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 bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
unsigned int dataoff, unsigned int *timeouts)
{
enum tcp_conntrack new_state;
const struct tcphdr *th;
struct tcphdr _tcph;
const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[0];
const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[1];
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
BUG_ON(th == NULL);
new_state = tcp_conntracks[0][get_conntrack_index(th)][TCP_CONNTRACK_NONE];
if (new_state >= TCP_CONNTRACK_MAX) {
pr_debug("nf_ct_tcp: invalid new deleting.\n");
return false;
}
if (new_state == TCP_CONNTRACK_SYN_SENT) {
memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp));
ct->proto.tcp.seen[0].td_end =
segment_seq_plus_len(ntohl(th->seq), skb->len,
dataoff, th);
ct->proto.tcp.seen[0].td_maxwin = ntohs(th->window);
if (ct->proto.tcp.seen[0].td_maxwin == 0)
ct->proto.tcp.seen[0].td_maxwin = 1;
ct->proto.tcp.seen[0].td_maxend =
ct->proto.tcp.seen[0].td_end;
tcp_options(skb, dataoff, th, &ct->proto.tcp.seen[0]);
} else if (nf_ct_tcp_loose == 0) {
return false;
} else {
memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp));
ct->proto.tcp.seen[0].td_end =
segment_seq_plus_len(ntohl(th->seq), skb->len,
dataoff, th);
ct->proto.tcp.seen[0].td_maxwin = ntohs(th->window);
if (ct->proto.tcp.seen[0].td_maxwin == 0)
ct->proto.tcp.seen[0].td_maxwin = 1;
ct->proto.tcp.seen[0].td_maxend =
ct->proto.tcp.seen[0].td_end +
ct->proto.tcp.seen[0].td_maxwin;
ct->proto.tcp.seen[0].flags =
ct->proto.tcp.seen[1].flags = IP_CT_TCP_FLAG_SACK_PERM |
IP_CT_TCP_FLAG_BE_LIBERAL;
}
ct->proto.tcp.last_index = TCP_NONE_SET;
pr_debug("tcp_new: sender end=%u maxend=%u maxwin=%u scale=%i "
"receiver end=%u maxend=%u maxwin=%u scale=%i\n",
sender->td_end, sender->td_maxend, sender->td_maxwin,
sender->td_scale,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
return true;
}
/* Called when a new connection for this protocol found. */
static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
unsigned int dataoff)
{
enum tcp_conntrack new_state;
const struct tcphdr *th;
struct tcphdr _tcph;
const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[0];
const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[1];
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
BUG_ON(th == NULL);
/* Don't need lock here: this conntrack not in circulation yet */
new_state
= tcp_conntracks[0][get_conntrack_index(th)]
[TCP_CONNTRACK_NONE];
/* Invalid: delete conntrack */
if (new_state >= TCP_CONNTRACK_MAX) {
pr_debug("nf_ct_tcp: invalid new deleting.\n");
return false;
}
if (new_state == TCP_CONNTRACK_SYN_SENT) {
/* SYN packet */
ct->proto.tcp.seen[0].td_end =
segment_seq_plus_len(ntohl(th->seq), skb->len,
dataoff, th);
ct->proto.tcp.seen[0].td_maxwin = ntohs(th->window);
if (ct->proto.tcp.seen[0].td_maxwin == 0)
ct->proto.tcp.seen[0].td_maxwin = 1;
ct->proto.tcp.seen[0].td_maxend =
ct->proto.tcp.seen[0].td_end;
tcp_options(skb, dataoff, th, &ct->proto.tcp.seen[0]);
ct->proto.tcp.seen[1].flags = 0;
} else if (nf_ct_tcp_loose == 0) {
/* Don't try to pick up connections. */
return false;
} 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.
