diff options
Diffstat (limited to 'net/ipv6')
42 files changed, 884 insertions, 1036 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index de7a194a64a..3381b4317c2 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -278,31 +278,31 @@ static void addrconf_mod_timer(struct inet6_ifaddr *ifp, static int snmp6_alloc_dev(struct inet6_dev *idev) { - if (snmp_mib_init((void **)idev->stats.ipv6, + if (snmp_mib_init((void __percpu **)idev->stats.ipv6, sizeof(struct ipstats_mib)) < 0) goto err_ip; - if (snmp_mib_init((void **)idev->stats.icmpv6, + if (snmp_mib_init((void __percpu **)idev->stats.icmpv6, sizeof(struct icmpv6_mib)) < 0) goto err_icmp; - if (snmp_mib_init((void **)idev->stats.icmpv6msg, + if (snmp_mib_init((void __percpu **)idev->stats.icmpv6msg, sizeof(struct icmpv6msg_mib)) < 0) goto err_icmpmsg; return 0; err_icmpmsg: - snmp_mib_free((void **)idev->stats.icmpv6); + snmp_mib_free((void __percpu **)idev->stats.icmpv6); err_icmp: - snmp_mib_free((void **)idev->stats.ipv6); + snmp_mib_free((void __percpu **)idev->stats.ipv6); err_ip: return -ENOMEM; } static void snmp6_free_dev(struct inet6_dev *idev) { - snmp_mib_free((void **)idev->stats.icmpv6msg); - snmp_mib_free((void **)idev->stats.icmpv6); - snmp_mib_free((void **)idev->stats.ipv6); + snmp_mib_free((void __percpu **)idev->stats.icmpv6msg); + snmp_mib_free((void __percpu **)idev->stats.icmpv6); + snmp_mib_free((void __percpu **)idev->stats.ipv6); } /* Nobody refers to this device, we may destroy it. */ @@ -502,8 +502,11 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) if (p == &net->ipv6.devconf_dflt->forwarding) return 0; - if (!rtnl_trylock()) + if (!rtnl_trylock()) { + /* Restore the original values before restarting */ + *p = old; return restart_syscall(); + } if (p == &net->ipv6.devconf_all->forwarding) { __s32 newf = net->ipv6.devconf_all->forwarding; @@ -989,8 +992,7 @@ struct ipv6_saddr_dst { static inline int ipv6_saddr_preferred(int type) { - if (type & (IPV6_ADDR_MAPPED|IPV6_ADDR_COMPATv4| - IPV6_ADDR_LOOPBACK|IPV6_ADDR_RESERVED)) + if (type & (IPV6_ADDR_MAPPED|IPV6_ADDR_COMPATv4|IPV6_ADDR_LOOPBACK)) return 1; return 0; } @@ -1378,6 +1380,8 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) if (dad_failed) ifp->flags |= IFA_F_DADFAILED; spin_unlock_bh(&ifp->lock); + if (dad_failed) + ipv6_ifa_notify(0, ifp); in6_ifa_put(ifp); #ifdef CONFIG_IPV6_PRIVACY } else if (ifp->flags&IFA_F_TEMPORARY) { @@ -2613,7 +2617,7 @@ static void addrconf_bonding_change(struct net_device *dev, unsigned long event) static int addrconf_ifdown(struct net_device *dev, int how) { struct inet6_dev *idev; - struct inet6_ifaddr *ifa, **bifa; + struct inet6_ifaddr *ifa, *keep_list, **bifa; struct net *net = dev_net(dev); int i; @@ -2646,11 +2650,12 @@ static int addrconf_ifdown(struct net_device *dev, int how) write_lock_bh(&addrconf_hash_lock); while ((ifa = *bifa) != NULL) { - if (ifa->idev == idev) { + if (ifa->idev == idev && + (how || !(ifa->flags&IFA_F_PERMANENT) || + ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)) { *bifa = ifa->lst_next; ifa->lst_next = NULL; - addrconf_del_timer(ifa); - in6_ifa_put(ifa); + __in6_ifa_put(ifa); continue; } bifa = &ifa->lst_next; @@ -2686,11 +2691,40 @@ static int addrconf_ifdown(struct net_device *dev, int how) write_lock_bh(&idev->lock); } #endif + keep_list = NULL; + bifa = &keep_list; while ((ifa = idev->addr_list) != NULL) { idev->addr_list = ifa->if_next; ifa->if_next = NULL; - ifa->dead = 1; + addrconf_del_timer(ifa); + + /* If just doing link down, and address is permanent + and not link-local, then retain it. */ + if (how == 0 && + (ifa->flags&IFA_F_PERMANENT) && + !(ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)) { + + /* Move to holding list */ + *bifa = ifa; + bifa = &ifa->if_next; + + /* If not doing DAD on this address, just keep it. */ + if ((dev->flags&(IFF_NOARP|IFF_LOOPBACK)) || + idev->cnf.accept_dad <= 0 || + (ifa->flags & IFA_F_NODAD)) + continue; + + /* If it was tentative already, no need to notify */ + if (ifa->flags & IFA_F_TENTATIVE) + continue; + + /* Flag it for later restoration when link comes up */ + ifa->flags |= IFA_F_TENTATIVE; + in6_ifa_hold(ifa); + } else { + ifa->dead = 1; + } write_unlock_bh(&idev->lock); __ipv6_ifa_notify(RTM_DELADDR, ifa); @@ -2699,6 +2733,9 @@ static int addrconf_ifdown(struct net_device *dev, int how) write_lock_bh(&idev->lock); } + + idev->addr_list = keep_list; + write_unlock_bh(&idev->lock); /* Step 5: Discard multicast list */ @@ -2724,28 +2761,29 @@ static int addrconf_ifdown(struct net_device *dev, int how) static void addrconf_rs_timer(unsigned long data) { struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data; + struct inet6_dev *idev = ifp->idev; - if (ifp->idev->cnf.forwarding) + read_lock(&idev->lock); + if (idev->dead || !(idev->if_flags & IF_READY)) goto out; - if (ifp->idev->if_flags & IF_RA_RCVD) { - /* - * Announcement received after solicitation - * was sent - */ + if (idev->cnf.forwarding) + goto out; + + /* Announcement received after solicitation was sent */ + if (idev->if_flags & IF_RA_RCVD) goto out; - } spin_lock(&ifp->lock); - if (ifp->probes++ < ifp->idev->cnf.rtr_solicits) { + if (ifp->probes++ < idev->cnf.rtr_solicits) { /* The wait after the last probe can be shorter */ addrconf_mod_timer(ifp, AC_RS, - (ifp->probes == ifp->idev->cnf.rtr_solicits) ? - ifp->idev->cnf.rtr_solicit_delay : - ifp->idev->cnf.rtr_solicit_interval); + (ifp->probes == idev->cnf.rtr_solicits) ? + idev->cnf.rtr_solicit_delay : + idev->cnf.rtr_solicit_interval); spin_unlock(&ifp->lock); - ndisc_send_rs(ifp->idev->dev, &ifp->addr, &in6addr_linklocal_allrouters); + ndisc_send_rs(idev->dev, &ifp->addr, &in6addr_linklocal_allrouters); } else { spin_unlock(&ifp->lock); /* @@ -2753,10 +2791,11 @@ static void addrconf_rs_timer(unsigned long data) * assumption any longer. */ printk(KERN_DEBUG "%s: no IPv6 routers present\n", - ifp->idev->dev->name); + idev->dev->name); } out: + read_unlock(&idev->lock); in6_ifa_put(ifp); } @@ -2789,14 +2828,14 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) read_lock_bh(&idev->lock); if (ifp->dead) goto out; - spin_lock_bh(&ifp->lock); + spin_lock(&ifp->lock); if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || idev->cnf.accept_dad < 1 || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); - spin_unlock_bh(&ifp->lock); + spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); addrconf_dad_completed(ifp); @@ -2804,7 +2843,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) } if (!(idev->if_flags & IF_READY)) { - spin_unlock_bh(&ifp->lock); + spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); /* * If the device is not ready: @@ -2824,7 +2863,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) ip6_ins_rt(ifp->rt); addrconf_dad_kick(ifp); - spin_unlock_bh(&ifp->lock); + spin_unlock(&ifp->lock); out: read_unlock_bh(&idev->lock); } @@ -2835,20 +2874,21 @@ static void addrconf_dad_timer(unsigned long data) struct inet6_dev *idev = ifp->idev; struct in6_addr mcaddr; - read_lock_bh(&idev->lock); - if (idev->dead) { - read_unlock_bh(&idev->lock); + read_lock(&idev->lock); + if (idev->dead || !(idev->if_flags & IF_READY)) { + read_unlock(&idev->lock); goto out; } - spin_lock_bh(&ifp->lock); + + spin_lock(&ifp->lock); if (ifp->probes == 0) { /* * DAD was successful */ ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); - spin_unlock_bh(&ifp->lock); - read_unlock_bh(&idev->lock); + spin_unlock(&ifp->lock); + read_unlock(&idev->lock); addrconf_dad_completed(ifp); @@ -2857,8 +2897,8 @@ static void addrconf_dad_timer(unsigned long data) ifp->probes--; addrconf_mod_timer(ifp, AC_DAD, ifp->idev->nd_parms->retrans_time); - spin_unlock_bh(&ifp->lock); - read_unlock_bh(&idev->lock); + spin_unlock(&ifp->lock); + read_unlock(&idev->lock); /* send a neighbour solicitation for our addr */ addrconf_addr_solict_mult(&ifp->addr, &mcaddr); @@ -2905,12 +2945,12 @@ static void addrconf_dad_run(struct inet6_dev *idev) { read_lock_bh(&idev->lock); for (ifp = idev->addr_list; ifp; ifp = ifp->if_next) { - spin_lock_bh(&ifp->lock); + spin_lock(&ifp->lock); if (!(ifp->flags & IFA_F_TENTATIVE)) { - spin_unlock_bh(&ifp->lock); + spin_unlock(&ifp->lock); continue; } - spin_unlock_bh(&ifp->lock); + spin_unlock(&ifp->lock); addrconf_dad_kick(ifp); } read_unlock_bh(&idev->lock); @@ -3027,14 +3067,14 @@ static const struct file_operations if6_fops = { .release = seq_release_net, }; -static int if6_proc_net_init(struct net *net) +static int __net_init if6_proc_net_init(struct net *net) { if (!proc_net_fops_create(net, "if_inet6", S_IRUGO, &if6_fops)) return -ENOMEM; return 0; } -static void if6_proc_net_exit(struct net *net) +static void __net_exit if6_proc_net_exit(struct net *net) { proc_net_remove(net, "if_inet6"); } @@ -3752,8 +3792,8 @@ static inline size_t inet6_if_nlmsg_size(void) ); } -static inline void __snmp6_fill_stats(u64 *stats, void **mib, int items, - int bytes) +static inline void __snmp6_fill_stats(u64 *stats, void __percpu **mib, + int items, int bytes) { int i; int pad = bytes - sizeof(u64) * items; @@ -3772,10 +3812,10 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, { switch(attrtype) { case IFLA_INET6_STATS: - __snmp6_fill_stats(stats, (void **)idev->stats.ipv6, IPSTATS_MIB_MAX, bytes); + __snmp6_fill_stats(stats, (void __percpu **)idev->stats.ipv6, IPSTATS_MIB_MAX, bytes); break; case IFLA_INET6_ICMP6STATS: - __snmp6_fill_stats(stats, (void **)idev->stats.icmpv6, ICMP6_MIB_MAX, bytes); + __snmp6_fill_stats(stats, (void __percpu **)idev->stats.icmpv6, ICMP6_MIB_MAX, bytes); break; } } @@ -4028,12 +4068,15 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write, { int *valp = ctl->data; int val = *valp; + loff_t pos = *ppos; int ret; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) ret = addrconf_fixup_forwarding(ctl, valp, val); + if (ret) + *ppos = pos; return ret; } @@ -4075,8 +4118,11 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int old) if (p == &net->ipv6.devconf_dflt->disable_ipv6) return 0; - if (!rtnl_trylock()) + if (!rtnl_trylock()) { + /* Restore the original values before restarting */ + *p = old; return restart_syscall(); + } if (p == &net->ipv6.devconf_all->disable_ipv6) { __s32 newf = net->ipv6.devconf_all->disable_ipv6; @@ -4095,12 +4141,15 @@ int addrconf_sysctl_disable(ctl_table *ctl, int write, { int *valp = ctl->data; int val = *valp; + loff_t pos = *ppos; int ret; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) ret = addrconf_disable_ipv6(ctl, valp, val); + if (ret) + *ppos = pos; return ret; } @@ -4402,8 +4451,7 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p) static void addrconf_sysctl_register(struct inet6_dev *idev) { - neigh_sysctl_register(idev->dev, idev->nd_parms, NET_IPV6, - NET_IPV6_NEIGH, "ipv6", + neigh_sysctl_register(idev->dev, idev->nd_parms, "ipv6", &ndisc_ifinfo_sysctl_change); __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, idev, &idev->cnf); @@ -4418,7 +4466,7 @@ static void addrconf_sysctl_unregister(struct inet6_dev *idev) #endif -static int addrconf_init_net(struct net *net) +static int __net_init addrconf_init_net(struct net *net) { int err; struct ipv6_devconf *all, *dflt; @@ -4467,7 +4515,7 @@ err_alloc_all: return err; } -static void addrconf_exit_net(struct net *net) +static void __net_exit addrconf_exit_net(struct net *net) { #ifdef CONFIG_SYSCTL __addrconf_sysctl_unregister(net->ipv6.devconf_dflt); diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 3f82e9542ed..6b03826552e 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -72,7 +72,7 @@ int __ipv6_addr_type(const struct in6_addr *addr) IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.3 */ } - return (IPV6_ADDR_RESERVED | + return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.4 */ } EXPORT_SYMBOL(__ipv6_addr_type); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 12e69d364dd..37d14e735c2 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -971,41 +971,41 @@ static void ipv6_packet_cleanup(void) static int __net_init ipv6_init_mibs(struct net *net) { - if (snmp_mib_init((void **)net->mib.udp_stats_in6, + if (snmp_mib_init((void __percpu **)net->mib.udp_stats_in6, sizeof (struct udp_mib)) < 0) return -ENOMEM; - if (snmp_mib_init((void **)net->mib.udplite_stats_in6, + if (snmp_mib_init((void __percpu **)net->mib.udplite_stats_in6, sizeof (struct udp_mib)) < 0) goto err_udplite_mib; - if (snmp_mib_init((void **)net->mib.ipv6_statistics, + if (snmp_mib_init((void __percpu **)net->mib.ipv6_statistics, sizeof(struct ipstats_mib)) < 0) goto err_ip_mib; - if (snmp_mib_init((void **)net->mib.icmpv6_statistics, + if (snmp_mib_init((void __percpu **)net->mib.icmpv6_statistics, sizeof(struct icmpv6_mib)) < 0) goto err_icmp_mib; - if (snmp_mib_init((void **)net->mib.icmpv6msg_statistics, + if (snmp_mib_init((void __percpu **)net->mib.icmpv6msg_statistics, sizeof(struct icmpv6msg_mib)) < 0) goto err_icmpmsg_mib; return 0; err_icmpmsg_mib: - snmp_mib_free((void **)net->mib.icmpv6_statistics); + snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics); err_icmp_mib: - snmp_mib_free((void **)net->mib.ipv6_statistics); + snmp_mib_free((void __percpu **)net->mib.ipv6_statistics); err_ip_mib: - snmp_mib_free((void **)net->mib.udplite_stats_in6); + snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6); err_udplite_mib: - snmp_mib_free((void **)net->mib.udp_stats_in6); + snmp_mib_free((void __percpu **)net->mib.udp_stats_in6); return -ENOMEM; } -static void __net_exit ipv6_cleanup_mibs(struct net *net) +static void ipv6_cleanup_mibs(struct net *net) { - snmp_mib_free((void **)net->mib.udp_stats_in6); - snmp_mib_free((void **)net->mib.udplite_stats_in6); - snmp_mib_free((void **)net->mib.ipv6_statistics); - snmp_mib_free((void **)net->mib.icmpv6_statistics); - snmp_mib_free((void **)net->mib.icmpv6msg_statistics); + snmp_mib_free((void __percpu **)net->mib.udp_stats_in6); + snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6); + snmp_mib_free((void __percpu **)net->mib.ipv6_statistics); + snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics); + snmp_mib_free((void __percpu **)net->mib.icmpv6msg_statistics); } static int __net_init inet6_net_init(struct net *net) @@ -1042,7 +1042,7 @@ out: #endif } -static void inet6_net_exit(struct net *net) +static void __net_exit inet6_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS udp6_proc_exit(net); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index c2f300c314b..5ac89025f9d 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -614,7 +614,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, type != ICMPV6_PKT_TOOBIG) return; - x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); + x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); if (!x) return; diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index f1c74c8ef9d..c4f6ca32fa7 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -538,7 +538,7 @@ static const struct file_operations