diff options
Diffstat (limited to 'net/ipv6/route.c')
| -rw-r--r-- | net/ipv6/route.c | 886 |
1 files changed, 503 insertions, 383 deletions
diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7c7e963260e..f23fbd28a50 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -57,6 +57,7 @@ #include <net/xfrm.h> #include <net/netevent.h> #include <net/netlink.h> +#include <net/nexthop.h> #include <asm/uaccess.h> @@ -64,6 +65,13 @@ #include <linux/sysctl.h> #endif +enum rt6_nud_state { + RT6_NUD_FAIL_HARD = -3, + RT6_NUD_FAIL_PROBE = -2, + RT6_NUD_FAIL_DO_RR = -1, + RT6_NUD_SUCCEED = 1 +}; + static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, const struct in6_addr *dest); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); @@ -76,12 +84,15 @@ static void ip6_dst_ifdown(struct dst_entry *, static int ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); -static int ip6_pkt_discard_out(struct sk_buff *skb); +static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb); +static int ip6_pkt_prohibit(struct sk_buff *skb); +static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); +static int rt6_score_route(struct rt6_info *rt, int oif, int strict); #ifdef CONFIG_IPV6_ROUTE_INFO static struct rt6_info *rt6_add_route_info(struct net *net, @@ -93,6 +104,36 @@ static struct rt6_info *rt6_get_route_info(struct net *net, const struct in6_addr *gwaddr, int ifindex); #endif +static void rt6_bind_peer(struct rt6_info *rt, int create) +{ + struct inet_peer_base *base; + struct inet_peer *peer; + + base = inetpeer_base_ptr(rt->_rt6i_peer); + if (!base) + return; + + peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create); + if (peer) { + if (!rt6_set_peer(rt, peer)) + inet_putpeer(peer); + } +} + +static struct inet_peer *__rt6_get_peer(struct rt6_info *rt, int create) +{ + if (rt6_has_peer(rt)) + return rt6_peer_ptr(rt); + + rt6_bind_peer(rt, create); + return (rt6_has_peer(rt) ? rt6_peer_ptr(rt) : NULL); +} + +static struct inet_peer *rt6_get_peer_create(struct rt6_info *rt) +{ + return __rt6_get_peer(rt, 1); +} + static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) { struct rt6_info *rt = (struct rt6_info *) dst; @@ -108,7 +149,8 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) unsigned long prev, new; p = peer->metrics; - if (inet_metrics_new(peer)) + if (inet_metrics_new(peer) || + (old & DST_METRICS_FORCE_OVERWRITE)) memcpy(p, old_p, sizeof(u32) * RTAX_MAX); new = (unsigned long) p; @@ -144,25 +186,12 @@ static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, struct neighbour *n; daddr = choose_neigh_daddr(rt, skb, daddr); - n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr); + n = __ipv6_neigh_lookup(dst->dev, daddr); if (n) return n; return neigh_create(&nd_tbl, daddr, dst->dev); } -static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev) -{ - struct neighbour *n = __ipv6_neigh_lookup(&nd_tbl, dev, &rt->rt6i_gateway); - if (!n) { - n = neigh_create(&nd_tbl, &rt->rt6i_gateway, dev); - if (IS_ERR(n)) - return PTR_ERR(n); - } - rt->n = n; - - return 0; -} - static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, .protocol = cpu_to_be16(ETH_P_IPV6), @@ -219,7 +248,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { }; static const u32 ip6_template_metrics[RTAX_MAX] = { - [RTAX_HOPLIMIT - 1] = 255, + [RTAX_HOPLIMIT - 1] = 0, }; static const struct rt6_info ip6_null_entry_template = { @@ -239,9 +268,6 @@ static const struct rt6_info ip6_null_entry_template = { #ifdef CONFIG_IPV6_MULTIPLE_TABLES -static int ip6_pkt_prohibit(struct sk_buff *skb); -static int ip6_pkt_prohibit_out(struct sk_buff *skb); - static const struct rt6_info ip6_prohibit_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), @@ -264,7 +290,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = { .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, .input = dst_discard, - .output = dst_discard, + .output = dst_discard_sk, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), .rt6i_protocol = RTPROT_KERNEL, @@ -288,7 +314,8 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); - rt->rt6i_genid = rt_genid(net); + rt->rt6i_genid = rt_genid_ipv6(net); + INIT_LIST_HEAD(&rt->rt6i_siblings); } return rt; } @@ -297,9 +324,7 @@ static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; - - if (rt->n) - neigh_release(rt->n); + struct dst_entry *from = dst->from; if (!