*/
ct->proto.tcp.seen[0].td_end =
segment_seq_plus_len(ntohl(th->seq), skb->len,
dataoff, th);
ct->proto.tcp.seen[0].td_maxwin = ntohs(th->window);
if (ct->proto.tcp.seen[0].td_maxwin == 0)
ct->proto.tcp.seen[0].td_maxwin = 1;
ct->proto.tcp.seen[0].td_maxend =
ct->proto.tcp.seen[0].td_end +
ct->proto.tcp.seen[0].td_maxwin;
ct->proto.tcp.seen[0].td_scale = 0;
/* We assume SACK and liberal window checking to handle
* window scaling */
ct->proto.tcp.seen[0].flags =
ct->proto.tcp.seen[1].flags = IP_CT_TCP_FLAG_SACK_PERM |
IP_CT_TCP_FLAG_BE_LIBERAL;
}
ct->proto.tcp.seen[1].td_end = 0;
ct->proto.tcp.seen[1].td_maxend = 0;
ct->proto.tcp.seen[1].td_maxwin = 0;
ct->proto.tcp.seen[1].td_scale = 0;
/* tcp_packet will set them */
ct->proto.tcp.state = TCP_CONNTRACK_NONE;
ct->proto.tcp.last_index = TCP_NONE_SET;
pr_debug("tcp_new: sender end=%u maxend=%u maxwin=%u scale=%i "
"receiver end=%u maxend=%u maxwin=%u scale=%i\n",
sender->td_end, sender->td_maxend, sender->td_maxwin,
sender->td_scale,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
return true;
}
static bool tcp_in_window(const struct nf_conn *ct,
struct ip_ct_tcp *state,
enum ip_conntrack_dir dir,
unsigned int index,
const struct sk_buff *skb,
unsigned int dataoff,
const struct tcphdr *tcph,
u_int8_t pf)
{
struct net *net = nf_ct_net(ct);
struct ip_ct_tcp_state *sender = &state->seen[dir];
struct ip_ct_tcp_state *receiver = &state->seen[!dir];
const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
__u32 seq, ack, sack, end, win, swin;
s16 receiver_offset;
bool res;
seq = ntohl(tcph->seq);
ack = sack = ntohl(tcph->ack_seq);
win = ntohs(tcph->window);
end = segment_seq_plus_len(seq, skb->len, dataoff, tcph);
if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM)
tcp_sack(skb, dataoff, tcph, &sack);
receiver_offset = NAT_OFFSET(pf, ct, !dir, ack - 1);
ack -= receiver_offset;
sack -= receiver_offset;
pr_debug("tcp_in_window: START\n");
pr_debug("tcp_in_window: ");
nf_ct_dump_tuple(tuple);
pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n",
seq, ack, receiver_offset, sack, receiver_offset, win, end);
pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
"receiver end=%u maxend=%u maxwin=%u scale=%i\n",
sender->td_end, sender->td_maxend, sender->td_maxwin,
sender->td_scale,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
if (sender->td_maxwin == 0) {
if (tcph->syn) {
sender->td_end =
sender->td_maxend = end;
sender->td_maxwin = (win == 0 ? 1 : win);
tcp_options(skb, dataoff, tcph, sender);
if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE
&& receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE))
sender->td_scale =
receiver->td_scale = 0;
if (!tcph->ack)
return true;
} else {
sender->td_end = end;
swin = win << sender->td_scale;
sender->td_maxwin = (swin == 0 ? 1 : swin);
sender->td_maxend = end + sender->td_maxwin;
if (receiver->td_maxwin == 0)
receiver->td_end = receiver->td_maxend = sack;
}
} else if (((state->state == TCP_CONNTRACK_SYN_SENT
&& dir == IP_CT_DIR_ORIGINAL)
|| (state->state == TCP_CONNTRACK_SYN_RECV
&& dir == IP_CT_DIR_REPLY))
&& after(end, sender->td_end)) {
sender->td_end =
sender->td_maxend = end;
sender->td_maxwin = (win == 0 ? 1 : win);
tcp_options(skb, dataoff, tcph, sender);
}
if (!(tcph->ack)) {
ack = sack = receiver->td_end;
} else if (((tcp_flag_word(tcph) & (TCP_FLAG_ACK|TCP_FLAG_RST)) ==
(TCP_FLAG_ACK|TCP_FLAG_RST))
&& (ack == 0)) {
ack = sack = receiver->td_end;
}
if (seq == end
&& (!tcph->rst
|| (seq == 0 && state->state == TCP_CONNTRACK_SYN_SENT)))
seq = end = sender->td_end;
pr_debug("tcp_in_window: ");
nf_ct_dump_tuple(tuple);
pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n",
seq, ack, receiver_offset, sack, receiver_offset, win, end);
pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
