From e898d4db2749c6052072e9bc4448e396cbdeb06a Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Sat, 1 Mar 2008 01:06:47 +0900 Subject: [UDP]: Allow users to configure UDP-Lite. Let's give users an option for disabling UDP-Lite (~4K). old: | text data bss dec hex filename | 286498 12432 6072 305002 4a76a net/ipv4/built-in.o | 193830 8192 3204 205226 321aa net/ipv6/ipv6.o new (without UDP-Lite): | text data bss dec hex filename | 284086 12136 5432 301654 49a56 net/ipv4/built-in.o | 191835 7832 3076 202743 317f7 net/ipv6/ipv6.o Signed-off-by: YOSHIFUJI Hideaki --- net/ipv6/proc.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/ipv6/proc.c') diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 199ef379e50..5ba7ae849d0 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -39,8 +39,10 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v) sock_prot_inuse_get(&tcpv6_prot)); seq_printf(seq, "UDP6: inuse %d\n", sock_prot_inuse_get(&udpv6_prot)); +#ifdef CONFIG_IP_UDPLITE seq_printf(seq, "UDPLITE6: inuse %d\n", sock_prot_inuse_get(&udplitev6_prot)); +#endif seq_printf(seq, "RAW6: inuse %d\n", sock_prot_inuse_get(&rawv6_prot)); seq_printf(seq, "FRAG6: inuse %d memory %d\n", @@ -111,6 +113,7 @@ static struct snmp_mib snmp6_udp6_list[] = { SNMP_MIB_SENTINEL }; +#ifdef CONFIG_IP_UDPLITE static struct snmp_mib snmp6_udplite6_list[] = { SNMP_MIB_ITEM("UdpLite6InDatagrams", UDP_MIB_INDATAGRAMS), SNMP_MIB_ITEM("UdpLite6NoPorts", UDP_MIB_NOPORTS), @@ -118,6 +121,7 @@ static struct snmp_mib snmp6_udplite6_list[] = { SNMP_MIB_ITEM("UdpLite6OutDatagrams", UDP_MIB_OUTDATAGRAMS), SNMP_MIB_SENTINEL }; +#endif static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib) { @@ -176,7 +180,9 @@ static int snmp6_seq_show(struct seq_file *seq, void *v) snmp6_seq_show_item(seq, (void **)icmpv6_statistics, snmp6_icmp6_list); snmp6_seq_show_icmpv6msg(seq, (void **)icmpv6msg_statistics); snmp6_seq_show_item(seq, (void **)udp_stats_in6, snmp6_udp6_list); +#ifdef CONFIG_IP_UDPLITE snmp6_seq_show_item(seq, (void **)udplite_stats_in6, snmp6_udplite6_list); +#endif } return 0; } -- cgit v1.2.3-70-g09d2 From 300bf591deca8d108799e70e9300dc31765643e3 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 5 Mar 2008 10:46:31 -0800 Subject: [NETNS][IPV6] proc - protect snmp6 from non-init_net calls This patchset avoids creation of the /proc entry for snmp6 when the call is made from a network namespace different from the init_net. Signed-off-by: Daniel Lezcano Signed-off-by: David S. Miller --- net/ipv6/proc.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/ipv6/proc.c') diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 5ba7ae849d0..2453f2229ef 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -220,6 +220,9 @@ int snmp6_register_dev(struct inet6_dev *idev) if (!idev || !idev->dev) return -EINVAL; + if (idev->dev->nd_net != &init_net) + return 0; + if (!proc_net_devsnmp6) return -ENOENT; -- cgit v1.2.3-70-g09d2 From db8dac20d5199307dcfcf4e01dac4bda5edf9e89 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 6 Mar 2008 16:22:02 -0800 Subject: [UDP]: Revert udplite and code split. This reverts commit db1ed684f6c430c4cdad67d058688b8a1b5e607c ("[IPV6] UDP: Rename IPv6 UDP files."), commit 8be8af8fa4405652e6c0797db5465a4be8afb998 ("[IPV4] UDP: Move IPv4-specific bits to other file.") and commit e898d4db2749c6052072e9bc4448e396cbdeb06a ("[UDP]: Allow users to configure UDP-Lite."). First, udplite is of such small cost, and it is a core protocol just like TCP and normal UDP are. We spent enormous amounts of effort to make udplite share as much code with core UDP as possible. All of that work is less valuable if we're just going to slap a config option on udplite support. It is also causing build failures, as reported on linux-next, showing that the changeset was not tested very well. In fact, this is the second build failure resulting from the udplite change. Finally, the config options provided was a bool, instead of a modular option. Meaning the udplite code does not even get build tested by allmodconfig builds, and furthermore the user is not presented with a reasonable modular build option which is particularly needed by distribution vendors. Signed-off-by: David S. Miller --- include/linux/udp.h | 10 - include/net/ipv6.h | 5 - include/net/transp_v6.h | 5 - include/net/udplite.h | 9 +- net/ipv4/Kconfig | 10 - net/ipv4/Makefile | 3 +- net/ipv4/af_inet.c | 7 +- net/ipv4/proc.c | 5 +- net/ipv4/udp.c | 1090 +++++++++++++++++++++++++++++++++++++++++++- net/ipv4/udp_ipv4.c | 1134 ---------------------------------------------- net/ipv4/udplite.c | 121 +++++ net/ipv4/udplite_ipv4.c | 121 ----- net/ipv6/Makefile | 3 +- net/ipv6/af_inet6.c | 14 - net/ipv6/ipv6_sockglue.c | 6 +- net/ipv6/proc.c | 6 - net/ipv6/udp.c | 1065 +++++++++++++++++++++++++++++++++++++++++++ net/ipv6/udp_ipv6.c | 1065 ------------------------------------------- net/ipv6/udplite.c | 125 +++++ net/ipv6/udplite_ipv6.c | 125 ----- 20 files changed, 2404 insertions(+), 2525 deletions(-) delete mode 100644 net/ipv4/udp_ipv4.c create mode 100644 net/ipv4/udplite.c delete mode 100644 net/ipv4/udplite_ipv4.c create mode 100644 net/ipv6/udp.c delete mode 100644 net/ipv6/udp_ipv6.c create mode 100644 net/ipv6/udplite.c delete mode 100644 net/ipv6/udplite_ipv6.c (limited to 'net/ipv6/proc.c') diff --git a/include/linux/udp.h b/include/linux/udp.h index 4144664d69d..1e7b7cb5703 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -70,10 +70,8 @@ struct udp_sock { #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 */ -#ifdef CONFIG_IP_UDPLITE __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ __u8 unused[3]; -#endif /* * For encapsulation sockets. */ @@ -85,15 +83,7 @@ static inline struct udp_sock *udp_sk(const struct sock *sk) return (struct udp_sock *)sk; } -#ifdef CONFIG_IP_UDPLITE #define IS_UDPLITE(__sk) (udp_sk(__sk)->pcflag) -#define IS_PROTO_UDPLITE(__proto) ((__proto) == IPPROTO_UDPLITE) -#define IS_SOL_UDPFAMILY(level) ((level) == SOL_UDP || (level) == SOL_UDPLITE) -#else -#define IS_UDPLITE(__sk) 0 -#define IS_PROTO_UDPLITE(__proto) 0 -#define IS_SOL_UDPFAMILY(level) ((level) == SOL_UDP) -#endif #endif diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 5f6df50a33a..8db06af1efb 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -599,13 +599,8 @@ extern int tcp6_proc_init(void); extern void tcp6_proc_exit(void); extern int udp6_proc_init(void); extern void udp6_proc_exit(void); -#ifdef CONFIG_IP_UDPLITE extern int udplite6_proc_init(void); extern void udplite6_proc_exit(void); -#else -static inline int udplite6_proc_init(void) { return 0; } -static inline void udplite6_proc_exit(void) { } -#endif extern int ipv6_misc_proc_init(void); extern void ipv6_misc_proc_exit(void); extern int snmp6_register_dev(struct inet6_dev *idev); diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index 902e6c6bc79..27394e0447d 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -27,13 +27,8 @@ extern int rawv6_init(void); extern void rawv6_exit(void); extern int udpv6_init(void); extern void udpv6_exit(void); -#ifdef CONFIG_IP_UDPLITE extern int udplitev6_init(void); extern void udplitev6_exit(void); -#else -static inline int udplitev6_init(void) { return 0; } -static inline void udplitev6_exit(void) { } -#endif extern int tcpv6_init(void); extern void tcpv6_exit(void); diff --git a/include/net/udplite.h b/include/net/udplite.h index 01ddb2c2026..b76b2e377af 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -25,9 +25,7 @@ static __inline__ int udplite_getfrag(void *from, char *to, int offset, /* Designate sk as UDP-Lite socket */ static inline int udplite_sk_init(struct sock *sk) { -#ifdef CONFIG_IP_UDPLITE udp_sk(sk)->pcflag = UDPLITE_BIT; -#endif return 0; } @@ -71,7 +69,7 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) static inline int udplite_sender_cscov(struct udp_sock *up, struct udphdr *uh) { int cscov = up->len; -#ifdef CONFIG_IP_UDPLITE + /* * Sender has set `partial coverage' option on UDP-Lite socket */ @@ -95,15 +93,13 @@ static inline int udplite_sender_cscov(struct udp_sock *up, struct udphdr *uh) * illegal, we fall back to the defaults here. */ } -#endif return cscov; } static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) { - __wsum csum = 0; -#ifdef CONFIG_IP_UDPLITE int cscov = udplite_sender_cscov(udp_sk(sk), udp_hdr(skb)); + __wsum csum = 0; skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ @@ -116,7 +112,6 @@ static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) if ((cscov -= len) <= 0) break; } -#endif return csum; } diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 5098fd2ff4d..9c7e5ffb223 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -632,15 +632,5 @@ config TCP_MD5SIG If unsure, say N. -config IP_UDPLITE - bool "IP: UDP-Lite Protocol (RFC 3828)" - default n - ---help--- - UDP-Lite (RFC 3828) is a UDP-like protocol with variable-length - checksum. Read for - details. - - If unsure, say N. - source "net/ipv4/ipvs/Kconfig" diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index d5226241d5e..ad40ef3f9eb 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -8,7 +8,7 @@ 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 udp_ipv4.o \ + datagram.o raw.o udp.o udplite.o \ arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o \ inet_fragment.o @@ -49,7 +49,6 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o -obj-$(CONFIG_IP_UDPLITE) += udplite_ipv4.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 25871c6c744..4cb8a138553 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1317,18 +1317,15 @@ static int __init init_ipv4_mibs(void) if (snmp_mib_init((void **)udp_statistics, sizeof(struct udp_mib)) < 0) goto err_udp_mib; -#ifdef CONFIG_IP_UDPLITE if (snmp_mib_init((void **)udplite_statistics, sizeof(struct udp_mib)) < 0) goto err_udplite_mib; -#endif + tcp_mib_init(); return 0; -#ifdef CONFIG_IP_UDPLITE err_udplite_mib: -#endif snmp_mib_free((void **)udp_statistics); err_udp_mib: snmp_mib_free((void **)tcp_statistics); @@ -1426,10 +1423,8 @@ static int __init inet_init(void) /* Setup UDP memory threshold */ udp_init(); -#ifdef CONFIG_IP_UDPLITE /* Add UDP-Lite (RFC 3828) */ udplite4_register(); -#endif /* * Set the ICMP layer up diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index d75ddb7fa4b..d63474c6b40 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -59,9 +59,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) atomic_read(&tcp_memory_allocated)); seq_printf(seq, "UDP: inuse %d mem %d\n", sock_prot_inuse_get(&udp_prot), atomic_read(&udp_memory_allocated)); -#ifdef CONFIG_IP_UDPLITE seq_printf(seq, "UDPLITE: inuse %d\n", sock_prot_inuse_get(&udplite_prot)); -#endif seq_printf(seq, "RAW: inuse %d\n", sock_prot_inuse_get(&raw_prot)); seq_printf(seq, "FRAG: inuse %d memory %d\n", ip_frag_nqueues(&init_net), ip_frag_mem(&init_net)); @@ -351,7 +349,6 @@ static int snmp_seq_show(struct seq_file *seq, void *v) snmp_fold_field((void **)udp_statistics, snmp4_udp_list[i].entry)); -#ifdef CONFIG_IP_UDPLITE /* the UDP and UDP-Lite MIBs are the same */ seq_puts(seq, "\nUdpLite:"); for (i = 0; snmp4_udp_list[i].name != NULL; i++) @@ -362,7 +359,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v) seq_printf(seq, " %lu", snmp_fold_field((void **)udplite_statistics, snmp4_udp_list[i].entry)); -#endif + seq_putc(seq, '\n'); return 0; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c53d7673b57..7ea1b67b6de 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -246,6 +246,553 @@ int udp_get_port(struct sock *sk, unsigned short snum, return __udp_lib_get_port(sk, snum, udp_hash, scmp); } +int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) +{ + struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2); + + return ( !ipv6_only_sock(sk2) && + (!inet1->rcv_saddr || !inet2->rcv_saddr || + inet1->rcv_saddr == inet2->rcv_saddr )); +} + +static inline int udp_v4_get_port(struct sock *sk, unsigned short snum) +{ + return udp_get_port(sk, snum, ipv4_rcv_saddr_equal); +} + +/* UDP is nearly always wildcards out the wazoo, it makes no sense to try + * harder than this. -DaveM + */ +static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, + __be16 sport, __be32 daddr, __be16 dport, + int dif, struct hlist_head udptable[]) +{ + struct sock *sk, *result = NULL; + struct hlist_node *node; + unsigned short hnum = ntohs(dport); + int badness = -1; + + read_lock(&udp_hash_lock); + sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) { + struct inet_sock *inet = inet_sk(sk); + + if (sk->sk_net == net && sk->sk_hash == hnum && + !ipv6_only_sock(sk)) { + int score = (sk->sk_family == PF_INET ? 1 : 0); + if (inet->rcv_saddr) { + if (inet->rcv_saddr != daddr) + continue; + score+=2; + } + if (inet->daddr) { + if (inet->daddr != saddr) + continue; + score+=2; + } + if (inet->dport) { + if (inet->dport != sport) + continue; + score+=2; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + continue; + score+=2; + } + if (score == 9) { + result = sk; + break; + } else if (score > badness) { + result = sk; + badness = score; + } + } + } + if (result) + sock_hold(result); + read_unlock(&udp_hash_lock); + return result; +} + +static inline struct sock *udp_v4_mcast_next(struct sock *sk, + __be16 loc_port, __be32 loc_addr, + __be16 rmt_port, __be32 rmt_addr, + int dif) +{ + struct hlist_node *node; + struct sock *s = sk; + unsigned short hnum = ntohs(loc_port); + + sk_for_each_from(s, node) { + struct inet_sock *inet = inet_sk(s); + + if (s->sk_hash != hnum || + (inet->daddr && inet->daddr != rmt_addr) || + (inet->dport != rmt_port && inet->dport) || + (inet->rcv_saddr && inet->rcv_saddr != loc_addr) || + ipv6_only_sock(s) || + (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)) + continue; + if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif)) + continue; + goto found; + } + s = NULL; +found: + return s; +} + +/* + * This routine is called by the ICMP module when it gets some + * sort of error condition. If err < 0 then the socket should + * be closed and the error returned to the user. If err > 0 + * it's just the icmp type << 8 | icmp code. + * Header points to the ip header of the error packet. We move + * on past this. Then (as it used to claim before adjustment) + * header points to the first 8 bytes of the udp header. We need + * to find the appropriate port. + */ + +void __udp4_lib_err(struct sk_buff *skb, u32 info, struct hlist_head udptable[]) +{ + struct inet_sock *inet; + struct iphdr *iph = (struct iphdr*)skb->data; + struct udphdr *uh = (struct udphdr*)(skb->data+(iph->ihl<<2)); + const int type = icmp_hdr(skb)->type; + const int code = icmp_hdr(skb)->code; + struct sock *sk; + int harderr; + int err; + + sk = __udp4_lib_lookup(skb->dev->nd_net, iph->daddr, uh->dest, + iph->saddr, uh->source, skb->dev->ifindex, udptable); + if (sk == NULL) { + ICMP_INC_STATS_BH(ICMP_MIB_INERRORS); + return; /* No socket for error */ + } + + err = 0; + harderr = 0; + inet = inet_sk(sk); + + switch (type) { + default: + case ICMP_TIME_EXCEEDED: + err = EHOSTUNREACH; + break; + case ICMP_SOURCE_QUENCH: + goto out; + case ICMP_PARAMETERPROB: + err = EPROTO; + harderr = 1; + break; + case ICMP_DEST_UNREACH: + if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ + if (inet->pmtudisc != IP_PMTUDISC_DONT) { + err = EMSGSIZE; + harderr = 1; + break; + } + goto out; + } + err = EHOSTUNREACH; + if (code <= NR_ICMP_UNREACH) { + harderr = icmp_err_convert[code].fatal; + err = icmp_err_convert[code].errno; + } + break; + } + + /* + * RFC1122: OK. Passes ICMP errors back to application, as per + * 4.1.3.3. + */ + if (!inet->recverr) { + if (!harderr || sk->sk_state != TCP_ESTABLISHED) + goto out; + } else { + ip_icmp_error(sk, skb, err, uh->dest, info, (u8*)(uh+1)); + } + sk->sk_err = err; + sk->sk_error_report(sk); +out: + sock_put(sk); +} + +void udp_err(struct sk_buff *skb, u32 info) +{ + __udp4_lib_err(skb, info, udp_hash); +} + +/* + * Throw away all pending data and cancel the corking. Socket is locked. + */ +static void udp_flush_pending_frames(struct sock *sk) +{ + struct udp_sock *up = udp_sk(sk); + + if (up->pending) { + up->len = 0; + up->pending = 0; + ip_flush_pending_frames(sk); + } +} + +/** + * udp4_hwcsum_outgoing - handle outgoing HW checksumming + * @sk: socket we are sending on + * @skb: sk_buff containing the filled-in UDP header + * (checksum field must be zeroed out) + */ +static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, + __be32 src, __be32 dst, int len ) +{ + unsigned int offset; + struct udphdr *uh = udp_hdr(skb); + __wsum csum = 0; + + if (skb_queue_len(&sk->sk_write_queue) == 1) { + /* + * Only one fragment on the socket. + */ + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + uh->check = ~csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, 0); + } else { + /* + * HW-checksum won't work as there are two or more + * fragments on the socket so that all csums of sk_buffs + * should be together + */ + offset = skb_transport_offset(skb); + skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); + + skb->ip_summed = CHECKSUM_NONE; + + skb_queue_walk(&sk->sk_write_queue, skb) { + csum = csum_add(csum, skb->csum); + } + + uh->check = csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } +} + +/* + * Push out all pending data as one UDP datagram. Socket is locked. + */ +static int udp_push_pending_frames(struct sock *sk) +{ + struct udp_sock *up = udp_sk(sk); + struct inet_sock *inet = inet_sk(sk); + struct flowi *fl = &inet->cork.fl; + struct sk_buff *skb; + struct udphdr *uh; + int err = 0; + int is_udplite = IS_UDPLITE(sk); + __wsum csum = 0; + + /* Grab the skbuff where UDP header space exists. */ + if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) + goto out; + + /* + * Create a UDP header + */ + uh = udp_hdr(skb); + uh->source = fl->fl_ip_sport; + uh->dest = fl->fl_ip_dport; + uh->len = htons(up->len); + uh->check = 0; + + if (is_udplite) /* UDP-Lite */ + csum = udplite_csum_outgoing(sk, skb); + + else if (sk->sk_no_check == UDP_CSUM_NOXMIT) { /* UDP csum disabled */ + + skb->ip_summed = CHECKSUM_NONE; + goto send; + + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ + + udp4_hwcsum_outgoing(sk, skb, fl->fl4_src,fl->fl4_dst, up->len); + goto send; + + } else /* `normal' UDP */ + csum = udp_csum_outgoing(sk, skb); + + /* add protocol-dependent pseudo-header */ + uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst, up->len, + sk->sk_protocol, csum ); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + +send: + err = ip_push_pending_frames(sk); +out: + up->len = 0; + up->pending = 0; + if (!err) + UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite); + return err; +} + +int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len) +{ + struct inet_sock *inet = inet_sk(sk); + struct udp_sock *up = udp_sk(sk); + int ulen = len; + struct ipcm_cookie ipc; + struct rtable *rt = NULL; + int free = 0; + int connected = 0; + __be32 daddr, faddr, saddr; + __be16 dport; + u8 tos; + int err, is_udplite = IS_UDPLITE(sk); + int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); + + if (len > 0xFFFF) + return -EMSGSIZE; + + /* + * Check the flags. + */ + + if (msg->msg_flags&MSG_OOB) /* Mirror BSD error message compatibility */ + return -EOPNOTSUPP; + + ipc.opt = NULL; + + if (up->pending) { + /* + * There are pending frames. + * The socket lock must be held while it's corked. + */ + lock_sock(sk); + if (likely(up->pending)) { + if (unlikely(up->pending != AF_INET)) { + release_sock(sk); + return -EINVAL; + } + goto do_append_data; + } + release_sock(sk); + } + ulen += sizeof(struct udphdr); + + /* + * Get and verify the address. + */ + if (msg->msg_name) { + struct sockaddr_in * usin = (struct sockaddr_in*)msg->msg_name; + if (msg->msg_namelen < sizeof(*usin)) + return -EINVAL; + if (usin->sin_family != AF_INET) { + if (usin->sin_family != AF_UNSPEC) + return -EAFNOSUPPORT; + } + + daddr = usin->sin_addr.s_addr; + dport = usin->sin_port; + if (dport == 0) + return -EINVAL; + } else { + if (sk->sk_state != TCP_ESTABLISHED) + return -EDESTADDRREQ; + daddr = inet->daddr; + dport = inet->dport; + /* Open fast path for connected socket. + Route will not be used, if at least one option is set. + */ + connected = 1; + } + ipc.addr = inet->saddr; + + ipc.oif = sk->sk_bound_dev_if; + if (msg->msg_controllen) { + err = ip_cmsg_send(msg, &ipc); + if (err) + return err; + if (ipc.opt) + free = 1; + connected = 0; + } + if (!ipc.opt) + ipc.opt = inet->opt; + + saddr = ipc.addr; + ipc.addr = faddr = daddr; + + if (ipc.opt && ipc.opt->srr) { + if (!daddr) + return -EINVAL; + faddr = ipc.opt->faddr; + connected = 0; + } + tos = RT_TOS(inet->tos); + if (sock_flag(sk, SOCK_LOCALROUTE) || + (msg->msg_flags & MSG_DONTROUTE) || + (ipc.opt && ipc.opt->is_strictroute)) { + tos |= RTO_ONLINK; + connected = 0; + } + + if (ipv4_is_multicast(daddr)) { + if (!ipc.oif) + ipc.oif = inet->mc_index; + if (!saddr) + saddr = inet->mc_addr; + connected = 0; + } + + if (connected) + rt = (struct rtable*)sk_dst_check(sk, 0); + + if (rt == NULL) { + struct flowi fl = { .oif = ipc.oif, + .nl_u = { .ip4_u = + { .daddr = faddr, + .saddr = saddr, + .tos = tos } }, + .proto = sk->sk_protocol, + .uli_u = { .ports = + { .sport = inet->sport, + .dport = dport } } }; + security_sk_classify_flow(sk, &fl); + err = ip_route_output_flow(&init_net, &rt, &fl, sk, 1); + if (err) { + if (err == -ENETUNREACH) + IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); + goto out; + } + + err = -EACCES; + if ((rt->rt_flags & RTCF_BROADCAST) && + !sock_flag(sk, SOCK_BROADCAST)) + goto out; + if (connected) + sk_dst_set(sk, dst_clone(&rt->u.dst)); + } + + if (msg->msg_flags&MSG_CONFIRM) + goto do_confirm; +back_from_confirm: + + saddr = rt->rt_src; + if (!ipc.addr) + daddr = ipc.addr = rt->rt_dst; + + lock_sock(sk); + if (unlikely(up->pending)) { + /* The socket is already corked while preparing it. */ + /* ... which is an evident application bug. --ANK */ + release_sock(sk); + + LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n"); + err = -EINVAL; + goto out; + } + /* + * Now cork the socket to pend data. + */ + inet->cork.fl.fl4_dst = daddr; + inet->cork.fl.fl_ip_dport = dport; + inet->cork.fl.fl4_src = saddr; + inet->cork.fl.fl_ip_sport = inet->sport; + up->pending = AF_INET; + +do_append_data: + up->len += ulen; + getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; + err = ip_append_data(sk, getfrag, msg->msg_iov, ulen, + sizeof(struct udphdr), &ipc, rt, + corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); + if (err) + udp_flush_pending_frames(sk); + else if (!corkreq) + err = udp_push_pending_frames(sk); + else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) + up->pending = 0; + release_sock(sk); + +out: + ip_rt_put(rt); + if (free) + kfree(ipc.opt); + if (!err) + return len; + /* + * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting + * ENOBUFS might not be good (it's not tunable per se), but otherwise + * we don't have a good statistic (IpOutDiscards but it can be too many + * things). We could add another new stat but at least for now that + * seems like overkill. + */ + if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { + UDP_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite); + } + return err; + +do_confirm: + dst_confirm(&rt->u.dst); + if (!(msg->msg_flags&MSG_PROBE) || len) + goto back_from_confirm; + err = 0; + goto out; +} + +int udp_sendpage(struct sock *sk, struct page *page, int offset, + size_t size, int flags) +{ + struct udp_sock *up = udp_sk(sk); + int ret; + + if (!up->pending) { + struct msghdr msg = { .msg_flags = flags|MSG_MORE }; + + /* Call udp_sendmsg to specify destination address which + * sendpage interface can't pass. + * This will succeed only when the socket is connected. + */ + ret = udp_sendmsg(NULL, sk, &msg, 0); + if (ret < 0) + return ret; + } + + lock_sock(sk); + + if (unlikely(!up->pending)) { + release_sock(sk); + + LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 3\n"); + return -EINVAL; + } + + ret = ip_append_page(sk, page, offset, size, flags); + if (ret == -EOPNOTSUPP) { + release_sock(sk); + return sock_no_sendpage(sk->sk_socket, page, offset, + size, flags); + } + if (ret < 0) { + udp_flush_pending_frames(sk); + goto out; + } + + up->len += size; + if (!(up->corkflag || (flags&MSG_MORE))) + ret = udp_push_pending_frames(sk); + if (!ret) + ret = size; +out: + release_sock(sk); + return ret; +} + /* * IOCTL requests applicable to the UDP protocol */ @@ -286,6 +833,107 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) return 0; } +/* + * This should be easy, if there is something there we + * return it, otherwise we block. + */ + +int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len, int noblock, int flags, int *addr_len) +{ + struct inet_sock *inet = inet_sk(sk); + struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; + struct sk_buff *skb; + unsigned int ulen, copied; + int peeked; + int err; + int is_udplite = IS_UDPLITE(sk); + + /* + * Check any passed addresses + */ + if (addr_len) + *addr_len=sizeof(*sin); + + if (flags & MSG_ERRQUEUE) + return ip_recv_error(sk, msg, len); + +try_again: + skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), + &peeked, &err); + if (!skb) + goto out; + + ulen = skb->len - sizeof(struct udphdr); + copied = len; + if (copied > ulen) + copied = ulen; + else if (copied < ulen) + msg->msg_flags |= MSG_TRUNC; + + /* + * If checksum is needed at all, try to do it while copying the + * data. If the data is truncated, or if we only want a partial + * coverage checksum (UDP-Lite), do it before the copy. + */ + + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (udp_lib_checksum_complete(skb)) + goto csum_copy_err; + } + + if (skb_csum_unnecessary(skb)) + err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), + msg->msg_iov, copied ); + else { + err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); + + if (err == -EINVAL) + goto csum_copy_err; + } + + if (err) + goto out_free; + + if (!peeked) + UDP_INC_STATS_USER(UDP_MIB_INDATAGRAMS, is_udplite); + + sock_recv_timestamp(msg, sk, skb); + + /* Copy the address. */ + if (sin) + { + sin->sin_family = AF_INET; + sin->sin_port = udp_hdr(skb)->source; + sin->sin_addr.s_addr = ip_hdr(skb)->saddr; + memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + } + if (inet->cmsg_flags) + ip_cmsg_recv(msg, skb); + + err = copied; + if (flags & MSG_TRUNC) + err = ulen; + +out_free: + lock_sock(sk); + skb_free_datagram(sk, skb); + release_sock(sk); +out: + return err; + +csum_copy_err: + lock_sock(sk); + if (!skb_kill_datagram(sk, skb, flags)) + UDP_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite); + release_sock(sk); + + if (noblock) + return -EAGAIN; + goto try_again; +} + + int udp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); @@ -308,6 +956,319 @@ int udp_disconnect(struct sock *sk, int flags) return 0; } +/* returns: + * -1: error + * 0: success + * >0: "udp encap" protocol resubmission + * + * Note that in the success and error cases, the skb is assumed to + * have either been requeued or freed. + */ +int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) +{ + struct udp_sock *up = udp_sk(sk); + int rc; + int is_udplite = IS_UDPLITE(sk); + + /* + * Charge it to the socket, dropping if the queue is full. + */ + if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) + goto drop; + nf_reset(skb); + + if (up->encap_type) { + /* + * This is an encapsulation socket so pass the skb to + * the socket's udp_encap_rcv() hook. Otherwise, just + * fall through and pass this up the UDP socket. + * up->encap_rcv() returns the following value: + * =0 if skb was successfully passed to the encap + * handler or was discarded by it. + * >0 if skb should be passed on to UDP. + * <0 if skb should be resubmitted as proto -N + */ + + /* if we're overly short, let UDP handle it */ + if (skb->len > sizeof(struct udphdr) && + up->encap_rcv != NULL) { + int ret; + + ret = (*up->encap_rcv)(sk, skb); + if (ret <= 0) { + UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, + is_udplite); + return -ret; + } + } + + /* FALLTHROUGH -- it's a UDP Packet */ + } + + /* + * UDP-Lite specific tests, ignored on UDP sockets + */ + if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + + /* + * MIB statistics other than incrementing the error count are + * disabled for the following two types of errors: these depend + * on the application settings, not on the functioning of the + * protocol stack as such. + * + * RFC 3828 here recommends (sec 3.3): "There should also be a + * way ... to ... at least let the receiving application block + * delivery of packets with coverage values less than a value + * provided by the application." + */ + if (up->pcrlen == 0) { /* full coverage was set */ + LIMIT_NETDEBUG(KERN_WARNING "UDPLITE: partial coverage " + "%d while full coverage %d requested\n", + UDP_SKB_CB(skb)->cscov, skb->len); + goto drop; + } + /* The next case involves violating the min. coverage requested + * by the receiver. This is subtle: if receiver wants x and x is + * greater than the buffersize/MTU then receiver will complain + * that it wants x while sender emits packets of smaller size y. + * Therefore the above ...