diff options
Diffstat (limited to 'net/ipv6')
42 files changed, 1756 insertions, 1223 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index a578096152a..36d7437ac05 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -229,6 +229,20 @@ config IPV6_MROUTE Experimental support for IPv6 multicast forwarding. If unsure, say N. +config IPV6_MROUTE_MULTIPLE_TABLES + bool "IPv6: multicast policy routing" + depends on IPV6_MROUTE + select FIB_RULES + help + Normally, a multicast router runs a userspace daemon and decides + what to do with a multicast packet based on the source and + destination addresses. If you say Y here, the multicast router + will also be able to take interfaces and packet marks into + account and run multiple instances of userspace daemons + simultaneously, each one handling a single table. + + If unsure, say N. + config IPV6_PIMSM_V2 bool "IPv6: PIM-SM version 2 support (EXPERIMENTAL)" depends on IPV6_MROUTE diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 413054f02aa..e1a698df570 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -82,7 +82,7 @@ #include <linux/random.h> #endif -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/unaligned.h> #include <linux/proc_fs.h> @@ -98,7 +98,11 @@ #endif #define INFINITY_LIFE_TIME 0xFFFFFFFF -#define TIME_DELTA(a,b) ((unsigned long)((long)(a) - (long)(b))) +#define TIME_DELTA(a, b) ((unsigned long)((long)(a) - (long)(b))) + +#define ADDRCONF_TIMER_FUZZ_MINUS (HZ > 50 ? HZ/50 : 1) +#define ADDRCONF_TIMER_FUZZ (HZ / 4) +#define ADDRCONF_TIMER_FUZZ_MAX (HZ) #ifdef CONFIG_SYSCTL static void addrconf_sysctl_register(struct inet6_dev *idev); @@ -127,8 +131,8 @@ static int ipv6_count_addresses(struct inet6_dev *idev); /* * Configured unicast address hash table */ -static struct inet6_ifaddr *inet6_addr_lst[IN6_ADDR_HSIZE]; -static DEFINE_RWLOCK(addrconf_hash_lock); +static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE]; +static DEFINE_SPINLOCK(addrconf_hash_lock); static void addrconf_verify(unsigned long); @@ -138,8 +142,8 @@ static DEFINE_SPINLOCK(addrconf_verify_lock); static void addrconf_join_anycast(struct inet6_ifaddr *ifp); static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); -static void addrconf_bonding_change(struct net_device *dev, - unsigned long event); +static void addrconf_type_change(struct net_device *dev, + unsigned long event); static int addrconf_ifdown(struct net_device *dev, int how); static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags); @@ -152,8 +156,8 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo); -static int ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, - struct net_device *dev); +static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, + struct net_device *dev); static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); @@ -250,8 +254,7 @@ static void addrconf_del_timer(struct inet6_ifaddr *ifp) __in6_ifa_put(ifp); } -enum addrconf_timer_t -{ +enum addrconf_timer_t { AC_NONE, AC_DAD, AC_RS, @@ -271,7 +274,8 @@ static void addrconf_mod_timer(struct inet6_ifaddr *ifp, case AC_RS: ifp->timer.function = addrconf_rs_timer; break; - default:; + default: + break; } ifp->timer.expires = jiffies + when; add_timer(&ifp->timer); @@ -318,7 +322,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev) { struct net_device *dev = idev->dev; - WARN_ON(idev->addr_list != NULL); + WARN_ON(!list_empty(&idev->addr_list)); WARN_ON(idev->mc_list != NULL); #ifdef NET_REFCNT_DEBUG @@ -326,7 +330,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev) #endif dev_put(dev); if (!idev->dead) { - printk("Freeing alive inet6 device %p\n", idev); + pr_warning("Freeing alive inet6 device %p\n", idev); return; } snmp6_free_dev(idev); @@ -351,6 +355,8 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) rwlock_init(&ndev->lock); ndev->dev = dev; + INIT_LIST_HEAD(&ndev->addr_list); + memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf)); ndev->cnf.mtu6 = dev->mtu; ndev->cnf.sysctl = NULL; @@ -402,6 +408,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) #endif #ifdef CONFIG_IPV6_PRIVACY + INIT_LIST_HEAD(&ndev->tempaddr_list); setup_timer(&ndev->regen_timer, ipv6_regen_rndid, (unsigned long)ndev); if ((dev->flags&IFF_LOOPBACK) || dev->type == ARPHRD_TUNNEL || @@ -439,8 +446,10 @@ static struct inet6_dev * ipv6_find_idev(struct net_device *dev) ASSERT_RTNL(); - if ((idev = __in6_dev_get(dev)) == NULL) { - if ((idev = ipv6_add_dev(dev)) == NULL) + idev = __in6_dev_get(dev); + if (!idev) { + idev = ipv6_add_dev(dev); + if (!idev) return NULL; } @@ -466,7 +475,8 @@ static void dev_forward_change(struct inet6_dev *idev) else ipv6_dev_mc_dec(dev, &in6addr_linklocal_allrouters); } - for (ifa=idev->addr_list; ifa; ifa=ifa->if_next) { + + list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa->flags&IFA_F_TENTATIVE) continue; if (idev->cnf.forwarding) @@ -523,12 +533,16 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) } #endif -/* Nobody refers to this ifaddr, destroy it */ +static void inet6_ifa_finish_destroy_rcu(struct rcu_head *head) +{ + struct inet6_ifaddr *ifp = container_of(head, struct inet6_ifaddr, rcu); + kfree(ifp); +} +/* Nobody refers to this ifaddr, destroy it */ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) { - WARN_ON(ifp->if_next != NULL); - WARN_ON(ifp->lst_next != NULL); + WARN_ON(!hlist_unhashed(&ifp->addr_lst)); #ifdef NET_REFCNT_DEBUG printk(KERN_DEBUG "inet6_ifa_finish_destroy\n"); @@ -537,54 +551,46 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) in6_dev_put(ifp->idev); if (del_timer(&ifp->timer)) - printk("Timer is still running, when freeing ifa=%p\n", ifp); + pr_notice("Timer is still running, when freeing ifa=%p\n", ifp); - if (!ifp->dead) { - printk("Freeing alive inet6 address %p\n", ifp); + if (ifp->state != INET6_IFADDR_STATE_DEAD) { + pr_warning("Freeing alive inet6 address %p\n", ifp); return; } dst_release(&ifp->rt->u.dst); - kfree(ifp); + call_rcu(&ifp->rcu, inet6_ifa_finish_destroy_rcu); } static void ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) { - struct inet6_ifaddr *ifa, **ifap; + struct list_head *p; int ifp_scope = ipv6_addr_src_scope(&ifp->addr); /* * Each device address list is sorted in order of scope - * global before linklocal. */ - for (ifap = &idev->addr_list; (ifa = *ifap) != NULL; - ifap = &ifa->if_next) { + list_for_each(p, &idev->addr_list) { + struct inet6_ifaddr *ifa + = list_entry(p, struct inet6_ifaddr, if_list); if (ifp_scope >= ipv6_addr_src_scope(&ifa->addr)) break; } - ifp->if_next = *ifap; - *ifap = ifp; + list_add_tail(&ifp->if_list, p); } -/* - * Hash function taken from net_alias.c - */ -static u8 ipv6_addr_hash(const struct in6_addr *addr) +static u32 ipv6_addr_hash(const struct in6_addr *addr) { - __u32 word; - /* * We perform the hash function over the last 64 bits of the address * This will include the IEEE address token on links that support it. */ - - word = (__force u32)(addr->s6_addr32[2] ^ addr->s6_addr32[3]); - word ^= (word >> 16); - word ^= (word >> 8); - - return ((word ^ (word >> 4)) & 0x0f); + return jhash_2words((__force u32)addr->s6_addr32[2], + (__force u32)addr->s6_addr32[3], 0) + & (IN6_ADDR_HSIZE - 1); } /* On success it returns ifp with increased reference count */ @@ -595,7 +601,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, { struct inet6_ifaddr *ifa = NULL; struct rt6_info *rt; - int hash; + unsigned int hash; int err = 0; int addr_type = ipv6_addr_type(addr); @@ -616,7 +622,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, goto out2; } - write_lock(&addrconf_hash_lock); + spin_lock(&addrconf_hash_lock); /* Ignore adding duplicate addresses on an interface */ if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) { @@ -642,7 +648,9 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, ipv6_addr_copy(&ifa->addr, addr); spin_lock_init(&ifa->lock); + spin_lock_init(&ifa->state_lock); init_timer(&ifa->timer); + INIT_HLIST_NODE(&ifa->addr_lst); ifa->timer.data = (unsigned long) ifa; ifa->scope = scope; ifa->prefix_len = pfxlen; @@ -669,10 +677,8 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, /* Add to big hash table */ hash = ipv6_addr_hash(addr); - ifa->lst_next = inet6_addr_lst[hash]; - inet6_addr_lst[hash] = ifa; - in6_ifa_hold(ifa); - write_unlock(&addrconf_hash_lock); + hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); + spin_unlock(&addrconf_hash_lock); write_lock(&idev->lock); /* Add to inet6_dev unicast addr list. */ @@ -680,8 +686,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, #ifdef CONFIG_IPV6_PRIVACY if (ifa->flags&IFA_F_TEMPORARY) { - ifa->tmp_next = idev->tempaddr_list; - idev->tempaddr_list = ifa; + list_add(&ifa->tmp_list, &idev->tempaddr_list); in6_ifa_hold(ifa); } #endif @@ -700,7 +705,7 @@ out2: return ifa; out: - write_unlock(&addrconf_hash_lock); + spin_unlock(&addrconf_hash_lock); goto out2; } @@ -708,52 +713,44 @@ out: static void ipv6_del_addr(struct inet6_ifaddr *ifp) { - struct inet6_ifaddr *ifa, **ifap; + struct inet6_ifaddr *ifa, *ifn; struct inet6_dev *idev = ifp->idev; + int state; int hash; int deleted = 0, onlink = 0; unsigned long expires = jiffies; hash = ipv6_addr_hash(&ifp->addr); - ifp->dead = 1; + spin_lock_bh(&ifp->state_lock); + state = ifp->state; + ifp->state = INET6_IFADDR_STATE_DEAD; + spin_unlock_bh(&ifp->state_lock); - write_lock_bh(&addrconf_hash_lock); - for (ifap = &inet6_addr_lst[hash]; (ifa=*ifap) != NULL; - ifap = &ifa->lst_next) { - if (ifa == ifp) { - *ifap = ifa->lst_next; - __in6_ifa_put(ifp); - ifa->lst_next = NULL; - break; - } - } - write_unlock_bh(&addrconf_hash_lock); + if (state == INET6_IFADDR_STATE_DEAD) + goto out; + + spin_lock_bh(&addrconf_hash_lock); + hlist_del_init_rcu(&ifp->addr_lst); + spin_unlock_bh(&addrconf_hash_lock); write_lock_bh(&idev->lock); #ifdef CONFIG_IPV6_PRIVACY if (ifp->flags&IFA_F_TEMPORARY) { - for (ifap = &idev->tempaddr_list; (ifa=*ifap) != NULL; - ifap = &ifa->tmp_next) { - if (ifa == ifp) { - *ifap = ifa->tmp_next; - if (ifp->ifpub) { - in6_ifa_put(ifp->ifpub); - ifp->ifpub = NULL; - } - __in6_ifa_put(ifp); - ifa->tmp_next = NULL; - break; - } + list_del(&ifp->tmp_list); + if (ifp->ifpub) { + in6_ifa_put(ifp->ifpub); + ifp->ifpub = NULL; } + __in6_ifa_put(ifp); } #endif - for (ifap = &idev->addr_list; (ifa=*ifap) != NULL;) { + list_for_each_entry_safe(ifa, ifn, &idev->addr_list, if_list) { if (ifa == ifp) { - *ifap = ifa->if_next; + list_del_init(&ifp->if_list); __in6_ifa_put(ifp); - ifa->if_next = NULL; + if (!(ifp->flags & IFA_F_PERMANENT) || onlink > 0) break; deleted = 1; @@ -786,7 +783,6 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) } } } - ifap = &ifa->if_next; } write_unlock_bh(&idev->lock); @@ -830,6 +826,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) dst_release(&rt->u.dst); } +out: in6_ifa_put(ifp); } @@ -1165,7 +1162,7 @@ int ipv6_dev_get_saddr(struct net *net, struct net_device *dst_dev, continue; read_lock_bh(&idev->lock); - for (score->ifa = idev->addr_list; score->ifa; score->ifa = score->ifa->if_next) { + list_for_each_entry(score->ifa, &idev->addr_list, if_list) { int i; /* @@ -1243,7 +1240,6 @@ try_nextdev: in6_ifa_put(hiscore->ifa); return 0; } - EXPORT_SYMBOL(ipv6_dev_get_saddr); int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, @@ -1253,12 +1249,14 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, int err = -EADDRNOTAVAIL; rcu_read_lock(); - if ((idev = __in6_dev_get(dev)) != NULL) { + idev = __in6_dev_get(dev); + if (idev) { struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) { - if (ifp->scope == IFA_LINK && !(ifp->flags & banned_flags)) { + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if (ifp->scope == IFA_LINK && + !(ifp->flags & banned_flags)) { ipv6_addr_copy(addr, &ifp->addr); err = 0; break; @@ -1276,7 +1274,7 @@ static int ipv6_count_addresses(struct inet6_dev *idev) struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) + list_for_each_entry(ifp, &idev->addr_list, if_list) cnt++; read_unlock_bh(&idev->lock); return cnt; @@ -1285,41 +1283,44 @@ static int ipv6_count_addresses(struct inet6_dev *idev) int ipv6_chk_addr(struct net *net, struct in6_addr *addr, struct net_device *dev, int strict) { - struct inet6_ifaddr * ifp; - u8 hash = ipv6_addr_hash(addr); + struct inet6_ifaddr *ifp; + struct hlist_node *node; + unsigned int hash = ipv6_addr_hash(addr); - read_lock_bh(&addrconf_hash_lock); - for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { + rcu_read_lock_bh(); + hlist_for_each_entry_rcu(ifp, node, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && - !(ifp->flags&IFA_F_TENTATIVE)) { - if (dev == NULL || ifp->idev->dev == dev || - !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) - break; + !(ifp->flags&IFA_F_TENTATIVE) && + (dev == NULL || ifp->idev->dev == dev || + !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) { + rcu_read_unlock_bh(); + return 1; } } - read_unlock_bh(&addrconf_hash_lock); - return ifp != NULL; + + rcu_read_unlock_bh(); + return 0; } EXPORT_SYMBOL(ipv6_chk_addr); -static -int ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, - struct net_device *dev) +static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, + struct net_device *dev) { - struct inet6_ifaddr * ifp; - u8 hash = ipv6_addr_hash(addr); + unsigned int hash = ipv6_addr_hash(addr); + struct inet6_ifaddr *ifp; + struct hlist_node *node; - for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { + hlist_for_each_entry(ifp, node, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { if (dev == NULL || ifp->idev->dev == dev) - break; + return true; } } - return ifp != NULL; + return false; } int ipv6_chk_prefix(struct in6_addr *addr, struct net_device *dev) @@ -1333,7 +1334,7 @@ int ipv6_chk_prefix(struct in6_addr *addr, struct net_device *dev) idev = __in6_dev_get(dev); if (idev) { read_lock_bh(&idev->lock); - for (ifa = idev->addr_list; ifa; ifa = ifa->if_next) { + list_for_each_entry(ifa, &idev->addr_list, if_list) { onlink = ipv6_prefix_equal(addr, &ifa->addr, ifa->prefix_len); if (onlink) @@ -1350,24 +1351,26 @@ EXPORT_SYMBOL(ipv6_chk_prefix); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict) { - struct inet6_ifaddr * ifp; - u8 hash = ipv6_addr_hash(addr); + struct inet6_ifaddr *ifp, *result = NULL; + unsigned int hash = ipv6_addr_hash(addr); + struct hlist_node *node; - read_lock_bh(&addrconf_hash_lock); - for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { + rcu_read_lock_bh(); + hlist_for_each_entry_rcu_bh(ifp, node, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { if (dev == NULL || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { + result = ifp; in6_ifa_hold(ifp); break; } } } - read_unlock_bh(&addrconf_hash_lock); + rcu_read_unlock_bh(); - return ifp; + return result; } /* Gets referenced address, destroys ifaddr */ @@ -1403,10 +1406,27 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) ipv6_del_addr(ifp); } +static int addrconf_dad_end(struct inet6_ifaddr *ifp) +{ + int err = -ENOENT; + + spin_lock(&ifp->state_lock); + if (ifp->state == INET6_IFADDR_STATE_DAD) { + ifp->state = INET6_IFADDR_STATE_POSTDAD; + err = 0; + } + spin_unlock(&ifp->state_lock); + + return err; +} + void addrconf_dad_failure(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; + if (addrconf_dad_end(ifp)) + return; + if (net_ratelimit()) printk(KERN_INFO "%s: IPv6 duplicate address %pI6c detected!\n", ifp->idev->dev->name, &ifp->addr); @@ -1570,7 +1590,7 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev) struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) { + list_for_each_entry(ifp, &idev->addr_list, if_list) { if (ifp->scope == IFA_LINK && !(ifp->flags&IFA_F_TENTATIVE)) { memcpy(eui, ifp->addr.s6_addr+8, 8); err = 0; @@ -1738,7 +1758,8 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev) ASSERT_RTNL(); - if ((idev = ipv6_find_idev(dev)) == NULL) + idev = ipv6_find_idev(dev); + if (!idev) return NULL; /* Add default multicast route */ @@ -1971,7 +1992,7 @@ ok: #ifdef CONFIG_IPV6_PRIVACY read_lock_bh(&in6_dev->lock); /* update all temporary addresses in the list */ - for (ift=in6_dev->tempaddr_list; ift; ift=ift->tmp_next) { + list_for_each_entry(ift, &in6_dev->tempaddr_list, tmp_list) { /* * When adjusting the lifetimes of an existing * temporary address, only lower the lifetimes. @@ -2174,7 +2195,7 @@ static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx, return -ENXIO; read_lock_bh(&idev->lock); - for (ifp = idev->addr_list; ifp; ifp=ifp->if_next) { + list_for_each_entry(ifp, &idev->addr_list, if_list) { if (ifp->prefix_len == plen && ipv6_addr_equal(pfx, &ifp->addr)) { in6_ifa_hold(ifp); @@ -2185,7 +2206,7 @@ static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx, /* If the last address is deleted administratively, disable IPv6 on this interface. */ - if (idev->addr_list == NULL) + if (list_empty(&idev->addr_list)) addrconf_ifdown(idev->dev, 1); return 0; } @@ -2446,7 +2467,8 @@ static void addrconf_ip6_tnl_config(struct net_device *dev) ASSERT_RTNL(); - if ((idev = addrconf_add_dev(dev)) == NULL) { + idev = addrconf_add_dev(dev); + if (!idev) { printk(KERN_DEBUG "init ip6-ip6: add_dev failed\n"); return; } @@ -2461,7 +2483,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, int run_pending = 0; int err; - switch(event) { + switch (event) { case NETDEV_REGISTER: if (!idev && dev->mtu >= IPV6_MIN_MTU) { idev = ipv6_add_dev(dev); @@ -2469,6 +2491,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, return notifier_from_errno(-ENOMEM); } break; + case NETDEV_UP: case NETDEV_CHANGE: if (dev->flags & IFF_SLAVE) @@ -2498,10 +2521,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, } if (idev) { - if (idev->if_flags & IF_READY) { + if (idev->if_flags & IF_READY) /* device is already configured. */ break; - } idev->if_flags |= IF_READY; } @@ -2513,7 +2535,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } - switch(dev->type) { + switch (dev->type) { #if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) case ARPHRD_SIT: addrconf_sit_config(dev); @@ -2530,25 +2552,30 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, addrconf_dev_config(dev); break; } + if (idev) { if (run_pending) addrconf_dad_run(idev); - /* If the MTU changed during the interface down, when the - interface up, the changed MTU must be reflected in the - idev as well as routers. + /* + * If the MTU changed during the interface down, + * when the interface up, the changed MTU must be + * reflected in the idev as well as routers. */ - if (idev->cnf.mtu6 != dev->mtu && dev->mtu >= IPV6_MIN_MTU) { + if (idev->cnf.mtu6 != dev->mtu && + dev->mtu >= IPV6_MIN_MTU) { rt6_mtu_change(dev, dev->mtu); idev->cnf.mtu6 = dev->mtu; } idev->tstamp = jiffies; inet6_ifinfo_notify(RTM_NEWLINK, idev); - /* If the changed mtu during down is lower than IPV6_MIN_MTU - stop IPv6 on this interface. + + /* + * If the changed mtu during down is lower than + * IPV6_MIN_MTU stop IPv6 on this interface. */ if (dev->mtu < IPV6_MIN_MTU) - addrconf_ifdown(dev, event != NETDEV_DOWN); + addrconf_ifdown(dev, 1); } break; @@ -2565,7 +2592,10 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, break; } - /* MTU falled under IPV6_MIN_MTU. Stop IPv6 on this interface. */ + /* + * MTU falled under IPV6_MIN_MTU. + * Stop IPv6 on this interface. + */ case NETDEV_DOWN: case NETDEV_UNREGISTER: @@ -2585,9 +2615,10 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, return notifier_from_errno(err); } break; - case NETDEV_BONDING_OLDTYPE: - case NETDEV_BONDING_NEWTYPE: - addrconf_bonding_change(dev, event); + + case NETDEV_PRE_TYPE_CHANGE: + case NETDEV_POST_TYPE_CHANGE: + addrconf_type_change(dev, event); break; } @@ -2599,28 +2630,28 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, */ static struct notifier_block ipv6_dev_notf = { .notifier_call = addrconf_notify, - .priority = 0 }; -static void addrconf_bonding_change(struct net_device *dev, unsigned long event) +static void addrconf_type_change(struct net_device *dev, unsigned long event) { struct inet6_dev *idev; ASSERT_RTNL(); idev = __in6_dev_get(dev); - if (event == NETDEV_BONDING_NEWTYPE) + if (event == NETDEV_POST_TYPE_CHANGE) ipv6_mc_remap(idev); - else if (event == NETDEV_BONDING_OLDTYPE) + else if (event == NETDEV_PRE_TYPE_CHANGE) ipv6_mc_unmap(idev); } static int addrconf_ifdown(struct net_device *dev, int how) { - struct inet6_dev *idev; - struct inet6_ifaddr *ifa, *keep_list, **bifa; struct net *net = dev_net(dev); - int i; + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + LIST_HEAD(keep_list); + int state; ASSERT_RTNL(); @@ -2631,8 +2662,9 @@ static int addrconf_ifdown(struct net_device *dev, int how) if (idev == NULL) return -ENODEV; - /* Step 1: remove reference to ipv6 device from parent device. - Do not dev_put! + /* + * Step 1: remove reference to ipv6 device from parent device. + * Do not dev_put! */ if (how) { idev->dead = 1; @@ -2645,41 +2677,21 @@ static int addrconf_ifdown(struct net_device *dev, int how) } - /* Step 2: clear hash table */ - for (i=0; i<IN6_ADDR_HSIZE; i++) { - bifa = &inet6_addr_lst[i]; - - write_lock_bh(&addrconf_hash_lock); - while ((ifa = *bifa) != NULL) { - 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; - __in6_ifa_put(ifa); - continue; - } - bifa = &ifa->lst_next; - } - write_unlock_bh(&addrconf_hash_lock); - } - write_lock_bh(&idev->lock); - /* Step 3: clear flags for stateless addrconf */ + /* Step 2: clear flags for stateless addrconf */ if (!how) idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY); - /* Step 4: clear address list */ #ifdef CONFIG_IPV6_PRIVACY if (how && del_timer(&idev->regen_timer)) in6_dev_put(idev); - /* clear tempaddr list */ - while ((ifa = idev->tempaddr_list) != NULL) { - idev->tempaddr_list = ifa->tmp_next; - ifa->tmp_next = NULL; - ifa->dead = 1; + /* Step 3: clear tempaddr list */ + while (!list_empty(&idev->tempaddr_list)) { + ifa = list_first_entry(&idev->tempaddr_list, + struct inet6_ifaddr, tmp_list); + list_del(&ifa->tmp_list); write_unlock_bh(&idev->lock); spin_lock_bh(&ifa->lock); @@ -2692,23 +2704,18 @@ 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; + while (!list_empty(&idev->addr_list)) { + ifa = list_first_entry(&idev->addr_list, + struct inet6_ifaddr, if_list); addrconf_del_timer(ifa); /* If just doing link down, and address is permanent and not link-local, then retain it. */ - if (how == 0 && + if (!how && (ifa->flags&IFA_F_PERMANENT) && !(ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)) { - - /* Move to holding list */ - *bifa = ifa; - bifa = &ifa->if_next; + list_move_tail(&ifa->if_list, &keep_list); /* If not doing DAD on this address, just keep it. */ if ((dev->flags&(IFF_NOARP|IFF_LOOPBACK)) || @@ -2722,25 +2729,45 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* Flag it for later restoration when link comes up */ ifa->flags |= IFA_F_TENTATIVE; + ifa->state = INET6_IFADDR_STATE_DAD; + + write_unlock_bh(&idev->lock); + in6_ifa_hold(ifa); } else { - ifa->dead = 1; + list_del(&ifa->if_list); + + /* clear hash table */ + spin_lock_bh(&addrconf_hash_lock); + hlist_del_init_rcu(&ifa->addr_lst); + spin_unlock_bh(&addrconf_hash_lock); + + write_unlock_bh(&idev->lock); + spin_lock_bh(&ifa->state_lock); + state = ifa->state; + ifa->state = INET6_IFADDR_STATE_DEAD; + spin_unlock_bh(&ifa->state_lock); + + if (state == INET6_IFADDR_STATE_DEAD) + goto put_ifa; } - write_unlock_bh(&idev->lock); __ipv6_ifa_notify(RTM_DELADDR, ifa); - atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa); + if (ifa->state == INET6_IFADDR_STATE_DEAD) + atomic_notifier_call_chain(&inet6addr_chain, + NETDEV_DOWN, ifa); + +put_ifa: in6_ifa_put(ifa); write_lock_bh(&idev->lock); } - idev->addr_list = keep_list; + list_splice(&keep_list, &idev->addr_list); write_unlock_bh(&idev->lock); /* Step 5: Discard multicast list */ - if (how) ipv6_mc_destroy_dev(idev); else @@ -2748,8 +2775,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) idev->tstamp = jiffies; - /* Shot the device (if unregistered) */ - + /* Last: Shot the device (if unregistered) */ if (how) { addrconf_sysctl_unregister(idev); neigh_parms_release(&nd_tbl, idev->nd_parms); @@ -2827,10 +2853,10 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) net_srandom(ifp->addr.s6_addr32[3]); read_lock_bh(&idev->lock); - if (ifp->dead) + spin_lock(&ifp->lock); + if (ifp->state == INET6_IFADDR_STATE_DEAD) goto out; - spin_lock(&ifp->lock); if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || idev->cnf.accept_dad < 1 || !(ifp->flags&IFA_F_TENTATIVE) || @@ -2860,12 +2886,12 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) * Optimistic nodes can start receiving * Frames right away */ - if(ifp->flags & IFA_F_OPTIMISTIC) + if (ifp->flags & IFA_F_OPTIMISTIC) ip6_ins_rt(ifp->rt); addrconf_dad_kick(ifp); - spin_unlock(&ifp->lock); out: + spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); } @@ -2875,6 +2901,9 @@ static void addrconf_dad_timer(unsigned long data) struct inet6_dev *idev = ifp->idev; struct in6_addr mcaddr; + if (!ifp->probes && addrconf_dad_end(ifp)) + goto out; + read_lock(&idev->lock); if (idev->dead || !(idev->if_flags & IF_READY)) { read_unlock(&idev->lock); @@ -2882,6 +2911,12 @@ static void addrconf_dad_timer(unsigned long data) } spin_lock(&ifp->lock); + if (ifp->state == INET6_IFADDR_STATE_DEAD) { + spin_unlock(&ifp->lock); + read_unlock(&idev->lock); + goto out; + } + if (ifp->probes == 0) { /* * DAD was successful @@ -2910,7 +2945,7 @@ out: static void addrconf_dad_completed(struct inet6_ifaddr *ifp) { - struct net_device * dev = ifp->idev->dev; + struct net_device *dev = ifp->idev->dev; /* * Configure the address for reception. Now it is valid. @@ -2941,18 +2976,17 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) } } -static void addrconf_dad_run(struct inet6_dev *idev) { +static void addrconf_dad_run(struct inet6_dev *idev) +{ struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp = idev->addr_list; ifp; ifp = ifp->if_next) { + list_for_each_entry(ifp, &idev->addr_list, if_list) { spin_lock(&ifp->lock); - if (!(ifp->flags & IFA_F_TENTATIVE)) { - spin_unlock(&ifp->lock); - continue; - } + if (ifp->flags & IFA_F_TENTATIVE && + ifp->state == INET6_IFADDR_STATE_DAD) + addrconf_dad_kick(ifp); spin_unlock(&ifp->lock); - addrconf_dad_kick(ifp); } read_unlock_bh(&idev->lock); } @@ -2970,36 +3004,35 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); for (state->bucket = 0; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { - ifa = inet6_addr_lst[state->bucket]; - - while (ifa && !net_eq(dev_net(ifa->idev->dev), net)) - ifa = ifa->lst_next; - if (ifa) - break; + struct hlist_node *n; + hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket], + addr_lst) + if (net_eq(dev_net(ifa->idev->dev), net)) + return ifa; } - return ifa; + return NULL; } -static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct inet6_ifaddr *ifa) +static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, + struct inet6_ifaddr *ifa) { struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + struct hlist_node *n = &ifa->addr_lst; - ifa = ifa->lst_next; -try_again: - if (ifa) { - if (!net_eq(dev_net(ifa->idev->dev), net)) { - ifa = ifa->lst_next; - goto try_again; - } - } + hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst) + if (net_eq(dev_net(ifa->idev->dev), net)) + return ifa; - if (!ifa && ++state->bucket < IN6_ADDR_HSIZE) { - ifa = inet6_addr_lst[state->bucket]; - goto try_again; + while (++state->bucket < IN6_ADDR_HSIZE) { + hlist_for_each_entry_rcu_bh(ifa, n, + &inet6_addr_lst[state->bucket], addr_lst) { + if (net_eq(dev_net(ifa->idev->dev), net)) + return ifa; + } } - return ifa; + return NULL; } static struct inet6_ifaddr *if6_get_idx(struct seq_file *seq, loff_t pos) @@ -3007,15 +3040,15 @@ static struct inet6_ifaddr *if6_get_idx(struct seq_file *seq, loff_t pos) struct inet6_ifaddr *ifa = if6_get_first(seq); if (ifa) - while(pos && (ifa = if6_get_next(seq, ifa)) != NULL) + while (pos && (ifa = if6_get_next(seq, ifa)) != NULL) --pos; return pos ? NULL : ifa; } static void *if6_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(addrconf_hash_lock) + __acquires(rcu_bh) { - read_lock_bh(&addrconf_hash_lock); + rcu_read_lock_bh(); return if6_get_idx(seq, *pos); } @@ -3029,9 +3062,9 @@ static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void if6_seq_stop(struct seq_file *seq, void *v) - __releases(addrconf_hash_lock) + __releases(rcu_bh) { - read_unlock_bh(&addrconf_hash_lock); + rcu_read_unlock_bh(); } static int if6_seq_show(struct seq_file *seq, void *v) @@ -3101,10 +3134,12 @@ void if6_proc_exit(void) int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr) { int ret = 0; - struct inet6_ifaddr * ifp; - u8 hash = ipv6_addr_hash(addr); - read_lock_bh(&addrconf_hash_lock); - for (ifp = inet6_addr_lst[hash]; ifp; ifp = ifp->lst_next) { + struct inet6_ifaddr *ifp = NULL; + struct hlist_node *n; + unsigned int hash = ipv6_addr_hash(addr); + + rcu_read_lock_bh(); + hlist_for_each_entry_rcu_bh(ifp, n, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && @@ -3113,7 +3148,7 @@ int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr) break; } } - read_unlock_bh(&addrconf_hash_lock); + rcu_read_unlock_bh(); return ret; } #endif @@ -3124,43 +3159,35 @@ int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr) static void addrconf_verify(unsigned long foo) { + unsigned long now, next, next_sec, next_sched; struct inet6_ifaddr *ifp; - unsigned long now, next; + struct hlist_node *node; int i; - spin_lock_bh(&addrconf_verify_lock); + rcu_read_lock_bh(); + spin_lock(&addrconf_verify_lock); now = jiffies; - next = now + ADDR_CHECK_FREQUENCY; + next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); del_timer(&addr_chk_timer); - for (i=0; i < IN6_ADDR_HSIZE; i++) { - + for (i = 0; i < IN6_ADDR_HSIZE; i++) { restart: - read_lock(&addrconf_hash_lock); - for (ifp=inet6_addr_lst[i]; ifp; ifp=ifp->lst_next) { + hlist_for_each_entry_rcu_bh(ifp, node, + &inet6_addr_lst[i], addr_lst) { unsigned long age; -#ifdef CONFIG_IPV6_PRIVACY - unsigned long regen_advance; -#endif if (ifp->flags & IFA_F_PERMANENT) continue; spin_lock(&ifp->lock); - age = (now - ifp->tstamp) / HZ; - -#ifdef CONFIG_IPV6_PRIVACY - regen_advance = ifp->idev->cnf.regen_max_retry * - ifp->idev->cnf.dad_transmits * - ifp->idev->nd_parms->retrans_time / HZ; -#endif + /* We try to batch several events at once. */ + age = (now - ifp->tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (ifp->valid_lft != INFINITY_LIFE_TIME && age >= ifp->valid_lft) { spin_unlock(&ifp->lock); in6_ifa_hold(ifp); - read_unlock(&addrconf_hash_lock); ipv6_del_addr(ifp); goto restart; } else if (ifp->prefered_lft == INFINITY_LIFE_TIME) { @@ -3182,7 +3209,6 @@ restart: if (deprecate) { in6_ifa_hold(ifp); - read_unlock(&addrconf_hash_lock); ipv6_ifa_notify(0, ifp); in6_ifa_put(ifp); @@ -3191,6 +3217,10 @@ restart: #ifdef CONFIG_IPV6_PRIVACY } else if ((ifp->flags&IFA_F_TEMPORARY) && !(ifp->flags&IFA_F_TENTATIVE)) { + unsigned long regen_advance = ifp->idev->cnf.regen_max_retry * + ifp->idev->cnf.dad_transmits * + ifp->idev->nd_parms->retrans_time / HZ; + if (age >= ifp->prefered_lft - regen_advance) { struct inet6_ifaddr *ifpub = ifp->ifpub; if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next)) @@ -3200,7 +3230,7 @@ restart: in6_ifa_hold(ifp); in6_ifa_hold(ifpub); spin_unlock(&ifp->lock); - read_unlock(&addrconf_hash_lock); + spin_lock(&ifpub->lock); ifpub->regen_count = 0; spin_unlock(&ifpub->lock); @@ -3220,12 +3250,26 @@ restart: spin_unlock(&ifp->lock); } } - read_unlock(&addrconf_hash_lock); } - addr_chk_timer.expires = time_before(next, jiffies + HZ) ? jiffies + HZ : next; + next_sec = round_jiffies_up(next); + next_sched = next; + + /* If rounded timeout is accurate enough, accept it. */ + if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ)) + next_sched = next_sec; + + /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */ + if (time_before(next_sched, jiffies + ADDRCONF_TIMER_FUZZ_MAX)) + next_sched = jiffies + ADDRCONF_TIMER_FUZZ_MAX; + + ADBG((KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", + now, next, next_sec, next_sched)); + + addr_chk_timer.expires = next_sched; add_timer(&addr_chk_timer); - spin_unlock_bh(&addrconf_verify_lock); + spin_unlock(&addrconf_verify_lock); + rcu_read_unlock_bh(); } static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local) @@ -3515,8 +3559,7 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, return nlmsg_end(skb, nlh); } -enum addr_type_t -{ +enum addr_type_t { UNICAST_ADDR, MULTICAST_ADDR, ANYCAST_ADDR, @@ -3527,7 +3570,6 @@ 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; @@ -3535,11 +3577,12 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, read_lock_bh(&idev->lock); switch (type) { - case UNICAST_ADDR: + case UNICAST_ADDR: { + struct inet6_ifaddr *ifa; + /* unicast address incl. temp addr */ - for (ifa = idev->addr_list; ifa; - ifa = ifa->if_next, ip_idx++) { - if (ip_idx < s_ip_idx) + list_for_each_entry(ifa, &idev->addr_list, if_list) { + if (++ip_idx < s_ip_idx) continue; err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid, @@ -3550,6 +3593,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, break; } break; + } case MULTICAST_ADDR: /* multicast address */ for (ifmca = idev->mc_list; ifmca; @@ -3614,7 +3658,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, if (h > s_h || idx > s_idx) s_ip_idx = 0; ip_idx = 0; - if ((idev = __in6_dev_get(dev)) == NULL) + idev = __in6_dev_get(dev); + if (!idev) goto cont; if (in6_dump_addrs(idev, skb, cb, type, @@ -3681,12 +3726,14 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh, if (ifm->ifa_index) dev = __dev_get_by_index(net, ifm->ifa_index); - if ((ifa = ipv6_get_ifaddr(net, addr, dev, 1)) == NULL) { + ifa = ipv6_get_ifaddr(net, addr, dev, 1); + if (!ifa) { err = -EADDRNOTAVAIL; goto errout; } - if ((skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_KERNEL)) == NULL) { + skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_KERNEL); + if (!skb) { err = -ENOBUFS; goto errout_ifa; } @@ -3811,7 +3858,7 @@ static inline void __snmp6_fill_stats(u64 *stats, void __percpu **mib, static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, int bytes) { - switch(attrtype) { + switch (attrtype) { case IFLA_INET6_STATS: __snmp6_fill_stats(stats, (void __percpu **)idev->stats.ipv6, IPSTATS_MIB_MAX, bytes); break; @@ -4047,7 +4094,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) addrconf_leave_anycast(ifp); addrconf_leave_solict(ifp->idev, &ifp->addr); dst_hold(&ifp->rt->u.dst); - if (ip6_del_rt(ifp->rt)) + + if (ifp->state == INET6_IFADDR_STATE_DEAD && + ip6_del_rt(ifp->rt)) dst_free(&ifp->rt->u.dst); break; } @@ -4163,211 +4212,211 @@ static struct addrconf_sysctl_table .sysctl_header = NULL, .addrconf_vars = { { - .procname = "forwarding", - .data = &ipv6_devconf.forwarding, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = addrconf_sysctl_forward, + .procname = "forwarding", + .data = &ipv6_devconf.forwarding, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = addrconf_sysctl_forward, }, { - .procname = "hop_limit", - .data = &ipv6_devconf.hop_limit, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "hop_limit", + .data = &ipv6_devconf.hop_limit, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "mtu", - .data = &ipv6_devconf.mtu6, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "mtu", + .data = &ipv6_devconf.mtu6, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "accept_ra", - .data = &ipv6_devconf.accept_ra, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "accept_ra", + .data = &ipv6_devconf.accept_ra, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "accept_redirects", - .data = &ipv6_devconf.accept_redirects, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "accept_redirects", + .data = &ipv6_devconf.accept_redirects, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "autoconf", - .data = &ipv6_devconf.autoconf, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "autoconf", + .data = &ipv6_devconf.autoconf, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "dad_transmits", - .data = &ipv6_devconf.dad_transmits, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "dad_transmits", + .data = &ipv6_devconf.dad_transmits, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "router_solicitations", - .data = &ipv6_devconf.rtr_solicits, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "router_solicitations", + .data = &ipv6_devconf.rtr_solicits, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "router_solicitation_interval", - .data = &ipv6_devconf.rtr_solicit_interval, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, + .procname = "router_solicitation_interval", + .data = &ipv6_devconf.rtr_solicit_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, }, { - .procname = "router_solicitation_delay", - .data = &ipv6_devconf.rtr_solicit_delay, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, + .procname = "router_solicitation_delay", + .data = &ipv6_devconf.rtr_solicit_delay, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, }, { - .procname = "force_mld_version", - .data = &ipv6_devconf.force_mld_version, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "force_mld_version", + .data = &ipv6_devconf.force_mld_version, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_IPV6_PRIVACY { - .procname = "use_tempaddr", - .data = &ipv6_devconf.use_tempaddr, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "use_tempaddr", + .data = &ipv6_devconf.use_tempaddr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "temp_valid_lft", - .data = &ipv6_devconf.temp_valid_lft, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "temp_valid_lft", + .data = &ipv6_devconf.temp_valid_lft, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "temp_prefered_lft", - .data = &ipv6_devconf.temp_prefered_lft, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "temp_prefered_lft", + .data = &ipv6_devconf.temp_prefered_lft, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "regen_max_retry", - .data = &ipv6_devconf.regen_max_retry, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "regen_max_retry", + .data = &ipv6_devconf.regen_max_retry, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "max_desync_factor", - .data = &ipv6_devconf.max_desync_factor, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "max_desync_factor", + .data = &ipv6_devconf.max_desync_factor, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, #endif { - .procname = "max_addresses", - .data = &ipv6_devconf.max_addresses, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "max_addresses", + .data = &ipv6_devconf.max_addresses, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "accept_ra_defrtr", - .data = &ipv6_devconf.accept_ra_defrtr, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "accept_ra_defrtr", + .data = &ipv6_devconf.accept_ra_defrtr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "accept_ra_pinfo", - .data = &ipv6_devconf.accept_ra_pinfo, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "accept_ra_pinfo", + .data = &ipv6_devconf.accept_ra_pinfo, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_IPV6_ROUTER_PREF { - .procname = "accept_ra_rtr_pref", - .data = &ipv6_devconf.accept_ra_rtr_pref, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "accept_ra_rtr_pref", + .data = &ipv6_devconf.accept_ra_rtr_pref, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "router_probe_interval", - .data = &ipv6_devconf.rtr_probe_interval, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, + .procname = "router_probe_interval", + .data = &ipv6_devconf.rtr_probe_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, }, #ifdef CONFIG_IPV6_ROUTE_INFO { - .procname = "accept_ra_rt_info_max_plen", - .data = &ipv6_devconf.accept_ra_rt_info_max_plen, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "accept_ra_rt_info_max_plen", + .data = &ipv6_devconf.accept_ra_rt_info_max_plen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, #endif #endif { - .procname = "proxy_ndp", - .data = &ipv6_devconf.proxy_ndp, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "proxy_ndp", + .data = &ipv6_devconf.proxy_ndp, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .procname = "accept_source_route", - .data = &ipv6_devconf.accept_source_route, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "accept_source_route", + .data = &ipv6_devconf.accept_source_route, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_IPV6_OPTIMISTIC_DAD { - .procname = "optimistic_dad", - .data = &ipv6_devconf.optimistic_dad, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "optimistic_dad", + .data = &ipv6_devconf.optimistic_dad, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_IPV6_MROUTE { - .procname = "mc_forwarding", - .data = &ipv6_devconf.mc_forwarding, - .maxlen = sizeof(int), - .mode = 0444, - .proc_handler = proc_dointvec, + .procname = "mc_forwarding", + .data = &ipv6_devconf.mc_forwarding, + .maxlen = sizeof(int), + .mode = 0444, + .proc_handler = proc_dointvec, }, #endif { - .procname = "disable_ipv6", - .data = &ipv6_devconf.disable_ipv6, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = addrconf_sysctl_disable, + .procname = "disable_ipv6", + .data = &ipv6_devconf.disable_ipv6, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = addrconf_sysctl_disable, }, { - .procname = "accept_dad", - .data = &ipv6_devconf.accept_dad, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "accept_dad", + .data = &ipv6_devconf.accept_dad, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { .procname = "force_tllao", @@ -4403,8 +4452,8 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, if (t == NULL) goto out; - for (i=0; t->addrconf_vars[i].data; i++) { - t->addrconf_vars[i].data += (char*)p - (char*)&ipv6_devconf; + for (i = 0; t->addrconf_vars[i].data; i++) { + t->addrconf_vars[i].data += (char *)p - (char *)&ipv6_devconf; t->addrconf_vars[i].extra1 = idev; /* embedded; no ref */ t->addrconf_vars[i].extra2 = net; } @@ -4541,14 +4590,12 @@ int register_inet6addr_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&inet6addr_chain, nb); } - EXPORT_SYMBOL(register_inet6addr_notifier); int unregister_inet6addr_notifier(struct notifier_block *nb) { - return atomic_notifier_chain_unregister(&inet6addr_chain,nb); + return atomic_notifier_chain_unregister(&inet6addr_chain, nb); } - EXPORT_SYMBOL(unregister_inet6addr_notifier); /* @@ -4557,11 +4604,12 @@ EXPORT_SYMBOL(unregister_inet6addr_notifier); int __init addrconf_init(void) { - int err; + int i, err; - if ((err = ipv6_addr_label_init()) < 0) { - printk(KERN_CRIT "IPv6 Addrconf: cannot initialize default policy table: %d.