"receiver end=%u maxend=%u maxwin=%u scale=%i\n",
sender->td_end, sender->td_maxend, sender->td_maxwin,
sender->td_scale,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
pr_debug("tcp_in_window: I=%i II=%i III=%i IV=%i\n",
before(seq, sender->td_maxend + 1),
after(end, sender->td_end - receiver->td_maxwin - 1),
before(sack, receiver->td_end + 1),
after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1));
if (before(seq, sender->td_maxend + 1) &&
after(end, sender->td_end - receiver->td_maxwin - 1) &&
before(sack, receiver->td_end + 1) &&
after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)) {
if (!tcph->syn)
win <<= sender->td_scale;
swin = win + (sack - ack);
if (sender->td_maxwin < swin)
sender->td_maxwin = swin;
if (after(end, sender->td_end)) {
sender->td_end = end;
sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
}
if (tcph->ack) {
if (!(sender->flags & IP_CT_TCP_FLAG_MAXACK_SET)) {
sender->td_maxack = ack;
sender->flags |= IP_CT_TCP_FLAG_MAXACK_SET;
} else if (after(ack, sender->td_maxack))
sender->td_maxack = ack;
}
if (receiver->td_maxwin != 0 && after(end, sender->td_maxend))
receiver->td_maxwin += end - sender->td_maxend;
if (after(sack + win, receiver->td_maxend - 1)) {
receiver->td_maxend = sack + win;
if (win == 0)
receiver->td_maxend++;
}
if (ack == receiver->td_end)
receiver->flags &= ~IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
if (index == TCP_ACK_SET) {
if (state->last_dir == dir
&& state->last_seq == seq
&& state->last_ack == ack
&& state->last_end == end
&& state->last_win == win)
state->retrans++;
else {
state->last_dir = dir;
state->last_seq = seq;
state->last_ack = ack;
state->last_end = end;
state->last_win = win;
state->retrans = 0;
}
}
res = true;
} else {
res = false;
if (sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL ||
nf_ct_tcp_be_liberal)
res = true;
if (!res && LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: %s ",
before(seq, sender->td_maxend + 1) ?
after(end, sender->td_end - receiver->td_maxwin - 1) ?
before(sack, receiver->td_end + 1) ?
after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1) ? "BUG"
: "ACK is under the lower bound (possible overly delayed ACK)"
: "ACK is over the upper bound (ACKed data not seen yet)"
: "SEQ is under the lower bound (already ACKed data retransmitted)"
: "SEQ is over the upper bound (over the window of the receiver)");
}
pr_debug("tcp_in_window: res=%u sender end=%u maxend=%u maxwin=%u "
"receiver end=%u maxend=%u maxwin=%u\n",
res, sender->td_end, sender->td_maxend, sender->td_maxwin,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin);
return res;
}
static int 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 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)
{
struct net *net = nf_ct_net(ct);
struct nf_conntrack_tuple *tuple;
enum tcp_conntrack new_state, old_state;
enum ip_conntrack_dir dir;
const struct tcphdr *th;
struct tcphdr _tcph;
unsigned long timeout;
unsigned int index;
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
BUG_ON(th == NULL);
spin_lock_bh(&ct->lock);
old_state = ct->proto.tcp.state;
dir = CTINFO2DIR(ctinfo);
index = get_conntrack_index(th);
new_state = tcp_conntracks[dir][index][old_state];
tuple = &ct->tuplehash[dir].tuple;
switch (new_state) {
case TCP_CONNTRACK_SYN_SENT:
if (old_state < TCP_CONNTRACK_TIME_WAIT)
break;
/* RFC 1122: "When a connection is closed actively,
* it MUST linger in TIME-WAIT state for a time 2xMSL
* (Maximum Segment Lifetime). However, it MAY accept
* a new SYN from the remote TCP to reopen the connection
* directly from TIME-WAIT state, if..."
* We ignore the conditions because we are in the
* TIME-WAIT state anyway.
*
* Handle aborted connections: we and the server
* think there is an existing connection but the client
* aborts it and starts a new one.
