* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
- *
- * Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>:
- * - Real stateful connection tracking
- * - Modified state transitions table
- * - Window scaling support added
- * - SACK support added
- *
- * Willy Tarreau:
- * - State table bugfixes
- * - More robust state changes
- * - Tuning timer parameters
- *
- * 27 Oct 2004: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
- * - genelized Layer 3 protocol part.
- *
- * Derived from net/ipv4/netfilter/ip_conntrack_proto_tcp.c
- *
- * version 2.2
*/
#include <linux/types.h>
-#include <linux/sched.h>
#include <linux/timer.h>
-#include <linux/netfilter.h>
#include <linux/module.h>
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/skbuff.h>
#include <linux/ipv6.h>
#include <net/ip6_checksum.h>
+#include <asm/unaligned.h>
#include <net/tcp.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_log.h>
+#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
+#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
-#if 0
-#define DEBUGP printk
-#define DEBUGP_VARS
-#else
-#define DEBUGP(format, args...)
-#endif
-
-/* Protects conntrack->proto.tcp */
-static DEFINE_RWLOCK(tcp_lock);
-
-/* "Be conservative in what you do,
- be liberal in what you accept from others."
+/* "Be conservative in what you do,
+ be liberal in what you accept from others."
If it's non-zero, we mark only out of window RST segments as INVALID. */
-int nf_ct_tcp_be_liberal __read_mostly = 0;
+static int nf_ct_tcp_be_liberal __read_mostly = 0;
-/* When connection is picked up from the middle, how many packets are required
- to pass in each direction when we assume we are in sync - if any side uses
- window scaling, we lost the game.
- If it is set to zero, we disable picking up already established
+/* If it is set to zero, we disable picking up already established
connections. */
-int nf_ct_tcp_loose __read_mostly = 3;
+static int nf_ct_tcp_loose __read_mostly = 1;
-/* Max number of the retransmitted packets without receiving an (acceptable)
- ACK from the destination. If this number is reached, a shorter timer
+/* Max number of the retransmitted packets without receiving an (acceptable)
+ ACK from the destination. If this number is reached, a shorter timer
will be started. */
-int nf_ct_tcp_max_retrans __read_mostly = 3;
+static int nf_ct_tcp_max_retrans __read_mostly = 3;
/* FIXME: Examine ipfilter's timeouts and conntrack transitions more
closely. They're more complex. --RR */
-static const char *tcp_conntrack_names[] = {
+static const char *const tcp_conntrack_names[] = {
"NONE",
"SYN_SENT",
"SYN_RECV",
"LAST_ACK",
"TIME_WAIT",
"CLOSE",
- "LISTEN"
+ "SYN_SENT2",
};
-
+
#define SECS * HZ
#define MINS * 60 SECS
#define HOURS * 60 MINS
#define DAYS * 24 HOURS
-static unsigned int nf_ct_tcp_timeout_syn_sent __read_mostly = 2 MINS;
-static unsigned int nf_ct_tcp_timeout_syn_recv __read_mostly = 60 SECS;
-static unsigned int nf_ct_tcp_timeout_established __read_mostly = 5 DAYS;
-static unsigned int nf_ct_tcp_timeout_fin_wait __read_mostly = 2 MINS;
-static unsigned int nf_ct_tcp_timeout_close_wait __read_mostly = 60 SECS;
-static unsigned int nf_ct_tcp_timeout_last_ack __read_mostly = 30 SECS;
-static unsigned int nf_ct_tcp_timeout_time_wait __read_mostly = 2 MINS;
-static unsigned int nf_ct_tcp_timeout_close __read_mostly = 10 SECS;
-
/* RFC1122 says the R2 limit should be at least 100 seconds.
