diff options
Diffstat (limited to 'net/ipv6')
54 files changed, 2264 insertions, 1977 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ead6c7a42f44..a578096152ab 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -170,6 +170,25 @@ config IPV6_SIT Saying M here will produce a module called sit. If unsure, say Y. +config IPV6_SIT_6RD + bool "IPv6: IPv6 Rapid Deployment (6RD) (EXPERIMENTAL)" + depends on IPV6_SIT && EXPERIMENTAL + default n + ---help--- + IPv6 Rapid Deployment (6rd; draft-ietf-softwire-ipv6-6rd) builds upon + mechanisms of 6to4 (RFC3056) to enable a service provider to rapidly + deploy IPv6 unicast service to IPv4 sites to which it provides + customer premise equipment. Like 6to4, it utilizes stateless IPv6 in + IPv4 encapsulation in order to transit IPv4-only network + infrastructure. Unlike 6to4, a 6rd service provider uses an IPv6 + prefix of its own in place of the fixed 6to4 prefix. + + With this option enabled, the SIT driver offers 6rd functionality by + providing additional ioctl API to configure the IPv6 Prefix for in + stead of static 2002::/16 for 6to4. + + If unsure, say N. + config IPV6_NDISC_NODETYPE bool diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1fd0a3d775d2..3381b4317c27 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. */ @@ -481,9 +481,8 @@ static void addrconf_forward_change(struct net *net, __s32 newf) struct net_device *dev; struct inet6_dev *idev; - read_lock(&dev_base_lock); - for_each_netdev(net, dev) { - rcu_read_lock(); + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.forwarding) ^ (!newf); @@ -491,9 +490,8 @@ static void addrconf_forward_change(struct net *net, __s32 newf) if (changed) dev_forward_change(idev); } - rcu_read_unlock(); } - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) @@ -504,8 +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; @@ -991,8 +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; } @@ -1137,10 +1137,9 @@ int ipv6_dev_get_saddr(struct net *net, struct net_device *dst_dev, hiscore->rule = -1; hiscore->ifa = NULL; - read_lock(&dev_base_lock); rcu_read_lock(); - for_each_netdev(net, dev) { + for_each_netdev_rcu(net, dev) { struct inet6_dev *idev; /* Candidate Source Address (section 4) @@ -1235,7 +1234,6 @@ try_nextdev: read_unlock_bh(&idev->lock); } rcu_read_unlock(); - read_unlock(&dev_base_lock); if (!hiscore->ifa) return -EADDRNOTAVAIL; @@ -1382,6 +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) { @@ -2617,7 +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; @@ -2650,11 +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; @@ -2690,11 +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); @@ -2703,6 +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 */ @@ -2728,28 +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); /* @@ -2757,10 +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); } @@ -2793,14 +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); @@ -2808,7 +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: @@ -2828,7 +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); } @@ -2839,20 +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); @@ -2861,8 +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); @@ -2909,12 +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); @@ -3031,14 +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"); } @@ -3485,85 +3521,114 @@ enum addr_type_t ANYCAST_ADDR, }; +/* called with rcu_read_lock() */ +static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, + struct netlink_callback *cb, enum addr_type_t type, + int s_ip_idx, int *p_ip_idx) +{ + struct inet6_ifaddr *ifa; + struct ifmcaddr6 *ifmca; + struct ifacaddr6 *ifaca; + int err = 1; + int ip_idx = *p_ip_idx; + + read_lock_bh(&idev->lock); + switch (type) { + case UNICAST_ADDR: + /* unicast address incl. temp addr */ + for (ifa = idev->addr_list; ifa; + ifa = ifa->if_next, ip_idx++) { + if (ip_idx < s_ip_idx) + continue; + err = inet6_fill_ifaddr(skb, ifa, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_NEWADDR, + NLM_F_MULTI); + if (err <= 0) + break; + } + break; + case MULTICAST_ADDR: + /* multicast address */ + for (ifmca = idev->mc_list; ifmca; + ifmca = ifmca->next, ip_idx++) { + if (ip_idx < s_ip_idx) + continue; + err = inet6_fill_ifmcaddr(skb, ifmca, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_GETMULTICAST, + NLM_F_MULTI); + if (err <= 0) + break; + } + break; + case ANYCAST_ADDR: + /* anycast address */ + for (ifaca = idev->ac_list; ifaca; + ifaca = ifaca->aca_next, ip_idx++) { + if (ip_idx < s_ip_idx) + continue; + err = inet6_fill_ifacaddr(skb, ifaca, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_GETANYCAST, + NLM_F_MULTI); + if (err <= 0) + break; + } + break; + default: + break; + } + read_unlock_bh(&idev->lock); + *p_ip_idx = ip_idx; + return err; +} + static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type) { + struct net *net = sock_net(skb->sk); + int h, s_h; int idx, ip_idx; int s_idx, s_ip_idx; - int err = 1; struct net_device *dev; - struct inet6_dev *idev = NULL; - struct inet6_ifaddr *ifa; - struct ifmcaddr6 *ifmca; - struct ifacaddr6 *ifaca; - struct net *net = sock_net(skb->sk); + struct inet6_dev *idev; + struct hlist_head *head; + struct hlist_node *node; - s_idx = cb->args[0]; - s_ip_idx = ip_idx = cb->args[1]; + s_h = cb->args[0]; + s_idx = idx = cb->args[1]; + s_ip_idx = ip_idx = cb->args[2]; - idx = 0; - for_each_netdev(net, dev) { - if (idx < s_idx) - goto cont; - if (idx > s_idx) - s_ip_idx = 0; - ip_idx = 0; - if ((idev = in6_dev_get(dev)) == NULL) - goto cont; - read_lock_bh(&idev->lock); - switch (type) { - case UNICAST_ADDR: - /* unicast address incl. temp addr */ - for (ifa = idev->addr_list; ifa; - ifa = ifa->if_next, ip_idx++) { - if (ip_idx < s_ip_idx) - continue; - err = inet6_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - RTM_NEWADDR, - NLM_F_MULTI); - } - break; - case MULTICAST_ADDR: - /* multicast address */ - for (ifmca = idev->mc_list; ifmca; - ifmca = ifmca->next, ip_idx++) { - if (ip_idx < s_ip_idx) - continue; - err = inet6_fill_ifmcaddr(skb, ifmca, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - RTM_GETMULTICAST, - NLM_F_MULTI); - } - break; - case ANYCAST_ADDR: - /* anycast address */ - for (ifaca = idev->ac_list; ifaca; - ifaca = ifaca->aca_next, ip_idx++) { - if (ip_idx < s_ip_idx) - continue; - err = inet6_fill_ifacaddr(skb, ifaca, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - RTM_GETANYCAST, - NLM_F_MULTI); - } - break; - default: - break; - } - read_unlock_bh(&idev->lock); - in6_dev_put(idev); - - if (err <= 0) - break; + rcu_read_lock(); + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + if (idx < s_idx) + goto cont; + if (idx > s_idx) + s_ip_idx = 0; + ip_idx = 0; + if ((idev = __in6_dev_get(dev)) == NULL) + goto cont; + + if (in6_dump_addrs(idev, skb, cb, type, + s_ip_idx, &ip_idx) <= 0) + goto done; cont: - idx++; + idx++; + } } - cb->args[0] = idx; - cb->args[1] = ip_idx; +done: + rcu_read_unlock(); + cb->args[0] = h; + cb->args[1] = idx; + cb->args[2] = ip_idx; + return skb->len; } @@ -3708,6 +3773,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, #endif array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; + array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; } static inline size_t inet6_if_nlmsg_size(void) @@ -3726,8 +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; @@ -3746,10 +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; } } @@ -3826,28 +3892,39 @@ nla_put_failure: static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - int idx, err; - int s_idx = cb->args[0]; + int h, s_h; + int idx = 0, s_idx; struct net_device *dev; struct inet6_dev *idev; + struct hlist_head *head; + struct hlist_node *node; - read_lock(&dev_base_lock); - idx = 0; - for_each_netdev(net, dev) { - if (idx < s_idx) - goto cont; - if ((idev = in6_dev_get(dev)) == NULL) - goto cont; - err = inet6_fill_ifinfo(skb, idev, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_NEWLINK, NLM_F_MULTI); - in6_dev_put(idev); - if (err <= 0) - break; + s_h = cb->args[0]; + s_idx = cb->args[1]; + + rcu_read_lock(); + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + if (idx < s_idx) + goto cont; + idev = __in6_dev_get(dev); + if (!idev) + goto cont; + if (inet6_fill_ifinfo(skb, idev, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_NEWLINK, NLM_F_MULTI) <= 0) + goto out; cont: - idx++; + idx++; + } } - read_unlock(&dev_base_lock); - cb->args[0] = idx; +out: + rcu_read_unlock(); + cb->args[1] = idx; + cb->args[0] = h; return skb->len; } @@ -3991,50 +4068,18 @@ 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; } -static int addrconf_sysctl_forward_strategy(ctl_table *table, - void __user *oldval, - size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - int *valp = table->data; - int val = *valp; - int new; - - if (!newval || !newlen) - return 0; - if (newlen != sizeof(int)) - return -EINVAL; - if (get_user(new, (int __user *)newval)) - return -EFAULT; - if (new == *valp) - return 0; - if (oldval && oldlenp) { - size_t len; - if (get_user(len, oldlenp)) - return -EFAULT; - if (len) { - if (len > table->maxlen) - len = table->maxlen; - if (copy_to_user(oldval, valp, len)) - return -EFAULT; - if (put_user(len, oldlenp)) - return -EFAULT; - } - } - - *valp = new; - return addrconf_fixup_forwarding(table, valp, val); -} - static void dev_disable_change(struct inet6_dev *idev) { if (!idev || !idev->dev) @@ -4051,9 +4096,8 @@ static void addrconf_disable_change(struct net *net, __s32 newf) struct net_device *dev; struct inet6_dev *idev; - read_lock(&dev_base_lock); - for_each_netdev(net, dev) { - rcu_read_lock(); + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.disable_ipv6) ^ (!newf); @@ -4061,9 +4105,8 @@ static void addrconf_disable_change(struct net *net, __s32 newf) if (changed) dev_disable_change(idev); } - rcu_read_unlock(); } - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int old) @@ -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; } @@ -4113,16 +4162,13 @@ static struct addrconf_sysctl_table .sysctl_header = NULL, .addrconf_vars = { { - .ctl_name = NET_IPV6_FORWARDING, .procname = "forwarding", .data = &ipv6_devconf.forwarding, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_forward, - .strategy = addrconf_sysctl_forward_strategy, }, { - .ctl_name = NET_IPV6_HOP_LIMIT, .procname = "hop_limit", .data = &ipv6_devconf.hop_limit, .maxlen = sizeof(int), @@ -4130,7 +4176,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_MTU, .procname = "mtu", .data = &ipv6_devconf.mtu6, .maxlen = sizeof(int), @@ -4138,7 +4183,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ACCEPT_RA, .procname = "accept_ra", .data = &ipv6_devconf.accept_ra, .maxlen = sizeof(int), @@ -4146,7 +4190,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ACCEPT_REDIRECTS, .procname = "accept_redirects", .data = &ipv6_devconf.accept_redirects, .maxlen = sizeof(int), @@ -4154,7 +4197,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_AUTOCONF, .procname = "autoconf", .data = &ipv6_devconf.autoconf, .maxlen = sizeof(int), @@ -4162,7 +4204,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_DAD_TRANSMITS, .procname = "dad_transmits", .data = &ipv6_devconf.dad_transmits, .maxlen = sizeof(int), @@ -4170,7 +4211,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_RTR_SOLICITS, .procname = "router_solicitations", .data = &ipv6_devconf.rtr_solicits, .maxlen = sizeof(int), @@ -4178,25 +4218,20 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_RTR_SOLICIT_INTERVAL, .procname = "router_solicitation_interval", .data = &ipv6_devconf.rtr_solicit_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_RTR_SOLICIT_DELAY, .procname = "router_solicitation_delay", .data = &ipv6_devconf.rtr_solicit_delay, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_FORCE_MLD_VERSION, .procname = "force_mld_version", .data = &ipv6_devconf.force_mld_version, .maxlen = sizeof(int), @@ -4205,7 +4240,6 @@ static struct addrconf_sysctl_table }, #ifdef CONFIG_IPV6_PRIVACY { - .ctl_name = NET_IPV6_USE_TEMPADDR, .procname = "use_tempaddr", .data = &ipv6_devconf.use_tempaddr, .maxlen = sizeof(int), @@ -4213,7 +4247,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_TEMP_VALID_LFT, .procname = "temp_valid_lft", .data = &ipv6_devconf.temp_valid_lft, .maxlen = sizeof(int), @@ -4221,7 +4254,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_TEMP_PREFERED_LFT, .procname = "temp_prefered_lft", .data = &ipv6_devconf.temp_prefered_lft, .maxlen = sizeof(int), @@ -4229,7 +4261,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_REGEN_MAX_RETRY, .procname = "regen_max_retry", .data = &ipv6_devconf.regen_max_retry, .maxlen = sizeof(int), @@ -4237,7 +4268,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_MAX_DESYNC_FACTOR, .procname = "max_desync_factor", .data = &ipv6_devconf.max_desync_factor, .maxlen = sizeof(int), @@ -4246,7 +4276,6 @@ static struct addrconf_sysctl_table }, #endif { - .ctl_name = NET_IPV6_MAX_ADDRESSES, .procname = "max_addresses", .data = &ipv6_devconf.max_addresses, .maxlen = sizeof(int), @@ -4254,7 +4283,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ACCEPT_RA_DEFRTR, .procname = "accept_ra_defrtr", .data = &ipv6_devconf.accept_ra_defrtr, .maxlen = sizeof(int), @@ -4262,7 +4290,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ACCEPT_RA_PINFO, .procname = "accept_ra_pinfo", .data = &ipv6_devconf.accept_ra_pinfo, .maxlen = sizeof(int), @@ -4271,7 +4298,6 @@ static struct addrconf_sysctl_table }, #ifdef CONFIG_IPV6_ROUTER_PREF { - .ctl_name = NET_IPV6_ACCEPT_RA_RTR_PREF, .procname = "accept_ra_rtr_pref", .data = &ipv6_devconf.accept_ra_rtr_pref, .maxlen = sizeof(int), @@ -4279,17 +4305,14 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_RTR_PROBE_INTERVAL, .procname = "router_probe_interval", .data = &ipv6_devconf.rtr_probe_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, #ifdef CONFIG_IPV6_ROUTE_INFO { - .ctl_name = NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN, .procname = "accept_ra_rt_info_max_plen", .data = &ipv6_devconf.accept_ra_rt_info_max_plen, .maxlen = sizeof(int), @@ -4299,7 +4322,6 @@ static struct addrconf_sysctl_table #endif #endif { - .ctl_name = NET_IPV6_PROXY_NDP, .procname = "proxy_ndp", .data = &ipv6_devconf.proxy_ndp, .maxlen = sizeof(int), @@ -4307,7 +4329,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ACCEPT_SOURCE_ROUTE, .procname = "accept_source_route", .data = &ipv6_devconf.accept_source_route, .maxlen = sizeof(int), @@ -4316,7 +4337,6 @@ static struct addrconf_sysctl_table }, #ifdef CONFIG_IPV6_OPTIMISTIC_DAD { - .ctl_name = CTL_UNNUMBERED, .procname = "optimistic_dad", .data = &ipv6_devconf.optimistic_dad, .maxlen = sizeof(int), @@ -4327,7 +4347,6 @@ static struct addrconf_sysctl_table #endif #ifdef CONFIG_IPV6_MROUTE { - .ctl_name = CTL_UNNUMBERED, .procname = "mc_forwarding", .data = &ipv6_devconf.mc_forwarding, .maxlen = sizeof(int), @@ -4336,16 +4355,13 @@ static struct addrconf_sysctl_table }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "disable_ipv6", .data = &ipv6_devconf.disable_ipv6, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_disable, - .strategy = sysctl_intvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "accept_dad", .data = &ipv6_devconf.accept_dad, .maxlen = sizeof(int), @@ -4353,13 +4369,20 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = 0, /* sentinel */ + .procname = "force_tllao", + .data = &ipv6_devconf.force_tllao, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + /* sentinel */ } }, }; static int __addrconf_sysctl_register(struct net *net, char *dev_name, - int ctl_name, struct inet6_dev *idev, struct ipv6_devconf *p) + struct inet6_dev *idev, struct ipv6_devconf *p) { int i; struct addrconf_sysctl_table *t; @@ -4367,9 +4390,9 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, #define ADDRCONF_CTL_PATH_DEV 3 struct ctl_path addrconf_ctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ipv6", .ctl_name = NET_IPV6, }, - { .procname = "conf", .ctl_name = NET_IPV6_CONF, }, + { .procname = "net", }, + { .procname = "ipv6", }, + { .procname = "conf", }, { /* to be set */ }, { }, }; @@ -4395,7 +4418,6 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, goto free; addrconf_ctl_path[ADDRCONF_CTL_PATH_DEV].procname = t->dev_name; - addrconf_ctl_path[ADDRCONF_CTL_PATH_DEV].ctl_name = ctl_name; t->sysctl_header = register_net_sysctl_table(net, addrconf_ctl_path, t->addrconf_vars); @@ -4429,12 +4451,10 @@ 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", - &ndisc_ifinfo_sysctl_change, - ndisc_ifinfo_sysctl_strategy); + neigh_sysctl_register(idev->dev, idev->nd_parms, "ipv6", + &ndisc_ifinfo_sysctl_change); __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, - idev->dev->ifindex, idev, &idev->cnf); + idev, &idev->cnf); } static void addrconf_sysctl_unregister(struct inet6_dev *idev) @@ -4446,7 +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; @@ -4455,7 +4475,7 @@ static int addrconf_init_net(struct net *net) all = &ipv6_devconf; dflt = &ipv6_devconf_dflt; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { all = kmemdup(all, sizeof(ipv6_devconf), GFP_KERNEL); if (all == NULL) goto err_alloc_all; @@ -4473,13 +4493,11 @@ static int addrconf_init_net(struct net *net) net->ipv6.devconf_dflt = dflt; #ifdef CONFIG_SYSCTL - err = __addrconf_sysctl_register(net, "all", NET_PROTO_CONF_ALL, - NULL, all); + err = __addrconf_sysctl_register(net, "all", NULL, all); if (err < 0) goto err_reg_all; - err = __addrconf_sysctl_register(net, "default", NET_PROTO_CONF_DEFAULT, - NULL, dflt); + err = __addrconf_sysctl_register(net, "default", NULL, dflt); if (err < 0) goto err_reg_dflt; #endif @@ -4497,13 +4515,13 @@ 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); __addrconf_sysctl_unregister(net->ipv6.devconf_all); #endif - if (net != &init_net) { + if (!net_eq(net, &init_net)) { kfree(net->ipv6.devconf_dflt); kfree(net->ipv6.devconf_all); } diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 3f82e9542eda..6b03826552e1 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 e127a32f9540..37d14e735c27 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -95,7 +95,8 @@ static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } -static int inet6_create(struct net *net, struct socket *sock, int protocol) +static int inet6_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct inet_sock *inet; struct ipv6_pinfo *np; @@ -158,7 +159,7 @@ lookup_protocol: } err = -EPERM; - if (answer->capability > 0 && !capable(answer->capability)) + if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; @@ -185,7 +186,7 @@ lookup_protocol: inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; if (SOCK_RAW == sock->type) { - inet->num = protocol; + inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet->hdrincl = 1; } @@ -228,12 +229,12 @@ lookup_protocol: */ sk_refcnt_debug_inc(sk); - if (inet->num) { + if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically shares. */ - inet->sport = htons(inet->num); + inet->inet_sport = htons(inet->inet_num); sk->sk_prot->hash(sk); } if (sk->sk_prot->init) { @@ -281,7 +282,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) lock_sock(sk); /* Check these errors (active socket, double bind). */ - if (sk->sk_state != TCP_CLOSE || inet->num) { + if (sk->sk_state != TCP_CLOSE || inet->inet_num) { err = -EINVAL; goto out; } @@ -314,6 +315,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; + rcu_read_lock(); if (addr_type & IPV6_ADDR_LINKLOCAL) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { @@ -326,12 +328,12 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) { err = -EINVAL; - goto out; + goto out_unlock; } - dev = dev_get_by_index(net, sk->sk_bound_dev_if); + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); if (!dev) { err = -ENODEV; - goto out; + goto out_unlock; } } @@ -342,19 +344,16 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (!(addr_type & IPV6_ADDR_MULTICAST)) { if (!ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { - if (dev) - dev_put(dev); err = -EADDRNOTAVAIL; - goto out; + goto out_unlock; } } - if (dev) - dev_put(dev); + rcu_read_unlock(); } } - inet->rcv_saddr = v4addr; - inet->saddr = v4addr; + inet->inet_rcv_saddr = v4addr; + inet->inet_saddr = v4addr; ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr); @@ -375,12 +374,15 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; - inet->sport = htons(inet->num); - inet->dport = 0; - inet->daddr = 0; + inet->inet_sport = htons(inet->inet_num); + inet->inet_dport = 0; + inet->inet_daddr = 0; out: release_sock(sk); return err; +out_unlock: + rcu_read_unlock(); + goto out; } EXPORT_SYMBOL(inet6_bind); @@ -441,12 +443,12 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_flowinfo = 0; sin->sin6_scope_id = 0; if (peer) { - if (!inet->dport) + if (!inet->inet_dport) return -ENOTCONN; if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && peer == 1) return -ENOTCONN; - sin->sin6_port = inet->dport; + sin->sin6_port = inet->inet_dport; ipv6_addr_copy(&sin->sin6_addr, &np->daddr); if (np->sndflow) sin->sin6_flowinfo = np->flow_label; @@ -456,7 +458,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, else ipv6_addr_copy(&sin->sin6_addr, &np->rcv_saddr); - sin->sin6_port = inet->sport; + sin->sin6_port = inet->inet_sport; } if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = sk->sk_bound_dev_if; @@ -552,7 +554,7 @@ const struct proto_ops inet6_dgram_ops = { #endif }; -static struct net_proto_family inet6_family_ops = { +static const struct net_proto_family inet6_family_ops = { .family = PF_INET6, .create = inet6_create, .owner = THIS_MODULE, @@ -654,8 +656,9 @@ int inet6_sk_rebuild_header(struct sock *sk) ipv6_addr_copy(&fl.fl6_src, &np->saddr); fl.fl6_flowlabel = np->flow_label; fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; + fl.mark = sk->sk_mark; + fl.fl_ip_dport = inet->inet_dport; + fl.fl_ip_sport = inet->inet_sport; security_sk_classify_flow(sk, &fl); if (np->opt && np->opt->srcrt) { @@ -968,41 +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) @@ -1039,7 +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 c1589e2f1dc9..5ac89025f9de 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -24,18 +24,92 @@ * This file is derived from net/ipv4/ah.c. */ +#include <crypto/hash.h> #include <linux/module.h> #include <net/ip.h> #include <net/ah.h> #include <linux/crypto.h> #include <linux/pfkeyv2.h> -#include <linux/spinlock.h> #include <linux/string.h> +#include <linux/scatterlist.h> #include <net/icmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/xfrm.h> +#define IPV6HDR_BASELEN 8 + +struct tmp_ext { +#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) + struct in6_addr saddr; +#endif + struct in6_addr daddr; + char hdrs[0]; +}; + +struct ah_skb_cb { + struct xfrm_skb_cb xfrm; + void *tmp; +}; + +#define AH_SKB_CB(__skb) ((struct ah_skb_cb *)&((__skb)->cb[0])) + +static void *ah_alloc_tmp(struct crypto_ahash *ahash, int nfrags, + unsigned int size) +{ + unsigned int len; + + len = size + crypto_ahash_digestsize(ahash) + + (crypto_ahash_alignmask(ahash) & + ~(crypto_tfm_ctx_alignment() - 1)); + + len = ALIGN(len, crypto_tfm_ctx_alignment()); + + len += sizeof(struct ahash_request) + crypto_ahash_reqsize(ahash); + len = ALIGN(len, __alignof__(struct scatterlist)); + + len += sizeof(struct scatterlist) * nfrags; + + return kmalloc(len, GFP_ATOMIC); +} + +static inline struct tmp_ext *ah_tmp_ext(void *base) +{ + return base + IPV6HDR_BASELEN; +} + +static inline u8 *ah_tmp_auth(u8 *tmp, unsigned int offset) +{ + return tmp + offset; +} + +static inline u8 *ah_tmp_icv(struct crypto_ahash *ahash, void *tmp, + unsigned int offset) +{ + return PTR_ALIGN((u8 *)tmp + offset, crypto_ahash_alignmask(ahash) + 1); +} + +static inline struct ahash_request *ah_tmp_req(struct crypto_ahash *ahash, + u8 *icv) +{ + struct ahash_request *req; + + req = (void *)PTR_ALIGN(icv + crypto_ahash_digestsize(ahash), + crypto_tfm_ctx_alignment()); + + ahash_request_set_tfm(req, ahash); + + return req; +} + +static inline struct scatterlist *ah_req_sg(struct crypto_ahash *ahash, + struct ahash_request *req) +{ + return (void *)ALIGN((unsigned long)(req + 1) + + crypto_ahash_reqsize(ahash), + __alignof__(struct scatterlist)); +} + static int zero_out_mutable_opts(struct ipv6_opt_hdr *opthdr) { u8 *opt = (u8 *)opthdr; @@ -218,24 +292,85 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) return 0; } +static void ah6_output_done(struct crypto_async_request *base, int err) +{ + int extlen; + u8 *iph_base; + u8 *icv; + struct sk_buff *skb = base->data; + struct xfrm_state *x = skb_dst(skb)->xfrm; + struct ah_data *ahp = x->data; + struct ipv6hdr *top_iph = ipv6_hdr(skb); + struct ip_auth_hdr *ah = ip_auth_hdr(skb); + struct tmp_ext *iph_ext; + + extlen = skb_network_header_len(skb) - sizeof(struct ipv6hdr); + if (extlen) + extlen += sizeof(*iph_ext); + + iph_base = AH_SKB_CB(skb)->tmp; + iph_ext = ah_tmp_ext(iph_base); + icv = ah_tmp_icv(ahp->ahash, iph_ext, extlen); + + memcpy(ah->auth_data, icv, ahp->icv_trunc_len); + memcpy(top_iph, iph_base, IPV6HDR_BASELEN); + + if (extlen) { +#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) + memcpy(&top_iph->saddr, iph_ext, extlen); +#else + memcpy(&top_iph->daddr, iph_ext, extlen); +#endif + } + + err = ah->nexthdr; + + kfree(AH_SKB_CB(skb)->tmp); + xfrm_output_resume(skb, err); +} + static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) { int err; + int nfrags; int extlen; + u8 *iph_base; + u8 *icv; + u8 nexthdr; + struct sk_buff *trailer; + struct crypto_ahash *ahash; + struct ahash_request *req; + struct scatterlist *sg; struct ipv6hdr *top_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; - u8 nexthdr; - char tmp_base[8]; - struct { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) - struct in6_addr saddr; -#endif - struct in6_addr daddr; - char hdrs[0]; - } *tmp_ext; + struct tmp_ext *iph_ext; + + ahp = x->data; + ahash = ahp->ahash; + + if ((err = skb_cow_data(skb, 0, &trailer)) < 0) + goto out; + nfrags = err; skb_push(skb, -skb_network_offset(skb)); + extlen = skb_network_header_len(skb) - sizeof(struct ipv6hdr); + if (extlen) + extlen += sizeof(*iph_ext); + + err = -ENOMEM; + iph_base = ah_alloc_tmp(ahash, nfrags, IPV6HDR_BASELEN + extlen); + if (!iph_base) + goto out; + + iph_ext = ah_tmp_ext(iph_base); + icv = ah_tmp_icv(ahash, iph_ext, extlen); + req = ah_tmp_req(ahash, icv); + sg = ah_req_sg(ahash, req); + + ah = ip_auth_hdr(skb); + memset(ah->auth_data, 0, ahp->icv_trunc_len); + top_iph = ipv6_hdr(skb); top_iph->payload_len = htons(skb->len - sizeof(*top_iph)); @@ -245,31 +380,22 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) /* When there are no extension headers, we only need to save the first * 8 bytes of the base IP header. */ - memcpy(tmp_base, top_iph, sizeof(tmp_base)); + memcpy(iph_base, top_iph, IPV6HDR_BASELEN); - tmp_ext = NULL; - extlen = skb_transport_offset(skb) - sizeof(struct ipv6hdr); if (extlen) { - extlen += sizeof(*tmp_ext); - tmp_ext = kmalloc(extlen, GFP_ATOMIC); - if (!tmp_ext) { - err = -ENOMEM; - goto error; - } #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) - memcpy(tmp_ext, &top_iph->saddr, extlen); + memcpy(iph_ext, &top_iph->saddr, extlen); #else - memcpy(tmp_ext, &top_iph->daddr, extlen); + memcpy(iph_ext, &top_iph->daddr, extlen); #endif err = ipv6_clear_mutable_options(top_iph, - extlen - sizeof(*tmp_ext) + + extlen - sizeof(*iph_ext) + sizeof(*top_iph), XFRM_POLICY_OUT); if (err) - goto error_free_iph; + goto out_free; } - ah = ip_auth_hdr(skb); ah->nexthdr = nexthdr; top_iph->priority = 0; @@ -278,36 +404,80 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->flow_lbl[2] = 0; top_iph->hop_limit = 0; - ahp = x->data; ah->hdrlen = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2; ah->reserved = 0; ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output); - spin_lock_bh(&x->lock); - err = ah_mac_digest(ahp, skb, ah->auth_data); - memcpy(ah->auth_data, ahp->work_icv, ahp->icv_trunc_len); - spin_unlock_bh(&x->lock); + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, 0, skb->len); - if (err) - goto error_free_iph; + ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_callback(req, 0, ah6_output_done, skb); + + AH_SKB_CB(skb)->tmp = iph_base; - memcpy(top_iph, tmp_base, sizeof(tmp_base)); - if (tmp_ext) { + err = crypto_ahash_digest(req); + if (err) { + if (err == -EINPROGRESS) + goto out; + + if (err == -EBUSY) + err = NET_XMIT_DROP; + goto out_free; + } + + memcpy(ah->auth_data, icv, ahp->icv_trunc_len); + memcpy(top_iph, iph_base, IPV6HDR_BASELEN); + + if (extlen) { #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) - memcpy(&top_iph->saddr, tmp_ext, extlen); + memcpy(&top_iph->saddr, iph_ext, extlen); #else - memcpy(&top_iph->daddr, tmp_ext, extlen); + memcpy(&top_iph->daddr, iph_ext, extlen); #endif -error_free_iph: - kfree(tmp_ext); } -error: +out_free: + kfree(iph_base); +out: return err; } +static void ah6_input_done(struct crypto_async_request *base, int err) +{ + u8 *auth_data; + u8 *icv; + u8 *work_iph; + struct sk_buff *skb = base->data; + struct xfrm_state *x = xfrm_input_state(skb); + struct ah_data *ahp = x->data; + struct ip_auth_hdr *ah = ip_auth_hdr(skb); + int hdr_len = skb_network_header_len(skb); + int ah_hlen = (ah->hdrlen + 2) << 2; + + work_iph = AH_SKB_CB(skb)->tmp; + auth_data = ah_tmp_auth(work_iph, hdr_len); + icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len); + + err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; + if (err) + goto out; + + skb->network_header += ah_hlen; + memcpy(skb_network_header(skb), work_iph, hdr_len); + __skb_pull(skb, ah_hlen + hdr_len); + skb_set_transport_header(skb, -hdr_len); + + err = ah->nexthdr; +out: + kfree(AH_SKB_CB(skb)->tmp); + xfrm_input_resume(skb, err); +} + + + static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) { /* @@ -325,14 +495,21 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) * There is offset of AH before IPv6 header after the process. */ + u8 *auth_data; + u8 *icv; + u8 *work_iph; + struct sk_buff *trailer; + struct crypto_ahash *ahash; + struct ahash_request *req; + struct scatterlist *sg; struct ip_auth_hdr *ah; struct ipv6hdr *ip6h; struct ah_data *ahp; - unsigned char *tmp_hdr = NULL; u16 hdr_len; u16 ah_hlen; int nexthdr; - int err = -EINVAL; + int nfrags; + int err = -ENOMEM; if (!pskb_may_pull(skb, sizeof(struct ip_auth_hdr))) goto out; @@ -345,9 +522,11 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) skb->ip_summed = CHECKSUM_NONE; - hdr_len = skb->data - skb_network_header(skb); + hdr_len = skb_network_header_len(skb); ah = (struct ip_auth_hdr *)skb->data; ahp = x->data; + ahash = ahp->ahash; + nexthdr = ah->nexthdr; ah_hlen = (ah->hdrlen + 2) << 2; @@ -358,48 +537,67 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, ah_hlen)) goto out; - tmp_hdr = kmemdup(skb_network_header(skb), hdr_len, GFP_ATOMIC); - if (!tmp_hdr) - goto out; ip6h = ipv6_hdr(skb); + + skb_push(skb, hdr_len); + + if ((err = skb_cow_data(skb, 0, &trailer)) < 0) + goto out; + nfrags = err; + + work_iph = ah_alloc_tmp(ahash, nfrags, hdr_len + ahp->icv_trunc_len); + if (!work_iph) + goto out; + + auth_data = ah_tmp_auth(work_iph, hdr_len); + icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); + req = ah_tmp_req(ahash, icv); + sg = ah_req_sg(ahash, req); + + memcpy(work_iph, ip6h, hdr_len); + memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); + memset(ah->auth_data, 0, ahp->icv_trunc_len); + if (ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN)) - goto free_out; + goto out_free; + ip6h->priority = 0; ip6h->flow_lbl[0] = 0; ip6h->flow_lbl[1] = 0; ip6h->flow_lbl[2] = 0; ip6h->hop_limit = 0; - spin_lock(&x->lock); - { - u8 auth_data[MAX_AH_AUTH_LEN]; + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, 0, skb->len); - memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); - memset(ah->auth_data, 0, ahp->icv_trunc_len); - skb_push(skb, hdr_len); - err = ah_mac_digest(ahp, skb, ah->auth_data); - if (err) - goto unlock; - if (memcmp(ahp->work_icv, auth_data, ahp->icv_trunc_len)) - err = -EBADMSG; + ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_callback(req, 0, ah6_input_done, skb); + + AH_SKB_CB(skb)->tmp = work_iph; + + err = crypto_ahash_digest(req); + if (err) { + if (err == -EINPROGRESS) + goto out; + + if (err == -EBUSY) + err = NET_XMIT_DROP; + goto out_free; } -unlock: - spin_unlock(&x->lock); + err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; if (err) - goto free_out; + goto out_free; skb->network_header += ah_hlen; - memcpy(skb_network_header(skb), tmp_hdr, hdr_len); + memcpy(skb_network_header(skb), work_iph, hdr_len); skb->transport_header = skb->network_header; __skb_pull(skb, ah_hlen + hdr_len); - kfree(tmp_hdr); + err = nexthdr; - return nexthdr; - -free_out: - kfree(tmp_hdr); +out_free: + kfree(work_iph); out: return err; } @@ -416,7 +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; @@ -430,7 +628,7 @@ static int ah6_init_state(struct xfrm_state *x) { struct ah_data *ahp = NULL; struct xfrm_algo_desc *aalg_desc; - struct crypto_hash *tfm; + struct crypto_ahash *ahash; if (!x->aalg) goto error; @@ -442,12 +640,12 @@ static int ah6_init_state(struct xfrm_state *x) if (ahp == NULL) return -ENOMEM; - tfm = crypto_alloc_hash(x->aalg->alg_name, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) + ahash = crypto_alloc_ahash(x->aalg->alg_name, 0, 0); + if (IS_ERR(ahash)) goto error; - ahp->tfm = tfm; - if (crypto_hash_setkey(tfm, x->aalg->alg_key, + ahp->ahash = ahash; + if (crypto_ahash_setkey(ahash, x->aalg->alg_key, (x->aalg->alg_key_len + 7) / 8)) goto error; @@ -461,22 +659,18 @@ static int ah6_init_state(struct xfrm_state *x) BUG_ON(!aalg_desc); if (aalg_desc->uinfo.auth.icv_fullbits/8 != - crypto_hash_digestsize(tfm)) { + crypto_ahash_digestsize(ahash)) { printk(KERN_INFO "AH: %s digestsize %u != %hu\n", - x->aalg->alg_name, crypto_hash_digestsize(tfm), + x->aalg->alg_name, crypto_ahash_digestsize(ahash), aalg_desc->uinfo.auth.icv_fullbits/8); goto error; } ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8; - ahp->icv_trunc_len = aalg_desc->uinfo.auth.icv_truncbits/8; + ahp->icv_trunc_len = x->aalg->alg_trunc_len/8; BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN); - ahp->work_icv = kmalloc(ahp->icv_full_len, GFP_KERNEL); - if (!ahp->work_icv) - goto