\n", - err); + err = ipv6_addr_label_init(); + if (err < 0) { + printk(KERN_CRIT "IPv6 Addrconf:" + " cannot initialize default policy table: %d.\n", err); return err; } @@ -4592,6 +4640,9 @@ int __init addrconf_init(void) if (err) goto errlo; + for (i = 0; i < IN6_ADDR_HSIZE; i++) + INIT_HLIST_HEAD(&inet6_addr_lst[i]); + register_netdevice_notifier(&ipv6_dev_notf); addrconf_verify(0); @@ -4620,7 +4671,6 @@ errlo: void addrconf_cleanup(void) { - struct inet6_ifaddr *ifa; struct net_device *dev; int i; @@ -4640,20 +4690,10 @@ void addrconf_cleanup(void) /* * Check hash table. */ - write_lock_bh(&addrconf_hash_lock); - for (i=0; i < IN6_ADDR_HSIZE; i++) { - for (ifa=inet6_addr_lst[i]; ifa; ) { - struct inet6_ifaddr *bifa; - - bifa = ifa; - ifa = ifa->lst_next; - printk(KERN_DEBUG "bug: IPv6 address leakage detected: ifa=%p\n", bifa); - /* Do not free it; something is wrong. - Now we can investigate it with debugger. - */ - } - } - write_unlock_bh(&addrconf_hash_lock); + spin_lock_bh(&addrconf_hash_lock); + for (i = 0; i < IN6_ADDR_HSIZE; i++) + WARN_ON(!hlist_empty(&inet6_addr_lst[i])); + spin_unlock_bh(&addrconf_hash_lock); del_timer(&addr_chk_timer); rtnl_unlock(); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index ae404c9a746..8c4348cb195 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -422,10 +422,6 @@ static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh, ifal->ifal_prefixlen > 128) return -EINVAL; - if (ifal->ifal_index && - !__dev_get_by_index(net, ifal->ifal_index)) - return -EINVAL; - if (!tb[IFAL_ADDRESS]) return -EINVAL; @@ -441,6 +437,10 @@ static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh, switch(nlh->nlmsg_type) { case RTM_NEWADDRLABEL: + if (ifal->ifal_index && + !__dev_get_by_index(net, ifal->ifal_index)) + return -EINVAL; + err = ip6addrlbl_add(net, pfx, ifal->ifal_prefixlen, ifal->ifal_index, label, nlh->nlmsg_flags & NLM_F_REPLACE); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3f9e86b15e0..e733942dafe 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -417,6 +417,9 @@ void inet6_destroy_sock(struct sock *sk) if ((skb = xchg(&np->pktoptions, NULL)) != NULL) kfree_skb(skb); + if ((skb = xchg(&np->rxpmtu, NULL)) != NULL) + kfree_skb(skb); + /* Free flowlabels */ fl6_free_socklist(sk); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 61573885e45..712684687c9 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -282,6 +282,45 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info) kfree_skb(skb); } +void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6hdr *iph; + struct sk_buff *skb; + struct ip6_mtuinfo *mtu_info; + + if (!np->rxopt.bits.rxpmtu) + return; + + skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); + if (!skb) + return; + + skb_put(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + iph = ipv6_hdr(skb); + ipv6_addr_copy(&iph->daddr, &fl->fl6_dst); + + mtu_info = IP6CBMTU(skb); + if (!mtu_info) { + kfree_skb(skb); + return; + } + + mtu_info->ip6m_mtu = mtu; + mtu_info->ip6m_addr.sin6_family = AF_INET6; + mtu_info->ip6m_addr.sin6_port = 0; + mtu_info->ip6m_addr.sin6_flowinfo = 0; + mtu_info->ip6m_addr.sin6_scope_id = fl->oif; + ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr); + + __skb_pull(skb, skb_tail_pointer(skb) - skb->data); + skb_reset_transport_header(skb); + + skb = xchg(&np->rxpmtu, skb); + kfree_skb(skb); +} + /* * Handle MSG_ERRQUEUE */ @@ -385,6 +424,54 @@ out: return err; } +/* + * Handle IPV6_RECVPATHMTU + */ +int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct sk_buff *skb; + struct sockaddr_in6 *sin; + struct ip6_mtuinfo mtu_info; + int err; + int copied; + + err = -EAGAIN; + skb = xchg(&np->rxpmtu, NULL); + if (skb == NULL) + goto out; + + copied = skb->len; + if (copied > len) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (err) + goto out_free_skb; + + sock_recv_timestamp(msg, sk, skb); + + memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info)); + + sin = (struct sockaddr_in6 *)msg->msg_name; + if (sin) { + sin->sin6_family = AF_INET6; + sin->sin6_flowinfo = 0; + sin->sin6_port = 0; + sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; + ipv6_addr_copy(&sin->sin6_addr, &mtu_info.ip6m_addr.sin6_addr); + } + + put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); + + err = copied; + +out_free_skb: + kfree_skb(skb); +out: + return err; +} int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) @@ -501,7 +588,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) int datagram_send_ctl(struct net *net, struct msghdr *msg, struct flowi *fl, struct ipv6_txoptions *opt, - int *hlimit, int *tclass) + int *hlimit, int *tclass, int *dontfrag) { struct in6_pktinfo *src_info; struct cmsghdr *cmsg; @@ -741,6 +828,25 @@ int datagram_send_ctl(struct net *net, break; } + + case IPV6_DONTFRAG: + { + int df; + + err = -EINVAL; + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) { + goto exit_f; + } + + df = *(int *)CMSG_DATA(cmsg); + if (df < 0 || df > 1) + goto exit_f; + + err = 0; + *dontfrag = df; + + break; + } default: LIMIT_NETDEBUG(KERN_DEBUG "invalid cmsg type: %d\n", cmsg->cmsg_type); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 5e463c43fcc..8e44f8f9c18 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -208,7 +208,6 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, { struct fib6_rule *rule6 = (struct fib6_rule *) rule; - frh->family = AF_INET6; frh->dst_len = rule6->dst.plen; frh->src_len = rule6->src.plen; frh->tos = rule6->tclass; @@ -238,7 +237,7 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) + nla_total_size(16); /* src */ } -static struct fib_rules_ops fib6_rules_ops_template = { +static const struct fib_rules_ops __net_initdata fib6_rules_ops_template = { .family = AF_INET6, .rule_size = sizeof(struct fib6_rule), .addr_size = sizeof(struct in6_addr), diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 3330a4bd615..ce799298255 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -481,8 +481,9 @@ route_done: len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl, (struct rt6_info*)dst, - MSG_DONTWAIT); + MSG_DONTWAIT, np->dontfrag); if (err) { + ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); ip6_flush_pending_frames(sk); goto out_put; } @@ -560,9 +561,11 @@ static void icmpv6_echo_reply(struct sk_buff *skb) err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl, - (struct rt6_info*)dst, MSG_DONTWAIT); + (struct rt6_info*)dst, MSG_DONTWAIT, + np->dontfrag); if (err) { + ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); ip6_flush_pending_frames(sk); goto out_put; } diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 628db24bcf2..0c5e3c3b7fd 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -178,7 +178,7 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) return dst; } -int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) +int inet6_csk_xmit(struct sk_buff *skb) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); @@ -234,7 +234,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) /* Restore final destination back after routing done */ ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - return ip6_xmit(sk, skb, &fl, np->opt, 0); + return ip6_xmit(sk, skb, &fl, np->opt); } EXPORT_SYMBOL_GPL(inet6_csk_xmit); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 6b82e02158c..92a122b7795 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -128,12 +128,24 @@ static __inline__ u32 fib6_new_sernum(void) /* * test bit */ +#if defined(__LITTLE_ENDIAN) +# define BITOP_BE32_SWIZZLE (0x1F & ~7) +#else +# define BITOP_BE32_SWIZZLE 0 +#endif static __inline__ __be32 addr_bit_set(void *token, int fn_bit) { __be32 *addr = token; - - return htonl(1 << ((~fn_bit)&0x1F)) & addr[fn_bit>>5]; + /* + * Here, + * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) + * is optimized version of + * htonl(1 << ((~fn_bit)&0x1F)) + * See include/asm-generic/bitops/le.h. + */ + return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) & + addr[fn_bit >> 5]; } static __inline__ struct fib6_node * node_alloc(void) diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 14e23216eb2..13654686aea 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -360,7 +360,8 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, msg.msg_control = (void*)(fl->opt+1); flowi.oif = 0; - err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, &junk); + err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, + &junk, &junk); if (err) goto done; err = -EINVAL; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 6aa7ee1295c..a83e9209cec 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -143,7 +143,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt /* Must drop socket now because of tproxy. */ skb_orphan(skb); - return NF_HOOK(PF_INET6, NF_INET_PRE_ROUTING, skb, dev, NULL, + return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, dev, NULL, ip6_rcv_finish); err: IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); @@ -236,7 +236,7 @@ discard: int ip6_input(struct sk_buff *skb) { - return NF_HOOK(PF_INET6, NF_INET_LOCAL_IN, skb, skb->dev, NULL, + return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, skb, skb->dev, NULL, ip6_input_finish); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 75d5ef83009..cd963f64e27 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -67,8 +67,8 @@ int __ip6_local_out(struct sk_buff *skb) len = 0; ipv6_hdr(skb)->payload_len = htons(len); - return nf_hook(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev, - dst_output); + return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, + skb_dst(skb)->dev, dst_output); } int ip6_local_out(struct sk_buff *skb) @@ -83,22 +83,6 @@ int ip6_local_out(struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ip6_local_out); -static int ip6_output_finish(struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - - if (dst->hh) - return neigh_hh_output(dst->hh, skb); - else if (dst->neighbour) - return dst->neighbour->output(skb); - - IP6_INC_STATS_BH(dev_net(dst->dev), - ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); - kfree_skb(skb); - return -EINVAL; - -} - /* dev_loopback_xmit for use with netfilter. */ static int ip6_dev_loopback_xmit(struct sk_buff *newskb) { @@ -112,8 +96,7 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb) return 0; } - -static int ip6_output2(struct sk_buff *skb) +static int ip6_finish_output2(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; @@ -125,7 +108,7 @@ static int ip6_output2(struct sk_buff *skb) struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) && - ((mroute6_socket(dev_net(dev)) && + ((mroute6_socket(dev_net(dev), skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr))) { @@ -135,8 +118,8 @@ static int ip6_output2(struct sk_buff *skb) is not supported in any case. */ if (newskb) - NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, newskb, - NULL, newskb->dev, + NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, + newskb, NULL, newskb->dev, ip6_dev_loopback_xmit); if (ipv6_hdr(skb)->hop_limit == 0) { @@ -151,8 +134,15 @@ static int ip6_output2(struct sk_buff *skb) skb->len); } - return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb->dev, - ip6_output_finish); + if (dst->hh) + return neigh_hh_output(dst->hh, skb); + else if (dst->neighbour) + return dst->neighbour->output(skb); + + IP6_INC_STATS_BH(dev_net(dst->dev), + ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); + kfree_skb(skb); + return -EINVAL; } static inline int ip6_skb_dst_mtu(struct sk_buff *skb) @@ -163,29 +153,37 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb) skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); } +static int ip6_finish_output(struct sk_buff *skb) +{ + if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || + dst_allfrag(skb_dst(skb))) + return ip6_fragment(skb, ip6_finish_output2); + else + return ip6_finish_output2(skb); +} + int ip6_output(struct sk_buff *skb) { + struct net_device *dev = skb_dst(skb)->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); if (unlikely(idev->cnf.disable_ipv6)) { - IP6_INC_STATS(dev_net(skb_dst(skb)->dev), idev, + IP6_INC_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } - if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || - dst_allfrag(skb_dst(skb))) - return ip6_fragment(skb, ip6_output2); - else - return ip6_output2(skb); + return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, dev, + ip6_finish_output, + !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } /* - * xmit an sk_buff (used by TCP) + * xmit an sk_buff (used by TCP, SCTP and DCCP) */ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct ipv6_txoptions *opt, int ipfragok) + struct ipv6_txoptions *opt) { struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -218,8 +216,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, } kfree_skb(skb); skb = skb2; - if (sk) - skb_set_owner_w(skb, sk); + skb_set_owner_w(skb, sk); } if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); @@ -231,10 +228,6 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, skb_reset_network_header(skb); hdr = ipv6_hdr(skb); - /* Allow local fragmentation. */ - if (ipfragok) - skb->local_df = 1; - /* * Fill in the IPv6 header */ @@ -261,8 +254,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) { IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUT, skb->len); - return NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev, - dst_output); + return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, + dst->dev, dst_output); } if (net_ratelimit()) @@ -538,7 +531,7 @@ int ip6_forward(struct sk_buff *skb) hdr->hop_limit--; IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); - return NF_HOOK(PF_INET6, NF_INET_FORWARD, skb, skb->dev, dst->dev, + return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev, ip6_forward_finish); error: @@ -1109,7 +1102,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi *fl, - struct rt6_info *rt, unsigned int flags) + struct rt6_info *rt, unsigned int flags, int dontfrag) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -1223,15 +1216,23 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, */ inet->cork.length += length; - if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) && - (rt->u.dst.dev->features & NETIF_F_UFO)) { + if (length > mtu) { + int proto = sk->sk_protocol; + if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){ + ipv6_local_rxpmtu(sk, fl, mtu-exthdrlen); + return -EMSGSIZE; + } - err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len, - fragheaderlen, transhdrlen, mtu, - flags); - if (err) - goto error; - return 0; + if (proto == IPPROTO_UDP && + (rt->u.dst.dev->features & NETIF_F_UFO)) { + + err = ip6_ufo_append_data(sk, getfrag, from, length, + hh_len, fragheaderlen, + transhdrlen, mtu, flags); + if (err) + goto error; + return 0; + } } if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 2599870747e..8f39893d808 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -723,14 +723,10 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, skb->protocol = htons(protocol); skb->pkt_type = PACKET_HOST; memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); - skb->dev = t->dev; - skb_dst_drop(skb); - nf_reset(skb); - dscp_ecn_decapsulate(t, ipv6h, skb); + skb_tunnel_rx(skb, t->dev); - t->dev->stats.rx_packets++; - t->dev->stats.rx_bytes += skb->len; + dscp_ecn_decapsulate(t, ipv6h, skb); netif_rx(skb); rcu_read_unlock(); return 0; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 3e333268db8..bd9e7d3e9c8 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -42,6 +42,7 @@ #include <linux/if_arp.h> #include <net/checksum.h> #include <net/netlink.h> +#include <net/fib_rules.h> #include <net/ipv6.h> #include <net/ip6_route.h> @@ -51,6 +52,34 @@ #include <linux/netfilter_ipv6.h> #include <net/ip6_checksum.h> +struct mr6_table { + struct list_head list; +#ifdef CONFIG_NET_NS + struct net *net; +#endif + u32 id; + struct sock *mroute6_sk; + struct timer_list ipmr_expire_timer; + struct list_head mfc6_unres_queue; + struct list_head mfc6_cache_array[MFC6_LINES]; + struct mif_device vif6_table[MAXMIFS]; + int maxvif; + atomic_t cache_resolve_queue_len; + int mroute_do_assert; + int mroute_do_pim; +#ifdef CONFIG_IPV6_PIMSM_V2 + int mroute_reg_vif_num; +#endif +}; + +struct ip6mr_rule { + struct fib_rule common; +}; + +struct ip6mr_result { + struct mr6_table *mrt; +}; + /* Big lock, protecting vif table, mrt cache and mroute socket state. Note that the changes are semaphored via rtnl_lock. */ @@ -61,9 +90,7 @@ static DEFINE_RWLOCK(mrt_lock); * Multicast router control variables */ -#define MIF_EXISTS(_net, _idx) ((_net)->ipv6.vif6_table[_idx].dev != NULL) - -static struct mfc6_cache *mfc_unres_queue; /* Queue of unresolved entries */ +#define MIF_EXISTS(_mrt, _idx) ((_mrt)->vif6_table[_idx].dev != NULL) /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); @@ -78,20 +105,233 @@ static DEFINE_SPINLOCK(mfc_unres_lock); static struct kmem_cache *mrt_cachep __read_mostly; -static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache); -static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, +static struct mr6_table *ip6mr_new_table(struct net *net, u32 id); +static void ip6mr_free_table(struct mr6_table *mrt); + +static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache); +static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); -static int ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm); -static void mroute_clean_tables(struct net *net); +static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, + struct mfc6_cache *c, struct rtmsg *rtm); +static int ip6mr_rtm_dumproute(struct sk_buff *skb, + struct netlink_callback *cb); +static void mroute_clean_tables(struct mr6_table *mrt); +static void ipmr_expire_process(unsigned long arg); + +#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES +#define ip6mr_for_each_table(mrt, met) \ + list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list) + +static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) +{ + struct mr6_table *mrt; + + ip6mr_for_each_table(mrt, net) { + if (mrt->id == id) + return mrt; + } + return NULL; +} + +static int ip6mr_fib_lookup(struct net *net, struct flowi *flp, + struct mr6_table **mrt) +{ + struct ip6mr_result res; + struct fib_lookup_arg arg = { .result = &res, }; + int err; + + err = fib_rules_lookup(net->ipv6.mr6_rules_ops, flp, 0, &arg); + if (err < 0) + return err; + *mrt = res.mrt; + return 0; +} + +static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) +{ + struct ip6mr_result *res = arg->result; + struct mr6_table *mrt; + + switch (rule->action) { + case FR_ACT_TO_TBL: + break; + case FR_ACT_UNREACHABLE: + return -ENETUNREACH; + case FR_ACT_PROHIBIT: + return -EACCES; + case FR_ACT_BLACKHOLE: + default: + return -EINVAL; + } + + mrt = ip6mr_get_table(rule->fr_net, rule->table); + if (mrt == NULL) + return -EAGAIN; + res->mrt = mrt; + return 0; +} + +static int ip6mr_rule_match(struct fib_rule *rule, struct flowi *flp, int flags) +{ + return 1; +} + +static const struct nla_policy ip6mr_rule_policy[FRA_MAX + 1] = { + FRA_GENERIC_POLICY, +}; + +static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh, struct nlattr **tb) +{ + return 0; +} + +static int ip6mr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + return 1; +} + +static int ip6mr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh) +{ + frh->dst_len = 0; + frh->src_len = 0; + frh->tos = 0; + return 0; +} + +static const struct fib_rules_ops __net_initdata ip6mr_rules_ops_template = { + .family = RTNL_FAMILY_IP6MR, + .rule_size = sizeof(struct ip6mr_rule), + .addr_size = sizeof(struct in6_addr), + .action = ip6mr_rule_action, + .match = ip6mr_rule_match, + .configure = ip6mr_rule_configure, + .compare = ip6mr_rule_compare, + .default_pref = fib_default_rule_pref, + .fill = ip6mr_rule_fill, + .nlgroup = RTNLGRP_IPV6_RULE, + .policy = ip6mr_rule_policy, + .owner = THIS_MODULE, +}; + +static int __net_init ip6mr_rules_init(struct net *net) +{ + struct fib_rules_ops *ops; + struct mr6_table *mrt; + int err; + + ops = fib_rules_register(&ip6mr_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + + INIT_LIST_HEAD(&net->ipv6.mr6_tables); + + mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) { + err = -ENOMEM; + goto err1; + } + + err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT, 0); + if (err < 0) + goto err2; + + net->ipv6.mr6_rules_ops = ops; + return 0; + +err2: + kfree(mrt); +err1: + fib_rules_unregister(ops); + return err; +} + +static void __net_exit ip6mr_rules_exit(struct net *net) +{ + struct mr6_table *mrt, *next; + + list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) + ip6mr_free_table(mrt); + fib_rules_unregister(net->ipv6.mr6_rules_ops); +} +#else +#define ip6mr_for_each_table(mrt, net) \ + for (mrt = net->ipv6.mrt6; mrt; mrt = NULL) + +static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) +{ + return net->ipv6.mrt6; +} + +static int ip6mr_fib_lookup(struct net *net, struct flowi *flp, + struct mr6_table **mrt) +{ + *mrt = net->ipv6.mrt6; + return 0; +} + +static int __net_init ip6mr_rules_init(struct net *net) +{ + net->ipv6.mrt6 = ip6mr_new_table(net, RT6_TABLE_DFLT); + return net->ipv6.mrt6 ? 