static unsigned int
target(struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
unsigned int hooknum,
const struct xt_target *target,
const void *targinfo)
{
const struct xt_connmark_target_info *markinfo = targinfo;
u_int32_t diff;
u_int32_t nfmark;
u_int32_t newmark;
u_int32_t ctinfo;
u_int32_t *ctmark = nf_ct_get_mark(*pskb, &ctinfo);
if (ctmark) {
switch(markinfo->mode) {
case XT_CONNMARK_SET:
newmark = (*ctmark & ~markinfo->mask) | markinfo->mark;
if (newmark != *ctmark) {
*ctmark = newmark;
#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE)
ip_conntrack_event_cache(IPCT_MARK, *pskb);
#else
nf_conntrack_event_cache(IPCT_MARK, *pskb);
#endif
}
break;
case XT_CONNMARK_SAVE:
newmark = (*ctmark & ~markinfo->mask) |
((*pskb)->nfmark & markinfo->mask);
if (*ctmark != newmark) {
*ctmark = newmark;
#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE)
ip_conntrack_event_cache(IPCT_MARK, *pskb);
#else
nf_conntrack_event_cache(IPCT_MARK, *pskb);
#endif
}
break;
case XT_CONNMARK_RESTORE:
nfmark = (*pskb)->nfmark;
diff = (*ctmark ^ nfmark) & markinfo->mask;
if (diff != 0)
(*pskb)->nfmark = nfmark ^ diff;
break;
}
}
return XT_CONTINUE;
}
/* Returns verdict for packet, and may modify conntracktype */
static int udp_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)
{
/* If we've seen traffic both ways, this is some kind of UDP
stream. Extend timeout. */
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
#ifdef CONFIG_MIPS_BRCM
unsigned timeout = nf_ct_udp_timeout_stream;
if (ct->derived_timeout == 0xFFFFFFFF){
timeout = 0xFFFFFFFF - jiffies;
} else if(ct->derived_timeout > 0) {
timeout = ct->derived_timeout;
}
nf_ct_refresh_acct(ct, ctinfo, skb, timeout);
#else
nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_udp_timeout_stream);
#endif
/* Also, more likely to be important, and not a probe */
if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_STATUS, ct);
} else
nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_udp_timeout);
return NF_ACCEPT;
}
static int ovs_ct_set_mark(struct sk_buff *skb, struct sw_flow_key *key,
u32 ct_mark, u32 mask)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
u32 new_mark;
/* The connection could be invalid, in which case set_mark is no-op. */
ct = nf_ct_get(skb, &ctinfo);
if (!ct)
return 0;
new_mark = ct_mark | (ct->mark & ~(mask));
if (ct->mark != new_mark) {
ct->mark = new_mark;
nf_conntrack_event_cache(IPCT_MARK, ct);
key->ct.mark = new_mark;
}
return 0;
#else
return -ENOTSUPP;
#endif
}
/* Returns verdict for packet, and may modify conntracktype */
int nf_conntrack_udplite_packet(struct nf_conn *ct,
struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
const struct nf_hook_state *state)
{
unsigned int *timeouts;
if (udplite_error(skb, dataoff, state))
return -NF_ACCEPT;
timeouts = nf_ct_timeout_lookup(ct);
if (!timeouts)
timeouts = udp_get_timeouts(nf_ct_net(ct));
/* If we've seen traffic both ways, this is some kind of UDP
stream. Extend timeout. */
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
nf_ct_refresh_acct(ct, ctinfo, skb,
timeouts[UDP_CT_REPLIED]);
/* Also, more likely to be important, and not a probe */
if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_ASSURED, ct);
} else {
nf_ct_refresh_acct(ct, ctinfo, skb,
timeouts[UDP_CT_UNREPLIED]);
}
return NF_ACCEPT;
}
int FASTPATHNET bcm_do_fastroute(struct nf_conn *ct,
struct sk_buff **pskb,
unsigned int hooknum,
int set_reply)
{
/* change status from new to seen_reply. when receive reply packet the status will set to establish */
