X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv6%2Froute.c;h=294cbe8b0725f7ad9f58690f2b511829d391a672;hb=aa679c36756003f1fabdb9fc6f00eb159559f7c3;hp=c797b9bbb7d1aedb32d97453a680f6d55a08a1ce;hpb=52e1635631b342803aecaf81a362c1464e3da2e5;p=safe%2Fjmp%2Flinux-2.6 diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c797b9b..294cbe8 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3,9 +3,7 @@ * FIB front-end. * * Authors: - * Pedro Roque - * - * $Id: route.c,v 1.56 2001/10/31 21:55:55 davem Exp $ + * Pedro Roque * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -22,10 +20,11 @@ * routers in REACHABLE, STALE, DELAY or PROBE states). * - always select the same router if it is (probably) * reachable. otherwise, round-robin the list. + * Ville Nuorvala + * Fixed routing subtrees. */ #include -#include #include #include #include @@ -35,15 +34,14 @@ #include #include #include +#include #include -#include #include - -#ifdef CONFIG_PROC_FS #include #include -#endif - +#include +#include +#include #include #include #include @@ -54,6 +52,8 @@ #include #include #include +#include +#include #include @@ -74,33 +74,32 @@ #define CLONE_OFFLINK_ROUTE 0 -#define RT6_SELECT_F_IFACE 0x1 -#define RT6_SELECT_F_REACHABLE 0x2 - -static int ip6_rt_max_size = 4096; -static int ip6_rt_gc_min_interval = HZ / 2; -static int ip6_rt_gc_timeout = 60*HZ; -int ip6_rt_gc_interval = 30*HZ; -static int ip6_rt_gc_elasticity = 9; -static int ip6_rt_mtu_expires = 10*60*HZ; -static int ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; - static struct rt6_info * ip6_rt_copy(struct rt6_info *ort); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); -static int ip6_dst_gc(void); +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 void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu); -static struct dst_ops ip6_dst_ops = { +#ifdef CONFIG_IPV6_ROUTE_INFO +static struct rt6_info *rt6_add_route_info(struct net *net, + struct in6_addr *prefix, int prefixlen, + struct in6_addr *gwaddr, int ifindex, + unsigned pref); +static struct rt6_info *rt6_get_route_info(struct net *net, + struct in6_addr *prefix, int prefixlen, + struct in6_addr *gwaddr, int ifindex); +#endif + +static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, - .protocol = __constant_htons(ETH_P_IPV6), + .protocol = cpu_to_be16(ETH_P_IPV6), .gc = ip6_dst_gc, .gc_thresh = 1024, .check = ip6_dst_check, @@ -109,43 +108,88 @@ static struct dst_ops ip6_dst_ops = { .negative_advice = ip6_negative_advice, .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, - .entry_size = sizeof(struct rt6_info), + .local_out = __ip6_local_out, + .entries = ATOMIC_INIT(0), +}; + +static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) +{ +} + +static struct dst_ops ip6_dst_blackhole_ops = { + .family = AF_INET6, + .protocol = cpu_to_be16(ETH_P_IPV6), + .destroy = ip6_dst_destroy, + .check = ip6_dst_check, + .update_pmtu = ip6_rt_blackhole_update_pmtu, + .entries = ATOMIC_INIT(0), }; -struct rt6_info ip6_null_entry = { +static struct rt6_info ip6_null_entry_template = { .u = { .dst = { .__refcnt = ATOMIC_INIT(1), .__use = 1, - .dev = &loopback_dev, .obsolete = -1, .error = -ENETUNREACH, .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, .input = ip6_pkt_discard, .output = ip6_pkt_discard_out, - .ops = &ip6_dst_ops, - .path = (struct dst_entry*)&ip6_null_entry, } }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), + .rt6i_protocol = RTPROT_KERNEL, .rt6i_metric = ~(u32) 0, .rt6i_ref = ATOMIC_INIT(1), }; -struct fib6_node ip6_routing_table = { - .leaf = &ip6_null_entry, - .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO, -}; +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + +static int ip6_pkt_prohibit(struct sk_buff *skb); +static int ip6_pkt_prohibit_out(struct sk_buff *skb); -/* Protects all the ip6 fib */ +static struct rt6_info ip6_prohibit_entry_template = { + .u = { + .dst = { + .__refcnt = ATOMIC_INIT(1), + .__use = 1, + .obsolete = -1, + .error = -EACCES, + .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, + .input = ip6_pkt_prohibit, + .output = ip6_pkt_prohibit_out, + } + }, + .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), + .rt6i_protocol = RTPROT_KERNEL, + .rt6i_metric = ~(u32) 0, + .rt6i_ref = ATOMIC_INIT(1), +}; -DEFINE_RWLOCK(rt6_lock); +static struct rt6_info ip6_blk_hole_entry_template = { + .u = { + .dst = { + .__refcnt = ATOMIC_INIT(1), + .__use = 1, + .obsolete = -1, + .error = -EINVAL, + .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, + .input = dst_discard, + .output = dst_discard, + } + }, + .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), + .rt6i_protocol = RTPROT_KERNEL, + .rt6i_metric = ~(u32) 0, + .rt6i_ref = ATOMIC_INIT(1), +}; +#endif /* allocate dst with ip6_dst_ops */ -static __inline__ struct rt6_info *ip6_dst_alloc(void) +static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops) { - return (struct rt6_info *)dst_alloc(&ip6_dst_ops); + return (struct rt6_info *)dst_alloc(ops); } static void ip6_dst_destroy(struct dst_entry *dst) @@ -156,7 +200,7 @@ static void ip6_dst_destroy(struct dst_entry *dst) if (idev != NULL) { rt->rt6i_idev = NULL; in6_dev_put(idev); - } + } } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -164,9 +208,12 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, { struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; + struct net_device *loopback_dev = + dev_net(dev)->loopback_dev; - if (dev != &loopback_dev && idev != NULL && idev->dev == dev) { - struct inet6_dev *loopback_idev = in6_dev_get(&loopback_dev); + if (dev != loopback_dev && idev != NULL && idev->dev == dev) { + struct inet6_dev *loopback_idev = + in6_dev_get(loopback_dev); if (loopback_idev != NULL) { rt->rt6i_idev = loopback_idev; in6_dev_put(idev); @@ -180,41 +227,60 @@ static __inline__ int rt6_check_expired(const struct rt6_info *rt) time_after(jiffies, rt->rt6i_expires)); } +static inline int rt6_need_strict(struct in6_addr *daddr) +{ + return (ipv6_addr_type(daddr) & + (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK)); +} + /* - * Route lookup. Any rt6_lock is implied. + * Route lookup. Any table->tb6_lock is implied. */ -static __inline__ struct rt6_info *rt6_device_match(struct rt6_info *rt, +static inline struct rt6_info *rt6_device_match(struct net *net, + struct rt6_info *rt, + struct in6_addr *saddr, int oif, - int strict) + int flags) { struct rt6_info *local = NULL; struct rt6_info *sprt; - if (oif) { - for (sprt = rt; sprt; sprt = sprt->u.next) { - struct net_device *dev = sprt->rt6i_dev; + if (!oif && ipv6_addr_any(saddr)) + goto out; + + for (sprt = rt; sprt; sprt = sprt->u.dst.rt6_next) { + struct net_device *dev = sprt->rt6i_dev; + + if (oif) { if (dev->ifindex == oif) return sprt; if (dev->flags & IFF_LOOPBACK) { if (sprt->rt6i_idev == NULL || sprt->rt6i_idev->dev->ifindex != oif) { - if (strict && oif) + if (flags & RT6_LOOKUP_F_IFACE && oif) continue; - if (local && (!oif || + if (local && (!oif || local->rt6i_idev->dev->ifindex == oif)) continue; } local = sprt; } + } else { + if (ipv6_chk_addr(net, saddr, dev, + flags & RT6_LOOKUP_F_IFACE)) + return sprt; } + } + if (oif) { if (local) return local; - if (strict) - return &ip6_null_entry; + if (flags & RT6_LOOKUP_F_IFACE) + return net->ipv6.ip6_null_entry; } +out: return rt; } @@ -250,14 +316,13 @@ static void rt6_probe(struct rt6_info *rt) #else static inline void rt6_probe(struct rt6_info *rt) { - return; } #endif /* * Default Router Selection (RFC 2461 6.3.6) */ -static int inline rt6_check_dev(struct rt6_info *rt, int oif) +static inline int rt6_check_dev(struct rt6_info *rt, int oif) { struct net_device *dev = rt->rt6i_dev; if (!oif || dev->ifindex == oif) @@ -268,122 +333,291 @@ static int inline rt6_check_dev(struct rt6_info *rt, int oif) return 0; } -static int inline rt6_check_neigh(struct rt6_info *rt) +static inline int rt6_check_neigh(struct rt6_info *rt) { struct neighbour *neigh = rt->rt6i_nexthop; - int m = 0; - if (neigh) { + int m; + if (rt->rt6i_flags & RTF_NONEXTHOP || + !