diff options
Diffstat (limited to 'net/ipv6')
42 files changed, 416 insertions, 248 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b5fd116c046a..78cef00c9596 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -94,15 +94,6 @@ #include <linux/seq_file.h> #include <linux/export.h> -/* Set to 3 to get tracing... */ -#define ACONF_DEBUG 2 - -#if ACONF_DEBUG >= 3 -#define ADBG(fmt, ...) printk(fmt, ##__VA_ARGS__) -#else -#define ADBG(fmt, ...) do { if (0) printk(fmt, ##__VA_ARGS__); } while (0) -#endif - #define INFINITY_LIFE_TIME 0xFFFFFFFF #define IPV6_MAX_STRLEN \ @@ -409,9 +400,8 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) dev_hold(dev); if (snmp6_alloc_dev(ndev) < 0) { - ADBG(KERN_WARNING - "%s: cannot allocate memory for statistics; dev=%s.\n", - __func__, dev->name); + netdev_dbg(dev, "%s: cannot allocate memory for statistics\n", + __func__); neigh_parms_release(&nd_tbl, ndev->nd_parms); dev_put(dev); kfree(ndev); @@ -419,9 +409,8 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) } if (snmp6_register_dev(ndev) < 0) { - ADBG(KERN_WARNING - "%s: cannot create /proc/net/dev_snmp6/%s\n", - __func__, dev->name); + netdev_dbg(dev, "%s: cannot create /proc/net/dev_snmp6/%s\n", + __func__, dev->name); goto err_release; } @@ -984,7 +973,7 @@ static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa) /* Ignore adding duplicate addresses on an interface */ if (ipv6_chk_same_addr(dev_net(dev), &ifa->addr, dev, hash)) { - ADBG("ipv6_add_addr: already assigned\n"); + netdev_dbg(dev, "ipv6_add_addr: already assigned\n"); err = -EEXIST; } else { hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); @@ -1044,7 +1033,6 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa = kzalloc(sizeof(*ifa), gfp_flags); if (!ifa) { - ADBG("ipv6_add_addr: malloc failed\n"); err = -ENOBUFS; goto out; } @@ -1851,22 +1839,42 @@ static int ipv6_count_addresses(const struct inet6_dev *idev) int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict) { - return ipv6_chk_addr_and_flags(net, addr, dev, strict, IFA_F_TENTATIVE); + return ipv6_chk_addr_and_flags(net, addr, dev, !dev, + strict, IFA_F_TENTATIVE); } EXPORT_SYMBOL(ipv6_chk_addr); +/* device argument is used to find the L3 domain of interest. If + * skip_dev_check is set, then the ifp device is not checked against + * the passed in dev argument. So the 2 cases for addresses checks are: + * 1. does the address exist in the L3 domain that dev is part of + * (skip_dev_check = true), or + * + * 2. does the address exist on the specific device + * (skip_dev_check = false) + */ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, - const struct net_device *dev, int strict, - u32 banned_flags) + const struct net_device *dev, bool skip_dev_check, + int strict, u32 banned_flags) { unsigned int hash = inet6_addr_hash(net, addr); + const struct net_device *l3mdev; struct inet6_ifaddr *ifp; u32 ifp_flags; rcu_read_lock(); + + l3mdev = l3mdev_master_dev_rcu(dev); + if (skip_dev_check) + dev = NULL; + hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; + + if (l3mdev_master_dev_rcu(ifp->idev->dev) != l3mdev) + continue; + /* Decouple optimistic from tentative for evaluation here. * Ban optimistic addresses explicitly, when required. */ @@ -2598,7 +2606,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) pinfo = (struct prefix_info *) opt; if (len < sizeof(struct prefix_info)) { - ADBG("addrconf: prefix option too short\n"); + netdev_dbg(dev, "addrconf: prefix option too short\n"); return; } @@ -4261,7 +4269,7 @@ static const struct file_operations if6_fops = { static int __net_init if6_proc_net_init(struct net *net) { - if (!proc_create("if_inet6", S_IRUGO, net->proc_net, &if6_fops)) + if (!proc_create("if_inet6", 0444, net->proc_net, &if6_fops)) return -ENOMEM; return 0; } @@ -4274,7 +4282,6 @@ static void __net_exit if6_proc_net_exit(struct net *net) static struct pernet_operations if6_proc_net_ops = { .init = if6_proc_net_init, .exit = if6_proc_net_exit, - .async = true, }; int __init if6_proc_init(void) @@ -4426,8 +4433,8 @@ restart: if (time_before(next_sched, jiffies + ADDRCONF_TIMER_FUZZ_MAX)) next_sched = jiffies + ADDRCONF_TIMER_FUZZ_MAX; - ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", - now, next, next_sec, next_sched); + pr_debug("now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", + now, next, next_sec, next_sched); mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now); rcu_read_unlock_bh(); } @@ -6584,7 +6591,6 @@ static void __net_exit addrconf_exit_net(struct net *net) static struct pernet_operations addrconf_ops = { .init = addrconf_init_net, .exit = addrconf_exit_net, - .async = true, }; static struct rtnl_af_ops inet6_ops __read_mostly = { diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index ba2e63633370..1d6ced37ad71 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -344,7 +344,6 @@ static void __net_exit ip6addrlbl_net_exit(struct net *net) static struct pernet_operations ipv6_addr_label_ops = { .init = ip6addrlbl_net_init, .exit = ip6addrlbl_net_exit, - .async = true, }; int __init ipv6_addr_label_init(void) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index dbbe04018813..c1e292db04db 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -857,7 +857,6 @@ static void __net_exit inet6_net_exit(struct net *net) static struct pernet_operations inet6_net_ops = { .init = inet6_net_init, .exit = inet6_net_exit, - .async = true, }; static const struct ipv6_stub ipv6_stub_impl = { diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index c61718dba2e6..bbcabbba9bd8 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -66,7 +66,11 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) return -EPERM; if (ipv6_addr_is_multicast(addr)) return -EINVAL; - if (ipv6_chk_addr(net, addr, NULL, 0)) + + if (ifindex) + dev = __dev_get_by_index(net, ifindex); + + if (ipv6_chk_addr_and_flags(net, addr, dev, true, 0, IFA_F_TENTATIVE)) return -EINVAL; pac = sock_kmalloc(sk, sizeof(struct ipv6_ac_socklist), GFP_KERNEL); @@ -90,8 +94,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) dev = __dev_get_by_flags(net, IFF_UP, IFF_UP | IFF_LOOPBACK); } - } else - dev = __dev_get_by_index(net, ifindex); + } if (!dev) { err = -ENODEV; @@ -541,7 +544,7 @@ static const struct file_operations ac6_seq_fops = { int __net_init ac6_proc_init(struct net *net) { - if (!proc_create("anycast6", S_IRUGO, net->proc_net, &ac6_seq_fops)) + if (!proc_create("anycast6", 0444, net->proc_net, &ac6_seq_fops)) return -ENOMEM; return 0; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index fbf08ce3f5ab..88bc2ef7c7a8 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -146,10 +146,12 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct in6_addr *daddr; + struct in6_addr *daddr, old_daddr; + __be32 fl6_flowlabel = 0; + __be32 old_fl6_flowlabel; + __be16 old_dport; int addr_type; int err; - __be32 fl6_flowlabel = 0; if (usin->sin6_family == AF_INET) { if (__ipv6_only_sock(sk)) @@ -238,9 +240,13 @@ ipv4_connected: } } + /* save the current peer information before updating it */ + old_daddr = sk->sk_v6_daddr; + old_fl6_flowlabel = np->flow_label; + old_dport = inet->inet_dport; + sk->sk_v6_daddr = *daddr; np->flow_label = fl6_flowlabel; - inet->inet_dport = usin->sin6_port; /* @@ -250,11 +256,12 @@ ipv4_connected: err = ip6_datagram_dst_update(sk, true); if (err) { - /* Reset daddr and dport so that udp_v6_early_demux() - * fails to find this socket + /* Restore the socket peer info, to keep it consistent with + * the old socket state */ - memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr)); - inet->inet_dport = 0; + sk->sk_v6_daddr = old_daddr; + np->flow_label = old_fl6_flowlabel; + inet->inet_dport = old_dport; goto out; } @@ -801,8 +808,9 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) && - !ipv6_chk_addr(net, &src_info->ipi6_addr, - strict ? dev : NULL, 0) && + !ipv6_chk_addr_and_flags(net, &src_info->ipi6_addr, + dev, !strict, 0, + IFA_F_TENTATIVE) && !ipv6_chk_acast_addr_src(net, dev, &src_info->ipi6_addr)) err = -EINVAL; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 3fd1ec775dc2..27f59b61f70f 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -165,6 +165,8 @@ static struct sk_buff *esp6_gso_segment(struct sk_buff *skb, if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle || (x->xso.dev != skb->dev)) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); + else if (!(features & NETIF_F_HW_ESP_TX_CSUM)) + esp_features = features & ~NETIF_F_CSUM_MASK; xo->flags |= XFRM_GSO_SEGMENT; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 00ef9467f3c0..df113c7b5fc8 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -397,7 +397,6 @@ static void __net_exit fib6_rules_net_exit(struct net *net) static struct pernet_operations fib6_rules_net_ops = { .init = fib6_rules_net_init, .exit = fib6_rules_net_exit, - .async = true, }; int __init fib6_rules_init(void) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 6f84668be6ea..d8c4b6374377 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -998,7 +998,6 @@ static void __net_exit icmpv6_sk_exit(struct net *net) static struct pernet_operations icmpv6_sk_ops = { .init = icmpv6_sk_init, .exit = icmpv6_sk_exit, - .async = true, }; int __init icmpv6_init(void) diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index e438699f000f..44c39c5f0638 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -613,7 +613,6 @@ static struct pernet_operations ila_net_ops = { .exit = ila_exit_net, .id = &ila_net_id, .size = sizeof(struct ila_net), - .async = true, }; static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2f995e9e3050..deab2db6692e 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1007,12 +1007,16 @@ add: if (err) return err; + err = call_fib6_entry_notifiers(info->nl_net, + FIB_EVENT_ENTRY_ADD, + rt, extack); + if (err) + return err; + rcu_assign_pointer(rt->rt6_next, iter); atomic_inc(&rt->rt6i_ref); rcu_assign_pointer(rt->rt6i_node, fn); rcu_assign_pointer(*ins, rt); - call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_ADD, - rt, extack); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; @@ -1036,12 +1040,16 @@ add: if (err) return err; + err = call_fib6_entry_notifiers(info->nl_net, + FIB_EVENT_ENTRY_REPLACE, + rt, extack); + if (err) + return err; + atomic_inc(&rt->rt6i_ref); rcu_assign_pointer(rt->rt6i_node, fn); rt->rt6_next = iter->rt6_next; rcu_assign_pointer(*ins, rt); - call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, - rt, extack); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { @@ -2161,7 +2169,6 @@ static void fib6_net_exit(struct net *net) static struct pernet_operations fib6_net_ops = { .init = fib6_net_init, .exit = fib6_net_exit, - .async = true, }; int __init fib6_init(void) diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 6ddf52282894..c05c4e82a7ca 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -844,7 +844,7 @@ static const struct file_operations ip6fl_seq_fops = { static int __net_init ip6_flowlabel_proc_init(struct net *net) { - if (!proc_create("ip6_flowlabel", S_IRUGO, net->proc_net, + if (!proc_create("ip6_flowlabel", 0444, net->proc_net, &ip6fl_seq_fops)) return -ENOMEM; return 0; @@ -873,7 +873,6 @@ static void __net_exit ip6_flowlabel_net_exit(struct net *net) static struct pernet_operations ip6_flowlabel_net_ops = { .init = ip6_flowlabel_proc_init, .exit = ip6_flowlabel_net_exit, - .async = true, }; int ip6_flowlabel_init(void) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 18a3dfbd0300..22e86557aca4 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -126,7 +126,8 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, struct ip6_tnl *t, *cand = NULL; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); int dev_type = (gre_proto == htons(ETH_P_TEB) || - gre_proto == htons(ETH_P_ERSPAN)) ? + gre_proto == htons(ETH_P_ERSPAN) || + gre_proto == htons(ETH_P_ERSPAN2)) ? ARPHRD_ETHER : ARPHRD_IP6GRE; int score, cand_score = 4; @@ -236,7 +237,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, return t; dev = ign->fb_tunnel_dev; - if (dev->flags & IFF_UP) + if (dev && dev->flags & IFF_UP) return netdev_priv(dev); return NULL; @@ -724,7 +725,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), - (flags | TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) + (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); } else { @@ -905,6 +906,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, truncate = true; } + if (skb_cow_head(skb, dev->needed_headroom)) + goto tx_err; + t->parms.o_flags &= ~TUNNEL_KEY; IPCB(skb)->flags = 0; @@ -947,6 +951,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, md->u.md2.dir, get_hwid(&md->u.md2), truncate, false); + } else { + goto tx_err; } } else { switch (skb->protocol) { @@ -1472,6 +1478,8 @@ static int __net_init ip6gre_init_net(struct net *net) struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); int err; + if (!net_has_fallback_tunnels(net)) + return 0; ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", NET_NAME_UNKNOWN, ip6gre_tunnel_setup); @@ -1520,7 +1528,6 @@ static struct pernet_operations ip6gre_net_ops = { .exit_batch = ip6gre_exit_batch_net, .id = &ip6gre_net_id, .size = sizeof(struct ip6gre_net), - .async = true, }; static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a6eb0e699b15..2c7f09c3c39e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -412,7 +412,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) if (skb->ignore_df) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 1124f310df5a..df4c29f7d59f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -758,9 +758,11 @@ int ip6_tnl_rcv_ctl(struct ip6_tnl *t, ldev = dev_get_by_index_rcu(net, p->link); if ((ipv6_addr_is_multicast(laddr) || - likely(ipv6_chk_addr(net, laddr, ldev, 0))) && + likely(ipv6_chk_addr_and_flags(net, laddr, ldev, false, + 0, IFA_F_TENTATIVE))) && ((p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) || - likely(!ipv6_chk_addr(net, raddr, NULL, 0)))) + likely(!ipv6_chk_addr_and_flags(net, raddr, ldev, true, + 0, IFA_F_TENTATIVE)))) ret = 1; } return ret; @@ -990,12 +992,14 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t, if (p->link) ldev = dev_get_by_index_rcu(net, p->link); - if (unlikely(!ipv6_chk_addr(net, laddr, ldev, 0))) + if (unlikely(!ipv6_chk_addr_and_flags(net, laddr, ldev, false, + 0, IFA_F_TENTATIVE))) pr_warn("%s xmit: Local address not yet configured!\n", p->name); else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) && !ipv6_addr_is_multicast(raddr) && - unlikely(ipv6_chk_addr(net, raddr, NULL, 0))) + unlikely(ipv6_chk_addr_and_flags(net, raddr, ldev, + true, 0, IFA_F_TENTATIVE))) pr_warn("%s xmit: Routing loop! Remote address found on this node!\n", p->name); else @@ -1982,14 +1986,14 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - struct ip6_tnl *nt, *t; struct ip_tunnel_encap ipencap; + struct ip6_tnl *nt, *t; + int err; nt = netdev_priv(dev); if (ip6_tnl_netlink_encap_parms(data, &ipencap)) { - int err = ip6_tnl_encap_setup(nt, &ipencap); - + err = ip6_tnl_encap_setup(nt, &ipencap); if (err < 0) return err; } @@ -2005,7 +2009,11 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, return -EEXIST; } - return ip6_tnl_create2(dev); + err = ip6_tnl_create2(dev); + if (!err && tb[IFLA_MTU]) + ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + + return err; } static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], @@ -2201,6 +2209,8 @@ static int __net_init ip6_tnl_init_net(struct net *net) ip6n->tnls[0] = ip6n->tnls_wc; ip6n->tnls[1] = ip6n->tnls_r_l; + if (!net_has_fallback_tunnels(net)) + return 0; err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0", NET_NAME_UNKNOWN, ip6_tnl_dev_setup); @@ -2250,7 +2260,6 @@ static struct pernet_operations ip6_tnl_net_ops = { .exit_batch = ip6_tnl_exit_batch_net, .id = &ip6_tnl_net_id, .size = sizeof(struct ip6_tnl_net), - .async = true, }; /** diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index a482b854eeea..60b771f49fb5 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -1148,7 +1148,6 @@ static struct pernet_operations vti6_net_ops = { .exit_batch = vti6_exit_batch_net, .id = &vti6_net_id, .size = sizeof(struct vti6_net), - .async = true, }; static struct xfrm6_protocol vti_esp6_protocol __read_mostly = { diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 2a38f9de45d3..298fd8b6ed17 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -258,6 +258,23 @@ static void __net_exit ip6mr_rules_exit(struct net *net) fib_rules_unregister(net->ipv6.mr6_rules_ops); rtnl_unlock(); } + +static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb) +{ + return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR); +} + +static unsigned int ip6mr_rules_seq_read(struct net *net) +{ + return fib_rules_seq_read(net, RTNL_FAMILY_IP6MR); +} + +bool ip6mr_rule_default(const struct fib_rule *rule) +{ + return fib_rule_matchall(rule) && rule->action == FR_ACT_TO_TBL && + rule->table == RT6_TABLE_DFLT && !rule->l3mdev; +} +EXPORT_SYMBOL(ip6mr_rule_default); #else #define ip6mr_for_each_table(mrt, net) \ for (mrt = net->ipv6.mrt6; mrt; mrt = NULL) @@ -295,6 +312,16 @@ static void __net_exit ip6mr_rules_exit(struct net *net) net->ipv6.mrt6 = NULL; rtnl_unlock(); } + +static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb) +{ + return 0; +} + +static unsigned int ip6mr_rules_seq_read(struct net *net) +{ + return 0; +} #endif static int ip6mr_hash_cmp(struct rhashtable_compare_arg *arg, @@ -653,10 +680,25 @@ failure: } #endif -/* - * Delete a VIF entry - */ +static int call_ip6mr_vif_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct vif_device *vif, + mifi_t vif_index, u32 tb_id) +{ + return mr_call_vif_notifiers(net, RTNL_FAMILY_IP6MR, event_type, + vif, vif_index, tb_id, + &net->ipv6.ipmr_seq); +} +static int call_ip6mr_mfc_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct mfc6_cache *mfc, u32 tb_id) +{ + return mr_call_mfc_notifiers(net, RTNL_FAMILY_IP6MR, event_type, + &mfc->_c, tb_id, &net->ipv6.ipmr_seq); +} + +/* Delete a VIF entry */ static int mif6_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { @@ -669,6 +711,11 @@ static int mif6_delete(struct mr_table *mrt, int vifi, int notify, v = &mrt->vif_table[vifi]; + if (VIF_EXISTS(mrt, vifi)) + call_ip6mr_vif_entry_notifiers(read_pnet(&mrt->net), + FIB_EVENT_VIF_DEL, v, vifi, + mrt->id); + write_lock_bh(&mrt_lock); dev = v->dev; v->dev = NULL; @@ -887,6 +934,8 @@ static int mif6_add(struct net *net, struct mr_table *mrt, if (vifi + 1 > mrt->maxvif) mrt->maxvif = vifi + 1; write_unlock_bh(&mrt_lock); + call_ip6mr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, + v, vifi, mrt->id); return 0; } @@ -940,6 +989,8 @@ static struct mfc6_cache *ip6mr_cache_alloc(void) return NULL; c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->_c.mfc_un.res.minvif = MAXMIFS; + c->_c.free = ip6mr_cache_free_rcu; + refcount_set(&c->_c.mfc_un.res.refcount, 1); return c; } @@ -1175,8 +1226,10 @@ static int ip6mr_mfc_delete(struct mr_table *mrt, struct mf6cctl *mfc, rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ip6mr_rht_params); list_del_rcu(&c->_c.list); + call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), + FIB_EVENT_ENTRY_DEL, c, mrt->id); mr6_netlink_event(mrt, c, RTM_DELROUTE); - ip6mr_cache_free(c); + mr_cache_put(&c->_c); return 0; } @@ -1203,21 +1256,63 @@ static int ip6mr_device_event(struct notifier_block *this, return NOTIFY_DONE; } +static unsigned int ip6mr_seq_read(struct net *net) +{ + ASSERT_RTNL(); + + return net->ipv6.ipmr_seq + ip6mr_rules_seq_read(net); +} + +static int ip6mr_dump(struct net *net, struct notifier_block *nb) +{ + return mr_dump(net, nb, RTNL_FAMILY_IP6MR, ip6mr_rules_dump, + ip6mr_mr_table_iter, &mrt_lock); +} + static struct notifier_block ip6_mr_notifier = { .notifier_call = ip6mr_device_event }; -/* - * Setup for IP multicast routing - */ +static const struct fib_notifier_ops ip6mr_notifier_ops_template = { + .family = RTNL_FAMILY_IP6MR, + .fib_seq_read = ip6mr_seq_read, + .fib_dump = ip6mr_dump, + .owner = THIS_MODULE, +}; + +static int __net_init ip6mr_notifier_init(struct net *net) +{ + struct fib_notifier_ops *ops; + + net->ipv6.ipmr_seq = 0; + ops = fib_notifier_ops_register(&ip6mr_notifier_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + + net->ipv6.ip6mr_notifier_ops = ops; + + return 0; +} + +static void __net_exit ip6mr_notifier_exit(struct net *net) +{ + fib_notifier_ops_unregister(net->ipv6.ip6mr_notifier_ops); + net->ipv6.ip6mr_notifier_ops = NULL; +} + +/* Setup for IP multicast routing */ static int __net_init ip6mr_net_init(struct net *net) { int err; + err = ip6mr_notifier_init(net); + if (err) + return err; + err = ip6mr_rules_init(net); if (err < 0) - goto fail; + goto ip6mr_rules_fail; #ifdef CONFIG_PROC_FS err = -ENOMEM; @@ -1235,7 +1330,8 @@ proc_cache_fail: proc_vif_fail: ip6mr_rules_exit(net); #endif -fail: +ip6mr_rules_fail: + ip6mr_notifier_exit(net); return err; } @@ -1246,12 +1342,12 @@ static void __net_exit ip6mr_net_exit(struct net *net) remove_proc_entry("ip6_mr_vif", net->proc_net); #endif ip6mr_rules_exit(net); + ip6mr_notifier_exit(net); } static struct pernet_operations ip6mr_net_ops = { .init = ip6mr_net_init, .exit = ip6mr_net_exit, - .async = true, }; int __init ip6_mr_init(void) @@ -1337,6 +1433,8 @@ static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt, if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); + call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, + c, mrt->id); mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1388,6 +1486,8 @@ static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt, ip6mr_cache_resolve(net, mrt, uc, c); ip6mr_cache_free(uc); } + call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, + c, mrt->id); mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1417,13 +1517,17 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params); list_del_rcu(&c->list); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); - ip6mr_cache_free((struct mfc6_cache *)c); + mr_cache_put(c); } if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); + call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), + FIB_EVENT_ENTRY_DEL, + (struct mfc6_cache *)c, + mrt->id); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); @@ -1443,6 +1547,7 @@ static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk) err = -EADDRINUSE; } else { rcu_assign_pointer(mrt->mroute_sk, sk); + sock_set_flag(sk, SOCK_RCU_FREE); net->ipv6.devconf_all->mc_forwarding++; } write_unlock_bh(&mrt_lock); @@ -1472,6 +1577,10 @@ int ip6mr_sk_done(struct sock *sk) if (sk == rtnl_dereference(mrt->mroute_sk)) { write_lock_bh(&mrt_lock); RCU_INIT_POINTER(mrt->mroute_sk, NULL); + /* Note that mroute_sk had SOCK_RCU_FREE set, + * so the RCU grace period before sk freeing + * is guaranteed by sk_destruct() + */ net->ipv6.devconf_all->mc_forwarding--; write_unlock_bh(&mrt_lock); inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, @@ -1485,7 +1594,6 @@ int ip6mr_sk_done(struct sock *sk) } } rtnl_unlock(); - synchronize_rcu(); return err; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index d1a0cefac273..793159d77d8a 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2921,9 +2921,9 @@ static int __net_init igmp6_proc_init(struct net *net) int err; err = -ENOMEM; - if (!proc_create("igmp6", S_IRUGO, net->proc_net, &igmp6_mc_seq_fops)) + if (!proc_create("igmp6", 0444, net->proc_net, &igmp6_mc_seq_fops)) goto out; - if (!proc_create("mcfilter6", S_IRUGO, net->proc_net, + if (!proc_create("mcfilter6", 0444, net->proc_net, &igmp6_mcf_seq_fops)) goto out_proc_net_igmp6; @@ -2997,7 +2997,6 @@ static void __net_exit igmp6_net_exit(struct net *net) static struct pernet_operations igmp6_net_ops = { .init = igmp6_net_init, .exit = igmp6_net_exit, - .async = true, }; int __init igmp6_init(void) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0a19ce3a6f7f..9de4dfb126ba 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -527,7 +527,7 @@ void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, } if (!dev->addr_len) - inc_opt = 0; + inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_ADVERTISEMENT); @@ -707,7 +707,7 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) int probes = atomic_read(&neigh->probes); if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr, - dev, 1, + dev, false, 1, IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) saddr = &ipv6_hdr(skb)->saddr; probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); @@ -1554,7 +1554,8 @@ static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, *(opt++) = (rd_len >> 3); opt += 6; - memcpy(opt, ipv6_hdr(orig_skb), rd_len - 8); + skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt, + rd_len - 8); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) @@ -1882,7 +1883,6 @@ static void __net_exit ndisc_net_exit(struct net *net) static struct pernet_operations ndisc_net_ops = { .init = ndisc_net_init, .exit = ndisc_net_exit, - .async = true, }; int __init ndisc_init(void) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index d95ceca7ff8f..531d6957af36 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -21,18 +21,19 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); + struct sock *sk = sk_to_full_sk(skb->sk); unsigned int hh_len; struct dst_entry *dst; struct flowi6 fl6 = { - .flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, + .flowi6_oif = sk ? sk->sk_bound_dev_if : 0, .flowi6_mark = skb->mark, - .flowi6_uid = sock_net_uid(net, skb->sk), + .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, .saddr = iph->saddr, }; int err; - dst = ip6_route_output(net, skb->sk, &fl6); + dst = ip6_route_output(net, sk, &fl6); err = dst->error; if (err) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@ -50,7 +51,7 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) { skb_dst_set(skb, NULL); - dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0); + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); skb_dst_set(skb, dst); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 3c36a4c77f29..65c9e1a58305 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1921,7 +1921,6 @@ static void __net_exit ip6_tables_net_exit(struct net *net) static struct pernet_operations ip6_tables_net_ops = { .init = ip6_tables_net_init, .exit = ip6_tables_net_exit, - .async = true, }; static int __init ip6_tables_init(void) diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 910a27318f58..d12f511929f5 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -48,10 +48,6 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, } fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - if ((flags & XT_RPFILTER_LOOSE) == 0) { - fl6.flowi6_oif = dev->ifindex; - lookup_flags |= RT6_LOOKUP_F_IFACE; - } rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags); if (rt->dst.error) diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index 32f98bc06900..c87b48359e8f 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -103,7 +103,6 @@ static void __net_exit defrag6_net_exit(struct net *net) static struct pernet_operations defrag6_net_ops = { .exit = defrag6_net_exit, - .async = true, }; static int __init nf_defrag_init(void) diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c index d346705d6ee6..207cb35569b1 100644 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c @@ -178,7 +178,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if (skb->len <= mtu) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index 0220e584589c..b397a8fe88b9 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -390,7 +390,6 @@ static void __net_exit nf_log_ipv6_net_exit(struct net *net) static struct pernet_operations nf_log_ipv6_net_ops = { .init = nf_log_ipv6_net_init, .exit = nf_log_ipv6_net_exit, - .async = true, }; static int __init nf_log_ipv6_init(void) diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index bed57ee65f7b..6b7f075f811f 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -99,6 +99,10 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, !l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff, target, maniptype)) return false; + + /* must reload, offset might have changed */ + ipv6h = (void *)skb->data + iphdroff; + manip_addr: if (maniptype == NF_NAT_MANIP_SRC) ipv6h->saddr = target->src.u3.in6; diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 3230b3d7b11b..36be3cf0adef 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -180,7 +180,6 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, } *dest = 0; - again: rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, pkt->skb, lookup_flags); if (rt->dst.error) @@ -190,15 +189,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL)) goto put_rt_err; - if (oif && oif != rt->rt6i_idev->dev) { - /* multipath route? Try again with F_IFACE */ - if ((lookup_flags & RT6_LOOKUP_F_IFACE) == 0) { - lookup_flags |= RT6_LOOKUP_F_IFACE; - fl6.flowi6_oif = oif->ifindex; - ip6_rt_put(rt); - goto again; - } - } + if (oif && oif != rt->rt6i_idev->dev) + goto put_rt_err; switch (priv->result) { case NFT_FIB_RESULT_OIF: diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 318c6e914234..d12c55dad7d1 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -240,7 +240,6 @@ static void __net_init ping_v6_proc_exit_net(struct net *net) static struct pernet_operations ping_v6_net_ops = { .init = ping_v6_proc_init_net, .exit = ping_v6_proc_exit_net, - .async = true, }; #endif diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 1678cf037688..6e57028d2e91 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -290,7 +290,7 @@ int snmp6_register_dev(struct inet6_dev *idev) if (!net->mib.proc_net_devsnmp6) return -ENOENT; - p = proc_create_data(idev->dev->name, S_IRUGO, + p = proc_create_data(idev->dev->name, 0444, net->mib.proc_net_devsnmp6, &snmp6_dev_seq_fops, idev); if (!p) @@ -314,11 +314,11 @@ int snmp6_unregister_dev(struct inet6_dev *idev) static int __net_init ipv6_proc_init_net(struct net *net) { - if (!proc_create("sockstat6", S_IRUGO, net->proc_net, + if (!proc_create("sockstat6", 0444, net->proc_net, &sockstat6_seq_fops)) return -ENOMEM; - if (!proc_create("snmp6", S_IRUGO, net->proc_net, &snmp6_seq_fops)) + if (!proc_create("snmp6", 0444, net->proc_net, &snmp6_seq_fops)) goto proc_snmp6_fail; net->mib.proc_net_devsnmp6 = proc_mkdir("dev_snmp6", net->proc_net); @@ -343,7 +343,6 @@ static void __net_exit ipv6_proc_exit_net(struct net *net) static struct pernet_operations ipv6_proc_ops = { .init = ipv6_proc_init_net, .exit = ipv6_proc_exit_net, - .async = true, }; int __init ipv6_misc_proc_init(void) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 10a4ac4933b7..5eb9b08947ed 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1318,7 +1318,7 @@ static const struct file_operations raw6_seq_fops = { static int __net_init raw6_init_net(struct net *net) { - if (!proc_create("raw6", S_IRUGO, net->proc_net, &raw6_seq_fops)) + if (!proc_create("raw6", 0444, net->proc_net, &raw6_seq_fops)) return -ENOMEM; return 0; @@ -1332,7 +1332,6 @@ static void __net_exit raw6_exit_net(struct net *net) static struct pernet_operations raw6_net_ops = { .init = raw6_init_net, .exit = raw6_exit_net, - .async = true, }; int __init raw6_proc_init(void) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index b5da69c83123..08a139f14d0f 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -650,10 +650,6 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net) table[1].data = &net->ipv6.frags.low_thresh; table[1].extra2 = &net->ipv6.frags.high_thresh; table[2].data = &net->ipv6.frags.timeout; - - /* Don't export sysctls to unprivileged users */ - if (net->user_ns != &init_user_ns) - table[0].procname = NULL; } hdr = register_net_sysctl(net, "net/ipv6", table); @@ -733,7 +729,6 @@ static void __net_exit ipv6_frags_exit_net(struct net *net) static struct pernet_operations ip6_frags_ops = { .init = ipv6_frags_init_net, .exit = ipv6_frags_exit_net, - .async = true, }; int __init ipv6_frag_init(void) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f0ae58424c45..ba8d5df50ebe 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -128,7 +128,7 @@ struct uncached_list { static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); -static void rt6_uncached_list_add(struct rt6_info *rt) +void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); @@ -139,7 +139,7 @@ static void rt6_uncached_list_add(struct rt6_info *rt) spin_unlock_bh(&ul->lock); } -static void rt6_uncached_list_del(struct rt6_info *rt) +void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->rt6i_uncached)) { struct uncached_list *ul = rt->rt6i_uncached_list; @@ -1514,7 +1514,30 @@ static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt) } } -static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) +static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, + struct rt6_info *rt, int mtu) +{ + /* If the new MTU is lower than the route PMTU, this new MTU will be the + * lowest MTU in the path: always allow updating the route PMTU to + * reflect PMTU decreases. + * + * If the new MTU is higher, and the route PMTU is equal to the local + * MTU, this means the old MTU is the lowest in the path, so allow + * updating it: if other nodes now have lower MTUs, PMTU discovery will + * handle this. + */ + + if (dst_mtu(&rt->dst) >= mtu) + return true; + + if (dst_mtu(&rt->dst) == idev->cnf.mtu6) + return true; + + return false; +} + +static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, + struct rt6_info *rt, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@ -1523,20 +1546,22 @@ static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, lockdep_is_held(&rt6_exception_lock)); - if (bucket) { - for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { - hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { - struct rt6_info *entry = rt6_ex->rt6i; - /* For RTF_CACHE with rt6i_pmtu == 0 - * (i.e. a redirected route), - * the metrics of its rt->dst.from has already - * been updated. - */ - if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu) - entry->rt6i_pmtu = mtu; - } - bucket++; + if (!bucket) + return; + + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + + /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected + * route), the metrics of its rt->dst.from have already + * been updated. + */ + if (entry->rt6i_pmtu && + rt6_mtu_change_route_allowed(idev, entry, mtu)) + entry->rt6i_pmtu = mtu; } + bucket++; } } @@ -1846,7 +1871,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, struct flow_keys hash_keys; u32 mhash; - switch (net->ipv6.sysctl.multipath_hash_policy) { + switch (ip6_multipath_hash_policy(net)) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; @@ -2550,7 +2575,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net, static int ip6_route_check_nh_onlink(struct net *net, struct fib6_config *cfg, - struct net_device *dev, + const struct net_device *dev, struct netlink_ext_ack *extack) { u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; @@ -2626,6 +2651,79 @@ out: return err; } +static int ip6_validate_gw(struct net *net, struct fib6_config *cfg, + struct net_device **_dev, struct inet6_dev **idev, + struct netlink_ext_ack *extack) +{ + const struct in6_addr *gw_addr = &cfg->fc_gateway; + int gwa_type = ipv6_addr_type(gw_addr); + bool skip_dev = gwa_type & IPV6_ADDR_LINKLOCAL ? false : true; + const struct net_device *dev = *_dev; + bool need_addr_check = !dev; + int err = -EINVAL; + + /* if gw_addr is local we will fail to detect this in case + * address is still TENTATIVE (DAD in progress). rt6_lookup() + * will return already-added prefix route via interface that + * prefix route was assigned to, which might be non-loopback. + */ + if (dev && + ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { + NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); + goto out; + } + + if (gwa_type != (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_UNICAST)) { + /* IPv6 strictly inhibits using not link-local + * addresses as nexthop address. + * Otherwise, router will not able to send redirects. + * It is very good, but in some (rare!) circumstances + * (SIT, PtP, NBMA NOARP links) it is handy to allow + * some exceptions. --ANK + * We allow IPv4-mapped nexthops to support RFC4798-type + * addressing + */ + if (!(gwa_type & (IPV6_ADDR_UNICAST | IPV6_ADDR_MAPPED))) { + NL_SET_ERR_MSG(extack, "Invalid gateway address"); + goto out; + } + + if (cfg->fc_flags & RTNH_F_ONLINK) + err = ip6_route_check_nh_onlink(net, cfg, dev, extack); + else + err = ip6_route_check_nh(net, cfg, _dev, idev); + + if (err) + goto out; + } + + /* reload in case device was changed */ + dev = *_dev; + + err = -EINVAL; + if (!dev) { + NL_SET_ERR_MSG(extack, "Egress device not specified"); + goto out; + } else if (dev->flags & IFF_LOOPBACK) { + NL_SET_ERR_MSG(extack, + "Egress device can not be loopback device for this route"); + goto out; + } + + /* if we did not check gw_addr above, do so now that the + * egress device has been resolved. + */ + if (need_addr_check && + ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { + NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); + goto out; + } + + err = 0; +out: + return err; +} + static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, struct netlink_ext_ack *extack) { @@ -2808,61 +2906,11 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, } if (cfg->fc_flags & RTF_GATEWAY) { - const struct in6_addr *gw_addr; - int gwa_type; - - gw_addr = &cfg->fc_gateway; - gwa_type = ipv6_addr_type(gw_addr); - - /* if gw_addr is local we will fail to detect this in case - * address is still TENTATIVE (DAD in progress). rt6_lookup() - * will return already-added prefix route via interface that - * prefix route was assigned to, which might be non-loopback. - */ - err = -EINVAL; - if (ipv6_chk_addr_and_flags(net, gw_addr, - gwa_type & IPV6_ADDR_LINKLOCAL ? - dev : NULL, 0, 0)) { - NL_SET_ERR_MSG(extack, "Invalid gateway address"); + err = ip6_validate_gw(net, cfg, &dev, &idev, extack); + if (err) goto out; - } - rt->rt6i_gateway = *gw_addr; - - if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) { - /* IPv6 strictly inhibits using not link-local - addresses as nexthop address. - Otherwise, router will not able to send redirects. - It is very good, but in some (rare!) circumstances - (SIT, PtP, NBMA NOARP links) it is handy to allow - some exceptions. --ANK - We allow IPv4-mapped nexthops to support RFC4798-type - addressing - */ - if (!(gwa_type & (IPV6_ADDR_UNICAST | - IPV6_ADDR_MAPPED))) { - NL_SET_ERR_MSG(extack, - "Invalid gateway address"); - goto out; - } - if (cfg->fc_flags & RTNH_F_ONLINK) { - err = ip6_route_check_nh_onlink(net, cfg, dev, - extack); - } else { - err = ip6_route_check_nh(net, cfg, &dev, &idev); - } - if (err) - goto out; - } - err = -EINVAL; - if (!dev) { - NL_SET_ERR_MSG(extack, "Egress device not specified"); - goto out; - } else if (dev->flags & IFF_LOOPBACK) { - NL_SET_ERR_MSG(extack, - "Egress device can not be loopback device for this route"); - goto out; - } + rt->rt6i_gateway = cfg->fc_gateway; } err = -ENODEV; @@ -3876,25 +3924,13 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) Since RFC 1981 doesn't include administrative MTU increase update PMTU increase is a MUST. (i.e. jumbo frame) */ - /* - If new MTU is less than route PMTU, this new MTU will be the - lowest MTU in the path, update the route PMTU to reflect PMTU - decreases; if new MTU is greater than route PMTU, and the - old MTU is the lowest MTU in the path, update the route PMTU - to reflect the increase. In this case if the other nodes' MTU - also have the lowest MTU, TOO BIG MESSAGE will be lead to - PMTU discovery. - */ if (rt->dst.dev == arg->dev && - dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { spin_lock_bh(&rt6_exception_lock); - if (dst_mtu(&rt->dst) >= arg->mtu || - (dst_mtu(&rt->dst) < arg->mtu && - dst_mtu(&rt->dst) == idev->cnf.mtu6)) { + if (dst_metric_raw(&rt->dst, RTAX_MTU) && + rt6_mtu_change_route_allowed(idev, rt, arg->mtu)) dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); - } - rt6_exceptions_update_pmtu(rt, arg->mtu); + rt6_exceptions_update_pmtu(idev, rt, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } return 0; @@ -4166,6 +4202,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, r_cfg.fc_encap_type = nla_get_u16(nla); } + r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); rt = ip6_route_info_create(&r_cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); @@ -5030,7 +5067,7 @@ static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS proc_create("ipv6_route", 0, net->proc_net, &ipv6_route_proc_fops); - proc_create("rt6_stats", S_IRUGO, net->proc_net, &rt6_stats_seq_fops); + proc_create("rt6_stats", 0444, net->proc_net, &rt6_stats_seq_fops); #endif return 0; } @@ -5046,7 +5083,6 @@ static void __net_exit ip6_route_net_exit_late(struct net *net) static struct pernet_operations ip6_route_net_ops = { .init = ip6_route_net_init, .exit = ip6_route_net_exit, - .async = true, }; static int __net_init ipv6_inetpeer_init(struct net *net) @@ -5072,13 +5108,11 @@ static void __net_exit ipv6_inetpeer_exit(struct net *net) static struct pernet_operations ipv6_inetpeer_ops = { .init = ipv6_inetpeer_init, .exit = ipv6_inetpeer_exit, - .async = true, }; static struct pernet_operations ip6_route_net_late_ops = { .init = ip6_route_net_init_late, .exit = ip6_route_net_exit_late, - .async = true, }; static struct notifier_block ip6_route_dev_notifier = { diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index c3f13c3bd8a9..7f5621d09571 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -395,7 +395,6 @@ static void __net_exit seg6_net_exit(struct net *net) static struct pernet_operations ip6_segments_ops = { .init = seg6_net_init, .exit = seg6_net_exit, - .async = true, }; static const struct genl_ops seg6_genl_ops[] = { diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index bd6cc688bd19..7a78dcfda68a 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -93,7 +93,8 @@ static void set_tun_src(struct net *net, struct net_device *dev, /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) { - struct net *net = dev_net(skb_dst(skb)->dev); + struct dst_entry *dst = skb_dst(skb); + struct net *net = dev_net(dst->dev); struct ipv6hdr *hdr, *inner_hdr; struct ipv6_sr_hdr *isrh; int hdrlen, tot_len, err; @@ -134,7 +135,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) isrh->nexthdr = proto; hdr->daddr = isrh->segments[isrh->first_segment]; - set_tun_src(net, skb->dev, &hdr->daddr, &hdr->saddr); + set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { @@ -418,7 +419,7 @@ static int seg6_build_state(struct nlattr *nla, slwt = seg6_lwt_lwtunnel(newts); - err = dst_cache_init(&slwt->cache, GFP_KERNEL); + err = dst_cache_init(&slwt->cache, GFP_ATOMIC); if (err) { kfree(newts); return err; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 182db078f01e..1522bcfd253f 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -182,7 +182,7 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel *t = netdev_priv(dev); - if (dev == sitn->fb_tunnel_dev) { + if (dev == sitn->fb_tunnel_dev || !sitn->fb_tunnel_dev) { ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0); t->ip6rd.relay_prefix = 0; t->ip6rd.prefixlen = 16; @@ -1578,6 +1578,13 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; + if (tb[IFLA_MTU]) { + u32 mtu = nla_get_u32(tb[IFLA_MTU]); + + if (mtu >= IPV6_MIN_MTU && mtu <= 0xFFF8 - dev->hard_header_len) + dev->mtu = mtu; + } + #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) err = ipip6_tunnel_update_6rd(nt, &ip6rd); @@ -1828,6 +1835,9 @@ static int __net_init sit_init_net(struct net *net) sitn->tunnels[2] = sitn->tunnels_r; sitn->tunnels[3] = sitn->tunnels_r_l; + if (!net_has_fallback_tunnels(net)) + return 0; + sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0", NET_NAME_UNKNOWN, ipip6_tunnel_setup); @@ -1878,7 +1888,6 @@ static struct pernet_operations sit_net_ops = { .exit_batch = sit_exit_batch_net, .id = &sit_net_id, .size = sizeof(struct sit_net), - .async = true, }; static void __exit sit_cleanup(void) diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 966c42af92f4..6fbdef630152 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -278,7 +278,6 @@ static void __net_exit ipv6_sysctl_net_exit(struct net *net) static struct pernet_operations ipv6_sysctl_net_ops = { .init = ipv6_sysctl_net_init, .exit = ipv6_sysctl_net_exit, - .async = true, }; static struct ctl_table_header *ip6_header; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5425d7b100ee..883df0ad5bfe 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2007,7 +2007,6 @@ static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, .exit_batch = tcpv6_net_exit_batch, - .async = true, }; int __init tcpv6_init(void) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 52e3ea0e6f50..ad30f5e31969 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1509,34 +1509,34 @@ void udp6_proc_exit(struct net *net) /* ------------------------------------------------------------------------ */ struct proto udpv6_prot = { - .name = "UDPv6", - .owner = THIS_MODULE, - .close = udp_lib_close, - .connect = ip6_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = udp_ioctl, - .init = udp_init_sock, - .destroy = udpv6_destroy_sock, - .setsockopt = udpv6_setsockopt, - .getsockopt = udpv6_getsockopt, - .sendmsg = udpv6_sendmsg, - .recvmsg = udpv6_recvmsg, - .release_cb = ip6_datagram_release_cb, - .hash = udp_lib_hash, - .unhash = udp_lib_unhash, - .rehash = udp_v6_rehash, - .get_port = udp_v6_get_port, - .memory_allocated = &udp_memory_allocated, - .sysctl_mem = sysctl_udp_mem, - .sysctl_wmem = &sysctl_udp_wmem_min, - .sysctl_rmem = &sysctl_udp_rmem_min, - .obj_size = sizeof(struct udp6_sock), - .h.udp_table = &udp_table, + .name = "UDPv6", + .owner = THIS_MODULE, + .close = udp_lib_close, + .connect = ip6_datagram_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .init = udp_init_sock, + .destroy = udpv6_destroy_sock, + .setsockopt = udpv6_setsockopt, + .getsockopt = udpv6_getsockopt, + .sendmsg = udpv6_sendmsg, + .recvmsg = udpv6_recvmsg, + .release_cb = ip6_datagram_release_cb, + .hash = udp_lib_hash, + .unhash = udp_lib_unhash, + .rehash = udp_v6_rehash, + .get_port = udp_v6_get_port, + .memory_allocated = &udp_memory_allocated, + .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), + .obj_size = sizeof(struct udp6_sock), + .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT - .compat_setsockopt = compat_udpv6_setsockopt, - .compat_getsockopt = compat_udpv6_getsockopt, + .compat_setsockopt = compat_udpv6_setsockopt, + .compat_getsockopt = compat_udpv6_getsockopt, #endif - .diag_destroy = udp_abort, + .diag_destroy = udp_abort, }; static struct inet_protosw udpv6_protosw = { diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index f3839780dc31..14ae32bb1f3d 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -123,7 +123,6 @@ static void __net_exit udplite6_proc_exit_net(struct net *net) static struct pernet_operations udplite6_net_ops = { .init = udplite6_proc_init_net, .exit = udplite6_proc_exit_net, - .async = true, }; int __init udplite6_proc_init(void) diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index bb935a3b7fea..de1b0b8c53b0 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -92,7 +92,8 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) skb_reset_network_header(skb); skb_mac_header_rebuild(skb); - eth_hdr(skb)->h_proto = skb->protocol; + if (skb->mac_len) + eth_hdr(skb)->h_proto = skb->protocol; err = 0; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8ae87d4ec5ff..5959ce9620eb 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -82,7 +82,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if ((!skb_is_gso(skb) && skb->len > mtu) || (skb_is_gso(skb) && - skb_gso_network_seglen(skb) > ip6_skb_dst_mtu(skb))) { + !skb_gso_validate_network_len(skb, ip6_skb_dst_mtu(skb)))) { skb->dev = dst->dev; skb->protocol = htons(ETH_P_IPV6); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 88cd0c90fa81..416fe67271a9 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -113,6 +113,9 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; xdst->u.rt6.rt6i_dst = rt->rt6i_dst; xdst->u.rt6.rt6i_src = rt->rt6i_src; + INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached); + rt6_uncached_list_add(&xdst->u.rt6); + atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache); return 0; } @@ -244,6 +247,8 @@ 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 (xdst->u.rt6.rt6i_uncached_list) + rt6_uncached_list_del(&xdst->u.rt6); xfrm_dst_destroy(xdst); } @@ -395,7 +400,6 @@ static void __net_exit xfrm6_net_exit(struct net *net) static struct pernet_operations xfrm6_net_ops = { .init = xfrm6_net_init, .exit = xfrm6_net_exit, - .async = true, }; int __init xfrm6_init(void) diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index a9673619e0e9..f85f0d7480ac 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -353,7 +353,6 @@ static struct pernet_operations xfrm6_tunnel_net_ops = { .exit = xfrm6_tunnel_net_exit, .id = &xfrm6_tunnel_net_id, .size = sizeof(struct xfrm6_tunnel_net), - .async = true, }; static int __init xfrm6_tunnel_init(void) |