*/
if (((ct->proto.tcp.seen[dir].flags
| ct->proto.tcp.seen[!dir].flags)
& IP_CT_TCP_FLAG_CLOSE_INIT)
|| (ct->proto.tcp.last_dir == dir
&& ct->proto.tcp.last_index == TCP_RST_SET)) {
/* Attempt to reopen a closed/aborted connection.
* Delete this connection and look up again. */
spin_unlock_bh(&ct->lock);
/* Only repeat if we can actually remove the timer.
* Destruction may already be in progress in process
* context and we must give it a chance to terminate.
*/
if (nf_ct_kill(ct))
return -NF_REPEAT;
return NF_DROP;
}
/* Fall through */
case TCP_CONNTRACK_IGNORE:
/* Ignored packets:
*
* Our connection entry may be out of sync, so ignore
* packets which may signal the real connection between
* the client and the server.
*
* a) SYN in ORIGINAL
* b) SYN/ACK in REPLY
* c) ACK in reply direction after initial SYN in original.
*
* If the ignored packet is invalid, the receiver will send
* a RST we'll catch below.
*/
if (index == TCP_SYNACK_SET
&& ct->proto.tcp.last_index == TCP_SYN_SET
&& ct->proto.tcp.last_dir != dir
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
/* b) This SYN/ACK acknowledges a SYN that we earlier
* ignored as invalid. This means that the client and
* the server are both in sync, while the firewall is
* not. We get in sync from the previously annotated
* values.
*/
old_state = TCP_CONNTRACK_SYN_SENT;
new_state = TCP_CONNTRACK_SYN_RECV;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_end =
ct->proto.tcp.last_end;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxend =
ct->proto.tcp.last_end;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxwin =
ct->proto.tcp.last_win == 0 ?
1 : ct->proto.tcp.last_win;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale =
ct->proto.tcp.last_wscale;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags =
ct->proto.tcp.last_flags;
memset(&ct->proto.tcp.seen[dir], 0,
sizeof(struct ip_ct_tcp_state));
break;
}
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
ct->proto.tcp.last_seq = ntohl(th->seq);
ct->proto.tcp.last_end =
segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th);
ct->proto.tcp.last_win = ntohs(th->window);
/* a) This is a SYN in ORIGINAL. The client and the server
* may be in sync but we are not. In that case, we annotate
* the TCP options and let the packet go through. If it is a
* valid SYN packet, the server will reply with a SYN/ACK, and
* then we'll get in sync. Otherwise, the server ignores it. */
if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) {
struct ip_ct_tcp_state seen = {};
ct->proto.tcp.last_flags =
ct->proto.tcp.last_wscale = 0;
tcp_options(skb, dataoff, th, &seen);
if (seen.flags & IP_CT_TCP_FLAG_WINDOW_SCALE) {
ct->proto.tcp.last_flags |=
IP_CT_TCP_FLAG_WINDOW_SCALE;
ct->proto.tcp.last_wscale = seen.td_scale;
}
if (seen.flags & IP_CT_TCP_FLAG_SACK_PERM) {
ct->proto.tcp.last_flags |=
IP_CT_TCP_FLAG_SACK_PERM;
}
}
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid packet ignored ");
return NF_ACCEPT;
case TCP_CONNTRACK_MAX:
/* Invalid packet */
pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n",
dir, get_conntrack_index(th), old_state);
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid state ");
return -NF_ACCEPT;
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
&& (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
&& before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) {
/* Invalid RST */
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid RST ");
return -NF_ACCEPT;
}
if (index == TCP_RST_SET
&& ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_SYN_SET)
|| (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_ACK_SET))
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
/* RST sent to invalid SYN or ACK we had let through
* at a) and c) above:
*
* a) SYN was in window then
* c) we hold a half-open connection.
*
* Delete our connection entry.