error; - x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) + ahp->icv_trunc_len); switch (x->props.mode) { @@ -495,8 +689,7 @@ static int ah6_init_state(struct xfrm_state *x) error: if (ahp) { - kfree(ahp->work_icv); - crypto_free_hash(ahp->tfm); + crypto_free_ahash(ahp->ahash); kfree(ahp); } return -EINVAL; @@ -509,8 +702,7 @@ static void ah6_destroy(struct xfrm_state *x) if (!ahp) return; - kfree(ahp->work_icv); - crypto_free_hash(ahp->tfm); + crypto_free_ahash(ahp->ahash); kfree(ahp); } diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 1ae58bec1de0..c4f6ca32fa74 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -404,13 +404,13 @@ int ipv6_chk_acast_addr(struct net *net, struct net_device *dev, if (dev) return ipv6_chk_acast_dev(dev, addr); - read_lock(&dev_base_lock); - for_each_netdev(net, dev) + rcu_read_lock(); + for_each_netdev_rcu(net, dev) if (ipv6_chk_acast_dev(dev, addr)) { found = 1; break; } - read_unlock(&dev_base_lock); + rcu_read_unlock(); return found; } @@ -431,9 +431,9 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); state->idev = NULL; - for_each_netdev(net, state->dev) { + for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; - idev = in6_dev_get(state->dev); + idev = __in6_dev_get(state->dev); if (!idev) continue; read_lock_bh(&idev->lock); @@ -443,7 +443,6 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq) break; } read_unlock_bh(&idev->lock); - in6_dev_put(idev); } return im; } @@ -454,16 +453,15 @@ static struct ifacaddr6 *ac6_get_next(struct seq_file *seq, struct ifacaddr6 *im im = im->aca_next; while (!im) { - if (likely(state->idev != NULL)) { + if (likely(state->idev != NULL)) read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); - } - state->dev = next_net_device(state->dev); + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; break; } - state->idev = in6_dev_get(state->dev); + state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; read_lock_bh(&state->idev->lock); @@ -482,29 +480,30 @@ static struct ifacaddr6 *ac6_get_idx(struct seq_file *seq, loff_t pos) } static void *ac6_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(RCU) { - read_lock(&dev_base_lock); + rcu_read_lock(); return ac6_get_idx(seq, *pos); } static void *ac6_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct ifacaddr6 *im; - im = ac6_get_next(seq, v); + struct ifacaddr6 *im = ac6_get_next(seq, v); + ++*pos; return im; } static void ac6_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(RCU) { struct ac6_iter_state *state = ac6_seq_private(seq); + if (likely(state->idev != NULL)) { read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); + state->idev = NULL; } - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int ac6_seq_show(struct seq_file *seq, void *v) @@ -539,7 +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/datagram.c b/net/ipv6/datagram.c index e2bdc6d83a43..e6f9cdf780fe 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -98,17 +98,15 @@ ipv4_connected: if (err) goto out; - ipv6_addr_set(&np->daddr, 0, 0, htonl(0x0000ffff), inet->daddr); + ipv6_addr_set_v4mapped(inet->inet_daddr, &np->daddr); - if (ipv6_addr_any(&np->saddr)) { - ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000ffff), - inet->saddr); - } + if (ipv6_addr_any(&np->saddr)) + ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); + + if (ipv6_addr_any(&np->rcv_saddr)) + ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, + &np->rcv_saddr); - if (ipv6_addr_any(&np->rcv_saddr)) { - ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000ffff), - inet->rcv_saddr); - } goto out; } @@ -136,7 +134,7 @@ ipv4_connected: ipv6_addr_copy(&np->daddr, daddr); np->flow_label = fl.fl6_flowlabel; - inet->dport = usin->sin6_port; + inet->inet_dport = usin->sin6_port; /* * Check for a route to destination an obtain the @@ -147,8 +145,9 @@ ipv4_connected: ipv6_addr_copy(&fl.fl6_dst, &np->daddr); ipv6_addr_copy(&fl.fl6_src, &np->saddr); fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; + fl.mark = sk->sk_mark; + fl.fl_ip_dport = inet->inet_dport; + fl.fl_ip_sport = inet->inet_sport; if (!fl.oif && (addr_type&IPV6_ADDR_MULTICAST)) fl.oif = np->mcast_oif; @@ -190,7 +189,7 @@ ipv4_connected: if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src); - inet->rcv_saddr = LOOPBACK4_IPV6; + inet->inet_rcv_saddr = LOOPBACK4_IPV6; } ip6_dst_store(sk, dst, @@ -329,9 +328,8 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = IP6CB(skb)->iif; } else { - ipv6_addr_set(&sin->sin6_addr, 0, 0, - htonl(0xffff), - *(__be32 *)(nh + serr->addr_offset)); + ipv6_addr_set_v4mapped(*(__be32 *)(nh + serr->addr_offset), + &sin->sin6_addr); } } @@ -351,8 +349,8 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) } else { struct inet_sock *inet = inet_sk(sk); - ipv6_addr_set(&sin->sin6_addr, 0, 0, - htonl(0xffff), ip_hdr(skb)->saddr); + ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, + &sin->sin6_addr); if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); } @@ -539,12 +537,17 @@ int datagram_send_ctl(struct net *net, addr_type = __ipv6_addr_type(&src_info->ipi6_addr); + rcu_read_lock(); if (fl->oif) { - dev = dev_get_by_index(net, fl->oif); - if (!dev) + dev = dev_get_by_index_rcu(net, fl->oif); + if (!dev) { + rcu_read_unlock(); return -ENODEV; - } else if (addr_type & IPV6_ADDR_LINKLOCAL) + } + } else if (addr_type & IPV6_ADDR_LINKLOCAL) { + rcu_read_unlock(); return -EINVAL; + } if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; @@ -555,8 +558,7 @@ int datagram_send_ctl(struct net *net, ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr); } - if (dev) - dev_put(dev); + rcu_read_unlock(); if (err) goto exit_f; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index af597c73ebe9..ee9b93bdd6a2 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", @@ -473,7 +473,7 @@ static int esp_init_authenc(struct xfrm_state *x) } err = crypto_aead_setauthsize( - aead, aalg_desc->uinfo.auth.icv_truncbits / 8); + aead, x->aalg->alg_trunc_len / 8); if (err) goto free_key; } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index df159fffe4bc..074f2c084f9f 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 00a7a5e4ac97..5e463c43fcc2 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, @@ -262,46 +255,38 @@ 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; - net->ipv6.fib6_rules_ops = kmemdup(&fib6_rules_ops_template, - sizeof(*net->ipv6.fib6_rules_ops), - GFP_KERNEL); - if (!net->ipv6.fib6_rules_ops) - goto out; + ops = fib_rules_register(&fib6_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + net->ipv6.fib6_rules_ops = ops; - net->ipv6.fib6_rules_ops->fro_net = net; - INIT_LIST_HEAD(&net->ipv6.fib6_rules_ops->rules_list); err = fib_default_rule_add(net->ipv6.fib6_rules_ops, 0, - RT6_TABLE_LOCAL, FIB_RULE_PERMANENT); + RT6_TABLE_LOCAL, 0); if (err) goto out_fib6_rules_ops; err = fib_default_rule_add(net->ipv6.fib6_rules_ops, 0x7FFE, RT6_TABLE_MAIN, 0); if (err) - goto out_fib6_default_rule_add; + goto out_fib6_rules_ops; - err = fib_rules_register(net->ipv6.fib6_rules_ops); - if (err) - goto out_fib6_default_rule_add; out: return err; -out_fib6_default_rule_add: - fib_rules_cleanup_ops(net->ipv6.fib6_rules_ops); out_fib6_rules_ops: - kfree(net->ipv6.fib6_rules_ops); + fib_rules_unregister(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); - kfree(net->ipv6.fib6_rules_ops); } static struct pernet_operations fib6_rules_net_ops = { diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f23ebbec0631..eb9abe24bdf0 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; @@ -942,18 +936,16 @@ EXPORT_SYMBOL(icmpv6_err_convert); #ifdef CONFIG_SYSCTL ctl_table ipv6_icmp_table_template[] = { { - .ctl_name = NET_IPV6_ICMP_RATELIMIT, .procname = "ratelimit", .data = &init_net.ipv6.sysctl.icmpv6_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, - .strategy = sysctl_ms_jiffies }, - { .ctl_name = 0 }, + { }, }; -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/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index cc4797dd8325..3516e6fe2e56 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -132,7 +132,7 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr) sin6->sin6_family = AF_INET6; ipv6_addr_copy(&sin6->sin6_addr, &np->daddr); - sin6->sin6_port = inet_sk(sk)->dport; + sin6->sin6_port = inet_sk(sk)->inet_dport; /* We do not store received flowlabel for TCP */ sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = 0; @@ -168,8 +168,7 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) if (dst) { struct rt6_info *rt = (struct rt6_info *)dst; if (rt->rt6i_flow_cache_genid != atomic_read(&flow_cache_genid)) { - sk->sk_dst_cache = NULL; - dst_release(dst); + __sk_dst_reset(sk); dst = NULL; } } @@ -194,8 +193,9 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) fl.fl6_flowlabel = np->flow_label; IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel); fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_sport = inet->sport; - fl.fl_ip_dport = inet->dport; + fl.mark = sk->sk_mark; + fl.fl_ip_sport = inet->inet_sport; + fl.fl_ip_dport = inet->inet_dport; security_sk_classify_flow(sk, &fl); if (np->opt && np->opt->srcrt) { diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 1bcc3431859e..633a6c266136 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -22,9 +22,10 @@ #include <net/inet6_hashtables.h> #include <net/ip.h> -void __inet6_hash(struct sock *sk) +int __inet6_hash(struct sock *sk, struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; + int twrefcnt = 0; WARN_ON(!sk_unhashed(sk)); @@ -45,10 +46,15 @@ void __inet6_hash(struct sock *sk) lock = inet_ehash_lockp(hashinfo, hash); spin_lock(lock); __sk_nulls_add_node_rcu(sk, list); + if (tw) { + WARN_ON(sk->sk_hash != tw->tw_hash); + twrefcnt = inet_twsk_unhash(tw); + } spin_unlock(lock); } sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + return twrefcnt; } EXPORT_SYMBOL(__inet6_hash); @@ -73,7 +79,7 @@ struct sock *__inet6_lookup_established(struct net *net, * have wildcards anyways. */ unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport); - unsigned int slot = hash & (hashinfo->ehash_size - 1); + unsigned int slot = hash & hashinfo->ehash_mask; struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; @@ -125,7 +131,7 @@ static int inline compute_score(struct sock *sk, struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && inet_sk(sk)->num == hnum && + if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && sk->sk_family == PF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); @@ -214,15 +220,16 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, const struct in6_addr *daddr = &np->rcv_saddr; const struct in6_addr *saddr = &np->daddr; const int dif = sk->sk_bound_dev_if; - const __portpair ports = INET_COMBINED_PORTS(inet->dport, lport); + const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); struct net *net = sock_net(sk); const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr, - inet->dport); + inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw; + int twrefcnt = 0; spin_lock(lock); @@ -248,21 +255,25 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, unique: /* Must record num and sport now. Otherwise we will see * in hash table socket with a funny identity. */ - inet->num = lport; - inet->sport = htons(lport); + inet->inet_num = lport; + inet->inet_sport = htons(lport); + sk->sk_hash = hash; WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); - sk->sk_hash = hash; + if (tw) { + twrefcnt = inet_twsk_unhash(tw); + NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); + } spin_unlock(lock); + if (twrefcnt) + inet_twsk_put(tw); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - if (twp != NULL) { + if (twp) { *twp = tw; - NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); - } else if (tw != NULL) { + } else if (tw) { /* Silly. Should hash-dance instead... */ inet_twsk_deschedule(tw, death_row); - NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); inet_twsk_put(tw); } @@ -279,7 +290,7 @@ static inline u32 inet6_sk_port_offset(const struct sock *sk) const struct ipv6_pinfo *np = inet6_sk(sk); return secure_ipv6_port_ephemeral(np->rcv_saddr.s6_addr32, np->daddr.s6_addr32, - inet->dport); + inet->inet_dport); } int inet6_hash_connect(struct inet_timewait_death_row *death_row, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 0e93ca56eb69..2f9847924fa5 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 7712578bdc66..e41eba8aacf1 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -67,7 +67,7 @@ static inline struct ip6_flowlabel *__fl_lookup(struct net *net, __be32 label) struct ip6_flowlabel *fl; for (fl=fl_ht[FL_HASH(label)]; fl; fl = fl->next) { - if (fl->label == label && fl->fl_net == net) + if (fl->label == label && net_eq(fl->fl_net, net)) return fl; } return NULL; @@ -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; @@ -163,7 +163,8 @@ static void ip6_fl_purge(struct net *net) struct ip6_flowlabel *fl, **flp; flp = &fl_ht[i]; while ((fl = *flp) != NULL) { - if (fl->fl_net == net && atomic_read(&fl->users) == 0) { + if (net_eq(fl->fl_net, net) && + atomic_read(&fl->users) == 0) { *flp = fl->next; fl_free(fl); atomic_dec(&fl_size); @@ -377,8 +378,8 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, goto done; fl->share = freq->flr_share; addr_type = ipv6_addr_type(&freq->flr_dst); - if ((addr_type&IPV6_ADDR_MAPPED) - || addr_type == IPV6_ADDR_ANY) { + if ((addr_type & IPV6_ADDR_MAPPED) || + addr_type == IPV6_ADDR_ANY) { err = -EINVAL; goto done; } @@ -421,8 +422,8 @@ static int mem_check(struct sock *sk) if (room <= 0 || ((count >= FL_MAX_PER_SOCK || - (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) - && !capable(CAP_NET_ADMIN))) + (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) && + !capable(CAP_NET_ADMIN))) return -ENOBUFS; return 0; @@ -630,7 +631,7 @@ static struct ip6_flowlabel *ip6fl_get_first(struct seq_file *seq) for (state->bucket = 0; state->bucket <= FL_HASH_MASK; ++state->bucket) { fl = fl_ht[state->bucket]; - while (fl && fl->fl_net != net) + while (fl && !net_eq(fl->fl_net, net)) fl = fl->next; if (fl) break; @@ -645,7 +646,7 @@ static struct ip6_flowlabel *ip6fl_get_next(struct seq_file *seq, struct ip6_flo fl = fl->next; try_again: - while (fl && fl->fl_net != net) + while (fl && !net_eq(fl->fl_net, net)) fl = fl->next; while (!fl) { @@ -734,7 +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)) @@ -742,7 +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"); } @@ -753,11 +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 237e2dba6e94..e28f9203deca 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 cd48801a8d6f..dabf108ad811 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 c595bbe1ed99..138980eec214 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -74,11 +74,10 @@ 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); -static int ip6_tnl_net_id; +static int ip6_tnl_net_id __read_mostly; struct ip6_tnl_net { /* the IPv6 tunnel fallback device */ struct net_device *fb_tnl_dev; @@ -88,8 +87,10 @@ struct ip6_tnl_net { struct ip6_tnl **tnls[2]; }; -/* lock for the tunnel lists */ -static DEFINE_RWLOCK(ip6_tnl_lock); +/* + * Locking : hash tables are protected by RCU and a spinlock + */ +static DEFINE_SPINLOCK(ip6_tnl_lock); static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) { @@ -130,6 +131,9 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) * else %NULL **/ +#define for_each_ip6_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) + static struct ip6_tnl * ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) { @@ -138,13 +142,14 @@ ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - for (t = ip6n->tnls_r_l[h0 ^ h1]; t; t = t->next) { + for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[h0 ^ h1]) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) return t; } - if ((t = ip6n->tnls_wc[0]) != NULL && (t->dev->flags & IFF_UP)) + t = rcu_dereference(ip6n->tnls_wc[0]); + if (t && (t->dev->flags & IFF_UP)) return t; return NULL; @@ -186,10 +191,10 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl **tp = ip6_tnl_bucket(ip6n, &t->parms); + spin_lock_bh(&ip6_tnl_lock); t->next = *tp; - write_lock_bh(&ip6_tnl_lock); - *tp = t; - write_unlock_bh(&ip6_tnl_lock); + rcu_assign_pointer(*tp, t); + spin_unlock_bh(&ip6_tnl_lock); } /** @@ -204,9 +209,9 @@ ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) for (tp = ip6_tnl_bucket(ip6n, &t->parms); *tp; tp = &(*tp)->next) { if (t == *tp) { - write_lock_bh(&ip6_tnl_lock); + spin_lock_bh(&ip6_tnl_lock); *tp = t->next; - write_unlock_bh(&ip6_tnl_lock); + spin_unlock_bh(&ip6_tnl_lock); break; } } @@ -313,9 +318,9 @@ ip6_tnl_dev_uninit(struct net_device *dev) struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev == ip6n->fb_tnl_dev) { - write_lock_bh(&ip6_tnl_lock); + spin_lock_bh(&ip6_tnl_lock); ip6n->tnls_wc[0] = NULL; - write_unlock_bh(&ip6_tnl_lock); + spin_unlock_bh(&ip6_tnl_lock); } else { ip6_tnl_unlink(ip6n, t); } @@ -409,7 +414,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, in trouble since we might need the source address for further processing of the error. */ - read_lock(&ip6_tnl_lock); + rcu_read_lock(); if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr, &ipv6h->saddr)) == NULL) goto