diff options
-rw-r--r-- | Documentation/networking/udplite.txt | 281 | ||||
-rw-r--r-- | include/linux/in.h | 1 | ||||
-rw-r--r-- | include/linux/socket.h | 1 | ||||
-rw-r--r-- | include/linux/udp.h | 12 | ||||
-rw-r--r-- | include/net/ipv6.h | 12 | ||||
-rw-r--r-- | include/net/transp_v6.h | 2 | ||||
-rw-r--r-- | include/net/udp.h | 91 | ||||
-rw-r--r-- | include/net/udplite.h | 149 | ||||
-rw-r--r-- | include/net/xfrm.h | 2 | ||||
-rw-r--r-- | net/ipv4/Makefile | 3 | ||||
-rw-r--r-- | net/ipv4/af_inet.c | 8 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_LOG.c | 11 | ||||
-rw-r--r-- | net/ipv4/proc.c | 13 | ||||
-rw-r--r-- | net/ipv4/udp.c | 518 | ||||
-rw-r--r-- | net/ipv4/udp_impl.h | 38 | ||||
-rw-r--r-- | net/ipv4/udplite.c | 119 | ||||
-rw-r--r-- | net/ipv4/xfrm4_policy.c | 1 | ||||
-rw-r--r-- | net/ipv6/Makefile | 4 | ||||
-rw-r--r-- | net/ipv6/af_inet6.c | 21 | ||||
-rw-r--r-- | net/ipv6/ipv6_sockglue.c | 11 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6t_LOG.c | 10 | ||||
-rw-r--r-- | net/ipv6/proc.c | 11 | ||||
-rw-r--r-- | net/ipv6/udp.c | 361 | ||||
-rw-r--r-- | net/ipv6/udp_impl.h | 34 | ||||
-rw-r--r-- | net/ipv6/udplite.c | 105 | ||||
-rw-r--r-- | net/ipv6/xfrm6_policy.c | 1 | ||||
-rw-r--r-- | net/netfilter/xt_multiport.c | 5 | ||||
-rw-r--r-- | net/netfilter/xt_tcpudp.c | 20 |
28 files changed, 1442 insertions, 403 deletions
diff --git a/Documentation/networking/udplite.txt b/Documentation/networking/udplite.txt new file mode 100644 index 000000000000..dd6f46b83dab --- /dev/null +++ b/Documentation/networking/udplite.txt @@ -0,0 +1,281 @@ + =========================================================================== + The UDP-Lite protocol (RFC 3828) + =========================================================================== + + + 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 also download 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, 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. + + + 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 + very 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); + + With just the above 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 (full coverage). + + To make use of the partial checksum coverage facilities requires setting a + single 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 need to 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, <gerrit@erg.abdn.ac.uk>. Initial + code was developed by William Stanislaus, <william@erg.abdn.ac.uk>. diff --git a/include/linux/in.h b/include/linux/in.h index 2619859f6e1b..1912e7c0bc26 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -45,6 +45,7 @@ enum { IPPROTO_COMP = 108, /* Compression Header protocol */ IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */ + IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */ IPPROTO_RAW = 255, /* Raw IP packets */ IPPROTO_MAX diff --git a/include/linux/socket.h b/include/linux/socket.h index 361409094649..592b66679823 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -264,6 +264,7 @@ struct ucred { #define SOL_IPV6 41 #define SOL_ICMPV6 58 #define SOL_SCTP 132 +#define SOL_UDPLITE 136 /* UDP-Lite (RFC 3828) */ #define SOL_RAW 255 #define SOL_IPX 256 #define SOL_AX25 257 diff --git a/include/linux/udp.h b/include/linux/udp.h index 014b41d1e308..564f3b050105 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -38,6 +38,7 @@ struct udphdr { #include <linux/types.h> #include <net/inet_sock.h> +#define UDP_HTABLE_SIZE 128 struct udp_sock { /* inet_sock has