT_RES)) {
const u_int32_t *rp;
u_int32_t _reserved;
rp = skb_header_pointer(skb,
ptr + offsetof(struct rt0_hdr,
reserved),
sizeof(_reserved),
&_reserved);
ret = (*rp == 0);
}
DEBUGP("#%d ", rtinfo->addrnr);
if (!(rtinfo->flags & IP6T_RT_FST)) {
return ret;
} else if (rtinfo->flags & IP6T_RT_FST_NSTRICT) {
DEBUGP("Not strict ");
if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) {
DEBUGP("There isn't enough space\n");
return false;
} else {
unsigned int i = 0;
DEBUGP("#%d ", rtinfo->addrnr);
for (temp = 0;
temp < (unsigned int)((hdrlen - 8) / 16);
temp++) {
ap = skb_header_pointer(skb,
ptr
+ sizeof(struct rt0_hdr)
+ temp * sizeof(_addr),
sizeof(_addr),
&_addr);
BUG_ON(ap == NULL);
if (ipv6_addr_equal(ap, &rtinfo->addrs[i])) {
DEBUGP("i=%d temp=%d;\n", i, temp);
i++;
}
if (i == rtinfo->addrnr)
break;
}
DEBUGP("i=%d #%d\n", i, rtinfo->addrnr);
if (i == rtinfo->addrnr)
return ret;
else
return false;
}
} else {
DEBUGP("Strict ");
if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) {
DEBUGP("There isn't enough space\n");
return false;
} else {
DEBUGP("#%d ", rtinfo->addrnr);
for (temp = 0; temp < rtinfo->addrnr; temp++) {
ap = skb_header_pointer(skb,
ptr
+ sizeof(struct rt0_hdr)
+ temp * sizeof(_addr),
sizeof(_addr),
&_addr);
BUG_ON(ap == NULL);
if (!ipv6_addr_equal(ap, &rtinfo->addrs[temp]))
break;
}
DEBUGP("temp=%d #%d\n", temp, rtinfo->addrnr);
if ((temp == rtinfo->addrnr) &&
(temp == (unsigned int)((hdrlen - 8) / 16)))
return ret;
else
return false;
}
}
return false;
}
static int ebt_filter_arp(const struct sk_buff *skb, const struct net_device *in,
const struct net_device *out, const void *data, unsigned int datalen)
{
const struct ebt_arp_info *info = data;
const struct arphdr *ah;
struct arphdr _arph;
ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
if (ah == NULL)
return EBT_NOMATCH;
if (info->bitmask & EBT_ARP_OPCODE && FWINV(info->opcode !=
ah->ar_op, EBT_ARP_OPCODE))
return EBT_NOMATCH;
if (info->bitmask & EBT_ARP_HTYPE && FWINV(info->htype !=
ah->ar_hrd, EBT_ARP_HTYPE))
return EBT_NOMATCH;
if (info->bitmask & EBT_ARP_PTYPE && FWINV(info->ptype !=
ah->ar_pro, EBT_ARP_PTYPE))
return EBT_NOMATCH;
if (info->bitmask & (EBT_ARP_SRC_IP | EBT_ARP_DST_IP | EBT_ARP_GRAT)) {
const __be32 *sap, *dap;
__be32 saddr, daddr;
if (ah->ar_pln != sizeof(__be32) || ah->ar_pro != htons(ETH_P_IP))
return EBT_NOMATCH;
sap = skb_header_pointer(skb, sizeof(struct arphdr) +
ah->ar_hln, sizeof(saddr),
&saddr);
if (sap == NULL)
return EBT_NOMATCH;
dap = skb_header_pointer(skb, sizeof(struct arphdr) +
2*ah->ar_hln+sizeof(saddr),
sizeof(daddr), &daddr);
if (dap == NULL)
return EBT_NOMATCH;
if (info->bitmask & EBT_ARP_SRC_IP &&
FWINV(info->saddr != (*sap & info->smsk), EBT_ARP_SRC_IP))
return EBT_NOMATCH;
if (info->bitmask & EBT_ARP_DST_IP &&
FWINV(info->daddr != (*dap & info->dmsk), EBT_ARP_DST_IP))
return EBT_NOMATCH;
if (info->bitmask & EBT_ARP_GRAT &&
FWINV(*dap != *sap, EBT_ARP_GRAT))
return EBT_NOMATCH;
}
if (info->bitmask & (EBT_ARP_SRC_MAC | EBT_ARP_DST_MAC)) {
const unsigned char *mp;
unsigned char _mac[ETH_ALEN];
uint8_t verdict, i;
if (ah->ar_hln != ETH_ALEN || ah->ar_hrd != htons(ARPHRD_ETHER))
return EBT_NOMATCH;
if (info->bitmask & EBT_ARP_SRC_MAC) {
mp = skb_header_pointer(skb, sizeof(struct arphdr),
sizeof(_mac), &_mac);
if (mp == NULL)
return EBT_NOMATCH;
verdict = 0;
for (i = 0; i < 6; i++)
