freebsd-skq/sys/netinet/tcp.h

173 lines
6.0 KiB
C
Raw Normal View History

1994-05-24 10:09:53 +00:00
/*
* Copyright (c) 1982, 1986, 1993
* The Regents of the University of California. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)tcp.h 8.1 (Berkeley) 6/10/93
1999-08-28 01:08:13 +00:00
* $FreeBSD$
1994-05-24 10:09:53 +00:00
*/
1994-08-21 05:27:42 +00:00
#ifndef _NETINET_TCP_H_
#define _NETINET_TCP_H_
#include <sys/cdefs.h>
#if __BSD_VISIBLE
typedef u_int32_t tcp_seq;
typedef u_int32_t tcp_cc; /* connection count per rfc1644 */
#define tcp6_seq tcp_seq /* for KAME src sync over BSD*'s */
#define tcp6hdr tcphdr /* for KAME src sync over BSD*'s */
1994-05-24 10:09:53 +00:00
/*
* TCP header.
* Per RFC 793, September, 1981.
*/
struct tcphdr {
u_short th_sport; /* source port */
u_short th_dport; /* destination port */
tcp_seq th_seq; /* sequence number */
tcp_seq th_ack; /* acknowledgement number */
1995-05-30 08:16:23 +00:00
#if BYTE_ORDER == LITTLE_ENDIAN
u_int th_x2:4, /* (unused) */
1994-05-24 10:09:53 +00:00
th_off:4; /* data offset */
#endif
1995-05-30 08:16:23 +00:00
#if BYTE_ORDER == BIG_ENDIAN
u_int th_off:4, /* data offset */
1994-05-24 10:09:53 +00:00
th_x2:4; /* (unused) */
#endif
u_char th_flags;
#define TH_FIN 0x01
#define TH_SYN 0x02
#define TH_RST 0x04
#define TH_PUSH 0x08
#define TH_ACK 0x10
#define TH_URG 0x20
#define TH_ECE 0x40
#define TH_CWR 0x80
#define TH_FLAGS (TH_FIN|TH_SYN|TH_RST|TH_ACK|TH_URG|TH_ECE|TH_CWR)
1994-05-24 10:09:53 +00:00
u_short th_win; /* window */
u_short th_sum; /* checksum */
u_short th_urp; /* urgent pointer */
};
#define TCPOPT_EOL 0
#define TCPOPT_NOP 1
#define TCPOPT_MAXSEG 2
#define TCPOLEN_MAXSEG 4
#define TCPOPT_WINDOW 3
#define TCPOLEN_WINDOW 3
#define TCPOPT_SACK_PERMITTED 4 /* Experimental */
#define TCPOLEN_SACK_PERMITTED 2
#define TCPOPT_SACK 5 /* Experimental */
#define TCPOLEN_SACK 8 /* 2*sizeof(tcp_seq) */
1994-05-24 10:09:53 +00:00
#define TCPOPT_TIMESTAMP 8
#define TCPOLEN_TIMESTAMP 10
#define TCPOLEN_TSTAMP_APPA (TCPOLEN_TIMESTAMP+2) /* appendix A */
#define TCPOPT_TSTAMP_HDR \
1994-05-24 10:09:53 +00:00
(TCPOPT_NOP<<24|TCPOPT_NOP<<16|TCPOPT_TIMESTAMP<<8|TCPOLEN_TIMESTAMP)
#define MAX_TCPOPTLEN 40 /* Absolute maximum TCP options len */
#define TCPOPT_CC 11 /* CC options: RFC-1644 */
#define TCPOPT_CCNEW 12
#define TCPOPT_CCECHO 13
#define TCPOLEN_CC 6
#define TCPOLEN_CC_APPA (TCPOLEN_CC+2)
#define TCPOPT_CC_HDR(ccopt) \
(TCPOPT_NOP<<24|TCPOPT_NOP<<16|(ccopt)<<8|TCPOLEN_CC)
Initial import of RFC 2385 (TCP-MD5) digest support. This is the first of two commits; bringing in the kernel support first. This can be enabled by compiling a kernel with options TCP_SIGNATURE and FAST_IPSEC. For the uninitiated, this is a TCP option which provides for a means of authenticating TCP sessions which came into being before IPSEC. It is still relevant today, however, as it is used by many commercial router vendors, particularly with BGP, and as such has become a requirement for interconnect at many major Internet points of presence. Several parts of the TCP and IP headers, including the segment payload, are digested with MD5, including a shared secret. The PF_KEY interface is used to manage the secrets using security associations in the SADB. There is a limitation here in that as there is no way to map a TCP flow per-port back to an SPI without polluting tcpcb or using the SPD; the code to do the latter is unstable at this time. Therefore this code only supports per-host keying granularity. Whilst FAST_IPSEC is mutually exclusive with KAME IPSEC (and thus