static int tftp_help(struct sk_buff *skb,
unsigned int protoff,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo)
{
const struct tftphdr *tfh;
struct tftphdr _tftph;
struct nf_conntrack_expect *exp;
struct nf_conntrack_tuple *tuple;
unsigned int ret = NF_ACCEPT;
typeof(nf_nat_tftp_hook) nf_nat_tftp;
#ifdef CONFIG_CAMEO_ALG_TFTP
if(!tftp_enable)
return NF_ACCEPT;
#endif
tfh = skb_header_pointer(skb, protoff + sizeof(struct udphdr),
sizeof(_tftph), &_tftph);
if (tfh == NULL)
return NF_ACCEPT;
switch (ntohs(tfh->opcode)) {
case TFTP_OPCODE_READ:
case TFTP_OPCODE_WRITE:
/* RRQ and WRQ works the same way */
nf_ct_dump_tuple(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
nf_ct_dump_tuple(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
exp = nf_ct_expect_alloc(ct);
if (exp == NULL)
return NF_DROP;
tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT,
nf_ct_l3num(ct),
&tuple->src.u3, &tuple->dst.u3,
IPPROTO_UDP, NULL, &tuple->dst.u.udp.port);
pr_debug("expect: ");
nf_ct_dump_tuple(&exp->tuple);
nf_nat_tftp = rcu_dereference(nf_nat_tftp_hook);
if (nf_nat_tftp && ct->status & IPS_NAT_MASK)
ret = nf_nat_tftp(skb, ctinfo, exp);
else if (nf_ct_expect_related(exp) != 0)
ret = NF_DROP;
nf_ct_expect_put(exp);
break;
case TFTP_OPCODE_DATA:
case TFTP_OPCODE_ACK:
pr_debug("Data/ACK opcode\n");
break;
case TFTP_OPCODE_ERROR:
pr_debug("Error opcode\n");
break;
default:
pr_debug("Unknown opcode\n");
}
return ret;
}
static int destroy_sibling_or_exp(struct net *net,
const struct nf_conntrack_tuple *t)
{
const struct nf_conntrack_tuple_hash *h;
struct nf_conntrack_expect *exp;
struct nf_conn *sibling;
pr_debug("trying to timeout ct or exp for tuple ");
nf_ct_dump_tuple(t);
h = nf_conntrack_find_get(net, t);
if (h) {
sibling = nf_ct_tuplehash_to_ctrack(h);
pr_debug("setting timeout of conntrack %p to 0\n", sibling);
sibling->proto.gre.timeout = 0;
sibling->proto.gre.stream_timeout = 0;
if (del_timer(&sibling->timeout))
sibling->timeout.function((unsigned long)sibling);
nf_ct_put(sibling);
return 1;
} else {
exp = nf_ct_expect_find_get(net, t);
if (exp) {
pr_debug("unexpect_related of expect %p\n", exp);
nf_ct_unexpect_related(exp);
nf_ct_expect_put(exp);
return 1;
}
}
return 0;
}
static int expect_q931(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned char **data,
TransportAddress *taddr, int count)
{
struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
int dir = CTINFO2DIR(ctinfo);
int ret = 0;
int i;
__be16 port;
union nf_inet_addr addr;
struct nf_conntrack_expect *exp;
typeof(nat_q931_hook) nat_q931;
#ifdef CONFIG_HTC_NETWORK_MODIFY
if (IS_ERR(info) || (!info))
printk(KERN_ERR "[NET] info is NULL in %s!\n", __func__);
#endif
for (i = 0; i < count; i++) {
if (get_h225_addr(ct, *data, &taddr[i], &addr, &port) &&
memcmp(&addr, &ct->tuplehash[dir].tuple.src.u3,
sizeof(addr)) == 0 && port != 0)
break;
}
if (i >= count)
return 0;
if ((exp = nf_ct_expect_alloc(ct)) == NULL)
return -1;
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
gkrouted_only ?
&ct->tuplehash[!dir].tuple.src.u3 : NULL,
&ct->tuplehash[!dir].tuple.dst.u3,
IPPROTO_TCP, NULL, &port);
exp->helper = nf_conntrack_helper_q931;
exp->flags = NF_CT_EXPECT_PERMANENT;
nat_q931 = rcu_dereference(nat_q931_hook);
if (nat_q931 && ct->status & IPS_NAT_MASK) {
ret = nat_q931(skb, ct, ctinfo, data, taddr, i, port, exp);
} else {
if (nf_ct_expect_related(exp) == 0) {
pr_debug("nf_ct_ras: expect Q.931 ");
nf_ct_dump_tuple(&exp->tuple);
info->sig_port[dir] = port;
} else
ret = -1;
}
nf_ct_expect_put(exp);
return ret;
}
static int expect_callforwarding(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned char **data, int dataoff,
TransportAddress *taddr)
{
int dir = CTINFO2DIR(ctinfo);
int ret = 0;
__be16 port;
union nf_inet_addr addr;
struct nf_conntrack_expect *exp;
typeof(nat_callforwarding_hook) nat_callforwarding;
if (!get_h225_addr(ct, *data, taddr, &addr, &port) || port == 0)
return 0;
if (callforward_filter &&
callforward_do_filter(&addr, &ct->tuplehash[!dir].tuple.src.u3,
nf_ct_l3num(ct))) {
pr_debug("nf_ct_q931: Call Forwarding not tracked\n");
return 0;
}
if ((exp = nf_ct_expect_alloc(ct)) == NULL)
return -1;
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&ct->tuplehash[!dir].tuple.src.u3, &addr,
IPPROTO_TCP, NULL, &port);
exp->helper = nf_conntrack_helper_q931;
if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
