// SPDX-License-Identifier: GPL-2.0-only

/* (C) 1999-2001 Paul `Rusty' Russell

* (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>

* (C) 2002-2013 Jozsef Kadlecsik <kadlec@netfilter.org>

* (C) 2006-2012 Patrick McHardy <kaber@trash.net>

*/

#include <linux/types.h>

#include <linux/timer.h>

#include <linux/module.h>

#include <linux/in.h>

#include <linux/tcp.h>

#include <linux/spinlock.h>

#include <linux/skbuff.h>

#include <linux/ipv6.h>

#include <net/ip6_checksum.h>

#include <linux/unaligned.h>

#include <net/tcp.h>

#include <linux/netfilter.h>

#include <linux/netfilter_ipv4.h>

#include <linux/netfilter_ipv6.h>

#include <net/netfilter/nf_conntrack.h>

#include <net/netfilter/nf_conntrack_l4proto.h>

#include <net/netfilter/nf_conntrack_ecache.h>

#include <net/netfilter/nf_conntrack_seqadj.h>

#include <net/netfilter/nf_conntrack_synproxy.h>

#include <net/netfilter/nf_conntrack_timeout.h>

#include <net/netfilter/nf_log.h>

#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>

#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>

/* FIXME: Examine ipfilter's timeouts and conntrack transitions more

closely. They're more complex. --RR */

static const char *const tcp_conntrack_names[] = {

"NONE",

"SYN_SENT",

"SYN_RECV",

"ESTABLISHED",

"FIN_WAIT",

"CLOSE_WAIT",

"LAST_ACK",

"TIME_WAIT",

"CLOSE",

"SYN_SENT2",

};

enum nf_ct_tcp_action {

NFCT_TCP_IGNORE,

NFCT_TCP_INVALID,

NFCT_TCP_ACCEPT,

};

#define SECS * HZ

#define MINS * 60 SECS

#define HOURS * 60 MINS

#define DAYS * 24 HOURS

static const unsigned int tcp_timeouts[TCP_CONNTRACK_TIMEOUT_MAX] = {

[TCP_CONNTRACK_SYN_SENT] = 2 MINS,

[TCP_CONNTRACK_SYN_RECV] = 60 SECS,

[TCP_CONNTRACK_ESTABLISHED] = 5 DAYS,

[TCP_CONNTRACK_FIN_WAIT] = 2 MINS,

[TCP_CONNTRACK_CLOSE_WAIT] = 60 SECS,

[TCP_CONNTRACK_LAST_ACK] = 30 SECS,

[TCP_CONNTRACK_TIME_WAIT] = 2 MINS,

[TCP_CONNTRACK_CLOSE] = 10 SECS,

[TCP_CONNTRACK_SYN_SENT2] = 2 MINS,

/* RFC1122 says the R2 limit should be at least 100 seconds.

Linux uses 15 packets as limit, which corresponds

to ~13-30min depending on RTO. */

[TCP_CONNTRACK_RETRANS] = 5 MINS,

[TCP_CONNTRACK_UNACK] = 5 MINS,

};

#define sNO TCP_CONNTRACK_NONE

#define sSS TCP_CONNTRACK_SYN_SENT

#define sSR TCP_CONNTRACK_SYN_RECV

#define sES TCP_CONNTRACK_ESTABLISHED

#define sFW TCP_CONNTRACK_FIN_WAIT

#define sCW TCP_CONNTRACK_CLOSE_WAIT

#define sLA TCP_CONNTRACK_LAST_ACK

#define sTW TCP_CONNTRACK_TIME_WAIT

#define sCL TCP_CONNTRACK_CLOSE

#define sS2 TCP_CONNTRACK_SYN_SENT2

#define sIV TCP_CONNTRACK_MAX

#define sIG TCP_CONNTRACK_IGNORE

/* What TCP flags are set from RST/SYN/FIN/ACK. */

enum tcp_bit_set {

TCP_SYN_SET,

TCP_SYNACK_SET,

TCP_FIN_SET,

TCP_ACK_SET,

TCP_RST_SET,

TCP_NONE_SET,

};

/*

* The TCP state transition table needs a few words...

