diff options
Diffstat (limited to 'net/ipv6')
-rw-r--r-- | net/ipv6/addrconf.c | 119 | ||||
-rw-r--r-- | net/ipv6/af_inet6.c | 2 | ||||
-rw-r--r-- | net/ipv6/esp6.c | 32 | ||||
-rw-r--r-- | net/ipv6/inet6_connection_sock.c | 54 | ||||
-rw-r--r-- | net/ipv6/ip6_output.c | 12 | ||||
-rw-r--r-- | net/ipv6/ip6_tunnel.c | 2 | ||||
-rw-r--r-- | net/ipv6/ip6mr.c | 4 | ||||
-rw-r--r-- | net/ipv6/mcast.c | 77 | ||||
-rw-r--r-- | net/ipv6/ndisc.c | 29 | ||||
-rw-r--r-- | net/ipv6/netfilter.c | 6 | ||||
-rw-r--r-- | net/ipv6/netfilter/Makefile | 4 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6t_REJECT.c | 2 | ||||
-rw-r--r-- | net/ipv6/reassembly.c | 36 | ||||
-rw-r--r-- | net/ipv6/route.c | 163 | ||||
-rw-r--r-- | net/ipv6/sit.c | 14 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 151 | ||||
-rw-r--r-- | net/ipv6/udp.c | 11 | ||||
-rw-r--r-- | net/ipv6/udplite.c | 1 | ||||
-rw-r--r-- | net/ipv6/xfrm6_mode_tunnel.c | 3 | ||||
-rw-r--r-- | net/ipv6/xfrm6_output.c | 16 |
20 files changed, 466 insertions, 272 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 93b7a93..5b189c9 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2669,8 +2669,9 @@ static int addrconf_ifdown(struct net_device *dev, int how) ASSERT_RTNL(); - rt6_ifdown(net, dev); - neigh_ifdown(&nd_tbl, dev); + /* Flush routes if device is being removed or it is not loopback */ + if (how || !(dev->flags & IFF_LOOPBACK)) + rt6_ifdown(net, dev); idev = __in6_dev_get(dev); if (idev == NULL) @@ -3836,6 +3837,15 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; } +static inline size_t inet6_ifla6_size(void) +{ + return nla_total_size(4) /* IFLA_INET6_FLAGS */ + + nla_total_size(sizeof(struct ifla_cacheinfo)) + + nla_total_size(DEVCONF_MAX * 4) /* IFLA_INET6_CONF */ + + nla_total_size(IPSTATS_MIB_MAX * 8) /* IFLA_INET6_STATS */ + + nla_total_size(ICMP6_MIB_MAX * 8); /* IFLA_INET6_ICMP6STATS */ +} + static inline size_t inet6_if_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) @@ -3843,13 +3853,7 @@ static inline size_t inet6_if_nlmsg_size(void) + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ - + nla_total_size( /* IFLA_PROTINFO */ - nla_total_size(4) /* IFLA_INET6_FLAGS */ - + nla_total_size(sizeof(struct ifla_cacheinfo)) - + nla_total_size(DEVCONF_MAX * 4) /* IFLA_INET6_CONF */ - + nla_total_size(IPSTATS_MIB_MAX * 8) /* IFLA_INET6_STATS */ - + nla_total_size(ICMP6_MIB_MAX * 8) /* IFLA_INET6_ICMP6STATS */ - ); + + nla_total_size(inet6_ifla6_size()); /* IFLA_PROTINFO */ } static inline void __snmp6_fill_stats(u64 *stats, void __percpu **mib, @@ -3896,15 +3900,70 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, } } +static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev) +{ + struct nlattr *nla; + struct ifla_cacheinfo ci; + + NLA_PUT_U32(skb, IFLA_INET6_FLAGS, idev->if_flags); + + ci.max_reasm_len = IPV6_MAXPLEN; + ci.tstamp = cstamp_delta(idev->tstamp); + ci.reachable_time = jiffies_to_msecs(idev->nd_parms->reachable_time); + ci.retrans_time = jiffies_to_msecs(idev->nd_parms->retrans_time); + NLA_PUT(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci); + + nla = nla_reserve(skb, IFLA_INET6_CONF, DEVCONF_MAX * sizeof(s32)); + if (nla == NULL) + goto nla_put_failure; + ipv6_store_devconf(&idev->cnf, nla_data(nla), nla_len(nla)); + + /* XXX - MC not implemented */ + + nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); + if (nla == NULL) + goto nla_put_failure; + snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla)); + + nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64)); + if (nla == NULL) + goto nla_put_failure; + snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla)); + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static size_t inet6_get_link_af_size(const struct net_device *dev) +{ + if (!__in6_dev_get(dev)) + return 0; + + return inet6_ifla6_size(); +} + +static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev) +{ + struct inet6_dev *idev = __in6_dev_get(dev); + + if (!idev) + return -ENODATA; + + if (inet6_fill_ifla6_attrs(skb, idev) < 0) + return -EMSGSIZE; + + return 0; +} + static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, u32 pid, u32 seq, int event, unsigned int flags) { struct net_device *dev = idev->dev; - struct nlattr *nla; struct ifinfomsg *hdr; struct nlmsghdr *nlh; void *protoinfo; - struct ifla_cacheinfo ci; nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags); if (nlh == NULL) @@ -3931,30 +3990,8 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, if (protoinfo == NULL) goto nla_put_failure; - NLA_PUT_U32(skb, IFLA_INET6_FLAGS, idev->if_flags); - - ci.max_reasm_len = IPV6_MAXPLEN; - ci.tstamp = cstamp_delta(idev->tstamp); - ci.reachable_time = jiffies_to_msecs(idev->nd_parms->reachable_time); - ci.retrans_time = jiffies_to_msecs(idev->nd_parms->retrans_time); - NLA_PUT(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci); - - nla = nla_reserve(skb, IFLA_INET6_CONF, DEVCONF_MAX * sizeof(s32)); - if (nla == NULL) - goto nla_put_failure; - ipv6_store_devconf(&idev->cnf, nla_data(nla), nla_len(nla)); - - /* XXX - MC not implemented */ - - nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); - if (nla == NULL) - goto nla_put_failure; - snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla)); - - nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64)); - if (nla == NULL) + if (inet6_fill_ifla6_attrs(skb, idev) < 0) goto nla_put_failure; - snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla)); nla_nest_end(skb, protoinfo); return nlmsg_end(skb, nlh); @@ -4625,6 +4662,12 @@ int unregister_inet6addr_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_inet6addr_notifier); +static struct rtnl_af_ops inet6_ops = { + .family = AF_INET6, + .fill_link_af = inet6_fill_link_af, + .get_link_af_size = inet6_get_link_af_size, +}; + /* * Init / cleanup code */ @@ -4676,6 +4719,10 @@ int __init addrconf_init(void) addrconf_verify(0); + err = rtnl_af_register(&inet6_ops); + if (err < 0) + goto errout_af; + err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo); if (err < 0) goto errout; @@ -4691,6 +4738,8 @@ int __init addrconf_init(void) return 0; errout: + rtnl_af_unregister(&inet6_ops); +errout_af: unregister_netdevice_notifier(&ipv6_dev_notf); errlo: unregister_pernet_subsys(&addrconf_ops); @@ -4711,6 +4760,8 @@ void addrconf_cleanup(void) rtnl_lock(); + __rtnl_af_unregister(&inet6_ops); + /* clean dev list */ for_each_netdev(&init_net, dev) { if (__in6_dev_get(dev) == NULL) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 54e8e42..059a3de 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -810,7 +810,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) } rcu_read_unlock(); - if (unlikely(IS_ERR(segs))) + if (IS_ERR(segs)) goto out; for (skb = segs; skb; skb = skb->next) { diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index ee9b93b..1b5c982 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -49,6 +49,8 @@ struct esp_skb_cb { #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0])) +static u32 esp6_get_mtu(struct xfrm_state *x, int mtu); + /* * Allocate an AEAD request structure with extra space for SG and IV. * @@ -140,6 +142,8 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) int blksize; int clen; int alen; + int plen; + int tfclen; int nfrags; u8 *iv; u8 *tail; @@ -148,18 +152,26 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) /* skb is pure payload to encrypt */ err = -ENOMEM; - /* Round to block size */ - clen = skb->len; - aead = esp->aead; alen = crypto_aead_authsize(aead); + tfclen = 0; + if (x->tfcpad) { + struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); + u32 padto; + + padto = min(x->tfcpad, esp6_get_mtu(x, dst->child_mtu_cached)); + if (skb->len < padto) + tfclen = padto - skb->len; + } blksize = ALIGN(crypto_aead_blocksize(aead), 4); - clen = ALIGN(clen + 2, blksize); + clen = ALIGN(skb->len + 2 + tfclen, blksize); if (esp->padlen) clen = ALIGN(clen, esp->padlen); + plen = clen - skb->len - tfclen; - if ((err = skb_cow_data(skb, clen - skb->len + alen, &trailer)) < 0) + err = skb_cow_data(skb, tfclen + plen + alen, &trailer); + if (err < 0) goto error; nfrags = err; @@ -174,13 +186,17 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) /* Fill padding... */ tail = skb_tail_pointer(trailer); + if (tfclen) { + memset(tail, 0, tfclen); + tail += tfclen; + } do { int i; - for (i=0; i<clen-skb->len - 2; i++) + for (i = 0; i < plen - 2; i++) tail[i] = i + 1; } while (0); - tail[clen-skb->len - 2] = (clen - skb->len) - 2; - tail[clen - skb->len - 1] = *skb_mac_header(skb); + tail[plen - 2] = plen - 2; + tail[plen - 1] = *skb_mac_header(skb); pskb_put(skb, trailer, clen - skb->len + alen); skb_push(skb, -skb_network_offset(skb)); diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 8a16280..e46305d 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -54,24 +54,54 @@ 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, + 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 flowi fl; + + memset(&fl, 0, sizeof(fl)); + fl.proto = IPPROTO_TCP; + ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); + final_p = fl6_update_dst(&fl, np->opt, &final); + ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); + fl.oif = sk->sk_bound_dev_if; + fl.mark = sk->sk_mark; + fl.fl_ip_dport = inet_rsk(req)->rmt_port; + fl.fl_ip_sport = inet_rsk(req)->loc_port; + security_req_classify_flow(req, &fl); + + if (ip6_dst_lookup(sk, &dst, &fl)) + return NULL; + + if (final_p) + ipv6_addr_copy(&fl.fl6_dst, final_p); + + if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) + return NULL; + + return dst; +} + /* * request_sock (formerly open request) hash tables. */ static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, const u32 rnd, const u16 synq_hsize) { - u32 a = (__force u32)raddr->s6_addr32[0]; - u32 b = (__force u32)raddr->s6_addr32[1]; - u32 c = (__force u32)raddr->s6_addr32[2]; - - a += JHASH_GOLDEN_RATIO; - b += JHASH_GOLDEN_RATIO; - c += rnd; - __jhash_mix(a, b, c); - - a += (__force u32)raddr->s6_addr32[3]; - b += (__force u32)rport; - __jhash_mix(a, b, c); + u32 c; + + c = jhash_3words((__force u32)raddr->s6_addr32[0], + (__force u32)raddr->s6_addr32[1], + (__force u32)raddr->s6_addr32[2], + rnd); + + c = jhash_2words((__force u32)raddr->s6_addr32[3], + (__force u32)rport, + c); return c & (synq_hsize - 1); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 99157b4..94b5bf1 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -56,7 +56,7 @@ #include <net/checksum.h> #include <linux/mroute6.h> -static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); +int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); int __ip6_local_out(struct sk_buff *skb) { @@ -145,14 +145,6 @@ static int ip6_finish_output2(struct sk_buff *skb) return -EINVAL; } -static inline int ip6_skb_dst_mtu(struct sk_buff *skb) -{ - struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; - - return (np && np->pmtudisc == IPV6_PMTUDISC_PROBE) ? - skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); -} - static int ip6_finish_output(struct sk_buff *skb) { if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || @@ -601,7 +593,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) return offset; } -static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) +int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = (struct rt6_info*)skb_dst(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 70e891a..4f4483e 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -58,8 +58,6 @@ MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); -#define IPV6_TLV_TEL_DST_SIZE 8 - #ifdef IP6_TNL_DEBUG #define IP6_TNL_TRACE(x...) printk(KERN_DEBUG "%s:" x "\n", __func__) #else diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 6f32ffc..9fab274 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1843,9 +1843,7 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, fl = (struct flowi) { .oif = vif->link, - .nl_u = { .ip6_u = - { .daddr = ipv6h->daddr, } - } + .fl6_dst = ipv6h->daddr, }; dst = ip6_route_output(net, NULL, &fl); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index d1444b9..49f986d 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -82,7 +82,7 @@ static void *__mld2_query_bugs[] __attribute__((__unused__)) = { static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT; /* Big mc list lock for all the sockets */ -static DEFINE_RWLOCK(ipv6_sk_mc_lock); +static DEFINE_SPINLOCK(ipv6_sk_mc_lock); static void igmp6_join_group(struct ifmcaddr6 *ma); static void igmp6_leave_group(struct ifmcaddr6 *ma); @@ -123,6 +123,11 @@ int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; * socket join on multicast group */ +#define for_each_pmc_rcu(np, pmc) \ + for (pmc = rcu_dereference(np->ipv6_mc_list); \ + pmc != NULL; \ + pmc = rcu_dereference(pmc->next)) + int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct net_device *dev = NULL; @@ -134,15 +139,15 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (!ipv6_addr_is_multicast(addr)) return -EINVAL; - read_lock_bh(&ipv6_sk_mc_lock); - for (mc_lst=np->ipv6_mc_list; mc_lst; mc_lst=mc_lst->next) { + rcu_read_lock(); + for_each_pmc_rcu(np, mc_lst) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { - read_unlock_bh(&ipv6_sk_mc_lock); + rcu_read_unlock(); return -EADDRINUSE; } } - read_unlock_bh(&ipv6_sk_mc_lock); + rcu_read_unlock(); mc_lst = sock_kmalloc(sk, sizeof(struct ipv6_mc_socklist), GFP_KERNEL); @@ -186,33 +191,41 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) return err; } - write_lock_bh(&ipv6_sk_mc_lock); + spin_lock(&ipv6_sk_mc_lock); mc_lst->next = np->ipv6_mc_list; - np->ipv6_mc_list = mc_lst; - write_unlock_bh(&ipv6_sk_mc_lock); + rcu_assign_pointer(np->ipv6_mc_list, mc_lst); + spin_unlock(&ipv6_sk_mc_lock); rcu_read_unlock(); return 0; } +static void ipv6_mc_socklist_reclaim(struct rcu_head *head) +{ + kfree(container_of(head, struct ipv6_mc_socklist, rcu)); +} /* * socket leave on multicast group */ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); - struct ipv6_mc_socklist *mc_lst, **lnk; + struct ipv6_mc_socklist *mc_lst; + struct ipv6_mc_socklist __rcu **lnk; struct net *net = sock_net(sk); - write_lock_bh(&ipv6_sk_mc_lock); - for (lnk = &np->ipv6_mc_list; (mc_lst = *lnk) !=NULL ; lnk = &mc_lst->next) { + spin_lock(&ipv6_sk_mc_lock); + for (lnk = &np->ipv6_mc_list; + (mc_lst = rcu_dereference_protected(*lnk, + lockdep_is_held(&ipv6_sk_mc_lock))) !=NULL ; + lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { struct net_device *dev; *lnk = mc_lst->next; - write_unlock_bh(&ipv6_sk_mc_lock); + spin_unlock(&ipv6_sk_mc_lock); rcu_read_lock(); dev = dev_get_by_index_rcu(net, mc_lst->ifindex); @@ -225,11 +238,12 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); rcu_read_unlock(); - sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); + atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); + call_rcu(&mc_lst->rcu, ipv6_mc_socklist_reclaim); return 0; } } - write_unlock_bh(&ipv6_sk_mc_lock); + spin_unlock(&ipv6_sk_mc_lock); return -EADDRNOTAVAIL; } @@ -257,7 +271,7 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, return NULL; idev = __in6_dev_get(dev); if (!idev) - return NULL;; + return NULL; read_lock_bh(&idev->lock); if (idev->dead) { read_unlock_bh(&idev->lock); @@ -272,12 +286,13 @@ void ipv6_sock_mc_close(struct sock *sk) struct ipv6_mc_socklist *mc_lst; struct net *net = sock_net(sk); - write_lock_bh(&ipv6_sk_mc_lock); - while ((mc_lst = np->ipv6_mc_list) != NULL) { + spin_lock(&ipv6_sk_mc_lock); + while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list, + lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) { struct net_device *dev; np->ipv6_mc_list = mc_lst->next; - write_unlock_bh(&ipv6_sk_mc_lock); + spin_unlock(&ipv6_sk_mc_lock); rcu_read_lock(); dev = dev_get_by_index_rcu(net, mc_lst->ifindex); @@ -290,11 +305,13 @@ void ipv6_sock_mc_close(struct sock *sk) } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); rcu_read_unlock(); - sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); - write_lock_bh(&ipv6_sk_mc_lock); + atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); + call_rcu(&mc_lst->rcu, ipv6_mc_socklist_reclaim); + + spin_lock(&ipv6_sk_mc_lock); } - write_unlock_bh(&ipv6_sk_mc_lock); + spin_unlock(&ipv6_sk_mc_lock); } int ip6_mc_source(int add, int omode, struct sock *sk, @@ -328,8 +345,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk, err = -EADDRNOTAVAIL; - read_lock(&ipv6_sk_mc_lock); - for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(inet6, pmc) { if (pgsr->gsr_interface && pmc->ifindex != pgsr->gsr_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) @@ -428,7 +444,6 @@ int ip6_mc_source(int add, int omode, struct sock *sk, done: if (pmclocked) write_unlock(&pmc->sflock); - read_unlock(&ipv6_sk_mc_lock); read_unlock_bh(&idev->lock); rcu_read_unlock(); if (leavegroup) @@ -466,14 +481,13 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) dev = idev->dev; err = 0; - read_lock(&ipv6_sk_mc_lock); if (gsf->gf_fmode == MCAST_INCLUDE && gsf->gf_numsrc == 0) { leavegroup = 1; goto done; } - for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(inet6, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) @@ -521,7 +535,6 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) write_unlock(&pmc->sflock); err = 0; done: - read_unlock(&ipv6_sk_mc_lock); read_unlock_bh(&idev->lock); rcu_read_unlock(); if (leavegroup) @@ -562,7 +575,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, * so reading the list is safe. */ - for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(inet6, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(group, &pmc->addr)) @@ -612,13 +625,13 @@ int inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, struct ip6_sf_socklist *psl; int rv = 1; - read_lock(&ipv6_sk_mc_lock); - for (mc = np->ipv6_mc_list; mc; mc = mc->next) { + rcu_read_lock(); + for_each_pmc_rcu(np, mc) { if (ipv6_addr_equal(&mc->addr, mc_addr)) break; } if (!mc) { - read_unlock(&ipv6_sk_mc_lock); + rcu_read_unlock(); return 1; } read_lock(&mc->sflock); @@ -638,7 +651,7 @@ int inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, rv = 0; } read_unlock(&mc->sflock); - read_unlock(&ipv6_sk_mc_lock); + rcu_read_unlock(); return rv; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 998d6d2..2342545 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -141,18 +141,18 @@ struct neigh_table nd_tbl = { .proxy_redo = pndisc_redo, .id = "ndisc_cache", .parms = { - .tbl = &nd_tbl, - .base_reachable_time = 30 * HZ, - .retrans_time = 1 * HZ, - .gc_staletime = 60 * HZ, - .reachable_time = 30 * HZ, - .delay_probe_time = 5 * HZ, - .queue_len = 3, - .ucast_probes = 3, - .mcast_probes = 3, - .anycast_delay = 1 * HZ, - .proxy_delay = (8 * HZ) / 10, - .proxy_qlen = 64, + .tbl = &nd_tbl, + .base_reachable_time = ND_REACHABLE_TIME, + .retrans_time = ND_RETRANS_TIMER, + .gc_staletime = 60 * HZ, + .reachable_time = ND_REACHABLE_TIME, + .delay_probe_time = 5 * HZ, + .queue_len = 3, + .ucast_probes = 3, + .mcast_probes = 3, + .anycast_delay = 1 * HZ, + .proxy_delay = (8 * HZ) / 10, + .proxy_qlen = 64, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, @@ -1259,7 +1259,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; if (rt) - rt->dst.metrics[RTAX_HOPLIMIT-1] = ra_msg->icmph.icmp6_hop_limit; + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, + ra_msg->icmph.icmp6_hop_limit); } skip_defrtr: @@ -1377,7 +1378,7 @@ skip_linkparms: in6_dev->cnf.mtu6 = mtu; if (rt) - rt->dst.metrics[RTAX_MTU-1] = mtu; + dst_metric_set(&rt->dst, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 7155b24..35915e8 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -18,10 +18,8 @@ int ip6_route_me_harder(struct sk_buff *skb) struct flowi fl = { .oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, .mark = skb->mark, - .nl_u = - { .ip6_u = - { .daddr = iph->daddr, - .saddr = iph->saddr, } }, + .fl6_dst = iph->daddr, + .fl6_src = iph->saddr, }; dst = ip6_route_output(net, skb->sk, &fl); diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 0a432c9..abfee91 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -11,13 +11,13 @@ obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o # objects for l3 independent conntrack -nf_conntrack_ipv6-objs := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o +nf_conntrack_ipv6-y := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o # l3 independent conntrack obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o nf_defrag_ipv6.o # defrag -nf_defrag_ipv6-objs := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o +nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o # matches diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 2933396..bf998fe 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -124,7 +124,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) skb_reset_network_header(nskb); ip6h = ipv6_hdr(nskb); ip6h->version = 6; - ip6h->hop_limit = dst_metric(dst, RTAX_HOPLIMIT); + ip6h->hop_limit = ip6_dst_hoplimit(dst); ip6h->nexthdr = IPPROTO_TCP; ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr); ipv6_addr_copy(&ip6h->daddr, &oip6h->saddr); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 0f27664..07beeb0 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -104,26 +104,22 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr, const struct in6_addr *daddr, u32 rnd) { - u32 a, b, c; - - a = (__force u32)saddr->s6_addr32[0]; - b = (__force u32)saddr->s6_addr32[1]; - c = (__force u32)saddr->s6_addr32[2]; - - a += JHASH_GOLDEN_RATIO; - b += JHASH_GOLDEN_RATIO; - c += rnd; - __jhash_mix(a, b, c); - - a += (__force u32)saddr->s6_addr32[3]; - b += (__force u32)daddr->s6_addr32[0]; - c += (__force u32)daddr->s6_addr32[1]; - __jhash_mix(a, b, c); - - a += (__force u32)daddr->s6_addr32[2]; - b += (__force u32)daddr->s6_addr32[3]; - c += (__force u32)id; - __jhash_mix(a, b, c); + u32 c; + + c = jhash_3words((__force u32)saddr->s6_addr32[0], + (__force u32)saddr->s6_addr32[1], + (__force u32)saddr->s6_addr32[2], + rnd); + + c = jhash_3words((__force u32)saddr->s6_addr32[3], + (__force u32)daddr->s6_addr32[0], + (__force u32)daddr->s6_addr32[1], + c); + + c = jhash_3words((__force u32)daddr->s6_addr32[2], + (__force u32)daddr->s6_addr32[3], + (__force u32)id, + c); return c & (INETFRAGS_HASHSZ - 1); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 96455ffb..373bd04 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -76,6 +76,8 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); +static unsigned int ip6_default_advmss(const struct dst_entry *dst); +static unsigned int ip6_default_mtu(const struct dst_entry *dst); static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, @@ -103,6 +105,8 @@ static struct dst_ops ip6_dst_ops_template = { .gc = ip6_dst_gc, .gc_thresh = 1024, .check = ip6_dst_check, + .default_advmss = ip6_default_advmss, + .default_mtu = ip6_default_mtu, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, .negative_advice = ip6_negative_advice, @@ -129,7 +133,6 @@ static struct rt6_info ip6_null_entry_template = { .__use = 1, .obsolete = -1, .error = -ENETUNREACH, - .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, .input = ip6_pkt_discard, .output = ip6_pkt_discard_out, }, @@ -150,7 +153,6 @@ static struct rt6_info ip6_prohibit_entry_template = { .__use = 1, .obsolete = -1, .error = -EACCES, - .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, .input = ip6_pkt_prohibit, .output = ip6_pkt_prohibit_out, }, @@ -166,7 +168,6 @@ static struct rt6_info ip6_blk_hole_entry_template = { .__use = 1, .obsolete = -1, .error = -EINVAL, - .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, .input = dst_discard, .output = dst_discard, }, @@ -188,11 +189,29 @@ 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 (idev != NULL) { rt->rt6i_idev = NULL; in6_dev_put(idev); } + if (peer) { + BUG_ON(!(rt->rt6i_flags & RTF_CACHE)); + rt->rt6i_peer = NULL; + inet_putpeer(peer); + } +} + +void rt6_bind_peer(struct rt6_info *rt, int create) +{ + struct inet_peer *peer; + + if (WARN_ON(!(rt->rt6i_flags & RTF_CACHE))) + return; + + peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create); + if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL) + inet_putpeer(peer); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -558,11 +577,7 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, { struct flowi fl = { .oif = oif, - .nl_u = { - .ip6_u = { - .daddr = *daddr, - }, - }, + .fl6_dst = *daddr, }; struct dst_entry *dst; int flags = strict ? RT6_LOOKUP_F_IFACE : 0; @@ -778,13 +793,9 @@ void ip6_route_input(struct sk_buff *skb) int flags = RT6_LOOKUP_F_HAS_SADDR; struct flowi fl = { .iif = skb->dev->ifindex, - .nl_u = { - .ip6_u = { - .daddr = iph->daddr, - .saddr = iph->saddr, - .flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK, - }, - }, + .fl6_dst = iph->daddr, + .fl6_src = iph->saddr, + .fl6_flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK, .mark = skb->mark, .proto = iph->nexthdr, }; @@ -834,7 +845,7 @@ int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl new->input = dst_discard; new->output = dst_discard; - memcpy(new->metrics, ort->dst.metrics, RTAX_MAX*sizeof(u32)); + dst_copy_metrics(new, &ort->dst); new->dev = ort->dst.dev; if (new->dev) dev_hold(new->dev); @@ -918,18 +929,22 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; if (mtu < IPV6_MIN_MTU) { + u32 features = dst_metric(dst, RTAX_FEATURES); mtu = IPV6_MIN_MTU; - dst->metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; + features |= RTAX_FEATURE_ALLFRAG; + dst_metric_set(dst, RTAX_FEATURES, features); } - dst->metrics[RTAX_MTU-1] = mtu; + dst_metric_set(dst, RTAX_MTU, mtu); call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst); } } -static int ipv6_get_mtu(struct net_device *dev); - -static inline unsigned int ipv6_advmss(struct net *net, unsigned int mtu) +static unsigned int ip6_default_advmss(const struct dst_entry *dst) { + struct net_device *dev = dst->dev; + unsigned int mtu = dst_mtu(dst); + struct net *net = dev_net(dev); + mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr); if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss) @@ -946,6 +961,20 @@ static inline unsigned int ipv6_advmss(struct net *net, unsigned int mtu) return mtu; } +static unsigned int ip6_default_mtu(const struct dst_entry *dst) +{ + unsigned int mtu = IPV6_MIN_MTU; + struct inet6_dev *idev; + + rcu_read_lock(); + idev = __in6_dev_get(dst->dev); + if (idev) + mtu = idev->cnf.mtu6; + rcu_read_unlock(); + + return mtu; +} + static struct dst_entry *icmp6_dst_gc_list; static DEFINE_SPINLOCK(icmp6_dst_lock); @@ -979,9 +1008,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->rt6i_idev = idev; rt->rt6i_nexthop = neigh; atomic_set(&rt->dst.__refcnt, 1); - rt->dst.metrics[RTAX_HOPLIMIT-1] = 255; - rt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev); - rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->dst)); + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); rt->dst.output = ip6_output; #if 0 /* there's no chance to use these for ndisc */ @@ -1080,23 +1107,10 @@ out: Remove it only when all the things will work! */ -static int ipv6_get_mtu(struct net_device *dev) -{ - int mtu = IPV6_MIN_MTU; - struct inet6_dev *idev; - - rcu_read_lock(); - idev = __in6_dev_get(dev); - if (idev) - mtu = idev->cnf.mtu6; - rcu_read_unlock(); - return mtu; -} - int ip6_dst_hoplimit(struct dst_entry *dst) { - int hoplimit = dst_metric(dst, RTAX_HOPLIMIT); - if (hoplimit < 0) { + int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); + if (hoplimit == 0) { struct net_device *dev = dst->dev; struct inet6_dev *idev; @@ -1110,6 +1124,7 @@ int ip6_dst_hoplimit(struct dst_entry *dst) } return hoplimit; } +EXPORT_SYMBOL(ip6_dst_hoplimit); /* * @@ -1295,17 +1310,11 @@ install_route: goto out; } - rt->dst.metrics[type - 1] = nla_get_u32(nla); + dst_metric_set(&rt->dst, type, nla_get_u32(nla)); } } } - if (dst_metric(&rt->dst, RTAX_HOPLIMIT) == 0) - rt->dst.metrics[RTAX_HOPLIMIT-1] = -1; - if (!dst_mtu(&rt->dst)) - rt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(dev); - if (!dst_metric(&rt->dst, RTAX_ADVMSS)) - rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->dst)); rt->dst.dev = dev; rt->rt6i_idev = idev; rt->rt6i_table = table; @@ -1463,12 +1472,8 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, struct ip6rd_flowi rdfl = { .fl = { .oif = dev->ifindex, - .nl_u = { - .ip6_u = { - .daddr = *dest, - .saddr = *src, - }, - }, + .fl6_dst = *dest, + .fl6_src = *src, }, }; @@ -1534,10 +1539,6 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *src, ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key); nrt->rt6i_nexthop = neigh_clone(neigh); - /* Reset pmtu, it may be better */ - nrt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev); - nrt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dev_net(neigh->dev), - dst_mtu(&nrt->dst)); if (ip6_ins_rt(nrt)) goto out; @@ -1565,11 +1566,16 @@ static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr, { struct rt6_info *rt, *nrt; int allfrag = 0; - +again: rt = rt6_lookup(net, daddr, saddr, ifindex, 0); if (rt == NULL) return; + if (rt6_check_expired(rt)) { + ip6_del_rt(rt); + goto again; + } + if (pmtu >= dst_mtu(&rt->dst)) goto out; @@ -1596,9 +1602,12 @@ static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr, would return automatically. */ if (rt->rt6i_flags & RTF_CACHE) { - rt->dst.metrics[RTAX_MTU-1] = pmtu; - if (allfrag) - rt->dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; + 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); + } dst_set_expires(&rt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires); rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES; goto out; @@ -1615,9 +1624,12 @@ static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr, nrt = rt6_alloc_clone(rt, daddr); if (nrt) { - nrt->dst.metrics[RTAX_MTU-1] = pmtu; - if (allfrag) - nrt->dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; + 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. @@ -1668,7 +1680,7 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) rt->dst.input = ort->dst.input; rt->dst.output = ort->dst.output; - memcpy(rt->dst.metrics, ort->dst.metrics, RTAX_MAX*sizeof(u32)); + dst_copy_metrics(&rt->dst, &ort->dst); rt->dst.error = ort->dst.error; rt->dst.dev = ort->dst.dev; if (rt->dst.dev) @@ -1960,9 +1972,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->dst.output = ip6_output; rt->rt6i_dev = net->loopback_dev; rt->rt6i_idev = idev; - rt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev); - rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->dst)); - rt->dst.metrics[RTAX_HOPLIMIT-1] = -1; + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, -1); rt->dst.obsolete = -1; rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP; @@ -1999,11 +2009,11 @@ struct arg_dev_net { static int fib6_ifdown(struct rt6_info *rt, void *arg) { - struct net_device *dev = ((struct arg_dev_net *)arg)->dev; - struct net *net = ((struct arg_dev_net *)arg)->net; + const struct arg_dev_net *adn = arg; + const struct net_device *dev = adn->dev; - if (((void *)rt->rt6i_dev == dev || dev == NULL) && - rt != net->ipv6.ip6_null_entry) { + if ((rt->rt6i_dev == dev || dev == NULL) && + rt != adn->net->ipv6.ip6_null_entry) { RT6_TRACE("deleted by ifdown %p\n", rt); return -1; } @@ -2031,7 +2041,6 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg; struct inet6_dev *idev; - struct net *net = dev_net(arg->dev); /* In IPv6 pmtu discovery is not optional, so that RTAX_MTU lock cannot disable it. @@ -2062,8 +2071,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) (dst_mtu(&rt->dst) >= arg->mtu || (dst_mtu(&rt->dst) < arg->mtu && dst_mtu(&rt->dst) == idev->cnf.mtu6))) { - rt->dst.metrics[RTAX_MTU-1] = arg->mtu; - rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, arg->mtu); + dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); } return 0; } @@ -2289,7 +2297,7 @@ static int rt6_fill_node(struct net *net, NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } - if (rtnetlink_put_metrics(skb, rt->dst.metrics) < 0) + if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; if (rt->dst.neighbour) @@ -2465,8 +2473,6 @@ static int ip6_route_dev_notify(struct notifier_block *this, #ifdef CONFIG_PROC_FS -#define RT6_INFO_LEN (32 + 4 + 32 + 4 + 32 + 40 + 5 + 1) - struct rt6_proc_arg { char *buffer; @@ -2682,6 +2688,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_null_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; + dst_metric_set(&net->ipv6.ip6_null_entry->dst, RTAX_HOPLIMIT, 255); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, @@ -2692,6 +2699,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_prohibit_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_prohibit_entry; net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; + dst_metric_set(&net->ipv6.ip6_prohibit_entry->dst, RTAX_HOPLIMIT, 255); net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), @@ -2701,6 +2709,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_blk_hole_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_blk_hole_entry; net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; + dst_metric_set(&net->ipv6.ip6_blk_hole_entry->dst, RTAX_HOPLIMIT, 255); #endif net->ipv6.sysctl.flush_delay = 0; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 8c4d00c..8ce38f1 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -731,10 +731,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } { - struct flowi fl = { .nl_u = { .ip4_u = - { .daddr = dst, - .saddr = tiph->saddr, - .tos = RT_TOS(tos) } }, + struct flowi fl = { .fl4_dst = dst, + .fl4_src = tiph->saddr, + .fl4_tos = RT_TOS(tos), .oif = tunnel->parms.link, .proto = IPPROTO_IPV6 }; if (ip_route_output_key(dev_net(dev), &rt, &fl)) { @@ -856,10 +855,9 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) iph = &tunnel->parms.iph; if (iph->daddr) { - struct flowi fl = { .nl_u = { .ip4_u = - { .daddr = iph->daddr, - .saddr = iph->saddr, - .tos = RT_TOS(iph->tos) } }, + struct flowi fl = { .fl4_dst = iph->daddr, + .fl4_src = iph->saddr, + .fl4_tos = RT_TOS(iph->tos), .oif = tunnel->parms.link, .proto = IPPROTO_IPV6 }; struct rtable *rt; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7e41e2c..20aa95e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -130,6 +130,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct in6_addr *saddr = NULL, *final_p, final; + struct rt6_info *rt; struct flowi fl; struct dst_entry *dst; int addr_type; @@ -280,6 +281,26 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_gso_type = SKB_GSO_TCPV6; __ip6_dst_store(sk, dst, NULL, NULL); + 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; + } + } + } + icsk->icsk_ext_hdr_len = 0; if (np->opt) icsk->icsk_ext_hdr_len = (np->opt->opt_flen + @@ -906,12 +927,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { }; #endif -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, -}; - static void __tcp_v6_send_check(struct sk_buff *skb, struct in6_addr *saddr, struct in6_addr *daddr) { @@ -1176,6 +1191,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); __u32 isn = TCP_SKB_CB(skb)->when; + struct dst_entry *dst = NULL; #ifdef CONFIG_SYN_COOKIES int want_cookie = 0; #else @@ -1273,6 +1289,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) TCP_ECN_create_request(req, tcp_hdr(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) { @@ -1285,13 +1303,57 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!sk->sk_bound_dev_if && ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) treq->iif = inet6_iif(skb); - if (!want_cookie) { - isn = tcp_v6_init_sequence(skb); - } else { + + if (want_cookie) { isn = cookie_v6_init_sequence(sk, skb, &req->mss); req->cookie_ts = tmp_opt.tstamp_ok; + goto have_isn; } + + /* VJ's idea. We save last timestamp seen + * from the destination in peer table, when entering + * state TIME-WAIT, and check against it before + * accepting new connection request. + * + * If "isn" is not zero, this request hit alive + * timewait bucket, so that all the necessary checks + * are made in the function processing timewait state. + */ + if (tmp_opt.saw_tstamp && + tcp_death_row.sysctl_tw_recycle && + (dst = inet6_csk_route_req(sk, req)) != NULL && + (peer = rt6_get_peer((struct rt6_info *)dst)) != NULL && + ipv6_addr_equal((struct in6_addr *)peer->daddr.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) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); + goto drop_and_release; + } + } + /* Kill the following clause, if you dislike this way. */ + else if (!sysctl_tcp_syncookies && + (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < + (sysctl_max_syn_backlog >> 2)) && + (!peer || !peer->tcp_ts_stamp) && + (!dst || !dst_metric(dst, RTAX_RTT))) { + /* Without syncookies last quarter of + * backlog is filled with destinations, + * proven to be alive. + * It means that we continue to communicate + * to destinations, already remembered + * to the moment of synflood. + */ + LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI6/%u\n", + &treq->rmt_addr, ntohs(tcp_hdr(skb)->source)); + goto drop_and_release; + } + + isn = tcp_v6_init_sequence(skb); } +have_isn: tcp_rsk(req)->snt_isn = isn; security_inet_conn_request(sk, skb, req); @@ -1304,6 +1366,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); return 0; +drop_and_release: + dst_release(dst); drop_and_free: reqsk_free(req); drop: @@ -1382,28 +1446,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, if (sk_acceptq_is_full(sk)) goto out_overflow; - if (dst == NULL) { - struct in6_addr *final_p, final; - struct flowi fl; - - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - final_p = fl6_update_dst(&fl, opt, &final); - ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); - fl.oif = sk->sk_bound_dev_if; - fl.mark = sk->sk_mark; - fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_rsk(req)->loc_port; - security_req_classify_flow(req, &fl); - - if (ip6_dst_lookup(sk, &dst, &fl)) - goto out; - - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) + if (!dst) { + dst = inet6_csk_route_req(sk, req); + if (!dst) goto out; } @@ -1476,7 +1521,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); - newtp->advmss = dst_metric(dst, RTAX_ADVMSS); + newtp->advmss = dst_metric_advmss(dst); tcp_initialize_rcv_mss(newsk); newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; @@ -1818,19 +1863,51 @@ do_time_wait: goto discard_it; } -static int tcp_v6_remember_stamp(struct sock *sk) +static struct inet_peer *tcp_v6_get_peer(struct sock *sk, bool *release_it) { - /* Alas, not yet... */ - return 0; + 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) +{ + struct inet6_timewait_sock *tw6 = inet6_twsk(sk); + 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 = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, - .remember_stamp = tcp_v6_remember_stamp, + .get_peer = tcp_v6_get_peer, .net_header_len = sizeof(struct ipv6hdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, @@ -1862,7 +1939,7 @@ 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, - .remember_stamp = tcp_v4_remember_stamp, + .get_peer = tcp_v4_get_peer, .net_header_len = sizeof(struct iphdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 91def93..9a009c6 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -54,8 +54,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); - __be32 sk1_rcv_saddr = inet_sk(sk)->inet_rcv_saddr; - __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2); + __be32 sk1_rcv_saddr = sk_rcv_saddr(sk); + __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); int sk_ipv6only = ipv6_only_sock(sk); int sk2_ipv6only = inet_v6_ipv6only(sk2); int addr_type = ipv6_addr_type(sk_rcv_saddr6); @@ -227,7 +227,7 @@ begin: if (result) { exact_match: - if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score2(result, net, saddr, sport, daddr, hnum, dif) < badness)) { @@ -294,7 +294,7 @@ begin: goto begin; if (result) { - if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score(result, net, hnum, saddr, sport, daddr, dport, dif) < badness)) { @@ -602,7 +602,7 @@ static void flush_stack(struct sock **stack, unsigned int count, sk = stack[i]; if (skb1) { - if (sk_rcvqueues_full(sk, skb)) { + if (sk_rcvqueues_full(sk, skb1)) { kfree_skb(skb1); goto drop; } @@ -1477,6 +1477,7 @@ struct proto udpv6_prot = { .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, #endif + .clear_sk = sk_prot_clear_portaddr_nulls, }; static struct inet_protosw udpv6_protosw = { diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 5f48fad..986c4de 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -55,6 +55,7 @@ struct proto udplitev6_prot = { .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, #endif + .clear_sk = sk_prot_clear_portaddr_nulls, }; static struct inet_protosw udplite6_protosw = { diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index b809812..645cb96 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -14,6 +14,7 @@ #include <net/dsfield.h> #include <net/dst.h> #include <net/inet_ecn.h> +#include <net/ip6_route.h> #include <net/ipv6.h> #include <net/xfrm.h> @@ -53,7 +54,7 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) if (x->props.flags & XFRM_STATE_NOECN) dsfield &= ~INET_ECN_MASK; ipv6_change_dsfield(top_iph, 0, dsfield); - top_iph->hop_limit = dst_metric(dst->child, RTAX_HOPLIMIT); + top_iph->hop_limit = ip6_dst_hoplimit(dst->child); ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr); ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr); return 0; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 6434bd5..8e688b3 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -17,6 +17,7 @@ #include <linux/netfilter_ipv6.h> #include <net/dst.h> #include <net/ipv6.h> +#include <net/ip6_route.h> #include <net/xfrm.h> int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, @@ -88,8 +89,21 @@ static int xfrm6_output_finish(struct sk_buff *skb) return xfrm_output(skb); } +static int __xfrm6_output(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct xfrm_state *x = dst->xfrm; + + if ((x && x->props.mode == XFRM_MODE_TUNNEL) && + ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || + dst_allfrag(skb_dst(skb)))) { + return ip6_fragment(skb, xfrm6_output_finish); + } + return xfrm6_output_finish(skb); +} + int xfrm6_output(struct sk_buff *skb) { return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, - skb_dst(skb)->dev, xfrm6_output_finish); + skb_dst(skb)->dev, __xfrm6_output); } |