&ct->tuplehash[!dir].tuple.dst.u3,
sizeof(ct->tuplehash[dir].tuple.src.u3)) &&
(nat_callforwarding = rcu_dereference(nat_callforwarding_hook)) &&
ct->status & IPS_NAT_MASK) {
ret = nat_callforwarding(skb, ct, ctinfo, data, dataoff,
taddr, port, exp);
} else {
if (nf_ct_expect_related(exp) == 0) {
pr_debug("nf_ct_q931: expect Call Forwarding ");
nf_ct_dump_tuple(&exp->tuple);
} else
ret = -1;
}
nf_ct_expect_put(exp);
return ret;
}
static int process_rcf(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned char **data, RegistrationConfirm *rcf)
{
struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
int dir = CTINFO2DIR(ctinfo);
int ret;
struct nf_conntrack_expect *exp;
typeof(set_sig_addr_hook) set_sig_addr;
pr_debug("nf_ct_ras: RCF\n");
#ifdef CONFIG_HTC_NETWORK_MODIFY
if (IS_ERR(info) || (!info))
printk(KERN_ERR "[NET] info is NULL in %s!\n", __func__);
#endif
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,
rcf->callSignalAddress.item,
rcf->callSignalAddress.count);
if (ret < 0)
return -1;
}
if (rcf->options & eRegistrationConfirm_timeToLive) {
pr_debug("nf_ct_ras: RCF TTL = %u seconds\n", rcf->timeToLive);
info->timeout = rcf->timeToLive;
}
if (info->timeout > 0) {
pr_debug("nf_ct_ras: set RAS connection timeout to "
"%u seconds\n", info->timeout);
nf_ct_refresh(ct, skb, info->timeout * HZ);
spin_lock_bh(&nf_conntrack_lock);
exp = find_expect(ct, &ct->tuplehash[dir].tuple.dst.u3,
info->sig_port[!dir]);
if (exp) {
pr_debug("nf_ct_ras: set Q.931 expect "
"timeout to %u seconds for",
info->timeout);
nf_ct_dump_tuple(&exp->tuple);
set_expect_timeout(exp, info->timeout);
}
spin_unlock_bh(&nf_conntrack_lock);
}
return 0;
}
static int h245_help(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
{
static MultimediaSystemControlMessage mscm;
unsigned char *data = NULL;
int datalen;
int dataoff;
int ret;
if (ctinfo != IP_CT_ESTABLISHED &&
ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) {
return NF_ACCEPT;
}
pr_debug("nf_ct_h245: skblen = %u\n", skb->len);
spin_lock_bh(&nf_h323_lock);
while (get_tpkt_data(skb, protoff, ct, ctinfo,
&data, &datalen, &dataoff)) {
pr_debug("nf_ct_h245: TPKT len=%d ", datalen);
nf_ct_dump_tuple(&ct->tuplehash[CTINFO2DIR(ctinfo)].tuple);
ret = DecodeMultimediaSystemControlMessage(data, datalen,
&mscm);
if (ret < 0) {
pr_debug("nf_ct_h245: decoding error: %s\n",
ret == H323_ERROR_BOUND ?
"out of bound" : "out of range");
break;
}
if (process_h245(skb, ct, ctinfo, &data, dataoff, &mscm) < 0)
goto drop;
}
spin_unlock_bh(&nf_h323_lock);
return NF_ACCEPT;
drop:
spin_unlock_bh(&nf_h323_lock);
if (net_ratelimit())
printk("nf_ct_h245: packet dropped\n");
return NF_DROP;
}
static int expect_t120(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned char **data, int dataoff,
H245_TransportAddress *taddr)
{
int dir = CTINFO2DIR(ctinfo);
int ret = 0;
__be16 port;
union nf_inet_addr addr;
struct nf_conntrack_expect *exp;
typeof(nat_t120_hook) nat_t120;
if (!get_h245_addr(ct, *data, taddr, &addr, &port) ||
memcmp(&addr, &ct->tuplehash[dir].tuple.src.u3, sizeof(addr)) ||
port == 0)
return 0;
if ((exp = nf_ct_expect_alloc(ct)) == NULL)
return -1;
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&ct->tuplehash[!dir].tuple.src.u3,
&ct->tuplehash[!dir].tuple.dst.u3,
IPPROTO_TCP, NULL, &port);
exp->flags = NF_CT_EXPECT_PERMANENT;
if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
&ct->tuplehash[!dir].tuple.dst.u3,
sizeof(ct->tuplehash[dir].tuple.src.u3)) &&
(nat_t120 = rcu_dereference(nat_t120_hook)) &&
ct->status & IPS_NAT_MASK) {
ret = nat_t120(skb, ct, ctinfo, data, dataoff, taddr,
port, exp);
} else {
if (nf_ct_expect_related(exp) == 0) {
pr_debug("nf_ct_h323: expect T.120 ");
nf_ct_dump_tuple(&exp->tuple);
} else
ret = -1;
}
nf_ct_expect_put(exp);
return ret;
}
static int q931_help(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
{
static Q931 q931;
unsigned char *data = NULL;
int datalen = 0;
int dataoff = 0;
int ret;
if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY)
return NF_ACCEPT;
pr_debug("nf_ct_q931: skblen = %u\n", skb->len);
spin_lock_bh(&nf_h323_lock);
while (get_tpkt_data(skb, protoff, ct, ctinfo,
&data, &datalen, &dataoff)) {
pr_debug("nf_ct_q931: TPKT len=%d ", datalen);
nf_ct_dump_tuple(&ct->tuplehash[CTINFO2DIR(ctinfo)].tuple);
ret = DecodeQ931(data, datalen, &q931);
if (ret < 0) {
pr_debug("nf_ct_q931: decoding error: %s\n",
ret == H323_ERROR_BOUND ?