*

* We are the man in the middle. All the packets go through us

* but might get lost in transit to the destination.

* It is assumed that the destinations can't receive segments

* we haven't seen.

*

* The checked segment is in window, but our windows are *not*

* equivalent with the ones of the sender/receiver. We always

* try to guess the state of the current sender.

*

* The meaning of the states are:

*

* NONE: initial state

* SYN_SENT: SYN-only packet seen

* SYN_SENT2: SYN-only packet seen from reply dir, simultaneous open

* SYN_RECV: SYN-ACK packet seen

* ESTABLISHED: ACK packet seen

* FIN_WAIT: FIN packet seen

* CLOSE_WAIT: ACK seen (after FIN)

* LAST_ACK: FIN seen (after FIN)

* TIME_WAIT: last ACK seen

* CLOSE: closed connection (RST)

*

* Packets marked as IGNORED (sIG):

* if they may be either invalid or valid

* and the receiver may send back a connection

* closing RST or a SYN/ACK.

*

* Packets marked as INVALID (sIV):

* if we regard them as truly invalid packets

*/

static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {

{

/* ORIGINAL */

/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */

/*syn*/ { sSS, sSS, sIG, sIG, sIG, sIG, sIG, sSS, sSS, sS2 },

/*

* sNO -> sSS Initialize a new connection

* sSS -> sSS Retransmitted SYN

* sS2 -> sS2 Late retransmitted SYN

* sSR -> sIG

* sES -> sIG Error: SYNs in window outside the SYN_SENT state

* are errors. Receiver will reply with RST

* and close the connection.

* Or we are not in sync and hold a dead connection.

* sFW -> sIG

* sCW -> sIG

* sLA -> sIG

* sTW -> sSS Reopened connection (RFC 1122).

* sCL -> sSS

*/

/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */

/*synack*/ { sIV, sIV, sSR, sIV, sIV, sIV, sIV, sIV, sIV, sSR },

/*

* sNO -> sIV Too late and no reason to do anything

* sSS -> sIV Client can't send SYN and then SYN/ACK

* sS2 -> sSR SYN/ACK sent to SYN2 in simultaneous open

* sSR -> sSR Late retransmitted SYN/ACK in simultaneous open

* sES -> sIV Invalid SYN/ACK packets sent by the client

* sFW -> sIV

* sCW -> sIV

* sLA -> sIV

* sTW -> sIV

* sCL -> sIV

*/

/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */

/*fin*/ { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV },

/*

* sNO -> sIV Too late and no reason to do anything...

* sSS -> sIV Client migth not send FIN in this state:

* we enforce waiting for a SYN/ACK reply first.

* sS2 -> sIV

* sSR -> sFW Close started.

* sES -> sFW

* sFW -> sLA FIN seen in both directions, waiting for

* the last ACK.

* Migth be a retransmitted FIN as well...

* sCW -> sLA

* sLA -> sLA Retransmitted FIN. Remain in the same state.

* sTW -> sTW

* sCL -> sCL

*/

/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */

/*ack*/ { sES, sIV, sES, sES, sCW, sCW, sTW, sTW, sCL, sIV },

/*

* sNO -> sES Assumed.

* sSS -> sIV ACK is invalid: we haven't seen a SYN/ACK yet.

* sS2 -> sIV

* sSR -> sES Established state is reached.

* sES -> sES :-)

* sFW -> sCW Normal close request answered by ACK.

* sCW -> sCW

* sLA -> sTW Last ACK detected (RFC5961 challenged)

* sTW -> sTW Retransmitted last ACK. Remain in the same state.

* sCL -> sCL

*/

/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */

/*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL },

/*none*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }

},

{

/* REPLY */

/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */

/*syn*/ { sIV, sS2, sIV, sIV, sIV, sIV, sIV, sSS, sIV, sS2 },

/*

* sNO -> sIV Never reached.