* We skip window checking, because packet might ACK
* segments we ignored. */
goto in_window;
}
/* Just fall through */
default:
/* Keep compilers happy. */
break;
}
if (!tcp_in_window(ct, &ct->proto.tcp, dir, index,
skb, dataoff, th, pf)) {
spin_unlock_bh(&ct->lock);
return -NF_ACCEPT;
}
in_window:
/* From now on we have got in-window packets */
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
pr_debug("tcp_conntracks: ");
nf_ct_dump_tuple(tuple);
pr_debug("syn=%i ack=%i fin=%i rst=%i old=%i new=%i\n",
(th->syn ? 1 : 0), (th->ack ? 1 : 0),
(th->fin ? 1 : 0), (th->rst ? 1 : 0),
old_state, new_state);
ct->proto.tcp.state = new_state;
if (old_state != new_state
&& new_state == TCP_CONNTRACK_FIN_WAIT)
ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT;
if (ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans &&
tcp_timeouts[new_state] > nf_ct_tcp_timeout_max_retrans)
timeout = nf_ct_tcp_timeout_max_retrans;
else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) &
IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED &&
tcp_timeouts[new_state] > nf_ct_tcp_timeout_unacknowledged)
timeout = nf_ct_tcp_timeout_unacknowledged;
else
timeout = tcp_timeouts[new_state];
spin_unlock_bh(&ct->lock);
if (new_state != old_state)
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
if (!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
/* If only reply is a RST, we can consider ourselves not to
have an established connection: this is a fairly common
problem case, so we can delete the conntrack
immediately. --RR */
if (th->rst) {
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
} else if (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& (old_state == TCP_CONNTRACK_SYN_RECV
|| old_state == TCP_CONNTRACK_ESTABLISHED)
&& new_state == TCP_CONNTRACK_ESTABLISHED) {
/* Set ASSURED if we see see valid ack in ESTABLISHED
after SYN_RECV or a valid answer for a picked up
connection. */
set_bit(IPS_ASSURED_BIT, &ct->status);
nf_conntrack_event_cache(IPCT_ASSURED, ct);
}
nf_ct_refresh_acct(ct, ctinfo, skb, timeout);
return NF_ACCEPT;
}
/* 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;
}
/* Called when a new connection for this protocol found. */
static int tcp_new(struct ip_conntrack *conntrack,
const struct sk_buff *skb)
{
enum tcp_conntrack new_state;
struct iphdr *iph = skb->nh.iph;
struct tcphdr *th, _tcph;
#ifdef DEBUGP_VARS
struct ip_ct_tcp_state *sender = &conntrack->proto.tcp.seen[0];
struct ip_ct_tcp_state *receiver = &conntrack->proto.tcp.seen[1];
#endif
th = skb_header_pointer(skb, iph->ihl * 4,
sizeof(_tcph), &_tcph);
BUG_ON(th == NULL);
/* Don't need lock here: this conntrack not in circulation yet */
new_state
= tcp_conntracks[0][get_conntrack_index(th)]
[TCP_CONNTRACK_NONE];
/* Invalid: delete conntrack */
if (new_state >= TCP_CONNTRACK_MAX) {
DEBUGP("ip_ct_tcp: invalid new deleting.\n");
return 0;
}
if (new_state == TCP_CONNTRACK_SYN_SENT) {
/* SYN packet */
conntrack->proto.tcp.seen[0].td_end =
segment_seq_plus_len(ntohl(th->seq), skb->len,
iph, th);
conntrack->proto.tcp.seen[0].td_maxwin = ntohs(th->window);
if (conntrack->proto.tcp.seen[0].td_maxwin == 0)
conntrack->proto.tcp.seen[0].td_maxwin = 1;
conntrack->proto.tcp.seen[0].td_maxend =
conntrack->proto.tcp.seen[0].td_end;
tcp_options(skb, iph, th, &conntrack->proto.tcp.seen[0]);
conntrack->proto.tcp.seen[1].flags = 0;
conntrack->proto.tcp.seen[0].loose =
conntrack->proto.tcp.seen[1].loose = 0;
} else if (ip_ct_tcp_loose == 0) {
/* Don't try to pick up connections. */
return 0;
} else {
/*
* We are in the middle of a connection,
* its history is lost for us.
* Let's try to use the data from the packet.