(rt->dst.flags & DST_HOST)) dst_destroy_metrics_generic(dst); @@ -309,8 +334,8 @@ static void ip6_dst_destroy(struct dst_entry *dst) in6_dev_put(idev); } - if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from) - dst_release(dst->from); + dst->from = NULL; + dst_release(from); if (rt6_has_peer(rt)) { struct inet_peer *peer = rt6_peer_ptr(rt); @@ -318,31 +343,6 @@ static void ip6_dst_destroy(struct dst_entry *dst) } } -static atomic_t __rt6_peer_genid = ATOMIC_INIT(0); - -static u32 rt6_peer_genid(void) -{ - return atomic_read(&__rt6_peer_genid); -} - -void rt6_bind_peer(struct rt6_info *rt, int create) -{ - struct inet_peer_base *base; - struct inet_peer *peer; - - base = inetpeer_base_ptr(rt->_rt6i_peer); - if (!base) - return; - - peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create); - if (peer) { - if (!rt6_set_peer(rt, peer)) - inet_putpeer(peer); - else - rt->rt6i_peer_genid = rt6_peer_genid(); - } -} - static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int how) { @@ -360,11 +360,6 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, in6_dev_put(idev); } } - if (rt->n && rt->n->dev == dev) { - rt->n->dev = loopback_dev; - dev_hold(loopback_dev); - dev_put(dev); - } } } @@ -379,10 +374,63 @@ static bool rt6_check_expired(const struct rt6_info *rt) return false; } -static bool rt6_need_strict(const struct in6_addr *daddr) +/* Multipath route selection: + * Hash based function using packet header and flowlabel. + * Adapted from fib_info_hashfn() + */ +static int rt6_info_hash_nhsfn(unsigned int candidate_count, + const struct flowi6 *fl6) +{ + unsigned int val = fl6->flowi6_proto; + + val ^= ipv6_addr_hash(&fl6->daddr); + val ^= ipv6_addr_hash(&fl6->saddr); + + /* Work only if this not encapsulated */ + switch (fl6->flowi6_proto) { + case IPPROTO_UDP: + case IPPROTO_TCP: + case IPPROTO_SCTP: + val ^= (__force u16)fl6->fl6_sport; + val ^= (__force u16)fl6->fl6_dport; + break; + + case IPPROTO_ICMPV6: + val ^= (__force u16)fl6->fl6_icmp_type; + val ^= (__force u16)fl6->fl6_icmp_code; + break; + } + /* RFC6438 recommands to use flowlabel */ + val ^= (__force u32)fl6->flowlabel; + + /* Perhaps, we need to tune, this function? */ + val = val ^ (val >> 7) ^ (val >> 12); + return val % candidate_count; +} + +static struct rt6_info *rt6_multipath_select(struct rt6_info *match, + struct flowi6 *fl6, int oif, + int strict) { - return ipv6_addr_type(daddr) & - (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); + struct rt6_info *sibling, *next_sibling; + int route_choosen; + + route_choosen = rt6_info_hash_nhsfn(match->rt6i_nsiblings + 1, fl6); + /* Don't change the route, if route_choosen == 0 + * (siblings does not include ourself) + */ + if (route_choosen) + list_for_each_entry_safe(sibling, next_sibling, + &match->rt6i_siblings, rt6i_siblings) { + route_choosen--; + if (route_choosen == 0) { + if (rt6_score_route(sibling, oif, strict) < 0) + break; + match = sibling; + break; + } + } + return match; } /* @@ -437,6 +485,24 @@ out: } #ifdef CONFIG_IPV6_ROUTER_PREF +struct __rt6_probe_work { + struct work_struct work; + struct in6_addr target; + struct net_device *dev; +}; + +static void rt6_probe_deferred(struct work_struct *w) +{ + struct in6_addr mcaddr; + struct __rt6_probe_work *work = + container_of(w, struct __rt6_probe_work, work); + + addrconf_addr_solict_mult(&work->target, &mcaddr); + ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL); + dev_put(work->dev); + kfree(w); +} + static void rt6_probe(struct rt6_info *rt) { struct neighbour *neigh; @@ -448,24 +514,40 @@ static void rt6_probe(struct rt6_info *rt) * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ - neigh = rt ? rt->n : NULL; - if (!neigh || (neigh->nud_state & NUD_VALID)) + if (!rt || !(rt->rt6i_flags & RTF_GATEWAY)) return; - read_lock_bh(&neigh->lock); - if (!(neigh->nud_state & NUD_VALID) && + rcu_read_lock_bh(); + neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + if (neigh) { + write_lock(&neigh->lock); + if (neigh->nud_state & NUD_VALID) + goto out; + } + + if (!neigh || time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { - struct in6_addr mcaddr; - struct in6_addr *target; + struct __rt6_probe_work *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); - neigh->updated = jiffies; - read_unlock_bh(&neigh->lock); + if (neigh && work) + __neigh_set_probe_once(neigh); - target = (struct in6_addr *)&neigh->primary_key; - addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL); + if (neigh) + write_unlock(&neigh->lock); + + if (work) { + INIT_WORK(&work->work, rt6_probe_deferred); + work->target = rt->rt6i_gateway; + dev_hold(rt->dst.dev); + work->dev = rt->dst.dev; + schedule_work(&work->work); + } } else { - read_unlock_bh(&neigh->lock); +out: + write_unlock(&neigh->lock); } + rcu_read_unlock_bh(); } #else static inline void rt6_probe(struct rt6_info *rt) @@ -487,76 +569,91 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif) return 0; } -static inline int rt6_check_neigh(struct rt6_info *rt) +static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt) { struct neighbour *neigh; - int m; + enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; - neigh = rt->n; if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) - m = 1; - else if (neigh) { - read_lock_bh(&neigh->lock); + return RT6_NUD_SUCCEED; + + rcu_read_lock_bh(); + neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + if (neigh) { + read_lock(&neigh->lock); if (neigh->nud_state & NUD_VALID) - m = 2; + ret = RT6_NUD_SUCCEED; #ifdef CONFIG_IPV6_ROUTER_PREF - else if (neigh->nud_state & NUD_FAILED) - m = 0; -#endif + else if (!