out; @@ -482,7 +487,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, *msg = rel_msg; out: - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); return err; } @@ -617,7 +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); @@ -652,6 +657,7 @@ static void ip6ip6_dscp_ecn_decapsulate(struct ip6_tnl *t, IP6_ECN_set_ce(ipv6_hdr(skb)); } +/* called with rcu_read_lock() */ static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t) { struct ip6_tnl_parm *p = &t->parms; @@ -662,15 +668,13 @@ static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t) struct net_device *ldev = NULL; if (p->link) - ldev = dev_get_by_index(net, p->link); + ldev = dev_get_by_index_rcu(net, p->link); if ((ipv6_addr_is_multicast(&p->laddr) || likely(ipv6_chk_addr(net, &p->laddr, ldev, 0))) && likely(!ipv6_chk_addr(net, &p->raddr, NULL, 0))) ret = 1; - if (ldev) - dev_put(ldev); } return ret; } @@ -693,23 +697,23 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, struct ip6_tnl *t; struct ipv6hdr *ipv6h = ipv6_hdr(skb); - read_lock(&ip6_tnl_lock); + rcu_read_lock(); if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr)) != NULL) { if (t->parms.proto != ipproto && t->parms.proto != 0) { - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); goto discard; } if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); goto discard; } if (!ip6_tnl_rcv_ctl(t)) { t->dev->stats.rx_dropped++; - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); goto discard; } secpath_reset(skb); @@ -727,10 +731,10 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, t->dev->stats.rx_packets++; t->dev->stats.rx_bytes += skb->len; netif_rx(skb); - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); return 0; } - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); return 1; discard: @@ -798,8 +802,9 @@ static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t) if (p->flags & IP6_TNL_F_CAP_XMIT) { struct net_device *ldev = NULL; + rcu_read_lock(); if (p->link) - ldev = dev_get_by_index(net, p->link); + ldev = dev_get_by_index_rcu(net, p->link); if (unlikely(!ipv6_chk_addr(net, &p->laddr, ldev, 0))) printk(KERN_WARNING @@ -813,8 +818,7 @@ static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t) p->name); else ret = 1; - if (ldev) - dev_put(ldev); + rcu_read_unlock(); } return ret; } @@ -1010,7 +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; @@ -1029,7 +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; } @@ -1359,7 +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); @@ -1383,33 +1387,29 @@ 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; + LIST_HEAD(list); for (h = 0; h < HASH_SIZE; h++) { - while ((t = ip6n->tnls_r_l[h]) != NULL) - unregister_netdevice(t->dev); + t = ip6n->tnls_r_l[h]; + while (t != NULL) { + unregister_netdevice_queue(t->dev, &list); + t = t->next; + } } t = ip6n->tnls_wc[0]; - unregister_netdevice(t->dev); + unregister_netdevice_queue(t->dev, &list); + 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; - struct ip6_tnl_net *ip6n; - - err = -ENOMEM; - ip6n = kzalloc(sizeof(struct ip6_tnl_net), GFP_KERNEL); - if (ip6n == NULL) - goto err_alloc; - - err = net_assign_generic(net, ip6_tnl_net_id, ip6n); - if (err < 0) - goto err_assign; ip6n->tnls[0] = ip6n->tnls_wc; ip6n->tnls[1] = ip6n->tnls_r_l; @@ -1432,27 +1432,23 @@ static int ip6_tnl_init_net(struct net *net) err_register: free_netdev(ip6n->fb_tnl_dev); err_alloc_dev: - /* nothing */ -err_assign: - kfree(ip6n); -err_alloc: 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; + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - ip6n = net_generic(net, ip6_tnl_net_id); rtnl_lock(); ip6_tnl_destroy_tunnels(ip6n); rtnl_unlock(); - kfree(ip6n); } static struct pernet_operations ip6_tnl_net_ops = { .init = ip6_tnl_init_net, .exit = ip6_tnl_exit_net, + .id = &ip6_tnl_net_id, + .size = sizeof(struct ip6_tnl_net), }; /** @@ -1465,27 +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_gen_device(&ip6_tnl_net_id, &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; } @@ -1501,7 +1499,7 @@ static void __exit ip6_tunnel_cleanup(void) if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6)) printk(KERN_INFO "ip6_tunnel close: can't deregister ip6ip6\n"); - unregister_pernet_gen_device(ip6_tnl_net_id, &ip6_tnl_net_ops); + unregister_pernet_device(&ip6_tnl_net_ops); } module_init(ip6_tunnel_init); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 090675e269ee..52e0f74fdfe0 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -477,7 +477,7 @@ failure: * Delete a VIF entry */ -static int mif6_delete(struct net *net, int vifi) +static int mif6_delete(struct net *net, int vifi, struct list_head *head) { struct mif_device *v; struct net_device *dev; @@ -519,7 +519,7 @@ static int mif6_delete(struct net *net, int vifi) in6_dev->cnf.mc_forwarding--; if (v->flags & MIFF_REGISTER) - unregister_netdevice(dev); + unregister_netdevice_queue(dev, head); dev_put(dev); return 0; @@ -976,6 +976,7 @@ static int ip6mr_device_event(struct notifier_block *this, struct net *net = dev_net(dev); struct mif_device *v; int ct; + LIST_HEAD(list); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; @@ -983,8 +984,10 @@ static int ip6mr_device_event(struct notifier_block *this, v = &net->ipv6.vif6_table[0]; for (ct = 0; ct < net->ipv6.maxvif; ct++, v++) { if (v->dev == dev) - mif6_delete(net, ct); + mif6_delete(net, ct, &list); } + unregister_netdevice_many(&list); + return NOTIFY_DONE; } @@ -1188,14 +1191,16 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) static void mroute_clean_tables(struct net *net) { int i; + LIST_HEAD(list); /* * Shut down all active vif entries */ for (i = 0; i < net->ipv6.maxvif; i++) { if (!(net->ipv6.vif6_table[i].flags & VIFF_STATIC)) - mif6_delete(net, i); + mif6_delete(net, i, &list); } + unregister_netdevice_many(&list); /* * Wipe the cache @@ -1281,7 +1286,7 @@ int ip6mr_sk_done(struct sock *sk) * MOSPF/PIM router set up we can clean this up. */ -int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int optlen) +int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { int ret; struct mif6ctl vif; @@ -1297,7 +1302,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int switch (optname) { case MRT6_INIT: if (sk->sk_type != SOCK_RAW || - inet_sk(sk)->num != IPPROTO_ICMPV6) + inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; if (optlen < sizeof(int)) return -EINVAL; @@ -1325,7 +1330,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int if (copy_from_user(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); - ret = mif6_delete(net, mifi); + ret = mif6_delete(net, mifi, NULL); rtnl_unlock(); return ret; diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 2f2a5ca2c878..85cccd6ed0b7 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/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index f5e0682b402d..430454ee5ead 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -64,7 +64,7 @@ int ip6_ra_control(struct sock *sk, int sel) struct ip6_ra_chain *ra, *new_ra, **rap; /* RA packet may be delivered ONLY to IPPROTO_RAW socket */ - if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num != IPPROTO_RAW) + if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_RAW) return -ENOPROTOOPT; new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; @@ -106,7 +106,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, if (inet_sk(sk)->is_icsk) { if (opt && !((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && - inet_sk(sk)->daddr != LOOPBACK4_IPV6) { + inet_sk(sk)->inet_daddr != LOOPBACK4_IPV6) { struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen; icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); @@ -123,7 +123,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, } static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); @@ -234,7 +234,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, case IPV6_V6ONLY: if (optlen < sizeof(int) || - inet_sk(sk)->num) + inet_sk(sk)->inet_num) goto e_inval; np->ipv6only = valbool; retv = 0; @@ -424,6 +424,7 @@ sticky_done: fl.fl6_flowlabel = 0; fl.oif = sk->sk_bound_dev_if; + fl.mark = sk->sk_mark; if (optlen == 0) goto update; @@ -496,13 +497,17 @@ done: goto e_inval; if (val) { + struct net_device *dev; + if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val) goto e_inval; - if (__dev_get_by_index(net, val) == NULL) { + dev = dev_get_by_index(net, val); + if (!dev) { retv = -ENODEV; break; } + dev_put(dev); } np->mcast_oif = val; retv = 0; @@ -661,7 +666,7 @@ done: case IPV6_MTU_DISCOVER: if (optlen < sizeof(int)) goto e_inval; - if (val<0 || val>3) + if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE) goto e_inval; np->pmtudisc = val; retv = 0; @@ -773,7 +778,7 @@ e_inval: } int ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; @@ -801,7 +806,7 @@ EXPORT_SYMBOL(ipv6_setsockopt); #ifdef CONFIG_COMPAT int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index f9fcf690bd5d..bcd971915969 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); @@ -2375,9 +2376,9 @@ static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); state->idev = NULL; - for_each_netdev(net, state->dev) { + for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; - idev = in6_dev_get(state->dev); + idev = __in6_dev_get(state->dev); if (!idev) continue; read_lock_bh(&idev->lock); @@ -2387,7 +2388,6 @@ static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq) break; } read_unlock_bh(&idev->lock); - in6_dev_put(idev); } return im; } @@ -2398,16 +2398,15 @@ static struct ifmcaddr6 *igmp6_mc_get_next(struct seq_file *seq, struct ifmcaddr im = im->next; while (!im) { - if (likely(state->idev != NULL)) { + if (likely(state->idev != NULL)) read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); - } - state->dev = next_net_device(state->dev); + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; break; } - state->idev = in6_dev_get(state->dev); + state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; read_lock_bh(&state->idev->lock); @@ -2426,31 +2425,31 @@ static struct ifmcaddr6 *igmp6_mc_get_idx(struct seq_file *seq, loff_t pos) } static void *igmp6_mc_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(RCU) { - read_lock(&dev_base_lock); + rcu_read_lock(); return igmp6_mc_get_idx(seq, *pos); } static void *igmp6_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct ifmcaddr6 *im; - im = igmp6_mc_get_next(seq, v); + struct ifmcaddr6 *im = igmp6_mc_get_next(seq, v); + ++*pos; return im; } static void igmp6_mc_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(RCU) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); + if (likely(state->idev != NULL)) { read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); state->idev = NULL; } state->dev = NULL; - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int igmp6_mc_seq_show(struct seq_file *seq, void *v) @@ -2507,9 +2506,9 @@ static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq) state->idev = NULL; state->im = NULL; - for_each_netdev(net, state->dev) { + for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; - idev = in6_dev_get(state->dev); + idev = __in6_dev_get(state->dev); if (unlikely(idev == NULL)) continue; read_lock_bh(&idev->lock); @@ -2525,7 +2524,6 @@ static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq) spin_unlock_bh(&im->mca_lock); } read_unlock_bh(&idev->lock); - in6_dev_put(idev); } return psf; } @@ -2539,16 +2537,15 @@ static struct ip6_sf_list *igmp6_mcf_get_next(struct seq_file *seq, struct ip6_s spin_unlock_bh(&state->im->mca_lock); state->im = state->im->next; while (!state->im) { - if (likely(state->idev != NULL)) { + if (likely(state->idev != NULL)) read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); - } - state->dev = next_net_device(state->dev); + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } - state->idev = in6_dev_get(state->dev); + state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; read_lock_bh(&state->idev->lock); @@ -2573,9 +2570,9 @@ static struct ip6_sf_list *igmp6_mcf_get_idx(struct seq_file *seq, loff_t pos) } static void *igmp6_mcf_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(RCU) { - read_lock(&dev_base_lock); + rcu_read_lock(); return *pos ? igmp6_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } @@ -2591,7 +2588,7 @@ static void *igmp6_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(RCU) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (likely(state->im != NULL)) { @@ -2600,11 +2597,10 @@ static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v) } if (likely(state->idev != NULL)) { read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); state->idev = NULL; } state->dev = NULL; - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int igmp6_mcf_seq_show(struct seq_file *seq, void *v) @@ -2651,7 +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; @@ -2671,23 +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; @@ -2713,7 +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 f797e8c6f3b3..2794b6002836 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 498b9b0b0fad..8bcc4b7db3bf 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -598,6 +598,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, icmp6h.icmp6_solicited = solicited; icmp6h.icmp6_override = override; + inc_opt |= ifp->idev->cnf.force_tllao; __ndisc_send(dev, neigh, daddr, src_addr, &icmp6h, solicited_addr, inc_opt ? ND_OPT_TARGET_LL_ADDR : 0); @@ -658,7 +659,6 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, &icmp6h, NULL, send_sllao ? ND_OPT_SOURCE_LL_ADDR : 0); } -EXPORT_SYMBOL(ndisc_send_rs); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb) @@ -1769,46 +1769,10 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *bu return ret; } -int ndisc_ifinfo_sysctl_strategy(ctl_table *ctl, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - struct net_device *dev = ctl->extra1; - struct inet6_dev *idev; - int ret; - - if (ctl->ctl_name == NET_NEIGH_RETRANS_TIME || - ctl->ctl_name == NET_NEIGH_REACHABLE_TIME) - ndisc_warn_deprecated_sysctl(ctl, "procfs", dev ? dev->name : "default"); - - switch (ctl->ctl_name) { - case NET_NEIGH_REACHABLE_TIME: - ret = sysctl_jiffies(ctl, oldval, oldlenp, newval, newlen); - break; - case NET_NEIGH_RETRANS_TIME_MS: - case NET_NEIGH_REACHABLE_TIME_MS: - ret = sysctl_ms_jiffies(ctl, oldval, oldlenp, newval, newlen); - break; - default: - ret = 0; - } - - if (newval && newlen && ret > 0 && - dev && (idev = in6_dev_get(dev)) != NULL) { - if (ctl->ctl_name == NET_NEIGH_REACHABLE_TIME || - ctl->ctl_name == NET_NEIGH_REACHABLE_TIME_MS) - idev->nd_parms->reachable_time = neigh_rand_reach_time(idev->nd_parms->base_reachable_time); - idev->tstamp = jiffies; - inet6_ifinfo_notify(RTM_NEWLINK, idev); - in6_dev_put(idev); - } - - return ret; -} #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; @@ -1833,7 +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); } @@ -1856,10 +1820,8 @@ 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", - &ndisc_ifinfo_sysctl_change, - &ndisc_ifinfo_sysctl_strategy); + err = neigh_sysctl_register(NULL, &nd_tbl.parms, "ipv6", + &ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; #endif diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 1cf3f0c6a959..7854052be60b 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -36,7 +36,6 @@ #define IPQ_QMAX_DEFAULT 1024 #define IPQ_PROC_FS_NAME "ip6_queue" -#define NET_IPQ_QMAX 2088 #define NET_IPQ_QMAX_NAME "ip6_queue_maxlen" typedef int (*ipq_cmpfn)(struct nf_queue_entry *, unsigned long); @@ -499,10 +498,9 @@ ipq_rcv_nl_event(struct notifier_block *this, { struct netlink_notify *n = ptr; - if (event == NETLINK_URELEASE && - n->protocol == NETLINK_IP6_FW && n->pid) { + if (event == NETLINK_URELEASE && n->protocol == NETLINK_IP6_FW) { write_lock_bh(&queue_lock); - if ((n->net == &init_net) && (n->pid == peer_pid)) + if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid)) __ipq_reset(); write_unlock_bh(&queue_lock); } @@ -518,14 +516,13 @@ static struct ctl_table_header *ipq_sysctl_header; static ctl_table ipq_table[] = { { - .ctl_name = NET_IPQ_QMAX, .procname = NET_IPQ_QMAX_NAME, .data = &queue_maxlen, .maxlen = sizeof(queue_maxlen), .mode = 0644, .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; #endif @@ -625,7 +622,7 @@ cleanup_netlink_notifier: static void __exit ip6_queue_fini(void) { nf_unregister_queue_handlers(&nfqh); - synchronize_net(); + ipq_flush(NULL, 0); #ifdef CONFIG_SYSCTL diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index cc9f8ef303fd..9210e312edf1 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 @@ -105,9 +112,9 @@ ip6_packet_match(const struct sk_buff *skb, #define FWINV(bool, invflg) ((bool) ^ !!(ip6info->invflags & (invflg))) if (FWINV(ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk, - &ip6info->src), IP6T_INV_SRCIP) - || FWINV(ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, - &ip6info->dst), IP6T_INV_DSTIP)) { + &ip6info->src), IP6T_INV_SRCIP) || + FWINV(ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, + &ip6info->dst), IP6T_INV_DSTIP)) { dprintf("Source or dest mismatch.\n"); /* dprintf("SRC: %u. Mask: %u. Target: %u.