if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_STATUS, *pskb);
if(hooknum == NF_IP_PRE_ROUTING) {
(*pskb)->cb[NF_FAST_ROUTE]=1;
/* this function will handle routing decision. the next hoook will be input or forward chain */
if (ip_rcv_finish(*pskb) == NF_FAST_NAT) {
/* Change skb owner to output device */
(*pskb)->dev = (*pskb)->dst->dev;
(*pskb)->protocol = htons(ETH_P_IP);
return NF_FAST_NAT;
}
/* this tell system no need to handle this packet. we will handle this. */
return NF_STOLEN;
} else {
if(hooknum == NF_IP_LOCAL_OUT) {
/* Change skb owner to output device */
(*pskb)->dev = (*pskb)->dst->dev;
(*pskb)->protocol = htons(ETH_P_IP);
return NF_FAST_NAT;
}
}
/* return accept for continue normal processing */
return NF_ACCEPT;
}
static void nft_ct_set_eval(const struct nft_expr *expr,
struct nft_regs *regs,
const struct nft_pktinfo *pkt)
{
const struct nft_ct *priv = nft_expr_priv(expr);
struct sk_buff *skb = pkt->skb;
#ifdef CONFIG_NF_CONNTRACK_MARK
u32 value = regs->data[priv->sreg];
#endif
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
ct = nf_ct_get(skb, &ctinfo);
if (ct == NULL)
return;
switch (priv->key) {
#ifdef CONFIG_NF_CONNTRACK_MARK
case NFT_CT_MARK:
if (ct->mark != value) {
ct->mark = value;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
#endif
default:
break;
}
}
static unsigned int
connmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_connmark_tginfo1 *info = par->targinfo;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
u_int32_t newmark;
ct = nf_ct_get(skb, &ctinfo);
if (ct == NULL)
return XT_CONTINUE;
switch (info->mode) {
case XT_CONNMARK_SET:
newmark = (ct->mark & ~info->ctmask) ^ info->ctmark;
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
case XT_CONNMARK_SAVE:
newmark = (ct->mark & ~info->ctmask) ^
(skb->mark & info->nfmask);
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
// ------------- START of KNOX_VPN -----------------//
knoxvpn_uidpid(skb,newmark);
// ------------- END of KNOX_VPN -------------------//
break;
case XT_CONNMARK_RESTORE:
newmark = (skb->mark & ~info->nfmask) ^
(ct->mark & info->ctmask);
skb->mark = newmark;
// ------------- START of KNOX_VPN -----------------//
knoxvpn_uidpid(skb,newmark);
// ------------- END of KNOX_VPN -------------------//
break;
}
return XT_CONTINUE;
}
void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
__be32 seq, s16 off)
{
if (!off)
return;
set_bit(IPS_SEQ_ADJUST_BIT, &ct->status);
adjust_tcp_sequence(ntohl(seq), off, ct, ctinfo);
nf_conntrack_event_cache(IPCT_NATSEQADJ, ct);
}
static unsigned int
target(struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
unsigned int hooknum,
const struct xt_target *target,
const void *targinfo)
{
const struct xt_connmark_target_info *markinfo = targinfo;
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
u_int32_t diff;
u_int32_t mark;
u_int32_t newmark;
ct = nf_ct_get(*pskb, &ctinfo);
if (ct) {
switch(markinfo->mode) {
case XT_CONNMARK_SET:
newmark = (ct->mark & ~markinfo->mask) | markinfo->mark;
if (newmark != ct->mark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, *pskb);
}
break;
case XT_CONNMARK_SAVE:
newmark = (ct->mark & ~markinfo->mask) |
((*pskb)->mark & markinfo->mask);
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, *pskb);
}
break;
case XT_CONNMARK_RESTORE:
mark = (*pskb)->mark;
diff = (ct->mark ^ mark) & markinfo->mask;
(*pskb)->mark = mark ^ diff;
break;
}
}
return XT_CONTINUE;
}
/*
* If the packet has a security mark and the connection does not, copy
* the security mark from the packet to the connection.