verdict |= (mp[i] ^ info->smaddr[i]) &
info->smmsk[i];
if (FWINV(verdict != 0, EBT_ARP_SRC_MAC))
return EBT_NOMATCH;
}
if (info->bitmask & EBT_ARP_DST_MAC) {
mp = skb_header_pointer(skb, sizeof(struct arphdr) +
ah->ar_hln + ah->ar_pln,
sizeof(_mac), &_mac);
if (mp == NULL)
return EBT_NOMATCH;
verdict = 0;
for (i = 0; i < 6; i++)
verdict |= (mp[i] ^ info->dmaddr[i]) &
info->dmmsk[i];
if (FWINV(verdict != 0, EBT_ARP_DST_MAC))
return EBT_NOMATCH;
}
}
return EBT_MATCH;
}
int
ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
struct rt6_info *rt; /* Route to the other host */
int local, rc;
EnterFunction(10);
rcu_read_lock();
/* check if it is a connection of no-client-port */
if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT && !ipvsh->fragoffs)) {
__be16 _pt, *p;
p = skb_header_pointer(skb, ipvsh->len, sizeof(_pt), &_pt);
if (p == NULL)
goto tx_error;
ip_vs_conn_fill_cport(cp, *p);
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
}
local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
NULL, ipvsh, 0,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR);
if (local < 0)
goto tx_error;
rt = (struct rt6_info *) skb_dst(skb);
/*
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct)) {
IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to local address");
goto tx_error;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) {
IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to loopback address");
goto tx_error;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, sizeof(struct ipv6hdr)))
goto tx_error;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error;
/* mangle the packet */
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, ipvsh))
goto tx_error;
ipv6_hdr(skb)->daddr = cp->daddr.in6;
IP_VS_DBG_PKT(10, AF_INET6, pp, skb, 0, "After DNAT");
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
MTU problem. */
/* Another hack: avoid icmp_send in ip_fragment */
skb->ignore_df = 1;
rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local);
rcu_read_unlock();
LeaveFunction(10);
return rc;
tx_error:
LeaveFunction(10);
kfree_skb(skb);
rcu_read_unlock();
return NF_STOLEN;
}
/* We must handle non-linear skbs */
static bool
get_port(const struct sk_buff *skb, int protocol, unsigned int protooff,
bool src, __be16 *port, u8 *proto)
{
switch (protocol) {
case IPPROTO_TCP: {
struct tcphdr _tcph;
const struct tcphdr *th;
th = skb_header_pointer(skb, protooff, sizeof(_tcph), &_tcph);
if (th == NULL)
/* No choice either */
return false;
*port = src ? th->source : th->dest;
break;
}
case IPPROTO_SCTP: {
sctp_sctphdr_t _sh;
const sctp_sctphdr_t *sh;
sh = skb_header_pointer(skb, protooff, sizeof(_sh), &_sh);
if (sh == NULL)
/* No choice either */
return false;
*port = src ? sh->source : sh->dest;
break;
}
case IPPROTO_UDP:
case IPPROTO_UDPLITE: {
struct udphdr _udph;
const struct udphdr *uh;
uh = skb_header_pointer(skb, protooff, sizeof(_udph), &_udph);
if (uh == NULL)
/* No choice either */
return false;
*port = src ? uh->source : uh->dest;
break;
}
case IPPROTO_ICMP: {
struct icmphdr _ich;
const struct icmphdr *ic;
ic = skb_header_pointer(skb, protooff, sizeof(_ich), &_ich);
if (ic == NULL)
return false;
*port = (__force __be16)htons((ic->type << 8) | ic->code);
break;
}
case IPPROTO_ICMPV6: {
struct icmp6hdr _ich;
const struct icmp6hdr *ic;