to be the first member */ @@ -50,12 +51,23 @@ struct udp_sock { * when the socket is uncorked. */ __u16 len; /* total length of pending frames */ + /* + * Fields specific to UDP-Lite. + */ + __u16 pcslen; + __u16 pcrlen; +/* indicator bits used by pcflag: */ +#define UDPLITE_BIT 0x1 /* set by udplite proto init function */ +#define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ +#define UDPLITE_RECV_CC 0x4 /* set via udplite setsocktopt */ + __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ }; static inline struct udp_sock *udp_sk(const struct sock *sk) { return (struct udp_sock *)sk; } +#define IS_UDPLITE(__sk) (udp_sk(__sk)->pcflag) #endif diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 3c266ad99a02..9390649bbfec 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -158,9 +158,13 @@ DECLARE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics); SNMP_INC_STATS_OFFSET_BH(icmpv6_statistics, field, _offset); \ }) DECLARE_SNMP_STAT(struct udp_mib, udp_stats_in6); -#define UDP6_INC_STATS(field) SNMP_INC_STATS(udp_stats_in6, field) -#define UDP6_INC_STATS_BH(field) SNMP_INC_STATS_BH(udp_stats_in6, field) -#define UDP6_INC_STATS_USER(field) SNMP_INC_STATS_USER(udp_stats_in6, field) +DECLARE_SNMP_STAT(struct udp_mib, udplite_stats_in6); +#define UDP6_INC_STATS_BH(field, is_udplite) do { \ + if (is_udplite) SNMP_INC_STATS_BH(udplite_stats_in6, field); \ + else SNMP_INC_STATS_BH(udp_stats_in6, field); } while(0) +#define UDP6_INC_STATS_USER(field, is_udplite) do { \ + if (is_udplite) SNMP_INC_STATS_USER(udplite_stats_in6, field); \ + else SNMP_INC_STATS_USER(udp_stats_in6, field); } while(0) int snmp6_register_dev(struct inet6_dev *idev); int snmp6_unregister_dev(struct inet6_dev *idev); @@ -604,6 +608,8 @@ extern int tcp6_proc_init(void); extern void tcp6_proc_exit(void); extern int udp6_proc_init(void); extern void udp6_proc_exit(void); +extern int udplite6_proc_init(void); +extern void udplite6_proc_exit(void); extern int ipv6_misc_proc_init(void); extern void ipv6_misc_proc_exit(void); diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index 61f724c1036f..409da3a9a455 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -11,6 +11,7 @@ extern struct proto rawv6_prot; extern struct proto udpv6_prot; +extern struct proto udplitev6_prot; extern struct proto tcpv6_prot; struct flowi; @@ -24,6 +25,7 @@ extern void ipv6_destopt_init(void); /* transport protocols */ extern void rawv6_init(void); extern void udpv6_init(void); +extern void udplitev6_init(void); extern void tcpv6_init(void); extern int udpv6_connect(struct sock *sk, diff --git a/include/net/udp.h b/include/net/udp.h index db0c05f67546..4f0626735ed3 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -26,9 +26,28 @@ #include <net/inet_sock.h> #include <net/sock.h> #include <net/snmp.h> +#include <net/ip.h> +#include <linux/ipv6.h> #include <linux/seq_file.h> -#define UDP_HTABLE_SIZE 128 +/** + * struct udp_skb_cb - UDP(-Lite) private variables + * + * @header: private variables used by IPv4/IPv6 + * @cscov: checksum coverage length (UDP-Lite only) + * @partial_cov: if set indicates partial csum coverage + */ +struct udp_skb_cb { + union { + struct inet_skb_parm h4; +#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) + struct inet6_skb_parm h6; +#endif + } header; + __u16 cscov; + __u8 partial_cov; +}; +#define UDP_SKB_CB(__skb) ((struct udp_skb_cb *)((__skb)->cb)) extern struct hlist_head udp_hash[UDP_HTABLE_SIZE]; extern rwlock_t udp_hash_lock; @@ -47,6 +66,62 @@ extern struct