ac6_seq_fops = { .release = seq_release_net, }; -int ac6_proc_init(struct net *net) +int __net_init ac6_proc_init(struct net *net) { if (!proc_net_fops_create(net, "anycast6", S_IRUGO, &ac6_seq_fops)) return -ENOMEM; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 668a46b655e..ee9b93bdd6a 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -365,7 +365,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, type != ICMPV6_PKT_TOOBIG) return; - x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); + x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); if (!x) return; printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%pI6\n", diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index df159fffe4b..074f2c084f9 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -481,7 +481,7 @@ looped_back: IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, - 0, skb->dev); + 0); kfree_skb(skb); return -1; } @@ -559,6 +559,11 @@ static inline struct inet6_dev *ipv6_skb_idev(struct sk_buff *skb) return skb_dst(skb) ? ip6_dst_idev(skb_dst(skb)) : __in6_dev_get(skb->dev); } +static inline struct net *ipv6_skb_net(struct sk_buff *skb) +{ + return skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev); +} + /* Router Alert as of RFC 2711 */ static int ipv6_hop_ra(struct sk_buff *skb, int optoff) @@ -580,8 +585,8 @@ static int ipv6_hop_ra(struct sk_buff *skb, int optoff) static int ipv6_hop_jumbo(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); + struct net *net = ipv6_skb_net(skb); u32 pkt_len; - struct net *net = dev_net(skb_dst(skb)->dev); if (nh[optoff + 1] != 4 || (optoff & 3) != 2) { LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b7aa7c64cc4..5e463c43fcc 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -84,18 +84,11 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, if ((rule->flags & FIB_RULE_FIND_SADDR) && r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) { struct in6_addr saddr; - unsigned int srcprefs = 0; - - if (flags & RT6_LOOKUP_F_SRCPREF_TMP) - srcprefs |= IPV6_PREFER_SRC_TMP; - if (flags & RT6_LOOKUP_F_SRCPREF_PUBLIC) - srcprefs |= IPV6_PREFER_SRC_PUBLIC; - if (flags & RT6_LOOKUP_F_SRCPREF_COA) - srcprefs |= IPV6_PREFER_SRC_COA; if (ipv6_dev_get_saddr(net, ip6_dst_idev(&rt->u.dst)->dev, - &flp->fl6_dst, srcprefs, + &flp->fl6_dst, + rt6_flags2srcprefs(flags), &saddr)) goto again; if (!ipv6_prefix_equal(&saddr, &r->src.addr, @@ -262,7 +255,7 @@ static struct fib_rules_ops fib6_rules_ops_template = { .fro_net = &init_net, }; -static int fib6_rules_net_init(struct net *net) +static int __net_init fib6_rules_net_init(struct net *net) { struct fib_rules_ops *ops; int err = -ENOMEM; @@ -291,7 +284,7 @@ out_fib6_rules_ops: goto out; } -static void fib6_rules_net_exit(struct net *net) +static void __net_exit fib6_rules_net_exit(struct net *net) { fib_rules_unregister(net->ipv6.fib6_rules_ops); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 4ae661bc367..eb9abe24bdf 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -67,11 +67,6 @@ #include <asm/uaccess.h> #include <asm/system.h> -DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics) __read_mostly; -EXPORT_SYMBOL(icmpv6_statistics); -DEFINE_SNMP_STAT(struct icmpv6msg_mib, icmpv6msg_statistics) __read_mostly; -EXPORT_SYMBOL(icmpv6msg_statistics); - /* * The ICMP socket(s). This is the most convenient way to flow control * our ICMP output as well as maintain a clean interface throughout @@ -119,7 +114,7 @@ static __inline__ void icmpv6_xmit_unlock(struct sock *sk) */ void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { - icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev); + icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos); kfree_skb(skb); } @@ -305,8 +300,7 @@ static inline void mip6_addr_swap(struct sk_buff *skb) {} /* * Send an ICMP message in response to a packet in error */ -void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - struct net_device *dev) +void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { struct net *net = dev_net(skb->dev); struct inet6_dev *idev = NULL; @@ -951,7 +945,7 @@ ctl_table ipv6_icmp_table_template[] = { { }, }; -struct ctl_table *ipv6_icmp_sysctl_init(struct net *net) +struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net) { struct ctl_table *table; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 0e93ca56eb6..2f9847924fa 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -93,29 +93,20 @@ static __u32 rt_sernum; static void fib6_gc_timer_cb(unsigned long arg); -static struct fib6_walker_t fib6_walker_list = { - .prev = &fib6_walker_list, - .next = &fib6_walker_list, -}; - -#define FOR_WALKERS(w) for ((w)=fib6_walker_list.next; (w) != &fib6_walker_list; (w)=(w)->next) +static LIST_HEAD(fib6_walkers); +#define FOR_WALKERS(w) list_for_each_entry(w, &fib6_walkers, lh) static inline void fib6_walker_link(struct fib6_walker_t *w) { write_lock_bh(&fib6_walker_lock); - w->next = fib6_walker_list.next; - w->prev = &fib6_walker_list; - w->next->prev = w; - w->prev->next = w; + list_add(&w->lh, &fib6_walkers); write_unlock_bh(&fib6_walker_lock); } static inline void fib6_walker_unlink(struct fib6_walker_t *w) { write_lock_bh(&fib6_walker_lock); - w->next->prev = w->prev; - w->prev->next = w->next; - w->prev = w->next = w; + list_del(&w->lh); write_unlock_bh(&fib6_walker_lock); } static __inline__ u32 fib6_new_sernum(void) @@ -239,7 +230,7 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) return NULL; } -static void fib6_tables_init(struct net *net) +static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); fib6_link_table(net, net->ipv6.fib6_local_tbl); @@ -262,7 +253,7 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl, return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl, flags); } -static void fib6_tables_init(struct net *net) +static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); } @@ -319,12 +310,26 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, w->root = &table->tb6_root; if (cb->args[4] == 0) { + w->count = 0; + w->skip = 0; + read_lock_bh(&table->tb6_lock); res = fib6_walk(w); read_unlock_bh(&table->tb6_lock); - if (res > 0) + if (res > 0) { cb->args[4] = 1; + cb->args[5] = w->root->fn_sernum; + } } else { + if (cb->args[5] != w->root->fn_sernum) { + /* Begin at the root if the tree changed */ + cb->args[5] = w->root->fn_sernum; + w->state = FWS_INIT; + w->node = w->root; + w->skip = w->count; + } else + w->skip = 0; + read_lock_bh(&table->tb6_lock); res = fib6_walk_continue(w); read_unlock_bh(&table->tb6_lock); @@ -1250,9 +1255,18 @@ static int fib6_walk_continue(struct fib6_walker_t *w) w->leaf = fn->leaf; case FWS_C: if (w->leaf && fn->fn_flags&RTN_RTINFO) { - int err = w->func(w); + int err; + + if (w->count < w->skip) { + w->count++; + continue; + } + + err = w->func(w); if (err) return err; + + w->count++; continue; } w->state = FWS_U; @@ -1346,6 +1360,8 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root, c.w.root = root; c.w.func = fib6_clean_node; c.w.prune = prune; + c.w.count = 0; + c.w.skip = 0; c.func = func; c.arg = arg; c.net = net; @@ -1469,7 +1485,7 @@ static void fib6_gc_timer_cb(unsigned long arg) fib6_run_gc(0, (struct net *)arg); } -static int fib6_net_init(struct net *net) +static int __net_init fib6_net_init(struct net *net) { setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 6e7bffa2205..e41eba8aacf 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -154,7 +154,7 @@ static void ip6_fl_gc(unsigned long dummy) write_unlock(&ip6_fl_lock); } -static void ip6_fl_purge(struct net *net) +static void __net_exit ip6_fl_purge(struct net *net) { int i; @@ -735,7 +735,7 @@ static const struct file_operations ip6fl_seq_fops = { .release = seq_release_net, }; -static int ip6_flowlabel_proc_init(struct net *net) +static int __net_init ip6_flowlabel_proc_init(struct net *net) { if (!proc_net_fops_create(net, "ip6_flowlabel", S_IRUGO, &ip6fl_seq_fops)) @@ -743,7 +743,7 @@ static int ip6_flowlabel_proc_init(struct net *net) return 0; } -static void ip6_flowlabel_proc_fini(struct net *net) +static void __net_exit ip6_flowlabel_proc_fini(struct net *net) { proc_net_remove(net, "ip6_flowlabel"); } @@ -754,11 +754,10 @@ static inline int ip6_flowlabel_proc_init(struct net *net) } static inline void ip6_flowlabel_proc_fini(struct net *net) { - return ; } #endif -static inline void ip6_flowlabel_net_exit(struct net *net) +static void __net_exit ip6_flowlabel_net_exit(struct net *net) { ip6_fl_purge(net); ip6_flowlabel_proc_fini(net); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 237e2dba6e9..e28f9203dec 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -216,8 +216,7 @@ resubmit: IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INUNKNOWNPROTOS); icmpv6_send(skb, ICMPV6_PARAMPROB, - ICMPV6_UNK_NEXTHDR, nhoff, - skb->dev); + ICMPV6_UNK_NEXTHDR, nhoff); } } else IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index cd48801a8d6..dabf108ad81 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -121,10 +121,9 @@ static int ip6_output2(struct sk_buff *skb) skb->dev = dev; if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { - struct ipv6_pinfo* np = skb->sk ? inet6_sk(skb->sk) : NULL; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) && + if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) && ((mroute6_socket(dev_net(dev)) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, @@ -268,7 +267,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, if (net_ratelimit()) printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n"); skb->dev = dst->dev; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; @@ -403,6 +402,7 @@ int ip6_forward(struct sk_buff *skb) struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(dst->dev); + u32 mtu; if (net->ipv6.devconf_all->forwarding == 0) goto error; @@ -442,8 +442,7 @@ int ip6_forward(struct sk_buff *skb) if (hdr->hop_limit <= 1) { /* Force OUTPUT device used as source address */ skb->dev = dst->dev; - icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, - 0, skb->dev); + icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); @@ -505,15 +504,19 @@ int ip6_forward(struct sk_buff *skb) goto error; if (addrtype & IPV6_ADDR_LINKLOCAL) { icmpv6_send(skb, ICMPV6_DEST_UNREACH, - ICMPV6_NOT_NEIGHBOUR, 0, skb->dev); + ICMPV6_NOT_NEIGHBOUR, 0); goto error; } } - if (skb->len > dst_mtu(dst)) { + mtu = dst_mtu(dst); + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + + if (skb->len > mtu) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, dst_mtu(dst), skb->dev); + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS); IP6_INC_STATS_BH(net, @@ -623,12 +626,11 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) mtu = ip6_skb_dst_mtu(skb); /* We must not fragment if the socket is set to force MTU discovery - * or if the skb it not generated by a local socket. (This last - * check should be redundant, but it's free.) + * or if the skb it not generated by a local socket. */ if (!skb->local_df) { skb->dev = skb_dst(skb)->dev; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index d453d07b0df..138980eec21 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -74,7 +74,6 @@ MODULE_LICENSE("GPL"); (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \ (HASH_SIZE - 1)) -static void ip6_fb_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); @@ -623,7 +622,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rt && rt->rt6i_dev) skb2->dev = rt->rt6i_dev; - icmpv6_send(skb2, rel_type, rel_code, rel_info, skb2->dev); + icmpv6_send(skb2, rel_type, rel_code, rel_info); if (rt) dst_release(&rt->u.dst); @@ -1015,7 +1014,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; if (tel->encap_limit == 0) { icmpv6_send(skb, ICMPV6_PARAMPROB, - ICMPV6_HDR_FIELD, offset + 2, skb->dev); + ICMPV6_HDR_FIELD, offset + 2); return -1; } encap_limit = tel->encap_limit - 1; @@ -1034,7 +1033,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu); if (err != 0) { if (err == -EMSGSIZE) - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev); + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -1; } @@ -1364,7 +1363,7 @@ static void ip6_tnl_dev_init(struct net_device *dev) * Return: 0 **/ -static void ip6_fb_tnl_dev_init(struct net_device *dev) +static void __net_init ip6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); @@ -1388,7 +1387,7 @@ static struct xfrm6_tunnel ip6ip6_handler = { .priority = 1, }; -static void ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) +static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) { int h; struct ip6_tnl *t; @@ -1407,7 +1406,7 @@ static void ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) unregister_netdevice_many(&list); } -static int ip6_tnl_init_net(struct net *net) +static int __net_init ip6_tnl_init_net(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); int err; @@ -1436,7 +1435,7 @@ err_alloc_dev: return err; } -static void ip6_tnl_exit_net(struct net *net) +static void __net_exit ip6_tnl_exit_net(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); @@ -1462,27 +1461,29 @@ static int __init ip6_tunnel_init(void) { int err; - if (xfrm6_tunnel_register(&ip4ip6_handler, AF_INET)) { + err = register_pernet_device(&ip6_tnl_net_ops); + if (err < 0) + goto out_pernet; + + err = xfrm6_tunnel_register(&ip4ip6_handler, AF_INET); + if (err < 0) { printk(KERN_ERR "ip6_tunnel init: can't register ip4ip6\n"); - err = -EAGAIN; - goto out; + goto out_ip4ip6; } - if (xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6)) { + err = xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6); + if (err < 0) { printk(KERN_ERR "ip6_tunnel init: can't register ip6ip6\n"); - err = -EAGAIN; - goto unreg_ip4ip6; + goto out_ip6ip6; } - err = register_pernet_device(&ip6_tnl_net_ops); - if (err < 0) - goto err_pernet; return 0; -err_pernet: - xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6); -unreg_ip4ip6: + +out_ip6ip6: xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET); -out: +out_ip4ip6: + unregister_pernet_device(&ip6_tnl_net_ops); +out_pernet: return err; } diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 2f2a5ca2c87..85cccd6ed0b 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -53,6 +53,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { + struct net *net = dev_net(skb->dev); __be32 spi; struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; struct ip_comp_hdr *ipcomph = @@ -63,7 +64,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; spi = htonl(ntohs(ipcomph->cpi)); - x = xfrm_state_lookup(&init_net, (xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6); + x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6); if (!x) return; @@ -74,14 +75,15 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) { + struct net *net = xs_net(x); struct xfrm_state *t = NULL; - t = xfrm_state_alloc(&init_net); + t = xfrm_state_alloc(net); if (!t) goto out; t->id.proto = IPPROTO_IPV6; - t->id.spi = xfrm6_tunnel_alloc_spi((xfrm_address_t *)&x->props.saddr); + t->id.spi = xfrm6_tunnel_alloc_spi(net, (xfrm_address_t *)&x->props.saddr); if (!t->id.spi) goto error; @@ -90,6 +92,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) t->props.family = AF_INET6; t->props.mode = x->props.mode; memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr)); + memcpy(&t->mark, &x->mark, sizeof(t->mark)); if (xfrm_init_state(t)) goto error; @@ -108,13 +111,15 @@ error: static int ipcomp6_tunnel_attach(struct xfrm_state *x) { + struct net *net = xs_net(x); int err = 0; struct xfrm_state *t = NULL; __be32 spi; + u32 mark = x->mark.m & x->mark.v; - spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&x->props.saddr); + spi = xfrm6_tunnel_spi_lookup(net, (xfrm_address_t *)&x->props.saddr); if (spi) - t = xfrm_state_lookup(&init_net, (xfrm_address_t *)&x->id.daddr, + t = xfrm_state_lookup(net, mark, (xfrm_address_t *)&x->id.daddr, spi, IPPROTO_IPV6, AF_INET6); if (!t) { t = ipcomp6_tunnel_create(x); @@ -154,16 +159,12 @@ static int ipcomp6_init_state(struct xfrm_state *x) if (x->props.mode == XFRM_MODE_TUNNEL) { err = ipcomp6_tunnel_attach(x); if (err) - goto error_tunnel; + goto out; } err = 0; out: return err; -error_tunnel: - ipcomp_destroy(x); - - goto out; } static const struct xfrm_type ipcomp6_type = diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 1f9c44442e6..bcd97191596 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -793,10 +793,10 @@ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) } spin_unlock_bh(&im->mca_lock); - write_lock_bh(&idev->mc_lock); + spin_lock_bh(&idev->mc_lock); pmc->next = idev->mc_tomb; idev->mc_tomb = pmc; - write_unlock_bh(&idev->mc_lock); + spin_unlock_bh(&idev->mc_lock); } static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *pmca) @@ -804,7 +804,7 @@ static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *pmca) struct ifmcaddr6 *pmc, *pmc_prev; struct ip6_sf_list *psf, *psf_next; - write_lock_bh(&idev->mc_lock); + spin_lock_bh(&idev->mc_lock); pmc_prev = NULL; for (pmc=idev->mc_tomb; pmc; pmc=pmc->next) { if (ipv6_addr_equal(&pmc->mca_addr, pmca)) @@ -817,7 +817,8 @@ static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *pmca) else idev->mc_tomb = pmc->next; } - write_unlock_bh(&idev->mc_lock); + spin_unlock_bh(&idev->mc_lock); + if (pmc) { for (psf=pmc->mca_tomb; psf; psf=psf_next) { psf_next = psf->sf_next; @@ -832,10 +833,10 @@ static void mld_clear_delrec(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *nextpmc; - write_lock_bh(&idev->mc_lock); + spin_lock_bh(&idev->mc_lock); pmc = idev->mc_tomb; idev->mc_tomb = NULL; - write_unlock_bh(&idev->mc_lock); + spin_unlock_bh(&idev->mc_lock); for (; pmc; pmc = nextpmc) { nextpmc = pmc->next; @@ -1696,7 +1697,7 @@ static void mld_send_cr(struct inet6_dev *idev) int type, dtype; read_lock_bh(&idev->lock); - write_lock_bh(&idev->mc_lock); + spin_lock(&idev->mc_lock); /* deleted MCA's */ pmc_prev = NULL; @@ -1730,7 +1731,7 @@ static void mld_send_cr(struct inet6_dev *idev) } else pmc_prev = pmc; } - write_unlock_bh(&idev->mc_lock); + spin_unlock(&idev->mc_lock); /* change recs */ for (pmc=idev->mc_list; pmc; pmc=pmc->next) { @@ -2311,7 +2312,7 @@ void ipv6_mc_up(struct inet6_dev *idev) void ipv6_mc_init_dev(struct inet6_dev *idev) { write_lock_bh(&idev->lock); - rwlock_init(&idev->mc_lock); + spin_lock_init(&idev->mc_lock); idev->mc_gq_running = 0; setup_timer(&idev->mc_gq_timer, mld_gq_timer_expire, (unsigned long)idev); @@ -2646,7 +2647,7 @@ static const struct file_operations igmp6_mcf_seq_fops = { .release = seq_release_net, }; -static int igmp6_proc_init(struct net *net) +static int __net_init igmp6_proc_init(struct net *net) { int err; @@ -2666,23 +2667,22 @@ out_proc_net_igmp6: goto out; } -static void igmp6_proc_exit(struct net *net) +static void __net_exit igmp6_proc_exit(struct net *net) { proc_net_remove(net, "mcfilter6"); proc_net_remove(net, "igmp6"); } #else -static int igmp6_proc_init(struct net *net) +static inline int igmp6_proc_init(struct net *net) { return 0; } -static void igmp6_proc_exit(struct net *net) +static inline void igmp6_proc_exit(struct net *net) { - ; } #endif -static int igmp6_net_init(struct net *net) +static int __net_init igmp6_net_init(struct net *net) { int err; @@ -2708,7 +2708,7 @@ out_sock_create: goto out; } -static void igmp6_net_exit(struct net *net) +static void __net_exit igmp6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.igmp_sk); igmp6_proc_exit(net); diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index f797e8c6f3b..2794b600283 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -56,7 +56,7 @@ static inline void *mip6_padn(__u8 *data, __u8 padlen) static inline void mip6_param_prob(struct sk_buff *skb, u8 code, int pos) { - icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev); + icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos); } static int mip6_mh_len(int type) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index c4585279809..8bcc4b7db3b 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1772,7 +1772,7 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *bu #endif -static int ndisc_net_init(struct net *net) +static int __net_init ndisc_net_init(struct net *net) { struct ipv6_pinfo *np; struct sock *sk; @@ -1797,7 +1797,7 @@ static int ndisc_net_init(struct net *net) return 0; } -static void ndisc_net_exit(struct net *net) +static void __net_exit ndisc_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.ndisc_sk); } @@ -1820,8 +1820,7 @@ int __init ndisc_init(void) neigh_table_init(&nd_tbl); #ifdef CONFIG_SYSCTL - err = neigh_sysctl_register(NULL, &nd_tbl.parms, NET_IPV6, - NET_IPV6_NEIGH, "ipv6", + err = neigh_sysctl_register(NULL, &nd_tbl.parms, "ipv6", &ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 480d7f8c980..9210e312edf 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -29,6 +29,7 @@ #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter/x_tables.h> #include <net/netfilter/nf_log.h> +#include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); @@ -67,6 +68,12 @@ do { \ #define inline #endif +void *ip6t_alloc_initial_table(const struct xt_table *info) +{ + return xt_alloc_initial_table(ip6t, IP6T); +} +EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); + /* We keep a set of rules for each CPU, so we can avoid write-locking them in the softirq when updating the counters and therefore @@ -201,7 +208,7 @@ ip6t_error(struct sk_buff *skb, const struct xt_target_param *par) /* Performance critical - called for every packet */ static inline bool -do_match(struct ip6t_entry_match *m, const struct sk_buff *skb, +do_match(const struct ip6t_entry_match *m, const struct sk_buff *skb, struct xt_match_param *par) { par->match = m->u.kernel.match; @@ -215,7 +222,7 @@ do_match(struct ip6t_entry_match *m, const struct sk_buff *skb, } static inline struct ip6t_entry * -get_entry(void *base, unsigned int offset) +get_entry(const void *base, unsigned int offset) { return (struct ip6t_entry *)(base + offset); } @@ -229,6 +236,12 @@ static inline bool unconditional(const struct ip6t_ip6 *ipv6) return memcmp(ipv6, &uncond, sizeof(uncond)) == 0; } +static inline const struct ip6t_entry_target * +ip6t_get_target_c(const struct ip6t_entry *e) +{ + return ip6t_get_target((struct ip6t_entry *)e); +} + #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) /* This cries for unification! */ @@ -264,11 +277,11 @@ static struct nf_loginfo trace_loginfo = { /* Mildly perf critical (only if packet tracing is on) */ static inline int -get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e, +get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { - struct ip6t_standard_target *t = (void *)ip6t_get_target(s); + const struct ip6t_standard_target *t = (void *)ip6t_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, IP6T_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ @@ -294,17 +307,18 @@ get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e, return 0; } -static void trace_packet(struct sk_buff *skb, +static void trace_packet(const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, const char *tablename, - struct xt_table_info *private, - struct ip6t_entry *e) + const struct xt_table_info *private, + const struct ip6t_entry *e) { - void *table_base; + const void *table_base; const struct ip6t_entry *root; const char *hookname, *chainname, *comment; + const struct ip6t_entry *iter; unsigned int rulenum = 0; table_base = private->entries[smp_processor_id()]; @@ -313,10 +327,10 @@ static void trace_packet(struct sk_buff *skb, hookname = chainname = hooknames[hook]; comment = comments[NF_IP6_TRACE_COMMENT_RULE]; - IP6T_ENTRY_ITERATE(root, - private->size - private->hook_entry[hook], - get_chainname_rulenum, - e, hookname, &chainname, &comment, &rulenum); + xt_entry_foreach(iter, root, private->size - private->hook_entry[hook]) + if (get_chainname_rulenum(iter, e, hookname, + &chainname, &comment, &rulenum) != 0) + break; nf_log_packet(AF_INET6, hook, skb, in, out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", @@ -345,9 +359,9 @@ ip6t_do_table(struct sk_buff *skb, /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; - void *table_base; + const void *table_base; struct ip6t_entry *e, *back; - struct xt_table_info *private; + const struct xt_table_info *private; struct xt_match_param mtpar; struct xt_target_param tgpar; @@ -378,22 +392,27 @@ ip6t_do_table(struct sk_buff *skb, back = get_entry(table_base, private->underflow[hook]); do { - struct ip6t_entry_target *t; + const struct ip6t_entry_target *t; + const struct xt_entry_match *ematch; IP_NF_ASSERT(e); IP_NF_ASSERT(back); if (!ip6_packet_match(skb, indev, outdev, &e->ipv6, - &mtpar.thoff, &mtpar.fragoff, &hotdrop) || - IP6T_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0) { + &mtpar.thoff, &mtpar.fragoff, &hotdrop)) { + no_match: e = ip6t_next_entry(e); continue; } + xt_ematch_foreach(ematch, e) + if (do_match(ematch, skb, &mtpar) != 0) + goto no_match; + ADD_COUNTER(e->counters, ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr), 1); - t = ip6t_get_target(e); + t = ip6t_get_target_c(e); IP_NF_ASSERT(t->u.kernel.target); #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ @@ -475,7 +494,7 @@ ip6t_do_table(struct sk_buff *skb, /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int -mark_source_chains(struct xt_table_info *newinfo, +mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0) { unsigned int hook; @@ -493,8 +512,8 @@ mark_source_chains(struct xt_table_info *newinfo, e->counters.pcnt = pos; for (;;) { - struct ip6t_standard_target *t - = (void *)ip6t_get_target(e); + const struct ip6t_standard_target *t + = (void *)ip6t_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) { @@ -584,27 +603,23 @@ mark_source_chains(struct xt_table_info *newinfo, return 1; } -static int -cleanup_match(struct ip6t_entry_match *m, unsigned int *i) +static void cleanup_match(struct ip6t_entry_match *m, struct net *net) { struct xt_mtdtor_param par; - if (i && (*i)-- == 0) - return 1; - + par.net = net; par.match = m->u.kernel.match; par.matchinfo = m->data; par.family = NFPROTO_IPV6; if (par.match->destroy != NULL) par.match->destroy(&par); module_put(par.match->me); - return 0; } static int -check_entry(struct ip6t_entry *e, const char *name) +check_entry(const struct ip6t_entry *e, const char *name) { - struct ip6t_entry_target *t; + const struct ip6t_entry_target *t; if (!ip6_checkentry(&e->ipv6)) { duprintf("ip_tables: ip check failed %p %s.\n", e, name); @@ -615,15 +630,14 @@ check_entry(struct ip6t_entry *e, const char *name) e->next_offset) return -EINVAL; - t = ip6t_get_target(e); + t = ip6t_get_target_c(e); if (e->target_offset + t->u.target_size > e->next_offset) return -EINVAL; return 0; } -static int check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par, - unsigned int *i) +static int check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par) { const struct ip6t_ip6 *ipv6 = par->entryinfo; int ret; @@ -638,13 +652,11 @@ static int check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par, par.match->name); return ret; } - ++*i; return 0; } static int -find_check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par, - unsigned int *i) +find_check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; @@ -658,7 +670,7 @@ find_check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par, } m->u.kernel.match = match; - ret = check_match(m, par, i); + ret = check_match(m, par); if (ret) goto err; @@ -668,10 +680,11 @@ err: return ret; } -static int check_target(struct ip6t_entry *e, const char *name) +static int check_target(struct ip6t_entry *e, struct net *net, const char *name) { struct ip6t_entry_target *t = ip6t_get_target(e); struct xt_tgchk_param par = { + .