static int
icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff,
enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum)
{
const struct icmp6hdr *icmp6h;
struct icmp6hdr _ih;
int type;
icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih);
if (icmp6h == NULL) {
if (LOG_INVALID(net, IPPROTO_ICMPV6))
nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
"nf_ct_icmpv6: short packet ");
return -NF_ACCEPT;
}
if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) {
if (LOG_INVALID(net, IPPROTO_ICMPV6))
nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
"nf_ct_icmpv6: ICMPv6 checksum failed ");
return -NF_ACCEPT;
}
type = icmp6h->icmp6_type - 130;
if (type >= 0 && type < sizeof(noct_valid_new) &&
noct_valid_new[type]) {
skb->nfct = &nf_conntrack_untracked.ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
return NF_ACCEPT;
}
if (icmp6h->icmp6_type >= 128)
return NF_ACCEPT;
return icmpv6_error_message(net, skb, dataoff, ctinfo, hooknum);
}
static int dccp_error(struct net *net, struct nf_conn *tmpl,
struct sk_buff *skb, unsigned int dataoff,
enum ip_conntrack_info *ctinfo,
u_int8_t pf, unsigned int hooknum)
{
struct dccp_hdr _dh, *dh;
unsigned int dccp_len = skb->len - dataoff;
unsigned int cscov;
const char *msg;
dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
if (dh == NULL) {
msg = "nf_ct_dccp: short packet ";
goto out_invalid;
}
if (dh->dccph_doff * 4 < sizeof(struct dccp_hdr) ||
dh->dccph_doff * 4 > dccp_len) {
msg = "nf_ct_dccp: truncated/malformed packet ";
goto out_invalid;
}
cscov = dccp_len;
if (dh->dccph_cscov) {
cscov = (dh->dccph_cscov - 1) * 4;
if (cscov > dccp_len) {
msg = "nf_ct_dccp: bad checksum coverage ";
goto out_invalid;
}
}
if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
nf_checksum_partial(skb, hooknum, dataoff, cscov, IPPROTO_DCCP,
pf)) {
msg = "nf_ct_dccp: bad checksum ";
goto out_invalid;
}
if (dh->dccph_type >= DCCP_PKT_INVALID) {
msg = "nf_ct_dccp: reserved packet type ";
goto out_invalid;
}
return NF_ACCEPT;
out_invalid:
if (LOG_INVALID(net, IPPROTO_DCCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL, msg);
return -NF_ACCEPT;
}
static unsigned int ipv4_confirm(const struct nf_hook_ops *ops,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
const struct nf_conn_help *help;
const struct nf_conntrack_helper *helper;
unsigned int ret;
/* This is where we call the helper: as the packet goes out. */
ct = nf_ct_get(skb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED_REPLY)
goto out;
help = nfct_help(ct);
if (!help)
goto out;
/* rcu_read_lock()ed by nf_hook_slow */
helper = rcu_dereference(help->helper);
if (!helper)
goto out;
ret = helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb),
ct, ctinfo);
if (ret != NF_ACCEPT) {
nf_log_packet(NFPROTO_IPV4, ops->hooknum, skb, in, out, NULL,
"nf_ct_%s: dropping packet", helper->name);
return ret;
}
/* adjust seqs for loopback traffic only in outgoing direction */
if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
!nf_is_loopback_packet(skb)) {
typeof(nf_nat_seq_adjust_hook) seq_adjust;
seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
if (!seq_adjust || !seq_adjust(skb, ct, ctinfo)) {
NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
return NF_DROP;
}
}
out:
/* We've seen it coming out the other side: confirm it */
return nf_conntrack_confirm(skb);
}
static unsigned int ipv4_confirm(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
const struct nf_conn_help *help;
const struct nf_conntrack_helper *helper;
unsigned int ret;
ct = nf_ct_get(skb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED_REPLY)
goto out;
help = nfct_help(ct);
if (!help)
goto out;
helper = rcu_dereference(help->helper);
if (!helper)
goto out;
ret = helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb),
ct, ctinfo);
if (ret != NF_ACCEPT) {
nf_log_packet(NFPROTO_IPV4, hooknum, skb, in, out, NULL,
