diff options
Diffstat (limited to 'net/ipv6')
53 files changed, 2281 insertions, 1202 deletions
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 17bb830872db..2fe68364bb20 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -16,7 +16,7 @@ ipv6-$(CONFIG_SYSCTL) = sysctl_net_ipv6.o ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \ - xfrm6_output.o + xfrm6_output.o xfrm6_protocol.o ipv6-$(CONFIG_NETFILTER) += netfilter.o ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o ipv6-$(CONFIG_PROC_FS) += proc.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 344e972426df..3e118dfddd02 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -108,11 +108,12 @@ static inline u32 cstamp_delta(unsigned long cstamp) } #ifdef CONFIG_SYSCTL -static void addrconf_sysctl_register(struct inet6_dev *idev); +static int addrconf_sysctl_register(struct inet6_dev *idev); static void addrconf_sysctl_unregister(struct inet6_dev *idev); #else -static inline void addrconf_sysctl_register(struct inet6_dev *idev) +static inline int addrconf_sysctl_register(struct inet6_dev *idev) { + return 0; } static inline void addrconf_sysctl_unregister(struct inet6_dev *idev) @@ -133,10 +134,12 @@ static int ipv6_count_addresses(struct inet6_dev *idev); static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE]; static DEFINE_SPINLOCK(addrconf_hash_lock); -static void addrconf_verify(unsigned long); +static void addrconf_verify(void); +static void addrconf_verify_rtnl(void); +static void addrconf_verify_work(struct work_struct *); -static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0); -static DEFINE_SPINLOCK(addrconf_verify_lock); +static struct workqueue_struct *addrconf_wq; +static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work); static void addrconf_join_anycast(struct inet6_ifaddr *ifp); static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); @@ -151,7 +154,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, u32 flags, u32 noflags); static void addrconf_dad_start(struct inet6_ifaddr *ifp); -static void addrconf_dad_timer(unsigned long data); +static void addrconf_dad_work(struct work_struct *w); static void addrconf_dad_completed(struct inet6_ifaddr *ifp); static void addrconf_dad_run(struct inet6_dev *idev); static void addrconf_rs_timer(unsigned long data); @@ -184,6 +187,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, + .accept_ra_from_local = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -220,6 +224,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, + .accept_ra_from_local = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -247,9 +252,9 @@ static void addrconf_del_rs_timer(struct inet6_dev *idev) __in6_dev_put(idev); } -static void addrconf_del_dad_timer(struct inet6_ifaddr *ifp) +static void addrconf_del_dad_work(struct inet6_ifaddr *ifp) { - if (del_timer(&ifp->dad_timer)) + if (cancel_delayed_work(&ifp->dad_work)) __in6_ifa_put(ifp); } @@ -261,31 +266,26 @@ static void addrconf_mod_rs_timer(struct inet6_dev *idev, mod_timer(&idev->rs_timer, jiffies + when); } -static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp, - unsigned long when) +static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp, + unsigned long delay) { - if (!timer_pending(&ifp->dad_timer)) + if (!delayed_work_pending(&ifp->dad_work)) in6_ifa_hold(ifp); - mod_timer(&ifp->dad_timer, jiffies + when); + mod_delayed_work(addrconf_wq, &ifp->dad_work, delay); } static int snmp6_alloc_dev(struct inet6_dev *idev) { int i; - if (snmp_mib_init((void __percpu **)idev->stats.ipv6, - sizeof(struct ipstats_mib), - __alignof__(struct ipstats_mib)) < 0) + idev->stats.ipv6 = alloc_percpu(struct ipstats_mib); + if (!idev->stats.ipv6) goto err_ip; for_each_possible_cpu(i) { struct ipstats_mib *addrconf_stats; - addrconf_stats = per_cpu_ptr(idev->stats.ipv6[0], i); - u64_stats_init(&addrconf_stats->syncp); -#if SNMP_ARRAY_SZ == 2 - addrconf_stats = per_cpu_ptr(idev->stats.ipv6[1], i); + addrconf_stats = per_cpu_ptr(idev->stats.ipv6, i); u64_stats_init(&addrconf_stats->syncp); -#endif } @@ -303,7 +303,7 @@ static int snmp6_alloc_dev(struct inet6_dev *idev) err_icmpmsg: kfree(idev->stats.icmpv6dev); err_icmp: - snmp_mib_free((void __percpu **)idev->stats.ipv6); + free_percpu(idev->stats.ipv6); err_ip: return -ENOMEM; } @@ -311,16 +311,16 @@ err_ip: static struct inet6_dev *ipv6_add_dev(struct net_device *dev) { struct inet6_dev *ndev; + int err = -ENOMEM; ASSERT_RTNL(); if (dev->mtu < IPV6_MIN_MTU) - return NULL; + return ERR_PTR(-EINVAL); ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL); - if (ndev == NULL) - return NULL; + return ERR_PTR(err); rwlock_init(&ndev->lock); ndev->dev = dev; @@ -333,7 +333,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); if (ndev->nd_parms == NULL) { kfree(ndev); - return NULL; + return ERR_PTR(err); } if (ndev->cnf.forwarding) dev_disable_lro(dev); @@ -347,17 +347,14 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) neigh_parms_release(&nd_tbl, ndev->nd_parms); dev_put(dev); kfree(ndev); - return NULL; + return ERR_PTR(err); } if (snmp6_register_dev(ndev) < 0) { ADBG(KERN_WARNING "%s: cannot create /proc/net/dev_snmp6/%s\n", __func__, dev->name); - neigh_parms_release(&nd_tbl, ndev->nd_parms); - ndev->dead = 1; - in6_dev_finish_destroy(ndev); - return NULL; + goto err_release; } /* One reference from device. We must do this before @@ -395,7 +392,12 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ipv6_mc_init_dev(ndev); ndev->tstamp = jiffies; - addrconf_sysctl_register(ndev); + err = addrconf_sysctl_register(ndev); + if (err) { + ipv6_mc_destroy_dev(ndev); + del_timer(&ndev->regen_timer); + goto err_release; + } /* protected by rtnl_lock */ rcu_assign_pointer(dev->ip6_ptr, ndev); @@ -410,6 +412,12 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); return ndev; + +err_release: + neigh_parms_release(&nd_tbl, ndev->nd_parms); + ndev->dead = 1; + in6_dev_finish_destroy(ndev); + return ERR_PTR(err); } static struct inet6_dev *ipv6_find_idev(struct net_device *dev) @@ -421,7 +429,7 @@ static struct inet6_dev *ipv6_find_idev(struct net_device *dev) idev = __in6_dev_get(dev); if (!idev) { idev = ipv6_add_dev(dev); - if (!idev) + if (IS_ERR(idev)) return NULL; } @@ -751,8 +759,9 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) in6_dev_put(ifp->idev); - if (del_timer(&ifp->dad_timer)) - pr_notice("Timer is still running, when freeing ifa=%p\n", ifp); + if (cancel_delayed_work(&ifp->dad_work)) + pr_notice("delayed DAD work was pending while freeing ifa=%p\n", + ifp); if (ifp->state != INET6_IFADDR_STATE_DEAD) { pr_warn("Freeing alive inet6 address %p\n", ifp); @@ -849,8 +858,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, spin_lock_init(&ifa->lock); spin_lock_init(&ifa->state_lock); - setup_timer(&ifa->dad_timer, addrconf_dad_timer, - (unsigned long)ifa); + INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work); INIT_HLIST_NODE(&ifa->addr_lst); ifa->scope = scope; ifa->prefix_len = pfxlen; @@ -990,6 +998,8 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP; unsigned long expires; + ASSERT_RTNL(); + spin_lock_bh(&ifp->state_lock); state = ifp->state; ifp->state = INET6_IFADDR_STATE_DEAD; @@ -1021,7 +1031,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) write_unlock_bh(&ifp->idev->lock); - addrconf_del_dad_timer(ifp); + addrconf_del_dad_work(ifp); ipv6_ifa_notify(RTM_DELADDR, ifp); @@ -1604,7 +1614,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) { if (ifp->flags&IFA_F_PERMANENT) { spin_lock_bh(&ifp->lock); - addrconf_del_dad_timer(ifp); + addrconf_del_dad_work(ifp); ifp->flags |= IFA_F_TENTATIVE; if (dad_failed) ifp->flags |= IFA_F_DADFAILED; @@ -1625,20 +1635,21 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) spin_unlock_bh(&ifp->lock); } ipv6_del_addr(ifp); - } else + } else { ipv6_del_addr(ifp); + } } static int addrconf_dad_end(struct inet6_ifaddr *ifp) { int err = -ENOENT; - spin_lock(&ifp->state_lock); + spin_lock_bh(&ifp->state_lock); if (ifp->state == INET6_IFADDR_STATE_DAD) { ifp->state = INET6_IFADDR_STATE_POSTDAD; err = 0; } - spin_unlock(&ifp->state_lock); + spin_unlock_bh(&ifp->state_lock); return err; } @@ -1671,11 +1682,16 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) } } - addrconf_dad_stop(ifp, 1); -} + spin_lock_bh(&ifp->state_lock); + /* transition from _POSTDAD to _ERRDAD */ + ifp->state = INET6_IFADDR_STATE_ERRDAD; + spin_unlock_bh(&ifp->state_lock); -/* Join to solicited addr multicast group. */ + addrconf_mod_dad_work(ifp, 0); +} +/* Join to solicited addr multicast group. + * caller must hold RTNL */ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) { struct in6_addr maddr; @@ -1687,6 +1703,7 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) ipv6_dev_mc_inc(dev, &maddr); } +/* caller must hold RTNL */ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) { struct in6_addr maddr; @@ -1698,9 +1715,11 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) __ipv6_dev_mc_dec(idev, &maddr); } +/* caller must hold RTNL */ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; + if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); @@ -1709,9 +1728,11 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) ipv6_dev_ac_inc(ifp->idev->dev, &addr); } +/* caller must hold RTNL */ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; + if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); @@ -2271,11 +2292,13 @@ ok: return; } - ifp->flags |= IFA_F_MANAGETEMPADDR; update_lft = 0; create = 1; + spin_lock_bh(&ifp->lock); + ifp->flags |= IFA_F_MANAGETEMPADDR; ifp->cstamp = jiffies; ifp->tokenized = tokenized; + spin_unlock_bh(&ifp->lock); addrconf_dad_start(ifp); } @@ -2326,7 +2349,7 @@ ok: create, now); in6_ifa_put(ifp); - addrconf_verify(0); + addrconf_verify(); } } inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo); @@ -2475,15 +2498,15 @@ static int inet6_addr_add(struct net *net, int ifindex, manage_tempaddrs(idev, ifp, valid_lft, prefered_lft, true, jiffies); in6_ifa_put(ifp); - addrconf_verify(0); + addrconf_verify_rtnl(); return 0; } return PTR_ERR(ifp); } -static int inet6_addr_del(struct net *net, int ifindex, const struct in6_addr *pfx, - unsigned int plen) +static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, + const struct in6_addr *pfx, unsigned int plen) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; @@ -2506,7 +2529,12 @@ static int inet6_addr_del(struct net *net, int ifindex, const struct in6_addr *p in6_ifa_hold(ifp); read_unlock_bh(&idev->lock); + if (!(ifp->flags & IFA_F_TEMPORARY) && + (ifa_flags & IFA_F_MANAGETEMPADDR)) + manage_tempaddrs(idev, ifp, 0, 0, false, + jiffies); ipv6_del_addr(ifp); + addrconf_verify_rtnl(); return 0; } } @@ -2546,7 +2574,7 @@ int addrconf_del_ifaddr(struct net *net, void __user *arg) return -EFAULT; rtnl_lock(); - err = inet6_addr_del(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, + err = inet6_addr_del(net, ireq.ifr6_ifindex, 0, &ireq.ifr6_addr, ireq.ifr6_prefixlen); rtnl_unlock(); return err; @@ -2706,9 +2734,25 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr } } +static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) +{ + if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) { + struct in6_addr addr; + + ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); + /* addrconf_add_linklocal also adds a prefix_route and we + * only need to care about prefix routes if ipv6_generate_eui64 + * couldn't generate one. + */ + if (ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) == 0) + addrconf_add_linklocal(idev, &addr); + else if (prefix_route) + addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); + } +} + static void addrconf_dev_config(struct net_device *dev) { - struct in6_addr addr; struct inet6_dev *idev; ASSERT_RTNL(); @@ -2729,11 +2773,7 @@ static void addrconf_dev_config(struct net_device *dev) if (IS_ERR(idev)) return; - memset(&addr, 0, sizeof(struct in6_addr)); - addr.s6_addr32[0] = htonl(0xFE800000); - - if (ipv6_generate_eui64(addr.s6_addr + 8, dev) == 0) - addrconf_add_linklocal(idev, &addr); + addrconf_addr_gen(idev, false); } #if IS_ENABLED(CONFIG_IPV6_SIT) @@ -2755,11 +2795,7 @@ static void addrconf_sit_config(struct net_device *dev) } if (dev->priv_flags & IFF_ISATAP) { - struct in6_addr addr; - - ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) - addrconf_add_linklocal(idev, &addr); + addrconf_addr_gen(idev, false); return; } @@ -2774,7 +2810,6 @@ static void addrconf_sit_config(struct net_device *dev) static void addrconf_gre_config(struct net_device *dev) { struct inet6_dev *idev; - struct in6_addr addr; ASSERT_RTNL(); @@ -2783,26 +2818,10 @@ static void addrconf_gre_config(struct net_device *dev) return; } - ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) - addrconf_add_linklocal(idev, &addr); - else - addrconf_prefix_route(&addr, 64, dev, 0, 0); + addrconf_addr_gen(idev, true); } #endif -static inline int -ipv6_inherit_linklocal(struct inet6_dev *idev, struct net_device *link_dev) -{ - struct in6_addr lladdr; - - if (!ipv6_get_lladdr(link_dev, &lladdr, IFA_F_TENTATIVE)) { - addrconf_add_linklocal(idev, &lladdr); - return 0; - } - return -1; -} - static int addrconf_notify(struct notifier_block *this, unsigned long event, void *ptr) { @@ -2815,8 +2834,8 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, case NETDEV_REGISTER: if (!idev && dev->mtu >= IPV6_MIN_MTU) { idev = ipv6_add_dev(dev); - if (!idev) - return notifier_from_errno(-ENOMEM); + if (IS_ERR(idev)) + return notifier_from_errno(PTR_ERR(idev)); } break; @@ -2836,7 +2855,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (!idev && dev->mtu >= IPV6_MIN_MTU) idev = ipv6_add_dev(dev); - if (idev) { + if (!IS_ERR_OR_NULL(idev)) { idev->if_flags |= IF_READY; run_pending = 1; } @@ -2879,7 +2898,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, break; } - if (idev) { + if (!IS_ERR_OR_NULL(idev)) { if (run_pending) addrconf_dad_run(idev); @@ -2914,7 +2933,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (!idev && dev->mtu >= IPV6_MIN_MTU) { idev = ipv6_add_dev(dev); - if (idev) + if (!IS_ERR(idev)) break; } @@ -2935,10 +2954,14 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (idev) { snmp6_unregister_dev(idev); addrconf_sysctl_unregister(idev); - addrconf_sysctl_register(idev); - err = snmp6_register_dev(idev); + err = addrconf_sysctl_register(idev); if (err) return notifier_from_errno(err); + err = snmp6_register_dev(idev); + if (err) { + addrconf_sysctl_unregister(idev); + return notifier_from_errno(err); + } } break; @@ -3011,7 +3034,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { hlist_del_init_rcu(&ifa->addr_lst); - addrconf_del_dad_timer(ifa); + addrconf_del_dad_work(ifa); goto restart; } } @@ -3049,7 +3072,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) while (!list_empty(&idev->addr_list)) { ifa = list_first_entry(&idev->addr_list, struct inet6_ifaddr, if_list); - addrconf_del_dad_timer(ifa); + addrconf_del_dad_work(ifa); list_del(&ifa->if_list); @@ -3071,11 +3094,13 @@ static int addrconf_ifdown(struct net_device *dev, int how) write_unlock_bh(&idev->lock); - /* Step 5: Discard multicast list */ - if (how) + /* Step 5: Discard anycast and multicast list */ + if (how) { + ipv6_ac_destroy_dev(idev); ipv6_mc_destroy_dev(idev); - else + } else { ipv6_mc_down(idev); + } idev->tstamp = jiffies; @@ -3148,10 +3173,10 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1); ifp->dad_probes = idev->cnf.dad_transmits; - addrconf_mod_dad_timer(ifp, rand_num); + addrconf_mod_dad_work(ifp, rand_num); } -static void addrconf_dad_start(struct inet6_ifaddr *ifp) +static void addrconf_dad_begin(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; @@ -3203,25 +3228,68 @@ out: read_unlock_bh(&idev->lock); } -static void addrconf_dad_timer(unsigned long data) +static void addrconf_dad_start(struct inet6_ifaddr *ifp) +{ + bool begin_dad = false; + + spin_lock_bh(&ifp->state_lock); + if (ifp->state != INET6_IFADDR_STATE_DEAD) { + ifp->state = INET6_IFADDR_STATE_PREDAD; + begin_dad = true; + } + spin_unlock_bh(&ifp->state_lock); + + if (begin_dad) + addrconf_mod_dad_work(ifp, 0); +} + +static void addrconf_dad_work(struct work_struct *w) { - struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data; + struct inet6_ifaddr *ifp = container_of(to_delayed_work(w), + struct inet6_ifaddr, + dad_work); struct inet6_dev *idev = ifp->idev; struct in6_addr mcaddr; + enum { + DAD_PROCESS, + DAD_BEGIN, + DAD_ABORT, + } action = DAD_PROCESS; + + rtnl_lock(); + + spin_lock_bh(&ifp->state_lock); + if (ifp->state == INET6_IFADDR_STATE_PREDAD) { + action = DAD_BEGIN; + ifp->state = INET6_IFADDR_STATE_DAD; + } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) { + action = DAD_ABORT; + ifp->state = INET6_IFADDR_STATE_POSTDAD; + } + spin_unlock_bh(&ifp->state_lock); + + if (action == DAD_BEGIN) { + addrconf_dad_begin(ifp); + goto out; + } else if (action == DAD_ABORT) { + addrconf_dad_stop(ifp, 1); + goto out; + } + if (!ifp->dad_probes && addrconf_dad_end(ifp)) goto out; - write_lock(&idev->lock); + write_lock_bh(&idev->lock); if (idev->dead || !(idev->if_flags & IF_READY)) { - write_unlock(&idev->lock); + write_unlock_bh(&idev->lock); goto out; } spin_lock(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DEAD) { spin_unlock(&ifp->lock); - write_unlock(&idev->lock); + write_unlock_bh(&idev->lock); goto out; } @@ -3232,7 +3300,7 @@ static void addrconf_dad_timer(unsigned long data) ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); - write_unlock(&idev->lock); + write_unlock_bh(&idev->lock); addrconf_dad_completed(ifp); @@ -3240,16 +3308,17 @@ static void addrconf_dad_timer(unsigned long data) } ifp->dad_probes--; - addrconf_mod_dad_timer(ifp, - NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME)); + addrconf_mod_dad_work(ifp, + NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME)); spin_unlock(&ifp->lock); - write_unlock(&idev->lock); + write_unlock_bh(&idev->lock); /* send a neighbour solicitation for our addr */ addrconf_addr_solict_mult(&ifp->addr, &mcaddr); ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any); out: in6_ifa_put(ifp); + rtnl_unlock(); } /* ifp->idev must be at least read locked */ @@ -3276,7 +3345,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) struct in6_addr lladdr; bool send_rs, send_mld; - addrconf_del_dad_timer(ifp); + addrconf_del_dad_work(ifp); /* * Configure the address for reception. Now it is valid. @@ -3517,23 +3586,23 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) * Periodic address status verification */ -static void addrconf_verify(unsigned long foo) +static void addrconf_verify_rtnl(void) { unsigned long now, next, next_sec, next_sched; struct inet6_ifaddr *ifp; int i; + ASSERT_RTNL(); + rcu_read_lock_bh(); - spin_lock(&addrconf_verify_lock); now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); - del_timer(&addr_chk_timer); + cancel_delayed_work(&addr_chk_work); for (i = 0; i < IN6_ADDR_HSIZE; i++) { restart: - hlist_for_each_entry_rcu_bh(ifp, - &inet6_addr_lst[i], addr_lst) { + hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) { unsigned long age; /* When setting preferred_lft to a value not zero or @@ -3628,13 +3697,22 @@ restart: 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(&addrconf_verify_lock); + mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now); rcu_read_unlock_bh(); } +static void addrconf_verify_work(struct work_struct *w) +{ + rtnl_lock(); + addrconf_verify_rtnl(); + rtnl_unlock(); +} + +static void addrconf_verify(void) +{ + mod_delayed_work(addrconf_wq, &addr_chk_work, 0); +} + static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local, struct in6_addr **peer_pfx) { @@ -3668,6 +3746,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *pfx, *peer_pfx; + u32 ifa_flags; int err; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy); @@ -3679,7 +3758,13 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) if (pfx == NULL) return -EINVAL; - return inet6_addr_del(net, ifm->ifa_index, pfx, ifm->ifa_prefixlen); + ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; + + /* We ignore other flags so far. */ + ifa_flags &= IFA_F_MANAGETEMPADDR; + + return inet6_addr_del(net, ifm->ifa_index, ifa_flags, pfx, + ifm->ifa_prefixlen); } static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, @@ -3691,6 +3776,8 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, bool was_managetempaddr; bool had_prefixroute; + ASSERT_RTNL(); + if (!valid_lft || (prefered_lft > valid_lft)) return -EINVAL; @@ -3756,7 +3843,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, !was_managetempaddr, jiffies); } - addrconf_verify(0); + addrconf_verify_rtnl(); return 0; } @@ -4249,6 +4336,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify; array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc; + array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local; } static inline size_t inet6_ifla6_size(void) @@ -4286,7 +4374,7 @@ static inline void __snmp6_fill_statsdev(u64 *stats, atomic_long_t *mib, memset(&stats[items], 0, pad); } -static inline void __snmp6_fill_stats64(u64 *stats, void __percpu **mib, +static inline void __snmp6_fill_stats64(u64 *stats, void __percpu *mib, int items, int bytes, size_t syncpoff) { int i; @@ -4306,7 +4394,7 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, { switch (attrtype) { case IFLA_INET6_STATS: - __snmp6_fill_stats64(stats, (void __percpu **)idev->stats.ipv6, + __snmp6_fill_stats64(stats, idev->stats.ipv6, IPSTATS_MIB_MAX, bytes, offsetof(struct ipstats_mib, syncp)); break; case IFLA_INET6_ICMP6STATS: @@ -4348,6 +4436,10 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev) nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr)); if (nla == NULL) goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->addr_gen_mode)) + goto nla_put_failure; + read_lock_bh(&idev->lock); memcpy(nla_data(nla), idev->token.s6_addr, nla_len(nla)); read_unlock_bh(&idev->lock); @@ -4386,6 +4478,8 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) bool update_rs = false; struct in6_addr ll_addr; + ASSERT_RTNL(); + if (token == NULL) return -EINVAL; if (ipv6_addr_any(token)) @@ -4434,7 +4528,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) } write_unlock_bh(&idev->lock); - addrconf_verify(0); + addrconf_verify_rtnl(); return 0; } @@ -4450,8 +4544,21 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) if (nla_parse_nested(tb, IFLA_INET6_MAX, nla, NULL) < 0) BUG(); - if (tb[IFLA_INET6_TOKEN]) + if (tb[IFLA_INET6_TOKEN]) { err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN])); + if (err) + return err; + } + + if (tb[IFLA_INET6_ADDR_GEN_MODE]) { + u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]); + + if (mode != IN6_ADDR_GEN_MODE_EUI64 && + mode != IN6_ADDR_GEN_MODE_NONE) + return -EINVAL; + idev->addr_gen_mode = mode; + err = 0; + } return err; } @@ -4636,6 +4743,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) { struct net *net = dev_net(ifp->idev->dev); + if (event) + ASSERT_RTNL(); + inet6_ifa_notify(event ? : RTM_NEWADDR, ifp); switch (event) { @@ -4660,24 +4770,21 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) addrconf_leave_solict(ifp->idev, &ifp->addr); if (!ipv6_addr_any(&ifp->peer_addr)) { struct rt6_info *rt; - struct net_device *dev = ifp->idev->dev; - - rt = rt6_lookup(dev_net(dev), &ifp->peer_addr, NULL, - dev->ifindex, 