proto udp_prot; struct sk_buff; +/* + * Generic checksumming routines for UDP(-Lite) v4 and v6 + */ +static inline u16 __udp_lib_checksum_complete(struct sk_buff *skb) +{ + if (! UDP_SKB_CB(skb)->partial_cov) + return __skb_checksum_complete(skb); + return csum_fold(skb_checksum(skb, 0, UDP_SKB_CB(skb)->cscov, + skb->csum)); +} + +static __inline__ int udp_lib_checksum_complete(struct sk_buff *skb) +{ + return skb->ip_summed != CHECKSUM_UNNECESSARY && + __udp_lib_checksum_complete(skb); +} + +/** + * udp_csum_outgoing - compute UDPv4/v6 checksum over fragments + * @sk: socket we are writing to + * @skb: sk_buff containing the filled-in UDP header + * (checksum field must be zeroed out) + */ +static inline u32 udp_csum_outgoing(struct sock *sk, struct sk_buff *skb) +{ + u32 csum = csum_partial(skb->h.raw, sizeof(struct udphdr), 0); + + skb_queue_walk(&sk->sk_write_queue, skb) { + csum = csum_add(csum, skb->csum); + } + return csum; +} + +/* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ +static inline void udp_lib_hash(struct sock *sk) +{ + BUG(); +} + +static inline void udp_lib_unhash(struct sock *sk) +{ + write_lock_bh(&udp_hash_lock); + if (sk_del_node_init(sk)) { + inet_sk(sk)->num = 0; + sock_prot_dec_use(sk->sk_prot); + } + write_unlock_bh(&udp_hash_lock); +} + +static inline void udp_lib_close(struct sock *sk, long timeout) +{ + sk_common_release(sk); +} + + +/* net/ipv4/udp.c */ extern int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, const struct sock *)); extern void udp_err(struct sk_buff *, u32); @@ -61,21 +136,29 @@ extern unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait); DECLARE_SNMP_STAT(struct udp_mib, udp_statistics); -#define UDP_INC_STATS(field) SNMP_INC_STATS(udp_statistics, field) -#define UDP_INC_STATS_BH(field) SNMP_INC_STATS_BH(udp_statistics, field) -#define UDP_INC_STATS_USER(field) SNMP_INC_STATS_USER(udp_statistics, field) +/* + * SNMP statistics for UDP and UDP-Lite + */ +#define UDP_INC_STATS_USER(field, is_udplite) do { \ + if (is_udplite) SNMP_INC_STATS_USER(udplite_statistics, field); \ + else SNMP_INC_STATS_USER(udp_statistics, field); } while(0) +#define UDP_INC_STATS_BH(field, is_udplite) do { \ + if (is_udplite) SNMP_INC_STATS_BH(udplite_statistics, field); \ + else SNMP_INC_STATS_BH(udp_statistics, field); } while(0) /* /proc */ struct udp_seq_afinfo { struct module *owner; char *name; sa_family_t family; + struct hlist_head *hashtable; int (*seq_show) (struct seq_file *m, void *v); struct file_operations *seq_fops; }; struct udp_iter_state { sa_family_t family; + struct hlist_head *hashtable; int bucket; struct seq_operations seq_ops; }; diff --git a/include/net/udplite.h b/include/net/udplite.h new file mode 100644 index 000000000000..1473b3e49044 --- /dev/null +++ b/include/net/udplite.h @@ -0,0 +1,149 @@ +/* + * Definitions for the UDP-Lite (RFC 3828) code. + */ +#ifndef _UDPLITE_H +#define _UDPLITE_H + +/* UDP-Lite socket options */ +#define UDPLITE_SEND_CSCOV 10 /* sender partial coverage (as sent) */ +#define UDPLITE_RECV_CSCOV 11 /* receiver partial coverage (threshold ) */ + +extern struct proto udplite_prot; +extern struct hlist_head udplite_hash[UDP_HTABLE_SIZE]; + +/* UDP-Lite does not have a standardized MIB yet, so we inherit from UDP */ +DECLARE_SNMP_STAT(struct udp_mib, udplite_statistics); + +/* + * Checksum computation is all in software, hence simpler getfrag. + */ +static __inline__ int udplite_getfrag(void *from, char *to, int offset, + int len, int odd, struct sk_buff *skb) +{ + return memcpy_fromiovecend(to, (struct iovec *) from, offset, len); +} + +/* Designate sk as UDP-Lite socket */ +static inline int udplite_sk_init(struct sock *sk) +{ + udp_sk(sk)->pcflag = UDPLITE_BIT; + return 0; +} + +/* + * Checksumming routines + */ +static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) +{ + u16 cscov; + + /* In UDPv4 a zero checksum means that the transmitter generated no + * checksum. UDP-Lite (like IPv6) mandates checksums, hence packets + * with a zero checksum field are illegal. */ + if (uh->check == 0) { + LIMIT_NETDEBUG(KERN_DEBUG "UDPLITE: zeroed checksum field\n"); + return 1; + } + + UDP_SKB_CB(skb)->partial_cov = 0; + cscov = ntohs(uh->len); + + if (cscov == 0) /* Indicates that full coverage is required. */ + cscov = skb->len; + else if (cscov < 8 || cscov > skb->len) { + /* + * Coverage length violates RFC 3828: log and discard silently. + */ + LIMIT_NETDEBUG(KERN_DEBUG "UDPLITE: bad csum coverage %d/%d\n", + cscov, skb->len); + return 1; + + } else if (cscov < skb->len) + UDP_SKB_CB(skb)->partial_cov = 1; + + UDP_SKB_CB(skb)->cscov = cscov; + + /* + * There is no known NIC manufacturer supporting UDP-Lite yet, + * hence ip_summed is always (re-)set to CHECKSUM_NONE. + */ + skb->ip_summed = CHECKSUM_NONE; + + return 0; +} + +static __inline__ int udplite4_csum_init(struct sk_buff *skb, struct udphdr *uh) +{ + int rc = udplite_checksum_init(skb, uh); + + if (!rc) + skb->csum = csum_tcpudp_nofold(skb->nh.iph->saddr, + skb->nh.iph->daddr, + skb->len, IPPROTO_UDPLITE, 0); + return rc; +} + +static __inline__ int udplite6_csum_init(struct sk_buff *skb, struct udphdr *uh) +{ + int rc = udplite_checksum_init(skb, uh); + + if (!rc) + skb->csum = ~csum_ipv6_magic(&skb->nh.ipv6h->saddr, + &skb->nh.ipv6h->daddr, + skb->len, IPPROTO_UDPLITE, 0); + return rc; +} + +static inline int udplite_sender_cscov(struct udp_sock *up, struct udphdr *uh) +{ + int cscov = up->len; + + /* + * Sender has set `partial coverage' option on UDP-Lite socket + */ + if (up->pcflag & UDPLITE_SEND_CC) { + if (up->pcslen < up->len) { + /* up->pcslen == 0 means that full coverage is required, + * partial coverage only if 0 < up->pcslen < up->len */ + if (0 < up->pcslen) { + cscov = up->pcslen; + } + uh->len = htons(up->pcslen); + } + /* + * NOTE: Causes for the error case `up->pcslen > up->len': + * (i) Application error (will not be penalized). + * (ii) Payload too big for send buffer: data is split + * into several packets, each with its own header. + * In this case (e.g. last segment), coverage may + * exceed packet length. + * Since packets with coverage length > packet length are + * illegal, we fall back to the defaults here. + */ + } + return cscov; +} + +static inline u32 udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) +{ + u32 csum = 0; + int off, len, cscov = udplite_sender_cscov(udp_sk(sk), skb->h.uh); + + skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ + + skb_queue_walk(&sk->sk_write_queue, skb) { + off = skb->h.raw - skb->data; + len = skb->len - off; + + csum = skb_checksum(skb, off, (cscov > len)? len : cscov, csum); + + if ((cscov -= len) <= 0) + break; + } + return csum; +} + +extern void udplite4_register(void); +extern int udplite_get_port(struct sock *sk, unsigned short snum, + int (*scmp)(const struct sock *, const struct sock *)); +#endif /* _UDPLITE_H */ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 81c91e8a328f..3878a88ff618 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/Makefile b/net/ipv4/Makefile index 15645c51520c..7a068626feea 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -8,7 +8,8 @@ obj-y := route.o inetpeer.o protocol.o \ inet_timewait_sock.o inet_connection_sock.