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, @@ -693,27 +706,32 @@ static int check_target(struct ip6t_entry *e, const char *name) } static int -find_check_entry(struct ip6t_entry *e, const char *name, unsigned int size, - unsigned int *i) +find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, + unsigned int size) { struct ip6t_entry_target *t; struct xt_target *target; int ret; unsigned int j; struct xt_mtchk_param mtpar; + struct xt_entry_match *ematch; ret = check_entry(e, name); if (ret) return ret; j = 0; + mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ipv6; mtpar.hook_mask = e->comefrom; mtpar.family = NFPROTO_IPV6; - ret = IP6T_MATCH_ITERATE(e, find_check_match, &mtpar, &j); - if (ret != 0) - goto cleanup_matches; + xt_ematch_foreach(ematch, e) { + ret = find_check_match(ematch, &mtpar); + if (ret != 0) + goto cleanup_matches; + ++j; + } t = ip6t_get_target(e); target = try_then_request_module(xt_find_target(AF_INET6, @@ -727,27 +745,29 @@ find_check_entry(struct ip6t_entry *e, const char *name, unsigned int size, } t->u.kernel.target = target; - ret = check_target(e, name); + ret = check_target(e, net, name); if (ret) goto err; - - (*i)++; return 0; err: module_put(t->u.kernel.target->me); cleanup_matches: - IP6T_MATCH_ITERATE(e, cleanup_match, &j); + xt_ematch_foreach(ematch, e) { + if (j-- == 0) + break; + cleanup_match(ematch, net); + } return ret; } -static bool check_underflow(struct ip6t_entry *e) +static bool check_underflow(const struct ip6t_entry *e) { const struct ip6t_entry_target *t; unsigned int verdict; if (!unconditional(&e->ipv6)) return false; - t = ip6t_get_target(e); + t = ip6t_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct ip6t_standard_target *)t)->verdict; @@ -758,12 +778,11 @@ static bool check_underflow(struct ip6t_entry *e) static int check_entry_size_and_hooks(struct ip6t_entry *e, struct xt_table_info *newinfo, - unsigned char *base, - unsigned char *limit, + const unsigned char *base, + const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, - unsigned int valid_hooks, - unsigned int *i) + unsigned int valid_hooks) { unsigned int h; @@ -800,50 +819,41 @@ check_entry_size_and_hooks(struct ip6t_entry *e, /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; - - (*i)++; return 0; } -static int -cleanup_entry(struct ip6t_entry *e, unsigned int *i) +static void cleanup_entry(struct ip6t_entry *e, struct net *net) { struct xt_tgdtor_param par; struct ip6t_entry_target *t; - - if (i && (*i)-- == 0) - return 1; + struct xt_entry_match *ematch; /* Cleanup all matches */ - IP6T_MATCH_ITERATE(e, cleanup_match, NULL); + xt_ematch_foreach(ematch, e) + cleanup_match(ematch, net); t = ip6t_get_target(e); + par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_IPV6; if (par.target->destroy != NULL) par.target->destroy(&par); module_put(par.target->me); - return 0; } /* Checks and translates the user-supplied table segment (held in newinfo) */ static int -translate_table(const char *name, - unsigned int valid_hooks, - struct xt_table_info *newinfo, - void *entry0, - unsigned int size, - unsigned int number, - const unsigned int *hook_entries, - const unsigned int *underflows) +translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, + const struct ip6t_replace *repl) { + struct ip6t_entry *iter; unsigned int i; - int ret; + int ret = 0; - newinfo->size = size; - newinfo->number = number; + newinfo->size = repl->size; + newinfo->number = repl->num_entries; /* Init all hooks to impossible value. */ for (i = 0; i < NF_INET_NUMHOOKS; i++) { @@ -854,49 +864,58 @@ translate_table(const char *name, duprintf("translate_table: size %u\n", newinfo->size); i = 0; /* Walk through entries, checking offsets. */ - ret = IP6T_ENTRY_ITERATE(entry0, newinfo->size, - check_entry_size_and_hooks, - newinfo, - entry0, - entry0 + size, - hook_entries, underflows, valid_hooks, &i); - if (ret != 0) - return ret; + xt_entry_foreach(iter, entry0, newinfo->size) { + ret = check_entry_size_and_hooks(iter, newinfo, entry0, + entry0 + repl->size, + repl->hook_entry, + repl->underflow, + repl->valid_hooks); + if (ret != 0) + return ret; + ++i; + } - if (i != number) { + if (i != repl->num_entries) { duprintf("translate_table: %u not %u entries\n", - i, number); + i, repl->num_entries); return -EINVAL; } /* Check hooks all assigned */ for (i = 0; i < NF_INET_NUMHOOKS; i++) { /* Only hooks which are valid */ - if (!(valid_hooks & (1 << i))) + if (!(repl->valid_hooks & (1 << i))) continue; if (newinfo->hook_entry[i] == 0xFFFFFFFF) { duprintf("Invalid hook entry %u %u\n", - i, hook_entries[i]); + i, repl->hook_entry[i]); return -EINVAL; } if (newinfo->underflow[i] == 0xFFFFFFFF) { duprintf("Invalid underflow %u %u\n", - i, underflows[i]); + i, repl->underflow[i]); return -EINVAL; } } - if (!mark_source_chains(newinfo, valid_hooks, entry0)) + if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) return -ELOOP; /* Finally, each sanity check must pass */ i = 0; - ret = IP6T_ENTRY_ITERATE(entry0, newinfo->size, - find_check_entry, name, size, &i); + xt_entry_foreach(iter, entry0, newinfo->size) { + ret = find_check_entry(iter, net, repl->name, repl->size); + if (ret != 0) + break; + ++i; + } if (ret != 0) { - IP6T_ENTRY_ITERATE(entry0, newinfo->size, - cleanup_entry, &i); + xt_entry_foreach(iter, entry0, newinfo->size) { + if (i-- == 0) + break; + cleanup_entry(iter, net); + } return ret; } @@ -909,33 +928,11 @@ translate_table(const char *name, return ret; } -/* Gets counters. */ -static inline int -add_entry_to_counter(const struct ip6t_entry *e, - struct xt_counters total[], - unsigned int *i) -{ - ADD_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt); - - (*i)++; - return 0; -} - -static inline int -set_entry_to_counter(const struct ip6t_entry *e, - struct ip6t_counters total[], - unsigned int *i) -{ - SET_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt); - - (*i)++; - return 0; -} - static void get_counters(const struct xt_table_info *t, struct xt_counters counters[]) { + struct ip6t_entry *iter; unsigned int cpu; unsigned int i; unsigned int curcpu; @@ -951,32 +948,32 @@ get_counters(const struct xt_table_info *t, curcpu = smp_processor_id(); i = 0; - IP6T_ENTRY_ITERATE(t->entries[curcpu], - t->size, - set_entry_to_counter, - counters, - &i); + xt_entry_foreach(iter, t->entries[curcpu], t->size) { + SET_COUNTER(counters[i], iter->counters.bcnt, + iter->counters.pcnt); + ++i; + } for_each_possible_cpu(cpu) { if (cpu == curcpu) continue; i = 0; xt_info_wrlock(cpu); - IP6T_ENTRY_ITERATE(t->entries[cpu], - t->size, - add_entry_to_counter, - counters, - &i); + xt_entry_foreach(iter, t->entries[cpu], t->size) { + ADD_COUNTER(counters[i], iter->counters.bcnt, + iter->counters.pcnt); + ++i; + } xt_info_wrunlock(cpu); } local_bh_enable(); } -static struct xt_counters *alloc_counters(struct xt_table *table) +static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - struct xt_table_info *private = table->private; + const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -994,11 +991,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table) static int copy_entries_to_user(unsigned int total_size, - struct xt_table *table, + const struct xt_table *table, void __user *userptr) { unsigned int off, num; - struct ip6t_entry *e; + const struct ip6t_entry *e; struct xt_counters *counters; const struct xt_table_info *private = table->private; int ret = 0; @@ -1050,7 +1047,7 @@ copy_entries_to_user(unsigned int total_size, } } - t = ip6t_get_target(e); + t = ip6t_get_target_c(e); if (copy_to_user(userptr + off + e->target_offset + offsetof(struct ip6t_entry_target, u.user.name), @@ -1067,7 +1064,7 @@ copy_entries_to_user(unsigned int total_size, } #ifdef CONFIG_COMPAT -static void compat_standard_from_user(void *dst, void *src) +static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; @@ -1076,7 +1073,7 @@ static void compat_standard_from_user(void *dst, void *src) memcpy(dst, &v, sizeof(v)); } -static int compat_standard_to_user(void __user *dst, void *src) +static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; @@ -1085,25 +1082,20 @@ static int compat_standard_to_user(void __user *dst, void *src) return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } -static inline int -compat_calc_match(struct ip6t_entry_match *m, int *size) -{ - *size += xt_compat_match_offset(m->u.kernel.match); - return 0; -} - -static int compat_calc_entry(struct ip6t_entry *e, +static int compat_calc_entry(const struct ip6t_entry *e, const struct xt_table_info *info, - void *base, struct xt_table_info *newinfo) + const void *base, struct xt_table_info *newinfo) { - struct ip6t_entry_target *t; + const struct xt_entry_match *ematch; + const struct ip6t_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - base; - IP6T_MATCH_ITERATE(e, compat_calc_match, &off); - t = ip6t_get_target(e); + xt_ematch_foreach(ematch, e) + off += xt_compat_match_offset(ematch->u.kernel.match); + t = ip6t_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(AF_INET6, entry_offset, off); @@ -1124,7 +1116,9 @@ static int compat_calc_entry(struct ip6t_entry *e, static int compat_table_info(const struct xt_table_info *info, struct xt_table_info *newinfo) { + struct ip6t_entry *iter; void *loc_cpu_entry; + int ret; if (!newinfo || !info) return -EINVAL; @@ -1133,13 +1127,17 @@ static int compat_table_info(const struct xt_table_info *info, memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries[raw_smp_processor_id()]; - return IP6T_ENTRY_ITERATE(loc_cpu_entry, info->size, - compat_calc_entry, info, loc_cpu_entry, - newinfo); + xt_entry_foreach(iter, loc_cpu_entry, info->size) { + ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); + if (ret != 0) + return ret; + } + return 0; } #endif -static int get_info(struct net *net, void __user *user, int *len, int compat) +static int get_info(struct net *net, void __user *user, + const int *len, int compat) { char name[IP6T_TABLE_MAXNAMELEN]; struct xt_table *t; @@ -1164,10 +1162,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat) if (t && !IS_ERR(t)) { struct ip6t_getinfo info; const struct xt_table_info *private = t->private; - #ifdef CONFIG_COMPAT + struct xt_table_info tmp; + if (compat) { - struct xt_table_info tmp; ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET6); private = &tmp; @@ -1199,7 +1197,8 @@ static int get_info(struct net *net, void __user *user, int *len, int compat) } static int -get_entries(struct net *net, struct ip6t_get_entries __user *uptr, int *len) +get_entries(struct net *net, struct ip6t_get_entries __user *uptr, + const int *len) { int ret; struct ip6t_get_entries get; @@ -1247,6 +1246,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_table_info *oldinfo; struct xt_counters *counters; const void *loc_cpu_old_entry; + struct ip6t_entry *iter; ret = 0; counters = vmalloc_node(num_counters * sizeof(struct xt_counters), @@ -1290,8 +1290,9 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; - IP6T_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry, - NULL); + xt_entry_foreach(iter, loc_cpu_old_entry, oldinfo->size) + cleanup_entry(iter, net); + xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) @@ -1310,12 +1311,13 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, } static int -do_replace(struct net *net, void __user *user, unsigned int len) +do_replace(struct net *net, const void __user *user, unsigned int len) { int ret; struct ip6t_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; + struct ip6t_entry *iter; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; @@ -1336,9 +1338,7 @@ do_replace(struct net *net, void __user *user, unsigned int len) goto free_newinfo; } - ret = translate_table(tmp.name, tmp.valid_hooks, - newinfo, loc_cpu_entry, tmp.size, tmp.num_entries, - tmp.hook_entry, tmp.underflow); + ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; @@ -1351,27 +1351,15 @@ do_replace(struct net *net, void __user *user, unsigned int len) return 0; free_newinfo_untrans: - IP6T_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL); + xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) + cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } -/* We're lazy, and add to the first CPU; overflow works its fey magic - * and everything is OK. */ static int -add_counter_to_entry(struct ip6t_entry *e, - const struct xt_counters addme[], - unsigned int *i) -{ - ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); - - (*i)++; - return 0; -} - -static int -do_add_counters(struct net *net, void __user *user, unsigned int len, +do_add_counters(struct net *net, const void __user *user, unsigned int len, int compat) { unsigned int i, curcpu; @@ -1385,6 +1373,7 @@ do_add_counters(struct net *net, void __user *user, unsigned int len, const struct xt_table_info *private; int ret = 0; const void *loc_cpu_entry; + struct ip6t_entry *iter; #ifdef CONFIG_COMPAT struct compat_xt_counters_info compat_tmp; @@ -1443,11 +1432,10 @@ do_add_counters(struct net *net, void __user *user, unsigned int len, curcpu = smp_processor_id(); xt_info_wrlock(curcpu); loc_cpu_entry = private->entries[curcpu]; - IP6T_ENTRY_ITERATE(loc_cpu_entry, - private->size, - add_counter_to_entry, - paddc, - &i); + xt_entry_foreach(iter, loc_cpu_entry, private->size) { + ADD_COUNTER(iter->counters, paddc[i].bcnt, paddc[i].pcnt); + ++i; + } xt_info_wrunlock(curcpu); unlock_up_free: @@ -1476,45 +1464,40 @@ struct compat_ip6t_replace { static int compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, - unsigned int *i) + unsigned int i) { struct ip6t_entry_target *t; struct compat_ip6t_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; - int ret; + const struct xt_entry_match *ematch; + int ret = 0; - ret = -EFAULT; origsize = *size; ce = (struct compat_ip6t_entry __user *)*dstptr; - if (copy_to_user(ce, e, sizeof(struct ip6t_entry))) - goto out; - - if (copy_to_user(&ce->counters, &counters[*i], sizeof(counters[*i]))) - goto out; + if (copy_to_user(ce, e, sizeof(struct ip6t_entry)) != 0 || + copy_to_user(&ce->counters, &counters[i], + sizeof(counters[i])) != 0) + return -EFAULT; *dstptr += sizeof(struct compat_ip6t_entry); *size -= sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); - ret = IP6T_MATCH_ITERATE(e, xt_compat_match_to_user, dstptr, size); + xt_ematch_foreach(ematch, e) { + ret = xt_compat_match_to_user(ematch, dstptr, size); + if (ret != 0) + return ret; + } target_offset = e->target_offset - (origsize - *size); - if (ret) - goto out; t = ip6t_get_target(e); ret = xt_compat_target_to_user(t, dstptr, size); if (ret) - goto out; - ret = -EFAULT; + return ret; next_offset = e->next_offset - (origsize - *size); - if (put_user(target_offset, &ce->target_offset)) - goto out; - if (put_user(next_offset, &ce->next_offset)) - goto out; - - (*i)++; + if (put_user(target_offset, &ce->target_offset) != 0 || + put_user(next_offset, &ce->next_offset) != 0) + return -EFAULT; return 0; -out: - return ret; } static int @@ -1522,7 +1505,7 @@ compat_find_calc_match(struct ip6t_entry_match *m, const char *name, const struct ip6t_ip6 *ipv6, unsigned int hookmask, - int *size, unsigned int *i) + int *size) { struct xt_match *match; @@ -1536,47 +1519,32 @@ compat_find_calc_match(struct ip6t_entry_match *m, } m->u.kernel.match = match; *size += xt_compat_match_offset(match); - - (*i)++; - return 0; -} - -static int -compat_release_match(struct ip6t_entry_match *m, unsigned int *i) -{ - if (i && (*i)-- == 0) - return 1; - - module_put(m->u.kernel.match->me); return 0; } -static int -compat_release_entry(struct compat_ip6t_entry *e, unsigned int *i) +static void compat_release_entry(struct compat_ip6t_entry *e) { struct ip6t_entry_target *t; - - if (i && (*i)-- == 0) - return 1; + struct xt_entry_match *ematch; /* Cleanup all matches */ - COMPAT_IP6T_MATCH_ITERATE(e, compat_release_match, NULL); + xt_ematch_foreach(ematch, e) + module_put(ematch->u.kernel.match->me); t = compat_ip6t_get_target(e); module_put(t->u.kernel.target->me); - return 0; } static int check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, struct xt_table_info *newinfo, unsigned int *size, - unsigned char *base, - unsigned char *limit, - unsigned int *hook_entries, - unsigned int *underflows, - unsigned int *i, + const unsigned char *base, + const unsigned char *limit, + const unsigned int *hook_entries, + const unsigned int *underflows, const char *name) { + struct xt_entry_match *ematch; struct ip6t_entry_target *t; struct xt_target *target; unsigned int entry_offset; @@ -1605,10 +1573,13 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - (void *)base; j = 0; - ret = COMPAT_IP6T_MATCH_ITERATE(e, compat_find_calc_match, name, - &e->ipv6, e->comefrom, &off, &j); - if (ret != 0) - goto release_matches; + xt_ematch_foreach(ematch, e) { + ret = compat_find_calc_match(ematch, name, + &e->ipv6, e->comefrom, &off); + if (ret != 0) + goto release_matches; + ++j; + } t = compat_ip6t_get_target(e); target = try_then_request_module(xt_find_target(AF_INET6, @@ -1640,14 +1611,16 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, /* Clear counters and