IPv6), TCP_SIGNATURE applies only to IPv4. For the vast majority of prospective users of this feature, this will not pose any problem. This implementation is output-only; that is, the option is honoured when responding to a host initiating a TCP session, but no effort is made [yet] to authenticate inbound traffic. This is, however, sufficient to interwork with Cisco equipment. Tested with a Cisco 2501 running IOS 12.0(27), and Quagga 0.96.4 with local patches. Patches for tcpdump to validate TCP-MD5 sessions are also available from me upon request. Sponsored by: sentex.net
2004-02-11 04:26:04 +00:00
#define TCPOPT_SIGNATURE 19 /* Keyed MD5: RFC 2385 */
#define TCPOLEN_SIGNATURE 18
/* Option definitions */
#define TCPOPT_SACK_PERMIT_HDR \
(TCPOPT_NOP<<24|TCPOPT_NOP<<16|TCPOPT_SACK_PERMITTED<<8|TCPOLEN_SACK_PERMITTED)
#define TCPOPT_SACK_HDR (TCPOPT_NOP<<24|TCPOPT_NOP<<16|TCPOPT_SACK<<8)
/* Miscellaneous constants */
#define MAX_SACK_BLKS 6 /* Max # SACK blocks stored at sender side */
#define TCP_MAX_SACK 3 /* MAX # SACKs sent in any segment */
1994-05-24 10:09:53 +00:00
/*
* Default maximum segment size for TCP.
Limiters and sanity checks for TCP MSS (maximum segement size) resource exhaustion attacks. For network link optimization TCP can adjust its MSS and thus packet size according to the observed path MTU. This is done dynamically based on feedback from the remote host and network components along the packet path. This information can be abused to pretend an extremely low path MTU. The resource exhaustion works in two ways: o during tcp connection setup the advertized local MSS is exchanged between the endpoints. The remote endpoint can set this arbitrarily low (except for a minimum MTU of 64 octets enforced in the BSD code). When the local host is sending data it is forced to send many small IP packets instead of a large one. For example instead of the normal TCP payload size of 1448 it forces TCP payload size of 12 (MTU 64) and thus we have a 120 times increase in workload and packets. On fast links this quickly saturates the local CPU and may also hit pps processing limites of network components along the path. This type of attack is particularly effective for servers where the attacker can download large files (WWW and FTP). We mitigate it by enforcing a minimum MTU settable by sysctl net.inet.tcp.minmss defaulting to 256 octets. o the local host is reveiving data on a TCP connection from the remote host. The local host has no control over the packet size the remote host is sending. The remote host may chose to do what is described in the first attack and send the data in packets with an TCP payload of at least one byte. For each packet the tcp_input() function will be entered, the packet is processed and a sowakeup() is signalled to the connected process. For example an attack with 2 Mbit/s gives 4716 packets per second and the same amount of sowakeup()s to the process (and context switches). This type of attack is particularly effective for servers where the attacker can upload large amounts of data. Normally this is the case with WWW server where large POSTs can be made. We mitigate this by calculating the average MSS payload per second. If it goes below 'net.inet.tcp.minmss' and the pps rate is above 'net.inet.tcp.minmssoverload' defaulting to 1000 this particular TCP connection is resetted and dropped. MITRE CVE: CAN-2004-0002 Reviewed by: sam (mentor) MFC after: 1 day
2004-01-08 17:40:07 +00:00
* With an IP MTU of 576, this is 536,
1994-05-24 10:09:53 +00:00
* but 512 is probably more convenient.