(rt->rt6i_flags & RTF_GATEWAY)) + m = 1; + else if (neigh) { read_lock_bh(&neigh->lock); if (neigh->nud_state & NUD_VALID) + m = 2; +#ifdef CONFIG_IPV6_ROUTER_PREF + else if (neigh->nud_state & NUD_FAILED) + m = 0; +#endif + else m = 1; read_unlock_bh(&neigh->lock); - } + } else + m = 0; return m; } static int rt6_score_route(struct rt6_info *rt, int oif, int strict) { - int m = rt6_check_dev(rt, oif); - if (!m && (strict & RT6_SELECT_F_IFACE)) + int m, n; + + m = rt6_check_dev(rt, oif); + if (!m && (strict & RT6_LOOKUP_F_IFACE)) return -1; #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; #endif - if (rt6_check_neigh(rt)) - m |= 16; - else if (strict & RT6_SELECT_F_REACHABLE) + n = rt6_check_neigh(rt); + if (!n && (strict & RT6_LOOKUP_F_REACHABLE)) return -1; return m; } -static struct rt6_info *rt6_select(struct rt6_info **head, int oif, - int strict) +static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, + int *mpri, struct rt6_info *match) +{ + int m; + + if (rt6_check_expired(rt)) + goto out; + + m = rt6_score_route(rt, oif, strict); + if (m < 0) + goto out; + + if (m > *mpri) { + if (strict & RT6_LOOKUP_F_REACHABLE) + rt6_probe(match); + *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) { - struct rt6_info *match = NULL, *last = NULL; - struct rt6_info *rt, *rt0 = *head; - u32 metric; + struct rt6_info *rt, *match; int mpri = -1; - RT6_TRACE("%s(head=%p(*head=%p), oif=%d)\n", - __FUNCTION__, head, head ? *head : NULL, oif); + match = NULL; + for (rt = rr_head; rt && rt->rt6i_metric == metric; + rt = rt->u.dst.rt6_next) + match = find_match(rt, oif, strict, &mpri, match); + for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric; + rt = rt->u.dst.rt6_next) + match = find_match(rt, oif, strict, &mpri, match); - for (rt = rt0, metric = rt0->rt6i_metric; - rt && rt->rt6i_metric == metric; - rt = rt->u.next) { - int m; + return match; +} - if (rt6_check_expired(rt)) - continue; +static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) +{ + struct rt6_info *match, *rt0; + struct net *net; - last = rt; + RT6_TRACE("%s(fn->leaf=%p, oif=%d)\n", + __func__, fn->leaf, oif); - m = rt6_score_route(rt, oif, strict); - if (m < 0) - continue; + rt0 = fn->rr_ptr; + if (!rt0) + fn->rr_ptr = rt0 = fn->leaf; - if (m > mpri) { - rt6_probe(match); - match = rt; - mpri = m; - } else { - rt6_probe(rt); - } - } + match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict); if (!match && - (strict & RT6_SELECT_F_REACHABLE) && - last && last != rt0) { + (strict & RT6_LOOKUP_F_REACHABLE)) { + struct rt6_info *next = rt0->u.dst.rt6_next; + /* no entries matched; do round-robin */ - *head = rt0->u.next; - rt0->u.next = last->u.next; - last->u.next = rt0; + if (!next || next->rt6i_metric != rt0->rt6i_metric) + next = fn->leaf; + + if (next != rt0) + fn->rr_ptr = next; + } + + RT6_TRACE("%s() => %p\n", + __func__, match); + + net = dev_net(rt0->rt6i_dev); + return (match ? match : net->ipv6.ip6_null_entry); +} + +#ifdef CONFIG_IPV6_ROUTE_INFO +int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, + struct in6_addr *gwaddr) +{ + struct net *net = dev_net(dev); + struct route_info *rinfo = (struct route_info *) opt; + struct in6_addr prefix_buf, *prefix; + unsigned int pref; + unsigned long lifetime; + struct rt6_info *rt; + + if (len < sizeof(struct route_info)) { + return -EINVAL; + } + + /* Sanity check for prefix_len and length */ + if (rinfo->length > 3) { + return -EINVAL; + } else if (rinfo->prefix_len > 128) { + return -EINVAL; + } else if (rinfo->prefix_len > 64) { + if (rinfo->length < 2) { + return -EINVAL; + } + } else if (rinfo->prefix_len > 0) { + if (rinfo->length < 1) { + return -EINVAL; + } + } + + pref = rinfo->route_pref; + if (pref == ICMPV6_ROUTER_PREF_INVALID) + return -EINVAL; + + lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ); + + if (rinfo->length == 3) + prefix = (struct in6_addr *)rinfo->prefix; + else { + /* this function is safe */ + ipv6_addr_prefix(&prefix_buf, + (struct in6_addr *)rinfo->prefix, + rinfo->prefix_len); + prefix = &prefix_buf; + } + + rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, + dev->ifindex); + + if (rt && !lifetime) { + ip6_del_rt(rt); + rt = NULL; } - RT6_TRACE("%s() => %p, score=%d\n", - __FUNCTION__, match, mpri); + if (!rt && lifetime) + rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev->ifindex, + pref); + else if (rt) + rt->rt6i_flags = RTF_ROUTEINFO | + (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); - return (match ? match : &ip6_null_entry); + if (rt) { + if (!addrconf_finite_timeout(lifetime)) { + rt->rt6i_flags &= ~RTF_EXPIRES; + } else { + rt->rt6i_expires = jiffies + HZ * lifetime; + rt->rt6i_flags |= RTF_EXPIRES; + } + dst_release(&rt->u.dst); + } + return 0; } +#endif + +#define BACKTRACK(__net, saddr) \ +do { \ + if (rt == __net->ipv6.ip6_null_entry) { \ + struct fib6_node *pn; \ + while (1) { \ + if (fn->fn_flags & RTN_TL_ROOT) \ + goto out; \ + pn = fn->parent; \ + if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) \ + fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr); \ + else \ + fn = pn; \ + if (fn->fn_flags & RTN_RTINFO) \ + goto restart; \ + } \ + } \ +} while(0) -struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr, - int oif, int strict) +static struct rt6_info *ip6_pol_route_lookup(struct net *net, + struct fib6_table *table, + struct flowi *fl, int flags) { struct fib6_node *fn; struct rt6_info *rt; - read_lock_bh(&rt6_lock); - fn = fib6_lookup(&ip6_routing_table, daddr, saddr); - rt = rt6_device_match(fn->leaf, oif, strict); - dst_hold(&rt->u.dst); - rt->u.dst.__use++; - read_unlock_bh(&rt6_lock); + read_lock_bh(&table->tb6_lock); + fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src); +restart: + rt = fn->leaf; + rt = rt6_device_match(net, rt, &fl->fl6_src, fl->oif, flags); + BACKTRACK(net, &fl->fl6_src); +out: + dst_use(&rt->u.dst, jiffies); + read_unlock_bh(&table->tb6_lock); + return rt; + +} + +struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, + const struct in6_addr *saddr, int oif, int strict) +{ + struct flowi fl = { + .oif = oif, + .nl_u = { + .ip6_u = { + .daddr = *daddr, + }, + }, + }; + struct dst_entry *dst; + int flags = strict ? RT6_LOOKUP_F_IFACE : 0; + + if (saddr) { + memcpy(&fl.fl6_src, saddr, sizeof(*saddr)); + flags |= RT6_LOOKUP_F_HAS_SADDR; + } + + dst = fib6_rule_lookup(net, &fl, flags, ip6_pol_route_lookup); + if (dst->error == 0) + return (struct rt6_info *) dst; + + dst_release(dst); - rt->u.dst.lastuse = jiffies; - if (rt->u.dst.error == 0) - return rt; - dst_release(&rt->u.dst); return NULL; } -/* ip6_ins_rt is called with FREE rt6_lock. +EXPORT_SYMBOL(rt6_lookup); + +/* ip6_ins_rt is called with FREE table->tb6_lock. It takes new route entry, the addition fails by any reason the route is freed. In any case, if caller does not hold it, it may be destroyed. */ -int ip6_ins_rt(struct rt6_info *rt, struct nlmsghdr *nlh, - void *_rtattr, struct netlink_skb_parms *req) +static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info) { int err; + struct fib6_table *table; - write_lock_bh(&rt6_lock); - err = fib6_add(&ip6_routing_table, rt, nlh, _rtattr, req); - write_unlock_bh(&rt6_lock); + table = rt->rt6i_table; + write_lock_bh(&table->tb6_lock); + err = fib6_add(&table->tb6_root, rt, info); + write_unlock_bh(&table->tb6_lock); return err; } +int ip6_ins_rt(struct rt6_info *rt) +{ + struct nl_info info = { + .nl_net = dev_net(rt->rt6i_dev), + }; + return __ip6_ins_rt(rt, &info); +} + static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr, struct in6_addr *saddr) { @@ -396,6 +630,9 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad rt = ip6_rt_copy(ort); if (rt) { + struct neighbour *neigh; + int attempts = !in_softirq(); + if (!(rt->rt6i_flags&RTF_GATEWAY)) { if (rt->rt6i_dst.plen != 128 && ipv6_addr_equal(&rt->rt6i_dst.addr, daddr)) @@ -415,7 +652,35 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad } #endif - rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway); + retry: + neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway); + if (IS_ERR(neigh)) { + struct net *net = dev_net(rt->rt6i_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; + } + + if (net_ratelimit()) + printk(KERN_WARNING + "Neighbour table overflow.