()->partial_cov statement is essential. + */ + if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { + LIMIT_NETDEBUG(KERN_WARNING + "UDPLITE: coverage %d too small, need min %d\n", + UDP_SKB_CB(skb)->cscov, up->pcrlen); + goto drop; + } + } + + if (sk->sk_filter) { + if (udp_lib_checksum_complete(skb)) + goto drop; + } + + if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { + /* Note that an ENOMEM error is charged twice */ + if (rc == -ENOMEM) + UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, is_udplite); + goto drop; + } + + return 0; + +drop: + UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite); + kfree_skb(skb); + return -1; +} + +/* + * Multicasts and broadcasts go to each listener. + * + * Note: called only from the BH handler context, + * so we don't need to lock the hashes. + */ +static int __udp4_lib_mcast_deliver(struct sk_buff *skb, + struct udphdr *uh, + __be32 saddr, __be32 daddr, + struct hlist_head udptable[]) +{ + struct sock *sk; + int dif; + + read_lock(&udp_hash_lock); + sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]); + dif = skb->dev->ifindex; + sk = udp_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif); + if (sk) { + struct sock *sknext = NULL; + + do { + struct sk_buff *skb1 = skb; + + sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr, + uh->source, saddr, dif); + if (sknext) + skb1 = skb_clone(skb, GFP_ATOMIC); + + if (skb1) { + int ret = 0; + + bh_lock_sock_nested(sk); + if (!sock_owned_by_user(sk)) + ret = udp_queue_rcv_skb(sk, skb1); + else + sk_add_backlog(sk, skb1); + bh_unlock_sock(sk); + + if (ret > 0) + /* we should probably re-process instead + * of dropping packets here. */ + kfree_skb(skb1); + } + sk = sknext; + } while (sknext); + } else + kfree_skb(skb); + read_unlock(&udp_hash_lock); + return 0; +} + +/* Initialize UDP checksum. If exited with zero value (success), + * CHECKSUM_UNNECESSARY means, that no more checks are required. + * Otherwise, csum completion requires chacksumming packet body, + * including udp header and folding it to skb->csum. + */ +static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, + int proto) +{ + const struct iphdr *iph; + int err; + + UDP_SKB_CB(skb)->partial_cov = 0; + UDP_SKB_CB(skb)->cscov = skb->len; + + if (proto == IPPROTO_UDPLITE) { + err = udplite_checksum_init(skb, uh); + if (err) + return err; + } + + iph = ip_hdr(skb); + if (uh->check == 0) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + } else if (skb->ip_summed == CHECKSUM_COMPLETE) { + if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len, + proto, skb->csum)) + skb->ip_summed = CHECKSUM_UNNECESSARY; + } + if (!skb_csum_unnecessary(skb)) + skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, + skb->len, proto, 0); + /* Probably, we should checksum udp header (it should be in cache + * in any case) and data in tiny packets (< rx copybreak). + */ + + return 0; +} + +/* + * All we need to do is get the socket, and then do a checksum. + */ + +int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], + int proto) +{ + struct sock *sk; + struct udphdr *uh = udp_hdr(skb); + unsigned short ulen; + struct rtable *rt = (struct rtable*)skb->dst; + __be32 saddr = ip_hdr(skb)->saddr; + __be32 daddr = ip_hdr(skb)->daddr; + + /* + * Validate the packet. + */ + if (!pskb_may_pull(skb, sizeof(struct udphdr))) + goto drop; /* No space for header. */ + + ulen = ntohs(uh->len); + if (ulen > skb->len) + goto short_packet; + + if (proto == IPPROTO_UDP) { + /* UDP validates ulen. */ + if (ulen < sizeof(*uh) || pskb_trim_rcsum(skb, ulen)) + goto short_packet; + uh = udp_hdr(skb); + } + + if (udp4_csum_init(skb, uh, proto)) + goto csum_error; + + if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) + return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable); + + sk = __udp4_lib_lookup(skb->dev->nd_net, saddr, uh->source, daddr, + uh->dest, inet_iif(skb), udptable); + + if (sk != NULL) { + int ret = 0; + bh_lock_sock_nested(sk); + if (!sock_owned_by_user(sk)) + ret = udp_queue_rcv_skb(sk, skb); + else + sk_add_backlog(sk, skb); + bh_unlock_sock(sk); + sock_put(sk); + + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; + return 0; + } + + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + nf_reset(skb); + + /* No socket. Drop packet silently, if checksum is wrong */ + if (udp_lib_checksum_complete(skb)) + goto csum_error; + + UDP_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + /* + * Hmm. We got an UDP packet to a port to which we + * don't wanna listen. Ignore it. + */ + kfree_skb(skb); + return 0; + +short_packet: + LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %u.%u.%u.%u:%u %d/%d to %u.%u.%u.%u:%u\n", + proto == IPPROTO_UDPLITE ? "-Lite" : "", + NIPQUAD(saddr), + ntohs(uh->source), + ulen, + skb->len, + NIPQUAD(daddr), + ntohs(uh->dest)); + goto drop; + +csum_error: + /* + * RFC1122: OK. Discards the bad packet silently (as far as + * the network is concerned, anyway) as per 4.1.3.4 (MUST). + */ + LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %d.%d.%d.%d:%d to %d.%d.%d.%d:%d ulen %d\n", + proto == IPPROTO_UDPLITE ? "-Lite" : "", + NIPQUAD(saddr), + ntohs(uh->source), + NIPQUAD(daddr), + ntohs(uh->dest), + ulen); +drop: + UDP_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); + kfree_skb(skb); + return 0; +} + +int udp_rcv(struct sk_buff *skb) +{ + return __udp4_lib_rcv(skb, udp_hash, IPPROTO_UDP); +} + +int udp_destroy_sock(struct sock *sk) +{ + lock_sock(sk); + udp_flush_pending_frames(sk); + release_sock(sk); + return 0; +} + /* * Socket option code for UDP */ @@ -318,9 +1279,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, struct udp_sock *up = udp_sk(sk); int val; int err = 0; -#ifdef CONFIG_IP_UDPLITE int is_udplite = IS_UDPLITE(sk); -#endif if (optlenpcrlen = val; up->pcflag |= UDPLITE_RECV_CC; break; -#endif default: err = -ENOPROTOOPT; @@ -392,6 +1349,26 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return err; } +int udp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_setsockopt(sk, level, optname, optval, optlen, + udp_push_pending_frames); + return ip_setsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +int compat_udp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_setsockopt(sk, level, optname, optval, optlen, + udp_push_pending_frames); + return compat_ip_setsockopt(sk, level, optname, optval, optlen); +} +#endif + int udp_lib_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -436,6 +1413,23 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, return 0; } +int udp_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_getsockopt(sk, level, optname, optval, optlen); + return ip_getsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +int compat_udp_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_getsockopt(sk, level, optname, optval, optlen); + return compat_ip_getsockopt(sk, level, optname, optval, optlen); +} +#endif /** * udp_poll - wait for a UDP event. * @file - file struct @@ -480,6 +1474,36 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) } +DEFINE_PROTO_INUSE(udp) + +struct proto udp_prot = { + .name = "UDP", + .owner = THIS_MODULE, + .close = udp_lib_close, + .connect = ip4_datagram_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .destroy = udp_destroy_sock, + .setsockopt = udp_setsockopt, + .getsockopt = udp_getsockopt, + .sendmsg = udp_sendmsg, + .recvmsg = udp_recvmsg, + .sendpage = udp_sendpage, + .backlog_rcv = udp_queue_rcv_skb, + .hash = udp_lib_hash, + .unhash = udp_lib_unhash, + .get_port = udp_v4_get_port, + .memory_allocated = &udp_memory_allocated, + .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem = &sysctl_udp_wmem_min, + .sysctl_rmem = &sysctl_udp_rmem_min, + .obj_size = sizeof(struct udp_sock), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_udp_setsockopt, + .compat_getsockopt = compat_udp_getsockopt, +#endif + REF_PROTO_INUSE(udp) +}; /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS @@ -612,6 +1636,62 @@ void udp_proc_unregister(struct udp_seq_afinfo *afinfo) proc_net_remove(&init_net, afinfo->name); memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops)); } + +/* ------------------------------------------------------------------------ */ +static void udp4_format_sock(struct sock *sp, char *tmpbuf, int bucket) +{ + struct inet_sock *inet = inet_sk(sp); + __be32 dest = inet->daddr; + __be32 src = inet->rcv_saddr; + __u16 destp = ntohs(inet->dport); + __u16 srcp = ntohs(inet->sport); + + sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X" + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p", + bucket, src, srcp, dest, destp, sp->sk_state, + atomic_read(&sp->sk_wmem_alloc), + atomic_read(&sp->sk_rmem_alloc), + 0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp), + atomic_read(&sp->sk_refcnt), sp); +} + +int udp4_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) + seq_printf(seq, "%-127s\n", + " sl local_address rem_address st tx_queue " + "rx_queue tr tm->when retrnsmt uid timeout " + "inode"); + else { + char tmpbuf[129]; + struct udp_iter_state *state = seq->private; + + udp4_format_sock(v, tmpbuf, state->bucket); + seq_printf(seq, "%-127s\n", tmpbuf); + } + return 0; +} + +/* ------------------------------------------------------------------------ */ +static struct file_operations udp4_seq_fops; +static struct udp_seq_afinfo udp4_seq_afinfo = { + .owner = THIS_MODULE, + .name = "udp", + .family = AF_INET, + .hashtable = udp_hash, + .seq_show = udp4_seq_show, + .seq_fops = &udp4_seq_fops, +}; + +int __init udp4_proc_init(void) +{ + return udp_proc_register(&udp4_seq_afinfo); +} + +void udp4_proc_exit(void) +{ + udp_proc_unregister(&udp4_seq_afinfo); +} #endif /* CONFIG_PROC_FS */ void __init udp_init(void) @@ -638,6 +1718,8 @@ EXPORT_SYMBOL(udp_hash); EXPORT_SYMBOL(udp_hash_lock); EXPORT_SYMBOL(udp_ioctl); EXPORT_SYMBOL(udp_get_port); +EXPORT_SYMBOL(udp_prot); +EXPORT_SYMBOL(udp_sendmsg); EXPORT_SYMBOL(udp_lib_getsockopt); EXPORT_SYMBOL(udp_lib_setsockopt); EXPORT_SYMBOL(udp_poll); diff --git a/net/ipv4/udp_ipv4.c b/net/ipv4/udp_ipv4.c deleted file mode 100644 index fd14c2c50ed..00000000000 --- a/net/ipv4/udp_ipv4.c +++ /dev/null @@ -1,1134 +0,0 @@ -/* - * INET An implementation of the TCP/IP protocol suite for the LINUX - * operating system. INET is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * UDP for IPv4. - * - * For full credits, see net/ipv4/udp.c. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include "udp_impl.h" - -int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) -{ - struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2); - - return ( !ipv6_only_sock(sk2) && - (!inet1->rcv_saddr || !inet2->rcv_saddr || - inet1->rcv_saddr == inet2->rcv_saddr )); -} - -static inline int udp_v4_get_port(struct sock *sk, unsigned short snum) -{ - return udp_get_port(sk, snum, ipv4_rcv_saddr_equal); -} - -/* UDP is nearly always wildcards out the wazoo, it makes no sense to try - * harder than this. -DaveM - */ -static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, - __be16 sport, __be32 daddr, __be16 dport, - int dif, struct hlist_head udptable[]) -{ - struct sock *sk, *result = NULL; - struct hlist_node *node; - unsigned short hnum = ntohs(dport); - int badness = -1; - - read_lock(&udp_hash_lock); - sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) { - struct inet_sock *inet = inet_sk(sk); - - if (sk->sk_net == net && sk->sk_hash == hnum && - !ipv6_only_sock(sk)) { - int score = (sk->sk_family == PF_INET ? 1 : 0); - if (inet->rcv_saddr) { - if (inet->rcv_saddr != daddr) - continue; - score+=2; - } - if (inet->daddr) { - if (inet->daddr != saddr) - continue; - score+=2; - } - if (inet->dport) { - if (inet->dport != sport) - continue; - score+=2; - } - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - continue; - score+=2; - } - if (score == 9) { - result = sk; - break; - } else if (score > badness) { - result = sk; - badness = score; - } - } - } - if (result) - sock_hold(result); - read_unlock(&udp_hash_lock); - return result; -} - -static inline struct sock *udp_v4_mcast_next(struct sock *sk, - __be16 loc_port, __be32 loc_addr, - __be16 rmt_port, __be32 rmt_addr, - int dif) -{ - struct hlist_node *node; - struct sock *s = sk; - unsigned short hnum = ntohs(loc_port); - - sk_for_each_from(s, node) { - struct inet_sock *inet = inet_sk(s); - - if (s->sk_hash != hnum || - (inet->daddr && inet->daddr != rmt_addr) || - (inet->dport != rmt_port && inet->dport) || - (inet->rcv_saddr && inet->rcv_saddr != loc_addr) || - ipv6_only_sock(s) || - (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)) - continue; - if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif)) - continue; - goto found; - } - s = NULL; -found: - return s; -} - -/* - * This routine is called by the ICMP module when it gets some - * sort of error condition. If err < 0 then the socket should - * be closed and the error returned to the user. If err > 0 - * it's just the icmp type << 8 | icmp code. - * Header points to the ip header of the error packet. We move - * on past this. Then (as it used to claim before adjustment) - * header points to the first 8 bytes of the udp header. We need - * to find the appropriate port. - */ - -void __udp4_lib_err(struct sk_buff *skb, u32 info, struct hlist_head udptable[]) -{ - struct inet_sock *inet; - struct iphdr *iph = (struct iphdr*)skb->data; - struct udphdr *uh = (struct udphdr*)(skb->data+(iph->ihl<<2)); - const int type = icmp_hdr(skb)->type; - const int code = icmp_hdr(skb)->code; - struct sock *sk; - int harderr; - int err; - - sk = __udp4_lib_lookup(skb->dev->nd_net, iph->daddr, uh->dest, - iph->saddr, uh->source, skb->dev->ifindex, udptable); - if (sk == NULL) { - ICMP_INC_STATS_BH(ICMP_MIB_INERRORS); - return; /* No socket for error */ - } - - err = 0; - harderr = 0; - inet = inet_sk(sk); - - switch (type) { - default: - case ICMP_TIME_EXCEEDED: - err = EHOSTUNREACH; - break; - case ICMP_SOURCE_QUENCH: - goto out; - case ICMP_PARAMETERPROB: - err = EPROTO; - harderr = 1; - break; - case ICMP_DEST_UNREACH: - if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ - if (inet->pmtudisc != IP_PMTUDISC_DONT) { - err = EMSGSIZE; - harderr = 1; - break; - } - goto out; - } - err = EHOSTUNREACH; - if (code <= NR_ICMP_UNREACH) { - harderr = icmp_err_convert[code].fatal; - err = icmp_err_convert[code].errno; - } - break; - } - - /* - * RFC1122: OK. Passes ICMP errors back to application, as per - * 4.1.3.3. - */ - if (!inet->recverr) { - if (!harderr || sk->sk_state != TCP_ESTABLISHED) - goto out; - } else { - ip_icmp_error(sk, skb, err, uh->dest, info, (u8*)(uh+1)); - } - sk->sk_err = err; - sk->sk_error_report(sk); -out: - sock_put(sk); -} - -void udp_err(struct sk_buff *skb, u32 info) -{ - __udp4_lib_err(skb, info, udp_hash); -} - -/* - * Throw away all pending data and cancel the corking. Socket is locked. - */ -static void udp_flush_pending_frames(struct sock *sk) -{ - struct udp_sock *up = udp_sk(sk); - - if (up->pending) { - up->len = 0; - up->pending = 0; - ip_flush_pending_frames(sk); - } -} - -/** - * udp4_hwcsum_outgoing - handle outgoing HW checksumming - * @sk: socket we are sending on - * @skb: sk_buff containing the filled-in UDP header - * (checksum field must be zeroed out) - */ -static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, - __be32 src, __be32 dst, int len ) -{ - unsigned int offset; - struct udphdr *uh = udp_hdr(skb); - __wsum csum = 0; - - if (skb_queue_len(&sk->sk_write_queue) == 1) { - /* - * Only one fragment on the socket. - */ - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct udphdr, check); - uh->check = ~csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, 0); - } else { - /* - * HW-checksum won't work as there are two or more - * fragments on the socket so that all csums of sk_buffs - * should be together - */ - offset = skb_transport_offset(skb); - skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); - - skb->ip_summed = CHECKSUM_NONE; - - skb_queue_walk(&sk->sk_write_queue, skb) { - csum = csum_add(csum, skb->csum); - } - - uh->check = csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, csum); - if (uh->check == 0) - uh->check = CSUM_MANGLED_0; - } -} - -/* - * Push out all pending data as one UDP datagram. Socket is locked. - */ -static int udp_push_pending_frames(struct sock *sk) -{ - struct udp_sock *up = udp_sk(sk); - struct inet_sock *inet = inet_sk(sk); - struct flowi *fl = &inet->cork.fl; - struct sk_buff *skb; - struct udphdr *uh; - int err = 0; - int is_udplite = IS_UDPLITE(sk); - __wsum csum = 0; - - /* Grab the skbuff where UDP header space exists. */ - if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) - goto out; - - /* - * Create a UDP header - */ - uh = udp_hdr(skb); - uh->source = fl->fl_ip_sport; - uh->dest = fl->fl_ip_dport; - uh->len = htons(up->len); - uh->check = 0; - - if (is_udplite) /* UDP-Lite */ - csum = udplite_csum_outgoing(sk, skb); - - else if (sk->sk_no_check == UDP_CSUM_NOXMIT) { /* UDP csum disabled */ - - skb->ip_summed = CHECKSUM_NONE; - goto send; - - } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ - - udp4_hwcsum_outgoing(sk, skb, fl->fl4_src,fl->fl4_dst, up->len); - goto send; - - } else /* `normal' UDP */ - csum = udp_csum_outgoing(sk, skb); - - /* add protocol-dependent pseudo-header */ - uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst, up->len, - sk->sk_protocol, csum ); - if (uh->check == 0) - uh->check = CSUM_MANGLED_0; - -send: - err = ip_push_pending_frames(sk); -out: - up->len = 0; - up->pending = 0; - if (!err) - UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite); - return err; -} - -int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len) -{ - struct inet_sock *inet = inet_sk(sk); - struct udp_sock *up = udp_sk(sk); - int ulen = len; - struct ipcm_cookie ipc; - struct rtable *rt = NULL; - int free = 0; - int connected = 0; - __be32 daddr, faddr, saddr; - __be16 dport; - u8 tos; - int err, is_udplite = IS_UDPLITE(sk); - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; - int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); - - if (len > 0xFFFF) - return -EMSGSIZE; - - /* - * Check the flags. - */ - - if (msg->msg_flags&MSG_OOB) /* Mirror BSD error message compatibility */ - return -EOPNOTSUPP; - - ipc.opt = NULL; - - if (up->pending) { - /* - * There are pending frames. - * The socket lock must be held while it's corked. - */ - lock_sock(sk); - if (likely(up->pending)) { - if (unlikely(up->pending != AF_INET)) { - release_sock(sk); - return -EINVAL; - } - goto do_append_data; - } - release_sock(sk); - } - ulen += sizeof(struct udphdr); - - /* - * Get and verify the address. - */ - if (msg->msg_name) { - struct sockaddr_in * usin = (struct sockaddr_in*)msg->msg_name; - if (msg->msg_namelen < sizeof(*usin)) - return -EINVAL; - if (usin->sin_family != AF_INET) { - if (usin->sin_family != AF_UNSPEC) - return -EAFNOSUPPORT; - } - - daddr = usin->sin_addr.s_addr; - dport = usin->sin_port; - if (dport == 0) - return -EINVAL; - } else { - if (sk->sk_state != TCP_ESTABLISHED) - return -EDESTADDRREQ; - daddr = inet->daddr; - dport = inet->dport; - /* Open fast path for connected socket. - Route will not be used, if at least one option is set. - */ - connected = 1; - } - ipc.addr = inet->saddr; - - ipc.oif = sk->sk_bound_dev_if; - if (msg->msg_controllen) { - err = ip_cmsg_send(msg, &ipc); - if (err) - return err; - if (ipc.opt) - free = 1; - connected = 0; - } - if (!ipc.opt) - ipc.opt = inet->opt; - - saddr = ipc.addr; - ipc.addr = faddr = daddr; - - if (ipc.opt && ipc.opt->srr) { - if (!daddr) - return -EINVAL; - faddr = ipc.opt->faddr; - connected = 0; - } - tos = RT_TOS(inet->tos); - if (sock_flag(sk, SOCK_LOCALROUTE) || - (msg->msg_flags & MSG_DONTROUTE) || - (ipc.opt && ipc.opt->is_strictroute)) { - tos |= RTO_ONLINK; - connected = 0; - } - - if (ipv4_is_multicast(daddr)) { - if (!ipc.oif) - ipc.oif = inet->mc_index; - if (!saddr) - saddr = inet->mc_addr; - connected = 0; - } - - if (connected) - rt = (struct rtable*)sk_dst_check(sk, 0); - - if (rt == NULL) { - struct flowi fl = { .oif = ipc.oif, - .nl_u = { .ip4_u = - { .daddr = faddr, - .saddr = saddr, - .tos = tos } }, - .proto = sk->sk_protocol, - .uli_u = { .ports = - { .sport = inet->sport, - .dport = dport } } }; - security_sk_classify_flow(sk, &fl); - err = ip_route_output_flow(&init_net, &rt, &fl, sk, 1); - if (err) { - if (err == -ENETUNREACH) - IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); - goto out; - } - - err = -EACCES; - if ((rt->rt_flags & RTCF_BROADCAST) && - !sock_flag(sk, SOCK_BROADCAST)) - goto out; - if (connected) - sk_dst_set(sk, dst_clone(&rt->u.dst)); - } - - if (msg->msg_flags&MSG_CONFIRM) - goto do_confirm; -back_from_confirm: - - saddr = rt->rt_src; - if (!ipc.addr) - daddr = ipc.addr = rt->rt_dst; - - lock_sock(sk); - if (unlikely(up->pending)) { - /* The socket is already corked while preparing it. */ - /* ... which is an evident application bug. --ANK */ - release_sock(sk); - - LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n"); - err = -EINVAL; - goto out; - } - /* - * Now cork the socket to pend data. - */ - inet->cork.fl.fl4_dst = daddr; - inet->cork.fl.fl_ip_dport = dport; - inet->cork.fl.fl4_src = saddr; - inet->cork.fl.fl_ip_sport = inet->sport; - up->pending = AF_INET; - -do_append_data: - up->len += ulen; - getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; - err = ip_append_data(sk, getfrag, msg->msg_iov, ulen, - sizeof(struct udphdr), &ipc, rt, - corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); - if (err) - udp_flush_pending_frames(sk); - else if (!corkreq) - err = udp_push_pending_frames(sk); - else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) - up->pending = 0; - release_sock(sk); - -out: - ip_rt_put(rt); - if (free) - kfree(ipc.opt); - if (!err) - return len; - /* - * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting - * ENOBUFS might not be good (it's not tunable per se), but otherwise - * we don't have a good statistic (IpOutDiscards but it can be too many - * things). We could add another new stat but at least for now that - * seems like overkill. - */ - if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { - UDP_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite); - } - return err; - -do_confirm: - dst_confirm(&rt->u.dst); - if (!(msg->msg_flags&MSG_PROBE) || len) - goto back_from_confirm; - err = 0; - goto out; -} - -int udp_sendpage(struct sock *sk, struct page *page, int offset, - size_t size, int flags) -{ - struct udp_sock *up = udp_sk(sk); - int ret; - - if (!up->pending) { - struct msghdr msg = { .msg_flags = flags|MSG_MORE }; - - /* Call udp_sendmsg to specify destination address which - * sendpage interface can't pass. - * This will succeed only when the socket is connected. - */ - ret = udp_sendmsg(NULL, sk, &msg, 0); - if (ret < 0) - return ret; - } - - lock_sock(sk); - - if (unlikely(!up->pending)) { - release_sock(sk); - - LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 3\n"); - return -EINVAL; - } - - ret = ip_append_page(sk, page, offset, size, flags); - if (ret == -EOPNOTSUPP) { - release_sock(sk); - return sock_no_sendpage(sk->sk_socket, page, offset, - size, flags); - } - if (ret < 0) { - udp_flush_pending_frames(sk); - goto out; - } - - up->len += size; - if (!(up->corkflag || (flags&MSG_MORE))) - ret = udp_push_pending_frames(sk); - if (!ret) - ret = size; -out: - release_sock(sk); - return ret; -} - -/* - * This should be easy, if there is something there we - * return it, otherwise we block. - */ - -int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, int *addr_len) -{ - struct inet_sock *inet = inet_sk(sk); - struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; - struct sk_buff *skb; - unsigned int ulen, copied; - int peeked; - int err; - int is_udplite = IS_UDPLITE(sk); - - /* - * Check any passed addresses - */ - if (addr_len) - *addr_len=sizeof(*sin); - - if (flags & MSG_ERRQUEUE) - return ip_recv_error(sk, msg, len); - -try_again: - skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), - &peeked, &err); - if (!skb) - goto out; - - ulen = skb->len - sizeof(struct udphdr); - copied = len; - if (copied > ulen) - copied = ulen; - else if (copied < ulen) - msg->msg_flags |= MSG_TRUNC; - - /* - * If checksum is needed at all, try to do it while copying the - * data. If the data is truncated, or if we only want a partial - * coverage checksum (UDP-Lite), do it before the copy. - */ - - if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { - if (udp_lib_checksum_complete(skb)) - goto csum_copy_err; - } - - if (skb_csum_unnecessary(skb)) - err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, copied ); - else { - err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); - - if (err == -EINVAL) - goto csum_copy_err; - } - - if (err) - goto out_free; - - if (!peeked) - UDP_INC_STATS_USER(UDP_MIB_INDATAGRAMS, is_udplite); - - sock_recv_timestamp(msg, sk, skb); - - /* Copy the address. */ - if (sin) - { - sin->sin_family = AF_INET; - sin->sin_port = udp_hdr(skb)->source; - sin->sin_addr.s_addr = ip_hdr(skb)->saddr; - memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); - } - if (inet->cmsg_flags) - ip_cmsg_recv(msg, skb); - - err = copied; - if (flags & MSG_TRUNC) - err = ulen; - -out_free: - lock_sock(sk); - skb_free_datagram(sk, skb); - release_sock(sk); -out: - return err; - -csum_copy_err: - lock_sock(sk); - if (!skb_kill_datagram(sk, skb, flags)) - UDP_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite); - release_sock(sk); - - if (noblock) - return -EAGAIN; - goto try_again; -} - - -/* returns: - * -1: error - * 0: success - * >0: "udp encap" protocol resubmission - * - * Note that in the success and error cases, the skb is assumed to - * have either been requeued or freed. - */ -int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) -{ - struct udp_sock *up = udp_sk(sk); - int rc; - int is_udplite = IS_UDPLITE(sk); - - /* - * Charge it to the socket, dropping if the queue is full. - */ - if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) - goto drop; - nf_reset(skb); - - if (up->encap_type) { - /* - * This is an encapsulation socket so pass the skb to - * the socket's udp_encap_rcv() hook. Otherwise, just - * fall through and pass this up the UDP socket. - * up->encap_rcv() returns the following value: - * =0 if skb was successfully passed to the encap - * handler or was discarded by it. - * >0 if skb should be passed on to UDP. - * <0 if skb should be resubmitted as proto -N - */ - - /* if we're overly short, let UDP handle it */ - if (skb->len > sizeof(struct udphdr) && - up->encap_rcv != NULL) { - int ret; - - ret = (*up->encap_rcv)(sk, skb); - if (ret <= 0) { - UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, - is_udplite); - return -ret; - } - } - - /* FALLTHROUGH -- it's a UDP Packet */ - } - - /* - * UDP-Lite specific tests, ignored on UDP sockets - */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { - - /* - * MIB statistics other than incrementing the error count are - * disabled for the following two types of errors: these depend - * on the application settings, not on the functioning of the - * protocol stack as such. - * - * RFC 3828 here recommends (sec 3.3): "There should also be a - * way ... to ... at least let the receiving application block - * delivery of packets with coverage values less than a value - * provided by the application." - */ - if (up->pcrlen == 0) { /* full coverage was set */ - LIMIT_NETDEBUG(KERN_WARNING "UDPLITE: partial coverage " - "%d while full coverage %d requested\n", - UDP_SKB_CB(skb)->cscov, skb->len); - goto drop; - } - /* The next case involves violating the min. coverage requested - * by the receiver. This is subtle: if receiver wants x and x is - * greater than the buffersize/MTU then receiver will complain - * that it wants x while sender emits packets of smaller size y. - * Therefore the above ...