"nf_ct_%s: dropping packet", helper->name);
return ret;
}
if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
!nf_is_loopback_packet(skb)) {
typeof(nf_nat_seq_adjust_hook) seq_adjust;
seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
if (!seq_adjust || !seq_adjust(skb, ct, ctinfo)) {
NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
return NF_DROP;
}
}
out:
return nf_conntrack_confirm(skb);
}
static void nf_log_bridge_packet(struct net *net, u_int8_t pf,
unsigned int hooknum,
const struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
const struct nf_loginfo *loginfo,
const char *prefix)
{
switch (eth_hdr(skb)->h_proto) {
case htons(ETH_P_IP):
nf_log_packet(net, NFPROTO_IPV4, hooknum, skb, in, out,
loginfo, "%s", prefix);
break;
case htons(ETH_P_IPV6):
nf_log_packet(net, NFPROTO_IPV6, hooknum, skb, in, out,
loginfo, "%s", prefix);
break;
case htons(ETH_P_ARP):
case htons(ETH_P_RARP):
nf_log_packet(net, NFPROTO_ARP, hooknum, skb, in, out,
loginfo, "%s", prefix);
break;
}
}
static unsigned int
ebt_nflog_tg(struct sk_buff *skb, const struct xt_target_param *par)
{
const struct ebt_nflog_info *info = par->targinfo;
struct nf_loginfo li;
li.type = NF_LOG_TYPE_ULOG;
li.u.ulog.copy_len = info->len;
li.u.ulog.group = info->group;
li.u.ulog.qthreshold = info->threshold;
nf_log_packet(PF_BRIDGE, par->hooknum, skb, par->in, par->out,
&li, "%s", info->prefix);
return EBT_CONTINUE;
}
static void ebt_nflog(const struct sk_buff *skb,
unsigned int hooknr,
const struct net_device *in,
const struct net_device *out,
const void *data, unsigned int datalen)
{
struct ebt_nflog_info *info = (struct ebt_nflog_info *)data;
struct nf_loginfo li;
li.type = NF_LOG_TYPE_ULOG;
li.u.ulog.copy_len = info->len;
li.u.ulog.group = info->group;
li.u.ulog.qthreshold = info->threshold;
nf_log_packet(PF_BRIDGE, hooknr, skb, in, out, &li, "%s", info->prefix);
}
static unsigned int
ebt_log_tg(struct sk_buff *skb, const struct xt_action_param *par) {
const struct ebt_log_info *info = par->targinfo;
struct nf_loginfo li;
li.type = NF_LOG_TYPE_LOG;
li.u.log.level = info->loglevel;
li.u.log.logflags = info->bitmask;
if (info->bitmask & EBT_LOG_NFLOG)
nf_log_packet(NFPROTO_BRIDGE, par->hooknum, skb, par->in,
par->out, &li, "%s", info->prefix);
else
ebt_log_packet(NFPROTO_BRIDGE, par->hooknum, skb, par->in,
par->out, &li, info->prefix);
return EBT_CONTINUE;
}
static unsigned int
nflog_tg(struct sk_buff *skb, const struct net_device *in,
const struct net_device *out, unsigned int hooknum,
const struct xt_target *target, const void *targinfo)
{
const struct xt_nflog_info *info = targinfo;
struct nf_loginfo li;
li.type = NF_LOG_TYPE_ULOG;
li.u.ulog.copy_len = info->len;
li.u.ulog.group = info->group;
li.u.ulog.qthreshold = info->threshold;
nf_log_packet(target->family, hooknum, skb, in, out, &li,
"%s", info->prefix);
return XT_CONTINUE;
}
static void ebt_log(const struct sk_buff *skb, unsigned int hooknr,
const struct net_device *in, const struct net_device *out,
const void *data, unsigned int datalen)
{
struct ebt_log_info *info = (struct ebt_log_info *)data;
struct nf_loginfo li;
li.type = NF_LOG_TYPE_LOG;
li.u.log.level = info->loglevel;
li.u.log.logflags = info->bitmask;
if (info->bitmask & EBT_LOG_NFLOG)
nf_log_packet(PF_BRIDGE, hooknr, skb, in, out, &li,
"%s", info->prefix);
else
ebt_log_packet(PF_BRIDGE, hooknr, skb, in, out, &li,
info->prefix);
}
static unsigned int
ipt_log_target(struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
unsigned int hooknum,
const void *targinfo,
void *userinfo)
{
const struct ipt_log_info *loginfo = targinfo;
struct nf_loginfo li;
li.type = NF_LOG_TYPE_LOG;
li.u.log.level = loginfo->level;
li.u.log.logflags = loginfo->logflags;
nf_log_packet(PF_INET, hooknum, *pskb, in, out, &li, loginfo->prefix);
return IPT_CONTINUE;
}
void nf_l4proto_log_invalid(const struct sk_buff *skb,
struct net *net,
u16 pf, u8 protonum,
const char *fmt, ...)