1); - if (rt) { - dst_hold(&rt->dst); - if (ip6_del_rt(rt)) - dst_free(&rt->dst); - } + + rt = addrconf_get_prefix_route(&ifp->peer_addr, 128, + ifp->idev->dev, 0, 0); + if (rt && ip6_del_rt(rt)) + dst_free(&rt->dst); } dst_hold(&ifp->rt->dst); if (ip6_del_rt(ifp->rt)) dst_free(&ifp->rt->dst); + + rt_genid_bump_ipv6(net); break; } atomic_inc(&net->ipv6.dev_addr_genid); - rt_genid_bump_ipv6(net); } static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) @@ -5091,6 +5198,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec }, { + .procname = "accept_ra_from_local", + .data = &ipv6_devconf.accept_ra_from_local, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { /* sentinel */ } }, @@ -5141,12 +5255,23 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p) kfree(t); } -static void addrconf_sysctl_register(struct inet6_dev *idev) +static int addrconf_sysctl_register(struct inet6_dev *idev) { - neigh_sysctl_register(idev->dev, idev->nd_parms, - &ndisc_ifinfo_sysctl_change); - __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, - idev, &idev->cnf); + int err; + + if (!sysctl_dev_name_is_allowed(idev->dev->name)) + return -EINVAL; + + err = neigh_sysctl_register(idev->dev, idev->nd_parms, + &ndisc_ifinfo_sysctl_change); + if (err) + return err; + err = __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, + idev, &idev->cnf); + if (err) + neigh_sysctl_unregister(idev->nd_parms); + + return err; } static void addrconf_sysctl_unregister(struct inet6_dev *idev) @@ -5231,6 +5356,7 @@ static struct rtnl_af_ops inet6_ops = { int __init addrconf_init(void) { + struct inet6_dev *idev; int i, err; err = ipv6_addr_label_init(); @@ -5244,6 +5370,12 @@ int __init addrconf_init(void) if (err < 0) goto out_addrlabel; + addrconf_wq = create_workqueue("ipv6_addrconf"); + if (!addrconf_wq) { + err = -ENOMEM; + goto out_nowq; + } + /* The addrconf netdev notifier requires that loopback_dev * has it's ipv6 private information allocated and setup * before it can bring up and give link-local addresses @@ -5263,18 +5395,19 @@ int __init addrconf_init(void) * device and it being up should be removed. */ rtnl_lock(); - if (!ipv6_add_dev(init_net.loopback_dev)) - err = -ENOMEM; + idev = ipv6_add_dev(init_net.loopback_dev); rtnl_unlock(); - if (err) + if (IS_ERR(idev)) { + err = PTR_ERR(idev); 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); + addrconf_verify(); rtnl_af_register(&inet6_ops); @@ -5302,6 +5435,8 @@ errout: rtnl_af_unregister(&inet6_ops); unregister_netdevice_notifier(&ipv6_dev_notf); errlo: + destroy_workqueue(addrconf_wq); +out_nowq: unregister_pernet_subsys(&addrconf_ops); out_addrlabel: ipv6_addr_label_cleanup(); @@ -5337,7 +5472,8 @@ void addrconf_cleanup(void) 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); + cancel_delayed_work(&addr_chk_work); rtnl_unlock(); + + destroy_workqueue(addrconf_wq); } diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 4c11cbcf8308..98cc4cd570e2 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -8,6 +8,13 @@ #include <net/addrconf.h> #include <net/ip.h> +/* if ipv6 module registers this function is used by xfrm to force all + * sockets to relookup their nodes - this is fairly expensive, be + * careful + */ +void (*__fib6_flush_trees)(struct net *); +EXPORT_SYMBOL(__fib6_flush_trees); + #define IPV6_ADDR_SCOPE_TYPE(scope) ((scope) << 16) static inline unsigned int ipv6_addr_scope2type(unsigned int scope) @@ -123,7 +130,7 @@ static void snmp6_free_dev(struct inet6_dev *idev) { kfree(idev->stats.icmpv6msgdev); kfree(idev->stats.icmpv6dev); - snmp_mib_free((void __percpu **)idev->stats.ipv6); + free_percpu(idev->stats.ipv6); } /* Nobody refers to this device, we may destroy it. */ diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index b30ad3741b46..fd0dc47f471d 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -6,7 +6,7 @@ */ /* * Author: - * YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org> + * YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org> */ #include <linux/kernel.h> @@ -22,14 +22,13 @@ #if 0 #define ADDRLABEL(x...) printk(x) #else -#define ADDRLABEL(x...) do { ; } while(0) +#define ADDRLABEL(x...) do { ; } while (0) #endif /* * Policy Table */ -struct ip6addrlbl_entry -{ +struct ip6addrlbl_entry { #ifdef CONFIG_NET_NS struct net *lbl_net; #endif @@ -88,39 +87,39 @@ static const __net_initconst struct ip6addrlbl_init_table { /* ::/0 */ .prefix = &in6addr_any, .label = 1, - },{ /* fc00::/7 */ - .prefix = &(struct in6_addr){{{ 0xfc }}}, + }, { /* fc00::/7 */ + .prefix = &(struct in6_addr){ { { 0xfc } } } , .prefixlen = 7, .label = 5, - },{ /* fec0::/10 */ - .prefix = &(struct in6_addr){{{ 0xfe, 0xc0 }}}, + }, { /* fec0::/10 */ + .prefix = &(struct in6_addr){ { { 0xfe, 0xc0 } } }, .prefixlen = 10, .label = 11, - },{ /* 2002::/16 */ - .prefix = &(struct in6_addr){{{ 0x20, 0x02 }}}, + }, { /* 2002::/16 */ + .prefix = &(struct in6_addr){ { { 0x20, 0x02 } } }, .prefixlen = 16, .label = 2, - },{ /* 3ffe::/16 */ - .prefix = &(struct in6_addr){{{ 0x3f, 0xfe }}}, + }, { /* 3ffe::/16 */ + .prefix = &(struct in6_addr){ { { 0x3f, 0xfe } } }, .prefixlen = 16, .label = 12, - },{ /* 2001::/32 */ - .prefix = &(struct in6_addr){{{ 0x20, 0x01 }}}, + }, { /* 2001::/32 */ + .prefix = &(struct in6_addr){ { { 0x20, 0x01 } } }, .prefixlen = 32, .label = 6, - },{ /* 2001:10::/28 */ - .prefix = &(struct in6_addr){{{ 0x20, 0x01, 0x00, 0x10 }}}, + }, { /* 2001:10::/28 */ + .prefix = &(struct in6_addr){ { { 0x20, 0x01, 0x00, 0x10 } } }, .prefixlen = 28, .label = 7, - },{ /* ::ffff:0:0 */ - .prefix = &(struct in6_addr){{{ [10] = 0xff, [11] = 0xff }}}, + }, { /* ::ffff:0:0 */ + .prefix = &(struct in6_addr){ { { [10] = 0xff, [11] = 0xff } } }, .prefixlen = 96, .label = 4, - },{ /* ::/96 */ + }, { /* ::/96 */ .prefix = &in6addr_any, .prefixlen = 96, .label = 3, - },{ /* ::1/128 */ + }, { /* ::1/128 */ .prefix = &in6addr_loopback, .prefixlen = 128, .label = 0, @@ -278,7 +277,7 @@ static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) last = p; } if (last) - hlist_add_after_rcu(&last->list, &newp->list); + hlist_add_behind_rcu(&newp->list, &last->list); else hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head); out: @@ -441,7 +440,7 @@ static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh) if (label == IPV6_ADDR_LABEL_DEFAULT) return -EINVAL; - switch(nlh->nlmsg_type) { + switch (nlh->nlmsg_type) { case RTM_NEWADDRLABEL: if (ifal->ifal_index && !__dev_get_by_index(net, ifal->ifal_index)) @@ -505,12 +504,13 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { if (idx >= s_idx && net_eq(ip6addrlbl_net(p), net)) { - if ((err = ip6addrlbl_fill(skb, p, - ip6addrlbl_table.seq, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWADDRLABEL, - NLM_F_MULTI)) <= 0) + err = ip6addrlbl_fill(skb, p, + ip6addrlbl_table.seq, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWADDRLABEL, + NLM_F_MULTI); + if (err <= 0) break; } idx++; @@ -527,7 +527,7 @@ static inline int ip6addrlbl_msgsize(void) + nla_total_size(4); /* IFAL_LABEL */ } -static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh) +static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh) { struct net *net = sock_net(in_skb->sk); struct ifaddrlblmsg *ifal; @@ -568,7 +568,8 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh) goto out; } - if (!(skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL))) { + skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL); + if (!skb) { ip6addrlbl_put(p); return -ENOBUFS; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d935889f1008..2daa3a133e49 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -106,7 +106,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol, struct inet_protosw *answer; struct proto *answer_prot; unsigned char answer_flags; - char answer_no_check; int try_loading_module = 0; int err; @@ -162,7 +161,6 @@ lookup_protocol: sock->ops = answer->ops; answer_prot = answer->prot; - answer_no_check = answer->no_check; answer_flags = answer->flags; rcu_read_unlock(); @@ -176,7 +174,6 @@ lookup_protocol: sock_init_data(sock, sk); err = 0; - sk->sk_no_check = answer_no_check; if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; @@ -200,7 +197,7 @@ lookup_protocol: np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; - np->ipv6only = net->ipv6.sysctl.bindv6only; + sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; /* Init the ipv4 part of the socket since we can have sockets * using v6 API for ipv4. @@ -297,7 +294,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* Binding to v4-mapped address on a v6-only socket * makes no sense */ - if (np->ipv6only) { + if (sk->sk_ipv6only) { err = -EINVAL; goto out; } @@ -374,7 +371,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_type != IPV6_ADDR_ANY) { sk->sk_userlocks |= SOCK_BINDADDR_LOCK; if (addr_type != IPV6_ADDR_MAPPED) - np->ipv6only = 1; + sk->sk_ipv6only = 1; } if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; @@ -715,33 +712,25 @@ static int __net_init ipv6_init_mibs(struct net *net) { int i; - if (snmp_mib_init((void __percpu **)net->mib.udp_stats_in6, - sizeof(struct udp_mib), - __alignof__(struct udp_mib)) < 0) + net->mib.udp_stats_in6 = alloc_percpu(struct udp_mib); + if (!net->mib.udp_stats_in6) return -ENOMEM; - if (snmp_mib_init((void __percpu **)net->mib.udplite_stats_in6, - sizeof(struct udp_mib), - __alignof__(struct udp_mib)) < 0) + net->mib.udplite_stats_in6 = alloc_percpu(struct udp_mib); + if (!net->mib.udplite_stats_in6) goto err_udplite_mib; - if (snmp_mib_init((void __percpu **)net->mib.ipv6_statistics, - sizeof(struct ipstats_mib), - __alignof__(struct ipstats_mib)) < 0) + net->mib.ipv6_statistics = alloc_percpu(struct ipstats_mib); + if (!net->mib.ipv6_statistics) goto err_ip_mib; for_each_possible_cpu(i) { struct ipstats_mib *af_inet6_stats; - af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics[0], i); + af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics, i); u64_stats_init(&af_inet6_stats->syncp); -#if SNMP_ARRAY_SZ == 2 - af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics[1], i); - u64_stats_init(&af_inet6_stats->syncp); -#endif } - if (snmp_mib_init((void __percpu **)net->mib.icmpv6_statistics, - sizeof(struct icmpv6_mib), - __alignof__(struct icmpv6_mib)) < 0) + net->mib.icmpv6_statistics = alloc_percpu(struct icmpv6_mib); + if (!net->mib.icmpv6_statistics) goto err_icmp_mib; net->mib.icmpv6msg_statistics = kzalloc(sizeof(struct icmpv6msg_mib), GFP_KERNEL); @@ -750,22 +739,22 @@ static int __net_init ipv6_init_mibs(struct net *net) return 0; err_icmpmsg_mib: - snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics); + free_percpu(net->mib.icmpv6_statistics); err_icmp_mib: - snmp_mib_free((void __percpu **)net->mib.ipv6_statistics); + free_percpu(net->mib.ipv6_statistics); err_ip_mib: - snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6); + free_percpu(net->mib.udplite_stats_in6); err_udplite_mib: - snmp_mib_free((void __percpu **)net->mib.udp_stats_in6); + free_percpu(net->mib.udp_stats_in6); return -ENOMEM; } static void ipv6_cleanup_mibs(struct net *net) { - snmp_mib_free((void __percpu **)net->mib.udp_stats_in6); - snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6); - snmp_mib_free((void __percpu **)net->mib.ipv6_statistics); - snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics); + free_percpu(net->mib.udp_stats_in6); + free_percpu(net->mib.udplite_stats_in6); + free_percpu(net->mib.ipv6_statistics); + free_percpu(net->mib.icmpv6_statistics); kfree(net->mib.icmpv6msg_statistics); } @@ -776,6 +765,7 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.bindv6only = 0; net->ipv6.sysctl.icmpv6_time = 1*HZ; net->ipv6.sysctl.flowlabel_consistency = 1; + net->ipv6.sysctl.auto_flowlabels = 0; atomic_set(&net->ipv6.rt_genid, 0); err = ipv6_init_mibs(net); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 81e496a2e008..72a4930bdc0a 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -346,6 +346,10 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) struct ip_auth_hdr *ah; struct ah_data *ahp; struct tmp_ext *iph_ext; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; ahp = x->data; ahash = ahp->ahash; @@ -359,15 +363,22 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) if (extlen) extlen += sizeof(*iph_ext); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } err = -ENOMEM; - iph_base = ah_alloc_tmp(ahash, nfrags, IPV6HDR_BASELEN + extlen); + iph_base = ah_alloc_tmp(ahash, nfrags + sglists, IPV6HDR_BASELEN + + extlen + seqhi_len); if (!iph_base) goto out; iph_ext = ah_tmp_ext(iph_base); - icv = ah_tmp_icv(ahash, iph_ext, extlen); + seqhi = (__be32 *)((char *)iph_ext + extlen); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; ah = ip_auth_hdr(skb); memset(ah->auth_data, 0, ahp->icv_trunc_len); @@ -411,10 +422,15 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah6_output_done, skb); AH_SKB_CB(skb)->tmp = iph_base; @@ -514,6 +530,10 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) int nexthdr; int nfrags; int err = -ENOMEM; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; if (!pskb_may_pull(skb, sizeof(struct ip_auth_hdr))) goto out; @@ -550,14 +570,22 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, hdr_len); - work_iph = ah_alloc_tmp(ahash, nfrags, hdr_len + ahp->icv_trunc_len); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } + + work_iph = ah_alloc_tmp(ahash, nfrags + sglists, hdr_len + + ahp->icv_trunc_len + seqhi_len); if (!work_iph) goto out; - auth_data = ah_tmp_auth(work_iph, hdr_len); - icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); + auth_data = ah_tmp_auth((u8 *)work_iph, hdr_len); + seqhi = (__be32 *)(auth_data + ahp->icv_trunc_len); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memcpy(work_iph, ip6h, hdr_len); memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); @@ -572,10 +600,16 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) ip6h->flow_lbl[2] = 0; ip6h->hop_limit = 0; - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); + + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; + sg_set_buf(seqhisg, seqhi, seqhi_len); + } - ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah6_input_done, skb); AH_SKB_CB(skb)->tmp = work_iph; @@ -609,8 +643,8 @@ out: return err; } -static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, __be32 info) +static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; @@ -619,17 +653,19 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) - return; + return 0; x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); if (!x) - return; + return 0; if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0); else ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); + + return 0; } static int ah6_init_state(struct xfrm_state *x) @@ -714,6 +750,11 @@ static void ah6_destroy(struct xfrm_state *x) kfree(ahp); } +static int ah6_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type ah6_type = { .description = "AH6", @@ -727,10 +768,11 @@ static const struct xfrm_type ah6_type = .hdr_offset = xfrm6_find_1stfragopt, }; -static const struct inet6_protocol ah6_protocol = { +static struct xfrm6_protocol ah6_protocol = { .handler = xfrm6_rcv, + .cb_handler = ah6_rcv_cb, .err_handler = ah6_err, - .flags = INET6_PROTO_NOPOLICY, + .priority = 0, }; static int __init ah6_init(void) @@ -740,7 +782,7 @@ static int __init ah6_init(void) return -EAGAIN; } - if (inet6_add_protocol(&ah6_protocol, IPPROTO_AH) < 0) { + if (xfrm6_protocol_register(&ah6_protocol, IPPROTO_AH) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ah6_type, AF_INET6); return -EAGAIN; @@ -751,7 +793,7 @@ static int __init ah6_init(void) static void __exit ah6_fini(void) { - if (inet6_del_protocol(&ah6_protocol, IPPROTO_AH) < 0) + if (xfrm6_protocol_deregister(&ah6_protocol, IPPROTO_AH) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ah6_type, AF_INET6) < 0) diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 210183244689..9a386842fd62 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -77,6 +77,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) pac->acl_next = NULL; pac->acl_addr = *addr; + rtnl_lock(); rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -137,6 +138,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) error: rcu_read_unlock(); + rtnl_unlock(); if (pac) sock_kfree_s(sk, pac, sizeof(*pac)); return err; @@ -171,11 +173,13 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) spin_unlock_bh(&ipv6_sk_ac_lock); + rtnl_lock(); rcu_read_lock(); dev = dev_get_by_index_rcu(net, pac->acl_ifindex); if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, pac, sizeof(*pac)); return 0; @@ -198,6 +202,7 @@ void ipv6_sock_ac_close(struct sock *sk) spin_unlock_bh(&ipv6_sk_ac_lock); prev_index = 0; + rtnl_lock(); rcu_read_lock(); while (pac) { struct ipv6_ac_socklist *next = pac->acl_next; @@ -212,6 +217,7 @@ void ipv6_sock_ac_close(struct sock *sk) pac = next; } rcu_read_unlock(); + rtnl_unlock(); } static void aca_put(struct ifacaddr6 *ac) @@ -233,6 +239,8 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr) struct rt6_info *rt; int err; + ASSERT_RTNL(); + idev = in6_dev_get(dev); if (idev == NULL) @@ -302,6 +310,8 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca, *prev_aca; + ASSERT_RTNL(); + write_lock_bh(&idev->lock); prev_aca = NULL; for (aca = idev->ac_list; aca; aca = aca->aca_next) { @@ -341,6 +351,27 @@ static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr) return __ipv6_dev_ac_dec(idev, addr); } +void ipv6_ac_destroy_dev(struct inet6_dev *idev) +{ + struct ifacaddr6 *aca; + + write_lock_bh(&idev->lock); + while ((aca = idev->ac_list) != NULL) { + idev->ac_list = aca->aca_next; + write_unlock_bh(&idev->lock); + + addrconf_leave_solict(idev, &aca->aca_addr); + + dst_hold(&aca->aca_rt->dst); + ip6_del_rt(aca->aca_rt); + + aca_put(aca); + + write_lock_bh(&idev->lock); + } + write_unlock_bh(&idev->lock); +} + /* * check if the interface has this anycast address * called with rcu_read_lock() diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index c3bf2d2e519e..2753319524f1 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -199,6 +199,7 @@ ipv4_connected: NULL); sk->sk_state = TCP_ESTABLISHED; + ip6_set_txhash(sk); out: fl6_sock_release(flowlabel); return err; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 6eef8a7e35f2..d15da1377149 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -421,8 +421,8 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu) net_adj) & ~(blksize - 1)) + net_adj - 2; } -static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, __be32 info) +static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; @@ -431,18 +431,20 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) - return; + return 0; x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); if (!x) - return; + return 0; if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0); else ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); + + return 0; } static void esp6_destroy(struct xfrm_state *x) @@ -614,6 +616,11 @@ error: return err; } +static int esp6_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type esp6_type = { .description = "ESP6", @@ -628,10 +635,11 @@ static const struct xfrm_type esp6_type = .hdr_offset = xfrm6_find_1stfragopt, }; -static const struct inet6_protocol esp6_protocol = { - .handler = xfrm6_rcv, +static struct xfrm6_protocol esp6_protocol = { + .handler = xfrm6_rcv, + .cb_handler = esp6_rcv_cb, .err_handler = esp6_err, - .flags = INET6_PROTO_NOPOLICY, + .priority = 0, }; static int __init esp6_init(void) @@ -640,7 +648,7 @@ static int __init esp6_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet6_add_protocol(&esp6_protocol, IPPROTO_ESP) < 0) { + if (xfrm6_protocol_register(&esp6_protocol, IPPROTO_ESP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&esp6_type, AF_INET6); return -EAGAIN; @@ -651,7 +659,7 @@ static int __init esp6_init(void) static void __exit esp6_fini(void) { - if (inet6_del_protocol(&esp6_protocol, IPPROTO_ESP) < 0) + if (xfrm6_protocol_deregister(&esp6_protocol, IPPROTO_ESP) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&esp6_type, AF_INET6) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f2610e157660..06ba3e58320b 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -400,6 +400,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) int len; int hlimit; int err = 0; + u32 mark = IP6_REPLY_MARK(net, skb->mark); if ((u8 *)hdr < skb->head || (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb)) @@ -466,6 +467,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) fl6.daddr = hdr->saddr; if (saddr) fl6.saddr = *saddr; + fl6.flowi6_mark = mark; fl6.flowi6_oif = iif; fl6.fl6_icmp_type = type; fl6.fl6_icmp_code = code; @@ -474,6 +476,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) sk = icmpv6_xmit_lock(net); if (sk == NULL) return; + sk->sk_mark = mark; np = inet6_sk(sk); if (!icmpv6_xrlim_allow(sk, type, &fl6)) @@ -493,12 +496,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) if (IS_ERR(dst)) goto out; - if (ipv6_addr_is_multicast(&fl6.daddr)) - hlimit = np->mcast_hops; - else - hlimit = np->hop_limit; - if (hlimit < 0) - hlimit = ip6_dst_hoplimit(dst); + hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); msg.skb = skb; msg.offset = skb_network_offset(skb); @@ -520,7 +518,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) np->tclass, NULL, &fl6, (struct rt6_info *)dst, MSG_DONTWAIT, np->dontfrag); if (err) { - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, @@ -556,6 +554,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) int err = 0; int hlimit; u8 tclass; + u32 mark = IP6_REPLY_MARK(net, skb->mark); saddr = &ipv6_hdr(skb)->daddr; @@ -574,11 +573,13 @@ static void icmpv6_echo_reply(struct sk_buff *skb) fl6.saddr = *saddr; fl6.flowi6_oif = skb->dev->ifindex; fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY; + fl6.flowi6_mark = mark; security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); sk = icmpv6_xmit_lock(net); if (sk == NULL) return; + sk->sk_mark = mark; np = inet6_sk(sk); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) @@ -593,12 +594,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (IS_ERR(dst)) goto out; - if (ipv6_addr_is_multicast(&fl6.daddr)) - hlimit = np->mcast_hops; - else - hlimit = np->hop_limit; - if (hlimit < 0) - hlimit = ip6_dst_hoplimit(dst); + hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); idev = __in6_dev_get(skb->dev); @@ -630,9 +626,10 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) int inner_offset; __be16 frag_off; u8 nexthdr; + struct net *net = dev_net(skb->dev); if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - return; + goto out; nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr; if (ipv6_ext_hdr(nexthdr)) { @@ -640,14 +637,14 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (inner_offset<0) - return; + goto out; } else { inner_offset = sizeof(struct ipv6hdr); } /* Checkin header including 8 bytes of inner protocol header. */ if (!pskb_may_pull(skb, inner_offset+8)) - return; + goto out; /* BUGGG_FUTURE: we should try to parse exthdrs in this packet. Without this we will not able f.e. to make source routed @@ -656,13 +653,15 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) --ANK (980726) */ - rcu_read_lock(); ipprot = rcu_dereference(inet6_protos[nexthdr]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, NULL, type, code, inner_offset, info); - rcu_read_unlock(); raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info); + return; + +out: + ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); } /* @@ -702,22 +701,11 @@ static int icmpv6_rcv(struct sk_buff *skb) saddr = &ipv6_hdr(skb)->saddr; daddr = &ipv6_hdr(skb)->daddr; - /* Perform checksum. */ - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - if (!csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, - skb->csum)) - break; - /* fall through */ - case CHECKSUM_NONE: - skb->csum = ~csum_unfold(csum_ipv6_magic(saddr, daddr, skb->len, - IPPROTO_ICMPV6, 0)); - if (__skb_checksum_complete(skb)) { - LIMIT_NETDEBUG(KERN_DEBUG - "ICMPv6 checksum failed [%pI6c > %pI6c]\n", - saddr, daddr); - goto csum_error; - } + if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) { + LIMIT_NETDEBUG(KERN_DEBUG + "ICMPv6 checksum failed [%pI6c > %pI6c]\n", + saddr, daddr); + goto csum_error; } if (!pskb_pull(skb, sizeof(*hdr))) diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index c9138189415a..a245e5ddffbd 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -81,7 +81,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, final_p = fl6_update_dst(fl6, np->opt, &final); fl6->saddr = ireq->ir_v6_loc_addr; fl6->flowi6_oif = ireq->ir_iif; - fl6->flowi6_mark = sk->sk_mark; + fl6->flowi6_mark = ireq->ir_mark; fl6->fl6_dport = ireq->ir_rmt_port; fl6->fl6_sport = htons(ireq->ir_num); security_req_classify_flow(req, flowi6_to_flowi(fl6)); @@ -224,9 +224,8 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, return dst; } -int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) +int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused) { - struct sock *sk = skb->sk; struct ipv6_pinfo *np = inet6_sk(sk); struct flowi6 fl6; struct dst_entry *dst; diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c index 72d198b8e4d2..9a4d7322fb22 100644 --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -75,23 +75,50 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) return err; } - if (uh->check == 0) { - /* RFC 2460 section 8.1 says that we SHOULD log - this error. Well, it is reasonable. - */ - LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n"); - return 1; - } - if (skb->ip_summed == CHECKSUM_COMPLETE && - !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, - skb->len, proto, skb->csum)) - skb->ip_summed = CHECKSUM_UNNECESSARY; + /* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels) + * we accept a checksum of zero here. When we find the socket + * for the UDP packet we'll check if that socket allows zero checksum + * for IPv6 (set by socket option). + */ + return skb_checksum_init_zero_check(skb, proto, uh->check, + ip6_compute_pseudo); +} +EXPORT_SYMBOL(udp6_csum_init); + +/* Function to set UDP checksum for an IPv6 UDP packet. This is intended + * for the simple case like when setting the checksum for a UDP tunnel. + */ +void udp6_set_csum(bool nocheck, struct sk_buff *skb, + const struct in6_addr *saddr, + const struct in6_addr *daddr, int len) +{ + struct udphdr *uh = udp_hdr(skb); + + if (nocheck) + uh->check = 0; + else if (skb_is_gso(skb)) + uh->check = ~udp_v6_check(len, saddr, daddr, 0); + else if (skb_dst(skb) && skb_dst(skb)->dev && + (skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) { - if (!skb_csum_unnecessary(skb)) - skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len, proto, 0)); + BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); - return 0; + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + uh->check = ~udp_v6_check(len, saddr, daddr, 0); + } else { + __wsum csum; + + BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); + + uh->check = 0; + csum = skb_checksum(skb, 0, len, 0); + uh->check = udp_v6_check(len, saddr, daddr, csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + } } -EXPORT_SYMBOL(udp6_csum_init); +EXPORT_SYMBOL(udp6_set_csum); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 075602fc6b6a..97b9fa8de377 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -9,14 +9,12 @@ * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. - */ - -/* - * Changes: - * Yuji SEKIYA @USAGI: Support default route on router node; - * remove ip6_null_entry from the top of - * routing table. - * Ville Nuorvala: Fixed routing subtrees. + * + * Changes: + * Yuji SEKIYA @USAGI: Support default route on router node; + * remove ip6_null_entry from the top of + * routing table. + * Ville Nuorvala: Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt @@ -46,10 +44,9 @@ #define RT6_TRACE(x...) do { ; } while (0) #endif -static struct kmem_cache * fib6_node_kmem __read_mostly; +static struct kmem_cache *fib6_node_kmem __read_mostly; -enum fib_walk_state_t -{ +enum fib_walk_state_t { #ifdef CONFIG_IPV6_SUBTREES FWS_S, #endif @@ -59,8 +56,7 @@ enum fib_walk_state_t FWS_U }; -struct fib6_cleaner_t -{ +struct fib6_cleaner_t { struct fib6_walker_t w; struct net *net; int (*func)(struct rt6_info *, void *arg); @@ -75,8 +71,7 @@ static DEFINE_RWLOCK(fib6_walker_lock); #define FWS_INIT FWS_L #endif -static void fib6_prune_clones(struct net *net, struct fib6_node *fn, - struct rt6_info *rt); +static void fib6_prune_clones(struct net *net, struct fib6_node *fn); static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn); static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn); static int fib6_walk(struct fib6_walker_t *w); @@ -138,7 +133,7 @@ static __inline__ __be32 addr_bit_set(const void *token, int fn_bit) const __be32 *addr = token; /* * Here, - * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) + * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) * is optimized version of * htonl(1 << ((~fn_bit)&0x1F)) * See include/asm-generic/bitops/le.h. @@ -147,7 +142,7 @@ static __inline__ __be32 addr_bit_set(const void *token, int fn_bit) addr[fn_bit >> 5]; } -static __inline__ struct fib6_node * node_alloc(void) +static __inline__ struct fib6_node *node_alloc(void) { struct fib6_node *fn; @@ -156,7 +151,7 @@ static __inline__ struct fib6_node * node_alloc(void) return fn; } -static __inline__ void node_free(struct fib6_node * fn) +static __inline__ void node_free(struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); } @@ -292,7 +287,7 @@ static int fib6_dump_node(struct fib6_walker_t *w) static void fib6_dump_end(struct netlink_callback *cb) { - struct fib6_walker_t *w = (void*)cb->args[2]; + struct fib6_walker_t *w = (void *)cb->args[2]; if (w) { if (cb->args[4]) { @@ -302,7 +297,7 @@ static void fib6_dump_end(struct netlink_callback *cb) cb->args[2] = 0; kfree(w); } - cb->done = (void*)cb->args[3]; + cb->done = (void *)cb->args[3]; cb->args[1] = 3; } @@ -485,7 +480,7 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, fn->fn_sernum = sernum; dir = addr_bit_set(addr, fn->fn_bit); pn = fn; - fn = dir ? fn->right: fn->left; + fn = dir ? fn->right : fn->left; } while (fn); if (!allow_create) { @@ -638,12 +633,41 @@ static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt) RTF_GATEWAY; } +static int fib6_commit_metrics(struct dst_entry *dst, + struct nlattr *mx, int mx_len) +{ + struct nlattr *nla; + int remaining; + u32 *mp; + + if (dst->flags & DST_HOST) { + mp = dst_metrics_write_ptr(dst); + } else { + mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC); + if (!mp) + return -ENOMEM; + dst_init_metrics(dst, mp, 0); + } + + nla_for_each_attr(nla, mx, mx_len, remaining) { + int type = nla_type(nla); + + if (type) { + if (type > RTAX_MAX) + return -EINVAL; + + mp[type - 1] = nla_get_u32(nla); + } + } + return 0; +} + /* * Insert routing information in a node. */ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, - struct nl_info *info) + struct nl_info *info, struct nlattr *mx, int mx_len) { struct rt6_info *iter = NULL; struct rt6_info **ins; @@ -653,6 +677,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); + int err; ins = &fn->leaf; @@ -751,6 +776,11 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, pr_warn("NLM_F_CREATE should be set when creating new route\n"); add: + if (mx) { + err = fib6_commit_metrics(&rt->dst, mx, mx_len); + if (err) + return err; + } rt->dst.rt6_next = iter; *ins = rt; rt->rt6i_node = fn; @@ -770,6 +800,11 @@ add: pr_warn("NLM_F_REPLACE set, but no existing node found!\n"); return -ENOENT; } + if (mx) { + err = fib6_commit_metrics(&rt->dst, mx, mx_len); + if (err) + return err; + } *ins = rt; rt->rt6i_node = fn; rt->dst.rt6_next = iter->dst.rt6_next; @@ -806,7 +841,8 @@ void fib6_force_start_gc(struct net *net) * with source addr info in sub-trees */ -int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) +int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info, + struct nlattr *mx, int mx_len) { struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; @@ -900,11 +936,11 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) } #endif - err = fib6_add_rt2node(fn, rt, info); + err = fib6_add_rt2node(fn, rt, info, mx, mx_len); if (!err) { fib6_start_gc(info->nl_net, rt); if (!(rt->rt6i_flags & RTF_CACHE)) - fib6_prune_clones(info->nl_net, pn, rt); + fib6_prune_clones(info->nl_net, pn); } out: @@ -955,8 +991,8 @@ struct lookup_args { const struct in6_addr *addr; /* search key */ }; -static struct fib6_node * fib6_lookup_1(struct fib6_node *root, - struct lookup_args *args) +static struct fib6_node *fib6_lookup_1(struct fib6_node *root, + struct lookup_args *args) { struct fib6_node *fn; __be32 dir; @@ -1018,8 +1054,8 @@ backtrack: return NULL; } -struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, - const struct in6_addr *saddr) +struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, + const struct in6_addr *saddr) { struct fib6_node *fn; struct lookup_args args[] = { @@ -1051,9 +1087,9 @@ struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *da */ -static struct fib6_node * fib6_locate_1(struct fib6_node *root, - const struct in6_addr *addr, - int plen, int offset) +static struct fib6_node *fib6_locate_1(struct fib6_node *root, + const struct in6_addr *addr, + int plen, int offset) { struct fib6_node *fn; @@ -1081,9 +1117,9 @@ static struct fib6_node * fib6_locate_1(struct fib6_node *root, return NULL; } -struct fib6_node * fib6_locate(struct fib6_node *root, - const struct in6_addr *daddr, int dst_len, - const struct in6_addr *saddr, int src_len) +struct fib6_node *fib6_locate(struct fib6_node *root, + const struct in6_addr *daddr, int dst_len, + const struct in6_addr *saddr, int src_len) { struct fib6_node *fn; @@ -1151,8 +1187,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net, children = 0; child = NULL; - if (fn->right) child = fn->right, children |= 1; - if (fn->left) child = fn->left, children |= 2; + if (fn->right) + child = fn->right, children |= 1; + if (fn->left) + child = fn->left, children |= 2; if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES @@ -1180,8 +1218,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net, } else { WARN_ON(fn->fn_flags & RTN_ROOT); #endif - if (pn->right == fn) pn->right = child; - else if (pn->left == fn) pn->left = child; + if (pn->right == fn) + pn->right = child; + else if (pn->left == fn) + pn->left = child; #if RT6_DEBUG >= 2 else WARN_ON(1); @@ -1213,10 +1253,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net, w->node = child; if (children&2) { RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); - w->state = w->state>=FWS_R ? FWS_U : FWS_INIT; + w->state = w->state >= FWS_R ? FWS_U : FWS_INIT; } else { RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); - w->state = w->state>=FWS_C ? FWS_U : FWS_INIT; + w->state = w->state >= FWS_C ? FWS_U : FWS_INIT; } } } @@ -1314,7 +1354,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) struct rt6_info **rtp; #if RT6_DEBUG >= 2 - if (rt->dst.obsolete>0) { + if (rt->dst.obsolete > 0) { WARN_ON(fn != NULL); return -ENOENT; } @@ -1334,7 +1374,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) pn = pn->parent; } #endif - fib6_prune_clones(info->nl_net, pn, rt); + fib6_prune_clones(info->nl_net, pn); } /* @@ -1418,7 +1458,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w) if (w->skip) { w->skip--; - continue; + goto skip; } err = w->func(w); @@ -1428,6 +1468,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w) w->count++; continue; } +skip: w->state = FWS_U; case FWS_U: if (fn == w->root) @@ -1559,10 +1600,27 @@ static int fib6_prune_clone(struct rt6_info *rt, void *arg) return 0; } -static void fib6_prune_clones(struct net *net, struct fib6_node *fn, - struct rt6_info *rt) +static void fib6_prune_clones(struct net *net, struct fib6_node *fn) { - fib6_clean_tree(net, fn, fib6_prune_clone, 1, rt); + fib6_clean_tree(net, fn, fib6_prune_clone, 1, NULL); +} + +static int fib6_update_sernum(struct rt6_info *rt, void *arg) +{ + __u32 sernum = *(__u32 *)arg; + + if (rt->rt6i_node && + rt->rt6i_node->fn_sernum != sernum) + rt->rt6i_node->fn_sernum = sernum; + + return 0; +} + +static void fib6_flush_trees(struct net *net) +{ + __u32 new_sernum = fib6_new_sernum(); + + fib6_clean_all(net, fib6_update_sernum, &new_sernum); } /* @@ -1707,7 +1765,7 @@ out_rt6_stats: kfree(net->ipv6.rt6_stats); out_timer: return -ENOMEM; - } +} static void fib6_net_exit(struct net *net) { @@ -1748,6 +1806,8 @@ int __init fib6_init(void) NULL); if (ret) goto out_unregister_subsys; + + __fib6_flush_trees = fib6_flush_trees; out: return ret; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index dfa41bb4e0dc..4052694c6f2c 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -15,9 +15,7 @@ #include <linux/socket.h> #include <linux/net.h> #include <linux/netdevice.h> -#include <linux/if_arp.h> #include <linux/in6.h> -#include <linux/route.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> @@ -28,12 +26,7 @@ #include <net/sock.h> #include <net/ipv6.h> -#include <net/ndisc.h> -#include <net/protocol.h> -#include <net/ip6_route.h> -#include <net/addrconf.h> #include <net/rawv6.h> -#include <net/icmp.h> #include <net/transp_v6.h> #include <asm/uaccess.h> diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index f3ffb43f59c0..f304471477dc 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -72,6 +72,7 @@ struct ip6gre_net { }; static struct rtnl_link_ops ip6gre_link_ops __read_mostly; +static struct rtnl_link_ops ip6gre_tap_ops __read_mostly; static int ip6gre_tunnel_init(struct net_device *dev); static void ip6gre_tunnel_setup(struct net_device *dev); static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t); @@ -313,6 +314,8 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net, struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); t = ip6gre_tunnel_find(net, parms, ARPHRD_IP6GRE); + if (t && create) + return NULL; if (t || !create) return t; @@ -321,7 +324,8 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net, else strcpy(name, "ip6gre%d"); - dev = alloc_netdev(sizeof(*t), name, ip6gre_tunnel_setup); + dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, + ip6gre_tunnel_setup); if (!dev) return NULL; @@ -353,10 +357,10 @@ failed_free: static void ip6gre_tunnel_uninit(struct net_device *dev) { - struct net *net = dev_net(dev); - struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + struct ip6_tnl *t = netdev_priv(dev); + struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id); - ip6gre_tunnel_unlink(ign, netdev_priv(dev)); + ip6gre_tunnel_unlink(ign, t); dev_put(dev); } @@ -467,17 +471,7 @@ static int ip6gre_rcv(struct sk_buff *skb) goto drop; if (flags&GRE_CSUM) { - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - csum = csum_fold(skb->csum); - if (!csum) - break; - /* fall through */ - case CHECKSUM_NONE: - skb->csum = 0; - csum = __skb_checksum_complete(skb); - skb->ip_summed = CHECKSUM_COMPLETE; - } + csum = skb_checksum_simple_validate(skb); offset += 4; } if (flags&GRE_KEY) { @@ -611,8 +605,8 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, int encap_limit, __u32 *pmtu) { - struct net *net = dev_net(dev); struct ip6_tnl *tunnel = netdev_priv(dev); + struct net *net = tunnel->net; struct net_device *tdev; /* Device to other host */ struct ipv6hdr *ipv6h; /* Our new IP header */ unsigned int max_headroom = 0; /* The extra header space needed */ @@ -732,7 +726,8 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, * Push down and install the IP header. */ ipv6h = ipv6_hdr(skb); - ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), fl6->flowlabel); + ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), + ip6_make_flowlabel(net, skb, fl6->flowlabel, false)); ipv6h->hop_limit = tunnel->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; @@ -979,7 +974,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)); - struct rt6_info *rt = rt6_lookup(dev_net(dev), + struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, p->link, strict); @@ -1063,13 +1058,12 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, int err = 0; struct ip6_tnl_parm2 p; struct __ip6_tnl_parm p1; - struct ip6_tnl *t; - struct net *net = dev_net(dev); + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = t->net; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); switch (cmd) { case SIOCGETTUNNEL: - t = NULL; if (dev == ign->fb_tunnel_dev) { if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { err = -EFAULT; @@ -1077,9 +1071,9 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, } ip6gre_tnl_parm_from_user(&p1, &p); t = ip6gre_tunnel_locate(net, &p1, 0); + if (t == NULL) + t = netdev_priv(dev); } - if (t == NULL) - t = netdev_priv(dev); memset(&p, 0, sizeof(p)); ip6gre_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) @@ -1184,7 +1178,9 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen); __be16 *p = (__be16 *)(ipv6h+1); - ip6_flow_hdr(ipv6h, 0, t->fl.u.ip6.flowlabel); + ip6_flow_hdr(ipv6h, 0, + ip6_make_flowlabel(dev_net(dev), skb, + t->fl.u.ip6.flowlabel, false)); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = NEXTHDR_GRE; ipv6h->saddr = t->parms.laddr; @@ -1242,7 +1238,6 @@ static void ip6gre_tunnel_setup(struct net_device *dev) dev->flags |= IFF_NOARP; dev->iflink = 0; dev->addr_len = sizeof(struct in6_addr); - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; } @@ -1297,11 +1292,17 @@ static struct inet6_protocol ip6gre_protocol __read_mostly = { .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; -static void ip6gre_destroy_tunnels(struct ip6gre_net *ign, - struct list_head *head) +static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head) { + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + struct net_device *dev, *aux; int prio; + for_each_netdev_safe(net, dev, aux) + if (dev->rtnl_link_ops == &ip6gre_link_ops || + dev->rtnl_link_ops == &ip6gre_tap_ops) + unregister_netdevice_queue(dev, head); + for (prio = 0; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { @@ -1310,7 +1311,12 @@ static void ip6gre_destroy_tunnels(struct ip6gre_net *ign, t = rtnl_dereference(ign->tunnels[prio][h]); while (t != NULL) { - unregister_netdevice_queue(t->dev, head); + /* If dev is in the same netns, it has already + * been added to the list by the previous loop. + */ + if (!net_eq(dev_net(t->dev), net)) + unregister_netdevice_queue(t->dev, + head); t = rtnl_dereference(t->next); } } @@ -1323,12 +1329,18 @@ static int __net_init ip6gre_init_net(struct net *net) int err; ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", - ip6gre_tunnel_setup); + NET_NAME_UNKNOWN, + ip6gre_tunnel_setup); if (!ign->fb_tunnel_dev) { err = -ENOMEM; goto err_alloc_dev; } dev_net_set(ign->fb_tunnel_dev, net); + /* FB netdevice is special: we have one, and only one per netns. + * Allowing to move it to another netns is clearly unsafe. + */ + ign->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + ip6gre_fb_tunnel_init(ign->fb_tunnel_dev); ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops; @@ -1349,12 +1361,10 @@ err_alloc_dev: static void __net_exit ip6gre_exit_net(struct net *net) { - struct ip6gre_net *ign; LIST_HEAD(list); - ign = net_generic(net, ip6gre_net_id); rtnl_lock(); - ip6gre_destroy_tunnels(ign, &list); + ip6gre_destroy_tunnels(net, &list); unregister_netdevice_many(&list); rtnl_unlock(); } @@ -1454,7 +1464,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[], static int ip6gre_tap_init(struct net_device *dev) { struct ip6_tnl *tunnel; - int i; tunnel = netdev_priv(dev); @@ -1464,16 +1473,10 @@ static int ip6gre_tap_init(struct net_device *dev) ip6gre_tnl_link_config(tunnel, 1); - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ip6gre_tap_stats; - ip6gre_tap_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ip6gre_tap_stats->syncp); - } - return 0; } @@ -1538,15 +1541,14 @@ out: static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - struct ip6_tnl *t, *nt; - struct net *net = dev_net(dev); + struct ip6_tnl *t, *nt = netdev_priv(dev); + struct net *net = nt->net; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); struct __ip6_tnl_parm p; if (dev == ign->fb_tunnel_dev) return -EINVAL; - nt = netdev_priv(dev); ip6gre_netlink_parms(data, &p); t = ip6gre_tunnel_locate(net, &p, 0); @@ -1566,6 +1568,15 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], return 0; } +static void ip6gre_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + + if (dev != ign->fb_tunnel_dev) + unregister_netdevice_queue(dev, head); +} + static size_t ip6gre_get_size(const struct net_device *dev) { return @@ -1643,6 +1654,7 @@ static struct rtnl_link_ops ip6gre_link_ops __read_mostly = { .validate = ip6gre_tunnel_validate, .newlink = ip6gre_newlink, .changelink = ip6gre_changelink, + .dellink = ip6gre_dellink, .get_size = ip6gre_get_size, .fill_info = ip6gre_fill_info, }; @@ -1714,4 +1726,5 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)"); MODULE_DESCRIPTION("GRE over IPv6 tunneling device"); MODULE_ALIAS_RTNL_LINK("ip6gre"); +MODULE_ALIAS_RTNL_LINK("ip6gretap"); MODULE_ALIAS_NETDEV("ip6gre0"); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 59f95affceb0..65eda2a8af48 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -97,9 +97,11 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_GRE | + SKB_GSO_GRE_CSUM | SKB_GSO_IPIP | SKB_GSO_SIT | SKB_GSO_UDP_TUNNEL | + SKB_GSO_UDP_TUNNEL_CSUM | SKB_GSO_MPLS | SKB_GSO_TCPV6 | 0))) @@ -196,7 +198,6 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, unsigned int off; u16 flush = 1; int proto; - __wsum csum; off = skb_gro_offset(skb); hlen = off + sizeof(*iph); @@ -264,13 +265,10 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, NAPI_GRO_CB(skb)->flush |= flush; - csum = skb->csum; - skb_postpull_rcsum(skb, iph, skb_network_header_len(skb)); + skb_gro_postpull_rcsum(skb, iph, nlen); pp = ops->callbacks.gro_receive(head, skb); - skb->csum = csum; - out_unlock: rcu_read_unlock(); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 16f91a2e7888..0a3448b2888f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -132,7 +132,7 @@ static int ip6_finish_output(struct sk_buff *skb) return ip6_finish_output2(skb); } -int ip6_output(struct sk_buff *skb) +int ip6_output(struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); @@ -205,7 +205,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - ip6_flow_hdr(hdr, tclass, fl6->flowlabel); + ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, + np->autoflowlabel)); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@ -219,7 +220,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, skb->mark = sk->sk_mark; mtu = dst_mtu(dst); - if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) { + if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUT, skb->len); return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, @@ -344,12 +345,16 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { - if (skb->len <= mtu || skb->local_df) + if (skb->len <= mtu) return false; + /* ipv6 conntrack defrag sets max_frag_size + ignore_df */ if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) return true; + if (skb->ignore_df) + return false; + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) return false; @@ -367,6 +372,9 @@ int ip6_forward(struct sk_buff *skb) if (net->ipv6.devconf_all->forwarding == 0) goto error; + if (skb->pkt_type != PACKET_HOST) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -376,9 +384,6 @@ int ip6_forward(struct sk_buff *skb) goto drop; } - if (skb->pkt_type != PACKET_HOST) - goto drop; - skb_forward_csum(skb); /* @@ -533,6 +538,20 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } +static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +{ + static u32 ip6_idents_hashrnd __read_mostly; + u32 hash, id; + + net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); + + hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd); + hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash); + + id = ip_idents_reserve(hash, 1); + fhdr->identification = htonl(id); +} + int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; @@ -555,7 +574,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) /* We must not fragment if the socket is set to force MTU discovery * or if the skb it not generated by a local socket. */ - if (unlikely(!skb->local_df && skb->len > mtu) || + if (unlikely(!skb->ignore_df && skb->len > mtu) || (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) { if (skb->sk && dst_allfrag(skb_dst(skb))) @@ -784,8 +803,8 @@ slow_path: /* * Copy a block of the IP datagram. */ - if (skb_copy_bits(skb, ptr, skb_transport_header(frag), len)) - BUG(); + BUG_ON(skb_copy_bits(skb, ptr, skb_transport_header(frag), + len)); left -= len; fh->frag_off = htons(offset); @@ -990,7 +1009,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); @@ -1022,7 +1041,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); @@ -1101,21 +1120,19 @@ static void ip6_append_data_mtu(unsigned int *mtu, unsigned int fragheaderlen, struct sk_buff *skb, struct rt6_info *rt, - bool pmtuprobe) + unsigned int orig_mtu) { if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { if (skb == NULL) { /* first fragment, reserve header_len */ - *mtu = *mtu - rt->dst.header_len; + *mtu = orig_mtu - rt->dst.header_len; } else { /* * this fragment is not first, the headers * space is regarded as data space. */ - *mtu = min(*mtu, pmtuprobe ? - rt->dst.dev->mtu : - dst_mtu(rt->dst.path)); + *mtu = orig_mtu; } *maxfraglen = ((*mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); @@ -1132,7 +1149,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, struct ipv6_pinfo *np = inet6_sk(sk); struct inet_cork *cork; struct sk_buff *skb, *skb_prev = NULL; - unsigned int maxfraglen, fragheaderlen, mtu; + unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu; int exthdrlen; int dst_exthdrlen; int hh_len; @@ -1140,6 +1157,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int err; int offset = 0; __u8 tx_flags = 0; + u32 tskey = 0; if (flags&MSG_PROBE) return 0; @@ -1214,6 +1232,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, dst_exthdrlen = 0; mtu = cork->fragsize; } + orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -1226,13 +1245,15 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, unsigned int maxnonfragsize, headersize; headersize = sizeof(struct ipv6hdr) + - (opt ? opt->tot_len : 0) + + (opt ? opt->opt_flen + opt->opt_nflen : 0) + (dst_allfrag(&rt->dst) ? sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; - maxnonfragsize = (np->pmtudisc >= IPV6_PMTUDISC_DO) ? - mtu : sizeof(struct ipv6hdr) + IPV6_MAXPLEN; + if (ip6_sk_ignore_df(sk)) + maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN; + else + maxnonfragsize = mtu; /* dontfrag active */ if ((cork->length + length > mtu - headersize) && dontfrag && @@ -1252,9 +1273,12 @@ emsgsize: } } - /* For UDP, check if TX timestamp is enabled */ - if (sk->sk_type == SOCK_DGRAM) + if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) { sock_tx_timestamp(sk, &tx_flags); + if (tx_flags & SKBTX_ANY_SW_TSTAMP && + sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) + tskey = sk->sk_tskey++; + } /* * Let's try using as much space as possible. @@ -1311,8 +1335,7 @@ alloc_new_skb: if (skb == NULL || skb_prev == NULL) ip6_append_data_mtu(&mtu, &maxfraglen, fragheaderlen, skb, rt, - np->pmtudisc >= - IPV6_PMTUDISC_PROBE); + orig_mtu); skb_prev = skb; @@ -1363,12 +1386,6 @@ alloc_new_skb: sk->sk_allocation); if (unlikely(skb == NULL)) err = -ENOBUFS; - else { - /* Only the initial fragment - * is time stamped. - */ - tx_flags = 0; - } } if (skb == NULL) goto error; @@ -1382,8 +1399,11 @@ alloc_new_skb: skb_reserve(skb, hh_len + sizeof(struct frag_hdr) + dst_exthdrlen); - if (sk->sk_type == SOCK_DGRAM) - skb_shinfo(skb)->tx_flags = tx_flags; + /* Only the initial fragment is time stamped */ + skb_shinfo(skb)->tx_flags = tx_flags; + tx_flags = 0; + skb_shinfo(skb)->tskey = tskey; + tskey = 0; /* * Find where to start putting bytes @@ -1540,8 +1560,7 @@ int ip6_push_pending_frames(struct sock *sk) } /* Allow local fragmentation. */ - if (np->pmtudisc < IPV6_PMTUDISC_DO) - skb->local_df = 1; + skb->ignore_df = ip6_sk_ignore_df(sk); *final_dst = fl6->daddr; __skb_pull(skb, skb_network_header_len(skb)); @@ -1554,7 +1573,9 @@ int ip6_push_pending_frames(struct sock *sk) skb_reset_network_header(skb); hdr = ipv6_hdr(skb); - ip6_flow_hdr(hdr, np->cork.tclass, fl6->flowlabel); + ip6_flow_hdr(hdr, np->cork.tclass, + ip6_make_flowlabel(net, skb, fl6->flowlabel, + np->autoflowlabel)); hdr->hop_limit = np->cork.hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; @@ -1568,8 +1589,8 @@ int ip6_push_pending_frames(struct sock *sk) if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type); - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); + ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } err = ip6_local_out(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5db8d310f9c0..69a84b464009 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -61,6 +61,7 @@ MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("ip6tnl"); MODULE_ALIAS_NETDEV("ip6tnl0"); #ifdef IP6_TNL_DEBUG @@ -108,12 +109,12 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) per_cpu_ptr(dev->tstats, i); do { - start = u64_stats_fetch_begin_bh(&tstats->syncp); + start = u64_stats_fetch_begin_irq(&tstats->syncp); tmp.rx_packets = tstats->rx_packets; tmp.rx_bytes = tstats->rx_bytes; tmp.tx_packets = tstats->tx_packets; tmp.tx_bytes = tstats->tx_bytes; - } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); sum.rx_packets += tmp.rx_packets; sum.rx_bytes += tmp.rx_bytes; @@ -314,7 +315,8 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) else sprintf(name, "ip6tnl%%d"); - dev = alloc_netdev(sizeof (*t), name, ip6_tnl_dev_setup); + dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, + ip6_tnl_dev_setup); if (dev == NULL) goto failed; @@ -362,8 +364,12 @@ static struct ip6_tnl *ip6_tnl_locate(struct net *net, (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && - ipv6_addr_equal(remote, &t->parms.raddr)) + ipv6_addr_equal(remote, &t->parms.raddr)) { + if (create) + return NULL; + return t; + } } if (!create) return NULL; @@ -1045,7 +1051,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); - ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), fl6->flowlabel); + ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), + ip6_make_flowlabel(net, skb, fl6->flowlabel, false)); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; @@ -1340,8 +1347,8 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) int err = 0; struct ip6_tnl_parm p; struct __ip6_tnl_parm p1; - struct ip6_tnl *t = NULL; - struct net *net = dev_net(dev); + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); switch (cmd) { @@ -1353,11 +1360,11 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); + if (t == NULL) + t = netdev_priv(dev); } else { memset(&p, 0, sizeof(p)); } - if (t == NULL) - t = netdev_priv(dev); ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof (p))) { err = -EFAULT; @@ -1502,19 +1509,12 @@ static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - int i; t->dev = dev; t->net = dev_net(dev); - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ip6_tnl_stats; - ip6_tnl_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ip6_tnl_stats->syncp); - } return 0; } @@ -1564,7 +1564,7 @@ static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) { u8 proto; - if (!data) + if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); @@ -1778,7 +1778,7 @@ static int __net_init ip6_tnl_init_net(struct net *net) err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0", - ip6_tnl_dev_setup); + NET_NAME_UNKNOWN, ip6_tnl_dev_setup); if (!ip6n->fb_tnl_dev) goto err_alloc_dev; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 2d19272b8cee..5833a2244467 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -204,7 +204,7 @@ static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p else sprintf(name, "ip6_vti%%d"); - dev = alloc_netdev(sizeof(*t), name, vti6_dev_setup); + dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup); if (dev == NULL) goto failed; @@ -253,8 +253,12 @@ static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p, (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && - ipv6_addr_equal(remote, &t->parms.raddr)) + ipv6_addr_equal(remote, &t->parms.raddr)) { + if (create) + return NULL; + return t; + } } if (!create) return NULL; @@ -278,7 +282,6 @@ static void vti6_dev_uninit(struct net_device *dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else vti6_tnl_unlink(ip6n, t); - ip6_tnl_dst_reset(t); dev_put(dev); } @@ -288,11 +291,8 @@ static int vti6_rcv(struct sk_buff *skb) const struct ipv6hdr *ipv6h = ipv6_hdr(skb); rcu_read_lock(); - if ((t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr)) != NULL) { - struct pcpu_sw_netstats *tstats; - if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) { rcu_read_unlock(); goto discard; @@ -309,27 +309,58 @@ static int vti6_rcv(struct sk_buff *skb) goto discard; } - tstats = this_cpu_ptr(t->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); - - skb->mark = 0; - secpath_reset(skb); - skb->dev = t->dev; + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t; + skb->mark = be32_to_cpu(t->parms.i_key); rcu_read_unlock(); - return 0; + + return xfrm6_rcv(skb); } rcu_read_unlock(); - return 1; - + return -EINVAL; discard: kfree_skb(skb); return 0; } +static int vti6_rcv_cb(struct sk_buff *skb, int err) +{ + unsigned short family; + struct net_device *dev; + struct pcpu_sw_netstats *tstats; + struct xfrm_state *x; + struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6; + + if (!t) + return 1; + + dev = t->dev; + + if (err) { + dev->stats.rx_errors++; + dev->stats.rx_dropped++; + + return 0; + } + + x = xfrm_input_state(skb); + family = x->inner_mode->afinfo->family; + + if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + return -EPERM; + + skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev))); + skb->dev = dev; + + tstats = this_cpu_ptr(dev->tstats); + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + return 0; +} + /** * vti6_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device @@ -349,44 +380,56 @@ vti6_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } +static bool vti6_state_check(const struct xfrm_state *x, + const struct in6_addr *dst, + const struct in6_addr *src) +{ + xfrm_address_t *daddr = (xfrm_address_t *)dst; + xfrm_address_t *saddr = (xfrm_address_t *)src; + + /* if there is no transform then this tunnel is not functional. + * Or if the xfrm is not mode tunnel. + */ + if (!x || x->props.mode != XFRM_MODE_TUNNEL || + x->props.family != AF_INET6) + return false; + + if (ipv6_addr_any(dst)) + return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET6); + + if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET6)) + return false; + + return true; +} + /** * vti6_xmit - send a packet * @skb: the outgoing socket buffer * @dev: the outgoing tunnel device + * @fl: the flow informations for the xfrm_lookup **/ -static int vti6_xmit(struct sk_buff *skb, struct net_device *dev) +static int +vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { - struct net *net = dev_net(dev); struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; - struct dst_entry *dst = NULL, *ndst = NULL; - struct flowi6 fl6; - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; int err = -1; - if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) || - !ip6_tnl_xmit_ctl(t) || vti6_addr_conflict(t, ipv6h)) - return err; - - dst = ip6_tnl_dst_check(t); - if (!dst) { - memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); - - ndst = ip6_route_output(net, NULL, &fl6); + if (!dst) + goto tx_err_link_failure; - if (ndst->error) - goto tx_err_link_failure; - ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(&fl6), NULL, 0); - if (IS_ERR(ndst)) { - err = PTR_ERR(ndst); - ndst = NULL; - goto tx_err_link_failure; - } - dst = ndst; + dst_hold(dst); + dst = xfrm_lookup(t->net, dst, fl, NULL, 0); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; + goto tx_err_link_failure; } - if (!dst->xfrm || dst->xfrm->props.mode != XFRM_MODE_TUNNEL) + if (!vti6_state_check(dst->xfrm, &t->parms.raddr, &t->parms.laddr)) goto tx_err_link_failure; tdev = dst->dev; @@ -398,14 +441,21 @@ static int vti6_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_err_dst_release; } + skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); + skb_dst_set(skb, dst); + skb->dev = skb_dst(skb)->dev; - skb_dst_drop(skb); - skb_dst_set_noref(skb, dst); + err = dst_output(skb); + if (net_xmit_eval(err) == 0) { + struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); - ip6tunnel_xmit(skb, dev); - if (ndst) { - dev->mtu = dst_mtu(ndst); - ip6_tnl_dst_store(t, ndst); + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += skb->len; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + stats->tx_errors++; + stats->tx_aborted_errors++; } return 0; @@ -413,7 +463,7 @@ tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: - dst_release(ndst); + dst_release(dst); return err; } @@ -422,16 +472,33 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; + struct ipv6hdr *ipv6h; + struct flowi fl; int ret; + memset(&fl, 0, sizeof(fl)); + skb->mark = be32_to_cpu(t->parms.o_key); + switch (skb->protocol) { case htons(ETH_P_IPV6): - ret = vti6_xmit(skb, dev); + ipv6h = ipv6_hdr(skb); + + if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) || + !ip6_tnl_xmit_ctl(t) || vti6_addr_conflict(t, ipv6h)) + goto tx_err; + + xfrm_decode_session(skb, &fl, AF_INET6); + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + break; + case htons(ETH_P_IP): + xfrm_decode_session(skb, &fl, AF_INET); + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); break; default: goto tx_err; } + ret = vti6_xmit(skb, dev, &fl); if (ret < 0) goto tx_err; @@ -444,24 +511,69 @@ tx_err: return NETDEV_TX_OK; } +static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + __be32 spi; + __u32 mark; + struct xfrm_state *x; + struct ip6_tnl *t; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah; + struct ip_comp_hdr *ipch; + struct net *net = dev_net(skb->dev); + const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; + int protocol = iph->nexthdr; + + t = vti6_tnl_lookup(dev_net(skb->dev), &iph->daddr, &iph->saddr); + if (!t) + return -1; + + mark = be32_to_cpu(t->parms.o_key); + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data + offset); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data + offset); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data + offset); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + if (type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) + return 0; + + x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET6); + if (!x) + return 0; + + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); + xfrm_state_put(x); + + return 0; +} + static void vti6_link_config(struct ip6_tnl *t) { - struct dst_entry *dst; struct net_device *dev = t->dev; struct __ip6_tnl_parm *p = &t->parms; - struct flowi6 *fl6 = &t->fl.u.ip6; memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); - /* Set up flowi template */ - fl6->saddr = p->laddr; - fl6->daddr = p->raddr; - fl6->flowi6_oif = p->link; - fl6->flowi6_mark = be32_to_cpu(p->i_key); - fl6->flowi6_proto = p->proto; - fl6->flowlabel = 0; - p->flags &= ~(IP6_TNL_F_CAP_XMIT | IP6_TNL_F_CAP_RCV | IP6_TNL_F_CAP_PER_PACKET); p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); @@ -472,28 +584,6 @@ static void vti6_link_config(struct ip6_tnl *t) dev->flags &= ~IFF_POINTOPOINT; dev->iflink = p->link; - - if (p->flags & IP6_TNL_F_CAP_XMIT) { - - dst = ip6_route_output(dev_net(dev), NULL, fl6); - if (dst->error) - return; - - dst = xfrm_lookup(dev_net(dev), dst, flowi6_to_flowi(fl6), - NULL, 0); - if (IS_ERR(dst)) - return; - - if (dst->dev) { - dev->hard_header_len = dst->dev->hard_header_len; - - dev->mtu = dst_mtu(dst); - - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; - } - dst_release(dst); - } } /** @@ -709,18 +799,14 @@ static const struct net_device_ops vti6_netdev_ops = { **/ static void vti6_dev_setup(struct net_device *dev) { - struct ip6_tnl *t; - dev->netdev_ops = &vti6_netdev_ops; dev->destructor = vti6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr); dev->mtu = ETH_DATA_LEN; - t = netdev_priv(dev); dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; } @@ -731,18 +817,12 @@ static void vti6_dev_setup(struct net_device *dev) static inline int vti6_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - int i; t->dev = dev; t->net = dev_net(dev); - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *stats; - stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&stats->syncp); - } return 0; } @@ -914,11 +994,6 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = { .fill_info = vti6_fill_info, }; -static struct xfrm_tunnel_notifier vti6_handler __read_mostly = { - .handler = vti6_rcv, - .priority = 1, -}; - static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n) { int h; @@ -949,7 +1024,7 @@ static int __net_init vti6_init_net(struct net *net) err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6_vti0", - vti6_dev_setup); + NET_NAME_UNKNOWN, vti6_dev_setup); if (!ip6n->fb_tnl_dev) goto err_alloc_dev; @@ -990,6 +1065,27 @@ static struct pernet_operations vti6_net_ops = { .size = sizeof(struct vti6_net), }; +static struct xfrm6_protocol vti_esp6_protocol __read_mostly = { + .handler = vti6_rcv, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 100, +}; + +static struct xfrm6_protocol vti_ah6_protocol __read_mostly = { + .handler = vti6_rcv, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 100, +}; + +static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = { + .handler = vti6_rcv, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 100, +}; + /** * vti6_tunnel_init - register protocol and reserve needed resources * @@ -997,17 +1093,26 @@ static struct pernet_operations vti6_net_ops = { **/ static int __init vti6_tunnel_init(void) { - int err; + const char *msg; + int err; + msg = "tunnel device"; err = register_pernet_device(&vti6_net_ops); if (err < 0) - goto out_pernet; + goto pernet_dev_failed; - err = xfrm6_mode_tunnel_input_register(&vti6_handler); - if (err < 0) { - pr_err("%s: can't register vti6\n", __func__); - goto out; - } + msg = "tunnel protocols"; + err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP); + if (err < 0) + goto xfrm_proto_esp_failed; + err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH); + if (err < 0) + goto xfrm_proto_ah_failed; + err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP); + if (err < 0) + goto xfrm_proto_comp_failed; + + msg = "netlink interface"; err = rtnl_link_register(&vti6_link_ops); if (err < 0) goto rtnl_link_failed; @@ -1015,10 +1120,15 @@ static int __init vti6_tunnel_init(void) return 0; rtnl_link_failed: - xfrm6_mode_tunnel_input_deregister(&vti6_handler); -out: + xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); +xfrm_proto_comp_failed: + xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); +xfrm_proto_ah_failed: + xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); +xfrm_proto_esp_failed: unregister_pernet_device(&vti6_net_ops); -out_pernet: +pernet_dev_failed: + pr_err("vti6 init: failed to register %s\n", msg); return err; } @@ -1028,9 +1138,9 @@ out_pernet: static void __exit vti6_tunnel_cleanup(void) { rtnl_link_unregister(&vti6_link_ops); - if (xfrm6_mode_tunnel_input_deregister(&vti6_handler)) - pr_info("%s: can't deregister vti6\n", __func__); - + xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); + xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); + xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); unregister_pernet_device(&vti6_net_ops); } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 0eb4038a4d63..f9a3fd320d1d 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -700,7 +700,7 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct mr6_table *mrt; struct flowi6 fl6 = { .flowi6_oif = dev->ifindex, - .flowi6_iif = skb->skb_iif, + .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_mark = skb->mark, }; int err; @@ -744,7 +744,7 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt) else sprintf(name, "pim6reg%u", mrt->id); - dev = alloc_netdev(0, name, reg_vif_setup); + dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup); if (dev == NULL) return NULL; @@ -1633,7 +1633,7 @@ struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) { struct mr6_table *mrt; struct flowi6 fl6 = { - .flowi6_iif = skb->skb_iif, + .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_oif = skb->dev->ifindex, .flowi6_mark = skb->mark, }; @@ -2349,13 +2349,14 @@ int ip6mr_get_route(struct net *net, } static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, - u32 portid, u32 seq, struct mfc6_cache *c, int cmd) + u32 portid, u32 seq, struct mfc6_cache *c, int cmd, + int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; - nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -2423,7 +2424,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, if (skb == NULL) goto errout; - err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd); + err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; @@ -2462,7 +2463,8 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (ip6mr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) goto done; next_entry: e++; @@ -2476,7 +2478,8 @@ next_entry: if (ip6mr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) { + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) { spin_unlock_bh(&mfc_unres_lock); goto done; } diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index da9becb42e81..d1c793cffcb5 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -53,7 +53,7 @@ #include <linux/icmpv6.h> #include <linux/mutex.h> -static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, +static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); @@ -65,19 +65,21 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) - return; + return 0; spi = htonl(ntohs(ipcomph->cpi)); x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6); if (!x) - return; + return 0; if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0); else ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); + + return 0; } static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) @@ -174,6 +176,11 @@ out: return err; } +static int ipcomp6_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type ipcomp6_type = { .description = "IPCOMP6", @@ -186,11 +193,12 @@ static const struct xfrm_type ipcomp6_type = .hdr_offset = xfrm6_find_1stfragopt, }; -static const struct inet6_protocol ipcomp6_protocol = +static struct xfrm6_protocol ipcomp6_protocol = { .handler = xfrm6_rcv, + .cb_handler = ipcomp6_rcv_cb, .err_handler = ipcomp6_err, - .flags = INET6_PROTO_NOPOLICY, + .priority = 0, }; static int __init ipcomp6_init(void) @@ -199,7 +207,7 @@ static int __init ipcomp6_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet6_add_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0) { + if (xfrm6_protocol_register(&ipcomp6_protocol, IPPROTO_COMP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ipcomp6_type, AF_INET6); return -EAGAIN; @@ -209,7 +217,7 @@ static int __init ipcomp6_init(void) static void __exit ipcomp6_fini(void) { - if (inet6_del_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0) + if (xfrm6_protocol_deregister(&ipcomp6_protocol, IPPROTO_COMP) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ipcomp6_type, AF_INET6) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 0a00f449de5e..0c289982796d 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -235,7 +235,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optlen < sizeof(int) || inet_sk(sk)->inet_num) goto e_inval; - np->ipv6only = valbool; + sk->sk_ipv6only = valbool; retv = 0; break; @@ -722,7 +722,7 @@ done: case IPV6_MTU_DISCOVER: if (optlen < sizeof(int)) goto e_inval; - if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_INTERFACE) + if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_OMIT) goto e_inval; np->pmtudisc = val; retv = 0; @@ -834,6 +834,10 @@ pref_skip_coa: np->dontfrag = valbool; retv = 0; break; + case IPV6_AUTOFLOWLABEL: + np->autoflowlabel = valbool; + retv = 0; + break; } release_sock(sk); @@ -1058,7 +1062,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, } case IPV6_V6ONLY: - val = np->ipv6only; + val = sk->sk_ipv6only; break; case IPV6_RECVPKTINFO: @@ -1158,7 +1162,6 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, return -EFAULT; return 0; - break; } case IPV6_TRANSPARENT: @@ -1273,6 +1276,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->dontfrag; break; + case IPV6_AUTOFLOWLABEL: + val = np->autoflowlabel; + break; + default: return -ENOPROTOOPT; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index e1e47350784b..a23b655a7627 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -172,6 +172,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) mc_lst->next = NULL; mc_lst->addr = *addr; + rtnl_lock(); rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -185,6 +186,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (dev == NULL) { rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } @@ -202,6 +204,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (err) { rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } @@ -212,6 +215,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) spin_unlock(&ipv6_sk_mc_lock); rcu_read_unlock(); + rtnl_unlock(); return 0; } @@ -229,6 +233,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) if (!ipv6_addr_is_multicast(addr)) return -EINVAL; + rtnl_lock(); spin_lock(&ipv6_sk_mc_lock); for (lnk = &np->ipv6_mc_list; (mc_lst = rcu_dereference_protected(*lnk, @@ -252,12 +257,15 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); rcu_read_unlock(); + rtnl_unlock(); + atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); return 0; } } spin_unlock(&ipv6_sk_mc_lock); + rtnl_unlock(); return -EADDRNOTAVAIL; } @@ -302,6 +310,7 @@ void ipv6_sock_mc_close(struct sock *sk) if (!rcu_access_pointer(np->ipv6_mc_list)) return; + rtnl_lock(); spin_lock(&ipv6_sk_mc_lock); while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list, lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) { @@ -328,6 +337,7 @@ void ipv6_sock_mc_close(struct sock *sk) spin_lock(&ipv6_sk_mc_lock); } spin_unlock(&ipv6_sk_mc_lock); + rtnl_unlock(); } int ip6_mc_source(int add, int omode, struct sock *sk, @@ -845,6 +855,8 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) struct ifmcaddr6 *mc; struct inet6_dev *idev; + ASSERT_RTNL(); + /* we need to take a reference on idev */ idev = in6_dev_get(dev); @@ -916,6 +928,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifmcaddr6 *ma, **map; + ASSERT_RTNL(); + write_lock_bh(&idev->lock); for (map = &idev->mc_list; (ma=*map) != NULL; map = &ma->next) { if (ipv6_addr_equal(&ma->mca_addr, addr)) { @@ -1301,8 +1315,17 @@ int igmp6_event_query(struct sk_buff *skb) len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); len -= skb_network_header_len(skb); - /* Drop queries with not link local source */ - if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) + /* RFC3810 6.2 + * Upon reception of an MLD message that contains a Query, the node + * checks if the source address of the message is a valid link-local + * address, if the Hop Limit is set to 1, and if the Router Alert + * option is present in the Hop-By-Hop Options header of the IPv6 + * packet. If any of these checks fails, the packet is dropped. + */ + if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL) || + ipv6_hdr(skb)->hop_limit != 1 || + !(IP6CB(skb)->flags & IP6SKB_ROUTERALERT) || + IP6CB(skb)->ra != htons(IPV6_OPT_ROUTERALERT_MLD)) return -EINVAL; idev = __in6_dev_get(skb->dev); @@ -1620,11 +1643,12 @@ static void mld_sendpack(struct sk_buff *skb) dst_output); out: if (!err) { - ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT); - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); - IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); - } else - IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS); + ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); + } else { + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + } rcu_read_unlock(); return; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 09a22f4f36c9..339078f95d1b 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -851,7 +851,7 @@ out: static void ndisc_recv_na(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); - const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; + struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + @@ -944,10 +944,7 @@ static void ndisc_recv_na(struct sk_buff *skb) /* * Change: router to host */ - struct rt6_info *rt; - rt = rt6_get_dflt_router(saddr, dev); - if (rt) - ip6_del_rt(rt); + rt6_clean_tohost(dev_net(dev), saddr); } out: @@ -1073,6 +1070,9 @@ static void ndisc_router_discovery(struct sk_buff *skb) optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) - sizeof(struct ra_msg); + ND_PRINTK(2, info, + "RA: %s, dev: %s\n", + __func__, skb->dev->name); if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "RA: source address is not link-local\n"); return; @@ -1105,13 +1105,21 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - if (!ipv6_accept_ra(in6_dev)) + if (!ipv6_accept_ra(in6_dev)) { + ND_PRINTK(2, info, + "RA: %s, did not accept ra for dev: %s\n", + __func__, skb->dev->name); goto skip_linkparms; + } #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ - if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) + if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { + ND_PRINTK(2, info, + "RA: %s, nodetype is NODEFAULT, dev: %s\n", + __func__, skb->dev->name); goto skip_linkparms; + } #endif if (in6_dev->if_flags & IF_RS_SENT) { @@ -1133,11 +1141,24 @@ static void ndisc_router_discovery(struct sk_buff *skb) (ra_msg->icmph.icmp6_addrconf_other ? IF_RA_OTHERCONF : 0); - if (!in6_dev->cnf.accept_ra_defrtr) + if (!in6_dev->cnf.accept_ra_defrtr) { + ND_PRINTK(2, info, + "RA: %s, defrtr is false for dev: %s\n", + __func__, skb->dev->name); goto skip_defrtr; + } - if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0)) + /* Do not accept RA with source-addr found on local machine unless + * accept_ra_from_local is set to true. + */ + if (!in6_dev->cnf.accept_ra_from_local && + ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, + NULL, 0)) { + ND_PRINTK(2, info, + "RA from local address detected on dev: %s: default router ignored\n", + skb->dev->name); goto skip_defrtr; + } lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); @@ -1166,8 +1187,10 @@ static void ndisc_router_discovery(struct sk_buff *skb) rt = NULL; } + ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, for dev: %s\n", + rt, lifetime, skb->dev->name); if (rt == NULL && lifetime) { - ND_PRINTK(3, dbg, "RA: adding default router\n"); + ND_PRINTK(3, info, "RA: adding default router\n"); rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref); if (rt == NULL) { @@ -1263,12 +1286,22 @@ skip_linkparms: NEIGH_UPDATE_F_ISROUTER); } - if (!ipv6_accept_ra(in6_dev)) + if (!ipv6_accept_ra(in6_dev)) { + ND_PRINTK(2, info, + "RA: %s, accept_ra is false for dev: %s\n", + __func__, skb->dev->name); goto out; + } #ifdef CONFIG_IPV6_ROUTE_INFO - if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0)) + if (!in6_dev->cnf.accept_ra_from_local && + ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, + NULL, 0)) { + ND_PRINTK(2, info, + "RA from local address detected on dev: %s: router info ignored.\n", + skb->dev->name); goto skip_routeinfo; + } if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; @@ -1296,8 +1329,12 @@ skip_routeinfo: #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific ndopts from interior routers */ - if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) + if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { + ND_PRINTK(2, info, + "RA: %s, nodetype is NODEFAULT (interior routes), dev: %s\n", + __func__, skb->dev->name); goto out; + } #endif if (in6_dev->cnf.accept_ra_pinfo && ndopts.nd_opts_pi) { @@ -1731,7 +1768,7 @@ int __init ndisc_init(void) #ifdef CONFIG_SYSCTL err = neigh_sysctl_register(NULL, &nd_tbl.parms, - &ndisc_ifinfo_sysctl_change); + ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; out: diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 95f3f1da0d7f..d38e6a8d8b9f 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -30,13 +30,15 @@ int ip6_route_me_harder(struct sk_buff *skb) .daddr = iph->daddr, .saddr = iph->saddr, }; + int err; dst = ip6_route_output(net, skb->sk, &fl6); - if (dst->error) { + err = dst->error; + if (err) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n"); dst_release(dst); - return dst->error; + return err; } /* Drop old route. */ diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 4bff1f297e39..2812816aabdc 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -55,6 +55,21 @@ config NFT_REJECT_IPV6 default NFT_REJECT tristate +config NF_LOG_IPV6 + tristate "IPv6 packet logging" + default m if NETFILTER_ADVANCED=n + select NF_LOG_COMMON + +config NF_NAT_IPV6 + tristate "IPv6 NAT" + depends on NF_CONNTRACK_IPV6 + depends on NETFILTER_ADVANCED + select NF_NAT + help + The IPv6 NAT option allows masquerading, port forwarding and other + forms of full Network Address Port Translation. This can be + controlled by iptables or nft. + config IP6_NF_IPTABLES tristate "IP6 tables support (required for filtering)" depends on INET && IPV6 @@ -227,19 +242,21 @@ config IP6_NF_SECURITY If unsure, say N. -config NF_NAT_IPV6 - tristate "IPv6 NAT" +config IP6_NF_NAT + tristate "ip6tables NAT support" depends on NF_CONNTRACK_IPV6 depends on NETFILTER_ADVANCED select NF_NAT + select NF_NAT_IPV6 + select NETFILTER_XT_NAT help - The IPv6 NAT option allows masquerading, port forwarding and other - forms of full Network Address Port Translation. It is controlled by - the `nat' table in ip6tables, see the man page for ip6tables(8). + This enables the `nat' table in ip6tables. This allows masquerading, + port forwarding and other forms of full Network Address Port + Translation. To compile it as a module, choose M here. If unsure, say N. -if NF_NAT_IPV6 +if IP6_NF_NAT config IP6_NF_TARGET_MASQUERADE tristate "MASQUERADE target support" @@ -260,7 +277,7 @@ config IP6_NF_TARGET_NPT To compile it as a module, choose M here. If unsure, say N. -endif # NF_NAT_IPV6 +endif # IP6_NF_NAT endif # IP6_NF_IPTABLES diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 70d3dd66f2cd..c3d3286db4bb 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o -obj-$(CONFIG_NF_NAT_IPV6) += ip6table_nat.o +obj-$(CONFIG_IP6_NF_NAT) += ip6table_nat.o # objects for l3 independent conntrack nf_conntrack_ipv6-y := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o @@ -23,6 +23,9 @@ obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o +# logging +obj-$(CONFIG_NF_LOG_IPV6) += nf_log_ipv6.o + # nf_tables obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 710238f58aa9..e080fbbbc0e5 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1241,8 +1241,10 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, - sizeof(struct xt_counters) * num_counters) != 0) - ret = -EFAULT; + sizeof(struct xt_counters) * num_counters) != 0) { + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n"); + } vfree(counters); xt_table_unlock(t); return ret; diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c index 54bd9790603f..8b147440fbdc 100644 --- a/net/ipv6/netfilter/ip6t_ipv6header.c +++ b/net/ipv6/netfilter/ip6t_ipv6header.c @@ -94,7 +94,6 @@ ipv6header_mt6(const struct sk_buff *skb, struct xt_action_param *par) break; default: return false; - break; } nexthdr = hp->nexthdr; diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index e0983f3648a6..790e0c6b19e1 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -33,6 +33,7 @@ static bool rpfilter_lookup_reverse6(const struct sk_buff *skb, struct ipv6hdr *iph = ipv6_hdr(skb); bool ret = false; struct flowi6 fl6 = { + .flowi6_iif = LOOPBACK_IFINDEX, .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK, .flowi6_proto = iph->nexthdr, .daddr = iph->saddr, diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 84c7f33d0cf8..387d8b8fc18d 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -90,17 +90,9 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, if (nf_ct_is_untracked(ct)) return NF_ACCEPT; - nat = nfct_nat(ct); - if (!nat) { - /* NAT module was loaded late. */ - if (nf_ct_is_confirmed(ct)) - return NF_ACCEPT; - nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); - if (nat == NULL) { - pr_debug("failed to add NAT extension\n"); - return NF_ACCEPT; - } - } + nat = nf_ct_nat_ext_add(ct); + if (nat == NULL) + return NF_ACCEPT; switch (ctinfo) { case IP_CT_RELATED: diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 767ab8da8218..6f187c8d8a1b 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -50,6 +50,7 @@ #include <linux/module.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> +static const char nf_frags_cache_name[] = "nf-frags"; struct nf_ct_frag6_skb_cb { @@ -63,6 +64,8 @@ struct nf_ct_frag6_skb_cb static struct inet_frags nf_frags; #ifdef CONFIG_SYSCTL +static int zero; + static struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", @@ -76,14 +79,17 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = { .data = &init_net.nf_frag.frags.low_thresh, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &init_net.nf_frag.frags.high_thresh }, { .procname = "nf_conntrack_frag6_high_thresh", .data = &init_net.nf_frag.frags.high_thresh, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &init_net.nf_frag.frags.low_thresh }, { } }; @@ -102,7 +108,10 @@ static int nf_ct_frag6_sysctl_register(struct net *net) table[0].data = &net->nf_frag.frags.timeout; table[1].data = &net->nf_frag.frags.low_thresh; + table[1].extra2 = &net->nf_frag.frags.high_thresh; table[2].data = &net->nf_frag.frags.high_thresh; + table[2].extra1 = &net->nf_frag.frags.low_thresh; + table[2].extra2 = &init_net.nf_frag.frags.high_thresh; } hdr = register_net_sysctl(net, "net/netfilter", table); @@ -147,16 +156,13 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr, const struct in6_addr *daddr) { - u32 c; - net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd)); - c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), - (__force u32)id, nf_frags.rnd); - return c & (INETFRAGS_HASHSZ - 1); + return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), + (__force u32)id, nf_frags.rnd); } -static unsigned int nf_hashfn(struct inet_frag_queue *q) +static unsigned int nf_hashfn(const struct inet_frag_queue *q) { const struct frag_queue *nq; @@ -196,7 +202,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id, arg.dst = dst; arg.ecn = ecn; - read_lock_bh(&nf_frags.lock); + local_bh_disable(); hash = nf_hash_frag(id, src, dst); q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash); @@ -217,7 +223,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, int offset, end; u8 ecn; - if (fq->q.last_in & INET_FRAG_COMPLETE) { + if (fq->q.flags & INET_FRAG_COMPLETE) { pr_debug("Already completed\n"); goto err; } @@ -248,11 +254,11 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, * or have different end, the segment is corrupted. */ if (end < fq->q.len || - ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) { + ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) { pr_debug("already received last fragment\n"); goto err; } - fq->q.last_in |= INET_FRAG_LAST_IN; + fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { /* Check if the fragment is rounded to 8 bytes. @@ -267,7 +273,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, } if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ - if (fq->q.last_in & INET_FRAG_LAST_IN) { + if (fq->q.flags & INET_FRAG_LAST_IN) { pr_debug("last packet already reached.\n"); goto err; } @@ -349,10 +355,9 @@ found: */ if (offset == 0) { fq->nhoffset = nhoff; - fq->q.last_in |= INET_FRAG_FIRST_IN; + fq->q.flags |= INET_FRAG_FIRST_IN; } - inet_frag_lru_move(&fq->q); return 0; discard_fq: @@ -451,7 +456,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) } sub_frag_mem_limit(&fq->q, head->truesize); - head->local_df = 1; + head->ignore_df = 1; head->next = NULL; head->dev = dev; head->tstamp = fq->q.stamp; @@ -597,10 +602,6 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) hdr = ipv6_hdr(clone); fhdr = (struct frag_hdr *)skb_transport_header(clone); - local_bh_disable(); - inet_frag_evictor(&net->nf_frag.frags, &nf_frags, false); - local_bh_enable(); - fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr, ip6_frag_ecn(hdr)); if (fq == NULL) { @@ -617,7 +618,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) goto ret_orig; } - if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { ret_skb = nf_ct_frag6_reasm(fq, dev); if (ret_skb == NULL) @@ -677,13 +678,15 @@ int nf_ct_frag6_init(void) nf_frags.qsize = sizeof(struct frag_queue); nf_frags.match = ip6_frag_match; nf_frags.frag_expire = nf_ct_frag6_expire; - nf_frags.secret_interval = 10 * 60 * HZ; - inet_frags_init(&nf_frags); - + nf_frags.frags_cache_name = nf_frags_cache_name; + ret = inet_frags_init(&nf_frags); + if (ret) + goto out; ret = register_pernet_subsys(&nf_ct_net_ops); if (ret) inet_frags_fini(&nf_frags); +out: return ret; } diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c new file mode 100644 index 000000000000..7b17a0be93e7 --- /dev/null +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -0,0 +1,417 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/skbuff.h> +#include <linux/if_arp.h> +#include <linux/ip.h> +#include <net/ipv6.h> +#include <net/icmp.h> +#include <net/udp.h> +#include <net/tcp.h> +#include <net/route.h> + +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter/xt_LOG.h> +#include <net/netfilter/nf_log.h> + +static struct nf_loginfo default_loginfo = { + .type = NF_LOG_TYPE_LOG, + .u = { + .log = { + .level = 5, + .logflags = NF_LOG_MASK, + }, + }, +}; + +/* One level of recursion won't kill us */ +static void dump_ipv6_packet(struct nf_log_buf *m, + const struct nf_loginfo *info, + const struct sk_buff *skb, unsigned int ip6hoff, + int recurse) +{ + u_int8_t currenthdr; + int fragment; + struct ipv6hdr _ip6h; + const struct ipv6hdr *ih; + unsigned int ptr; + unsigned int hdrlen = 0; + unsigned int logflags; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_MASK; + + ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h); + if (ih == NULL) { + nf_log_buf_add(m, "TRUNCATED"); + return; + } + + /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */ + nf_log_buf_add(m, "SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); + + /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ + nf_log_buf_add(m, "LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", + ntohs(ih->payload_len) + sizeof(struct ipv6hdr), + (ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20, + ih->hop_limit, + (ntohl(*(__be32 *)ih) & 0x000fffff)); + + fragment = 0; + ptr = ip6hoff + sizeof(struct ipv6hdr); + currenthdr = ih->nexthdr; + while (currenthdr != NEXTHDR_NONE && ip6t_ext_hdr(currenthdr)) { + struct ipv6_opt_hdr _hdr; + const struct ipv6_opt_hdr *hp; + + hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); + if (hp == NULL) { + nf_log_buf_add(m, "TRUNCATED"); + return; + } + + /* Max length: 48 "OPT (...) " */ + if (logflags & XT_LOG_IPOPT) + nf_log_buf_add(m, "OPT ( "); + + switch (currenthdr) { + case IPPROTO_FRAGMENT: { + struct frag_hdr _fhdr; + const struct frag_hdr *fh; + + nf_log_buf_add(m, "FRAG:"); + fh = skb_header_pointer(skb, ptr, sizeof(_fhdr), + &_fhdr); + if (fh == NULL) { + nf_log_buf_add(m, "TRUNCATED "); + return; + } + + /* Max length: 6 "65535 " */ + nf_log_buf_add(m, "%u ", ntohs(fh->frag_off) & 0xFFF8); + + /* Max length: 11 "INCOMPLETE " */ + if (fh->frag_off & htons(0x0001)) + nf_log_buf_add(m, "INCOMPLETE "); + + nf_log_buf_add(m, "ID:%08x ", + ntohl(fh->identification)); + + if (ntohs(fh->frag_off) & 0xFFF8) + fragment = 1; + + hdrlen = 8; + + break; + } + case IPPROTO_DSTOPTS: + case IPPROTO_ROUTING: + case IPPROTO_HOPOPTS: + if (fragment) { + if (logflags & XT_LOG_IPOPT) + nf_log_buf_add(m, ")"); + return; + } + hdrlen = ipv6_optlen(hp); + break; + /* Max Length */ + case IPPROTO_AH: + if (logflags & XT_LOG_IPOPT) { + struct ip_auth_hdr _ahdr; + const struct ip_auth_hdr *ah; + + /* Max length: 3 "AH " */ + nf_log_buf_add(m, "AH "); + + if (fragment) { + nf_log_buf_add(m, ")"); + return; + } + + ah = skb_header_pointer(skb, ptr, sizeof(_ahdr), + &_ahdr); + if (ah == NULL) { + /* + * Max length: 26 "INCOMPLETE [65535 + * bytes] )" + */ + nf_log_buf_add(m, "INCOMPLETE [%u bytes] )", + skb->len - ptr); + return; + } + + /* Length: 15 "SPI=0xF1234567 */ + nf_log_buf_add(m, "SPI=0x%x ", ntohl(ah->spi)); + + } + + hdrlen = (hp->hdrlen+2)<<2; + break; + case IPPROTO_ESP: + if (logflags & XT_LOG_IPOPT) { + struct ip_esp_hdr _esph; + const struct ip_esp_hdr *eh; + + /* Max length: 4 "ESP " */ + nf_log_buf_add(m, "ESP "); + + if (fragment) { + nf_log_buf_add(m, ")"); + return; + } + + /* + * Max length: 26 "INCOMPLETE [65535 bytes] )" + */ + eh = skb_header_pointer(skb, ptr, sizeof(_esph), + &_esph); + if (eh == NULL) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] )", + skb->len - ptr); + return; + } + + /* Length: 16 "SPI=0xF1234567 )" */ + nf_log_buf_add(m, "SPI=0x%x )", + ntohl(eh->spi)); + } + return; + default: + /* Max length: 20 "Unknown Ext Hdr 255" */ + nf_log_buf_add(m, "Unknown Ext Hdr %u", currenthdr); + return; + } + if (logflags & XT_LOG_IPOPT) + nf_log_buf_add(m, ") "); + + currenthdr = hp->nexthdr; + ptr += hdrlen; + } + + switch (currenthdr) { + case IPPROTO_TCP: + if (nf_log_dump_tcp_header(m, skb, currenthdr, fragment, + ptr, logflags)) + return; + break; + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + if (nf_log_dump_udp_header(m, skb, currenthdr, fragment, ptr)) + return; + break; + case IPPROTO_ICMPV6: { + struct icmp6hdr _icmp6h; + const struct icmp6hdr *ic; + + /* Max length: 13 "PROTO=ICMPv6 " */ + nf_log_buf_add(m, "PROTO=ICMPv6 "); + + if (fragment) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h); + if (ic == NULL) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", + skb->len - ptr); + return; + } + + /* Max length: 18 "TYPE=255 CODE=255 " */ + nf_log_buf_add(m, "TYPE=%u CODE=%u ", + ic->icmp6_type, ic->icmp6_code); + + switch (ic->icmp6_type) { + case ICMPV6_ECHO_REQUEST: + case ICMPV6_ECHO_REPLY: + /* Max length: 19 "ID=65535 SEQ=65535 " */ + nf_log_buf_add(m, "ID=%u SEQ=%u ", + ntohs(ic->icmp6_identifier), + ntohs(ic->icmp6_sequence)); + break; + case ICMPV6_MGM_QUERY: + case ICMPV6_MGM_REPORT: + case ICMPV6_MGM_REDUCTION: + break; + + case ICMPV6_PARAMPROB: + /* Max length: 17 "POINTER=ffffffff " */ + nf_log_buf_add(m, "POINTER=%08x ", + ntohl(ic->icmp6_pointer)); + /* Fall through */ + case ICMPV6_DEST_UNREACH: + case ICMPV6_PKT_TOOBIG: + case ICMPV6_TIME_EXCEED: + /* Max length: 3+maxlen */ + if (recurse) { + nf_log_buf_add(m, "["); + dump_ipv6_packet(m, info, skb, + ptr + sizeof(_icmp6h), 0); + nf_log_buf_add(m, "] "); + } + + /* Max length: 10 "MTU=65535 " */ + if (ic->icmp6_type == ICMPV6_PKT_TOOBIG) { + nf_log_buf_add(m, "MTU=%u ", + ntohl(ic->icmp6_mtu)); + } + } + break; + } + /* Max length: 10 "PROTO=255 " */ + default: + nf_log_buf_add(m, "PROTO=%u ", currenthdr); + } + + /* Max length: 15 "UID=4294967295 " */ + if ((logflags & XT_LOG_UID) && recurse) + nf_log_dump_sk_uid_gid(m, skb->sk); + + /* Max length: 16 "MARK=0xFFFFFFFF " */ + if (recurse && skb->mark) + nf_log_buf_add(m, "MARK=0x%x ", skb->mark); +} + +static void dump_ipv6_mac_header(struct nf_log_buf *m, + const struct nf_loginfo *info, + const struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + unsigned int logflags = 0; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + + if (!(logflags & XT_LOG_MACDECODE)) + goto fallback; + + switch (dev->type) { + case ARPHRD_ETHER: + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + ntohs(eth_hdr(skb)->h_proto)); + return; + default: + break; + } + +fallback: + nf_log_buf_add(m, "MAC="); + if (dev->hard_header_len && + skb->mac_header != skb->network_header) { + const unsigned char *p = skb_mac_header(skb); + unsigned int len = dev->hard_header_len; + unsigned int i; + + if (dev->type == ARPHRD_SIT) { + p -= ETH_HLEN; + + if (p < skb->head) + p = NULL; + } + + if (p != NULL) { + nf_log_buf_add(m, "%02x", *p++); + for (i = 1; i < len; i++) + nf_log_buf_add(m, ":%02x", *p++); + } + nf_log_buf_add(m, " "); + + if (dev->type == ARPHRD_SIT) { + const struct iphdr *iph = + (struct iphdr *)skb_mac_header(skb); + nf_log_buf_add(m, "TUNNEL=%pI4->%pI4 ", &iph->saddr, + &iph->daddr); + } + } else { + nf_log_buf_add(m, " "); + } +} + +static void nf_log_ip6_packet(struct net *net, u_int8_t pf, + unsigned int hooknum, const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + struct nf_log_buf *m; + + /* FIXME: Disabled from containers until syslog ns is supported */ + if (!net_eq(net, &init_net)) + return; + + m = nf_log_buf_open(); + + if (!loginfo) + loginfo = &default_loginfo; + + nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, + loginfo, prefix); + + if (in != NULL) + dump_ipv6_mac_header(m, loginfo, skb); + + dump_ipv6_packet(m, loginfo, skb, skb_network_offset(skb), 1); + + nf_log_buf_close(m); +} + +static struct nf_logger nf_ip6_logger __read_mostly = { + .name = "nf_log_ipv6", + .type = NF_LOG_TYPE_LOG, + .logfn = nf_log_ip6_packet, + .me = THIS_MODULE, +}; + +static int __net_init nf_log_ipv6_net_init(struct net *net) +{ + nf_log_set(net, NFPROTO_IPV6, &nf_ip6_logger); + return 0; +} + +static void __net_exit nf_log_ipv6_net_exit(struct net *net) +{ + nf_log_unset(net, &nf_ip6_logger); +} + +static struct pernet_operations nf_log_ipv6_net_ops = { + .init = nf_log_ipv6_net_init, + .exit = nf_log_ipv6_net_exit, +}; + +static int __init nf_log_ipv6_init(void) +{ + int ret; + + ret = register_pernet_subsys(&nf_log_ipv6_net_ops); + if (ret < 0) + return ret; + + nf_log_register(NFPROTO_IPV6, &nf_ip6_logger); + return 0; +} + +static void __exit nf_log_ipv6_exit(void) +{ + unregister_pernet_subsys(&nf_log_ipv6_net_ops); + nf_log_unregister(&nf_ip6_logger); +} + +module_init(nf_log_ipv6_init); +module_exit(nf_log_ipv6_exit); + +MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); +MODULE_DESCRIPTION("Netfilter IPv4 packet logging"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NF_LOGGER(AF_INET6, 0); diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index abfe75a2e316..fc8e49b2ff3e 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -158,6 +158,7 @@ static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, htons(oldlen), htons(datalen), 1); } +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[], struct nf_nat_range *range) { @@ -175,6 +176,7 @@ static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[], return 0; } +#endif static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = { .l3proto = NFPROTO_IPV6, @@ -183,7 +185,9 @@ static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = { .manip_pkt = nf_nat_ipv6_manip_pkt, .csum_update = nf_nat_ipv6_csum_update, .csum_recalc = nf_nat_ipv6_csum_recalc, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_to_range = nf_nat_ipv6_nlattr_to_range, +#endif #ifdef CONFIG_XFRM .decode_session = nf_nat_ipv6_decode_session, #endif diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c index 9c3297a768fd..d189fcb437fe 100644 --- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c @@ -47,15 +47,9 @@ static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, if (ct == NULL || nf_ct_is_untracked(ct)) return NF_ACCEPT; - nat = nfct_nat(ct); - if (nat == NULL) { - /* Conntrack module was loaded late, can't add extension. */ - if (nf_ct_is_confirmed(ct)) - return NF_ACCEPT; - nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); - if (nat == NULL) - return NF_ACCEPT; - } + nat = nf_ct_nat_ext_add(ct); + if (nat == NULL) + return NF_ACCEPT; switch (ctinfo) { case IP_CT_RELATED: diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 827f795209cf..5ec867e4a8b7 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -6,35 +6,7 @@ #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/addrconf.h> - -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) -{ - static atomic_t ipv6_fragmentation_id; - int old, new; - -#if IS_ENABLED(CONFIG_IPV6) - if (rt && !(rt->dst.flags & DST_NOPEER)) { - struct inet_peer *peer; - struct net *net; - - net = dev_net(rt->dst.dev); - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); - if (peer) { - fhdr->identification = htonl(inet_getid(peer, 0)); - inet_putpeer(peer); - return; - } - } -#endif - do { - old = atomic_read(&ipv6_fragmentation_id); - new = old + 1; - if (!new) - new = 1; - } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); - fhdr->identification = htonl(new); -} -EXPORT_SYMBOL(ipv6_select_ident); +#include <net/secure_seq.h> int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { @@ -106,6 +78,7 @@ int __ip6_local_out(struct sk_buff *skb) if (len > IPV6_MAXPLEN) len = 0; ipv6_hdr(skb)->payload_len = htons(len); + IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev, dst_output); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 587bbdcb22b4..5b7a1ed2aba9 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -51,7 +51,6 @@ static struct inet_protosw pingv6_protosw = { .protocol = IPPROTO_ICMPV6, .prot = &pingv6_prot, .ops = &inet6_dgram_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_REUSE, }; @@ -168,12 +167,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, pfh.wcheck = 0; pfh.family = AF_INET6; - if (ipv6_addr_is_multicast(&fl6.daddr)) - hlimit = np->mcast_hops; - else - hlimit = np->hop_limit; - if (hlimit < 0) - hlimit = ip6_dst_hoplimit(dst); + hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); lock_sock(sk); err = ip6_append_data(sk, ping_getfrag, &pfh, len, @@ -182,8 +176,8 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, MSG_DONTWAIT, np->dontfrag); if (err) { - ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev, - ICMP6_MIB_OUTERRORS); + ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev, + ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { err = icmpv6_push_pending_frames(sk, &fl6, diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 091d066a57b3..2d6f860e5c1e 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -33,6 +33,7 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; + unsigned int frag_mem = ip6_frag_mem(net); seq_printf(seq, "TCP6: inuse %d\n", sock_prot_inuse_get(net, &tcpv6_prot)); @@ -42,8 +43,7 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v) sock_prot_inuse_get(net, &udplitev6_prot)); seq_printf(seq, "RAW6: inuse %d\n", sock_prot_inuse_get(net, &rawv6_prot)); - seq_printf(seq, "FRAG6: inuse %d memory %d\n", - ip6_frag_nqueues(net), ip6_frag_mem(net)); + seq_printf(seq, "FRAG6: inuse %u memory %u\n", !!frag_mem, frag_mem); return 0; } @@ -186,7 +186,7 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, atomic_long_t *smib) /* can be called either with percpu mib (pcpumib != NULL), * or shared one (smib != NULL) */ -static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **pcpumib, +static void snmp6_seq_show_item(struct seq_file *seq, void __percpu *pcpumib, atomic_long_t *smib, const struct snmp_mib *itemlist) { @@ -201,7 +201,7 @@ static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **pcpumib, } } -static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu **mib, +static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu *mib, const struct snmp_mib *itemlist, size_t syncpoff) { int i; @@ -215,14 +215,14 @@ static int snmp6_seq_show(struct seq_file *seq, void *v) { struct net *net = (struct net *)seq->private; - snmp6_seq_show_item64(seq, (void __percpu **)net->mib.ipv6_statistics, + snmp6_seq_show_item64(seq, net->mib.ipv6_statistics, snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp)); - snmp6_seq_show_item(seq, (void __percpu **)net->mib.icmpv6_statistics, + snmp6_seq_show_item(seq, net->mib.icmpv6_statistics, NULL, snmp6_icmp6_list); snmp6_seq_show_icmpv6msg(seq, net->mib.icmpv6msg_statistics->mibs); - snmp6_seq_show_item(seq, (void __percpu **)net->mib.udp_stats_in6, + snmp6_seq_show_item(seq, net->mib.udp_stats_in6, NULL, snmp6_udp6_list); - snmp6_seq_show_item(seq, (void __percpu **)net->mib.udplite_stats_in6, + snmp6_seq_show_item(seq, net->mib.udplite_stats_in6, NULL, snmp6_udplite6_list); return 0; } @@ -245,7 +245,7 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v) struct inet6_dev *idev = (struct inet6_dev *)seq->private; seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex); - snmp6_seq_show_item64(seq, (void __percpu **)idev->stats.ipv6, + snmp6_seq_show_item64(seq, idev->stats.ipv6, snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp)); snmp6_seq_show_item(seq, NULL, idev->stats.icmpv6dev->mibs, snmp6_icmp6_list); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 1f29996e368a..39d44226e402 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -176,7 +176,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) goto out; net = dev_net(skb->dev); - sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, IP6CB(skb)->iif); + sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, inet6_iif(skb)); while (sk) { int filtered; @@ -220,7 +220,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) } } sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr, - IP6CB(skb)->iif); + inet6_iif(skb)); } out: read_unlock(&raw_v6_hashinfo.lock); @@ -375,7 +375,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, net = dev_net(skb->dev); while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr, - IP6CB(skb)->iif))) { + inet6_iif(skb)))) { rawv6_err(sk, skb, NULL, type, code, inner_offset, info); sk = sk_next(sk); @@ -506,7 +506,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, - IP6CB(skb)->iif); + inet6_iif(skb)); *addr_len = sizeof(*sin6); } @@ -588,8 +588,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, } offset += skb_transport_offset(skb); - if (skb_copy_bits(skb, offset, &csum, 2)) - BUG(); + BUG_ON(skb_copy_bits(skb, offset, &csum, 2)); /* in case cksum was not initialized */ if (unlikely(csum)) @@ -601,8 +600,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP) csum = CSUM_MANGLED_0; - if (skb_store_bits(skb, offset, &csum, 2)) - BUG(); + BUG_ON(skb_store_bits(skb, offset, &csum, 2)); send: err = ip6_push_pending_frames(sk); @@ -873,14 +871,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, err = PTR_ERR(dst); goto out; } - if (hlimit < 0) { - if (ipv6_addr_is_multicast(&fl6.daddr)) - hlimit = np->mcast_hops; - else - hlimit = np->hop_limit; - if (hlimit < 0) - hlimit = ip6_dst_hoplimit(dst); - } + if (hlimit < 0) + hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); if (tclass < 0) tclass = np->tclass; @@ -1328,7 +1320,6 @@ static struct inet_protosw rawv6_protosw = { .protocol = IPPROTO_IP, /* wild card */ .prot = &rawv6_prot, .ops = &inet6_sockraw_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_REUSE, }; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index cc85a9ba5010..c6557d9f7808 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -60,6 +60,8 @@ #include <net/inet_frag.h> #include <net/inet_ecn.h> +static const char ip6_frag_cache_name[] = "ip6-frags"; + struct ip6frag_skb_cb { struct inet6_skb_parm h; @@ -85,27 +87,23 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr, const struct in6_addr *daddr) { - u32 c; - net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd)); - c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), - (__force u32)id, ip6_frags.rnd); - - return c & (INETFRAGS_HASHSZ - 1); + return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), + (__force u32)id, ip6_frags.rnd); } -static unsigned int ip6_hashfn(struct inet_frag_queue *q) +static unsigned int ip6_hashfn(const struct inet_frag_queue *q) { - struct frag_queue *fq; + const struct frag_queue *fq; fq = container_of(q, struct frag_queue, q); return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr); } -bool ip6_frag_match(struct inet_frag_queue *q, void *a) +bool ip6_frag_match(const struct inet_frag_queue *q, const void *a) { - struct frag_queue *fq; - struct ip6_create_arg *arg = a; + const struct frag_queue *fq; + const struct ip6_create_arg *arg = a; fq = container_of(q, struct frag_queue, q); return fq->id == arg->id && @@ -115,10 +113,10 @@ bool ip6_frag_match(struct inet_frag_queue *q, void *a) } EXPORT_SYMBOL(ip6_frag_match); -void ip6_frag_init(struct inet_frag_queue *q, void *a) +void ip6_frag_init(struct inet_frag_queue *q, const void *a) { struct frag_queue *fq = container_of(q, struct frag_queue, q); - struct ip6_create_arg *arg = a; + const struct ip6_create_arg *arg = a; fq->id = arg->id; fq->user = arg->user; @@ -135,7 +133,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, spin_lock(&fq->q.lock); - if (fq->q.last_in & INET_FRAG_COMPLETE) + if (fq->q.flags & INET_FRAG_COMPLETE) goto out; inet_frag_kill(&fq->q, frags); @@ -145,17 +143,20 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, if (!dev) goto out_rcu_unlock; - IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); + if (fq->q.flags & INET_FRAG_EVICTED) + goto out_rcu_unlock; + + IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); + /* Don't send error if the first segment did not arrive. */ - if (!(fq->q.last_in & INET_FRAG_FIRST_IN) || !fq->q.fragments) + if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !fq->q.fragments) goto out_rcu_unlock; - /* - But use as source device on which LAST ARRIVED - segment was received. And do not use fq->dev - pointer directly, device might already disappeared. + /* But use as source device on which LAST ARRIVED + * segment was received. And do not use fq->dev + * pointer directly, device might already disappeared. */ fq->q.fragments->dev = dev; icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); @@ -192,7 +193,6 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, arg.dst = dst; arg.ecn = ecn; - read_lock(&ip6_frags.lock); hash = inet6_hash_frag(id, src, dst); q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash); @@ -212,7 +212,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct net *net = dev_net(skb_dst(skb)->dev); u8 ecn; - if (fq->q.last_in & INET_FRAG_COMPLETE) + if (fq->q.flags & INET_FRAG_COMPLETE) goto err; offset = ntohs(fhdr->frag_off) & ~0x7; @@ -243,9 +243,9 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, * or have different end, the segment is corrupted. */ if (end < fq->q.len || - ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) + ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) goto err; - fq->q.last_in |= INET_FRAG_LAST_IN; + fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { /* Check if the fragment is rounded to 8 bytes. @@ -263,7 +263,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, } if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ - if (fq->q.last_in & INET_FRAG_LAST_IN) + if (fq->q.flags & INET_FRAG_LAST_IN) goto err; fq->q.len = end; } @@ -338,10 +338,10 @@ found: */ if (offset == 0) { fq->nhoffset = nhoff; - fq->q.last_in |= INET_FRAG_FIRST_IN; + fq->q.flags |= INET_FRAG_FIRST_IN; } - if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { int res; unsigned long orefdst = skb->_skb_refdst; @@ -353,14 +353,13 @@ found: } skb_dst_drop(skb); - inet_frag_lru_move(&fq->q); return -1; discard_fq: inet_frag_kill(&fq->q, &ip6_frags); err: - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_REASMFAILS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -1; } @@ -523,7 +522,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct frag_queue *fq; const struct ipv6hdr *hdr = ipv6_hdr(skb); struct net *net = dev_net(skb_dst(skb)->dev); - int evicted; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) goto fail_hdr; @@ -552,11 +550,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; } - evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags, false); - if (evicted) - IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_REASMFAILS, evicted); - fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr, ip6_frag_ecn(hdr)); if (fq != NULL) { @@ -576,7 +569,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return -1; fail_hdr: - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb)); return -1; } @@ -588,20 +582,25 @@ static const struct inet6_protocol frag_protocol = }; #ifdef CONFIG_SYSCTL +static int zero; + static struct ctl_table ip6_frags_ns_ctl_table[] = { { .procname = "ip6frag_high_thresh", .data = &init_net.ipv6.frags.high_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &init_net.ipv6.frags.low_thresh }, { .procname = "ip6frag_low_thresh", .data = &init_net.ipv6.frags.low_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &init_net.ipv6.frags.high_thresh }, { .procname = "ip6frag_time", @@ -613,10 +612,12 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = { { } }; +/* secret interval has been deprecated */ +static int ip6_frags_secret_interval_unused; static struct ctl_table ip6_frags_ctl_table[] = { { .procname = "ip6frag_secret_interval", - .data = &ip6_frags.secret_interval, + .data = &ip6_frags_secret_interval_unused, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -636,7 +637,10 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net) goto err_alloc; table[0].data = &net->ipv6.frags.high_thresh; + table[0].extra1 = &net->ipv6.frags.low_thresh; + table[0].extra2 = &init_net.ipv6.frags.high_thresh; table[1].data = &net->ipv6.frags.low_thresh; + table[1].extra2 = &net->ipv6.frags.high_thresh; table[2].data = &net->ipv6.frags.timeout; /* Don't export sysctls to unprivileged users */ @@ -746,8 +750,10 @@ int __init ipv6_frag_init(void) ip6_frags.qsize = sizeof(struct frag_queue); ip6_frags.match = ip6_frag_match; ip6_frags.frag_expire = ip6_frag_expire; - ip6_frags.secret_interval = 10 * 60 * HZ; - inet_frags_init(&ip6_frags); + ip6_frags.frags_cache_name = ip6_frag_cache_name; + ret = inet_frags_init(&ip6_frags); + if (ret) + goto err_pernet; out: return ret; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fba54a407bb2..bafde82324c5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -84,9 +84,9 @@ static void ip6_dst_ifdown(struct dst_entry *, static int ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); -static int ip6_pkt_discard_out(struct sk_buff *skb); +static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb); static int ip6_pkt_prohibit(struct sk_buff *skb); -static int ip6_pkt_prohibit_out(struct sk_buff *skb); +static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); @@ -149,7 +149,8 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) unsigned long prev, new; p = peer->metrics; - if (inet_metrics_new(peer)) + if (inet_metrics_new(peer) || + (old & DST_METRICS_FORCE_OVERWRITE)) memcpy(p, old_p, sizeof(u32) * RTAX_MAX); new = (unsigned long) p; @@ -289,7 +290,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = { .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, .input = dst_discard, - .output = dst_discard, + .output = dst_discard_sk, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), .rt6i_protocol = RTPROT_KERNEL, @@ -313,7 +314,6 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); - rt->rt6i_genid = rt_genid_ipv6(net); INIT_LIST_HEAD(&rt->rt6i_siblings); } return rt; @@ -373,12 +373,6 @@ static bool rt6_check_expired(const struct rt6_info *rt) return false; } -static bool rt6_need_strict(const struct in6_addr *daddr) -{ - return ipv6_addr_type(daddr) & - (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); -} - /* Multipath route selection: * Hash based function using packet header and flowlabel. * Adapted from fib_info_hashfn() @@ -857,14 +851,15 @@ EXPORT_SYMBOL(rt6_lookup); be destroyed. */ -static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info) +static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, + struct nlattr *mx, int mx_len) { int err; struct fib6_table *table; table = rt->rt6i_table; write_lock_bh(&table->tb6_lock); - err = fib6_add(&table->tb6_root, rt, info); + err = fib6_add(&table->tb6_root, rt, info, mx, mx_len); write_unlock_bh(&table->tb6_lock); return err; @@ -875,7 +870,7 @@ int ip6_ins_rt(struct rt6_info *rt) struct nl_info info = { .nl_net = dev_net(rt->dst.dev), }; - return __ip6_ins_rt(rt, &info); + return __ip6_ins_rt(rt, &info, NULL, 0); } static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, @@ -1062,7 +1057,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori new->__use = 1; new->input = dst_discard; - new->output = dst_discard; + new->output = dst_discard_sk; if (dst_metrics_read_only(&ort->dst)) new->_metrics = ort->dst._metrics; @@ -1102,9 +1097,6 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ - if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev))) - return NULL; - if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) return NULL; @@ -1180,7 +1172,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = oif; - fl6.flowi6_mark = mark; + fl6.flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark); fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; fl6.flowlabel = ip6_flowinfo(iph); @@ -1277,6 +1269,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_iif = LOOPBACK_IFINDEX; fl6.flowi6_oif = oif; fl6.flowi6_mark = mark; fl6.daddr = iph->daddr; @@ -1298,6 +1291,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif, struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_iif = LOOPBACK_IFINDEX; fl6.flowi6_oif = oif; fl6.flowi6_mark = mark; fl6.daddr = msg->dest; @@ -1342,7 +1336,7 @@ static unsigned int ip6_mtu(const struct dst_entry *dst) unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) - return mtu; + goto out; mtu = IPV6_MIN_MTU; @@ -1352,7 +1346,8 @@ static unsigned int ip6_mtu(const struct dst_entry *dst) mtu = idev->cnf.mtu6; rcu_read_unlock(); - return mtu; +out: + return min_t(unsigned int, mtu, IP6_MAX_MTU); } static struct dst_entry *icmp6_dst_gc_list; @@ -1456,7 +1451,7 @@ static int ip6_dst_gc(struct dst_ops *ops) goto out; net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, entries > rt_max_size); + fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; @@ -1543,17 +1538,11 @@ int ip6_route_add(struct fib6_config *cfg) ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->rt6i_dst.plen = cfg->fc_dst_len; - if (rt->rt6i_dst.plen == 128) - rt->dst.flags |= DST_HOST; - - if (!(rt->dst.flags & DST_HOST) && cfg->fc_mx) { - u32 *metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); - if (!metrics) { - err = -ENOMEM; - goto out; - } - dst_init_metrics(&rt->dst, metrics, 0); + if (rt->rt6i_dst.plen == 128) { + rt->dst.flags |= DST_HOST; + dst_metrics_set_force_overwrite(&rt->dst); } + #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); rt->rt6i_src.plen = cfg->fc_src_len; @@ -1586,7 +1575,7 @@ int ip6_route_add(struct fib6_config *cfg) switch (cfg->fc_type) { case RTN_BLACKHOLE: rt->dst.error = -EINVAL; - rt->dst.output = dst_discard; + rt->dst.output = dst_discard_sk; rt->dst.input = dst_discard; break; case RTN_PROHIBIT: @@ -1672,31 +1661,13 @@ int ip6_route_add(struct fib6_config *cfg) rt->rt6i_flags = cfg->fc_flags; install_route: - if (cfg->fc_mx) { - struct nlattr *nla; - int remaining; - - nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { - int type = nla_type(nla); - - if (type) { - if (type > RTAX_MAX) { - err = -EINVAL; - goto out; - } - - dst_metric_set(&rt->dst, type, nla_get_u32(nla)); - } - } - } - rt->dst.dev = dev; rt->rt6i_idev = idev; rt->rt6i_table = table; cfg->fc_nlinfo.nl_net = dev_net(dev); - return __ip6_ins_rt(rt, &cfg->fc_nlinfo); + return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len); out: if (dev) @@ -2156,7 +2127,7 @@ static int ip6_pkt_discard(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES); } -static int ip6_pkt_discard_out(struct sk_buff *skb) +static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); @@ -2167,7 +2138,7 @@ static int ip6_pkt_prohibit(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); } -static int ip6_pkt_prohibit_out(struct sk_buff *skb) +static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); @@ -2259,6 +2230,27 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) fib6_clean_all(net, fib6_remove_prefsrc, &adni); } +#define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY) +#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) + +/* Remove routers and update dst entries when gateway turn into host. */ +static int fib6_clean_tohost(struct rt6_info *rt, void *arg) +{ + struct in6_addr *gateway = (struct in6_addr *)arg; + + if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) || + ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) && + ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { + return -1; + } + return 0; +} + +void rt6_clean_tohost(struct net *net, struct in6_addr *gateway) +{ + fib6_clean_all(net, fib6_clean_tohost, gateway); +} + struct arg_dev_net { struct net_device *dev; struct net *net; @@ -2734,6 +2726,9 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh) if (tb[RTA_OIF]) oif = nla_get_u32(tb[RTA_OIF]); + if (tb[RTA_MARK]) + fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]); + if (iif) { struct net_device *dev; int flags = 0; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b4d74c86586c..6163f851dc01 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -101,19 +101,19 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } @@ -250,7 +250,8 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, else strcpy(name, "sit%d"); - dev = alloc_netdev(sizeof(*t), name, ipip6_tunnel_setup); + dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, + ipip6_tunnel_setup); if (dev == NULL) return NULL; @@ -560,12 +561,12 @@ static int ipip6_err(struct sk_buff *skb, u32 info) if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, - t->dev->ifindex, 0, IPPROTO_IPV6, 0); + t->parms.link, 0, IPPROTO_IPV6, 0); err = 0; goto out; } if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, IPPROTO_IPV6, 0); err = 0; goto out; @@ -974,8 +975,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, goto out; } - err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, IPPROTO_IPV6, tos, - ttl, df, !net_eq(tunnel->net, dev_net(dev))); + err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr, + IPPROTO_IPV6, tos, ttl, df, + !net_eq(tunnel->net, dev_net(dev))); iptunnel_xmit_stats(err, &dev->stats, dev->tstats); return NETDEV_TX_OK; @@ -1126,8 +1128,8 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) int err = 0; struct ip_tunnel_parm p; struct ip_tunnel_prl prl; - struct ip_tunnel *t; - struct net *net = dev_net(dev); + struct ip_tunnel *t = netdev_priv(dev); + struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; @@ -1138,16 +1140,15 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) #ifdef CONFIG_IPV6_SIT_6RD case SIOCGET6RD: #endif - t = NULL; if (dev == sitn->fb_tunnel_dev) { if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { err = -EFAULT; break; } t = ipip6_tunnel_locate(net, &p, 0); + if (t == NULL) + t = netdev_priv(dev); } - if (t == NULL) - t = netdev_priv(dev); err = -EFAULT; if (cmd == SIOCGETTUNNEL) { @@ -1243,9 +1244,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) err = -EINVAL; if (dev == sitn->fb_tunnel_dev) goto done; - err = -ENOENT; - if (!(t = netdev_priv(dev))) - goto done; err = ipip6_tunnel_get_prl(t, ifr->ifr_ifru.ifru_data); break; @@ -1261,9 +1259,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) err = -EFAULT; if (copy_from_user(&prl, ifr->ifr_ifru.ifru_data, sizeof(prl))) goto done; - err = -ENOENT; - if (!(t = netdev_priv(dev))) - goto done; switch (cmd) { case SIOCDELPRL: @@ -1291,8 +1286,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) sizeof(ip6rd))) goto done; - t = netdev_priv(dev); - if (cmd != SIOCDEL6RD) { err = ipip6_tunnel_update_6rd(t, &ip6rd); if (err < 0) @@ -1363,7 +1356,6 @@ static void ipip6_tunnel_setup(struct net_device *dev) static int ipip6_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - int i; tunnel->dev = dev; tunnel->net = dev_net(dev); @@ -1372,16 +1364,10 @@ static int ipip6_tunnel_init(struct net_device *dev) memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); ipip6_tunnel_bind_dev(dev); - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ipip6_tunnel_stats; - ipip6_tunnel_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ipip6_tunnel_stats->syncp); - } - tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); if (!tunnel->dst_cache) { free_percpu(dev->tstats); @@ -1397,7 +1383,6 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) struct iphdr *iph = &tunnel->parms.iph; struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); - int i; tunnel->dev = dev; tunnel->net = dev_net(dev); @@ -1408,16 +1393,10 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; iph->ttl = 64; - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ipip6_fb_stats; - ipip6_fb_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ipip6_fb_stats->syncp); - } - tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); if (!tunnel->dst_cache) { free_percpu(dev->tstats); @@ -1751,6 +1730,7 @@ static int __net_init sit_init_net(struct net *net) sitn->tunnels[3] = sitn->tunnels_r_l; sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0", + NET_NAME_UNKNOWN, ipip6_tunnel_setup); if (!sitn->fb_tunnel_dev) { err = -ENOMEM; @@ -1850,4 +1830,5 @@ xfrm_tunnel_failed: module_init(sit_init); module_exit(sit_cleanup); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("sit"); MODULE_ALIAS_NETDEV("sit0"); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index bb53a5e73c1a..83cea1d39466 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -187,7 +187,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet6_reqsk_alloc(&tcp6_request_sock_ops); + req = inet_reqsk_alloc(&tcp6_request_sock_ops); if (!req) goto out; @@ -216,6 +216,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = inet6_iif(skb); + ireq->ir_mark = inet_request_mark(sk, skb); + req->expires = 0UL; req->num_retrans = 0; ireq->ecn_ok = ecn_ok; @@ -242,7 +244,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) final_p = fl6_update_dst(&fl6, np->opt, &final); fl6.saddr = ireq->ir_v6_loc_addr; fl6.flowi6_oif = sk->sk_bound_dev_if; - fl6.flowi6_mark = sk->sk_mark; + fl6.flowi6_mark = ireq->ir_mark; fl6.fl6_dport = ireq->ir_rmt_port; fl6.fl6_sport = inet_sk(sk)->inet_sport; security_req_classify_flow(req, flowi6_to_flowi(&fl6)); diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 7f405a168822..0c56c93619e0 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -38,6 +38,20 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "auto_flowlabels", + .data = &init_net.ipv6.sysctl.auto_flowlabels, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "fwmark_reflect", + .data = &init_net.ipv6.sysctl.fwmark_reflect, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; @@ -67,6 +81,8 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[0].data = &net->ipv6.sysctl.bindv6only; ipv6_table[1].data = &net->ipv6.sysctl.anycast_src_echo_reply; ipv6_table[2].data = &net->ipv6.sysctl.flowlabel_consistency; + ipv6_table[3].data = &net->ipv6.sysctl.auto_flowlabels; + ipv6_table[4].data = &net->ipv6.sysctl.fwmark_reflect; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index cb21fccf2089..03a5d1ed3340 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -39,7 +39,7 @@ #include <linux/ipsec.h> #include <linux/times.h> #include <linux/slab.h> - +#include <linux/uaccess.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/random.h> @@ -64,8 +64,6 @@ #include <net/tcp_memcontrol.h> #include <net/busy_poll.h> -#include <asm/uaccess.h> - #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -199,6 +197,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; + ip6_set_txhash(sk); + /* * TCP over IPv4 */ @@ -341,7 +341,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct sock *sk; int err; struct tcp_sock *tp; - __u32 seq; + struct request_sock *fastopen; + __u32 seq, snd_una; struct net *net = dev_net(skb->dev); sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr, @@ -372,8 +373,11 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, tp = tcp_sk(sk); seq = ntohl(th->seq); + /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ + fastopen = tp->fastopen_rsk; + snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && - !between(seq, tp->snd_una, tp->snd_nxt)) { + !between(seq, snd_una, tp->snd_nxt)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -437,8 +441,13 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out; case TCP_SYN_SENT: - case TCP_SYN_RECV: /* Cannot happen. - It can, it SYNs are crossed. --ANK */ + case TCP_SYN_RECV: + /* Only in fast or simultaneous open. If a fast open socket is + * is already accepted it is treated as a connected one below. + */ + if (fastopen && fastopen->sk == NULL) + break; + if (!sock_owned_by_user(sk)) { sk->sk_err = err; sk->sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ @@ -462,12 +471,14 @@ out: static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, - struct flowi6 *fl6, + struct flowi *fl, struct request_sock *req, - u16 queue_mapping) + u16 queue_mapping, + struct tcp_fastopen_cookie *foc) { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); + struct flowi6 *fl6 = &fl->u.ip6; struct sk_buff *skb; int err = -ENOMEM; @@ -475,7 +486,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL) goto done; - skb = tcp_make_synack(sk, dst, req, NULL); + skb = tcp_make_synack(sk, dst, req, foc); if (skb) { __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, @@ -494,16 +505,6 @@ done: return err; } -static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req) -{ - struct flowi6 fl6; - int res; - - res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0); - if (!res) - TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return res; -} static void tcp_v6_reqsk_destructor(struct request_sock *req) { @@ -529,8 +530,8 @@ static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk, return tcp_v6_md5_do_lookup(sk, &inet_rsk(req)->ir_v6_rmt_addr); } -static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval, - int optlen) +static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, + int optlen) { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; @@ -665,7 +666,8 @@ clear_hash_noput: return 1; } -static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) +static int __tcp_v6_inbound_md5_hash(struct sock *sk, + const struct sk_buff *skb) { const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; @@ -705,27 +707,83 @@ static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) } return 0; } + +static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) +{ + int ret; + + rcu_read_lock(); + ret = __tcp_v6_inbound_md5_hash(sk, skb); + rcu_read_unlock(); + + return ret; +} + #endif +static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, + struct sk_buff *skb) +{ + struct inet_request_sock *ireq = inet_rsk(req); + struct ipv6_pinfo *np = inet6_sk(sk); + + ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; + ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; + + ireq->ir_iif = sk->sk_bound_dev_if; + + /* So that link locals have meaning */ + if (!sk->sk_bound_dev_if && + ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) + ireq->ir_iif = inet6_iif(skb); + + if (!TCP_SKB_CB(skb)->when && + (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || + np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || + np->rxopt.bits.rxohlim || np->repflow)) { + atomic_inc(&skb->users); + ireq->pktopts = skb; + } +} + +static struct dst_entry *tcp_v6_route_req(struct sock *sk, struct flowi *fl, + const struct request_sock *req, + bool *strict) +{ + if (strict) + *strict = true; + return inet6_csk_route_req(sk, &fl->u.ip6, req); +} + struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .family = AF_INET6, .obj_size = sizeof(struct tcp6_request_sock), - .rtx_syn_ack = tcp_v6_rtx_synack, + .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, .send_reset = tcp_v6_send_reset, - .syn_ack_timeout = tcp_syn_ack_timeout, + .syn_ack_timeout = tcp_syn_ack_timeout, }; -#ifdef CONFIG_TCP_MD5SIG static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { + .mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - + sizeof(struct ipv6hdr), +#ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v6_reqsk_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, -}; #endif + .init_req = tcp_v6_init_req, +#ifdef CONFIG_SYN_COOKIES + .cookie_init_seq = cookie_v6_init_sequence, +#endif + .route_req = tcp_v6_route_req, + .init_seq = tcp_v6_init_sequence, + .send_synack = tcp_v6_send_synack, + .queue_hash_add = inet6_csk_reqsk_queue_hash_add, +}; static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, - u32 tsval, u32 tsecr, + u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int rst, u8 tclass, u32 label) { @@ -797,8 +855,11 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr); fl6.flowi6_proto = IPPROTO_TCP; - if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL) + if (rt6_need_strict(&fl6.daddr) && !oif) fl6.flowi6_oif = inet6_iif(skb); + else + fl6.flowi6_oif = oif; + fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark); fl6.fl6_dport = t1->dest; fl6.fl6_sport = t1->source; security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); @@ -832,6 +893,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) int genhash; struct sock *sk1 = NULL; #endif + int oif; if (th->rst) return; @@ -875,7 +937,8 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); - tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, key, 1, 0, 0); + oif = sk ? sk->sk_bound_dev_if : 0; + tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0); #ifdef CONFIG_TCP_MD5SIG release_sk1: @@ -887,11 +950,11 @@ release_sk1: } static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, - u32 win, u32 tsval, u32 tsecr, + u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, u8 tclass, u32 label) { - tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, key, 0, tclass, + tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, oif, key, 0, tclass, label); } @@ -903,7 +966,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, - tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw), + tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_tclass, (tw->tw_flowlabel << 12)); inet_twsk_put(tw); @@ -912,8 +975,13 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { - tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, - req->rcv_wnd, tcp_time_stamp, req->ts_recent, + /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV + * sk->sk_state == TCP_SYN_RECV -> for Fast Open. + */ + tcp_v6_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? + tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, + tcp_rsk(req)->rcv_nxt, + req->rcv_wnd, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); } @@ -952,142 +1020,17 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) return sk; } -/* FIXME: this is substantially similar to the ipv4 code. - * Can some kind of merge be done? -- erics - */ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { - struct tcp_options_received tmp_opt; - struct request_sock *req; - struct inet_request_sock *ireq; - struct ipv6_pinfo *np = inet6_sk(sk); - struct tcp_sock *tp = tcp_sk(sk); - __u32 isn = TCP_SKB_CB(skb)->when; - struct dst_entry *dst = NULL; - struct flowi6 fl6; - bool want_cookie = false; - if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) goto drop; - if ((sysctl_tcp_syncookies == 2 || - inet_csk_reqsk_queue_is_full(sk)) && !isn) { - want_cookie = tcp_syn_flood_action(sk, skb, "TCPv6"); - if (!want_cookie) - goto drop; - } - - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); - goto drop; - } + return tcp_conn_request(&tcp6_request_sock_ops, + &tcp_request_sock_ipv6_ops, sk, skb); - req = inet6_reqsk_alloc(&tcp6_request_sock_ops); - if (req == NULL) - goto drop; - -#ifdef CONFIG_TCP_MD5SIG - tcp_rsk(req)->af_specific = &tcp_request_sock_ipv6_ops; -#endif - - tcp_clear_options(&tmp_opt); - tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); - tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, 0, NULL); - - if (want_cookie && !tmp_opt.saw_tstamp) - tcp_clear_options(&tmp_opt); - - tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; - tcp_openreq_init(req, &tmp_opt, skb); - - ireq = inet_rsk(req); - ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; - ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; - if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, skb, sock_net(sk)); - - ireq->ir_iif = sk->sk_bound_dev_if; - - /* So that link locals have meaning */ - if (!sk->sk_bound_dev_if && - ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) - ireq->ir_iif = inet6_iif(skb); - - if (!isn) { - if (ipv6_opt_accepted(sk, skb) || - np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || - np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || - np->repflow) { - atomic_inc(&skb->users); - ireq->pktopts = skb; - } - - if (want_cookie) { - isn = cookie_v6_init_sequence(sk, skb, &req->mss); - req->cookie_ts = tmp_opt.tstamp_ok; - goto have_isn; - } - - /* VJ's idea. We save last timestamp seen - * from the destination in peer table, when entering - * state TIME-WAIT, and check against it before - * accepting new connection request. - * - * If "isn" is not zero, this request hit alive - * timewait bucket, so that all the necessary checks - * are made in the function processing timewait state. - */ - if (tmp_opt.saw_tstamp && - tcp_death_row.sysctl_tw_recycle && - (dst = inet6_csk_route_req(sk, &fl6, req)) != NULL) { - if (!tcp_peer_is_proven(req, dst, true)) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); - goto drop_and_release; - } - } - /* Kill the following clause, if you dislike this way. */ - else if (!sysctl_tcp_syncookies && - (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < - (sysctl_max_syn_backlog >> 2)) && - !tcp_peer_is_proven(req, dst, false)) { - /* Without syncookies last quarter of - * backlog is filled with destinations, - * proven to be alive. - * It means that we continue to communicate - * to destinations, already remembered - * to the moment of synflood. - */ - LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI6/%u\n", - &ireq->ir_v6_rmt_addr, ntohs(tcp_hdr(skb)->source)); - goto drop_and_release; - } - - isn = tcp_v6_init_sequence(skb); - } -have_isn: - tcp_rsk(req)->snt_isn = isn; - - if (security_inet_conn_request(sk, skb, req)) - goto drop_and_release; - - if (tcp_v6_send_synack(sk, dst, &fl6, req, - skb_get_queue_mapping(skb)) || - want_cookie) - goto drop_and_free; - - tcp_rsk(req)->snt_synack = tcp_time_stamp; - tcp_rsk(req)->listener = NULL; - inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); - return 0; - -drop_and_release: - dst_release(dst); -drop_and_free: - reqsk_free(req); drop: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; /* don't send reset */ @@ -1203,6 +1146,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; newsk->sk_bound_dev_if = ireq->ir_iif; + ip6_set_txhash(newsk); + /* Now IPv6 options... First: no IPv4 options. @@ -1258,7 +1203,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ - if ((key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr)) != NULL) { + key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr); + if (key != NULL) { /* We're using one, so create a matching key * on the newsk structure. If we fail to get * memory, then we end up not copying the key @@ -1288,26 +1234,6 @@ out: return NULL; } -static __sum16 tcp_v6_checksum_init(struct sk_buff *skb) -{ - if (skb->ip_summed == CHECKSUM_COMPLETE) { - if (!tcp_v6_check(skb->len, &ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, skb->csum)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - return 0; - } - } - - skb->csum = ~csum_unfold(tcp_v6_check(skb->len, - &ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, 0)); - - if (skb->len <= 76) { - return __skb_checksum_complete(skb); - } - return 0; -} - /* The socket must have it's spinlock held when we get * here. * @@ -1333,11 +1259,6 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); -#ifdef CONFIG_TCP_MD5SIG - if (tcp_v6_inbound_md5_hash (sk, skb)) - goto discard; -#endif - if (sk_filter(sk, skb)) goto discard; @@ -1481,7 +1402,7 @@ static int tcp_v6_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, th->doff*4)) goto discard_it; - if (!skb_csum_unnecessary(skb) && tcp_v6_checksum_init(skb)) + if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo)) goto csum_error; th = tcp_hdr(skb); @@ -1510,6 +1431,11 @@ process: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; +#ifdef CONFIG_TCP_MD5SIG + if (tcp_v6_inbound_md5_hash(sk, skb)) + goto discard_and_relse; +#endif + if (sk_filter(sk, skb)) goto discard_and_relse; @@ -1591,7 +1517,8 @@ do_time_wait: break; case TCP_TW_RST: goto no_tcp_socket; - case TCP_TW_SUCCESS:; + case TCP_TW_SUCCESS: + ; } goto discard_it; } @@ -1636,7 +1563,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), .twsk_unique = tcp_twsk_unique, - .twsk_destructor= tcp_twsk_destructor, + .twsk_destructor = tcp_twsk_destructor, }; static const struct inet_connection_sock_af_ops ipv6_specific = { @@ -1657,6 +1584,7 @@ static const struct inet_connection_sock_af_ops ipv6_specific = { .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, #endif + .mtu_reduced = tcp_v6_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG @@ -1670,7 +1598,6 @@ static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = { /* * TCP over IPv4 via INET6 API */ - static const struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, @@ -1688,6 +1615,7 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, #endif + .mtu_reduced = tcp_v4_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG @@ -1764,6 +1692,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) const struct inet_sock *inet = inet_sk(sp); const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); + struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq; dest = &sp->sk_v6_daddr; src = &sp->sk_v6_rcv_saddr; @@ -1806,7 +1735,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, - tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh + sp->sk_state == TCP_LISTEN ? + (fastopenq ? fastopenq->max_qlen : 0) : + (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) ); } @@ -1924,7 +1855,6 @@ struct proto tcpv6_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, - .mtu_reduced = tcp_v6_mtu_reduced, .hash = tcp_v6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, @@ -1966,7 +1896,6 @@ static struct inet_protosw tcpv6_protosw = { .protocol = IPPROTO_TCP, .prot = &tcpv6_prot, .ops = &inet6_stream_ops, - .no_check = 0, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }; diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 0d78132ff18a..01b0ff9a0c2c 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -42,7 +42,7 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, if (NAPI_GRO_CB(skb)->flush) goto skip_csum; - wsum = skb->csum; + wsum = NAPI_GRO_CB(skb)->csum; switch (skb->ip_summed) { case CHECKSUM_NONE: @@ -73,7 +73,7 @@ static int tcp6_gro_complete(struct sk_buff *skb, int thoff) th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr, &iph->daddr, 0); - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; return tcp_gro_complete(skb); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1e586d92260e..4836af8f582d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -79,7 +79,6 @@ static unsigned int udp6_ehashfn(struct net *net, int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); - int sk_ipv6only = ipv6_only_sock(sk); int sk2_ipv6only = inet_v6_ipv6only(sk2); int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; @@ -95,7 +94,7 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) return 1; if (addr_type == IPV6_ADDR_ANY && - !(sk_ipv6only && addr_type2 == IPV6_ADDR_MAPPED)) + !(ipv6_only_sock(sk) && addr_type2 == IPV6_ADDR_MAPPED)) return 1; if (sk2_rcv_saddr6 && @@ -473,7 +472,7 @@ try_again: sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, - IP6CB(skb)->iif); + inet6_iif(skb)); } *addr_len = sizeof(*sin6); } @@ -534,11 +533,15 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct udphdr *uh = (struct udphdr*)(skb->data+offset); struct sock *sk; int err; + struct net *net = dev_net(skb->dev); - sk = __udp6_lib_lookup(dev_net(skb->dev), daddr, uh->dest, + sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), udptable); - if (sk == NULL) + if (sk == NULL) { + ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), + ICMP6_MIB_INERRORS); return; + } if (type == ICMPV6_PKT_TOOBIG) { if (!ip6_sk_accept_pmtu(sk)) @@ -634,6 +637,10 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) { int ret; + /* Verify checksum before giving to encap */ + if (udp_lib_checksum_complete(skb)) + goto csum_error; + ret = encap_rcv(sk, skb); if (ret <= 0) { UDP_INC_STATS_BH(sock_net(sk), @@ -670,8 +677,11 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto csum_error; } - if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) + if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { + UDP6_INC_STATS_BH(sock_net(sk), + UDP_MIB_RCVBUFERRORS, is_udplite); goto drop; + } skb_dst_drop(skb); @@ -686,6 +696,7 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) bh_unlock_sock(sk); return rc; + csum_error: UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: @@ -695,44 +706,26 @@ drop: return -1; } -static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, - __be16 loc_port, const struct in6_addr *loc_addr, - __be16 rmt_port, const struct in6_addr *rmt_addr, - int dif) +static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk, + __be16 loc_port, const struct in6_addr *loc_addr, + __be16 rmt_port, const struct in6_addr *rmt_addr, + int dif, unsigned short hnum) { - struct hlist_nulls_node *node; - struct sock *s = sk; - unsigned short num = ntohs(loc_port); - - sk_nulls_for_each_from(s, node) { - struct inet_sock *inet = inet_sk(s); - - if (!net_eq(sock_net(s), net)) - continue; - - if (udp_sk(s)->udp_port_hash == num && - s->sk_family == PF_INET6) { - if (inet->inet_dport) { - if (inet->inet_dport != rmt_port) - continue; - } - if (!ipv6_addr_any(&sk->sk_v6_daddr) && - !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) - continue; - - if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif) - continue; + struct inet_sock *inet = inet_sk(sk); - if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { - if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) - continue; - } - if (!inet6_mc_check(s, loc_addr, rmt_addr)) - continue; - return s; - } - } - return NULL; + if (!net_eq(sock_net(sk), net)) + return false; + + if (udp_sk(sk)->udp_port_hash != hnum || + sk->sk_family != PF_INET6 || + (inet->inet_dport && inet->inet_dport != rmt_port) || + (!ipv6_addr_any(&sk->sk_v6_daddr) && + !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || + (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + return false; + if (!inet6_mc_check(sk, loc_addr, rmt_addr)) + return false; + return true; } static void flush_stack(struct sock **stack, unsigned int count, @@ -756,10 +749,22 @@ static void flush_stack(struct sock **stack, unsigned int count, if (skb1 && udpv6_queue_rcv_skb(sk, skb1) <= 0) skb1 = NULL; + sock_put(sk); } if (unlikely(skb1)) kfree_skb(skb1); } + +static void udp6_csum_zero_error(struct sk_buff *skb) +{ + /* RFC 2460 section 8.1 says that we SHOULD log + * this error. Well, it is reasonable. + */ + LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n", + &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source), + &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest)); +} + /* * Note: called only from the BH handler context, * so we don't need to lock the hashes. @@ -770,38 +775,51 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, { struct sock *sk, *stack[256 / sizeof(struct sock *)]; const struct udphdr *uh = udp_hdr(skb); - struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest)); - int dif; - unsigned int i, count = 0; + struct hlist_nulls_node *node; + unsigned short hnum = ntohs(uh->dest); + struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum); + int dif = inet6_iif(skb); + unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node); + unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); + + if (use_hash2) { + hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) & + udp_table.mask; + hash2 = udp6_portaddr_hash(net, daddr, hnum) & udp_table.mask; +start_lookup: + hslot = &udp_table.hash2[hash2]; + offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); + } spin_lock(&hslot->lock); - sk = sk_nulls_head(&hslot->head); - dif = inet6_iif(skb); - sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); - while (sk) { - stack[count++] = sk; - sk = udp_v6_mcast_next(net, sk_nulls_next(sk), uh->dest, daddr, - uh->source, saddr, dif); - if (unlikely(count == ARRAY_SIZE(stack))) { - if (!sk) - break; - flush_stack(stack, count, skb, ~0); - count = 0; + sk_nulls_for_each_entry_offset(sk, node, &hslot->head, offset) { + if (__udp_v6_is_mcast_sock(net, sk, + uh->dest, daddr, + uh->source, saddr, + dif, hnum) && + /* If zero checksum and no_check is not on for + * the socket then skip it. + */ + (uh->check || udp_sk(sk)->no_check6_rx)) { + if (unlikely(count == ARRAY_SIZE(stack))) { + flush_stack(stack, count, skb, ~0); + count = 0; + } + stack[count++] = sk; + sock_hold(sk); } } - /* - * before releasing the lock, we must take reference on sockets - */ - for (i = 0; i < count; i++) - sock_hold(stack[i]); spin_unlock(&hslot->lock); + /* Also lookup *:port if we are using hash2 and haven't done so yet. */ + if (use_hash2 && hash2 != hash2_any) { + hash2 = hash2_any; + goto start_lookup; + } + if (count) { flush_stack(stack, count, skb, count - 1); - - for (i = 0; i < count; i++) - sock_put(stack[i]); } else { kfree_skb(skb); } @@ -867,6 +885,12 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (sk != NULL) { int ret; + if (!uh->check && !udp_sk(sk)->no_check6_rx) { + sock_put(sk); + udp6_csum_zero_error(skb); + goto csum_error; + } + ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); @@ -879,6 +903,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, return 0; } + if (!uh->check) { + udp6_csum_zero_error(skb); + goto csum_error; + } + if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; @@ -1006,7 +1035,10 @@ static int udp_v6_push_pending_frames(struct sock *sk) if (is_udplite) csum = udplite_csum_outgoing(sk, skb); - else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ + else if (up->no_check6_tx) { /* UDP csum disabled */ + skb->ip_summed = CHECKSUM_NONE; + goto send; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, up->len); goto send; @@ -1232,14 +1264,8 @@ do_udp_sendmsg: goto out; } - if (hlimit < 0) { - if (ipv6_addr_is_multicast(&fl6.daddr)) - hlimit = np->mcast_hops; - else - hlimit = np->hop_limit; - if (hlimit < 0) - hlimit = ip6_dst_hoplimit(dst); - } + if (hlimit < 0) + hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); if (tclass < 0) tclass = np->tclass; @@ -1479,7 +1505,6 @@ static struct inet_protosw udpv6_protosw = { .protocol = IPPROTO_UDP, .prot = &udpv6_prot, .ops = &inet6_dgram_ops, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_PERMANENT, }; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index b261ee8b83fc..0ae3d98f83e0 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -63,7 +63,9 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_UDP_TUNNEL | + SKB_GSO_UDP_TUNNEL_CSUM | SKB_GSO_GRE | + SKB_GSO_GRE_CSUM | SKB_GSO_IPIP | SKB_GSO_SIT | SKB_GSO_MPLS) || @@ -76,7 +78,8 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, goto out; } - if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) + if (skb->encapsulation && skb_shinfo(skb)->gso_type & + (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)) segs = skb_udp_tunnel_segment(skb, features); else { /* Do software UFO. Complete and fill in the UDP checksum as HW cannot diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index dfcc4be46898..9cf097e206e9 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -64,7 +64,6 @@ static struct inet_protosw udplite6_protosw = { .protocol = IPPROTO_UDPLITE, .prot = &udplitev6_prot, .ops = &inet6_dgram_ops, - .no_check = 0, .flags = INET_PROTOSW_PERMANENT, }; diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index cb04f7a16b5e..901ef6f8addc 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -18,65 +18,6 @@ #include <net/ipv6.h> #include <net/xfrm.h> -/* Informational hook. The decap is still done here. */ -static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly; -static DEFINE_MUTEX(xfrm6_mode_tunnel_input_mutex); - -int xfrm6_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler) -{ - struct xfrm_tunnel_notifier __rcu **pprev; - struct xfrm_tunnel_notifier *t; - int ret = -EEXIST; - int priority = handler->priority; - - mutex_lock(&xfrm6_mode_tunnel_input_mutex); - - for (pprev = &rcv_notify_handlers; - (t = rcu_dereference_protected(*pprev, - lockdep_is_held(&xfrm6_mode_tunnel_input_mutex))) != NULL; - pprev = &t->next) { - if (t->priority > priority) - break; - if (t->priority == priority) - goto err; - - } - - handler->next = *pprev; - rcu_assign_pointer(*pprev, handler); - - ret = 0; - -err: - mutex_unlock(&xfrm6_mode_tunnel_input_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(xfrm6_mode_tunnel_input_register); - -int xfrm6_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler) -{ - struct xfrm_tunnel_notifier __rcu **pprev; - struct xfrm_tunnel_notifier *t; - int ret = -ENOENT; - - mutex_lock(&xfrm6_mode_tunnel_input_mutex); - for (pprev = &rcv_notify_handlers; - (t = rcu_dereference_protected(*pprev, - lockdep_is_held(&xfrm6_mode_tunnel_input_mutex))) != NULL; - pprev = &t->next) { - if (t == handler) { - *pprev = handler->next; - ret = 0; - break; - } - } - mutex_unlock(&xfrm6_mode_tunnel_input_mutex); - synchronize_net(); - - return ret; -} -EXPORT_SYMBOL_GPL(xfrm6_mode_tunnel_input_deregister); - static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) { const struct ipv6hdr *outer_iph = ipv6_hdr(skb); @@ -130,7 +71,6 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - struct xfrm_tunnel_notifier *handler; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6) @@ -138,9 +78,6 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; - for_each_input_rcu(rcv_notify_handlers, handler) - handler->handler(skb); - err = skb_unclone(skb, GFP_ATOMIC); if (err) goto out; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 6cd625e37706..433672d07d0b 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -78,7 +78,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if (!skb->local_df && skb->len > mtu) { + if (!skb->ignore_df && skb->len > mtu) { skb->dev = dst->dev; if (xfrm6_local_dontfrag(skb)) @@ -114,13 +114,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) if (err) return err; - memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); -#ifdef CONFIG_NETFILTER - IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; -#endif - - skb->protocol = htons(ETH_P_IPV6); - skb->local_df = 1; + skb->ignore_df = 1; return x->outer_mode->output2(x, skb); } @@ -128,11 +122,13 @@ EXPORT_SYMBOL(xfrm6_prepare_output); int xfrm6_output_finish(struct sk_buff *skb) { + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + skb->protocol = htons(ETH_P_IPV6); + #ifdef CONFIG_NETFILTER IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; #endif - skb->protocol = htons(ETH_P_IPV6); return xfrm_output(skb); } @@ -142,6 +138,13 @@ static int __xfrm6_output(struct sk_buff *skb) struct xfrm_state *x = dst->xfrm; int mtu; +#ifdef CONFIG_NETFILTER + if (!x) { + IP6CB(skb)->flags |= IP6SKB_REROUTED; + return dst_output(skb); + } +#endif + if (skb->protocol == htons(ETH_P_IPV6)) mtu = ip6_skb_dst_mtu(skb); else @@ -150,7 +153,7 @@ static int __xfrm6_output(struct sk_buff *skb) if (skb->len > mtu && xfrm6_local_dontfrag(skb)) { xfrm6_local_rxpmtu(skb, mtu); return -EMSGSIZE; - } else if (!skb->local_df && skb->len > mtu && skb->sk) { + } else if (!skb->ignore_df && skb->len > mtu && skb->sk) { xfrm_local_error(skb, mtu); return -EMSGSIZE; } @@ -163,8 +166,9 @@ static int __xfrm6_output(struct sk_buff *skb) return x->outer_mode->afinfo->output_finish(skb); } -int xfrm6_output(struct sk_buff *skb) +int xfrm6_output(struct sock *sk, struct sk_buff *skb) { - return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, - skb_dst(skb)->dev, __xfrm6_output); + return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, + NULL, skb_dst(skb)->dev, __xfrm6_output, + !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 5f8e128c512d..2a0bbda2c76a 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -389,11 +389,17 @@ int __init xfrm6_init(void) if (ret) goto out_policy; + ret = xfrm6_protocol_init(); + if (ret) + goto out_state; + #ifdef CONFIG_SYSCTL register_pernet_subsys(&xfrm6_net_ops); #endif out: return ret; +out_state: + xfrm6_state_fini(); out_policy: xfrm6_policy_fini(); goto out; @@ -404,6 +410,7 @@ void xfrm6_fini(void) #ifdef CONFIG_SYSCTL unregister_pernet_subsys(&xfrm6_net_ops); #endif + xfrm6_protocol_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); dst_entries_destroy(&xfrm6_dst_ops); diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c new file mode 100644 index 000000000000..54d13f8dbbae --- /dev/null +++ b/net/ipv6/xfrm6_protocol.c @@ -0,0 +1,279 @@ +/* xfrm6_protocol.c - Generic xfrm protocol multiplexer for ipv6. + * + * Copyright (C) 2013 secunet Security Networks AG + * + * Author: + * Steffen Klassert <steffen.klassert@secunet.com> + * + * Based on: + * net/ipv4/xfrm4_protocol.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/init.h> +#include <linux/mutex.h> +#include <linux/skbuff.h> +#include <linux/icmpv6.h> +#include <net/ipv6.h> +#include <net/protocol.h> +#include <net/xfrm.h> + +static struct xfrm6_protocol __rcu *esp6_handlers __read_mostly; +static struct xfrm6_protocol __rcu *ah6_handlers __read_mostly; +static struct xfrm6_protocol __rcu *ipcomp6_handlers __read_mostly; +static DEFINE_MUTEX(xfrm6_protocol_mutex); + +static inline struct xfrm6_protocol __rcu **proto_handlers(u8 protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp6_handlers; + case IPPROTO_AH: + return &ah6_handlers; + case IPPROTO_COMP: + return &ipcomp6_handlers; + } + + return NULL; +} + +#define for_each_protocol_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) \ + +int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err) +{ + int ret; + struct xfrm6_protocol *handler; + struct xfrm6_protocol __rcu **head = proto_handlers(protocol); + + if (!head) + return 0; + + for_each_protocol_rcu(*proto_handlers(protocol), handler) + if ((ret = handler->cb_handler(skb, err)) <= 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(xfrm6_rcv_cb); + +static int xfrm6_esp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm6_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + + for_each_protocol_rcu(esp6_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct xfrm6_protocol *handler; + + for_each_protocol_rcu(esp6_handlers, handler) + if (!handler->err_handler(skb, opt, type, code, offset, info)) + break; +} + +static int xfrm6_ah_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm6_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + + for_each_protocol_rcu(ah6_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct xfrm6_protocol *handler; + + for_each_protocol_rcu(ah6_handlers, handler) + if (!handler->err_handler(skb, opt, type, code, offset, info)) + break; +} + +static int xfrm6_ipcomp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm6_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + + for_each_protocol_rcu(ipcomp6_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct xfrm6_protocol *handler; + + for_each_protocol_rcu(ipcomp6_handlers, handler) + if (!handler->err_handler(skb, opt, type, code, offset, info)) + break; +} + +static const struct inet6_protocol esp6_protocol = { + .handler = xfrm6_esp_rcv, + .err_handler = xfrm6_esp_err, + .flags = INET6_PROTO_NOPOLICY, +}; + +static const struct inet6_protocol ah6_protocol = { + .handler = xfrm6_ah_rcv, + .err_handler = xfrm6_ah_err, + .flags = INET6_PROTO_NOPOLICY, +}; + +static const struct inet6_protocol ipcomp6_protocol = { + .handler = xfrm6_ipcomp_rcv, + .err_handler = xfrm6_ipcomp_err, + .flags = INET6_PROTO_NOPOLICY, +}; + +static struct xfrm_input_afinfo xfrm6_input_afinfo = { + .family = AF_INET6, + .owner = THIS_MODULE, + .callback = xfrm6_rcv_cb, +}; + +static inline const struct inet6_protocol *netproto(unsigned char protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp6_protocol; + case IPPROTO_AH: + return &ah6_protocol; + case IPPROTO_COMP: + return &ipcomp6_protocol; + } + + return NULL; +} + +int xfrm6_protocol_register(struct xfrm6_protocol *handler, + unsigned char protocol) +{ + struct xfrm6_protocol __rcu **pprev; + struct xfrm6_protocol *t; + bool add_netproto = false; + int ret = -EEXIST; + int priority = handler->priority; + + if (!proto_handlers(protocol) || !netproto(protocol)) + return -EINVAL; + + mutex_lock(&xfrm6_protocol_mutex); + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm6_protocol_mutex))) + add_netproto = true; + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t->priority < priority) + break; + if (t->priority == priority) + goto err; + } + + handler->next = *pprev; + rcu_assign_pointer(*pprev, handler); + + ret = 0; + +err: + mutex_unlock(&xfrm6_protocol_mutex); + + if (add_netproto) { + if (inet6_add_protocol(netproto(protocol), protocol)) { + pr_err("%s: can't add protocol\n", __func__); + ret = -EAGAIN; + } + } + + return ret; +} +EXPORT_SYMBOL(xfrm6_protocol_register); + +int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, + unsigned char protocol) +{ + struct xfrm6_protocol __rcu **pprev; + struct xfrm6_protocol *t; + int ret = -ENOENT; + + if (!proto_handlers(protocol) || !netproto(protocol)) + return -EINVAL; + + mutex_lock(&xfrm6_protocol_mutex); + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t == handler) { + *pprev = handler->next; + ret = 0; + break; + } + } + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm6_protocol_mutex))) { + if (inet6_del_protocol(netproto(protocol), protocol) < 0) { + pr_err("%s: can't remove protocol\n", __func__); + ret = -EAGAIN; + } + } + + mutex_unlock(&xfrm6_protocol_mutex); + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(xfrm6_protocol_deregister); + +int __init xfrm6_protocol_init(void) +{ + return xfrm_input_register_afinfo(&xfrm6_input_afinfo); +} + +void xfrm6_protocol_fini(void) +{ + xfrm_input_unregister_afinfo(&xfrm6_input_afinfo); +} |