- Linux uses 15 packets as limit, which corresponds
+ Linux uses 15 packets as limit, which corresponds
to ~13-30min depending on RTO. */
-static unsigned int nf_ct_tcp_timeout_max_retrans __read_mostly = 5 MINS;
-
-static unsigned int * tcp_timeouts[] = {
- NULL, /* TCP_CONNTRACK_NONE */
- &nf_ct_tcp_timeout_syn_sent, /* TCP_CONNTRACK_SYN_SENT, */
- &nf_ct_tcp_timeout_syn_recv, /* TCP_CONNTRACK_SYN_RECV, */
- &nf_ct_tcp_timeout_established, /* TCP_CONNTRACK_ESTABLISHED, */
- &nf_ct_tcp_timeout_fin_wait, /* TCP_CONNTRACK_FIN_WAIT, */
- &nf_ct_tcp_timeout_close_wait, /* TCP_CONNTRACK_CLOSE_WAIT, */
- &nf_ct_tcp_timeout_last_ack, /* TCP_CONNTRACK_LAST_ACK, */
- &nf_ct_tcp_timeout_time_wait, /* TCP_CONNTRACK_TIME_WAIT, */
- &nf_ct_tcp_timeout_close, /* TCP_CONNTRACK_CLOSE, */
- NULL, /* TCP_CONNTRACK_LISTEN */
- };
-
+static unsigned int nf_ct_tcp_timeout_max_retrans __read_mostly = 5 MINS;
+static unsigned int nf_ct_tcp_timeout_unacknowledged __read_mostly = 5 MINS;
+
+static unsigned int tcp_timeouts[TCP_CONNTRACK_MAX] __read_mostly = {
+ [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,
+};
+
#define sNO TCP_CONNTRACK_NONE
#define sSS TCP_CONNTRACK_SYN_SENT
#define sSR TCP_CONNTRACK_SYN_RECV
#define sLA TCP_CONNTRACK_LAST_ACK
#define sTW TCP_CONNTRACK_TIME_WAIT
#define sCL TCP_CONNTRACK_CLOSE
-#define sLI TCP_CONNTRACK_LISTEN
+#define sS2 TCP_CONNTRACK_SYN_SENT2
#define sIV TCP_CONNTRACK_MAX
#define sIG TCP_CONNTRACK_IGNORE
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
+ * 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*
* The meaning of the states are:
*
* NONE: initial state
- * SYN_SENT: SYN-only packet seen
+ * 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)
+ * CLOSE_WAIT: ACK seen (after FIN)
* LAST_ACK: FIN seen (after FIN)
* TIME_WAIT: last ACK seen
- * CLOSE: closed connection
- *
- * LISTEN state is not used.
+ * 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
+ * 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 they are invalid
- * or we do not support the request (simultaneous open)
+ * if we regard them as truly invalid packets
*/
-static enum tcp_conntrack tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
+static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
{
/* ORIGINAL */
-/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */
-/*syn*/ { sSS, sSS, sIG, sIG, sIG, sIG, sIG, sSS, sSS, sIV },
+/* 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
- * sSR -> sIG Late 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
+ * are errors. Receiver will reply with RST
* and close the connection.
* Or we are not in sync and hold a dead connection.
* sFW -> sIG
* sTW -> sSS Reopened connection (RFC 1122).
* sCL -> sSS
*/
-/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */
-/*synack*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV },
+/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */
+/*synack*/ { sIV, sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, sSR },
/*
- * A SYN/ACK from the client is always invalid:
- * - either it tries to set up a simultaneous open, which is
- * not supported;
- * - or the firewall has just been inserted between the two hosts
- * during the session set-up. The SYN will be retransmitted
- * by the true client (or it'll time out).
+ * 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 -> 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 -> sIG
+ * sCL -> sIG
*/
-/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */
+/* 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.
+ * 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, sLI */
+/* 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.
* sTW -> sTW Retransmitted last ACK. Remain in the same state.
* sCL -> sCL
*/
-/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */
-/*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV },
+/* 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, sLI */
-/*syn*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV },
+/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */
+/*syn*/ { sIV, sS2, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sS2 },
/*
* sNO -> sIV Never reached.
- * sSS -> sIV Simultaneous open, not supported
- * sSR -> sIV Simultaneous open, not supported.
- * sES -> sIV Server may not initiate a connection.
+ * 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 -> sIV Reopened connection, but server may not do it.
* sCL -> sIV
*/
-/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */
-/*synack*/ { sIV, sSR, sSR, sIG, sIG, sIG, sIG, sIG, sIG, sIV },
+/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */
+/*synack*/ { sIV, sSR, sSR, sIG, sIG, sIG, sIG, sIG, sIG, sSR },
/*
* sSS -> sSR Standard open.
+ * sS2 -> sSR Simultaneous open
* sSR -> sSR Retransmitted SYN/ACK.
* sES -> sIG Late retransmitted SYN/ACK?
* sFW -> sIG Might be SYN/ACK answering ignored SYN
* sTW -> sIG
* sCL -> sIG
*/
-/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */
+/* 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.
* sTW -> sTW
* sCL -> sCL
*/
-/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */
-/*ack*/ { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIV },
+/* 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.
* sTW -> sTW Retransmitted last ACK.
