diff options
Diffstat (limited to 'net/ipv6')
39 files changed, 1039 insertions, 917 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ea71e4b0ab7a..6794ddf0547c 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -278,6 +278,7 @@ config IPV6_SUBTREES config IPV6_MROUTE bool "IPv6: multicast routing" depends on IPV6 + select IP_MROUTE_COMMON ---help--- Experimental support for IPv6 multicast forwarding. If unsure, say N. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e1846b97ee69..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; } @@ -1459,6 +1447,21 @@ static bool ipv6_use_optimistic_addr(struct net *net, #endif } +static bool ipv6_allow_optimistic_dad(struct net *net, + struct inet6_dev *idev) +{ +#ifdef CONFIG_IPV6_OPTIMISTIC_DAD + if (!idev) + return false; + if (!net->ipv6.devconf_all->optimistic_dad && !idev->cnf.optimistic_dad) + return false; + + return true; +#else + return false; +#endif +} + static int ipv6_get_saddr_eval(struct net *net, struct ipv6_saddr_score *score, struct ipv6_saddr_dst *dst, @@ -1836,22 +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. */ @@ -1968,6 +1991,8 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) spin_lock_bh(&ifp->lock); addrconf_del_dad_work(ifp); ifp->flags |= IFA_F_TENTATIVE; + if (dad_failed) + ifp->flags &= ~IFA_F_OPTIMISTIC; spin_unlock_bh(&ifp->lock); if (dad_failed) ipv6_ifa_notify(0, ifp); @@ -2581,7 +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; } @@ -4244,7 +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; } @@ -4408,8 +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(); } @@ -4500,6 +4525,9 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, (ifp->flags & IFA_F_TEMPORARY || ifp->prefix_len != 64)) return -EINVAL; + if (!(ifp->flags & IFA_F_TENTATIVE) || ifp->flags & IFA_F_DADFAILED) + ifa_flags &= ~IFA_F_OPTIMISTIC; + timeout = addrconf_timeout_fixup(valid_lft, HZ); if (addrconf_finite_timeout(timeout)) { expires = jiffies_to_clock_t(timeout * HZ); @@ -4573,6 +4601,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct in6_addr *pfx, *peer_pfx; struct inet6_ifaddr *ifa; struct net_device *dev; + struct inet6_dev *idev; u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME; u32 ifa_flags; int err; @@ -4606,7 +4635,19 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, /* We ignore other flags so far. */ ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | - IFA_F_NOPREFIXROUTE | IFA_F_MCAUTOJOIN; + IFA_F_NOPREFIXROUTE | IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC; + + idev = ipv6_find_idev(dev); + if (IS_ERR(idev)) + return PTR_ERR(idev); + + if (!ipv6_allow_optimistic_dad(net, idev)) + ifa_flags &= ~IFA_F_OPTIMISTIC; + + if (ifa_flags & IFA_F_NODAD && ifa_flags & IFA_F_OPTIMISTIC) { + NL_SET_ERR_MSG(extack, "IFA_F_NODAD and IFA_F_OPTIMISTIC are mutually exclusive"); + return -EINVAL; + } ifa = ipv6_get_ifaddr(net, pfx, dev, 1); if (!ifa) { diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 8e085cc05aeb..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); @@ -78,7 +82,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (ifindex == 0) { struct rt6_info *rt; - rt = rt6_lookup(net, addr, NULL, 0, 0); + rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; ip6_rt_put(rt); @@ -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; @@ -552,4 +555,3 @@ void ac6_proc_exit(struct net *net) remove_proc_entry("anycast6", net->proc_net); } #endif - 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/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 11025f8d124b..b643f5ce6c80 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -279,4 +279,3 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, return nexthdr; } EXPORT_SYMBOL(ipv6_find_hdr); - diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b240f24a6e52..df113c7b5fc8 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -61,11 +61,13 @@ unsigned int fib6_rules_seq_read(struct net *net) } struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, + const struct sk_buff *skb, int flags, pol_lookup_t lookup) { if (net->ipv6.fib6_has_custom_rules) { struct fib_lookup_arg arg = { .lookup_ptr = lookup, + .lookup_data = skb, .flags = FIB_LOOKUP_NOREF, }; @@ -80,11 +82,11 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, } else { struct rt6_info *rt; - rt = lookup(net, net->ipv6.fib6_local_tbl, fl6, flags); + rt = lookup(net, net->ipv6.fib6_local_tbl, fl6, skb, flags); if (rt != net->ipv6.ip6_null_entry && rt->dst.error != -EAGAIN) return &rt->dst; ip6_rt_put(rt); - rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error != -EAGAIN) return &rt->dst; ip6_rt_put(rt); @@ -130,7 +132,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, goto out; } - rt = lookup(net, table, flp6, flags); + rt = lookup(net, table, flp6, arg->lookup_data, flags); if (rt != net->ipv6.ip6_null_entry) { struct fib6_rule *r = (struct fib6_rule *)rule; @@ -223,6 +225,17 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) if (r->tclass && r->tclass != ip6_tclass(fl6->flowlabel)) return 0; + if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto)) + return 0; + + if (fib_rule_port_range_set(&rule->sport_range) && + !fib_rule_port_inrange(&rule->sport_range, fl6->fl6_sport)) + return 0; + + if (fib_rule_port_range_set(&rule->dport_range) && + !fib_rule_port_inrange(&rule->dport_range, fl6->fl6_dport)) + return 0; + return 1; } @@ -258,12 +271,26 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule6->dst.plen = frh->dst_len; rule6->tclass = frh->tos; + if (fib_rule_requires_fldissect(rule)) + net->ipv6.fib6_rules_require_fldissect++; + net->ipv6.fib6_has_custom_rules = true; err = 0; errout: return err; } +static int fib6_rule_delete(struct fib_rule *rule) +{ + struct net *net = rule->fr_net; + + if (net->ipv6.fib6_rules_require_fldissect && + fib_rule_requires_fldissect(rule)) + net->ipv6.fib6_rules_require_fldissect--; + + return 0; +} + static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { @@ -323,6 +350,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .match = fib6_rule_match, .suppress = fib6_rule_suppress, .configure = fib6_rule_configure, + .delete = fib6_rule_delete, .compare = fib6_rule_compare, .fill = fib6_rule_fill, .nlmsg_payload = fib6_rule_nlmsg_payload, @@ -350,6 +378,7 @@ static int __net_init fib6_rules_net_init(struct net *net) goto out_fib6_rules_ops; net->ipv6.fib6_rules_ops = ops; + net->ipv6.fib6_rules_require_fldissect = 0; out: return err; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 6ae5dd3f4d0d..d8c4b6374377 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -522,7 +522,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, fl6.fl6_icmp_type = type; fl6.fl6_icmp_code = code; fl6.flowi6_uid = sock_net_uid(net, NULL); - fl6.mp_hash = rt6_multipath_hash(&fl6, skb); + fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL); security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); sk = icmpv6_xmit_lock(net); @@ -629,7 +629,8 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, skb_pull(skb2, nhs); skb_reset_network_header(skb2); - rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0); + rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, + skb, 0); if (rt && rt->dst.dev) skb2->dev = rt->dst.dev; diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c index ec43d18b5ff9..547515e8450a 100644 --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -73,6 +73,11 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) err = udplite_checksum_init(skb, uh); if (err) return err; + + if (UDP_SKB_CB(skb)->partial_cov) { + skb->csum = ip6_compute_pseudo(skb, proto); + return 0; + } } /* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 92b8d8c75eed..908b8e5b615a 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -299,11 +299,12 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) } struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, + const struct sk_buff *skb, int flags, pol_lookup_t lookup) { struct rt6_info *rt; - rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error == -EAGAIN) { ip6_rt_put(rt); rt = net->ipv6.ip6_null_entry; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 3dab664ff503..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; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 3c353125546d..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; @@ -695,9 +696,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, else fl6->daddr = tunnel->parms.raddr; - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; - /* Push GRE header. */ protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto; @@ -720,14 +718,20 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, fl6->flowi6_uid = sock_net_uid(dev_net(dev), NULL); dsfield = key->tos; - flags = key->tun_flags & (TUNNEL_CSUM | TUNNEL_KEY); + flags = key->tun_flags & + (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); tunnel->tun_hlen = gre_calc_hlen(flags); gre_build_header(skb, tunnel->tun_hlen, flags, protocol, - tunnel_id_to_key32(tun_info->key.tun_id), 0); + tunnel_id_to_key32(tun_info->key.tun_id), + (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) + : 0); } else { + if (tunnel->parms.o_flags & TUNNEL_SEQ) + tunnel->o_seqno++; + gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno)); @@ -902,6 +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; @@ -944,6 +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) { @@ -1053,7 +1062,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, - p->link, strict); + p->link, NULL, strict); if (!rt) return; @@ -1469,6 +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); @@ -1784,6 +1795,12 @@ static void ip6gre_tap_setup(struct net_device *dev) netif_keep_dst(dev); } +bool is_ip6gretap_dev(const struct net_device *dev) +{ + return dev->netdev_ops == &ip6gre_tap_netdev_ops; +} +EXPORT_SYMBOL_GPL(is_ip6gretap_dev); + static bool ip6gre_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *ipencap) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 997c7f19ad62..2c7f09c3c39e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -71,7 +71,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) && - ((mroute6_socket(net, skb) && + ((mroute6_is_socket(net, skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr))) { @@ -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 4b15fe928278..df4c29f7d59f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -679,7 +679,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Try to guess incoming interface */ rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, - NULL, 0, 0); + NULL, 0, skb2, 0); if (rt && rt->dst.dev) skb2->dev = rt->dst.dev; @@ -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 @@ -1444,7 +1448,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, - p->link, strict); + p->link, NULL, strict); if (!rt) return; @@ -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); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index fa3ae1cb50d3..60b771f49fb5 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -645,7 +645,7 @@ static void vti6_link_config(struct ip6_tnl *t) (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, - p->link, strict); + p->link, NULL, strict); if (rt) tdev = rt->dst.dev; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 9f6cace9c817..298fd8b6ed17 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -20,7 +20,6 @@ #include <linux/types.h> #include <linux/sched.h> #include <linux/errno.h> -#include <linux/timer.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/fcntl.h> @@ -32,11 +31,9 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> -#include <linux/slab.h> #include <linux/compat.h> #include <net/protocol.h> #include <linux/skbuff.h> -#include <net/sock.h> #include <net/raw.h> #include <linux/notifier.h> #include <linux/if_arp.h> @@ -54,30 +51,12 @@ #include <net/ip6_checksum.h> #include <linux/netconf.h> -struct mr6_table { - struct list_head list; - possible_net_t net; - u32 id; - struct sock *mroute6_sk; - struct timer_list ipmr_expire_timer; - struct list_head mfc6_unres_queue; - struct list_head mfc6_cache_array[MFC6_LINES]; - struct mif_device vif6_table[MAXMIFS]; - int maxvif; - atomic_t cache_resolve_queue_len; - bool mroute_do_assert; - bool mroute_do_pim; -#ifdef CONFIG_IPV6_PIMSM_V2 - int mroute_reg_vif_num; -#endif -}; - struct ip6mr_rule { struct fib_rule common; }; struct ip6mr_result { - struct mr6_table *mrt; + struct mr_table *mrt; }; /* Big lock, protecting vif table, mrt cache and mroute socket state. @@ -86,11 +65,7 @@ struct ip6mr_result { static DEFINE_RWLOCK(mrt_lock); -/* - * Multicast router control variables - */ - -#define MIF_EXISTS(_mrt, _idx) ((_mrt)->vif6_table[_idx].dev != NULL) +/* Multicast router control variables */ /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); @@ -105,30 +80,45 @@ static DEFINE_SPINLOCK(mfc_unres_lock); static struct kmem_cache *mrt_cachep __read_mostly; -static struct mr6_table *ip6mr_new_table(struct net *net, u32 id); -static void ip6mr_free_table(struct mr6_table *mrt); +static struct mr_table *ip6mr_new_table(struct net *net, u32 id); +static void ip6mr_free_table(struct mr_table *mrt); -static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, +static void ip6_mr_forward(struct net *net, struct mr_table *mrt, struct sk_buff *skb, struct mfc6_cache *cache); -static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, +static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); -static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, - struct mfc6_cache *c, struct rtmsg *rtm); -static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, +static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, int cmd); -static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt); +static void mrt6msg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt); static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb); -static void mroute_clean_tables(struct mr6_table *mrt, bool all); +static void mroute_clean_tables(struct mr_table *mrt, bool all); static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES #define ip6mr_for_each_table(mrt, net) \ list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list) -static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) +static struct mr_table *ip6mr_mr_table_iter(struct net *net, + struct mr_table *mrt) { - struct mr6_table *mrt; + struct mr_table *ret; + + if (!mrt) + ret = list_entry_rcu(net->ipv6.mr6_tables.next, + struct mr_table, list); + else + ret = list_entry_rcu(mrt->list.next, + struct mr_table, list); + + if (&ret->list == &net->ipv6.mr6_tables) + return NULL; + return ret; +} + +static struct mr_table *ip6mr_get_table(struct net *net, u32 id) +{ + struct mr_table *mrt; ip6mr_for_each_table(mrt, net) { if (mrt->id == id) @@ -138,7 +128,7 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) } static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, - struct mr6_table **mrt) + struct mr_table **mrt) { int err; struct ip6mr_result res; @@ -159,7 +149,7 @@ static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { struct ip6mr_result *res = arg->result; - struct mr6_table *mrt; + struct mr_table *mrt; switch (rule->action) { case FR_ACT_TO_TBL: @@ -227,7 +217,7 @@ static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = { static int __net_init ip6mr_rules_init(struct net *net) { struct fib_rules_ops *ops; - struct mr6_table *mrt; + struct mr_table *mrt; int err; ops = fib_rules_register(&ip6mr_rules_ops_template, net); @@ -258,7 +248,7 @@ err1: static void __net_exit ip6mr_rules_exit(struct net *net) { - struct mr6_table *mrt, *next; + struct mr_table *mrt, *next; rtnl_lock(); list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) { @@ -268,17 +258,42 @@ 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) -static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) +static struct mr_table *ip6mr_mr_table_iter(struct net *net, + struct mr_table *mrt) +{ + if (!mrt) + return net->ipv6.mrt6; + return NULL; +} + +static struct mr_table *ip6mr_get_table(struct net *net, u32 id) { return net->ipv6.mrt6; } static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, - struct mr6_table **mrt) + struct mr_table **mrt) { *mrt = net->ipv6.mrt6; return 0; @@ -297,114 +312,87 @@ static void __net_exit ip6mr_rules_exit(struct net *net) net->ipv6.mrt6 = NULL; rtnl_unlock(); } -#endif -static struct mr6_table *ip6mr_new_table(struct net *net, u32 id) +static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb) { - struct mr6_table *mrt; - unsigned int i; - - mrt = ip6mr_get_table(net, id); - if (mrt) - return mrt; + return 0; +} - mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); - if (!mrt) - return NULL; - mrt->id = id; - write_pnet(&mrt->net, net); +static unsigned int ip6mr_rules_seq_read(struct net *net) +{ + return 0; +} +#endif - /* Forwarding cache */ - for (i = 0; i < MFC6_LINES; i++) - INIT_LIST_HEAD(&mrt->mfc6_cache_array[i]); +static int ip6mr_hash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct mfc6_cache_cmp_arg *cmparg = arg->key; + struct mfc6_cache *c = (struct mfc6_cache *)ptr; - INIT_LIST_HEAD(&mrt->mfc6_unres_queue); + return !ipv6_addr_equal(&c->mf6c_mcastgrp, &cmparg->mf6c_mcastgrp) || + !ipv6_addr_equal(&c->mf6c_origin, &cmparg->mf6c_origin); +} - timer_setup(&mrt->ipmr_expire_timer, ipmr_expire_process, 0); +static const struct rhashtable_params ip6mr_rht_params = { + .head_offset = offsetof(struct mr_mfc, mnode), + .key_offset = offsetof(struct mfc6_cache, cmparg), + .key_len = sizeof(struct mfc6_cache_cmp_arg), + .nelem_hint = 3, + .locks_mul = 1, + .obj_cmpfn = ip6mr_hash_cmp, + .automatic_shrinking = true, +}; -#ifdef CONFIG_IPV6_PIMSM_V2 - mrt->mroute_reg_vif_num = -1; -#endif +static void ip6mr_new_table_set(struct mr_table *mrt, + struct net *net) +{ #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES list_add_tail_rcu(&mrt->list, &net->ipv6.mr6_tables); #endif - return mrt; -} - -static void ip6mr_free_table(struct mr6_table *mrt) -{ - del_timer_sync(&mrt->ipmr_expire_timer); - mroute_clean_tables(mrt, true); - kfree(mrt); } -#ifdef CONFIG_PROC_FS - -struct ipmr_mfc_iter { - struct seq_net_private p; - struct mr6_table *mrt; - struct list_head *cache; - int ct; +static struct mfc6_cache_cmp_arg ip6mr_mr_table_ops_cmparg_any = { + .mf6c_origin = IN6ADDR_ANY_INIT, + .mf6c_mcastgrp = IN6ADDR_ANY_INIT, }; +static struct mr_table_ops ip6mr_mr_table_ops = { + .rht_params = &ip6mr_rht_params, + .cmparg_any = &ip6mr_mr_table_ops_cmparg_any, +}; -static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, - struct ipmr_mfc_iter *it, loff_t pos) +static struct mr_table *ip6mr_new_table(struct net *net, u32 id) { - struct mr6_table *mrt = it->mrt; - struct mfc6_cache *mfc; + struct mr_table *mrt; - read_lock(&mrt_lock); - for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) { - it->cache = &mrt->mfc6_cache_array[it->ct]; - list_for_each_entry(mfc, it->cache, list) - if (pos-- == 0) - return mfc; - } - read_unlock(&mrt_lock); - - spin_lock_bh(&mfc_unres_lock); - it->cache = &mrt->mfc6_unres_queue; - list_for_each_entry(mfc, it->cache, list) - if (pos-- == 0) - return mfc; - spin_unlock_bh(&mfc_unres_lock); + mrt = ip6mr_get_table(net, id); + if (mrt) + return mrt; - it->cache = NULL; - return NULL; + return mr_table_alloc(net, id, &ip6mr_mr_table_ops, + ipmr_expire_process, ip6mr_new_table_set); } -/* - * The /proc interfaces to multicast routing /proc/ip6_mr_cache /proc/ip6_mr_vif - */ - -struct ipmr_vif_iter { - struct seq_net_private p; - struct mr6_table *mrt; - int ct; -}; - -static struct mif_device *ip6mr_vif_seq_idx(struct net *net, - struct ipmr_vif_iter *iter, - loff_t pos) +static void ip6mr_free_table(struct mr_table *mrt) { - struct mr6_table *mrt = iter->mrt; - - for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { - if (!MIF_EXISTS(mrt, iter->ct)) - continue; - if (pos-- == 0) - return &mrt->vif6_table[iter->ct]; - } - return NULL; + del_timer_sync(&mrt->ipmr_expire_timer); + mroute_clean_tables(mrt, true); + rhltable_destroy(&mrt->mfc_hash); + kfree(mrt); } +#ifdef CONFIG_PROC_FS +/* The /proc interfaces to multicast routing + * /proc/ip6_mr_cache /proc/ip6_mr_vif + */ + static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(mrt_lock) { - struct ipmr_vif_iter *iter = seq->private; + struct mr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); - struct mr6_table *mrt; + struct mr_table *mrt; mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) @@ -413,26 +401,7 @@ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) iter->mrt = mrt; read_lock(&mrt_lock); - return *pos ? ip6mr_vif_seq_idx(net, seq->private, *pos - 1) - : SEQ_START_TOKEN; -} - -static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct ipmr_vif_iter *iter = seq->private; - struct net *net = seq_file_net(seq); - struct mr6_table *mrt = iter->mrt; - - ++*pos; - if (v == SEQ_START_TOKEN) - return ip6mr_vif_seq_idx(net, iter, 0); - - while (++iter->ct < mrt->maxvif) { - if (!MIF_EXISTS(mrt, iter->ct)) - continue; - return &mrt->vif6_table[iter->ct]; - } - return NULL; + return mr_vif_seq_start(seq, pos); } static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) @@ -443,19 +412,19 @@ static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) { - struct ipmr_vif_iter *iter = seq->private; - struct mr6_table *mrt = iter->mrt; + struct mr_vif_iter *iter = seq->private; + struct mr_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Interface BytesIn PktsIn BytesOut PktsOut Flags\n"); } else { - const struct mif_device *vif = v; + const struct vif_device *vif = v; const char *name = vif->dev ? vif->dev->name : "none"; seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", - vif - mrt->vif6_table, + vif - mrt->vif_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags); @@ -465,7 +434,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) static const struct seq_operations ip6mr_vif_seq_ops = { .start = ip6mr_vif_seq_start, - .next = ip6mr_vif_seq_next, + .next = mr_vif_seq_next, .stop = ip6mr_vif_seq_stop, .show = ip6mr_vif_seq_show, }; @@ -473,7 +442,7 @@ static const struct seq_operations ip6mr_vif_seq_ops = { static int ip6mr_vif_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &ip6mr_vif_seq_ops, - sizeof(struct ipmr_vif_iter)); + sizeof(struct mr_vif_iter)); } static const struct file_operations ip6mr_vif_fops = { @@ -485,72 +454,14 @@ static const struct file_operations ip6mr_vif_fops = { static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { - struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); - struct mr6_table *mrt; + struct mr_table *mrt; mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) return ERR_PTR(-ENOENT); - it->mrt = mrt; - it->cache = NULL; - return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) - : SEQ_START_TOKEN; -} - -static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct mfc6_cache *mfc = v; - struct ipmr_mfc_iter *it = seq->private; - struct net *net = seq_file_net(seq); - struct mr6_table *mrt = it->mrt; - - ++*pos; - - if (v == SEQ_START_TOKEN) - return ipmr_mfc_seq_idx(net, seq->private, 0); - - if (mfc->list.next != it->cache) - return list_entry(mfc->list.next, struct mfc6_cache, list); - - if (it->cache == &mrt->mfc6_unres_queue) - goto end_of_list; - - BUG_ON(it->cache != &mrt->mfc6_cache_array[it->ct]); - - while (++it->ct < MFC6_LINES) { - it->cache = &mrt->mfc6_cache_array[it->ct]; - if (list_empty(it->cache)) - continue; - return list_first_entry(it->cache, struct mfc6_cache, list); - } - - /* exhausted cache_array, show unresolved */ - read_unlock(&mrt_lock); - it->cache = &mrt->mfc6_unres_queue; - it->ct = 0; - - spin_lock_bh(&mfc_unres_lock); - if (!list_empty(it->cache)) - return list_first_entry(it->cache, struct mfc6_cache, list); - - end_of_list: - spin_unlock_bh(&mfc_unres_lock); - it->cache = NULL; - - return NULL; -} - -static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) -{ - struct ipmr_mfc_iter *it = seq->private; - struct mr6_table *mrt = it->mrt; - - if (it->cache == &mrt->mfc6_unres_queue) - spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == &mrt->mfc6_cache_array[it->ct]) - read_unlock(&mrt_lock); + return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) @@ -564,25 +475,25 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) "Iif Pkts Bytes Wrong Oifs\n"); } else { const struct mfc6_cache *mfc = v; - const struct ipmr_mfc_iter *it = seq->private; - struct mr6_table *mrt = it->mrt; + const struct mr_mfc_iter *it = seq->private; + struct mr_table *mrt = it->mrt; seq_printf(seq, "%pI6 %pI6 %-3hd", &mfc->mf6c_mcastgrp, &mfc->mf6c_origin, - mfc->mf6c_parent); + mfc->_c.mfc_parent); - if (it->cache != &mrt->mfc6_unres_queue) { + if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", - mfc->mfc_un.res.pkt, - mfc->mfc_un.res.bytes, - mfc->mfc_un.res.wrong_if); - for (n = mfc->mfc_un.res.minvif; - n < mfc->mfc_un.res.maxvif; n++) { - if (MIF_EXISTS(mrt, n) && - mfc->mfc_un.res.ttls[n] < 255) + mfc->_c.mfc_un.res.pkt, + mfc->_c.mfc_un.res.bytes, + mfc->_c.mfc_un.res.wrong_if); + for (n = mfc->_c.mfc_un.res.minvif; + n < mfc->_c.mfc_un.res.maxvif; n++) { + if (VIF_EXISTS(mrt, n) && + mfc->_c.mfc_un.res.ttls[n] < 255) seq_printf(seq, - " %2d:%-3d", - n, mfc->mfc_un.res.ttls[n]); + " %2d:%-3d", n, + mfc->_c.mfc_un.res.ttls[n]); } } else { /* unresolved mfc_caches don't contain @@ -597,15 +508,15 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) static const struct seq_operations ipmr_mfc_seq_ops = { .start = ipmr_mfc_seq_start, - .next = ipmr_mfc_seq_next, - .stop = ipmr_mfc_seq_stop, + .next = mr_mfc_seq_next, + .stop = mr_mfc_seq_stop, .show = ipmr_mfc_seq_show, }; static int ipmr_mfc_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &ipmr_mfc_seq_ops, - sizeof(struct ipmr_mfc_iter)); + sizeof(struct mr_mfc_iter)); } static const struct file_operations ip6mr_mfc_fops = { @@ -624,7 +535,7 @@ static int pim6_rcv(struct sk_buff *skb) struct ipv6hdr *encap; struct net_device *reg_dev = NULL; struct net *net = dev_net(skb->dev); - struct mr6_table *mrt; + struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .flowi6_mark = skb->mark, @@ -658,7 +569,7 @@ static int pim6_rcv(struct sk_buff *skb) read_lock(&mrt_lock); if (reg_vif_num >= 0) - reg_dev = mrt->vif6_table[reg_vif_num].dev; + reg_dev = mrt->vif_table[reg_vif_num].dev; if (reg_dev) dev_hold(reg_dev); read_unlock(&mrt_lock); @@ -693,7 +604,7 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); - struct mr6_table *mrt; + struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_oif = dev->ifindex, .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, @@ -736,7 +647,7 @@ static void reg_vif_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; } -static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt) +static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt) { struct net_device *dev; char name[IFNAMSIZ]; @@ -769,21 +680,41 @@ 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); +} -static int mif6_delete(struct mr6_table *mrt, int vifi, int notify, +/* Delete a VIF entry */ +static int mif6_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { - struct mif_device *v; + struct vif_device *v; struct net_device *dev; struct inet6_dev *in6_dev; if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; - v = &mrt->vif6_table[vifi]; + 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; @@ -802,7 +733,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, int notify, if (vifi + 1 == mrt->maxvif) { int tmp; for (tmp = vifi - 1; tmp >= 0; tmp--) { - if (MIF_EXISTS(mrt, tmp)) + if (VIF_EXISTS(mrt, tmp)) break; } mrt->maxvif = tmp + 1; @@ -827,23 +758,30 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, int notify, return 0; } +static inline void ip6mr_cache_free_rcu(struct rcu_head *head) +{ + struct mr_mfc *c = container_of(head, struct mr_mfc, rcu); + + kmem_cache_free(mrt_cachep, (struct mfc6_cache *)c); +} + static inline void ip6mr_cache_free(struct mfc6_cache *c) { - kmem_cache_free(mrt_cachep, c); + call_rcu(&c->_c.rcu, ip6mr_cache_free_rcu); } /* Destroy an unresolved cache entry, killing queued skbs and reporting error to netlink readers. */ -static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c) +static void ip6mr_destroy_unres(struct mr_table *mrt, struct mfc6_cache *c) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; atomic_dec(&mrt->cache_resolve_queue_len); - while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) { + while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved)) != NULL) { if (ipv6_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct ipv6hdr)); @@ -862,13 +800,13 @@ static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c) /* Timer process for all the unresolved queue. */ -static void ipmr_do_expire_process(struct mr6_table *mrt) +static void ipmr_do_expire_process(struct mr_table *mrt) { unsigned long now = jiffies; unsigned long expires = 10 * HZ; - struct mfc6_cache *c, *next; + struct mr_mfc *c, *next; - list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { + list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { /* not yet... */ unsigned long interval = c->mfc_un.unres.expires - now; @@ -878,24 +816,24 @@ static void ipmr_do_expire_process(struct mr6_table *mrt) } list_del(&c->list); - mr6_netlink_event(mrt, c, RTM_DELROUTE); - ip6mr_destroy_unres(mrt, c); + mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); + ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); } - if (!list_empty(&mrt->mfc6_unres_queue)) + if (!list_empty(&mrt->mfc_unres_queue)) mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); } static void ipmr_expire_process(struct timer_list *t) { - struct mr6_table *mrt = from_timer(mrt, t, ipmr_expire_timer); + struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer); if (!spin_trylock(&mfc_unres_lock)) { mod_timer(&mrt->ipmr_expire_timer, jiffies + 1); return; } - if (!list_empty(&mrt->mfc6_unres_queue)) + if (!list_empty(&mrt->mfc_unres_queue)) ipmr_do_expire_process(mrt); spin_unlock(&mfc_unres_lock); @@ -903,7 +841,8 @@ static void ipmr_expire_process(struct timer_list *t) /* Fill oifs list. It is called under write locked mrt_lock. */ -static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *cache, +static void ip6mr_update_thresholds(struct mr_table *mrt, + struct mr_mfc *cache, unsigned char *ttls) { int vifi; @@ -913,7 +852,7 @@ static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *ca memset(cache->mfc_un.res.ttls, 255, MAXMIFS); for (vifi = 0; vifi < mrt->maxvif; vifi++) { - if (MIF_EXISTS(mrt, vifi) && + if (VIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) @@ -925,17 +864,17 @@ static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *ca cache->mfc_un.res.lastuse = jiffies; } -static int mif6_add(struct net *net, struct mr6_table *mrt, +static int mif6_add(struct net *net, struct mr_table *mrt, struct mif6ctl *vifc, int mrtsock) { int vifi = vifc->mif6c_mifi; - struct mif_device *v = &mrt->vif6_table[vifi]; + struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct inet6_dev *in6_dev; int err; /* Is vif busy ? */ - if (MIF_EXISTS(mrt, vifi)) + if (VIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->mif6c_flags) { @@ -980,21 +919,10 @@ static int mif6_add(struct net *net, struct mr6_table *mrt, dev->ifindex, &in6_dev->cnf); } - /* - * Fill in the VIF structures - */ - v->rate_limit = vifc->vifc_rate_limit; - v->flags = vifc->mif6c_flags; - if (!mrtsock) - v->flags |= VIFF_STATIC; - v->threshold = vifc->vifc_threshold; - v->bytes_in = 0; - v->bytes_out = 0; - v->pkt_in = 0; - v->pkt_out = 0; - v->link = dev->ifindex; - if (v->flags & MIFF_REGISTER) - v->link = dev_get_iflink(dev); + /* Fill in the VIF structures */ + vif_device_init(v, dev, vifc->vifc_rate_limit, vifc->vifc_threshold, + vifc->mif6c_flags | (!mrtsock ? VIFF_STATIC : 0), + MIFF_REGISTER); /* And finish update writing critical data */ write_lock_bh(&mrt_lock); @@ -1006,78 +934,63 @@ static int mif6_add(struct net *net, struct mr6_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; } -static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt, +static struct mfc6_cache *ip6mr_cache_find(struct mr_table *mrt, const struct in6_addr *origin, const struct in6_addr *mcastgrp) { - int line = MFC6_HASH(mcastgrp, origin); - struct mfc6_cache *c; - - list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { - if (ipv6_addr_equal(&c->mf6c_origin, origin) && - ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) - return c; - } - return NULL; -} - -/* Look for a (*,*,oif) entry */ -static struct mfc6_cache *ip6mr_cache_find_any_parent(struct mr6_table *mrt, - mifi_t mifi) -{ - int line = MFC6_HASH(&in6addr_any, &in6addr_any); - struct mfc6_cache *c; - - list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) - if (ipv6_addr_any(&c->mf6c_origin) && - ipv6_addr_any(&c->mf6c_mcastgrp) && - (c->mfc_un.res.ttls[mifi] < 255)) - return c; + struct mfc6_cache_cmp_arg arg = { + .mf6c_origin = *origin, + .mf6c_mcastgrp = *mcastgrp, + }; - return NULL; + return mr_mfc_find(mrt, &arg); } /* Look for a (*,G) entry */ -static struct mfc6_cache *ip6mr_cache_find_any(struct mr6_table *mrt, +static struct mfc6_cache *ip6mr_cache_find_any(struct mr_table *mrt, struct in6_addr *mcastgrp, mifi_t mifi) { - int line = MFC6_HASH(mcastgrp, &in6addr_any); - struct mfc6_cache *c, *proxy; + struct mfc6_cache_cmp_arg arg = { + .mf6c_origin = in6addr_any, + .mf6c_mcastgrp = *mcastgrp, + }; if (ipv6_addr_any(mcastgrp)) - goto skip; - - list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) - if (ipv6_addr_any(&c->mf6c_origin) && - ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) { - if (c->mfc_un.res.ttls[mifi] < 255) - return c; - - /* It's ok if the mifi is part of the static tree */ - proxy = ip6mr_cache_find_any_parent(mrt, - c->mf6c_parent); - if (proxy && proxy->mfc_un.res.ttls[mifi] < 255) - return c; - } + return mr_mfc_find_any_parent(mrt, mifi); + return mr_mfc_find_any(mrt, mifi, &arg); +} -skip: - return ip6mr_cache_find_any_parent(mrt, mifi); +/* Look for a (S,G,iif) entry if parent != -1 */ +static struct mfc6_cache * +ip6mr_cache_find_parent(struct mr_table *mrt, + const struct in6_addr *origin, + const struct in6_addr *mcastgrp, + int parent) +{ + struct mfc6_cache_cmp_arg arg = { + .mf6c_origin = *origin, + .mf6c_mcastgrp = *mcastgrp, + }; + + return mr_mfc_find_parent(mrt, &arg, parent); } -/* - * Allocate a multicast cache entry - */ +/* Allocate a multicast cache entry */ static struct mfc6_cache *ip6mr_cache_alloc(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (!c) return NULL; - c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; - c->mfc_un.res.minvif = MAXMIFS; + 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; } @@ -1086,8 +999,8 @@ static struct mfc6_cache *ip6mr_cache_alloc_unres(void) struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (!c) return NULL; - skb_queue_head_init(&c->mfc_un.unres.unresolved); - c->mfc_un.unres.expires = jiffies + 10 * HZ; + skb_queue_head_init(&c->_c.mfc_un.unres.unresolved); + c->_c.mfc_un.unres.expires = jiffies + 10 * HZ; return c; } @@ -1095,7 +1008,7 @@ static struct mfc6_cache *ip6mr_cache_alloc_unres(void) * A cache entry has gone into a resolved state from queued */ -static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, +static void ip6mr_cache_resolve(struct net *net, struct mr_table *mrt, struct mfc6_cache *uc, struct mfc6_cache *c) { struct sk_buff *skb; @@ -1104,12 +1017,13 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, * Play the pending entries through our router */ - while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { + while ((skb = __skb_dequeue(&uc->_c.mfc_un.unres.unresolved))) { if (ipv6_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct ipv6hdr)); - if (__ip6mr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) { + if (mr_fill_mroute(mrt, skb, &c->_c, + nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; @@ -1129,9 +1043,10 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, * Called under mrt_lock. */ -static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, +static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert) { + struct sock *mroute6_sk; struct sk_buff *skb; struct mrt6msg *msg; int ret; @@ -1201,17 +1116,19 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, skb->ip_summed = CHECKSUM_UNNECESSARY; } - if (!mrt->mroute6_sk) { + rcu_read_lock(); + mroute6_sk = rcu_dereference(mrt->mroute_sk); + if (!mroute6_sk) { + rcu_read_unlock(); kfree_skb(skb); return -EINVAL; } mrt6msg_netlink_event(mrt, skb); - /* - * Deliver to user space multicast routing algorithms - */ - ret = sock_queue_rcv_skb(mrt->mroute6_sk, skb); + /* Deliver to user space multicast routing algorithms */ + ret = sock_queue_rcv_skb(mroute6_sk, skb); + rcu_read_unlock(); if (ret < 0) { net_warn_ratelimited("mroute6: pending queue full, dropping entries\n"); kfree_skb(skb); @@ -1220,19 +1137,16 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, return ret; } -/* - * Queue a packet for resolution. It gets locked cache entry! - */ - -static int -ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) +/* Queue a packet for resolution. It gets locked cache entry! */ +static int ip6mr_cache_unresolved(struct mr_table *mrt, mifi_t mifi, + struct sk_buff *skb) { + struct mfc6_cache *c; bool found = false; int err; - struct mfc6_cache *c; spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(c, &mrt->mfc6_unres_queue, list) { + list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) { if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) { found = true; @@ -1253,10 +1167,8 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) return -ENOBUFS; } - /* - * Fill in the new cache entry - */ - c->mf6c_parent = -1; + /* Fill in the new cache entry */ + c->_c.mfc_parent = -1; c->mf6c_origin = ipv6_hdr(skb)->saddr; c->mf6c_mcastgrp = ipv6_hdr(skb)->daddr; @@ -1276,20 +1188,18 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) } atomic_inc(&mrt->cache_resolve_queue_len); - list_add(&c->list, &mrt->mfc6_unres_queue); + list_add(&c->_c.list, &mrt->mfc_unres_queue); mr6_netlink_event(mrt, c, RTM_NEWROUTE); ipmr_do_expire_process(mrt); } - /* - * See if we can append the packet - */ - if (c->mfc_un.unres.unresolved.qlen > 3) { + /* See if we can append the packet */ + if (c->_c.mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; } else { - skb_queue_tail(&c->mfc_un.unres.unresolved, skb); + skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb); err = 0; } @@ -1301,29 +1211,26 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) * MFC6 cache manipulation by user space */ -static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc, +static int ip6mr_mfc_delete(struct mr_table *mrt, struct mf6cctl *mfc, int parent) { - int line; - struct mfc6_cache *c, *next; - - line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); + struct mfc6_cache *c; - list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[line], list) { - if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, - &mfc->mf6cc_mcastgrp.sin6_addr) && - (parent == -1 || parent == c->mf6c_parent)) { - write_lock_bh(&mrt_lock); - list_del(&c->list); - write_unlock_bh(&mrt_lock); + /* The entries are added/deleted only under RTNL */ + rcu_read_lock(); + c = ip6mr_cache_find_parent(mrt, &mfc->mf6cc_origin.sin6_addr, + &mfc->mf6cc_mcastgrp.sin6_addr, parent); + rcu_read_unlock(); + if (!c) + return -ENOENT; + rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ip6mr_rht_params); + list_del_rcu(&c->_c.list); - mr6_netlink_event(mrt, c, RTM_DELROUTE); - ip6mr_cache_free(c); - return 0; - } - } - return -ENOENT; + call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), + FIB_EVENT_ENTRY_DEL, c, mrt->id); + mr6_netlink_event(mrt, c, RTM_DELROUTE); + mr_cache_put(&c->_c); + return 0; } static int ip6mr_device_event(struct notifier_block *this, @@ -1331,15 +1238,15 @@ static int ip6mr_device_event(struct notifier_block *this, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); - struct mr6_table *mrt; - struct mif_device *v; + struct mr_table *mrt; + struct vif_device *v; int ct; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; ip6mr_for_each_table(mrt, net) { - v = &mrt->vif6_table[0]; + v = &mrt->vif_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (v->dev == dev) mif6_delete(mrt, ct, 1, NULL); @@ -1349,21 +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; @@ -1381,7 +1330,8 @@ proc_cache_fail: proc_vif_fail: ip6mr_rules_exit(net); #endif -fail: +ip6mr_rules_fail: + ip6mr_notifier_exit(net); return err; } @@ -1392,6 +1342,7 @@ 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 = { @@ -1452,14 +1403,14 @@ void ip6_mr_cleanup(void) kmem_cache_destroy(mrt_cachep); } -static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, +static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt, struct mf6cctl *mfc, int mrtsock, int parent) { - bool found = false; - int line; - struct mfc6_cache *uc, *c; unsigned char ttls[MAXMIFS]; - int i; + struct mfc6_cache *uc, *c; + struct mr_mfc *_uc; + bool found; + int i, err; if (mfc->mf6cc_parent >= MAXMIFS) return -ENFILE; @@ -1468,28 +1419,22 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, for (i = 0; i < MAXMIFS; i++) { if (IF_ISSET(i, &mfc->mf6cc_ifset)) ttls[i] = 1; - } - line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); - - list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { - if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, - &mfc->mf6cc_mcastgrp.sin6_addr) && - (parent == -1 || parent == mfc->mf6cc_parent)) { - found = true; - break; - } - } - - if (found) { + /* The entries are added/deleted only under RTNL */ + rcu_read_lock(); + c = ip6mr_cache_find_parent(mrt, &mfc->mf6cc_origin.sin6_addr, + &mfc->mf6cc_mcastgrp.sin6_addr, parent); + rcu_read_unlock(); + if (c) { write_lock_bh(&mrt_lock); - c->mf6c_parent = mfc->mf6cc_parent; - ip6mr_update_thresholds(mrt, c, ttls); + c->_c.mfc_parent = mfc->mf6cc_parent; + ip6mr_update_thresholds(mrt, &c->_c, ttls); if (!mrtsock) - c->mfc_flags |= MFC_STATIC; + 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; } @@ -1504,31 +1449,36 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, c->mf6c_origin = mfc->mf6cc_origin.sin6_addr; c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr; - c->mf6c_parent = mfc->mf6cc_parent; - ip6mr_update_thresholds(mrt, c, ttls); + c->_c.mfc_parent = mfc->mf6cc_parent; + ip6mr_update_thresholds(mrt, &c->_c, ttls); if (!mrtsock) - c->mfc_flags |= MFC_STATIC; + c->_c.mfc_flags |= MFC_STATIC; - write_lock_bh(&mrt_lock); - list_add(&c->list, &mrt->mfc6_cache_array[line]); - write_unlock_bh(&mrt_lock); + err = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->_c.mnode, + ip6mr_rht_params); + if (err) { + pr_err("ip6mr: rhtable insert error %d\n", err); + ip6mr_cache_free(c); + return err; + } + list_add_tail_rcu(&c->_c.list, &mrt->mfc_cache_list); - /* - * Check to see if we resolved a queued list. If so we - * need to send on the frames and tidy up. + /* Check to see if we resolved a queued list. If so we + * need to send on the frames and tidy up. */ found = false; spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(uc, &mrt->mfc6_unres_queue, list) { + list_for_each_entry(_uc, &mrt->mfc_unres_queue, list) { + uc = (struct mfc6_cache *)_uc; if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { - list_del(&uc->list); + list_del(&_uc->list); atomic_dec(&mrt->cache_resolve_queue_len); found = true; break; } } - if (list_empty(&mrt->mfc6_unres_queue)) + if (list_empty(&mrt->mfc_unres_queue)) del_timer(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); @@ -1536,6 +1486,8 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_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; } @@ -1544,61 +1496,59 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, * Close the multicast socket, and clear the vif tables etc */ -static void mroute_clean_tables(struct mr6_table *mrt, bool all) +static void mroute_clean_tables(struct mr_table *mrt, bool all) { - int i; + struct mr_mfc *c, *tmp; LIST_HEAD(list); - struct mfc6_cache *c, *next; + int i; - /* - * Shut down all active vif entries - */ + /* Shut down all active vif entries */ for (i = 0; i < mrt->maxvif; i++) { - if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC)) + if (!all && (mrt->vif_table[i].flags & VIFF_STATIC)) continue; mif6_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); - /* - * Wipe the cache - */ - for (i = 0; i < MFC6_LINES; i++) { - list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) { - if (!all && (c->mfc_flags & MFC_STATIC)) - continue; - write_lock_bh(&mrt_lock); - list_del(&c->list); - write_unlock_bh(&mrt_lock); - - mr6_netlink_event(mrt, c, RTM_DELROUTE); - ip6mr_cache_free(c); - } + /* Wipe the cache */ + list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) { + if (!all && (c->mfc_flags & MFC_STATIC)) + continue; + 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); + 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, next, &mrt->mfc6_unres_queue, list) { + list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); - mr6_netlink_event(mrt, c, RTM_DELROUTE); - ip6mr_destroy_unres(mrt, c); + 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); } spin_unlock_bh(&mfc_unres_lock); } } -static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk) +static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk) { int err = 0; struct net *net = sock_net(sk); rtnl_lock(); write_lock_bh(&mrt_lock); - if (likely(mrt->mroute6_sk == NULL)) { - mrt->mroute6_sk = sk; - net->ipv6.devconf_all->mc_forwarding++; - } else { + if (rtnl_dereference(mrt->mroute_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); @@ -1616,7 +1566,7 @@ int ip6mr_sk_done(struct sock *sk) { int err = -EACCES; struct net *net = sock_net(sk); - struct mr6_table *mrt; + struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) @@ -1624,9 +1574,13 @@ int ip6mr_sk_done(struct sock *sk) rtnl_lock(); ip6mr_for_each_table(mrt, net) { - if (sk == mrt->mroute6_sk) { + if (sk == rtnl_dereference(mrt->mroute_sk)) { write_lock_bh(&mrt_lock); - mrt->mroute6_sk = NULL; + 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, @@ -1644,9 +1598,9 @@ int ip6mr_sk_done(struct sock *sk) return err; } -struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) +bool mroute6_is_socket(struct net *net, struct sk_buff *skb) { - struct mr6_table *mrt; + struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_oif = skb->dev->ifindex, @@ -1656,8 +1610,9 @@ struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) return NULL; - return mrt->mroute6_sk; + return rcu_access_pointer(mrt->mroute_sk); } +EXPORT_SYMBOL(mroute6_is_socket); /* * Socket options and virtual interface manipulation. The whole @@ -1673,7 +1628,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns struct mf6cctl mfc; mifi_t mifi; struct net *net = sock_net(sk); - struct mr6_table *mrt; + struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) @@ -1684,7 +1639,8 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns return -ENOENT; if (optname != MRT6_INIT) { - if (sk != mrt->mroute6_sk && !ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (sk != rcu_access_pointer(mrt->mroute_sk) && + !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EACCES; } @@ -1706,7 +1662,8 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (vif.mif6c_mifi >= MAXMIFS) return -ENFILE; rtnl_lock(); - ret = mif6_add(net, mrt, &vif, sk == mrt->mroute6_sk); + ret = mif6_add(net, mrt, &vif, + sk == rtnl_dereference(mrt->mroute_sk)); rtnl_unlock(); return ret; @@ -1741,7 +1698,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns ret = ip6mr_mfc_delete(mrt, &mfc, parent); else ret = ip6mr_mfc_add(net, mrt, &mfc, - sk == mrt->mroute6_sk, parent); + sk == + rtnl_dereference(mrt->mroute_sk), + parent); rtnl_unlock(); return ret; @@ -1793,7 +1752,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns /* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */ if (v != RT_TABLE_DEFAULT && v >= 100000000) return -EINVAL; - if (sk == mrt->mroute6_sk) + if (sk == rcu_access_pointer(mrt->mroute_sk)) return -EBUSY; rtnl_lock(); @@ -1824,7 +1783,7 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int olr; int val; struct net *net = sock_net(sk); - struct mr6_table *mrt; + struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) @@ -1872,10 +1831,10 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) { struct sioc_sg_req6 sr; struct sioc_mif_req6 vr; - struct mif_device *vif; + struct vif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); - struct mr6_table *mrt; + struct mr_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) @@ -1888,8 +1847,8 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) if (vr.mifi >= mrt->maxvif) return -EINVAL; read_lock(&mrt_lock); - vif = &mrt->vif6_table[vr.mifi]; - if (MIF_EXISTS(mrt, vr.mifi)) { + vif = &mrt->vif_table[vr.mifi]; + if (VIF_EXISTS(mrt, vr.mifi)) { vr.icount = vif->pkt_in; vr.ocount = vif->pkt_out; vr.ibytes = vif->bytes_in; @@ -1906,19 +1865,19 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; - read_lock(&mrt_lock); + rcu_read_lock(); c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { - sr.pktcnt = c->mfc_un.res.pkt; - sr.bytecnt = c->mfc_un.res.bytes; - sr.wrong_if = c->mfc_un.res.wrong_if; - read_unlock(&mrt_lock); + sr.pktcnt = c->_c.mfc_un.res.pkt; + sr.bytecnt = c->_c.mfc_un.res.bytes; + sr.wrong_if = c->_c.mfc_un.res.wrong_if; + rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } - read_unlock(&mrt_lock); + rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; @@ -1946,10 +1905,10 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { struct compat_sioc_sg_req6 sr; struct compat_sioc_mif_req6 vr; - struct mif_device *vif; + struct vif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); - struct mr6_table *mrt; + struct mr_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) @@ -1962,8 +1921,8 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) if (vr.mifi >= mrt->maxvif) return -EINVAL; read_lock(&mrt_lock); - vif = &mrt->vif6_table[vr.mifi]; - if (MIF_EXISTS(mrt, vr.mifi)) { + vif = &mrt->vif_table[vr.mifi]; + if (VIF_EXISTS(mrt, vr.mifi)) { vr.icount = vif->pkt_in; vr.ocount = vif->pkt_out; vr.ibytes = vif->bytes_in; @@ -1980,19 +1939,19 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; - read_lock(&mrt_lock); + rcu_read_lock(); c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { - sr.pktcnt = c->mfc_un.res.pkt; - sr.bytecnt = c->mfc_un.res.bytes; - sr.wrong_if = c->mfc_un.res.wrong_if; - read_unlock(&mrt_lock); + sr.pktcnt = c->_c.mfc_un.res.pkt; + sr.bytecnt = c->_c.mfc_un.res.bytes; + sr.wrong_if = c->_c.mfc_un.res.wrong_if; + rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } - read_unlock(&mrt_lock); + rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; @@ -2013,11 +1972,11 @@ static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct * Processing handlers for ip6mr_forward */ -static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, +static int ip6mr_forward2(struct net *net, struct mr_table *mrt, struct sk_buff *skb, struct mfc6_cache *c, int vifi) { struct ipv6hdr *ipv6h; - struct mif_device *vif = &mrt->vif6_table[vifi]; + struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *dev; struct dst_entry *dst; struct flowi6 fl6; @@ -2087,46 +2046,50 @@ out_free: return 0; } -static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev) +static int ip6mr_find_vif(struct mr_table *mrt, struct net_device *dev) { int ct; for (ct = mrt->maxvif - 1; ct >= 0; ct--) { - if (mrt->vif6_table[ct].dev == dev) + if (mrt->vif_table[ct].dev == dev) break; } return ct; } -static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, - struct sk_buff *skb, struct mfc6_cache *cache) +static void ip6_mr_forward(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, struct mfc6_cache *c) { int psend = -1; int vif, ct; int true_vifi = ip6mr_find_vif(mrt, skb->dev); - vif = cache->mf6c_parent; - cache->mfc_un.res.pkt++; - cache->mfc_un.res.bytes += skb->len; - cache->mfc_un.res.lastuse = jiffies; + vif = c->_c.mfc_parent; + c->_c.mfc_un.res.pkt++; + c->_c.mfc_un.res.bytes += skb->len; + c->_c.mfc_un.res.lastuse = jiffies; - if (ipv6_addr_any(&cache->mf6c_origin) && true_vifi >= 0) { + if (ipv6_addr_any(&c->mf6c_origin) && true_vifi >= 0) { struct mfc6_cache *cache_proxy; /* For an (*,G) entry, we only check that the incoming * interface is part of the static tree. */ - cache_proxy = ip6mr_cache_find_any_parent(mrt, vif); + rcu_read_lock(); + cache_proxy = mr_mfc_find_any_parent(mrt, vif); if (cache_proxy && - cache_proxy->mfc_un.res.ttls[true_vifi] < 255) + cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) { + rcu_read_unlock(); goto forward; + } + rcu_read_unlock(); } /* * Wrong interface: drop packet and (maybe) send PIM assert. */ - if (mrt->vif6_table[vif].dev != skb->dev) { - cache->mfc_un.res.wrong_if++; + if (mrt->vif_table[vif].dev != skb->dev) { + c->_c.mfc_un.res.wrong_if++; if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -2135,52 +2098,55 @@ static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, large chunk of pimd to kernel. Ough... --ANK */ (mrt->mroute_do_pim || - cache->mfc_un.res.ttls[true_vifi] < 255) && + c->_c.mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, - cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { - cache->mfc_un.res.last_assert = jiffies; + c->_c.mfc_un.res.last_assert + + MFC_ASSERT_THRESH)) { + c->_c.mfc_un.res.last_assert = jiffies; ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRONGMIF); } goto dont_forward; } forward: - mrt->vif6_table[vif].pkt_in++; - mrt->vif6_table[vif].bytes_in += skb->len; + mrt->vif_table[vif].pkt_in++; + mrt->vif_table[vif].bytes_in += skb->len; /* * Forward the frame */ - if (ipv6_addr_any(&cache->mf6c_origin) && - ipv6_addr_any(&cache->mf6c_mcastgrp)) { + if (ipv6_addr_any(&c->mf6c_origin) && + ipv6_addr_any(&c->mf6c_mcastgrp)) { if (true_vifi >= 0 && - true_vifi != cache->mf6c_parent && + true_vifi != c->_c.mfc_parent && ipv6_hdr(skb)->hop_limit > - cache->mfc_un.res.ttls[cache->mf6c_parent]) { + c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { /* It's an (*,*) entry and the packet is not coming from * the upstream: forward the packet to the upstream * only. */ - psend = cache->mf6c_parent; + psend = c->_c.mfc_parent; goto last_forward; } goto dont_forward; } - for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) { + for (ct = c->_c.mfc_un.res.maxvif - 1; + ct >= c->_c.mfc_un.res.minvif; ct--) { /* For (*,G) entry, don't forward to the incoming interface */ - if ((!ipv6_addr_any(&cache->mf6c_origin) || ct != true_vifi) && - ipv6_hdr(skb)->hop_limit > cache->mfc_un.res.ttls[ct]) { + if ((!ipv6_addr_any(&c->mf6c_origin) || ct != true_vifi) && + ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ip6mr_forward2(net, mrt, skb2, cache, psend); + ip6mr_forward2(net, mrt, skb2, + c, psend); } psend = ct; } } last_forward: if (psend != -1) { - ip6mr_forward2(net, mrt, skb, cache, psend); + ip6mr_forward2(net, mrt, skb, c, psend); return; } @@ -2197,7 +2163,7 @@ int ip6_mr_input(struct sk_buff *skb) { struct mfc6_cache *cache; struct net *net = dev_net(skb->dev); - struct mr6_table *mrt; + struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .flowi6_mark = skb->mark, @@ -2247,66 +2213,11 @@ int ip6_mr_input(struct sk_buff *skb) return 0; } - -static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, - struct mfc6_cache *c, struct rtmsg *rtm) -{ - struct rta_mfc_stats mfcs; - struct nlattr *mp_attr; - struct rtnexthop *nhp; - unsigned long lastuse; - int ct; - - /* If cache is unresolved, don't try to parse IIF and OIF */ - if (c->mf6c_parent >= MAXMIFS) { - rtm->rtm_flags |= RTNH_F_UNRESOLVED; - return -ENOENT; - } - - if (MIF_EXISTS(mrt, c->mf6c_parent) && - nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0) - return -EMSGSIZE; - mp_attr = nla_nest_start(skb, RTA_MULTIPATH); - if (!mp_attr) - return -EMSGSIZE; - - for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { - if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { - nhp = nla_reserve_nohdr(skb, sizeof(*nhp)); - if (!nhp) { - nla_nest_cancel(skb, mp_attr); - return -EMSGSIZE; - } - - nhp->rtnh_flags = 0; - nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; - nhp->rtnh_ifindex = mrt->vif6_table[ct].dev->ifindex; - nhp->rtnh_len = sizeof(*nhp); - } - } - - nla_nest_end(skb, mp_attr); - - lastuse = READ_ONCE(c->mfc_un.res.lastuse); - lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; - - mfcs.mfcs_packets = c->mfc_un.res.pkt; - mfcs.mfcs_bytes = c->mfc_un.res.bytes; - mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; - if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || - nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), - RTA_PAD)) - return -EMSGSIZE; - - rtm->rtm_type = RTN_MULTICAST; - return 1; -} - int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, u32 portid) { int err; - struct mr6_table *mrt; + struct mr_table *mrt; struct mfc6_cache *cache; struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); @@ -2367,15 +2278,12 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, return err; } - if (rtm->rtm_flags & RTM_F_NOTIFY) - cache->mfc_flags |= MFC_NOTIFY; - - err = __ip6mr_fill_mroute(mrt, skb, cache, rtm); + err = mr_fill_mroute(mrt, skb, &cache->_c, rtm); read_unlock(&mrt_lock); return err; } -static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, +static int ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mfc6_cache *c, int cmd, int flags) { @@ -2397,7 +2305,7 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; - if (c->mfc_flags & MFC_STATIC) + if (c->_c.mfc_flags & MFC_STATIC) rtm->rtm_protocol = RTPROT_STATIC; else rtm->rtm_protocol = RTPROT_MROUTED; @@ -2406,7 +2314,7 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, if (nla_put_in6_addr(skb, RTA_SRC, &c->mf6c_origin) || nla_put_in6_addr(skb, RTA_DST, &c->mf6c_mcastgrp)) goto nla_put_failure; - err = __ip6mr_fill_mroute(mrt, skb, c, rtm); + err = mr_fill_mroute(mrt, skb, &c->_c, rtm); /* do not break the dump if cache is unresolved */ if (err < 0 && err != -ENOENT) goto nla_put_failure; @@ -2419,6 +2327,14 @@ nla_put_failure: return -EMSGSIZE; } +static int _ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, + u32 portid, u32 seq, struct mr_mfc *c, + int cmd, int flags) +{ + return ip6mr_fill_mroute(mrt, skb, portid, seq, (struct mfc6_cache *)c, + cmd, flags); +} + static int mr6_msgsize(bool unresolved, int maxvif) { size_t len = @@ -2440,14 +2356,14 @@ static int mr6_msgsize(bool unresolved, int maxvif) return len; } -static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, +static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, int cmd) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(mr6_msgsize(mfc->mf6c_parent >= MAXMIFS, mrt->maxvif), + skb = nlmsg_new(mr6_msgsize(mfc->_c.mfc_parent >= MAXMIFS, mrt->maxvif), GFP_ATOMIC); if (!skb) goto errout; @@ -2482,7 +2398,7 @@ static size_t mrt6msg_netlink_msgsize(size_t payloadlen) return len; } -static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt) +static void mrt6msg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt) { struct net *net = read_pnet(&mrt->net); struct nlmsghdr *nlh; @@ -2532,65 +2448,6 @@ errout: static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = sock_net(skb->sk); - struct mr6_table *mrt; - struct mfc6_cache *mfc; - unsigned int t = 0, s_t; - unsigned int h = 0, s_h; - unsigned int e = 0, s_e; - - s_t = cb->args[0]; - s_h = cb->args[1]; - s_e = cb->args[2]; - - read_lock(&mrt_lock); - ip6mr_for_each_table(mrt, net) { - if (t < s_t) - goto next_table; - if (t > s_t) - s_h = 0; - for (h = s_h; h < MFC6_LINES; h++) { - list_for_each_entry(mfc, &mrt->mfc6_cache_array[h], list) { - if (e < s_e) - goto next_entry; - if (ip6mr_fill_mroute(mrt, skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE, - NLM_F_MULTI) < 0) - goto done; -next_entry: - e++; - } - e = s_e = 0; - } - spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(mfc, &mrt->mfc6_unres_queue, list) { - if (e < s_e) - goto next_entry2; - if (ip6mr_fill_mroute(mrt, skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE, - NLM_F_MULTI) < 0) { - spin_unlock_bh(&mfc_unres_lock); - goto done; - } -next_entry2: - e++; - } - spin_unlock_bh(&mfc_unres_lock); - e = s_e = 0; - s_h = 0; -next_table: - t++; - } -done: - read_unlock(&mrt_lock); - - cb->args[2] = e; - cb->args[1] = h; - cb->args[0] = t; - - return skb->len; + return mr_rtm_dumproute(skb, cb, ip6mr_mr_table_iter, + _ip6mr_fill_mroute, &mfc_unres_lock); } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index d78d41fc4b1a..4d780c7f0130 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1367,10 +1367,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - lock_sock(sk); - err = nf_getsockopt(sk, PF_INET6, optname, optval, - &len); - release_sock(sk); + err = nf_getsockopt(sk, PF_INET6, optname, optval, &len); if (err >= 0) err = put_user(len, optlen); } @@ -1409,10 +1406,7 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - lock_sock(sk); - err = compat_nf_getsockopt(sk, PF_INET6, - optname, optval, &len); - release_sock(sk); + err = compat_nf_getsockopt(sk, PF_INET6, optname, optval, &len); if (err >= 0) err = put_user(len, optlen); } @@ -1421,4 +1415,3 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, } EXPORT_SYMBOL(compat_ipv6_getsockopt); #endif - diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 9b9d2ff01b35..793159d77d8a 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -165,7 +165,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (ifindex == 0) { struct rt6_info *rt; - rt = rt6_lookup(net, addr, NULL, 0, 0); + rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; ip6_rt_put(rt); @@ -254,7 +254,7 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, struct inet6_dev *idev = NULL; if (ifindex == 0) { - struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, 0); + struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; @@ -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; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f61a5b613b52..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) 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 af4c917e0836..62358b93bbac 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -352,6 +352,10 @@ ip6t_do_table(struct sk_buff *skb, } if (table_base + v != ip6t_next_entry(e) && !(e->ipv6.flags & IP6T_F_GOTO)) { + if (unlikely(stackidx >= private->stacksize)) { + verdict = NF_DROP; + break; + } jumpstack[stackidx++] = e; } diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index fa51a205918d..38dea8ff680f 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -85,14 +85,14 @@ static int reject_tg6_check(const struct xt_tgchk_param *par) const struct ip6t_entry *e = par->entryinfo; if (rejinfo->with == IP6T_ICMP6_ECHOREPLY) { - pr_info("ECHOREPLY is not supported.\n"); + pr_info_ratelimited("ECHOREPLY is not supported\n"); return -EINVAL; } else if (rejinfo->with == IP6T_TCP_RESET) { /* Must specify that it's a TCP packet */ if (!(e->ipv6.flags & IP6T_F_PROTO) || e->ipv6.proto != IPPROTO_TCP || (e->ipv6.invflags & XT_INV_PROTO)) { - pr_info("TCP_RESET illegal for non-tcp\n"); + pr_info_ratelimited("TCP_RESET illegal for non-tcp\n"); return -EINVAL; } } diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index b12e61b7b16c..d12f511929f5 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -48,12 +48,8 @@ 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, lookup_flags); + rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags); if (rt->dst.error) goto out; @@ -103,14 +99,14 @@ static int rpfilter_check(const struct xt_mtchk_param *par) unsigned int options = ~XT_RPFILTER_OPTION_MASK; if (info->flags & options) { - pr_info("unknown options encountered"); + pr_info_ratelimited("unknown options\n"); return -EINVAL; } if (strcmp(par->table, "mangle") != 0 && strcmp(par->table, "raw") != 0) { - pr_info("match only valid in the \'raw\' " - "or \'mangle\' tables, not \'%s\'.\n", par->table); + pr_info_ratelimited("only valid in \'raw\' or \'mangle\' table, not \'%s\'\n", + par->table); return -EINVAL; } diff --git a/net/ipv6/netfilter/ip6t_srh.c b/net/ipv6/netfilter/ip6t_srh.c index 9642164107ce..33719d5560c8 100644 --- a/net/ipv6/netfilter/ip6t_srh.c +++ b/net/ipv6/netfilter/ip6t_srh.c @@ -122,12 +122,14 @@ static int srh_mt6_check(const struct xt_mtchk_param *par) const struct ip6t_srh *srhinfo = par->matchinfo; if (srhinfo->mt_flags & ~IP6T_SRH_MASK) { - pr_err("unknown srh match flags %X\n", srhinfo->mt_flags); + pr_info_ratelimited("unknown srh match flags %X\n", + srhinfo->mt_flags); return -EINVAL; } if (srhinfo->mt_invflags & ~IP6T_SRH_INV_MASK) { - pr_err("unknown srh invflags %X\n", srhinfo->mt_invflags); + pr_info_ratelimited("unknown srh invflags %X\n", + srhinfo->mt_invflags); return -EINVAL; } 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_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 cc5174c7254c..36be3cf0adef 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -180,8 +180,8 @@ 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, lookup_flags); + rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, pkt->skb, + lookup_flags); if (rt->dst.error) goto put_rt_err; @@ -189,15 +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/proc.c b/net/ipv6/proc.c index b67814242f78..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); @@ -354,4 +354,3 @@ void ipv6_misc_proc_exit(void) { unregister_pernet_subsys(&ipv6_proc_ops); } - diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 4c25339b1984..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; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9dcfadddd800..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; @@ -450,8 +450,10 @@ static bool rt6_check_expired(const struct rt6_info *rt) return false; } -static struct rt6_info *rt6_multipath_select(struct rt6_info *match, +static struct rt6_info *rt6_multipath_select(const struct net *net, + struct rt6_info *match, struct flowi6 *fl6, int oif, + const struct sk_buff *skb, int strict) { struct rt6_info *sibling, *next_sibling; @@ -460,7 +462,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match, * case it will always be non-zero. Otherwise now is the time to do it. */ if (!fl6->mp_hash) - fl6->mp_hash = rt6_multipath_hash(fl6, NULL); + fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL); if (fl6->mp_hash <= atomic_read(&match->rt6i_nh_upper_bound)) return match; @@ -914,7 +916,9 @@ static bool ip6_hold_safe(struct net *net, struct rt6_info **prt, static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, - struct flowi6 *fl6, int flags) + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags) { struct rt6_info *rt, *rt_cache; struct fib6_node *fn; @@ -929,8 +933,8 @@ restart: rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags); if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) - rt = rt6_multipath_select(rt, fl6, - fl6->flowi6_oif, flags); + rt = rt6_multipath_select(net, rt, fl6, fl6->flowi6_oif, + skb, flags); } if (rt == net->ipv6.ip6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); @@ -954,14 +958,15 @@ restart: } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, - int flags) + const struct sk_buff *skb, int flags) { - return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_lookup); + return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_lookup); } EXPORT_SYMBOL_GPL(ip6_route_lookup); struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, - const struct in6_addr *saddr, int oif, int strict) + const struct in6_addr *saddr, int oif, + const struct sk_buff *skb, int strict) { struct flowi6 fl6 = { .flowi6_oif = oif, @@ -975,7 +980,7 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, flags |= RT6_LOOKUP_F_HAS_SADDR; } - dst = fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_lookup); + dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup); if (dst->error == 0) return (struct rt6_info *) dst; @@ -1509,7 +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; @@ -1518,20 +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++; } } @@ -1647,7 +1677,8 @@ void rt6_age_exceptions(struct rt6_info *rt, } struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, - int oif, struct flowi6 *fl6, int flags) + int oif, struct flowi6 *fl6, + const struct sk_buff *skb, int flags) { struct fib6_node *fn, *saved_fn; struct rt6_info *rt, *rt_cache; @@ -1669,7 +1700,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, redo_rt6_select: rt = rt6_select(net, fn, oif, strict); if (rt->rt6i_nsiblings) - rt = rt6_multipath_select(rt, fl6, oif, strict); + rt = rt6_multipath_select(net, rt, fl6, oif, skb, strict); if (rt == net->ipv6.ip6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) @@ -1768,28 +1799,35 @@ uncached_rt_out: } EXPORT_SYMBOL_GPL(ip6_pol_route); -static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, - struct flowi6 *fl6, int flags) +static struct rt6_info *ip6_pol_route_input(struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags) { - return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags); + return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, skb, flags); } struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, - struct flowi6 *fl6, int flags) + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags) { if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG) flags |= RT6_LOOKUP_F_IFACE; - return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_input); + return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_input); } EXPORT_SYMBOL_GPL(ip6_route_input_lookup); static void ip6_multipath_l3_keys(const struct sk_buff *skb, - struct flow_keys *keys) + struct flow_keys *keys, + struct flow_keys *flkeys) { const struct ipv6hdr *outer_iph = ipv6_hdr(skb); const struct ipv6hdr *key_iph = outer_iph; + struct flow_keys *_flkeys = flkeys; const struct ipv6hdr *inner_iph; const struct icmp6hdr *icmph; struct ipv6hdr _inner_iph; @@ -1811,26 +1849,76 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb, goto out; key_iph = inner_iph; + _flkeys = NULL; out: - memset(keys, 0, sizeof(*keys)); - keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; - keys->addrs.v6addrs.src = key_iph->saddr; - keys->addrs.v6addrs.dst = key_iph->daddr; - keys->tags.flow_label = ip6_flowinfo(key_iph); - keys->basic.ip_proto = key_iph->nexthdr; + if (_flkeys) { + keys->addrs.v6addrs.src = _flkeys->addrs.v6addrs.src; + keys->addrs.v6addrs.dst = _flkeys->addrs.v6addrs.dst; + keys->tags.flow_label = _flkeys->tags.flow_label; + keys->basic.ip_proto = _flkeys->basic.ip_proto; + } else { + keys->addrs.v6addrs.src = key_iph->saddr; + keys->addrs.v6addrs.dst = key_iph->daddr; + keys->tags.flow_label = ip6_flowinfo(key_iph); + keys->basic.ip_proto = key_iph->nexthdr; + } } /* if skb is set it will be used and fl6 can be NULL */ -u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb) +u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, + const struct sk_buff *skb, struct flow_keys *flkeys) { struct flow_keys hash_keys; + u32 mhash; - if (skb) { - ip6_multipath_l3_keys(skb, &hash_keys); - return flow_hash_from_keys(&hash_keys) >> 1; + 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; + if (skb) { + ip6_multipath_l3_keys(skb, &hash_keys, flkeys); + } else { + hash_keys.addrs.v6addrs.src = fl6->saddr; + hash_keys.addrs.v6addrs.dst = fl6->daddr; + hash_keys.tags.flow_label = (__force u32)fl6->flowlabel; + hash_keys.basic.ip_proto = fl6->flowi6_proto; + } + break; + case 1: + if (skb) { + unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; + struct flow_keys keys; + + /* short-circuit if we already have L4 hash present */ + if (skb->l4_hash) + return skb_get_hash_raw(skb) >> 1; + + memset(&hash_keys, 0, sizeof(hash_keys)); + + if (!flkeys) { + skb_flow_dissect_flow_keys(skb, &keys, flag); + flkeys = &keys; + } + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src; + hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst; + hash_keys.ports.src = flkeys->ports.src; + hash_keys.ports.dst = flkeys->ports.dst; + hash_keys.basic.ip_proto = flkeys->basic.ip_proto; + } else { + memset(&hash_keys, 0, sizeof(hash_keys)); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + hash_keys.addrs.v6addrs.src = fl6->saddr; + hash_keys.addrs.v6addrs.dst = fl6->daddr; + hash_keys.ports.src = fl6->fl6_sport; + hash_keys.ports.dst = fl6->fl6_dport; + hash_keys.basic.ip_proto = fl6->flowi6_proto; + } + break; } + mhash = flow_hash_from_keys(&hash_keys); - return get_hash_from_flowi6(fl6) >> 1; + return mhash >> 1; } void ip6_route_input(struct sk_buff *skb) @@ -1847,20 +1935,29 @@ void ip6_route_input(struct sk_buff *skb) .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, }; + struct flow_keys *flkeys = NULL, _flkeys; tun_info = skb_tunnel_info(skb); if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id; + + if (fib6_rules_early_flow_dissect(net, skb, &fl6, &_flkeys)) + flkeys = &_flkeys; + if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6)) - fl6.mp_hash = rt6_multipath_hash(&fl6, skb); + fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, flkeys); skb_dst_drop(skb); - skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags)); + skb_dst_set(skb, + ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags)); } -static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, - struct flowi6 *fl6, int flags) +static struct rt6_info *ip6_pol_route_output(struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags) { - return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags); + return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, skb, flags); } struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, @@ -1888,7 +1985,7 @@ struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, else if (sk) flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs); - return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output); + return fib6_rule_lookup(net, fl6, NULL, flags, ip6_pol_route_output); } EXPORT_SYMBOL_GPL(ip6_route_output_flags); @@ -2137,6 +2234,7 @@ struct ip6rd_flowi { static struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, struct flowi6 *fl6, + const struct sk_buff *skb, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; @@ -2210,8 +2308,9 @@ out: }; static struct dst_entry *ip6_route_redirect(struct net *net, - const struct flowi6 *fl6, - const struct in6_addr *gateway) + const struct flowi6 *fl6, + const struct sk_buff *skb, + const struct in6_addr *gateway) { int flags = RT6_LOOKUP_F_HAS_SADDR; struct ip6rd_flowi rdfl; @@ -2219,7 +2318,7 @@ static struct dst_entry *ip6_route_redirect(struct net *net, rdfl.fl6 = *fl6; rdfl.gateway = *gateway; - return fib6_rule_lookup(net, &rdfl.fl6, + return fib6_rule_lookup(net, &rdfl.fl6, skb, flags, __ip6_route_redirect); } @@ -2239,7 +2338,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, fl6.flowlabel = ip6_flowinfo(iph); fl6.flowi6_uid = uid; - dst = ip6_route_redirect(net, &fl6, &ipv6_hdr(skb)->saddr); + dst = ip6_route_redirect(net, &fl6, skb, &ipv6_hdr(skb)->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } @@ -2261,7 +2360,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif, fl6.saddr = iph->daddr; fl6.flowi6_uid = sock_net_uid(net, NULL); - dst = ip6_route_redirect(net, &fl6, &iph->saddr); + dst = ip6_route_redirect(net, &fl6, skb, &iph->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } @@ -2463,7 +2562,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net, flags |= RT6_LOOKUP_F_HAS_SADDR; flags |= RT6_LOOKUP_F_IGNORE_LINKSTATE; - rt = ip6_pol_route(net, table, cfg->fc_ifindex, &fl6, flags); + rt = ip6_pol_route(net, table, cfg->fc_ifindex, &fl6, NULL, flags); /* if table lookup failed, fall back to full lookup */ if (rt == net->ipv6.ip6_null_entry) { @@ -2476,7 +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; @@ -2526,7 +2625,7 @@ static int ip6_route_check_nh(struct net *net, } if (!grt) - grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, 1); + grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, NULL, 1); if (!grt) goto out; @@ -2552,6 +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) { @@ -2671,14 +2843,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, if (err) goto out; rt->dst.lwtstate = lwtstate_get(lwtstate); - if (lwtunnel_output_redirect(rt->dst.lwtstate)) { - rt->dst.lwtstate->orig_output = rt->dst.output; - rt->dst.output = lwtunnel_output; - } - if (lwtunnel_input_redirect(rt->dst.lwtstate)) { - rt->dst.lwtstate->orig_input = rt->dst.input; - rt->dst.input = lwtunnel_input; - } + lwtunnel_set_redirect(&rt->dst); } ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); @@ -2741,61 +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; @@ -3809,25 +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; @@ -4099,6 +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); @@ -4598,7 +4702,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (!ipv6_addr_any(&fl6.saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; - dst = ip6_route_input_lookup(net, dev, &fl6, flags); + dst = ip6_route_input_lookup(net, dev, &fl6, NULL, flags); rcu_read_unlock(); } else { @@ -4963,7 +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; } 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/seg6_local.c b/net/ipv6/seg6_local.c index ba3767ef5e93..45722327375a 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -161,7 +161,7 @@ static void lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH; if (!tbl_id) { - dst = ip6_route_input_lookup(net, skb->dev, &fl6, flags); + dst = ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags); } else { struct fib6_table *table; @@ -169,7 +169,7 @@ static void lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, if (!table) goto out; - rt = ip6_pol_route(net, table, 0, &fl6, flags); + rt = ip6_pol_route(net, table, 0, &fl6, skb, flags); dst = &rt->dst; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3873d3877135..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 (t->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); diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index a789a8ac6a64..6fbdef630152 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -16,14 +16,31 @@ #include <net/ipv6.h> #include <net/addrconf.h> #include <net/inet_frag.h> +#include <net/netevent.h> #ifdef CONFIG_NETLABEL #include <net/calipso.h> #endif +static int zero; static int one = 1; static int auto_flowlabels_min; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; +static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct net *net; + int ret; + + net = container_of(table->data, struct net, + ipv6.sysctl.multipath_hash_policy); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (write && ret == 0) + call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); + + return ret; +} static struct ctl_table ipv6_table_template[] = { { @@ -126,6 +143,15 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "fib_multipath_hash_policy", + .data = &init_net.ipv6.sysctl.multipath_hash_policy, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_rt6_multipath_hash_policy, + .extra1 = &zero, + .extra2 = &one, + }, { } }; @@ -190,6 +216,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[11].data = &net->ipv6.sysctl.max_hbh_opts_cnt; ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len; ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len; + ipv6_table[14].data = &net->ipv6.sysctl.multipath_hash_policy, ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 412139f4eccd..883df0ad5bfe 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1451,6 +1451,7 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); + bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; @@ -1470,10 +1471,20 @@ process: th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); - nsk = tcp_check_req(sk, skb, req, false); + nsk = tcp_check_req(sk, skb, req, false, &req_stolen); } if (!nsk) { reqsk_put(req); + if (req_stolen) { + /* Another cpu got exclusive access to req + * and created a full blown socket. + * Try to feed this packet to this socket + * instead of discarding it. + */ + tcp_v6_restore_cb(skb); + sock_put(sk); + goto lookup; + } goto discard_and_relse; } if (nsk == sk) { 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/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 09fb44ee3b45..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); } diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index b15075a5c227..16f434791763 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -196,4 +196,3 @@ void xfrm6_state_fini(void) { xfrm_state_unregister_afinfo(&xfrm6_state_afinfo); } - |