()->partial_cov statement is essential. - */ - if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { - LIMIT_NETDEBUG(KERN_WARNING - "UDPLITE: coverage %d too small, need min %d\n", - UDP_SKB_CB(skb)->cscov, up->pcrlen); - goto drop; - } - } - - if (sk->sk_filter) { - if (udp_lib_checksum_complete(skb)) - goto drop; - } - - if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { - /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) - UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, is_udplite); - goto drop; - } - - return 0; - -drop: - UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite); - kfree_skb(skb); - return -1; -} - -/* - * Multicasts and broadcasts go to each listener. - * - * Note: called only from the BH handler context, - * so we don't need to lock the hashes. - */ -static int __udp4_lib_mcast_deliver(struct sk_buff *skb, - struct udphdr *uh, - __be32 saddr, __be32 daddr, - struct hlist_head udptable[]) -{ - struct sock *sk; - int dif; - - read_lock(&udp_hash_lock); - sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]); - dif = skb->dev->ifindex; - sk = udp_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif); - if (sk) { - struct sock *sknext = NULL; - - do { - struct sk_buff *skb1 = skb; - - sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr, - uh->source, saddr, dif); - if (sknext) - skb1 = skb_clone(skb, GFP_ATOMIC); - - if (skb1) { - int ret = 0; - - bh_lock_sock_nested(sk); - if (!sock_owned_by_user(sk)) - ret = udp_queue_rcv_skb(sk, skb1); - else - sk_add_backlog(sk, skb1); - bh_unlock_sock(sk); - - if (ret > 0) - /* we should probably re-process instead - * of dropping packets here. */ - kfree_skb(skb1); - } - sk = sknext; - } while (sknext); - } else - kfree_skb(skb); - read_unlock(&udp_hash_lock); - return 0; -} - -/* Initialize UDP checksum. If exited with zero value (success), - * CHECKSUM_UNNECESSARY means, that no more checks are required. - * Otherwise, csum completion requires chacksumming packet body, - * including udp header and folding it to skb->csum. - */ -static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, - int proto) -{ - const struct iphdr *iph; - int err; - - UDP_SKB_CB(skb)->partial_cov = 0; - UDP_SKB_CB(skb)->cscov = skb->len; - - if (IS_PROTO_UDPLITE(proto)) { - err = udplite_checksum_init(skb, uh); - if (err) - return err; - } - - iph = ip_hdr(skb); - if (uh->check == 0) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - } else if (skb->ip_summed == CHECKSUM_COMPLETE) { - if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len, - proto, skb->csum)) - skb->ip_summed = CHECKSUM_UNNECESSARY; - } - if (!skb_csum_unnecessary(skb)) - skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, - skb->len, proto, 0); - /* Probably, we should checksum udp header (it should be in cache - * in any case) and data in tiny packets (< rx copybreak). - */ - - return 0; -} - -/* - * All we need to do is get the socket, and then do a checksum. - */ - -int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], - int proto) -{ - struct sock *sk; - struct udphdr *uh = udp_hdr(skb); - unsigned short ulen; - struct rtable *rt = skb->rtable; - __be32 saddr = ip_hdr(skb)->saddr; - __be32 daddr = ip_hdr(skb)->daddr; - - /* - * Validate the packet. - */ - if (!pskb_may_pull(skb, sizeof(struct udphdr))) - goto drop; /* No space for header. */ - - ulen = ntohs(uh->len); - if (ulen > skb->len) - goto short_packet; - - if (IS_PROTO_UDPLITE(proto)) { - /* UDP validates ulen. */ - if (ulen < sizeof(*uh) || pskb_trim_rcsum(skb, ulen)) - goto short_packet; - uh = udp_hdr(skb); - } - - if (udp4_csum_init(skb, uh, proto)) - goto csum_error; - - if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) - return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable); - - sk = __udp4_lib_lookup(skb->dev->nd_net, saddr, uh->source, daddr, - uh->dest, inet_iif(skb), udptable); - - if (sk != NULL) { - int ret = 0; - bh_lock_sock_nested(sk); - if (!sock_owned_by_user(sk)) - ret = udp_queue_rcv_skb(sk, skb); - else - sk_add_backlog(sk, skb); - bh_unlock_sock(sk); - sock_put(sk); - - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ - if (ret > 0) - return -ret; - return 0; - } - - if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) - goto drop; - nf_reset(skb); - - /* No socket. Drop packet silently, if checksum is wrong */ - if (udp_lib_checksum_complete(skb)) - goto csum_error; - - UDP_INC_STATS_BH(UDP_MIB_NOPORTS, IS_PROTO_UDPLITE(proto)); - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); - - /* - * Hmm. We got an UDP packet to a port to which we - * don't wanna listen. Ignore it. - */ - kfree_skb(skb); - return 0; - -short_packet: - LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %u.%u.%u.%u:%u %d/%d to %u.%u.%u.%u:%u\n", - IS_PROTO_UDPLITE(proto) ? "-Lite" : "", - NIPQUAD(saddr), - ntohs(uh->source), - ulen, - skb->len, - NIPQUAD(daddr), - ntohs(uh->dest)); - goto drop; - -csum_error: - /* - * RFC1122: OK. Discards the bad packet silently (as far as - * the network is concerned, anyway) as per 4.1.3.4 (MUST). - */ - LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %d.%d.%d.%d:%d to %d.%d.%d.%d:%d ulen %d\n", - IS_PROTO_UDPLITE(proto) ? "-Lite" : "", - NIPQUAD(saddr), - ntohs(uh->source), - NIPQUAD(daddr), - ntohs(uh->dest), - ulen); -drop: - UDP_INC_STATS_BH(UDP_MIB_INERRORS, IS_PROTO_UDPLITE(proto)); - kfree_skb(skb); - return 0; -} - -int udp_rcv(struct sk_buff *skb) -{ - return __udp4_lib_rcv(skb, udp_hash, IPPROTO_UDP); -} - -int udp_destroy_sock(struct sock *sk) -{ - lock_sock(sk); - udp_flush_pending_frames(sk); - release_sock(sk); - return 0; -} - -int udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) -{ - if (IS_SOL_UDPFAMILY(level)) - return udp_lib_setsockopt(sk, level, optname, optval, optlen, - udp_push_pending_frames); - return ip_setsockopt(sk, level, optname, optval, optlen); -} - -#ifdef CONFIG_COMPAT -int compat_udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) -{ - if (IS_SOL_UDPFAMILY(level)) - return udp_lib_setsockopt(sk, level, optname, optval, optlen, - udp_push_pending_frames); - return compat_ip_setsockopt(sk, level, optname, optval, optlen); -} -#endif - -int udp_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - if (IS_SOL_UDPFAMILY(level)) - return udp_lib_getsockopt(sk, level, optname, optval, optlen); - return ip_getsockopt(sk, level, optname, optval, optlen); -} - -#ifdef CONFIG_COMPAT -int compat_udp_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - if (IS_SOL_UDPFAMILY(level)) - return udp_lib_getsockopt(sk, level, optname, optval, optlen); - return compat_ip_getsockopt(sk, level, optname, optval, optlen); -} -#endif - -/* ------------------------------------------------------------------------ */ -DEFINE_PROTO_INUSE(udp) - -struct proto udp_prot = { - .name = "UDP", - .owner = THIS_MODULE, - .close = udp_lib_close, - .connect = ip4_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = udp_ioctl, - .destroy = udp_destroy_sock, - .setsockopt = udp_setsockopt, - .getsockopt = udp_getsockopt, - .sendmsg = udp_sendmsg, - .recvmsg = udp_recvmsg, - .sendpage = udp_sendpage, - .backlog_rcv = udp_queue_rcv_skb, - .hash = udp_lib_hash, - .unhash = udp_lib_unhash, - .get_port = udp_v4_get_port, - .memory_allocated = &udp_memory_allocated, - .sysctl_mem = sysctl_udp_mem, - .sysctl_wmem = &sysctl_udp_wmem_min, - .sysctl_rmem = &sysctl_udp_rmem_min, - .obj_size = sizeof(struct udp_sock), -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_udp_setsockopt, - .compat_getsockopt = compat_udp_getsockopt, -#endif - REF_PROTO_INUSE(udp) -}; - -/* ------------------------------------------------------------------------ */ -static void udp4_format_sock(struct sock *sp, char *tmpbuf, int bucket) -{ - struct inet_sock *inet = inet_sk(sp); - __be32 dest = inet->daddr; - __be32 src = inet->rcv_saddr; - __u16 destp = ntohs(inet->dport); - __u16 srcp = ntohs(inet->sport); - - sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p", - bucket, src, srcp, dest, destp, sp->sk_state, - atomic_read(&sp->sk_wmem_alloc), - atomic_read(&sp->sk_rmem_alloc), - 0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp); -} - -int udp4_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) - seq_printf(seq, "%-127s\n", - " sl local_address rem_address st tx_queue " - "rx_queue tr tm->when retrnsmt uid timeout " - "inode"); - else { - char tmpbuf[129]; - struct udp_iter_state *state = seq->private; - - udp4_format_sock(v, tmpbuf, state->bucket); - seq_printf(seq, "%-127s\n", tmpbuf); - } - return 0; -} - -/* ------------------------------------------------------------------------ */ -#ifdef CONFIG_PROC_FS -static struct file_operations udp4_seq_fops; -static struct udp_seq_afinfo udp4_seq_afinfo = { - .owner = THIS_MODULE, - .name = "udp", - .family = AF_INET, - .hashtable = udp_hash, - .seq_show = udp4_seq_show, - .seq_fops = &udp4_seq_fops, -}; - -int __init udp4_proc_init(void) -{ - return udp_proc_register(&udp4_seq_afinfo); -} - -void udp4_proc_exit(void) -{ - udp_proc_unregister(&udp4_seq_afinfo); -} -#endif /* CONFIG_PROC_FS */ - -EXPORT_SYMBOL(udp_prot); -EXPORT_SYMBOL(udp_sendmsg); - diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c new file mode 100644 index 00000000000..d49c6d68c8a --- /dev/null +++ b/net/ipv4/udplite.c @@ -0,0 +1,121 @@ +/* + * UDPLITE An implementation of the UDP-Lite protocol (RFC 3828). + * + * Version: $Id: udplite.c,v 1.25 2006/10/19 07:22:36 gerrit Exp $ + * + * Authors: Gerrit Renker + * + * Changes: + * Fixes: + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include "udp_impl.h" +DEFINE_SNMP_STAT(struct udp_mib, udplite_statistics) __read_mostly; + +struct hlist_head udplite_hash[UDP_HTABLE_SIZE]; + +int udplite_get_port(struct sock *sk, unsigned short p, + int (*c)(const struct sock *, const struct sock *)) +{ + return __udp_lib_get_port(sk, p, udplite_hash, c); +} + +static int udplite_v4_get_port(struct sock *sk, unsigned short snum) +{ + return udplite_get_port(sk, snum, ipv4_rcv_saddr_equal); +} + +static int udplite_rcv(struct sk_buff *skb) +{ + return __udp4_lib_rcv(skb, udplite_hash, IPPROTO_UDPLITE); +} + +static void udplite_err(struct sk_buff *skb, u32 info) +{ + __udp4_lib_err(skb, info, udplite_hash); +} + +static struct net_protocol udplite_protocol = { + .handler = udplite_rcv, + .err_handler = udplite_err, + .no_policy = 1, +}; + +DEFINE_PROTO_INUSE(udplite) + +struct proto udplite_prot = { + .name = "UDP-Lite", + .owner = THIS_MODULE, + .close = udp_lib_close, + .connect = ip4_datagram_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .init = udplite_sk_init, + .destroy = udp_destroy_sock, + .setsockopt = udp_setsockopt, + .getsockopt = udp_getsockopt, + .sendmsg = udp_sendmsg, + .recvmsg = udp_recvmsg, + .sendpage = udp_sendpage, + .backlog_rcv = udp_queue_rcv_skb, + .hash = udp_lib_hash, + .unhash = udp_lib_unhash, + .get_port = udplite_v4_get_port, + .obj_size = sizeof(struct udp_sock), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_udp_setsockopt, + .compat_getsockopt = compat_udp_getsockopt, +#endif + REF_PROTO_INUSE(udplite) +}; + +static struct inet_protosw udplite4_protosw = { + .type = SOCK_DGRAM, + .protocol = IPPROTO_UDPLITE, + .prot = &udplite_prot, + .ops = &inet_dgram_ops, + .capability = -1, + .no_check = 0, /* must checksum (RFC 3828) */ + .flags = INET_PROTOSW_PERMANENT, +}; + +#ifdef CONFIG_PROC_FS +static struct file_operations udplite4_seq_fops; +static struct udp_seq_afinfo udplite4_seq_afinfo = { + .owner = THIS_MODULE, + .name = "udplite", + .family = AF_INET, + .hashtable = udplite_hash, + .seq_show = udp4_seq_show, + .seq_fops = &udplite4_seq_fops, +}; +#endif + +void __init udplite4_register(void) +{ + if (proto_register(&udplite_prot, 1)) + goto out_register_err; + + if (inet_add_protocol(&udplite_protocol, IPPROTO_UDPLITE) < 0) + goto out_unregister_proto; + + inet_register_protosw(&udplite4_protosw); + +#ifdef CONFIG_PROC_FS + if (udp_proc_register(&udplite4_seq_afinfo)) /* udplite4_proc_init() */ + printk(KERN_ERR "%s: Cannot register /proc!\n", __func__); +#endif + return; + +out_unregister_proto: + proto_unregister(&udplite_prot); +out_register_err: + printk(KERN_CRIT "%s: Cannot add UDP-Lite protocol.\n", __func__); +} + +EXPORT_SYMBOL(udplite_hash); +EXPORT_SYMBOL(udplite_prot); +EXPORT_SYMBOL(udplite_get_port); diff --git a/net/ipv4/udplite_ipv4.c b/net/ipv4/udplite_ipv4.c deleted file mode 100644 index d49c6d68c8a..00000000000 --- a/net/ipv4/udplite_ipv4.c +++ /dev/null @@ -1,121 +0,0 @@ -/* - * UDPLITE An implementation of the UDP-Lite protocol (RFC 3828). - * - * Version: $Id: udplite.c,v 1.25 2006/10/19 07:22:36 gerrit Exp $ - * - * Authors: Gerrit Renker - * - * Changes: - * Fixes: - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ -#include "udp_impl.h" -DEFINE_SNMP_STAT(struct udp_mib, udplite_statistics) __read_mostly; - -struct hlist_head udplite_hash[UDP_HTABLE_SIZE]; - -int udplite_get_port(struct sock *sk, unsigned short p, - int (*c)(const struct sock *, const struct sock *)) -{ - return __udp_lib_get_port(sk, p, udplite_hash, c); -} - -static int udplite_v4_get_port(struct sock *sk, unsigned short snum) -{ - return udplite_get_port(sk, snum, ipv4_rcv_saddr_equal); -} - -static int udplite_rcv(struct sk_buff *skb) -{ - return __udp4_lib_rcv(skb, udplite_hash, IPPROTO_UDPLITE); -} - -static void udplite_err(struct sk_buff *skb, u32 info) -{ - __udp4_lib_err(skb, info, udplite_hash); -} - -static struct net_protocol udplite_protocol = { - .handler = udplite_rcv, - .err_handler = udplite_err, - .no_policy = 1, -}; - -DEFINE_PROTO_INUSE(udplite) - -struct proto udplite_prot = { - .name = "UDP-Lite", - .owner = THIS_MODULE, - .close = udp_lib_close, - .connect = ip4_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = udp_ioctl, - .init = udplite_sk_init, - .destroy = udp_destroy_sock, - .setsockopt = udp_setsockopt, - .getsockopt = udp_getsockopt, - .sendmsg = udp_sendmsg, - .recvmsg = udp_recvmsg, - .sendpage = udp_sendpage, - .backlog_rcv = udp_queue_rcv_skb, - .hash = udp_lib_hash, - .unhash = udp_lib_unhash, - .get_port = udplite_v4_get_port, - .obj_size = sizeof(struct udp_sock), -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_udp_setsockopt, - .compat_getsockopt = compat_udp_getsockopt, -#endif - REF_PROTO_INUSE(udplite) -}; - -static struct inet_protosw udplite4_protosw = { - .type = SOCK_DGRAM, - .protocol = IPPROTO_UDPLITE, - .prot = &udplite_prot, - .ops = &inet_dgram_ops, - .capability = -1, - .no_check = 0, /* must checksum (RFC 3828) */ - .flags = INET_PROTOSW_PERMANENT, -}; - -#ifdef CONFIG_PROC_FS -static struct file_operations udplite4_seq_fops; -static struct udp_seq_afinfo udplite4_seq_afinfo = { - .owner = THIS_MODULE, - .name = "udplite", - .family = AF_INET, - .hashtable = udplite_hash, - .seq_show = udp4_seq_show, - .seq_fops = &udplite4_seq_fops, -}; -#endif - -void __init udplite4_register(void) -{ - if (proto_register(&udplite_prot, 1)) - goto out_register_err; - - if (inet_add_protocol(&udplite_protocol, IPPROTO_UDPLITE) < 0) - goto out_unregister_proto; - - inet_register_protosw(&udplite4_protosw); - -#ifdef CONFIG_PROC_FS - if (udp_proc_register(&udplite4_seq_afinfo)) /* udplite4_proc_init() */ - printk(KERN_ERR "%s: Cannot register /proc!\n", __func__); -#endif - return; - -out_unregister_proto: - proto_unregister(&udplite_prot); -out_register_err: - printk(KERN_CRIT "%s: Cannot add UDP-Lite protocol.\n", __func__); -} - -EXPORT_SYMBOL(udplite_hash); -EXPORT_SYMBOL(udplite_prot); -EXPORT_SYMBOL(udplite_get_port); diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 107051f7c22..ae14617e607 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -6,7 +6,7 @@ obj-$(CONFIG_IPV6) += ipv6.o ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ addrlabel.o \ - route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp_ipv6.o \ + route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ raw.o protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o @@ -17,7 +17,6 @@ ipv6-$(CONFIG_NETFILTER) += netfilter.o ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o ipv6-$(CONFIG_PROC_FS) += proc.o ipv6-$(CONFIG_SYN_COOKIES) += syncookies.o -ipv6-$(CONFIG_IP_UDPLITE) += udplite_ipv6.o ipv6-objs += $(ipv6-y) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index afe9276d042..730a861b8f4 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -813,16 +813,12 @@ static int __init init_ipv6_mibs(void) goto err_icmpmsg_mib; if (snmp_mib_init((void **)udp_stats_in6, sizeof (struct udp_mib)) < 0) goto err_udp_mib; -#ifdef CONFIG_IP_UDPLITE if (snmp_mib_init((void **)udplite_stats_in6, sizeof (struct udp_mib)) < 0) goto err_udplite_mib; -#endif return 0; -#ifdef CONFIG_IP_UDPLITE err_udplite_mib: -#endif snmp_mib_free((void **)udp_stats_in6); err_udp_mib: snmp_mib_free((void **)icmpv6msg_statistics); @@ -841,9 +837,7 @@ static void cleanup_ipv6_mibs(void) snmp_mib_free((void **)icmpv6_statistics); snmp_mib_free((void **)icmpv6msg_statistics); snmp_mib_free((void **)udp_stats_in6); -#ifdef CONFIG_IP_UDPLITE snmp_mib_free((void **)udplite_stats_in6); -#endif } static int inet6_net_init(struct net *net) @@ -888,11 +882,9 @@ static int __init inet6_init(void) if (err) goto out_unregister_tcp_proto; -#ifdef CONFIG_IP_UDPLITE err = proto_register(&udplitev6_prot, 1); if (err) goto out_unregister_udp_proto; -#endif err = proto_register(&rawv6_prot, 1); if (err) @@ -1063,10 +1055,8 @@ out_sock_register_fail: out_unregister_raw_proto: proto_unregister(&rawv6_prot); out_unregister_udplite_proto: -#ifdef CONFIG_IP_UDPLITE proto_unregister(&udplitev6_prot); out_unregister_udp_proto: -#endif proto_unregister(&udpv6_prot); out_unregister_tcp_proto: proto_unregister(&tcpv6_prot); @@ -1085,9 +1075,7 @@ static void __exit inet6_exit(void) ipv6_sysctl_unregister(); #endif udpv6_exit(); -#ifdef CONFIG_IP_UDPLITE udplitev6_exit(); -#endif tcpv6_exit(); /* Cleanup code parts. */ @@ -1117,9 +1105,7 @@ static void __exit inet6_exit(void) unregister_pernet_subsys(&inet6_net_ops); cleanup_ipv6_mibs(); proto_unregister(&rawv6_prot); -#ifdef CONFIG_IP_UDPLITE proto_unregister(&udplitev6_prot); -#endif proto_unregister(&udpv6_prot); proto_unregister(&tcpv6_prot); } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 3bbfdff698d..5eea6fa506e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -127,9 +127,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, struct sk_buff *pktopt; if (sk->sk_protocol != IPPROTO_UDP && -#ifdef CONFIG_IP_UDPLITE sk->sk_protocol != IPPROTO_UDPLITE && -#endif sk->sk_protocol != IPPROTO_TCP) break; @@ -169,7 +167,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, } else { struct proto *prot = &udp_prot; - if (IS_PROTO_UDPLITE(sk->sk_protocol)) + if (sk->sk_protocol == IPPROTO_UDPLITE) prot = &udplite_prot; local_bh_disable(); sock_prot_inuse_add(sk->sk_prot, -1); @@ -734,9 +732,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, switch (optname) { case IPV6_ADDRFORM: if (sk->sk_protocol != IPPROTO_UDP && -#ifdef CONFIG_IP_UDPLITE sk->sk_protocol != IPPROTO_UDPLITE && -#endif sk->sk_protocol != IPPROTO_TCP) return -EINVAL; if (sk->sk_state != TCP_ESTABLISHED) diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 2453f2229ef..8a5be290c71 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -39,10 +39,8 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v) sock_prot_inuse_get(&tcpv6_prot)); seq_printf(seq, "UDP6: inuse %d\n", sock_prot_inuse_get(&udpv6_prot)); -#ifdef CONFIG_IP_UDPLITE seq_printf(seq, "UDPLITE6: inuse %d\n", sock_prot_inuse_get(&udplitev6_prot)); -#endif seq_printf(seq, "RAW6: inuse %d\n", sock_prot_inuse_get(&rawv6_prot)); seq_printf(seq, "FRAG6: inuse %d memory %d\n", @@ -113,7 +111,6 @@ static struct snmp_mib snmp6_udp6_list[] = { SNMP_MIB_SENTINEL }; -#ifdef CONFIG_IP_UDPLITE static struct snmp_mib snmp6_udplite6_list[] = { SNMP_MIB_ITEM("UdpLite6InDatagrams", UDP_MIB_INDATAGRAMS), SNMP_MIB_ITEM("UdpLite6NoPorts", UDP_MIB_NOPORTS), @@ -121,7 +118,6 @@ static struct snmp_mib snmp6_udplite6_list[] = { SNMP_MIB_ITEM("UdpLite6OutDatagrams", UDP_MIB_OUTDATAGRAMS), SNMP_MIB_SENTINEL }; -#endif static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib) { @@ -180,9 +176,7 @@ static int snmp6_seq_show(struct seq_file *seq, void *v) snmp6_seq_show_item(seq, (void **)icmpv6_statistics, snmp6_icmp6_list); snmp6_seq_show_icmpv6msg(seq, (void **)icmpv6msg_statistics); snmp6_seq_show_item(seq, (void **)udp_stats_in6, snmp6_udp6_list); -#ifdef CONFIG_IP_UDPLITE snmp6_seq_show_item(seq, (void **)udplite_stats_in6, snmp6_udplite6_list); -#endif } return 0; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c new file mode 100644 index 00000000000..53739de829d --- /dev/null +++ b/net/ipv6/udp.c @@ -0,0 +1,1065 @@ +/* + * UDP over IPv6 + * Linux INET6 implementation + * + * Authors: + * Pedro Roque + * + * Based on linux/ipv4/udp.c + * + * $Id: udp.c,v 1.65 2002/02/01 22:01:04 davem Exp $ + * + * Fixes: + * Hideaki YOSHIFUJI : sin6_scope_id support + * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which + * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind + * a single port at the same time. + * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data + * YOSHIFUJI Hideaki @USAGI: convert /proc/net/udp6 to seq_file. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include "udp_impl.h" + +static inline int udp_v6_get_port(struct sock *sk, unsigned short snum) +{ + return udp_get_port(sk, snum, ipv6_rcv_saddr_equal); +} + +static struct sock *__udp6_lib_lookup(struct net *net, + struct in6_addr *saddr, __be16 sport, + struct in6_addr *daddr, __be16 dport, + int dif, struct hlist_head udptable[]) +{ + struct sock *sk, *result = NULL; + struct hlist_node *node; + unsigned short hnum = ntohs(dport); + int badness = -1; + + read_lock(&udp_hash_lock); + sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) { + struct inet_sock *inet = inet_sk(sk); + + if (sk->sk_net == net && sk->sk_hash == hnum && + sk->sk_family == PF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + int score = 0; + if (inet->dport) { + if (inet->dport != sport) + continue; + score++; + } + if (!ipv6_addr_any(&np->rcv_saddr)) { + if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + continue; + score++; + } + if (!ipv6_addr_any(&np->daddr)) { + if (!ipv6_addr_equal(&np->daddr, saddr)) + continue; + score++; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + continue; + score++; + } + if (score == 4) { + result = sk; + break; + } else if (score > badness) { + result = sk; + badness = score; + } + } + } + if (result) + sock_hold(result); + read_unlock(&udp_hash_lock); + return result; +} + +/* + * This should be easy, if there is something there we + * return it, otherwise we block. + */ + +int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, + struct msghdr *msg, size_t len, + int noblock, int flags, int *addr_len) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct inet_sock *inet = inet_sk(sk); + struct sk_buff *skb; + unsigned int ulen, copied; + int peeked; + int err; + int is_udplite = IS_UDPLITE(sk); + + if (addr_len) + *addr_len=sizeof(struct sockaddr_in6); + + if (flags & MSG_ERRQUEUE) + return ipv6_recv_error(sk, msg, len); + +try_again: + skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), + &peeked, &err); + if (!skb) + goto out; + + ulen = skb->len - sizeof(struct udphdr); + copied = len; + if (copied > ulen) + copied = ulen; + else if (copied < ulen) + msg->msg_flags |= MSG_TRUNC; + + /* + * If checksum is needed at all, try to do it while copying the + * data. If the data is truncated, or if we only want a partial + * coverage checksum (UDP-Lite), do it before the copy. + */ + + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (udp_lib_checksum_complete(skb)) + goto csum_copy_err; + } + + if (skb_csum_unnecessary(skb)) + err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), + msg->msg_iov, copied ); + else { + err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); + if (err == -EINVAL) + goto csum_copy_err; + } + if (err) + goto out_free; + + if (!peeked) + UDP6_INC_STATS_USER(UDP_MIB_INDATAGRAMS, is_udplite); + + sock_recv_timestamp(msg, sk, skb); + + /* Copy the address. */ + if (msg->msg_name) { + struct sockaddr_in6 *sin6; + + sin6 = (struct sockaddr_in6 *) msg->msg_name; + sin6->sin6_family = AF_INET6; + sin6->sin6_port = udp_hdr(skb)->source; + sin6->sin6_flowinfo = 0; + sin6->sin6_scope_id = 0; + + if (skb->protocol == htons(ETH_P_IP)) + ipv6_addr_set(&sin6->sin6_addr, 0, 0, + htonl(0xffff), ip_hdr(skb)->saddr); + else { + ipv6_addr_copy(&sin6->sin6_addr, + &ipv6_hdr(skb)->saddr); + if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) + sin6->sin6_scope_id = IP6CB(skb)->iif; + } + + } + if (skb->protocol == htons(ETH_P_IP)) { + if (inet->cmsg_flags) + ip_cmsg_recv(msg, skb); + } else { + if (np->rxopt.all) + datagram_recv_ctl(sk, msg, skb); + } + + err = copied; + if (flags & MSG_TRUNC) + err = ulen; + +out_free: + lock_sock(sk); + skb_free_datagram(sk, skb); + release_sock(sk); +out: + return err; + +csum_copy_err: + lock_sock(sk); + if (!skb_kill_datagram(sk, skb, flags)) + UDP6_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite); + release_sock(sk); + + if (flags & MSG_DONTWAIT) + return -EAGAIN; + goto try_again; +} + +void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + int type, int code, int offset, __be32 info, + struct hlist_head udptable[] ) +{ + struct ipv6_pinfo *np; + struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; + struct in6_addr *saddr = &hdr->saddr; + struct in6_addr *daddr = &hdr->daddr; + struct udphdr *uh = (struct udphdr*)(skb->data+offset); + struct sock *sk; + int err; + + sk = __udp6_lib_lookup(skb->dev->nd_net, daddr, uh->dest, + saddr, uh->source, inet6_iif(skb), udptable); + if (sk == NULL) + return; + + np = inet6_sk(sk); + + if (!icmpv6_err_convert(type, code, &err) && !np->recverr) + goto out; + + if (sk->sk_state != TCP_ESTABLISHED && !np->recverr) + goto out; + + if (np->recverr) + ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1)); + + sk->sk_err = err; + sk->sk_error_report(sk); +out: + sock_put(sk); +} + +static __inline__ void udpv6_err(struct sk_buff *skb, + struct inet6_skb_parm *opt, int type, + int code, int offset, __be32 info ) +{ + __udp6_lib_err(skb, opt, type, code, offset, info, udp_hash); +} + +int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) +{ + struct udp_sock *up = udp_sk(sk); + int rc; + int is_udplite = IS_UDPLITE(sk); + + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) + goto drop; + + /* + * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). + */ + if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + + if (up->pcrlen == 0) { /* full coverage was set */ + LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: partial coverage" + " %d while full coverage %d requested\n", + UDP_SKB_CB(skb)->cscov, skb->len); + goto drop; + } + if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { + LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: coverage %d " + "too small, need min %d\n", + UDP_SKB_CB(skb)->cscov, up->pcrlen); + goto drop; + } + } + + if (sk->sk_filter) { + if (udp_lib_checksum_complete(skb)) + goto drop; + } + + if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { + /* Note that an ENOMEM error is charged twice */ + if (rc == -ENOMEM) + UDP6_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, is_udplite); + goto drop; + } + + return 0; +drop: + UDP6_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite); + kfree_skb(skb); + return -1; +} + +static struct sock *udp_v6_mcast_next(struct sock *sk, + __be16 loc_port, struct in6_addr *loc_addr, + __be16 rmt_port, struct in6_addr *rmt_addr, + int dif) +{ + struct hlist_node *node; + struct sock *s = sk; + unsigned short num = ntohs(loc_port); + + sk_for_each_from(s, node) { + struct inet_sock *inet = inet_sk(s); + + if (s->sk_hash == num && s->sk_family == PF_INET6) { + struct ipv6_pinfo *np = inet6_sk(s); + if (inet->dport) { + if (inet->dport != rmt_port) + continue; + } + if (!ipv6_addr_any(&np->daddr) && + !ipv6_addr_equal(&np->daddr, rmt_addr)) + continue; + + if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif) + continue; + + if (!ipv6_addr_any(&np->rcv_saddr)) { + if (!ipv6_addr_equal(&np->rcv_saddr, loc_addr)) + continue; + } + if (!inet6_mc_check(s, loc_addr, rmt_addr)) + continue; + return s; + } + } + return NULL; +} + +/* + * Note: called only from the BH handler context, + * so we don't need to lock the hashes. + */ +static int __udp6_lib_mcast_deliver(struct sk_buff *skb, struct in6_addr *saddr, + struct in6_addr *daddr, struct hlist_head udptable[]) +{ + struct sock *sk, *sk2; + const struct udphdr *uh = udp_hdr(skb); + int dif; + + read_lock(&udp_hash_lock); + sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]); + dif = inet6_iif(skb); + sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif); + if (!sk) { + kfree_skb(skb); + goto out; + } + + sk2 = sk; + while ((sk2 = udp_v6_mcast_next(sk_next(sk2), uh->dest, daddr, + uh->source, saddr, dif))) { + struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC); + if (buff) { + bh_lock_sock_nested(sk2); + if (!sock_owned_by_user(sk2)) + udpv6_queue_rcv_skb(sk2, buff); + else + sk_add_backlog(sk2, buff); + bh_unlock_sock(sk2); + } + } + bh_lock_sock_nested(sk); + if (!sock_owned_by_user(sk)) + udpv6_queue_rcv_skb(sk, skb); + else + sk_add_backlog(sk, skb); + bh_unlock_sock(sk); +out: + read_unlock(&udp_hash_lock); + return 0; +} + +static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, + int proto) +{ + int err; + + UDP_SKB_CB(skb)->partial_cov = 0; + UDP_SKB_CB(skb)->cscov = skb->len; + + if (proto == IPPROTO_UDPLITE) { + err = udplite_checksum_init(skb, uh); + if (err) + return err; + } + + if (uh->check == 0) { + /* RFC 2460 section 8.1 says that we SHOULD log + this error. Well, it is reasonable. + */ + LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n"); + return 1; + } + if (skb->ip_summed == CHECKSUM_COMPLETE && + !