* sCL -> sCL
*/
-/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */
-/*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV },
+/* 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 }
- }
+ }
};
-static int tcp_pkt_to_tuple(const struct sk_buff *skb,
- unsigned int dataoff,
- struct nf_conntrack_tuple *tuple)
+static bool tcp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
+ struct nf_conntrack_tuple *tuple)
{
- struct tcphdr _hdr, *hp;
+ const struct tcphdr *hp;
+ struct tcphdr _hdr;
/* Actually only need first 8 bytes. */
hp = skb_header_pointer(skb, dataoff, 8, &_hdr);
if (hp == NULL)
- return 0;
+ return false;
tuple->src.u.tcp.port = hp->source;
tuple->dst.u.tcp.port = hp->dest;
- return 1;
+ return true;
}
-static int tcp_invert_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_conntrack_tuple *orig)
+static bool tcp_invert_tuple(struct nf_conntrack_tuple *tuple,
+ const struct nf_conntrack_tuple *orig)
{
tuple->src.u.tcp.port = orig->dst.u.tcp.port;
tuple->dst.u.tcp.port = orig->src.u.tcp.port;
- return 1;
+ return true;
}
/* Print out the per-protocol part of the tuple. */
}
/* Print out the private part of the conntrack. */
-static int tcp_print_conntrack(struct seq_file *s,
- const struct nf_conn *conntrack)
+static int tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
{
enum tcp_conntrack state;
- read_lock_bh(&tcp_lock);
- state = conntrack->proto.tcp.state;
- read_unlock_bh(&tcp_lock);
+ spin_lock_bh(&ct->lock);
+ state = ct->proto.tcp.state;
+ spin_unlock_bh(&ct->lock);
return seq_printf(s, "%s ", tcp_conntrack_names[state]);
}
/* TCP connection tracking based on 'Real Stateful TCP Packet Filtering
in IP Filter' by Guido van Rooij.
-
+
http://www.nluug.nl/events/sane2000/papers.html
http://www.iae.nl/users/guido/papers/tcp_filtering.ps.gz
-
+
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_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 ack: sack <= receiver.td_end
- IV. Lower bound for valid ack: ack >= receiver.td_end - MAXACKWINDOW
+ 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.
+ 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 ack is not ignored -
- we doesn't have to deal with fragments.
+ 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,
- struct tcphdr *tcph)
+ 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,
- struct tcphdr *tcph,
+ const struct tcphdr *tcph,
struct ip_ct_tcp_state *state)
{
unsigned char buff[(15 * 4) - sizeof(struct tcphdr)];
- unsigned char *ptr;
+ const unsigned char *ptr;
int length = (tcph->doff*4) - sizeof(struct tcphdr);
if (!length)
length, buff);
BUG_ON(ptr == NULL);
- state->td_scale =
+ state->td_scale =
state->flags = 0;
while (length > 0) {
if (opsize > length)
break; /* don't parse partial options */
- if (opcode == TCPOPT_SACK_PERM
+ if (opcode == TCPOPT_SACK_PERM
&& opsize == TCPOLEN_SACK_PERM)
state->flags |= IP_CT_TCP_FLAG_SACK_PERM;
else if (opcode == TCPOPT_WINDOW
}
static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff,
- struct tcphdr *tcph, __u32 *sack)
+ const struct tcphdr *tcph, __u32 *sack)
{
- unsigned char buff[(15 * 4) - sizeof(struct tcphdr)];
- unsigned char *ptr;
+ unsigned char buff[(15 * 4) - sizeof(struct tcphdr)];
+ const unsigned char *ptr;
int length = (tcph->doff*4) - sizeof(struct tcphdr);
__u32 tmp;
/* Fast path for timestamp-only option */
if (length == TCPOLEN_TSTAMP_ALIGNED*4
- && *(__u32 *)ptr ==
- __constant_ntohl((TCPOPT_NOP << 24)
- | (TCPOPT_NOP << 16)
- | (TCPOPT_TIMESTAMP << 8)
- | TCPOLEN_TIMESTAMP))
+ && *(__be32 *)ptr == htonl((TCPOPT_NOP << 24)
+ | (TCPOPT_NOP << 16)
+ | (TCPOPT_TIMESTAMP << 8)
+ | TCPOLEN_TIMESTAMP))
return;
while (length > 0) {
if (opsize > length)
break; /* 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) {
- memcpy(&tmp, (__u32 *)(ptr + i) + 1,
- sizeof(__u32));
- tmp = ntohl(tmp);
+ 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;
}
}
-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)
+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;
- int res;
+ bool res;
/*
* Get the required data from the packet.
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) {
+ pr_debug("tcp_in_window: START\n");
+ pr_debug("tcp_in_window: ");
+ nf_ct_dump_tuple(tuple);
+ pr_debug("seq=%u ack=%u sack=%u win=%u end=%u\n",
+ seq, ack, sack, 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 && tcph->ack) {
+ if (tcph->syn) {
/*
- * Outgoing SYN-ACK in reply to a SYN.
+ * SYN-ACK in reply to a SYN
+ * or SYN from reply direction in simultaneous open.
*/
- sender->td_end =
+ 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 =
+ 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;
&& 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
+ * not wait at all; it must only be sure to use sequence
* numbers larger than those recently used."