0 : -ENOMEM; +} -static struct timer_list ipmr_expire_timer; +static void __net_exit ip6mr_rules_exit(struct net *net) +{ + ip6mr_free_table(net->ipv6.mrt6); +} +#endif + +static struct mr6_table *ip6mr_new_table(struct net *net, u32 id) +{ + struct mr6_table *mrt; + unsigned int i; + + mrt = ip6mr_get_table(net, id); + if (mrt != NULL) + return mrt; + + mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); + if (mrt == NULL) + return NULL; + mrt->id = id; + write_pnet(&mrt->net, net); + + /* Forwarding cache */ + for (i = 0; i < MFC6_LINES; i++) + INIT_LIST_HEAD(&mrt->mfc6_cache_array[i]); + + INIT_LIST_HEAD(&mrt->mfc6_unres_queue); + setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process, + (unsigned long)mrt); + +#ifdef CONFIG_IPV6_PIMSM_V2 + mrt->mroute_reg_vif_num = -1; +#endif +#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES + list_add_tail_rcu(&mrt->list, &net->ipv6.mr6_tables); +#endif + return mrt; +} + +static void ip6mr_free_table(struct mr6_table *mrt) +{ + del_timer(&mrt->ipmr_expire_timer); + mroute_clean_tables(mrt); + kfree(mrt); +} #ifdef CONFIG_PROC_FS struct ipmr_mfc_iter { struct seq_net_private p; - struct mfc6_cache **cache; + struct mr6_table *mrt; + struct list_head *cache; int ct; }; @@ -99,22 +339,22 @@ struct ipmr_mfc_iter { static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, struct ipmr_mfc_iter *it, loff_t pos) { + struct mr6_table *mrt = it->mrt; struct mfc6_cache *mfc; - it->cache = net->ipv6.mfc6_cache_array; read_lock(&mrt_lock); - for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) - for (mfc = net->ipv6.mfc6_cache_array[it->ct]; - mfc; mfc = mfc->next) + for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) { + it->cache = &mrt->mfc6_cache_array[it->ct]; + list_for_each_entry(mfc, it->cache, list) if (pos-- == 0) return mfc; + } read_unlock(&mrt_lock); - it->cache = &mfc_unres_queue; spin_lock_bh(&mfc_unres_lock); - for (mfc = mfc_unres_queue; mfc; mfc = mfc->next) - if (net_eq(mfc6_net(mfc), net) && - pos-- == 0) + it->cache = &mrt->mfc6_unres_queue; + list_for_each_entry(mfc, it->cache, list) + if (pos-- == 0) return mfc; spin_unlock_bh(&mfc_unres_lock); @@ -122,15 +362,13 @@ static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, return NULL; } - - - /* * The /proc interfaces to multicast routing /proc/ip6_mr_cache /proc/ip6_mr_vif */ struct ipmr_vif_iter { struct seq_net_private p; + struct mr6_table *mrt; int ct; }; @@ -138,11 +376,13 @@ static struct mif_device *ip6mr_vif_seq_idx(struct net *net, struct ipmr_vif_iter *iter, loff_t pos) { - for (iter->ct = 0; iter->ct < net->ipv6.maxvif; ++iter->ct) { - if (!MIF_EXISTS(net, iter->ct)) + struct mr6_table *mrt = iter->mrt; + + for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { + if (!MIF_EXISTS(mrt, iter->ct)) continue; if (pos-- == 0) - return &net->ipv6.vif6_table[iter->ct]; + return &mrt->vif6_table[iter->ct]; } return NULL; } @@ -150,7 +390,15 @@ static struct mif_device *ip6mr_vif_seq_idx(struct net *net, static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(mrt_lock) { + struct ipmr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) + return ERR_PTR(-ENOENT); + + iter->mrt = mrt; read_lock(&mrt_lock); return *pos ? ip6mr_vif_seq_idx(net, seq->private, *pos - 1) @@ -161,15 +409,16 @@ static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ipmr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt = iter->mrt; ++*pos; if (v == SEQ_START_TOKEN) return ip6mr_vif_seq_idx(net, iter, 0); - while (++iter->ct < net->ipv6.maxvif) { - if (!MIF_EXISTS(net, iter->ct)) + while (++iter->ct < mrt->maxvif) { + if (!MIF_EXISTS(mrt, iter->ct)) continue; - return &net->ipv6.vif6_table[iter->ct]; + return &mrt->vif6_table[iter->ct]; } return NULL; } @@ -182,7 +431,8 @@ static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) { - struct net *net = seq_file_net(seq); + struct ipmr_vif_iter *iter = seq->private; + struct mr6_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -193,7 +443,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", - vif - net->ipv6.vif6_table, + vif - mrt->vif6_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags); @@ -224,8 +474,15 @@ static const struct file_operations ip6mr_vif_fops = { static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { + struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt; + mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) + return ERR_PTR(-ENOENT); + + it->mrt = mrt; return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) : SEQ_START_TOKEN; } @@ -235,35 +492,36 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct mfc6_cache *mfc = v; struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt = it->mrt; ++*pos; if (v == SEQ_START_TOKEN) return ipmr_mfc_seq_idx(net, seq->private, 0); - if (mfc->next) - return mfc->next; + if (mfc->list.next != it->cache) + return list_entry(mfc->list.next, struct mfc6_cache, list); - if (it->cache == &mfc_unres_queue) + if (it->cache == &mrt->mfc6_unres_queue) goto end_of_list; - BUG_ON(it->cache != net->ipv6.mfc6_cache_array); + BUG_ON(it->cache != &mrt->mfc6_cache_array[it->ct]); while (++it->ct < MFC6_LINES) { - mfc = net->ipv6.mfc6_cache_array[it->ct]; - if (mfc) - return mfc; + it->cache = &mrt->mfc6_cache_array[it->ct]; + if (list_empty(it->cache)) + continue; + return list_first_entry(it->cache, struct mfc6_cache, list); } /* exhausted cache_array, show unresolved */ read_unlock(&mrt_lock); - it->cache = &mfc_unres_queue; + it->cache = &mrt->mfc6_unres_queue; it->ct = 0; spin_lock_bh(&mfc_unres_lock); - mfc = mfc_unres_queue; - if (mfc) - return mfc; + if (!list_empty(it->cache)) + return list_first_entry(it->cache, struct mfc6_cache, list); end_of_list: spin_unlock_bh(&mfc_unres_lock); @@ -275,18 +533,17 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) { struct ipmr_mfc_iter *it = seq->private; - struct net *net = seq_file_net(seq); + struct mr6_table *mrt = it->mrt; - if (it->cache == &mfc_unres_queue) + if (it->cache == &mrt->mfc6_unres_queue) spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == net->ipv6.mfc6_cache_array) + else if (it->cache == mrt->mfc6_cache_array) read_unlock(&mrt_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; - struct net *net = seq_file_net(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -296,19 +553,20 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) } else { const struct mfc6_cache *mfc = v; const struct ipmr_mfc_iter *it = seq->private; + struct mr6_table *mrt = it->mrt; seq_printf(seq, "%pI6 %pI6 %-3hd", &mfc->mf6c_mcastgrp, &mfc->mf6c_origin, mfc->mf6c_parent); - if (it->cache != &mfc_unres_queue) { + if (it->cache != &mrt->mfc6_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", mfc->mfc_un.res.pkt, mfc->mfc_un.res.bytes, mfc->mfc_un.res.wrong_if); for (n = mfc->mfc_un.res.minvif; n < mfc->mfc_un.res.maxvif; n++) { - if (MIF_EXISTS(net, n) && + if (MIF_EXISTS(mrt, n) && mfc->mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", @@ -355,7 +613,12 @@ static int pim6_rcv(struct sk_buff *skb) struct ipv6hdr *encap; struct net_device *reg_dev = NULL; struct net *net = dev_net(skb->dev); - int reg_vif_num = net->ipv6.mroute_reg_vif_num; + struct mr6_table *mrt; + struct flowi fl = { + .iif = skb->dev->ifindex, + .mark = skb->mark, + }; + int reg_vif_num; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap))) goto drop; @@ -378,9 +641,13 @@ static int pim6_rcv(struct sk_buff *skb) ntohs(encap->payload_len) + sizeof(*pim) > skb->len) goto drop; + if (ip6mr_fib_lookup(net, &fl, &mrt) < 0) + goto drop; + reg_vif_num = mrt->mroute_reg_vif_num; + read_lock(&mrt_lock); if (reg_vif_num >= 0) - reg_dev = net->ipv6.vif6_table[reg_vif_num].dev; + reg_dev = mrt->vif6_table[reg_vif_num].dev; if (reg_dev) dev_hold(reg_dev); read_unlock(&mrt_lock); @@ -391,14 +658,12 @@ static int pim6_rcv(struct sk_buff *skb) skb->mac_header = skb->network_header; skb_pull(skb, (u8 *)encap - skb->data); skb_reset_network_header(skb); - skb->dev = reg_dev; skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = 0; skb->pkt_type = PACKET_HOST; - skb_dst_drop(skb); - reg_dev->stats.rx_bytes += skb->len; - reg_dev->stats.rx_packets++; - nf_reset(skb); + + skb_tunnel_rx(skb, reg_dev); + netif_rx(skb); dev_put(reg_dev); return 0; @@ -417,12 +682,22 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); + struct mr6_table *mrt; + struct flowi fl = { + .oif = dev->ifindex, + .iif = skb->skb_iif, + .mark = skb->mark, + }; + int err; + + err = ip6mr_fib_lookup(net, &fl, &mrt); + if (err < 0) + return err; read_lock(&mrt_lock); dev->stats.tx_bytes += skb->len; dev->stats.tx_packets++; - ip6mr_cache_report(net, skb, net->ipv6.mroute_reg_vif_num, - MRT6MSG_WHOLEPKT); + ip6mr_cache_report(mrt, skb, mrt->mroute_reg_vif_num, MRT6MSG_WHOLEPKT); read_unlock(&mrt_lock); kfree_skb(skb); return NETDEV_TX_OK; @@ -442,11 +717,17 @@ static void reg_vif_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; } -static struct net_device *ip6mr_reg_vif(struct net *net) +static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt) { struct net_device *dev; + char name[IFNAMSIZ]; + + if (mrt->id == RT6_TABLE_DFLT) + sprintf(name, "pim6reg"); + else + sprintf(name, "pim6reg%u", mrt->id); - dev = alloc_netdev(0, "pim6reg", reg_vif_setup); + dev = alloc_netdev(0, name, reg_vif_setup); if (dev == NULL) return NULL; @@ -478,15 +759,16 @@ failure: * Delete a VIF entry */ -static int mif6_delete(struct net *net, int vifi, struct list_head *head) +static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) { struct mif_device *v; struct net_device *dev; struct inet6_dev *in6_dev; - if (vifi < 0 || vifi >= net->ipv6.maxvif) + + if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; - v = &net->ipv6.vif6_table[vifi]; + v = &mrt->vif6_table[vifi]; write_lock_bh(&mrt_lock); dev = v->dev; @@ -498,17 +780,17 @@ static int mif6_delete(struct net *net, int vifi, struct list_head *head) } #ifdef CONFIG_IPV6_PIMSM_V2 - if (vifi == net->ipv6.mroute_reg_vif_num) - net->ipv6.mroute_reg_vif_num = -1; + if (vifi == mrt->mroute_reg_vif_num) + mrt->mroute_reg_vif_num = -1; #endif - if (vifi + 1 == net->ipv6.maxvif) { + if (vifi + 1 == mrt->maxvif) { int tmp; for (tmp = vifi - 1; tmp >= 0; tmp--) { - if (MIF_EXISTS(net, tmp)) + if (MIF_EXISTS(mrt, tmp)) break; } - net->ipv6.maxvif = tmp + 1; + mrt->maxvif = tmp + 1; } write_unlock_bh(&mrt_lock); @@ -528,7 +810,6 @@ static int mif6_delete(struct net *net, int vifi, struct list_head *head) static inline void ip6mr_cache_free(struct mfc6_cache *c) { - release_net(mfc6_net(c)); kmem_cache_free(mrt_cachep, c); } @@ -536,12 +817,12 @@ static inline void ip6mr_cache_free(struct mfc6_cache *c) and reporting error to netlink readers. */ -static void ip6mr_destroy_unres(struct mfc6_cache *c) +static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c) { + struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; - struct net *net = mfc6_net(c); - atomic_dec(&net->ipv6.cache_resolve_queue_len); + atomic_dec(&mrt->cache_resolve_queue_len); while((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) { if (ipv6_hdr(skb)->version == 0) { @@ -559,60 +840,59 @@ static void ip6mr_destroy_unres(struct mfc6_cache *c) } -/* Single timer process for all the unresolved queue. */ +/* Timer process for all the unresolved queue. */ -static void ipmr_do_expire_process(unsigned long dummy) +static void ipmr_do_expire_process(struct mr6_table *mrt) { unsigned long now = jiffies; unsigned long expires = 10 * HZ; - struct mfc6_cache *c, **cp; - - cp = &mfc_unres_queue; + struct mfc6_cache *c, *next; - while ((c = *cp) != NULL) { + list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { /* not yet... */ unsigned long interval = c->mfc_un.unres.expires - now; if (interval < expires) expires = interval; - cp = &c->next; continue; } - *cp = c->next; - ip6mr_destroy_unres(c); + list_del(&c->list); + ip6mr_destroy_unres(mrt, c); } - if (mfc_unres_queue != NULL) - mod_timer(&ipmr_expire_timer, jiffies + expires); + if (!list_empty(&mrt->mfc6_unres_queue)) + mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); } -static void ipmr_expire_process(unsigned long dummy) +static void ipmr_expire_process(unsigned long arg) { + struct mr6_table *mrt = (struct mr6_table *)arg; + if (!spin_trylock(&mfc_unres_lock)) { - mod_timer(&ipmr_expire_timer, jiffies + 1); + mod_timer(&mrt->ipmr_expire_timer, jiffies + 1); return; } - if (mfc_unres_queue != NULL) - ipmr_do_expire_process(dummy); + if (!list_empty(&mrt->mfc6_unres_queue)) + ipmr_do_expire_process(mrt); spin_unlock(&mfc_unres_lock); } /* Fill oifs list. It is called under write locked mrt_lock. */ -static void ip6mr_update_thresholds(struct mfc6_cache *cache, unsigned char *ttls) +static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *cache, + unsigned char *ttls) { int vifi; - struct net *net = mfc6_net(cache); cache->mfc_un.res.minvif = MAXMIFS; cache->mfc_un.res.maxvif = 0; memset(cache->mfc_un.res.ttls, 255, MAXMIFS); - for (vifi = 0; vifi < net->ipv6.maxvif; vifi++) { - if (MIF_EXISTS(net, vifi) && + for (vifi = 0; vifi < mrt->maxvif; vifi++) { + if (MIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) @@ -623,16 +903,17 @@ static void ip6mr_update_thresholds(struct mfc6_cache *cache, unsigned char *ttl } } -static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock) +static int mif6_add(struct net *net, struct mr6_table *mrt, + struct mif6ctl *vifc, int mrtsock) { int vifi = vifc->mif6c_mifi; - struct mif_device *v = &net->ipv6.vif6_table[vifi]; + struct mif_device *v = &mrt->vif6_table[vifi]; struct net_device *dev; struct inet6_dev *in6_dev; int err; /* Is vif busy ? */ - if (MIF_EXISTS(net, vifi)) + if (MIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->mif6c_flags) { @@ -642,9 +923,9 @@ static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock) * Special Purpose VIF in PIM * All the packets will be sent to the daemon */ - if (net->ipv6.mroute_reg_vif_num >= 0) + if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; - dev = ip6mr_reg_vif(net); + dev = ip6mr_reg_vif(net, mrt); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); @@ -694,50 +975,48 @@ static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock) v->dev = dev; #ifdef CONFIG_IPV6_PIMSM_V2 if (v->flags & MIFF_REGISTER) - net->ipv6.mroute_reg_vif_num = vifi; + mrt->mroute_reg_vif_num = vifi; #endif - if (vifi + 1 > net->ipv6.maxvif) - net->ipv6.maxvif = vifi + 1; + if (vifi + 1 > mrt->maxvif) + mrt->maxvif = vifi + 1; write_unlock_bh(&mrt_lock); return 0; } -static struct mfc6_cache *ip6mr_cache_find(struct net *net, +static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt, struct in6_addr *origin, struct in6_addr *mcastgrp) { int line = MFC6_HASH(mcastgrp, origin); struct mfc6_cache *c; - for (c = net->ipv6.mfc6_cache_array[line]; c; c = c->next) { + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, origin) && ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) - break; + return c; } - return c; + return NULL; } /* * Allocate a multicast cache entry */ -static struct mfc6_cache *ip6mr_cache_alloc(struct net *net) +static struct mfc6_cache *ip6mr_cache_alloc(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (c == NULL) return NULL; c->mfc_un.res.minvif = MAXMIFS; - mfc6_net_set(c, net); return c; } -static struct mfc6_cache *ip6mr_cache_alloc_unres(struct net *net) +static struct mfc6_cache *ip6mr_cache_alloc_unres(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (c == NULL) return NULL; skb_queue_head_init(&c->mfc_un.unres.unresolved); c->mfc_un.unres.expires = jiffies + 10 * HZ; - mfc6_net_set(c, net); return c; } @@ -745,7 +1024,8 @@ static struct mfc6_cache *ip6mr_cache_alloc_unres(struct net *net) * A cache entry has gone into a resolved state from queued */ -static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c) +static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, + struct mfc6_cache *uc, struct mfc6_cache *c) { struct sk_buff *skb; @@ -758,7 +1038,7 @@ static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c) int err; struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr)); - if (ip6mr_fill_mroute(skb, c, NLMSG_DATA(nlh)) > 0) { + if (__ip6mr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; @@ -766,9 +1046,9 @@ static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c) skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -EMSGSIZE; } - err = rtnl_unicast(skb, mfc6_net(uc), NETLINK_CB(skb).pid); + err = rtnl_unicast(skb, net, NETLINK_CB(skb).pid); } else - ip6_mr_forward(skb, c); + ip6_mr_forward(net, mrt, skb, c); } } @@ -779,8 +1059,8 @@ static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c) * Called under mrt_lock. */ -static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, - int assert) +static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, + mifi_t mifi, int assert) { struct sk_buff *skb; struct mrt6msg *msg; @@ -816,7 +1096,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, msg = (struct mrt6msg *)skb_transport_header(skb); msg->im6_mbz = 0; msg->im6_msgtype = MRT6MSG_WHOLEPKT; - msg->im6_mif = net->ipv6.mroute_reg_vif_num; + msg->im6_mif = mrt->mroute_reg_vif_num; msg->im6_pad = 0; ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr); ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr); @@ -851,7 +1131,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, skb->ip_summed = CHECKSUM_UNNECESSARY; } - if (net->ipv6.mroute6_sk == NULL) { + if (mrt->mroute6_sk == NULL) { kfree_skb(skb); return -EINVAL; } @@ -859,7 +1139,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, /* * Deliver to user space multicast routing algorithms */ - ret = sock_queue_rcv_skb(net->ipv6.mroute6_sk, skb); + ret = sock_queue_rcv_skb(mrt->mroute6_sk, skb); if (ret < 0) { if (net_ratelimit()) printk(KERN_WARNING "mroute6: pending queue full, dropping entries.