{
struct va_format vaf;
va_list args;
if (net->ct.sysctl_log_invalid != protonum ||
net->ct.sysctl_log_invalid != IPPROTO_RAW)
return;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL,
"nf_ct_proto_%d: %pV ", protonum, &vaf);
va_end(args);
}
static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
unsigned int dataoff, unsigned int *timeouts)
{
struct net *net = nf_ct_net(ct);
struct dccp_net *dn;
struct dccp_hdr _dh, *dh;
const char *msg;
u_int8_t state;
dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
BUG_ON(dh == NULL);
state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE];
switch (state) {
default:
dn = dccp_pernet(net);
if (dn->dccp_loose == 0) {
msg = "nf_ct_dccp: not picking up existing connection ";
goto out_invalid;
}
case CT_DCCP_REQUEST:
break;
case CT_DCCP_INVALID:
msg = "nf_ct_dccp: invalid state transition ";
goto out_invalid;
}
ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT;
ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER;
ct->proto.dccp.state = CT_DCCP_NONE;
ct->proto.dccp.last_pkt = DCCP_PKT_REQUEST;
ct->proto.dccp.last_dir = IP_CT_DIR_ORIGINAL;
ct->proto.dccp.handshake_seq = 0;
return true;
out_invalid:
if (LOG_INVALID(net, IPPROTO_DCCP))
nf_log_packet(net, nf_ct_l3num(ct), 0, skb, NULL, NULL,
NULL, "%s", msg);
return false;
}
/* Called when a new connection for this protocol found. */
static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb,
unsigned int dataoff)
{
static const u_int8_t valid_new[] = {
[ICMPV6_ECHO_REQUEST - 128] = 1,
[ICMPV6_NI_QUERY - 128] = 1
};
int type = ct->tuplehash[0].tuple.dst.u.icmp.type - 128;
if (type < 0 || type >= sizeof(valid_new) || !valid_new[type]) {
/* Can't create a new ICMPv6 `conn' with this. */
pr_debug("icmpv6: can't create new conn with type %u\n",
type + 128);
nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple);
if (LOG_INVALID(nf_ct_net(ct), IPPROTO_ICMPV6))
nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
"nf_ct_icmpv6: invalid new with type %d ",
type + 128);
return false;
}
return true;
}
static unsigned int
ebt_log_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ebt_log_info *info = par->targinfo;
struct nf_loginfo li;
struct net *net = xt_net(par);
li.type = NF_LOG_TYPE_LOG;
li.u.log.level = info->loglevel;
li.u.log.logflags = info->bitmask;
/* Remember that we have to use ebt_log_packet() not to break backward
* compatibility. We cannot use the default bridge packet logger via
* nf_log_packet() with NFT_LOG_TYPE_LOG here. --Pablo
*/
if (info->bitmask & EBT_LOG_NFLOG)
nf_log_packet(net, NFPROTO_BRIDGE, xt_hooknum(par), skb,
xt_in(par), xt_out(par), &li, "%s",
info->prefix);
else
ebt_log_packet(net, NFPROTO_BRIDGE, xt_hooknum(par), skb,
xt_in(par), xt_out(par), &li, info->prefix);
return EBT_CONTINUE;
}
/* Returns verdict for packet, or -1 for invalid. */
static int tcp_packet(struct ip_conntrack *conntrack,
const struct sk_buff *skb,
enum ip_conntrack_info ctinfo)
{
enum tcp_conntrack new_state, old_state;
enum ip_conntrack_dir dir;
struct iphdr *iph = skb->nh.iph;
struct tcphdr *th, _tcph;
unsigned long timeout;
unsigned int index;
th = skb_header_pointer(skb, iph->ihl * 4,
sizeof(_tcph), &_tcph);
BUG_ON(th == NULL);
WRITE_LOCK(&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:
/* Either SYN in ORIGINAL
* or SYN/ACK in REPLY
* or ACK in REPLY direction (half-open connection). */
if (index == TCP_SYNACK_SET
&& conntrack->proto.tcp.last_index == TCP_SYN_SET
&& conntrack->proto.tcp.last_dir != dir
&& after(ntohl(th->ack_seq),
conntrack->proto.tcp.last_seq)) {
/* 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(&tcp_lock);
if (LOG_INVALID(IPPROTO_TCP))
nf_log_packet(PF_INET, 0, skb, NULL, NULL,
"ip_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);
WRITE_UNLOCK(&tcp_lock);
if (LOG_INVALID(IPPROTO_TCP))
nf_log_packet(PF_INET, 0, skb, NULL, NULL,
"ip_ct_tcp: invalid packet ignored ");
return NF_ACCEPT;
case TCP_CONNTRACK_MAX:
/* Invalid packet */
DEBUGP("ip_ct_tcp: Invalid dir=%i index=%u ostate=%u\n",
dir, get_conntrack_index(th),
old_state);
WRITE_UNLOCK(&tcp_lock);
if (LOG_INVALID(IPPROTO_TCP))
nf_log_packet(PF_INET, 0, skb, NULL, NULL,
"ip_ct_tcp: invalid state ");
return -NF_ACCEPT;
case TCP_CONNTRACK_SYN_SENT:
if (old_state >= TCP_CONNTRACK_TIME_WAIT) {
/* Attempt to reopen a closed connection.