*/
sender->td_end =
* 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))
+ } 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
*/
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 (sender->loose || receiver->loose ||
- (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)))) {
- /*
+ pr_debug("tcp_in_window: ");
+ nf_ct_dump_tuple(tuple);
+ pr_debug("seq=%u ack=%u sack =%u win=%u end=%u\n",
+ seq, ack, sack, 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)
swin = win + (sack - ack);
if (sender->td_maxwin < swin)
sender->td_maxwin = swin;
- if (after(end, sender->td_end))
+ 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 (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) {
state->retrans = 0;
}
}
- /*
- * Close the window of disabled window tracking :-)
- */
- if (sender->loose)
- sender->loose--;
-
- res = 1;
+ res = true;
} else {
- if (LOG_INVALID(IPPROTO_TCP))
+ 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) ?
: "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)");
+ }
- res = nf_ct_tcp_be_liberal;
- }
-
- 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);
+ 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;
}
-#ifdef CONFIG_IP_NF_NAT_NEEDED
+#ifdef CONFIG_NF_NAT_NEEDED
/* Update sender->td_end after NAT successfully mangled the packet */
/* Caller must linearize skb at tcp header. */
-void nf_conntrack_tcp_update(struct sk_buff *skb,
+void nf_conntrack_tcp_update(const struct sk_buff *skb,
unsigned int dataoff,
- struct nf_conn *conntrack,
+ struct nf_conn *ct,
int dir)
{
- struct tcphdr *tcph = (void *)skb->data + dataoff;
+ const struct tcphdr *tcph = (const void *)skb->data + dataoff;
+ const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[dir];
+ const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[!dir];
__u32 end;
-#ifdef DEBUGP_VARS
- struct ip_ct_tcp_state *sender = &conntrack->proto.tcp.seen[dir];
- struct ip_ct_tcp_state *receiver = &conntrack->proto.tcp.seen[!dir];
-#endif
end = segment_seq_plus_len(ntohl(tcph->seq), skb->len, dataoff, tcph);
- write_lock_bh(&tcp_lock);
+ spin_lock_bh(&ct->lock);
/*
* We have to worry for the ack in the reply packet only...
*/
- if (after(end, conntrack->proto.tcp.seen[dir].td_end))
- conntrack->proto.tcp.seen[dir].td_end = end;
- conntrack->proto.tcp.last_end = end;
- write_unlock_bh(&tcp_lock);
- DEBUGP("tcp_update: 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 (after(end, ct->proto.tcp.seen[dir].td_end))
+ ct->proto.tcp.seen[dir].td_end = end;
+ ct->proto.tcp.last_end = end;
+ spin_unlock_bh(&ct->lock);
+ pr_debug("tcp_update: 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);
}
-
+EXPORT_SYMBOL_GPL(nf_conntrack_tcp_update);
#endif
#define TH_FIN 0x01
#define TH_ECE 0x40
#define TH_CWR 0x80
-/* table of valid flag combinations - ECE and CWR are always valid */
-static u8 tcp_valid_flags[(TH_FIN|TH_SYN|TH_RST|TH_PUSH|TH_ACK|TH_URG) + 1] =
+/* table of valid flag combinations - PUSH, ECE and CWR are always valid */
+static const u8 tcp_valid_flags[(TH_FIN|TH_SYN|TH_RST|TH_ACK|TH_URG) + 1] =
{
[TH_SYN] = 1,
+ [TH_SYN|TH_URG] = 1,
[TH_SYN|TH_ACK] = 1,
- [TH_SYN|TH_PUSH] = 1,
- [TH_SYN|TH_ACK|TH_PUSH] = 1,
[TH_RST] = 1,
[TH_RST|TH_ACK] = 1,
- [TH_RST|TH_ACK|TH_PUSH] = 1,
[TH_FIN|TH_ACK] = 1,
+ [TH_FIN|TH_ACK|TH_URG] = 1,
[TH_ACK] = 1,
- [TH_ACK|TH_PUSH] = 1,
[TH_ACK|TH_URG] = 1,
- [TH_ACK|TH_URG|TH_PUSH] = 1,
- [TH_FIN|TH_ACK|TH_PUSH] = 1,
- [TH_FIN|TH_ACK|TH_URG] = 1,
- [TH_FIN|TH_ACK|TH_URG|TH_PUSH] = 1,
};
/* Protect conntrack agaist broken packets. Code taken from ipt_unclean.c. */
-static int tcp_error(struct sk_buff *skb,
+static int tcp_error(struct net *net,
+ struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info *ctinfo,
- int pf,
+ u_int8_t pf,
unsigned int hooknum)
{
- struct tcphdr _tcph, *th;
+ const struct tcphdr *th;
+ struct tcphdr _tcph;
unsigned int tcplen = skb->len - dataoff;
u_int8_t tcpflags;
/* Smaller that minimal TCP header? */
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
if (th == NULL) {
- if (LOG_INVALID(IPPROTO_TCP))
+ if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: short packet ");
return -NF_ACCEPT;
- }
-
+ }
+
/* Not whole TCP header or malformed packet */
if (th->doff*4 < sizeof(struct tcphdr) || tcplen < th->doff*4) {
- if (LOG_INVALID(IPPROTO_TCP))
+ if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: truncated/malformed packet ");
return -NF_ACCEPT;
}
-
+
/* 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 (nf_conntrack_checksum &&
- ((pf == PF_INET && hooknum == NF_IP_PRE_ROUTING) ||
- (pf == PF_INET6 && hooknum == NF_IP6_PRE_ROUTING)) &&
+ if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
nf_checksum(skb, hooknum, dataoff, IPPROTO_TCP, pf)) {
- if (LOG_INVALID(IPPROTO_TCP))
+ if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: bad TCP checksum ");
return -NF_ACCEPT;
}
/* Check TCP flags. */
- tcpflags = (((u_int8_t *)th)[13] & ~(TH_ECE|TH_CWR));
+ tcpflags = (((u_int8_t *)th)[13] & ~(TH_ECE|TH_CWR|TH_PUSH));
if (!tcp_valid_flags[tcpflags]) {
- if (LOG_INVALID(IPPROTO_TCP))
+ if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid TCP flag combination ");
return -NF_ACCEPT;
}
/* Returns verdict for packet, or -1 for invalid. */
-static int tcp_packet(struct nf_conn *conntrack,
+static int tcp_packet(struct nf_conn *ct,
const struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
- int pf,
+ 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;
- struct tcphdr *th, _tcph;
+ 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);
- write_lock_bh(&tcp_lock);
- old_state = conntrack->proto.tcp.state;
+ 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.