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, + skb->len, proto, skb->csum)) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + if (!skb_csum_unnecessary(skb)) + skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len, proto, 0)); + + return 0; +} + +int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], + int proto) +{ + struct sock *sk; + struct udphdr *uh; + struct net_device *dev = skb->dev; + struct in6_addr *saddr, *daddr; + u32 ulen = 0; + + if (!pskb_may_pull(skb, sizeof(struct udphdr))) + goto short_packet; + + saddr = &ipv6_hdr(skb)->saddr; + daddr = &ipv6_hdr(skb)->daddr; + uh = udp_hdr(skb); + + ulen = ntohs(uh->len); + if (ulen > skb->len) + goto short_packet; + + if (proto == IPPROTO_UDP) { + /* UDP validates ulen. */ + + /* Check for jumbo payload */ + if (ulen == 0) + ulen = skb->len; + + if (ulen < sizeof(*uh)) + goto short_packet; + + if (ulen < skb->len) { + if (pskb_trim_rcsum(skb, ulen)) + goto short_packet; + saddr = &ipv6_hdr(skb)->saddr; + daddr = &ipv6_hdr(skb)->daddr; + uh = udp_hdr(skb); + } + } + + if (udp6_csum_init(skb, uh, proto)) + goto discard; + + /* + * Multicast receive code + */ + if (ipv6_addr_is_multicast(daddr)) + return __udp6_lib_mcast_deliver(skb, saddr, daddr, udptable); + + /* Unicast */ + + /* + * check socket cache ... must talk to Alan about his plans + * for sock caches... i'll skip this for now. + */ + sk = __udp6_lib_lookup(skb->dev->nd_net, saddr, uh->source, + daddr, uh->dest, inet6_iif(skb), udptable); + + if (sk == NULL) { + if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto discard; + + if (udp_lib_checksum_complete(skb)) + goto discard; + UDP6_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); + + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev); + + kfree_skb(skb); + return 0; + } + + /* deliver */ + + bh_lock_sock_nested(sk); + if (!sock_owned_by_user(sk)) + udpv6_queue_rcv_skb(sk, skb); + else + sk_add_backlog(sk, skb); + bh_unlock_sock(sk); + sock_put(sk); + return 0; + +short_packet: + LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: %d/%u\n", + proto == IPPROTO_UDPLITE ? "-Lite" : "", + ulen, skb->len); + +discard: + UDP6_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); + kfree_skb(skb); + return 0; +} + +static __inline__ int udpv6_rcv(struct sk_buff *skb) +{ + return __udp6_lib_rcv(skb, udp_hash, IPPROTO_UDP); +} + +/* + * Throw away all pending data and cancel the corking. Socket is locked. + */ +static void udp_v6_flush_pending_frames(struct sock *sk) +{ + struct udp_sock *up = udp_sk(sk); + + if (up->pending) { + up->len = 0; + up->pending = 0; + ip6_flush_pending_frames(sk); + } +} + +/* + * Sending + */ + +static int udp_v6_push_pending_frames(struct sock *sk) +{ + struct sk_buff *skb; + struct udphdr *uh; + struct udp_sock *up = udp_sk(sk); + struct inet_sock *inet = inet_sk(sk); + struct flowi *fl = &inet->cork.fl; + int err = 0; + int is_udplite = IS_UDPLITE(sk); + __wsum csum = 0; + + /* Grab the skbuff where UDP header space exists. */ + if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) + goto out; + + /* + * Create a UDP header + */ + uh = udp_hdr(skb); + uh->source = fl->fl_ip_sport; + uh->dest = fl->fl_ip_dport; + uh->len = htons(up->len); + uh->check = 0; + + if (is_udplite) + csum = udplite_csum_outgoing(sk, skb); + else + csum = udp_csum_outgoing(sk, skb); + + /* add protocol-dependent pseudo-header */ + uh->check = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst, + up->len, fl->proto, csum ); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + + err = ip6_push_pending_frames(sk); +out: + up->len = 0; + up->pending = 0; + if (!err) + UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite); + return err; +} + +int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, + struct msghdr *msg, size_t len) +{ + struct ipv6_txoptions opt_space; + struct udp_sock *up = udp_sk(sk); + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) msg->msg_name; + struct in6_addr *daddr, *final_p = NULL, final; + struct ipv6_txoptions *opt = NULL; + struct ip6_flowlabel *flowlabel = NULL; + struct flowi fl; + struct dst_entry *dst; + int addr_len = msg->msg_namelen; + int ulen = len; + int hlimit = -1; + int tclass = -1; + int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int err; + int connected = 0; + int is_udplite = IS_UDPLITE(sk); + int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); + + /* destination address check */ + if (sin6) { + if (addr_len < offsetof(struct sockaddr, sa_data)) + return -EINVAL; + + switch (sin6->sin6_family) { + case AF_INET6: + if (addr_len < SIN6_LEN_RFC2133) + return -EINVAL; + daddr = &sin6->sin6_addr; + break; + case AF_INET: + goto do_udp_sendmsg; + case AF_UNSPEC: + msg->msg_name = sin6 = NULL; + msg->msg_namelen = addr_len = 0; + daddr = NULL; + break; + default: + return -EINVAL; + } + } else if (!up->pending) { + if (sk->sk_state != TCP_ESTABLISHED) + return -EDESTADDRREQ; + daddr = &np->daddr; + } else + daddr = NULL; + + if (daddr) { + if (ipv6_addr_v4mapped(daddr)) { + struct sockaddr_in sin; + sin.sin_family = AF_INET; + sin.sin_port = sin6 ? sin6->sin6_port : inet->dport; + sin.sin_addr.s_addr = daddr->s6_addr32[3]; + msg->msg_name = &sin; + msg->msg_namelen = sizeof(sin); +do_udp_sendmsg: + if (__ipv6_only_sock(sk)) + return -ENETUNREACH; + return udp_sendmsg(iocb, sk, msg, len); + } + } + + if (up->pending == AF_INET) + return udp_sendmsg(iocb, sk, msg, len); + + /* Rough check on arithmetic overflow, + better check is made in ip6_append_data(). + */ + if (len > INT_MAX - sizeof(struct udphdr)) + return -EMSGSIZE; + + if (up->pending) { + /* + * There are pending frames. + * The socket lock must be held while it's corked. + */ + lock_sock(sk); + if (likely(up->pending)) { + if (unlikely(up->pending != AF_INET6)) { + release_sock(sk); + return -EAFNOSUPPORT; + } + dst = NULL; + goto do_append_data; + } + release_sock(sk); + } + ulen += sizeof(struct udphdr); + + memset(&fl, 0, sizeof(fl)); + + if (sin6) { + if (sin6->sin6_port == 0) + return -EINVAL; + + fl.fl_ip_dport = sin6->sin6_port; + daddr = &sin6->sin6_addr; + + if (np->sndflow) { + fl.fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; + if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); + if (flowlabel == NULL) + return -EINVAL; + daddr = &flowlabel->dst; + } + } + + /* + * Otherwise it will be difficult to maintain + * sk->sk_dst_cache. + */ + if (sk->sk_state == TCP_ESTABLISHED && + ipv6_addr_equal(daddr, &np->daddr)) + daddr = &np->daddr; + + if (addr_len >= sizeof(struct sockaddr_in6) && + sin6->sin6_scope_id && + ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL) + fl.oif = sin6->sin6_scope_id; + } else { + if (sk->sk_state != TCP_ESTABLISHED) + return -EDESTADDRREQ; + + fl.fl_ip_dport = inet->dport; + daddr = &np->daddr; + fl.fl6_flowlabel = np->flow_label; + connected = 1; + } + + if (!fl.oif) + fl.oif = sk->sk_bound_dev_if; + + if (msg->msg_controllen) { + opt = &opt_space; + memset(opt, 0, sizeof(struct ipv6_txoptions)); + opt->tot_len = sizeof(*opt); + + err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); + if (err < 0) { + fl6_sock_release(flowlabel); + return err; + } + if ((fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { + flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); + if (flowlabel == NULL) + return -EINVAL; + } + if (!(opt->opt_nflen|opt->opt_flen)) + opt = NULL; + connected = 0; + } + if (opt == NULL) + opt = np->opt; + if (flowlabel) + opt = fl6_merge_options(&opt_space, flowlabel, opt); + opt = ipv6_fixup_options(&opt_space, opt); + + fl.proto = sk->sk_protocol; + ipv6_addr_copy(&fl.fl6_dst, daddr); + if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr)) + ipv6_addr_copy(&fl.fl6_src, &np->saddr); + fl.fl_ip_sport = inet->sport; + + /* merge ip6_build_xmit from ip6_output */ + if (opt && opt->srcrt) { + struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; + ipv6_addr_copy(&final, &fl.fl6_dst); + ipv6_addr_copy(&fl.fl6_dst, rt0->addr); + final_p = &final; + connected = 0; + } + + if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) { + fl.oif = np->mcast_oif; + connected = 0; + } + + security_sk_classify_flow(sk, &fl); + + err = ip6_sk_dst_lookup(sk, &dst, &fl); + if (err) + goto out; + if (final_p) + ipv6_addr_copy(&fl.fl6_dst, final_p); + + if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) { + if (err == -EREMOTE) + err = ip6_dst_blackhole(sk, &dst, &fl); + if (err < 0) + goto out; + } + + if (hlimit < 0) { + if (ipv6_addr_is_multicast(&fl.fl6_dst)) + hlimit = np->mcast_hops; + else + hlimit = np->hop_limit; + if (hlimit < 0) + hlimit = dst_metric(dst, RTAX_HOPLIMIT); + if (hlimit < 0) + hlimit = ipv6_get_hoplimit(dst->dev); + } + + if (tclass < 0) { + tclass = np->tclass; + if (tclass < 0) + tclass = 0; + } + + if (msg->msg_flags&MSG_CONFIRM) + goto do_confirm; +back_from_confirm: + + lock_sock(sk); + if (unlikely(up->pending)) { + /* The socket is already corked while preparing it. */ + /* ... which is an evident application bug. --ANK */ + release_sock(sk); + + LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n"); + err = -EINVAL; + goto out; + } + + up->pending = AF_INET6; + +do_append_data: + up->len += ulen; + getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; + err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, + sizeof(struct udphdr), hlimit, tclass, opt, &fl, + (struct rt6_info*)dst, + corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); + if (err) + udp_v6_flush_pending_frames(sk); + else if (!corkreq) + err = udp_v6_push_pending_frames(sk); + else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) + up->pending = 0; + + if (dst) { + if (connected) { + ip6_dst_store(sk, dst, + ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ? + &np->daddr : NULL, +#ifdef CONFIG_IPV6_SUBTREES + ipv6_addr_equal(&fl.fl6_src, &np->saddr) ? + &np->saddr : +#endif + NULL); + } else { + dst_release(dst); + } + } + + if (err > 0) + err = np->recverr ? net_xmit_errno(err) : 0; + release_sock(sk); +out: + fl6_sock_release(flowlabel); + if (!err) + return len; + /* + * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting + * ENOBUFS might not be good (it's not tunable per se), but otherwise + * we don't have a good statistic (IpOutDiscards but it can be too many + * things). We could add another new stat but at least for now that + * seems like overkill. + */ + if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { + UDP6_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite); + } + return err; + +do_confirm: + dst_confirm(dst); + if (!(msg->msg_flags&MSG_PROBE) || len) + goto back_from_confirm; + err = 0; + goto out; +} + +int udpv6_destroy_sock(struct sock *sk) +{ + lock_sock(sk); + udp_v6_flush_pending_frames(sk); + release_sock(sk); + + inet6_destroy_sock(sk); + + return 0; +} + +/* + * Socket option code for UDP + */ +int udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_setsockopt(sk, level, optname, optval, optlen, + udp_v6_push_pending_frames); + return ipv6_setsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_setsockopt(sk, level, optname, optval, optlen, + udp_v6_push_pending_frames); + return compat_ipv6_setsockopt(sk, level, optname, optval, optlen); +} +#endif + +int udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_getsockopt(sk, level, optname, optval, optlen); + return ipv6_getsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_getsockopt(sk, level, optname, optval, optlen); + return compat_ipv6_getsockopt(sk, level, optname, optval, optlen); +} +#endif + +static struct inet6_protocol udpv6_protocol = { + .handler = udpv6_rcv, + .err_handler = udpv6_err, + .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, +}; + +/* ------------------------------------------------------------------------ */ +#ifdef CONFIG_PROC_FS + +static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket) +{ + struct inet_sock *inet = inet_sk(sp); + struct ipv6_pinfo *np = inet6_sk(sp); + struct in6_addr *dest, *src; + __u16 destp, srcp; + + dest = &np->daddr; + src = &np->rcv_saddr; + destp = ntohs(inet->dport); + srcp = ntohs(inet->sport); + seq_printf(seq, + "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p\n", + bucket, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp, + sp->sk_state, + atomic_read(&sp->sk_wmem_alloc), + atomic_read(&sp->sk_rmem_alloc), + 0, 0L, 0, + sock_i_uid(sp), 0, + sock_i_ino(sp), + atomic_read(&sp->sk_refcnt), sp); +} + +int udp6_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) + seq_printf(seq, + " sl " + "local_address " + "remote_address " + "st tx_queue rx_queue tr tm->when retrnsmt" + " uid timeout inode\n"); + else + udp6_sock_seq_show(seq, v, ((struct udp_iter_state *)seq->private)->bucket); + return 0; +} + +static struct file_operations udp6_seq_fops; +static struct udp_seq_afinfo udp6_seq_afinfo = { + .owner = THIS_MODULE, + .name = "udp6", + .family = AF_INET6, + .hashtable = udp_hash, + .seq_show = udp6_seq_show, + .seq_fops = &udp6_seq_fops, +}; + +int __init udp6_proc_init(void) +{ + return udp_proc_register(&udp6_seq_afinfo); +} + +void udp6_proc_exit(void) { + udp_proc_unregister(&udp6_seq_afinfo); +} +#endif /* CONFIG_PROC_FS */ + +/* ------------------------------------------------------------------------ */ + +DEFINE_PROTO_INUSE(udpv6) + +struct proto udpv6_prot = { + .name = "UDPv6", + .owner = THIS_MODULE, + .close = udp_lib_close, + .connect = ip6_datagram_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .destroy = udpv6_destroy_sock, + .setsockopt = udpv6_setsockopt, + .getsockopt = udpv6_getsockopt, + .sendmsg = udpv6_sendmsg, + .recvmsg = udpv6_recvmsg, + .backlog_rcv = udpv6_queue_rcv_skb, + .hash = udp_lib_hash, + .unhash = udp_lib_unhash, + .get_port = udp_v6_get_port, + .memory_allocated = &udp_memory_allocated, + .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem = &sysctl_udp_wmem_min, + .sysctl_rmem = &sysctl_udp_rmem_min, + .obj_size = sizeof(struct udp6_sock), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_udpv6_setsockopt, + .compat_getsockopt = compat_udpv6_getsockopt, +#endif + REF_PROTO_INUSE(udpv6) +}; + +static struct inet_protosw udpv6_protosw = { + .type = SOCK_DGRAM, + .protocol = IPPROTO_UDP, + .prot = &udpv6_prot, + .ops = &inet6_dgram_ops, + .capability =-1, + .no_check = UDP_CSUM_DEFAULT, + .flags = INET_PROTOSW_PERMANENT, +}; + + +int __init udpv6_init(void) +{ + int ret; + + ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP); + if (ret) + goto out; + + ret = inet6_register_protosw(&udpv6_protosw); + if (ret) + goto out_udpv6_protocol; +out: + return ret; + +out_udpv6_protocol: + inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); + goto out; +} + +void udpv6_exit(void) +{ + inet6_unregister_protosw(&udpv6_protosw); + inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); +} diff --git a/net/ipv6/udp_ipv6.c b/net/ipv6/udp_ipv6.c deleted file mode 100644 index 55feac7ba71..00000000000 --- a/net/ipv6/udp_ipv6.c +++ /dev/null @@ -1,1065 +0,0 @@ -/* - * UDP over IPv6 - * Linux INET6 implementation - * - * Authors: - * Pedro Roque - * - * Based on linux/ipv4/udp.c - * - * $Id: udp.c,v 1.65 2002/02/01 22:01:04 davem Exp $ - * - * Fixes: - * Hideaki YOSHIFUJI : sin6_scope_id support - * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which - * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind - * a single port at the same time. - * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data - * YOSHIFUJI Hideaki @USAGI: convert /proc/net/udp6 to seq_file. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include "udp_impl.h" - -static inline int udp_v6_get_port(struct sock *sk, unsigned short snum) -{ - return udp_get_port(sk, snum, ipv6_rcv_saddr_equal); -} - -static struct sock *__udp6_lib_lookup(struct net *net, - struct in6_addr *saddr, __be16 sport, - struct in6_addr *daddr, __be16 dport, - int dif, struct hlist_head udptable[]) -{ - struct sock *sk, *result = NULL; - struct hlist_node *node; - unsigned short hnum = ntohs(dport); - int badness = -1; - - read_lock(&udp_hash_lock); - sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) { - struct inet_sock *inet = inet_sk(sk); - - if (sk->sk_net == net && sk->sk_hash == hnum && - sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - int score = 0; - if (inet->dport) { - if (inet->dport != sport) - continue; - score++; - } - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) - continue; - score++; - } - if (!ipv6_addr_any(&np->daddr)) { - if (!ipv6_addr_equal(&np->daddr, saddr)) - continue; - score++; - } - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - continue; - score++; - } - if (score == 4) { - result = sk; - break; - } else if (score > badness) { - result = sk; - badness = score; - } - } - } - if (result) - sock_hold(result); - read_unlock(&udp_hash_lock); - return result; -} - -/* - * This should be easy, if there is something there we - * return it, otherwise we block. - */ - -int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, - int noblock, int flags, int *addr_len) -{ - struct ipv6_pinfo *np = inet6_sk(sk); - struct inet_sock *inet = inet_sk(sk); - struct sk_buff *skb; - unsigned int ulen, copied; - int peeked; - int err; - int is_udplite = IS_UDPLITE(sk); - - if (addr_len) - *addr_len=sizeof(struct sockaddr_in6); - - if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); - -try_again: - skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), - &peeked, &err); - if (!skb) - goto out; - - ulen = skb->len - sizeof(struct udphdr); - copied = len; - if (copied > ulen) - copied = ulen; - else if (copied < ulen) - msg->msg_flags |= MSG_TRUNC; - - /* - * If checksum is needed at all, try to do it while copying the - * data. If the data is truncated, or if we only want a partial - * coverage checksum (UDP-Lite), do it before the copy. - */ - - if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { - if (udp_lib_checksum_complete(skb)) - goto csum_copy_err; - } - - if (skb_csum_unnecessary(skb)) - err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, copied ); - else { - err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); - if (err == -EINVAL) - goto csum_copy_err; - } - if (err) - goto out_free; - - if (!peeked) - UDP6_INC_STATS_USER(UDP_MIB_INDATAGRAMS, is_udplite); - - sock_recv_timestamp(msg, sk, skb); - - /* Copy the address. */ - if (msg->msg_name) { - struct sockaddr_in6 *sin6; - - sin6 = (struct sockaddr_in6 *) msg->msg_name; - sin6->sin6_family = AF_INET6; - sin6->sin6_port = udp_hdr(skb)->source; - sin6->sin6_flowinfo = 0; - sin6->sin6_scope_id = 0; - - if (skb->protocol == htons(ETH_P_IP)) - ipv6_addr_set(&sin6->sin6_addr, 0, 0, - htonl(0xffff), ip_hdr(skb)->saddr); - else { - ipv6_addr_copy(&sin6->sin6_addr, - &ipv6_hdr(skb)->saddr); - if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) - sin6->sin6_scope_id = IP6CB(skb)->iif; - } - - } - if (skb->protocol == htons(ETH_P_IP)) { - if (inet->cmsg_flags) - ip_cmsg_recv(msg, skb); - } else { - if (np->rxopt.all) - datagram_recv_ctl(sk, msg, skb); - } - - err = copied; - if (flags & MSG_TRUNC) - err = ulen; - -out_free: - lock_sock(sk); - skb_free_datagram(sk, skb); - release_sock(sk); -out: - return err; - -csum_copy_err: - lock_sock(sk); - if (!skb_kill_datagram(sk, skb, flags)) - UDP6_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite); - release_sock(sk); - - if (flags & MSG_DONTWAIT) - return -EAGAIN; - goto try_again; -} - -void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info, - struct hlist_head udptable[] ) -{ - struct ipv6_pinfo *np; - struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; - struct in6_addr *saddr = &hdr->saddr; - struct in6_addr *daddr = &hdr->daddr; - struct udphdr *uh = (struct udphdr*)(skb->data+offset); - struct sock *sk; - int err; - - sk = __udp6_lib_lookup(skb->dev->nd_net, daddr, uh->dest, - saddr, uh->source, inet6_iif(skb), udptable); - if (sk == NULL) - return; - - np = inet6_sk(sk); - - if (!icmpv6_err_convert(type, code, &err) && !np->recverr) - goto out; - - if (sk->sk_state != TCP_ESTABLISHED && !np->recverr) - goto out; - - if (np->recverr) - ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1)); - - sk->sk_err = err; - sk->sk_error_report(sk); -out: - sock_put(sk); -} - -static __inline__ void udpv6_err(struct sk_buff *skb, - struct inet6_skb_parm *opt, int type, - int code, int offset, __be32 info ) -{ - __udp6_lib_err(skb, opt, type, code, offset, info, udp_hash); -} - -int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) -{ - struct udp_sock *up = udp_sk(sk); - int rc; - int is_udplite = IS_UDPLITE(sk); - - if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) - goto drop; - - /* - * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). - */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { - - if (up->pcrlen == 0) { /* full coverage was set */ - LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: partial coverage" - " %d while full coverage %d requested\n", - UDP_SKB_CB(skb)->cscov, skb->len); - goto drop; - } - if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { - LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: coverage %d " - "too small, need min %d\n", - UDP_SKB_CB(skb)->cscov, up->pcrlen); - goto drop; - } - } - - if (sk->sk_filter) { - if (udp_lib_checksum_complete(skb)) - goto drop; - } - - if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { - /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) - UDP6_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, is_udplite); - goto drop; - } - - return 0; -drop: - UDP6_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite); - kfree_skb(skb); - return -1; -} - -static struct sock *udp_v6_mcast_next(struct sock *sk, - __be16 loc_port, struct in6_addr *loc_addr, - __be16 rmt_port, struct in6_addr *rmt_addr, - int dif) -{ - struct hlist_node *node; - struct sock *s = sk; - unsigned short num = ntohs(loc_port); - - sk_for_each_from(s, node) { - struct inet_sock *inet = inet_sk(s); - - if (s->sk_hash == num && s->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(s); - if (inet->dport) { - if (inet->dport != rmt_port) - continue; - } - if (!ipv6_addr_any(&np->daddr) && - !ipv6_addr_equal(&np->daddr, rmt_addr)) - continue; - - if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif) - continue; - - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, loc_addr)) - continue; - } - if (!inet6_mc_check(s, loc_addr, rmt_addr)) - continue; - return s; - } - } - return NULL; -} - -/* - * Note: called only from the BH handler context, - * so we don't need to lock the hashes. - */ -static int __udp6_lib_mcast_deliver(struct sk_buff *skb, struct in6_addr *saddr, - struct in6_addr *daddr, struct hlist_head udptable[]) -{ - struct sock *sk, *sk2; - const struct udphdr *uh = udp_hdr(skb); - int dif; - - read_lock(&udp_hash_lock); - sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]); - dif = inet6_iif(skb); - sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif); - if (!sk) { - kfree_skb(skb); - goto out; - } - - sk2 = sk; - while ((sk2 = udp_v6_mcast_next(sk_next(sk2), uh->dest, daddr, - uh->source, saddr, dif))) { - struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC); - if (buff) { - bh_lock_sock_nested(sk2); - if (!sock_owned_by_user(sk2)) - udpv6_queue_rcv_skb(sk2, buff); - else - sk_add_backlog(sk2, buff); - bh_unlock_sock(sk2); - } - } - bh_lock_sock_nested(sk); - if (!sock_owned_by_user(sk)) - udpv6_queue_rcv_skb(sk, skb); - else - sk_add_backlog(sk, skb); - bh_unlock_sock(sk); -out: - read_unlock(&udp_hash_lock); - return 0; -} - -static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, - int proto) -{ - int err; - - UDP_SKB_CB(skb)->partial_cov = 0; - UDP_SKB_CB(skb)->cscov = skb->len; - - if (IS_PROTO_UDPLITE(proto)) { - err = udplite_checksum_init(skb, uh); - if (err) - return err; - } - - if (uh->check == 0) { - /* RFC 2460 section 8.1 says that we SHOULD log - this error. Well, it is reasonable. - */ - LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n"); - return 1; - } - if (skb->ip_summed == CHECKSUM_COMPLETE && - !