*/
static void secmark_save(const struct sk_buff *skb)
{
if (skb->secmark) {
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
ct = nf_ct_get(skb, &ctinfo);
if (ct && !ct->secmark) {
ct->secmark = skb->secmark;
nf_conntrack_event_cache(IPCT_SECMARK, ct);
}
}
}
/* Returns verdict for packet, and may modify conntracktype */
static int udp_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)
{
/* If we've seen traffic both ways, this is some kind of UDP
stream. Extend timeout. */
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
/* Dino @20120203 */
#if defined(CONFIG_CAMEO_CT_NEW)
if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num == AF_INET6)
{
if((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port < 1024) ||
(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.udp.port < 1024))
{
cameo_nf_ct_refresh_acct_udp(ct, ctinfo, skb, nf_ct_udp6_timeout_stream, "AS"); // assured
}
else
{
cameo_nf_ct_refresh_acct_udp(ct, ctinfo, skb, nf_ct_udp6_timeout_stream_out_wkport, "AS"); // assured
}
}
else
{
cameo_nf_ct_refresh_acct_udp(ct, ctinfo, skb, nf_ct_udp_timeout_stream, "AS"); // assured
}
#else
/* Dino */
nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_udp_timeout_stream);
#endif
/* Also, more likely to be important, and not a probe */
if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_ASSURED, ct);
} else
/* Dino @20120203 */
#if defined(CONFIG_CAMEO_CT_NEW)
if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num ==AF_INET6)
cameo_nf_ct_refresh_acct_udp(ct, ctinfo, skb, nf_ct_udp6_timeout, "UR"); // unreplied
else
cameo_nf_ct_refresh_acct_udp(ct, ctinfo, skb, nf_ct_udp_timeout, "UR"); // unreplied
#else
/* Dino */
nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_udp_timeout);
#endif
return NF_ACCEPT;
}
int nf_connlabel_set(struct nf_conn *ct, u16 bit)
{
struct nf_conn_labels *labels = nf_ct_labels_find(ct);
if (!labels || bit >= label_bits(labels))
return -ENOSPC;
if (test_bit(bit, labels->bits))
return 0;
if (test_and_set_bit(bit, labels->bits))
nf_conntrack_event_cache(IPCT_LABEL, ct);
return 0;
}
/* Returns verdict for packet, and may modify conntracktype */
static int udp_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)
{
/* If we've seen traffic both ways, this is some kind of UDP
stream. Extend timeout. */
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_udp_timeout_stream);
/* Also, more likely to be important, and not a probe */
if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_ASSURED, ct);
} else
nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_udp_timeout);
return NF_ACCEPT;
}
/* Returns verdict for packet, or -1 for invalid. */
static int icmp_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)
{
/* Try to delete connection immediately after all replies:
won't actually vanish as we still have skb, and del_timer
means this will only run once even if count hits zero twice
(theoretically possible with SMP) */
if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) {
if (atomic_dec_and_test(&ct->proto.icmp.count))
nf_ct_kill_acct(ct, ctinfo, skb);
} else {
atomic_inc(&ct->proto.icmp.count);
nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, ct);
nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout);
}
return NF_ACCEPT;
}
static int udp_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)
{
/*
*/
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
nf_ct_refresh_acct(ct, ctinfo, skb,
timeouts[UDP_CT_REPLIED]);
/* */
if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_ASSURED, ct);
} else {
nf_ct_refresh_acct(ct, ctinfo, skb,
timeouts[UDP_CT_UNREPLIED]);
}
return NF_ACCEPT;
}
/* Returns verdict for packet, and may modify conntracktype */
int nf_conntrack_udp_packet(struct nf_conn *ct,
struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
const struct nf_hook_state *state)
{
unsigned int *timeouts;
if (udp_error(skb, dataoff, state))
return -NF_ACCEPT;
timeouts = nf_ct_timeout_lookup(ct);
if (!timeouts)
timeouts = udp_get_timeouts(nf_ct_net(ct));
if (!nf_ct_is_confirmed(ct))
ct->proto.udp.stream_ts = 2 * HZ + jiffies;
/* If we've seen traffic both ways, this is some kind of UDP
* stream. Set Assured.