(neigh->nud_state & NUD_FAILED)) + ret = RT6_NUD_SUCCEED; else - m = 1; - read_unlock_bh(&neigh->lock); - } else - m = 0; - return m; + ret = RT6_NUD_FAIL_PROBE; +#endif + read_unlock(&neigh->lock); + } else { + ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? + RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR; + } + rcu_read_unlock_bh(); + + return ret; } static int rt6_score_route(struct rt6_info *rt, int oif, int strict) { - int m, n; + int m; m = rt6_check_dev(rt, oif); if (!m && (strict & RT6_LOOKUP_F_IFACE)) - return -1; + return RT6_NUD_FAIL_HARD; #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; #endif - n = rt6_check_neigh(rt); - if (!n && (strict & RT6_LOOKUP_F_REACHABLE)) - return -1; + if (strict & RT6_LOOKUP_F_REACHABLE) { + int n = rt6_check_neigh(rt); + if (n < 0) + return n; + } return m; } static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, - int *mpri, struct rt6_info *match) + int *mpri, struct rt6_info *match, + bool *do_rr) { int m; + bool match_do_rr = false; if (rt6_check_expired(rt)) goto out; m = rt6_score_route(rt, oif, strict); - if (m < 0) + if (m == RT6_NUD_FAIL_DO_RR) { + match_do_rr = true; + m = 0; /* lowest valid score */ + } else if (m == RT6_NUD_FAIL_HARD) { goto out; + } + if (strict & RT6_LOOKUP_F_REACHABLE) + rt6_probe(rt); + + /* note that m can be RT6_NUD_FAIL_PROBE at this point */ if (m > *mpri) { - if (strict & RT6_LOOKUP_F_REACHABLE) - rt6_probe(match); + *do_rr = match_do_rr; *mpri = m; match = rt; - } else if (strict & RT6_LOOKUP_F_REACHABLE) { - rt6_probe(rt); } - out: return match; } static struct rt6_info *find_rr_leaf(struct fib6_node *fn, struct rt6_info *rr_head, - u32 metric, int oif, int strict) + u32 metric, int oif, int strict, + bool *do_rr) { struct rt6_info *rt, *match; int mpri = -1; @@ -564,10 +661,10 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = NULL; for (rt = rr_head; rt && rt->rt6i_metric == metric; rt = rt->dst.rt6_next) - match = find_match(rt, oif, strict, &mpri, match); + match = find_match(rt, oif, strict, &mpri, match, do_rr); for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric; rt = rt->dst.rt6_next) - match = find_match(rt, oif, strict, &mpri, match); + match = find_match(rt, oif, strict, &mpri, match, do_rr); return match; } @@ -576,15 +673,16 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) { struct rt6_info *match, *rt0; struct net *net; + bool do_rr = false; rt0 = fn->rr_ptr; if (!rt0) fn->rr_ptr = rt0 = fn->leaf; - match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict); + match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict, + &do_rr); - if (!match && - (strict & RT6_LOOKUP_F_REACHABLE)) { + if (do_rr) { struct rt6_info *next = rt0->dst.rt6_next; /* no entries matched; do round-robin */ @@ -645,8 +743,11 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, prefix = &prefix_buf; } - rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, - dev->ifindex); + if (rinfo->prefix_len == 0) + rt = rt6_get_dflt_router(gwaddr, dev); + else + rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, + gwaddr, dev->ifindex); if (rt && !lifetime) { ip6_del_rt(rt); @@ -666,7 +767,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, else rt6_set_expires(rt, jiffies + HZ * lifetime); - dst_release(&rt->dst); + ip6_rt_put(rt); } return 0; } @@ -702,6 +803,8 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net, restart: rt = fn->leaf; 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); BACKTRACK(net, &fl6->saddr); out: dst_use(&rt->dst, jiffies); @@ -749,14 +852,15 @@ EXPORT_SYMBOL(rt6_lookup); be destroyed. */ -static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info) +static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, + struct nlattr *mx, int mx_len) { int err; struct fib6_table *table; table = rt->rt6i_table; write_lock_bh(&table->tb6_lock); - err = fib6_add(&table->tb6_root, rt, info); + err = fib6_add(&table->tb6_root, rt, info, mx, mx_len); write_unlock_bh(&table->tb6_lock); return err; @@ -767,7 +871,7 @@ int ip6_ins_rt(struct rt6_info *rt) struct nl_info info = { .nl_net = dev_net(rt->dst.dev), }; - return __ip6_ins_rt(rt, &info); + return __ip6_ins_rt(rt, &info, NULL, 0); } static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, @@ -783,14 +887,9 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, rt = ip6_rt_copy(ort, daddr); if (rt) { - int attempts = !in_softirq(); - - if (!(rt->rt6i_flags & RTF_GATEWAY)) { - if (ort->rt6i_dst.plen != 128 && - ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) - rt->rt6i_flags |= RTF_ANYCAST; - rt->rt6i_gateway = *daddr; - } + if (ort->rt6i_dst.plen != 128 && + ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) + rt->rt6i_flags |= RTF_ANYCAST; rt->rt6i_flags |= RTF_CACHE; @@ -800,32 +899,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, rt->rt6i_src.plen = 128; } #endif - - retry: - if (rt6_bind_neighbour(rt, rt->dst.dev)) { - struct net *net = dev_net(rt->dst.dev); - int saved_rt_min_interval = - net->ipv6.sysctl.ip6_rt_gc_min_interval; - int saved_rt_elasticity = - net->ipv6.sysctl.ip6_rt_gc_elasticity; - - if (attempts-- > 0) { - net->ipv6.sysctl.ip6_rt_gc_elasticity = 1; - net->ipv6.sysctl.ip6_rt_gc_min_interval = 