* Delete this connection and look up again. */
WRITE_UNLOCK(&tcp_lock);
if (del_timer(&conntrack->timeout))
conntrack->timeout.function((unsigned long)
conntrack);
return -NF_REPEAT;
}
break;
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
&& ((test_bit(IPS_SEEN_REPLY_BIT, &conntrack->status)
&& conntrack->proto.tcp.last_index <= TCP_SYNACK_SET)
|| (!test_bit(IPS_ASSURED_BIT, &conntrack->status)
&& conntrack->proto.tcp.last_index == TCP_ACK_SET))
&& after(ntohl(th->ack_seq),
conntrack->proto.tcp.last_seq)) {
/* Ignore RST closing down invalid SYN or ACK
we had let trough. */
WRITE_UNLOCK(&tcp_lock);
if (LOG_INVALID(IPPROTO_TCP))
nf_log_packet(PF_INET, 0, skb, NULL, NULL,
"ip_ct_tcp: invalid RST (ignored) ");
return NF_ACCEPT;
}
/* Just fall trough */
default:
/* Keep compilers happy. */
break;
}
if (!tcp_in_window(&conntrack->proto.tcp, dir, &index,
skb, iph, th)) {
WRITE_UNLOCK(&tcp_lock);
return -NF_ACCEPT;
}
/* From now on we have got in-window packets */
/* If FIN was trimmed off, we don't change state. */
conntrack->proto.tcp.last_index = index;
new_state = tcp_conntracks[dir][index][old_state];
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;
timeout = conntrack->proto.tcp.retrans >= ip_ct_tcp_max_retrans
&& *tcp_timeouts[new_state] > ip_ct_tcp_timeout_max_retrans
? ip_ct_tcp_timeout_max_retrans : *tcp_timeouts[new_state];
WRITE_UNLOCK(&tcp_lock);
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);
}
ip_ct_refresh_acct(conntrack, ctinfo, skb, timeout);
return NF_ACCEPT;
}
static int dccp_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);
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
struct dccp_hdr _dh, *dh;
u_int8_t type, old_state, new_state;
enum ct_dccp_roles role;
dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
BUG_ON(dh == NULL);
type = dh->dccph_type;
if (type == DCCP_PKT_RESET &&
!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
/* Tear down connection immediately if only reply is a RESET */
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
spin_lock_bh(&ct->lock);
role = ct->proto.dccp.role[dir];
old_state = ct->proto.dccp.state;
new_state = dccp_state_table[role][type][old_state];
switch (new_state) {
case CT_DCCP_REQUEST:
if (old_state == CT_DCCP_TIMEWAIT &&
role == CT_DCCP_ROLE_SERVER) {
/* Reincarnation in the reverse direction: reopen and
* reverse client/server roles. */
ct->proto.dccp.role[dir] = CT_DCCP_ROLE_CLIENT;
ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_SERVER;
}
break;
case CT_DCCP_RESPOND:
if (old_state == CT_DCCP_REQUEST)
ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh);
break;
case CT_DCCP_PARTOPEN:
if (old_state == CT_DCCP_RESPOND &&
type == DCCP_PKT_ACK &&
dccp_ack_seq(dh) == ct->proto.dccp.handshake_seq)
set_bit(IPS_ASSURED_BIT, &ct->status);
break;
case CT_DCCP_IGNORE:
/*
* Connection tracking might be out of sync, so we ignore
* packets that might establish a new connection and resync
* if the server responds with a valid Response.