"out of bound" : "out of range");
break;
}
if (process_q931(skb, ct, ctinfo, &data, dataoff, &q931) < 0)
goto drop;
}
spin_unlock_bh(&nf_h323_lock);
return NF_ACCEPT;
drop:
spin_unlock_bh(&nf_h323_lock);
if (net_ratelimit())
pr_info("nf_ct_q931: packet dropped\n");
return NF_DROP;
}
static int process_acf(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned char **data, AdmissionConfirm *acf)
{
int dir = CTINFO2DIR(ctinfo);
int ret = 0;
__be16 port;
union nf_inet_addr addr;
struct nf_conntrack_expect *exp;
typeof(set_sig_addr_hook) set_sig_addr;
pr_debug("nf_ct_ras: ACF\n");
if (!get_h225_addr(ct, *data, &acf->destCallSignalAddress,
&addr, &port))
return 0;
if (!memcmp(&addr, &ct->tuplehash[dir].tuple.dst.u3, sizeof(addr))) {
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,
&acf->destCallSignalAddress, 1);
return 0;
}
if ((exp = nf_ct_expect_alloc(ct)) == NULL)
return -1;
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&ct->tuplehash[!dir].tuple.src.u3, &addr,
IPPROTO_TCP, NULL, &port);
exp->flags = NF_CT_EXPECT_PERMANENT;
exp->helper = nf_conntrack_helper_q931;
if (nf_ct_expect_related(exp) == 0) {
pr_debug("nf_ct_ras: expect Q.931 ");
nf_ct_dump_tuple(&exp->tuple);
} else
ret = -1;
nf_ct_expect_put(exp);
return ret;
}
static int process_gcf(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned char **data, GatekeeperConfirm *gcf)
{
int dir = CTINFO2DIR(ctinfo);
int ret = 0;
__be16 port;
union nf_inet_addr addr;
struct nf_conntrack_expect *exp;
pr_debug("nf_ct_ras: GCF\n");
if (!get_h225_addr(ct, *data, &gcf->rasAddress, &addr, &port))
return 0;
if (!memcmp(&addr, &ct->tuplehash[dir].tuple.src.u3, sizeof(addr)) &&
port == ct->tuplehash[dir].tuple.src.u.udp.port)
return 0;
if (test_bit(IPS_EXPECTED_BIT, &ct->status))
return 0;
if ((exp = nf_ct_expect_alloc(ct)) == NULL)
return -1;
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&ct->tuplehash[!dir].tuple.src.u3, &addr,
IPPROTO_UDP, NULL, &port);
exp->helper = nf_conntrack_helper_ras;
if (nf_ct_expect_related(exp) == 0) {
pr_debug("nf_ct_ras: expect RAS ");
nf_ct_dump_tuple(&exp->tuple);
} else
ret = -1;
nf_ct_expect_put(exp);
return ret;
}
static int ras_help(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
{
static RasMessage ras;
unsigned char *data;
int datalen = 0;
int ret;
pr_debug("nf_ct_ras: skblen = %u\n", skb->len);
spin_lock_bh(&nf_h323_lock);
data = get_udp_data(skb, protoff, &datalen);
if (data == NULL)
goto accept;
pr_debug("nf_ct_ras: RAS message len=%d ", datalen);
nf_ct_dump_tuple(&ct->tuplehash[CTINFO2DIR(ctinfo)].tuple);
ret = DecodeRasMessage(data, datalen, &ras);
if (ret < 0) {
pr_debug("nf_ct_ras: decoding error: %s\n",
ret == H323_ERROR_BOUND ?
"out of bound" : "out of range");
goto accept;
}
if (process_ras(skb, ct, ctinfo, &data, &ras) < 0)
goto drop;
accept:
spin_unlock_bh(&nf_h323_lock);
return NF_ACCEPT;
drop:
spin_unlock_bh(&nf_h323_lock);
if (net_ratelimit())
pr_info("nf_ct_ras: packet dropped\n");
return NF_DROP;
}
static void pptp_expectfn(struct nf_conn *ct,
struct nf_conntrack_expect *exp)
{
struct net *net = nf_ct_net(ct);
typeof(nf_nat_pptp_hook_expectfn) nf_nat_pptp_expectfn;
pr_debug("increasing timeouts\n");
/* increase timeout of GRE data channel conntrack entry */
ct->proto.gre.timeout = PPTP_GRE_TIMEOUT;
ct->proto.gre.stream_timeout = PPTP_GRE_STREAM_TIMEOUT;
/* Can you see how rusty this code is, compared with the pre-2.6.11
* one? That's what happened to my shiny newnat of 2002 ;( -HW */
rcu_read_lock();
nf_nat_pptp_expectfn = rcu_dereference(nf_nat_pptp_hook_expectfn);
if (nf_nat_pptp_expectfn && ct->master->status & IPS_NAT_MASK)
nf_nat_pptp_expectfn(ct, exp);
else {
struct nf_conntrack_tuple inv_t;
struct nf_conntrack_expect *exp_other;
/* obviously this tuple inversion only works until you do NAT */
nf_ct_invert_tuplepr(&inv_t, &exp->tuple);
pr_debug("trying to unexpect other dir: ");
nf_ct_dump_tuple(&inv_t);
exp_other = nf_ct_expect_find_get(net, &inv_t);
if (exp_other) {
/* delete other expectation. */
pr_debug("found\n");
nf_ct_unexpect_related(exp_other);
nf_ct_expect_put(exp_other);
} else {
pr_debug("not found\n");
}
}
rcu_read_unlock();
}
static int process_lcf(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned char **data, LocationConfirm *lcf)
{
int dir = CTINFO2DIR(ctinfo);
int ret = 0;
__be16 port;
union nf_inet_addr addr;
struct nf_conntrack_expect *exp;
pr_debug("nf_ct_ras: LCF\n");
if (!get_h225_addr(ct, *data, &lcf->callSignalAddress,
&addr, &port))
return 0;
if ((exp = nf_ct_expect_alloc(ct)) == NULL)
return -1;
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&ct->tuplehash[!dir].tuple.src.u3, &addr,
IPPROTO_TCP, NULL, &port);
exp->flags = NF_CT_EXPECT_PERMANENT;
exp->helper = nf_conntrack_helper_q931;
if (nf_ct_expect_related(exp) == 0) {
pr_debug("nf_ct_ras: expect Q.931 ");
nf_ct_dump_tuple(&exp->tuple);
} else
ret = -1;
nf_ct_expect_put(exp);
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;
#if defined(CONFIG_MV_ETH_NFP_CT_LEARN)
struct nf_conntrack_tuple *tupleInverseDir;
#endif
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;
#if defined(CONFIG_MV_ETH_NFP_CT_LEARN)
tupleInverseDir = &ct->tuplehash[!dir].tuple;
#endif
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 kill this session and block the SYN/ACK so
* that the client cannot but retransmit its SYN and
* thus initiate a clean new session.