* sSS -> sS2 Simultaneous open

* sS2 -> sS2 Retransmitted simultaneous SYN

* sSR -> sIV Invalid SYN packets sent by the server

* sES -> sIV

* sFW -> sIV

* sCW -> sIV

* sLA -> sIV

* sTW -> sSS Reopened connection, but server may have switched role

* sCL -> sIV

*/

/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */

/*synack*/ { sIV, sSR, sIG, sIG, sIG, sIG, sIG, sIG, sIG, sSR },

/*

* sSS -> sSR Standard open.

* sS2 -> sSR Simultaneous open

* sSR -> sIG Retransmitted SYN/ACK, ignore it.

* sES -> sIG Late retransmitted SYN/ACK?

* sFW -> sIG Might be SYN/ACK answering ignored SYN

* sCW -> sIG

* sLA -> sIG

* sTW -> sIG

* sCL -> sIG

*/

/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */

/*fin*/ { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV },

/*

* sSS -> sIV Server might not send FIN in this state.

* sS2 -> sIV

* sSR -> sFW Close started.

* sES -> sFW

* sFW -> sLA FIN seen in both directions.

* sCW -> sLA

* sLA -> sLA Retransmitted FIN.

* sTW -> sTW

* sCL -> sCL

*/

/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */

/*ack*/ { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIG },

/*

* sSS -> sIG Might be a half-open connection.

* sS2 -> sIG

* sSR -> sSR Might answer late resent SYN.

* sES -> sES :-)

* sFW -> sCW Normal close request answered by ACK.

* sCW -> sCW

* sLA -> sTW Last ACK detected (RFC5961 challenged)

* sTW -> sTW Retransmitted last ACK.

* sCL -> sCL

*/

/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */

/*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL },

/*none*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }

}

};

#ifdef CONFIG_NF_CONNTRACK_PROCFS

/* Print out the private part of the conntrack. */

static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)

{

if (test_bit(IPS_OFFLOAD_BIT, &ct->status))

return;

seq_printf(s, "%s ", tcp_conntrack_names[ct->proto.tcp.state]);

}

#endif

static unsigned int get_conntrack_index(const struct tcphdr *tcph)

{

if (tcph->rst) return TCP_RST_SET;

else if (tcph->syn) return (tcph->ack ? TCP_SYNACK_SET : TCP_SYN_SET);

else if (tcph->fin) return TCP_FIN_SET;

else if (tcph->ack) return TCP_ACK_SET;

else return TCP_NONE_SET;

}

/* TCP connection tracking based on 'Real Stateful TCP Packet Filtering

in IP Filter' by Guido van Rooij.

http://www.sane.nl/events/sane2000/papers.html

http://www.darkart.com/mirrors/www.obfuscation.org/ipf/

The boundaries and the conditions are changed according to RFC793:

the packet must intersect the window (i.e. segments may be

after the right or before the left edge) and thus receivers may ACK

segments after the right edge of the window.

td_maxend = max(sack + max(win,1)) seen in reply packets

td_maxwin = max(max(win, 1)) + (sack - ack) seen in sent packets

td_maxwin += seq + len - sender.td_maxend

if seq + len > sender.td_maxend

td_end = max(seq + len) seen in sent packets

I. Upper bound for valid data: seq <= sender.td_maxend

II. Lower bound for valid data: seq + len >= sender.td_end - receiver.td_maxwin

III. Upper bound for valid (s)ack: sack <= receiver.td_end

IV. Lower bound for valid (s)ack: sack >= receiver.td_end - MAXACKWINDOW

where sack is the highest right edge of sack block found in the packet

or ack in the case of packet without SACK option.

The upper bound limit for a valid (s)ack is not ignored -

we doesn't have to deal with fragments.

*/

static inline __u32 segment_seq_plus_len(__u32 seq,

size_t len,

unsigned int dataoff,

const struct tcphdr *tcph)

{

/* XXX Should I use payload length field in IP/IPv6 header ?

