Miscellaneous files to support UDP-Lite, including basic xfrm and netfilter support.
Signed-off-by: Gerrit Renker <[EMAIL PROTECTED]> --- Documentation/networking/udplite.txt | 291 +++++++++++++++++++++++++++++++++++ include/net/xfrm.h | 2 net/ipv4/netfilter/ipt_LOG.c | 11 - net/ipv4/xfrm4_policy.c | 1 net/ipv6/netfilter/ip6t_LOG.c | 10 - net/ipv6/xfrm6_policy.c | 1 net/netfilter/xt_multiport.c | 5 net/netfilter/xt_tcpudp.c | 20 ++ 8 files changed, 332 insertions(+), 9 deletions(-) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 737fdb2..70a8d2d 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -468,6 +468,7 @@ __be16 xfrm_flowi_sport(struct flowi *fl switch(fl->proto) { case IPPROTO_TCP: case IPPROTO_UDP: + case IPPROTO_UDPLITE: case IPPROTO_SCTP: port = fl->fl_ip_sport; break; @@ -493,6 +494,7 @@ __be16 xfrm_flowi_dport(struct flowi *fl switch(fl->proto) { case IPPROTO_TCP: case IPPROTO_UDP: + case IPPROTO_UDPLITE: case IPPROTO_SCTP: port = fl->fl_ip_dport; break; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 1bed0cd..af6867f 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -199,6 +199,7 @@ _decode_session4(struct sk_buff *skb, st if (!(iph->frag_off & htons(IP_MF | IP_OFFSET))) { switch (iph->protocol) { case IPPROTO_UDP: + case IPPROTO_UDPLITE: case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 73cee2e..8a25db1 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -272,6 +272,7 @@ _decode_session6(struct sk_buff *skb, st break; case IPPROTO_UDP: + case IPPROTO_UDPLITE: case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: diff --git a/net/netfilter/xt_multiport.c b/net/netfilter/xt_multiport.c index d3aefd3..c3b4bc0 100644 --- a/net/netfilter/xt_multiport.c +++ b/net/netfilter/xt_multiport.c @@ -1,5 +1,5 @@ -/* Kernel module to match one of a list of TCP/UDP/SCTP/DCCP ports: ports are in - the same place so we can treat them as equal. */ +/* Kernel module to match one of a list of TCP/UDP(-Lite)/SCTP/DCCP ports: + ports are in the same place so we can treat them as equal. */ /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <[EMAIL PROTECTED]> @@ -162,6 +162,7 @@ check(u_int16_t proto, { /* Must specify supported protocol, no unknown flags or bad count */ return (proto == IPPROTO_TCP || proto == IPPROTO_UDP + || proto == IPPROTO_UDPLITE || proto == IPPROTO_SCTP || proto == IPPROTO_DCCP) && !(ip_invflags & XT_INV_PROTO) && (match_flags == XT_MULTIPORT_SOURCE diff --git a/net/netfilter/xt_tcpudp.c b/net/netfilter/xt_tcpudp.c index e76a68e..46414b5 100644 --- a/net/netfilter/xt_tcpudp.c +++ b/net/netfilter/xt_tcpudp.c @@ -10,7 +10,7 @@ #include <linux/netfilter/xt_tcpudp.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> -MODULE_DESCRIPTION("x_tables match for TCP and UDP, supports IPv4 and IPv6"); +MODULE_DESCRIPTION("x_tables match for TCP and UDP(-Lite), supports IPv4 and IPv6"); MODULE_LICENSE("GPL"); MODULE_ALIAS("xt_tcp"); MODULE_ALIAS("xt_udp"); @@ -234,6 +234,24 @@ static struct xt_match xt_tcpudp_match[] .proto = IPPROTO_UDP, .me = THIS_MODULE, }, + { + .name = "udplite", + .family = AF_INET, + .checkentry = udp_checkentry, + .match = udp_match, + .matchsize = sizeof(struct xt_udp), + .proto = IPPROTO_UDPLITE, + .me = THIS_MODULE, + }, + { + .name = "udplite", + .family = AF_INET6, + .checkentry = udp_checkentry, + .match = udp_match, + .matchsize = sizeof(struct xt_udp), + .proto = IPPROTO_UDPLITE, + .me = THIS_MODULE, + }, }; static int __init xt_tcpudp_init(void) diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index 7dc820d..46eee64 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -171,11 +171,15 @@ static void dump_packet(const struct nf_ } break; } - case IPPROTO_UDP: { + case IPPROTO_UDP: + case IPPROTO_UDPLITE: { struct udphdr _udph, *uh; - /* Max length: 10 "PROTO=UDP " */ - printk("PROTO=UDP "); + if (ih->protocol == IPPROTO_UDP) + /* Max length: 10 "PROTO=UDP " */ + printk("PROTO=UDP " ); + else /* Max length: 14 "PROTO=UDPLITE " */ + printk("PROTO=UDPLITE "); if (ntohs(ih->frag_off) & IP_OFFSET) break; @@ -341,6 +345,7 @@ static void dump_packet(const struct nf_ /* IP: 40+46+6+11+127 = 230 */ /* TCP: 10+max(25,20+30+13+9+32+11+127) = 252 */ /* UDP: 10+max(25,20) = 35 */ + /* UDPLITE: 14+max(25,20) = 39 */ /* ICMP: 11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */ /* ESP: 10+max(25)+15 = 50 */ /* AH: 9+max(25)+15 = 49 */ diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 0cf537d..3cb6bb7 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -270,11 +270,15 @@ static void dump_packet(const struct nf_ } break; } - case IPPROTO_UDP: { + case IPPROTO_UDP: + case IPPROTO_UDPLITE: { struct udphdr _udph, *uh; - /* Max length: 10 "PROTO=UDP " */ - printk("PROTO=UDP "); + if (currenthdr == IPPROTO_UDP) + /* Max length: 10 "PROTO=UDP " */ + printk("PROTO=UDP " ); + else /* Max length: 14 "PROTO=UDPLITE " */ + printk("PROTO=UDPLITE "); if (fragment) break; diff --git a/Documentation/networking/udplite.txt b/Documentation/networking/udplite.txt new file mode 100644 index 0000000..a899fa1 --- /dev/null +++ b/Documentation/networking/udplite.txt @@ -0,0 +1,291 @@ + =========================================================================== + The UDP-Lite protocol (RFC 3828) + =========================================================================== + last modified: Mon 18th September 2006 + + + UDP-Lite is a Standards-Track IETF transport protocol whose characteristic + is a variable-length checksum. This has advantages for transport of multimedia + (video, VoIP) over wireless networks, as partly damaged packets can still be + fed into the codec instead of being discarded due to a failed checksum test. + + This file briefly describes the existing kernel support and the socket API. + For in-depth information, you can consult: + + o The UDP-Lite Homepage: http://www.erg.abdn.ac.uk/users/gerrit/udp-lite/ + Fom here you can always also download the latest patch for the stable + kernel tree and some example application source code. + + o The UDP-Lite HOWTO on + http://www.erg.abdn.ac.uk/users/gerrit/udp-lite/files/UDP-Lite-HOWTO.txt + + o The Wireshark UDP-Lite WiKi (with capture files): + http://wiki.wireshark.org/Lightweight_User_Datagram_Protocol + + o The Protocol Spec, RFC 3828, on http://www.ietf.org/rfc/rfc3828.txt + + + I) APPLICATIONS + + Several applications have been ported successfully to UDP-Lite. Ethereal + (now called wireshark) has UDP-Litev4/v6 support by default. The tarball on + + http://www.erg.abdn.ac.uk/users/gerrit/udp-lite/files/udplite_linux.tar.gz + + has source code for several v4/v6 client-server and network testing examples. + + Porting applications to UDP-Lite is straightforward: only socket level and + IPPROTO need to be changed; senders additionally set the checksum coverage + length (default = header length = 8). Details are in the next section. + UDP-Lite is not enabled per default: set CONFIG_IP_UDPLITE=y to support it. + + + II) PROGRAMMING API + + UDP-Lite provides a connectionless, unreliable datagram service and hence + uses the same socket type as UDP. In fact, porting from UDP to UDP-Lite is + dead easy: simply add `IPPROTO_UDPLITE' as the last argument of the socket(2) + call so that the statement looks like: + + s = socket(PF_INET, SOCK_DGRAM, IPPROTO_UDPLITE); + + or, respectively, + + s = socket(PF_INET6, SOCK_DGRAM, IPPROTO_UDPLITE); + + Since both UDP-Litev4 and UDP-Litev6 are supported, the porting process is the + same in both occasions. With just this change you are able to run UDP-Lite + services or connect to UDP-Lite servers. The kernel will assume that you are + not interested in using partial checksum coverage and so emulate UDP mode. + + To make use of the partial checksum coverage facilities requires setting just + one socket option which takes an integer specifying the coverage length: + + * Sender checksum coverage: UDPLITE_SEND_CSCOV + + For example, + + int val = 20; + setsockopt(s, SOL_UDPLITE, UDPLITE_SEND_CSCOV, &val, sizeof(int)); + + sets the checksum coverage length to 20 bytes (12b data + 8b header). + Of each packet only the first 20 bytes (plus the pseudo-header) will be + checksummed. This is useful for RTP applications which have a 12-byte + base