comefrom */ memset(&e->counters, 0, sizeof(e->counters)); e->comefrom = 0; - - (*i)++; return 0; out: module_put(t->u.kernel.target->me); release_matches: - IP6T_MATCH_ITERATE(e, compat_release_match, &j); + xt_ematch_foreach(ematch, e) { + if (j-- == 0) + break; + module_put(ematch->u.kernel.match->me); + } return ret; } @@ -1661,6 +1634,7 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, struct ip6t_entry *de; unsigned int origsize; int ret, h; + struct xt_entry_match *ematch; ret = 0; origsize = *size; @@ -1671,10 +1645,11 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, *dstptr += sizeof(struct ip6t_entry); *size += sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); - ret = COMPAT_IP6T_MATCH_ITERATE(e, xt_compat_match_from_user, - dstptr, size); - if (ret) - return ret; + xt_ematch_foreach(ematch, e) { + ret = xt_compat_match_from_user(ematch, dstptr, size); + if (ret != 0) + return ret; + } de->target_offset = e->target_offset - (origsize - *size); t = compat_ip6t_get_target(e); target = t->u.kernel.target; @@ -1690,36 +1665,44 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, return ret; } -static int compat_check_entry(struct ip6t_entry *e, const char *name, - unsigned int *i) +static int compat_check_entry(struct ip6t_entry *e, struct net *net, + const char *name) { unsigned int j; - int ret; + int ret = 0; struct xt_mtchk_param mtpar; + struct xt_entry_match *ematch; j = 0; + mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ipv6; mtpar.hook_mask = e->comefrom; mtpar.family = NFPROTO_IPV6; - ret = IP6T_MATCH_ITERATE(e, check_match, &mtpar, &j); - if (ret) - goto cleanup_matches; + xt_ematch_foreach(ematch, e) { + ret = check_match(ematch, &mtpar); + if (ret != 0) + goto cleanup_matches; + ++j; + } - ret = check_target(e, name); + ret = check_target(e, net, name); if (ret) goto cleanup_matches; - - (*i)++; return 0; cleanup_matches: - IP6T_MATCH_ITERATE(e, cleanup_match, &j); + xt_ematch_foreach(ematch, e) { + if (j-- == 0) + break; + cleanup_match(ematch, net); + } return ret; } static int -translate_compat_table(const char *name, +translate_compat_table(struct net *net, + const char *name, unsigned int valid_hooks, struct xt_table_info **pinfo, void **pentry0, @@ -1731,8 +1714,10 @@ translate_compat_table(const char *name, unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; + struct compat_ip6t_entry *iter0; + struct ip6t_entry *iter1; unsigned int size; - int ret; + int ret = 0; info = *pinfo; entry0 = *pentry0; @@ -1749,13 +1734,17 @@ translate_compat_table(const char *name, j = 0; xt_compat_lock(AF_INET6); /* Walk through entries, checking offsets. */ - ret = COMPAT_IP6T_ENTRY_ITERATE(entry0, total_size, - check_compat_entry_size_and_hooks, - info, &size, entry0, - entry0 + total_size, - hook_entries, underflows, &j, name); - if (ret != 0) - goto out_unlock; + xt_entry_foreach(iter0, entry0, total_size) { + ret = check_compat_entry_size_and_hooks(iter0, info, &size, + entry0, + entry0 + total_size, + hook_entries, + underflows, + name); + if (ret != 0) + goto out_unlock; + ++j; + } ret = -EINVAL; if (j != number) { @@ -1794,9 +1783,12 @@ translate_compat_table(const char *name, entry1 = newinfo->entries[raw_smp_processor_id()]; pos = entry1; size = total_size; - ret = COMPAT_IP6T_ENTRY_ITERATE(entry0, total_size, - compat_copy_entry_from_user, - &pos, &size, name, newinfo, entry1); + xt_entry_foreach(iter0, entry0, total_size) { + ret = compat_copy_entry_from_user(iter0, &pos, &size, + name, newinfo, entry1); + if (ret != 0) + break; + } xt_compat_flush_offsets(AF_INET6); xt_compat_unlock(AF_INET6); if (ret) @@ -1807,13 +1799,32 @@ translate_compat_table(const char *name, goto free_newinfo; i = 0; - ret = IP6T_ENTRY_ITERATE(entry1, newinfo->size, compat_check_entry, - name, &i); + xt_entry_foreach(iter1, entry1, newinfo->size) { + ret = compat_check_entry(iter1, net, name); + if (ret != 0) + break; + ++i; + } if (ret) { + /* + * The first i matches need cleanup_entry (calls ->destroy) + * because they had called ->check already. The other j-i + * entries need only release. + */ + int skip = i; j -= i; - COMPAT_IP6T_ENTRY_ITERATE_CONTINUE(entry0, newinfo->size, i, - compat_release_entry, &j); - IP6T_ENTRY_ITERATE(entry1, newinfo->size, cleanup_entry, &i); + xt_entry_foreach(iter0, entry0, newinfo->size) { + if (skip-- > 0) + continue; + if (j-- == 0) + break; + compat_release_entry(iter0); + } + xt_entry_foreach(iter1, entry1, newinfo->size) { + if (i-- == 0) + break; + cleanup_entry(iter1, net); + } xt_free_table_info(newinfo); return ret; } @@ -1831,7 +1842,11 @@ translate_compat_table(const char *name, free_newinfo: xt_free_table_info(newinfo); out: - COMPAT_IP6T_ENTRY_ITERATE(entry0, total_size, compat_release_entry, &j); + xt_entry_foreach(iter0, entry0, total_size) { + if (j-- == 0) + break; + compat_release_entry(iter0); + } return ret; out_unlock: xt_compat_flush_offsets(AF_INET6); @@ -1846,6 +1861,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) struct compat_ip6t_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; + struct ip6t_entry *iter; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; @@ -1868,7 +1884,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) goto free_newinfo; } - ret = translate_compat_table(tmp.name, tmp.valid_hooks, + ret = translate_compat_table(net, tmp.name, tmp.valid_hooks, &newinfo, &loc_cpu_entry, tmp.size, tmp.num_entries, tmp.hook_entry, tmp.underflow); @@ -1884,7 +1900,8 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) return 0; free_newinfo_untrans: - IP6T_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL); + xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) + cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; @@ -1933,6 +1950,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, int ret = 0; const void *loc_cpu_entry; unsigned int i = 0; + struct ip6t_entry *iter; counters = alloc_counters(table); if (IS_ERR(counters)) @@ -1945,9 +1963,12 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, loc_cpu_entry = private->entries[raw_smp_processor_id()]; pos = userptr; size = total_size; - ret = IP6T_ENTRY_ITERATE(loc_cpu_entry, total_size, - compat_copy_entry_to_user, - &pos, &size, counters, &i); + xt_entry_foreach(iter, loc_cpu_entry, total_size) { + ret = compat_copy_entry_to_user(iter, &pos, + &size, counters, i++); + if (ret != 0) + break; + } vfree(counters); return ret; @@ -2121,11 +2142,7 @@ struct xt_table *ip6t_register_table(struct net *net, loc_cpu_entry = newinfo->entries[raw_smp_processor_id()]; memcpy(loc_cpu_entry, repl->entries, repl->size); - ret = translate_table(table->name, table->valid_hooks, - newinfo, loc_cpu_entry, repl->size, - repl->num_entries, - repl->hook_entry, - repl->underflow); + ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) goto out_free; @@ -2142,17 +2159,19 @@ out: return ERR_PTR(ret); } -void ip6t_unregister_table(struct xt_table *table) +void ip6t_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; struct module *table_owner = table->me; + struct ip6t_entry *iter; private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries[raw_smp_processor_id()]; - IP6T_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, NULL); + xt_entry_foreach(iter, loc_cpu_entry, private->size) + cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 8311ca31816..dd8afbaf00a 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -169,7 +169,7 @@ send_unreach(struct net *net, struct sk_buff *skb_in, unsigned char code, if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) skb_in->dev = net->loopback_dev; - icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0, NULL); + icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); } static unsigned int diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index ad378efd0eb..36b72cafc22 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -21,99 +21,26 @@ MODULE_DESCRIPTION("ip6tables filter table"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) -static struct -{ - struct ip6t_replace repl; - struct ip6t_standard entries[3]; - struct ip6t_error term; -} initial_table __net_initdata = { - .repl = { - .name = "filter", - .valid_hooks = FILTER_VALID_HOOKS, - .num_entries = 4, - .size = sizeof(struct ip6t_standard) * 3 + sizeof(struct ip6t_error), - .hook_entry = { - [NF_INET_LOCAL_IN] = 0, - [NF_INET_FORWARD] = sizeof(struct ip6t_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2 - }, - .underflow = { - [NF_INET_LOCAL_IN] = 0, - [NF_INET_FORWARD] = sizeof(struct ip6t_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2 - }, - }, - .entries = { - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* FORWARD */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - }, - .term = IP6T_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_FILTER, }; /* The work comes in here from netfilter.c. */ static unsigned int -ip6t_in_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_filter); -} - -static unsigned int -ip6t_local_out_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ip6table_filter_hook(unsigned int hook, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { -#if 0 - /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) || - ip_hdrlen(skb) < sizeof(struct iphdr)) { - if (net_ratelimit()) - printk("ip6t_hook: happy cracking.\n"); - return NF_ACCEPT; - } -#endif + const struct net *net = dev_net((in != NULL) ? in : out); - return ip6t_do_table(skb, hook, in, out, - dev_net(out)->ipv6.ip6table_filter); + return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_filter); } -static struct nf_hook_ops ip6t_ops[] __read_mostly = { - { - .hook = ip6t_in_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP6_PRI_FILTER, - }, - { - .hook = ip6t_in_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_FORWARD, - .priority = NF_IP6_PRI_FILTER, - }, - { - .hook = ip6t_local_out_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP6_PRI_FILTER, - }, -}; +static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ static int forward = NF_ACCEPT; @@ -121,9 +48,18 @@ module_param(forward, bool, 0000); static int __net_init ip6table_filter_net_init(struct net *net) { - /* Register table */ + struct ip6t_replace *repl; + + repl = ip6t_alloc_initial_table(&packet_filter); + if (repl == NULL) + return -ENOMEM; + /* Entry 1 is the FORWARD hook */ + ((struct ip6t_standard *)repl->entries)[1].target.verdict = + -forward - 1; + net->ipv6.ip6table_filter = - ip6t_register_table(net, &packet_filter, &initial_table.repl); + ip6t_register_table(net, &packet_filter, repl); + kfree(repl); if (IS_ERR(net->ipv6.ip6table_filter)) return PTR_ERR(net->ipv6.ip6table_filter); return 0; @@ -131,7 +67,7 @@ static int __net_init ip6table_filter_net_init(struct net *net) static void __net_exit ip6table_filter_net_exit(struct net *net) { - ip6t_unregister_table(net->ipv6.ip6table_filter); + ip6t_unregister_table(net, net->ipv6.ip6table_filter); } static struct pernet_operations ip6table_filter_net_ops = { @@ -148,17 +84,16 @@ static int __init ip6table_filter_init(void) return -EINVAL; } - /* Entry 1 is the FORWARD hook */ - initial_table.entries[1].target.verdict = -forward - 1; - ret = register_pernet_subsys(&ip6table_filter_net_ops); if (ret < 0) return ret; /* Register hooks */ - ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); - if (ret < 0) + filter_ops = xt_hook_link(&packet_filter, ip6table_filter_hook); + if (IS_ERR(filter_ops)) { + ret = PTR_ERR(filter_ops); goto cleanup_table; + } return ret; @@ -169,7 +104,7 @@ static int __init ip6table_filter_init(void) static void __exit ip6table_filter_fini(void) { - nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); + xt_hook_unlink(&packet_filter, filter_ops); unregister_pernet_subsys(&ip6table_filter_net_ops); } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index a929c19d30e..7844e557c0e 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -21,80 +21,17 @@ MODULE_DESCRIPTION("ip6tables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) -static const struct -{ - struct ip6t_replace repl; - struct ip6t_standard entries[5]; - struct ip6t_error term; -} initial_table __net_initdata = { - .repl = { - .name = "mangle", - .valid_hooks = MANGLE_VALID_HOOKS, - .num_entries = 6, - .size = sizeof(struct ip6t_standard) * 5 + sizeof(struct ip6t_error), - .hook_entry = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_LOCAL_IN] = sizeof(struct ip6t_standard), - [NF_INET_FORWARD] = sizeof(struct ip6t_standard) * 2, - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 3, - [NF_INET_POST_ROUTING] = sizeof(struct ip6t_standard) * 4, - }, - .underflow = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_LOCAL_IN] = sizeof(struct ip6t_standard), - [NF_INET_FORWARD] = sizeof(struct ip6t_standard) * 2, - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 3, - [NF_INET_POST_ROUTING] = sizeof(struct ip6t_standard) * 4, - }, - }, - .entries = { - IP6T_STANDARD_INIT(NF_ACCEPT), /* PRE_ROUTING */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* FORWARD */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* POST_ROUTING */ - }, - .term = IP6T_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_MANGLE, }; -/* The work comes in here from netfilter.c. */ -static unsigned int -ip6t_in_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_mangle); -} - -static unsigned int -ip6t_post_routing_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ip6t_do_table(skb, hook, in, out, - dev_net(out)->ipv6.ip6table_mangle); -} - static unsigned int -ip6t_local_out_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out) { - unsigned int ret; struct in6_addr saddr, daddr; u_int8_t hop_limit; @@ -119,7 +56,7 @@ ip6t_local_out_hook(unsigned int hook, /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u_int32_t *)ipv6_hdr(skb)); - ret = ip6t_do_table(skb, hook, in, out, + ret = ip6t_do_table(skb, NF_INET_LOCAL_OUT, NULL, out, dev_net(out)->ipv6.ip6table_mangle); if (ret != NF_DROP && ret != NF_STOLEN && @@ -132,49 +69,33 @@ ip6t_local_out_hook(unsigned int hook, return ret; } -static struct nf_hook_ops ip6t_ops[] __read_mostly = { - { - .hook = ip6t_in_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP6_PRI_MANGLE, - }, - { - .hook = ip6t_in_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP6_PRI_MANGLE, - }, - { - .hook = ip6t_in_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_FORWARD, - .priority = NF_IP6_PRI_MANGLE, - }, - { - .hook = ip6t_local_out_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP6_PRI_MANGLE, - }, - { - .hook = ip6t_post_routing_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP6_PRI_MANGLE, - }, -}; +/* The work comes in here from netfilter.c. */ +static unsigned int +ip6table_mangle_hook(unsigned int hook, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + if (hook == NF_INET_LOCAL_OUT) + return ip6t_mangle_out(skb, out); + if (hook == NF_INET_POST_ROUTING) + return