* - YK */

return (seq + len - dataoff - tcph->doff*4

+ (tcph->syn ? 1 : 0) + (tcph->fin ? 1 : 0));

}

/* Fixme: what about big packets? */

#define MAXACKWINCONST 66000

#define MAXACKWINDOW(sender) \

((sender)->td_maxwin > MAXACKWINCONST ? (sender)->td_maxwin \

: MAXACKWINCONST)

/*

* Simplified tcp_parse_options routine from tcp_input.c

*/

static void tcp_options(const struct sk_buff *skb,

unsigned int dataoff,

const struct tcphdr *tcph,

struct ip_ct_tcp_state *state)

{

unsigned char buff[(15 * 4) - sizeof(struct tcphdr)];

const unsigned char *ptr;

int length = (tcph->doff*4) - sizeof(struct tcphdr);

if (!length)

return;

ptr = skb_header_pointer(skb, dataoff + sizeof(struct tcphdr),

length, buff);

if (!ptr)

return;

state->td_scale = 0;

state->flags &= IP_CT_TCP_FLAG_BE_LIBERAL;

while (length > 0) {

int opcode=*ptr++;

int opsize;

switch (opcode) {

case TCPOPT_EOL:

return;

case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */

length--;

continue;

default:

if (length < 2)

return;

opsize=*ptr++;

if (opsize < 2) /* "silly options" */

return;

if (opsize > length)

return; /* don't parse partial options */

if (opcode == TCPOPT_SACK_PERM

&& opsize == TCPOLEN_SACK_PERM)

state->flags |= IP_CT_TCP_FLAG_SACK_PERM;

else if (opcode == TCPOPT_WINDOW

&& opsize == TCPOLEN_WINDOW) {

state->td_scale = *(u_int8_t *)ptr;

if (state->td_scale > TCP_MAX_WSCALE)

state->td_scale = TCP_MAX_WSCALE;

state->flags |=

IP_CT_TCP_FLAG_WINDOW_SCALE;

}

ptr += opsize - 2;

length -= opsize;

}

}

}

static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff,

const struct tcphdr *tcph, __u32 *sack)

{

unsigned char buff[(15 * 4) - sizeof(struct tcphdr)];

const unsigned char *ptr;

int length = (tcph->doff*4) - sizeof(struct tcphdr);

__u32 tmp;

if (!length)

return;

ptr = skb_header_pointer(skb, dataoff + sizeof(struct tcphdr),

length, buff);

if (!ptr)

return;

/* Fast path for timestamp-only option */

if (length == TCPOLEN_TSTAMP_ALIGNED

&& *(__be32 *)ptr == htonl((TCPOPT_NOP << 24)

| (TCPOPT_NOP << 16)

| (TCPOPT_TIMESTAMP << 8)

| TCPOLEN_TIMESTAMP))

return;

while (length > 0) {

int opcode = *ptr++;

int opsize, i;

switch (opcode) {

case TCPOPT_EOL:

return;

case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */

length--;

continue;

default:

if (length < 2)

return;

opsize = *ptr++;

if (opsize < 2) /* "silly options" */

return;

if (opsize > length)

return; /* don't parse partial options */

if (opcode == TCPOPT_SACK

&& opsize >= (TCPOLEN_SACK_BASE

+ TCPOLEN_SACK_PERBLOCK)

&& !((opsize - TCPOLEN_SACK_BASE)

% TCPOLEN_SACK_PERBLOCK)) {

for (i = 0;

i < (opsize - TCPOLEN_SACK_BASE);

i += TCPOLEN_SACK_PERBLOCK) {

tmp = get_unaligned_be32((__be32 *)(ptr+i)+1);

if (after(tmp, *sack))

*sack = tmp;

}

return;

}

ptr += opsize - 2;

length -= opsize;

}

}

}

static void tcp_init_sender(struct ip_ct_tcp_state *sender,

struct ip_ct_tcp_state *receiver,

const struct sk_buff *skb,

unsigned int dataoff,

const struct tcphdr *tcph,

u32 end, u32 win,

enum ip_conntrack_dir dir)

{

/* 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 (dir == IP_CT_DIR_REPLY &&

!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE &&

receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) {

sender->td_scale = 0;

receiver->td_scale = 0;

}

}

__printf(6, 7)

static enum nf_ct_tcp_action nf_tcp_log_invalid(const struct sk_buff *skb,

const struct nf_conn *ct,

const struct nf_hook_state *state,

const struct ip_ct_tcp_state *sender,

enum nf_ct_tcp_action ret,

const char *fmt, ...)