\n"); @@ -874,26 +1154,28 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, */ static int -ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) +ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) { + bool found = false; int err; struct mfc6_cache *c; spin_lock_bh(&mfc_unres_lock); - for (c = mfc_unres_queue; c; c = c->next) { - if (net_eq(mfc6_net(c), net) && - ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && - ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) + list_for_each_entry(c, &mrt->mfc6_unres_queue, list) { + if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && + ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) { + found = true; break; + } } - if (c == NULL) { + if (!found) { /* * Create a new entry if allowable */ - if (atomic_read(&net->ipv6.cache_resolve_queue_len) >= 10 || - (c = ip6mr_cache_alloc_unres(net)) == NULL) { + if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 || + (c = ip6mr_cache_alloc_unres()) == NULL) { spin_unlock_bh(&mfc_unres_lock); kfree_skb(skb); @@ -910,7 +1192,7 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) /* * Reflect first query at pim6sd */ - err = ip6mr_cache_report(net, skb, mifi, MRT6MSG_NOCACHE); + err = ip6mr_cache_report(mrt, skb, mifi, MRT6MSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker @@ -922,11 +1204,10 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) return err; } - atomic_inc(&net->ipv6.cache_resolve_queue_len); - c->next = mfc_unres_queue; - mfc_unres_queue = c; + atomic_inc(&mrt->cache_resolve_queue_len); + list_add(&c->list, &mrt->mfc6_unres_queue); - ipmr_do_expire_process(1); + ipmr_do_expire_process(mrt); } /* @@ -948,19 +1229,18 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) * MFC6 cache manipulation by user space */ -static int ip6mr_mfc_delete(struct net *net, struct mf6cctl *mfc) +static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc) { int line; - struct mfc6_cache *c, **cp; + struct mfc6_cache *c, *next; line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); - for (cp = &net->ipv6.mfc6_cache_array[line]; - (c = *cp) != NULL; cp = &c->next) { + list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { write_lock_bh(&mrt_lock); - *cp = c->next; + list_del(&c->list); write_unlock_bh(&mrt_lock); ip6mr_cache_free(c); @@ -975,6 +1255,7 @@ static int ip6mr_device_event(struct notifier_block *this, { struct net_device *dev = ptr; struct net *net = dev_net(dev); + struct mr6_table *mrt; struct mif_device *v; int ct; LIST_HEAD(list); @@ -982,10 +1263,12 @@ static int ip6mr_device_event(struct notifier_block *this, if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; - v = &net->ipv6.vif6_table[0]; - for (ct = 0; ct < net->ipv6.maxvif; ct++, v++) { - if (v->dev == dev) - mif6_delete(net, ct, &list); + ip6mr_for_each_table(mrt, net) { + v = &mrt->vif6_table[0]; + for (ct = 0; ct < mrt->maxvif; ct++, v++) { + if (v->dev == dev) + mif6_delete(mrt, ct, &list); + } } unregister_netdevice_many(&list); @@ -1002,26 +1285,11 @@ static struct notifier_block ip6_mr_notifier = { static int __net_init ip6mr_net_init(struct net *net) { - int err = 0; - net->ipv6.vif6_table = kcalloc(MAXMIFS, sizeof(struct mif_device), - GFP_KERNEL); - if (!net->ipv6.vif6_table) { - err = -ENOMEM; - goto fail; - } - - /* Forwarding cache */ - net->ipv6.mfc6_cache_array = kcalloc(MFC6_LINES, - sizeof(struct mfc6_cache *), - GFP_KERNEL); - if (!net->ipv6.mfc6_cache_array) { - err = -ENOMEM; - goto fail_mfc6_cache; - } + int err; -#ifdef CONFIG_IPV6_PIMSM_V2 - net->ipv6.mroute_reg_vif_num = -1; -#endif + err = ip6mr_rules_init(net); + if (err < 0) + goto fail; #ifdef CONFIG_PROC_FS err = -ENOMEM; @@ -1030,16 +1298,15 @@ static int __net_init ip6mr_net_init(struct net *net) if (!proc_net_fops_create(net, "ip6_mr_cache", 0, &ip6mr_mfc_fops)) goto proc_cache_fail; #endif + return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: proc_net_remove(net, "ip6_mr_vif"); proc_vif_fail: - kfree(net->ipv6.mfc6_cache_array); + ip6mr_rules_exit(net); #endif -fail_mfc6_cache: - kfree(net->ipv6.vif6_table); fail: return err; } @@ -1050,9 +1317,7 @@ static void __net_exit ip6mr_net_exit(struct net *net) proc_net_remove(net, "ip6_mr_cache"); proc_net_remove(net, "ip6_mr_vif"); #endif - mroute_clean_tables(net); - kfree(net->ipv6.mfc6_cache_array); - kfree(net->ipv6.vif6_table); + ip6mr_rules_exit(net); } static struct pernet_operations ip6mr_net_ops = { @@ -1075,7 +1340,6 @@ int __init ip6_mr_init(void) if (err) goto reg_pernet_fail; - setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0); err = register_netdevice_notifier(&ip6_mr_notifier); if (err) goto reg_notif_fail; @@ -1086,13 +1350,13 @@ int __init ip6_mr_init(void) goto add_proto_fail; } #endif + rtnl_register(RTNL_FAMILY_IP6MR, RTM_GETROUTE, NULL, ip6mr_rtm_dumproute); return 0; #ifdef CONFIG_IPV6_PIMSM_V2 add_proto_fail: unregister_netdevice_notifier(&ip6_mr_notifier); #endif reg_notif_fail: - del_timer(&ipmr_expire_timer); unregister_pernet_subsys(&ip6mr_net_ops); reg_pernet_fail: kmem_cache_destroy(mrt_cachep); @@ -1102,15 +1366,16 @@ reg_pernet_fail: void ip6_mr_cleanup(void) { unregister_netdevice_notifier(&ip6_mr_notifier); - del_timer(&ipmr_expire_timer); unregister_pernet_subsys(&ip6mr_net_ops); kmem_cache_destroy(mrt_cachep); } -static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) +static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, + struct mf6cctl *mfc, int mrtsock) { + bool found = false; int line; - struct mfc6_cache *uc, *c, **cp; + struct mfc6_cache *uc, *c; unsigned char ttls[MAXMIFS]; int i; @@ -1126,17 +1391,18 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); - for (cp = &net->ipv6.mfc6_cache_array[line]; - (c = *cp) != NULL; cp = &c->next) { + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) + ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { + found = true; break; + } } - if (c != NULL) { + if (found) { write_lock_bh(&mrt_lock); c->mf6c_parent = mfc->mf6cc_parent; - ip6mr_update_thresholds(c, ttls); + ip6mr_update_thresholds(mrt, c, ttls); if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); @@ -1146,43 +1412,42 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) if (!ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) return -EINVAL; - c = ip6mr_cache_alloc(net); + c = ip6mr_cache_alloc(); if (c == NULL) return -ENOMEM; c->mf6c_origin = mfc->mf6cc_origin.sin6_addr; c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr; c->mf6c_parent = mfc->mf6cc_parent; - ip6mr_update_thresholds(c, ttls); + ip6mr_update_thresholds(mrt, c, ttls); if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_lock_bh(&mrt_lock); - c->next = net->ipv6.mfc6_cache_array[line]; - net->ipv6.mfc6_cache_array[line] = c; + list_add(&c->list, &mrt->mfc6_cache_array[line]); write_unlock_bh(&mrt_lock); /* * Check to see if we resolved a queued list. If so we * need to send on the frames and tidy up. */ + found = false; spin_lock_bh(&mfc_unres_lock); - for (cp = &mfc_unres_queue; (uc = *cp) != NULL; - cp = &uc->next) { - if (net_eq(mfc6_net(uc), net) && - ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && + list_for_each_entry(uc, &mrt->mfc6_unres_queue, list) { + if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { - *cp = uc->next; - atomic_dec(&net->ipv6.cache_resolve_queue_len); + list_del(&uc->list); + atomic_dec(&mrt->cache_resolve_queue_len); + found = true; break; } } - if (mfc_unres_queue == NULL) - del_timer(&ipmr_expire_timer); + if (list_empty(&mrt->mfc6_unres_queue)) + del_timer(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); - if (uc) { - ip6mr_cache_resolve(uc, c); + if (found) { + ip6mr_cache_resolve(net, mrt, uc, c); ip6mr_cache_free(uc); } return 0; @@ -1192,17 +1457,18 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) * Close the multicast socket, and clear the vif tables etc */ -static void mroute_clean_tables(struct net *net) +static void mroute_clean_tables(struct mr6_table *mrt) { int i; LIST_HEAD(list); + struct mfc6_cache *c, *next; /* * 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, &list); + for (i = 0; i < mrt->maxvif; i++) { + if (!(mrt->vif6_table[i].flags & VIFF_STATIC)) + mif6_delete(mrt, i, &list); } unregister_netdevice_many(&list); @@ -1210,48 +1476,36 @@ static void mroute_clean_tables(struct net *net) * Wipe the cache */ for (i = 0; i < MFC6_LINES; i++) { - struct mfc6_cache *c, **cp; - - cp = &net->ipv6.mfc6_cache_array[i]; - while ((c = *cp) != NULL) { - if (c->mfc_flags & MFC_STATIC) { - cp = &c->next; + list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) { + if (c->mfc_flags & MFC_STATIC) continue; - } write_lock_bh(&mrt_lock); - *cp = c->next; + list_del(&c->list); write_unlock_bh(&mrt_lock); ip6mr_cache_free(c); } } - if (atomic_read(&net->ipv6.cache_resolve_queue_len) != 0) { - struct mfc6_cache *c, **cp; - + if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); - cp = &mfc_unres_queue; - while ((c = *cp) != NULL) { - if (!net_eq(mfc6_net(c), net)) { - cp = &c->next; - continue; - } - *cp = c->next; - ip6mr_destroy_unres(c); + list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { + list_del(&c->list); + ip6mr_destroy_unres(mrt, c); } spin_unlock_bh(&mfc_unres_lock); } } -static int ip6mr_sk_init(struct sock *sk) +static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk) { int err = 0; struct net *net = sock_net(sk); rtnl_lock(); write_lock_bh(&mrt_lock); - if (likely(net->ipv6.mroute6_sk == NULL)) { - net->ipv6.mroute6_sk = sk; + if (likely(mrt->mroute6_sk == NULL)) { + mrt->mroute6_sk = sk; net->ipv6.devconf_all->mc_forwarding++; } else @@ -1265,24 +1519,43 @@ static int ip6mr_sk_init(struct sock *sk) int ip6mr_sk_done(struct sock *sk) { - int err = 0; + int err = -EACCES; struct net *net = sock_net(sk); + struct mr6_table *mrt; rtnl_lock(); - if (sk == net->ipv6.mroute6_sk) { - write_lock_bh(&mrt_lock); - net->ipv6.mroute6_sk = NULL; - net->ipv6.devconf_all->mc_forwarding--; - write_unlock_bh(&mrt_lock); + ip6mr_for_each_table(mrt, net) { + if (sk == mrt->mroute6_sk) { + write_lock_bh(&mrt_lock); + mrt->mroute6_sk = NULL; + net->ipv6.devconf_all->mc_forwarding--; + write_unlock_bh(&mrt_lock); - mroute_clean_tables(net); - } else - err = -EACCES; + mroute_clean_tables(mrt); + err = 0; + break; + } + } rtnl_unlock(); return err; } +struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) +{ + struct mr6_table *mrt; + struct flowi fl = { + .iif = skb->skb_iif, + .oif = skb->dev->ifindex, + .mark = skb->mark, + }; + + if (ip6mr_fib_lookup(net, &fl, &mrt) < 0) + return NULL; + + return mrt->mroute6_sk; +} + /* * Socket options and virtual interface manipulation. The whole * virtual interface system is a complete heap, but unfortunately @@ -1297,9 +1570,14 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns struct mf6cctl mfc; mifi_t mifi; struct net *net = sock_net(sk); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; if (optname != MRT6_INIT) { - if (sk != net->ipv6.mroute6_sk && !capable(CAP_NET_ADMIN)) + if (sk != mrt->mroute6_sk && !capable(CAP_NET_ADMIN)) return -EACCES; } @@ -1311,7 +1589,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (optlen < sizeof(int)) return -EINVAL; - return ip6mr_sk_init(sk); + return ip6mr_sk_init(mrt, sk); case MRT6_DONE: return ip6mr_sk_done(sk); @@ -1324,7 +1602,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (vif.mif6c_mifi >= MAXMIFS) return -ENFILE; rtnl_lock(); - ret = mif6_add(net, &vif, sk == net->ipv6.mroute6_sk); + ret = mif6_add(net, mrt, &vif, sk == mrt->mroute6_sk); rtnl_unlock(); return ret; @@ -1334,7 +1612,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (copy_from_user(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); - ret = mif6_delete(net, mifi, NULL); + ret = mif6_delete(mrt, mifi, NULL); rtnl_unlock(); return ret; @@ -1350,10 +1628,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns return -EFAULT; rtnl_lock(); if (optname == MRT6_DEL_MFC) - ret = ip6mr_mfc_delete(net, &mfc); + ret = ip6mr_mfc_delete(mrt, &mfc); else - ret = ip6mr_mfc_add(net, &mfc, - sk == net->ipv6.mroute6_sk); + ret = ip6mr_mfc_add(net, mrt, &mfc, sk == mrt->mroute6_sk); rtnl_unlock(); return ret; @@ -1365,7 +1642,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns int v; if (get_user(v, (int __user *)optval)) return -EFAULT; - net->ipv6.mroute_do_assert = !!v; + mrt->mroute_do_assert = !!v; return 0; } @@ -1378,15 +1655,36 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns v = !!v; rtnl_lock(); ret = 0; - if (v != net->ipv6.mroute_do_pim) { - net->ipv6.mroute_do_pim = v; - net->ipv6.mroute_do_assert = v; + if (v != mrt->mroute_do_pim) { + mrt->mroute_do_pim = v; + mrt->mroute_do_assert = v; } rtnl_unlock(); return ret; } #endif +#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES + case MRT6_TABLE: + { + u32 v; + + if (optlen != sizeof(u32)) + return -EINVAL; + if (get_user(v, (u32 __user *)optval)) + return -EFAULT; + if (sk == mrt->mroute6_sk) + return -EBUSY; + + rtnl_lock(); + ret = 0; + if (!ip6mr_new_table(net, v)) + ret = -ENOMEM; + raw6_sk(sk)->ip6mr_table = v; + rtnl_unlock(); + return ret; + } +#endif /* * Spurious command, or MRT6_VERSION which you cannot * set. @@ -1406,6 +1704,11 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int olr; int val; struct net *net = sock_net(sk); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; switch (optname) { case MRT6_VERSION: @@ -1413,11 +1716,11 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, break; #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: - val = net->ipv6.mroute_do_pim; + val = mrt->mroute_do_pim; break; #endif case MRT6_ASSERT: - val = net->ipv6.mroute_do_assert; + val = mrt->mroute_do_assert; break; default: return -ENOPROTOOPT; @@ -1448,16 +1751,21 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) struct mif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; switch (cmd) { case SIOCGETMIFCNT_IN6: if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; - if (vr.mifi >= net->ipv6.maxvif) + if (vr.mifi >= mrt->maxvif) return -EINVAL; read_lock(&mrt_lock); - vif = &net->ipv6.vif6_table[vr.mifi]; - if (MIF_EXISTS(net, vr.mifi)) { + vif = &mrt->vif6_table[vr.mifi]; + if (MIF_EXISTS(mrt, vr.mifi)) { vr.icount = vif->pkt_in; vr.ocount = vif->pkt_out; vr.ibytes = vif->bytes_in; @@ -1475,7 +1783,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) return -EFAULT; read_lock(&mrt_lock); - c = ip6mr_cache_find(net, &sr.src.sin6_addr, &sr.grp.sin6_addr); + c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { sr.pktcnt = c->mfc_un.res.pkt; sr.bytecnt = c->mfc_un.res.bytes; @@ -1505,11 +1813,11 @@ static inline int ip6mr_forward2_finish(struct sk_buff *skb) * Processing handlers for ip6mr_forward */ -static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi) +static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *c, int vifi) { struct ipv6hdr *ipv6h; - struct net *net = mfc6_net(c); - struct mif_device *vif = &net->ipv6.vif6_table[vifi]; + struct mif_device *vif = &mrt->vif6_table[vifi]; struct net_device *dev; struct dst_entry *dst; struct flowi fl; @@ -1523,7 +1831,7 @@ static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi) vif->bytes_out += skb->len; vif->dev->stats.tx_bytes += skb->len; vif->dev->stats.tx_packets++; - ip6mr_cache_report(net, skb, vifi, MRT6MSG_WHOLEPKT); + ip6mr_cache_report(mrt, skb, vifi, MRT6MSG_WHOLEPKT); goto out_free; } #endif @@ -1570,7 +1878,7 @@ static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi) IP6CB(skb)->flags |= IP6SKB_FORWARDED; - return NF_HOOK(PF_INET6, NF_INET_FORWARD, skb, skb->dev, dev, + return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dev, ip6mr_forward2_finish); out_free: @@ -1578,22 +1886,22 @@ out_free: return 0; } -static int ip6mr_find_vif(struct net_device *dev) +static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev) { - struct net *net = dev_net(dev); int ct; - for (ct = net->ipv6.maxvif - 1; ct >= 0; ct--) { - if (net->ipv6.vif6_table[ct].dev == dev) + + for (ct = mrt->maxvif - 1; ct >= 0; ct--) { + if (mrt->vif6_table[ct].dev == dev) break; } return ct; } -static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache) +static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache) { int psend = -1; int vif, ct; - struct net *net = mfc6_net(cache); vif = cache->mf6c_parent; cache->mfc_un.res.pkt++; @@ -1602,30 +1910,30 @@ static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache) /* * Wrong interface: drop packet and (maybe) send PIM assert. */ - if (net->ipv6.vif6_table[vif].dev != skb->dev) { + if (mrt->vif6_table[vif].dev != skb->dev) { int true_vifi; cache->mfc_un.res.wrong_if++; - true_vifi = ip6mr_find_vif(skb->dev); + true_vifi = ip6mr_find_vif(mrt, skb->dev); - if (true_vifi >= 0 && net->ipv6.mroute_do_assert && + if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, so that we cannot check that packet arrived on an oif. It is bad, but otherwise we would need to move pretty large chunk of pimd to kernel. Ough... --ANK */ - (net->ipv6.mroute_do_pim || + (mrt->mroute_do_pim || cache->mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { cache->mfc_un.res.last_assert = jiffies; - ip6mr_cache_report(net, skb, true_vifi, MRT6MSG_WRONGMIF); + ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRONGMIF); } goto dont_forward; } - net->ipv6.vif6_table[vif].pkt_in++; - net->ipv6.vif6_table[vif].bytes_in += skb->len; + mrt->vif6_table[vif].pkt_in++; + mrt->vif6_table[vif].bytes_in += skb->len; /* * Forward the frame @@ -1635,13 +1943,13 @@ static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache) if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ip6mr_forward2(skb2, cache, psend); + ip6mr_forward2(net, mrt, skb2, cache, psend); } psend = ct; } } if (psend != -1) { - ip6mr_forward2(skb, cache, psend); + ip6mr_forward2(net, mrt, skb, cache, psend); return 0; } @@ -1659,9 +1967,19 @@ int ip6_mr_input(struct sk_buff *skb) { struct mfc6_cache *cache; struct net *net = dev_net(skb->dev); + struct mr6_table *mrt; + struct flowi fl = { + .iif = skb->dev->ifindex, + .mark = skb->mark, + }; + int err; + + err = ip6mr_fib_lookup(net, &fl, &mrt); + if (err < 0) + return err; read_lock(&mrt_lock); - cache = ip6mr_cache_find(net, + cache = ip6mr_cache_find(mrt, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); /* @@ -1670,9 +1988,9 @@ int ip6_mr_input(struct sk_buff *skb) if (cache == NULL) { int vif; - vif = ip6mr_find_vif(skb->dev); + vif = ip6mr_find_vif(mrt, skb->dev); if (vif >= 0) { - int err = ip6mr_cache_unresolved(net, vif, skb); + int err = ip6mr_cache_unresolved(mrt, vif, skb); read_unlock(&mrt_lock); return err; @@ -1682,7 +2000,7 @@ int ip6_mr_input(struct sk_buff *skb) return -ENODEV; } - ip6_mr_forward(skb, cache); + ip6_mr_forward(net, mrt, skb, cache); read_unlock(&mrt_lock); @@ -1690,12 +2008,11 @@ int ip6_mr_input(struct sk_buff *skb) } -static int -ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm) +static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, + struct mfc6_cache *c, struct rtmsg *rtm) { int ct; struct rtnexthop *nhp; - struct net *net = mfc6_net(c); u8 *b = skb_tail_pointer(skb); struct rtattr *mp_head; @@ -1703,19 +2020,19 @@ ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm) if (c->mf6c_parent > MAXMIFS) return -ENOENT; - if (MIF_EXISTS(net, c->mf6c_parent)) - RTA_PUT(skb, RTA_IIF, 4, &net->ipv6.vif6_table[c->mf6c_parent].dev->ifindex); + if (MIF_EXISTS(mrt, c->mf6c_parent)) + RTA_PUT(skb, RTA_IIF, 4, &mrt->vif6_table[c->mf6c_parent].dev->ifindex); mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0)); for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { - if (MIF_EXISTS(net, ct) && c->mfc_un.res.ttls[ct] < 255) { + if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) goto rtattr_failure; nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); nhp->rtnh_flags = 0; nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; - nhp->rtnh_ifindex = net->ipv6.vif6_table[ct].dev->ifindex; + nhp->rtnh_ifindex = mrt->vif6_table[ct].dev->ifindex; nhp->rtnh_len = sizeof(*nhp); } } @@ -1733,11 +2050,16 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, int nowait) { int err; + struct mr6_table *mrt; struct mfc6_cache *cache; struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; + read_lock(&mrt_lock); - cache = ip6mr_cache_find(net, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); + cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); if (!cache) { struct sk_buff *skb2; @@ -1751,7 +2073,7 @@ int ip6mr_get_route(struct net *net, } dev = skb->dev; - if (dev == NULL || (vif = ip6mr_find_vif(dev)) < 0) { + if (dev == NULL || (vif = ip6mr_find_vif(mrt, dev)) < 0) { read_unlock(&mrt_lock); return -ENODEV; } @@ -1780,7 +2102,7 @@ int ip6mr_get_route(struct net *net, ipv6_addr_copy(&iph->saddr, &rt->rt6i_src.addr); ipv6_addr_copy(&iph->daddr, &rt->rt6i_dst.addr); - err = ip6mr_cache_unresolved(net, vif, skb2); + err = ip6mr_cache_unresolved(mrt, vif, skb2); read_unlock(&mrt_lock); return err; @@ -1789,8 +2111,88 @@ int ip6mr_get_route(struct net *net, if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY)) cache->mfc_flags |= MFC_NOTIFY; - err = ip6mr_fill_mroute(skb, cache, rtm); + err = __ip6mr_fill_mroute(mrt, skb, cache, rtm); read_unlock(&mrt_lock); return err; } +static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, + u32 pid, u32 seq, struct mfc6_cache *c) +{ + struct nlmsghdr *nlh; + struct rtmsg *rtm; + + nlh = nlmsg_put(skb, pid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); + if (nlh == NULL) + return -EMSGSIZE; + + rtm = nlmsg_data(nlh); + rtm->rtm_family = RTNL_FAMILY_IPMR; + rtm->rtm_dst_len = 128; + rtm->rtm_src_len = 128; + rtm->rtm_tos = 0; + rtm->rtm_table = mrt->id; + NLA_PUT_U32(skb, RTA_TABLE, mrt->id); + rtm->rtm_scope = RT_SCOPE_UNIVERSE; + rtm->rtm_protocol = RTPROT_UNSPEC; + rtm->rtm_flags = 0; + + NLA_PUT(skb, RTA_SRC, 16, &c->mf6c_origin); + NLA_PUT(skb, RTA_DST, 16, &c->mf6c_mcastgrp); + + if (__ip6mr_fill_mroute(mrt, skb, c, rtm) < 0) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct mr6_table *mrt; + struct mfc6_cache *mfc; + unsigned int t = 0, s_t; + unsigned int h = 0, s_h; + unsigned int e = 0, s_e; + + s_t = cb->args[0]; + s_h = cb->args[1]; + s_e = cb->args[2]; + + read_lock(&mrt_lock); + ip6mr_for_each_table(mrt, net) { + if (t < s_t) + goto next_table; + if (t > s_t) + s_h = 0; + for (h = s_h; h < MFC6_LINES; h++) { + list_for_each_entry(mfc, &mrt->mfc6_cache_array[h], list) { + if (e < s_e) + goto next_entry; + if (ip6mr_fill_mroute(mrt, skb, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + mfc) < 0) + goto done; +next_entry: + e++; + } + e = s_e = 0; + } + s_h = 0; +next_table: + t++; + } +done: + read_unlock(&mrt_lock); + + cb->args[2] = e; + cb->args[1] = h; + cb->args[0] = t; + + return skb->len; +} diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 33f60fca7aa..bd43f0152c2 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -114,9 +114,9 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, } opt = xchg(&inet6_sk(sk)->opt, opt); } else { - write_lock(&sk->sk_dst_lock); + spin_lock(&sk->sk_dst_lock); opt = xchg(&inet6_sk(sk)->opt, opt); - write_unlock(&sk->sk_dst_lock); + spin_unlock(&sk->sk_dst_lock); } sk_dst_reset(sk); @@ -337,6 +337,13 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = 0; break; + case IPV6_RECVPATHMTU: + if (optlen < sizeof(int)) + goto e_inval; + np->rxopt.bits.rxpmtu = valbool; + retv = 0; + break; + case IPV6_HOPOPTS: case IPV6_RTHDRDSTOPTS: case IPV6_RTHDR: @@ -451,7 +458,8 @@ sticky_done: msg.msg_controllen = optlen; msg.msg_control = (void*)(opt+1); - retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk); + retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk, + &junk); if (retv) goto done; update: @@ -767,6 +775,17 @@ pref_skip_coa: break; } + case IPV6_MINHOPCOUNT: + if (optlen < sizeof(int)) + goto e_inval; + if (val < 0 || val > 255) + goto e_inval; + np->min_hopcount = val; + break; + case IPV6_DONTFRAG: + np->dontfrag = valbool; + retv = 0; + break; } release_sock(sk); @@ -971,14 +990,13 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, case IPV6_MTU: { struct dst_entry *dst; + val = 0; - lock_sock(sk); - dst = sk_dst_get(sk); - if (dst) { + rcu_read_lock(); + dst = __sk_dst_get(sk); + if (dst) val = dst_mtu(dst); - dst_release(dst); - } - release_sock(sk); + rcu_read_unlock(); if (!val) return -ENOTCONN; break; @@ -1056,6 +1074,38 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->rxopt.bits.rxflow; break; + case IPV6_RECVPATHMTU: + val = np->rxopt.bits.rxpmtu; + break; + + case IPV6_PATHMTU: + { + struct dst_entry *dst; + struct ip6_mtuinfo mtuinfo; + + if (len < sizeof(mtuinfo)) + return -EINVAL; + + len = sizeof(mtuinfo); + memset(&mtuinfo, 0, sizeof(mtuinfo)); + + rcu_read_lock(); + dst = __sk_dst_get(sk); + if (dst) + mtuinfo.ip6m_mtu = dst_mtu(dst); + rcu_read_unlock(); + if (!mtuinfo.ip6m_mtu) + return -ENOTCONN; + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &mtuinfo, len)) + return -EFAULT; + + return 0; + break; + } + case IPV6_UNICAST_HOPS: case IPV6_MULTICAST_HOPS: { @@ -1066,12 +1116,14 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, else val = np->mcast_hops; - dst = sk_dst_get(sk); - if (dst) { - if (val < 0) + if (val < 0) { + rcu_read_lock(); + dst = __sk_dst_get(sk); + if (dst) val = ip6_dst_hoplimit(dst); - dst_release(dst); + rcu_read_unlock(); } + if (val < 0) val = sock_net(sk)->ipv6.devconf_all->hop_limit; break; @@ -1115,6 +1167,14 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val |= IPV6_PREFER_SRC_HOME; break; + case IPV6_MINHOPCOUNT: + val = np->min_hopcount; + break; + + case IPV6_DONTFRAG: + val = np->dontfrag; + break; + default: return -ENOPROTOOPT; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index c483ab9fd67..59f1881968c 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -44,6 +44,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> +#include <net/mld.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> @@ -71,54 +72,11 @@ #define MDBG(x) #endif -/* - * These header formats should be in a separate include file, but icmpv6.h - * doesn't have in6_addr defined in all cases, there is no __u128, and no - * other files reference these. - * - * +-DLS 4/14/03 - */ - -/* Multicast Listener Discovery version 2 headers */ - -struct mld2_grec { - __u8 grec_type; - __u8 grec_auxwords; - __be16 grec_nsrcs; - struct in6_addr grec_mca; - struct in6_addr grec_src[0]; -}; - -struct mld2_report { - __u8 type; - __u8 resv1; - __sum16 csum; - __be16 resv2; - __be16 ngrec; - struct mld2_grec grec[0]; -}; - -struct mld2_query { - __u8 type; - __u8 code; - __sum16 csum; - __be16 mrc; - __be16 resv1; - struct in6_addr mca; -#if defined(__LITTLE_ENDIAN_BITFIELD) - __u8 qrv:3, - suppress:1, - resv2:4; -#elif defined(__BIG_ENDIAN_BITFIELD) - __u8 resv2:4, - suppress:1, - qrv:3; -#else -#error "Please fix <asm/byteorder.h>" -#endif - __u8 qqic; - __be16 nsrcs; - struct in6_addr srcs[0]; +/* Ensure that we have struct in6_addr aligned on 32bit word. */ +static void *__mld2_query_bugs[] __attribute__((__unused__)) = { + BUILD_BUG_ON_NULL(offsetof(struct mld2_query, mld2q_srcs) % 4), + BUILD_BUG_ON_NULL(offsetof(struct mld2_report, mld2r_grec) % 4), + BUILD_BUG_ON_NULL(offsetof(struct mld2_grec, grec_mca) % 4) }; static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT; @@ -157,14 +115,6 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, ((idev)->mc_v1_seen && \ time_before(jiffies, (idev)->mc_v1_seen))) -#define MLDV2_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value)) -#define MLDV2_EXP(thresh, nbmant, nbexp, value) \ - ((value) < (thresh) ? (value) : \ - ((MLDV2_MASK(value, nbmant) | (1<<(nbmant))) << \ - (MLDV2_MASK((value) >> (nbmant), nbexp) + (nbexp)))) - -#define MLDV2_MRC(value) MLDV2_EXP(0x8000, 12, 3, value) - #define IPV6_MLD_MAX_MSF 64 int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; @@ -715,7 +665,7 @@ static void igmp6_group_added(struct ifmcaddr6 *mc) if (!(mc->mca_flags&MAF_LOADED)) { mc->mca_flags |= MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) - dev_mc_add(dev, buf, dev->addr_len, 0); + dev_mc_add(dev, buf); } spin_unlock_bh(&mc->mca_lock); @@ -741,7 +691,7 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc) if (mc->mca_flags&MAF_LOADED) { mc->mca_flags &= ~MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) - dev_mc_delete(dev, buf, dev->addr_len, 0); + dev_mc_del(dev, buf); } if (mc->mca_flags & MAF_NOREPORT) @@ -1161,7 +1111,7 @@ int igmp6_event_query(struct sk_buff *skb) struct in6_addr *group; unsigned long max_delay; struct inet6_dev *idev; - struct icmp6hdr *hdr; + struct mld_msg *mld; int group_type; int mark = 0; int len; @@ -1182,8 +1132,8 @@ int igmp6_event_query(struct sk_buff *skb) if (idev == NULL) return 0; - hdr = icmp6_hdr(skb); - group = (struct in6_addr *) (hdr + 1); + mld = (struct mld_msg *)icmp6_hdr(skb); + group = &mld->mld_mca; group_type = ipv6_addr_type(group); if (group_type != IPV6_ADDR_ANY && @@ -1197,7 +1147,7 @@ int igmp6_event_query(struct sk_buff *skb) /* MLDv1 router present */ /* Translate milliseconds to jiffies */ - max_delay = (ntohs(hdr->icmp6_maxdelay)*HZ)/1000; + max_delay = (ntohs(mld->mld_maxdelay)*HZ)/1000; switchback = (idev->mc_qrv + 1) * max_delay; idev->mc_v1_seen = jiffies + switchback; @@ -1216,14 +1166,14 @@ int igmp6_event_query(struct sk_buff *skb) return -EINVAL; } mlh2 = (struct mld2_query *)skb_transport_header(skb); - max_delay = (MLDV2_MRC(ntohs(mlh2->mrc))*HZ)/1000; + max_delay = (MLDV2_MRC(ntohs(mlh2->mld2q_mrc))*HZ)/1000; if (!max_delay) max_delay = 1; idev->mc_maxdelay = max_delay; - if (mlh2->qrv) - idev->mc_qrv = mlh2->qrv; + if (mlh2->mld2q_qrv) + idev->mc_qrv = mlh2->mld2q_qrv; if (group_type == IPV6_ADDR_ANY) { /* general query */ - if (mlh2->nsrcs) { + if (mlh2->mld2q_nsrcs) { in6_dev_put(idev); return -EINVAL; /* no sources allowed */ } @@ -1232,9 +1182,9 @@ int igmp6_event_query(struct sk_buff *skb) return 0; } /* mark sources to include, if group & source-specific */ - if (mlh2->nsrcs != 0) { + if (mlh2->mld2q_nsrcs != 0) { if (!pskb_may_pull(skb, srcs_offset + - ntohs(mlh2->nsrcs) * sizeof(struct in6_addr))) { + ntohs(mlh2->mld2q_nsrcs) * sizeof(struct in6_addr))) { in6_dev_put(idev); return -EINVAL; } @@ -1270,7 +1220,7 @@ int igmp6_event_query(struct sk_buff *skb) ma->mca_flags &= ~MAF_GSQUERY; } if (!(ma->mca_flags & MAF_GSQUERY) || - mld_marksources(ma, ntohs(mlh2->nsrcs), mlh2->srcs)) + mld_marksources(ma, ntohs(mlh2->mld2q_nsrcs), mlh2->mld2q_srcs)) igmp6_group_queried(ma, max_delay); spin_unlock_bh(&ma->mca_lock); break; @@ -1286,9 +1236,8 @@ int igmp6_event_query(struct sk_buff *skb) int igmp6_event_report(struct sk_buff *skb) { struct ifmcaddr6 *ma; - struct in6_addr *addrp; struct inet6_dev *idev; - struct icmp6hdr *hdr; + struct mld_msg *mld; int addr_type; /* Our own report looped back. Ignore it. */ @@ -1300,10 +1249,10 @@ int igmp6_event_report(struct sk_buff *skb) skb->pkt_type != PACKET_BROADCAST) return 0; - if (!pskb_may_pull(skb, sizeof(struct in6_addr))) + if (!pskb_may_pull(skb, sizeof(*mld) - sizeof(struct icmp6hdr))) return -EINVAL; - hdr = icmp6_hdr(skb); + mld = (struct mld_msg *)icmp6_hdr(skb); /* Drop reports with not link local source */ addr_type = ipv6_addr_type(&ipv6_hdr(skb)->saddr); @@ -1311,8 +1260,6 @@ int igmp6_event_report(struct sk_buff *skb) !(addr_type&IPV6_ADDR_LINKLOCAL)) return -EINVAL; - addrp = (struct in6_addr *) (hdr + 1); - idev = in6_dev_get(skb->dev); if (idev == NULL) return -ENODEV; @@ -1323,7 +1270,7 @@ int igmp6_event_report(struct sk_buff *skb) read_lock_bh(&idev->lock); for (ma = idev->mc_list; ma; ma=ma->next) { - if (ipv6_addr_equal(&ma->mca_addr, addrp)) { + if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) { spin_lock(&ma->mca_lock); if (del_timer(&ma->mca_timer)) atomic_dec(&ma->mca_refcnt); @@ -1432,11 +1379,11 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size) skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data); skb_put(skb, sizeof(*pmr)); pmr = (struct mld2_report *)skb_transport_header(skb); - pmr->type = ICMPV6_MLD2_REPORT; - pmr->resv1 = 0; - pmr->csum = 0; - pmr->resv2 = 0; - pmr->ngrec = 0; + pmr->mld2r_type = ICMPV6_MLD2_REPORT; + pmr->mld2r_resv1 = 0; + pmr->mld2r_cksum = 0; + pmr->mld2r_resv2 = 0; + pmr->mld2r_ngrec = 0; return skb; } @@ -1458,9 +1405,10 @@ static void mld_sendpack(struct sk_buff *skb) mldlen = skb->tail - skb->transport_header; pip6->payload_len = htons(payload_len); - pmr->csum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, - IPPROTO_ICMPV6, csum_partial(skb_transport_header(skb), - mldlen, 0)); + pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, + IPPROTO_ICMPV6, + csum_partial(skb_transport_header(skb), + mldlen, 0)); dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr); @@ -1480,7 +1428,7 @@ static void mld_sendpack(struct sk_buff *skb) payload_len = skb->len; - err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev, + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev, dst_output); out: if (!err) { @@ -1521,7 +1469,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->mca_addr; /* structure copy */ pmr = (struct mld2_report *)skb_transport_header(skb); - pmr->ngrec = htons(ntohs(pmr->ngrec)+1); + pmr->mld2r_ngrec = htons(ntohs(pmr->mld2r_ngrec)+1); *ppgr = pgr; return skb; } @@ -1557,7 +1505,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { - if (pmr && pmr->ngrec && + if (pmr && pmr->mld2r_ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); @@ -1770,9 +1718,8 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) struct sock *sk = net->ipv6.igmp_sk; struct inet6_dev *idev; struct sk_buff *skb; - struct icmp6hdr *hdr; + struct mld_msg *hdr; const struct in6_addr *snd_addr, *saddr; - struct in6_addr *addrp; struct in6_addr addr_buf; int err, len, payload_len, full_len; u8 ra[8] = { IPPROTO_ICMPV6, 0, @@ -1820,16 +1767,14 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra)); - hdr = (struct icmp6hdr *) skb_put(skb, sizeof(struct icmp6hdr)); - memset(hdr, 0, sizeof(struct icmp6hdr)); - hdr->icmp6_type = type; + hdr = (struct mld_msg *) skb_put(skb, sizeof(struct mld_msg)); + memset(hdr, 0, sizeof(struct mld_msg)); + hdr->mld_type = type; + ipv6_addr_copy(&hdr->mld_mca, addr); - addrp = (struct in6_addr *) skb_put(skb, sizeof(struct in6_addr)); - ipv6_addr_copy(addrp, addr); - - hdr->icmp6_cksum = csum_ipv6_magic(saddr, snd_addr, len, - IPPROTO_ICMPV6, - csum_partial(hdr, len, 0)); + hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len, + IPPROTO_ICMPV6, + csum_partial(hdr, len, 0)); idev = in6_dev_get(skb->dev); @@ -1848,7 +1793,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) goto err_out; skb_dst_set(skb, dst); - err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev, + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev, dst_output); out: if (!err) { diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index da0a4d2adc6..0abdc242ddb 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -536,7 +536,7 @@ void ndisc_send_skb(struct sk_buff *skb, idev = in6_dev_get(dst->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); - err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev, + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev, dst_output); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); @@ -890,8 +890,6 @@ out: in6_ifa_put(ifp); else in6_dev_put(idev); - - return; } static void ndisc_recv_na(struct sk_buff *skb) @@ -1618,7 +1616,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, skb_dst_set(buff, dst); idev = in6_dev_get(dst->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); - err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, buff, NULL, dst->dev, + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, buff, NULL, dst->dev, dst_output); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, NDISC_REDIRECT); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index d5ed92b1434..a74951c039b 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -25,20 +25,6 @@ int ip6_route_me_harder(struct sk_buff *skb) }; dst = ip6_route_output(net, skb->sk, &fl); - -#ifdef CONFIG_XFRM - if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && - xfrm_decode_session(skb, &fl, AF_INET6) == 0) { - struct dst_entry *dst2 = skb_dst(skb); - - if (xfrm_lookup(net, &dst2, &fl, skb->sk, 0)) { - skb_dst_set(skb, NULL); - return -1; - } - skb_dst_set(skb, dst2); - } -#endif - if (dst->error) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n"); @@ -50,6 +36,17 @@ int ip6_route_me_harder(struct sk_buff *skb) skb_dst_drop(skb); skb_dst_set(skb, dst); + +#ifdef CONFIG_XFRM + if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + xfrm_decode_session(skb, &fl, AF_INET6) == 0) { + skb_dst_set(skb, NULL); + if (xfrm_lookup(net, &dst, &fl, skb->sk, 0)) + return -1; + skb_dst_set(skb, dst); + } +#endif + return 0; } EXPORT_SYMBOL(ip6_route_me_harder); diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 6a68a74d14a..8c201743d96 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -162,8 +162,7 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) break; case IPQ_COPY_PACKET: - if ((entry->skb->ip_summed == CHECKSUM_PARTIAL || - entry->skb->ip_summed == CHECKSUM_COMPLETE) && + if (entry->skb->ip_summed == CHECKSUM_PARTIAL && (*errp = skb_checksum_help(entry->skb))) { read_unlock_bh(&queue_lock); return NULL; @@ -463,7 +462,6 @@ __ipq_rcv_skb(struct sk_buff *skb) if (flags & NLM_F_ACK) netlink_ack(skb, nlh, 0); - return; } static void diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 9210e312edf..6f517bd8369 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -40,24 +40,19 @@ MODULE_DESCRIPTION("IPv6 packet filter"); /*#define DEBUG_IP_FIREWALL_USER*/ #ifdef DEBUG_IP_FIREWALL -#define dprintf(format, args...) printk(format , ## args) +#define dprintf(format, args...) pr_info(format , ## args) #else #define dprintf(format, args...) #endif #ifdef DEBUG_IP_FIREWALL_USER -#define duprintf(format, args...) printk(format , ## args) +#define duprintf(format, args...) pr_info(format , ## args) #else #define duprintf(format, args...) #endif #ifdef CONFIG_NETFILTER_DEBUG -#define IP_NF_ASSERT(x) \ -do { \ - if (!(x)) \ - printk("IP_NF_ASSERT: %s:%s:%u\n", \ - __func__, __FILE__, __LINE__); \ -} while(0) +#define IP_NF_ASSERT(x) WARN_ON(!(x)) #else #define IP_NF_ASSERT(x) #endif @@ -197,30 +192,14 @@ ip6_checkentry(const struct ip6t_ip6 *ipv6) } static unsigned int -ip6t_error(struct sk_buff *skb, const struct xt_target_param *par) +ip6t_error(struct sk_buff *skb, const struct xt_action_param *par) { if (net_ratelimit()) - printk("ip6_tables: error: `%s'\n", - (const char *)par->targinfo); + pr_info("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } -/* Performance critical - called for every packet */ -static inline bool -do_match(const struct ip6t_entry_match *m, const struct sk_buff *skb, - struct xt_match_param *par) -{ - par->match = m->u.kernel.match; - par->matchinfo = m->data; - - /* Stop iteration if it doesn't match */ - if (!m->u.kernel.match->match(skb, par)) - return true; - else - return false; -} - static inline struct ip6t_entry * get_entry(const void *base, unsigned int offset) { @@ -352,18 +331,15 @@ ip6t_do_table(struct sk_buff *skb, const struct net_device *out, struct xt_table *table) { -#define tb_comefrom ((struct ip6t_entry *)table_base)->comefrom - static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); - bool hotdrop = false; /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; const void *table_base; - struct ip6t_entry *e, *back; + struct ip6t_entry *e, **jumpstack; + unsigned int *stackptr, origptr, cpu; const struct xt_table_info *private; - struct xt_match_param mtpar; - struct xt_target_param tgpar; + struct xt_action_param acpar; /* Initialization */ indev = in ? in->name : nulldevname; @@ -374,39 +350,42 @@ ip6t_do_table(struct sk_buff *skb, * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ - mtpar.hotdrop = &hotdrop; - mtpar.in = tgpar.in = in; - mtpar.out = tgpar.out = out; - mtpar.family = tgpar.family = NFPROTO_IPV6; - mtpar.hooknum = tgpar.hooknum = hook; + acpar.hotdrop = false; + acpar.in = in; + acpar.out = out; + acpar.family = NFPROTO_IPV6; + acpar.hooknum = hook; IP_NF_ASSERT(table->valid_hooks & (1 << hook)); xt_info_rdlock_bh(); private = table->private; - table_base = private->entries[smp_processor_id()]; + cpu = smp_processor_id(); + table_base = private->entries[cpu]; + jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; + stackptr = &private->stackptr[cpu]; + origptr = *stackptr; e = get_entry(table_base, private->hook_entry[hook]); - /* For return from builtin chain */ - back = get_entry(table_base, private->underflow[hook]); - do { 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)) { + &acpar.thoff, &acpar.fragoff, &acpar.hotdrop)) { no_match: e = ip6t_next_entry(e); continue; } - xt_ematch_foreach(ematch, e) - if (do_match(ematch, skb, &mtpar) != 0) + xt_ematch_foreach(ematch, e) { + acpar.match = ematch->u.kernel.match; + acpar.matchinfo = ematch->data; + if (!acpar.match->match(skb, &acpar)) goto no_match; + } ADD_COUNTER(e->counters, ntohs(ipv6_hdr(skb)->payload_len) + @@ -433,62 +412,47 @@ ip6t_do_table(struct sk_buff *skb, verdict = (unsigned)(-v) - 1; break; } - e = back; - back = get_entry(table_base, back->comefrom); + if (*stackptr == 0) + e = get_entry(table_base, + private->underflow[hook]); + else + e = ip6t_next_entry(jumpstack[--*stackptr]); continue; } 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; - /* set back pointer to next entry */ - back = next; + if (*stackptr >= private->stacksize) { + verdict = NF_DROP; + break; + } + jumpstack[(*stackptr)++] = e; } e = get_entry(table_base, v); continue; } - /* Targets which reenter must return - abs. verdicts */ - tgpar.target = t->u.kernel.target; - tgpar.targinfo = t->data; - -#ifdef CONFIG_NETFILTER_DEBUG - tb_comefrom = 0xeeeeeeec; -#endif - verdict = t->u.kernel.target->target(skb, &tgpar); + acpar.target = t->u.kernel.target; + acpar.targinfo = t->data; -#ifdef CONFIG_NETFILTER_DEBUG - if (tb_comefrom != 0xeeeeeeec && verdict == IP6T_CONTINUE) { - printk("Target %s reentered!