*/
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: killing out of sync session ");
nf_ct_kill(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);
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 defined(CONFIG_MV_ETH_NFP_CT_LEARN)
/*
* When connection is handled by NFP, we have to relax TCP tracking
* rules as not all packets goes through Linux conntrack.
*/
if ((tuple->nfp) || (tupleInverseDir->nfp))
goto in_window;
#endif /* CONFIG_MV_ETH_NFP_CT_LEARN */
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_STATUS, ct);
}
nf_ct_refresh_acct(ct, ctinfo, skb, timeout);
return NF_ACCEPT;
}
static bool tcp_in_window(const struct nf_conn *ct,
struct ip_ct_tcp *state,
enum ip_conntrack_dir dir,
unsigned int index,
const struct sk_buff *skb,
unsigned int dataoff,
const struct tcphdr *tcph,
u_int8_t pf)
{
struct net *net = nf_ct_net(ct);
struct ip_ct_tcp_state *sender = &state->seen[dir];
struct ip_ct_tcp_state *receiver = &state->seen[!dir];
const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
__u32 seq, ack, sack, end, win, swin;
s16 receiver_offset;
bool res;
/*
* Get the required data from the packet.
*/
seq = ntohl(tcph->seq);
ack = sack = ntohl(tcph->ack_seq);
win = ntohs(tcph->window);
end = segment_seq_plus_len(seq, skb->len, dataoff, tcph);
if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM)
tcp_sack(skb, dataoff, tcph, &sack);
/* Take into account NAT sequence number mangling */
receiver_offset = NAT_OFFSET(pf, ct, !dir, ack - 1);
ack -= receiver_offset;
sack -= receiver_offset;
pr_debug("tcp_in_window: START\n");
pr_debug("tcp_in_window: ");
nf_ct_dump_tuple(tuple);
pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n",
seq, ack, receiver_offset, sack, receiver_offset, win, end);
pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
"receiver end=%u maxend=%u maxwin=%u scale=%i\n",
sender->td_end, sender->td_maxend, sender->td_maxwin,
sender->td_scale,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
if (sender->td_maxwin == 0) {
/*
* Initialize sender data.
*/
if (tcph->syn) {
/*
* SYN-ACK in reply to a SYN
* or SYN from reply direction in simultaneous open.
*/
sender->td_end =
sender->td_maxend = end;
sender->td_maxwin = (win == 0 ? 1 : win);
tcp_options(skb, dataoff, tcph, sender);
/*
* RFC 1323:
* Both sides must send the Window Scale option
* to enable window scaling in either direction.
*/
if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE
&& receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE))
sender->td_scale =
receiver->td_scale = 0;
if (!tcph->ack)
/* Simultaneous open */
return true;
} 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.
*/
sender->td_end = end;
<<<<<<< HEAD
win <<= sender->td_scale;
sender->td_maxwin = (win == 0 ? 1 : win);
sender->td_maxend = end + sender->td_maxwin;
/*
* We haven't seen traffic in the other direction yet
* but we have to tweak window tracking to pass III
* and IV until that happens.
*/
if (receiver->td_maxwin == 0)
receiver->td_end = receiver->td_maxend = sack;
=======
sender->td_maxwin = (win == 0 ? 1 : win);
sender->td_maxend = end + sender->td_maxwin;
>>>>>>> 296c66da8a02d52243f45b80521febece5ed498a
}
} else if (((state->state == TCP_CONNTRACK_SYN_SENT
static bool tcp_in_window(const struct nf_conn *ct,
struct ip_ct_tcp *state,
enum ip_conntrack_dir dir,
unsigned int index,
const struct sk_buff *skb,
unsigned int dataoff,
const struct tcphdr *tcph,
u_int8_t pf)
{
struct net *net = nf_ct_net(ct);
struct ip_ct_tcp_state *sender = &state->seen[dir];
struct ip_ct_tcp_state *receiver = &state->seen[!dir];
const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
__u32 seq, ack, sack, end, win, swin;
s16 receiver_offset;
bool res;
/*
* Get the required data from the packet.