{

const struct nf_tcp_net *tn = nf_tcp_pernet(nf_ct_net(ct));

struct va_format vaf;

va_list args;

bool be_liberal;

be_liberal = sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL || tn->tcp_be_liberal;

if (be_liberal)

return NFCT_TCP_ACCEPT;

va_start(args, fmt);

vaf.fmt = fmt;

vaf.va = &args;

nf_ct_l4proto_log_invalid(skb, ct, state, "%pV", &vaf);

va_end(args);

return ret;

}

static enum nf_ct_tcp_action

tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir,

unsigned int index, const struct sk_buff *skb,

unsigned int dataoff, const struct tcphdr *tcph,

const struct nf_hook_state *hook_state)

{

struct ip_ct_tcp *state = &ct->proto.tcp;

struct ip_ct_tcp_state *sender = &state->seen[dir];

struct ip_ct_tcp_state *receiver = &state->seen[!dir];

__u32 seq, ack, sack, end, win, swin;

bool in_recv_win, seq_ok;

s32 receiver_offset;

u16 win_raw;

/*

* Get the required data from the packet.

*/

seq = ntohl(tcph->seq);

ack = sack = ntohl(tcph->ack_seq);

win_raw = ntohs(tcph->window);

win = win_raw;

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 = nf_ct_seq_offset(ct, !dir, ack - 1);

ack -= receiver_offset;

sack -= receiver_offset;

if (sender->td_maxwin == 0) {

/*

* Initialize sender data.

*/

if (tcph->syn) {

tcp_init_sender(sender, receiver,

skb, dataoff, tcph,

end, win, dir);

if (!tcph->ack)

/* Simultaneous open */

return NFCT_TCP_ACCEPT;

} 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;

swin = win << sender->td_scale;

sender->td_maxwin = (swin == 0 ? 1 : swin);

sender->td_maxend = end + sender->td_maxwin;

if (receiver->td_maxwin == 0) {

/* 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.

*/

receiver->td_end = receiver->td_maxend = sack;

} else if (sack == receiver->td_end + 1) {

/* Likely a reply to a keepalive.

* Needed for III.

*/

receiver->td_end++;

}

}

} else if (tcph->syn &&

after(end, sender->td_end) &&

(state->state == TCP_CONNTRACK_SYN_SENT ||

state->state == TCP_CONNTRACK_SYN_RECV)) {

/*

* 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."

*

* Re-init state for this direction, just like for the first

* syn(-ack) reply, it might differ in seq, ack or tcp options.

*/

tcp_init_sender(sender, receiver,

skb, dataoff, tcph,

end, win, dir);

if (dir == IP_CT_DIR_REPLY && !tcph->ack)

return NFCT_TCP_ACCEPT;

}

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 (tcph->rst && seq == 0 && state->state == TCP_CONNTRACK_SYN_SENT)

/*

* RST sent answering SYN.

*/

seq = end = sender->td_end;

seq_ok = before(seq, sender->td_maxend + 1);

if (!seq_ok) {

u32 overshot = end - sender->td_maxend + 1;

bool ack_ok;

ack_ok = after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1);

in_recv_win = receiver->td_maxwin &&

after(end, sender->td_end - receiver->td_maxwin - 1);

if (in_recv_win &&

ack_ok &&

overshot <= receiver->td_maxwin &&

before(sack, receiver->td_end + 1)) {

/* Work around TCPs that send more bytes than allowed by

* the receive window.

*

* If the (marked as invalid) packet is allowed to pass by

* the ruleset and the peer acks this data, then its possible

* all future packets will trigger 'ACK is over upper bound' check.

*

* Thus if only the sequence check fails then do update td_end so

* possible ACK for this data can update internal state.