header. + + + * Receiver checksum coverage: UDPLITE_RECV_CSCOV + + This option is the receiver-side analogue. It is truly optional, i.e. not + required to enable traffic with partial checksum coverage. Its function is + that of a traffic filter: when enabled, it instructs the kernel to drop + all packets which have a coverage _less_ than this value. For example, if + RTP and UDP headers are to be protected, a receiver can enforce that only + packets with a minimum coverage of 20 are admitted: + + int min = 20; + setsockopt(s, SOL_UDPLITE, UDPLITE_RECV_CSCOV, &min, sizeof(int)); + + The calls to getsockopt(2) are analogous. Being an extension and not a stand- + alone protocol, all socket options known from UDP can be used in exactly the + same manner as before, e.g. UDP_CORK or UDP_ENCAP. + + A detailed discussion of UDP-Lite checksum coverage options is in section IV. + + + + III) HEADER FILES + + The socket API requires support through header files in /usr/include: + + * /usr/include/netinet/in.h + to define IPPROTO_UDPLITE + + * /usr/include/netinet/udplite.h + for UDP-Lite header fields and protocol constants + + For testing purposes, the following can serve as a `mini' header file: + + #define IPPROTO_UDPLITE 136 + #define SOL_UDPLITE 136 + #define UDPLITE_SEND_CSCOV 10 + #define UDPLITE_RECV_CSCOV 11 + + Ready-made header files for various distros are in the UDP-Lite tarball. + + + + IV) KERNEL BEHAVIOUR WITH REGARD TO THE VARIOUS SOCKET OPTIONS + + To enable debugging messages, the log level must be set to 8, as most + messages use the KERN_DEBUG level (7). + + + 1) Sender Socket Options + + If the sender specifies a value of 0 as coverage length, the module + assumes full coverage, transmits a packet with coverage length of 0 + and according checksum. If the sender specifies a coverage < 8 and + different from 0, the kernel assumes 8 as default value. Finally, + if the specified coverage length exceeds the packet length, the packet + length is used instead as coverage length. + + + 2) Receiver Socket Options + + The receiver specifies the minimum value of the coverage length it + is willing to accept. A value of 0 here indicates that the receiver + always wants the whole of the packet covered. In this case, all + partially covered packets are dropped and an error is logged. + + It is not possible to specify illegal values (<0 and <8); in these + cases the default of 8 is assumed. + + All packets arriving with a coverage value less than the specified + threshold are discarded, these events are also logged. + + + 3) Disabling the Checksum Computation + + On both sender and receiver, checksumming will always be performed + and can not be disabled using SO_NO_CHECK. Thus + + setsockopt(sockfd, SOL_SOCKET, SO_NO_CHECK, ... ); + + will always will be ignored, while the value of + + getsockopt(sockfd, SOL_SOCKET, SO_NO_CHECK, &value, ...); + + is meaningless (as in TCP). Packets with a zero checksum field are + illegal (cf. RFC 3828, sec. 3.1) will be silently discarded. + + + 4) Fragmentation + + The checksum computation respects both buffersize and MTU. The size + of UDP-Lite packets is determined by the size of the send buffer. The + minimum size of the send buffer is 2048 (defined as SOCK_MIN_SNDBUF + in include/net/sock.h), the default value is configurable as + net.core.wmem_default or via setting the SO_SNDBUF socket(7) + option. The maximum upper bound for the send buffer is determined + by net.core.wmem_max. + + Given a payload size larger than the send buffer size, UDP-Lite will + split the payload into several individual packets, filling up the + send buffer size in each case. + + The precise value also depends on the interface MTU. The interface MTU, + in turn, may trigger IP fragmentation. In this case, the generated + UDP-Lite packet is split into several IP packets, of which only the + first one contains the L4 header. + + The send buffer size has implications on the checksum coverage length. + Consider the following example: + + Payload: 1536 bytes Send Buffer: 1024 bytes + MTU: 1500 bytes Coverage Length: 856 bytes + + UDP-Lite will