*/
seq = ntohl(tcph->seq);
ack = sack = ntohl(tcph->ack_seq);
win = ntohs(tcph->window);
end = segment_seq_plus_len(seq, skb->len, dataoff, tcph);
if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM)
tcp_sack(skb, dataoff, tcph, &sack);
/* Take into account NAT sequence number mangling */
receiver_offset = NAT_OFFSET(pf, ct, !dir, ack - 1);
ack -= receiver_offset;
sack -= receiver_offset;
pr_debug("tcp_in_window: START\n");
pr_debug("tcp_in_window: ");
nf_ct_dump_tuple(tuple);
pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n",
seq, ack, receiver_offset, sack, receiver_offset, win, end);
pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
"receiver end=%u maxend=%u maxwin=%u scale=%i\n",
sender->td_end, sender->td_maxend, sender->td_maxwin,
sender->td_scale,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
if (sender->td_maxwin == 0) {
/*
* Initialize sender data.
*/
if (tcph->syn) {
/*
* SYN-ACK in reply to a SYN
* or SYN from reply direction in simultaneous open.
*/
sender->td_end =
sender->td_maxend = end;
sender->td_maxwin = (win == 0 ? 1 : win);
tcp_options(skb, dataoff, tcph, sender);
/*
* RFC 1323:
* Both sides must send the Window Scale option
* to enable window scaling in either direction.
*/
if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE
&& receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE))
sender->td_scale =
receiver->td_scale = 0;
if (!tcph->ack)
/* Simultaneous open */
return true;
} 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.
*/
sender->td_end = end;
sender->td_maxwin = (win == 0 ? 1 : win);
sender->td_maxend = end + sender->td_maxwin;
}
} else if (((state->state == TCP_CONNTRACK_SYN_SENT
&& dir == IP_CT_DIR_ORIGINAL)
|| (state->state == TCP_CONNTRACK_SYN_RECV
&& dir == IP_CT_DIR_REPLY))
&& after(end, sender->td_end)) {
/*
* RFC 793: "if a TCP is reinitialized ... then it need
* not wait at all; it must only be sure to use sequence
* numbers larger than those recently used."
*/
sender->td_end =
sender->td_maxend = end;
sender->td_maxwin = (win == 0 ? 1 : win);
tcp_options(skb, dataoff, tcph, sender);
}
if (!(tcph->ack)) {
/*
* If there is no ACK, just pretend it was set and OK.
*/
ack = sack = receiver->td_end;
} else if (((tcp_flag_word(tcph) & (TCP_FLAG_ACK|TCP_FLAG_RST)) ==
(TCP_FLAG_ACK|TCP_FLAG_RST))
&& (ack == 0)) {
/*
* Broken TCP stacks, that set ACK in RST packets as well
* with zero ack value.
*/
ack = sack = receiver->td_end;
}
if (seq == end
&& (!tcph->rst
|| (seq == 0 && state->state == TCP_CONNTRACK_SYN_SENT)))
/*
* Packets contains no data: we assume it is valid
* and check the ack value only.
* However RST segments are always validated by their
* SEQ number, except when seq == 0 (reset sent answering
* SYN.
*/
seq = end = sender->td_end;
pr_debug("tcp_in_window: ");
nf_ct_dump_tuple(tuple);
pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n",
seq, ack, receiver_offset, sack, receiver_offset, win, end);
pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
"receiver end=%u maxend=%u maxwin=%u scale=%i\n",
sender->td_end, sender->td_maxend, sender->td_maxwin,
sender->td_scale,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
pr_debug("tcp_in_window: I=%i II=%i III=%i IV=%i\n",
before(seq, sender->td_maxend + 1),
after(end, sender->td_end - receiver->td_maxwin - 1),
before(sack, receiver->td_end + 1),
after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1));
if (before(seq, sender->td_maxend + 1) &&
after(end, sender->td_end - receiver->td_maxwin - 1) &&
before(sack, receiver->td_end + 1) &&
after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)) {
/*
* Take into account window scaling (RFC 1323).
*/
if (!tcph->syn)
win <<= sender->td_scale;
/*
* Update sender data.
*/
swin = win + (sack - ack);
if (sender->td_maxwin < swin)
sender->td_maxwin = swin;
if (after(end, sender->td_end)) {
sender->td_end = end;
sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
}
if (tcph->ack) {
if (!(sender->flags & IP_CT_TCP_FLAG_MAXACK_SET)) {
sender->td_maxack = ack;
sender->flags |= IP_CT_TCP_FLAG_MAXACK_SET;
} else if (after(ack, sender->td_maxack))
sender->td_maxack = ack;
}
/*
* Update receiver data.
*/
if (after(end, sender->td_maxend))
receiver->td_maxwin += end - sender->td_maxend;
if (after(sack + win, receiver->td_maxend - 1)) {
receiver->td_maxend = sack + win;
if (win == 0)
receiver->td_maxend++;
}
if (ack == receiver->td_end)
receiver->flags &= ~IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
/*
* Check retransmissions.
*/
if (index == TCP_ACK_SET) {
if (state->last_dir == dir
&& state->last_seq == seq
&& state->last_ack == ack
&& state->last_end == end
&& state->last_win == win)
state->retrans++;
else {
state->last_dir = dir;
state->last_seq = seq;
state->last_ack = ack;
state->last_end = end;
state->last_win = win;
state->retrans = 0;
}
}
res = true;
} else {
res = false;
if (sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL ||
nf_ct_tcp_be_liberal)
res = true;
if (!res && LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: %s ",
before(seq, sender->td_maxend + 1) ?
after(end, sender->td_end - receiver->td_maxwin - 1) ?
before(sack, receiver->td_end + 1) ?