ip6t_do_table(skb, hook, in, out, + dev_net(out)->ipv6.ip6table_mangle); + /* INPUT/FORWARD */ + return ip6t_do_table(skb, hook, in, out, + dev_net(in)->ipv6.ip6table_mangle); +} +static struct nf_hook_ops *mangle_ops __read_mostly; static int __net_init ip6table_mangle_net_init(struct net *net) { - /* Register table */ + struct ip6t_replace *repl; + + repl = ip6t_alloc_initial_table(&packet_mangler); + if (repl == NULL) + return -ENOMEM; net->ipv6.ip6table_mangle = - ip6t_register_table(net, &packet_mangler, &initial_table.repl); + ip6t_register_table(net, &packet_mangler, repl); + kfree(repl); if (IS_ERR(net->ipv6.ip6table_mangle)) return PTR_ERR(net->ipv6.ip6table_mangle); return 0; @@ -182,7 +103,7 @@ static int __net_init ip6table_mangle_net_init(struct net *net) static void __net_exit ip6table_mangle_net_exit(struct net *net) { - ip6t_unregister_table(net->ipv6.ip6table_mangle); + ip6t_unregister_table(net, net->ipv6.ip6table_mangle); } static struct pernet_operations ip6table_mangle_net_ops = { @@ -199,9 +120,11 @@ static int __init ip6table_mangle_init(void) return ret; /* Register hooks */ - ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); - if (ret < 0) + mangle_ops = xt_hook_link(&packet_mangler, ip6table_mangle_hook); + if (IS_ERR(mangle_ops)) { + ret = PTR_ERR(mangle_ops); goto cleanup_table; + } return ret; @@ -212,7 +135,7 @@ static int __init ip6table_mangle_init(void) static void __exit ip6table_mangle_fini(void) { - nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); + xt_hook_unlink(&packet_mangler, mangle_ops); unregister_pernet_subsys(&ip6table_mangle_net_ops); } diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index ed1a1180f3b..aef31a29de9 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -8,85 +8,37 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) -static const struct -{ - struct ip6t_replace repl; - struct ip6t_standard entries[2]; - struct ip6t_error term; -} initial_table __net_initdata = { - .repl = { - .name = "raw", - .valid_hooks = RAW_VALID_HOOKS, - .num_entries = 3, - .size = sizeof(struct ip6t_standard) * 2 + sizeof(struct ip6t_error), - .hook_entry = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) - }, - .underflow = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) - }, - }, - .entries = { - IP6T_STANDARD_INIT(NF_ACCEPT), /* PRE_ROUTING */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - }, - .term = IP6T_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_FIRST, }; /* The work comes in here from netfilter.c. */ static unsigned int -ip6t_pre_routing_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ip6table_raw_hook(unsigned int hook, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_raw); -} + const struct net *net = dev_net((in != NULL) ? in : out); -static unsigned int -ip6t_local_out_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ip6t_do_table(skb, hook, in, out, - dev_net(out)->ipv6.ip6table_raw); + return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_raw); } -static struct nf_hook_ops ip6t_ops[] __read_mostly = { - { - .hook = ip6t_pre_routing_hook, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP6_PRI_FIRST, - .owner = THIS_MODULE, - }, - { - .hook = ip6t_local_out_hook, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP6_PRI_FIRST, - .owner = THIS_MODULE, - }, -}; +static struct nf_hook_ops *rawtable_ops __read_mostly; static int __net_init ip6table_raw_net_init(struct net *net) { - /* Register table */ + struct ip6t_replace *repl; + + repl = ip6t_alloc_initial_table(&packet_raw); + if (repl == NULL) + return -ENOMEM; net->ipv6.ip6table_raw = - ip6t_register_table(net, &packet_raw, &initial_table.repl); + ip6t_register_table(net, &packet_raw, repl); + kfree(repl); if (IS_ERR(net->ipv6.ip6table_raw)) return PTR_ERR(net->ipv6.ip6table_raw); return 0; @@ -94,7 +46,7 @@ static int __net_init ip6table_raw_net_init(struct net *net) static void __net_exit ip6table_raw_net_exit(struct net *net) { - ip6t_unregister_table(net->ipv6.ip6table_raw); + ip6t_unregister_table(net, net->ipv6.ip6table_raw); } static struct pernet_operations ip6table_raw_net_ops = { @@ -111,9 +63,11 @@ static int __init ip6table_raw_init(void) return ret; /* Register hooks */ - ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); - if (ret < 0) + rawtable_ops = xt_hook_link(&packet_raw, ip6table_raw_hook); + if (IS_ERR(rawtable_ops)) { + ret = PTR_ERR(rawtable_ops); goto cleanup_table; + } return ret; @@ -124,7 +78,7 @@ static int __init ip6table_raw_init(void) static void __exit ip6table_raw_fini(void) { - nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); + xt_hook_unlink(&packet_raw, rawtable_ops); unregister_pernet_subsys(&ip6table_raw_net_ops); } diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 41b444c6093..0824d865aa9 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -26,106 +26,37 @@ MODULE_DESCRIPTION("ip6tables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) -static const struct -{ - struct ip6t_replace repl; - struct ip6t_standard entries[3]; - struct ip6t_error term; -} initial_table __net_initdata = { - .repl = { - .name = "security", - .valid_hooks = SECURITY_VALID_HOOKS, - .num_entries = 4, - .size = sizeof(struct ip6t_standard) * 3 + sizeof(struct ip6t_error), - .hook_entry = { - [NF_INET_LOCAL_IN] = 0, - [NF_INET_FORWARD] = sizeof(struct ip6t_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2, - }, - .underflow = { - [NF_INET_LOCAL_IN] = 0, - [NF_INET_FORWARD] = sizeof(struct ip6t_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2, - }, - }, - .entries = { - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* FORWARD */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - }, - .term = IP6T_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_SECURITY, }; static unsigned int -ip6t_local_in_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_security); -} - -static unsigned int -ip6t_forward_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ip6table_security_hook(unsigned int hook, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_security); -} + const struct net *net = dev_net((in != NULL) ? in : out); -static unsigned int -ip6t_local_out_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - /* TBD: handle short packets via raw socket */ - return ip6t_do_table(skb, hook, in, out, - dev_net(out)->ipv6.ip6table_security); + return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_security); } -static struct nf_hook_ops ip6t_ops[] __read_mostly = { - { - .hook = ip6t_local_in_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP6_PRI_SECURITY, - }, - { - .hook = ip6t_forward_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_FORWARD, - .priority = NF_IP6_PRI_SECURITY, - }, - { - .hook = ip6t_local_out_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP6_PRI_SECURITY, - }, -}; +static struct nf_hook_ops *sectbl_ops __read_mostly; static int __net_init ip6table_security_net_init(struct net *net) { - net->ipv6.ip6table_security = - ip6t_register_table(net, &security_table, &initial_table.repl); + struct ip6t_replace *repl; + repl = ip6t_alloc_initial_table(&security_table); + if (repl == NULL) + return -ENOMEM; + net->ipv6.ip6table_security = + ip6t_register_table(net, &security_table, repl); + kfree(repl); if (IS_ERR(net->ipv6.ip6table_security)) return PTR_ERR(net->ipv6.ip6table_security); @@ -134,7 +65,7 @@ static int __net_init ip6table_security_net_init(struct net *net) static void __net_exit ip6table_security_net_exit(struct net *net) { - ip6t_unregister_table(net->ipv6.ip6table_security); + ip6t_unregister_table(net, net->ipv6.ip6table_security); } static struct pernet_operations ip6table_security_net_ops = { @@ -150,9 +81,11 @@ static int __init ip6table_security_init(void) if (ret < 0) return ret; - ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); - if (ret < 0) + sectbl_ops = xt_hook_link(&security_table, ip6table_security_hook); + if (IS_ERR(sectbl_ops)) { + ret = PTR_ERR(sectbl_ops); goto cleanup_table; + } return ret; @@ -163,7 +96,7 @@ cleanup_table: static void __exit ip6table_security_fini(void) { - nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); + xt_hook_unlink(&security_table, sectbl_ops); unregister_pernet_subsys(&ip6table_security_net_ops); } diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 0956ebabbff..996c3f41fec 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -27,6 +27,7 @@ #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> #include <net/netfilter/nf_log.h> @@ -191,15 +192,20 @@ out: static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, struct sk_buff *skb) { + u16 zone = NF_CT_DEFAULT_ZONE; + + if (skb->nfct) + zone = nf_ct_zone((struct nf_conn *)skb->nfct); + #ifdef CONFIG_BRIDGE_NETFILTER if (skb->nf_bridge && skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) - return IP6_DEFRAG_CONNTRACK_BRIDGE_IN; + return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone; #endif if (hooknum == NF_INET_PRE_ROUTING) - return IP6_DEFRAG_CONNTRACK_IN; + return IP6_DEFRAG_CONNTRACK_IN + zone; else - return IP6_DEFRAG_CONNTRACK_OUT; + return IP6_DEFRAG_CONNTRACK_OUT + zone; } @@ -212,7 +218,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum, struct sk_buff *reasm; /* Previously seen (loopback)? */ - if (skb->nfct) + if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct)) return NF_ACCEPT; reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb)); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index c7b8bd1d798..9be81776415 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -23,6 +23,7 @@ #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_conntrack_icmpv6.h> #include <net/netfilter/nf_log.h> @@ -128,7 +129,7 @@ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb, } static int -icmpv6_error_message(struct net *net, +icmpv6_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int icmp6off, enum ip_conntrack_info *ctinfo, @@ -137,6 +138,7 @@ icmpv6_error_message(struct net *net, struct nf_conntrack_tuple intuple, origtuple; const struct nf_conntrack_tuple_hash *h; const struct nf_conntrack_l4proto *inproto; + u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; NF_CT_ASSERT(skb->nfct == NULL); @@ -163,7 +165,7 @@ icmpv6_error_message(struct net *net, *ctinfo = IP_CT_RELATED; - h = nf_conntrack_find_get(net, &intuple); + h = nf_conntrack_find_get(net, zone, &intuple); if (!h) { pr_debug("icmpv6_error: no match\n"); return -NF_ACCEPT; @@ -179,7 +181,8 @@ icmpv6_error_message(struct net *net, } static int -icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff, +icmpv6_error(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum) { const struct icmp6hdr *icmp6h; @@ -215,7 +218,7 @@ icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff, if (icmp6h->icmp6_type >= 128) return NF_ACCEPT; - return icmpv6_error_message(net, skb, dataoff, ctinfo, hooknum); + return icmpv6_error_message(net, tmpl, skb, dataoff, ctinfo, hooknum); } #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 312c20adc83..f1171b74465 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -45,9 +45,6 @@ #include <linux/kernel.h> #include <linux/module.h> -#define NF_CT_FRAG6_HIGH_THRESH 262144 /* == 256*1024 */ -#define NF_CT_FRAG6_LOW_THRESH 196608 /* == 192*1024 */ -#define NF_CT_FRAG6_TIMEOUT IPV6_FRAG_TIMEOUT struct nf_ct_frag6_skb_cb { @@ -63,6 +60,7 @@ struct nf_ct_frag6_queue struct inet_frag_queue q; __be32 id; /* fragment id */ + u32 user; struct in6_addr saddr; struct in6_addr daddr; @@ -471,7 +469,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) /* all original skbs are linked into the NFCT_FRAG6_CB(head).orig */ fp = skb_shinfo(head)->frag_list; - if (NFCT_FRAG6_CB(fp)->orig == NULL) + if (fp && NFCT_FRAG6_CB(fp)->orig == NULL) /* at above code, head skb is divided into two skbs. */ fp = fp->next; @@ -597,12 +595,6 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) hdr = ipv6_hdr(clone); fhdr = (struct frag_hdr *)skb_transport_header(clone); - if (!(fhdr->frag_off & htons(0xFFF9))) { - pr_debug("Invalid fragment offset\n"); - /* It is not a fragmented frame */ - goto ret_orig; - } - if (atomic_read(&nf_init_frags.mem) > nf_init_frags.high_thresh) nf_ct_frag6_evictor(); @@ -669,8 +661,8 @@ int nf_ct_frag6_init(void) nf_frags.frag_expire = nf_ct_frag6_expire; nf_frags.secret_interval = 10 * 60 * HZ; nf_init_frags.timeout = IPV6_FRAG_TIMEOUT; - nf_init_frags.high_thresh = 256 * 1024; - nf_init_frags.low_thresh = 192 * 1024; + nf_init_frags.high_thresh = IPV6_FRAG_HIGH_THRESH; + nf_init_frags.low_thresh = IPV6_FRAG_LOW_THRESH; inet_frags_init_net(&nf_init_frags); inet_frags_init(&nf_frags); diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index c9605c3ad91..58344c0fbd1 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -59,7 +59,7 @@ static const struct file_operations sockstat6_seq_fops = { .release = single_release_net, }; -static struct snmp_mib snmp6_ipstats_list[] = { +static const struct snmp_mib snmp6_ipstats_list[] = { /* ipv6 mib according to RFC 2465 */ SNMP_MIB_ITEM("Ip6InReceives", IPSTATS_MIB_INPKTS), SNMP_MIB_ITEM("Ip6InHdrErrors", IPSTATS_MIB_INHDRERRORS), @@ -92,7 +92,7 @@ static struct snmp_mib snmp6_ipstats_list[] = { SNMP_MIB_SENTINEL }; -static struct snmp_mib snmp6_icmp6_list[] = { +static const struct snmp_mib snmp6_icmp6_list[] = { /* icmpv6 mib according to RFC 2466 */ SNMP_MIB_ITEM("Icmp6InMsgs", ICMP6_MIB_INMSGS), SNMP_MIB_ITEM("Icmp6InErrors", ICMP6_MIB_INERRORS), @@ -120,7 +120,7 @@ static const char *const icmp6type2name[256] = { }; -static struct snmp_mib snmp6_udp6_list[] = { +static const struct snmp_mib snmp6_udp6_list[] = { SNMP_MIB_ITEM("Udp6InDatagrams", UDP_MIB_INDATAGRAMS), SNMP_MIB_ITEM("Udp6NoPorts", UDP_MIB_NOPORTS), SNMP_MIB_ITEM("Udp6InErrors", UDP_MIB_INERRORS), @@ -128,7 +128,7 @@ static struct snmp_mib snmp6_udp6_list[] = { SNMP_MIB_SENTINEL }; -static struct snmp_mib snmp6_udplite6_list[] = { +static const struct snmp_mib snmp6_udplite6_list[] = { SNMP_MIB_ITEM("UdpLite6InDatagrams", UDP_MIB_INDATAGRAMS), SNMP_MIB_ITEM("UdpLite6NoPorts", UDP_MIB_NOPORTS), SNMP_MIB_ITEM("UdpLite6InErrors", UDP_MIB_INERRORS), @@ -136,7 +136,7 @@ static struct snmp_mib snmp6_udplite6_list[] = { SNMP_MIB_SENTINEL }; -static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib) +static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **mib) { char name[32]; int i; @@ -170,8 +170,8 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib) return; } -static inline void -snmp6_seq_show_item(struct seq_file *seq, void **mib, struct snmp_mib *itemlist) +static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **mib, + const struct snmp_mib *itemlist) { int i; for (i=0; itemlist[i].name; i++) @@ -183,14 +183,15 @@ static int snmp6_seq_show(struct seq_file *seq, void *v) { struct net *net = (struct net *)seq->private; - snmp6_seq_show_item(seq, (void **)net->mib.ipv6_statistics, + snmp6_seq_show_item(seq, (void __percpu **)net->mib.ipv6_statistics, snmp6_ipstats_list); - snmp6_seq_show_item(seq, (void **)net->mib.icmpv6_statistics, + snmp6_seq_show_item(seq, (void __percpu **)net->mib.icmpv6_statistics, snmp6_icmp6_list); - snmp6_seq_show_icmpv6msg(seq, (void **)net->mib.icmpv6msg_statistics); - snmp6_seq_show_item(seq, (void **)net->mib.udp_stats_in6, + snmp6_seq_show_icmpv6msg(seq, + (void __percpu **)net->mib.icmpv6msg_statistics); + snmp6_seq_show_item(seq, (void __percpu **)net->mib.udp_stats_in6, snmp6_udp6_list); - snmp6_seq_show_item(seq, (void **)net->mib.udplite_stats_in6, + snmp6_seq_show_item(seq, (void __percpu **)net->mib.udplite_stats_in6, snmp6_udplite6_list); return 0; } @@ -213,9 +214,11 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v) struct inet6_dev *idev = (struct inet6_dev *)seq->private; seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex); - snmp6_seq_show_item(seq, (void **)idev->stats.ipv6, snmp6_ipstats_list); - snmp6_seq_show_item(seq, (void **)idev->stats.icmpv6, snmp6_icmp6_list); - snmp6_seq_show_icmpv6msg(seq, (void **)idev->stats.icmpv6msg); + snmp6_seq_show_item(seq, (void __percpu **)idev->stats.ipv6, + snmp6_ipstats_list); + snmp6_seq_show_item(seq, (void __percpu **)idev->stats.icmpv6, + snmp6_icmp6_list); + snmp6_seq_show_icmpv6msg(seq, (void __percpu **)idev->stats.icmpv6msg); return 0; } @@ -259,7 +262,7 @@ int snmp6_unregister_dev(struct inet6_dev *idev) struct net *net = dev_net(idev->dev); if (!net->mib.proc_net_devsnmp6) return -ENOENT; - if (!idev || !idev->stats.proc_dir_entry) + if (!idev->stats.proc_dir_entry) return -EINVAL; remove_proc_entry(idev->stats.proc_dir_entry->name, net->mib.proc_net_devsnmp6); @@ -267,7 +270,7 @@ int snmp6_unregister_dev(struct inet6_dev *idev) return 0; } -static int ipv6_proc_init_net(struct net *net) +static int __net_init ipv6_proc_init_net(struct net *net) { if (!proc_net_fops_create(net, "sockstat6", S_IRUGO, &sockstat6_seq_fops)) @@ -288,7 +291,7 @@ proc_dev_snmp6_fail: return -ENOMEM; } -static void ipv6_proc_exit_net(struct net *net) +static void __net_exit ipv6_proc_exit_net(struct net *net) { proc_net_remove(net, "sockstat6"); proc_net_remove(net, "dev_snmp6"); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 926ce8eeffa..ed31c37c6e3 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1275,7 +1275,7 @@ static const struct file_operations raw6_seq_fops = { .release = seq_release_net, }; -static int raw6_init_net(struct net *net) +static int __net_init raw6_init_net(struct net *net) { if (!proc_net_fops_create(net, "raw6", S_IRUGO, &raw6_seq_fops)) return -ENOMEM; @@ -1283,7 +1283,7 @@ static int raw6_init_net(struct net *net) return 0; } -static void raw6_exit_net(struct net *net) +static void __net_exit raw6_exit_net(struct net *net) { proc_net_remove(net, "raw6"); } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 2cddea3bd6b..a555156e977 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -228,7 +228,7 @@ static void ip6_frag_expire(unsigned long data) pointer directly, device might already disappeared. */ fq->q.fragments->dev = dev; - icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0, dev); + icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); out_rcu_unlock: rcu_read_unlock(); out: @@ -237,8 +237,7 @@ out: } static __inline__ struct frag_queue * -fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst, - struct inet6_dev *idev) +fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst) { struct inet_frag_queue *q; struct ip6_create_arg arg; @@ -254,13 +253,9 @@ fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst, q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash); if (q == NULL) - goto oom; + return NULL; return container_of(q, struct frag_queue, q); - -oom: - IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_REASMFAILS); - return NULL; } static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, @@ -606,8 +601,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb) if (atomic_read(&net->ipv6.frags.mem) > net->ipv6.frags.high_thresh) ip6_evictor(net, ip6_dst_idev(skb_dst(skb))); - if ((fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr, - ip6_dst_idev(skb_dst(skb)))) != NULL) { + fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr); + if (fq != NULL) { int ret; spin_lock(&fq->q.lock); @@ -672,7 +667,7 @@ static struct ctl_table ip6_frags_ctl_table[] = { { } }; -static int ip6_frags_ns_sysctl_register(struct net *net) +static int __net_init ip6_frags_ns_sysctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -702,7 +697,7 @@ err_alloc: return -ENOMEM; } -static void ip6_frags_ns_sysctl_unregister(struct net *net) +static void __net_exit ip6_frags_ns_sysctl_unregister(struct net *net) { struct ctl_table *table; @@ -745,10 +740,10 @@ static inline void ip6_frags_sysctl_unregister(void) } #endif -static int ipv6_frags_init_net(struct net *net) +static int __net_init ipv6_frags_init_net(struct net *net) { - net->ipv6.frags.high_thresh = 256 * 1024; - net->ipv6.frags.low_thresh = 192 * 1024; + net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; + net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH; net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT; inet_frags_init_net(&net->ipv6.frags); @@ -756,7 +751,7 @@ static int ipv6_frags_init_net(struct net *net) return ip6_frags_ns_sysctl_register(net); } -static void ipv6_frags_exit_net(struct net *net) +static void __net_exit ipv6_frags_exit_net(struct net *net) { ip6_frags_ns_sysctl_unregister(net); inet_frags_exit_net(&net->ipv6.frags, &ip6_frags); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c2bd74c5f8d..52cd3eff31d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -819,15 +819,8 @@ struct dst_entry * ip6_route_output(struct net *net, struct sock *sk, if (!ipv6_addr_any(&fl->fl6_src)) flags |= RT6_LOOKUP_F_HAS_SADDR; - else if (sk) { - unsigned int prefs = inet6_sk(sk)->srcprefs; - if (prefs & IPV6_PREFER_SRC_TMP) - flags |= RT6_LOOKUP_F_SRCPREF_TMP; - if (prefs & IPV6_PREFER_SRC_PUBLIC) - flags |= RT6_LOOKUP_F_SRCPREF_PUBLIC; - if (prefs & IPV6_PREFER_SRC_COA) - flags |= RT6_LOOKUP_F_SRCPREF_COA; - } + else if (sk) + flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs); return fib6_rule_lookup(net, fl, flags, ip6_pol_route_output); } @@ -909,7 +902,7 @@ static void ip6_link_failure(struct sk_buff *skb) { struct rt6_info *rt; - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev); + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); rt = (struct rt6_info *) skb_dst(skb); if (rt) { @@ -1873,7 +1866,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) switch (ipstats_mib_noroutes) { case IPSTATS_MIB_INNOROUTES: type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); - if (type == IPV6_ADDR_ANY || type == IPV6_ADDR_RESERVED) { + if (type == IPV6_ADDR_ANY) { IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS); break; @@ -1884,7 +1877,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) ipstats_mib_noroutes); break; } - icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0, skb->dev); + icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0); kfree_skb(skb); return 0; } @@ -2612,7 +2605,7 @@ ctl_table ipv6_route_table_template[] = { { } }; -struct ctl_table *ipv6_route_sysctl_init(struct net *net) +struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) { struct ctl_table *table; @@ -2637,7 +2630,7 @@ struct ctl_table *ipv6_route_sysctl_init(struct net *net) } #endif -static int ip6_route_net_init(struct net *net) +static int __net_init ip6_route_net_init(struct net *net) { int ret = -ENOMEM; @@ -2702,7 +2695,7 @@ out_ip6_dst_ops: goto out; } -static void ip6_route_net_exit(struct net *net) +static void __net_exit ip6_route_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS proc_net_remove(net, "ipv6_route"); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 976e68244b9..b1eea811be4 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -62,7 +62,6 @@ #define HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) -static void ipip6_fb_tunnel_init(struct net_device *dev); static void ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); @@ -364,7 +363,6 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) goto out; } - INIT_RCU_HEAD(&p->rcu_head); p->next = t->prl; p->addr = a->addr; p->flags = a->flags; @@ -745,7 +743,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (skb->len > mtu) { - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev); + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; } @@ -1120,7 +1118,7 @@ static void ipip6_tunnel_init(struct net_device *dev) ipip6_tunnel_bind_dev(dev); } -static void ipip6_fb_tunnel_init(struct net_device *dev) +static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -1145,7 +1143,7 @@ static struct xfrm_tunnel sit_handler = { .priority = 1, }; -static void sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) +static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) { int prio; @@ -1162,7 +1160,7 @@ static void sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) } } -static int sit_init_net(struct net *net) +static int __net_init sit_init_net(struct net *net) { struct sit_net *sitn = net_generic(net, sit_net_id); int err; @@ -1195,7 +1193,7 @@ err_alloc_dev: return err; } -static void sit_exit_net(struct net *net) +static void __net_exit sit_exit_net(struct net *net) { struct sit_net *sitn = net_generic(net, sit_net_id); LIST_HEAD(list); @@ -1228,15 +1226,14 @@ static int __init sit_init(void) printk(KERN_INFO "IPv6 over IPv4 tunneling driver\n"); - if (xfrm4_tunnel_register(&sit_handler, AF_INET6) < 0) { - printk(KERN_INFO "sit init: Can't add protocol\n"); - return -EAGAIN; - } - err = register_pernet_device(&sit_net_ops); if (err < 0) - xfrm4_tunnel_deregister(&sit_handler, AF_INET6); - + return err; + err = xfrm4_tunnel_register(&sit_handler, AF_INET6); + if (err < 0) { + unregister_pernet_device(&sit_net_ops); + printk(KERN_INFO "sit init: Can't add protocol\n"); + } return err; } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7208a06576c..34d1f0690d7 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -269,7 +269,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); tcp_select_initial_window(tcp_full_space(sk), req->mss, &req->rcv_wnd, &req->window_clamp, - ireq->wscale_ok, &rcv_wscale); + ireq->wscale_ok, &rcv_wscale, + dst_metric(dst, RTAX_INITRWND)); ireq->rcv_wscale = rcv_wscale; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index c690736885b..f841d93bf98 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -55,7 +55,7 @@ struct ctl_path net_ipv6_ctl_path[] = { }; EXPORT_SYMBOL_GPL(net_ipv6_ctl_path); -static int ipv6_sysctl_net_init(struct net *net) +static int __net_init ipv6_sysctl_net_init(struct net *net) { struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; @@ -98,7 +98,7 @@ out_ipv6_table: goto out; } -static void ipv6_sysctl_net_exit(struct net *net) +static void __net_exit ipv6_sysctl_net_exit(struct net *net) { struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index febfd595a40..9b6dbba80d3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -520,6 +520,13 @@ done: return err; } +static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req, + struct request_values *rvp) +{ + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + return tcp_v6_send_synack(sk, req, rvp); +} + static inline void syn_flood_warning(struct sk_buff *skb) { #ifdef CONFIG_SYN_COOKIES @@ -876,7 +883,7 @@ static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) if (genhash || memcmp(hash_location, newhash, 16) != 0) { if (net_ratelimit()) { - printk(KERN_INFO "MD5 Hash %s for (%pI6, %u)->(%pI6, %u)\n", + printk(KERN_INFO "MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n", genhash ? "failed" : "mismatch", &ip6h->saddr, ntohs(th->source), &ip6h->daddr, ntohs(th->dest)); @@ -890,10 +897,11 @@ static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .family = AF_INET6, .obj_size = sizeof(struct tcp6_request_sock), - .rtx_syn_ack = tcp_v6_send_synack, + .rtx_syn_ack = tcp_v6_rtx_synack, .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, - .send_reset = tcp_v6_send_reset + .send_reset = tcp_v6_send_reset, + .syn_ack_timeout = tcp_syn_ack_timeout, }; #ifdef CONFIG_TCP_MD5SIG @@ -1732,8 +1740,11 @@ process: if (!tcp_prequeue(sk, skb)) ret = tcp_v6_do_rcv(sk, skb); } - } else - sk_add_backlog(sk, skb); + } else if (unlikely(sk_add_backlog(sk, skb))) { + bh_unlock_sock(sk); + NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP); + goto discard_and_relse; + } bh_unlock_sock(sk); sock_put(sk); @@ -2105,7 +2116,7 @@ static struct tcp_seq_afinfo tcp6_seq_afinfo = { }, }; -int tcp6_proc_init(struct net *net) +int __net_init tcp6_proc_init(struct net *net) { return tcp_proc_register(net, &tcp6_seq_afinfo); } @@ -2174,18 +2185,18 @@ static struct inet_protosw tcpv6_protosw = { INET_PROTOSW_ICSK, }; -static int tcpv6_net_init(struct net *net) +static int __net_init tcpv6_net_init(struct net *net) { return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, SOCK_RAW, IPPROTO_TCP, net); } -static void tcpv6_net_exit(struct net *net) +static void __net_exit tcpv6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.tcp_sk); } -static void tcpv6_net_exit_batch(struct list_head *net_exit_list) +static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) { inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET6); } diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 51e2832d13a..e17bc1dfc1a 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -98,7 +98,7 @@ static int tunnel6_rcv(struct sk_buff *skb) if (!handler->handler(skb)) return 0; - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, skb->dev); + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); @@ -116,7 +116,7 @@ static int tunnel46_rcv(struct sk_buff *skb) if (!handler->handler(skb)) return 0; - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, skb->dev); + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 69ebdbe78c4..3c0c9c755c9 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -322,7 +322,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; - unsigned int ulen, copied; + unsigned int ulen; int peeked; int err; int is_udplite = IS_UDPLITE(sk); @@ -341,10 +341,9 @@ try_again: goto out; ulen = skb->len - sizeof(struct udphdr); - copied = len; - if (copied > ulen) - copied = ulen; - else if (copied < ulen) + if (len > ulen) + len = ulen; + else if (len < ulen) msg->msg_flags |= MSG_TRUNC; is_udp4 = (skb->protocol == htons(ETH_P_IP)); @@ -355,14 +354,14 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (len < 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 ); + msg->msg_iov,len); else { err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); if (err == -EINVAL) @@ -411,7 +410,7 @@ try_again: datagram_recv_ctl(sk, msg, skb); } - err = copied; + err = len; if (flags & MSG_TRUNC) err = ulen; @@ -584,16 +583,20 @@ static void flush_stack(struct sock **stack, unsigned int