*/
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
unsigned long extra = timeouts[UDP_CT_UNREPLIED];
/* Still active after two seconds? Extend timeout. */
if (time_after(jiffies, ct->proto.udp.stream_ts))
extra = timeouts[UDP_CT_REPLIED];
nf_ct_refresh_acct(ct, ctinfo, skb, extra);
/* Also, more likely to be important, and not a probe */
if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_ASSURED, ct);
} else {
nf_ct_refresh_acct(ct, ctinfo, skb,
timeouts[UDP_CT_UNREPLIED]);
}
return NF_ACCEPT;
}
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 *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;
}
/* 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;
}
/* 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 unsigned int ipv6_synproxy_hook(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *nhs)
{
struct net *net = nhs->net;
struct synproxy_net *snet = synproxy_pernet(net);
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
struct nf_conn_synproxy *synproxy;
struct synproxy_options opts = {};
const struct ip_ct_tcp *state;
struct tcphdr *th, _th;
__be16 frag_off;
u8 nexthdr;
int thoff;
ct = nf_ct_get(skb, &ctinfo);
if (ct == NULL)
return NF_ACCEPT;
synproxy = nfct_synproxy(ct);
if (synproxy == NULL)
return NF_ACCEPT;
if (nf_is_loopback_packet(skb))
return NF_ACCEPT;
nexthdr = ipv6_hdr(skb)->nexthdr;
thoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
&frag_off);
if (thoff < 0 || nexthdr != IPPROTO_TCP)
return NF_ACCEPT;
th = skb_header_pointer(skb, thoff, sizeof(_th), &_th);
if (th == NULL)
return NF_DROP;
state = &ct->proto.tcp;
switch (state->state) {
case TCP_CONNTRACK_CLOSE:
if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
nf_ct_seqadj_init(ct, ctinfo, synproxy->isn -
ntohl(th->seq) + 1);
break;
}
if (!th->syn || th->ack ||
CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
break;
/* Reopened connection - reset the sequence number and timestamp
* adjustments, they will get initialized once the connection is
* reestablished.
*/
nf_ct_seqadj_init(ct, ctinfo, 0);
synproxy->tsoff = 0;
this_cpu_inc(snet->stats->conn_reopened);
/* fall through */
case TCP_CONNTRACK_SYN_SENT:
if (!synproxy_parse_options(skb, thoff, th, &opts))
return NF_DROP;
if (!th->syn && th->ack &&
CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
/* Keep-Alives are sent with SEG.SEQ = SND.NXT-1,
* therefore we need to add 1 to make the SYN sequence
* number match the one of first SYN.
*/
if (synproxy_recv_client_ack(net, skb, th, &opts,
ntohl(th->seq) + 1)) {
this_cpu_inc(snet->stats->cookie_retrans);
consume_skb(skb);
return NF_STOLEN;
} else {
return NF_DROP;
}
}
synproxy->isn = ntohl(th->ack_seq);
if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy->its = opts.tsecr;
nf_conntrack_event_cache(IPCT_SYNPROXY, ct);
break;
case TCP_CONNTRACK_SYN_RECV:
if (!th->syn || !th->ack)
break;
if (!synproxy_parse_options(skb, thoff, th, &opts))
return NF_DROP;
if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) {
synproxy->tsoff = opts.tsval - synproxy->its;
nf_conntrack_event_cache(IPCT_SYNPROXY, ct);
}
opts.options &= ~(XT_SYNPROXY_OPT_MSS |
XT_SYNPROXY_OPT_WSCALE |
XT_SYNPROXY_OPT_SACK_PERM);
swap(opts.tsval, opts.tsecr);
synproxy_send_server_ack(net, state, skb, th, &opts);
nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq));
nf_conntrack_event_cache(IPCT_SEQADJ, ct);
swap(opts.tsval, opts.tsecr);
synproxy_send_client_ack(net, skb, th, &opts);
consume_skb(skb);
return NF_STOLEN;
default:
break;
}
synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy);
return NF_ACCEPT;
}
static int 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;
}
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;
}