%s\n", ip->saddr, @@ -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 */ @@ -277,11 +290,11 @@ get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ip6t_entry) - && strcmp(t->target.u.kernel.target->name, - IP6T_STANDARD_TARGET) == 0 - && t->verdict < 0 - && unconditional(&s->ipv6)) { + if (s->target_offset == sizeof(struct ip6t_entry) && + strcmp(t->target.u.kernel.target->name, + IP6T_STANDARD_TARGET) == 0 && + t->verdict < 0 && + unconditional(&s->ipv6)) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP6_TRACE_COMMENT_POLICY] @@ -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) || \ @@ -418,8 +437,8 @@ ip6t_do_table(struct sk_buff *skb, back = get_entry(table_base, back->comefrom); continue; } - if (table_base + v != ip6t_next_entry(e) - && !(e->ipv6.flags & IP6T_F_GOTO)) { + if (table_base + v != ip6t_next_entry(e) && + !(e->ipv6.flags & IP6T_F_GOTO)) { /* Save old back ptr in next entry */ struct ip6t_entry *next = ip6t_next_entry(e); next->comefrom = (void *)back - table_base; @@ -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)) { @@ -505,11 +524,11 @@ mark_source_chains(struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ip6t_entry) - && (strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0) - && t->verdict < 0 - && unconditional(&e->ipv6)) || visited) { + if ((e->target_offset == sizeof(struct ip6t_entry) && + (strcmp(t->target.u.user.name, + IP6T_STANDARD_TARGET) == 0) && + t->verdict < 0 && + unconditional(&e->ipv6)) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -556,8 +575,8 @@ mark_source_chains(struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0 - && newpos >= 0) { + IP6T_STANDARD_TARGET) == 0 && + newpos >= 0) { if (newpos > newinfo->size - sizeof(struct ip6t_entry)) { duprintf("mark_source_chains: " @@ -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; @@ -758,17 +778,16 @@ 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; - if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 - || (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || + (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -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; @@ -1584,8 +1552,8 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, int ret, off, h; duprintf("check_compat_entry_size_and_hooks %p\n", e); - if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 - || (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || + (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } @@ -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_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 7018cac4fddc..b285fdf19050 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -249,8 +249,8 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 11 "URGP=65535 " */ printk("URGP=%u ", ntohs(th->urg_ptr)); - if ((logflags & IP6T_LOG_TCPOPT) - && th->doff * 4 > sizeof(struct tcphdr)) { + if ((logflags & IP6T_LOG_TCPOPT) && + th->doff * 4 > sizeof(struct tcphdr)) { u_int8_t _opt[60 - sizeof(struct tcphdr)]; const u_int8_t *op; unsigned int i; diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 5a7f00cd15ce..dd8afbaf00a8 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 @@ -223,8 +223,8 @@ static bool reject_tg6_check(const struct xt_tgchk_param *par) return false; } else if (rejinfo->with == IP6T_TCP_RESET) { /* Must specify that it's a TCP packet */ - if (e->ipv6.proto != IPPROTO_TCP - || (e->ipv6.invflags & XT_INV_PROTO)) { + if (e->ipv6.proto != IPPROTO_TCP || + (e->ipv6.invflags & XT_INV_PROTO)) { printk("ip6t_REJECT: TCP_RESET illegal for non-tcp\n"); return false; } diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index 3a82f24746b9..ac0b7c629d78 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -77,17 +77,14 @@ static bool ah_mt6(const struct sk_buff *skb, const struct xt_match_param *par) ahinfo->hdrres, ah->reserved, !(ahinfo->hdrres && ah->reserved)); - return (ah != NULL) - && - spi_match(ahinfo->spis[0], ahinfo->spis[1], - ntohl(ah->spi), - !!(ahinfo->invflags & IP6T_AH_INV_SPI)) - && - (!ahinfo->hdrlen || - (ahinfo->hdrlen == hdrlen) ^ - !!(ahinfo->invflags & IP6T_AH_INV_LEN)) - && - !(ahinfo->hdrres && ah->reserved); + return (ah != NULL) && + spi_match(ahinfo->spis[0], ahinfo->spis[1], + ntohl(ah->spi), + !!(ahinfo->invflags & IP6T_AH_INV_SPI)) && + (!ahinfo->hdrlen || + (ahinfo->hdrlen == hdrlen) ^ + !!(ahinfo->invflags & IP6T_AH_INV_LEN)) && + !(ahinfo->hdrres && ah->reserved); } static bool ah_mt6_check(const struct xt_mtchk_param *par) diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index 673aa0a5084e..7b91c2598ed5 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -70,41 +70,36 @@ frag_mt6(const struct sk_buff *skb, const struct xt_match_param *par) pr_debug("res %02X %02X%04X %02X ", fraginfo->flags & IP6T_FRAG_RES, fh->reserved, ntohs(fh->frag_off) & 0x6, - !((fraginfo->flags & IP6T_FRAG_RES) - && (fh->reserved || (ntohs(fh->frag_off) & 0x06)))); + !((fraginfo->flags & IP6T_FRAG_RES) && + (fh->reserved || (ntohs(fh->frag_off) & 0x06)))); pr_debug("first %02X %02X %02X ", fraginfo->flags & IP6T_FRAG_FST, ntohs(fh->frag_off) & ~0x7, - !((fraginfo->flags & IP6T_FRAG_FST) - && (ntohs(fh->frag_off) & ~0x7))); + !((fraginfo->flags & IP6T_FRAG_FST) && + (ntohs(fh->frag_off) & ~0x7))); pr_debug("mf %02X %02X %02X ", fraginfo->flags & IP6T_FRAG_MF, ntohs(fh->frag_off) & IP6_MF, - !((fraginfo->flags & IP6T_FRAG_MF) - && !((ntohs(fh->frag_off) & IP6_MF)))); + !((fraginfo->flags & IP6T_FRAG_MF) && + !((ntohs(fh->frag_off) & IP6_MF)))); pr_debug("last %02X %02X %02X\n", fraginfo->flags & IP6T_FRAG_NMF, ntohs(fh->frag_off) & IP6_MF, - !((fraginfo->flags & IP6T_FRAG_NMF) - && (ntohs(fh->frag_off) & IP6_MF))); - - return (fh != NULL) - && - id_match(fraginfo->ids[0], fraginfo->ids[1], - ntohl(fh->identification), - !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)) - && - !((fraginfo->flags & IP6T_FRAG_RES) - && (fh->reserved || (ntohs(fh->frag_off) & 0x6))) - && - !((fraginfo->flags & IP6T_FRAG_FST) - && (ntohs(fh->frag_off) & ~0x7)) - && - !((fraginfo->flags & IP6T_FRAG_MF) - && !(ntohs(fh->frag_off) & IP6_MF)) - && - !((fraginfo->flags & IP6T_FRAG_NMF) - && (ntohs(fh->frag_off) & IP6_MF)); + !((fraginfo->flags & IP6T_FRAG_NMF) && + (ntohs(fh->frag_off) & IP6_MF))); + + return (fh != NULL) && + id_match(fraginfo->ids[0], fraginfo->ids[1], + ntohl(fh->identification), + !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)) && + !((fraginfo->flags & IP6T_FRAG_RES) && + (fh->reserved || (ntohs(fh->frag_off) & 0x6))) && + !((fraginfo->flags & IP6T_FRAG_FST) && + (ntohs(fh->frag_off) & ~0x7)) && + !((fraginfo->flags & IP6T_FRAG_MF) && + !(ntohs(fh->frag_off) & IP6_MF)) && + !((fraginfo->flags & IP6T_FRAG_NMF) && + (ntohs(fh->frag_off) & IP6_MF)); } static bool frag_mt6_check(const struct xt_mtchk_param *par) diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index 356b8d6f6baa..b77307fc8743 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -92,16 +92,13 @@ static bool rt_mt6(const struct sk_buff *skb, const struct xt_match_param *par) !((rtinfo->flags & IP6T_RT_RES) && (((const struct rt0_hdr *)rh)->reserved))); - ret = (rh != NULL) - && + ret = (rh != NULL) && (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], rh->segments_left, - !!(rtinfo->invflags & IP6T_RT_INV_SGS))) - && + !!(rtinfo->invflags & IP6T_RT_INV_SGS))) && (!(rtinfo->flags & IP6T_RT_LEN) || ((rtinfo->hdrlen == hdrlen) ^ - !!(rtinfo->invflags & IP6T_RT_INV_LEN))) - && + !!(rtinfo->invflags & IP6T_RT_INV_LEN))) && (!(rtinfo->flags & IP6T_RT_TYP) || ((rtinfo->rt_type == rh->type) ^ !!(rtinfo->invflags & IP6T_RT_INV_TYP))); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 6f4383ad86f9..36b72cafc227 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 0ad91433ed61..7844e557c0ec 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; @@ -102,8 +39,8 @@ ip6t_local_out_hook(unsigned int hook, #if 0 /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) - || ip_hdrlen(skb) < sizeof(struct iphdr)) { + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) { if (net_ratelimit()) printk("ip6t_hook: happy cracking.\n"); return NF_ACCEPT; @@ -119,62 +56,46 @@ 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 - && (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) - || memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) - || skb->mark != mark - || ipv6_hdr(skb)->hop_limit != hop_limit)) + if (ret != NF_DROP && ret != NF_STOLEN && + (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || + memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || + skb->mark != mark || + ipv6_hdr(skb)->hop_limit != hop_limit)) return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP; 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 ed1a1180f3b3..aef31a29de9e 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 41b444c60934..0824d865aa9b 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 5f2ec208a8c3..996c3f41fecd 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -20,12 +20,14 @@ #include <net/ipv6.h> #include <net/inet_frag.h> +#include <linux/netfilter_bridge.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #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> @@ -187,6 +189,26 @@ out: return nf_conntrack_confirm(skb); } +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 + zone; +#endif + if (hooknum == NF_INET_PRE_ROUTING) + return IP6_DEFRAG_CONNTRACK_IN + zone; + else + return IP6_DEFRAG_CONNTRACK_OUT + zone; + +} + static unsigned int ipv6_defrag(unsigned int hooknum, struct sk_buff *skb, const struct net_device *in, @@ -196,11 +218,10 @@ 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); - + reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb)); /* queued */ if (reasm == NULL) return NF_STOLEN; diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 642dcb127bab..9be81776415e 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) @@ -244,18 +247,18 @@ static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = { static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *tuple) { - if (!tb[CTA_PROTO_ICMPV6_TYPE] - || !tb[CTA_PROTO_ICMPV6_CODE] - || !tb[CTA_PROTO_ICMPV6_ID]) + if (!tb[CTA_PROTO_ICMPV6_TYPE] || + !tb[CTA_PROTO_ICMPV6_CODE] || + !tb[CTA_PROTO_ICMPV6_ID]) return -EINVAL; tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); - if (tuple->dst.u.icmp.type < 128 - || tuple->dst.u.icmp.type - 128 >= sizeof(invmap) - || !invmap[tuple->dst.u.icmp.type - 128]) + if (tuple->dst.u.icmp.type < 128 || + tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type - 128]) return -EINVAL; return 0; @@ -277,9 +280,7 @@ static struct ctl_table icmpv6_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .ctl_name = 0 - } + { } }; #endif /* CONFIG_SYSCTL */ diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index f3aba255ad9f..f1171b744650 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; @@ -83,7 +81,6 @@ struct ctl_table nf_ct_ipv6_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_NF_CONNTRACK_FRAG6_LOW_THRESH, .procname = "nf_conntrack_frag6_low_thresh", .data = &nf_init_frags.low_thresh, .maxlen = sizeof(unsigned int), @@ -91,14 +88,13 @@ struct ctl_table nf_ct_ipv6_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NF_CONNTRACK_FRAG6_HIGH_THRESH, .procname = "nf_conntrack_frag6_high_thresh", .data = &nf_init_frags.high_thresh, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, }, - { .ctl_name = 0 } + { } }; #endif @@ -170,13 +166,14 @@ out: /* Creation primitives. */ static __inline__ struct nf_ct_frag6_queue * -fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst) +fq_find(__be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst) { struct inet_frag_queue *q; struct ip6_create_arg arg; unsigned int hash; arg.id = id; + arg.user = user; arg.src = src; arg.dst = dst; @@ -472,7 +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; @@ -561,7 +558,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) return 0; } -struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb) +struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) { struct sk_buff *clone; struct net_device *dev = skb->dev; @@ -598,16 +595,10 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb) 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(); - fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr); + fq = fq_find(fhdr->identification, user, &hdr->saddr, &hdr->daddr); if (fq == NULL) { pr_debug("Can't find and can't create new queue\n"); goto ret_orig; @@ -670,8 +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 c9605c3ad91f..58344c0fbd13 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 7d675b8d82d3..ed31c37c6e39 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -72,7 +72,7 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, int is_multicast = ipv6_addr_is_multicast(loc_addr); sk_for_each_from(sk, node) - if (inet_sk(sk)->num == num) { + if (inet_sk(sk)->inet_num == num) { struct ipv6_pinfo *np = inet6_sk(sk); if (!net_eq(sock_net(sk), net)) @@ -249,7 +249,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* Raw sockets are IPv6 only */ if (addr_type == IPV6_ADDR_MAPPED) - return(-EADDRNOTAVAIL); + return -EADDRNOTAVAIL; lock_sock(sk); @@ -257,6 +257,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (sk->sk_state != TCP_CLOSE) goto out; + rcu_read_lock(); /* Check if the address belongs to the host. */ if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; @@ -272,13 +273,13 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) - goto out; + goto out_unlock; - dev = dev_get_by_index(sock_net(sk), sk->sk_bound_dev_if); - if (!dev) { - err = -ENODEV; - goto out; - } + err = -ENODEV; + dev = dev_get_by_index_rcu(sock_net(sk), + sk->sk_bound_dev_if); + if (!dev) + goto out_unlock; } /* ipv4 addr of the socket is invalid. Only the @@ -289,20 +290,18 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { - if (dev) - dev_put(dev); - goto out; + goto out_unlock; } } - if (dev) - dev_put(dev); } - inet->rcv_saddr = inet->saddr = v4addr; + inet->inet_rcv_saddr = inet->inet_saddr = v4addr; ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr); if (!(addr_type & IPV6_ADDR_MULTICAST)) ipv6_addr_copy(&np->saddr, &addr->sin6_addr); err = 0; +out_unlock: + rcu_read_unlock(); out: release_sock(sk); return err; @@ -381,8 +380,7 @@ static inline int rawv6_rcv_skb(struct sock * sk, struct sk_buff * skb) } /* Charge it to the socket. */ - if (sock_queue_rcv_skb(sk,skb)<0) { - atomic_inc(&sk->sk_drops); + if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } @@ -416,14 +414,14 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) skb_network_header_len(skb)); if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, - skb->len, inet->num, skb->csum)) + skb->len, inet->inet_num, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } if (!skb_csum_unnecessary(skb)) skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, - inet->num, 0)); + inet->inet_num, 0)); if (inet->hdrincl) { if (skb_checksum_complete(skb)) { @@ -497,7 +495,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, sin6->sin6_scope_id = IP6CB(skb)->iif; } - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); if (np->rxopt.all) datagram_recv_ctl(sk, msg, skb); @@ -518,7 +516,6 @@ csum_copy_err: as some normal condition. */ err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH; - atomic_inc(&sk->sk_drops); goto out; } @@ -766,8 +763,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, proto = ntohs(sin6->sin6_port); if (!proto) - proto = inet->num; - else if (proto != inet->num) + proto = inet->inet_num; + else if (proto != inet->inet_num) return(-EINVAL); if (proto > 255) @@ -800,7 +797,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - proto = inet->num; + proto = inet->inet_num; daddr = &np->daddr; fl.fl6_flowlabel = np->flow_label; } @@ -957,7 +954,7 @@ static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; @@ -967,7 +964,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case IPV6_CHECKSUM: - if (inet_sk(sk)->num == IPPROTO_ICMPV6 && + if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && level == IPPROTO_IPV6) { /* * RFC3542 tells that IPV6_CHECKSUM socket @@ -1000,14 +997,14 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, } static int rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { switch(level) { case SOL_RAW: break; case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); @@ -1024,13 +1021,13 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: @@ -1087,7 +1084,7 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, break; case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); @@ -1110,7 +1107,7 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, case SOL_RAW: break; case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: @@ -1157,7 +1154,7 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) static void rawv6_close(struct sock *sk, long timeout) { - if (inet_sk(sk)->num == IPPROTO_RAW) + if (inet_sk(sk)->inet_num == IPPROTO_RAW) ip6_ra_control(sk, -1); ip6mr_sk_done(sk); sk_common_release(sk); @@ -1176,7 +1173,7 @@ static int rawv6_init_sk(struct sock *sk) { struct raw6_sock *rp = raw6_sk(sk); - switch (inet_sk(sk)->num) { + switch (inet_sk(sk)->inet_num) { case IPPROTO_ICMPV6: rp->checksum = 1; rp->offset = 2; @@ -1226,7 +1223,7 @@ static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) dest = &np->daddr; src = &np->rcv_saddr; destp = 0; - srcp = inet_sk(sp)->num; + srcp = inet_sk(sp)->inet_num; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", @@ -1278,7 +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; @@ -1286,7 +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"); } @@ -1338,7 +1335,6 @@ static struct inet_protosw rawv6_protosw = { .protocol = IPPROTO_IP, /* wild card */ .prot = &rawv6_prot, .ops = &inet6_sockraw_ops, - .capability = CAP_NET_RAW, .