diff options
author | NeilBrown <neilb@suse.de> | 2012-08-01 12:40:02 +0200 |
---|---|---|
committer | NeilBrown <neilb@suse.de> | 2012-08-01 12:40:02 +0200 |
commit | bb181e2e48f8c85db08c9cb015cbba9618dbf05c (patch) | |
tree | 191bc24dd97bcb174535cc217af082f16da3b43d /net/ipv6 | |
parent | md/RAID1: Add missing case for attempting to repair known bad blocks. (diff) | |
parent | dm raid: move sectors_per_dev calculation (diff) | |
download | linux-bb181e2e48f8c85db08c9cb015cbba9618dbf05c.tar.xz linux-bb181e2e48f8c85db08c9cb015cbba9618dbf05c.zip |
Merge commit 'c039c332f23e794deb6d6f37b9f07ff3b27fb2cf' into md
Pull in pre-requisites for adding raid10 support to dm-raid.
Diffstat (limited to 'net/ipv6')
-rw-r--r-- | net/ipv6/addrconf.c | 21 | ||||
-rw-r--r-- | net/ipv6/ah6.c | 11 | ||||
-rw-r--r-- | net/ipv6/esp6.c | 11 | ||||
-rw-r--r-- | net/ipv6/exthdrs.c | 4 | ||||
-rw-r--r-- | net/ipv6/icmp.c | 23 | ||||
-rw-r--r-- | net/ipv6/inet6_connection_sock.c | 103 | ||||
-rw-r--r-- | net/ipv6/ip6_fib.c | 5 | ||||
-rw-r--r-- | net/ipv6/ip6_input.c | 9 | ||||
-rw-r--r-- | net/ipv6/ip6_output.c | 40 | ||||
-rw-r--r-- | net/ipv6/ip6_tunnel.c | 96 | ||||
-rw-r--r-- | net/ipv6/ip6mr.c | 5 | ||||
-rw-r--r-- | net/ipv6/ipcomp6.c | 11 | ||||
-rw-r--r-- | net/ipv6/mcast.c | 3 | ||||
-rw-r--r-- | net/ipv6/ndisc.c | 129 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 131 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 51 | ||||
-rw-r--r-- | net/ipv6/protocol.c | 8 | ||||
-rw-r--r-- | net/ipv6/raw.c | 11 | ||||
-rw-r--r-- | net/ipv6/route.c | 538 | ||||
-rw-r--r-- | net/ipv6/sit.c | 25 | ||||
-rw-r--r-- | net/ipv6/syncookies.c | 5 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 204 | ||||
-rw-r--r-- | net/ipv6/udp.c | 13 | ||||
-rw-r--r-- | net/ipv6/xfrm6_policy.c | 26 |
24 files changed, 717 insertions, 766 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8f6411c97189..79181819a24f 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -63,6 +63,7 @@ #include <linux/delay.h> #include <linux/notifier.h> #include <linux/string.h> +#include <linux/hash.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -579,15 +580,9 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) list_add_tail(&ifp->if_list, p); } -static u32 ipv6_addr_hash(const struct in6_addr *addr) +static u32 inet6_addr_hash(const struct in6_addr *addr) { - /* - * We perform the hash function over the last 64 bits of the address - * This will include the IEEE address token on links that support it. - */ - return jhash_2words((__force u32)addr->s6_addr32[2], - (__force u32)addr->s6_addr32[3], 0) - & (IN6_ADDR_HSIZE - 1); + return hash_32(ipv6_addr_hash(addr), IN6_ADDR_HSIZE_SHIFT); } /* On success it returns ifp with increased reference count */ @@ -662,7 +657,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, in6_ifa_hold(ifa); /* Add to big hash table */ - hash = ipv6_addr_hash(addr); + hash = inet6_addr_hash(addr); hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); spin_unlock(&addrconf_hash_lock); @@ -1270,7 +1265,7 @@ int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, { struct inet6_ifaddr *ifp; struct hlist_node *node; - unsigned int hash = ipv6_addr_hash(addr); + unsigned int hash = inet6_addr_hash(addr); rcu_read_lock_bh(); hlist_for_each_entry_rcu(ifp, node, &inet6_addr_lst[hash], addr_lst) { @@ -1293,7 +1288,7 @@ EXPORT_SYMBOL(ipv6_chk_addr); static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, struct net_device *dev) { - unsigned int hash = ipv6_addr_hash(addr); + unsigned int hash = inet6_addr_hash(addr); struct inet6_ifaddr *ifp; struct hlist_node *node; @@ -1336,7 +1331,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add struct net_device *dev, int strict) { struct inet6_ifaddr *ifp, *result = NULL; - unsigned int hash = ipv6_addr_hash(addr); + unsigned int hash = inet6_addr_hash(addr); struct hlist_node *node; rcu_read_lock_bh(); @@ -3223,7 +3218,7 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) int ret = 0; struct inet6_ifaddr *ifp = NULL; struct hlist_node *n; - unsigned int hash = ipv6_addr_hash(addr); + unsigned int hash = inet6_addr_hash(addr); rcu_read_lock_bh(); hlist_for_each_entry_rcu_bh(ifp, n, &inet6_addr_lst[hash], addr_lst) { diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index f1a4a2c28ed3..7e6139508ee7 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -35,6 +35,7 @@ #include <linux/pfkeyv2.h> #include <linux/string.h> #include <linux/scatterlist.h> +#include <net/ip6_route.h> #include <net/icmp.h> #include <net/ipv6.h> #include <net/protocol.h> @@ -612,16 +613,18 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct xfrm_state *x; if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG) + type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) return; x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); if (!x) return; - NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/%pI6\n", - ntohl(ah->spi), &iph->daddr); - + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index db1521fcda5b..6dc7fd353ef5 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -39,6 +39,7 @@ #include <linux/random.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <net/ip6_route.h> #include <net/icmp.h> #include <net/ipv6.h> #include <net/protocol.h> @@ -433,15 +434,19 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct xfrm_state *x; if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG) + type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) return; x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); if (!x) return; - pr_debug("pmtu discovery on SA ESP/%08x/%pI6\n", - ntohl(esph->spi), &iph->daddr); + + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 6447dc49429f..fa3d9c328092 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -791,14 +791,14 @@ static int ipv6_renew_option(void *ohdr, if (ohdr) { memcpy(*p, ohdr, ipv6_optlen((struct ipv6_opt_hdr *)ohdr)); *hdr = (struct ipv6_opt_hdr *)*p; - *p += CMSG_ALIGN(ipv6_optlen(*(struct ipv6_opt_hdr **)hdr)); + *p += CMSG_ALIGN(ipv6_optlen(*hdr)); } } else { if (newopt) { if (copy_from_user(*p, newopt, newoptlen)) return -EFAULT; *hdr = (struct ipv6_opt_hdr *)*p; - if (ipv6_optlen(*(struct ipv6_opt_hdr **)hdr) > newoptlen) + if (ipv6_optlen(*hdr) > newoptlen) return -EINVAL; *p += CMSG_ALIGN(newoptlen); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 091a2971c7b7..24d69dbca4d6 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -188,14 +188,16 @@ static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type, } else { struct rt6_info *rt = (struct rt6_info *)dst; int tmo = net->ipv6.sysctl.icmpv6_time; + struct inet_peer *peer; /* Give more bandwidth to wider prefixes. */ if (rt->rt6i_dst.plen < 128) tmo >>= ((128 - rt->rt6i_dst.plen)>>5); - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - res = inet_peer_xrlim_allow(rt->rt6i_peer, tmo); + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + res = inet_peer_xrlim_allow(peer, tmo); + if (peer) + inet_putpeer(peer); } dst_release(dst); return res; @@ -596,13 +598,12 @@ out: icmpv6_xmit_unlock(sk); } -static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) +void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { const struct inet6_protocol *ipprot; int inner_offset; - int hash; - u8 nexthdr; __be16 frag_off; + u8 nexthdr; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return; @@ -629,10 +630,8 @@ static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) --ANK (980726) */ - hash = nexthdr & (MAX_INET_PROTOS - 1); - rcu_read_lock(); - ipprot = rcu_dereference(inet6_protos[hash]); + ipprot = rcu_dereference(inet6_protos[nexthdr]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, NULL, type, code, inner_offset, info); rcu_read_unlock(); @@ -649,7 +648,6 @@ static int icmpv6_rcv(struct sk_buff *skb) struct net_device *dev = skb->dev; struct inet6_dev *idev = __in6_dev_get(dev); const struct in6_addr *saddr, *daddr; - const struct ipv6hdr *orig_hdr; struct icmp6hdr *hdr; u8 type; @@ -661,7 +659,7 @@ static int icmpv6_rcv(struct sk_buff *skb) XFRM_STATE_ICMP)) goto drop_no_count; - if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(*orig_hdr))) + if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr))) goto drop_no_count; nh = skb_network_offset(skb); @@ -722,9 +720,6 @@ static int icmpv6_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto discard_it; hdr = icmp6_hdr(skb); - orig_hdr = (struct ipv6hdr *) (hdr + 1); - rt6_pmtu_discovery(&orig_hdr->daddr, &orig_hdr->saddr, dev, - ntohl(hdr->icmp6_mtu)); /* * Drop through to notify diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index e6cee5292a0b..0251a6005be8 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -55,26 +55,26 @@ int inet6_csk_bind_conflict(const struct sock *sk, EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict); struct dst_entry *inet6_csk_route_req(struct sock *sk, + struct flowi6 *fl6, const struct request_sock *req) { struct inet6_request_sock *treq = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *final_p, final; struct dst_entry *dst; - struct flowi6 fl6; - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_TCP; - fl6.daddr = treq->rmt_addr; - final_p = fl6_update_dst(&fl6, np->opt, &final); - fl6.saddr = treq->loc_addr; - fl6.flowi6_oif = sk->sk_bound_dev_if; - fl6.flowi6_mark = sk->sk_mark; - fl6.fl6_dport = inet_rsk(req)->rmt_port; - fl6.fl6_sport = inet_rsk(req)->loc_port; - security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + memset(fl6, 0, sizeof(*fl6)); + fl6->flowi6_proto = IPPROTO_TCP; + fl6->daddr = treq->rmt_addr; + final_p = fl6_update_dst(fl6, np->opt, &final); + fl6->saddr = treq->loc_addr; + fl6->flowi6_oif = treq->iif; + fl6->flowi6_mark = sk->sk_mark; + fl6->fl6_dport = inet_rsk(req)->rmt_port; + fl6->fl6_sport = inet_rsk(req)->loc_port; + security_req_classify_flow(req, flowi6_to_flowi(fl6)); + + dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); if (IS_ERR(dst)) return NULL; @@ -171,7 +171,8 @@ EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr); static inline void __inet6_csk_dst_store(struct sock *sk, struct dst_entry *dst, - struct in6_addr *daddr, struct in6_addr *saddr) + const struct in6_addr *daddr, + const struct in6_addr *saddr) { __ip6_dst_store(sk, dst, daddr, saddr); @@ -203,43 +204,52 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) return dst; } -int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) +static struct dst_entry *inet6_csk_route_socket(struct sock *sk, + struct flowi6 *fl6) { - struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct flowi6 fl6; - struct dst_entry *dst; struct in6_addr *final_p, final; - int res; + struct dst_entry *dst; - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = sk->sk_protocol; - fl6.daddr = np->daddr; - fl6.saddr = np->saddr; - fl6.flowlabel = np->flow_label; - IP6_ECN_flow_xmit(sk, fl6.flowlabel); - fl6.flowi6_oif = sk->sk_bound_dev_if; - fl6.flowi6_mark = sk->sk_mark; - fl6.fl6_sport = inet->inet_sport; - fl6.fl6_dport = inet->inet_dport; - security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + memset(fl6, 0, sizeof(*fl6)); + fl6->flowi6_proto = sk->sk_protocol; + fl6->daddr = np->daddr; + fl6->saddr = np->saddr; + fl6->flowlabel = np->flow_label; + IP6_ECN_flow_xmit(sk, fl6->flowlabel); + fl6->flowi6_oif = sk->sk_bound_dev_if; + fl6->flowi6_mark = sk->sk_mark; + fl6->fl6_sport = inet->inet_sport; + fl6->fl6_dport = inet->inet_dport; + security_sk_classify_flow(sk, flowi6_to_flowi(fl6)); - final_p = fl6_update_dst(&fl6, np->opt, &final); + final_p = fl6_update_dst(fl6, np->opt, &final); dst = __inet6_csk_dst_check(sk, np->dst_cookie); + if (!dst) { + dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); - if (dst == NULL) { - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + if (!IS_ERR(dst)) + __inet6_csk_dst_store(sk, dst, NULL, NULL); + } + return dst; +} - if (IS_ERR(dst)) { - sk->sk_err_soft = -PTR_ERR(dst); - sk->sk_route_caps = 0; - kfree_skb(skb); - return PTR_ERR(dst); - } +int inet6_csk_xmit(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; + int res; - __inet6_csk_dst_store(sk, dst, NULL, NULL); + dst = inet6_csk_route_socket(sk, &fl6); + if (IS_ERR(dst)) { + sk->sk_err_soft = -PTR_ERR(dst); + sk->sk_route_caps = 0; + kfree_skb(skb); + return PTR_ERR(dst); } rcu_read_lock(); @@ -253,3 +263,16 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) return res; } EXPORT_SYMBOL_GPL(inet6_csk_xmit); + +struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) +{ + struct flowi6 fl6; + struct dst_entry *dst = inet6_csk_route_socket(sk, &fl6); + + if (IS_ERR(dst)) + return NULL; + dst->ops->update_pmtu(dst, sk, NULL, mtu); + + return inet6_csk_route_socket(sk, &fl6); +} +EXPORT_SYMBOL_GPL(inet6_csk_update_pmtu); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 608327661960..13690d650c3e 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -197,6 +197,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) table->tb6_id = id; table->tb6_root.leaf = net->ipv6.ip6_null_entry; table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; + inet_peer_base_init(&table->tb6_peers); } return table; @@ -1633,6 +1634,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; + inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl), @@ -1643,6 +1645,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; + inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); #endif fib6_tables_init(net); @@ -1666,8 +1669,10 @@ static void fib6_net_exit(struct net *net) del_timer_sync(&net->ipv6.ip6_fib_timer); #ifdef CONFIG_IPV6_MULTIPLE_TABLES + inetpeer_invalidate_tree(&net->ipv6.fib6_local_tbl->tb6_peers); kfree(net->ipv6.fib6_local_tbl); #endif + inetpeer_invalidate_tree(&net->ipv6.fib6_main_tbl->tb6_peers); kfree(net->ipv6.fib6_main_tbl); kfree(net->ipv6.fib_table_hash); kfree(net->ipv6.rt6_stats); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 21a15dfe4a9e..5ab923e51af3 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -168,13 +168,12 @@ drop: static int ip6_input_finish(struct sk_buff *skb) { + struct net *net = dev_net(skb_dst(skb)->dev); const struct inet6_protocol *ipprot; + struct inet6_dev *idev; unsigned int nhoff; int nexthdr; bool raw; - u8 hash; - struct inet6_dev *idev; - struct net *net = dev_net(skb_dst(skb)->dev); /* * Parse extension headers @@ -189,9 +188,7 @@ resubmit: nexthdr = skb_network_header(skb)[nhoff]; raw = raw6_local_deliver(skb, nexthdr); - - hash = nexthdr & (MAX_INET_PROTOS - 1); - if ((ipprot = rcu_dereference(inet6_protos[hash])) != NULL) { + if ((ipprot = rcu_dereference(inet6_protos[nexthdr])) != NULL) { int ret; if (ipprot->flags & INET6_PROTO_FINAL) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index decc21d19c53..5b2d63ed793e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -83,24 +83,12 @@ int ip6_local_out(struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ip6_local_out); -/* dev_loopback_xmit for use with netfilter. */ -static int ip6_dev_loopback_xmit(struct sk_buff *newskb) -{ - skb_reset_mac_header(newskb); - __skb_pull(newskb, skb_network_offset(newskb)); - newskb->pkt_type = PACKET_LOOPBACK; - newskb->ip_summed = CHECKSUM_UNNECESSARY; - WARN_ON(!skb_dst(newskb)); - - netif_rx_ni(newskb); - return 0; -} - static int ip6_finish_output2(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct neighbour *neigh; + struct rt6_info *rt; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; @@ -121,7 +109,7 @@ static int ip6_finish_output2(struct sk_buff *skb) if (newskb) NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, newskb, NULL, newskb->dev, - ip6_dev_loopback_xmit); + dev_loopback_xmit); if (ipv6_hdr(skb)->hop_limit == 0) { IP6_INC_STATS(dev_net(dev), idev, @@ -136,9 +124,10 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_lock(); - neigh = dst_get_neighbour_noref(dst); + rt = (struct rt6_info *) dst; + neigh = rt->n; if (neigh) { - int res = neigh_output(neigh, skb); + int res = dst_neigh_output(dst, neigh, skb); rcu_read_unlock(); return res; @@ -463,6 +452,7 @@ int ip6_forward(struct sk_buff *skb) */ if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; + struct inet_peer *peer; struct rt6_info *rt; /* @@ -476,14 +466,15 @@ int ip6_forward(struct sk_buff *skb) else target = &hdr->daddr; - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ - if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) + if (inet_peer_xrlim_allow(peer, 1*HZ)) ndisc_send_redirect(skb, target); + if (peer) + inet_putpeer(peer); } else { int addrtype = ipv6_addr_type(&hdr->saddr); @@ -604,12 +595,13 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) if (rt && !(rt->dst.flags & DST_NOPEER)) { struct inet_peer *peer; + struct net *net; - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - peer = rt->rt6i_peer; + 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; } } @@ -960,6 +952,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, struct net *net = sock_net(sk); #ifdef CONFIG_IPV6_OPTIMISTIC_DAD struct neighbour *n; + struct rt6_info *rt; #endif int err; @@ -988,7 +981,8 @@ static int ip6_dst_lookup_tail(struct sock *sk, * dst entry of the nexthop router */ rcu_read_lock(); - n = dst_get_neighbour_noref(*dst); + rt = (struct rt6_info *) *dst; + n = rt->n; if (n && !(n->nud_state & NUD_VALID)) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index c9015fad8d65..9a1d5fe6aef8 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -40,6 +40,7 @@ #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> #include <linux/slab.h> +#include <linux/hash.h> #include <asm/uaccess.h> #include <linux/atomic.h> @@ -70,11 +71,15 @@ MODULE_ALIAS_NETDEV("ip6tnl0"); #define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) #define IPV6_TCLASS_SHIFT 20 -#define HASH_SIZE 32 +#define HASH_SIZE_SHIFT 5 +#define HASH_SIZE (1 << HASH_SIZE_SHIFT) -#define HASH(addr) ((__force u32)((addr)->s6_addr32[0] ^ (addr)->s6_addr32[1] ^ \ - (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \ - (HASH_SIZE - 1)) +static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) +{ + u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); + + return hash_32(hash, HASH_SIZE_SHIFT); +} static int ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); @@ -166,12 +171,11 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) static struct ip6_tnl * ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local) { - unsigned int h0 = HASH(remote); - unsigned int h1 = HASH(local); + unsigned int hash = HASH(remote, local); struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[h0 ^ h1]) { + for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) @@ -205,7 +209,7 @@ ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct ip6_tnl_parm *p) if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { prio = 1; - h = HASH(remote) ^ HASH(local); + h = HASH(remote, local); } return &ip6n->tnls[prio][h]; } @@ -252,7 +256,7 @@ static void ip6_dev_free(struct net_device *dev) } /** - * ip6_tnl_create() - create a new tunnel + * ip6_tnl_create - create a new tunnel * @p: tunnel parameters * @pt: pointer to new tunnel * @@ -550,6 +554,9 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_FRAG_NEEDED; break; + case NDISC_REDIRECT: + rel_type = ICMP_REDIRECT; + rel_code = ICMP_REDIR_HOST; default: return 0; } @@ -606,8 +613,10 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rel_info > dst_mtu(skb_dst(skb2))) goto out; - skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), rel_info); + skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, rel_info); } + if (rel_type == ICMP_REDIRECT) + skb_dst(skb2)->ops->redirect(skb_dst(skb2), NULL, skb2); icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); @@ -684,24 +693,50 @@ static void ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, IP6_ECN_set_ce(ipv6_hdr(skb)); } +static __u32 ip6_tnl_get_cap(struct ip6_tnl *t, + const struct in6_addr *laddr, + const struct in6_addr *raddr) +{ + struct ip6_tnl_parm *p = &t->parms; + int ltype = ipv6_addr_type(laddr); + int rtype = ipv6_addr_type(raddr); + __u32 flags = 0; + + if (ltype == IPV6_ADDR_ANY || rtype == IPV6_ADDR_ANY) { + flags = IP6_TNL_F_CAP_PER_PACKET; + } else if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && + rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && + !((ltype|rtype) & IPV6_ADDR_LOOPBACK) && + (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) { + if (ltype&IPV6_ADDR_UNICAST) + flags |= IP6_TNL_F_CAP_XMIT; + if (rtype&IPV6_ADDR_UNICAST) + flags |= IP6_TNL_F_CAP_RCV; + } + return flags; +} + /* called with rcu_read_lock() */ -static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t) +static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t, + const struct in6_addr *laddr, + const struct in6_addr *raddr) { struct ip6_tnl_parm *p = &t->parms; int ret = 0; struct net *net = dev_net(t->dev); - if (p->flags & IP6_TNL_F_CAP_RCV) { + if ((p->flags & IP6_TNL_F_CAP_RCV) || + ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && + (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_RCV))) { struct net_device *ldev = NULL; if (p->link) ldev = dev_get_by_index_rcu(net, p->link); - if ((ipv6_addr_is_multicast(&p->laddr) || - likely(ipv6_chk_addr(net, &p->laddr, ldev, 0))) && - likely(!ipv6_chk_addr(net, &p->raddr, NULL, 0))) + if ((ipv6_addr_is_multicast(laddr) || + likely(ipv6_chk_addr(net, laddr, ldev, 0))) && + likely(!ipv6_chk_addr(net, raddr, NULL, 0))) ret = 1; - } return ret; } @@ -740,7 +775,7 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, goto discard; } - if (!ip6_tnl_rcv_ctl(t)) { + if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { t->dev->stats.rx_dropped++; rcu_read_unlock(); goto discard; @@ -921,7 +956,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->len > mtu) { *pmtu = mtu; err = -EMSGSIZE; @@ -1114,25 +1149,6 @@ tx_err: return NETDEV_TX_OK; } -static void ip6_tnl_set_cap(struct ip6_tnl *t) -{ - struct ip6_tnl_parm *p = &t->parms; - int ltype = ipv6_addr_type(&p->laddr); - int rtype = ipv6_addr_type(&p->raddr); - - p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV); - - if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && - rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && - !((ltype|rtype) & IPV6_ADDR_LOOPBACK) && - (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) { - if (ltype&IPV6_ADDR_UNICAST) - p->flags |= IP6_TNL_F_CAP_XMIT; - if (rtype&IPV6_ADDR_UNICAST) - p->flags |= IP6_TNL_F_CAP_RCV; - } -} - static void ip6_tnl_link_config(struct ip6_tnl *t) { struct net_device *dev = t->dev; @@ -1153,7 +1169,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL)) fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; - ip6_tnl_set_cap(t); + 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); if (p->flags&IP6_TNL_F_CAP_XMIT && p->flags&IP6_TNL_F_CAP_RCV) dev->flags |= IFF_POINTOPOINT; @@ -1438,6 +1455,9 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) t->parms.proto = IPPROTO_IPV6; dev_hold(dev); + + ip6_tnl_link_config(t); + rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 461e47c8e956..4532973f0dd4 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2104,8 +2104,9 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, if (c->mf6c_parent >= MAXMIFS) return -ENOENT; - if (MIF_EXISTS(mrt, c->mf6c_parent)) - RTA_PUT(skb, RTA_IIF, 4, &mrt->vif6_table[c->mf6c_parent].dev->ifindex); + if (MIF_EXISTS(mrt, c->mf6c_parent) && + nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0) + return -EMSGSIZE; mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0)); diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 5cb75bfe45b1..7af5aee75d98 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -46,6 +46,7 @@ #include <linux/list.h> #include <linux/vmalloc.h> #include <linux/rtnetlink.h> +#include <net/ip6_route.h> #include <net/icmp.h> #include <net/ipv6.h> #include <net/protocol.h> @@ -63,7 +64,9 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, (struct ip_comp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && type != ICMPV6_PKT_TOOBIG) + if (type != ICMPV6_DEST_UNREACH && + type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) return; spi = htonl(ntohs(ipcomph->cpi)); @@ -72,8 +75,10 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!x) return; - pr_debug("pmtu discovery on SA IPCOMP/%08x/%pI6\n", - spi, &iph->daddr); + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 6d0f5dc8e3a6..92f8e48e4ba4 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -211,6 +211,9 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) struct ipv6_mc_socklist __rcu **lnk; struct net *net = sock_net(sk); + if (!ipv6_addr_is_multicast(addr)) + return -EINVAL; + spin_lock(&ipv6_sk_mc_lock); for (lnk = &np->ipv6_mc_list; (mc_lst = rcu_dereference_protected(*lnk, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 54f62d3b8dd6..ff36194a71aa 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -143,40 +143,6 @@ struct neigh_table nd_tbl = { .gc_thresh3 = 1024, }; -/* ND options */ -struct ndisc_options { - struct nd_opt_hdr *nd_opt_array[__ND_OPT_ARRAY_MAX]; -#ifdef CONFIG_IPV6_ROUTE_INFO - struct nd_opt_hdr *nd_opts_ri; - struct nd_opt_hdr *nd_opts_ri_end; -#endif - struct nd_opt_hdr *nd_useropts; - struct nd_opt_hdr *nd_useropts_end; -}; - -#define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] -#define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] -#define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] -#define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] -#define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] -#define nd_opts_mtu nd_opt_array[ND_OPT_MTU] - -#define NDISC_OPT_SPACE(len) (((len)+2+7)&~7) - -/* - * Return the padding between the option length and the start of the - * link addr. Currently only IP-over-InfiniBand needs this, although - * if RFC 3831 IPv6-over-Fibre Channel is ever implemented it may - * also need a pad of 2. - */ -static int ndisc_addr_option_pad(unsigned short type) -{ - switch (type) { - case ARPHRD_INFINIBAND: return 2; - default: return 0; - } -} - static inline int ndisc_opt_addr_space(struct net_device *dev) { return NDISC_OPT_SPACE(dev->addr_len + ndisc_addr_option_pad(dev->type)); @@ -233,8 +199,8 @@ static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur, return cur <= end && ndisc_is_useropt(cur) ? cur : NULL; } -static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, - struct ndisc_options *ndopts) +struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, + struct ndisc_options *ndopts) { struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt; @@ -297,17 +263,6 @@ static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, return ndopts; } -static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, - struct net_device *dev) -{ - u8 *lladdr = (u8 *)(p + 1); - int lladdrlen = p->nd_opt_len << 3; - int prepad = ndisc_addr_option_pad(dev->type); - if (lladdrlen != NDISC_OPT_SPACE(dev->addr_len + prepad)) - return NULL; - return lladdr + prepad; -} - int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir) { switch (dev->type) { @@ -1379,16 +1334,6 @@ out: static void ndisc_redirect_rcv(struct sk_buff *skb) { - struct inet6_dev *in6_dev; - struct icmp6hdr *icmph; - const struct in6_addr *dest; - const struct in6_addr *target; /* new first hop to destination */ - struct neighbour *neigh; - int on_link = 0; - struct ndisc_options ndopts; - int optlen; - u8 *lladdr = NULL; - #ifdef CONFIG_IPV6_NDISC_NODETYPE switch (skb->ndisc_nodetype) { case NDISC_NODETYPE_HOST: @@ -1405,65 +1350,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) return; } - optlen = skb->tail - skb->transport_header; - optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); - - if (optlen < 0) { - ND_PRINTK(2, warn, "Redirect: packet too short\n"); - return; - } - - icmph = icmp6_hdr(skb); - target = (const struct in6_addr *) (icmph + 1); - dest = target + 1; - - if (ipv6_addr_is_multicast(dest)) { - ND_PRINTK(2, warn, - "Redirect: destination address is multicast\n"); - return; - } - - if (ipv6_addr_equal(dest, target)) { - on_link = 1; - } else if (ipv6_addr_type(target) != - (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK(2, warn, - "Redirect: target address is not link-local unicast\n"); - return; - } - - in6_dev = __in6_dev_get(skb->dev); - if (!in6_dev) - return; - if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects) - return; - - /* RFC2461 8.1: - * The IP source address of the Redirect MUST be the same as the current - * first-hop router for the specified ICMP Destination Address. - */ - - if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { - ND_PRINTK(2, warn, "Redirect: invalid ND options\n"); - return; - } - if (ndopts.nd_opts_tgt_lladdr) { - lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, - skb->dev); - if (!lladdr) { - ND_PRINTK(2, warn, - "Redirect: invalid link-layer address length\n"); - return; - } - } - - neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1); - if (neigh) { - rt6_redirect(dest, &ipv6_hdr(skb)->daddr, - &ipv6_hdr(skb)->saddr, neigh, lladdr, - on_link); - neigh_release(neigh); - } + icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) @@ -1472,6 +1359,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; int len = sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); + struct inet_peer *peer; struct sk_buff *buff; struct icmp6hdr *icmph; struct in6_addr saddr_buf; @@ -1485,6 +1373,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) int rd_len; int err; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL; + bool ret; if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n", @@ -1518,9 +1407,11 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) "Redirect: destination is not a neighbour\n"); goto release; } - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - if (!inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + ret = inet_peer_xrlim_allow(peer, 1*HZ); + if (peer) + inet_putpeer(peer); + if (!ret) goto release; if (dev->addr_len) { diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 3224ef90a21a..4794f96cf2e0 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -143,11 +143,11 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, return NF_ACCEPT; } -static unsigned int ipv6_confirm(unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int ipv6_helper(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { struct nf_conn *ct; const struct nf_conn_help *help; @@ -161,15 +161,15 @@ static unsigned int ipv6_confirm(unsigned int hooknum, /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(skb, &ctinfo); if (!ct || ctinfo == IP_CT_RELATED_REPLY) - goto out; + return NF_ACCEPT; help = nfct_help(ct); if (!help) - goto out; + return NF_ACCEPT; /* rcu_read_lock()ed by nf_hook_slow */ helper = rcu_dereference(help->helper); if (!helper) - goto out; + return NF_ACCEPT; protoff = nf_ct_ipv6_skip_exthdr(skb, extoff, &pnum, skb->len - extoff); @@ -179,12 +179,19 @@ static unsigned int ipv6_confirm(unsigned int hooknum, } ret = helper->help(skb, protoff, ct, ctinfo); - if (ret != NF_ACCEPT) { + if (ret != NF_ACCEPT && (ret & NF_VERDICT_MASK) != NF_QUEUE) { nf_log_packet(NFPROTO_IPV6, hooknum, skb, in, out, NULL, "nf_ct_%s: dropping packet", helper->name); - return ret; } -out: + return ret; +} + +static unsigned int ipv6_confirm(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ /* We've seen it coming out the other side: confirm it */ return nf_conntrack_confirm(skb); } @@ -254,6 +261,13 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { .priority = NF_IP6_PRI_CONNTRACK, }, { + .hook = ipv6_helper, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK_HELPER, + }, + { .hook = ipv6_confirm, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, @@ -261,6 +275,13 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { .priority = NF_IP6_PRI_LAST, }, { + .hook = ipv6_helper, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_CONNTRACK_HELPER, + }, + { .hook = ipv6_confirm, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, @@ -333,37 +354,75 @@ MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>"); -static int __init nf_conntrack_l3proto_ipv6_init(void) +static int ipv6_net_init(struct net *net) { int ret = 0; - need_conntrack(); - nf_defrag_ipv6_enable(); - - ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_tcp6); + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_tcp6); if (ret < 0) { - pr_err("nf_conntrack_ipv6: can't register tcp.\n"); - return ret; + printk(KERN_ERR "nf_conntrack_l4proto_tcp6: protocol register failed\n"); + goto out; } - - ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udp6); + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_udp6); if (ret < 0) { - pr_err("nf_conntrack_ipv6: can't register udp.\n"); - goto cleanup_tcp; + printk(KERN_ERR "nf_conntrack_l4proto_udp6: protocol register failed\n"); + goto cleanup_tcp6; } - - ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_icmpv6); + ret = nf_conntrack_l4proto_register(net, + &nf_conntrack_l4proto_icmpv6); if (ret < 0) { - pr_err("nf_conntrack_ipv6: can't register icmpv6.\n"); - goto cleanup_udp; + printk(KERN_ERR "nf_conntrack_l4proto_icmp6: protocol register failed\n"); + goto cleanup_udp6; } - - ret = nf_conntrack_l3proto_register(&nf_conntrack_l3proto_ipv6); + ret = nf_conntrack_l3proto_register(net, + &nf_conntrack_l3proto_ipv6); if (ret < 0) { - pr_err("nf_conntrack_ipv6: can't register ipv6\n"); + printk(KERN_ERR "nf_conntrack_l3proto_ipv6: protocol register failed\n"); goto cleanup_icmpv6; } + return 0; + cleanup_icmpv6: + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_icmpv6); + cleanup_udp6: + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_udp6); + cleanup_tcp6: + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_tcp6); + out: + return ret; +} +static void ipv6_net_exit(struct net *net) +{ + nf_conntrack_l3proto_unregister(net, + &nf_conntrack_l3proto_ipv6); + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_icmpv6); + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_udp6); + nf_conntrack_l4proto_unregister(net, + &nf_conntrack_l4proto_tcp6); +} + +static struct pernet_operations ipv6_net_ops = { + .init = ipv6_net_init, + .exit = ipv6_net_exit, +}; + +static int __init nf_conntrack_l3proto_ipv6_init(void) +{ + int ret = 0; + + need_conntrack(); + nf_defrag_ipv6_enable(); + + ret = register_pernet_subsys(&ipv6_net_ops); + if (ret < 0) + goto cleanup_pernet; ret = nf_register_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); if (ret < 0) { @@ -374,13 +433,8 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) return ret; cleanup_ipv6: - nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv6); - cleanup_icmpv6: - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); - cleanup_udp: - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp6); - cleanup_tcp: - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp6); + unregister_pernet_subsys(&ipv6_net_ops); + cleanup_pernet: return ret; } @@ -388,10 +442,7 @@ static void __exit nf_conntrack_l3proto_ipv6_fini(void) { synchronize_net(); nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); - nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv6); - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp6); - nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp6); + unregister_pernet_subsys(&ipv6_net_ops); } module_init(nf_conntrack_l3proto_ipv6_init); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 3e81904fbbcd..2d54b2061d68 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -29,6 +29,11 @@ static unsigned int nf_ct_icmpv6_timeout __read_mostly = 30*HZ; +static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6; +} + static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct nf_conntrack_tuple *tuple) @@ -90,7 +95,7 @@ static int icmpv6_print_tuple(struct seq_file *s, static unsigned int *icmpv6_get_timeouts(struct net *net) { - return &nf_ct_icmpv6_timeout; + return &icmpv6_pernet(net)->timeout; } /* Returns verdict for packet, or -1 for invalid. */ @@ -281,16 +286,18 @@ static int icmpv6_nlattr_tuple_size(void) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> -static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) { unsigned int *timeout = data; + struct nf_icmp_net *in = icmpv6_pernet(net); if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) { *timeout = ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ; } else { /* Set default ICMPv6 timeout. */ - *timeout = nf_ct_icmpv6_timeout; + *timeout = in->timeout; } return 0; } @@ -315,11 +322,9 @@ icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL -static struct ctl_table_header *icmpv6_sysctl_header; static struct ctl_table icmpv6_sysctl_table[] = { { .procname = "nf_conntrack_icmpv6_timeout", - .data = &nf_ct_icmpv6_timeout, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -328,6 +333,36 @@ static struct ctl_table icmpv6_sysctl_table[] = { }; #endif /* CONFIG_SYSCTL */ +static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct nf_icmp_net *in) +{ +#ifdef CONFIG_SYSCTL + pn->ctl_table = kmemdup(icmpv6_sysctl_table, + sizeof(icmpv6_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &in->timeout; +#endif + return 0; +} + +static int icmpv6_init_net(struct net *net, u_int16_t proto) +{ + struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_proto_net *pn = &in->pn; + + in->timeout = nf_ct_icmpv6_timeout; + + return icmpv6_kmemdup_sysctl_table(pn, in); +} + +static struct nf_proto_net *icmpv6_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6.pn; +} + struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = { .l3proto = PF_INET6, @@ -355,8 +390,6 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = .nla_policy = icmpv6_timeout_nla_policy, }, #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#ifdef CONFIG_SYSCTL - .ctl_table_header = &icmpv6_sysctl_header, - .ctl_table = icmpv6_sysctl_table, -#endif + .init_net = icmpv6_init_net, + .get_net_proto = icmpv6_get_net_proto, }; diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index 9a7978fdc02a..053082dfc93e 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -29,9 +29,7 @@ const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly; int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol) { - int hash = protocol & (MAX_INET_PROTOS - 1); - - return !cmpxchg((const struct inet6_protocol **)&inet6_protos[hash], + return !cmpxchg((const struct inet6_protocol **)&inet6_protos[protocol], NULL, prot) ? 0 : -1; } EXPORT_SYMBOL(inet6_add_protocol); @@ -42,9 +40,9 @@ EXPORT_SYMBOL(inet6_add_protocol); int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol) { - int ret, hash = protocol & (MAX_INET_PROTOS - 1); + int ret; - ret = (cmpxchg((const struct inet6_protocol **)&inet6_protos[hash], + ret = (cmpxchg((const struct inet6_protocol **)&inet6_protos[protocol], prot, NULL) == prot) ? 0 : -1; synchronize_net(); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 93d69836fded..ef0579d5bca6 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -165,7 +165,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; - hash = nexthdr & (MAX_INET_PROTOS - 1); + hash = nexthdr & (RAW_HTABLE_SIZE - 1); read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); @@ -229,7 +229,7 @@ bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) { struct sock *raw_sk; - raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (MAX_INET_PROTOS - 1)]); + raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (RAW_HTABLE_SIZE - 1)]); if (raw_sk && !ipv6_raw_deliver(skb, nexthdr)) raw_sk = NULL; @@ -328,9 +328,12 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, return; harderr = icmpv6_err_convert(type, code, &err); - if (type == ICMPV6_PKT_TOOBIG) + if (type == ICMPV6_PKT_TOOBIG) { + ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); - + } + if (type == NDISC_REDIRECT) + ip6_sk_redirect(skb, sk); if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index becb048d18d4..cf02cb97bbdd 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -78,7 +78,10 @@ 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 void ip6_link_failure(struct sk_buff *skb); -static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu); +static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu); +static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); #ifdef CONFIG_IPV6_ROUTE_INFO static struct rt6_info *rt6_add_route_info(struct net *net, @@ -99,10 +102,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) if (!(rt->dst.flags & DST_HOST)) return NULL; - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - - peer = rt->rt6i_peer; + peer = rt6_get_peer_create(rt); if (peer) { u32 *old_p = __DST_METRICS_PTR(old); unsigned long prev, new; @@ -123,21 +123,27 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) return p; } -static inline const void *choose_neigh_daddr(struct rt6_info *rt, const void *daddr) +static inline const void *choose_neigh_daddr(struct rt6_info *rt, + struct sk_buff *skb, + const void *daddr) { struct in6_addr *p = &rt->rt6i_gateway; if (!ipv6_addr_any(p)) return (const void *) p; + else if (skb) + return &ipv6_hdr(skb)->daddr; return daddr; } -static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, const void *daddr) +static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) { struct rt6_info *rt = (struct rt6_info *) dst; struct neighbour *n; - daddr = choose_neigh_daddr(rt, daddr); + daddr = choose_neigh_daddr(rt, skb, daddr); n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr); if (n) return n; @@ -152,7 +158,7 @@ static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev) if (IS_ERR(n)) return PTR_ERR(n); } - dst_set_neighbour(&rt->dst, n); + rt->n = n; return 0; } @@ -171,6 +177,7 @@ static struct dst_ops ip6_dst_ops_template = { .negative_advice = ip6_negative_advice, .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, + .redirect = rt6_do_redirect, .local_out = __ip6_local_out, .neigh_lookup = ip6_neigh_lookup, }; @@ -182,7 +189,13 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) return mtu ? : dst->dev->mtu; } -static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) +static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) +{ +} + +static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) { } @@ -200,6 +213,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .mtu = ip6_blackhole_mtu, .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, + .redirect = ip6_rt_blackhole_redirect, .cow_metrics = ip6_rt_blackhole_cow_metrics, .neigh_lookup = ip6_neigh_lookup, }; @@ -261,16 +275,20 @@ static struct rt6_info ip6_blk_hole_entry_template = { #endif /* allocate dst with ip6_dst_ops */ -static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops, +static inline struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, - int flags) + int flags, + struct fib6_table *table) { - struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags); + struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, + 0, DST_OBSOLETE_NONE, flags); - if (rt) - memset(&rt->rt6i_table, 0, - sizeof(*rt) - sizeof(struct dst_entry)); + if (rt) { + struct dst_entry *dst = &rt->dst; + memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); + rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); + } return rt; } @@ -278,7 +296,9 @@ static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; - struct inet_peer *peer = rt->rt6i_peer; + + if (rt->n) + neigh_release(rt->n); if (!(rt->dst.flags & DST_HOST)) dst_destroy_metrics_generic(dst); @@ -291,8 +311,8 @@ static void ip6_dst_destroy(struct dst_entry *dst) if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from) dst_release(dst->from); - if (peer) { - rt->rt6i_peer = NULL; + if (rt6_has_peer(rt)) { + struct inet_peer *peer = rt6_peer_ptr(rt); inet_putpeer(peer); } } @@ -306,13 +326,20 @@ static u32 rt6_peer_genid(void) void rt6_bind_peer(struct rt6_info *rt, int create) { + struct inet_peer_base *base; struct inet_peer *peer; - peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create); - if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL) - inet_putpeer(peer); - else - rt->rt6i_peer_genid = rt6_peer_genid(); + base = inetpeer_base_ptr(rt->_rt6i_peer); + if (!base) + return; + + peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create); + if (peer) { + if (!rt6_set_peer(rt, peer)) + inet_putpeer(peer); + else + rt->rt6i_peer_genid = rt6_peer_genid(); + } } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -323,12 +350,19 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, struct net_device *loopback_dev = dev_net(dev)->loopback_dev; - if (dev != loopback_dev && idev && idev->dev == dev) { - struct inet6_dev *loopback_idev = - in6_dev_get(loopback_dev); - if (loopback_idev) { - rt->rt6i_idev = loopback_idev; - in6_dev_put(idev); + if (dev != loopback_dev) { + if (idev && idev->dev == dev) { + struct inet6_dev *loopback_idev = + in6_dev_get(loopback_dev); + if (loopback_idev) { + rt->rt6i_idev = loopback_idev; + in6_dev_put(idev); + } + } + if (rt->n && rt->n->dev == dev) { + rt->n->dev = loopback_dev; + dev_hold(loopback_dev); + dev_put(dev); } } } @@ -418,7 +452,7 @@ static void rt6_probe(struct rt6_info *rt) * to no more than one per minute. */ rcu_read_lock(); - neigh = rt ? dst_get_neighbour_noref(&rt->dst) : NULL; + neigh = rt ? rt->n : NULL; if (!neigh || (neigh->nud_state & NUD_VALID)) goto out; read_lock_bh(&neigh->lock); @@ -465,7 +499,7 @@ static inline int rt6_check_neigh(struct rt6_info *rt) int m; rcu_read_lock(); - neigh = dst_get_neighbour_noref(&rt->dst); + neigh = rt->n; if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) m = 1; @@ -812,7 +846,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, if (rt) { rt->rt6i_flags |= RTF_CACHE; - dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_noref_raw(&ort->dst))); + rt->n = neigh_clone(ort->n); } return rt; } @@ -846,7 +880,7 @@ restart: dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); - if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl6->daddr); @@ -931,6 +965,8 @@ struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk, { int flags = 0; + fl6->flowi6_iif = net->loopback_dev->ifindex; + if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr)) flags |= RT6_LOOKUP_F_IFACE; @@ -949,12 +985,13 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig; struct dst_entry *new = NULL; - rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0); + rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, DST_OBSOLETE_NONE, 0); if (rt) { - memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry)); - new = &rt->dst; + memset(new + 1, 0, sizeof(*rt) - sizeof(*new)); + rt6_init_peer(rt, net->ipv6.peers); + new->__use = 1; new->input = dst_discard; new->output = dst_discard; @@ -996,7 +1033,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) { if (rt->rt6i_peer_genid != rt6_peer_genid()) { - if (!rt->rt6i_peer) + if (!rt6_has_peer(rt)) rt6_bind_peer(rt, 0); rt->rt6i_peer_genid = rt6_peer_genid(); } @@ -1038,11 +1075,15 @@ static void ip6_link_failure(struct sk_buff *skb) } } -static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) +static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { struct rt6_info *rt6 = (struct rt6_info*)dst; + dst_confirm(dst); if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) { + struct net *net = dev_net(dst->dev); + rt6->rt6i_flags |= RTF_MODIFIED; if (mtu < IPV6_MIN_MTU) { u32 features = dst_metric(dst, RTAX_FEATURES); @@ -1051,9 +1092,66 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) dst_metric_set(dst, RTAX_FEATURES, features); } dst_metric_set(dst, RTAX_MTU, mtu); + rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires); } } +void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, + int oif, u32 mark) +{ + const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = oif; + fl6.flowi6_mark = mark; + fl6.flowi6_flags = 0; + fl6.daddr = iph->daddr; + fl6.saddr = iph->saddr; + fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK; + + dst = ip6_route_output(net, NULL, &fl6); + if (!dst->error) + ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu)); + dst_release(dst); +} +EXPORT_SYMBOL_GPL(ip6_update_pmtu); + +void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) +{ + ip6_update_pmtu(skb, sock_net(sk), mtu, + sk->sk_bound_dev_if, sk->sk_mark); +} +EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu); + +void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) +{ + const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = oif; + fl6.flowi6_mark = mark; + fl6.flowi6_flags = 0; + fl6.daddr = iph->daddr; + fl6.saddr = iph->saddr; + fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK; + + dst = ip6_route_output(net, NULL, &fl6); + if (!dst->error) + rt6_do_redirect(dst, NULL, skb); + dst_release(dst); +} +EXPORT_SYMBOL_GPL(ip6_redirect); + +void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) +{ + ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark); +} +EXPORT_SYMBOL_GPL(ip6_sk_redirect); + static unsigned int ip6_default_advmss(const struct dst_entry *dst) { struct net_device *dev = dst->dev; @@ -1110,7 +1208,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, if (unlikely(!idev)) return ERR_PTR(-ENODEV); - rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0); + rt = ip6_dst_alloc(net, dev, 0, NULL); if (unlikely(!rt)) { in6_dev_put(idev); dst = ERR_PTR(-ENOMEM); @@ -1120,7 +1218,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, if (neigh) neigh_hold(neigh); else { - neigh = ip6_neigh_lookup(&rt->dst, &fl6->daddr); + neigh = ip6_neigh_lookup(&rt->dst, NULL, &fl6->daddr); if (IS_ERR(neigh)) { in6_dev_put(idev); dst_free(&rt->dst); @@ -1130,7 +1228,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; - dst_set_neighbour(&rt->dst, neigh); + rt->n = neigh; atomic_set(&rt->dst.__refcnt, 1); rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; @@ -1292,7 +1390,7 @@ int ip6_route_add(struct fib6_config *cfg) if (!table) goto out; - rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT); + rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table); if (!rt) { err = -ENOMEM; @@ -1546,107 +1644,94 @@ static int ip6_route_del(struct fib6_config *cfg) return err; } -/* - * Handle redirects - */ -struct ip6rd_flowi { - struct flowi6 fl6; - struct in6_addr gateway; -}; - -static struct rt6_info *__ip6_route_redirect(struct net *net, - struct fib6_table *table, - struct flowi6 *fl6, - int flags) +static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { - struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; - struct rt6_info *rt; - struct fib6_node *fn; + struct net *net = dev_net(skb->dev); + struct netevent_redirect netevent; + struct rt6_info *rt, *nrt = NULL; + const struct in6_addr *target; + struct ndisc_options ndopts; + const struct in6_addr *dest; + struct neighbour *old_neigh; + struct inet6_dev *in6_dev; + struct neighbour *neigh; + struct icmp6hdr *icmph; + int optlen, on_link; + u8 *lladdr; - /* - * Get the "current" route for this destination and - * check if the redirect has come from approriate router. - * - * RFC 2461 specifies that redirects should only be - * accepted if they come from the nexthop to the target. - * Due to the way the routes are chosen, this notion - * is a bit fuzzy and one might need to check all possible - * routes. - */ + optlen = skb->tail - skb->transport_header; + optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); - read_lock_bh(&table->tb6_lock); - fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); -restart: - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { - /* - * Current route is on-link; redirect is always invalid. - * - * Seems, previous statement is not true. It could - * be node, which looks for us as on-link (f.e. proxy ndisc) - * But then router serving it might decide, that we should - * know truth 8)8) --ANK (980726). - */ - if (rt6_check_expired(rt)) - continue; - if (!(rt->rt6i_flags & RTF_GATEWAY)) - continue; - if (fl6->flowi6_oif != rt->dst.dev->ifindex) - continue; - if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) - continue; - break; + if (optlen < 0) { + net_dbg_ratelimited("rt6_do_redirect: packet too short\n"); + return; } - if (!rt) - rt = net->ipv6.ip6_null_entry; - BACKTRACK(net, &fl6->saddr); -out: - dst_hold(&rt->dst); - - read_unlock_bh(&table->tb6_lock); - - return rt; -}; + icmph = icmp6_hdr(skb); + target = (const struct in6_addr *) (icmph + 1); + dest = target + 1; -static struct rt6_info *ip6_route_redirect(const struct in6_addr *dest, - const struct in6_addr *src, - const struct in6_addr *gateway, - struct net_device *dev) -{ - int flags = RT6_LOOKUP_F_HAS_SADDR; - struct net *net = dev_net(dev); - struct ip6rd_flowi rdfl = { - .fl6 = { - .flowi6_oif = dev->ifindex, - .daddr = *dest, - .saddr = *src, - }, - }; + if (ipv6_addr_is_multicast(dest)) { + net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n"); + return; + } - rdfl.gateway = *gateway; + on_link = 0; + if (ipv6_addr_equal(dest, target)) { + on_link = 1; + } else if (ipv6_addr_type(target) != + (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { + net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n"); + return; + } - if (rt6_need_strict(dest)) - flags |= RT6_LOOKUP_F_IFACE; + in6_dev = __in6_dev_get(skb->dev); + if (!in6_dev) + return; + if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects) + return; - return (struct rt6_info *)fib6_rule_lookup(net, &rdfl.fl6, - flags, __ip6_route_redirect); -} + /* RFC2461 8.1: + * The IP source address of the Redirect MUST be the same as the current + * first-hop router for the specified ICMP Destination Address. + */ -void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, - const struct in6_addr *saddr, - struct neighbour *neigh, u8 *lladdr, int on_link) -{ - struct rt6_info *rt, *nrt = NULL; - struct netevent_redirect netevent; - struct net *net = dev_net(neigh->dev); + if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { + net_dbg_ratelimited("rt6_redirect: invalid ND options\n"); + return; + } - rt = ip6_route_redirect(dest, src, saddr, neigh->dev); + lladdr = NULL; + if (ndopts.nd_opts_tgt_lladdr) { + lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, + skb->dev); + if (!lladdr) { + net_dbg_ratelimited("rt6_redirect: invalid link-layer address length\n"); + return; + } + } + rt = (struct rt6_info *) dst; if (rt == net->ipv6.ip6_null_entry) { net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n"); - goto out; + return; } + /* Redirect received -> path was valid. + * Look, redirects are sent only in response to data packets, + * so that this nexthop apparently is reachable. --ANK + */ + dst_confirm(&rt->dst); + + neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1); + if (!neigh) + return; + + /* Duplicate redirect: silently ignore. */ + old_neigh = rt->n; + if (neigh == old_neigh) + goto out; + /* * We have finally decided to accept it. */ @@ -1658,17 +1743,6 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, NEIGH_UPDATE_F_ISROUTER)) ); - /* - * Redirect received -> path was valid. - * Look, redirects are sent only in response to data packets, - * so that this nexthop apparently is reachable. --ANK - */ - dst_confirm(&rt->dst); - - /* Duplicate redirect: silently ignore. */ - if (neigh == dst_get_neighbour_noref_raw(&rt->dst)) - goto out; - nrt = ip6_rt_copy(rt, dest); if (!nrt) goto out; @@ -1678,132 +1752,25 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, nrt->rt6i_flags &= ~RTF_GATEWAY; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; - dst_set_neighbour(&nrt->dst, neigh_clone(neigh)); + nrt->n = neigh_clone(neigh); if (ip6_ins_rt(nrt)) goto out; netevent.old = &rt->dst; + netevent.old_neigh = old_neigh; netevent.new = &nrt->dst; + netevent.new_neigh = neigh; + netevent.daddr = dest; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); if (rt->rt6i_flags & RTF_CACHE) { + rt = (struct rt6_info *) dst_clone(&rt->dst); ip6_del_rt(rt); - return; } out: - dst_release(&rt->dst); -} - -/* - * Handle ICMP "packet too big" messages - * i.e. Path MTU discovery - */ - -static void rt6_do_pmtu_disc(const struct in6_addr *daddr, const struct in6_addr *saddr, - struct net *net, u32 pmtu, int ifindex) -{ - struct rt6_info *rt, *nrt; - int allfrag = 0; -again: - rt = rt6_lookup(net, daddr, saddr, ifindex, 0); - if (!rt) - return; - - if (rt6_check_expired(rt)) { - ip6_del_rt(rt); - goto again; - } - - if (pmtu >= dst_mtu(&rt->dst)) - goto out; - - if (pmtu < IPV6_MIN_MTU) { - /* - * According to RFC2460, PMTU is set to the IPv6 Minimum Link - * MTU (1280) and a fragment header should always be included - * after a node receiving Too Big message reporting PMTU is - * less than the IPv6 Minimum Link MTU. - */ - pmtu = IPV6_MIN_MTU; - allfrag = 1; - } - - /* New mtu received -> path was valid. - They are sent only in response to data packets, - so that this nexthop apparently is reachable. --ANK - */ - dst_confirm(&rt->dst); - - /* Host route. If it is static, it would be better - not to override it, but add new one, so that - when cache entry will expire old pmtu - would return automatically. - */ - if (rt->rt6i_flags & RTF_CACHE) { - dst_metric_set(&rt->dst, RTAX_MTU, pmtu); - if (allfrag) { - u32 features = dst_metric(&rt->dst, RTAX_FEATURES); - features |= RTAX_FEATURE_ALLFRAG; - dst_metric_set(&rt->dst, RTAX_FEATURES, features); - } - rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); - rt->rt6i_flags |= RTF_MODIFIED; - goto out; - } - - /* Network route. - Two cases are possible: - 1. It is connected route. Action: COW - 2. It is gatewayed route or NONEXTHOP route. Action: clone it. - */ - if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) - nrt = rt6_alloc_cow(rt, daddr, saddr); - else - nrt = rt6_alloc_clone(rt, daddr); - - if (nrt) { - dst_metric_set(&nrt->dst, RTAX_MTU, pmtu); - if (allfrag) { - u32 features = dst_metric(&nrt->dst, RTAX_FEATURES); - features |= RTAX_FEATURE_ALLFRAG; - dst_metric_set(&nrt->dst, RTAX_FEATURES, features); - } - - /* According to RFC 1981, detecting PMTU increase shouldn't be - * happened within 5 mins, the recommended timer is 10 mins. - * Here this route expiration time is set to ip6_rt_mtu_expires - * which is 10 mins. After 10 mins the decreased pmtu is expired - * and detecting PMTU increase will be automatically happened. - */ - rt6_update_expires(nrt, net->ipv6.sysctl.ip6_rt_mtu_expires); - nrt->rt6i_flags |= RTF_DYNAMIC; - ip6_ins_rt(nrt); - } -out: - dst_release(&rt->dst); -} - -void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *saddr, - struct net_device *dev, u32 pmtu) -{ - struct net *net = dev_net(dev); - - /* - * RFC 1981 states that a node "MUST reduce the size of the packets it - * is sending along the path" that caused the Packet Too Big message. - * Since it's not possible in the general case to determine which - * interface was used to send the original packet, we update the MTU - * on the interface that will be used to send future packets. We also - * update the MTU on the interface that received the Packet Too Big in - * case the original packet was forced out that interface with - * SO_BINDTODEVICE or similar. This is the next best thing to the - * correct behaviour, which would be to update the MTU on all - * interfaces. - */ - rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0); - rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex); + neigh_release(neigh); } /* @@ -1814,8 +1781,8 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, const struct in6_addr *dest) { struct net *net = dev_net(ort->dst.dev); - struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, - ort->dst.dev, 0); + struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0, + ort->rt6i_table); if (rt) { rt->dst.input = ort->dst.input; @@ -2099,8 +2066,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, bool anycast) { struct net *net = dev_net(idev->dev); - struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, - net->loopback_dev, 0); + struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL); int err; if (!rt) { @@ -2396,13 +2362,11 @@ static int rt6_fill_node(struct net *net, int iif, int type, u32 pid, u32 seq, int prefix, int nowait, unsigned int flags) { - const struct inet_peer *peer; struct rtmsg *rtm; struct nlmsghdr *nlh; long expires; u32 table; struct neighbour *n; - u32 ts, tsage; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -2440,10 +2404,12 @@ static int rt6_fill_node(struct net *net, rtm->rtm_protocol = rt->rt6i_protocol; if (rt->rt6i_flags & RTF_DYNAMIC) rtm->rtm_protocol = RTPROT_REDIRECT; - else if (rt->rt6i_flags & RTF_ADDRCONF) - rtm->rtm_protocol = RTPROT_KERNEL; - else if (rt->rt6i_flags & RTF_DEFAULT) - rtm->rtm_protocol = RTPROT_RA; + else if (rt->rt6i_flags & RTF_ADDRCONF) { + if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ROUTEINFO)) + rtm->rtm_protocol = RTPROT_RA; + else + rtm->rtm_protocol = RTPROT_KERNEL; + } if (rt->rt6i_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; @@ -2500,7 +2466,7 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; rcu_read_lock(); - n = dst_get_neighbour_noref(&rt->dst); + n = rt->n; if (n) { if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0) { rcu_read_unlock(); @@ -2521,15 +2487,7 @@ static int rt6_fill_node(struct net *net, else expires = INT_MAX; - peer = rt->rt6i_peer; - ts = tsage = 0; - if (peer && peer->tcp_ts_stamp) { - ts = peer->tcp_ts; - tsage = get_seconds() - peer->tcp_ts_stamp; - } - - if (rtnl_put_cacheinfo(skb, &rt->dst, 0, ts, tsage, - expires, rt->dst.error) < 0) + if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -2722,7 +2680,7 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) seq_puts(m, "00000000000000000000000000000000 00 "); #endif rcu_read_lock(); - n = dst_get_neighbour_noref(&rt->dst); + n = rt->n; if (n) { seq_printf(m, "%pi6", n->primary_key); } else { @@ -3007,6 +2965,31 @@ static struct pernet_operations ip6_route_net_ops = { .exit = ip6_route_net_exit, }; +static int __net_init ipv6_inetpeer_init(struct net *net) +{ + struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); + + if (!bp) + return -ENOMEM; + inet_peer_base_init(bp); + net->ipv6.peers = bp; + return 0; +} + +static void __net_exit ipv6_inetpeer_exit(struct net *net) +{ + struct inet_peer_base *bp = net->ipv6.peers; + + net->ipv6.peers = NULL; + inetpeer_invalidate_tree(bp); + kfree(bp); +} + +static struct pernet_operations ipv6_inetpeer_ops = { + .init = ipv6_inetpeer_init, + .exit = ipv6_inetpeer_exit, +}; + static struct pernet_operations ip6_route_net_late_ops = { .init = ip6_route_net_init_late, .exit = ip6_route_net_exit_late, @@ -3032,10 +3015,14 @@ int __init ip6_route_init(void) if (ret) goto out_kmem_cache; - ret = register_pernet_subsys(&ip6_route_net_ops); + ret = register_pernet_subsys(&ipv6_inetpeer_ops); if (ret) goto out_dst_entries; + ret = register_pernet_subsys(&ip6_route_net_ops); + if (ret) + goto out_register_inetpeer; + ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; /* Registering of the loopback is done before this portion of code, @@ -3088,6 +3075,8 @@ out_fib6_init: fib6_gc_cleanup(); out_register_subsys: unregister_pernet_subsys(&ip6_route_net_ops); +out_register_inetpeer: + unregister_pernet_subsys(&ipv6_inetpeer_ops); out_dst_entries: dst_entries_destroy(&ip6_dst_blackhole_ops); out_kmem_cache: @@ -3102,6 +3091,7 @@ void ip6_route_cleanup(void) fib6_rules_cleanup(); xfrm6_fini(); fib6_gc_cleanup(); + unregister_pernet_subsys(&ipv6_inetpeer_ops); unregister_pernet_subsys(&ip6_route_net_ops); dst_entries_destroy(&ip6_dst_blackhole_ops); kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 60415711563f..3bd1bfc01f85 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -527,9 +527,6 @@ static int ipip6_err(struct sk_buff *skb, u32 info) case ICMP_PORT_UNREACH: /* Impossible event. */ return 0; - case ICMP_FRAG_NEEDED: - /* Soft state for pmtu is maintained by IP core. */ - return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, @@ -542,6 +539,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info) if (code != ICMP_EXC_TTL) return 0; break; + case ICMP_REDIRECT: + break; } err = -ENOENT; @@ -551,7 +550,23 @@ static int ipip6_err(struct sk_buff *skb, u32 info) skb->dev, iph->daddr, iph->saddr); - if (t == NULL || t->parms.iph.daddr == 0) + if (t == NULL) + goto out; + + 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); + err = 0; + goto out; + } + if (type == ICMP_REDIRECT) { + ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + IPPROTO_IPV6, 0); + err = 0; + goto out; + } + + if (t->parms.iph.daddr == 0) goto out; err = 0; @@ -792,7 +807,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (tunnel->parms.iph.daddr && skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->len > mtu) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 8e951d8d3b81..bb46061c813a 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -21,9 +21,6 @@ #include <net/ipv6.h> #include <net/tcp.h> -extern int sysctl_tcp_syncookies; -extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS]; - #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) @@ -180,7 +177,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, &hash_location, 0); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL); if (!cookie_check_timestamp(&tcp_opt, &ecn_ok)) goto out; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 9df64a50b075..f49476e2d884 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -277,22 +277,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, rt = (struct rt6_info *) dst; if (tcp_death_row.sysctl_tw_recycle && !tp->rx_opt.ts_recent_stamp && - ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr)) { - struct inet_peer *peer = rt6_get_peer(rt); - /* - * VJ's idea. We save last timestamp seen from - * the destination in peer table, when entering state - * TIME-WAIT * and initialize rx_opt.ts_recent from it, - * when trying new connection. - */ - if (peer) { - inet_peer_refcheck(peer); - if ((u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) { - tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp; - tp->rx_opt.ts_recent = peer->tcp_ts; - } - } - } + ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr)) + tcp_fetch_timewait_stamp(sk, dst); icsk->icsk_ext_hdr_len = 0; if (np->opt) @@ -329,6 +315,23 @@ failure: return err; } +static void tcp_v6_mtu_reduced(struct sock *sk) +{ + struct dst_entry *dst; + + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + return; + + dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info); + if (!dst) + return; + + if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { + tcp_sync_mss(sk, dst_mtu(dst)); + tcp_simple_retransmit(sk); + } +} + static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { @@ -356,7 +359,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } bh_lock_sock(sk); - if (sock_owned_by_user(sk)) + if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) @@ -377,49 +380,19 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); - if (type == ICMPV6_PKT_TOOBIG) { - struct dst_entry *dst; - - if (sock_owned_by_user(sk)) - goto out; - if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) - goto out; - - /* icmp should have updated the destination cache entry */ - dst = __sk_dst_check(sk, np->dst_cookie); - - if (dst == NULL) { - struct inet_sock *inet = inet_sk(sk); - struct flowi6 fl6; - - /* BUGGG_FUTURE: Again, it is not clear how - to handle rthdr case. Ignore this complexity - for now. - */ - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_TCP; - fl6.daddr = np->daddr; - fl6.saddr = np->saddr; - fl6.flowi6_oif = sk->sk_bound_dev_if; - fl6.flowi6_mark = sk->sk_mark; - fl6.fl6_dport = inet->inet_dport; - fl6.fl6_sport = inet->inet_sport; - security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); - - dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false); - if (IS_ERR(dst)) { - sk->sk_err_soft = -PTR_ERR(dst); - goto out; - } + if (type == NDISC_REDIRECT) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - } else - dst_hold(dst); + if (dst) + dst->ops->redirect(dst, sk, skb); + } - if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { - tcp_sync_mss(sk, dst_mtu(dst)); - tcp_simple_retransmit(sk); - } /* else let the usual retransmit timer handle it */ - dst_release(dst); + if (type == ICMPV6_PKT_TOOBIG) { + tp->mtu_info = ntohl(info); + if (!sock_owned_by_user(sk)) + tcp_v6_mtu_reduced(sk); + else + set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags); goto out; } @@ -475,62 +448,43 @@ out: } -static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, +static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, + struct flowi6 *fl6, + struct request_sock *req, struct request_values *rvp, u16 queue_mapping) { struct inet6_request_sock *treq = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff * skb; - struct ipv6_txoptions *opt = NULL; - struct in6_addr * final_p, final; - struct flowi6 fl6; - struct dst_entry *dst; - int err; + int err = -ENOMEM; - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_TCP; - fl6.daddr = treq->rmt_addr; - fl6.saddr = treq->loc_addr; - fl6.flowlabel = 0; - fl6.flowi6_oif = treq->iif; - fl6.flowi6_mark = sk->sk_mark; - fl6.fl6_dport = inet_rsk(req)->rmt_port; - fl6.fl6_sport = inet_rsk(req)->loc_port; - security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - - opt = np->opt; - final_p = fl6_update_dst(&fl6, opt, &final); - - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); - if (IS_ERR(dst)) { - err = PTR_ERR(dst); - dst = NULL; + /* First, grab a route. */ + if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL) goto done; - } + skb = tcp_make_synack(sk, dst, req, rvp); - err = -ENOMEM; + if (skb) { __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); - fl6.daddr = treq->rmt_addr; + fl6->daddr = treq->rmt_addr; skb_set_queue_mapping(skb, queue_mapping); - err = ip6_xmit(sk, skb, &fl6, opt, np->tclass); + err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass); err = net_xmit_eval(err); } done: - if (opt && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); - dst_release(dst); return err; } static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req, struct request_values *rvp) { + struct flowi6 fl6; + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return tcp_v6_send_synack(sk, req, rvp, 0); + return tcp_v6_send_synack(sk, NULL, &fl6, req, rvp, 0); } static void tcp_v6_reqsk_destructor(struct request_sock *req) @@ -1057,6 +1011,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) 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)) @@ -1085,7 +1040,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, &hash_location, 0); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); if (tmp_opt.cookie_plus > 0 && tmp_opt.saw_tstamp && @@ -1150,8 +1105,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) treq->iif = inet6_iif(skb); if (!isn) { - struct inet_peer *peer = NULL; - if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { @@ -1176,14 +1129,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) */ if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && - (dst = inet6_csk_route_req(sk, req)) != NULL && - (peer = rt6_get_peer((struct rt6_info *)dst)) != NULL && - ipv6_addr_equal((struct in6_addr *)peer->daddr.addr.a6, - &treq->rmt_addr)) { - inet_peer_refcheck(peer); - if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && - (s32)(peer->tcp_ts - req->ts_recent) > - TCP_PAWS_WINDOW) { + (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; } @@ -1192,8 +1139,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) else if (!sysctl_tcp_syncookies && (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < (sysctl_max_syn_backlog >> 2)) && - (!peer || !peer->tcp_ts_stamp) && - (!dst || !dst_metric(dst, RTAX_RTT))) { + !tcp_peer_is_proven(req, dst, false)) { /* Without syncookies last quarter of * backlog is filled with destinations, * proven to be alive. @@ -1215,7 +1161,7 @@ have_isn: if (security_inet_conn_request(sk, skb, req)) goto drop_and_release; - if (tcp_v6_send_synack(sk, req, + if (tcp_v6_send_synack(sk, dst, &fl6, req, (struct request_values *)&tmp_ext, skb_get_queue_mapping(skb)) || want_cookie) @@ -1242,10 +1188,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; - struct ipv6_txoptions *opt; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; #endif + struct flowi6 fl6; if (skb->protocol == htons(ETH_P_IP)) { /* @@ -1302,13 +1248,12 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } treq = inet6_rsk(req); - opt = np->opt; if (sk_acceptq_is_full(sk)) goto out_overflow; if (!dst) { - dst = inet6_csk_route_req(sk, req); + dst = inet6_csk_route_req(sk, &fl6, req); if (!dst) goto out; } @@ -1371,11 +1316,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, but we make one more one thing there: reattach optmem to newsk. */ - if (opt) { - newnp->opt = ipv6_dup_options(newsk, opt); - if (opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); - } + if (np->opt) + newnp->opt = ipv6_dup_options(newsk, np->opt); inet_csk(newsk)->icsk_ext_hdr_len = 0; if (newnp->opt) @@ -1422,8 +1364,6 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, out_overflow: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); out_nonewsk: - if (opt && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); dst_release(dst); out: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); @@ -1734,42 +1674,10 @@ do_time_wait: goto discard_it; } -static struct inet_peer *tcp_v6_get_peer(struct sock *sk, bool *release_it) -{ - struct rt6_info *rt = (struct rt6_info *) __sk_dst_get(sk); - struct ipv6_pinfo *np = inet6_sk(sk); - struct inet_peer *peer; - - if (!rt || - !ipv6_addr_equal(&np->daddr, &rt->rt6i_dst.addr)) { - peer = inet_getpeer_v6(&np->daddr, 1); - *release_it = true; - } else { - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - peer = rt->rt6i_peer; - *release_it = false; - } - - return peer; -} - -static void *tcp_v6_tw_get_peer(struct sock *sk) -{ - const struct inet6_timewait_sock *tw6 = inet6_twsk(sk); - const struct inet_timewait_sock *tw = inet_twsk(sk); - - if (tw->tw_family == AF_INET) - return tcp_v4_tw_get_peer(sk); - - return inet_getpeer_v6(&tw6->tw_v6_daddr, 1); -} - 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_getpeer = tcp_v6_tw_get_peer, }; static const struct inet_connection_sock_af_ops ipv6_specific = { @@ -1778,7 +1686,6 @@ static const struct inet_connection_sock_af_ops ipv6_specific = { .rebuild_header = inet6_sk_rebuild_header, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, - .get_peer = tcp_v6_get_peer, .net_header_len = sizeof(struct ipv6hdr), .net_frag_header_len = sizeof(struct frag_hdr), .setsockopt = ipv6_setsockopt, @@ -1810,7 +1717,6 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .rebuild_header = inet_sk_rebuild_header, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, - .get_peer = tcp_v4_get_peer, .net_header_len = sizeof(struct iphdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, @@ -2049,6 +1955,8 @@ struct proto tcpv6_prot = { .sendmsg = tcp_sendmsg, .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, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index f05099fc5901..99d0077b56b8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -48,6 +48,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <trace/events/skb.h> #include "udp_impl.h" int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) @@ -385,15 +386,16 @@ try_again: if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, copied ); + msg->msg_iov, copied); else { err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); if (err == -EINVAL) goto csum_copy_err; } - if (err) + if (unlikely(err)) { + trace_kfree_skb(skb, udpv6_recvmsg); goto out_free; - + } if (!peeked) { if (is_udp4) UDP_INC_STATS_USER(sock_net(sk), @@ -479,6 +481,11 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (sk == NULL) return; + if (type == ICMPV6_PKT_TOOBIG) + ip6_sk_update_pmtu(skb, sk, info); + if (type == NDISC_REDIRECT) + ip6_sk_redirect(skb, sk); + np = inet6_sk(sk); if (!icmpv6_err_convert(type, code, &err) && !np->recverr) diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8625fba96db9..ef39812107b1 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -99,12 +99,11 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, if (!xdst->u.rt6.rt6i_idev) return -ENODEV; - xdst->u.rt6.rt6i_peer = rt->rt6i_peer; - if (rt->rt6i_peer) - atomic_inc(&rt->rt6i_peer->refcnt); + rt6_transfer_peer(&xdst->u.rt6, rt); /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ + xdst->u.rt6.n = neigh_clone(rt->n); xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | RTF_LOCAL); xdst->u.rt6.rt6i_metric = rt->rt6i_metric; @@ -208,12 +207,22 @@ static inline int xfrm6_garbage_collect(struct dst_ops *ops) return dst_entries_get_fast(ops) > ops->gc_thresh * 2; } -static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu) +static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, mtu); + path->ops->update_pmtu(path, sk, skb, mtu); +} + +static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) +{ + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + struct dst_entry *path = xdst->route; + + path->ops->redirect(path, sk, skb); } static void xfrm6_dst_destroy(struct dst_entry *dst) @@ -223,8 +232,10 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); - if (likely(xdst->u.rt6.rt6i_peer)) - inet_putpeer(xdst->u.rt6.rt6i_peer); + if (rt6_has_peer(&xdst->u.rt6)) { + struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6); + inet_putpeer(peer); + } xfrm_dst_destroy(xdst); } @@ -260,6 +271,7 @@ static struct dst_ops xfrm6_dst_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, + .redirect = xfrm6_redirect, .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, |