*/

sender->td_end = end;

sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;

return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE,

"%u bytes more than expected", overshot);

}

return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_INVALID,

"SEQ is over upper bound %u (over the window of the receiver)",

sender->td_maxend + 1);

}

if (!before(sack, receiver->td_end + 1))

return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_INVALID,

"ACK is over upper bound %u (ACKed data not seen yet)",

receiver->td_end + 1);

/* Is the ending sequence in the receive window (if available)? */

in_recv_win = !receiver->td_maxwin ||

after(end, sender->td_end - receiver->td_maxwin - 1);

if (!in_recv_win)

return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE,

"SEQ is under lower bound %u (already ACKed data retransmitted)",

sender->td_end - receiver->td_maxwin - 1);

if (!after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1))

return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE,

"ignored ACK under lower bound %u (possible overly delayed)",

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 (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;

/* 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_raw) {

state->retrans++;

} else {

state->last_dir = dir;

state->last_seq = seq;

state->last_ack = ack;

state->last_end = end;

state->last_win = win_raw;

state->retrans = 0;

}

}

return NFCT_TCP_ACCEPT;

}

static void __cold nf_tcp_handle_invalid(struct nf_conn *ct,

enum ip_conntrack_dir dir,

int index,

const struct sk_buff *skb,

const struct nf_hook_state *hook_state)

{

const unsigned int *timeouts;

const struct nf_tcp_net *tn;

unsigned int timeout;

u32 expires;

if (!test_bit(IPS_ASSURED_BIT, &ct->status) ||

test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status))

return;

/* We don't want to have connections hanging around in ESTABLISHED

* state for long time 'just because' conntrack deemed a FIN/RST

* out-of-window.

*

* Shrink the timeout just like when there is unacked data.

* This speeds up eviction of 'dead' connections where the

* connection and conntracks internal state are out of sync.

*/

switch (index) {

case TCP_RST_SET:

case TCP_FIN_SET:

break;

default:

return;

}

if (ct->proto.tcp.last_dir != dir &&

(ct->proto.tcp.last_index == TCP_FIN_SET ||

ct->proto.tcp.last_index == TCP_RST_SET)) {

expires = nf_ct_expires(ct);

if (expires < 120 * HZ)

return;

tn = nf_tcp_pernet(nf_ct_net(ct));

timeouts = nf_ct_timeout_lookup(ct);

if (!timeouts)

timeouts = tn->timeouts;

timeout = READ_ONCE(timeouts[TCP_CONNTRACK_UNACK]);

if (expires > timeout) {

nf_ct_l4proto_log_invalid(skb, ct, hook_state,

"packet (index %d, dir %d) response for index %d lower timeout to %u",

index, dir, ct->proto.tcp.last_index, timeout);

WRITE_ONCE(ct->timeout, timeout + nfct_time_stamp);

}

} else {

ct->proto.tcp.last_index = index;

ct->proto.tcp.last_dir = dir;

}

}

/* table of valid flag combinations - PUSH, ECE and CWR are always valid */

static const u8 tcp_valid_flags[(TCPHDR_FIN|TCPHDR_SYN|TCPHDR_RST|TCPHDR_ACK|

TCPHDR_URG) + 1] =

{

[TCPHDR_SYN] = 1,

[TCPHDR_SYN|TCPHDR_URG] = 1,

[TCPHDR_SYN|TCPHDR_ACK] = 1,

[TCPHDR_RST] = 1,

[TCPHDR_RST|TCPHDR_ACK] = 1,

[TCPHDR_FIN|TCPHDR_ACK] = 1,

[TCPHDR_FIN|TCPHDR_ACK|TCPHDR_URG] = 1,

[TCPHDR_ACK] = 1,

[TCPHDR_ACK|TCPHDR_URG] = 1,

};

static void tcp_error_log(const struct sk_buff *skb,

const struct nf_hook_state *state,

const char *msg)

{

nf_l4proto_log_invalid(skb, state, IPPROTO_TCP, "%s", msg);

}

/* Protect conntrack agaist broken packets. Code taken from ipt_unclean.c. */

static bool tcp_error(const struct tcphdr *th,

struct sk_buff *skb,

unsigned int dataoff,

const struct nf_hook_state *state)

{

unsigned int tcplen = skb->len - dataoff;

u8 tcpflags;

/* Not whole TCP header or malformed packet */

if (th->doff*4 < sizeof(struct tcphdr) || tcplen < th->doff*4) {

tcp_error_log(skb, state, "truncated packet");

return true;

}

/* Checksum invalid? Ignore.