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ tcp_minisocks.o tcp_cong.o \ - datagram.o raw.o udp.o arp.o icmp.o devinet.o af_inet.o igmp.o \ + datagram.o raw.o udp.o udplite.o \ + arp.o icmp.o devinet.o af_inet.o igmp.o \ sysctl_net_ipv4.o fib_frontend.o fib_semantics.o obj-$(CONFIG_IP_FIB_HASH) += fib_hash.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 4a81d54a7569..8db39f7e3bf0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -104,6 +104,7 @@ #include <net/inet_connection_sock.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/udplite.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/raw.h> @@ -1223,10 +1224,13 @@ static int __init init_ipv4_mibs(void) tcp_statistics[1] = alloc_percpu(struct tcp_mib); udp_statistics[0] = alloc_percpu(struct udp_mib); udp_statistics[1] = alloc_percpu(struct udp_mib); + udplite_statistics[0] = alloc_percpu(struct udp_mib); + udplite_statistics[1] = alloc_percpu(struct udp_mib); if (! (net_statistics[0] && net_statistics[1] && ip_statistics[0] && ip_statistics[1] && tcp_statistics[0] && tcp_statistics[1] - && udp_statistics[0] && udp_statistics[1])) + && udp_statistics[0] && udp_statistics[1] + && udplite_statistics[0] && udplite_statistics[1] ) ) return -ENOMEM; (void) tcp_mib_init(); @@ -1313,6 +1317,8 @@ static int __init inet_init(void) /* Setup TCP slab cache for open requests. */ tcp_init(); + /* Add UDP-Lite (RFC 3828) */ + udplite4_register(); /* * Set the ICMP layer up diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index 7dc820df8bc5..46eee64a11f6 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_loginfo *info, } 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_loginfo *info, /* 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/ipv4/proc.c b/net/ipv4/proc.c index 9c6cbe3d9fb8..cd873da54cbe 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -38,6 +38,7 @@ #include <net/protocol.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/udplite.h> #include <linux/inetdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -66,6 +67,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) tcp_death_row.tw_count, atomic_read(&tcp_sockets_allocated), atomic_read(&tcp_memory_allocated)); seq_printf(seq, "UDP: inuse %d\n", fold_prot_inuse(&udp_prot)); + seq_printf(seq, "UDPLITE: inuse %d\n", fold_prot_inuse(&udplite_prot)); seq_printf(seq, "RAW: inuse %d\n", fold_prot_inuse(&raw_prot)); seq_printf(seq, "FRAG: inuse %d memory %d\n", ip_frag_nqueues, atomic_read(&ip_frag_mem)); @@ -304,6 +306,17 @@ static int snmp_seq_show(struct seq_file *seq, void *v) fold_field((void **) udp_statistics, snmp4_udp_list[i].entry)); + /* the UDP and UDP-Lite MIBs are the same */ + seq_puts(seq, "\nUdpLite:"); + for (i = 0; snmp4_udp_list[i].name != NULL; i++) + seq_printf(seq, " %s", snmp4_udp_list[i].name); + + seq_puts(seq, "\nUdpLite:"); + for (i = 0; snmp4_udp_list[i].name != NULL; i++) + seq_printf(seq, " %lu", + fold_field((void **) udplite_statistics, + snmp4_udp_list[i].entry) ); + seq_putc(seq, '\n'); return 0; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 9e1bd374875e..98ba75096175 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -92,22 +92,16 @@ #include <linux/timer.h> #include <linux/mm.h> #include <linux/inet.h> -#include <linux/ipv6.h> #include <linux/netdevice.h> -#include <net/snmp.h> -#include < |