\n"); + dst_free(&rt->u.dst); + return NULL; + } + rt->rt6i_nexthop = neigh; } @@ -429,70 +694,57 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *d ipv6_addr_copy(&rt->rt6i_dst.addr, daddr); rt->rt6i_dst.plen = 128; rt->rt6i_flags |= RTF_CACHE; - if (rt->rt6i_flags & RTF_REJECT) - rt->u.dst.error = ort->u.dst.error; rt->u.dst.flags |= DST_HOST; rt->rt6i_nexthop = neigh_clone(ort->rt6i_nexthop); } return rt; } -#define BACKTRACK() \ -if (rt == &ip6_null_entry) { \ - while ((fn = fn->parent) != NULL) { \ - if (fn->fn_flags & RTN_ROOT) { \ - goto out; \ - } \ - if (fn->fn_flags & RTN_RTINFO) \ - goto restart; \ - } \ -} - - -void ip6_route_input(struct sk_buff *skb) +static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, + struct flowi *fl, int flags) { struct fib6_node *fn; struct rt6_info *rt, *nrt; - int strict; + int strict = 0; int attempts = 3; int err; - int reachable = RT6_SELECT_F_REACHABLE; + int reachable = net->ipv6.devconf_all->forwarding ? 0 : RT6_LOOKUP_F_REACHABLE; - strict = ipv6_addr_type(&skb->nh.ipv6h->daddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL) ? RT6_SELECT_F_IFACE : 0; + strict |= flags & RT6_LOOKUP_F_IFACE; relookup: - read_lock_bh(&rt6_lock); + read_lock_bh(&table->tb6_lock); restart_2: - fn = fib6_lookup(&ip6_routing_table, &skb->nh.ipv6h->daddr, - &skb->nh.ipv6h->saddr); + fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src); restart: - rt = rt6_select(&fn->leaf, skb->dev->ifindex, strict | reachable); - BACKTRACK(); - if (rt == &ip6_null_entry || + rt = rt6_select(fn, oif, strict | reachable); + + BACKTRACK(net, &fl->fl6_src); + if (rt == net->ipv6.ip6_null_entry || rt->rt6i_flags & RTF_CACHE) goto out; dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) - nrt = rt6_alloc_cow(rt, &skb->nh.ipv6h->daddr, &skb->nh.ipv6h->saddr); + nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src); else { #if CLONE_OFFLINK_ROUTE - nrt = rt6_alloc_clone(rt, &skb->nh.ipv6h->daddr); + nrt = rt6_alloc_clone(rt, &fl->fl6_dst); #else goto out2; #endif } dst_release(&rt->u.dst); - rt = nrt ? : &ip6_null_entry; + rt = nrt ? : net->ipv6.ip6_null_entry; dst_hold(&rt->u.dst); if (nrt) { - err = ip6_ins_rt(nrt, NULL, NULL, &NETLINK_CB(skb)); + err = ip6_ins_rt(nrt); if (!err) goto out2; } @@ -501,7 +753,7 @@ restart: goto out2; /* - * Race condition! In the gap, when rt6_lock was + * Race condition! In the gap, when table->tb6_lock was * released someone could insert this route. Relookup. */ dst_release(&rt->u.dst); @@ -513,84 +765,109 @@ out: goto restart_2; } dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); out2: rt->u.dst.lastuse = jiffies; rt->u.dst.__use++; - skb->dst = (struct dst_entry *) rt; - return; + + return rt; } -struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl) +static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, + struct flowi *fl, int flags) { - struct fib6_node *fn; - struct rt6_info *rt, *nrt; - int strict; - int attempts = 3; - int err; - int reachable = RT6_SELECT_F_REACHABLE; + return ip6_pol_route(net, table, fl->iif, fl, flags); +} - strict = ipv6_addr_type(&fl->fl6_dst) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL) ? RT6_SELECT_F_IFACE : 0; +void ip6_route_input(struct sk_buff *skb) +{ + struct ipv6hdr *iph = ipv6_hdr(skb); + struct net *net = dev_net(skb->dev); + int flags = RT6_LOOKUP_F_HAS_SADDR; + struct flowi fl = { + .iif = skb->dev->ifindex, + .nl_u = { + .ip6_u = { + .daddr = iph->daddr, + .saddr = iph->saddr, + .flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK, + }, + }, + .mark = skb->mark, + .proto = iph->nexthdr, + }; -relookup: - read_lock_bh(&rt6_lock); + if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG) + flags |= RT6_LOOKUP_F_IFACE; -restart_2: - fn = fib6_lookup(&ip6_routing_table, &fl->fl6_dst, &fl->fl6_src); + skb_dst_set(skb, fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input)); +} -restart: - rt = rt6_select(&fn->leaf, fl->oif, strict | reachable); - BACKTRACK(); - if (rt == &ip6_null_entry || - rt->rt6i_flags & RTF_CACHE) - goto out; +static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, + struct flowi *fl, int flags) +{ + return ip6_pol_route(net, table, fl->oif, fl, flags); +} - dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); +struct dst_entry * ip6_route_output(struct net *net, struct sock *sk, + struct flowi *fl) +{ + int flags = 0; - if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) - nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src); - else { -#if CLONE_OFFLINK_ROUTE - nrt = rt6_alloc_clone(rt, &fl->fl6_dst); -#else - goto out2; -#endif - } + if (fl->oif || rt6_need_strict(&fl->fl6_dst)) + flags |= RT6_LOOKUP_F_IFACE; - dst_release(&rt->u.dst); - rt = nrt ? : &ip6_null_entry; + if (!ipv6_addr_any(&fl->fl6_src)) + flags |= RT6_LOOKUP_F_HAS_SADDR; + else if (sk) + flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs); - dst_hold(&rt->u.dst); - if (nrt) { - err = ip6_ins_rt(nrt, NULL, NULL, NULL); - if (!err) - goto out2; - } + return fib6_rule_lookup(net, fl, flags, ip6_pol_route_output); +} - if (--attempts <= 0) - goto out2; +EXPORT_SYMBOL(ip6_route_output); - /* - * Race condition! In the gap, when rt6_lock was - * released someone could insert this route. Relookup. - */ - dst_release(&rt->u.dst); - goto relookup; +int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl) +{ + struct rt6_info *ort = (struct rt6_info *) *dstp; + struct rt6_info *rt = (struct rt6_info *) + dst_alloc(&ip6_dst_blackhole_ops); + struct dst_entry *new = NULL; -out: - if (reachable) { - reachable = 0; - goto restart_2; + if (rt) { + new = &rt->u.dst; + + atomic_set(&new->__refcnt, 1); + new->__use = 1; + new->input = dst_discard; + new->output = dst_discard; + + memcpy(new->metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32)); + new->dev = ort->u.dst.dev; + if (new->dev) + dev_hold(new->dev); + rt->rt6i_idev = ort->rt6i_idev; + if (rt->rt6i_idev) + in6_dev_hold(rt->rt6i_idev); + rt->rt6i_expires = 0; + + ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway); + rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES; + rt->rt6i_metric = 0; + + memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); +#ifdef CONFIG_IPV6_SUBTREES + memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); +#endif + + dst_free(new); } - dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); -out2: - rt->u.dst.lastuse = jiffies; - rt->u.dst.__use++; - return &rt->u.dst; -} + dst_release(*dstp); + *dstp = new; + return (new ? 0 : -ENOMEM); +} +EXPORT_SYMBOL_GPL(ip6_dst_blackhole); /* * Destination cache support functions @@ -602,7 +879,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt = (struct rt6_info *) dst; - if (rt && rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) + if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) return dst; return NULL; @@ -613,21 +890,26 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) struct rt6_info *rt = (struct rt6_info *) dst; if (rt) { - if (rt->rt6i_flags & RTF_CACHE) - ip6_del_rt(rt, NULL, NULL, NULL); - else + if (rt->rt6i_flags & RTF_CACHE) { + if (rt6_check_expired(rt)) { + ip6_del_rt(rt); + dst = NULL; + } + } else { dst_release(dst); + dst = NULL; + } } - return NULL; + return dst; } static void ip6_link_failure(struct sk_buff *skb) { struct rt6_info *rt; - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev); + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); - rt = (struct rt6_info *) skb->dst; + rt = (struct rt6_info *) skb_dst(skb); if (rt) { if (rt->rt6i_flags&RTF_CACHE) { dst_set_expires(&rt->u.dst, 0); @@ -648,24 +930,23 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) dst->metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; } dst->metrics[RTAX_MTU-1] = mtu; + call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst); } } -/* Protected by rt6_lock. */ -static struct dst_entry *ndisc_dst_gc_list; static int ipv6_get_mtu(struct net_device *dev); -static inline unsigned int ipv6_advmss(unsigned int mtu) +static inline unsigned int ipv6_advmss(struct net *net, unsigned int mtu) { mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr); - if (mtu < ip6_rt_min_advmss) - mtu = ip6_rt_min_advmss; + if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss) + mtu = net->ipv6.sysctl.ip6_rt_min_advmss; /* - * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and - * corresponding MSS is IPV6_MAXPLEN - tcp_header_size. - * IPV6_MAXPLEN is also valid and means: "any MSS, + * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and + * corresponding MSS is IPV6_MAXPLEN - tcp_header_size. + * IPV6_MAXPLEN is also valid and means: "any MSS, * rely only on pmtu discovery" */ if (mtu > IPV6_MAXPLEN - sizeof(struct tcphdr)) @@ -673,18 +954,21 @@ static inline unsigned int ipv6_advmss(unsigned int mtu) return mtu; } -struct dst_entry *ndisc_dst_alloc(struct net_device *dev, +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 in6_addr *addr, - int (*output)(struct sk_buff *)) + const struct in6_addr *addr) { struct rt6_info *rt; struct inet6_dev *idev = in6_dev_get(dev); + struct net *net = dev_net(dev); if (unlikely(idev == NULL)) return NULL; - rt = ip6_dst_alloc(); + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); if (unlikely(rt == NULL)) { in6_dev_put(idev); goto out; @@ -693,8 +977,11 @@ struct dst_entry *ndisc_dst_alloc(struct net_device *dev, dev_hold(dev); if (neigh) neigh_hold(neigh); - else + else { neigh = ndisc_get_neigh(dev, addr); + if (IS_ERR(neigh)) + neigh = NULL; + } rt->rt6i_dev = dev; rt->rt6i_idev = idev; @@ -702,69 +989,94 @@ struct dst_entry *ndisc_dst_alloc(struct net_device *dev, atomic_set(&rt->u.dst.__refcnt, 1); rt->u.dst.metrics[RTAX_HOPLIMIT-1] = 255; rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev); - rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst)); - rt->u.dst.output = output; + rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst)); + rt->u.dst.output = ip6_output; #if 0 /* there's no chance to use these for ndisc */ - rt->u.dst.flags = ipv6_addr_type(addr) & IPV6_ADDR_UNICAST - ? DST_HOST + rt->u.dst.flags = ipv6_addr_type(addr) & IPV6_ADDR_UNICAST + ? DST_HOST : 0; ipv6_addr_copy(&rt->rt6i_dst.addr, addr); rt->rt6i_dst.plen = 128; #endif - write_lock_bh(&rt6_lock); - rt->u.dst.next = ndisc_dst_gc_list; - ndisc_dst_gc_list = &rt->u.dst; - write_unlock_bh(&rt6_lock); + spin_lock_bh(&icmp6_dst_lock); + rt->u.dst.next = icmp6_dst_gc_list; + icmp6_dst_gc_list = &rt->u.dst; + spin_unlock_bh(&icmp6_dst_lock); - fib6_force_start_gc(); + fib6_force_start_gc(net); out: - return (struct dst_entry *)rt; + return &rt->u.dst; } -int ndisc_dst_gc(int *more) +int icmp6_dst_gc(void) { struct dst_entry *dst, *next, **pprev; - int freed; + int more = 0; next = NULL; - pprev = &ndisc_dst_gc_list; - freed = 0; + + spin_lock_bh(&icmp6_dst_lock); + pprev = &icmp6_dst_gc_list; + while ((dst = *pprev) != NULL) { if (!atomic_read(&dst->__refcnt)) { *pprev = dst->next; dst_free(dst); - freed++; } else { pprev = &dst->next; - (*more)++; + ++more; } } - return freed; + spin_unlock_bh(&icmp6_dst_lock); + + return more; } -static int ip6_dst_gc(void) +static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg), + void *arg) { - static unsigned expire = 30*HZ; - static unsigned long last_gc; - unsigned long now = jiffies; + struct dst_entry *dst, **pprev; - if (time_after(last_gc + ip6_rt_gc_min_interval, now) && - atomic_read(&ip6_dst_ops.entries) <= ip6_rt_max_size) - goto out; + spin_lock_bh(&icmp6_dst_lock); + pprev = &icmp6_dst_gc_list; + while ((dst = *pprev) != NULL) { + struct rt6_info *rt = (struct rt6_info *) dst; + if (func(rt, arg)) { + *pprev = dst->next; + dst_free(dst); + } else { + pprev = &dst->next; + } + } + spin_unlock_bh(&icmp6_dst_lock); +} - expire++; - fib6_run_gc(expire); - last_gc = now; - if (atomic_read(&ip6_dst_ops.entries) < ip6_dst_ops.gc_thresh) - expire = ip6_rt_gc_timeout>>1; +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; + int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; + int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; + unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; + + if (time_after(rt_last_gc + rt_min_interval, now) && + atomic_read(&ops->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; + if (atomic_read(&ops->entries) < ops->gc_thresh) + net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; out: - expire -= expire>>ip6_rt_gc_elasticity; - return (atomic_read(&ip6_dst_ops.entries) > ip6_rt_max_size); + net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity; + return (atomic_read(&ops->entries) > rt_max_size); } /* Clean host part of a prefix. Not necessary in radix tree, @@ -786,15 +1098,17 @@ static int ipv6_get_mtu(struct net_device *dev) return mtu; } -int ipv6_get_hoplimit(struct net_device *dev) +int ip6_dst_hoplimit(struct dst_entry *dst) { - int hoplimit = ipv6_devconf.hop_limit; - struct inet6_dev *idev; - - idev = in6_dev_get(dev); - if (idev) { - hoplimit = idev->cnf.hop_limit; - in6_dev_put(idev); + int hoplimit = dst_metric(dst, RTAX_HOPLIMIT); + if (hoplimit < 0) { + struct net_device *dev = dst->dev; + struct inet6_dev *idev = in6_dev_get(dev); + if (idev) { + hoplimit = idev->cnf.hop_limit; + in6_dev_put(idev); + } else + hoplimit = dev_net(dev)->ipv6.devconf_all->hop_limit; } return hoplimit; } @@ -803,28 +1117,25 @@ int ipv6_get_hoplimit(struct net_device *dev) * */ -int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, - void *_rtattr, struct netlink_skb_parms *req) +int ip6_route_add(struct fib6_config *cfg) { int err; - struct rtmsg *r; - struct rtattr **rta; + struct net *net = cfg->fc_nlinfo.nl_net; struct rt6_info *rt = NULL; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; + struct fib6_table *table; int addr_type; - rta = (struct rtattr **) _rtattr; - - if (rtmsg->rtmsg_dst_len > 128 || rtmsg->rtmsg_src_len > 128) + if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) return -EINVAL; #ifndef CONFIG_IPV6_SUBTREES - if (rtmsg->rtmsg_src_len) + if (cfg->fc_src_len) return -EINVAL; #endif - if (rtmsg->rtmsg_ifindex) { + if (cfg->fc_ifindex) { err = -ENODEV; - dev = dev_get_by_index(rtmsg->rtmsg_ifindex); + dev = dev_get_by_index(net, cfg->fc_ifindex); if (!dev) goto out; idev = in6_dev_get(dev); @@ -832,10 +1143,16 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, goto out; } - if (rtmsg->rtmsg_metric == 0) - rtmsg->rtmsg_metric = IP6_RT_PRIO_USER; + if (cfg->fc_metric == 0) + cfg->fc_metric = IP6_RT_PRIO_USER; + + table = fib6_new_table(net, cfg->fc_table); + if (table == NULL) { + err = -ENOBUFS; + goto out; + } - rt = ip6_dst_alloc(); + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); if (rt == NULL) { err = -ENOMEM; @@ -843,14 +1160,15 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, } rt->u.dst.obsolete = -1; - rt->rt6i_expires = jiffies + clock_t_to_jiffies(rtmsg->rtmsg_info); - if (nlh && (r = NLMSG_DATA(nlh))) { - rt->rt6i_protocol = r->rtm_protocol; - } else { - rt->rt6i_protocol = RTPROT_BOOT; - } + rt->rt6i_expires = (cfg->fc_flags & RTF_EXPIRES) ? + jiffies + clock_t_to_jiffies(cfg->fc_expires) : + 0; + + if (cfg->fc_protocol == RTPROT_UNSPEC) + cfg->fc_protocol = RTPROT_BOOT; + rt->rt6i_protocol = cfg->fc_protocol; - addr_type = ipv6_addr_type(&rtmsg->rtmsg_dst); + addr_type = ipv6_addr_type(&cfg->fc_dst); if (addr_type & IPV6_ADDR_MULTICAST) rt->u.dst.input = ip6_mc_input; @@ -859,32 +1177,30 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, rt->u.dst.output = ip6_output; - ipv6_addr_prefix(&rt->rt6i_dst.addr, - &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len); - rt->rt6i_dst.plen = rtmsg->rtmsg_dst_len; + 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->u.dst.flags = DST_HOST; #ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_prefix(&rt->rt6i_src.addr, - &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len); - rt->rt6i_src.plen = rtmsg->rtmsg_src_len; + ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); + rt->rt6i_src.plen = cfg->fc_src_len; #endif - rt->rt6i_metric = rtmsg->rtmsg_metric; + rt->rt6i_metric = cfg->fc_metric; /* We cannot add true routes via loopback here, they would result in kernel looping; promote them to reject routes */ - if ((rtmsg->rtmsg_flags&RTF_REJECT) || + if ((cfg->fc_flags & RTF_REJECT) || (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) { /* hold loopback dev/idev if we haven't done so. */ - if (dev != &loopback_dev) { + if (dev != net->loopback_dev) { if (dev) { dev_put(dev); in6_dev_put(idev); } - dev = &loopback_dev; + dev = net->loopback_dev; dev_hold(dev); idev = in6_dev_get(dev); if (!idev) { @@ -899,12 +1215,12 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, goto install_route; } - if (rtmsg->rtmsg_flags & RTF_GATEWAY) { + if (cfg->fc_flags & RTF_GATEWAY) { struct in6_addr *gw_addr; int gwa_type; - gw_addr = &rtmsg->rtmsg_gateway; - ipv6_addr_copy(&rt->rt6i_gateway, &rtmsg->rtmsg_gateway); + gw_addr = &cfg->fc_gateway; + ipv6_addr_copy(&rt->rt6i_gateway, gw_addr); gwa_type = ipv6_addr_type(gw_addr); if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) { @@ -921,7 +1237,7 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, if (!