* We skip checking packets on the outgoing path

* because the checksum is assumed to be correct.

*/

/* FIXME: Source route IP option packets --RR */

if (state->net->ct.sysctl_checksum &&

state->hook == NF_INET_PRE_ROUTING &&

nf_checksum(skb, state->hook, dataoff, IPPROTO_TCP, state->pf)) {

tcp_error_log(skb, state, "bad checksum");

return true;

}

/* Check TCP flags. */

tcpflags = (tcp_flag_byte(th) & ~(TCPHDR_ECE|TCPHDR_CWR|TCPHDR_PSH));

if (!tcp_valid_flags[tcpflags]) {

tcp_error_log(skb, state, "invalid tcp flag combination");

return true;

}

return false;

}

static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,

unsigned int dataoff,

const struct tcphdr *th,

const struct nf_hook_state *state)

{

enum tcp_conntrack new_state;

struct net *net = nf_ct_net(ct);

const struct nf_tcp_net *tn = nf_tcp_pernet(net);

/* 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) {

tcp_error_log(skb, state, "invalid new");

return false;

}

if (new_state == TCP_CONNTRACK_SYN_SENT) {

memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp));

/* 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]);

} else if (tn->tcp_loose == 0) {

/* Don't try to pick up connections. */

return false;

} else {

memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp));

/*

* 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;

/* 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;

}

/* tcp_packet will set them */

ct->proto.tcp.last_index = TCP_NONE_SET;

return true;

}

static bool tcp_can_early_drop(const struct nf_conn *ct)

{

switch (ct->proto.tcp.state) {

case TCP_CONNTRACK_FIN_WAIT:

case TCP_CONNTRACK_LAST_ACK:

case TCP_CONNTRACK_TIME_WAIT:

case TCP_CONNTRACK_CLOSE:

case TCP_CONNTRACK_CLOSE_WAIT:

return true;

default:

break;

}

return false;

}

void nf_conntrack_tcp_set_closing(struct nf_conn *ct)

{

enum tcp_conntrack old_state;

const unsigned int *timeouts;

u32 timeout;

if (!nf_ct_is_confirmed(ct))

return;

spin_lock_bh(&ct->lock);

old_state = ct->proto.tcp.state;

ct->proto.tcp.state = TCP_CONNTRACK_CLOSE;

if (old_state == TCP_CONNTRACK_CLOSE ||

test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) {

spin_unlock_bh(&ct->lock);

return;

}

timeouts = nf_ct_timeout_lookup(ct);

if (!timeouts) {

const struct nf_tcp_net *tn;

tn = nf_tcp_pernet(nf_ct_net(ct));

timeouts = tn->timeouts;

}

timeout = timeouts[TCP_CONNTRACK_CLOSE];

WRITE_ONCE(ct->timeout, timeout + nfct_time_stamp);

spin_unlock_bh(&ct->lock);

nf_conntrack_event_cache(IPCT_PROTOINFO, ct);

}

static void nf_ct_tcp_state_reset(struct ip_ct_tcp_state *state)

{

state->td_end = 0;

state->td_maxend = 0;

state->td_maxwin = 0;

state->td_maxack = 0;

state->td_scale = 0;

state->flags &= IP_CT_TCP_FLAG_BE_LIBERAL;

}

/* Returns verdict for packet, or -1 for invalid. */

int nf_conntrack_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);

enum tcp_conntrack new_state, old_state;

unsigned int index, *timeouts;

enum nf_ct_tcp_action res;

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, state))

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];

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