*/
conntrack->proto.tcp.seen[0].td_end =
segment_seq_plus_len(ntohl(th->seq), skb->len,
iph, th);
conntrack->proto.tcp.seen[0].td_maxwin = ntohs(th->window);
if (conntrack->proto.tcp.seen[0].td_maxwin == 0)
conntrack->proto.tcp.seen[0].td_maxwin = 1;
conntrack->proto.tcp.seen[0].td_maxend =
conntrack->proto.tcp.seen[0].td_end +
conntrack->proto.tcp.seen[0].td_maxwin;
conntrack->proto.tcp.seen[0].td_scale = 0;
/* We assume SACK. Should we assume window scaling too? */
conntrack->proto.tcp.seen[0].flags =
conntrack->proto.tcp.seen[1].flags = IP_CT_TCP_FLAG_SACK_PERM;
conntrack->proto.tcp.seen[0].loose =
conntrack->proto.tcp.seen[1].loose = ip_ct_tcp_loose;
}
conntrack->proto.tcp.seen[1].td_end = 0;
conntrack->proto.tcp.seen[1].td_maxend = 0;
conntrack->proto.tcp.seen[1].td_maxwin = 1;
conntrack->proto.tcp.seen[1].td_scale = 0;
/* tcp_packet will set them */
conntrack->proto.tcp.state = TCP_CONNTRACK_NONE;
conntrack->proto.tcp.last_index = TCP_NONE_SET;
DEBUGP("tcp_new: sender end=%u maxend=%u maxwin=%u scale=%i "
"receiver end=%u maxend=%u maxwin=%u scale=%i\n",
sender->td_end, sender->td_maxend, sender->td_maxwin,
sender->td_scale,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
return 1;
}
static bool tcp_in_window(const struct nf_conn *ct,
struct ip_ct_tcp *state,
enum ip_conntrack_dir dir,
unsigned int index,
const struct sk_buff *skb,
unsigned int dataoff,
const struct tcphdr *tcph,
u_int8_t pf)
{
struct net *net = nf_ct_net(ct);
struct ip_ct_tcp_state *sender = &state->seen[dir];
struct ip_ct_tcp_state *receiver = &state->seen[!dir];
const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
__u32 seq, ack, sack, end, win, swin;
s16 receiver_offset;
bool res;
/*
* Get the required data from the packet.
*/
seq = ntohl(tcph->seq);
ack = sack = ntohl(tcph->ack_seq);
win = ntohs(tcph->window);
end = segment_seq_plus_len(seq, skb->len, dataoff, tcph);
if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM)
tcp_sack(skb, dataoff, tcph, &sack);
/* Take into account NAT sequence number mangling */
receiver_offset = NAT_OFFSET(pf, ct, !dir, ack - 1);
ack -= receiver_offset;
sack -= receiver_offset;
pr_debug("tcp_in_window: START\n");
pr_debug("tcp_in_window: ");
nf_ct_dump_tuple(tuple);
pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n",
seq, ack, receiver_offset, sack, receiver_offset, win, end);
pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
"receiver end=%u maxend=%u maxwin=%u scale=%i\n",
sender->td_end, sender->td_maxend, sender->td_maxwin,
sender->td_scale,
receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
receiver->td_scale);
if (sender->td_maxwin == 0) {
/*
* Initialize sender data.
*/
if (tcph->syn) {
/*
* SYN-ACK in reply to a SYN
* or SYN from reply direction in simultaneous open.
*/
sender->td_end =
sender->td_maxend = end;
sender->td_maxwin = (win == 0 ? 1 : win);
tcp_options(skb, dataoff, tcph, sender);
/*
* RFC 1323:
* Both sides must send the Window Scale option
* to enable window scaling in either direction.
*/
if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE
&& receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE))
sender->td_scale =
receiver->td_scale = 0;
if (!tcph->ack)
/* Simultaneous open */
return true;
} else {
/*
* We are in the middle of a connection,
* its history is lost for us.
* Let's try to use the data from the packet.
*/
sender->td_end = end;
<<<<<<< HEAD
win <<= sender->td_scale;
sender->td_maxwin = (win == 0 ? 1 : win);
sender->td_maxend = end + sender->td_maxwin;
/*
* We haven't seen traffic in the other direction yet
* but we have to tweak window tracking to pass III
* and IV until that happens.
*/
if (receiver->td_maxwin == 0)
receiver->td_end = receiver->td_maxend = sack;
=======
sender->td_maxwin = (win == 0 ? 1 : win);
sender->td_maxend = end + sender->td_maxwin;
>>>>>>> 296c66da8a02d52243f45b80521febece5ed498a
}
} else if (((state->state == TCP_CONNTRACK_SYN_SENT