+ * 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
- && 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
+ && 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
+ * 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))
+ 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 ");
- if (del_timer(&conntrack->timeout))
- conntrack->timeout.function((unsigned long)
- conntrack);
- return -NF_DROP;
+ nf_ct_kill(ct);
+ 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 =
+ 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);
- write_unlock_bh(&tcp_lock);
- if (LOG_INVALID(IPPROTO_TCP))
+ spin_unlock_bh(&ct->lock);
+ if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
- "nf_ct_tcp: invalid packed ignored ");
+ "nf_ct_tcp: invalid packet 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))
+ 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_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 {
+ 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 */
write_unlock_bh(&tcp_lock);
- if (LOG_INVALID(IPPROTO_TCP))
- nf_log_packet(pf, 0, skb, NULL, NULL,
- NULL, "nf_ct_tcp: invalid SYN");
+ if (LOG_INVALID(net, IPPROTO_TCP))
+ nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
+ "nf_ct_tcp: invalid RST ");
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) {
+ && ((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:
*
break;
}
- if (!tcp_in_window(&conntrack->proto.tcp, dir, index,
+ if (!tcp_in_window(ct, &ct->proto.tcp, dir, index,
skb, dataoff, th, pf)) {
- write_unlock_bh(&tcp_lock);
+ spin_unlock_bh(&ct->lock);
return -NF_ACCEPT;
}
in_window:
/* From now on we have got in-window packets */
- conntrack->proto.tcp.last_index = index;
+ ct->proto.tcp.last_index = index;
+ ct->proto.tcp.last_dir = dir;
- 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);
+ 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);
- conntrack->proto.tcp.state = new_state;
+ ct->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);
+ && 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, skb);
+ nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
- if (!test_bit(IPS_SEEN_REPLY_BIT, &conntrack->status)) {
+ 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) {
- if (del_timer(&conntrack->timeout))
- conntrack->timeout.function((unsigned long)
- conntrack);
+ nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
- } else if (!test_bit(IPS_ASSURED_BIT, &conntrack->status)
+ } 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
+ /* 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);
+ set_bit(IPS_ASSURED_BIT, &ct->status);
+ nf_conntrack_event_cache(IPCT_STATUS, ct);
}
- nf_ct_refresh_acct(conntrack, ctinfo, skb, timeout);
+ 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 nf_conn *conntrack,
- const struct sk_buff *skb,
- unsigned int dataoff)
+static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
+ unsigned int dataoff)
{
enum tcp_conntrack new_state;
- 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
+ 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);
/* Invalid: delete conntrack */
if (new_state >= TCP_CONNTRACK_MAX) {
- DEBUGP("nf_ct_tcp: invalid new deleting.\n");
- return 0;
+ pr_debug("nf_ct_tcp: invalid new deleting.\n");
+ return false;
}
if (new_state == TCP_CONNTRACK_SYN_SENT) {
/* SYN packet */
- conntrack->proto.tcp.seen[0].td_end =
+ ct->proto.tcp.seen[0].td_end =
segment_seq_plus_len(ntohl(th->seq), skb->len,
dataoff, 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, dataoff, 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;
+ 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 0;
+ 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.