ic = skb_header_pointer(skb, protooff, sizeof(_ich), &_ich);
if (ic == NULL)
return false;
*port = (__force __be16)
htons((ic->icmp6_type << 8) | ic->icmp6_code);
break;
}
default:
break;
}
*proto = protocol;
return true;
}
/**
* ipv6_skb_to_auditdata : fill auditdata from skb
* @skb : the skb
* @ad : the audit data to fill
* @proto : the layer 4 protocol
*
* return 0 on success
*/
int ipv6_skb_to_auditdata(struct sk_buff *skb,
struct common_audit_data *ad, u8 *proto)
{
int offset, ret = 0;
struct ipv6hdr *ip6;
u8 nexthdr;
__be16 frag_off;
ip6 = ipv6_hdr(skb);
if (ip6 == NULL)
return -EINVAL;
ad->u.net->v6info.saddr = ip6->saddr;
ad->u.net->v6info.daddr = ip6->daddr;
ret = 0;
/* IPv6 can have several extension header before the Transport header
* skip them */
offset = skb_network_offset(skb);
offset += sizeof(*ip6);
nexthdr = ip6->nexthdr;
offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
if (offset < 0)
return 0;
if (proto)
*proto = nexthdr;
switch (nexthdr) {
case IPPROTO_TCP: {
struct tcphdr _tcph, *th;
th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
if (th == NULL)
break;
ad->u.net->sport = th->source;
ad->u.net->dport = th->dest;
break;
}
case IPPROTO_UDP: {
struct udphdr _udph, *uh;
uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph);
if (uh == NULL)
break;
ad->u.net->sport = uh->source;
ad->u.net->dport = uh->dest;
break;
}
case IPPROTO_DCCP: {
struct dccp_hdr _dccph, *dh;
dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph);
if (dh == NULL)
break;
ad->u.net->sport = dh->dccph_sport;
ad->u.net->dport = dh->dccph_dport;
break;
}
case IPPROTO_SCTP: {
struct sctphdr _sctph, *sh;
sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph);
if (sh == NULL)
break;
ad->u.net->sport = sh->source;
ad->u.net->dport = sh->dest;
break;
}
default:
ret = -EINVAL;
}
return ret;
}
static int
tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
struct ip_vs_proto_data *pd,
int *verdict, struct ip_vs_conn **cpp,
struct ip_vs_iphdr *iph)
{
struct ip_vs_service *svc;
struct tcphdr _tcph, *th;
__be16 _ports[2], *ports = NULL;
/* In the event of icmp, we're only guaranteed to have the first 8
* bytes of the transport header, so we only check the rest of the
* TCP packet for non-ICMP packets
*/
if (likely(!ip_vs_iph_icmp(iph))) {
th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph);
if (th) {
if (th->rst || !(sysctl_sloppy_tcp(ipvs) || th->syn))
return 1;
ports = &th->source;
}
} else {
ports = skb_header_pointer(
skb, iph->len, sizeof(_ports), &_ports);
}
if (!ports) {
*verdict = NF_DROP;
return 0;
}
/* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */
rcu_read_lock();
if (likely(!ip_vs_iph_inverse(iph)))
svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol,
&iph->daddr, ports[1]);
else
svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol,
&iph->saddr, ports[0]);
if (svc) {
int ignored;
if (ip_vs_todrop(ipvs)) {
/*
* It seems that we are very loaded.
* We have to drop this packet :(
*/
rcu_read_unlock();
*verdict = NF_DROP;
return 0;
}
/*
* Let the virtual server select a real server for the
* incoming connection, and create a connection entry.
*/
*cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph);
if (!*cpp && ignored <= 0) {
if (!ignored)
*verdict = ip_vs_leave(svc, skb, pd, iph);
else
*verdict = NF_DROP;
rcu_read_unlock();
return 0;
}
}
rcu_read_unlock();
/* NF_ACCEPT */
return 1;
}