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, - skb->len, proto, skb->csum)) - skb->ip_summed = CHECKSUM_UNNECESSARY; - - if (!skb_csum_unnecessary(skb)) - skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len, proto, 0)); - - return 0; -} - -int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], - int proto) -{ - struct sock *sk; - struct udphdr *uh; - struct net_device *dev = skb->dev; - struct in6_addr *saddr, *daddr; - u32 ulen = 0; - - if (!pskb_may_pull(skb, sizeof(struct udphdr))) - goto short_packet; - - saddr = &ipv6_hdr(skb)->saddr; - daddr = &ipv6_hdr(skb)->daddr; - uh = udp_hdr(skb); - - ulen = ntohs(uh->len); - if (ulen > skb->len) - goto short_packet; - - if (proto == IPPROTO_UDP) { - /* UDP validates ulen. */ - - /* Check for jumbo payload */ - if (ulen == 0) - ulen = skb->len; - - if (ulen < sizeof(*uh)) - goto short_packet; - - if (ulen < skb->len) { - if (pskb_trim_rcsum(skb, ulen)) - goto short_packet; - saddr = &ipv6_hdr(skb)->saddr; - daddr = &ipv6_hdr(skb)->daddr; - uh = udp_hdr(skb); - } - } - - if (udp6_csum_init(skb, uh, proto)) - goto discard; - - /* - * Multicast receive code - */ - if (ipv6_addr_is_multicast(daddr)) - return __udp6_lib_mcast_deliver(skb, saddr, daddr, udptable); - - /* Unicast */ - - /* - * check socket cache ... must talk to Alan about his plans - * for sock caches... i'll skip this for now. - */ - sk = __udp6_lib_lookup(skb->dev->nd_net, saddr, uh->source, - daddr, uh->dest, inet6_iif(skb), udptable); - - if (sk == NULL) { - if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) - goto discard; - - if (udp_lib_checksum_complete(skb)) - goto discard; - UDP6_INC_STATS_BH(UDP_MIB_NOPORTS, IS_PROTO_UDPLITE(proto)); - - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev); - - kfree_skb(skb); - return 0; - } - - /* deliver */ - - bh_lock_sock_nested(sk); - if (!sock_owned_by_user(sk)) - udpv6_queue_rcv_skb(sk, skb); - else - sk_add_backlog(sk, skb); - bh_unlock_sock(sk); - sock_put(sk); - return 0; - -short_packet: - LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: %d/%u\n", - IS_PROTO_UDPLITE(proto) ? "-Lite" : "", - ulen, skb->len); - -discard: - UDP6_INC_STATS_BH(UDP_MIB_INERRORS, IS_PROTO_UDPLITE(proto)); - kfree_skb(skb); - return 0; -} - -static __inline__ int udpv6_rcv(struct sk_buff *skb) -{ - return __udp6_lib_rcv(skb, udp_hash, IPPROTO_UDP); -} - -/* - * Throw away all pending data and cancel the corking. Socket is locked. - */ -static void udp_v6_flush_pending_frames(struct sock *sk) -{ - struct udp_sock *up = udp_sk(sk); - - if (up->pending) { - up->len = 0; - up->pending = 0; - ip6_flush_pending_frames(sk); - } -} - -/* - * Sending - */ - -static int udp_v6_push_pending_frames(struct sock *sk) -{ - struct sk_buff *skb; - struct udphdr *uh; - struct udp_sock *up = udp_sk(sk); - struct inet_sock *inet = inet_sk(sk); - struct flowi *fl = &inet->cork.fl; - int err = 0; - int is_udplite = IS_UDPLITE(sk); - __wsum csum = 0; - - /* Grab the skbuff where UDP header space exists. */ - if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) - goto out; - - /* - * Create a UDP header - */ - uh = udp_hdr(skb); - uh->source = fl->fl_ip_sport; - uh->dest = fl->fl_ip_dport; - uh->len = htons(up->len); - uh->check = 0; - - if (is_udplite) - csum = udplite_csum_outgoing(sk, skb); - else - csum = udp_csum_outgoing(sk, skb); - - /* add protocol-dependent pseudo-header */ - uh->check = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst, - up->len, fl->proto, csum ); - if (uh->check == 0) - uh->check = CSUM_MANGLED_0; - - err = ip6_push_pending_frames(sk); -out: - up->len = 0; - up->pending = 0; - if (!err) - UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite); - return err; -} - -int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len) -{ - struct ipv6_txoptions opt_space; - struct udp_sock *up = udp_sk(sk); - struct inet_sock *inet = inet_sk(sk); - struct ipv6_pinfo *np = inet6_sk(sk); - struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) msg->msg_name; - struct in6_addr *daddr, *final_p = NULL, final; - struct ipv6_txoptions *opt = NULL; - struct ip6_flowlabel *flowlabel = NULL; - struct flowi fl; - struct dst_entry *dst; - int addr_len = msg->msg_namelen; - int ulen = len; - int hlimit = -1; - int tclass = -1; - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; - int err; - int connected = 0; - int is_udplite = IS_UDPLITE(sk); - int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); - - /* destination address check */ - if (sin6) { - if (addr_len < offsetof(struct sockaddr, sa_data)) - return -EINVAL; - - switch (sin6->sin6_family) { - case AF_INET6: - if (addr_len < SIN6_LEN_RFC2133) - return -EINVAL; - daddr = &sin6->sin6_addr; - break; - case AF_INET: - goto do_udp_sendmsg; - case AF_UNSPEC: - msg->msg_name = sin6 = NULL; - msg->msg_namelen = addr_len = 0; - daddr = NULL; - break; - default: - return -EINVAL; - } - } else if (!up->pending) { - if (sk->sk_state != TCP_ESTABLISHED) - return -EDESTADDRREQ; - daddr = &np->daddr; - } else - daddr = NULL; - - if (daddr) { - if (ipv6_addr_v4mapped(daddr)) { - struct sockaddr_in sin; - sin.sin_family = AF_INET; - sin.sin_port = sin6 ? sin6->sin6_port : inet->dport; - sin.sin_addr.s_addr = daddr->s6_addr32[3]; - msg->msg_name = &sin; - msg->msg_namelen = sizeof(sin); -do_udp_sendmsg: - if (__ipv6_only_sock(sk)) - return -ENETUNREACH; - return udp_sendmsg(iocb, sk, msg, len); - } - } - - if (up->pending == AF_INET) - return udp_sendmsg(iocb, sk, msg, len); - - /* Rough check on arithmetic overflow, - better check is made in ip6_append_data(). - */ - if (len > INT_MAX - sizeof(struct udphdr)) - return -EMSGSIZE; - - if (up->pending) { - /* - * There are pending frames. - * The socket lock must be held while it's corked. - */ - lock_sock(sk); - if (likely(up->pending)) { - if (unlikely(up->pending != AF_INET6)) { - release_sock(sk); - return -EAFNOSUPPORT; - } - dst = NULL; - goto do_append_data; - } - release_sock(sk); - } - ulen += sizeof(struct udphdr); - - memset(&fl, 0, sizeof(fl)); - - if (sin6) { - if (sin6->sin6_port == 0) - return -EINVAL; - - fl.fl_ip_dport = sin6->sin6_port; - daddr = &sin6->sin6_addr; - - if (np->sndflow) { - fl.fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; - if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) { - flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); - if (flowlabel == NULL) - return -EINVAL; - daddr = &flowlabel->dst; - } - } - - /* - * Otherwise it will be difficult to maintain - * sk->sk_dst_cache. - */ - if (sk->sk_state == TCP_ESTABLISHED && - ipv6_addr_equal(daddr, &np->daddr)) - daddr = &np->daddr; - - if (addr_len >= sizeof(struct sockaddr_in6) && - sin6->sin6_scope_id && - ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL) - fl.oif = sin6->sin6_scope_id; - } else { - if (sk->sk_state != TCP_ESTABLISHED) - return -EDESTADDRREQ; - - fl.fl_ip_dport = inet->dport; - daddr = &np->daddr; - fl.fl6_flowlabel = np->flow_label; - connected = 1; - } - - if (!fl.oif) - fl.oif = sk->sk_bound_dev_if; - - if (msg->msg_controllen) { - opt = &opt_space; - memset(opt, 0, sizeof(struct ipv6_txoptions)); - opt->tot_len = sizeof(*opt); - - err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); - if (err < 0) { - fl6_sock_release(flowlabel); - return err; - } - if ((fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { - flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); - if (flowlabel == NULL) - return -EINVAL; - } - if (!(opt->opt_nflen|opt->opt_flen)) - opt = NULL; - connected = 0; - } - if (opt == NULL) - opt = np->opt; - if (flowlabel) - opt = fl6_merge_options(&opt_space, flowlabel, opt); - opt = ipv6_fixup_options(&opt_space, opt); - - fl.proto = sk->sk_protocol; - ipv6_addr_copy(&fl.fl6_dst, daddr); - if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.fl_ip_sport = inet->sport; - - /* merge ip6_build_xmit from ip6_output */ - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - connected = 0; - } - - if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) { - fl.oif = np->mcast_oif; - connected = 0; - } - - security_sk_classify_flow(sk, &fl); - - err = ip6_sk_dst_lookup(sk, &dst, &fl); - if (err) - goto out; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) { - if (err == -EREMOTE) - err = ip6_dst_blackhole(sk, &dst, &fl); - if (err < 0) - goto out; - } - - if (hlimit < 0) { - if (ipv6_addr_is_multicast(&fl.fl6_dst)) - hlimit = np->mcast_hops; - else - hlimit = np->hop_limit; - if (hlimit < 0) - hlimit = dst_metric(dst, RTAX_HOPLIMIT); - if (hlimit < 0) - hlimit = ipv6_get_hoplimit(dst->dev); - } - - if (tclass < 0) { - tclass = np->tclass; - if (tclass < 0) - tclass = 0; - } - - if (msg->msg_flags&MSG_CONFIRM) - goto do_confirm; -back_from_confirm: - - lock_sock(sk); - if (unlikely(up->pending)) { - /* The socket is already corked while preparing it. */ - /* ... which is an evident application bug. --ANK */ - release_sock(sk); - - LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n"); - err = -EINVAL; - goto out; - } - - up->pending = AF_INET6; - -do_append_data: - up->len += ulen; - getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; - err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, - sizeof(struct udphdr), hlimit, tclass, opt, &fl, - (struct rt6_info*)dst, - corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); - if (err) - udp_v6_flush_pending_frames(sk); - else if (!corkreq) - err = udp_v6_push_pending_frames(sk); - else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) - up->pending = 0; - - if (dst) { - if (connected) { - ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ? - &np->daddr : NULL, -#ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_equal(&fl.fl6_src, &np->saddr) ? - &np->saddr : -#endif - NULL); - } else { - dst_release(dst); - } - } - - if (err > 0) - err = np->recverr ? net_xmit_errno(err) : 0; - release_sock(sk); -out: - fl6_sock_release(flowlabel); - if (!err) - return len; - /* - * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting - * ENOBUFS might not be good (it's not tunable per se), but otherwise - * we don't have a good statistic (IpOutDiscards but it can be too many - * things). We could add another new stat but at least for now that - * seems like overkill. - */ - if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { - UDP6_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite); - } - return err; - -do_confirm: - dst_confirm(dst); - if (!(msg->msg_flags&MSG_PROBE) || len) - goto back_from_confirm; - err = 0; - goto out; -} - -int udpv6_destroy_sock(struct sock *sk) -{ - lock_sock(sk); - udp_v6_flush_pending_frames(sk); - release_sock(sk); - - inet6_destroy_sock(sk); - - return 0; -} - -/* - * Socket option code for UDP - */ -int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) -{ - if (IS_SOL_UDPFAMILY(level)) - return udp_lib_setsockopt(sk, level, optname, optval, optlen, - udp_v6_push_pending_frames); - return ipv6_setsockopt(sk, level, optname, optval, optlen); -} - -#ifdef CONFIG_COMPAT -int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) -{ - if (IS_SOL_UDPFAMILY(level)) - return udp_lib_setsockopt(sk, level, optname, optval, optlen, - udp_v6_push_pending_frames); - return compat_ipv6_setsockopt(sk, level, optname, optval, optlen); -} -#endif - -int udpv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - if (IS_SOL_UDPFAMILY(level)) - return udp_lib_getsockopt(sk, level, optname, optval, optlen); - return ipv6_getsockopt(sk, level, optname, optval, optlen); -} - -#ifdef CONFIG_COMPAT -int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - if (IS_SOL_UDPFAMILY(level)) - return udp_lib_getsockopt(sk, level, optname, optval, optlen); - return compat_ipv6_getsockopt(sk, level, optname, optval, optlen); -} -#endif - -static struct inet6_protocol udpv6_protocol = { - .handler = udpv6_rcv, - .err_handler = udpv6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, -}; - -/* ------------------------------------------------------------------------ */ -#ifdef CONFIG_PROC_FS - -static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket) -{ - struct inet_sock *inet = inet_sk(sp); - struct ipv6_pinfo *np = inet6_sk(sp); - struct in6_addr *dest, *src; - __u16 destp, srcp; - - dest = &np->daddr; - src = &np->rcv_saddr; - destp = ntohs(inet->dport); - srcp = ntohs(inet->sport); - seq_printf(seq, - "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p\n", - bucket, - src->s6_addr32[0], src->s6_addr32[1], - src->s6_addr32[2], src->s6_addr32[3], srcp, - dest->s6_addr32[0], dest->s6_addr32[1], - dest->s6_addr32[2], dest->s6_addr32[3], destp, - sp->sk_state, - atomic_read(&sp->sk_wmem_alloc), - atomic_read(&sp->sk_rmem_alloc), - 0, 0L, 0, - sock_i_uid(sp), 0, - sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp); -} - -int udp6_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) - seq_printf(seq, - " sl " - "local_address " - "remote_address " - "st tx_queue rx_queue tr tm->when retrnsmt" - " uid timeout inode\n"); - else - udp6_sock_seq_show(seq, v, ((struct udp_iter_state *)seq->private)->bucket); - return 0; -} - -static struct file_operations udp6_seq_fops; -static struct udp_seq_afinfo udp6_seq_afinfo = { - .owner = THIS_MODULE, - .name = "udp6", - .family = AF_INET6, - .hashtable = udp_hash, - .seq_show = udp6_seq_show, - .seq_fops = &udp6_seq_fops, -}; - -int __init udp6_proc_init(void) -{ - return udp_proc_register(&udp6_seq_afinfo); -} - -void udp6_proc_exit(void) { - udp_proc_unregister(&udp6_seq_afinfo); -} -#endif /* CONFIG_PROC_FS */ - -/* ------------------------------------------------------------------------ */ - -DEFINE_PROTO_INUSE(udpv6) - -struct proto udpv6_prot = { - .name = "UDPv6", - .owner = THIS_MODULE, - .close = udp_lib_close, - .connect = ip6_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = udp_ioctl, - .destroy = udpv6_destroy_sock, - .setsockopt = udpv6_setsockopt, - .getsockopt = udpv6_getsockopt, - .sendmsg = udpv6_sendmsg, - .recvmsg = udpv6_recvmsg, - .backlog_rcv = udpv6_queue_rcv_skb, - .hash = udp_lib_hash, - .unhash = udp_lib_unhash, - .get_port = udp_v6_get_port, - .memory_allocated = &udp_memory_allocated, - .sysctl_mem = sysctl_udp_mem, - .sysctl_wmem = &sysctl_udp_wmem_min, - .sysctl_rmem = &sysctl_udp_rmem_min, - .obj_size = sizeof(struct udp6_sock), -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_udpv6_setsockopt, - .compat_getsockopt = compat_udpv6_getsockopt, -#endif - REF_PROTO_INUSE(udpv6) -}; - -static struct inet_protosw udpv6_protosw = { - .type = SOCK_DGRAM, - .protocol = IPPROTO_UDP, - .prot = &udpv6_prot, - .ops = &inet6_dgram_ops, - .capability =-1, - .no_check = UDP_CSUM_DEFAULT, - .flags = INET_PROTOSW_PERMANENT, -}; - - -int __init udpv6_init(void) -{ - int ret; - - ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP); - if (ret) - goto out; - - ret = inet6_register_protosw(&udpv6_protosw); - if (ret) - goto out_udpv6_protocol; -out: - return ret; - -out_udpv6_protocol: - inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); - goto out; -} - -void udpv6_exit(void) -{ - inet6_unregister_protosw(&udpv6_protosw); - inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); -} diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c new file mode 100644 index 00000000000..87d4202522e --- /dev/null +++ b/net/ipv6/udplite.c @@ -0,0 +1,125 @@ +/* + * UDPLITEv6 An implementation of the UDP-Lite protocol over IPv6. + * See also net/ipv4/udplite.c + * + * Version: $Id: udplite.c,v 1.9 2006/10/19 08:28:10 gerrit Exp $ + * + * Authors: Gerrit Renker + * + * Changes: + * Fixes: + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include "udp_impl.h" + +DEFINE_SNMP_STAT(struct udp_mib, udplite_stats_in6) __read_mostly; + +static int udplitev6_rcv(struct sk_buff *skb) +{ + return __udp6_lib_rcv(skb, udplite_hash, IPPROTO_UDPLITE); +} + +static void udplitev6_err(struct sk_buff *skb, + struct inet6_skb_parm *opt, + int type, int code, int offset, __be32 info) +{ + __udp6_lib_err(skb, opt, type, code, offset, info, udplite_hash); +} + +static struct inet6_protocol udplitev6_protocol = { + .handler = udplitev6_rcv, + .err_handler = udplitev6_err, + .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, +}; + +static int udplite_v6_get_port(struct sock *sk, unsigned short snum) +{ + return udplite_get_port(sk, snum, ipv6_rcv_saddr_equal); +} + +DEFINE_PROTO_INUSE(udplitev6) + +struct proto udplitev6_prot = { + .name = "UDPLITEv6", + .owner = THIS_MODULE, + .close = udp_lib_close, + .connect = ip6_datagram_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .init = udplite_sk_init, + .destroy = udpv6_destroy_sock, + .setsockopt = udpv6_setsockopt, + .getsockopt = udpv6_getsockopt, + .sendmsg = udpv6_sendmsg, + .recvmsg = udpv6_recvmsg, + .backlog_rcv = udpv6_queue_rcv_skb, + .hash = udp_lib_hash, + .unhash = udp_lib_unhash, + .get_port = udplite_v6_get_port, + .obj_size = sizeof(struct udp6_sock), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_udpv6_setsockopt, + .compat_getsockopt = compat_udpv6_getsockopt, +#endif + REF_PROTO_INUSE(udplitev6) +}; + +static struct inet_protosw udplite6_protosw = { + .type = SOCK_DGRAM, + .protocol = IPPROTO_UDPLITE, + .prot = &udplitev6_prot, + .ops = &inet6_dgram_ops, + .capability = -1, + .no_check = 0, + .flags = INET_PROTOSW_PERMANENT, +}; + +int __init udplitev6_init(void) +{ + int ret; + + ret = inet6_add_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); + if (ret) + goto out; + + ret = inet6_register_protosw(&udplite6_protosw); + if (ret) + goto out_udplitev6_protocol; +out: + return ret; + +out_udplitev6_protocol: + inet6_del_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); + goto out; +} + +void udplitev6_exit(void) +{ + inet6_unregister_protosw(&udplite6_protosw); + inet6_del_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); +} + +#ifdef CONFIG_PROC_FS +static struct file_operations udplite6_seq_fops; +static struct udp_seq_afinfo udplite6_seq_afinfo = { + .owner = THIS_MODULE, + .name = "udplite6", + .family = AF_INET6, + .hashtable = udplite_hash, + .seq_show = udp6_seq_show, + .seq_fops = &udplite6_seq_fops, +}; + +int __init udplite6_proc_init(void) +{ + return udp_proc_register(&udplite6_seq_afinfo); +} + +void udplite6_proc_exit(void) +{ + udp_proc_unregister(&udplite6_seq_afinfo); +} +#endif diff --git a/net/ipv6/udplite_ipv6.c b/net/ipv6/udplite_ipv6.c deleted file mode 100644 index 87d4202522e..00000000000 --- a/net/ipv6/udplite_ipv6.c +++ /dev/null @@ -1,125 +0,0 @@ -/* - * UDPLITEv6 An implementation of the UDP-Lite protocol over IPv6. - * See also net/ipv4/udplite.c - * - * Version: $Id: udplite.c,v 1.9 2006/10/19 08:28:10 gerrit Exp $ - * - * Authors: Gerrit Renker - * - * Changes: - * Fixes: - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ -#include "udp_impl.h" - -DEFINE_SNMP_STAT(struct udp_mib, udplite_stats_in6) __read_mostly; - -static int udplitev6_rcv(struct sk_buff *skb) -{ - return __udp6_lib_rcv(skb, udplite_hash, IPPROTO_UDPLITE); -} - -static void udplitev6_err(struct sk_buff *skb, - struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) -{ - __udp6_lib_err(skb, opt, type, code, offset, info, udplite_hash); -} - -static struct inet6_protocol udplitev6_protocol = { - .handler = udplitev6_rcv, - .err_handler = udplitev6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, -}; - -static int udplite_v6_get_port(struct sock *sk, unsigned short snum) -{ - return udplite_get_port(sk, snum, ipv6_rcv_saddr_equal); -} - -DEFINE_PROTO_INUSE(udplitev6) - -struct proto udplitev6_prot = { - .name = "UDPLITEv6", - .owner = THIS_MODULE, - .close = udp_lib_close, - .connect = ip6_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = udp_ioctl, - .init = udplite_sk_init, - .destroy = udpv6_destroy_sock, - .setsockopt = udpv6_setsockopt, - .getsockopt = udpv6_getsockopt, - .sendmsg = udpv6_sendmsg, - .recvmsg = udpv6_recvmsg, - .backlog_rcv = udpv6_queue_rcv_skb, - .hash = udp_lib_hash, - .unhash = udp_lib_unhash, - .get_port = udplite_v6_get_port, - .obj_size = sizeof(struct udp6_sock), -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_udpv6_setsockopt, - .compat_getsockopt = compat_udpv6_getsockopt, -#endif - REF_PROTO_INUSE(udplitev6) -}; - -static struct inet_protosw udplite6_protosw = { - .type = SOCK_DGRAM, - .protocol = IPPROTO_UDPLITE, - .prot = &udplitev6_prot, - .ops = &inet6_dgram_ops, - .capability = -1, - .no_check = 0, - .flags = INET_PROTOSW_PERMANENT, -}; - -int __init udplitev6_init(void) -{ - int ret; - - ret = inet6_add_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); - if (ret) - goto out; - - ret = inet6_register_protosw(&udplite6_protosw); - if (ret) - goto out_udplitev6_protocol; -out: - return ret; - -out_udplitev6_protocol: - inet6_del_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); - goto out; -} - -void udplitev6_exit(void) -{ - inet6_unregister_protosw(&udplite6_protosw); - inet6_del_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); -} - -#ifdef CONFIG_PROC_FS -static struct file_operations udplite6_seq_fops; -static struct udp_seq_afinfo udplite6_seq_afinfo = { - .owner = THIS_MODULE, - .name = "udplite6", - .family = AF_INET6, - .hashtable = udplite_hash, - .seq_show = udp6_seq_show, - .seq_fops = &udplite6_seq_fops, -}; - -int __init udplite6_proc_init(void) -{ - return udp_proc_register(&udplite6_seq_afinfo); -} - -void udplite6_proc_exit(void) -{ - udp_proc_unregister(&udplite6_seq_afinfo); -} -#endif -- cgit v1.2.3-70-g09d2 From c346dca10840a874240c78efe3f39acf4312a1f2 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Tue, 25 Mar 2008 21:47:49 +0900 Subject: [NET] NETNS: Omit net_device->nd_net without CONFIG_NET_NS. Introduce per-net_device inlines: dev_net(), dev_net_set(). Without CONFIG_NET_NS, no namespace other than &init_net exists. Let's explicitly define them to help compiler optimizations. Signed-off-by: YOSHIFUJI Hideaki --- arch/ia64/hp/sim/simeth.c | 2 +- drivers/block/aoe/aoenet.c | 2 +- drivers/net/bonding/bond_3ad.c | 2 +- drivers/net/bonding/bond_alb.c | 2 +- drivers/net/bonding/bond_main.c | 6 ++--- drivers/net/hamradio/bpqether.c | 4 ++-- drivers/net/loopback.c | 2 +- drivers/net/macvlan.c | 2 +- drivers/net/pppoe.c | 6 ++--- drivers/net/veth.c | 2 +- drivers/net/via-velocity.c | 2 +- drivers/net/wan/dlci.c | 2 +- drivers/net/wan/hdlc.c | 4 ++-- drivers/net/wan/lapbether.c | 4 ++-- drivers/net/wan/syncppp.c | 2 +- drivers/s390/net/qeth_l3_main.c | 2 +- include/linux/inetdevice.h | 6 ++--- include/linux/netdevice.h | 25 ++++++++++++++++++++- net/8021q/vlan.c | 2 +- net/8021q/vlan_dev.c | 2 +- net/appletalk/aarp.c | 4 ++-- net/appletalk/ddp.c | 6 ++--- net/atm/clip.c | 2 +- net/atm/mpc.c | 2 +- net/ax25/af_ax25.c | 2 +- net/ax25/ax25_in.c | 2 +- net/bridge/br_notify.c | 2 +- net/bridge/br_stp_bpdu.c | 2 +- net/can/af_can.c | 4 ++-- net/can/bcm.c | 2 +- net/can/raw.c | 2 +- net/core/dev.c | 22 +++++++++---------- net/core/dst.c | 2 +- net/core/fib_rules.c | 2 +- net/core/neighbour.c | 12 +++++----- net/core/pktgen.c | 2 +- net/core/rtnetlink.c | 4 ++-- net/decnet/af_decnet.c | 2 +- net/decnet/dn_route.c | 2 +- net/econet/af_econet.c | 4 ++-- net/ipv4/arp.c | 14 ++++++------ net/ipv4/devinet.c | 10 ++++----- net/ipv4/fib_frontend.c | 12 +++++----- net/ipv4/icmp.c | 8 +++---- net/ipv4/igmp.c | 16 +++++++------- net/ipv4/ip_fragment.c | 2 +- net/ipv4/ip_gre.c | 2 +- net/ipv4/ip_input.c | 6 ++--- net/ipv4/ip_options.c | 2 +- net/ipv4/ipconfig.c | 4 ++-- net/ipv4/ipmr.c | 2 +- net/ipv4/netfilter/ip_queue.c | 2 +- net/ipv4/netfilter/ipt_MASQUERADE.c | 2 +- net/ipv4/raw.c | 4 ++-- net/ipv4/route.c | 28 +++++++++++------------ net/ipv4/tcp_ipv4.c | 6 ++--- net/ipv4/udp.c | 4 ++-- net/ipv4/xfrm4_policy.c | 2 +- net/ipv6/addrconf.c | 44 ++++++++++++++++++------------------- net/ipv6/icmp.c | 4 ++-- net/ipv6/ip6_output.c | 2 +- net/ipv6/mcast.c | 6 ++--- net/ipv6/ndisc.c | 24 ++++++++++---------- net/ipv6/netfilter/ip6_queue.c | 2 +- net/ipv6/proc.c | 2 +- net/ipv6/raw.c | 4 ++-- net/ipv6/reassembly.c | 2 +- net/ipv6/route.c | 40 ++++++++++++++++----------------- net/ipv6/tcp_ipv6.c | 10 ++++----- net/ipv6/udp.c | 4 ++-- net/ipv6/xfrm6_policy.c | 2 +- net/ipx/af_ipx.c | 4 ++-- net/irda/irlap_frame.c | 2 +- net/llc/llc_input.c | 2 +- net/netfilter/core.c | 2 +- net/netfilter/nfnetlink_queue.c | 2 +- net/netlabel/netlabel_unlabeled.c | 2 +- net/netrom/af_netrom.c | 2 +- net/packet/af_packet.c | 8 +++---- net/rose/af_rose.c | 2 +- net/sctp/protocol.c | 2 +- net/tipc/eth_media.c | 4 ++-- net/wireless/wext.c | 2 +- net/x25/af_x25.c | 2 +- net/x25/x25_dev.c | 2 +- net/xfrm/xfrm_policy.c | 4 ++-- security/selinux/netif.c | 2 +- 87 files changed, 251 insertions(+), 228 deletions(-) (limited to 'net/ipv6/proc.c') diff --git a/arch/ia64/hp/sim/simeth.c b/arch/ia64/hp/sim/simeth.c index 969fe9f443c..3d47839a0c4 100644 --- a/arch/ia64/hp/sim/simeth.c +++ b/arch/ia64/hp/sim/simeth.c @@ -294,7 +294,7 @@ simeth_device_event(struct notifier_block *this,unsigned long event, void *ptr) return NOTIFY_DONE; } - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if ( event != NETDEV_UP && event != NETDEV_DOWN ) return NOTIFY_DONE; diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c index 8460ef736d5..18d243c73ee 100644 --- a/drivers/block/aoe/aoenet.c +++ b/drivers/block/aoe/aoenet.c @@ -115,7 +115,7 @@ aoenet_rcv(struct sk_buff *skb, struct net_device *ifp, struct packet_type *pt, struct aoe_hdr *h; u32 n; - if (ifp->nd_net != &init_net) + if (dev_net(ifp) != &init_net) goto exit; skb = skb_share_check(skb, GFP_ATOMIC); diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index cb3c6faa788..457d81f73e3 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -2429,7 +2429,7 @@ int bond_3ad_lacpdu_recv(struct sk_buff *skb, struct net_device *dev, struct pac struct slave *slave = NULL; int ret = NET_RX_DROP; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto out; if (!(dev->flags & IFF_MASTER)) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index b57bc9467db..b986dacf5d3 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -345,7 +345,7 @@ static int rlb_arp_recv(struct sk_buff *skb, struct net_device *bond_dev, struct struct arp_pkt *arp = (struct arp_pkt *)skb->data; int res = NET_RX_DROP; - if (bond_dev->nd_net != &init_net) + if (dev_net(bond_dev) != &init_net) goto out; if (!(bond_dev->flags & IFF_MASTER)) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 5fc9d8d58ec..ac688fcb27d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2629,7 +2629,7 @@ static int bond_arp_rcv(struct sk_buff *skb, struct net_device *dev, struct pack unsigned char *arp_ptr; __be32 sip, tip; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto out; if (!(dev->priv_flags & IFF_BONDING) || !(dev->flags & IFF_MASTER)) @@ -3470,7 +3470,7 @@ static int bond_netdev_event(struct notifier_block *this, unsigned long event, v { struct net_device *event_dev = (struct net_device *)ptr; - if (event_dev->nd_net != &init_net) + if (dev_net(event_dev) != &init_net) return NOTIFY_DONE; dprintk("event_dev: %s, event: %lx\n", @@ -3508,7 +3508,7 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, struct bonding *bond, *bond_next; struct vlan_entry *vlan, *vlan_next; - if (ifa->ifa_dev->dev->nd_net != &init_net) + if (dev_net(ifa->ifa_dev->dev) != &init_net) return NOTIFY_DONE; list_for_each_entry_safe(bond, bond_next, &bond_dev_list, bond_list) { diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index 5ddf8b0c34f..5f4b4c6c9f7 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -172,7 +172,7 @@ static int bpq_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_ty struct ethhdr *eth; struct bpqdev *bpq; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto drop; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) @@ -553,7 +553,7 @@ static int bpq_device_event(struct notifier_block *this,unsigned long event, voi { struct net_device *dev = (struct net_device *)ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (!dev_is_ethdev(dev)) diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index f2a6e713224..41b774baac4 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -258,7 +258,7 @@ static __net_init int loopback_net_init(struct net *net) if (!dev) goto out; - dev->nd_net = net; + dev_net_set(dev, net); err = register_netdev(dev); if (err) goto out_free_netdev; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index f651a816b28..2056cfc624d 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -402,7 +402,7 @@ static int macvlan_newlink(struct net_device *dev, if (!tb[IFLA_LINK]) return -EINVAL; - lowerdev = __dev_get_by_index(dev->nd_net, nla_get_u32(tb[IFLA_LINK])); + lowerdev = __dev_get_by_index(dev_net(dev), nla_get_u32(tb[IFLA_LINK])); if (lowerdev == NULL) return -ENODEV; diff --git a/drivers/net/pppoe.c b/drivers/net/pppoe.c index ac0ac98b19c..4fad4ddb350 100644 --- a/drivers/net/pppoe.c +++ b/drivers/net/pppoe.c @@ -301,7 +301,7 @@ static int pppoe_device_event(struct notifier_block *this, { struct net_device *dev = (struct net_device *) ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; /* Only look at sockets that are using this specific device. */ @@ -392,7 +392,7 @@ static int pppoe_rcv(struct sk_buff *skb, if (!(skb = skb_share_check(skb, GFP_ATOMIC))) goto out; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto drop; if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr))) @@ -424,7 +424,7 @@ static int pppoe_disc_rcv(struct sk_buff *skb, struct pppoe_hdr *ph; struct pppox_sock *po; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto abort; if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr))) diff --git a/drivers/net/veth.c b/drivers/net/veth.c index e2ad98bee6e..31cd817f33f 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -375,7 +375,7 @@ static int veth_newlink(struct net_device *dev, else snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d"); - peer = rtnl_create_link(dev->nd_net, ifname, &veth_link_ops, tbp); + peer = rtnl_create_link(dev_net(dev), ifname, &veth_link_ops, tbp); if (IS_ERR(peer)) return PTR_ERR(peer); diff --git a/drivers/net/via-velocity.c b/drivers/net/via-velocity.c index 1525e8a8984..ed1afaf683a 100644 --- a/drivers/net/via-velocity.c +++ b/drivers/net/via-velocity.c @@ -3464,7 +3464,7 @@ static int velocity_netdev_event(struct notifier_block *nb, unsigned long notifi struct velocity_info *vptr; unsigned long flags; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; spin_lock_irqsave(&velocity_dev_list_lock, flags); diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c index 96b232446c0..b14242768fa 100644 --- a/drivers/net/wan/dlci.c +++ b/drivers/net/wan/dlci.c @@ -517,7 +517,7 @@ static int dlci_dev_event(struct notifier_block *unused, { struct net_device *dev = (struct net_device *) ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (event == NETDEV_UNREGISTER) { diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c index 39951d0c34d..9a83c9d5b8c 100644 --- a/drivers/net/wan/hdlc.c +++ b/drivers/net/wan/hdlc.c @@ -68,7 +68,7 @@ static int hdlc_rcv(struct sk_buff *skb, struct net_device *dev, { struct hdlc_device *hdlc = dev_to_hdlc(dev); - if (dev->nd_net != &init_net) { + if (dev_net(dev) != &init_net) { kfree_skb(skb); return 0; } @@ -105,7 +105,7 @@ static int hdlc_device_event(struct notifier_block *this, unsigned long event, unsigned long flags; int on; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (dev->get_stats != hdlc_get_stats) diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index fb37b809523..629c909e05f 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -91,7 +91,7 @@ static int lapbeth_rcv(struct sk_buff *skb, struct net_device *dev, struct packe int len, err; struct lapbethdev *lapbeth; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto drop; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) @@ -393,7 +393,7 @@ static int lapbeth_device_event(struct notifier_block *this, struct lapbethdev *lapbeth; struct net_device *dev = ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (!dev_is_ethdev(dev)) diff --git a/drivers/net/wan/syncppp.c b/drivers/net/wan/syncppp.c index 61e24b7a45a..29b4b94e494 100644 --- a/drivers/net/wan/syncppp.c +++ b/drivers/net/wan/syncppp.c @@ -1444,7 +1444,7 @@ static void sppp_print_bytes (u_char *p, u16 len) static int sppp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *p, struct net_device *orig_dev) { - if (dev->nd_net != &init_net) { + if (dev_net(dev) != &init_net) { kfree_skb(skb); return 0; } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index a856cb47fc7..21c439046b3 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -3250,7 +3250,7 @@ static int qeth_l3_ip_event(struct notifier_block *this, struct qeth_ipaddr *addr; struct qeth_card *card; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; QETH_DBF_TEXT(trace, 3, "ipevent"); diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index da05ab47ff2..7009b0cdd06 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -70,13 +70,13 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) ipv4_devconf_set((in_dev), NET_IPV4_CONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ - (IPV4_DEVCONF_ALL(in_dev->dev->nd_net, attr) && \ + (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ - (IPV4_DEVCONF_ALL(in_dev->dev->nd_net, attr) || \ + (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr) || \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_MAXCONF(in_dev, attr) \ - (max(IPV4_DEVCONF_ALL(in_dev->dev->nd_net, attr), \ + (max(IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ced61f87660..d146be40f46 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -708,8 +708,10 @@ struct net_device void (*poll_controller)(struct net_device *dev); #endif +#ifdef CONFIG_NET_NS /* Network namespace this network device is inside */ struct net *nd_net; +#endif /* bridge stuff */ struct net_bridge_port *br_port; @@ -737,6 +739,27 @@ struct net_device #define NETDEV_ALIGN 32 #define NETDEV_ALIGN_CONST (NETDEV_ALIGN - 1) +/* + * Net namespace inlines + */ +static inline +struct net *dev_net(const struct net_device *dev) +{ +#ifdef CONFIG_NET_NS + return dev->nd_net; +#else + return &init_net; +#endif +} + +static inline +void dev_net_set(struct net_device *dev, const struct net *net) +{ +#ifdef CONFIG_NET_NS + dev->nd_dev = net; +#endif +} + /** * netdev_priv - access network device private data * @dev: network device @@ -813,7 +836,7 @@ static inline struct net_device *next_net_device(struct net_device *dev) struct list_head *lh; struct net *net; - net = dev->nd_net; + net = dev_net(dev); lh = dev->dev_list.next; return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index dbc81b96509..c35dc230365 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -382,7 +382,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, int i, flgs; struct net_device *vlandev; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (!grp) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 1e5c9904571..e536162b1eb 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -153,7 +153,7 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, struct net_device_stats *stats; unsigned short vlan_TCI; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto err_free; skb = skb_share_check(skb, GFP_ATOMIC); diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index 61166f66479..25aa37ce943 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -333,7 +333,7 @@ static int aarp_device_event(struct notifier_block *this, unsigned long event, struct net_device *dev = ptr; int ct; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (event == NETDEV_DOWN) { @@ -716,7 +716,7 @@ static int aarp_rcv(struct sk_buff *skb, struct net_device *dev, struct atalk_addr sa, *ma, da; struct atalk_iface *ifa; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto out0; /* We only do Ethernet SNAP AARP. */ diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 3be55c8ca4e..44cd42f7786 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -648,7 +648,7 @@ static int ddp_device_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (event == NETDEV_DOWN) @@ -1405,7 +1405,7 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, int origlen; __u16 len_hops; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto freeit; /* Don't mangle buffer if shared */ @@ -1493,7 +1493,7 @@ freeit: static int ltalk_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto freeit; /* Expand any short form frames */ diff --git a/net/atm/clip.c b/net/atm/clip.c index e82da674672..6f8223ebf55 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -612,7 +612,7 @@ static int clip_device_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = arg; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (event == NETDEV_UNREGISTER) { diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 9c7f712fc7e..9db332e7a6c 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -964,7 +964,7 @@ static int mpoa_event_listener(struct notifier_block *mpoa_notifier, unsigned lo dev = (struct net_device *)dev_ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (dev->name == NULL || strncmp(dev->name, "lec", 3)) diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 48bfcc741f2..ee9dd83e756 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -116,7 +116,7 @@ static int ax25_device_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = (struct net_device *)ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; /* Reject non AX.25 devices */ diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c index d1be080dcb2..33790a8efbc 100644 --- a/net/ax25/ax25_in.c +++ b/net/ax25/ax25_in.c @@ -451,7 +451,7 @@ int ax25_kiss_rcv(struct sk_buff *skb, struct net_device *dev, skb->sk = NULL; /* Initially we don't know who it's for */ skb->destructor = NULL; /* Who initializes this, dammit?! */ - if (dev->nd_net != &init_net) { + if (dev_net(dev) != &init_net) { kfree_skb(skb); return 0; } diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c index 07ac3ae68d8..00644a544e3 100644 --- a/net/bridge/br_notify.c +++ b/net/bridge/br_notify.c @@ -37,7 +37,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v struct net_bridge_port *p = dev->br_port; struct net_bridge *br; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; /* not a port of a bridge */ diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 0edbd2a1c3f..8deab645ef7 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -142,7 +142,7 @@ int br_stp_rcv(struct sk_buff *skb, struct net_device *dev, struct net_bridge *br; const unsigned char *buf; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto err; if (!p) diff --git a/net/can/af_can.c b/net/can/af_can.c index 36b9f22ed83..2759b76f731 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -599,7 +599,7 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, struct dev_rcv_lists *d; int matches; - if (dev->type != ARPHRD_CAN || dev->nd_net != &init_net) { + if (dev->type != ARPHRD_CAN || dev_net(dev) != &init_net) { kfree_skb(skb); return 0; } @@ -710,7 +710,7 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg, struct net_device *dev = (struct net_device *)data; struct dev_rcv_lists *d; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (dev->type != ARPHRD_CAN) diff --git a/net/can/bcm.c b/net/can/bcm.c index bd4282dae75..e9f99b2c6bc 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1285,7 +1285,7 @@ static int bcm_notifier(struct notifier_block *nb, unsigned long msg, struct bcm_op *op; int notify_enodev = 0; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (dev->type != ARPHRD_CAN) diff --git a/net/can/raw.c b/net/can/raw.c index 94cd7f27c44..ead50c7c0d4 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -210,7 +210,7 @@ static int raw_notifier(struct notifier_block *nb, struct raw_sock *ro = container_of(nb, struct raw_sock, notifier); struct sock *sk = &ro->sk; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (dev->type != ARPHRD_CAN) diff --git a/net/core/dev.c b/net/core/dev.c index aebd0860604..81253482891 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -216,7 +216,7 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) /* Device list insertion */ static int list_netdevice(struct net_device *dev) { - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); ASSERT_RTNL(); @@ -852,8 +852,8 @@ int dev_alloc_name(struct net_device *dev, const char *name) struct net *net; int ret; - BUG_ON(!dev->nd_net); - net = dev->nd_net; + BUG_ON(!dev_net(dev)); + net = dev_net(dev); ret = __dev_alloc_name(net, name, buf); if (ret >= 0) strlcpy(dev->name, buf, IFNAMSIZ); @@ -877,9 +877,9 @@ int dev_change_name(struct net_device *dev, char *newname) struct net *net; ASSERT_RTNL(); - BUG_ON(!dev->nd_net); + BUG_ON(!dev_net(dev)); - net = dev->nd_net; + net = dev_net(dev); if (dev->flags & IFF_UP) return -EBUSY; @@ -2615,7 +2615,7 @@ static int ptype_seq_show(struct seq_file *seq, void *v) if (v == SEQ_START_TOKEN) seq_puts(seq, "Type Device Function\n"); - else if (pt->dev == NULL || pt->dev->nd_net == seq_file_net(seq)) { + else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else @@ -3689,8 +3689,8 @@ int register_netdevice(struct net_device *dev) /* When net_device's are persistent, this will be fatal. */ BUG_ON(dev->reg_state != NETREG_UNINITIALIZED); - BUG_ON(!dev->nd_net); - net = dev->nd_net; + BUG_ON(!dev_net(dev)); + net = dev_net(dev); spin_lock_init(&dev->queue_lock); spin_lock_init(&dev->_xmit_lock); @@ -4011,7 +4011,7 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, dev = (struct net_device *) (((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST); dev->padded = (char *)dev - (char *)p; - dev->nd_net = &init_net; + dev_net_set(dev, &init_net); if (sizeof_priv) { dev->priv = ((char *)dev + @@ -4136,7 +4136,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Get out if there is nothing todo */ err = 0; - if (dev->nd_net == net) + if (dev_net(dev) == net) goto out; /* Pick the destination device name, and ensure @@ -4187,7 +4187,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char dev_addr_discard(dev); /* Actually switch the network namespace */ - dev->nd_net = net; + dev_net_set(dev, net); /* Assign the new device name */ if (destname != dev->name) diff --git a/net/core/dst.c b/net/core/dst.c index 3a01a819ba4..694cd2a3f6d 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -279,7 +279,7 @@ static inline void dst_ifdown(struct dst_entry *dst, struct net_device *dev, if (!unregister) { dst->input = dst->output = dst_discard; } else { - dst->dev = dst->dev->nd_net->loopback_dev; + dst->dev = dev_net(dst->dev)->loopback_dev; dev_hold(dst->dev); dev_put(dev); if (dst->neighbour && dst->neighbour->dev == dev) { diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 42ccaf5b850..942be93a2eb 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -618,7 +618,7 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = ptr; - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); struct fib_rules_ops *ops; ASSERT_RTNL(); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 23c0a10c0c3..c978bd1cd65 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -388,7 +388,7 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, hash_val = tbl->hash(pkey, NULL); for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) { if (!memcmp(n->primary_key, pkey, key_len) && - (net == n->dev->nd_net)) { + dev_net(n->dev) == net) { neigh_hold(n); NEIGH_CACHE_STAT_INC(tbl, hits); break; @@ -1298,7 +1298,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_parms *p, *ref; struct net *net; - net = dev->nd_net; + net = dev_net(dev); ref = lookup_neigh_params(tbl, net, 0); if (!ref) return NULL; @@ -2050,7 +2050,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, s_idx = 0; for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next) { int lidx; - if (n->dev->nd_net != net) + if (dev_net(n->dev) != net) continue; lidx = idx++; if (lidx < s_idx) @@ -2155,7 +2155,7 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) n = tbl->hash_buckets[bucket]; while (n) { - if (n->dev->nd_net != net) + if (dev_net(n->dev) != net) goto next; if (state->neigh_sub_iter) { loff_t fakep = 0; @@ -2198,7 +2198,7 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, while (1) { while (n) { - if (n->dev->nd_net != net) + if (dev_net(n->dev) != net) goto next; if (state->neigh_sub_iter) { void *v = state->neigh_sub_iter(state, n, pos); @@ -2482,7 +2482,7 @@ static inline size_t neigh_nlmsg_size(void) static void __neigh_notify(struct neighbour *n, int type, int flags) { - struct net *net = n->dev->nd_net; + struct net *net = dev_net(n->dev); struct sk_buff *skb; int err = -ENOBUFS; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 20e63b302ba..a803b442234 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1874,7 +1874,7 @@ static int pktgen_device_event(struct notifier_block *unused, { struct net_device *dev = ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; /* It is OK that we do not hold the group lock right now, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2bd9c5f7627..09250a0800f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -972,7 +972,7 @@ struct net_device *rtnl_create_link(struct net *net, char *ifname, goto err_free; } - dev->nd_net = net; + dev_net_set(dev, net); dev->rtnl_link_ops = ops; if (tb[IFLA_MTU]) @@ -1198,7 +1198,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) { - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 23fd95a7ad1..3554fb3d251 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -2089,7 +2089,7 @@ static int dn_device_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = (struct net_device *)ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; switch(event) { diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 9dc0abb50ea..0a46b6c10e5 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -580,7 +580,7 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type struct dn_dev *dn = (struct dn_dev *)dev->dn_ptr; unsigned char padlen = 0; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto dump_it; if (dn == NULL) diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index bc0f6252613..68d15448004 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -1064,7 +1064,7 @@ static int econet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet struct sock *sk; struct ec_device *edev = dev->ec_ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto drop; if (skb->pkt_type == PACKET_OTHERHOST) @@ -1121,7 +1121,7 @@ static int econet_notifier(struct notifier_block *this, unsigned long msg, void struct net_device *dev = (struct net_device *)data; struct ec_device *edev; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; switch (msg) { diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 832473e30b3..3ce2e137e7b 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -242,7 +242,7 @@ static int arp_constructor(struct neighbour *neigh) return -EINVAL; } - neigh->type = inet_addr_type(dev->nd_net, addr); + neigh->type = inet_addr_type(dev_net(dev), addr); parms = in_dev->arp_parms; __neigh_parms_put(neigh->parms); @@ -341,14 +341,14 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) switch (IN_DEV_ARP_ANNOUNCE(in_dev)) { default: case 0: /* By default announce any local IP */ - if (skb && inet_addr_type(dev->nd_net, ip_hdr(skb)->saddr) == RTN_LOCAL) + if (skb && inet_addr_type(dev_net(dev), ip_hdr(skb)->saddr) == RTN_LOCAL) saddr = ip_hdr(skb)->saddr; break; case 1: /* Restrict announcements of saddr in same subnet */ if (!skb) break; saddr = ip_hdr(skb)->saddr; - if (inet_addr_type(dev->nd_net, saddr) == RTN_LOCAL) { + if (inet_addr_type(dev_net(dev), saddr) == RTN_LOCAL) { /* saddr should be known to target */ if (inet_addr_onlink(in_dev, target, saddr)) break; @@ -424,7 +424,7 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) int flag = 0; /*unsigned long now; */ - if (ip_route_output_key(dev->nd_net, &rt, &fl) < 0) + if (ip_route_output_key(dev_net(dev), &rt, &fl) < 0) return 1; if (rt->u.dst.dev != dev) { NET_INC_STATS_BH(LINUX_MIB_ARPFILTER); @@ -477,7 +477,7 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb) paddr = skb->rtable->rt_gateway; - if (arp_set_predefined(inet_addr_type(dev->nd_net, paddr), haddr, paddr, dev)) + if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr, paddr, dev)) return 0; n = __neigh_lookup(&arp_tbl, &paddr, dev, 1); @@ -709,7 +709,7 @@ static int arp_process(struct sk_buff *skb) u16 dev_type = dev->type; int addr_type; struct neighbour *n; - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); /* arp_rcv below verifies the ARP header and verifies the device * is ARP'able. @@ -858,7 +858,7 @@ static int arp_process(struct sk_buff *skb) n = __neigh_lookup(&arp_tbl, &sip, dev, 0); - if (IPV4_DEVCONF_ALL(dev->nd_net, ARP_ACCEPT)) { + if (IPV4_DEVCONF_ALL(dev_net(dev), ARP_ACCEPT)) { /* Unsolicited ARP is not accepted by default. It is possible, that this option should be enabled for some devices (strip is candidate) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 4a10dbbbe0a..823c724a859 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -165,7 +165,7 @@ static struct in_device *inetdev_init(struct net_device *dev) if (!in_dev) goto out; INIT_RCU_HEAD(&in_dev->rcu_head); - memcpy(&in_dev->cnf, dev->nd_net->ipv4.devconf_dflt, + memcpy(&in_dev->cnf, dev_net(dev)->ipv4.devconf_dflt, sizeof(in_dev->cnf)); in_dev->cnf.sysctl = NULL; in_dev->dev = dev; @@ -872,7 +872,7 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { __be32 addr = 0; struct in_device *in_dev; - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); @@ -974,7 +974,7 @@ __be32 inet_confirm_addr(struct in_device *in_dev, if (scope != RT_SCOPE_LINK) return confirm_addr_indev(in_dev, dst, local, scope); - net = in_dev->dev->nd_net; + net = dev_net(in_dev->dev); read_lock(&dev_base_lock); rcu_read_lock(); for_each_netdev(net, dev) { @@ -1203,7 +1203,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr* ifa, struct nlmsghdr *nlh, int err = -ENOBUFS; struct net *net; - net = ifa->ifa_dev->dev->nd_net; + net = dev_net(ifa->ifa_dev->dev); skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL); if (skb == NULL) goto errout; @@ -1517,7 +1517,7 @@ static void devinet_sysctl_register(struct in_device *idev) { neigh_sysctl_register(idev->dev, idev->arp_parms, NET_IPV4, NET_IPV4_NEIGH, "ipv4", NULL, NULL); - __devinet_sysctl_register(idev->dev->nd_net, idev->dev->name, + __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, idev->dev->ifindex, &idev->cnf); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 86ff2711fc9..0e4b34b07cb 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -257,7 +257,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, if (in_dev == NULL) goto e_inval; - net = dev->nd_net; + net = dev_net(dev); if (fib_lookup(net, &fl, &res)) goto last_resort; if (res.type != RTN_UNICAST) @@ -674,7 +674,7 @@ out: static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa) { - struct net *net = ifa->ifa_dev->dev->nd_net; + struct net *net = dev_net(ifa->ifa_dev->dev); struct fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, @@ -801,15 +801,15 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim); /* Check, that this local address finally disappeared. */ - if (inet_addr_type(dev->nd_net, ifa->ifa_local) != RTN_LOCAL) { + if (inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) { /* And the last, but not the least thing. We must flush stray FIB entries. First of all, we scan fib_info list searching for stray nexthop entries, then ignite fib_flush. */ - if (fib_sync_down_addr(dev->nd_net, ifa->ifa_local)) - fib_flush(dev->nd_net); + if (fib_sync_down_addr(dev_net(dev), ifa->ifa_local)) + fib_flush(dev_net(dev)); } } #undef LOCAL_OK @@ -899,7 +899,7 @@ static void nl_fib_lookup_exit(struct net *net) static void fib_disable_ip(struct net_device *dev, int force) { if (fib_sync_down_dev(dev, force)) - fib_flush(dev->nd_net); + fib_flush(dev_net(dev)); rt_cache_flush(0); arp_ifdown(dev); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index ff9a8e643fc..f38f093ef75 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -351,7 +351,7 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param, struct sock *sk; struct sk_buff *skb; - sk = icmp_sk(rt->u.dst.dev->nd_net); + sk = icmp_sk(dev_net(rt->u.dst.dev)); if (ip_append_data(sk, icmp_glue_bits, icmp_param, icmp_param->data_len+icmp_param->head_len, icmp_param->head_len, @@ -382,7 +382,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) { struct ipcm_cookie ipc; struct rtable *rt = skb->rtable; - struct net *net = rt->u.dst.dev->nd_net; + struct net *net = dev_net(rt->u.dst.dev); struct sock *sk = icmp_sk(net); struct inet_sock *inet = inet_sk(sk); __be32 daddr; @@ -447,7 +447,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) if (!rt) goto out; - net = rt->u.dst.dev->nd_net; + net = dev_net(rt->u.dst.dev); sk = icmp_sk(net); /* @@ -677,7 +677,7 @@ static void icmp_unreach(struct sk_buff *skb) u32 info = 0; struct net *net; - net = skb->dst->dev->nd_net; + net = dev_net(skb->dst->dev); /* * Incomplete header ? diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6a4ee8da699..682f632bfb7 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -130,12 +130,12 @@ */ #define IGMP_V1_SEEN(in_dev) \ - (IPV4_DEVCONF_ALL(in_dev->dev->nd_net, FORCE_IGMP_VERSION) == 1 || \ + (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1 || \ ((in_dev)->mr_v1_seen && \ time_before(jiffies, (in_dev)->mr_v1_seen))) #define IGMP_V2_SEEN(in_dev) \ - (IPV4_DEVCONF_ALL(in_dev->dev->nd_net, FORCE_IGMP_VERSION) == 2 || \ + (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2 || \ ((in_dev)->mr_v2_seen && \ time_before(jiffies, (in_dev)->mr_v2_seen))) @@ -1198,7 +1198,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) ASSERT_RTNL(); - if (in_dev->dev->nd_net != &init_net) + if (dev_net(in_dev->dev) != &init_net) return; for (im=in_dev->mc_list; im; im=im->next) { @@ -1280,7 +1280,7 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) ASSERT_RTNL(); - if (in_dev->dev->nd_net != &init_net) + if (dev_net(in_dev->dev) != &init_net) return; for (ip=&in_dev->mc_list; (i=*ip)!=NULL; ip=&i->next) { @@ -1310,7 +1310,7 @@ void ip_mc_down(struct in_device *in_dev) ASSERT_RTNL(); - if (in_dev->dev->nd_net != &init_net) + if (dev_net(in_dev->dev) != &init_net) return; for (i=in_dev->mc_list; i; i=i->next) @@ -1333,7 +1333,7 @@ void ip_mc_init_dev(struct in_device *in_dev) { ASSERT_RTNL(); - if (in_dev->dev->nd_net != &init_net) + if (dev_net(in_dev->dev) != &init_net) return; in_dev->mc_tomb = NULL; @@ -1359,7 +1359,7 @@ void ip_mc_up(struct in_device *in_dev) ASSERT_RTNL(); - if (in_dev->dev->nd_net != &init_net) + if (dev_net(in_dev->dev) != &init_net) return; ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); @@ -1378,7 +1378,7 @@ void ip_mc_destroy_dev(struct in_device *in_dev) ASSERT_RTNL(); - if (in_dev->dev->nd_net != &init_net) + if (dev_net(in_dev->dev) != &init_net) return; /* Deactivate timers */ diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 8b448c4b908..fcb60e76b23 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -571,7 +571,7 @@ int ip_defrag(struct sk_buff *skb, u32 user) IP_INC_STATS_BH(IPSTATS_MIB_REASMREQDS); - net = skb->dev ? skb->dev->nd_net : skb->dst->dev->nd_net; + net = skb->dev ? dev_net(skb->dev) : dev_net(skb->dst->dev); /* Start by cleaning up the memory. */ if (atomic_read(&net->ipv4.frags.mem) > net->ipv4.frags.high_thresh) ip_evictor(net); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f9ee84420cb..50972b397a9 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1190,7 +1190,7 @@ static int ipgre_close(struct net_device *dev) struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) { struct in_device *in_dev; - in_dev = inetdev_by_index(dev->nd_net, t->mlink); + in_dev = inetdev_by_index(dev_net(dev), t->mlink); if (in_dev) { ip_mc_dec_group(in_dev, t->parms.iph.daddr); in_dev_put(in_dev); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 2aeea5d1542..26685c83a14 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -172,7 +172,7 @@ int ip_call_ra_chain(struct sk_buff *skb) if (sk && inet_sk(sk)->num == protocol && (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex) && - sk->sk_net == dev->nd_net) { + sk->sk_net == dev_net(dev)) { if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) { read_unlock(&ip_ra_lock); @@ -199,7 +199,7 @@ int ip_call_ra_chain(struct sk_buff *skb) static int ip_local_deliver_finish(struct sk_buff *skb) { - struct net *net = skb->dev->nd_net; + struct net *net = dev_net(skb->dev); __skb_pull(skb, ip_hdrlen(skb)); @@ -291,7 +291,7 @@ static inline int ip_rcv_options(struct sk_buff *skb) opt = &(IPCB(skb)->opt); opt->optlen = iph->ihl*4 - sizeof(struct iphdr); - if (ip_options_compile(dev->nd_net, opt, skb)) { + if (ip_options_compile(dev_net(dev), opt, skb)) { IP_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); goto drop; } diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 87cc1222c60..d107543d3f8 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -145,7 +145,7 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) __be32 addr; memcpy(&addr, sptr+soffset-1, 4); - if (inet_addr_type(skb->dst->dev->nd_net, addr) != RTN_LOCAL) { + if (inet_addr_type(dev_net(skb->dst->dev), addr) != RTN_LOCAL) { dopt->ts_needtime = 1; soffset += 8; } diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 96138b128de..08e8fb60d31 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -434,7 +434,7 @@ ic_rarp_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt unsigned char *sha, *tha; /* s for "source", t for "target" */ struct ic_device *d; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto drop; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) @@ -854,7 +854,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str struct ic_device *d; int len, ext_len; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto drop; /* Perform verifications before taking the lock. */ diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 7d63d74ef62..e54bc136447 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1089,7 +1089,7 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v struct vif_device *v; int ct; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (event != NETDEV_UNREGISTER) diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index fe05da41d6b..500998a2dec 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -481,7 +481,7 @@ ipq_rcv_dev_event(struct notifier_block *this, { struct net_device *dev = ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; /* Drop any packets associated with the downed device */ diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index c6817b18366..84c26dd27d8 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -120,7 +120,7 @@ static int masq_device_event(struct notifier_block *this, { const struct net_device *dev = ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (event == NETDEV_DOWN) { diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 3f68a937b60..8756d502a47 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -168,7 +168,7 @@ static int raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash) if (hlist_empty(head)) goto out; - net = skb->dev->nd_net; + net = dev_net(skb->dev); sk = __raw_v4_lookup(net, __sk_head(head), iph->protocol, iph->saddr, iph->daddr, skb->dev->ifindex); @@ -276,7 +276,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]); if (raw_sk != NULL) { iph = (struct iphdr *)skb->data; - net = skb->dev->nd_net; + net = dev_net(skb->dev); while ((raw_sk = __raw_v4_lookup(net, raw_sk, protocol, iph->daddr, iph->saddr, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 2941ef21f20..7768d718e19 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -284,7 +284,7 @@ static struct rtable *rt_cache_get_first(struct rt_cache_iter_state *st) rcu_read_lock_bh(); r = rcu_dereference(rt_hash_table[st->bucket].chain); while (r) { - if (r->u.dst.dev->nd_net == st->p.net && + if (dev_net(r->u.dst.dev) == st->p.net && r->rt_genid == st->genid) return r; r = rcu_dereference(r->u.dst.rt_next); @@ -312,7 +312,7 @@ static struct rtable *rt_cache_get_next(struct rt_cache_iter_state *st, struct rtable *r) { while ((r = __rt_cache_get_next(st, r)) != NULL) { - if (r->u.dst.dev->nd_net != st->p.net) + if (dev_net(r->u.dst.dev) != st->p.net) continue; if (r->rt_genid == st->genid) break; @@ -680,7 +680,7 @@ static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) static inline int compare_netns(struct rtable *rt1, struct rtable *rt2) { - return rt1->u.dst.dev->nd_net == rt2->u.dst.dev->nd_net; + return dev_net(rt1->u.dst.dev) == dev_net(rt2->u.dst.dev); } /* @@ -1164,7 +1164,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, if (!in_dev) return; - net = dev->nd_net; + net = dev_net(dev); if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) || ipv4_is_zeronet(new_gw)) @@ -1195,7 +1195,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, rth->fl.oif != ikeys[k] || rth->fl.iif != 0 || rth->rt_genid != atomic_read(&rt_genid) || - rth->u.dst.dev->nd_net != net) { + dev_net(rth->u.dst.dev) != net) { rthp = &rth->u.dst.rt_next; continue; } @@ -1454,7 +1454,7 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, rth->rt_src == iph->saddr && rth->fl.iif == 0 && !(dst_metric_locked(&rth->u.dst, RTAX_MTU)) && - rth->u.dst.dev->nd_net == net && + dev_net(rth->u.dst.dev) == net && rth->rt_genid == atomic_read(&rt_genid)) { unsigned short mtu = new_mtu; @@ -1530,9 +1530,9 @@ static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, { struct rtable *rt = (struct rtable *) dst; struct in_device *idev = rt->idev; - if (dev != dev->nd_net->loopback_dev && idev && idev->dev == dev) { + if (dev != dev_net(dev)->loopback_dev && idev && idev->dev == dev) { struct in_device *loopback_idev = - in_dev_get(dev->nd_net->loopback_dev); + in_dev_get(dev_net(dev)->loopback_dev); if (loopback_idev) { rt->idev = loopback_idev; in_dev_put(idev); @@ -1576,7 +1576,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt) if (rt->fl.iif == 0) src = rt->rt_src; - else if (fib_lookup(rt->u.dst.dev->nd_net, &rt->fl, &res) == 0) { + else if (fib_lookup(dev_net(rt->u.dst.dev), &rt->fl, &res) == 0) { src = FIB_RES_PREFSRC(res); fib_res_put(&res); } else @@ -1900,7 +1900,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, __be32 spec_dst; int err = -EINVAL; int free_res = 0; - struct net * net = dev->nd_net; + struct net * net = dev_net(dev); /* IP on this device is disabled. */ @@ -2071,7 +2071,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, int iif = dev->ifindex; struct net *net; - net = dev->nd_net; + net = dev_net(dev); tos &= IPTOS_RT_MASK; hash = rt_hash(daddr, saddr, iif); @@ -2084,7 +2084,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->fl.oif == 0 && rth->fl.mark == skb->mark && rth->fl.fl4_tos == tos && - rth->u.dst.dev->nd_net == net && + dev_net(rth->u.dst.dev) == net && rth->rt_genid == atomic_read(&rt_genid)) { dst_use(&rth->u.dst, jiffies); RT_CACHE_STAT_INC(in_hit); @@ -2486,7 +2486,7 @@ int __ip_route_output_key(struct net *net, struct rtable **rp, rth->fl.mark == flp->mark && !((rth->fl.fl4_tos ^ flp->fl4_tos) & (IPTOS_RT_MASK | RTO_ONLINK)) && - rth->u.dst.dev->nd_net == net && + dev_net(rth->u.dst.dev) == net && rth->rt_genid == atomic_read(&rt_genid)) { dst_use(&rth->u.dst, jiffies); RT_CACHE_STAT_INC(out_hit); @@ -2795,7 +2795,7 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock_bh(); for (rt = rcu_dereference(rt_hash_table[h].chain), idx = 0; rt; rt = rcu_dereference(rt->u.dst.rt_next), idx++) { - if (rt->u.dst.dev->nd_net != net || idx < s_idx) + if (dev_net(rt->u.dst.dev) != net || idx < s_idx) continue; if (rt->rt_genid != atomic_read(&rt_genid)) continue; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 649d00a50cb..28bece6f281 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -353,7 +353,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) return; } - sk = inet_lookup(skb->dev->nd_net, &tcp_hashinfo, iph->daddr, th->dest, + sk = inet_lookup(dev_net(skb->dev), &tcp_hashinfo, iph->daddr, th->dest, iph->saddr, th->source, inet_iif(skb)); if (!sk) { ICMP_INC_STATS_BH(ICMP_MIB_INERRORS); @@ -1644,7 +1644,7 @@ int tcp_v4_rcv(struct sk_buff *skb) TCP_SKB_CB(skb)->flags = iph->tos; TCP_SKB_CB(skb)->sacked = 0; - sk = __inet_lookup(skb->dev->nd_net, &tcp_hashinfo, iph->saddr, + sk = __inet_lookup(dev_net(skb->dev), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); if (!sk) goto no_tcp_socket; @@ -1718,7 +1718,7 @@ do_time_wait: } switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { case TCP_TW_SYN: { - struct sock *sk2 = inet_lookup_listener(skb->dev->nd_net, + struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, iph->daddr, th->dest, inet_iif(skb)); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index b37581dfd02..e2cd9348135 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -357,7 +357,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct hlist_head udptable[]) int harderr; int err; - sk = __udp4_lib_lookup(skb->dev->nd_net, iph->daddr, uh->dest, + sk = __udp4_lib_lookup(dev_net(skb->dev), iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, udptable); if (sk == NULL) { ICMP_INC_STATS_BH(ICMP_MIB_INERRORS); @@ -1181,7 +1181,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable); - sk = __udp4_lib_lookup(skb->dev->nd_net, saddr, uh->source, daddr, + sk = __udp4_lib_lookup(dev_net(skb->dev), saddr, uh->source, daddr, uh->dest, inet_iif(skb), udptable); if (sk != NULL) { diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 10ed7049143..c63de0a72ab 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -221,7 +221,7 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, xdst = (struct xfrm_dst *)dst; if (xdst->u.rt.idev->dev == dev) { struct in_device *loopback_idev = - in_dev_get(dev->nd_net->loopback_dev); + in_dev_get(dev_net(dev)->loopback_dev); BUG_ON(!loopback_idev); do { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 89954885dee..d1de9ec7426 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -335,7 +335,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) rwlock_init(&ndev->lock); ndev->dev = dev; - memcpy(&ndev->cnf, dev->nd_net->ipv6.devconf_dflt, sizeof(ndev->cnf)); + memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf)); ndev->cnf.mtu6 = dev->mtu; ndev->cnf.sysctl = NULL; ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); @@ -561,7 +561,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, write_lock(&addrconf_hash_lock); /* Ignore adding duplicate addresses on an interface */ - if (ipv6_chk_same_addr(idev->dev->nd_net, addr, idev->dev)) { + if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) { ADBG(("ipv6_add_addr: already assigned\n")); err = -EEXIST; goto out; @@ -751,7 +751,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if ((ifp->flags & IFA_F_PERMANENT) && onlink < 1) { struct in6_addr prefix; struct rt6_info *rt; - struct net *net = ifp->idev->dev->nd_net; + struct net *net = dev_net(ifp->idev->dev); ipv6_addr_prefix(&prefix, &ifp->addr, ifp->prefix_len); rt = rt6_lookup(net, &prefix, NULL, ifp->idev->dev->ifindex, 1); @@ -1044,7 +1044,7 @@ int ipv6_dev_get_saddr(struct net_device *dst_dev, { struct ipv6_saddr_score scores[2], *score = &scores[0], *hiscore = &scores[1]; - struct net *net = dst_dev->nd_net; + struct net *net = dev_net(dst_dev); struct ipv6_saddr_dst dst; struct net_device *dev; int dst_type; @@ -1217,7 +1217,7 @@ int ipv6_chk_addr(struct net *net, struct in6_addr *addr, read_lock_bh(&addrconf_hash_lock); for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { - if (ifp->idev->dev->nd_net != net) + if (dev_net(ifp->idev->dev) != net) continue; if (ipv6_addr_equal(&ifp->addr, addr) && !(ifp->flags&IFA_F_TENTATIVE)) { @@ -1239,7 +1239,7 @@ int ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, u8 hash = ipv6_addr_hash(addr); for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { - if (ifp->idev->dev->nd_net != net) + if (dev_net(ifp->idev->dev) != net) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { if (dev == NULL || ifp->idev->dev == dev) @@ -1257,7 +1257,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, struct in6_addr *addr, read_lock_bh(&addrconf_hash_lock); for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { - if (ifp->idev->dev->nd_net != net) + if (dev_net(ifp->idev->dev) != net) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { if (dev == NULL || ifp->idev->dev == dev || @@ -1559,7 +1559,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, .fc_expires = expires, .fc_dst_len = plen, .fc_flags = RTF_UP | flags, - .fc_nlinfo.nl_net = dev->nd_net, + .fc_nlinfo.nl_net = dev_net(dev), }; ipv6_addr_copy(&cfg.fc_dst, pfx); @@ -1586,7 +1586,7 @@ static void addrconf_add_mroute(struct net_device *dev) .fc_ifindex = dev->ifindex, .fc_dst_len = 8, .fc_flags = RTF_UP, - .fc_nlinfo.nl_net = dev->nd_net, + .fc_nlinfo.nl_net = dev_net(dev), }; ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); @@ -1603,7 +1603,7 @@ static void sit_route_add(struct net_device *dev) .fc_ifindex = dev->ifindex, .fc_dst_len = 96, .fc_flags = RTF_UP | RTF_NONEXTHOP, - .fc_nlinfo.nl_net = dev->nd_net, + .fc_nlinfo.nl_net = dev_net(dev), }; /* prefix length - 96 bits "::d.d.d.d" */ @@ -1704,7 +1704,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) if (pinfo->onlink) { struct rt6_info *rt; - rt = rt6_lookup(dev->nd_net, &pinfo->prefix, NULL, + rt = rt6_lookup(dev_net(dev), &pinfo->prefix, NULL, dev->ifindex, 1); if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) { @@ -1748,7 +1748,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) ok: - ifp = ipv6_get_ifaddr(dev->nd_net, &addr, dev, 1); + ifp = ipv6_get_ifaddr(dev_net(dev), &addr, dev, 1); if (ifp == NULL && valid_lft) { int max_addresses = in6_dev->cnf.max_addresses; @@ -2071,7 +2071,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) struct inet6_ifaddr * ifp; struct in6_addr addr; struct net_device *dev; - struct net *net = idev->dev->nd_net; + struct net *net = dev_net(idev->dev); int scope; ASSERT_RTNL(); @@ -2261,7 +2261,7 @@ ipv6_inherit_linklocal(struct inet6_dev *idev, struct net_device *link_dev) static void ip6_tnl_add_linklocal(struct inet6_dev *idev) { struct net_device *link_dev; - struct net *net = idev->dev->nd_net; + struct net *net = dev_net(idev->dev); /* first try to inherit the link-local address from the link device */ if (idev->dev->iflink && @@ -2442,7 +2442,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) { struct inet6_dev *idev; struct inet6_ifaddr *ifa, **bifa; - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); int i; ASSERT_RTNL(); @@ -2771,7 +2771,7 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq) for (state->bucket = 0; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { ifa = inet6_addr_lst[state->bucket]; - while (ifa && ifa->idev->dev->nd_net != net) + while (ifa && dev_net(ifa->idev->dev) != net) ifa = ifa->lst_next; if (ifa) break; @@ -2787,7 +2787,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct inet6_ifad ifa = ifa->lst_next; try_again: if (ifa) { - if (ifa->idev->dev->nd_net != net) { + if (dev_net(ifa->idev->dev) != net) { ifa = ifa->lst_next; goto try_again; } @@ -2905,7 +2905,7 @@ int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr) u8 hash = ipv6_addr_hash(addr); read_lock_bh(&addrconf_hash_lock); for (ifp = inet6_addr_lst[hash]; ifp; ifp = ifp->lst_next) { - if (ifp->idev->dev->nd_net != net) + if (dev_net(ifp->idev->dev) != net) continue; if (ipv6_addr_cmp(&ifp->addr, addr) == 0 && (ifp->flags & IFA_F_HOMEADDRESS)) { @@ -3469,7 +3469,7 @@ errout: static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) { struct sk_buff *skb; - struct net *net = ifa->idev->dev->nd_net; + struct net *net = dev_net(ifa->idev->dev); int err = -ENOBUFS; skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC); @@ -3675,7 +3675,7 @@ cont: void inet6_ifinfo_notify(int event, struct inet6_dev *idev) { struct sk_buff *skb; - struct net *net = idev->dev->nd_net; + struct net *net = dev_net(idev->dev); int err = -ENOBUFS; skb = nlmsg_new(inet6_if_nlmsg_size(), GFP_ATOMIC); @@ -3745,7 +3745,7 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo) { struct sk_buff *skb; - struct net *net = idev->dev->nd_net; + struct net *net = dev_net(idev->dev); int err = -ENOBUFS; skb = nlmsg_new(inet6_prefix_nlmsg_size(), GFP_ATOMIC); @@ -4157,7 +4157,7 @@ static void addrconf_sysctl_register(struct inet6_dev *idev) NET_IPV6_NEIGH, "ipv6", &ndisc_ifinfo_sysctl_change, NULL); - __addrconf_sysctl_register(idev->dev->nd_net, idev->dev->name, + __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, idev->dev->ifindex, idev, &idev->cnf); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 86332417b40..50857662e6b 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -306,7 +306,7 @@ static inline void mip6_addr_swap(struct sk_buff *skb) {} void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, struct net_device *dev) { - struct net *net = skb->dev->nd_net; + struct net *net = dev_net(skb->dev); struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); struct sock *sk; @@ -507,7 +507,7 @@ EXPORT_SYMBOL(icmpv6_send); static void icmpv6_echo_reply(struct sk_buff *skb) { - struct net *net = skb->dev->nd_net; + struct net *net = dev_net(skb->dev); struct sock *sk; struct inet6_dev *idev; struct ipv6_pinfo *np; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d34aa61353b..556300f0eba 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -402,7 +402,7 @@ int ip6_forward(struct sk_buff *skb) struct dst_entry *dst = skb->dst; struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); - struct net *net = dst->dev->nd_net; + struct net *net = dev_net(dst->dev); if (ipv6_devconf.forwarding == 0) goto error; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 957ac7e9e92..0357de8e78c 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1400,7 +1400,7 @@ mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) static struct sk_buff *mld_newpack(struct net_device *dev, int size) { - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); struct sock *sk = net->ipv6.igmp_sk; struct sk_buff *skb; struct mld2_report *pmr; @@ -1448,7 +1448,7 @@ static void mld_sendpack(struct sk_buff *skb) (struct mld2_report *)skb_transport_header(skb); int payload_len, mldlen; struct inet6_dev *idev = in6_dev_get(skb->dev); - struct net *net = skb->dev->nd_net; + struct net *net = dev_net(skb->dev); int err; struct flowi fl; @@ -1762,7 +1762,7 @@ static void mld_send_cr(struct inet6_dev *idev) static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) { - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); struct sock *sk = net->ipv6.igmp_sk; struct inet6_dev *idev; struct sk_buff *skb; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 3f68a6eae7b..79af57f586e 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -447,7 +447,7 @@ static void __ndisc_send(struct net_device *dev, { struct flowi fl; struct dst_entry *dst; - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; struct sk_buff *skb; struct icmp6hdr *hdr; @@ -539,7 +539,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, }; /* for anycast or proxy, solicited_addr != src_addr */ - ifp = ipv6_get_ifaddr(dev->nd_net, solicited_addr, dev, 1); + ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1); if (ifp) { src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) @@ -547,7 +547,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, in6_ifa_put(ifp); } else { if (ipv6_dev_get_saddr(dev, daddr, - inet6_sk(dev->nd_net->ipv6.ndisc_sk)->srcprefs, + inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs, &tmpaddr)) return; src_addr = &tmpaddr; @@ -601,7 +601,7 @@ void ndisc_send_rs(struct net_device *dev, struct in6_addr *saddr, * suppress the inclusion of the sllao. */ if (send_sllao) { - struct inet6_ifaddr *ifp = ipv6_get_ifaddr(dev->nd_net, saddr, + struct inet6_ifaddr *ifp = ipv6_get_ifaddr(dev_net(dev), saddr, dev, 1); if (ifp) { if (ifp->flags & IFA_F_OPTIMISTIC) { @@ -639,7 +639,7 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) struct in6_addr *target = (struct in6_addr *)&neigh->primary_key; int probes = atomic_read(&neigh->probes); - if (skb && ipv6_chk_addr(dev->nd_net, &ipv6_hdr(skb)->saddr, dev, 1)) + if (skb && ipv6_chk_addr(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, 1)) saddr = &ipv6_hdr(skb)->saddr; if ((probes -= neigh->parms->ucast_probes) < 0) { @@ -727,7 +727,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) inc = ipv6_addr_is_multicast(daddr); - ifp = ipv6_get_ifaddr(dev->nd_net, &msg->target, dev, 1); + ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) { @@ -776,7 +776,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) if (ipv6_chk_acast_addr(dev, &msg->target) || (idev->cnf.forwarding && (ipv6_devconf.proxy_ndp || idev->cnf.proxy_ndp) && - (pneigh = pneigh_lookup(&nd_tbl, dev->nd_net, + (pneigh = pneigh_lookup(&nd_tbl, dev_net(dev), &msg->target, dev, 0)) != NULL)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && @@ -886,7 +886,7 @@ static void ndisc_recv_na(struct sk_buff *skb) return; } } - ifp = ipv6_get_ifaddr(dev->nd_net, &msg->target, dev, 1); + ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { if (ifp->flags & IFA_F_TENTATIVE) { addrconf_dad_failure(ifp); @@ -918,7 +918,7 @@ static void ndisc_recv_na(struct sk_buff *skb) */ if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && ipv6_devconf.forwarding && ipv6_devconf.proxy_ndp && - pneigh_lookup(&nd_tbl, dev->nd_net, &msg->target, dev, 0)) { + pneigh_lookup(&nd_tbl, dev_net(dev), &msg->target, dev, 0)) { /* XXX: idev->cnf.prixy_ndp */ goto out; } @@ -1008,7 +1008,7 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) struct sk_buff *skb; struct nlmsghdr *nlh; struct nduseroptmsg *ndmsg; - struct net *net = ra->dev->nd_net; + struct net *net = dev_net(ra->dev); int err; int base_size = NLMSG_ALIGN(sizeof(struct nduseroptmsg) + (opt->nd_opt_len << 3)); @@ -1395,7 +1395,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, struct in6_addr *target) { struct net_device *dev = skb->dev; - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; int len = sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); struct sk_buff *buff; @@ -1597,7 +1597,7 @@ int ndisc_rcv(struct sk_buff *skb) static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = ptr; - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); switch (event) { case NETDEV_CHANGEADDR: diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index cc2f9afcf80..a6d30626b47 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -484,7 +484,7 @@ ipq_rcv_dev_event(struct notifier_block *this, { struct net_device *dev = ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; /* Drop any packets associated with the downed device */ diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 8a5be290c71..364dc332532 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -214,7 +214,7 @@ int snmp6_register_dev(struct inet6_dev *idev) if (!idev || !idev->dev) return -EINVAL; - if (idev->dev->nd_net != &init_net) + if (dev_net(idev->dev) != &init_net) return 0; if (!proc_net_devsnmp6) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 548d0763f4d..efb0047f688 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -176,7 +176,7 @@ static int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) if (sk == NULL) goto out; - net = skb->dev->nd_net; + net = dev_net(skb->dev); sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, IP6CB(skb)->iif); while (sk) { @@ -363,7 +363,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, if (sk != NULL) { saddr = &ipv6_hdr(skb)->saddr; daddr = &ipv6_hdr(skb)->daddr; - net = skb->dev->nd_net; + net = dev_net(skb->dev); while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr, IP6CB(skb)->iif))) { diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index f936d045a39..4e1447634f3 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -600,7 +600,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; } - net = skb->dev->nd_net; + net = dev_net(skb->dev); if (atomic_read(&net->ipv6.frags.mem) > net->ipv6.frags.high_thresh) ip6_evictor(net, ip6_dst_idev(skb->dst)); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 06faa46920e..65053fba8c1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -208,7 +208,7 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; struct net_device *loopback_dev = - dev->nd_net->loopback_dev; + dev_net(dev)->loopback_dev; if (dev != loopback_dev && idev != NULL && idev->dev == dev) { struct inet6_dev *loopback_idev = @@ -433,7 +433,7 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) RT6_TRACE("%s() => %p\n", __func__, match); - net = rt0->rt6i_dev->nd_net; + net = dev_net(rt0->rt6i_dev); return (match ? match : net->ipv6.ip6_null_entry); } @@ -441,7 +441,7 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, struct in6_addr *gwaddr) { - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); struct route_info *rinfo = (struct route_info *) opt; struct in6_addr prefix_buf, *prefix; unsigned int pref; @@ -607,7 +607,7 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info) int ip6_ins_rt(struct rt6_info *rt) { struct nl_info info = { - .nl_net = rt->rt6i_dev->nd_net, + .nl_net = dev_net(rt->rt6i_dev), }; return __ip6_ins_rt(rt, &info); } @@ -745,7 +745,7 @@ static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table * void ip6_route_input(struct sk_buff *skb) { struct ipv6hdr *iph = ipv6_hdr(skb); - struct net *net = skb->dev->nd_net; + struct net *net = dev_net(skb->dev); int flags = RT6_LOOKUP_F_HAS_SADDR; struct flowi fl = { .iif = skb->dev->ifindex, @@ -928,7 +928,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, { struct rt6_info *rt; struct inet6_dev *idev = in6_dev_get(dev); - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); if (unlikely(idev == NULL)) return NULL; @@ -1252,7 +1252,7 @@ install_route: rt->rt6i_idev = idev; rt->rt6i_table = table; - cfg->fc_nlinfo.nl_net = dev->nd_net; + cfg->fc_nlinfo.nl_net = dev_net(dev); return __ip6_ins_rt(rt, &cfg->fc_nlinfo); @@ -1270,7 +1270,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) { int err; struct fib6_table *table; - struct net *net = rt->rt6i_dev->nd_net; + struct net *net = dev_net(rt->rt6i_dev); if (rt == net->ipv6.ip6_null_entry) return -ENOENT; @@ -1289,7 +1289,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) int ip6_del_rt(struct rt6_info *rt) { struct nl_info info = { - .nl_net = rt->rt6i_dev->nd_net, + .nl_net = dev_net(rt->rt6i_dev), }; return __ip6_del_rt(rt, &info); } @@ -1401,7 +1401,7 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, struct net_device *dev) { int flags = RT6_LOOKUP_F_HAS_SADDR; - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); struct ip6rd_flowi rdfl = { .fl = { .oif = dev->ifindex, @@ -1428,7 +1428,7 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *src, { struct rt6_info *rt, *nrt = NULL; struct netevent_redirect netevent; - struct net *net = neigh->dev->nd_net; + struct net *net = dev_net(neigh->dev); rt = ip6_route_redirect(dest, src, saddr, neigh->dev); @@ -1477,7 +1477,7 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *src, nrt->rt6i_nexthop = neigh_clone(neigh); /* Reset pmtu, it may be better */ nrt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev); - nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(neigh->dev->nd_net, + nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dev_net(neigh->dev), dst_mtu(&nrt->u.dst)); if (ip6_ins_rt(nrt)) @@ -1506,7 +1506,7 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, struct net_device *dev, u32 pmtu) { struct rt6_info *rt, *nrt; - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); int allfrag = 0; rt = rt6_lookup(net, daddr, saddr, dev->ifindex, 0); @@ -1583,7 +1583,7 @@ out: static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) { - struct net *net = ort->rt6i_dev->nd_net; + struct net *net = dev_net(ort->rt6i_dev); struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops); if (rt) { @@ -1682,7 +1682,7 @@ struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *d struct rt6_info *rt; struct fib6_table *table; - table = fib6_get_table(dev->nd_net, RT6_TABLE_DFLT); + table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT); if (table == NULL) return NULL; @@ -1713,7 +1713,7 @@ struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr, RTF_UP | RTF_EXPIRES | RTF_PREF(pref), .fc_nlinfo.pid = 0, .fc_nlinfo.nlh = NULL, - .fc_nlinfo.nl_net = dev->nd_net, + .fc_nlinfo.nl_net = dev_net(dev), }; ipv6_addr_copy(&cfg.fc_gateway, gwaddr); @@ -1862,7 +1862,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, const struct in6_addr *addr, int anycast) { - struct net *net = idev->dev->nd_net; + struct net *net = dev_net(idev->dev); struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops); if (rt == NULL) @@ -1939,7 +1939,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg; struct inet6_dev *idev; - struct net *net = arg->dev->nd_net; + struct net *net = dev_net(arg->dev); /* In IPv6 pmtu discovery is not optional, so that RTAX_MTU lock cannot disable it. @@ -1983,7 +1983,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned mtu) .mtu = mtu, }; - fib6_clean_all(dev->nd_net, rt6_mtu_change_route, 0, &arg); + fib6_clean_all(dev_net(dev), rt6_mtu_change_route, 0, &arg); } static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { @@ -2321,7 +2321,7 @@ static int ip6_route_dev_notify(struct notifier_block *this, unsigned long event, void *data) { struct net_device *dev = (struct net_device *)data; - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) { net->ipv6.ip6_null_entry->u.dst.dev = dev; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8dd72966ff7..086deffff9c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -321,7 +321,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct tcp_sock *tp; __u32 seq; - sk = inet6_lookup(skb->dev->nd_net, &tcp_hashinfo, &hdr->daddr, + sk = inet6_lookup(dev_net(skb->dev), &tcp_hashinfo, &hdr->daddr, th->dest, &hdr->saddr, th->source, skb->dev->ifindex); if (sk == NULL) { @@ -988,7 +988,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) struct tcphdr *th = tcp_hdr(skb), *t1; struct sk_buff *buff; struct flowi fl; - struct net *net = skb->dst->dev->nd_net; + struct net *net = dev_net(skb->dst->dev); struct sock *ctl_sk = net->ipv6.tcp_sk; unsigned int tot_len = sizeof(*th); #ifdef CONFIG_TCP_MD5SIG @@ -1093,7 +1093,7 @@ static void tcp_v6_send_ack(struct tcp_timewait_sock *tw, struct tcphdr *th = tcp_hdr(skb), *t1; struct sk_buff *buff; struct flowi fl; - struct net *net = skb->dev->nd_net; + struct net *net = dev_net(skb->dev); struct sock *ctl_sk = net->ipv6.tcp_sk; unsigned int tot_len = sizeof(struct tcphdr); __be32 *topt; @@ -1739,7 +1739,7 @@ static int tcp_v6_rcv(struct sk_buff *skb) TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(ipv6_hdr(skb)); TCP_SKB_CB(skb)->sacked = 0; - sk = __inet6_lookup(skb->dev->nd_net, &tcp_hashinfo, + sk = __inet6_lookup(dev_net(skb->dev), &tcp_hashinfo, &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), inet6_iif(skb)); @@ -1822,7 +1822,7 @@ do_time_wait: { struct sock *sk2; - sk2 = inet6_lookup_listener(skb->dev->nd_net, &tcp_hashinfo, + sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, &ipv6_hdr(skb)->daddr, ntohs(th->dest), inet6_iif(skb)); if (sk2 != NULL) { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 593d3efadaf..6683c04b427 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -235,7 +235,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct sock *sk; int err; - sk = __udp6_lib_lookup(skb->dev->nd_net, daddr, uh->dest, + sk = __udp6_lib_lookup(dev_net(skb->dev), daddr, uh->dest, saddr, uh->source, inet6_iif(skb), udptable); if (sk == NULL) return; @@ -483,7 +483,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], * check socket cache ... must talk to Alan about his plans * for sock caches... i'll skip this for now. */ - sk = __udp6_lib_lookup(skb->dev->nd_net, saddr, uh->source, + sk = __udp6_lib_lookup(dev_net(skb->dev), saddr, uh->source, daddr, uh->dest, inet6_iif(skb), udptable); if (sk == NULL) { diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index d92d1fceb8c..8f1e0543b3c 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -247,7 +247,7 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, xdst = (struct xfrm_dst *)dst; if (xdst->u.rt6.rt6i_idev->dev == dev) { struct inet6_dev *loopback_idev = - in6_dev_get(dev->nd_net->loopback_dev); + in6_dev_get(dev_net(dev)->loopback_dev); BUG_ON(!loopback_idev); do { diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index c76a9523091..81ae8735f5e 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -335,7 +335,7 @@ static int ipxitf_device_event(struct notifier_block *notifier, struct net_device *dev = ptr; struct ipx_interface *i, *tmp; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (event != NETDEV_DOWN && event != NETDEV_UP) @@ -1636,7 +1636,7 @@ static int ipx_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_ty u16 ipx_pktsize; int rc = 0; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto drop; /* Not ours */ diff --git a/net/irda/irlap_frame.c b/net/irda/irlap_frame.c index a38b231c868..90894534f3c 100644 --- a/net/irda/irlap_frame.c +++ b/net/irda/irlap_frame.c @@ -1326,7 +1326,7 @@ int irlap_driver_rcv(struct sk_buff *skb, struct net_device *dev, int command; __u8 control; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto out; /* FIXME: should we get our own field? */ diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index b9143d2a04e..a69c5c427fe 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -146,7 +146,7 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, int (*rcv)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto drop; /* diff --git a/net/netfilter/core.c b/net/netfilter/core.c index ec05684c56d..292fa28146f 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -168,7 +168,7 @@ int nf_hook_slow(int pf, unsigned int hook, struct sk_buff *skb, #ifdef CONFIG_NET_NS struct net *net; - net = indev == NULL ? outdev->nd_net : indev->nd_net; + net = indev == NULL ? dev_net(outdev) : dev_net(indev); if (net != &init_net) return 1; #endif diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 012cb691082..81fb048add8 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -557,7 +557,7 @@ nfqnl_rcv_dev_event(struct notifier_block *this, { struct net_device *dev = ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; /* Drop any packets associated with the downed device */ diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 4478f2f6079..a547c6320eb 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -954,7 +954,7 @@ static int netlbl_unlhsh_netdev_handler(struct notifier_block *this, struct net_device *dev = ptr; struct netlbl_unlhsh_iface *iface = NULL; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; /* XXX - should this be a check for NETDEV_DOWN or _UNREGISTER? */ diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 972250c974f..a270ebf9f76 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -106,7 +106,7 @@ static int nr_device_event(struct notifier_block *this, unsigned long event, voi { struct net_device *dev = (struct net_device *)ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (event != NETDEV_DOWN) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a56ed2120e0..baa290d3444 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -263,7 +263,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct if (skb->pkt_type == PACKET_LOOPBACK) goto out; - if (dev->nd_net != sk->sk_net) + if (dev_net(dev) != sk->sk_net) goto out; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) @@ -451,7 +451,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet sk = pt->af_packet_priv; po = pkt_sk(sk); - if (dev->nd_net != sk->sk_net) + if (dev_net(dev) != sk->sk_net) goto drop; skb->dev = dev; @@ -568,7 +568,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe sk = pt->af_packet_priv; po = pkt_sk(sk); - if (dev->nd_net != sk->sk_net) + if (dev_net(dev) != sk->sk_net) goto drop; if (dev->header_ops) { @@ -1450,7 +1450,7 @@ static int packet_notifier(struct notifier_block *this, unsigned long msg, void struct sock *sk; struct hlist_node *node; struct net_device *dev = data; - struct net *net = dev->nd_net; + struct net *net = dev_net(dev); read_lock(&net->packet.sklist_lock); sk_for_each(sk, node, &net->packet.sklist) { diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 4a31a81059a..1a7f143cf74 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -197,7 +197,7 @@ static int rose_device_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = (struct net_device *)ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (event != NETDEV_DOWN) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index beea2fb18b1..2faa0d8839e 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -630,7 +630,7 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, struct sctp_sockaddr_entry *temp; int found = 0; - if (ifa->ifa_dev->dev->nd_net != &init_net) + if (dev_net(ifa->ifa_dev->dev) != &init_net) return NOTIFY_DONE; switch (ev) { diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index 3bbef2ab22a..9cd35eec3e7 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -101,7 +101,7 @@ static int recv_msg(struct sk_buff *buf, struct net_device *dev, struct eth_bearer *eb_ptr = (struct eth_bearer *)pt->af_packet_priv; u32 size; - if (dev->nd_net != &init_net) { + if (dev_net(dev) != &init_net) { kfree_skb(buf); return 0; } @@ -198,7 +198,7 @@ static int recv_notification(struct notifier_block *nb, unsigned long evt, struct eth_bearer *eb_ptr = ð_bearers[0]; struct eth_bearer *stop = ð_bearers[MAX_ETH_BEARERS]; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; while ((eb_ptr->dev != dev)) { diff --git a/net/wireless/wext.c b/net/wireless/wext.c index 2c569b63e7d..947188a5b93 100644 --- a/net/wireless/wext.c +++ b/net/wireless/wext.c @@ -1157,7 +1157,7 @@ static void rtmsg_iwinfo(struct net_device *dev, char *event, int event_len) struct sk_buff *skb; int err; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 339ca4a8e89..7a46ea73fe2 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -191,7 +191,7 @@ static int x25_device_event(struct notifier_block *this, unsigned long event, struct net_device *dev = ptr; struct x25_neigh *nb; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (dev->type == ARPHRD_X25 diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index f0679d28311..3ff206c0ae9 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -95,7 +95,7 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev, struct sk_buff *nskb; struct x25_neigh *nb; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto drop; nskb = skb_copy(skb, GFP_ATOMIC); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 8e588f20c60..15d73e47cc2 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2079,7 +2079,7 @@ static int stale_bundle(struct dst_entry *dst) void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { while ((dst = dst->child) && dst->xfrm && dst->dev == dev) { - dst->dev = dev->nd_net->loopback_dev; + dst->dev = dev_net(dev)->loopback_dev; dev_hold(dst->dev); dev_put(dev); } @@ -2350,7 +2350,7 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void { struct net_device *dev = ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; switch (event) { diff --git a/security/selinux/netif.c b/security/selinux/netif.c index 013d3117a86..9c8a82aa8ba 100644 --- a/security/selinux/netif.c +++ b/security/selinux/netif.c @@ -281,7 +281,7 @@ static int sel_netif_netdev_notifier_handler(struct notifier_block *this, { struct net_device *dev = ptr; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (event == NETDEV_DOWN) -- cgit v1.2.3-70-g09d2 From c29a0bc4dfc4d833eb702b1929cec96a3eeb9f7a Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 31 Mar 2008 19:41:46 -0700 Subject: [SOCK][NETNS]: Add a struct net argument to sock_prot_inuse_add and _get. This counter is about to become per-proto-and-per-net, so we'll need two arguments to determine which cell in this "table" to work with. All the places, but proc already pass proper net to it - proc will be tuned a bit later. Some indentation with spaces in proc files is done to keep the file coding style consistent. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/net/sock.h | 7 ++++--- include/net/udp.h | 2 +- net/core/sock.c | 4 ++-- net/ipv4/inet_hashtables.c | 8 ++++---- net/ipv4/inet_timewait_sock.c | 2 +- net/ipv4/proc.c | 11 +++++++---- net/ipv4/raw.c | 4 ++-- net/ipv4/udp.c | 2 +- net/ipv6/inet6_hashtables.c | 4 ++-- net/ipv6/ipv6_sockglue.c | 10 ++++++---- net/ipv6/proc.c | 8 ++++---- 11 files changed, 34 insertions(+), 28 deletions(-) (limited to 'net/ipv6/proc.c') diff --git a/include/net/sock.h b/include/net/sock.h index 2a3344f666a..f4fdd101c9a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -635,10 +635,11 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #ifdef CONFIG_PROC_FS /* Called with local bh disabled */ -extern void sock_prot_inuse_add(struct proto *prot, int inc); -extern int sock_prot_inuse_get(struct proto *proto); +extern void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc); +extern int sock_prot_inuse_get(struct net *net, struct proto *proto); #else -static void inline sock_prot_inuse_add(struct proto *prot, int inc) +static void inline sock_prot_inuse_add(struct net *net, struct proto *prot, + int inc) { } #endif diff --git a/include/net/udp.h b/include/net/udp.h index 24a41fa3164..3e55a99b0ba 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -115,7 +115,7 @@ 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_inuse_add(sk->sk_prot, -1); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); } write_unlock_bh(&udp_hash_lock); } diff --git a/net/core/sock.c b/net/core/sock.c index c1ae56eb96e..6f36ab91bb5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1949,13 +1949,13 @@ struct prot_inuse { static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR); static DEFINE_PER_CPU(struct prot_inuse, prot_inuse); -void sock_prot_inuse_add(struct proto *prot, int val) +void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) { __get_cpu_var(prot_inuse).val[prot->inuse_idx] += val; } EXPORT_SYMBOL_GPL(sock_prot_inuse_add); -int sock_prot_inuse_get(struct proto *prot) +int sock_prot_inuse_get(struct net *net, struct proto *prot) { int cpu, idx = prot->inuse_idx; int res = 0; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 1b6ff513c75..32ca2f8b581 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -288,7 +288,7 @@ unique: sk->sk_hash = hash; BUG_TRAP(sk_unhashed(sk)); __sk_add_node(sk, &head->chain); - sock_prot_inuse_add(sk->sk_prot, 1); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); write_unlock(lock); if (twp) { @@ -332,7 +332,7 @@ void __inet_hash_nolisten(struct sock *sk) write_lock(lock); __sk_add_node(sk, list); - sock_prot_inuse_add(sk->sk_prot, 1); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); write_unlock(lock); } EXPORT_SYMBOL_GPL(__inet_hash_nolisten); @@ -354,7 +354,7 @@ static void __inet_hash(struct sock *sk) inet_listen_wlock(hashinfo); __sk_add_node(sk, list); - sock_prot_inuse_add(sk->sk_prot, 1); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); write_unlock(lock); wake_up(&hashinfo->lhash_wait); } @@ -387,7 +387,7 @@ void inet_unhash(struct sock *sk) } if (__sk_del_node_init(sk)) - sock_prot_inuse_add(sk->sk_prot, -1); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); write_unlock_bh(lock); out: if (sk->sk_state == TCP_LISTEN) diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index f12bc24de46..a74137866fb 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -91,7 +91,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, /* Step 2: Remove SK from established hash. */ if (__sk_del_node_init(sk)) - sock_prot_inuse_add(sk->sk_prot, -1); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); /* Step 3: Hash TW into TIMEWAIT chain. */ inet_twsk_add_node(tw, &ehead->twchain); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index d63474c6b40..8156c26f933 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -53,14 +53,17 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) { socket_seq_show(seq); seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n", - sock_prot_inuse_get(&tcp_prot), + sock_prot_inuse_get(&init_net, &tcp_prot), atomic_read(&tcp_orphan_count), tcp_death_row.tw_count, atomic_read(&tcp_sockets_allocated), atomic_read(&tcp_memory_allocated)); - seq_printf(seq, "UDP: inuse %d mem %d\n", sock_prot_inuse_get(&udp_prot), + seq_printf(seq, "UDP: inuse %d mem %d\n", + sock_prot_inuse_get(&init_net, &udp_prot), atomic_read(&udp_memory_allocated)); - seq_printf(seq, "UDPLITE: inuse %d\n", sock_prot_inuse_get(&udplite_prot)); - seq_printf(seq, "RAW: inuse %d\n", sock_prot_inuse_get(&raw_prot)); + seq_printf(seq, "UDPLITE: inuse %d\n", + sock_prot_inuse_get(&init_net, &udplite_prot)); + seq_printf(seq, "RAW: inuse %d\n", + sock_prot_inuse_get(&init_net, &raw_prot)); seq_printf(seq, "FRAG: inuse %d memory %d\n", ip_frag_nqueues(&init_net), ip_frag_mem(&init_net)); return 0; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 34920504855..11d7f753a82 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -93,7 +93,7 @@ void raw_hash_sk(struct sock *sk) write_lock_bh(&h->lock); sk_add_node(sk, head); - sock_prot_inuse_add(sk->sk_prot, 1); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); write_unlock_bh(&h->lock); } EXPORT_SYMBOL_GPL(raw_hash_sk); @@ -104,7 +104,7 @@ void raw_unhash_sk(struct sock *sk) write_lock_bh(&h->lock); if (sk_del_node_init(sk)) - sock_prot_inuse_add(sk->sk_prot, -1); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); write_unlock_bh(&h->lock); } EXPORT_SYMBOL_GPL(raw_unhash_sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 9143645f9a1..03bd7069748 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -231,7 +231,7 @@ gotit: if (sk_unhashed(sk)) { head = &udptable[snum & (UDP_HTABLE_SIZE - 1)]; sk_add_node(sk, head); - sock_prot_inuse_add(sk->sk_prot, 1); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); } error = 0; fail: diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 340c7d42b83..580014aea4d 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -43,7 +43,7 @@ void __inet6_hash(struct sock *sk) } __sk_add_node(sk, list); - sock_prot_inuse_add(sk->sk_prot, 1); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); write_unlock(lock); } EXPORT_SYMBOL(__inet6_hash); @@ -204,7 +204,7 @@ unique: BUG_TRAP(sk_unhashed(sk)); __sk_add_node(sk, &head->chain); sk->sk_hash = hash; - sock_prot_inuse_add(sk->sk_prot, 1); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); write_unlock(lock); if (twp != NULL) { diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index d3d93d752e1..4195ac92345 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -155,10 +155,11 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (sk->sk_protocol == IPPROTO_TCP) { struct inet_connection_sock *icsk = inet_csk(sk); + struct net *net = sock_net(sk); local_bh_disable(); - sock_prot_inuse_add(sk->sk_prot, -1); - sock_prot_inuse_add(&tcp_prot, 1); + sock_prot_inuse_add(net, sk->sk_prot, -1); + sock_prot_inuse_add(net, &tcp_prot, 1); local_bh_enable(); sk->sk_prot = &tcp_prot; icsk->icsk_af_ops = &ipv4_specific; @@ -167,12 +168,13 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } else { struct proto *prot = &udp_prot; + struct net *net = sock_net(sk); if (sk->sk_protocol == IPPROTO_UDPLITE) prot = &udplite_prot; local_bh_disable(); - sock_prot_inuse_add(sk->sk_prot, -1); - sock_prot_inuse_add(prot, 1); + sock_prot_inuse_add(net, sk->sk_prot, -1); + sock_prot_inuse_add(net, prot, 1); local_bh_enable(); sk->sk_prot = prot; sk->sk_socket->ops = &inet_dgram_ops; diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 364dc332532..4b9d5a90572 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -36,13 +36,13 @@ static struct proc_dir_entry *proc_net_devsnmp6; static int sockstat6_seq_show(struct seq_file *seq, void *v) { seq_printf(seq, "TCP6: inuse %d\n", - sock_prot_inuse_get(&tcpv6_prot)); + sock_prot_inuse_get(&init_net, &tcpv6_prot)); seq_printf(seq, "UDP6: inuse %d\n", - sock_prot_inuse_get(&udpv6_prot)); + sock_prot_inuse_get(&init_net, &udpv6_prot)); seq_printf(seq, "UDPLITE6: inuse %d\n", - sock_prot_inuse_get(&udplitev6_prot)); + sock_prot_inuse_get(&init_net, &udplitev6_prot)); seq_printf(seq, "RAW6: inuse %d\n", - sock_prot_inuse_get(&rawv6_prot)); + sock_prot_inuse_get(&init_net, &rawv6_prot)); seq_printf(seq, "FRAG6: inuse %d memory %d\n", ip6_frag_nqueues(&init_net), ip6_frag_mem(&init_net)); return 0; -- cgit v1.2.3-70-g09d2 From d0538ca3554a3985c09921903cf8f5e38fa56123 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 31 Mar 2008 19:42:37 -0700 Subject: [SOCK][NETNS]: Register sockstat(6) files in each net. Currently they live in init_net only, but now almost all the info they can provide is available per-net. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/ipv4/proc.c | 27 ++++++++++++++++++++++----- net/ipv6/proc.c | 29 ++++++++++++++++++++++++----- 2 files changed, 46 insertions(+), 10 deletions(-) (limited to 'net/ipv6/proc.c') diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 8156c26f933..24ae23bb512 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -426,25 +426,42 @@ static const struct file_operations netstat_seq_fops = { .release = single_release, }; +static __net_init int ip_proc_init_net(struct net *net) +{ + if (!proc_net_fops_create(net, "sockstat", S_IRUGO, &sockstat_seq_fops)) + return -ENOMEM; + return 0; +} + +static __net_exit void ip_proc_exit_net(struct net *net) +{ + proc_net_remove(net, "sockstat"); +} + +static __net_initdata struct pernet_operations ip_proc_ops = { + .init = ip_proc_init_net, + .exit = ip_proc_exit_net, +}; + int __init ip_misc_proc_init(void) { int rc = 0; + if (register_pernet_subsys(&ip_proc_ops)) + goto out_pernet; + if (!proc_net_fops_create(&init_net, "netstat", S_IRUGO, &netstat_seq_fops)) goto out_netstat; if (!proc_net_fops_create(&init_net, "snmp", S_IRUGO, &snmp_seq_fops)) goto out_snmp; - - if (!proc_net_fops_create(&init_net, "sockstat", S_IRUGO, &sockstat_seq_fops)) - goto out_sockstat; out: return rc; -out_sockstat: - proc_net_remove(&init_net, "snmp"); out_snmp: proc_net_remove(&init_net, "netstat"); out_netstat: + unregister_pernet_subsys(&ip_proc_ops); +out_pernet: rc = -ENOMEM; goto out; } diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 4b9d5a90572..562366015e5 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -243,27 +243,45 @@ int snmp6_unregister_dev(struct inet6_dev *idev) return 0; } +static int ipv6_proc_init_net(struct net *net) +{ + if (!proc_net_fops_create(net, "sockstat6", S_IRUGO, + &sockstat6_seq_fops)) + return -ENOMEM; + return 0; +} + +static void ipv6_proc_exit_net(struct net *net) +{ + proc_net_remove(net, "sockstat6"); +} + +static struct pernet_operations ipv6_proc_ops = { + .init = ipv6_proc_init_net, + .exit = ipv6_proc_exit_net, +}; + int __init ipv6_misc_proc_init(void) { int rc = 0; + if (register_pernet_subsys(&ipv6_proc_ops)) + goto proc_net_fail; + if (!proc_net_fops_create(&init_net, "snmp6", S_IRUGO, &snmp6_seq_fops)) goto proc_snmp6_fail; proc_net_devsnmp6 = proc_mkdir("dev_snmp6", init_net.proc_net); if (!proc_net_devsnmp6) goto proc_dev_snmp6_fail; - - if (!proc_net_fops_create(&init_net, "sockstat6", S_IRUGO, &sockstat6_seq_fops)) - goto proc_sockstat6_fail; out: return rc; -proc_sockstat6_fail: - proc_net_remove(&init_net, "dev_snmp6"); proc_dev_snmp6_fail: proc_net_remove(&init_net, "snmp6"); proc_snmp6_fail: + unregister_pernet_subsys(&ipv6_proc_ops); +proc_net_fail: rc = -ENOMEM; goto out; } @@ -273,5 +291,6 @@ void ipv6_misc_proc_exit(void) proc_net_remove(&init_net, "sockstat6"); proc_net_remove(&init_net, "dev_snmp6"); proc_net_remove(&init_net, "snmp6"); + unregister_pernet_subsys(&ipv6_proc_ops); } -- cgit v1.2.3-70-g09d2 From dfb12eb70fc926562488515a9596c88b8eadc545 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 31 Mar 2008 19:43:43 -0700 Subject: [IPV6][NETNS]: Display per-net info in sockstat6 file. Do with the sockstat6 file what we've already done for the sockstat. Same good side effect - ipv6 reassembling stats are now shown per-net. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/ipv6/proc.c | 41 ++++++++++++++++++++++++++++++++++------- 1 file changed, 34 insertions(+), 7 deletions(-) (limited to 'net/ipv6/proc.c') diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 562366015e5..ca8b82f96fe 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -35,16 +35,18 @@ static struct proc_dir_entry *proc_net_devsnmp6; static int sockstat6_seq_show(struct seq_file *seq, void *v) { + struct net *net = seq->private; + seq_printf(seq, "TCP6: inuse %d\n", - sock_prot_inuse_get(&init_net, &tcpv6_prot)); + sock_prot_inuse_get(net, &tcpv6_prot)); seq_printf(seq, "UDP6: inuse %d\n", - sock_prot_inuse_get(&init_net, &udpv6_prot)); + sock_prot_inuse_get(net, &udpv6_prot)); seq_printf(seq, "UDPLITE6: inuse %d\n", - sock_prot_inuse_get(&init_net, &udplitev6_prot)); + sock_prot_inuse_get(net, &udplitev6_prot)); seq_printf(seq, "RAW6: inuse %d\n", - sock_prot_inuse_get(&init_net, &rawv6_prot)); + sock_prot_inuse_get(net, &rawv6_prot)); seq_printf(seq, "FRAG6: inuse %d memory %d\n", - ip6_frag_nqueues(&init_net), ip6_frag_mem(&init_net)); + ip6_frag_nqueues(net), ip6_frag_mem(net)); return 0; } @@ -183,7 +185,32 @@ static int snmp6_seq_show(struct seq_file *seq, void *v) static int sockstat6_seq_open(struct inode *inode, struct file *file) { - return single_open(file, sockstat6_seq_show, NULL); + int err; + struct net *net; + + err = -ENXIO; + net = get_proc_net(inode); + if (net == NULL) + goto err_net; + + err = single_open(file, sockstat6_seq_show, net); + if (err < 0) + goto err_open; + + return 0; + +err_open: + put_net(net); +err_net: + return err; +} + +static int sockstat6_seq_release(struct inode *inode, struct file *file) +{ + struct net *net = ((struct seq_file *)file->private_data)->private; + + put_net(net); + return single_release(inode, file); } static const struct file_operations sockstat6_seq_fops = { @@ -191,7 +218,7 @@ static const struct file_operations sockstat6_seq_fops = { .open = sockstat6_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = sockstat6_seq_release, }; static int snmp6_seq_open(struct inode *inode, struct file *file) -- cgit v1.2.3-70-g09d2