0; - - ip6_dst_gc(&net->ipv6.ip6_dst_ops); - - net->ipv6.sysctl.ip6_rt_gc_elasticity = - saved_rt_elasticity; - net->ipv6.sysctl.ip6_rt_gc_min_interval = - saved_rt_min_interval; - goto retry; - } - - net_warn_ratelimited("Neighbour table overflow\n"); - dst_free(&rt->dst); - return NULL; - } } return rt; @@ -836,10 +909,8 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, { struct rt6_info *rt = ip6_rt_copy(ort, daddr); - if (rt) { + if (rt) rt->rt6i_flags |= RTF_CACHE; - rt->n = neigh_clone(ort->n); - } return rt; } @@ -863,7 +934,8 @@ restart_2: restart: rt = rt6_select(fn, oif, strict | reachable); - + if (rt->rt6i_nsiblings) + rt = rt6_multipath_select(rt, fl6, oif, strict | reachable); BACKTRACK(net, &fl6->saddr); if (rt == net->ipv6.ip6_null_entry || rt->rt6i_flags & RTF_CACHE) @@ -872,14 +944,14 @@ restart: dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); - if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY))) nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl6->daddr); else goto out2; - dst_release(&rt->dst); + ip6_rt_put(rt); rt = nrt ? : net->ipv6.ip6_null_entry; dst_hold(&rt->dst); @@ -896,7 +968,7 @@ restart: * Race condition! In the gap, when table->tb6_lock was * released someone could insert this route. Relookup. */ - dst_release(&rt->dst); + ip6_rt_put(rt); goto relookup; out: @@ -938,7 +1010,7 @@ void ip6_route_input(struct sk_buff *skb) .flowi6_iif = skb->dev->ifindex, .daddr = iph->daddr, .saddr = iph->saddr, - .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK, + .flowlabel = ip6_flowinfo(iph), .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, }; @@ -986,7 +1058,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori new->__use = 1; new->input = dst_discard; - new->output = dst_discard; + new->output = dst_discard_sk; if (dst_metrics_read_only(&ort->dst)) new->_metrics = ort->dst._metrics; @@ -998,7 +1070,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags; - rt6_clean_expires(rt); rt->rt6i_metric = 0; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); @@ -1027,18 +1098,16 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ - if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev))) + if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev))) return NULL; - if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) { - if (rt->rt6i_peer_genid != rt6_peer_genid()) { - if (!rt6_has_peer(rt)) - rt6_bind_peer(rt, 0); - rt->rt6i_peer_genid = rt6_peer_genid(); - } - return dst; - } - return NULL; + if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) + return NULL; + + if (rt6_check_expired(rt)) + return NULL; + + return dst; } static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) @@ -1067,10 +1136,13 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { - if (rt->rt6i_flags & RTF_CACHE) - rt6_update_expires(rt, 0); - else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) + if (rt->rt6i_flags & RTF_CACHE) { + dst_hold(&rt->dst); + if (ip6_del_rt(rt)) + dst_free(&rt->dst); + } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) { rt->rt6i_node->fn_sernum = -1; + } } } @@ -1104,11 +1176,10 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = oif; - fl6.flowi6_mark = mark; - fl6.flowi6_flags = 0; + fl6.flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark); fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; - fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK; + fl6.flowlabel = ip6_flowinfo(iph); dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) @@ -1124,6 +1195,77 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) } EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu); +/* Handle redirects */ +struct ip6rd_flowi { + struct flowi6 fl6; + struct in6_addr gateway; +}; + +static struct rt6_info *__ip6_route_redirect(struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, + int flags) +{ + struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; + struct rt6_info *rt; + struct fib6_node *fn; + + /* Get the "current" route for this destination and + * check if the redirect has come from approriate router. + * + * RFC 4861 specifies that redirects should only be + * accepted if they come from the nexthop to the target. + * Due to the way the routes are chosen, this notion + * is a bit fuzzy and one might need to check all possible + * routes. + */ + + read_lock_bh(&table->tb6_lock); + fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); +restart: + for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + if (rt6_check_expired(rt)) + continue; + if (rt->dst.error) + break; + if (!