\n", - t->u.kernel.target->name); - verdict = NF_DROP; - } - tb_comefrom = 0x57acc001; -#endif + verdict = t->u.kernel.target->target(skb, &acpar); if (verdict == IP6T_CONTINUE) e = ip6t_next_entry(e); else /* Verdict */ break; - } while (!hotdrop); + } while (!acpar.hotdrop); -#ifdef CONFIG_NETFILTER_DEBUG - tb_comefrom = NETFILTER_LINK_POISON; -#endif xt_info_rdunlock_bh(); + *stackptr = origptr; #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; #else - if (hotdrop) + if (acpar.hotdrop) return NF_DROP; else return verdict; #endif - -#undef tb_comefrom } /* Figures out from what hook each rule can be called: returns 0 if @@ -517,7 +481,7 @@ mark_source_chains(const struct xt_table_info *newinfo, int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) { - printk("iptables: loop hook %u pos %u %08X.\n", + pr_err("iptables: loop hook %u pos %u %08X.\n", hook, pos, e->comefrom); return 0; } @@ -661,12 +625,11 @@ find_check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par) struct xt_match *match; int ret; - match = try_then_request_module(xt_find_match(AF_INET6, m->u.user.name, - m->u.user.revision), - "ip6t_%s", m->u.user.name); - if (IS_ERR(match) || !match) { + match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, + m->u.user.revision); + if (IS_ERR(match)) { duprintf("find_check_match: `%s' not found\n", m->u.user.name); - return match ? PTR_ERR(match) : -ENOENT; + return PTR_ERR(match); } m->u.kernel.match = match; @@ -734,13 +697,11 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, } t = ip6t_get_target(e); - target = try_then_request_module(xt_find_target(AF_INET6, - t->u.user.name, - t->u.user.revision), - "ip6t_%s", t->u.user.name); - if (IS_ERR(target) || !target) { + target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, + t->u.user.revision); + if (IS_ERR(target)) { duprintf("find_check_entry: `%s' not found\n", t->u.user.name); - ret = target ? PTR_ERR(target) : -ENOENT; + ret = PTR_ERR(target); goto cleanup_matches; } t->u.kernel.target = target; @@ -873,6 +834,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, if (ret != 0) return ret; ++i; + if (strcmp(ip6t_get_target(iter)->u.user.name, + XT_ERROR_TARGET) == 0) + ++newinfo->stacksize; } if (i != repl->num_entries) { @@ -1509,13 +1473,12 @@ compat_find_calc_match(struct ip6t_entry_match *m, { struct xt_match *match; - match = try_then_request_module(xt_find_match(AF_INET6, m->u.user.name, - m->u.user.revision), - "ip6t_%s", m->u.user.name); - if (IS_ERR(match) || !match) { + match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, + m->u.user.revision); + if (IS_ERR(match)) { duprintf("compat_check_calc_match: `%s' not found\n", m->u.user.name); - return match ? PTR_ERR(match) : -ENOENT; + return PTR_ERR(match); } m->u.kernel.match = match; *size += xt_compat_match_offset(match); @@ -1582,14 +1545,12 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, } t = compat_ip6t_get_target(e); - target = try_then_request_module(xt_find_target(AF_INET6, - t->u.user.name, - t->u.user.revision), - "ip6t_%s", t->u.user.name); - if (IS_ERR(target) || !target) { + target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, + t->u.user.revision); + if (IS_ERR(target)) { duprintf("check_compat_entry_size_and_hooks: `%s' not found\n", t->u.user.name); - ret = target ? PTR_ERR(target) : -ENOENT; + ret = PTR_ERR(target); goto release_matches; } t->u.kernel.target = target; @@ -2127,8 +2088,7 @@ struct xt_table *ip6t_register_table(struct net *net, { int ret; struct xt_table_info *newinfo; - struct xt_table_info bootstrap - = { 0, 0, 0, { 0 }, { 0 }, { } }; + struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; @@ -2188,7 +2148,7 @@ icmp6_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code, } static bool -icmp6_match(const struct sk_buff *skb, const struct xt_match_param *par) +icmp6_match(const struct sk_buff *skb, struct xt_action_param *par) { const struct icmp6hdr *ic; struct icmp6hdr _icmph; @@ -2204,7 +2164,7 @@ icmp6_match(const struct sk_buff *skb, const struct xt_match_param *par) * can't. Hence, no choice but to drop. */ duprintf("Dropping evil ICMP tinygram.\n"); - *par->hotdrop = true; + par->hotdrop = true; return false; } @@ -2216,31 +2176,32 @@ icmp6_match(const struct sk_buff *skb, const struct xt_match_param *par) } /* Called when user tries to insert an entry of this type. */ -static bool icmp6_checkentry(const struct xt_mtchk_param *par) +static int icmp6_checkentry(const struct xt_mtchk_param *par) { const struct ip6t_icmp *icmpinfo = par->matchinfo; /* Must specify no unknown invflags */ - return !(icmpinfo->invflags & ~IP6T_ICMP_INV); + return (icmpinfo->invflags & ~IP6T_ICMP_INV) ? -EINVAL : 0; } /* The built-in targets: standard (NULL) and error. */ -static struct xt_target ip6t_standard_target __read_mostly = { - .name = IP6T_STANDARD_TARGET, - .targetsize = sizeof(int), - .family = NFPROTO_IPV6, +static struct xt_target ip6t_builtin_tg[] __read_mostly = { + { + .name = IP6T_STANDARD_TARGET, + .targetsize = sizeof(int), + .family = NFPROTO_IPV6, #ifdef CONFIG_COMPAT - .compatsize = sizeof(compat_int_t), - .compat_from_user = compat_standard_from_user, - .compat_to_user = compat_standard_to_user, + .compatsize = sizeof(compat_int_t), + .compat_from_user = compat_standard_from_user, + .compat_to_user = compat_standard_to_user, #endif -}; - -static struct xt_target ip6t_error_target __read_mostly = { - .name = IP6T_ERROR_TARGET, - .target = ip6t_error, - .targetsize = IP6T_FUNCTION_MAXNAMELEN, - .family = NFPROTO_IPV6, + }, + { + .name = IP6T_ERROR_TARGET, + .target = ip6t_error, + .targetsize = IP6T_FUNCTION_MAXNAMELEN, + .family = NFPROTO_IPV6, + }, }; static struct nf_sockopt_ops ip6t_sockopts = { @@ -2260,13 +2221,15 @@ static struct nf_sockopt_ops ip6t_sockopts = { .owner = THIS_MODULE, }; -static struct xt_match icmp6_matchstruct __read_mostly = { - .name = "icmp6", - .match = icmp6_match, - .matchsize = sizeof(struct ip6t_icmp), - .checkentry = icmp6_checkentry, - .proto = IPPROTO_ICMPV6, - .family = NFPROTO_IPV6, +static struct xt_match ip6t_builtin_mt[] __read_mostly = { + { + .name = "icmp6", + .match = icmp6_match, + .matchsize = sizeof(struct ip6t_icmp), + .checkentry = icmp6_checkentry, + .proto = IPPROTO_ICMPV6, + .family = NFPROTO_IPV6, + }, }; static int __net_init ip6_tables_net_init(struct net *net) @@ -2293,13 +2256,10 @@ static int __init ip6_tables_init(void) goto err1; /* Noone else will be downing sem now, so we won't sleep */ - ret = xt_register_target(&ip6t_standard_target); + ret = xt_register_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); if (ret < 0) goto err2; - ret = xt_register_target(&ip6t_error_target); - if (ret < 0) - goto err3; - ret = xt_register_match(&icmp6_matchstruct); + ret = xt_register_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt)); if (ret < 0) goto err4; @@ -2308,15 +2268,13 @@ static int __init ip6_tables_init(void) if (ret < 0) goto err5; - printk(KERN_INFO "ip6_tables: (C) 2000-2006 Netfilter Core Team\n"); + pr_info("(C) 2000-2006 Netfilter Core Team\n"); return 0; err5: - xt_unregister_match(&icmp6_matchstruct); + xt_unregister_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt)); err4: - xt_unregister_target(&ip6t_error_target); -err3: - xt_unregister_target(&ip6t_standard_target); + xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); err2: unregister_pernet_subsys(&ip6_tables_net_ops); err1: @@ -2327,10 +2285,8 @@ static void __exit ip6_tables_fini(void) { nf_unregister_sockopt(&ip6t_sockopts); - xt_unregister_match(&icmp6_matchstruct); - xt_unregister_target(&ip6t_error_target); - xt_unregister_target(&ip6t_standard_target); - + xt_unregister_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt)); + xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); unregister_pernet_subsys(&ip6_tables_net_ops); } diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index b285fdf1905..af4ee11f206 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -9,9 +9,8 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/ip.h> @@ -378,7 +377,7 @@ static struct nf_loginfo default_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { - .level = 0, + .level = 5, .logflags = NF_LOG_MASK, }, }, @@ -437,7 +436,7 @@ ip6t_log_packet(u_int8_t pf, } static unsigned int -log_tg6(struct sk_buff *skb, const struct xt_target_param *par) +log_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct ip6t_log_info *loginfo = par->targinfo; struct nf_loginfo li; @@ -452,20 +451,19 @@ log_tg6(struct sk_buff *skb, const struct xt_target_param *par) } -static bool log_tg6_check(const struct xt_tgchk_param *par) +static int log_tg6_check(const struct xt_tgchk_param *par) { const struct ip6t_log_info *loginfo = par->targinfo; if (loginfo->level >= 8) { - pr_debug("LOG: level %u >= 8\n", loginfo->level); - return false; + pr_debug("level %u >= 8\n", loginfo->level); + return -EINVAL; } if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { - pr_debug("LOG: prefix term %i\n", - loginfo->prefix[sizeof(loginfo->prefix)-1]); - return false; + pr_debug("prefix not null-terminated\n"); + return -EINVAL; } - return true; + return 0; } static struct xt_target log_tg6_reg __read_mostly = { diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 39b50c3768e..47d22771375 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -14,6 +14,7 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/gfp.h> #include <linux/module.h> @@ -50,7 +51,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) || (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) { - pr_debug("ip6t_REJECT: addr is not unicast.\n"); + pr_debug("addr is not unicast.\n"); return; } @@ -58,7 +59,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto); if ((tcphoff < 0) || (tcphoff > oldskb->len)) { - pr_debug("ip6t_REJECT: Can't get TCP header.\n"); + pr_debug("Cannot get TCP header.\n"); return; } @@ -66,7 +67,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) /* IP header checks: fragment, too short. */ if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) { - pr_debug("ip6t_REJECT: proto(%d) != IPPROTO_TCP, " + pr_debug("proto(%d) != IPPROTO_TCP, " "or too short. otcplen = %d\n", proto, otcplen); return; @@ -77,14 +78,14 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) /* No RST for RST. */ if (otcph.rst) { - pr_debug("ip6t_REJECT: RST is set\n"); + pr_debug("RST is set\n"); return; } /* Check checksum. */ if (csum_ipv6_magic(&oip6h->saddr, &oip6h->daddr, otcplen, IPPROTO_TCP, skb_checksum(oldskb, tcphoff, otcplen, 0))) { - pr_debug("ip6t_REJECT: TCP checksum is invalid\n"); + pr_debug("TCP checksum is invalid\n"); return; } @@ -108,7 +109,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) if (!nskb) { if (net_ratelimit()) - printk("ip6t_REJECT: Can't alloc skb\n"); + pr_debug("cannot alloc skb\n"); dst_release(dst); return; } @@ -174,15 +175,12 @@ send_unreach(struct net *net, struct sk_buff *skb_in, unsigned char code, } static unsigned int -reject_tg6(struct sk_buff *skb, const struct xt_target_param *par) +reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct ip6t_reject_info *reject = par->targinfo; struct net *net = dev_net((par->in != NULL) ? par->in : par->out); pr_debug("%s: medium point\n", __func__); - /* WARNING: This code causes reentry within ip6tables. - This means that the ip6tables jump stack is now crap. We - must return an absolute verdict. --RR */ switch (reject->with) { case IP6T_ICMP6_NO_ROUTE: send_unreach(net, skb, ICMPV6_NOROUTE, par->hooknum); @@ -207,30 +205,30 @@ reject_tg6(struct sk_buff *skb, const struct xt_target_param *par) break; default: if (net_ratelimit()) - printk(KERN_WARNING "ip6t_REJECT: case %u not handled yet\n", reject->with); + pr_info("case %u not handled yet\n", reject->with); break; } return NF_DROP; } -static bool reject_tg6_check(const struct xt_tgchk_param *par) +static int reject_tg6_check(const struct xt_tgchk_param *par) { const struct ip6t_reject_info *rejinfo = par->targinfo; const struct ip6t_entry *e = par->entryinfo; if (rejinfo->with == IP6T_ICMP6_ECHOREPLY) { - printk("ip6t_REJECT: ECHOREPLY is not supported.\n"); - return false; + pr_info("ECHOREPLY is not supported.\n"); + return -EINVAL; } 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)) { - printk("ip6t_REJECT: TCP_RESET illegal for non-tcp\n"); - return false; + pr_info("TCP_RESET illegal for non-tcp\n"); + return -EINVAL; } } - return true; + return 0; } static struct xt_target reject_tg6_reg __read_mostly = { diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index ac0b7c629d7..89cccc5a9c9 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -6,7 +6,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ip.h> @@ -29,14 +29,14 @@ spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert) { bool r; - pr_debug("ah spi_match:%c 0x%x <= 0x%x <= 0x%x", + pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n", invert ? '!' : ' ', min, spi, max); r = (spi >= min && spi <= max) ^ invert; pr_debug(" result %s\n", r ? "PASS" : "FAILED"); return r; } -static bool ah_mt6(const struct sk_buff *skb, const struct xt_match_param *par) +static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par) { struct ip_auth_hdr _ah; const struct ip_auth_hdr *ah; @@ -48,13 +48,13 @@ static bool ah_mt6(const struct sk_buff *skb, const struct xt_match_param *par) err = ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL); if (err < 0) { if (err != -ENOENT) - *par->hotdrop = true; + par->hotdrop = true; return false; } ah = skb_header_pointer(skb, ptr, sizeof(_ah), &_ah); if (ah == NULL) { - *par->hotdrop = true; + par->hotdrop = true; return false; } @@ -87,15 +87,15 @@ static bool ah_mt6(const struct sk_buff *skb, const struct xt_match_param *par) !(ahinfo->hdrres && ah->reserved); } -static bool ah_mt6_check(const struct xt_mtchk_param *par) +static int ah_mt6_check(const struct xt_mtchk_param *par) { const struct ip6t_ah *ahinfo = par->matchinfo; if (ahinfo->invflags & ~IP6T_AH_INV_MASK) { - pr_debug("ip6t_ah: unknown flags %X\n", ahinfo->invflags); - return false; + pr_debug("unknown flags %X\n", ahinfo->invflags); + return -EINVAL; } - return true; + return 0; } static struct xt_match ah_mt6_reg __read_mostly = { diff --git a/net/ipv6/netfilter/ip6t_eui64.c b/net/ipv6/netfilter/ip6t_eui64.c index ca287f6d2bc..aab0706908c 100644 --- a/net/ipv6/netfilter/ip6t_eui64.c +++ b/net/ipv6/netfilter/ip6t_eui64.c @@ -20,14 +20,14 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); static bool -eui64_mt6(const struct sk_buff *skb, const struct xt_match_param *par) +eui64_mt6(const struct sk_buff *skb, struct xt_action_param *par) { unsigned char eui64[8]; if (!(skb_mac_header(skb) >= skb->head && skb_mac_header(skb) + ETH_HLEN <= skb->data) && par->fragoff != 0) { - *par->hotdrop = true; + par->hotdrop = true; return false; } diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index 7b91c2598ed..eda898fda6c 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -6,7 +6,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ipv6.h> @@ -27,7 +27,7 @@ static inline bool id_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert) { bool r; - pr_debug("frag id_match:%c 0x%x <= 0x%x <= 0x%x", invert ? '!' : ' ', + pr_debug("id_match:%c 0x%x <= 0x%x <= 0x%x\n", invert ? '!' : ' ', min, id, max); r = (id >= min && id <= max) ^ invert; pr_debug(" result %s\n", r ? "PASS" : "FAILED"); @@ -35,7 +35,7 @@ id_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert) } static bool -frag_mt6(const struct sk_buff *skb, const struct xt_match_param *par) +frag_mt6(const struct sk_buff *skb, struct xt_action_param *par) { struct frag_hdr _frag; const struct frag_hdr *fh; @@ -46,13 +46,13 @@ frag_mt6(const struct sk_buff *skb, const struct xt_match_param *par) err = ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL); if (err < 0) { if (err != -ENOENT) - *par->hotdrop = true; + par->hotdrop = true; return false; } fh = skb_header_pointer(skb, ptr, sizeof(_frag), &_frag); if (fh == NULL) { - *par->hotdrop = true; + par->hotdrop = true; return false; } @@ -102,15 +102,15 @@ frag_mt6(const struct sk_buff *skb, const struct xt_match_param *par) (ntohs(fh->frag_off) & IP6_MF)); } -static bool frag_mt6_check(const struct xt_mtchk_param *par) +static int frag_mt6_check(const struct xt_mtchk_param *par) { const struct ip6t_frag *fraginfo = par->matchinfo; if (fraginfo->invflags & ~IP6T_FRAG_INV_MASK) { - pr_debug("ip6t_frag: unknown flags %X\n", fraginfo->invflags); - return false; + pr_debug("unknown flags %X\n", fraginfo->invflags); + return -EINVAL; } - return true; + return 0; } static struct xt_match frag_mt6_reg __read_mostly = { diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index cbe8dec9744..59df051eaef 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -6,7 +6,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ipv6.h> @@ -41,8 +41,10 @@ MODULE_ALIAS("ip6t_dst"); * 5 -> RTALERT 2 x x */ +static struct xt_match hbh_mt6_reg[] __read_mostly; + static bool -hbh_mt6(const struct sk_buff *skb, const struct xt_match_param *par) +hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par) { struct ipv6_opt_hdr _optsh; const struct ipv6_opt_hdr *oh; @@ -58,16 +60,18 @@ hbh_mt6(const struct sk_buff *skb, const struct xt_match_param *par) unsigned int optlen; int err; - err = ipv6_find_hdr(skb, &ptr, par->match->data, NULL); + err = ipv6_find_hdr(skb, &ptr, + (par->match == &hbh_mt6_reg[0]) ? + NEXTHDR_HOP : NEXTHDR_DEST, NULL); if (err < 0) { if (err != -ENOENT) - *par->hotdrop = true; + par->hotdrop = true; return false; } oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh); if (oh == NULL) { - *par->hotdrop = true; + par->hotdrop = true; return false; } @@ -141,11 +145,11 @@ hbh_mt6(const struct sk_buff *skb, const struct xt_match_param *par) } /* Step to the next */ - pr_debug("len%04X \n", optlen); + pr_debug("len%04X\n", optlen); if ((ptr > skb->len - optlen || hdrlen < optlen) && temp < optinfo->optsnr - 1) { - pr_debug("new pointer is too large! \n"); + pr_debug("new pointer is too large!\n"); break; } ptr += optlen; @@ -160,32 +164,32 @@ hbh_mt6(const struct sk_buff *skb, const struct xt_match_param *par) return false; } -static bool hbh_mt6_check(const struct xt_mtchk_param *par) +static int hbh_mt6_check(const struct xt_mtchk_param *par) { const struct ip6t_opts *optsinfo = par->matchinfo; if (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) { - pr_debug("ip6t_opts: unknown flags %X\n", optsinfo->invflags); - return false; + pr_debug("unknown flags %X\n", optsinfo->invflags); + return -EINVAL; } if (optsinfo->flags & IP6T_OPTS_NSTRICT) { - pr_debug("ip6t_opts: Not strict - not implemented"); - return false; + pr_debug("Not strict - not implemented"); + return -EINVAL; } - return true; + return 0; } static struct xt_match hbh_mt6_reg[] __read_mostly = { { + /* Note, hbh_mt6 relies on the order of hbh_mt6_reg */ .name = "hbh", .family = NFPROTO_IPV6, .match = hbh_mt6, .matchsize = sizeof(struct ip6t_opts), .checkentry = hbh_mt6_check, .me = THIS_MODULE, - .data = NEXTHDR_HOP, }, { .name = "dst", @@ -194,7 +198,6 @@ static struct xt_match hbh_mt6_reg[] __read_mostly = { .matchsize = sizeof(struct ip6t_opts), .checkentry = hbh_mt6_check, .me = THIS_MODULE, - .data = NEXTHDR_DEST, }, }; diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c index 91490ad9302..54bd9790603 100644 --- a/net/ipv6/netfilter/ip6t_ipv6header.c +++ b/net/ipv6/netfilter/ip6t_ipv6header.c @@ -27,7 +27,7 @@ MODULE_DESCRIPTION("Xtables: IPv6 header types match"); MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); static bool -ipv6header_mt6(const struct sk_buff *skb, const struct xt_match_param *par) +ipv6header_mt6(const struct sk_buff *skb, struct xt_action_param *par) { const struct ip6t_ipv6header_info *info = par->matchinfo; unsigned int temp; @@ -118,16 +118,16 @@ ipv6header_mt6(const struct sk_buff *skb, const struct xt_match_param *par) } } -static bool ipv6header_mt6_check(const struct xt_mtchk_param *par) +static int ipv6header_mt6_check(const struct xt_mtchk_param *par) { const struct ip6t_ipv6header_info *info = par->matchinfo; /* invflags is 0 or 0xff in hard mode */ if ((!info->modeflag) && info->invflags != 0x00 && info->invflags != 0xFF) - return false; + return -EINVAL; - return true; + return 0; } static struct xt_match ipv6header_mt6_reg __read_mostly = { diff --git a/net/ipv6/netfilter/ip6t_mh.c b/net/ipv6/netfilter/ip6t_mh.c index aafe4e66577..0c90c66b199 100644 --- a/net/ipv6/netfilter/ip6t_mh.c +++ b/net/ipv6/netfilter/ip6t_mh.c @@ -11,6 +11,7 @@ * Based on net/netfilter/xt_tcpudp.c * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/module.h> #include <net/ip.h> @@ -24,12 +25,6 @@ MODULE_DESCRIPTION("Xtables: IPv6 Mobility Header match"); MODULE_LICENSE("GPL"); -#ifdef DEBUG_IP_FIREWALL_USER -#define duprintf(format, args...) printk(format , ## args) -#else -#define duprintf(format, args...) -#endif - /* Returns 1 if the type is matched by the range, 0 otherwise */ static inline bool type_match(u_int8_t min, u_int8_t max, u_int8_t type, bool invert) @@ -37,7 +32,7 @@ type_match(u_int8_t min, u_int8_t max, u_int8_t type, bool invert) return (type >= min && type <= max) ^ invert; } -static bool mh_mt6(const struct sk_buff *skb, const struct xt_match_param *par) +static bool mh_mt6(const struct sk_buff *skb, struct xt_action_param *par) { struct ip6_mh _mh; const struct ip6_mh *mh; @@ -51,15 +46,15 @@ static bool mh_mt6(const struct sk_buff *skb, const struct xt_match_param *par) if (mh == NULL) { /* We've been asked to examine this packet, and we can't. Hence, no choice but to drop. */ - duprintf("Dropping evil MH tinygram.