after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1) ? "BUG"
: "ACK is under the lower bound (possible overly delayed ACK)"
: "ACK is over the upper bound (ACKed data not seen yet)"
: "SEQ is under the lower bound (already ACKed data retransmitted)"
: "SEQ is over the upper bound (over the window of the receiver)");
}
pr_debug("tcp_in_window: res=%u sender end=%u maxend=%u maxwin=%u "
"receiver end=%u maxend=%u maxwin=%u\n",
res, sender->td_end, sender->td_maxend, sender->td_maxwin,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin);
return res;
}
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,
unsigned int *timeouts)
{
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;
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)) {
spin_unlock_bh(&ct->lock);
if (nf_ct_kill(ct))
return -NF_REPEAT;
return NF_DROP;
}
case TCP_CONNTRACK_IGNORE:
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) {
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);
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:
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)) {
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) {
goto in_window;
}
default:
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:
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 &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS])
timeout = timeouts[TCP_CONNTRACK_RETRANS];
else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) &
IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK])
timeout = timeouts[TCP_CONNTRACK_UNACK];
else
timeout = 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 (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_bit(IPS_ASSURED_BIT, &ct->status);
nf_conntrack_event_cache(IPCT_ASSURED, ct);
}
nf_ct_refresh_acct(ct, ctinfo, skb, timeout);
return NF_ACCEPT;
}
/* Returns verdict for packet, or -1 for invalid. */
static int tcp_packet(struct nf_conn *ct,
struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
const struct nf_hook_state *state)
{
struct net *net = nf_ct_net(ct);
struct nf_tcp_net *tn = nf_tcp_pernet(net);
struct nf_conntrack_tuple *tuple;
enum tcp_conntrack new_state, old_state;
unsigned int index, *timeouts;
enum ip_conntrack_dir dir;
const struct tcphdr *th;
struct tcphdr _tcph;
unsigned long timeout;
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
if (th == NULL)
return -NF_ACCEPT;
if (tcp_error(th, skb, dataoff, state))
return -NF_ACCEPT;
if (!nf_ct_is_confirmed(ct) && !tcp_new(ct, skb, dataoff, th))
return -NF_ACCEPT;
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.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK;
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 potentially
* responds with a challenge ACK if implementing RFC5961.
*/
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;
}
/* Mark the potential for RFC5961 challenge ACK,
* this pose a special problem for LAST_ACK state
* as ACK is intrepretated as ACKing last FIN.
*/
if (old_state == TCP_CONNTRACK_LAST_ACK)
ct->proto.tcp.last_flags |=
IP_CT_EXP_CHALLENGE_ACK;
}
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, "invalid packet ignored in "
"state %s ", tcp_conntrack_names[old_state]);
return NF_ACCEPT;
case TCP_CONNTRACK_MAX:
/* Special case for SYN proxy: when the SYN to the server or
* the SYN/ACK from the server is lost, the client may transmit
* a keep-alive packet while in SYN_SENT state. This needs to
* be associated with the original conntrack entry in order to
* generate a new SYN with the correct sequence number.
*/
if (nfct_synproxy(ct) && old_state == TCP_CONNTRACK_SYN_SENT &&
index == TCP_ACK_SET && dir == IP_CT_DIR_ORIGINAL &&
ct->proto.tcp.last_dir == IP_CT_DIR_ORIGINAL &&
ct->proto.tcp.seen[dir].td_end - 1 == ntohl(th->seq)) {
pr_debug("nf_ct_tcp: SYN proxy client keep alive\n");
spin_unlock_bh(&ct->lock);
return NF_ACCEPT;
}
/* 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);
nf_ct_l4proto_log_invalid(skb, ct, "invalid state");
return -NF_ACCEPT;
case TCP_CONNTRACK_TIME_WAIT:
/* RFC5961 compliance cause stack to send "challenge-ACK"
* e.g. in response to spurious SYNs. Conntrack MUST
* not believe this ACK is acking last FIN.
*/
if (old_state == TCP_CONNTRACK_LAST_ACK &&
index == TCP_ACK_SET &&
ct->proto.tcp.last_dir != dir &&
ct->proto.tcp.last_index == TCP_SYN_SET &&
(ct->proto.tcp.last_flags & IP_CT_EXP_CHALLENGE_ACK)) {
/* Detected RFC5961 challenge ACK */
ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK;
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, "challenge-ack ignored");
return NF_ACCEPT; /* Don't change state */
}
break;
case TCP_CONNTRACK_SYN_SENT2:
/* tcp_conntracks table is not smart enough to handle
* simultaneous open.
*/
ct->proto.tcp.last_flags |= IP_CT_TCP_SIMULTANEOUS_OPEN;
break;
case TCP_CONNTRACK_SYN_RECV:
if (dir == IP_CT_DIR_REPLY && index == TCP_ACK_SET &&
ct->proto.tcp.last_flags & IP_CT_TCP_SIMULTANEOUS_OPEN)
new_state = TCP_CONNTRACK_ESTABLISHED;
break;
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);
nf_ct_l4proto_log_invalid(skb, ct, "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)) {
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;
timeouts = nf_ct_timeout_lookup(ct);
if (!timeouts)
timeouts = tn->timeouts;
if (ct->proto.tcp.retrans >= tn->tcp_max_retrans &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS])
timeout = timeouts[TCP_CONNTRACK_RETRANS];
else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) &
IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK])
timeout = timeouts[TCP_CONNTRACK_UNACK];
else if (ct->proto.tcp.last_win == 0 &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS])
timeout = timeouts[TCP_CONNTRACK_RETRANS];
else
timeout = 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;
}
/* ESTABLISHED without SEEN_REPLY, i.e. mid-connection
* pickup with loose=1. Avoid large ESTABLISHED timeout.