*/
if (ct->proto.dccp.last_dir == !dir &&
ct->proto.dccp.last_pkt == DCCP_PKT_REQUEST &&
type == DCCP_PKT_RESPONSE) {
ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_CLIENT;
ct->proto.dccp.role[dir] = CT_DCCP_ROLE_SERVER;
ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh);
new_state = CT_DCCP_RESPOND;
break;
}
ct->proto.dccp.last_dir = dir;
ct->proto.dccp.last_pkt = type;
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_DCCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_dccp: invalid packet ignored ");
return NF_ACCEPT;
case CT_DCCP_INVALID:
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_DCCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_dccp: invalid state transition ");
return -NF_ACCEPT;
}
ct->proto.dccp.last_dir = dir;
ct->proto.dccp.last_pkt = type;
ct->proto.dccp.state = new_state;
spin_unlock_bh(&ct->lock);
if (new_state != old_state)
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);
return NF_ACCEPT;
}
/* 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;
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 dccp_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 dccp_net *dn;
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
struct dccp_hdr _dh, *dh;
u_int8_t type, old_state, new_state;
enum ct_dccp_roles role;
dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
BUG_ON(dh == NULL);
type = dh->dccph_type;
if (type == DCCP_PKT_RESET &&
!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
spin_lock_bh(&ct->lock);
role = ct->proto.dccp.role[dir];
old_state = ct->proto.dccp.state;
new_state = dccp_state_table[role][type][old_state];
switch (new_state) {
case CT_DCCP_REQUEST:
if (old_state == CT_DCCP_TIMEWAIT &&
role == CT_DCCP_ROLE_SERVER) {
ct->proto.dccp.role[dir] = CT_DCCP_ROLE_CLIENT;
ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_SERVER;
}
break;
case CT_DCCP_RESPOND:
if (old_state == CT_DCCP_REQUEST)
ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh);
break;
case CT_DCCP_PARTOPEN:
if (old_state == CT_DCCP_RESPOND &&
type == DCCP_PKT_ACK &&
dccp_ack_seq(dh) == ct->proto.dccp.handshake_seq)
set_bit(IPS_ASSURED_BIT, &ct->status);
break;
case CT_DCCP_IGNORE:
if (ct->proto.dccp.last_dir == !dir &&
ct->proto.dccp.last_pkt == DCCP_PKT_REQUEST &&
type == DCCP_PKT_RESPONSE) {
ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_CLIENT;
ct->proto.dccp.role[dir] = CT_DCCP_ROLE_SERVER;
ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh);
new_state = CT_DCCP_RESPOND;
break;
}
ct->proto.dccp.last_dir = dir;
ct->proto.dccp.last_pkt = type;
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_DCCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_dccp: invalid packet ignored ");
return NF_ACCEPT;
case CT_DCCP_INVALID:
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_DCCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_dccp: invalid state transition ");
return -NF_ACCEPT;
}
ct->proto.dccp.last_dir = dir;
ct->proto.dccp.last_pkt = type;
ct->proto.dccp.state = new_state;
spin_unlock_bh(&ct->lock);
if (new_state != old_state)
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
dn = dccp_pernet(net);
nf_ct_refresh_acct(ct, ctinfo, skb, dn->dccp_timeout[new_state]);
return NF_ACCEPT;
}
static unsigned int
ip_nat_fn(unsigned int hooknum,
struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct ip_conntrack *ct;
enum ip_conntrack_info ctinfo;
struct ip_nat_info *info;
/* maniptype == SRC for postrouting. */
enum ip_nat_manip_type maniptype = HOOK2MANIP(hooknum);
/* We never see fragments: conntrack defrags on pre-routing
and local-out, and ip_nat_out protects post-routing. */
IP_NF_ASSERT(!((*pskb)->nh.iph->frag_off
& htons(IP_MF|IP_OFFSET)));
ct = ip_conntrack_get(*pskb, &ctinfo);
/* Can't track? It's not due to stress, or conntrack would
have dropped it. Hence it's the user's responsibilty to
packet filter it out, or implement conntrack/NAT for that
protocol. 8) --RR */
if (!ct) {
/* Exception: ICMP redirect to new connection (not in
hash table yet). We must not let this through, in
case we're doing NAT to the same network. */
if ((*pskb)->nh.iph->protocol == IPPROTO_ICMP) {
struct icmphdr _hdr, *hp;
hp = skb_header_pointer(*pskb,
(*pskb)->nh.iph->ihl*4,
sizeof(_hdr), &_hdr);
if (hp != NULL &&
hp->type == ICMP_REDIRECT) {
if (LOG_INVALID(IPPROTO_ICMP))
nf_log_packet(PF_INET, 0, *pskb,
NULL, NULL, NULL, "ip_nat_fn: "
"untracked ICMP redirect ");
return NF_DROP;
}
}
return NF_ACCEPT;
}