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_REUSE, }; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index da5bd0ed83df..a555156e9779 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -72,6 +72,7 @@ struct frag_queue struct inet_frag_queue q; __be32 id; /* fragment id */ + u32 user; struct in6_addr saddr; struct in6_addr daddr; @@ -141,7 +142,7 @@ int ip6_frag_match(struct inet_frag_queue *q, void *a) struct ip6_create_arg *arg = a; fq = container_of(q, struct frag_queue, q); - return (fq->id == arg->id && + return (fq->id == arg->id && fq->user == arg->user && ipv6_addr_equal(&fq->saddr, arg->src) && ipv6_addr_equal(&fq->daddr, arg->dst)); } @@ -163,6 +164,7 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a) struct ip6_create_arg *arg = a; fq->id = arg->id; + fq->user = arg->user; ipv6_addr_copy(&fq->saddr, arg->src); ipv6_addr_copy(&fq->daddr, arg->dst); } @@ -208,18 +210,17 @@ static void ip6_frag_expire(unsigned long data) fq_kill(fq); net = container_of(fq->q.net, struct net, ipv6.frags); - dev = dev_get_by_index(net, fq->iif); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, fq->iif); if (!dev) - goto out; + goto out_rcu_unlock; - rcu_read_lock(); IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); - rcu_read_unlock(); /* Don't send error if the first segment did not arrive. */ if (!(fq->q.last_in & INET_FRAG_FIRST_IN) || !fq->q.fragments) - goto out; + goto out_rcu_unlock; /* But use as source device on which LAST ARRIVED @@ -227,23 +228,23 @@ 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: - if (dev) - dev_put(dev); spin_unlock(&fq->q.lock); fq_put(fq); } 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; unsigned int hash; arg.id = id; + arg.user = IP6_DEFRAG_LOCAL_DELIVER; arg.src = src; arg.dst = dst; @@ -252,13 +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, @@ -604,8 +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); @@ -636,7 +633,6 @@ static const struct inet6_protocol frag_protocol = #ifdef CONFIG_SYSCTL static struct ctl_table ip6_frags_ns_ctl_table[] = { { - .ctl_name = NET_IPV6_IP6FRAG_HIGH_THRESH, .procname = "ip6frag_high_thresh", .data = &init_net.ipv6.frags.high_thresh, .maxlen = sizeof(int), @@ -644,7 +640,6 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV6_IP6FRAG_LOW_THRESH, .procname = "ip6frag_low_thresh", .data = &init_net.ipv6.frags.low_thresh, .maxlen = sizeof(int), @@ -652,37 +647,33 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV6_IP6FRAG_TIME, .procname = "ip6frag_time", .data = &init_net.ipv6.frags.timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { } }; static struct ctl_table ip6_frags_ctl_table[] = { { - .ctl_name = NET_IPV6_IP6FRAG_SECRET_INTERVAL, .procname = "ip6frag_secret_interval", .data = &ip6_frags.secret_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies }, { } }; -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; table = ip6_frags_ns_ctl_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ip6_frags_ns_ctl_table), GFP_KERNEL); if (table == NULL) goto err_alloc; @@ -700,19 +691,20 @@ static int ip6_frags_ns_sysctl_register(struct net *net) return 0; err_reg: - if (net != &init_net) + if (!net_eq(net, &init_net)) kfree(table); 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; table = net->ipv6.sysctl.frags_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv6.sysctl.frags_hdr); - kfree(table); + if (!net_eq(net, &init_net)) + kfree(table); } static struct ctl_table_header *ip6_ctl_header; @@ -748,10 +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); @@ -759,7 +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 d6fe7646a8ff..52cd3eff31dc 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) { @@ -1471,9 +1464,10 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, }, }, }, - .gateway = *gateway, }; + ipv6_addr_copy(&rdfl.gateway, gateway); + if (rt6_need_strict(dest)) flags |= RT6_LOOKUP_F_IFACE; @@ -1872,7 +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; @@ -1883,7 +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; } @@ -2546,7 +2540,6 @@ ctl_table ipv6_route_table_template[] = { .proc_handler = ipv6_sysctl_rtcache_flush }, { - .ctl_name = NET_IPV6_ROUTE_GC_THRESH, .procname = "gc_thresh", .data = &ip6_dst_ops_template.gc_thresh, .maxlen = sizeof(int), @@ -2554,7 +2547,6 @@ ctl_table ipv6_route_table_template[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ROUTE_MAX_SIZE, .procname = "max_size", .data = &init_net.ipv6.sysctl.ip6_rt_max_size, .maxlen = sizeof(int), @@ -2562,72 +2554,58 @@ ctl_table ipv6_route_table_template[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL, .procname = "gc_min_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_TIMEOUT, .procname = "gc_timeout", .data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_INTERVAL, .procname = "gc_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_ELASTICITY, .procname = "gc_elasticity", .data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_MTU_EXPIRES, .procname = "mtu_expires", .data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_MIN_ADVMSS, .procname = "min_adv_mss", .data = &init_net.ipv6.sysctl.ip6_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS, .procname = "gc_min_interval_ms", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, - .strategy = sysctl_ms_jiffies, }, - { .ctl_name = 0 } + { } }; -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; @@ -2645,13 +2623,14 @@ struct ctl_table *ipv6_route_sysctl_init(struct net *net) table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity; table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires; table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; + table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; } return table; } #endif -static int ip6_route_net_init(struct net *net) +static int __net_init ip6_route_net_init(struct net *net) { int ret = -ENOMEM; @@ -2716,7 +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 fcb539628847..b1eea811be48 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -15,7 +15,6 @@ * Roger Venning <r.venning@telstra.com>: 6to4 support * Nate Thompson <nate@thebog.net>: 6to4 support * Fred Templin <fred.l.templin@boeing.com>: isatap support - * Sascha Hlusiak <mail@saschahlusiak.de>: stateless autoconf for isatap */ #include <linux/module.h> @@ -63,11 +62,10 @@ #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); -static int sit_net_id; +static int sit_net_id __read_mostly; struct sit_net { struct ip_tunnel *tunnels_r_l[HASH_SIZE]; struct ip_tunnel *tunnels_r[HASH_SIZE]; @@ -78,8 +76,17 @@ struct sit_net { struct net_device *fb_tunnel_dev; }; -static DEFINE_RWLOCK(ipip6_lock); +/* + * Locking : hash tables are protected by RCU and a spinlock + */ +static DEFINE_SPINLOCK(ipip6_lock); +#define for_each_ip_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) + +/* + * Must be invoked with rcu_read_lock + */ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, struct net_device *dev, __be32 remote, __be32 local) { @@ -88,26 +95,26 @@ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); - for (t = sitn->tunnels_r_l[h0^h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - for (t = sitn->tunnels_r[h0]; t; t = t->next) { + for_each_ip_tunnel_rcu(sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - for (t = sitn->tunnels_l[h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - t = sitn->tunnels_wc[0]; + t = rcu_dereference(sitn->tunnels_wc[0]); if ((t != NULL) && (t->dev->flags & IFF_UP)) return t; return NULL; @@ -144,9 +151,9 @@ static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) for (tp = ipip6_bucket(sitn, t); *tp; tp = &(*tp)->next) { if (t == *tp) { - write_lock_bh(&ipip6_lock); + spin_lock_bh(&ipip6_lock); *tp = t->next; - write_unlock_bh(&ipip6_lock); + spin_unlock_bh(&ipip6_lock); break; } } @@ -156,10 +163,27 @@ static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t) { struct ip_tunnel **tp = ipip6_bucket(sitn, t); + spin_lock_bh(&ipip6_lock); t->next = *tp; - write_lock_bh(&ipip6_lock); - *tp = t; - write_unlock_bh(&ipip6_lock); + rcu_assign_pointer(*tp, t); + spin_unlock_bh(&ipip6_lock); +} + +static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) +{ +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel *t = netdev_priv(dev); + + if (t->dev == sitn->fb_tunnel_dev) { + ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0); + t->ip6rd.relay_prefix = 0; + t->ip6rd.prefixlen = 16; + t->ip6rd.relay_prefixlen = 0; + } else { + struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev); + memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd)); + } +#endif } static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, @@ -205,6 +229,7 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, nt->parms = *parms; ipip6_tunnel_init(dev); + ipip6_tunnel_clone_6rd(dev, sitn); if (parms->i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; @@ -223,53 +248,22 @@ failed: return NULL; } -static void ipip6_tunnel_rs_timer(unsigned long data) -{ - struct ip_tunnel_prl_entry *p = (struct ip_tunnel_prl_entry *) data; - struct inet6_dev *ifp; - struct inet6_ifaddr *addr; - - spin_lock(&p->lock); - ifp = __in6_dev_get(p->tunnel->dev); +static DEFINE_SPINLOCK(ipip6_prl_lock); - read_lock_bh(&ifp->lock); - for (addr = ifp->addr_list; addr; addr = addr->if_next) { - struct in6_addr rtr; - - if (!(ipv6_addr_type(&addr->addr) & IPV6_ADDR_LINKLOCAL)) - continue; - - /* Send RS to guessed linklocal address of router - * - * Better: send to ff02::2 encapsuled in unicast directly - * to router-v4 instead of guessing the v6 address. - * - * Cisco/Windows seem to not set the u/l bit correctly, - * so we won't guess right. - */ - ipv6_addr_set(&rtr, htonl(0xFE800000), 0, 0, 0); - if (!__ipv6_isatap_ifid(rtr.s6_addr + 8, - p->addr)) { - ndisc_send_rs(p->tunnel->dev, &addr->addr, &rtr); - } - } - read_unlock_bh(&ifp->lock); - - mod_timer(&p->rs_timer, jiffies + HZ * p->rs_delay); - spin_unlock(&p->lock); - - return; -} +#define for_each_prl_rcu(start) \ + for (prl = rcu_dereference(start); \ + prl; \ + prl = rcu_dereference(prl->next)) static struct ip_tunnel_prl_entry * __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) { - struct ip_tunnel_prl_entry *p = (struct ip_tunnel_prl_entry *)NULL; + struct ip_tunnel_prl_entry *prl; - for (p = t->prl; p; p = p->next) - if (p->addr == addr) + for_each_prl_rcu(t->prl) + if (prl->addr == addr) break; - return p; + return prl; } @@ -294,7 +288,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, kcalloc(cmax, sizeof(*kp), GFP_KERNEL) : NULL; - read_lock(&ipip6_lock); + rcu_read_lock(); ca = t->prl_count < cmax ? t->prl_count : cmax; @@ -312,20 +306,19 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, } c = 0; - for (prl = t->prl; prl; prl = prl->next) { - if (c > cmax) + for_each_prl_rcu(t->prl) { + if (c >= cmax) break; if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr) continue; kp[c].addr = prl->addr; kp[c].flags = prl->flags; - kp[c].rs_delay = prl->rs_delay; c++; if (kprl.addr != htonl(INADDR_ANY)) break; } out: - read_unlock(&ipip6_lock); + rcu_read_unlock(); len = sizeof(*kp) * c; ret = 0; @@ -346,12 +339,14 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) if (a->addr == htonl(INADDR_ANY)) return -EINVAL; - write_lock(&ipip6_lock); + spin_lock(&ipip6_prl_lock); for (p = t->prl; p; p = p->next) { if (p->addr == a->addr) { - if (chg) - goto update; + if (chg) { + p->flags = a->flags; + goto out; + } err = -EEXIST; goto out; } @@ -369,63 +364,61 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) } p->next = t->prl; - p->tunnel = t; - t->prl = p; - t->prl_count++; - - spin_lock_init(&p->lock); - setup_timer(&p->rs_timer, ipip6_tunnel_rs_timer, (unsigned long) p); -update: p->addr = a->addr; p->flags = a->flags; - p->rs_delay = a->rs_delay; - if (p->rs_delay == 0) - p->rs_delay = IPTUNNEL_RS_DEFAULT_DELAY; - spin_lock(&p->lock); - del_timer(&p->rs_timer); - if (p->flags & PRL_DEFAULT) - mod_timer(&p->rs_timer, jiffies + 1); - spin_unlock(&p->lock); + t->prl_count++; + rcu_assign_pointer(t->prl, p); out: - write_unlock(&ipip6_lock); + spin_unlock(&ipip6_prl_lock); return err; } +static void prl_entry_destroy_rcu(struct rcu_head *head) +{ + kfree(container_of(head, struct ip_tunnel_prl_entry, rcu_head)); +} + +static void prl_list_destroy_rcu(struct rcu_head *head) +{ + struct ip_tunnel_prl_entry *p, *n; + + p = container_of(head, struct ip_tunnel_prl_entry, rcu_head); + do { + n = p->next; + kfree(p); + p = n; + } while (p); +} + static int ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) { struct ip_tunnel_prl_entry *x, **p; int err = 0; - write_lock(&ipip6_lock); + spin_lock(&ipip6_prl_lock); if (a && a->addr != htonl(INADDR_ANY)) { for (p = &t->prl; *p; p = &(*p)->next) { if ((*p)->addr == a->addr) { x = *p; *p = x->next; - spin_lock(&x->lock); - del_timer(&x->rs_timer); - spin_unlock(&x->lock); - kfree(x); + call_rcu(&x->rcu_head, prl_entry_destroy_rcu); t->prl_count--; goto out; } } err = -ENXIO; } else { - while (t->prl) { + if (t->prl) { + t->prl_count = 0; x = t->prl; - t->prl = t->prl->next; - spin_lock(&x->lock); - del_timer(&x->rs_timer); - spin_unlock(&x->lock); - kfree(x); - t->prl_count--; + call_rcu(&x->rcu_head, prl_list_destroy_rcu); + t->prl = NULL; } } out: - write_unlock(&ipip6_lock); + spin_unlock(&ipip6_prl_lock); return err; } @@ -435,7 +428,7 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t) struct ip_tunnel_prl_entry *p; int ok = 1; - read_lock(&ipip6_lock); + rcu_read_lock(); p = __ipip6_tunnel_locate_prl(t, iph->saddr); if (p) { if (p->flags & PRL_DEFAULT) @@ -451,7 +444,7 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t) else ok = 0; } - read_unlock(&ipip6_lock); + rcu_read_unlock(); return ok; } @@ -461,9 +454,9 @@ static void ipip6_tunnel_uninit(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); if (dev == sitn->fb_tunnel_dev) { - write_lock_bh(&ipip6_lock); + spin_lock_bh(&ipip6_lock); sitn->tunnels_wc[0] = NULL; - write_unlock_bh(&ipip6_lock); + spin_unlock_bh(&ipip6_lock); dev_put(dev); } else { ipip6_tunnel_unlink(sitn, netdev_priv(dev)); @@ -516,7 +509,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info) err = -ENOENT; - read_lock(&ipip6_lock); + rcu_read_lock(); t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->daddr, @@ -534,7 +527,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info) t->err_count = 1; t->err_time = jiffies; out: - read_unlock(&ipip6_lock); + rcu_read_unlock(); return err; } @@ -554,7 +547,7 @@ static int ipip6_rcv(struct sk_buff *skb) iph = ip_hdr(skb); - read_lock(&ipip6_lock); + rcu_read_lock(); tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); if (tunnel != NULL) { @@ -568,7 +561,7 @@ static int ipip6_rcv(struct sk_buff *skb) if ((tunnel->dev->priv_flags & IFF_ISATAP) && !isatap_chksrc(skb, iph, tunnel)) { tunnel->dev->stats.rx_errors++; - read_unlock(&ipip6_lock); + rcu_read_unlock(); kfree_skb(skb); return 0; } @@ -579,28 +572,52 @@ static int ipip6_rcv(struct sk_buff *skb) nf_reset(skb); ipip6_ecn_decapsulate(iph, skb); netif_rx(skb); - read_unlock(&ipip6_lock); + rcu_read_unlock(); return 0; } icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); - read_unlock(&ipip6_lock); + rcu_read_unlock(); out: kfree_skb(skb); return 0; } -/* Returns the embedded IPv4 address if the IPv6 address - comes from 6to4 (RFC 3056) addr space */ - -static inline __be32 try_6to4(struct in6_addr *v6dst) +/* + * Returns the embedded IPv4 address if the IPv6 address + * comes from 6rd / 6to4 (RFC 3056) addr space. + */ +static inline +__be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel) { __be32 dst = 0; +#ifdef CONFIG_IPV6_SIT_6RD + if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix, + tunnel->ip6rd.prefixlen)) { + unsigned pbw0, pbi0; + int pbi1; + u32 d; + + pbw0 = tunnel->ip6rd.prefixlen >> 5; + pbi0 = tunnel->ip6rd.prefixlen & 0x1f; + + d = (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >> + tunnel->ip6rd.relay_prefixlen; + + pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen; + if (pbi1 > 0) + d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >> + (32 - pbi1); + + dst = tunnel->ip6rd.relay_prefix | htonl(d); + } +#else if (v6dst->s6_addr16[0] == htons(0x2002)) { /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */ memcpy(&dst, &v6dst->s6_addr16[1], 4); } +#endif return dst; } @@ -613,10 +630,12 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct net_device_stats *stats = &tunnel->dev->stats; + struct net_device_stats *stats = &dev->stats; + struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); struct iphdr *tiph = &tunnel->parms.iph; struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; + __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ struct iphdr *iph; /* Our new IP header */ @@ -653,7 +672,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (!dst) - dst = try_6to4(&iph6->daddr); + dst = try_6rd(&iph6->daddr, tunnel); if (!dst) { struct neighbour *neigh = NULL; @@ -706,25 +725,28 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, goto tx_error; } - if (tiph->frag_off) + if (df) { mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); - else - mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; - if (mtu < 68) { - stats->collisions++; - ip_rt_put(rt); - goto tx_error; - } - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; - if (tunnel->parms.iph.daddr && skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + if (mtu < 68) { + stats->collisions++; + ip_rt_put(rt); + goto tx_error; + } - if (skb->len > mtu) { - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev); - ip_rt_put(rt); - goto tx_error; + if (mtu < IPV6_MIN_MTU) { + mtu = IPV6_MIN_MTU; + df = 0; + } + + if (tunnel->parms.iph.daddr && skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + + if (skb->len > mtu) { + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + ip_rt_put(rt); + goto tx_error; + } } if (tunnel->err_count > 0) { @@ -746,7 +768,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); - stats->tx_dropped++; + txq->tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -772,11 +794,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, iph = ip_hdr(skb); iph->version = 4; iph->ihl = sizeof(struct iphdr)>>2; - if (mtu > IPV6_MIN_MTU) - iph->frag_off = tiph->frag_off; - else - iph->frag_off = 0; - + iph->frag_off = df; iph->protocol = IPPROTO_IPV6; iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); iph->daddr = rt->rt_dst; @@ -843,9 +861,15 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) struct ip_tunnel *t; struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd ip6rd; +#endif switch (cmd) { case SIOCGETTUNNEL: +#ifdef CONFIG_IPV6_SIT_6RD + case SIOCGET6RD: +#endif t = NULL; if (dev == sitn->fb_tunnel_dev) { if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { @@ -856,9 +880,25 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) } if (t == NULL) t = netdev_priv(dev); - memcpy(&p, &t->parms, sizeof(p)); - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) - err = -EFAULT; + + err = -EFAULT; + if (cmd == SIOCGETTUNNEL) { + memcpy(&p, &t->parms, sizeof(p)); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, + sizeof(p))) + goto done; +#ifdef CONFIG_IPV6_SIT_6RD + } else { + ipv6_addr_copy(&ip6rd.prefix, &t->ip6rd.prefix); + ip6rd.relay_prefix = t->ip6rd.relay_prefix; + ip6rd.prefixlen = t->ip6rd.prefixlen; + ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen; + if (copy_to_user(ifr->ifr_ifru.ifru_data, &ip6rd, + sizeof(ip6rd))) + goto done; +#endif + } + err = 0; break; case SIOCADDTUNNEL: @@ -979,6 +1019,54 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) netdev_state_change(dev); break; +#ifdef CONFIG_IPV6_SIT_6RD + case SIOCADD6RD: + case SIOCCHG6RD: + case SIOCDEL6RD: + err = -EPERM; + if (!capable(CAP_NET_ADMIN)) + goto done; + + err = -EFAULT; + if (copy_from_user(&ip6rd, ifr->ifr_ifru.ifru_data, + sizeof(ip6rd))) + goto done; + + t = netdev_priv(dev); + + if (cmd != SIOCDEL6RD) { + struct in6_addr prefix; + __be32 relay_prefix; + + err = -EINVAL; + if (ip6rd.relay_prefixlen > 32 || + ip6rd.prefixlen + (32 - ip6rd.relay_prefixlen) > 64) + goto done; + + ipv6_addr_prefix(&prefix, &ip6rd.prefix, + ip6rd.prefixlen); + if (!ipv6_addr_equal(&prefix, &ip6rd.prefix)) + goto done; + if (ip6rd.relay_prefixlen) + relay_prefix = ip6rd.relay_prefix & + htonl(0xffffffffUL << + (32 - ip6rd.relay_prefixlen)); + else + relay_prefix = 0; + if (relay_prefix != ip6rd.relay_prefix) + goto done; + + ipv6_addr_copy(&t->ip6rd.prefix, &prefix); + t->ip6rd.relay_prefix = relay_prefix; + t->ip6rd.prefixlen = ip6rd.prefixlen; + t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen; + } else + ipip6_tunnel_clone_6rd(dev, sitn); + + err = 0; + break; +#endif + default: err = -EINVAL; } @@ -1030,7 +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; @@ -1055,33 +1143,27 @@ static struct xfrm_tunnel sit_handler = { .priority = 1, }; -static void sit_destroy_tunnels(struct sit_net *sitn) +static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) { int prio; for (prio = 1; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t; - while ((t = sitn->tunnels[prio][h]) != NULL) - unregister_netdevice(t->dev); + struct ip_tunnel *t = sitn->tunnels[prio][h]; + + while (t != NULL) { + unregister_netdevice_queue(t->dev, head); + t = t->next; + } } } } -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; - struct sit_net *sitn; - - err = -ENOMEM; - sitn = kzalloc(sizeof(struct sit_net), GFP_KERNEL); - if (sitn == NULL) - goto err_alloc; - - err = net_assign_generic(net, sit_net_id, sitn); - if (err < 0) - goto err_assign; sitn->tunnels[0] = sitn->tunnels_wc; sitn->tunnels[1] = sitn->tunnels_l; @@ -1097,6 +1179,7 @@ static int sit_init_net(struct net *net) dev_net_set(sitn->fb_tunnel_dev, net); ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); + ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn); if ((err = register_netdev(sitn->fb_tunnel_dev))) goto err_reg_dev; @@ -1107,35 +1190,34 @@ err_reg_dev: dev_put(sitn->fb_tunnel_dev); free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: - /* nothing */ -err_assign: - kfree(sitn); -err_alloc: return err; } -static void sit_exit_net(struct net *net) +static void __net_exit sit_exit_net(struct net *net) { - struct sit_net *sitn; + struct sit_net *sitn = net_generic(net, sit_net_id); + LIST_HEAD(list); - sitn = net_generic(net, sit_net_id); rtnl_lock(); - sit_destroy_tunnels(sitn); - unregister_netdevice(sitn->fb_tunnel_dev); + sit_destroy_tunnels(sitn, &list); + unregister_netdevice_queue(sitn->fb_tunnel_dev, &list); + unregister_netdevice_many(&list); rtnl_unlock(); - kfree(sitn); } static struct pernet_operations sit_net_ops = { .init = sit_init_net, .exit = sit_exit_net, + .id = &sit_net_id, + .size = sizeof(struct sit_net), }; static void __exit sit_cleanup(void) { xfrm4_tunnel_deregister(&sit_handler, AF_INET6); - unregister_pernet_gen_device(sit_net_id, &sit_net_ops); + unregister_pernet_device(&sit_net_ops); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } static int __init sit_init(void) @@ -1144,15 +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) { + err = register_pernet_device(&sit_net_ops); + if (err < 0) + 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 -EAGAIN; } - - err = register_pernet_gen_device(&sit_net_id, &sit_net_ops); - if (err < 0) - xfrm4_tunnel_deregister(&sit_handler, AF_INET6); - return err; } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 6b6ae913b5d4..34d1f0690d7e 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -159,6 +159,8 @@ static inline int cookie_check(struct sk_buff *skb, __u32 cookie) struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) { + struct tcp_options_received tcp_opt; + u8 *hash_location; struct inet_request_sock *ireq; struct inet6_request_sock *ireq6; struct tcp_request_sock *treq; @@ -171,7 +173,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) int mss; struct dst_entry *dst; __u8 rcv_wscale; - struct tcp_options_received tcp_opt; if (!sysctl_tcp_syncookies || !th->ack) goto out; @@ -186,7 +187,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0); if (tcp_opt.saw_tstamp) cookie_check_timestamp(&tcp_opt); @@ -252,8 +253,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) } ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr); fl.oif = sk->sk_bound_dev_if; + fl.mark = sk->sk_mark; fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_sk(sk)->sport; + fl.fl_ip_sport = inet_sk(sk)->inet_sport; security_req_classify_flow(req, &fl); if (ip6_dst_lookup(sk, &dst, &fl)) goto out_free; @@ -267,7 +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 0dc6a4e5ed4a..f841d93bf987 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -16,50 +16,46 @@ static ctl_table ipv6_table_template[] = { { - .ctl_name = NET_IPV6_ROUTE, .procname = "route", .maxlen = 0, .mode = 0555, .child = ipv6_route_table_template }, { - .ctl_name = NET_IPV6_ICMP, .procname = "icmp", .maxlen = 0, .mode = 0555, .child = ipv6_icmp_table_template }, { - .ctl_name = NET_IPV6_BINDV6ONLY, .procname = "bindv6only", .data = &init_net.ipv6.sysctl.bindv6only, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; static ctl_table ipv6_rotable[] = { { - .ctl_name = NET_IPV6_MLD_MAX_MSF, .procname = "mld_max_msf", .data = &sysctl_mld_max_msf, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; struct ctl_path net_ipv6_ctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ipv6", .ctl_name = NET_IPV6, }, + { .procname = "net", }, + { .procname = "ipv6", }, { }, }; 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; @@ -102,7 +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 21d100b68b19..9b6dbba80d31 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -96,7 +96,7 @@ static void tcp_v6_hash(struct sock *sk) return; } local_bh_disable(); - __inet6_hash(sk); + __inet6_hash(sk, NULL); local_bh_enable(); } } @@ -226,10 +226,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, #endif goto failure; } else { - ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF), - inet->saddr); - ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF), - inet->rcv_saddr); + ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); + ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, + &np->rcv_saddr); } return err; @@ -243,8 +242,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, ipv6_addr_copy(&fl.fl6_src, (saddr ? saddr : &np->saddr)); fl.oif = sk->sk_bound_dev_if; + fl.mark = sk->sk_mark; fl.fl_ip_dport = usin->sin6_port; - fl.fl_ip_sport = inet->sport; + fl.fl_ip_sport = inet->inet_sport; if (np->opt && np->opt->srcrt) { struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; @@ -276,7 +276,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, /* set the source address */ ipv6_addr_copy(&np->saddr, saddr); - inet->rcv_saddr = LOOPBACK4_IPV6; + inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; __ip6_dst_store(sk, dst, NULL, NULL); @@ -288,7 +288,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); - inet->dport = usin->sin6_port; + inet->inet_dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); err = inet6_hash_connect(&tcp_death_row, sk); @@ -298,8 +298,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (!tp->write_seq) tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, np->daddr.s6_addr32, - inet->sport, - inet->dport); + inet->inet_sport, + inet->inet_dport); err = tcp_connect(sk); if (err) @@ -311,7 +311,7 @@ late_failure: tcp_set_state(sk, TCP_CLOSE); __sk_dst_reset(sk); failure: - inet->dport = 0; + inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } @@ -383,8 +383,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, ipv6_addr_copy(&fl.fl6_dst, &np->daddr); ipv6_addr_copy(&fl.fl6_src, &np->saddr); fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; + fl.mark = sk->sk_mark; + fl.fl_ip_dport = inet->inet_dport; + fl.fl_ip_sport = inet->inet_sport; security_skb_classify_flow(skb, &fl); if ((err = ip6_dst_lookup(sk, &dst, &fl))) { @@ -460,7 +461,8 @@ out: } -static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) +static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, + struct request_values *rvp) { struct inet6_request_sock *treq = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); @@ -477,6 +479,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); fl.fl6_flowlabel = 0; fl.oif = treq->iif; + fl.mark = sk->sk_mark; fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_rsk(req)->loc_port; security_req_classify_flow(req, &fl); @@ -497,7 +500,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) goto done; - skb = tcp_make_synack(sk, dst, req); + skb = tcp_make_synack(sk, dst, req, rvp); if (skb) { struct tcphdr *th = tcp_hdr(skb); @@ -517,6 +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 @@ -873,7 +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)); @@ -887,10 +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 @@ -1159,11 +1170,13 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) */ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { + struct tcp_extend_values tmp_ext; + struct tcp_options_received tmp_opt; + u8 *hash_location; + struct request_sock *req; struct inet6_request_sock *treq; struct ipv6_pinfo *np = inet6_sk(sk); - struct tcp_options_received tmp_opt; struct tcp_sock *tp = tcp_sk(sk); - struct request_sock *req = NULL; __u32 isn = TCP_SKB_CB(skb)->when; #ifdef CONFIG_SYN_COOKIES int want_cookie = 0; @@ -1202,8 +1215,52 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); tmp_opt.user_mss = tp->rx_opt.user_mss; + tcp_parse_options(skb, &tmp_opt, &hash_location, 0); + + if (tmp_opt.cookie_plus > 0 && + tmp_opt.saw_tstamp && + !tp->rx_opt.cookie_out_never && + (sysctl_tcp_cookie_size > 0 || + (tp->cookie_values != NULL && + tp->cookie_values->cookie_desired > 0))) { + u8 *c; + u32 *d; + u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS]; + int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE; + + if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0) + goto drop_and_free; + + /* Secret recipe starts with IP addresses */ + d = &ipv6_hdr(skb)->daddr.s6_addr32[0]; + *mess++ ^= *d++; + *mess++ ^= *d++; + *mess++ ^= *d++; + *mess++ ^= *d++; + d = &ipv6_hdr(skb)->saddr.s6_addr32[0]; + *mess++ ^= *d++; + *mess++ ^= *d++; + *mess++ ^= *d++; + *mess++ ^= *d++; + + /* plus variable length Initiator Cookie */ + c = (u8 *)mess; + while (l-- > 0) + *c++ ^= *hash_location++; - tcp_parse_options(skb, &tmp_opt, 0); +#ifdef CONFIG_SYN_COOKIES + want_cookie = 0; /* not our kind of cookie */ +#endif + tmp_ext.cookie_out_never = 0; /* false */ + tmp_ext.cookie_plus = tmp_opt.cookie_plus; + } else if (!tp->rx_opt.cookie_in_always) { + /* redundant indications, but ensure initialization. */ + tmp_ext.cookie_out_never = 1; /* true */ + tmp_ext.cookie_plus = 0; + } else { + goto drop_and_free; + } + tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always; if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); @@ -1236,23 +1293,21 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) isn = tcp_v6_init_sequence(skb); } - tcp_rsk(req)->snt_isn = isn; security_inet_conn_request(sk, skb, req); - if (tcp_v6_send_synack(sk, req)) - goto drop; + if (tcp_v6_send_synack(sk, req, + (struct request_values *)&tmp_ext) || + want_cookie) + goto drop_and_free; - if (!want_cookie) { - inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); - return 0; - } + inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + return 0; +drop_and_free: + reqsk_free(req); drop: - if (req) - reqsk_free(req); - return 0; /* don't send reset */ } @@ -1290,11 +1345,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF), - newinet->daddr); + ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr); - ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF), - newinet->saddr); + ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); @@ -1345,6 +1398,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); fl.oif = sk->sk_bound_dev_if; + fl.mark = sk->sk_mark; fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_rsk(req)->loc_port; security_req_classify_flow(req, &fl); @@ -1431,7 +1485,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = dst_metric(dst, RTAX_ADVMSS); tcp_initialize_rcv_mss(newsk); - newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6; + newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; + newinet->inet_rcv_saddr = LOOPBACK4_IPV6; #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ @@ -1448,7 +1503,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } #endif - __inet6_hash(newsk); + __inet6_hash(newsk, NULL); __inet_inherit_port(sk, newsk); return newsk; @@ -1685,8 +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); @@ -1848,7 +1906,7 @@ static int tcp_v6_init_sock(struct sock *sk) */ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; - tp->mss_cache = 536; + tp->mss_cache = TCP_MSS_DEFAULT; tp->reordering = sysctl_tcp_reordering; @@ -1864,6 +1922,19 @@ static int tcp_v6_init_sock(struct sock *sk) tp->af_specific = &tcp_sock_ipv6_specific; #endif + /* TCP Cookie Transactions */ + if (sysctl_tcp_cookie_size > 0) { + /* Default, cookies without s_data_payload. */ + tp->cookie_values = + kzalloc(sizeof(*tp->cookie_values), + sk->sk_allocation); + if (tp->cookie_values != NULL) + kref_init(&tp->cookie_values->kref); + } + /* Presumed zeroed, in order of appearance: + * cookie_in_always, cookie_out_never, + * s_data_constant, s_data_in, s_data_out + */ sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; @@ -1931,8 +2002,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) dest = &np->daddr; src = &np->rcv_saddr; - destp = ntohs(inet->dport); - srcp = ntohs(inet->sport); + destp = ntohs(inet->inet_dport); + srcp = ntohs(inet->inet_sport); if (icsk->icsk_pending == ICSK_TIME_RETRANS) { timer_active = 1; @@ -2045,7 +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); } @@ -2109,27 +2180,31 @@ static struct inet_protosw tcpv6_protosw = { .protocol = IPPROTO_TCP, .prot = &tcpv6_prot, .ops = &inet6_stream_ops, - .capability = -1, .no_check = 0, .flags = INET_PROTOSW_PERMANENT | 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); - inet_twsk_purge(net, &tcp_hashinfo, &tcp_death_row, AF_INET6); +} + +static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET6); } static struct pernet_operations tcpv6_net_ops = { - .init = tcpv6_net_init, - .exit = tcpv6_net_exit, + .init = tcpv6_net_init, + .exit = tcpv6_net_exit, + .