* This should be defined as MIN(512, IP_MSS - sizeof (struct tcpiphdr)).
*/
#define TCP_MSS 512
Limiters and sanity checks for TCP MSS (maximum segement size) resource exhaustion attacks. For network link optimization TCP can adjust its MSS and thus packet size according to the observed path MTU. This is done dynamically based on feedback from the remote host and network components along the packet path. This information can be abused to pretend an extremely low path MTU. The resource exhaustion works in two ways: o during tcp connection setup the advertized local MSS is exchanged between the endpoints. The remote endpoint can set this arbitrarily low (except for a minimum MTU of 64 octets enforced in the BSD code). When the local host is sending data it is forced to send many small IP packets instead of a large one. For example instead of the normal TCP payload size of 1448 it forces TCP payload size of 12 (MTU 64) and thus we have a 120 times increase in workload and packets. On fast links this quickly saturates the local CPU and may also hit pps processing limites of network components along the path. This type of attack is particularly effective for servers where the attacker can download large files (WWW and FTP). We mitigate it by enforcing a minimum MTU settable by sysctl net.inet.tcp.minmss defaulting to 256 octets. o the local host is reveiving data on a TCP connection from the remote host. The local host has no control over the packet size the remote host is sending. The remote host may chose to do what is described in the first attack and send the data in packets with an TCP payload of at least one byte. For each packet the tcp_input() function will be entered, the packet is processed and a sowakeup() is signalled to the connected process. For example an attack with 2 Mbit/s gives 4716 packets per second and the same amount of sowakeup()s to the process (and context switches). This type of attack is particularly effective for servers where the attacker can upload large amounts of data. Normally this is the case with WWW server where large POSTs can be made. We mitigate this by calculating the average MSS payload per second. If it goes below 'net.inet.tcp.minmss' and the pps rate is above 'net.inet.tcp.minmssoverload' defaulting to 1000 this particular TCP connection is resetted and dropped. MITRE CVE: CAN-2004-0002 Reviewed by: sam (mentor) MFC after: 1 day
2004-01-08 17:40:07 +00:00
/*
* TCP_MINMSS is defined to be 216 which is fine for the smallest
* link MTU (256 bytes, AX.25 packet radio) in the Internet.
Limiters and sanity checks for TCP MSS (maximum segement size) resource exhaustion attacks. For network link optimization TCP can adjust its MSS and thus packet size according to the observed path MTU. This is done dynamically based on feedback from the remote host and network components along the packet path. This information can be abused to pretend an extremely low path MTU. The resource exhaustion works in two ways: o during tcp connection setup the advertized local MSS is exchanged between the endpoints. The remote endpoint can set this arbitrarily low (except for a minimum MTU of 64 octets enforced in the BSD code). When the local host is sending data it is forced to send many small IP packets instead of a large one. For example instead of the normal TCP payload size of 1448 it forces TCP payload size of 12 (MTU 64) and thus we have a 120 times increase in workload and packets. On fast links this quickly saturates the local CPU and may also hit pps processing limites of network components along the path. This type of attack is particularly effective for servers where the attacker can download large files (WWW and FTP). We mitigate it by enforcing a minimum MTU settable by sysctl net.inet.tcp.minmss defaulting to 256 octets. o the local host is reveiving data on a TCP connection from the remote host. The local host has no control over the packet size the remote host is sending. The remote host may chose to do what is described in the first attack and send the data in packets with an TCP payload of at least one byte. For each packet the tcp_input() function will be entered, the packet is processed and a sowakeup() is signalled to the connected process. For example an attack with 2 Mbit/s gives 4716 packets per second and the same amount of sowakeup()s to the process (and context switches). This type of attack is particularly effective for servers where the attacker can upload large amounts of data. Normally this is the case with WWW server where large POSTs can be made. We mitigate this by calculating the average MSS payload per second. If it goes below 'net.inet.tcp.minmss' and the pps rate is above 'net.inet.tcp.minmssoverload' defaulting to 1000 this particular TCP connection is resetted and dropped. MITRE CVE: CAN-2004-0002 Reviewed by: sam (mentor) MFC after: 1 day
2004-01-08 17:40:07 +00:00
* However it is very unlikely to come across such low MTU interfaces
* these days (anno dato 2003).