*/
- conntrack->proto.tcp.seen[0].td_end =
+ ct->proto.tcp.seen[0].td_end =
segment_seq_plus_len(ntohl(th->seq), skb->len,
dataoff, 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 = nf_ct_tcp_loose;
+ 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;
}
-
- 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;
+
+ 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 */
- 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;
+ 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;
}
-#if defined(CONFIG_NF_CT_NETLINK) || \
- defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
-static int tcp_to_nfattr(struct sk_buff *skb, struct nfattr *nfa,
- const struct nf_conn *ct)
+static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
+ struct nf_conn *ct)
{
- struct nfattr *nest_parms;
-
- read_lock_bh(&tcp_lock);
- nest_parms = NFA_NEST(skb, CTA_PROTOINFO_TCP);
- NFA_PUT(skb, CTA_PROTOINFO_TCP_STATE, sizeof(u_int8_t),
- &ct->proto.tcp.state);
- read_unlock_bh(&tcp_lock);
+ struct nlattr *nest_parms;
+ struct nf_ct_tcp_flags tmp = {};
+
+ spin_lock_bh(&ct->lock);
+ nest_parms = nla_nest_start(skb, CTA_PROTOINFO_TCP | NLA_F_NESTED);
+ if (!nest_parms)
+ goto nla_put_failure;
+
+ NLA_PUT_U8(skb, CTA_PROTOINFO_TCP_STATE, ct->proto.tcp.state);
+
+ NLA_PUT_U8(skb, CTA_PROTOINFO_TCP_WSCALE_ORIGINAL,
+ ct->proto.tcp.seen[0].td_scale);
- NFA_NEST_END(skb, nest_parms);
+ NLA_PUT_U8(skb, CTA_PROTOINFO_TCP_WSCALE_REPLY,
+ ct->proto.tcp.seen[1].td_scale);
+
+ tmp.flags = ct->proto.tcp.seen[0].flags;
+ NLA_PUT(skb, CTA_PROTOINFO_TCP_FLAGS_ORIGINAL,
+ sizeof(struct nf_ct_tcp_flags), &tmp);
+
+ tmp.flags = ct->proto.tcp.seen[1].flags;
+ NLA_PUT(skb, CTA_PROTOINFO_TCP_FLAGS_REPLY,
+ sizeof(struct nf_ct_tcp_flags), &tmp);
+ spin_unlock_bh(&ct->lock);
+
+ nla_nest_end(skb, nest_parms);
return 0;
-nfattr_failure:
- read_unlock_bh(&tcp_lock);
+nla_put_failure:
+ spin_unlock_bh(&ct->lock);
return -1;
}
-static const size_t cta_min_tcp[CTA_PROTOINFO_TCP_MAX] = {
- [CTA_PROTOINFO_TCP_STATE-1] = sizeof(u_int8_t),
+static const struct nla_policy tcp_nla_policy[CTA_PROTOINFO_TCP_MAX+1] = {
+ [CTA_PROTOINFO_TCP_STATE] = { .type = NLA_U8 },
+ [CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] = { .type = NLA_U8 },
+ [CTA_PROTOINFO_TCP_WSCALE_REPLY] = { .type = NLA_U8 },
+ [CTA_PROTOINFO_TCP_FLAGS_ORIGINAL] = { .len = sizeof(struct nf_ct_tcp_flags) },
+ [CTA_PROTOINFO_TCP_FLAGS_REPLY] = { .len = sizeof(struct nf_ct_tcp_flags) },
};
-static int nfattr_to_tcp(struct nfattr *cda[], struct nf_conn *ct)
+static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct)
{
- struct nfattr *attr = cda[CTA_PROTOINFO_TCP-1];
- struct nfattr *tb[CTA_PROTOINFO_TCP_MAX];
+ struct nlattr *pattr = cda[CTA_PROTOINFO_TCP];
+ struct nlattr *tb[CTA_PROTOINFO_TCP_MAX+1];
+ int err;
/* updates could not contain anything about the private
* protocol info, in that case skip the parsing */
- if (!attr)
+ if (!pattr)
return 0;
- nfattr_parse_nested(tb, CTA_PROTOINFO_TCP_MAX, attr);
+ err = nla_parse_nested(tb, CTA_PROTOINFO_TCP_MAX, pattr, tcp_nla_policy);
+ if (err < 0)
+ return err;
- if (nfattr_bad_size(tb, CTA_PROTOINFO_TCP_MAX, cta_min_tcp))
+ if (tb[CTA_PROTOINFO_TCP_STATE] &&
+ nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]) >= TCP_CONNTRACK_MAX)
return -EINVAL;
- if (!tb[CTA_PROTOINFO_TCP_STATE-1])
- return -EINVAL;
+ spin_lock_bh(&ct->lock);
+ if (tb[CTA_PROTOINFO_TCP_STATE])
+ ct->proto.tcp.state = nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]);
+
+ if (tb[CTA_PROTOINFO_TCP_FLAGS_ORIGINAL]) {
+ struct nf_ct_tcp_flags *attr =
+ nla_data(tb[CTA_PROTOINFO_TCP_FLAGS_ORIGINAL]);
+ ct->proto.tcp.seen[0].flags &= ~attr->mask;
+ ct->proto.tcp.seen[0].flags |= attr->flags & attr->mask;
+ }
- write_lock_bh(&tcp_lock);
- ct->proto.tcp.state =
- *(u_int8_t *)NFA_DATA(tb[CTA_PROTOINFO_TCP_STATE-1]);
- write_unlock_bh(&tcp_lock);
+ if (tb[CTA_PROTOINFO_TCP_FLAGS_REPLY]) {
+ struct nf_ct_tcp_flags *attr =
+ nla_data(tb[CTA_PROTOINFO_TCP_FLAGS_REPLY]);