(gwa_type&IPV6_ADDR_UNICAST)) goto out; - grt = rt6_lookup(gw_addr, NULL, rtmsg->rtmsg_ifindex, 1); + grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, 1); err = -EHOSTUNREACH; if (grt == NULL) @@ -953,7 +1269,7 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, if (dev == NULL) goto out; - if (rtmsg->rtmsg_flags & (RTF_GATEWAY|RTF_NONEXTHOP)) { + if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) { rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev); if (IS_ERR(rt->rt6i_nexthop)) { err = PTR_ERR(rt->rt6i_nexthop); @@ -962,36 +1278,40 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, } } - rt->rt6i_flags = rtmsg->rtmsg_flags; + rt->rt6i_flags = cfg->fc_flags; install_route: - if (rta && rta[RTA_METRICS-1]) { - int attrlen = RTA_PAYLOAD(rta[RTA_METRICS-1]); - struct rtattr *attr = RTA_DATA(rta[RTA_METRICS-1]); - - while (RTA_OK(attr, attrlen)) { - unsigned flavor = attr->rta_type; - if (flavor) { - if (flavor > RTAX_MAX) { + 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; } - rt->u.dst.metrics[flavor-1] = - *(u32 *)RTA_DATA(attr); + + rt->u.dst.metrics[type - 1] = nla_get_u32(nla); } - attr = RTA_NEXT(attr, attrlen); } } - if (rt->u.dst.metrics[RTAX_HOPLIMIT-1] == 0) + if (dst_metric(&rt->u.dst, RTAX_HOPLIMIT) == 0) rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1; - if (!rt->u.dst.metrics[RTAX_MTU-1]) + if (!dst_mtu(&rt->u.dst)) rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(dev); - if (!rt->u.dst.metrics[RTAX_ADVMSS-1]) - rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst)); + if (!dst_metric(&rt->u.dst, RTAX_ADVMSS)) + rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst)); rt->u.dst.dev = dev; rt->rt6i_idev = idev; - return ip6_ins_rt(rt, nlh, _rtattr, req); + rt->rt6i_table = table; + + cfg->fc_nlinfo.nl_net = dev_net(dev); + + return __ip6_ins_rt(rt, &cfg->fc_nlinfo); out: if (dev) @@ -999,55 +1319,73 @@ out: if (idev) in6_dev_put(idev); if (rt) - dst_free((struct dst_entry *) rt); + dst_free(&rt->u.dst); return err; } -int ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) { int err; + struct fib6_table *table; + struct net *net = dev_net(rt->rt6i_dev); - write_lock_bh(&rt6_lock); + if (rt == net->ipv6.ip6_null_entry) + return -ENOENT; - err = fib6_del(rt, nlh, _rtattr, req); + table = rt->rt6i_table; + write_lock_bh(&table->tb6_lock); + + err = fib6_del(rt, info); dst_release(&rt->u.dst); - write_unlock_bh(&rt6_lock); + write_unlock_bh(&table->tb6_lock); return err; } -static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +int ip6_del_rt(struct rt6_info *rt) +{ + struct nl_info info = { + .nl_net = dev_net(rt->rt6i_dev), + }; + return __ip6_del_rt(rt, &info); +} + +static int ip6_route_del(struct fib6_config *cfg) { + struct fib6_table *table; struct fib6_node *fn; struct rt6_info *rt; int err = -ESRCH; - read_lock_bh(&rt6_lock); + table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); + if (table == NULL) + return err; + + read_lock_bh(&table->tb6_lock); + + fn = fib6_locate(&table->tb6_root, + &cfg->fc_dst, cfg->fc_dst_len, + &cfg->fc_src, cfg->fc_src_len); - fn = fib6_locate(&ip6_routing_table, - &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len, - &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len); - if (fn) { - for (rt = fn->leaf; rt; rt = rt->u.next) { - if (rtmsg->rtmsg_ifindex && + for (rt = fn->leaf; rt; rt = rt->u.dst.rt6_next) { + if (cfg->fc_ifindex && (rt->rt6i_dev == NULL || - rt->rt6i_dev->ifindex != rtmsg->rtmsg_ifindex)) + rt->rt6i_dev->ifindex != cfg->fc_ifindex)) continue; - if (rtmsg->rtmsg_flags&RTF_GATEWAY && - !ipv6_addr_equal(&rtmsg->rtmsg_gateway, &rt->rt6i_gateway)) + if (cfg->fc_flags & RTF_GATEWAY && + !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) continue; - if (rtmsg->rtmsg_metric && - rtmsg->rtmsg_metric != rt->rt6i_metric) + if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric) continue; dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); - return ip6_del_rt(rt, nlh, _rtattr, req); + return __ip6_del_rt(rt, &cfg->fc_nlinfo); } } - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); return err; } @@ -1055,67 +1393,115 @@ static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, void *_r /* * Handle redirects */ -void rt6_redirect(struct in6_addr *dest, struct in6_addr *saddr, - struct neighbour *neigh, u8 *lladdr, int on_link) +struct ip6rd_flowi { + struct flowi fl; + struct in6_addr gateway; +}; + +static struct rt6_info *__ip6_route_redirect(struct net *net, + struct fib6_table *table, + struct flowi *fl, + int flags) { - struct rt6_info *rt, *nrt; + struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl; + struct rt6_info *rt; + struct fib6_node *fn; - /* Locate old route to this destination. */ - rt = rt6_lookup(dest, NULL, neigh->dev->ifindex, 1); + /* + * Get the "current" route for this destination and + * check if the redirect has come from approriate router. + * + * RFC 2461 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. + */ - if (rt == NULL) - return; + read_lock_bh(&table->tb6_lock); + fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src); +restart: + for (rt = fn->leaf; rt; rt = rt->u.dst.rt6_next) { + /* + * Current route is on-link; redirect is always invalid. + * + * Seems, previous statement is not true. It could + * be node, which looks for us as on-link (f.e. proxy ndisc) + * But then router serving it might decide, that we should + * know truth 8)8) --ANK (980726). + */ + if (rt6_check_expired(rt)) + continue; + if (!(rt->rt6i_flags & RTF_GATEWAY)) + continue; + if (fl->oif != rt->rt6i_dev->ifindex) + continue; + if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) + continue; + break; + } - if (neigh->dev != rt->rt6i_dev) - goto out; + if (!rt) + rt = net->ipv6.ip6_null_entry; + BACKTRACK(net, &fl->fl6_src); +out: + dst_hold(&rt->u.dst); - /* - * Current route is on-link; redirect is always invalid. - * - * Seems, previous statement is not true. It could - * be node, which looks for us as on-link (f.e. proxy ndisc) - * But then router serving it might decide, that we should - * know truth 8)8) --ANK (980726). - */ - if (!