diff options
Diffstat (limited to 'net/ipv6')
-rw-r--r-- | net/ipv6/addrconf.c | 17 | ||||
-rw-r--r-- | net/ipv6/af_inet6.c | 2 | ||||
-rw-r--r-- | net/ipv6/ah6.c | 5 | ||||
-rw-r--r-- | net/ipv6/datagram.c | 8 | ||||
-rw-r--r-- | net/ipv6/esp6.c | 3 | ||||
-rw-r--r-- | net/ipv6/icmp.c | 10 | ||||
-rw-r--r-- | net/ipv6/inet6_connection_sock.c | 2 | ||||
-rw-r--r-- | net/ipv6/inet6_hashtables.c | 182 | ||||
-rw-r--r-- | net/ipv6/ip6_flowlabel.c | 2 | ||||
-rw-r--r-- | net/ipv6/ip6_tunnel.c | 37 | ||||
-rw-r--r-- | net/ipv6/ip6mr.c | 19 | ||||
-rw-r--r-- | net/ipv6/ipcomp6.c | 6 | ||||
-rw-r--r-- | net/ipv6/ipv6_sockglue.c | 5 | ||||
-rw-r--r-- | net/ipv6/mcast.c | 6 | ||||
-rw-r--r-- | net/ipv6/mip6.c | 3 | ||||
-rw-r--r-- | net/ipv6/ndisc.c | 98 | ||||
-rw-r--r-- | net/ipv6/netfilter.c | 2 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6t_REJECT.c | 2 | ||||
-rw-r--r-- | net/ipv6/proc.c | 6 | ||||
-rw-r--r-- | net/ipv6/raw.c | 3 | ||||
-rw-r--r-- | net/ipv6/route.c | 2 | ||||
-rw-r--r-- | net/ipv6/sit.c | 35 | ||||
-rw-r--r-- | net/ipv6/syncookies.c | 2 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 20 | ||||
-rw-r--r-- | net/ipv6/udp.c | 63 | ||||
-rw-r--r-- | net/ipv6/xfrm6_input.c | 9 | ||||
-rw-r--r-- | net/ipv6/xfrm6_policy.c | 13 | ||||
-rw-r--r-- | net/ipv6/xfrm6_state.c | 3 |
28 files changed, 348 insertions, 217 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 07ee758de9e1..e92ad8455c63 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2031,8 +2031,8 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg) #if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) if (dev->type == ARPHRD_SIT) { + const struct net_device_ops *ops = dev->netdev_ops; struct ifreq ifr; - mm_segment_t oldfs; struct ip_tunnel_parm p; err = -EADDRNOTAVAIL; @@ -2048,9 +2048,14 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg) p.iph.ttl = 64; ifr.ifr_ifru.ifru_data = (__force void __user *)&p; - oldfs = get_fs(); set_fs(KERNEL_DS); - err = dev->do_ioctl(dev, &ifr, SIOCADDTUNNEL); - set_fs(oldfs); + if (ops->ndo_do_ioctl) { + mm_segment_t oldfs = get_fs(); + + set_fs(KERNEL_DS); + err = ops->ndo_do_ioctl(dev, &ifr, SIOCADDTUNNEL); + set_fs(oldfs); + } else + err = -EOPNOTSUPP; if (err == 0) { err = -ENOBUFS; @@ -2483,8 +2488,10 @@ 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 (idev) { idev->if_flags |= IF_READY; + run_pending = 1; + } } else { if (!addrconf_qdisc_ok(dev)) { /* device is still not ready. */ diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 01edac888510..437b750b98fd 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -637,7 +637,7 @@ int inet6_sk_rebuild_header(struct sock *sk) if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { + if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) { sk->sk_err_soft = -err; return err; } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 7a8a01369e5c..52449f7a1b71 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -407,6 +407,7 @@ out: static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int type, int code, int offset, __be32 info) { + struct net *net = dev_net(skb->dev); struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+offset); struct xfrm_state *x; @@ -415,7 +416,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, type != ICMPV6_PKT_TOOBIG) return; - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); + x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); if (!x) return; @@ -509,9 +510,7 @@ static void ah6_destroy(struct xfrm_state *x) return; kfree(ahp->work_icv); - ahp->work_icv = NULL; crypto_free_hash(ahp->tfm); - ahp->tfm = NULL; kfree(ahp); } diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 410046a8cc91..e2bdc6d83a43 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -175,7 +175,8 @@ ipv4_connected: if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) { + err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); + if (err < 0) { if (err == -EREMOTE) err = ip6_dst_blackhole(sk, &dst, &fl); if (err < 0) @@ -661,6 +662,11 @@ int datagram_send_ctl(struct net *net, switch (rthdr->type) { #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) case IPV6_SRCRT_TYPE_2: + if (rthdr->hdrlen != 2 || + rthdr->segments_left != 1) { + err = -EINVAL; + goto exit_f; + } break; #endif default: diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index c02a6308defe..c2f250150db1 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -356,6 +356,7 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu) static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int type, int code, int offset, __be32 info) { + struct net *net = dev_net(skb->dev); struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data + offset); struct xfrm_state *x; @@ -364,7 +365,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, type != ICMPV6_PKT_TOOBIG) return; - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); + x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); if (!x) return; printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%pI6\n", diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index be351009fd03..4f433847d95f 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -233,7 +233,7 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct icmp6h->icmp6_cksum = 0; if (skb_queue_len(&sk->sk_write_queue) == 1) { - skb->csum = csum_partial((char *)icmp6h, + skb->csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), skb->csum); icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst, @@ -246,7 +246,7 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct tmp_csum = csum_add(tmp_csum, skb->csum); } - tmp_csum = csum_partial((char *)icmp6h, + tmp_csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), tmp_csum); icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst, @@ -427,7 +427,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, /* No need to clone since we're just using its address. */ dst2 = dst; - err = xfrm_lookup(&dst, &fl, sk, 0); + err = xfrm_lookup(net, &dst, &fl, sk, 0); switch (err) { case 0: if (dst != dst2) @@ -446,7 +446,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, if (ip6_dst_lookup(sk, &dst2, &fl)) goto relookup_failed; - err = xfrm_lookup(&dst2, &fl, sk, XFRM_LOOKUP_ICMP); + err = xfrm_lookup(net, &dst2, &fl, sk, XFRM_LOOKUP_ICMP); switch (err) { case 0: dst_release(dst); @@ -552,7 +552,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) err = ip6_dst_lookup(sk, &dst, &fl); if (err) goto out; - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + if ((err = xfrm_lookup(net, &dst, &fl, sk, 0)) < 0) goto out; if (ipv6_addr_is_multicast(&fl.fl6_dst)) diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 16d43f20b32f..3c3732d50c1a 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -219,7 +219,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { + if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) { sk->sk_route_caps = 0; kfree_skb(skb); return err; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 1646a5658255..8fe267feb81e 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -25,26 +25,30 @@ void __inet6_hash(struct sock *sk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - struct hlist_head *list; - rwlock_t *lock; WARN_ON(!sk_unhashed(sk)); if (sk->sk_state == TCP_LISTEN) { - list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; - lock = &hashinfo->lhash_lock; - inet_listen_wlock(hashinfo); + struct inet_listen_hashbucket *ilb; + + ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; + spin_lock(&ilb->lock); + __sk_nulls_add_node_rcu(sk, &ilb->head); + spin_unlock(&ilb->lock); } else { unsigned int hash; + struct hlist_nulls_head *list; + spinlock_t *lock; + sk->sk_hash = hash = inet6_sk_ehashfn(sk); list = &inet_ehash_bucket(hashinfo, hash)->chain; lock = inet_ehash_lockp(hashinfo, hash); - write_lock(lock); + spin_lock(lock); + __sk_nulls_add_node_rcu(sk, list); + spin_unlock(lock); } - __sk_add_node(sk, list); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - write_unlock(lock); } EXPORT_SYMBOL(__inet6_hash); @@ -63,77 +67,122 @@ struct sock *__inet6_lookup_established(struct net *net, const int dif) { struct sock *sk; - const struct hlist_node *node; + const struct hlist_nulls_node *node; const __portpair ports = INET_COMBINED_PORTS(sport, hnum); /* Optimize here for direct hit, only listening connections can * have wildcards anyways. */ unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport); - struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash); - rwlock_t *lock = inet_ehash_lockp(hashinfo, hash); + unsigned int slot = hash & (hashinfo->ehash_size - 1); + struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; - prefetch(head->chain.first); - read_lock(lock); - sk_for_each(sk, node, &head->chain) { + + rcu_read_lock(); +begin: + sk_nulls_for_each_rcu(sk, node, &head->chain) { /* For IPV6 do the cheaper port and family tests first. */ - if (INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) - goto hit; /* You sunk my battleship! */ + if (INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) + goto begintw; + if (!INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + sock_put(sk); + goto begin; + } + goto out; + } } + if (get_nulls_value(node) != slot) + goto begin; + +begintw: /* Must check for a TIME_WAIT'er before going to listener hash. */ - sk_for_each(sk, node, &head->twchain) { - if (INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) - goto hit; + sk_nulls_for_each_rcu(sk, node, &head->twchain) { + if (INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) { + sk = NULL; + goto out; + } + if (!INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + sock_put(sk); + goto begintw; + } + goto out; + } } - read_unlock(lock); - return NULL; - -hit: - sock_hold(sk); - read_unlock(lock); + if (get_nulls_value(node) != slot) + goto begintw; + sk = NULL; +out: + rcu_read_unlock(); return sk; } EXPORT_SYMBOL(__inet6_lookup_established); +static int inline compute_score(struct sock *sk, struct net *net, + const unsigned short hnum, + const struct in6_addr *daddr, + const int dif) +{ + int score = -1; + + if (net_eq(sock_net(sk), net) && inet_sk(sk)->num == hnum && + sk->sk_family == PF_INET6) { + const struct ipv6_pinfo *np = inet6_sk(sk); + + score = 1; + if (!ipv6_addr_any(&np->rcv_saddr)) { + if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + return -1; + score++; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score++; + } + } + return score; +} + struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *daddr, const unsigned short hnum, const int dif) { struct sock *sk; - const struct hlist_node *node; - struct sock *result = NULL; - int score, hiscore = 0; - - read_lock(&hashinfo->lhash_lock); - sk_for_each(sk, node, - &hashinfo->listening_hash[inet_lhashfn(net, hnum)]) { - if (net_eq(sock_net(sk), net) && inet_sk(sk)->num == hnum && - sk->sk_family == PF_INET6) { - const struct ipv6_pinfo *np = inet6_sk(sk); - - score = 1; - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) - continue; - score++; - } - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - continue; - score++; - } - if (score == 3) { - result = sk; - break; - } - if (score > hiscore) { - hiscore = score; - result = sk; - } + const struct hlist_nulls_node *node; + struct sock *result; + int score, hiscore; + unsigned int hash = inet_lhashfn(net, hnum); + struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; + + rcu_read_lock(); +begin: + result = NULL; + hiscore = -1; + sk_nulls_for_each(sk, node, &ilb->head) { + score = compute_score(sk, net, hnum, daddr, dif); + if (score > hiscore) { + hiscore = score; + result = sk; + } + } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != hash + LISTENING_NULLS_BASE) + goto begin; + if (result) { + if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + result = NULL; + else if (unlikely(compute_score(result, net, hnum, daddr, + dif) < hiscore)) { + sock_put(result); + goto begin; } } - if (result) - sock_hold(result); - read_unlock(&hashinfo->lhash_lock); + rcu_read_unlock(); return result; } @@ -170,16 +219,15 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr, inet->dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); - rwlock_t *lock = inet_ehash_lockp(hinfo, hash); + spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; - const struct hlist_node *node; + const struct hlist_nulls_node *node; struct inet_timewait_sock *tw; - prefetch(head->chain.first); - write_lock(lock); + spin_lock(lock); /* Check TIME-WAIT sockets first. */ - sk_for_each(sk2, node, &head->twchain) { + sk_nulls_for_each(sk2, node, &head->twchain) { tw = inet_twsk(sk2); if (INET6_TW_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) { @@ -192,7 +240,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, tw = NULL; /* And established part... */ - sk_for_each(sk2, node, &head->chain) { + sk_nulls_for_each(sk2, node, &head->chain) { if (INET6_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) goto not_unique; } @@ -203,10 +251,10 @@ unique: inet->num = lport; inet->sport = htons(lport); WARN_ON(!sk_unhashed(sk)); - __sk_add_node(sk, &head->chain); + __sk_nulls_add_node_rcu(sk, &head->chain); sk->sk_hash = hash; + spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - write_unlock(lock); if (twp != NULL) { *twp = tw; @@ -221,7 +269,7 @@ unique: return 0; not_unique: - write_unlock(lock); + spin_unlock(lock); return -EADDRNOTAVAIL; } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 7927a8498d17..5656e8aa47d8 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -464,7 +464,7 @@ static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl, int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) { - int err; + int uninitialized_var(err); struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_flowlabel_req freq; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 64ce3d33d9c6..58e2b0d93758 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -74,8 +74,8 @@ MODULE_LICENSE("GPL"); (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \ (HASH_SIZE - 1)) -static int ip6_fb_tnl_dev_init(struct net_device *dev); -static int ip6_tnl_dev_init(struct net_device *dev); +static void ip6_fb_tnl_dev_init(struct net_device *dev); +static void ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); static int ip6_tnl_net_id; @@ -249,7 +249,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) } t = netdev_priv(dev); - dev->init = ip6_tnl_dev_init; + ip6_tnl_dev_init(dev); t->parms = *p; if ((err = register_netdevice(dev)) < 0) @@ -846,6 +846,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, int encap_limit, __u32 *pmtu) { + struct net *net = dev_net(dev); struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; struct ipv6hdr *ipv6h = ipv6_hdr(skb); @@ -861,9 +862,9 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, if ((dst = ip6_tnl_dst_check(t)) != NULL) dst_hold(dst); else { - dst = ip6_route_output(dev_net(dev), NULL, fl); + dst = ip6_route_output(net, NULL, fl); - if (dst->error || xfrm_lookup(&dst, fl, NULL, 0) < 0) + if (dst->error || xfrm_lookup(net, &dst, fl, NULL, 0) < 0) goto tx_err_link_failure; } @@ -1150,7 +1151,6 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) * ip6_tnl_change - update the tunnel parameters * @t: tunnel to be changed * @p: tunnel configuration parameters - * @active: != 0 if tunnel is ready for use * * Description: * ip6_tnl_change() updates the tunnel parameters @@ -1306,6 +1306,14 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) return 0; } + +static const struct net_device_ops ip6_tnl_netdev_ops = { + .ndo_uninit = ip6_tnl_dev_uninit, + .ndo_start_xmit = ip6_tnl_xmit, + .ndo_do_ioctl = ip6_tnl_ioctl, + .ndo_change_mtu = ip6_tnl_change_mtu, +}; + /** * ip6_tnl_dev_setup - setup virtual tunnel device * @dev: virtual device associated with tunnel @@ -1316,11 +1324,8 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) static void ip6_tnl_dev_setup(struct net_device *dev) { - dev->uninit = ip6_tnl_dev_uninit; + dev->netdev_ops = &ip6_tnl_netdev_ops; dev->destructor = free_netdev; - dev->hard_start_xmit = ip6_tnl_xmit; - dev->do_ioctl = ip6_tnl_ioctl; - dev->change_mtu = ip6_tnl_change_mtu; dev->type = ARPHRD_TUNNEL6; dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr); @@ -1349,13 +1354,11 @@ ip6_tnl_dev_init_gen(struct net_device *dev) * @dev: virtual device associated with tunnel **/ -static int -ip6_tnl_dev_init(struct net_device *dev) +static void ip6_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); ip6_tnl_dev_init_gen(dev); ip6_tnl_link_config(t); - return 0; } /** @@ -1365,8 +1368,7 @@ ip6_tnl_dev_init(struct net_device *dev) * Return: 0 **/ -static int -ip6_fb_tnl_dev_init(struct net_device *dev) +static void ip6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); @@ -1376,7 +1378,6 @@ ip6_fb_tnl_dev_init(struct net_device *dev) t->parms.proto = IPPROTO_IPV6; dev_hold(dev); ip6n->tnls_wc[0] = t; - return 0; } static struct xfrm6_tunnel ip4ip6_handler = { @@ -1428,10 +1429,10 @@ static int ip6_tnl_init_net(struct net *net) if (!ip6n->fb_tnl_dev) goto err_alloc_dev; - - ip6n->fb_tnl_dev->init = ip6_fb_tnl_dev_init; dev_net_set(ip6n->fb_tnl_dev, net); + ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); + err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index c491fb98a5e3..dfba9fd0c248 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -224,7 +224,7 @@ static struct file_operations ip6mr_vif_fops = { .open = ip6mr_vif_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) @@ -337,7 +337,7 @@ static struct file_operations ip6mr_mfc_fops = { .open = ipmr_mfc_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; #endif @@ -416,12 +416,16 @@ static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) return 0; } +static const struct net_device_ops reg_vif_netdev_ops = { + .ndo_start_xmit = reg_vif_xmit, +}; + static void reg_vif_setup(struct net_device *dev) { dev->type = ARPHRD_PIMREG; dev->mtu = 1500 - sizeof(struct ipv6hdr) - 8; dev->flags = IFF_NOARP; - dev->hard_start_xmit = reg_vif_xmit; + dev->netdev_ops = ®_vif_netdev_ops; dev->destructor = free_netdev; } @@ -980,14 +984,15 @@ int __init ip6_mr_init(void) goto proc_cache_fail; #endif return 0; -reg_notif_fail: - kmem_cache_destroy(mrt_cachep); #ifdef CONFIG_PROC_FS -proc_vif_fail: - unregister_netdevice_notifier(&ip6_mr_notifier); proc_cache_fail: proc_net_remove(&init_net, "ip6_mr_vif"); +proc_vif_fail: + unregister_netdevice_notifier(&ip6_mr_notifier); #endif +reg_notif_fail: + del_timer(&ipmr_expire_timer); + kmem_cache_destroy(mrt_cachep); return err; } diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index d4576a9c154f..3a0b3be7ece5 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -63,7 +63,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; spi = htonl(ntohs(ipcomph->cpi)); - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6); + x = xfrm_state_lookup(&init_net, (xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6); if (!x) return; @@ -76,7 +76,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) { struct xfrm_state *t = NULL; - t = xfrm_state_alloc(); + t = xfrm_state_alloc(&init_net); if (!t) goto out; @@ -114,7 +114,7 @@ static int ipcomp6_tunnel_attach(struct xfrm_state *x) spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&x->props.saddr); if (spi) - t = xfrm_state_lookup((xfrm_address_t *)&x->id.daddr, + t = xfrm_state_lookup(&init_net, (xfrm_address_t *)&x->id.daddr, spi, IPPROTO_IPV6, AF_INET6); if (!t) { t = ipcomp6_tunnel_create(x); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 4e5eac301f91..2aa294be0c79 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -366,11 +366,16 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, } /* routing header option needs extra check */ + retv = -EINVAL; if (optname == IPV6_RTHDR && opt && opt->srcrt) { struct ipv6_rt_hdr *rthdr = opt->srcrt; switch (rthdr->type) { #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) case IPV6_SRCRT_TYPE_2: + if (rthdr->hdrlen != 2 || + rthdr->segments_left != 1) + goto sticky_done; + break; #endif default: diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index a76199ecad23..0f3896032830 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1466,7 +1466,7 @@ static void mld_sendpack(struct sk_buff *skb) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - err = xfrm_lookup(&skb->dst, &fl, NULL, 0); + err = xfrm_lookup(net, &skb->dst, &fl, NULL, 0); if (err) goto err_out; @@ -1817,7 +1817,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) hdr->icmp6_cksum = csum_ipv6_magic(saddr, snd_addr, len, IPPROTO_ICMPV6, - csum_partial((__u8 *) hdr, len, 0)); + csum_partial(hdr, len, 0)); idev = in6_dev_get(skb->dev); @@ -1831,7 +1831,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - err = xfrm_lookup(&skb->dst, &fl, NULL, 0); + err = xfrm_lookup(net, &skb->dst, &fl, NULL, 0); if (err) goto err_out; diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 31295c8f6196..f995e19c87a9 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -205,6 +205,7 @@ static inline int mip6_report_rl_allow(struct timeval *stamp, static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, struct flowi *fl) { + struct net *net = xs_net(x); struct inet6_skb_parm *opt = (struct inet6_skb_parm *)skb->cb; struct ipv6_destopt_hao *hao = NULL; struct xfrm_selector sel; @@ -247,7 +248,7 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, struct sel.sport_mask = htons(~0); sel.ifindex = fl->oif; - err = km_report(IPPROTO_DSTOPTS, &sel, + err = km_report(net, IPPROTO_DSTOPTS, &sel, (hao ? (xfrm_address_t *)&hao->addr : NULL)); out: diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 2a6752dae09d..e4acc212345e 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -437,38 +437,20 @@ static void pndisc_destructor(struct pneigh_entry *n) ipv6_dev_mc_dec(dev, &maddr); } -/* - * Send a Neighbour Advertisement - */ -static void __ndisc_send(struct net_device *dev, - struct neighbour *neigh, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h, const struct in6_addr *target, - int llinfo) +struct sk_buff *ndisc_build_skb(struct net_device *dev, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h, + const struct in6_addr *target, + int llinfo) { - struct flowi fl; - struct dst_entry *dst; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; struct sk_buff *skb; struct icmp6hdr *hdr; - struct inet6_dev *idev; int len; int err; - u8 *opt, type; - - type = icmp6h->icmp6_type; - - icmpv6_flow_init(sk, &fl, type, saddr, daddr, dev->ifindex); - - dst = icmp6_dst_alloc(dev, neigh, daddr); - if (!dst) - return; - - err = xfrm_lookup(&dst, &fl, NULL, 0); - if (err < 0) - return; + u8 *opt; if (!dev->addr_len) llinfo = 0; @@ -485,8 +467,7 @@ static void __ndisc_send(struct net_device *dev, ND_PRINTK0(KERN_ERR "ICMPv6 ND: %s() failed to allocate an skb.\n", __func__); - dst_release(dst); - return; + return NULL; } skb_reserve(skb, LL_RESERVED_SPACE(dev)); @@ -510,9 +491,45 @@ static void __ndisc_send(struct net_device *dev, hdr->icmp6_cksum = csum_ipv6_magic(saddr, daddr, len, IPPROTO_ICMPV6, - csum_partial((__u8 *) hdr, + csum_partial(hdr, len, 0)); + return skb; +} + +EXPORT_SYMBOL(ndisc_build_skb); + +void ndisc_send_skb(struct sk_buff *skb, + struct net_device *dev, + struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h) +{ + struct flowi fl; + struct dst_entry *dst; + struct net *net = dev_net(dev); + struct sock *sk = net->ipv6.ndisc_sk; + struct inet6_dev *idev; + int err; + u8 type; + + type = icmp6h->icmp6_type; + + icmpv6_flow_init(sk, &fl, type, saddr, daddr, dev->ifindex); + + dst = icmp6_dst_alloc(dev, neigh, daddr); + if (!dst) { + kfree_skb(skb); + return; + } + + err = xfrm_lookup(net, &dst, &fl, NULL, 0); + if (err < 0) { + kfree_skb(skb); + return; + } + skb->dst = dst; idev = in6_dev_get(dst->dev); @@ -529,6 +546,27 @@ static void __ndisc_send(struct net_device *dev, in6_dev_put(idev); } +EXPORT_SYMBOL(ndisc_send_skb); + +/* + * Send a Neighbour Discover packet + */ +static void __ndisc_send(struct net_device *dev, + struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h, const struct in6_addr *target, + int llinfo) +{ + struct sk_buff *skb; + + skb = ndisc_build_skb(dev, daddr, saddr, icmp6h, target, llinfo); + if (!skb) + return; + + ndisc_send_skb(skb, dev, neigh, daddr, saddr, icmp6h); +} + static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, @@ -1486,7 +1524,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, if (dst == NULL) return; - err = xfrm_lookup(&dst, &fl, NULL, 0); + err = xfrm_lookup(net, &dst, &fl, NULL, 0); if (err) return; @@ -1574,7 +1612,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, icmph->icmp6_cksum = csum_ipv6_magic(&saddr_buf, &ipv6_hdr(skb)->saddr, len, IPPROTO_ICMPV6, - csum_partial((u8 *) icmph, len, 0)); + csum_partial(icmph, len, 0)); buff->dst = dst; idev = in6_dev_get(dst->dev); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 0b88c5632793..834cea69fb53 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -29,7 +29,7 @@ int ip6_route_me_harder(struct sk_buff *skb) #ifdef CONFIG_XFRM if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && xfrm_decode_session(skb, &fl, AF_INET6) == 0) - if (xfrm_lookup(&skb->dst, &fl, skb->sk, 0)) + if (xfrm_lookup(net, &skb->dst, &fl, skb->sk, 0)) return -1; #endif diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 0981b4ccb8b1..5a2d0a41694a 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -97,7 +97,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) dst = ip6_route_output(net, NULL, &fl); if (dst == NULL) return; - if (dst->error || xfrm_lookup(&dst, &fl, NULL, 0)) + if (dst->error || xfrm_lookup(net, &dst, &fl, NULL, 0)) return; hh_len = (dst->dev->hard_header_len + 15)&~15; diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 07f0b76e7427..97c17fdd6f75 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -132,7 +132,7 @@ static struct snmp_mib snmp6_udplite6_list[] = { static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib) { - static char name[32]; + char name[32]; int i; /* print by name -- deprecated items */ @@ -144,7 +144,7 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib) p = icmp6type2name[icmptype]; if (!p) /* don't print un-named types here */ continue; - (void) snprintf(name, sizeof(name)-1, "Icmp6%s%s", + snprintf(name, sizeof(name), "Icmp6%s%s", i & 0x100 ? "Out" : "In", p); seq_printf(seq, "%-32s\t%lu\n", name, snmp_fold_field(mib, i)); @@ -157,7 +157,7 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib) val = snmp_fold_field(mib, i); if (!val) continue; - (void) snprintf(name, sizeof(name)-1, "Icmp6%sType%u", + snprintf(name, sizeof(name), "Icmp6%sType%u", i & 0x100 ? "Out" : "In", i & 0xff); seq_printf(seq, "%-32s\t%lu\n", name, val); } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 2ba04d41dc25..61f6827e5906 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -860,7 +860,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) { + err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); + if (err < 0) { if (err == -EREMOTE) err = ip6_dst_blackhole(sk, &dst, &fl); if (err < 0) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4d40dc214b2d..9da1ece466a2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -108,7 +108,6 @@ static struct dst_ops ip6_dst_ops_template = { .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, .local_out = __ip6_local_out, - .entry_size = sizeof(struct rt6_info), .entries = ATOMIC_INIT(0), }; @@ -122,7 +121,6 @@ static struct dst_ops ip6_dst_blackhole_ops = { .destroy = ip6_dst_destroy, .check = ip6_dst_check, .update_pmtu = ip6_rt_blackhole_update_pmtu, - .entry_size = sizeof(struct rt6_info), .entries = ATOMIC_INIT(0), }; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b7a50e968506..d3467e563f02 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -62,8 +62,8 @@ #define HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) -static int ipip6_fb_tunnel_init(struct net_device *dev); -static int ipip6_tunnel_init(struct net_device *dev); +static void ipip6_fb_tunnel_init(struct net_device *dev); +static void ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); static int sit_net_id; @@ -188,7 +188,8 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, } nt = netdev_priv(dev); - dev->init = ipip6_tunnel_init; + ipip6_tunnel_init(dev); + nt->parms = *parms; if (parms->i_flags & SIT_ISATAP) @@ -926,13 +927,17 @@ static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu) return 0; } +static const struct net_device_ops ipip6_netdev_ops = { + .ndo_uninit = ipip6_tunnel_uninit, + .ndo_start_xmit = ipip6_tunnel_xmit, + .ndo_do_ioctl = ipip6_tunnel_ioctl, + .ndo_change_mtu = ipip6_tunnel_change_mtu, +}; + static void ipip6_tunnel_setup(struct net_device *dev) { - dev->uninit = ipip6_tunnel_uninit; + dev->netdev_ops = &ipip6_netdev_ops; dev->destructor = free_netdev; - dev->hard_start_xmit = ipip6_tunnel_xmit; - dev->do_ioctl = ipip6_tunnel_ioctl; - dev->change_mtu = ipip6_tunnel_change_mtu; dev->type = ARPHRD_SIT; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); @@ -943,11 +948,9 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; } -static int ipip6_tunnel_init(struct net_device *dev) +static void ipip6_tunnel_init(struct net_device *dev) { - struct ip_tunnel *tunnel; - - tunnel = netdev_priv(dev); + struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->dev = dev; strcpy(tunnel->parms.name, dev->name); @@ -956,11 +959,9 @@ static int ipip6_tunnel_init(struct net_device *dev) memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); ipip6_tunnel_bind_dev(dev); - - return 0; } -static int ipip6_fb_tunnel_init(struct net_device *dev) +static void ipip6_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -977,7 +978,6 @@ static int ipip6_fb_tunnel_init(struct net_device *dev) dev_hold(dev); sitn->tunnels_wc[0] = tunnel; - return 0; } static struct xfrm_tunnel sit_handler = { @@ -1025,16 +1025,17 @@ static int sit_init_net(struct net *net) err = -ENOMEM; goto err_alloc_dev; } - - sitn->fb_tunnel_dev->init = ipip6_fb_tunnel_init; dev_net_set(sitn->fb_tunnel_dev, net); + ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); + if ((err = register_netdev(sitn->fb_tunnel_dev))) goto err_reg_dev; return 0; err_reg_dev: + dev_put(sitn->fb_tunnel_dev); free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: /* nothing */ diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 676c80b5b14b..711175e0571f 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -259,7 +259,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0) + if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) goto out_free; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 984276463a8d..8702b06cb60a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -260,7 +260,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) { + err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); + if (err < 0) { if (err == -EREMOTE) err = ip6_dst_blackhole(sk, &dst, &fl); if (err < 0) @@ -390,7 +391,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out; } - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { + if ((err = xfrm_lookup(net, &dst, &fl, sk, 0)) < 0) { sk->sk_err_soft = -err; goto out; } @@ -492,7 +493,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) goto done; if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) goto done; skb = tcp_make_synack(sk, dst, req); @@ -501,7 +502,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) th->check = tcp_v6_check(th, skb->len, &treq->loc_addr, &treq->rmt_addr, - csum_partial((char *)th, skb->len, skb->csum)); + csum_partial(th, skb->len, skb->csum)); ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); err = ip6_xmit(sk, skb, &fl, opt, 0); @@ -915,7 +916,7 @@ static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) skb->csum_offset = offsetof(struct tcphdr, check); } else { th->check = csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, - csum_partial((char *)th, th->doff<<2, + csum_partial(th, th->doff<<2, skb->csum)); } } @@ -997,7 +998,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, } #endif - buff->csum = csum_partial((char *)t1, tot_len, 0); + buff->csum = csum_partial(t1, tot_len, 0); memset(&fl, 0, sizeof(fl)); ipv6_addr_copy(&fl.fl6_dst, &ipv6_hdr(skb)->saddr); @@ -1018,7 +1019,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, * namespace */ if (!ip6_dst_lookup(ctl_sk, &buff->dst, &fl)) { - if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) { + if (xfrm_lookup(net, &buff->dst, &fl, NULL, 0) >= 0) { ip6_xmit(ctl_sk, buff, &fl, NULL, 0); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); if (rst) @@ -1316,7 +1317,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0) + if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) goto out; } @@ -1829,7 +1830,7 @@ static int tcp_v6_init_sock(struct sock *sk) sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; - atomic_inc(&tcp_sockets_allocated); + percpu_counter_inc(&tcp_sockets_allocated); return 0; } @@ -2043,6 +2044,7 @@ struct proto tcpv6_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), + .slab_flags = SLAB_DESTROY_BY_RCU, .twsk_prot = &tcp6_timewait_sock_ops, .rsk_prot = &tcp6_request_sock_ops, .h.hashinfo = &tcp_hashinfo, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 32d914db6c4f..38390dd19636 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -98,7 +98,7 @@ static struct sock *__udp6_lib_lookup(struct net *net, int dif, struct udp_table *udptable) { struct sock *sk, *result; - struct hlist_node *node, *next; + struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash = udp_hashfn(net, hnum); struct udp_hslot *hslot = &udptable->hash[hash]; @@ -108,19 +108,21 @@ static struct sock *__udp6_lib_lookup(struct net *net, begin: result = NULL; badness = -1; - sk_for_each_rcu_safenext(sk, node, &hslot->head, next) { - /* - * lockless reader, and SLAB_DESTROY_BY_RCU items: - * We must check this item was not moved to another chain - */ - if (udp_hashfn(net, sk->sk_hash) != hash) - goto begin; + sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; } } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != hash) + goto begin; + if (result) { if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; @@ -165,6 +167,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, int peeked; int err; int is_udplite = IS_UDPLITE(sk); + int is_udp4; if (addr_len) *addr_len=sizeof(struct sockaddr_in6); @@ -185,6 +188,8 @@ try_again: else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; + is_udp4 = (skb->protocol == htons(ETH_P_IP)); + /* * If checksum is needed at all, try to do it while copying the * data. If the data is truncated, or if we only want a partial @@ -207,9 +212,14 @@ try_again: if (err) goto out_free; - if (!peeked) - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_INDATAGRAMS, is_udplite); + if (!peeked) { + if (is_udp4) + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); + else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); + } sock_recv_timestamp(msg, sk, skb); @@ -223,7 +233,7 @@ try_again: sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = 0; - if (skb->protocol == htons(ETH_P_IP)) + if (is_udp4) ipv6_addr_set(&sin6->sin6_addr, 0, 0, htonl(0xffff), ip_hdr(skb)->saddr); else { @@ -234,7 +244,7 @@ try_again: } } - if (skb->protocol == htons(ETH_P_IP)) { + if (is_udp4) { if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); } else { @@ -255,8 +265,14 @@ out: csum_copy_err: lock_sock(sk); - if (!skb_kill_datagram(sk, skb, flags)) - UDP6_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + if (!skb_kill_datagram(sk, skb, flags)) { + if (is_udp4) + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, is_udplite); + else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, is_udplite); + } release_sock(sk); if (flags & MSG_DONTWAIT) @@ -355,19 +371,19 @@ drop: return -1; } -static struct sock *udp_v6_mcast_next(struct sock *sk, +static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, __be16 loc_port, struct in6_addr *loc_addr, __be16 rmt_port, struct in6_addr *rmt_addr, int dif) { - struct hlist_node *node; + struct hlist_nulls_node *node; struct sock *s = sk; unsigned short num = ntohs(loc_port); - sk_for_each_from(s, node) { + sk_nulls_for_each_from(s, node) { struct inet_sock *inet = inet_sk(s); - if (sock_net(s) != sock_net(sk)) + if (!net_eq(sock_net(s), net)) continue; if (s->sk_hash == num && s->sk_family == PF_INET6) { @@ -409,16 +425,16 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, int dif; spin_lock(&hslot->lock); - sk = sk_head(&hslot->head); + sk = sk_nulls_head(&hslot->head); dif = inet6_iif(skb); - sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif); + sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); if (!sk) { kfree_skb(skb); goto out; } sk2 = sk; - while ((sk2 = udp_v6_mcast_next(sk_next(sk2), uh->dest, daddr, + while ((sk2 = udp_v6_mcast_next(net, sk_nulls_next(sk2), uh->dest, daddr, uh->source, saddr, dif))) { struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC); if (buff) { @@ -833,7 +849,8 @@ do_udp_sendmsg: if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) { + err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); + if (err < 0) { if (err == -EREMOTE) err = ip6_dst_blackhole(sk, &dst, &fl); if (err < 0) diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index a71c7ddcb41e..9084582d236b 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -58,6 +58,7 @@ EXPORT_SYMBOL(xfrm6_rcv); int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto) { + struct net *net = dev_net(skb->dev); struct xfrm_state *x = NULL; int i = 0; @@ -67,7 +68,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, sp = secpath_dup(skb->sp); if (!sp) { - XFRM_INC_STATS(LINUX_MIB_XFRMINERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); goto drop; } if (skb->sp) @@ -76,7 +77,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, } if (1 + skb->sp->len == XFRM_MAX_DEPTH) { - XFRM_INC_STATS(LINUX_MIB_XFRMINBUFFERERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto drop; } @@ -100,7 +101,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, break; } - x = xfrm_state_lookup_byaddr(dst, src, proto, AF_INET6); + x = xfrm_state_lookup_byaddr(net, dst, src, proto, AF_INET6); if (!x) continue; @@ -122,7 +123,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, } if (!x) { - XFRM_INC_STATS(LINUX_MIB_XFRMINNOSTATES); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); xfrm_audit_state_notfound_simple(skb, AF_INET6); goto drop; } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 604bc0a96c05..97ab068e8ccc 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -27,7 +27,8 @@ static struct dst_ops xfrm6_dst_ops; static struct xfrm_policy_afinfo xfrm6_policy_afinfo; -static struct dst_entry *xfrm6_dst_lookup(int tos, xfrm_address_t *saddr, +static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, + xfrm_address_t *saddr, xfrm_address_t *daddr) { struct flowi fl = {}; @@ -38,7 +39,7 @@ static struct dst_entry *xfrm6_dst_lookup(int tos, xfrm_address_t *saddr, if (saddr) memcpy(&fl.fl6_src, saddr, sizeof(fl.fl6_src)); - dst = ip6_route_output(&init_net, NULL, &fl); + dst = ip6_route_output(net, NULL, &fl); err = dst->error; if (dst->error) { @@ -49,12 +50,13 @@ static struct dst_entry *xfrm6_dst_lookup(int tos, xfrm_address_t *saddr, return dst; } -static int xfrm6_get_saddr(xfrm_address_t *saddr, xfrm_address_t *daddr) +static int xfrm6_get_saddr(struct net *net, + xfrm_address_t *saddr, xfrm_address_t *daddr) { struct dst_entry *dst; struct net_device *dev; - dst = xfrm6_dst_lookup(0, NULL, daddr); + dst = xfrm6_dst_lookup(net, 0, NULL, daddr); if (IS_ERR(dst)) return -EHOSTUNREACH; @@ -220,7 +222,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) static inline int xfrm6_garbage_collect(struct dst_ops *ops) { - xfrm6_policy_afinfo.garbage_collect(); + xfrm6_policy_afinfo.garbage_collect(&init_net); return (atomic_read(&xfrm6_dst_ops.entries) > xfrm6_dst_ops.gc_thresh*2); } @@ -277,7 +279,6 @@ static struct dst_ops xfrm6_dst_ops = { .ifdown = xfrm6_dst_ifdown, .local_out = __ip6_local_out, .gc_thresh = 1024, - .entry_size = sizeof(struct xfrm_dst), .entries = ATOMIC_INIT(0), }; diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index 89884a4f23aa..0e685b05496e 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -19,8 +19,6 @@ #include <net/ipv6.h> #include <net/addrconf.h> -static struct xfrm_state_afinfo xfrm6_state_afinfo; - static void __xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, struct xfrm_tmpl *tmpl, @@ -34,6 +32,7 @@ __xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, x->sel.dport_mask = htons(0xffff); x->sel.sport = xfrm_flowi_sport(fl); x->sel.sport_mask = htons(0xffff); + x->sel.family = AF_INET6; x->sel.prefixlen_d = 128; x->sel.prefixlen_s = 128; x->sel.proto = fl->proto; |