+ ct->proto.tcp.seen[1].flags &= ~attr->mask;
+ ct->proto.tcp.seen[1].flags |= attr->flags & attr->mask;
+ }
+
+ if (tb[CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] &&
+ tb[CTA_PROTOINFO_TCP_WSCALE_REPLY] &&
+ ct->proto.tcp.seen[0].flags & IP_CT_TCP_FLAG_WINDOW_SCALE &&
+ ct->proto.tcp.seen[1].flags & IP_CT_TCP_FLAG_WINDOW_SCALE) {
+ ct->proto.tcp.seen[0].td_scale =
+ nla_get_u8(tb[CTA_PROTOINFO_TCP_WSCALE_ORIGINAL]);
+ ct->proto.tcp.seen[1].td_scale =
+ nla_get_u8(tb[CTA_PROTOINFO_TCP_WSCALE_REPLY]);
+ }
+ spin_unlock_bh(&ct->lock);
return 0;
}
+
+static int tcp_nlattr_size(void)
+{
+ return nla_total_size(0) /* CTA_PROTOINFO_TCP */
+ + nla_policy_len(tcp_nla_policy, CTA_PROTOINFO_TCP_MAX + 1);
+}
+
+static int tcp_nlattr_tuple_size(void)
+{
+ return nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1);
+}
#endif
#ifdef CONFIG_SYSCTL
static struct ctl_table_header *tcp_sysctl_header;
static struct ctl_table tcp_sysctl_table[] = {
{
- .ctl_name = NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT,
.procname = "nf_conntrack_tcp_timeout_syn_sent",
- .data = &nf_ct_tcp_timeout_syn_sent,
+ .data = &tcp_timeouts[TCP_CONNTRACK_SYN_SENT],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV,
.procname = "nf_conntrack_tcp_timeout_syn_recv",
- .data = &nf_ct_tcp_timeout_syn_recv,
+ .data = &tcp_timeouts[TCP_CONNTRACK_SYN_RECV],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED,
.procname = "nf_conntrack_tcp_timeout_established",
- .data = &nf_ct_tcp_timeout_established,
+ .data = &tcp_timeouts[TCP_CONNTRACK_ESTABLISHED],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT,
.procname = "nf_conntrack_tcp_timeout_fin_wait",
- .data = &nf_ct_tcp_timeout_fin_wait,
+ .data = &tcp_timeouts[TCP_CONNTRACK_FIN_WAIT],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT,
.procname = "nf_conntrack_tcp_timeout_close_wait",
- .data = &nf_ct_tcp_timeout_close_wait,
+ .data = &tcp_timeouts[TCP_CONNTRACK_CLOSE_WAIT],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK,
.procname = "nf_conntrack_tcp_timeout_last_ack",
- .data = &nf_ct_tcp_timeout_last_ack,
+ .data = &tcp_timeouts[TCP_CONNTRACK_LAST_ACK],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT,
.procname = "nf_conntrack_tcp_timeout_time_wait",
- .data = &nf_ct_tcp_timeout_time_wait,
+ .data = &tcp_timeouts[TCP_CONNTRACK_TIME_WAIT],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE,
.procname = "nf_conntrack_tcp_timeout_close",
- .data = &nf_ct_tcp_timeout_close,
+ .data = &tcp_timeouts[TCP_CONNTRACK_CLOSE],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS,
.procname = "nf_conntrack_tcp_timeout_max_retrans",
.data = &nf_ct_tcp_timeout_max_retrans,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ {
+ .procname = "nf_conntrack_tcp_timeout_unacknowledged",
+ .data = &nf_ct_tcp_timeout_unacknowledged,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
},
{
.ctl_name = NET_NF_CONNTRACK_TCP_LOOSE,
.data = &nf_ct_tcp_loose,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
.ctl_name = NET_NF_CONNTRACK_TCP_BE_LIBERAL,
.data = &nf_ct_tcp_be_liberal,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
.ctl_name = NET_NF_CONNTRACK_TCP_MAX_RETRANS,
.data = &nf_ct_tcp_max_retrans,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
.ctl_name = 0
#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT
static struct ctl_table tcp_compat_sysctl_table[] = {
{
- .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT,
.procname = "ip_conntrack_tcp_timeout_syn_sent",
- .data = &nf_ct_tcp_timeout_syn_sent,
+ .data = &tcp_timeouts[TCP_CONNTRACK_SYN_SENT],
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ {
+ .procname = "ip_conntrack_tcp_timeout_syn_sent2",
+ .data = &tcp_timeouts[TCP_CONNTRACK_SYN_SENT2],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV,
.procname = "ip_conntrack_tcp_timeout_syn_recv",
- .data = &nf_ct_tcp_timeout_syn_recv,
+ .data = &tcp_timeouts[TCP_CONNTRACK_SYN_RECV],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED,