(rt->rt6i_flags&RTF_GATEWAY)) - goto out; + read_unlock_bh(&table->tb6_lock); + + return rt; +}; + +static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, + struct in6_addr *src, + struct in6_addr *gateway, + struct net_device *dev) +{ + int flags = RT6_LOOKUP_F_HAS_SADDR; + struct net *net = dev_net(dev); + struct ip6rd_flowi rdfl = { + .fl = { + .oif = dev->ifindex, + .nl_u = { + .ip6_u = { + .daddr = *dest, + .saddr = *src, + }, + }, + }, + }; + + ipv6_addr_copy(&rdfl.gateway, gateway); + + if (rt6_need_strict(dest)) + flags |= RT6_LOOKUP_F_IFACE; + + return (struct rt6_info *)fib6_rule_lookup(net, (struct flowi *)&rdfl, + flags, __ip6_route_redirect); +} + +void rt6_redirect(struct in6_addr *dest, struct in6_addr *src, + struct in6_addr *saddr, + struct neighbour *neigh, u8 *lladdr, int on_link) +{ + struct rt6_info *rt, *nrt = NULL; + struct netevent_redirect netevent; + struct net *net = dev_net(neigh->dev); - /* - * RFC 2461 specifies that redirects should only be - * accepted if they come from the nexthop to the target. - * Due to the way default routers are chosen, this notion - * is a bit fuzzy and one might need to check all default - * routers. - */ - if (!ipv6_addr_equal(saddr, &rt->rt6i_gateway)) { - if (rt->rt6i_flags & RTF_DEFAULT) { - struct rt6_info *rt1; - - read_lock(&rt6_lock); - for (rt1 = ip6_routing_table.leaf; rt1; rt1 = rt1->u.next) { - if (ipv6_addr_equal(saddr, &rt1->rt6i_gateway)) { - dst_hold(&rt1->u.dst); - dst_release(&rt->u.dst); - read_unlock(&rt6_lock); - rt = rt1; - goto source_ok; - } - } - read_unlock(&rt6_lock); - } + rt = ip6_route_redirect(dest, src, saddr, neigh->dev); + + if (rt == net->ipv6.ip6_null_entry) { if (net_ratelimit()) printk(KERN_DEBUG "rt6_redirect: source isn't a valid nexthop " "for redirect target\n"); goto out; } -source_ok: - /* * We have finally decided to accept it. */ - neigh_update(neigh, lladdr, NUD_STALE, + neigh_update(neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| (on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER| @@ -1149,19 +1535,23 @@ source_ok: nrt->rt6i_nexthop = neigh_clone(neigh); /* Reset pmtu, it may be better */ nrt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev); - nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&nrt->u.dst)); + nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dev_net(neigh->dev), + dst_mtu(&nrt->u.dst)); - if (ip6_ins_rt(nrt, NULL, NULL, NULL)) + if (ip6_ins_rt(nrt)) goto out; + netevent.old = &rt->u.dst; + netevent.new = &nrt->u.dst; + call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); + if (rt->rt6i_flags&RTF_CACHE) { - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); return; } out: - dst_release(&rt->u.dst); - return; + dst_release(&rt->u.dst); } /* @@ -1173,9 +1563,10 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, struct net_device *dev, u32 pmtu) { struct rt6_info *rt, *nrt; + struct net *net = dev_net(dev); int allfrag = 0; - rt = rt6_lookup(daddr, saddr, dev->ifindex, 0); + rt = rt6_lookup(net, daddr, saddr, dev->ifindex, 0); if (rt == NULL) return; @@ -1184,7 +1575,7 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, if (pmtu < IPV6_MIN_MTU) { /* - * According to RFC2460, PMTU is set to the IPv6 Minimum Link + * According to RFC2460, PMTU is set to the IPv6 Minimum Link * MTU (1280) and a fragment header should always be included * after a node receiving Too Big message reporting PMTU is * less than the IPv6 Minimum Link MTU. @@ -1208,7 +1599,7 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, rt->u.dst.metrics[RTAX_MTU-1] = pmtu; if (allfrag) rt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; - dst_set_expires(&rt->u.dst, ip6_rt_mtu_expires); + dst_set_expires(&rt->u.dst, net->ipv6.sysctl.ip6_rt_mtu_expires); rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES; goto out; } @@ -1234,10 +1625,10 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, * which is 10 mins. After 10 mins the decreased pmtu is expired * and detecting PMTU increase will be automatically happened. */ - dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires); + dst_set_expires(&nrt->u.dst, net->ipv6.sysctl.ip6_rt_mtu_expires); nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES; - ip6_ins_rt(nrt, NULL, NULL, NULL); + ip6_ins_rt(nrt); } out: dst_release(&rt->u.dst); @@ -1249,13 +1640,15 @@ out: static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) { - struct rt6_info *rt = ip6_dst_alloc(); + struct net *net = dev_net(ort->rt6i_dev); + struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); if (rt) { rt->u.dst.input = ort->u.dst.input; rt->u.dst.output = ort->u.dst.output; memcpy(rt->u.dst.metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32)); + rt->u.dst.error = ort->u.dst.error; rt->u.dst.dev = ort->u.dst.dev; if (rt->u.dst.dev) dev_hold(rt->u.dst.dev); @@ -1273,19 +1666,85 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) #ifdef CONFIG_IPV6_SUBTREES memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); #endif + rt->rt6i_table = ort->rt6i_table; + } + return rt; +} + +#ifdef CONFIG_IPV6_ROUTE_INFO +static struct rt6_info *rt6_get_route_info(struct net *net, + struct in6_addr *prefix, int prefixlen, + struct in6_addr *gwaddr, int ifindex) +{ + struct fib6_node *fn; + struct rt6_info *rt = NULL; + struct fib6_table *table; + + table = fib6_get_table(net, RT6_TABLE_INFO); + if (table == NULL) + return NULL; + + write_lock_bh(&table->tb6_lock); + fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0); + if (!fn) + goto out; + + for (rt = fn->leaf; rt; rt = rt->u.dst.rt6_next) { + if (rt->rt6i_dev->ifindex != ifindex) + continue; + if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) + continue; + if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr)) + continue; + dst_hold(&rt->u.dst); + break; } +out: + write_unlock_bh(&table->tb6_lock); return rt; } +static struct rt6_info *rt6_add_route_info(struct net *net, + struct in6_addr *prefix, int prefixlen, + struct in6_addr *gwaddr, int ifindex, + unsigned pref) +{ + struct fib6_config cfg = { + .fc_table = RT6_TABLE_INFO, + .fc_metric = IP6_RT_PRIO_USER, + .fc_ifindex = ifindex, + .fc_dst_len = prefixlen, + .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | + RTF_UP | RTF_PREF(pref), + .fc_nlinfo.pid = 0, + .fc_nlinfo.nlh = NULL, + .fc_nlinfo.nl_net = net, + }; + + ipv6_addr_copy(&cfg.fc_dst, prefix); + ipv6_addr_copy(&cfg.fc_gateway, gwaddr); + + /* We should treat it as a default route if prefix length is 0. */ + if (!prefixlen) + cfg.fc_flags |= RTF_DEFAULT; + + ip6_route_add(&cfg); + + return rt6_get_route_info(net, prefix, prefixlen, gwaddr, ifindex); +} +#endif + struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *dev) -{ +{ struct rt6_info *rt; - struct fib6_node *fn; + struct fib6_table *table; - fn = &ip6_routing_table; + table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT); + if (table == NULL) + return NULL; - write_lock_bh(&rt6_lock); - for (rt = fn->leaf; rt; rt=rt->u.next) { + write_lock_bh(&table->tb6_lock); + for (rt = table->tb6_root.leaf; rt; rt=rt->u.dst.rt6_next) { if (dev == rt->rt6i_dev && ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&rt->rt6i_gateway, addr)) @@ -1293,7 +1752,7 @@ struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *d } if (rt) dst_hold(&rt->u.dst); - write_unlock_bh(&rt6_lock); + write_unlock_bh(&table->tb6_lock); return rt; } @@ -1301,43 +1760,71 @@ struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref) { - struct in6_rtmsg rtmsg; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_DFLT, + .fc_metric = IP6_RT_PRIO_USER, + .fc_ifindex = dev->ifindex, + .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | + RTF_UP | RTF_EXPIRES | RTF_PREF(pref), + .fc_nlinfo.pid = 0, + .fc_nlinfo.nlh = NULL, + .fc_nlinfo.nl_net = dev_net(dev), + }; - memset(&rtmsg, 0, sizeof(struct in6_rtmsg)); - rtmsg.rtmsg_type = RTMSG_NEWROUTE; - ipv6_addr_copy(&rtmsg.rtmsg_gateway, gwaddr); - rtmsg.rtmsg_metric = 1024; - rtmsg.rtmsg_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | - RTF_PREF(pref); + ipv6_addr_copy(&cfg.fc_gateway, gwaddr); - rtmsg.rtmsg_ifindex = dev->ifindex; + ip6_route_add(&cfg); - ip6_route_add(&rtmsg, NULL, NULL, NULL); return rt6_get_dflt_router(gwaddr, dev); } -void rt6_purge_dflt_routers(void) +void rt6_purge_dflt_routers(struct net *net) { struct rt6_info *rt; + struct fib6_table *table; + + /* NOTE: Keep consistent with rt6_get_dflt_router */ + table = fib6_get_table(net, RT6_TABLE_DFLT); + if (table == NULL) + return; restart: - read_lock_bh(&rt6_lock); - for (rt = ip6_routing_table.leaf; rt; rt = rt->u.next) { + read_lock_bh(&table->tb6_lock); + for (rt = table->tb6_root.leaf; rt; rt = rt->u.dst.rt6_next) { if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) { dst_hold(&rt->u.dst); - - read_unlock_bh(&rt6_lock); - - ip6_del_rt(rt, NULL, NULL, NULL); - + read_unlock_bh(&table->tb6_lock); + ip6_del_rt(rt); goto restart; } } - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); +} + +static void rtmsg_to_fib6_config(struct net *net, + struct in6_rtmsg *rtmsg, + struct fib6_config *cfg) +{ + memset(cfg, 0, sizeof(*cfg)); + + cfg->fc_table = RT6_TABLE_MAIN; + cfg->fc_ifindex = rtmsg->rtmsg_ifindex; + cfg->fc_metric = rtmsg->rtmsg_metric; + cfg->fc_expires = rtmsg->rtmsg_info; + cfg->fc_dst_len = rtmsg->rtmsg_dst_len; + cfg->fc_src_len = rtmsg->rtmsg_src_len; + cfg->fc_flags = rtmsg->rtmsg_flags; + + cfg->fc_nlinfo.nl_net = net; + + ipv6_addr_copy(&cfg->fc_dst, &rtmsg->rtmsg_dst); + ipv6_addr_copy(&cfg->fc_src, &rtmsg->rtmsg_src); + ipv6_addr_copy(&cfg->fc_gateway, &rtmsg->rtmsg_gateway); } -int ipv6_route_ioctl(unsigned int cmd, void __user *arg) +int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) { + struct fib6_config cfg; struct in6_rtmsg rtmsg; int err; @@ -1350,14 +1837,16 @@ int ipv6_route_ioctl(unsigned int cmd, void __user *arg) sizeof(struct in6_rtmsg)); if (err) return -EFAULT; - + + rtmsg_to_fib6_config(net, &rtmsg, &cfg); + rtnl_lock(); switch (cmd) { case SIOCADDRT: - err = ip6_route_add(&rtmsg, NULL, NULL, NULL); + err = ip6_route_add(&cfg); break; case SIOCDELRT: - err = ip6_route_del(&rtmsg, NULL, NULL, NULL); + err = ip6_route_del(&cfg); break; default: err = -EINVAL; @@ -1365,7 +1854,7 @@ int ipv6_route_ioctl(unsigned int cmd, void __user *arg) rtnl_unlock(); return err; - }; + } return -EINVAL; } @@ -1374,20 +1863,55 @@ int ipv6_route_ioctl(unsigned int cmd, void __user *arg) * Drop the packet on the floor */ -static int ip6_pkt_discard(struct sk_buff *skb) +static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) { - IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES); - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_NOROUTE, 0, skb->dev); + int type; + struct dst_entry *dst = skb_dst(skb); + switch (ipstats_mib_noroutes) { + case IPSTATS_MIB_INNOROUTES: + type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); + if (type == IPV6_ADDR_ANY) { + IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), + IPSTATS_MIB_INADDRERRORS); + break; + } + /* FALLTHROUGH */ + case IPSTATS_MIB_OUTNOROUTES: + IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), + ipstats_mib_noroutes); + break; + } + icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0); kfree_skb(skb); return 0; } +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) { - skb->dev = skb->dst->dev; - return ip6_pkt_discard(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) +{ + 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. */ @@ -1396,21 +1920,23 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, const struct in6_addr *addr, int anycast) { - struct rt6_info *rt = ip6_dst_alloc(); + struct net *net = dev_net(idev->dev); + struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); + struct neighbour *neigh; if (rt == NULL) return ERR_PTR(-ENOMEM); - dev_hold(&loopback_dev); + dev_hold(net->loopback_dev); in6_dev_hold(idev); rt->u.dst.flags = DST_HOST; rt->u.dst.input = ip6_input; rt->u.dst.output = ip6_output; - rt->rt6i_dev = &loopback_dev; + rt->rt6i_dev = net->loopback_dev; rt->rt6i_idev = idev; rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev); - rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst)); + rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst)); rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1; rt->u.dst.obsolete = -1; @@ -1419,35 +1945,55 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_flags |= RTF_ANYCAST; else rt->rt6i_flags |= RTF_LOCAL; - rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway); - if (rt->rt6i_nexthop == NULL) { - dst_free((struct dst_entry *) rt); - return ERR_PTR(-ENOMEM); + neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway); + if (IS_ERR(neigh)) { + dst_free(&rt->u.dst); + + /* We are casting this because that is the return + * value type. But an errno encoded pointer is the + * same regardless of the underlying pointer type, + * and that's what we are returning. So this is OK. + */ + return (struct rt6_info *) neigh; } + rt->rt6i_nexthop = neigh; ipv6_addr_copy(&rt->rt6i_dst.addr, addr); rt->rt6i_dst.plen = 128; + rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); atomic_set(&rt->u.dst.__refcnt, 1); return rt; } +struct arg_dev_net { + struct net_device *dev; + struct net *net; +}; + static int fib6_ifdown(struct rt6_info *rt, void *arg) { - if (((void*)rt->rt6i_dev == arg || arg == NULL) && - rt != &ip6_null_entry) { + struct net_device *dev = ((struct arg_dev_net *)arg)->dev; + struct net *net = ((struct arg_dev_net *)arg)->net; + + if (((void *)rt->rt6i_dev == dev || dev == NULL) && + rt != net->ipv6.ip6_null_entry) { RT6_TRACE("deleted by ifdown %p\n", rt); return -1; } return 0; } -void rt6_ifdown(struct net_device *dev) +void rt6_ifdown(struct net *net, struct net_device *dev) { - write_lock_bh(&rt6_lock); - fib6_clean_tree(&ip6_routing_table, fib6_ifdown, 0, dev); - write_unlock_bh(&rt6_lock); + struct arg_dev_net adn = { + .dev = dev, + .net = net, + }; + + fib6_clean_all(net, fib6_ifdown, 0, &adn); + icmp6_clean_all(fib6_ifdown, &adn); } struct rt6_mtu_change_arg @@ -1460,6 +2006,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg; struct inet6_dev *idev; + struct net *net = dev_net(arg->dev); /* In IPv6 pmtu discovery is not optional, so that RTAX_MTU lock cannot disable it. @@ -1487,100 +2034,152 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) */ if (rt->rt6i_dev == arg->dev && !dst_metric_locked(&rt->u.dst, RTAX_MTU) && - (dst_mtu(&rt->u.dst) > arg->mtu || - (dst_mtu(&rt->u.dst) < arg->mtu && - dst_mtu(&rt->u.dst) == idev->cnf.mtu6))) + (dst_mtu(&rt->u.dst) >= arg->mtu || + (dst_mtu(&rt->u.dst) < arg->mtu && + dst_mtu(&rt->u.dst) == idev->cnf.mtu6))) { rt->u.dst.metrics[RTAX_MTU-1] = arg->mtu; - rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(arg->mtu); + rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, arg->mtu); + } return 0; } void rt6_mtu_change(struct net_device *dev, unsigned mtu) { - struct rt6_mtu_change_arg arg; + struct rt6_mtu_change_arg arg = { + .dev = dev, + .mtu = mtu, + }; - arg.dev = dev; - arg.mtu = mtu; - read_lock_bh(&rt6_lock); - fib6_clean_tree(&ip6_routing_table, rt6_mtu_change_route, 0, &arg); - read_unlock_bh(&rt6_lock); + fib6_clean_all(dev_net(dev), rt6_mtu_change_route, 0, &arg); } -static int inet6_rtm_to_rtmsg(struct rtmsg *r, struct rtattr **rta, - struct in6_rtmsg *rtmsg) +static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { + [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, + [RTA_OIF] = { .type = NLA_U32 }, + [RTA_IIF] = { .type = NLA_U32 }, + [RTA_PRIORITY] = { .type = NLA_U32 }, + [RTA_METRICS] = { .type = NLA_NESTED }, +}; + +static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, + struct fib6_config *cfg) { - memset(rtmsg, 0, sizeof(*rtmsg)); + struct rtmsg *rtm; + struct nlattr *tb[RTA_MAX+1]; + int err; - rtmsg->rtmsg_dst_len = r->rtm_dst_len; - rtmsg->rtmsg_src_len = r->rtm_src_len; - rtmsg->rtmsg_flags = RTF_UP; - if (r->rtm_type == RTN_UNREACHABLE) - rtmsg->rtmsg_flags |= RTF_REJECT; + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy); + if (err < 0) + goto errout; - if (rta[RTA_GATEWAY-1]) { - if (rta[RTA_GATEWAY-1]->rta_len != RTA_LENGTH(16)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_gateway, RTA_DATA(rta[RTA_GATEWAY-1]), 16); - rtmsg->rtmsg_flags |= RTF_GATEWAY; - } - if (rta[RTA_DST-1]) { - if (RTA_PAYLOAD(rta[RTA_DST-1]) < ((r->rtm_dst_len+7)>>3)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_dst, RTA_DATA(rta[RTA_DST-1]), ((r->rtm_dst_len+7)>>3)); + err = -EINVAL; + rtm = nlmsg_data(nlh); + memset(cfg, 0, sizeof(*cfg)); + + cfg->fc_table = rtm->rtm_table; + cfg->fc_dst_len = rtm->rtm_dst_len; + cfg->fc_src_len = rtm->rtm_src_len; + cfg->fc_flags = RTF_UP; + cfg->fc_protocol = rtm->rtm_protocol; + + if (rtm->rtm_type == RTN_UNREACHABLE) + cfg->fc_flags |= RTF_REJECT; + + cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid; + cfg->fc_nlinfo.nlh = nlh; + cfg->fc_nlinfo.nl_net = sock_net(skb->sk); + + if (tb[RTA_GATEWAY]) { + nla_memcpy(&cfg->fc_gateway, tb[RTA_GATEWAY], 16); + cfg->fc_flags |= RTF_GATEWAY; } - if (rta[RTA_SRC-1]) { - if (RTA_PAYLOAD(rta[RTA_SRC-1]) < ((r->rtm_src_len+7)>>3)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_src, RTA_DATA(rta[RTA_SRC-1]), ((r->rtm_src_len+7)>>3)); + + if (tb[RTA_DST]) { + int plen = (rtm->rtm_dst_len + 7) >> 3; + + if (nla_len(tb[RTA_DST]) < plen) + goto