*/
if (new_state == TCP_CONNTRACK_ESTABLISHED &&
timeout > timeouts[TCP_CONNTRACK_UNACK])
timeout = timeouts[TCP_CONNTRACK_UNACK];
} 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 tcp_in_window(const struct nf_conn *ct,
struct ip_ct_tcp *state,
enum ip_conntrack_dir dir,
unsigned int index,
const struct sk_buff *skb,
unsigned int dataoff,
const struct tcphdr *tcph,
u_int8_t pf)
{
struct net *net = nf_ct_net(ct);
struct ip_ct_tcp_state *sender = &state->seen[dir];
struct ip_ct_tcp_state *receiver = &state->seen[!dir];
const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
__u32 seq, ack, sack, end, win, swin;
s16 receiver_offset;
bool res;
seq = ntohl(tcph->seq);
ack = sack = ntohl(tcph->ack_seq);
win = ntohs(tcph->window);
end = segment_seq_plus_len(seq, skb->len, dataoff, tcph);
if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM)
tcp_sack(skb, dataoff, tcph, &sack);
receiver_offset = NAT_OFFSET(pf, ct, !dir, ack - 1);
ack -= receiver_offset;
sack -= receiver_offset;
pr_debug("tcp_in_window: START\n");
pr_debug("tcp_in_window: ");
nf_ct_dump_tuple(tuple);
pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n",
seq, ack, receiver_offset, sack, receiver_offset, win, end);
pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
"receiver end=%u maxend=%u maxwin=%u scale=%i\n",
sender->td_end, sender->td_maxend, sender->td_maxwin,
sender->td_scale,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
if (sender->td_maxwin == 0) {
if (tcph->syn) {
sender->td_end =
sender->td_maxend = end;
sender->td_maxwin = (win == 0 ? 1 : win);
tcp_options(skb, dataoff, tcph, sender);
if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE
&& receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE))
sender->td_scale =
receiver->td_scale = 0;
if (!tcph->ack)
return true;
} else {
sender->td_end = end;
swin = win << sender->td_scale;
sender->td_maxwin = (swin == 0 ? 1 : swin);
sender->td_maxend = end + sender->td_maxwin;
if (receiver->td_maxwin == 0)
receiver->td_end = receiver->td_maxend = sack;
}
} else if (((state->state == TCP_CONNTRACK_SYN_SENT
&& dir == IP_CT_DIR_ORIGINAL)
|| (state->state == TCP_CONNTRACK_SYN_RECV
&& dir == IP_CT_DIR_REPLY))
&& after(end, sender->td_end)) {
sender->td_end =
sender->td_maxend = end;
sender->td_maxwin = (win == 0 ? 1 : win);
tcp_options(skb, dataoff, tcph, sender);
}
if (!(tcph->ack)) {
ack = sack = receiver->td_end;
} else if (((tcp_flag_word(tcph) & (TCP_FLAG_ACK|TCP_FLAG_RST)) ==
(TCP_FLAG_ACK|TCP_FLAG_RST))
&& (ack == 0)) {
ack = sack = receiver->td_end;
}
if (seq == end
&& (!tcph->rst
|| (seq == 0 && state->state == TCP_CONNTRACK_SYN_SENT)))
seq = end = sender->td_end;
pr_debug("tcp_in_window: ");
nf_ct_dump_tuple(tuple);
pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n",
seq, ack, receiver_offset, sack, receiver_offset, win, end);
pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
"receiver end=%u maxend=%u maxwin=%u scale=%i\n",
sender->td_end, sender->td_maxend, sender->td_maxwin,
sender->td_scale,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
pr_debug("tcp_in_window: I=%i II=%i III=%i IV=%i\n",
before(seq, sender->td_maxend + 1),
after(end, sender->td_end - receiver->td_maxwin - 1),
before(sack, receiver->td_end + 1),
after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1));
if (before(seq, sender->td_maxend + 1) &&
after(end, sender->td_end - receiver->td_maxwin - 1) &&
before(sack, receiver->td_end + 1) &&
after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)) {
if (!tcph->syn)
win <<= sender->td_scale;
swin = win + (sack - ack);
if (sender->td_maxwin < swin)
sender->td_maxwin = swin;
if (after(end, sender->td_end)) {
sender->td_end = end;
sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
}
if (tcph->ack) {
if (!(sender->flags & IP_CT_TCP_FLAG_MAXACK_SET)) {
sender->td_maxack = ack;
sender->flags |= IP_CT_TCP_FLAG_MAXACK_SET;
} else if (after(ack, sender->td_maxack))
sender->td_maxack = ack;
}
if (receiver->td_maxwin != 0 && after(end, sender->td_maxend))
receiver->td_maxwin += end - sender->td_maxend;
if (after(sack + win, receiver->td_maxend - 1)) {
receiver->td_maxend = sack + win;
if (win == 0)
receiver->td_maxend++;
}
if (ack == receiver->td_end)
receiver->flags &= ~IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
if (index == TCP_ACK_SET) {
if (state->last_dir == dir
&& state->last_seq == seq
&& state->last_ack == ack
&& state->last_end == end
&& state->last_win == win)
state->retrans++;
else {
state->last_dir = dir;
state->last_seq = seq;
state->last_ack = ack;
state->last_end = end;
state->last_win = win;
state->retrans = 0;
}
}
res = true;
} else {
res = false;
if (sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL ||
nf_ct_tcp_be_liberal)
res = true;
if (!res && LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: %s ",
before(seq, sender->td_maxend + 1) ?
after(end, sender->td_end - receiver->td_maxwin - 1) ?
before(sack, receiver->td_end + 1) ?