(rt->rt6i_flags & RTF_GATEWAY)) + continue; + if (fl6->flowi6_oif != rt->dst.dev->ifindex) + continue; + if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) + continue; + break; + } + + if (!rt) + rt = net->ipv6.ip6_null_entry; + else if (rt->dst.error) { + rt = net->ipv6.ip6_null_entry; + goto out; + } + BACKTRACK(net, &fl6->saddr); +out: + dst_hold(&rt->dst); + + read_unlock_bh(&table->tb6_lock); + + return rt; +}; + +static struct dst_entry *ip6_route_redirect(struct net *net, + const struct flowi6 *fl6, + const struct in6_addr *gateway) +{ + int flags = RT6_LOOKUP_F_HAS_SADDR; + struct ip6rd_flowi rdfl; + + rdfl.fl6 = *fl6; + rdfl.gateway = *gateway; + + return fib6_rule_lookup(net, &rdfl.fl6, + flags, __ip6_route_redirect); +} + void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) { const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; @@ -1131,20 +1273,39 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_iif = LOOPBACK_IFINDEX; fl6.flowi6_oif = oif; fl6.flowi6_mark = mark; - fl6.flowi6_flags = 0; fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; - fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK; + fl6.flowlabel = ip6_flowinfo(iph); - dst = ip6_route_output(net, NULL, &fl6); - if (!dst->error) - rt6_do_redirect(dst, NULL, skb); + dst = ip6_route_redirect(net, &fl6, &ipv6_hdr(skb)->saddr); + rt6_do_redirect(dst, NULL, skb); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_redirect); +void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif, + u32 mark) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + const struct rd_msg *msg = (struct rd_msg *)icmp6_hdr(skb); + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_iif = LOOPBACK_IFINDEX; + fl6.flowi6_oif = oif; + fl6.flowi6_mark = mark; + fl6.daddr = msg->dest; + fl6.saddr = iph->daddr; + + dst = ip6_route_redirect(net, &fl6, &iph->saddr); + rt6_do_redirect(dst, NULL, skb); + dst_release(dst); +} + void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark); @@ -1179,7 +1340,7 @@ static unsigned int ip6_mtu(const struct dst_entry *dst) unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) - return mtu; + goto out; mtu = IPV6_MIN_MTU; @@ -1189,14 +1350,14 @@ static unsigned int ip6_mtu(const struct dst_entry *dst) mtu = idev->cnf.mtu6; rcu_read_unlock(); - return mtu; +out: + return min_t(unsigned int, mtu, IP6_MAX_MTU); } static struct dst_entry *icmp6_dst_gc_list; static DEFINE_SPINLOCK(icmp6_dst_lock); struct dst_entry *icmp6_dst_alloc(struct net_device *dev, - struct neighbour *neigh, struct flowi6 *fl6) { struct dst_entry *dst; @@ -1214,25 +1375,14 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, goto out; } - if (neigh) - neigh_hold(neigh); - else { - neigh = ip6_neigh_lookup(&rt->dst, NULL, &fl6->daddr); - if (IS_ERR(neigh)) { - in6_dev_put(idev); - dst_free(&rt->dst); - return ERR_CAST(neigh); - } - } - rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; - rt->n = neigh; atomic_set(&rt->dst.__refcnt, 1); + rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); spin_lock_bh(&icmp6_dst_lock); rt->dst.next = icmp6_dst_gc_list; @@ -1291,7 +1441,6 @@ static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg), static int ip6_dst_gc(struct dst_ops *ops) { - unsigned long now = jiffies; struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size; @@ -1301,13 +1450,12 @@ static int ip6_dst_gc(struct dst_ops *ops) int entries; entries = dst_entries_get_fast(ops); - if (time_after(rt_last_gc + rt_min_interval, now) && + if (time_after(rt_last_gc + rt_min_interval, jiffies) && entries <= rt_max_size) goto out; net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net); - net->ipv6.ip6_rt_last_gc = now; + fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; @@ -1316,31 +1464,6 @@ out: return entries > rt_max_size; } -/* Clean host part of a prefix. Not necessary in radix tree, - but results in cleaner routing tables. - - Remove it only when all the things will work! - */ - -int ip6_dst_hoplimit(struct dst_entry *dst) -{ - int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); - if (hoplimit == 0) { - struct net_device *dev = dst->dev; - struct inet6_dev *idev; - - rcu_read_lock(); - idev = __in6_dev_get(dev); - if (idev) - hoplimit = idev->cnf.hop_limit; - else - hoplimit = dev_net(dev)->ipv6.devconf_all->hop_limit; - rcu_read_unlock(); - } - return hoplimit; -} -EXPORT_SYMBOL(ip6_dst_hoplimit); - /* * */ @@ -1389,7 +1512,7 @@ int ip6_route_add(struct fib6_config *cfg) if (!table) goto out; - rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table); + rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table); if (!rt) { err = -ENOMEM; @@ -1419,17 +1542,11 @@ int ip6_route_add(struct fib6_config *cfg) ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->rt6i_dst.plen = cfg->fc_dst_len; - if (rt->rt6i_dst.plen == 128) - rt->dst.flags |= DST_HOST; - - if (!(rt->dst.flags & DST_HOST) && cfg->fc_mx) { - u32 *metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); - if (!metrics) { - err = -ENOMEM; - goto out; - } - dst_init_metrics(&rt->dst, metrics, 0); + if (rt->rt6i_dst.plen == 128) { + rt->dst.flags |= DST_HOST; + dst_metrics_set_force_overwrite(&rt->dst); } + #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); rt->rt6i_src.plen = cfg->fc_src_len; @@ -1458,21 +1575,24 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } } - rt->dst.output = ip6_pkt_discard_out; - rt->dst.input = ip6_pkt_discard; rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP; switch (cfg->fc_type) { case RTN_BLACKHOLE: rt->dst.error = -EINVAL; + rt->dst.output = dst_discard_sk; + rt->dst.input = dst_discard; break; case RTN_PROHIBIT: rt->dst.error = -EACCES; + rt->dst.output = ip6_pkt_prohibit_out; + rt->dst.input = ip6_pkt_prohibit; break; case RTN_THROW: - rt->dst.error = -EAGAIN; - break; default: - rt->dst.error = -ENETUNREACH; + rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN + : -ENETUNREACH; + rt->dst.output = ip6_pkt_discard_out; + rt->dst.input = ip6_pkt_discard; break; } goto install_route; @@ -1507,7 +1627,7 @@ int ip6_route_add(struct fib6_config *cfg) goto out; if (dev) { if (dev != grt->dst.dev) { - dst_release(&grt->dst); + ip6_rt_put(grt); goto out; } } else { @@ -1518,7 +1638,7 @@ int ip6_route_add(struct fib6_config *cfg) } if (!