ship the 1536 bytes in two separate packets: + + Packet 1: 1024 payload + 8 byte header + 20 byte IP header = 1052 bytes + Packet 2: 512 payload + 8 byte header + 20 byte IP header = 540 bytes + + The coverage packet covers the UDP-Lite header and 848 bytes of the + payload in the first packet, the second packet is fully covered. Note + that for the second packet, the coverage length exceeds the packet + length. The kernel always re-adjusts the coverage length to the packet + length in such cases. + + As an example of what happens when one UDP-Lite packet is split into + several tiny fragments, consider the following example. + + Payload: 1024 bytes Send buffer size: 1024 bytes + MTU: 300 bytes Coverage length: 575 bytes + + +-+-----------+--------------+--------------+--------------+ + |8| 272 | 280 | 280 | 280 | + +-+-----------+--------------+--------------+--------------+ + 280 560 840 1032 + ^ + *****checksum coverage************* + + The UDP-Lite module generates one 1032 byte packet (1024 + 8 byte + header). According to the interface MTU, these are split into 4 IP + packets (280 byte IP payload + 20 byte IP header). The kernel module + sums the contents of the entire first two packets, plus 15 bytes of + the last packet before releasing the fragments to the IP module. + + To see the analogous case for IPv6 fragmentation, consider a link + MTU of 1280 bytes and a write buffer of 3356 bytes. If the checksum + coverage is less than 1232 bytes (MTU minus IPv6/fragment header + lengths), only the first fragment needs to be considered. When using + larger checksum coverage lengths, each eligible fragment needs to be + checksummed. Suppose we have a checksum coverage of 3062. The buffer + of 3356 bytes will be split into the following fragments: + + Fragment 1: 1280 bytes carrying 1232 bytes of UDP-Lite data + Fragment 2: 1280 bytes carrying 1232 bytes of UDP-Lite data + Fragment 3: 948 bytes carrying 900 bytes of UDP-Lite data + + The first two fragments have to be checksummed in full, of the last + fragment only 598 (= 3062 - 2*1232) bytes are checksummed. + + While it is important that such cases are dealt with correctly, they + are (annoyingly) rare: UDP-Lite is designed for optimising multimedia + performance over wireless (or generally noisy) links and thus smaller + coverage lenghts are likely to be expected. + + + V) UDP-LITE RUNTIME STATISTICS AND THEIR MEANING + + Exceptional and error conditions are logged to syslog at the KERN_DEBUG + level. Live statistics about UDP-Lite are available in /proc/net/snmp + and can (with newer versions of netstat) be viewed using + + netstat -svu + + This displays UDP-Lite statistics variables, whose meaning is as follows. + + InDatagrams: Total number of received datagrams. + + NoPorts: Number of packets received to an unknown port. + These cases are counted separately (not as InErrors). + + InErrors: Number of erroneous UDP-Lite packets. Errors include: + * internal socket queue receive errors + * packet too short (less than 8 bytes or stated + coverage length exceeds received length) + * xfrm4_policy_check() returned with error + * application has specified larger min. coverage + length than that of incoming packet + * checksum coverage violated + * bad checksum + + OutDatagrams: Total number of sent datagrams. + + These statistics derive from the UDP MIB (RFC 2013). + + + VI) IPTABLES + + There is packet match support for UDP-Lite as well as support for the LOG target. + If you copy and paste the following line into /etc/protcols, + + udplite 136 UDP-Lite # UDP-Lite [RFC 3828] + + then + iptables -A INPUT -p udplite -j LOG + + will produce logging output to syslog. Dropping and rejecting packets also works. + + + VII) MAINTAINER ADDRESS + + The UDP-Lite patch was developed at + University of Aberdeen + Electronics Research Group + Department of Engineering + Fraser Noble Building + Aberdeen AB24 3UE; UK + The current maintainer is Gerrit Renker, <[EMAIL PROTECTED]>. Initial + code had been developed by William Stanislaus, <[EMAIL PROTECTED]>. - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html