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 51e2832d13a6..e17bc1dfc1a4 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 b265b7047d3e..3c0c9c755c92 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -53,7 +53,7 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); - __be32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr; + __be32 sk1_rcv_saddr = inet_sk(sk)->inet_rcv_saddr; __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2); int sk_ipv6only = ipv6_only_sock(sk); int sk2_ipv6only = inet_v6_ipv6only(sk2); @@ -63,8 +63,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) /* if both are mapped, treat as IPv4 */ if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) return (!sk2_ipv6only && - (!sk_rcv_saddr || !sk2_rcv_saddr || - sk_rcv_saddr == sk2_rcv_saddr)); + (!sk1_rcv_saddr || !sk2_rcv_saddr || + sk1_rcv_saddr == sk2_rcv_saddr)); if (addr_type2 == IPV6_ADDR_ANY && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) @@ -81,9 +81,33 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) return 0; } +static unsigned int udp6_portaddr_hash(struct net *net, + const struct in6_addr *addr6, + unsigned int port) +{ + unsigned int hash, mix = net_hash_mix(net); + + if (ipv6_addr_any(addr6)) + hash = jhash_1word(0, mix); + else if (ipv6_addr_v4mapped(addr6)) + hash = jhash_1word(addr6->s6_addr32[3], mix); + else + hash = jhash2(addr6->s6_addr32, 4, mix); + + return hash ^ port; +} + + int udp_v6_get_port(struct sock *sk, unsigned short snum) { - return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal); + unsigned int hash2_nulladdr = + udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum); + unsigned int hash2_partial = + udp6_portaddr_hash(sock_net(sk), &inet6_sk(sk)->rcv_saddr, 0); + + /* precompute partial secondary hash */ + udp_sk(sk)->udp_portaddr_hash = hash2_partial; + return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr); } static inline int compute_score(struct sock *sk, struct net *net, @@ -94,14 +118,14 @@ static inline int compute_score(struct sock *sk, struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum && + if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && sk->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); score = 0; - if (inet->dport) { - if (inet->dport != sport) + if (inet->inet_dport) { + if (inet->inet_dport != sport) return -1; score++; } @@ -124,6 +148,86 @@ static inline int compute_score(struct sock *sk, struct net *net, return score; } +#define SCORE2_MAX (1 + 1 + 1) +static inline int compute_score2(struct sock *sk, struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, unsigned short hnum, + int dif) +{ + int score = -1; + + if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && + sk->sk_family == PF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + struct inet_sock *inet = inet_sk(sk); + + if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + return -1; + score = 0; + if (inet->inet_dport) { + if (inet->inet_dport != sport) + return -1; + score++; + } + if (!ipv6_addr_any(&np->daddr)) { + if (!ipv6_addr_equal(&np->daddr, saddr)) + return -1; + score++; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score++; + } + } + return score; +} + + +/* called with read_rcu_lock() */ +static struct sock *udp6_lib_lookup2(struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, unsigned int hnum, int dif, + struct udp_hslot *hslot2, unsigned int slot2) +{ + struct sock *sk, *result; + struct hlist_nulls_node *node; + int score, badness; + +begin: + result = NULL; + badness = -1; + udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { + score = compute_score2(sk, net, saddr, sport, + daddr, hnum, dif); + if (score > badness) { + result = sk; + badness = score; + if (score == SCORE2_MAX) + goto exact_match; + } + } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot2) + goto begin; + + if (result) { +exact_match: + if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + result = NULL; + else if (unlikely(compute_score2(result, net, saddr, sport, + daddr, hnum, dif) < badness)) { + sock_put(result); + goto begin; + } + } + return result; +} + static struct sock *__udp6_lib_lookup(struct net *net, struct in6_addr *saddr, __be16 sport, struct in6_addr *daddr, __be16 dport, @@ -132,11 +236,35 @@ static struct sock *__udp6_lib_lookup(struct net *net, struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); - unsigned int hash = udp_hashfn(net, hnum); - struct udp_hslot *hslot = &udptable->hash[hash]; + unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); + struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness; rcu_read_lock(); + if (hslot->count > 10) { + hash2 = udp6_portaddr_hash(net, daddr, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + if (hslot->count < hslot2->count) + goto begin; + + result = udp6_lib_lookup2(net, saddr, sport, + daddr, hnum, dif, + hslot2, slot2); + if (!result) { + hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + if (hslot->count < hslot2->count) + goto begin; + + result = udp6_lib_lookup2(net, &in6addr_any, sport, + daddr, hnum, dif, + hslot2, slot2); + } + rcu_read_unlock(); + return result; + } begin: result = NULL; badness = -1; @@ -152,7 +280,7 @@ begin: * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ - if (get_nulls_value(node) != hash) + if (get_nulls_value(node) != slot) goto begin; if (result) { @@ -194,7 +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); @@ -213,10 +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)); @@ -227,14 +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) @@ -252,7 +379,7 @@ try_again: UDP_MIB_INDATAGRAMS, is_udplite); } - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); /* Copy the address. */ if (msg->msg_name) { @@ -265,8 +392,8 @@ try_again: sin6->sin6_scope_id = 0; if (is_udp4) - ipv6_addr_set(&sin6->sin6_addr, 0, 0, - htonl(0xffff), ip_hdr(skb)->saddr); + ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, + &sin6->sin6_addr); else { ipv6_addr_copy(&sin6->sin6_addr, &ipv6_hdr(skb)->saddr); @@ -283,14 +410,12 @@ try_again: datagram_recv_ctl(sk, msg, skb); } - err = copied; + err = len; if (flags & MSG_TRUNC) err = ulen; out_free: - lock_sock(sk); - skb_free_datagram(sk, skb); - release_sock(sk); + skb_free_datagram_locked(sk, skb); out: return err; @@ -385,18 +510,18 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) goto drop; } - if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { + if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) { /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) { + if (rc == -ENOMEM) UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); - atomic_inc(&sk->sk_drops); - } - goto drop; + goto drop_no_sk_drops_inc; } return 0; drop: + atomic_inc(&sk->sk_drops); +drop_no_sk_drops_inc: UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); return -1; @@ -417,10 +542,11 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, if (!net_eq(sock_net(s), net)) continue; - if (s->sk_hash == num && s->sk_family == PF_INET6) { + if (udp_sk(s)->udp_port_hash == num && + s->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(s); - if (inet->dport) { - if (inet->dport != rmt_port) + if (inet->inet_dport) { + if (inet->inet_dport != rmt_port) continue; } if (!ipv6_addr_any(&np->daddr) && @@ -442,6 +568,37 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, return NULL; } +static void flush_stack(struct sock **stack, unsigned int count, + struct sk_buff *skb, unsigned int final) +{ + unsigned int i; + struct sock *sk; + struct sk_buff *skb1; + + for (i = 0; i < count; i++) { + skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); + + sk = stack[i]; + if (skb1) { + bh_lock_sock(sk); + if (!sock_owned_by_user(sk)) + udpv6_queue_rcv_skb(sk, skb1); + else if (sk_add_backlog(sk, skb1)) { + kfree_skb(skb1); + bh_unlock_sock(sk); + goto drop; + } + bh_unlock_sock(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)); + } +} /* * Note: called only from the BH handler context, * so we don't need to lock the hashes. @@ -450,41 +607,43 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct in6_addr *saddr, struct in6_addr *daddr, struct udp_table *udptable) { - struct sock *sk, *sk2; + struct sock *sk, *stack[256 / sizeof(struct sock *)]; const struct udphdr *uh = udp_hdr(skb); - struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))]; + struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest)); int dif; + unsigned int i, count = 0; spin_lock(&hslot->lock); sk = sk_nulls_head(&hslot->head); dif = inet6_iif(skb); sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); - if (!sk) { - kfree_skb(skb); - goto out; - } - - sk2 = sk; - while ((sk2 = udp_v6_mcast_next(net, sk_nulls_next(sk2), uh->dest, daddr, - uh->source, saddr, dif))) { - struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC); - if (buff) { - bh_lock_sock(sk2); - if (!sock_owned_by_user(sk2)) - udpv6_queue_rcv_skb(sk2, buff); - else - sk_add_backlog(sk2, buff); - bh_unlock_sock(sk2); + while (sk) { + stack[count++] = sk; + sk = udp_v6_mcast_next(net, sk_nulls_next(sk), uh->dest, daddr, + uh->source, saddr, dif); + if (unlikely(count == ARRAY_SIZE(stack))) { + if (!sk) + break; + flush_stack(stack, count, skb, ~0); + count = 0; } } - bh_lock_sock(sk); - if (!sock_owned_by_user(sk)) - udpv6_queue_rcv_skb(sk, skb); - else - sk_add_backlog(sk, skb); - bh_unlock_sock(sk); -out: + /* + * before releasing the lock, we must take reference on sockets + */ + for (i = 0; i < count; i++) + sock_hold(stack[i]); + spin_unlock(&hslot->lock); + + if (count) { + flush_stack(stack, count, skb, count - 1); + + for (i = 0; i < count; i++) + sock_put(stack[i]); + } else { + kfree_skb(skb); + } return 0; } @@ -525,12 +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; @@ -589,7 +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; @@ -600,8 +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; @@ -794,7 +956,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (ipv6_addr_v4mapped(daddr)) { struct sockaddr_in sin; sin.sin_family = AF_INET; - sin.sin_port = sin6 ? sin6->sin6_port : inet->dport; + sin.sin_port = sin6 ? sin6->sin6_port : inet->inet_dport; sin.sin_addr.s_addr = daddr->s6_addr32[3]; msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); @@ -867,7 +1029,7 @@ do_udp_sendmsg: if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - fl.fl_ip_dport = inet->dport; + fl.fl_ip_dport = inet->inet_dport; daddr = &np->daddr; fl.fl6_flowlabel = np->flow_label; connected = 1; @@ -879,6 +1041,8 @@ do_udp_sendmsg: if (!fl.oif) fl.oif = np->sticky_pktinfo.ipi6_ifindex; + fl.mark = sk->sk_mark; + if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); @@ -911,7 +1075,7 @@ do_udp_sendmsg: fl.fl6_dst.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr)) ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.fl_ip_sport = inet->sport; + fl.fl_ip_sport = inet->inet_sport; /* merge ip6_build_xmit from ip6_output */ if (opt && opt->srcrt) { @@ -1044,7 +1208,7 @@ void udpv6_destroy_sock(struct sock *sk) * Socket option code for UDP */ int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, @@ -1054,7 +1218,7 @@ int udpv6_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, @@ -1192,10 +1356,10 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket dest = &np->daddr; src = &np->rcv_saddr; - destp = ntohs(inet->dport); - srcp = ntohs(inet->sport); + destp = ntohs(inet->inet_dport); + srcp = ntohs(inet->inet_sport); seq_printf(seq, - "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " + "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", bucket, src->s6_addr32[0], src->s6_addr32[1], @@ -1238,7 +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); } @@ -1284,7 +1448,6 @@ static struct inet_protosw udpv6_protosw = { .protocol = IPPROTO_UDP, .prot = &udpv6_prot, .ops = &inet6_dgram_ops, - .capability =-1, .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_PERMANENT, }; diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 6bb303471e20..d7571046bfc4 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -16,10 +16,10 @@ extern int udp_v6_get_port(struct sock *sk, unsigned short snum); extern int udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); #ifdef CONFIG_COMPAT extern int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #endif diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index d737a27ee010..5f48fadc27f7 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -62,7 +62,6 @@ static struct inet_protosw udplite6_protosw = { .protocol = IPPROTO_UDPLITE, .prot = &udplitev6_prot, .ops = &inet6_dgram_ops, - .capability = -1, .no_check = 0, .flags = INET_PROTOSW_PERMANENT, }; @@ -105,12 +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 9084582d236b..2bc98ede1235 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 c4f4eef032a3..0c92112dcba3 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 8ec3d45cd1d9..ae181651c75a 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) @@ -309,9 +311,8 @@ static void xfrm6_policy_fini(void) #ifdef CONFIG_SYSCTL static struct ctl_table xfrm6_policy_table[] = { { - .ctl_name = CTL_UNNUMBERED, .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, @@ -327,13 +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 @@ -347,6 +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 81a95c00e503..fa85a7d22dc4 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -23,41 +23,50 @@ */ #include <linux/module.h> #include <linux/xfrm.h> -#include <linux/list.h> +#include <linux/rculist.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/ipv6.h> #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") * per xfrm_address_t. */ struct xfrm6_tunnel_spi { - struct hlist_node list_byaddr; - struct hlist_node list_byspi; - xfrm_address_t addr; - u32 spi; - atomic_t refcnt; + struct hlist_node list_byaddr; + struct hlist_node list_byspi; + xfrm_address_t addr; + u32 spi; + atomic_t refcnt; + struct rcu_head rcu_head; }; -static DEFINE_RWLOCK(xfrm6_tunnel_spi_lock); - -static u32 xfrm6_tunnel_spi; - -#define XFRM6_TUNNEL_SPI_MIN 1 -#define XFRM6_TUNNEL_SPI_MAX 0xffffffff +static DEFINE_SPINLOCK(xfrm6_tunnel_spi_lock); 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; @@ -75,49 +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; - } - 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(x6spi, pos, - &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], + hlist_for_each_entry_rcu(x6spi, pos, + &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) return x6spi; @@ -126,28 +100,29 @@ 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; - read_lock_bh(&xfrm6_tunnel_spi_lock); - x6spi = __xfrm6_tunnel_spi_lookup(saddr); + rcu_read_lock_bh(); + x6spi = __xfrm6_tunnel_spi_lookup(net, saddr); spi = x6spi ? x6spi->spi : 0; - read_unlock_bh(&xfrm6_tunnel_spi_lock); + rcu_read_unlock_bh(); return htonl(spi); } 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; @@ -155,32 +130,33 @@ 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; @@ -189,54 +165,61 @@ alloc_spi: x6spi->spi = spi; atomic_set(&x6spi->refcnt, 1); - hlist_add_head(&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(&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; - write_lock_bh(&xfrm6_tunnel_spi_lock); - x6spi = __xfrm6_tunnel_spi_lookup(saddr); + spin_lock_bh(&xfrm6_tunnel_spi_lock); + x6spi = __xfrm6_tunnel_spi_lookup(net, saddr); if (x6spi) { atomic_inc(&x6spi->refcnt); spi = x6spi->spi; } else - spi = __xfrm6_tunnel_alloc_spi(saddr); - write_unlock_bh(&xfrm6_tunnel_spi_lock); + spi = __xfrm6_tunnel_alloc_spi(net, saddr); + spin_unlock_bh(&xfrm6_tunnel_spi_lock); return htonl(spi); } EXPORT_SYMBOL(xfrm6_tunnel_alloc_spi); -void xfrm6_tunnel_free_spi(xfrm_address_t *saddr) +static void x6spi_destroy_rcu(struct rcu_head *head) +{ + kmem_cache_free(xfrm6_tunnel_spi_kmem, + container_of(head, struct xfrm6_tunnel_spi, rcu_head)); +} + +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; - write_lock_bh(&xfrm6_tunnel_spi_lock); + 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) { if (atomic_dec_and_test(&x6spi->refcnt)) { - hlist_del(&x6spi->list_byaddr); - hlist_del(&x6spi->list_byspi); - kmem_cache_free(xfrm6_tunnel_spi_kmem, x6spi); + hlist_del_rcu(&x6spi->list_byaddr); + hlist_del_rcu(&x6spi->list_byspi); + call_rcu(&x6spi->rcu_head, x6spi_destroy_rcu); break; } } } - write_unlock_bh(&xfrm6_tunnel_spi_lock); + spin_unlock_bh(&xfrm6_tunnel_spi_lock); } EXPORT_SYMBOL(xfrm6_tunnel_free_spi); @@ -254,10 +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; } @@ -317,7 +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 = { @@ -342,34 +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); |