diff options
Diffstat (limited to 'net/ipv6/ndisc.c')
| -rw-r--r-- | net/ipv6/ndisc.c | 1117 |
1 files changed, 713 insertions, 404 deletions
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index b3b5730b48c5..59d17b6f06bf 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Neighbour Discovery for IPv6 * Linux INET6 implementation @@ -5,11 +6,6 @@ * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Mike Shaver <shaver@ingenia.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ /* @@ -46,6 +42,7 @@ #endif #include <linux/if_addr.h> +#include <linux/if_ether.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> @@ -72,24 +69,19 @@ #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> -/* Set to 3 to get tracing... */ -#define ND_DEBUG 1 - -#define ND_PRINTK(val, level, fmt, ...) \ -do { \ - if (val <= ND_DEBUG) \ - net_##level##_ratelimited(fmt, ##__VA_ARGS__); \ -} while (0) - static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); +static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey); +static bool ndisc_allow_add(const struct net_device *dev, + struct netlink_ext_ack *extack); static int ndisc_constructor(struct neighbour *neigh); static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); static int pndisc_constructor(struct pneigh_entry *n); static void pndisc_destructor(struct pneigh_entry *n); static void pndisc_redo(struct sk_buff *skb); +static int ndisc_is_multicast(const void *pkey); static const struct neigh_ops ndisc_generic_ops = { .family = AF_INET6, @@ -117,37 +109,44 @@ static const struct neigh_ops ndisc_direct_ops = { struct neigh_table nd_tbl = { .family = AF_INET6, .key_len = sizeof(struct in6_addr), + .protocol = cpu_to_be16(ETH_P_IPV6), .hash = ndisc_hash, + .key_eq = ndisc_key_eq, .constructor = ndisc_constructor, .pconstructor = pndisc_constructor, .pdestructor = pndisc_destructor, .proxy_redo = pndisc_redo, + .is_multicast = ndisc_is_multicast, + .allow_add = ndisc_allow_add, .id = "ndisc_cache", .parms = { .tbl = &nd_tbl, - .base_reachable_time = ND_REACHABLE_TIME, - .retrans_time = ND_RETRANS_TIMER, - .gc_staletime = 60 * HZ, .reachable_time = ND_REACHABLE_TIME, - .delay_probe_time = 5 * HZ, - .queue_len_bytes = 64*1024, - .ucast_probes = 3, - .mcast_probes = 3, - .anycast_delay = 1 * HZ, - .proxy_delay = (8 * HZ) / 10, - .proxy_qlen = 64, + .data = { + [NEIGH_VAR_MCAST_PROBES] = 3, + [NEIGH_VAR_UCAST_PROBES] = 3, + [NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER, + [NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME, + [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, + [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, + [NEIGH_VAR_GC_STALETIME] = 60 * HZ, + [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_DEFAULT, + [NEIGH_VAR_PROXY_QLEN] = 64, + [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, + [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, + }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, .gc_thresh2 = 512, .gc_thresh3 = 1024, }; +EXPORT_SYMBOL_GPL(nd_tbl); -static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data) +void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, + int data_len, int pad) { - int pad = ndisc_addr_option_pad(skb->dev->type); - int data_len = skb->dev->addr_len; - int space = ndisc_opt_addr_space(skb->dev); + int space = __ndisc_opt_addr_space(data_len, pad); u8 *opt = skb_put(skb, space); opt[0] = type; @@ -160,9 +159,27 @@ static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data) memcpy(opt+2, data, data_len); data_len += 2; opt += data_len; - if ((space -= data_len) > 0) + space -= data_len; + if (space > 0) memset(opt, 0, space); } +EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option); + +static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type, + const void *data, u8 icmp6_type) +{ + __ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len, + ndisc_addr_option_pad(skb->dev->type)); + ndisc_ops_fill_addr_option(skb->dev, skb, icmp6_type); +} + +static inline void ndisc_fill_redirect_addr_option(struct sk_buff *skb, + void *ha, + const u8 *ops_data) +{ + ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha, NDISC_REDIRECT); + ndisc_ops_fill_redirect_addr_option(skb->dev, skb, ops_data); +} static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, struct nd_opt_hdr *end) @@ -173,28 +190,35 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, type = cur->nd_opt_type; do { cur = ((void *)cur) + (cur->nd_opt_len << 3); - } while(cur < end && cur->nd_opt_type != type); + } while (cur < end && cur->nd_opt_type != type); return cur <= end && cur->nd_opt_type == type ? cur : NULL; } -static inline int ndisc_is_useropt(struct nd_opt_hdr *opt) +static inline int ndisc_is_useropt(const struct net_device *dev, + struct nd_opt_hdr *opt) { - return opt->nd_opt_type == ND_OPT_RDNSS || - opt->nd_opt_type == ND_OPT_DNSSL; + return opt->nd_opt_type == ND_OPT_PREFIX_INFO || + opt->nd_opt_type == ND_OPT_RDNSS || + opt->nd_opt_type == ND_OPT_DNSSL || + opt->nd_opt_type == ND_OPT_6CO || + opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || + opt->nd_opt_type == ND_OPT_PREF64; } -static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur, +static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev, + struct nd_opt_hdr *cur, struct nd_opt_hdr *end) { if (!cur || !end || cur >= end) return NULL; do { cur = ((void *)cur) + (cur->nd_opt_len << 3); - } while(cur < end && !ndisc_is_useropt(cur)); - return cur <= end && ndisc_is_useropt(cur) ? cur : NULL; + } while (cur < end && !ndisc_is_useropt(dev, cur)); + return cur <= end && ndisc_is_useropt(dev, cur) ? cur : NULL; } -struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, +struct ndisc_options *ndisc_parse_options(const struct net_device *dev, + u8 *opt, int opt_len, struct ndisc_options *ndopts) { struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt; @@ -203,21 +227,24 @@ struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, return NULL; memset(ndopts, 0, sizeof(*ndopts)); while (opt_len) { + bool unknown = false; int l; if (opt_len < sizeof(struct nd_opt_hdr)) return NULL; l = nd_opt->nd_opt_len << 3; if (opt_len < l || l == 0) return NULL; + if (ndisc_ops_parse_options(dev, nd_opt, ndopts)) + goto next_opt; switch (nd_opt->nd_opt_type) { case ND_OPT_SOURCE_LL_ADDR: case ND_OPT_TARGET_LL_ADDR: case ND_OPT_MTU: + case ND_OPT_NONCE: case ND_OPT_REDIRECT_HDR: if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) { - ND_PRINTK(2, warn, - "%s: duplicated ND6 option found: type=%d\n", - __func__, nd_opt->nd_opt_type); + net_dbg_ratelimited("%s: duplicated ND6 option found: type=%d\n", + __func__, nd_opt->nd_opt_type); } else { ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; } @@ -235,23 +262,22 @@ struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, break; #endif default: - if (ndisc_is_useropt(nd_opt)) { - ndopts->nd_useropts_end = nd_opt; - if (!ndopts->nd_useropts) - ndopts->nd_useropts = nd_opt; - } else { - /* - * Unknown options must be silently ignored, - * to accommodate future extension to the - * protocol. - */ - ND_PRINTK(2, notice, - "%s: ignored unsupported option; type=%d, len=%d\n", - __func__, - nd_opt->nd_opt_type, - nd_opt->nd_opt_len); - } + unknown = true; } + if (ndisc_is_useropt(dev, nd_opt)) { + ndopts->nd_useropts_end = nd_opt; + if (!ndopts->nd_useropts) + ndopts->nd_useropts = nd_opt; + } else if (unknown) { + /* + * Unknown options must be silently ignored, + * to accommodate future extension to the + * protocol. + */ + net_dbg_ratelimited("%s: ignored unsupported option; type=%d, len=%d\n", + __func__, nd_opt->nd_opt_type, nd_opt->nd_opt_len); + } +next_opt: opt_len -= l; nd_opt = ((void *)nd_opt) + l; } @@ -282,7 +308,6 @@ int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, } return -EINVAL; } - EXPORT_SYMBOL(ndisc_mc_map); static u32 ndisc_hash(const void *pkey, @@ -292,16 +317,21 @@ static u32 ndisc_hash(const void *pkey, return ndisc_hashfn(pkey, dev, hash_rnd); } +static bool ndisc_key_eq(const struct neighbour *n, const void *pkey) +{ + return neigh_key_eq128(n, pkey); +} + static int ndisc_constructor(struct neighbour *neigh) { - struct in6_addr *addr = (struct in6_addr*)&neigh->primary_key; + struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key; struct net_device *dev = neigh->dev; struct inet6_dev *in6_dev; struct neigh_parms *parms; bool is_multicast = ipv6_addr_is_multicast(addr); in6_dev = in6_dev_get(dev); - if (in6_dev == NULL) { + if (!in6_dev) { return -EINVAL; } @@ -342,46 +372,54 @@ static int ndisc_constructor(struct neighbour *neigh) static int pndisc_constructor(struct pneigh_entry *n) { - struct in6_addr *addr = (struct in6_addr*)&n->key; - struct in6_addr maddr; + struct in6_addr *addr = (struct in6_addr *)&n->key; struct net_device *dev = n->dev; + struct in6_addr maddr; - if (dev == NULL || __in6_dev_get(dev) == NULL) + if (!dev) return -EINVAL; + addrconf_addr_solict_mult(addr, &maddr); - ipv6_dev_mc_inc(dev, &maddr); - return 0; + return ipv6_dev_mc_inc(dev, &maddr); } static void pndisc_destructor(struct pneigh_entry *n) { - struct in6_addr *addr = (struct in6_addr*)&n->key; - struct in6_addr maddr; + struct in6_addr *addr = (struct in6_addr *)&n->key; struct net_device *dev = n->dev; + struct in6_addr maddr; - if (dev == NULL || __in6_dev_get(dev) == NULL) + if (!dev) return; + addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_dec(dev, &maddr); } +/* called with rtnl held */ +static bool ndisc_allow_add(const struct net_device *dev, + struct netlink_ext_ack *extack) +{ + struct inet6_dev *idev = __in6_dev_get(dev); + + if (!idev || idev->cnf.disable_ipv6) { + NL_SET_ERR_MSG(extack, "IPv6 is disabled on this device"); + return false; + } + + return true; +} + static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, int len) { int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; - struct sock *sk = dev_net(dev)->ipv6.ndisc_sk; struct sk_buff *skb; - int err; - skb = sock_alloc_send_skb(sk, - hlen + sizeof(struct ipv6hdr) + len + tlen, - 1, &err); - if (!skb) { - ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb, err=%d\n", - __func__, err); + skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC); + if (!skb) return NULL; - } skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; @@ -389,6 +427,13 @@ static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, skb_reserve(skb, hlen + sizeof(struct ipv6hdr)); skb_reset_transport_header(skb); + /* Manually assign socket ownership as we avoid calling + * sock_alloc_send_pskb() to bypass wmem buffer limits + */ + rcu_read_lock(); + skb_set_owner_w(skb, dev_net_rcu(dev)->ipv6.ndisc_sk); + rcu_read_unlock(); + return skb; } @@ -398,12 +443,19 @@ static void ip6_nd_hdr(struct sk_buff *skb, int hop_limit, int len) { struct ipv6hdr *hdr; + struct inet6_dev *idev; + unsigned tclass; + + rcu_read_lock(); + idev = __in6_dev_get(skb->dev); + tclass = idev ? READ_ONCE(idev->cnf.ndisc_tclass) : 0; + rcu_read_unlock(); skb_push(skb, sizeof(*hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); - ip6_flow_hdr(hdr, 0, 0); + ip6_flow_hdr(hdr, tclass, 0); hdr->payload_len = htons(len); hdr->nexthdr = IPPROTO_ICMPV6; @@ -413,27 +465,32 @@ static void ip6_nd_hdr(struct sk_buff *skb, hdr->daddr = *daddr; } -static void ndisc_send_skb(struct sk_buff *skb, - const struct in6_addr *daddr, - const struct in6_addr *saddr) +void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, + const struct in6_addr *saddr) { + struct icmp6hdr *icmp6h = icmp6_hdr(skb); struct dst_entry *dst = skb_dst(skb); - struct net *net = dev_net(skb->dev); - struct sock *sk = net->ipv6.ndisc_sk; + struct net_device *dev; struct inet6_dev *idev; + struct net *net; + struct sock *sk; int err; - struct icmp6hdr *icmp6h = icmp6_hdr(skb); u8 type; type = icmp6h->icmp6_type; + rcu_read_lock(); + + net = dev_net_rcu(skb->dev); + sk = net->ipv6.ndisc_sk; if (!dst) { - struct sock *sk = net->ipv6.ndisc_sk; struct flowi6 fl6; + int oif = skb->dev->ifindex; - icmpv6_flow_init(sk, &fl6, type, saddr, daddr, skb->dev->ifindex); + icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif); dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { + rcu_read_unlock(); kfree_skb(skb); return; } @@ -446,13 +503,14 @@ static void ndisc_send_skb(struct sk_buff *skb, csum_partial(icmp6h, skb->len, 0)); - ip6_nd_hdr(skb, saddr, daddr, inet6_sk(sk)->hop_limit, skb->len); + ip6_nd_hdr(skb, saddr, daddr, READ_ONCE(inet6_sk(sk)->hop_limit), skb->len); - rcu_read_lock(); - idev = __in6_dev_get(dst->dev); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + dev = dst_dev_rcu(dst); + idev = __in6_dev_get(dev); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); - err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev, + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, + net, sk, skb, NULL, dev, dst_output); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); @@ -461,11 +519,11 @@ static void ndisc_send_skb(struct sk_buff *skb, rcu_read_unlock(); } +EXPORT_SYMBOL(ndisc_send_skb); -static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *daddr, - const struct in6_addr *solicited_addr, - bool router, bool solicited, bool override, bool inc_opt) +void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, + const struct in6_addr *solicited_addr, + bool router, bool solicited, bool override, bool inc_opt) { struct sk_buff *skb; struct in6_addr tmpaddr; @@ -479,8 +537,8 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, if (ifp) { src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) - override = 0; - inc_opt |= ifp->idev->cnf.force_tllao; + override = false; + inc_opt |= READ_ONCE(ifp->idev->cnf.force_tllao); in6_ifa_put(ifp); } else { if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr, @@ -491,15 +549,16 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, } if (!dev->addr_len) - inc_opt = 0; + inc_opt = false; if (inc_opt) - optlen += ndisc_opt_addr_space(dev); + optlen += ndisc_opt_addr_space(dev, + NDISC_NEIGHBOUR_ADVERTISEMENT); skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; - msg = (struct nd_msg *)skb_put(skb, sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, @@ -512,8 +571,8 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, if (inc_opt) ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, - dev->dev_addr); - + dev->dev_addr, + NDISC_NEIGHBOUR_ADVERTISEMENT); ndisc_send_skb(skb, daddr, src_addr); } @@ -529,7 +588,12 @@ static void ndisc_send_unsol_na(struct net_device *dev) read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { - ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &ifa->addr, + /* skip tentative addresses until dad completes */ + if (ifa->flags & IFA_F_TENTATIVE && + !(ifa->flags & IFA_F_OPTIMISTIC)) + continue; + + ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); @@ -539,33 +603,30 @@ static void ndisc_send_unsol_na(struct net_device *dev) in6_dev_put(idev); } -void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *solicit, - const struct in6_addr *daddr, const struct in6_addr *saddr) +struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit, + const struct in6_addr *saddr, u64 nonce) { - struct sk_buff *skb; - struct in6_addr addr_buf; int inc_opt = dev->addr_len; - int optlen = 0; + struct sk_buff *skb; struct nd_msg *msg; + int optlen = 0; - if (saddr == NULL) { - if (ipv6_get_lladdr(dev, &addr_buf, - (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC))) - return; - saddr = &addr_buf; - } + if (!saddr) + return NULL; if (ipv6_addr_any(saddr)) - inc_opt = 0; + inc_opt = false; if (inc_opt) - optlen += ndisc_opt_addr_space(dev); + optlen += ndisc_opt_addr_space(dev, + NDISC_NEIGHBOUR_SOLICITATION); + if (nonce != 0) + optlen += 8; skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) - return; + return NULL; - msg = (struct nd_msg *)skb_put(skb, sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, @@ -575,9 +636,38 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, if (inc_opt) ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, - dev->dev_addr); + dev->dev_addr, + NDISC_NEIGHBOUR_SOLICITATION); + if (nonce != 0) { + u8 *opt = skb_put(skb, 8); - ndisc_send_skb(skb, daddr, saddr); + opt[0] = ND_OPT_NONCE; + opt[1] = 8 >> 3; + memcpy(opt + 2, &nonce, 6); + } + + return skb; +} +EXPORT_SYMBOL(ndisc_ns_create); + +void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, + const struct in6_addr *daddr, const struct in6_addr *saddr, + u64 nonce) +{ + struct in6_addr addr_buf; + struct sk_buff *skb; + + if (!saddr) { + if (ipv6_get_lladdr(dev, &addr_buf, + (IFA_F_TENTATIVE | IFA_F_OPTIMISTIC))) + return; + saddr = &addr_buf; + } + + skb = ndisc_ns_create(dev, solicit, saddr, nonce); + + if (skb) + ndisc_send_skb(skb, daddr, saddr); } void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, @@ -611,13 +701,13 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, } #endif if (send_sllao) - optlen += ndisc_opt_addr_space(dev); + optlen += ndisc_opt_addr_space(dev, NDISC_ROUTER_SOLICITATION); skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; - msg = (struct rs_msg *)skb_put(skb, sizeof(*msg)); + msg = skb_put(skb, sizeof(*msg)); *msg = (struct rs_msg) { .icmph = { .icmp6_type = NDISC_ROUTER_SOLICITATION, @@ -626,7 +716,8 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, if (send_sllao) ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, - dev->dev_addr); + dev->dev_addr, + NDISC_ROUTER_SOLICITATION); ndisc_send_skb(skb, daddr, saddr); } @@ -652,23 +743,22 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) struct in6_addr *target = (struct in6_addr *)&neigh->primary_key; int probes = atomic_read(&neigh->probes); - if (skb && ipv6_chk_addr(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, 1)) + if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr, + dev, false, 1, + IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) saddr = &ipv6_hdr(skb)->saddr; - - if ((probes -= neigh->parms->ucast_probes) < 0) { - if (!(neigh->nud_state & NUD_VALID)) { - ND_PRINTK(1, dbg, - "%s: trying to ucast probe in NUD_INVALID: %pI6\n", - __func__, target); + probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); + if (probes < 0) { + if (!(READ_ONCE(neigh->nud_state) & NUD_VALID)) { + net_dbg_ratelimited("%s: trying to ucast probe in NUD_INVALID: %pI6\n", + __func__, target); } - ndisc_send_ns(dev, neigh, target, target, saddr); - } else if ((probes -= neigh->parms->app_probes) < 0) { -#ifdef CONFIG_ARPD + ndisc_send_ns(dev, target, target, saddr, 0); + } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); -#endif } else { addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(dev, NULL, target, &mcaddr, saddr); + ndisc_send_ns(dev, target, &mcaddr, saddr, 0); } } @@ -678,16 +768,23 @@ static int pndisc_is_router(const void *pkey, struct pneigh_entry *n; int ret = -1; - read_lock_bh(&nd_tbl.lock); - n = __pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev); + n = pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev); if (n) - ret = !!(n->flags & NTF_ROUTER); - read_unlock_bh(&nd_tbl.lock); + ret = !!(READ_ONCE(n->flags) & NTF_ROUTER); return ret; } -static void ndisc_recv_ns(struct sk_buff *skb) +void ndisc_update(const struct net_device *dev, struct neighbour *neigh, + const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, + struct ndisc_options *ndopts) +{ + neigh_update(neigh, lladdr, new, flags, 0); + /* report ndisc ops about neighbour update */ + ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts); +} + +static enum skb_drop_reason ndisc_recv_ns(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; @@ -701,17 +798,17 @@ static void ndisc_recv_ns(struct sk_buff *skb) struct inet6_dev *idev = NULL; struct neighbour *neigh; int dad = ipv6_addr_any(saddr); - bool inc; int is_router = -1; + SKB_DR(reason); + u64 nonce = 0; + bool inc; - if (skb->len < sizeof(struct nd_msg)) { - ND_PRINTK(2, warn, "NS: packet too short\n"); - return; - } + if (skb->len < sizeof(struct nd_msg)) + return SKB_DROP_REASON_PKT_TOO_SMALL; if (ipv6_addr_is_multicast(&msg->target)) { - ND_PRINTK(2, warn, "NS: multicast target address\n"); - return; + net_dbg_ratelimited("NS: multicast target address\n"); + return reason; } /* @@ -719,21 +816,18 @@ static void ndisc_recv_ns(struct sk_buff *skb) * DAD has to be destined for solicited node multicast address. */ if (dad && !ipv6_addr_is_solict_mult(daddr)) { - ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n"); - return; + net_dbg_ratelimited("NS: bad DAD packet (wrong destination)\n"); + return reason; } - if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) { - ND_PRINTK(2, warn, "NS: invalid ND options\n"); - return; - } + if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) + return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev); if (!lladdr) { - ND_PRINTK(2, warn, - "NS: invalid link-layer address length\n"); - return; + net_dbg_ratelimited("NS: invalid link-layer address length\n"); + return reason; } /* RFC2461 7.1.1: @@ -742,26 +836,34 @@ static void ndisc_recv_ns(struct sk_buff *skb) * in the message. */ if (dad) { - ND_PRINTK(2, warn, - "NS: bad DAD packet (link-layer address option)\n"); - return; + net_dbg_ratelimited("NS: bad DAD packet (link-layer address option)\n"); + return reason; } } + if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1) + memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6); inc = ipv6_addr_is_multicast(daddr); ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { - +have_ifp: if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) { if (dad) { + if (nonce != 0 && ifp->dad_nonce == nonce) { + u8 *np = (u8 *)&nonce; + /* Matching nonce if looped back */ + net_dbg_ratelimited("%s: IPv6 DAD loopback for address %pI6c nonce %pM ignored\n", + ifp->idev->dev->name, &ifp->addr, np); + goto out; + } /* * We are colliding with another node * who is doing DAD * so fail our DAD process */ - addrconf_dad_failure(ifp); - return; + addrconf_dad_failure(skb, ifp); + return reason; } else { /* * This is not a dad solicitation. @@ -778,20 +880,33 @@ static void ndisc_recv_ns(struct sk_buff *skb) } else { struct net *net = dev_net(dev); + /* perhaps an address on the master device */ + if (netif_is_l3_slave(dev)) { + struct net_device *mdev; + + mdev = netdev_master_upper_dev_get_rcu(dev); + if (mdev) { + ifp = ipv6_get_ifaddr(net, &msg->target, mdev, 1); + if (ifp) + goto have_ifp; + } + } + idev = in6_dev_get(dev); if (!idev) { /* XXX: count this drop? */ - return; + return reason; } if (ipv6_chk_acast_addr(net, dev, &msg->target) || - (idev->cnf.forwarding && - (net->ipv6.devconf_all->proxy_ndp || idev->cnf.proxy_ndp) && + (READ_ONCE(idev->cnf.forwarding) && + (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) || + READ_ONCE(idev->cnf.proxy_ndp)) && (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && - inc != 0 && - idev->nd_parms->proxy_delay != 0) { + inc && + NEIGH_VAR(idev->nd_parms, PROXY_DELAY) != 0) { /* * for anycast or proxy, * sender should delay its response @@ -804,15 +919,17 @@ static void ndisc_recv_ns(struct sk_buff *skb) pneigh_enqueue(&nd_tbl, idev->nd_parms, n); goto out; } - } else + } else { + SKB_DR_SET(reason, IPV6_NDISC_NS_OTHERHOST); goto out; + } } if (is_router < 0) - is_router = idev->cnf.forwarding; + is_router = READ_ONCE(idev->cnf.forwarding); if (dad) { - ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &msg->target, + ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target, !!is_router, false, (ifp != NULL), true); goto out; } @@ -829,15 +946,16 @@ static void ndisc_recv_ns(struct sk_buff *skb) neigh = __neigh_lookup(&nd_tbl, saddr, dev, !inc || lladdr || !dev->addr_len); if (neigh) - neigh_update(neigh, lladdr, NUD_STALE, + ndisc_update(dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| - NEIGH_UPDATE_F_OVERRIDE); + NEIGH_UPDATE_F_OVERRIDE, + NDISC_NEIGHBOUR_SOLICITATION, &ndopts); if (neigh || !dev->header_ops) { - ndisc_send_na(dev, neigh, saddr, &msg->target, - !!is_router, + ndisc_send_na(dev, saddr, &msg->target, !!is_router, true, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); + reason = SKB_CONSUMED; } out: @@ -845,55 +963,83 @@ out: in6_ifa_put(ifp); else in6_dev_put(idev); + return reason; } -static void ndisc_recv_na(struct sk_buff *skb) +static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr) +{ + struct inet6_dev *idev = __in6_dev_get(dev); + + switch (READ_ONCE(idev->cnf.accept_untracked_na)) { + case 0: /* Don't accept untracked na (absent in neighbor cache) */ + return 0; + case 1: /* Create new entries from na if currently untracked */ + return 1; + case 2: /* Create new entries from untracked na only if saddr is in the + * same subnet as an address configured on the interface that + * received the na + */ + return !!ipv6_chk_prefix(saddr, dev); + default: + return 0; + } +} + +static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); - const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; + struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; + struct inet6_dev *idev = __in6_dev_get(dev); struct inet6_ifaddr *ifp; struct neighbour *neigh; + SKB_DR(reason); + u8 new_state; - if (skb->len < sizeof(struct nd_msg)) { - ND_PRINTK(2, warn, "NA: packet too short\n"); - return; - } + if (skb->len < sizeof(struct nd_msg)) + return SKB_DROP_REASON_PKT_TOO_SMALL; if (ipv6_addr_is_multicast(&msg->target)) { - ND_PRINTK(2, warn, "NA: target address is multicast\n"); - return; + net_dbg_ratelimited("NA: target address is multicast\n"); + return reason; } if (ipv6_addr_is_multicast(daddr) && msg->icmph.icmp6_solicited) { - ND_PRINTK(2, warn, "NA: solicited NA is multicasted\n"); - return; + net_dbg_ratelimited("NA: solicited NA is multicasted\n"); + return reason; } - if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) { - ND_PRINTK(2, warn, "NS: invalid ND option\n"); - return; - } + /* For some 802.11 wireless deployments (and possibly other networks), + * there will be a NA proxy and unsolicitd packets are attacks + * and thus should not be accepted. + * drop_unsolicited_na takes precedence over accept_untracked_na + */ + if (!msg->icmph.icmp6_solicited && idev && + READ_ONCE(idev->cnf.drop_unsolicited_na)) + return reason; + + if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) + return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; + if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, dev); if (!lladdr) { - ND_PRINTK(2, warn, - "NA: invalid link-layer address length\n"); - return; + net_dbg_ratelimited("NA: invalid link-layer address length\n"); + return reason; } } ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { if (skb->pkt_type != PACKET_LOOPBACK && (ifp->flags & IFA_F_TENTATIVE)) { - addrconf_dad_failure(ifp); - return; + addrconf_dad_failure(skb, ifp); + return reason; } /* What should we make now? The advertisement is invalid, but ndisc specs say nothing @@ -905,19 +1051,43 @@ static void ndisc_recv_na(struct sk_buff *skb) unsolicited advertisement. */ if (skb->pkt_type != PACKET_LOOPBACK) - ND_PRINTK(1, warn, - "NA: someone advertises our address %pI6 on %s!\n", - &ifp->addr, ifp->idev->dev->name); + net_warn_ratelimited("NA: %pM advertised our address %pI6c on %s!\n", + eth_hdr(skb)->h_source, &ifp->addr, + ifp->idev->dev->name); in6_ifa_put(ifp); - return; + return reason; } + neigh = neigh_lookup(&nd_tbl, &msg->target, dev); - if (neigh) { + /* RFC 9131 updates original Neighbour Discovery RFC 4861. + * NAs with Target LL Address option without a corresponding + * entry in the neighbour cache can now create a STALE neighbour + * cache entry on routers. + * + * entry accept fwding solicited behaviour + * ------- ------ ------ --------- ---------------------- + * present X X 0 Set state to STALE + * present X X 1 Set state to REACHABLE + * absent 0 X X Do nothing + * absent 1 0 X Do nothing + * absent 1 1 X Add a new STALE entry + * + * Note that we don't do a (daddr == all-routers-mcast) check. + */ + new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE; + if (!neigh && lladdr && idev && READ_ONCE(idev->cnf.forwarding)) { + if (accept_untracked_na(dev, saddr)) { + neigh = neigh_create(&nd_tbl, &msg->target, dev); + new_state = NUD_STALE; + } + } + + if (neigh && !IS_ERR(neigh)) { u8 old_flags = neigh->flags; struct net *net = dev_net(dev); - if (neigh->nud_state & NUD_FAILED) + if (READ_ONCE(neigh->nud_state) & NUD_FAILED) goto out; /* @@ -926,35 +1096,35 @@ static void ndisc_recv_na(struct sk_buff *skb) * has already sent a NA to us. */ if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && - net->ipv6.devconf_all->forwarding && net->ipv6.devconf_all->proxy_ndp && - pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) { + READ_ONCE(net->ipv6.devconf_all->forwarding) && + READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && + pneigh_lookup(&nd_tbl, net, &msg->target, dev)) { /* XXX: idev->cnf.proxy_ndp */ goto out; } - neigh_update(neigh, lladdr, - msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE, + ndisc_update(dev, neigh, lladdr, + new_state, NEIGH_UPDATE_F_WEAK_OVERRIDE| (msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| - (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0)); + (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0), + NDISC_NEIGHBOUR_ADVERTISEMENT, &ndopts); if ((old_flags & ~neigh->flags) & NTF_ROUTER) { /* * Change: router to host */ - struct rt6_info *rt; - rt = rt6_get_dflt_router(saddr, dev); - if (rt) - ip6_del_rt(rt); + rt6_clean_tohost(dev_net(dev), saddr); } - + reason = SKB_CONSUMED; out: neigh_release(neigh); } + return reason; } -static void ndisc_recv_rs(struct sk_buff *skb) +static enum skb_drop_reason ndisc_recv_rs(struct sk_buff *skb) { struct rs_msg *rs_msg = (struct rs_msg *)skb_transport_header(skb); unsigned long ndoptlen = skb->len - sizeof(*rs_msg); @@ -963,18 +1133,19 @@ static void ndisc_recv_rs(struct sk_buff *skb) const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; struct ndisc_options ndopts; u8 *lladdr = NULL; + SKB_DR(reason); if (skb->len < sizeof(*rs_msg)) - return; + return SKB_DROP_REASON_PKT_TOO_SMALL; idev = __in6_dev_get(skb->dev); if (!idev) { - ND_PRINTK(1, err, "RS: can't find in6 device\n"); - return; + net_err_ratelimited("RS: can't find in6 device\n"); + return reason; } /* Don't accept RS if we're not in router mode */ - if (!idev->cnf.forwarding) + if (!READ_ONCE(idev->cnf.forwarding)) goto out; /* @@ -985,10 +1156,8 @@ static void ndisc_recv_rs(struct sk_buff *skb) goto out; /* Parse ND options */ - if (!ndisc_parse_options(rs_msg->opt, ndoptlen, &ndopts)) { - ND_PRINTK(2, notice, "NS: invalid ND option, ignored\n"); - goto out; - } + if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts)) + return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, @@ -999,14 +1168,16 @@ static void ndisc_recv_rs(struct sk_buff *skb) neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1); if (neigh) { - neigh_update(neigh, lladdr, NUD_STALE, + ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| - NEIGH_UPDATE_F_OVERRIDE_ISROUTER); + NEIGH_UPDATE_F_OVERRIDE_ISROUTER, + NDISC_ROUTER_SOLICITATION, &ndopts); neigh_release(neigh); + reason = SKB_CONSUMED; } out: - return; + return reason; } static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) @@ -1022,13 +1193,13 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) size_t msg_size = base_size + nla_total_size(sizeof(struct in6_addr)); skb = nlmsg_new(msg_size, GFP_ATOMIC); - if (skb == NULL) { + if (!skb) { err = -ENOBUFS; goto errout; } nlh = nlmsg_put(skb, 0, 0, RTM_NEWNDUSEROPT, base_size, 0); - if (nlh == NULL) { + if (!nlh) { goto nla_put_failure; } @@ -1041,8 +1212,7 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3); - if (nla_put(skb, NDUSEROPT_SRCADDR, sizeof(struct in6_addr), - &ipv6_hdr(ra)->saddr)) + if (nla_put_in6_addr(skb, NDUSEROPT_SRCADDR, &ipv6_hdr(ra)->saddr)) goto nla_put_failure; nlmsg_end(skb, nlh); @@ -1056,61 +1226,65 @@ errout: rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err); } -static void ndisc_router_discovery(struct sk_buff *skb) +static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) { struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb); + bool send_ifinfo_notify = false; struct neighbour *neigh = NULL; + struct ndisc_options ndopts; + struct fib6_info *rt = NULL; struct inet6_dev *in6_dev; - struct rt6_info *rt = NULL; + struct fib6_table *table; + u32 defrtr_usr_metric; + unsigned int pref = 0; + __u32 old_if_flags; + struct net *net; + SKB_DR(reason); int lifetime; - struct ndisc_options ndopts; int optlen; - unsigned int pref = 0; - __u8 * opt = (__u8 *)(ra_msg + 1); + __u8 *opt = (__u8 *)(ra_msg + 1); optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) - sizeof(struct ra_msg); + net_dbg_ratelimited("RA: %s, dev: %s\n", __func__, skb->dev->name); if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK(2, warn, "RA: source address is not link-local\n"); - return; - } - if (optlen < 0) { - ND_PRINTK(2, warn, "RA: packet too short\n"); - return; + net_dbg_ratelimited("RA: source address is not link-local\n"); + return reason; } + if (optlen < 0) + return SKB_DROP_REASON_PKT_TOO_SMALL; #ifdef CONFIG_IPV6_NDISC_NODETYPE if (skb->ndisc_nodetype == NDISC_NODETYPE_HOST) { - ND_PRINTK(2, warn, "RA: from host or unauthorized router\n"); - return; + net_dbg_ratelimited("RA: from host or unauthorized router\n"); + return reason; } #endif - /* - * set the RA_RECV flag in the interface - */ - in6_dev = __in6_dev_get(skb->dev); - if (in6_dev == NULL) { - ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n", - skb->dev->name); - return; + if (!in6_dev) { + net_err_ratelimited("RA: can't find inet6 device for %s\n", skb->dev->name); + return reason; } - if (!ndisc_parse_options(opt, optlen, &ndopts)) { - ND_PRINTK(2, warn, "RA: invalid ND options\n"); - return; - } + if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) + return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; - if (!ipv6_accept_ra(in6_dev)) + if (!ipv6_accept_ra(in6_dev)) { + net_dbg_ratelimited("RA: %s, did not accept ra for dev: %s\n", __func__, + skb->dev->name); goto skip_linkparms; + } #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ - if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) + if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { + net_dbg_ratelimited("RA: %s, nodetype is NODEFAULT, dev: %s\n", __func__, + skb->dev->name); goto skip_linkparms; + } #endif if (in6_dev->if_flags & IF_RS_SENT) { @@ -1125,6 +1299,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) * Remember the managed/otherconf flags from most recently * received RA message (RFC 2462) -- yoshfuji */ + old_if_flags = in6_dev->if_flags; in6_dev->if_flags = (in6_dev->if_flags & ~(IF_RA_MANAGED | IF_RA_OTHERCONF)) | (ra_msg->icmph.icmp6_addrconf_managed ? @@ -1132,70 +1307,116 @@ static void ndisc_router_discovery(struct sk_buff *skb) (ra_msg->icmph.icmp6_addrconf_other ? IF_RA_OTHERCONF : 0); - if (!in6_dev->cnf.accept_ra_defrtr) - goto skip_defrtr; + if (old_if_flags != in6_dev->if_flags) + send_ifinfo_notify = true; - if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0)) + if (!READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) { + net_dbg_ratelimited("RA: %s, defrtr is false for dev: %s\n", __func__, + skb->dev->name); goto skip_defrtr; + } lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); + if (lifetime != 0 && + lifetime < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) { + net_dbg_ratelimited("RA: router lifetime (%ds) is too short: %s\n", lifetime, + skb->dev->name); + goto skip_defrtr; + } + + /* Do not accept RA with source-addr found on local machine unless + * accept_ra_from_local is set to true. + */ + net = dev_net(in6_dev->dev); + if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && + ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { + net_dbg_ratelimited("RA from local address detected on dev: %s: default router ignored\n", + skb->dev->name); + goto skip_defrtr; + } #ifdef CONFIG_IPV6_ROUTER_PREF pref = ra_msg->icmph.icmp6_router_pref; /* 10b is handled as if it were 00b (medium) */ if (pref == ICMPV6_ROUTER_PREF_INVALID || - !in6_dev->cnf.accept_ra_rtr_pref) + !READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref)) pref = ICMPV6_ROUTER_PREF_MEDIUM; #endif - - rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev); - + /* routes added from RAs do not use nexthop objects */ + rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev); if (rt) { - neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); + neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6, + rt->fib6_nh->fib_nh_dev, NULL, + &ipv6_hdr(skb)->saddr); if (!neigh) { - ND_PRINTK(0, err, - "RA: %s got default router without neighbour\n", - __func__); - ip6_rt_put(rt); - return; + net_err_ratelimited("RA: %s got default router without neighbour\n", + __func__); + fib6_info_release(rt); + return reason; } } - if (rt && lifetime == 0) { - ip6_del_rt(rt); + /* Set default route metric as specified by user */ + defrtr_usr_metric = in6_dev->cnf.ra_defrtr_metric; + /* delete the route if lifetime is 0 or if metric needs change */ + if (rt && (lifetime == 0 || rt->fib6_metric != defrtr_usr_metric)) { + ip6_del_rt(net, rt, false); rt = NULL; } - if (rt == NULL && lifetime) { - ND_PRINTK(3, dbg, "RA: adding default router\n"); + net_dbg_ratelimited("RA: rt: %p lifetime: %d, metric: %d, for dev: %s\n", rt, lifetime, + defrtr_usr_metric, skb->dev->name); + if (!rt && lifetime) { + net_dbg_ratelimited("RA: adding default router\n"); - rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref); - if (rt == NULL) { - ND_PRINTK(0, err, - "RA: %s failed to add default route\n", - __func__); - return; + if (neigh) + neigh_release(neigh); + + rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, + skb->dev, pref, defrtr_usr_metric, + lifetime); + if (!rt) { + net_err_ratelimited("RA: %s failed to add default route\n", __func__); + return reason; } - neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); - if (neigh == NULL) { - ND_PRINTK(0, err, - "RA: %s got default router without neighbour\n", - __func__); - ip6_rt_put(rt); - return; + neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6, + rt->fib6_nh->fib_nh_dev, NULL, + &ipv6_hdr(skb)->saddr); + if (!neigh) { + net_err_ratelimited("RA: %s got default router without neighbour\n", + __func__); + fib6_info_release(rt); + return reason; } neigh->flags |= NTF_ROUTER; - } else if (rt) { - rt->rt6i_flags = (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); + } else if (rt && IPV6_EXTRACT_PREF(rt->fib6_flags) != pref) { + struct nl_info nlinfo = { + .nl_net = net, + }; + rt->fib6_flags = (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); + inet6_rt_notify(RTM_NEWROUTE, rt, &nlinfo, NLM_F_REPLACE); } - if (rt) - rt6_set_expires(rt, jiffies + (HZ * lifetime)); - if (ra_msg->icmph.icmp6_hop_limit) { - in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; - if (rt) - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, - ra_msg->icmph.icmp6_hop_limit); + if (rt) { + table = rt->fib6_table; + spin_lock_bh(&table->tb6_lock); + + fib6_set_expires(rt, jiffies + (HZ * lifetime)); + fib6_add_gc_list(rt); + + spin_unlock_bh(&table->tb6_lock); + } + if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) < 256 && + ra_msg->icmph.icmp6_hop_limit) { + if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) <= + ra_msg->icmph.icmp6_hop_limit) { + WRITE_ONCE(in6_dev->cnf.hop_limit, + ra_msg->icmph.icmp6_hop_limit); + fib6_metric_set(rt, RTAX_HOPLIMIT, + ra_msg->icmph.icmp6_hop_limit); + } else { + net_dbg_ratelimited("RA: Got route advertisement with lower hop_limit than minimum\n"); + } } skip_defrtr: @@ -1209,11 +1430,11 @@ skip_defrtr: if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/HZ) { rtime = (rtime*HZ)/1000; - if (rtime < HZ/10) - rtime = HZ/10; - in6_dev->nd_parms->retrans_time = rtime; + if (rtime < HZ/100) + rtime = HZ/100; + NEIGH_VAR_SET(in6_dev->nd_parms, RETRANS_TIME, rtime); in6_dev->tstamp = jiffies; - inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); + send_ifinfo_notify = true; } rtime = ntohl(ra_msg->reachable_time); @@ -1223,12 +1444,14 @@ skip_defrtr: if (rtime < HZ/10) rtime = HZ/10; - if (rtime != in6_dev->nd_parms->base_reachable_time) { - in6_dev->nd_parms->base_reachable_time = rtime; - in6_dev->nd_parms->gc_staletime = 3 * rtime; - in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime); + if (rtime != NEIGH_VAR(in6_dev->nd_parms, BASE_REACHABLE_TIME)) { + NEIGH_VAR_SET(in6_dev->nd_parms, + BASE_REACHABLE_TIME, rtime); + NEIGH_VAR_SET(in6_dev->nd_parms, + GC_STALETIME, 3 * rtime); + neigh_set_reach_time(in6_dev->nd_parms); in6_dev->tstamp = jiffies; - inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); + send_ifinfo_notify = true; } } } @@ -1248,26 +1471,35 @@ skip_linkparms: lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) { - ND_PRINTK(2, warn, - "RA: invalid link-layer address length\n"); + net_dbg_ratelimited("RA: invalid link-layer address length\n"); goto out; } } - neigh_update(neigh, lladdr, NUD_STALE, + ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| - NEIGH_UPDATE_F_ISROUTER); + NEIGH_UPDATE_F_ISROUTER, + NDISC_ROUTER_ADVERTISEMENT, &ndopts); + reason = SKB_CONSUMED; } - if (!ipv6_accept_ra(in6_dev)) + if (!ipv6_accept_ra(in6_dev)) { + net_dbg_ratelimited("RA: %s, accept_ra is false for dev: %s\n", __func__, + skb->dev->name); goto out; + } #ifdef CONFIG_IPV6_ROUTE_INFO - if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0)) + if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && + ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, + in6_dev->dev, 0)) { + net_dbg_ratelimited("RA from local address detected on dev: %s: router info ignored.\n", + skb->dev->name); goto skip_routeinfo; + } - if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) { + if (READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref) && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_ri; p; @@ -1278,9 +1510,17 @@ skip_linkparms: ri->prefix_len == 0) continue; #endif - if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen) + if (ri->prefix_len == 0 && + !READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) + continue; + if (ri->lifetime != 0 && + ntohl(ri->lifetime) < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) + continue; + if (ri->prefix_len < READ_ONCE(in6_dev->cnf.accept_ra_rt_info_min_plen)) continue; - rt6_route_rcv(skb->dev, (u8*)p, (p->nd_opt_len) << 3, + if (ri->prefix_len > READ_ONCE(in6_dev->cnf.accept_ra_rt_info_max_plen)) + continue; + rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, &ipv6_hdr(skb)->saddr); } } @@ -1290,11 +1530,14 @@ skip_routeinfo: #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific ndopts from interior routers */ - if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) + if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { + net_dbg_ratelimited("RA: %s, nodetype is NODEFAULT (interior routes), dev: %s\n", + __func__, skb->dev->name); goto out; + } #endif - if (in6_dev->cnf.accept_ra_pinfo && ndopts.nd_opts_pi) { + if (READ_ONCE(in6_dev->cnf.accept_ra_pinfo) && ndopts.nd_opts_pi) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_pi; p; @@ -1305,21 +1548,23 @@ skip_routeinfo: } } - if (ndopts.nd_opts_mtu) { + if (ndopts.nd_opts_mtu && READ_ONCE(in6_dev->cnf.accept_ra_mtu)) { __be32 n; u32 mtu; - memcpy(&n, ((u8*)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); + memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); mtu = ntohl(n); - if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) { - ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu); - } else if (in6_dev->cnf.mtu6 != mtu) { - in6_dev->cnf.mtu6 = mtu; - - if (rt) - dst_metric_set(&rt->dst, RTAX_MTU, mtu); + if (in6_dev->ra_mtu != mtu) { + in6_dev->ra_mtu = mtu; + send_ifinfo_notify = true; + } + if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) { + net_dbg_ratelimited("RA: invalid mtu: %d\n", mtu); + } else if (READ_ONCE(in6_dev->cnf.mtu6) != mtu) { + WRITE_ONCE(in6_dev->cnf.mtu6, mtu); + fib6_metric_set(rt, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } } @@ -1328,56 +1573,66 @@ skip_routeinfo: struct nd_opt_hdr *p; for (p = ndopts.nd_useropts; p; - p = ndisc_next_useropt(p, ndopts.nd_useropts_end)) { + p = ndisc_next_useropt(skb->dev, p, + ndopts.nd_useropts_end)) { ndisc_ra_useropt(skb, p); } } if (ndopts.nd_opts_tgt_lladdr || ndopts.nd_opts_rh) { - ND_PRINTK(2, warn, "RA: invalid RA options\n"); + net_dbg_ratelimited("RA: invalid RA options\n"); } out: - ip6_rt_put(rt); + /* Send a notify if RA changed managed/otherconf flags or + * timer settings or ra_mtu value + */ + if (send_ifinfo_notify) + inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); + + fib6_info_release(rt); if (neigh) neigh_release(neigh); + return reason; } -static void ndisc_redirect_rcv(struct sk_buff *skb) +static enum skb_drop_reason ndisc_redirect_rcv(struct sk_buff *skb) { - u8 *hdr; - struct ndisc_options ndopts; struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb); u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct rd_msg, opt)); + struct ndisc_options ndopts; + SKB_DR(reason); + u8 *hdr; #ifdef CONFIG_IPV6_NDISC_NODETYPE switch (skb->ndisc_nodetype) { case NDISC_NODETYPE_HOST: case NDISC_NODETYPE_NODEFAULT: - ND_PRINTK(2, warn, - "Redirect: from host or unauthorized router\n"); - return; + net_dbg_ratelimited("Redirect: from host or unauthorized router\n"); + return reason; } #endif if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK(2, warn, - "Redirect: source address is not link-local\n"); - return; + net_dbg_ratelimited("Redirect: source address is not link-local\n"); + return reason; } - if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) - return; + if (!ndisc_parse_options(skb->dev, msg->opt, ndoptlen, &ndopts)) + return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; - if (!ndopts.nd_opts_rh) - return; + if (!ndopts.nd_opts_rh) { + ip6_redirect_no_header(skb, dev_net(skb->dev), + skb->dev->ifindex); + return reason; + } hdr = (u8 *)ndopts.nd_opts_rh; hdr += 8; if (!pskb_pull(skb, hdr - skb_transport_header(skb))) - return; + return SKB_DROP_REASON_PKT_TOO_SMALL; - icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); + return icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, @@ -1391,13 +1646,14 @@ 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) { struct net_device *dev = skb->dev; - struct net *net = dev_net(dev); + struct net *net = dev_net_rcu(dev); struct sock *sk = net->ipv6.ndisc_sk; int optlen = 0; struct inet_peer *peer; @@ -1408,19 +1664,24 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) struct dst_entry *dst; struct flowi6 fl6; int rd_len; - u8 ha_buf[MAX_ADDR_LEN], *ha = NULL; + u8 ha_buf[MAX_ADDR_LEN], *ha = NULL, + ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL; bool ret; + if (netif_is_l3_master(dev)) { + dev = dev_get_by_index_rcu(net, IPCB(skb)->iif); + if (!dev) + return; + } + if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { - ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n", - dev->name); + net_dbg_ratelimited("Redirect: no link-local address on %s\n", dev->name); return; } if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) && ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK(2, warn, - "Redirect: target address is not link-local unicast\n"); + net_dbg_ratelimited("Redirect: target address is not link-local unicast\n"); return; } @@ -1436,25 +1697,23 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) if (IS_ERR(dst)) return; - rt = (struct rt6_info *) dst; + rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_GATEWAY) { - ND_PRINTK(2, warn, - "Redirect: destination is not a neighbour\n"); + net_dbg_ratelimited("Redirect: destination is not a neighbour\n"); goto release; } - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + + peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr); ret = inet_peer_xrlim_allow(peer, 1*HZ); - if (peer) - inet_putpeer(peer); + if (!ret) goto release; if (dev->addr_len) { struct neighbour *neigh = dst_neigh_lookup(skb_dst(skb), target); if (!neigh) { - ND_PRINTK(2, warn, - "Redirect: no neigh for target address\n"); + net_dbg_ratelimited("Redirect: no neigh for target address\n"); goto release; } @@ -1463,7 +1722,9 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) memcpy(ha_buf, neigh->ha, dev->addr_len); read_unlock_bh(&neigh->lock); ha = ha_buf; - optlen += ndisc_opt_addr_space(dev); + optlen += ndisc_redirect_opt_addr_space(dev, neigh, + ops_data_buf, + &ops_data); } else read_unlock_bh(&neigh->lock); @@ -1480,7 +1741,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) if (!buff) goto release; - msg = (struct rd_msg *)skb_put(buff, sizeof(*msg)); + msg = skb_put(buff, sizeof(*msg)); *msg = (struct rd_msg) { .icmph = { .icmp6_type = NDISC_REDIRECT, @@ -1494,7 +1755,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) */ if (ha) - ndisc_fill_addr_option(buff, ND_OPT_TARGET_LL_ADDR, ha); + ndisc_fill_redirect_addr_option(buff, ha, ops_data); /* * build redirect option and copy skb over to the new packet. @@ -1513,80 +1774,122 @@ release: static void pndisc_redo(struct sk_buff *skb) { - ndisc_recv_ns(skb); - kfree_skb(skb); + enum skb_drop_reason reason = ndisc_recv_ns(skb); + + kfree_skb_reason(skb, reason); } -int ndisc_rcv(struct sk_buff *skb) +static int ndisc_is_multicast(const void *pkey) +{ + return ipv6_addr_is_multicast((struct in6_addr *)pkey); +} + +static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) +{ + struct inet6_dev *idev = __in6_dev_get(skb->dev); + + if (!idev) + return true; + if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED && + READ_ONCE(idev->cnf.suppress_frag_ndisc)) { + net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n"); + return true; + } + return false; +} + +enum skb_drop_reason ndisc_rcv(struct sk_buff *skb) { struct nd_msg *msg; + SKB_DR(reason); + + if (ndisc_suppress_frag_ndisc(skb)) + return SKB_DROP_REASON_IPV6_NDISC_FRAG; if (skb_linearize(skb)) - return 0; + return SKB_DROP_REASON_NOMEM; msg = (struct nd_msg *)skb_transport_header(skb); __skb_push(skb, skb->data - skb_transport_header(skb)); if (ipv6_hdr(skb)->hop_limit != 255) { - ND_PRINTK(2, warn, "NDISC: invalid hop-limit: %d\n", - ipv6_hdr(skb)->hop_limit); - return 0; + net_dbg_ratelimited("NDISC: invalid hop-limit: %d\n", ipv6_hdr(skb)->hop_limit); + return SKB_DROP_REASON_IPV6_NDISC_HOP_LIMIT; } if (msg->icmph.icmp6_code != 0) { - ND_PRINTK(2, warn, "NDISC: invalid ICMPv6 code: %d\n", - msg->icmph.icmp6_code); - return 0; + net_dbg_ratelimited("NDISC: invalid ICMPv6 code: %d\n", msg->icmph.icmp6_code); + return SKB_DROP_REASON_IPV6_NDISC_BAD_CODE; } - memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); - switch (msg->icmph.icmp6_type) { case NDISC_NEIGHBOUR_SOLICITATION: - ndisc_recv_ns(skb); + memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); + reason = ndisc_recv_ns(skb); break; case NDISC_NEIGHBOUR_ADVERTISEMENT: - ndisc_recv_na(skb); + reason = ndisc_recv_na(skb); break; case NDISC_ROUTER_SOLICITATION: - ndisc_recv_rs(skb); + reason = ndisc_recv_rs(skb); break; case NDISC_ROUTER_ADVERTISEMENT: - ndisc_router_discovery(skb); + reason = ndisc_router_discovery(skb); break; case NDISC_REDIRECT: - ndisc_redirect_rcv(skb); + reason = ndisc_redirect_rcv(skb); break; } - return 0; + return reason; } static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_change_info *change_info; struct net *net = dev_net(dev); struct inet6_dev *idev; + bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); - fib6_run_gc(~0UL, net); + fib6_run_gc(0, net, false); + fallthrough; + case NETDEV_UP: idev = in6_dev_get(dev); if (!idev) break; - if (idev->cnf.ndisc_notify) + if (READ_ONCE(idev->cnf.ndisc_notify) || + READ_ONCE(net->ipv6.devconf_all->ndisc_notify)) ndisc_send_unsol_na(dev); in6_dev_put(idev); break; + case NETDEV_CHANGE: + idev = in6_dev_get(dev); + if (!idev) + evict_nocarrier = true; + else { + evict_nocarrier = READ_ONCE(idev->cnf.ndisc_evict_nocarrier) && + READ_ONCE(net->ipv6.devconf_all->ndisc_evict_nocarrier); + in6_dev_put(idev); + } + + change_info = ptr; + if (change_info->flags_changed & IFF_NOARP) + neigh_changeaddr(&nd_tbl, dev); + if (evict_nocarrier && !netif_carrier_ok(dev)) + neigh_carrier_down(&nd_tbl, dev); + break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); - fib6_run_gc(~0UL, net); + fib6_run_gc(0, net, false); break; case NETDEV_NOTIFY_PEERS: ndisc_send_unsol_na(dev); @@ -1600,16 +1903,17 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, static struct notifier_block ndisc_netdev_notifier = { .notifier_call = ndisc_netdev_event, + .priority = ADDRCONF_NOTIFY_PRIORITY - 5, }; #ifdef CONFIG_SYSCTL -static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl, +static void ndisc_warn_deprecated_sysctl(const struct ctl_table *ctl, const char *func, const char *dev_name) { static char warncomm[TASK_COMM_LEN]; static int warned; if (strcmp(warncomm, current->comm) && warned < 5) { - strcpy(warncomm, current->comm); + strscpy(warncomm, current->comm); pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n", warncomm, func, dev_name, ctl->procname, @@ -1618,7 +1922,8 @@ static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl, } } -int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) +int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write, void *buffer, + size_t *lenp, loff_t *ppos) { struct net_device *dev = ctl->extra1; struct inet6_dev *idev; @@ -1629,23 +1934,24 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *bu ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default"); if (strcmp(ctl->procname, "retrans_time") == 0) - ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + ret = neigh_proc_dointvec(ctl, write, buffer, lenp, ppos); else if (strcmp(ctl->procname, "base_reachable_time") == 0) - ret = proc_dointvec_jiffies(ctl, write, - buffer, lenp, ppos); + ret = neigh_proc_dointvec_jiffies(ctl, write, + buffer, lenp, ppos); else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) || (strcmp(ctl->procname, "base_reachable_time_ms") == 0)) - ret = proc_dointvec_ms_jiffies(ctl, write, - buffer, lenp, ppos); + ret = neigh_proc_dointvec_ms_jiffies(ctl, write, + buffer, lenp, ppos); else ret = -1; if (write && ret == 0 && dev && (idev = in6_dev_get(dev)) != NULL) { - if (ctl->data == &idev->nd_parms->base_reachable_time) - idev->nd_parms->reachable_time = neigh_rand_reach_time(idev->nd_parms->base_reachable_time); - idev->tstamp = jiffies; + if (ctl->data == NEIGH_VAR_PTR(idev->nd_parms, BASE_REACHABLE_TIME)) + neigh_set_reach_time(idev->nd_parms); + + WRITE_ONCE(idev->tstamp, jiffies); inet6_ifinfo_notify(RTM_NEWLINK, idev); in6_dev_put(idev); } @@ -1664,9 +1970,8 @@ static int __net_init ndisc_net_init(struct net *net) err = inet_ctl_sock_create(&sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { - ND_PRINTK(0, err, - "NDISC: Failed to initialize the control socket (err %d)\n", - err); + net_err_ratelimited("NDISC: Failed to initialize the control socket (err %d)\n", + err); return err; } @@ -1675,7 +1980,7 @@ static int __net_init ndisc_net_init(struct net *net) np = inet6_sk(sk); np->hop_limit = 255; /* Do not loopback ndisc messages */ - np->mc_loop = 0; + inet6_clear_bit(MC6_LOOP, sk); return 0; } @@ -1700,35 +2005,39 @@ int __init ndisc_init(void) /* * Initialize the neighbour table */ - neigh_table_init(&nd_tbl); + neigh_table_init(NEIGH_ND_TABLE, &nd_tbl); #ifdef CONFIG_SYSCTL - err = neigh_sysctl_register(NULL, &nd_tbl.parms, "ipv6", - &ndisc_ifinfo_sysctl_change); + err = neigh_sysctl_register(NULL, &nd_tbl.parms, + ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; -#endif - err = register_netdevice_notifier(&ndisc_netdev_notifier); - if (err) - goto out_unregister_sysctl; out: +#endif return err; -out_unregister_sysctl: #ifdef CONFIG_SYSCTL - neigh_sysctl_unregister(&nd_tbl.parms); out_unregister_pernet: -#endif unregister_pernet_subsys(&ndisc_net_ops); goto out; +#endif } -void ndisc_cleanup(void) +int __init ndisc_late_init(void) +{ + return register_netdevice_notifier(&ndisc_netdev_notifier); +} + +void ndisc_late_cleanup(void) { unregister_netdevice_notifier(&ndisc_netdev_notifier); +} + +void ndisc_cleanup(void) +{ #ifdef CONFIG_SYSCTL neigh_sysctl_unregister(&nd_tbl.parms); #endif - neigh_table_clear(&nd_tbl); + neigh_table_clear(NEIGH_ND_TABLE, &nd_tbl); unregister_pernet_subsys(&ndisc_net_ops); } |