* See tcp_subr.c tcp_minmss SYSCTL declaration for more comments.
* Setting this to "0" disables the minmss check.
*/
#define TCP_MINMSS 216
Limiters and sanity checks for TCP MSS (maximum segement size) resource exhaustion attacks. For network link optimization TCP can adjust its MSS and thus packet size according to the observed path MTU. This is done dynamically based on feedback from the remote host and network components along the packet path. This information can be abused to pretend an extremely low path MTU. The resource exhaustion works in two ways: o during tcp connection setup the advertized local MSS is exchanged between the endpoints. The remote endpoint can set this arbitrarily low (except for a minimum MTU of 64 octets enforced in the BSD code). When the local host is sending data it is forced to send many small IP packets instead of a large one. For example instead of the normal TCP payload size of 1448 it forces TCP payload size of 12 (MTU 64) and thus we have a 120 times increase in workload and packets. On fast links this quickly saturates the local CPU and may also hit pps processing limites of network components along the path. This type of attack is particularly effective for servers where the attacker can download large files (WWW and FTP). We mitigate it by enforcing a minimum MTU settable by sysctl net.inet.tcp.minmss defaulting to 256 octets. o the local host is reveiving data on a TCP connection from the remote host. The local host has no control over the packet size the remote host is sending. The remote host may chose to do what is described in the first attack and send the data in packets with an TCP payload of at least one byte. For each packet the tcp_input() function will be entered, the packet is processed and a sowakeup() is signalled to the connected process. For example an attack with 2 Mbit/s gives 4716 packets per second and the same amount of sowakeup()s to the process (and context switches). This type of attack is particularly effective for servers where the attacker can upload large amounts of data. Normally this is the case with WWW server where large POSTs can be made. We mitigate this by calculating the average MSS payload per second. If it goes below 'net.inet.tcp.minmss' and the pps rate is above 'net.inet.tcp.minmssoverload' defaulting to 1000 this particular TCP connection is resetted and dropped. MITRE CVE: CAN-2004-0002 Reviewed by: sam (mentor) MFC after: 1 day
2004-01-08 17:40:07 +00:00
/*
* TCP_MINMSSOVERLOAD is defined to be 1000 which should cover any type
* of interactive TCP session.
* See tcp_subr.c tcp_minmssoverload SYSCTL declaration and tcp_input.c
* for more comments.
* Setting this to "0" disables the minmssoverload check.
*/
#define TCP_MINMSSOVERLOAD 0 /* XXX: Disabled until refined */
1994-05-24 10:09:53 +00:00
/*
* Default maximum segment size for TCP6.
* With an IP6 MSS of 1280, this is 1220,
* but 1024 is probably more convenient. (xxx kazu in doubt)
* This should be defined as MIN(1024, IP6_MSS - sizeof (struct tcpip6hdr))
*/
#define TCP6_MSS 1024
1994-05-24 10:09:53 +00:00
#define TCP_MAXWIN 65535 /* largest value for (unscaled) window */
#define TTCP_CLIENT_SND_WND 4096 /* dflt send window for T/TCP client */
1994-05-24 10:09:53 +00:00
#define TCP_MAX_WINSHIFT 14 /* maximum window shift */
#define TCP_MAXBURST 4 /* maximum segments in a burst */
#define TCP_MAXHLEN (0xf<<2) /* max length of header in bytes */
#define TCP_MAXOLEN (TCP_MAXHLEN - sizeof(struct tcphdr))
/* max space left for options */
#endif /* __BSD_VISIBLE */
1994-05-24 10:09:53 +00:00
/*
* User-settable options (used with setsockopt).
*/
#define TCP_NODELAY 0x01 /* don't delay send to coalesce packets */
#if __BSD_VISIBLE
1994-05-24 10:09:53 +00:00
#define TCP_MAXSEG 0x02 /* set maximum segment size */
#define TCP_NOPUSH 0x04 /* don't push last block of write */
#define TCP_NOOPT 0x08 /* don't use TCP options */
#define TCP_MD5SIG 0x10 /* use MD5 digests (RFC2385) */
1994-08-21 05:27:42 +00:00
#endif
#endif /* !_NETINET_TCP_H_ */