(grt->rt6i_flags & RTF_GATEWAY)) err = 0; - dst_release(&grt->dst); + ip6_rt_put(grt); if (err) goto out; @@ -1542,40 +1662,16 @@ int ip6_route_add(struct fib6_config *cfg) } else rt->rt6i_prefsrc.plen = 0; - if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) { - err = rt6_bind_neighbour(rt, dev); - if (err) - goto out; - } - rt->rt6i_flags = cfg->fc_flags; install_route: - if (cfg->fc_mx) { - struct nlattr *nla; - int remaining; - - nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { - int type = nla_type(nla); - - if (type) { - if (type > RTAX_MAX) { - err = -EINVAL; - goto out; - } - - dst_metric_set(&rt->dst, type, nla_get_u32(nla)); - } - } - } - rt->dst.dev = dev; rt->rt6i_idev = idev; rt->rt6i_table = table; cfg->fc_nlinfo.nl_net = dev_net(dev); - return __ip6_ins_rt(rt, &cfg->fc_nlinfo); + return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len); out: if (dev) @@ -1604,7 +1700,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) write_unlock_bh(&table->tb6_lock); out: - dst_release(&rt->dst); + ip6_rt_put(rt); return err; } @@ -1660,37 +1756,32 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu struct net *net = dev_net(skb->dev); struct netevent_redirect netevent; struct rt6_info *rt, *nrt = NULL; - const struct in6_addr *target; struct ndisc_options ndopts; - const struct in6_addr *dest; - struct neighbour *old_neigh; struct inet6_dev *in6_dev; struct neighbour *neigh; - struct icmp6hdr *icmph; + struct rd_msg *msg; int optlen, on_link; u8 *lladdr; - optlen = skb->tail - skb->transport_header; - optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); + optlen = skb_tail_pointer(skb) - skb_transport_header(skb); + optlen -= sizeof(*msg); if (optlen < 0) { net_dbg_ratelimited("rt6_do_redirect: packet too short\n"); return; } - icmph = icmp6_hdr(skb); - target = (const struct in6_addr *) (icmph + 1); - dest = target + 1; + msg = (struct rd_msg *)icmp6_hdr(skb); - if (ipv6_addr_is_multicast(dest)) { + if (ipv6_addr_is_multicast(&msg->dest)) { net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n"); return; } on_link = 0; - if (ipv6_addr_equal(dest, target)) { + if (ipv6_addr_equal(&msg->dest, &msg->target)) { on_link = 1; - } else if (ipv6_addr_type(target) != + } else if (ipv6_addr_type(&msg->target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n"); return; @@ -1707,7 +1798,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu * first-hop router for the specified ICMP Destination Address. */ - if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { + if (!ndisc_parse_options(msg->opt, optlen, &ndopts)) { net_dbg_ratelimited("rt6_redirect: invalid ND options\n"); return; } @@ -1734,15 +1825,10 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu */ dst_confirm(&rt->dst); - neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1); + neigh = __neigh_lookup(&nd_tbl, &msg->target, skb->dev, 1); if (!neigh) return; - /* Duplicate redirect: silently ignore. */ - old_neigh = rt->n; - if (neigh == old_neigh) - goto out; - /* * We have finally decided to accept it. */ @@ -1754,7 +1840,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu NEIGH_UPDATE_F_ISROUTER)) ); - nrt = ip6_rt_copy(rt, dest); + nrt = ip6_rt_copy(rt, &msg->dest); if (!nrt) goto out; @@ -1763,16 +1849,14 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu nrt->rt6i_flags &= ~RTF_GATEWAY; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; - nrt->n = neigh_clone(neigh); if (ip6_ins_rt(nrt)) goto out; netevent.old = &rt->dst; - netevent.old_neigh = old_neigh; netevent.new = &nrt->dst; - netevent.new_neigh = neigh; - netevent.daddr = dest; + netevent.daddr = &msg->dest; + netevent.neigh = neigh; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); if (rt->rt6i_flags & RTF_CACHE) { @@ -1809,13 +1893,12 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, in6_dev_hold(rt->rt6i_idev); rt->dst.lastuse = jiffies; - rt->rt6i_gateway = ort->rt6i_gateway; - rt->rt6i_flags = ort->rt6i_flags; - if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == - (RTF_DEFAULT | RTF_ADDRCONF)) - rt6_set_from(rt, ort); + if (ort->rt6i_flags & RTF_GATEWAY) + rt->rt6i_gateway = ort->rt6i_gateway; else - rt6_clean_expires(rt); + rt->rt6i_gateway = *dest; + rt->rt6i_flags = ort->rt6i_flags; + rt6_set_from(rt, ort); rt->rt6i_metric = 0; #ifdef CONFIG_IPV6_SUBTREES @@ -1947,7 +2030,8 @@ void rt6_purge_dflt_routers(struct net *net) restart: read_lock_bh(&table->tb6_lock); for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { - if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) { + if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && + (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); ip6_del_rt(rt); @@ -1987,7 +2071,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) switch(cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; err = copy_from_user(&rtmsg, arg, sizeof(struct in6_rtmsg)); @@ -2047,27 +2131,23 @@ static int ip6_pkt_discard(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES); } -static int ip6_pkt_discard_out(struct sk_buff *skb) +static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); } -#ifdef CONFIG_IPV6_MULTIPLE_TABLES - static int ip6_pkt_prohibit(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); } -static int ip6_pkt_prohibit_out(struct sk_buff *skb) +static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } -#endif - /* * Allocate a dst for local (unicast / anycast) address. */ @@ -2077,13 +2157,10 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, bool anycast) { struct net *net = dev_net(idev->dev); - struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL); - int err; - - if (!rt) { - net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n"); + struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, + DST_NOCOUNT, NULL); + if (!rt) return ERR_PTR(-ENOMEM); - } in6_dev_hold(idev); @@ -2097,12 +2174,8 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_flags |= RTF_ANYCAST; else rt->rt6i_flags |= RTF_LOCAL; - err = rt6_bind_neighbour(rt, rt->dst.dev); - if (err) { - dst_free(&rt->dst); - return ERR_PTR(err); - } + rt->rt6i_gateway = *addr; rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); @@ -2158,7 +2231,28 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) .net = net, .addr = &ifp->addr, }; - fib6_clean_all(net, fib6_remove_prefsrc, 0, &adni); + fib6_clean_all(net, fib6_remove_prefsrc, &adni); +} + +#define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY) +#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) + +/* Remove routers and update dst entries when gateway turn into host. */ +static int fib6_clean_tohost(struct rt6_info *rt, void *arg) +{ + struct in6_addr *gateway = (struct in6_addr *)arg; + + if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) || + ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) && + ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { + return -1; + } + return 0; +} + +void rt6_clean_tohost(struct net *net, struct in6_addr *gateway) +{ + fib6_clean_all(net, fib6_clean_tohost, gateway); } struct arg_dev_net { @@ -2185,7 +2279,7 @@ void rt6_ifdown(struct net *net, struct net_device *dev) .net = net, }; - fib6_clean_all(net, fib6_ifdown, 0, &adn); + fib6_clean_all(net, fib6_ifdown, &adn); icmp6_clean_all(fib6_ifdown, &adn); } @@ -2240,7 +2334,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu) .mtu = mtu, }; - fib6_clean_all(dev_net(dev), rt6_mtu_change_route, 0, &arg); + fib6_clean_all(dev_net(dev), rt6_mtu_change_route, &arg); } static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { @@ -2249,6 +2343,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, + [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2326,12 +2421,72 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_TABLE]) cfg->fc_table = nla_get_u32(tb[RTA_TABLE]); + if (tb[RTA_MULTIPATH]) { + cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]); + cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); + } + err = 0; errout: return err; } -static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int ip6_route_multipath(struct fib6_config *cfg, int add) +{ + struct fib6_config r_cfg; + struct rtnexthop *rtnh; + int remaining; + int attrlen; + int err = 0, last_err = 0; + +beginning: + rtnh = (struct rtnexthop *)cfg->fc_mp; + remaining = cfg->fc_mp_len; + + /* Parse a Multipath Entry */ + while (rtnh_ok(rtnh, remaining)) { + memcpy(&r_cfg, cfg, sizeof(*cfg)); + if (rtnh->rtnh_ifindex) + r_cfg.fc_ifindex = rtnh->rtnh_ifindex; + + attrlen = rtnh_attrlen(rtnh); + if (attrlen > 0) { + struct nlattr *nla, *attrs = rtnh_attrs(rtnh); + + nla = nla_find(attrs, attrlen, RTA_GATEWAY); + if (nla) { + nla_memcpy(&r_cfg.fc_gateway, nla, 16); + r_cfg.fc_flags |= RTF_GATEWAY; + } + } + err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg); + if (err) { + last_err = err; + /* If we are trying to remove a route, do not stop the + * loop when ip6_route_del() fails (because next hop is + * already gone), we should try to remove all next hops. + */ + if (add) { + /* If add fails, we should try to delete all + * next hops that have been already added. + */ + add = 0; + goto beginning; + } + } + /* Because each route is added like a single route we remove + * this flag after the first nexthop (if there is a collision, + * we have already fail to add the first nexthop: + * fib6_add_rt2node() has reject it). + */ + cfg->fc_nlinfo.nlh->nlmsg_flags &= ~NLM_F_EXCL; + rtnh = rtnh_next(rtnh, &remaining); + } + + return