.procname = "ip_conntrack_tcp_timeout_established",
- .data = &nf_ct_tcp_timeout_established,
+ .data = &tcp_timeouts[TCP_CONNTRACK_ESTABLISHED],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT,
.procname = "ip_conntrack_tcp_timeout_fin_wait",
- .data = &nf_ct_tcp_timeout_fin_wait,
+ .data = &tcp_timeouts[TCP_CONNTRACK_FIN_WAIT],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT,
.procname = "ip_conntrack_tcp_timeout_close_wait",
- .data = &nf_ct_tcp_timeout_close_wait,
+ .data = &tcp_timeouts[TCP_CONNTRACK_CLOSE_WAIT],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK,
.procname = "ip_conntrack_tcp_timeout_last_ack",
- .data = &nf_ct_tcp_timeout_last_ack,
+ .data = &tcp_timeouts[TCP_CONNTRACK_LAST_ACK],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT,
.procname = "ip_conntrack_tcp_timeout_time_wait",
- .data = &nf_ct_tcp_timeout_time_wait,
+ .data = &tcp_timeouts[TCP_CONNTRACK_TIME_WAIT],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE,
.procname = "ip_conntrack_tcp_timeout_close",
- .data = &nf_ct_tcp_timeout_close,
+ .data = &tcp_timeouts[TCP_CONNTRACK_CLOSE],
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS,
.procname = "ip_conntrack_tcp_timeout_max_retrans",
.data = &nf_ct_tcp_timeout_max_retrans,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
.ctl_name = NET_IPV4_NF_CONNTRACK_TCP_LOOSE,
.data = &nf_ct_tcp_loose,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
.ctl_name = NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL,
.data = &nf_ct_tcp_be_liberal,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
.ctl_name = NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS,
.data = &nf_ct_tcp_max_retrans,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
.ctl_name = 0
#endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */
#endif /* CONFIG_SYSCTL */
-struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 =
+struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly =
{
.l3proto = PF_INET,
.l4proto = IPPROTO_TCP,
.packet = tcp_packet,
.new = tcp_new,
.error = tcp_error,
-#if defined(CONFIG_NF_CT_NETLINK) || \
- defined(CONFIG_NF_CT_NETLINK_MODULE)
- .to_nfattr = tcp_to_nfattr,
- .from_nfattr = nfattr_to_tcp,
- .tuple_to_nfattr = nf_ct_port_tuple_to_nfattr,
- .nfattr_to_tuple = nf_ct_port_nfattr_to_tuple,
+#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+ .to_nlattr = tcp_to_nlattr,
+ .nlattr_size = tcp_nlattr_size,
+ .from_nlattr = nlattr_to_tcp,
+ .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
+ .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
+ .nlattr_tuple_size = tcp_nlattr_tuple_size,
+ .nla_policy = nf_ct_port_nla_policy,
#endif
#ifdef CONFIG_SYSCTL
.ctl_table_users = &tcp_sysctl_table_users,
#endif
#endif
};
+EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_tcp4);
-struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 =
+struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly =
{
.l3proto = PF_INET6,
.l4proto = IPPROTO_TCP,
.packet = tcp_packet,
.new = tcp_new,
.error = tcp_error,
-#if defined(CONFIG_NF_CT_NETLINK) || \
- defined(CONFIG_NF_CT_NETLINK_MODULE)
- .to_nfattr = tcp_to_nfattr,
- .from_nfattr = nfattr_to_tcp,
- .tuple_to_nfattr = nf_ct_port_tuple_to_nfattr,
- .nfattr_to_tuple = nf_ct_port_nfattr_to_tuple,
+#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+ .to_nlattr = tcp_to_nlattr,
+ .nlattr_size = tcp_nlattr_size,
+ .from_nlattr = nlattr_to_tcp,
+ .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
+ .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
+ .nlattr_tuple_size = tcp_nlattr_tuple_size,
+ .nla_policy = nf_ct_port_nla_policy,
#endif
#ifdef CONFIG_SYSCTL
.ctl_table_users = &tcp_sysctl_table_users,
.ctl_table = tcp_sysctl_table,
#endif
};
-
-EXPORT_SYMBOL(nf_conntrack_l4proto_tcp4);
-EXPORT_SYMBOL(nf_conntrack_l4proto_tcp6);
+EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_tcp6);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff