diff options
Diffstat (limited to 'net/ipv6')
34 files changed, 1040 insertions, 638 deletions
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index b39e0494059..6460eec834b 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -8,7 +8,7 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o sit.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o raw.o \ protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ exthdrs.o sysctl_net_ipv6.o datagram.o proc.o \ - ip6_flowlabel.o ipv6_syms.o + ip6_flowlabel.o ipv6_syms.o netfilter.o ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \ xfrm6_output.o @@ -23,3 +23,5 @@ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o obj-y += exthdrs_core.o + +obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 77004b9456c..937ad32db77 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1041,9 +1041,9 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; const struct in6_addr *sk2_rcv_saddr6 = tcp_v6_rcv_saddr(sk2); u32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr; - u32 sk2_rcv_saddr = tcp_v4_rcv_saddr(sk2); + u32 sk2_rcv_saddr = inet_rcv_saddr(sk2); int sk_ipv6only = ipv6_only_sock(sk); - int sk2_ipv6only = tcp_v6_ipv6only(sk2); + int sk2_ipv6only = inet_v6_ipv6only(sk2); int addr_type = ipv6_addr_type(sk_rcv_saddr6); int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; @@ -1126,7 +1126,7 @@ void addrconf_leave_solict(struct inet6_dev *idev, struct in6_addr *addr) __ipv6_dev_mc_dec(idev, &maddr); } -void addrconf_join_anycast(struct inet6_ifaddr *ifp) +static void addrconf_join_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); @@ -1135,7 +1135,7 @@ void addrconf_join_anycast(struct inet6_ifaddr *ifp) ipv6_dev_ac_inc(ifp->idev->dev, &addr); } -void addrconf_leave_anycast(struct inet6_ifaddr *ifp) +static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); @@ -2858,16 +2858,16 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) skb = alloc_skb(size, GFP_ATOMIC); if (!skb) { - netlink_set_err(rtnl, 0, RTMGRP_IPV6_IFADDR, ENOBUFS); + netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFADDR, ENOBUFS); return; } if (inet6_fill_ifaddr(skb, ifa, current->pid, 0, event, 0) < 0) { kfree_skb(skb); - netlink_set_err(rtnl, 0, RTMGRP_IPV6_IFADDR, EINVAL); + netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFADDR, EINVAL); return; } - NETLINK_CB(skb).dst_groups = RTMGRP_IPV6_IFADDR; - netlink_broadcast(rtnl, skb, 0, RTMGRP_IPV6_IFADDR, GFP_ATOMIC); + NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_IFADDR; + netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_IFADDR, GFP_ATOMIC); } static void inline ipv6_store_devconf(struct ipv6_devconf *cnf, @@ -2994,16 +2994,16 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev) skb = alloc_skb(size, GFP_ATOMIC); if (!skb) { - netlink_set_err(rtnl, 0, RTMGRP_IPV6_IFINFO, ENOBUFS); + netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFINFO, ENOBUFS); return; } if (inet6_fill_ifinfo(skb, idev, current->pid, 0, event, 0) < 0) { kfree_skb(skb); - netlink_set_err(rtnl, 0, RTMGRP_IPV6_IFINFO, EINVAL); + netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFINFO, EINVAL); return; } - NETLINK_CB(skb).dst_groups = RTMGRP_IPV6_IFINFO; - netlink_broadcast(rtnl, skb, 0, RTMGRP_IPV6_IFINFO, GFP_ATOMIC); + NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_IFINFO; + netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_IFINFO, GFP_ATOMIC); } static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, @@ -3054,16 +3054,16 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, skb = alloc_skb(size, GFP_ATOMIC); if (!skb) { - netlink_set_err(rtnl, 0, RTMGRP_IPV6_PREFIX, ENOBUFS); + netlink_set_err(rtnl, 0, RTNLGRP_IPV6_PREFIX, ENOBUFS); return; } if (inet6_fill_prefix(skb, idev, pinfo, current->pid, 0, event, 0) < 0) { kfree_skb(skb); - netlink_set_err(rtnl, 0, RTMGRP_IPV6_PREFIX, EINVAL); + netlink_set_err(rtnl, 0, RTNLGRP_IPV6_PREFIX, EINVAL); return; } - NETLINK_CB(skb).dst_groups = RTMGRP_IPV6_PREFIX; - netlink_broadcast(rtnl, skb, 0, RTMGRP_IPV6_PREFIX, GFP_ATOMIC); + NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_PREFIX; + netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_PREFIX, GFP_ATOMIC); } static struct rtnetlink_link inet6_rtnetlink_table[RTM_NR_MSGTYPES] = { diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 28d9bcab097..4f8795af2ed 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -44,6 +44,7 @@ #include <linux/netdevice.h> #include <linux/icmpv6.h> #include <linux/smp_lock.h> +#include <linux/netfilter_ipv6.h> #include <net/ip.h> #include <net/ipv6.h> @@ -66,45 +67,14 @@ MODULE_AUTHOR("Cast of dozens"); MODULE_DESCRIPTION("IPv6 protocol stack for Linux"); MODULE_LICENSE("GPL"); -/* IPv6 procfs goodies... */ - -#ifdef CONFIG_PROC_FS -extern int raw6_proc_init(void); -extern void raw6_proc_exit(void); -extern int tcp6_proc_init(void); -extern void tcp6_proc_exit(void); -extern int udp6_proc_init(void); -extern void udp6_proc_exit(void); -extern int ipv6_misc_proc_init(void); -extern void ipv6_misc_proc_exit(void); -extern int ac6_proc_init(void); -extern void ac6_proc_exit(void); -extern int if6_proc_init(void); -extern void if6_proc_exit(void); -#endif - int sysctl_ipv6_bindv6only; -#ifdef INET_REFCNT_DEBUG -atomic_t inet6_sock_nr; -EXPORT_SYMBOL(inet6_sock_nr); -#endif - /* The inetsw table contains everything that inet_create needs to * build a new socket. */ static struct list_head inetsw6[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw6_lock); -static void inet6_sock_destruct(struct sock *sk) -{ - inet_sock_destruct(sk); - -#ifdef INET_REFCNT_DEBUG - atomic_dec(&inet6_sock_nr); -#endif -} - static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) { const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo); @@ -185,7 +155,7 @@ static int inet6_create(struct socket *sock, int protocol) inet->hdrincl = 1; } - sk->sk_destruct = inet6_sock_destruct; + sk->sk_destruct = inet_sock_destruct; sk->sk_family = PF_INET6; sk->sk_protocol = protocol; @@ -212,12 +182,17 @@ static int inet6_create(struct socket *sock, int protocol) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; + /* + * Increment only the relevant sk_prot->socks debug field, this changes + * the previous behaviour of incrementing both the equivalent to + * answer->prot->socks (inet6_sock_nr) and inet_sock_nr. + * + * This allows better debug granularity as we'll know exactly how many + * UDPv6, TCPv6, etc socks were allocated, not the sum of all IPv6 + * transport protocol socks. -acme + */ + sk_refcnt_debug_inc(sk); - -#ifdef INET_REFCNT_DEBUG - atomic_inc(&inet6_sock_nr); - atomic_inc(&inet_sock_nr); -#endif if (inet->num) { /* It assumes that any protocol which allows * the user to assign a number at socket @@ -513,11 +488,6 @@ static struct net_proto_family inet6_family_ops = { .owner = THIS_MODULE, }; -#ifdef CONFIG_SYSCTL -extern void ipv6_sysctl_register(void); -extern void ipv6_sysctl_unregister(void); -#endif - /* Same as inet6_dgram_ops, sans udp_poll. */ static struct proto_ops inet6_sockraw_ops = { .family = PF_INET6, @@ -684,8 +654,6 @@ static void cleanup_ipv6_mibs(void) snmp6_mib_free((void **)udp_stats_in6); } -extern int ipv6_misc_proc_init(void); - static int __init inet6_init(void) { struct sk_buff *dummy_skb; @@ -757,6 +725,9 @@ static int __init inet6_init(void) err = igmp6_init(&inet6_family_ops); if (err) goto igmp_fail; + err = ipv6_netfilter_init(); + if (err) + goto netfilter_fail; /* Create /proc/foo6 entries. */ #ifdef CONFIG_PROC_FS err = -ENOMEM; @@ -813,6 +784,8 @@ proc_tcp6_fail: raw6_proc_exit(); proc_raw6_fail: #endif + ipv6_netfilter_fini(); +netfilter_fail: igmp6_cleanup(); igmp_fail: ndisc_cleanup(); @@ -852,6 +825,7 @@ static void __exit inet6_exit(void) ip6_route_cleanup(); ipv6_packet_cleanup(); igmp6_cleanup(); + ipv6_netfilter_fini(); ndisc_cleanup(); icmpv6_cleanup(); #ifdef CONFIG_SYSCTL diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 986fdfdccbc..0ebfad907a0 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -131,10 +131,10 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len) case NEXTHDR_HOP: case NEXTHDR_DEST: if (!zero_out_mutable_opts(exthdr.opth)) { - LIMIT_NETDEBUG(printk( + LIMIT_NETDEBUG( KERN_WARNING "overrun %sopts\n", nexthdr == NEXTHDR_HOP ? - "hop" : "dest")); + "hop" : "dest"); return -EINVAL; } break; @@ -293,8 +293,7 @@ static int ah6_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struc skb_push(skb, skb->data - skb->nh.raw); ahp->icv(ahp, skb, ah->auth_data); if (memcmp(ah->auth_data, auth_data, ahp->icv_trunc_len)) { - LIMIT_NETDEBUG( - printk(KERN_WARNING "ipsec ah authentication error\n")); + LIMIT_NETDEBUG(KERN_WARNING "ipsec ah authentication error\n"); x->stats.integrity_failed++; goto free_out; } @@ -332,9 +331,9 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!x) return; - NETDEBUG(printk(KERN_DEBUG "pmtu discovery on SA AH/%08x/" - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", - ntohl(ah->spi), NIP6(iph->daddr))); + NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/" + "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + ntohl(ah->spi), NIP6(iph->daddr)); xfrm_state_put(x); } diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 5229365cd8b..01468fab3d3 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -29,6 +29,7 @@ #include <net/addrconf.h> #include <net/transp_v6.h> #include <net/ip6_route.h> +#include <net/tcp_states.h> #include <linux/errqueue.h> #include <asm/uaccess.h> @@ -588,8 +589,8 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, break; default: - LIMIT_NETDEBUG( - printk(KERN_DEBUG "invalid cmsg type: %d\n", cmsg->cmsg_type)); + LIMIT_NETDEBUG(KERN_DEBUG "invalid cmsg type: %d\n", + cmsg->cmsg_type); err = -EINVAL; break; }; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 324db62515a..e8bff9d3d96 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -212,8 +212,7 @@ static int esp6_input(struct xfrm_state *x, struct xfrm_decap_state *decap, stru padlen = nexthdr[0]; if (padlen+2 >= elen) { - LIMIT_NETDEBUG( - printk(KERN_WARNING "ipsec esp packet is garbage padlen=%d, elen=%d\n", padlen+2, elen)); + LIMIT_NETDEBUG(KERN_WARNING "ipsec esp packet is garbage padlen=%d, elen=%d\n", padlen+2, elen); ret = -EINVAL; goto out; } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index e0839eafc3a..5be6da2584e 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -424,8 +424,8 @@ static int ipv6_hop_ra(struct sk_buff *skb, int optoff) IP6CB(skb)->ra = optoff; return 1; } - LIMIT_NETDEBUG( - printk(KERN_DEBUG "ipv6_hop_ra: wrong RA length %d\n", skb->nh.raw[optoff+1])); + LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_ra: wrong RA length %d\n", + skb->nh.raw[optoff+1]); kfree_skb(skb); return 0; } @@ -437,8 +437,8 @@ static int ipv6_hop_jumbo(struct sk_buff *skb, int optoff) u32 pkt_len; if (skb->nh.raw[optoff+1] != 4 || (optoff&3) != 2) { - LIMIT_NETDEBUG( - printk(KERN_DEBUG "ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", skb->nh.raw[optoff+1])); + LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", + skb->nh.raw[optoff+1]); IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); goto drop; } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index ff3ec9822e3..5176fc655ea 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -67,7 +67,7 @@ #include <asm/uaccess.h> #include <asm/system.h> -DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics); +DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics) __read_mostly; /* * The ICMP socket(s). This is the most convenient way to flow control @@ -332,8 +332,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, * for now we don't know that. */ if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) { - LIMIT_NETDEBUG( - printk(KERN_DEBUG "icmpv6_send: addr_any/mcast source\n")); + LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: addr_any/mcast source\n"); return; } @@ -341,8 +340,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, * Never answer to a ICMP packet. */ if (is_ineligible(skb)) { - LIMIT_NETDEBUG( - printk(KERN_DEBUG "icmpv6_send: no reply to icmp error\n")); + LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: no reply to icmp error\n"); return; } @@ -393,8 +391,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, len = skb->len - msg.offset; len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) -sizeof(struct icmp6hdr)); if (len < 0) { - LIMIT_NETDEBUG( - printk(KERN_DEBUG "icmp: len problem\n")); + LIMIT_NETDEBUG(KERN_DEBUG "icmp: len problem\n"); goto out_dst_release; } @@ -551,7 +548,8 @@ static void icmpv6_notify(struct sk_buff *skb, int type, int code, u32 info) read_lock(&raw_v6_lock); if ((sk = sk_head(&raw_v6_htable[hash])) != NULL) { - while((sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr))) { + while((sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr, + skb->dev->ifindex))) { rawv6_err(sk, skb, NULL, type, code, inner_offset, info); sk = sk_next(sk); } @@ -583,17 +581,15 @@ static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp) skb->ip_summed = CHECKSUM_UNNECESSARY; if (csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, skb->csum)) { - LIMIT_NETDEBUG( - printk(KERN_DEBUG "ICMPv6 hw checksum failed\n")); + LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 hw checksum failed\n"); skb->ip_summed = CHECKSUM_NONE; } } if (skb->ip_summed == CHECKSUM_NONE) { if (csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, skb_checksum(skb, 0, skb->len, 0))) { - LIMIT_NETDEBUG( - printk(KERN_DEBUG "ICMPv6 checksum failed [%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x > %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x]\n", - NIP6(*saddr), NIP6(*daddr))); + LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x > %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x]\n", + NIP6(*saddr), NIP6(*daddr)); goto discard_it; } } @@ -669,8 +665,7 @@ static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp) break; default: - LIMIT_NETDEBUG( - printk(KERN_DEBUG "icmpv6: msg of unknown type\n")); + LIMIT_NETDEBUG(KERN_DEBUG "icmpv6: msg of unknown type\n"); /* informational */ if (type & ICMPV6_INFOMSG_MASK) diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c new file mode 100644 index 00000000000..01d5f46d4e4 --- /dev/null +++ b/net/ipv6/inet6_hashtables.c @@ -0,0 +1,81 @@ +/* + * 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. + * + * Generic INET6 transport hashtables + * + * Authors: Lotsa people, from code originally in tcp + * + * 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 <linux/config.h> + +#include <linux/module.h> + +#include <net/inet_connection_sock.h> +#include <net/inet_hashtables.h> +#include <net/inet6_hashtables.h> + +struct sock *inet6_lookup_listener(struct inet_hashinfo *hashinfo, + const struct in6_addr *daddr, + const unsigned short hnum, const int dif) +{ + struct sock *sk; + const struct hlist_node *node; + struct sock *result = NULL; + int score, hiscore = 0; + + read_lock(&hashinfo->lhash_lock); + sk_for_each(sk, node, &hashinfo->listening_hash[inet_lhashfn(hnum)]) { + if (inet_sk(sk)->num == hnum && sk->sk_family == PF_INET6) { + const struct ipv6_pinfo *np = inet6_sk(sk); + + score = 1; + if (!ipv6_addr_any(&np->rcv_saddr)) { + if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + continue; + score++; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + continue; + score++; + } + if (score == 3) { + result = sk; + break; + } + if (score > hiscore) { + hiscore = score; + result = sk; + } + } + } + if (result) + sock_hold(result); + read_unlock(&hashinfo->lhash_lock); + return result; +} + +EXPORT_SYMBOL_GPL(inet6_lookup_listener); + +struct sock *inet6_lookup(struct inet_hashinfo *hashinfo, + const struct in6_addr *saddr, const u16 sport, + const struct in6_addr *daddr, const u16 dport, + const int dif) +{ + struct sock *sk; + + local_bh_disable(); + sk = __inet6_lookup(hashinfo, saddr, sport, daddr, ntohs(dport), dif); + local_bh_enable(); + + return sk; +} + +EXPORT_SYMBOL_GPL(inet6_lookup); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1b354aa9793..16af874c9e8 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -49,7 +49,7 @@ struct rt6_statistics rt6_stats; -static kmem_cache_t * fib6_node_kmem; +static kmem_cache_t * fib6_node_kmem __read_mostly; enum fib_walk_state_t { diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 10fbb50daea..6e348042693 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -56,7 +56,7 @@ static inline int ip6_rcv_finish( struct sk_buff *skb) return dst_input(skb); } -int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) +int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct ipv6hdr *hdr; u32 pkt_len; @@ -166,8 +166,8 @@ resubmit: nexthdr = skb->nh.raw[nhoff]; raw_sk = sk_head(&raw_v6_htable[nexthdr & (MAX_INET_PROTOS - 1)]); - if (raw_sk) - ipv6_raw_deliver(skb, nexthdr); + if (raw_sk && !ipv6_raw_deliver(skb, nexthdr)) + raw_sk = NULL; hash = nexthdr & (MAX_INET_PROTOS - 1); if ((ipprot = rcu_dereference(inet6_protos[hash])) != NULL) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ae652ca14bc..01ef94f7c7f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -153,51 +153,6 @@ int ip6_output(struct sk_buff *skb) return ip6_output2(skb); } -#ifdef CONFIG_NETFILTER -int ip6_route_me_harder(struct sk_buff *skb) -{ - struct ipv6hdr *iph = skb->nh.ipv6h; - struct dst_entry *dst; - struct flowi fl = { - .oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, - .nl_u = - { .ip6_u = - { .daddr = iph->daddr, - .saddr = iph->saddr, } }, - .proto = iph->nexthdr, - }; - - dst = ip6_route_output(skb->sk, &fl); - - if (dst->error) { - IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES); - LIMIT_NETDEBUG( - printk(KERN_DEBUG "ip6_route_me_harder: No more route.\n")); - dst_release(dst); - return -EINVAL; - } - - /* Drop old route. */ - dst_release(skb->dst); - - skb->dst = dst; - return 0; -} -#endif - -static inline int ip6_maybe_reroute(struct sk_buff *skb) -{ -#ifdef CONFIG_NETFILTER - if (skb->nfcache & NFC_ALTERED){ - if (ip6_route_me_harder(skb) != 0){ - kfree_skb(skb); - return -EINVAL; - } - } -#endif /* CONFIG_NETFILTER */ - return dst_output(skb); -} - /* * xmit an sk_buff (used by TCP) */ @@ -266,7 +221,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, mtu = dst_mtu(dst); if ((skb->len <= mtu) || ipfragok) { IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); - return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, ip6_maybe_reroute); + return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, + dst_output); } if (net_ratelimit()) @@ -321,7 +277,9 @@ static int ip6_call_ra_chain(struct sk_buff *skb, int sel) read_lock(&ip6_ra_lock); for (ra = ip6_ra_chain; ra; ra = ra->next) { struct sock *sk = ra->sk; - if (sk && ra->sel == sel) { + if (sk && ra->sel == sel && + (!sk->sk_bound_dev_if || + sk->sk_bound_dev_if == skb->dev->ifindex)) { if (last) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) @@ -667,7 +625,7 @@ slow_path: */ if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_RESERVED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) { - NETDEBUG(printk(KERN_INFO "IPv6: frag: no memory for new fragment!\n")); + NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n"); IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 3bc144a79fa..76466af8331 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -55,7 +55,7 @@ #include <asm/uaccess.h> -DEFINE_SNMP_STAT(struct ipstats_mib, ipv6_statistics); +DEFINE_SNMP_STAT(struct ipstats_mib, ipv6_statistics) __read_mostly; static struct packet_type ipv6_packet_type = { .type = __constant_htons(ETH_P_IPV6), @@ -109,13 +109,6 @@ int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *)) return 0; } -extern int ip6_mc_source(int add, int omode, struct sock *sk, - struct group_source_req *pgsr); -extern int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf); -extern int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, - struct group_filter __user *optval, int __user *optlen); - - int ipv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen) { @@ -163,6 +156,13 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, fl6_free_socklist(sk); ipv6_sock_mc_close(sk); + /* + * Sock is moving from IPv6 to IPv4 (sk_prot), so + * remove it from the refcnt debug socks count in the + * original family... + */ + sk_refcnt_debug_dec(sk); + if (sk->sk_protocol == IPPROTO_TCP) { struct tcp_sock *tp = tcp_sk(sk); @@ -192,9 +192,11 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, kfree_skb(pktopt); sk->sk_destruct = inet_sock_destruct; -#ifdef INET_REFCNT_DEBUG - atomic_dec(&inet6_sock_nr); -#endif + /* + * ... and add it to the refcnt debug socks count + * in the new family. -acme + */ + sk_refcnt_debug_inc(sk); module_put(THIS_MODULE); retv = 0; break; @@ -437,7 +439,6 @@ done: } case MCAST_MSFILTER: { - extern int sysctl_optmem_max; extern int sysctl_mld_max_msf; struct group_filter *gsf; diff --git a/net/ipv6/ipv6_syms.c b/net/ipv6/ipv6_syms.c index 5ade5a5d199..37a4a99c9fe 100644 --- a/net/ipv6/ipv6_syms.c +++ b/net/ipv6/ipv6_syms.c @@ -15,9 +15,6 @@ EXPORT_SYMBOL(ndisc_mc_map); EXPORT_SYMBOL(register_inet6addr_notifier); EXPORT_SYMBOL(unregister_inet6addr_notifier); EXPORT_SYMBOL(ip6_route_output); -#ifdef CONFIG_NETFILTER -EXPORT_SYMBOL(ip6_route_me_harder); -#endif EXPORT_SYMBOL(addrconf_lock); EXPORT_SYMBOL(ipv6_setsockopt); EXPORT_SYMBOL(ipv6_getsockopt); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 7ae72d4c9bd..a7eae30f455 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -812,7 +812,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) if (ipv6_chk_acast_addr(dev, &msg->target) || (idev->cnf.forwarding && pneigh_lookup(&nd_tbl, &msg->target, dev, 0))) { - if (skb->stamp.tv_sec != LOCALLY_ENQUEUED && + if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && inc != 0 && idev->nd_parms->proxy_delay != 0) { @@ -1487,6 +1487,8 @@ int ndisc_rcv(struct sk_buff *skb) return 0; } + memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); + switch (msg->icmph.icmp6_type) { case NDISC_NEIGHBOUR_SOLICITATION: ndisc_recv_ns(skb); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c new file mode 100644 index 00000000000..f8626ebf90f --- /dev/null +++ b/net/ipv6/netfilter.c @@ -0,0 +1,104 @@ +#include <linux/config.h> +#include <linux/init.h> + +#ifdef CONFIG_NETFILTER + +#include <linux/kernel.h> +#include <linux/ipv6.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <net/dst.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> + +int ip6_route_me_harder(struct sk_buff *skb) +{ + struct ipv6hdr *iph = skb->nh.ipv6h; + struct dst_entry *dst; + struct flowi fl = { + .oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, + .nl_u = + { .ip6_u = + { .daddr = iph->daddr, + .saddr = iph->saddr, } }, + .proto = iph->nexthdr, + }; + + dst = ip6_route_output(skb->sk, &fl); + + if (dst->error) { + IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES); + LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n"); + dst_release(dst); + return -EINVAL; + } + + /* Drop old route. */ + dst_release(skb->dst); + + skb->dst = dst; + return 0; +} +EXPORT_SYMBOL(ip6_route_me_harder); + +/* + * Extra routing may needed on local out, as the QUEUE target never + * returns control to the table. + */ + +struct ip6_rt_info { + struct in6_addr daddr; + struct in6_addr saddr; +}; + +static void save(const struct sk_buff *skb, struct nf_info *info) +{ + struct ip6_rt_info *rt_info = nf_info_reroute(info); + + if (info->hook == NF_IP6_LOCAL_OUT) { + struct ipv6hdr *iph = skb->nh.ipv6h; + + rt_info->daddr = iph->daddr; + rt_info->saddr = iph->saddr; + } |