count, bh_lock_sock(sk); if (!sock_owned_by_user(sk)) udpv6_queue_rcv_skb(sk, skb1); - else - sk_add_backlog(sk, skb1); + else if (sk_add_backlog(sk, skb1)) { + kfree_skb(skb1); + bh_unlock_sock(sk); + goto drop; + } bh_unlock_sock(sk); - } else { - atomic_inc(&sk->sk_drops); - UDP6_INC_STATS_BH(sock_net(sk), - UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk)); - UDP6_INC_STATS_BH(sock_net(sk), - UDP_MIB_INERRORS, IS_UDPLITE(sk)); + continue; } +drop: + atomic_inc(&sk->sk_drops); + UDP6_INC_STATS_BH(sock_net(sk), + UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk)); + UDP6_INC_STATS_BH(sock_net(sk), + UDP_MIB_INERRORS, IS_UDPLITE(sk)); } } /* @@ -681,12 +684,11 @@ static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { + struct net *net = dev_net(skb->dev); struct sock *sk; struct udphdr *uh; - struct net_device *dev = skb->dev; struct in6_addr *saddr, *daddr; u32 ulen = 0; - struct net *net = dev_net(skb->dev); if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto short_packet; @@ -745,7 +747,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, UDP6_INC_STATS_BH(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev); + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; @@ -756,8 +758,12 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, bh_lock_sock(sk); if (!sock_owned_by_user(sk)) udpv6_queue_rcv_skb(sk, skb); - else - sk_add_backlog(sk, skb); + else if (sk_add_backlog(sk, skb)) { + atomic_inc(&sk->sk_drops); + bh_unlock_sock(sk); + sock_put(sk); + goto discard; + } bh_unlock_sock(sk); sock_put(sk); return 0; @@ -1396,7 +1402,7 @@ static struct udp_seq_afinfo udp6_seq_afinfo = { }, }; -int udp6_proc_init(struct net *net) +int __net_init udp6_proc_init(struct net *net) { return udp_proc_register(net, &udp6_seq_afinfo); } diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 6ea6938919e..5f48fadc27f 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -104,12 +104,12 @@ static struct udp_seq_afinfo udplite6_seq_afinfo = { }, }; -static int udplite6_proc_init_net(struct net *net) +static int __net_init udplite6_proc_init_net(struct net *net) { return udp_proc_register(net, &udplite6_seq_afinfo); } -static void udplite6_proc_exit_net(struct net *net) +static void __net_exit udplite6_proc_exit_net(struct net *net) { udp_proc_unregister(net, &udplite6_seq_afinfo); } diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 9084582d236..2bc98ede123 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -101,7 +101,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, break; } - x = xfrm_state_lookup_byaddr(net, dst, src, proto, AF_INET6); + x = xfrm_state_lookup_byaddr(net, skb->mark, dst, src, proto, AF_INET6); if (!x) continue; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index c4f4eef032a..0c92112dcba 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -38,7 +38,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if (!skb->local_df && skb->len > mtu) { skb->dev = dst->dev; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ret = -EMSGSIZE; } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 7254e3f899a..ae181651c75 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -24,7 +24,6 @@ #include <net/mip6.h> #endif -static struct dst_ops xfrm6_dst_ops; static struct xfrm_policy_afinfo xfrm6_policy_afinfo; static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, @@ -117,7 +116,8 @@ static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst, return 0; } -static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev) +static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, + struct flowi *fl) { struct rt6_info *rt = (struct rt6_info*)xdst->route; @@ -224,8 +224,10 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) static inline int xfrm6_garbage_collect(struct dst_ops *ops) { - xfrm6_policy_afinfo.garbage_collect(&init_net); - return (atomic_read(&xfrm6_dst_ops.entries) > xfrm6_dst_ops.gc_thresh*2); + struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops); + + xfrm6_policy_afinfo.garbage_collect(net); + return (atomic_read(&ops->entries) > ops->gc_thresh * 2); } static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -310,7 +312,7 @@ static void xfrm6_policy_fini(void) static struct ctl_table xfrm6_policy_table[] = { { .procname = "xfrm6_gc_thresh", - .data = &xfrm6_dst_ops.gc_thresh, + .data = &init_net.xfrm.xfrm6_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, @@ -326,13 +328,6 @@ int __init xfrm6_init(void) int ret; unsigned int gc_thresh; - ret = xfrm6_policy_init(); - if (ret) - goto out; - - ret = xfrm6_state_init(); - if (ret) - goto out_policy; /* * We need a good default value for the xfrm6 gc threshold. * In ipv4 we set it to the route hash table size * 8, which @@ -346,6 +341,15 @@ int __init xfrm6_init(void) */ gc_thresh = FIB6_TABLE_HASHSZ * 8; xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh; + + ret = xfrm6_policy_init(); + if (ret) + goto out; + + ret = xfrm6_state_init(); + if (ret) + goto out_policy; + #ifdef CONFIG_SYSCTL sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv6_ctl_path, xfrm6_policy_table); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 438831d3359..fa85a7d22dc 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -30,6 +30,25 @@ #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/mutex.h> +#include <net/netns/generic.h> + +#define XFRM6_TUNNEL_SPI_BYADDR_HSIZE 256 +#define XFRM6_TUNNEL_SPI_BYSPI_HSIZE 256 + +#define XFRM6_TUNNEL_SPI_MIN 1 +#define XFRM6_TUNNEL_SPI_MAX 0xffffffff + +struct xfrm6_tunnel_net { + struct hlist_head spi_byaddr[XFRM6_TUNNEL_SPI_BYADDR_HSIZE]; + struct hlist_head spi_byspi[XFRM6_TUNNEL_SPI_BYSPI_HSIZE]; + u32 spi; +}; + +static int xfrm6_tunnel_net_id __read_mostly; +static inline struct xfrm6_tunnel_net *xfrm6_tunnel_pernet(struct net *net) +{ + return net_generic(net, xfrm6_tunnel_net_id); +} /* * xfrm_tunnel_spi things are for allocating unique id ("spi") @@ -46,19 +65,8 @@ struct xfrm6_tunnel_spi { static DEFINE_SPINLOCK(xfrm6_tunnel_spi_lock); -static u32 xfrm6_tunnel_spi; - -#define XFRM6_TUNNEL_SPI_MIN 1 -#define XFRM6_TUNNEL_SPI_MAX 0xffffffff - static struct kmem_cache *xfrm6_tunnel_spi_kmem __read_mostly; -#define XFRM6_TUNNEL_SPI_BYADDR_HSIZE 256 -#define XFRM6_TUNNEL_SPI_BYSPI_HSIZE 256 - -static struct hlist_head xfrm6_tunnel_spi_byaddr[XFRM6_TUNNEL_SPI_BYADDR_HSIZE]; -static struct hlist_head xfrm6_tunnel_spi_byspi[XFRM6_TUNNEL_SPI_BYSPI_HSIZE]; - static inline unsigned xfrm6_tunnel_spi_hash_byaddr(xfrm_address_t *addr) { unsigned h; @@ -76,50 +84,14 @@ static inline unsigned xfrm6_tunnel_spi_hash_byspi(u32 spi) return spi % XFRM6_TUNNEL_SPI_BYSPI_HSIZE; } - -static int xfrm6_tunnel_spi_init(void) -{ - int i; - - xfrm6_tunnel_spi = 0; - xfrm6_tunnel_spi_kmem = kmem_cache_create("xfrm6_tunnel_spi", - sizeof(struct xfrm6_tunnel_spi), - 0, SLAB_HWCACHE_ALIGN, - NULL); - if (!xfrm6_tunnel_spi_kmem) - return -ENOMEM; - - for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) - INIT_HLIST_HEAD(&xfrm6_tunnel_spi_byaddr[i]); - for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++) - INIT_HLIST_HEAD(&xfrm6_tunnel_spi_byspi[i]); - return 0; -} - -static void xfrm6_tunnel_spi_fini(void) -{ - int i; - - for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) { - if (!hlist_empty(&xfrm6_tunnel_spi_byaddr[i])) - return; - } - for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++) { - if (!hlist_empty(&xfrm6_tunnel_spi_byspi[i])) - return; - } - rcu_barrier(); - kmem_cache_destroy(xfrm6_tunnel_spi_kmem); - xfrm6_tunnel_spi_kmem = NULL; -} - -static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) +static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, xfrm_address_t *saddr) { + struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; struct hlist_node *pos; hlist_for_each_entry_rcu(x6spi, pos, - &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], + &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) return x6spi; @@ -128,13 +100,13 @@ static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) return NULL; } -__be32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) +__be32 xfrm6_tunnel_spi_lookup(struct net *net, xfrm_address_t *saddr) { struct xfrm6_tunnel_spi *x6spi; u32 spi; rcu_read_lock_bh(); - x6spi = __xfrm6_tunnel_spi_lookup(saddr); + x6spi = __xfrm6_tunnel_spi_lookup(net, saddr); spi = x6spi ? x6spi->spi : 0; rcu_read_unlock_bh(); return htonl(spi); @@ -142,14 +114,15 @@ __be32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) EXPORT_SYMBOL(xfrm6_tunnel_spi_lookup); -static int __xfrm6_tunnel_spi_check(u32 spi) +static int __xfrm6_tunnel_spi_check(struct net *net, u32 spi) { + struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; int index = xfrm6_tunnel_spi_hash_byspi(spi); struct hlist_node *pos; hlist_for_each_entry(x6spi, pos, - &xfrm6_tunnel_spi_byspi[index], + &xfrm6_tn->spi_byspi[index], list_byspi) { if (x6spi->spi == spi) return -1; @@ -157,61 +130,61 @@ static int __xfrm6_tunnel_spi_check(u32 spi) return index; } -static u32 __xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr) +static u32 __xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr) { + struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); u32 spi; struct xfrm6_tunnel_spi *x6spi; int index; - if (xfrm6_tunnel_spi < XFRM6_TUNNEL_SPI_MIN || - xfrm6_tunnel_spi >= XFRM6_TUNNEL_SPI_MAX) - xfrm6_tunnel_spi = XFRM6_TUNNEL_SPI_MIN; + if (xfrm6_tn->spi < XFRM6_TUNNEL_SPI_MIN || + xfrm6_tn->spi >= XFRM6_TUNNEL_SPI_MAX) + xfrm6_tn->spi = XFRM6_TUNNEL_SPI_MIN; else - xfrm6_tunnel_spi++; + xfrm6_tn->spi++; - for (spi = xfrm6_tunnel_spi; spi <= XFRM6_TUNNEL_SPI_MAX; spi++) { - index = __xfrm6_tunnel_spi_check(spi); + for (spi = xfrm6_tn->spi; spi <= XFRM6_TUNNEL_SPI_MAX; spi++) { + index = __xfrm6_tunnel_spi_check(net, spi); if (index >= 0) goto alloc_spi; } - for (spi = XFRM6_TUNNEL_SPI_MIN; spi < xfrm6_tunnel_spi; spi++) { - index = __xfrm6_tunnel_spi_check(spi); + for (spi = XFRM6_TUNNEL_SPI_MIN; spi < xfrm6_tn->spi; spi++) { + index = __xfrm6_tunnel_spi_check(net, spi); if (index >= 0) goto alloc_spi; } spi = 0; goto out; alloc_spi: - xfrm6_tunnel_spi = spi; + xfrm6_tn->spi = spi; x6spi = kmem_cache_alloc(xfrm6_tunnel_spi_kmem, GFP_ATOMIC); if (!x6spi) goto out; - INIT_RCU_HEAD(&x6spi->rcu_head); memcpy(&x6spi->addr, saddr, sizeof(x6spi->addr)); x6spi->spi = spi; atomic_set(&x6spi->refcnt, 1); - hlist_add_head_rcu(&x6spi->list_byspi, &xfrm6_tunnel_spi_byspi[index]); + hlist_add_head_rcu(&x6spi->list_byspi, &xfrm6_tn->spi_byspi[index]); index = xfrm6_tunnel_spi_hash_byaddr(saddr); - hlist_add_head_rcu(&x6spi->list_byaddr, &xfrm6_tunnel_spi_byaddr[index]); + hlist_add_head_rcu(&x6spi->list_byaddr, &xfrm6_tn->spi_byaddr[index]); out: return spi; } -__be32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr) +__be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr) { struct xfrm6_tunnel_spi *x6spi; u32 spi; spin_lock_bh(&xfrm6_tunnel_spi_lock); - x6spi = __xfrm6_tunnel_spi_lookup(saddr); + x6spi = __xfrm6_tunnel_spi_lookup(net, saddr); if (x6spi) { atomic_inc(&x6spi->refcnt); spi = x6spi->spi; } else - spi = __xfrm6_tunnel_alloc_spi(saddr); + spi = __xfrm6_tunnel_alloc_spi(net, saddr); spin_unlock_bh(&xfrm6_tunnel_spi_lock); return htonl(spi); @@ -225,15 +198,16 @@ static void x6spi_destroy_rcu(struct rcu_head *head) container_of(head, struct xfrm6_tunnel_spi, rcu_head)); } -void xfrm6_tunnel_free_spi(xfrm_address_t *saddr) +void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) { + struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; struct hlist_node *pos, *n; spin_lock_bh(&xfrm6_tunnel_spi_lock); hlist_for_each_entry_safe(x6spi, pos, n, - &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], + &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) { @@ -263,10 +237,11 @@ static int xfrm6_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_tunnel_rcv(struct sk_buff *skb) { + struct net *net = dev_net(skb->dev); struct ipv6hdr *iph = ipv6_hdr(skb); __be32 spi; - spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&iph->saddr); + spi = xfrm6_tunnel_spi_lookup(net, (xfrm_address_t *)&iph->saddr); return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi) > 0 ? : 0; } @@ -326,7 +301,9 @@ static int xfrm6_tunnel_init_state(struct xfrm_state *x) static void xfrm6_tunnel_destroy(struct xfrm_state *x) { - xfrm6_tunnel_free_spi((xfrm_address_t *)&x->props.saddr); + struct net *net = xs_net(x); + + xfrm6_tunnel_free_spi(net, (xfrm_address_t *)&x->props.saddr); } static const struct xfrm_type xfrm6_tunnel_type = { @@ -351,34 +328,73 @@ static struct xfrm6_tunnel xfrm46_tunnel_handler = { .priority = 2, }; +static int __net_init xfrm6_tunnel_net_init(struct net *net) +{ + struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); + unsigned int i; + + for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) + INIT_HLIST_HEAD(&xfrm6_tn->spi_byaddr[i]); + for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++) + INIT_HLIST_HEAD(&xfrm6_tn->spi_byspi[i]); + xfrm6_tn->spi = 0; + + return 0; +} + +static void __net_exit xfrm6_tunnel_net_exit(struct net *net) +{ +} + +static struct pernet_operations xfrm6_tunnel_net_ops = { + .init = xfrm6_tunnel_net_init, + .exit = xfrm6_tunnel_net_exit, + .id = &xfrm6_tunnel_net_id, + .size = sizeof(struct xfrm6_tunnel_net), +}; + static int __init xfrm6_tunnel_init(void) { - if (xfrm_register_type(&xfrm6_tunnel_type, AF_INET6) < 0) - goto err; - if (xfrm6_tunnel_register(&xfrm6_tunnel_handler, AF_INET6)) - goto unreg; - if (xfrm6_tunnel_register(&xfrm46_tunnel_handler, AF_INET)) - goto dereg6; - if (xfrm6_tunnel_spi_init() < 0) - goto dereg46; + int rv; + + xfrm6_tunnel_spi_kmem = kmem_cache_create("xfrm6_tunnel_spi", + sizeof(struct xfrm6_tunnel_spi), + 0, SLAB_HWCACHE_ALIGN, + NULL); + if (!xfrm6_tunnel_spi_kmem) + return -ENOMEM; + rv = register_pernet_subsys(&xfrm6_tunnel_net_ops); + if (rv < 0) + goto out_pernet; + rv = xfrm_register_type(&xfrm6_tunnel_type, AF_INET6); + if (rv < 0) + goto out_type; + rv = xfrm6_tunnel_register(&xfrm6_tunnel_handler, AF_INET6); + if (rv < 0) + goto out_xfrm6; + rv = xfrm6_tunnel_register(&xfrm46_tunnel_handler, AF_INET); + if (rv < 0) + goto out_xfrm46; return 0; -dereg46: - xfrm6_tunnel_deregister(&xfrm46_tunnel_handler, AF_INET); -dereg6: +out_xfrm46: xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6); -unreg: +out_xfrm6: xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); -err: - return -EAGAIN; +out_type: + unregister_pernet_subsys(&xfrm6_tunnel_net_ops); +out_pernet: + kmem_cache_destroy(xfrm6_tunnel_spi_kmem); + return rv; } static void __exit xfrm6_tunnel_fini(void) { - xfrm6_tunnel_spi_fini(); xfrm6_tunnel_deregister(&xfrm46_tunnel_handler, AF_INET); xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6); xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); + unregister_pernet_subsys(&xfrm6_tunnel_net_ops); + kmem_cache_destroy(xfrm6_tunnel_spi_kmem); } module_init(xfrm6_tunnel_init); |