/* Don't try to NAT if this packet is not conntracked */
if (ct == &ip_conntrack_untracked)
return NF_ACCEPT;
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED+IP_CT_IS_REPLY:
if ((*pskb)->nh.iph->protocol == IPPROTO_ICMP) {
if (!ip_nat_icmp_reply_translation(ct, ctinfo,
hooknum, pskb))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
case IP_CT_NEW:
info = &ct->nat.info;
/* Seen it before? This can happen for loopback, retrans,
or local packets.. */
if (!ip_nat_initialized(ct, maniptype)) {
unsigned int ret;
if (unlikely(is_confirmed(ct)))
/* NAT module was loaded late */
ret = alloc_null_binding_confirmed(ct, info,
hooknum);
else if (hooknum == NF_IP_LOCAL_IN)
/* LOCAL_IN hook doesn't have a chain! */
ret = alloc_null_binding(ct, info, hooknum);
else
ret = ip_nat_rule_find(pskb, hooknum,
in, out, ct,
info);
if (ret != NF_ACCEPT) {
return ret;
}
} else
DEBUGP("Already setup manip %s for ct %p\n",
maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
break;
default:
/* ESTABLISHED */
IP_NF_ASSERT(ctinfo == IP_CT_ESTABLISHED
|| ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY));
info = &ct->nat.info;
}
IP_NF_ASSERT(info);
return ip_nat_packet(ct, ctinfo, hooknum, pskb);
}
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;
}
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;
}
/* 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 int tcp_in_window(struct ip_ct_tcp *state,
enum ip_conntrack_dir dir,
unsigned int index,
const struct sk_buff *skb,
unsigned int dataoff,
struct tcphdr *tcph,
int pf)
{
struct ip_ct_tcp_state *sender = &state->seen[dir];
struct ip_ct_tcp_state *receiver = &state->seen[!dir];
__u32 seq, ack, sack, end, win;
#if defined (CONFIG_RA_NAT_NONE)
__u32 swin;
#endif
int 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);
DEBUGP("tcp_in_window: START\n");
DEBUGP("tcp_in_window: src=%u.%u.%u.%u:%hu dst=%u.%u.%u.%u:%hu "
"seq=%u ack=%u sack=%u win=%u end=%u\n",
NIPQUAD(iph->saddr), ntohs(tcph->source),
NIPQUAD(iph->daddr), ntohs(tcph->dest),
seq, ack, sack, win, end);
DEBUGP("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_end == 0) {
/*
* Initialize sender data.
*/
if (tcph->syn && tcph->ack) {
/*
* Outgoing SYN-ACK in reply to a SYN.
*/
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;
} 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;
DEBUGP("tcp_in_window: src=%u.%u.%u.%u:%hu dst=%u.%u.%u.%u:%hu "
"seq=%u ack=%u sack =%u win=%u end=%u\n",
NIPQUAD(iph->saddr), ntohs(tcph->source),
NIPQUAD(iph->daddr), ntohs(tcph->dest),
seq, ack, sack, win, end);
DEBUGP("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);
DEBUGP("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(ack, receiver->td_end - MAXACKWINDOW(sender)));
#if defined (CONFIG_RA_NAT_NONE)
if (before(seq, sender->td_maxend + 1) &&
after(end, sender->td_end - receiver->td_maxwin - 1) &&
before(sack, receiver->td_end + 1) &&
after(ack, receiver->td_end - MAXACKWINDOW(sender))) {
/*
* Take into account window scaling (RFC 1323).
*/
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;
/*
* 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++;
}
/*
* 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 = 1;
} else {
res = 0;
if (sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL ||
nf_ct_tcp_be_liberal)
res = 1;
if (!res && LOG_INVALID(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(ack, receiver->td_end - MAXACKWINDOW(sender)) ? "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)");
}
#else
res = 1;
#endif
DEBUGP("tcp_in_window: res=%i 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;
}
/* 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,
unsigned int *timeouts)
{
struct net *net = nf_ct_net(ct);
struct nf_tcp_net *tn = tcp_pernet(net);
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.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);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: 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);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: 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);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: challenge-ACK ignored ");
return NF_ACCEPT; /* Don't change state */
}
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);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(net, 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 >= 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
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;
}