last_err; +} + +static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh) { struct fib6_config cfg; int err; @@ -2340,10 +2495,13 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *a if (err < 0) return err; - return ip6_route_del(&cfg); + if (cfg.fc_mp) + return ip6_route_multipath(&cfg, 0); + else + return ip6_route_del(&cfg); } -static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh) { struct fib6_config cfg; int err; @@ -2352,7 +2510,10 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *a if (err < 0) return err; - return ip6_route_add(&cfg); + if (cfg.fc_mp) + return ip6_route_multipath(&cfg, 1); + else + return ip6_route_add(&cfg); } static inline size_t rt6_nlmsg_size(void) @@ -2380,7 +2541,6 @@ static int rt6_fill_node(struct net *net, struct nlmsghdr *nlh; long expires; u32 table; - struct neighbour *n; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -2493,9 +2653,8 @@ static int rt6_fill_node(struct net *net, if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; - n = rt->n; - if (n) { - if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0) + if (rt->rt6i_flags & RTF_GATEWAY) { + if (nla_put(skb, RTA_GATEWAY, 16, &rt->rt6i_gateway) < 0) goto nla_put_failure; } @@ -2534,7 +2693,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg) prefix, 0, NLM_F_MULTI); } -static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) +static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; @@ -2571,6 +2730,9 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void if (tb[RTA_OIF]) oif = nla_get_u32(tb[RTA_OIF]); + if (tb[RTA_MARK]) + fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]); + if (iif) { struct net_device *dev; int flags = 0; @@ -2596,7 +2758,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { - dst_release(&rt->dst); + ip6_rt_put(rt); err = -ENOBUFS; goto errout; } @@ -2653,9 +2815,9 @@ errout: } static int ip6_route_dev_notify(struct notifier_block *this, - unsigned long event, void *data) + unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) { @@ -2678,58 +2840,12 @@ static int ip6_route_dev_notify(struct notifier_block *this, #ifdef CONFIG_PROC_FS -struct rt6_proc_arg -{ - char *buffer; - int offset; - int length; - int skip; - int len; -}; - -static int rt6_info_route(struct rt6_info *rt, void *p_arg) -{ - struct seq_file *m = p_arg; - struct neighbour *n; - - seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen); - -#ifdef CONFIG_IPV6_SUBTREES - seq_printf(m, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen); -#else - seq_puts(m, "00000000000000000000000000000000 00 "); -#endif - n = rt->n; - if (n) { - seq_printf(m, "%pi6", n->primary_key); - } else { - seq_puts(m, "00000000000000000000000000000000"); - } - seq_printf(m, " %08x %08x %08x %08x %8s\n", - rt->rt6i_metric, atomic_read(&rt->dst.__refcnt), - rt->dst.__use, rt->rt6i_flags, - rt->dst.dev ? rt->dst.dev->name : ""); - return 0; -} - -static int ipv6_route_show(struct seq_file *m, void *v) -{ - struct net *net = (struct net *)m->private; - fib6_clean_all_ro(net, rt6_info_route, 0, m); - return 0; -} - -static int ipv6_route_open(struct inode *inode, struct file *file) -{ - return single_open_net(inode, file, ipv6_route_show); -} - static const struct file_operations ipv6_route_proc_fops = { .owner = THIS_MODULE, .open = ipv6_route_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release_net, + .release = seq_release_net, }; static int rt6_stats_seq_show(struct seq_file *seq, void *v) @@ -2764,7 +2880,7 @@ static const struct file_operations rt6_stats_seq_fops = { #ifdef CONFIG_SYSCTL static -int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, +int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net *net; @@ -2775,11 +2891,11 @@ int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, net = (struct net *)ctl->extra1; delay = net->ipv6.sysctl.flush_delay; proc_dointvec(ctl, write, buffer, lenp, ppos); - fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); + fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } -ctl_table ipv6_route_table_template[] = { +struct ctl_table ipv6_route_table_template[] = { { .procname = "flush", .data = &init_net.ipv6.sysctl.flush_delay, @@ -2873,6 +2989,10 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires; table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; } return table; @@ -2964,8 +3084,8 @@ static void __net_exit ip6_route_net_exit(struct net *net) static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS - proc_net_fops_create(net, "ipv6_route", 0, &ipv6_route_proc_fops); - proc_net_fops_create(net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops); + 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); #endif return 0; } @@ -2973,8 +3093,8 @@ static int __net_init ip6_route_net_init_late(struct net *net) static void __net_exit ip6_route_net_exit_late(struct net *net) { #ifdef CONFIG_PROC_FS - proc_net_remove(net, "ipv6_route"); - proc_net_remove(net, "rt6_stats"); + remove_proc_entry("ipv6_route", net->proc_net); + remove_proc_entry("rt6_stats", net->proc_net); #endif } |