after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1) ? "BUG"
: "ACK is under the lower bound (possible overly delayed ACK)"
: "ACK is over the upper bound (ACKed data not seen yet)"
: "SEQ is under the lower bound (already ACKed data retransmitted)"
: "SEQ is over the upper bound (over the window of the receiver)");
}
pr_debug("tcp_in_window: res=%u sender end=%u maxend=%u maxwin=%u "
"receiver end=%u maxend=%u maxwin=%u\n",
res, sender->td_end, sender->td_maxend, sender->td_maxwin,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin);
return res;
}
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+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;
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;
}
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;
}
static int
cone_nat_help(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
{
int dir = CTINFO2DIR(ctinfo);
struct nf_conntrack_expect *exp;
struct nf_conntrack_tuple *tuple;
union nf_inet_addr *src_addr = NULL;
__be16 *src_port = NULL;
int ret = NF_ACCEPT;
if (ctinfo == IP_CT_ESTABLISHED || dir != IP_CT_DIR_ORIGINAL)
return NF_ACCEPT;
pr_debug("skb[%p] ctinfo[%d] dir[%d]\n", skb, ctinfo, dir);
pr_debug("packet[%d bytes] "
"%pI4:%hu->%pI4:%hu, "
"reply: %pI4:%hu->%pI4:%hu\n",
skb->len,
&(ct->tuplehash[dir].tuple.src.u3.ip),
ntohs(ct->tuplehash[dir].tuple.src.u.udp.port),
&(ct->tuplehash[dir].tuple.dst.u3.ip),
ntohs(ct->tuplehash[dir].tuple.dst.u.udp.port),
&(ct->tuplehash[!dir].tuple.src.u3.ip),
ntohs(ct->tuplehash[!dir].tuple.src.u.udp.port),
&(ct->tuplehash[!dir].tuple.dst.u3.ip),
ntohs(ct->tuplehash[!dir].tuple.dst.u.udp.port));
/* Create expect */
if ((exp = nf_ct_expect_alloc(ct)) == NULL)
return NF_ACCEPT;
/*
IP_CT_DIR_REPLY
0 - symmetric nat
1 - full, *:* -> natip:natport -> lanip:lanport
2 - restricted, wanip:* -> natip:natport -> lanip:lanport
3 - port restricted, wanip:wanport -> natip:natport -> lanip:lanport
*/
tuple = &ct->tuplehash[!dir].tuple;
switch (conenat_type)
{
case 1:
src_addr = NULL;
src_port = NULL;
break;
case 2:
src_addr = &tuple->src.u3;
src_port = NULL;
break;
case 3:
src_addr = &tuple->src.u3;
src_port = &tuple->src.u.udp.port;
break;
default:
src_addr = NULL;
src_port = NULL;
break;
}
nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT,
nf_ct_l3num(ct),
src_addr, &tuple->dst.u3,
tuple->dst.protonum,
src_port, &tuple->dst.u.udp.port);
exp->dir = !dir;
exp->flags = NF_CT_EXPECT_PERMANENT;
exp->saved_ip = ct->tuplehash[dir].tuple.src.u3.ip;
exp->saved_proto = ct->tuplehash[dir].tuple.src.u;
exp->expectfn = cone_nat_expect;
pr_debug("save %pI4:%hu, ",
&exp->saved_ip, ntohs(exp->saved_proto.udp.port));
nf_ct_dump_tuple(&exp->tuple);
/* Setup expect */
ret = nf_ct_expect_related(exp);
nf_ct_expect_put(exp);
if (ret == 0)
{
pr_debug("expect setup, skb=%p, ret=%d.\n", skb, ret);
}
else
{
pr_debug("expect setup failed.\n");
}
return NF_ACCEPT;
}
static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned char **data, int dataoff,
H245_TransportAddress *taddr)
{
int dir = CTINFO2DIR(ctinfo);
int ret = 0;
__be16 port;
__be16 rtp_port, rtcp_port;
union nf_inet_addr addr;
struct nf_conntrack_expect *rtp_exp;
struct nf_conntrack_expect *rtcp_exp;
typeof(nat_rtp_rtcp_hook) nat_rtp_rtcp;
if (!get_h245_addr(ct, *data, taddr, &addr, &port) ||
memcmp(&addr, &ct->tuplehash[dir].tuple.src.u3, sizeof(addr)) ||
port == 0)
return 0;
port &= htons(~1);
rtp_port = port;
rtcp_port = htons(ntohs(port) + 1);
if ((rtp_exp = nf_ct_expect_alloc(ct)) == NULL)
return -1;
nf_ct_expect_init(rtp_exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&ct->tuplehash[!dir].tuple.src.u3,
&ct->tuplehash[!dir].tuple.dst.u3,
IPPROTO_UDP, NULL, &rtp_port);
if ((rtcp_exp = nf_ct_expect_alloc(ct)) == NULL) {
nf_ct_expect_put(rtp_exp);
return -1;
}
nf_ct_expect_init(rtcp_exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
&ct->tuplehash[!dir].tuple.src.u3,
&ct->tuplehash[!dir].tuple.dst.u3,
IPPROTO_UDP, NULL, &rtcp_port);
if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
&ct->tuplehash[!dir].tuple.dst.u3,
sizeof(ct->tuplehash[dir].tuple.src.u3)) &&
(nat_rtp_rtcp = rcu_dereference(nat_rtp_rtcp_hook)) &&
ct->status & IPS_NAT_MASK) {
ret = nat_rtp_rtcp(skb, ct, ctinfo, data, dataoff,
taddr, port, rtp_port, rtp_exp, rtcp_exp);
} else {
if (nf_ct_expect_related(rtp_exp) == 0) {
if (nf_ct_expect_related(rtcp_exp) == 0) {
pr_debug("nf_ct_h323: expect RTP ");
nf_ct_dump_tuple(&rtp_exp->tuple);
pr_debug("nf_ct_h323: expect RTCP ");
nf_ct_dump_tuple(&rtcp_exp->tuple);
} else {
nf_ct_unexpect_related(rtp_exp);
ret = -1;
}
} else
ret = -1;
}
nf_ct_expect_put(rtp_exp);
nf_ct_expect_put(rtcp_exp);
return ret;
}