\n"); - *par->hotdrop = true; + pr_debug("Dropping evil MH tinygram.\n"); + par->hotdrop = true; return false; } if (mh->ip6mh_proto != IPPROTO_NONE) { - duprintf("Dropping invalid MH Payload Proto: %u\n", + pr_debug("Dropping invalid MH Payload Proto: %u\n", mh->ip6mh_proto); - *par->hotdrop = true; + par->hotdrop = true; return false; } @@ -67,12 +62,12 @@ static bool mh_mt6(const struct sk_buff *skb, const struct xt_match_param *par) !!(mhinfo->invflags & IP6T_MH_INV_TYPE)); } -static bool mh_mt6_check(const struct xt_mtchk_param *par) +static int mh_mt6_check(const struct xt_mtchk_param *par) { const struct ip6t_mh *mhinfo = par->matchinfo; /* Must specify no unknown invflags */ - return !(mhinfo->invflags & ~IP6T_MH_INV_MASK); + return (mhinfo->invflags & ~IP6T_MH_INV_MASK) ? -EINVAL : 0; } static struct xt_match mh_mt6_reg __read_mostly = { diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index b77307fc874..d8488c50a8e 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -6,7 +6,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ipv6.h> @@ -29,14 +29,14 @@ static inline bool segsleft_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert) { bool r; - pr_debug("rt segsleft_match:%c 0x%x <= 0x%x <= 0x%x", + pr_debug("segsleft_match:%c 0x%x <= 0x%x <= 0x%x\n", invert ? '!' : ' ', min, id, max); r = (id >= min && id <= max) ^ invert; pr_debug(" result %s\n", r ? "PASS" : "FAILED"); return r; } -static bool rt_mt6(const struct sk_buff *skb, const struct xt_match_param *par) +static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) { struct ipv6_rt_hdr _route; const struct ipv6_rt_hdr *rh; @@ -52,13 +52,13 @@ static bool rt_mt6(const struct sk_buff *skb, const struct xt_match_param *par) err = ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL); if (err < 0) { if (err != -ENOENT) - *par->hotdrop = true; + par->hotdrop = true; return false; } rh = skb_header_pointer(skb, ptr, sizeof(_route), &_route); if (rh == NULL) { - *par->hotdrop = true; + par->hotdrop = true; return false; } @@ -183,23 +183,23 @@ static bool rt_mt6(const struct sk_buff *skb, const struct xt_match_param *par) return false; } -static bool rt_mt6_check(const struct xt_mtchk_param *par) +static int rt_mt6_check(const struct xt_mtchk_param *par) { const struct ip6t_rt *rtinfo = par->matchinfo; if (rtinfo->invflags & ~IP6T_RT_INV_MASK) { - pr_debug("ip6t_rt: unknown flags %X\n", rtinfo->invflags); - return false; + pr_debug("unknown flags %X\n", rtinfo->invflags); + return -EINVAL; } if ((rtinfo->flags & (IP6T_RT_RES | IP6T_RT_FST_MASK)) && (!(rtinfo->flags & IP6T_RT_TYP) || (rtinfo->rt_type != 0) || (rtinfo->invflags & IP6T_RT_INV_TYP))) { pr_debug("`--rt-type 0' required before `--rt-0-*'"); - return false; + return -EINVAL; } - return true; + return 0; } static struct xt_match rt_mt6_reg __read_mostly = { diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index d6fc9aff316..c9e37c8fd62 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -81,7 +81,7 @@ static int __init ip6table_filter_init(void) int ret; if (forward < 0 || forward > NF_MAX_VERDICT) { - printk("iptables forward must be 0 or 1\n"); + pr_err("iptables forward must be 0 or 1\n"); return -EINVAL; } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 6a102b57f35..679a0a3b7b3 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -43,7 +43,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out) if (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr)) { if (net_ratelimit()) - printk("ip6t_hook: happy cracking.\n"); + pr_warning("ip6t_hook: happy cracking.\n"); return NF_ACCEPT; } #endif diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 996c3f41fec..ff43461704b 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -280,7 +280,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum, /* root is playing with raw sockets. */ if (skb->len < sizeof(struct ipv6hdr)) { if (net_ratelimit()) - printk("ipv6_conntrack_local: packet too short\n"); + pr_notice("ipv6_conntrack_local: packet too short\n"); return NF_ACCEPT; } return __ipv6_conntrack_in(dev_net(out), hooknum, skb, okfn); @@ -406,37 +406,37 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) ret = nf_ct_frag6_init(); if (ret < 0) { - printk("nf_conntrack_ipv6: can't initialize frag6.\n"); + pr_err("nf_conntrack_ipv6: can't initialize frag6.\n"); return ret; } ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_tcp6); if (ret < 0) { - printk("nf_conntrack_ipv6: can't register tcp.\n"); + pr_err("nf_conntrack_ipv6: can't register tcp.\n"); goto cleanup_frag6; } ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udp6); if (ret < 0) { - printk("nf_conntrack_ipv6: can't register udp.\n"); + pr_err("nf_conntrack_ipv6: can't register udp.\n"); goto cleanup_tcp; } ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_icmpv6); if (ret < 0) { - printk("nf_conntrack_ipv6: can't register icmpv6.\n"); + pr_err("nf_conntrack_ipv6: can't register icmpv6.\n"); goto cleanup_udp; } ret = nf_conntrack_l3proto_register(&nf_conntrack_l3proto_ipv6); if (ret < 0) { - printk("nf_conntrack_ipv6: can't register ipv6\n"); + pr_err("nf_conntrack_ipv6: can't register ipv6\n"); goto cleanup_icmpv6; } ret = nf_register_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); if (ret < 0) { - printk("nf_conntrack_ipv6: can't register pre-routing defrag " + pr_err("nf_conntrack_ipv6: can't register pre-routing defrag " "hook.\n"); goto cleanup_ipv6; } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index dd5b9bd61c6..6fb890187de 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -644,7 +644,7 @@ void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb, s2 = s->next; s->next = NULL; - NF_HOOK_THRESH(PF_INET6, hooknum, s, in, out, okfn, + NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s, in, out, okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1); s = s2; } diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 58344c0fbd1..566798d69f3 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -97,6 +97,7 @@ static const struct snmp_mib snmp6_icmp6_list[] = { SNMP_MIB_ITEM("Icmp6InMsgs", ICMP6_MIB_INMSGS), SNMP_MIB_ITEM("Icmp6InErrors", ICMP6_MIB_INERRORS), SNMP_MIB_ITEM("Icmp6OutMsgs", ICMP6_MIB_OUTMSGS), + SNMP_MIB_ITEM("Icmp6OutErrors", ICMP6_MIB_OUTERRORS), SNMP_MIB_SENTINEL }; @@ -167,7 +168,6 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **mib) i & 0x100 ? "Out" : "In", i & 0xff); seq_printf(seq, "%-32s\t%lu\n", name, val); } - return; } static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **mib, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8763b1a0814..4a4dcbe4f8b 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -381,7 +381,7 @@ 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) { + if (ip_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } @@ -461,6 +461,9 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len); + if (np->rxpmtu && np->rxopt.bits.rxpmtu) + return ipv6_recv_rxpmtu(sk, msg, len); + skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; @@ -637,8 +640,8 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, goto error_fault; IP6_UPD_PO_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); - err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev, - dst_output); + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, + rt->u.dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) @@ -733,6 +736,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, int addr_len = msg->msg_namelen; int hlimit = -1; int tclass = -1; + int dontfrag = -1; u16 proto; int err; @@ -811,7 +815,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, + &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -880,6 +885,9 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (tclass < 0) tclass = np->tclass; + if (dontfrag < 0) + dontfrag = np->dontfrag; + if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; @@ -890,7 +898,7 @@ back_from_confirm: lock_sock(sk); err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, len, 0, hlimit, tclass, opt, &fl, (struct rt6_info*)dst, - msg->msg_flags); + msg->msg_flags, dontfrag); if (err) ip6_flush_pending_frames(sk); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 05ebd783304..294cbe8b072 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -316,7 +316,6 @@ static void rt6_probe(struct rt6_info *rt) #else static inline void rt6_probe(struct rt6_info *rt) { - return; } #endif @@ -1553,7 +1552,6 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *src, out: dst_release(&rt->u.dst); - return; } /* diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 5abae10cd88..e51e650ea80 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -566,11 +566,9 @@ static int ipip6_rcv(struct sk_buff *skb) kfree_skb(skb); return 0; } - tunnel->dev->stats.rx_packets++; - tunnel->dev->stats.rx_bytes += skb->len; - skb->dev = tunnel->dev; - skb_dst_drop(skb); - nf_reset(skb); + + skb_tunnel_rx(skb, tunnel->dev); + ipip6_ecn_decapsulate(iph, skb); netif_rx(skb); rcu_read_unlock(); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 075f540ec19..2b7c3a100e2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -75,6 +75,9 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req); static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); +static void __tcp_v6_send_check(struct sk_buff *skb, + struct in6_addr *saddr, + struct in6_addr *daddr); static const struct inet_connection_sock_af_ops ipv6_mapped; static const struct inet_connection_sock_af_ops ipv6_specific; @@ -350,6 +353,11 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (sk->sk_state == TCP_CLOSE) goto out; + if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) { + NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); + goto out; + } + tp = tcp_sk(sk); seq = ntohl(th->seq); if (sk->sk_state != TCP_LISTEN && @@ -503,14 +511,10 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, skb = tcp_make_synack(sk, dst, req, rvp); if (skb) { - struct tcphdr *th = tcp_hdr(skb); - - th->check = tcp_v6_check(skb->len, - &treq->loc_addr, &treq->rmt_addr, - csum_partial(th, skb->len, skb->csum)); + __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - err = ip6_xmit(sk, skb, &fl, opt, 0); + err = ip6_xmit(sk, skb, &fl, opt); err = net_xmit_eval(err); } @@ -600,7 +604,7 @@ static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer, kfree(newkey); return -ENOMEM; } - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); } if (tcp_alloc_md5sig_pool(sk) == NULL) { kfree(newkey); @@ -737,7 +741,7 @@ static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval, return -ENOMEM; tp->md5sig_info = p; - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); } newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); @@ -918,22 +922,29 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_destructor= tcp_twsk_destructor, }; -static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) +static void __tcp_v6_send_check(struct sk_buff *skb, + struct in6_addr *saddr, struct in6_addr *daddr) { - struct ipv6_pinfo *np = inet6_sk(sk); struct tcphdr *th = tcp_hdr(skb); if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 0); + th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } else { - th->check = csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, - csum_partial(th, th->doff<<2, - skb->csum)); + th->check = tcp_v6_check(skb->len, saddr, daddr, + csum_partial(th, th->doff << 2, + skb->csum)); } } +static void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + + __tcp_v6_send_check(skb, &np->saddr, &np->daddr); +} + static int tcp_v6_gso_send_check(struct sk_buff *skb) { struct ipv6hdr *ipv6h; @@ -946,11 +957,8 @@ static int tcp_v6_gso_send_check(struct sk_buff *skb) th = tcp_hdr(skb); th->check = 0; - th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, - IPPROTO_TCP, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; + __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr); return 0; } @@ -1047,15 +1055,14 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, } #endif - buff->csum = csum_partial(t1, tot_len, 0); - memset(&fl, 0, sizeof(fl)); ipv6_addr_copy(&fl.fl6_dst, &ipv6_hdr(skb)->saddr); ipv6_addr_copy(&fl.fl6_src, &ipv6_hdr(skb)->daddr); - t1->check = csum_ipv6_magic(&fl.fl6_src, &fl.fl6_dst, - tot_len, IPPROTO_TCP, - buff->csum); + buff->ip_summed = CHECKSUM_PARTIAL; + buff->csum = 0; + + __tcp_v6_send_check(buff, &fl.fl6_src, &fl.fl6_dst); fl.proto = IPPROTO_TCP; fl.oif = inet6_iif(skb); @@ -1070,7 +1077,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) { if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) { skb_dst_set(buff, dst); - ip6_xmit(ctl_sk, buff, &fl, NULL, 0); + ip6_xmit(ctl_sk, buff, &fl, NULL); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); @@ -1233,12 +1240,12 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; /* Secret recipe starts with IP addresses */ - d = &ipv6_hdr(skb)->daddr.s6_addr32[0]; + d = (__force u32 *)&ipv6_hdr(skb)->daddr.s6_addr32[0]; *mess++ ^= *d++; *mess++ ^= *d++; *mess++ ^= *d++; *mess++ ^= *d++; - d = &ipv6_hdr(skb)->saddr.s6_addr32[0]; + d = (__force u32 *)&ipv6_hdr(skb)->saddr.s6_addr32[0]; *mess++ ^= *d++; *mess++ ^= *d++; *mess++ ^= *d++; @@ -1676,6 +1683,7 @@ ipv6_pktoptions: static int tcp_v6_rcv(struct sk_buff *skb) { struct tcphdr *th; + struct ipv6hdr *hdr; struct sock *sk; int ret; struct net *net = dev_net(skb->dev); @@ -1702,12 +1710,13 @@ static int tcp_v6_rcv(struct sk_buff *skb) goto bad_packet; th = tcp_hdr(skb); + hdr = ipv6_hdr(skb); TCP_SKB_CB(skb)->seq = ntohl(th->seq); TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + skb->len - th->doff*4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->when = 0; - TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(ipv6_hdr(skb)); + TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(hdr); TCP_SKB_CB(skb)->sacked = 0; sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest); @@ -1718,6 +1727,11 @@ process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; + if (hdr->hop_limit < inet6_sk(sk)->min_hopcount) { + NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); + goto discard_and_relse; + } + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 90824852f59..3d7a2c0b836 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -91,9 +91,9 @@ static unsigned int udp6_portaddr_hash(struct net *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); + hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix); else - hash = jhash2(addr6->s6_addr32, 4, mix); + hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix); return hash ^ port; } @@ -335,6 +335,9 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len); + if (np->rxpmtu && np->rxopt.bits.rxpmtu) + return ipv6_recv_rxpmtu(sk, msg, len); + try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), &peeked, &err); @@ -421,7 +424,7 @@ out: return err; csum_copy_err: - lock_sock(sk); + lock_sock_bh(sk); if (!skb_kill_datagram(sk, skb, flags)) { if (is_udp4) UDP_INC_STATS_USER(sock_net(sk), @@ -430,7 +433,7 @@ csum_copy_err: UDP6_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } - release_sock(sk); + unlock_sock_bh(sk); if (flags & MSG_DONTWAIT) return -EAGAIN; @@ -511,7 +514,7 @@ 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 = ip_queue_rcv_skb(sk, skb)) < 0) { /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) UDP6_INC_STATS_BH(sock_net(sk), @@ -581,6 +584,10 @@ static void flush_stack(struct sock **stack, unsigned int count, sk = stack[i]; if (skb1) { + if (sk_rcvqueues_full(sk, skb)) { + kfree_skb(skb1); + goto drop; + } bh_lock_sock(sk); if (!sock_owned_by_user(sk)) udpv6_queue_rcv_skb(sk, skb1); @@ -692,7 +699,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, u32 ulen = 0; if (!pskb_may_pull(skb, sizeof(struct udphdr))) - goto short_packet; + goto discard; saddr = &ipv6_hdr(skb)->saddr; daddr = &ipv6_hdr(skb)->daddr; @@ -756,6 +763,10 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, /* deliver */ + if (sk_rcvqueues_full(sk, skb)) { + sock_put(sk); + goto discard; + } bh_lock_sock(sk); if (!sock_owned_by_user(sk)) udpv6_queue_rcv_skb(sk, skb); @@ -770,9 +781,14 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, return 0; short_packet: - LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: %d/%u\n", + LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n", proto == IPPROTO_UDPLITE ? "-Lite" : "", - ulen, skb->len); + saddr, + ntohs(uh->source), + ulen, + skb->len, + daddr, + ntohs(uh->dest)); discard: UDP6_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); @@ -919,6 +935,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, int ulen = len; int hlimit = -1; int tclass = -1; + int dontfrag = -1; int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; int err; int connected = 0; @@ -1049,7 +1066,8 @@ do_udp_sendmsg: memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, + &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -1120,6 +1138,9 @@ do_udp_sendmsg: if (tclass < 0) tclass = np->tclass; + if (dontfrag < 0) + dontfrag = np->dontfrag; + if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: @@ -1143,7 +1164,7 @@ do_append_data: err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, sizeof(struct udphdr), hlimit, tclass, opt, &fl, (struct rt6_info*)dst, - corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); + corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag); if (err) udp_v6_flush_pending_frames(sk); else if (!corkreq) diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 2bc98ede123..f8c3cf842f5 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -42,7 +42,7 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async) ipv6_hdr(skb)->payload_len = htons(skb->len); __skb_push(skb, skb->data - skb_network_header(skb)); - NF_HOOK(PF_INET6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, ip6_rcv_finish); return -1; } diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 0c92112dcba..6434bd5ce08 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -90,6 +90,6 @@ static int xfrm6_output_finish(struct sk_buff *skb) int xfrm6_output(struct sk_buff *skb) { - return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb_dst(skb)->dev, - xfrm6_output_finish); + return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, + skb_dst(skb)->dev, xfrm6_output_finish); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 00bf7c962b7..4a0e77e1446 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -67,36 +67,6 @@ static int xfrm6_get_saddr(struct net *net, return 0; } -static struct dst_entry * -__xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy) -{ - struct dst_entry *dst; - - /* Still not clear if we should set fl->fl6_{src,dst}... */ - read_lock_bh(&policy->lock); - for (dst = policy->bundles; dst; dst = dst->next) { - struct xfrm_dst *xdst = (struct xfrm_dst*)dst; - struct in6_addr fl_dst_prefix, fl_src_prefix; - - ipv6_addr_prefix(&fl_dst_prefix, - &fl->fl6_dst, - xdst->u.rt6.rt6i_dst.plen); - ipv6_addr_prefix(&fl_src_prefix, - &fl->fl6_src, - xdst->u.rt6.rt6i_src.plen); - if (ipv6_addr_equal(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) && - ipv6_addr_equal(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) && - xfrm_bundle_ok(policy, xdst, fl, AF_INET6, - (xdst->u.rt6.rt6i_dst.plen != 128 || - xdst->u.rt6.rt6i_src.plen != 128))) { - dst_clone(dst); - break; - } - } - read_unlock_bh(&policy->lock); - return dst; -} - static int xfrm6_get_tos(struct flowi *fl) { return 0; @@ -291,7 +261,6 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .dst_ops = &xfrm6_dst_ops, .dst_lookup = xfrm6_dst_lookup, .get_saddr = xfrm6_get_saddr, - .find_bundle = __xfrm6_find_bundle, .decode_session = _decode_session6, .get_tos = xfrm6_get_tos, .init_path = xfrm6_init_path, |