errout; + + nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen); } - if (rta[RTA_OIF-1]) { - if (rta[RTA_OIF-1]->rta_len != RTA_LENGTH(sizeof(int))) - return -EINVAL; - memcpy(&rtmsg->rtmsg_ifindex, RTA_DATA(rta[RTA_OIF-1]), sizeof(int)); + + if (tb[RTA_SRC]) { + int plen = (rtm->rtm_src_len + 7) >> 3; + + if (nla_len(tb[RTA_SRC]) < plen) + goto errout; + + nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen); } - if (rta[RTA_PRIORITY-1]) { - if (rta[RTA_PRIORITY-1]->rta_len != RTA_LENGTH(4)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_metric, RTA_DATA(rta[RTA_PRIORITY-1]), 4); + + if (tb[RTA_OIF]) + cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]); + + if (tb[RTA_PRIORITY]) + cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]); + + if (tb[RTA_METRICS]) { + cfg->fc_mx = nla_data(tb[RTA_METRICS]); + cfg->fc_mx_len = nla_len(tb[RTA_METRICS]); } - return 0; + + if (tb[RTA_TABLE]) + cfg->fc_table = nla_get_u32(tb[RTA_TABLE]); + + err = 0; +errout: + return err; } -int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct rtmsg *r = NLMSG_DATA(nlh); - struct in6_rtmsg rtmsg; + struct fib6_config cfg; + int err; - if (inet6_rtm_to_rtmsg(r, arg, &rtmsg)) - return -EINVAL; - return ip6_route_del(&rtmsg, nlh, arg, &NETLINK_CB(skb)); + err = rtm_to_fib6_config(skb, nlh, &cfg); + if (err < 0) + return err; + + return ip6_route_del(&cfg); } -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, void *arg) { - struct rtmsg *r = NLMSG_DATA(nlh); - struct in6_rtmsg rtmsg; + struct fib6_config cfg; + int err; - if (inet6_rtm_to_rtmsg(r, arg, &rtmsg)) - return -EINVAL; - return ip6_route_add(&rtmsg, nlh, arg, &NETLINK_CB(skb)); + err = rtm_to_fib6_config(skb, nlh, &cfg); + if (err < 0) + return err; + + return ip6_route_add(&cfg); } -struct rt6_rtnl_dump_arg -{ - struct sk_buff *skb; - struct netlink_callback *cb; -}; +static inline size_t rt6_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct rtmsg)) + + nla_total_size(16) /* RTA_SRC */ + + nla_total_size(16) /* RTA_DST */ + + nla_total_size(16) /* RTA_GATEWAY */ + + nla_total_size(16) /* RTA_PREFSRC */ + + nla_total_size(4) /* RTA_TABLE */ + + nla_total_size(4) /* RTA_IIF */ + + nla_total_size(4) /* RTA_OIF */ + + nla_total_size(4) /* RTA_PRIORITY */ + + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ + + nla_total_size(sizeof(struct rta_cacheinfo)); +} -static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, +static int rt6_fill_node(struct net *net, + struct sk_buff *skb, struct rt6_info *rt, struct in6_addr *dst, struct in6_addr *src, int iif, int type, u32 pid, u32 seq, - int prefix, unsigned int flags) + int prefix, int nowait, unsigned int flags) { struct rtmsg *rtm; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - struct rta_cacheinfo ci; + struct nlmsghdr *nlh; + long expires; + u32 table; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -1589,13 +2188,21 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, } } - nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*rtm), flags); - rtm = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags); + if (nlh == NULL) + return -EMSGSIZE; + + rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; rtm->rtm_dst_len = rt->rt6i_dst.plen; rtm->rtm_src_len = rt->rt6i_src.plen; rtm->rtm_tos = 0; - rtm->rtm_table = RT_TABLE_MAIN; + if (rt->rt6i_table) + table = rt->rt6i_table->tb6_id; + else + table = RT6_TABLE_UNSPEC; + rtm->rtm_table = table; + NLA_PUT_U32(skb, RTA_TABLE, table); if (rt->rt6i_flags&RTF_REJECT) rtm->rtm_type = RTN_UNREACHABLE; else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK)) @@ -1616,252 +2223,210 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, rtm->rtm_flags |= RTM_F_CLONED; if (dst) { - RTA_PUT(skb, RTA_DST, 16, dst); - rtm->rtm_dst_len = 128; + NLA_PUT(skb, RTA_DST, 16, dst); + rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - RTA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr); + NLA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (src) { - RTA_PUT(skb, RTA_SRC, 16, src); - rtm->rtm_src_len = 128; + NLA_PUT(skb, RTA_SRC, 16, src); + rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len) - RTA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr); + NLA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr); +#endif + if (iif) { +#ifdef CONFIG_IPV6_MROUTE + if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) { + int err = ip6mr_get_route(net, skb, rtm, nowait); + if (err <= 0) { + if (!nowait) { + if (err == 0) + return 0; + goto nla_put_failure; + } else { + if (err == -EMSGSIZE) + goto nla_put_failure; + } + } + } else #endif - if (iif) - RTA_PUT(skb, RTA_IIF, 4, &iif); - else if (dst) { + NLA_PUT_U32(skb, RTA_IIF, iif); + } else if (dst) { + struct inet6_dev *idev = ip6_dst_idev(&rt->u.dst); struct in6_addr saddr_buf; - if (ipv6_get_saddr(&rt->u.dst, dst, &saddr_buf) == 0) - RTA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); + if (ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, + dst, 0, &saddr_buf) == 0) + NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } + if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0) - goto rtattr_failure; + goto nla_put_failure; + if (rt->u.dst.neighbour) - RTA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key); + NLA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key); + if (rt->u.dst.dev) - RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->rt6i_dev->ifindex); - RTA_PUT(skb, RTA_PRIORITY, 4, &rt->rt6i_metric); - ci.rta_lastuse = jiffies_to_clock_t(jiffies - rt->u.dst.lastuse); - if (rt->rt6i_expires) - ci.rta_expires = jiffies_to_clock_t(rt->rt6i_expires - jiffies); + NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex); + + NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric); + + if (!(rt->rt6i_flags & RTF_EXPIRES)) + expires = 0; + else if (rt->rt6i_expires - jiffies < INT_MAX) + expires = rt->rt6i_expires - jiffies; else - ci.rta_expires = 0; - ci.rta_used = rt->u.dst.__use; - ci.rta_clntref = atomic_read(&rt->u.dst.__refcnt); - ci.rta_error = rt->u.dst.error; - ci.rta_id = 0; - ci.rta_ts = 0; - ci.rta_tsage = 0; - RTA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + expires = INT_MAX; + + if (rtnl_put_cacheinfo(skb, &rt->u.dst, 0, 0, 0, + expires, rt->u.dst.error) < 0) + goto nla_put_failure; -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } -static int rt6_dump_route(struct rt6_info *rt, void *p_arg) +int rt6_dump_route(struct rt6_info *rt, void *p_arg) { struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg; int prefix; - if (arg->cb->nlh->nlmsg_len >= NLMSG_LENGTH(sizeof(struct rtmsg))) { - struct rtmsg *rtm = NLMSG_DATA(arg->cb->nlh); + if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) { + struct rtmsg *rtm = nlmsg_data(arg->cb->nlh); prefix = (rtm->rtm_flags & RTM_F_PREFIX) != 0; } else prefix = 0; - return rt6_fill_node(arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, + return rt6_fill_node(arg->net, + arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq, - prefix, NLM_F_MULTI); + prefix, 0, NLM_F_MULTI); } -static int fib6_dump_node(struct fib6_walker_t *w) +static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) { - int res; + struct net *net = sock_net(in_skb->sk); + struct nlattr *tb[RTA_MAX+1]; struct rt6_info *rt; + struct sk_buff *skb; + struct rtmsg *rtm; + struct flowi fl; + int err, iif = 0; - for (rt = w->leaf; rt; rt = rt->u.next) { - res = rt6_dump_route(rt, w->args); - if (res < 0) { - /* Frame is full, suspend walking */ - w->leaf = rt; - return 1; - } - BUG_TRAP(res!=0); - } - w->leaf = NULL; - return 0; -} - -static void fib6_dump_end(struct netlink_callback *cb) -{ - struct fib6_walker_t *w = (void*)cb->args[0]; - - if (w) { - cb->args[0] = 0; - fib6_walker_unlink(w); - kfree(w); - } - cb->done = (void*)cb->args[1]; - cb->args[1] = 0; -} - -static int fib6_dump_done(struct netlink_callback *cb) -{ - fib6_dump_end(cb); - return cb->done ? cb->done(cb) : 0; -} - -int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct rt6_rtnl_dump_arg arg; - struct fib6_walker_t *w; - int res; + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy); + if (err < 0) + goto errout; - arg.skb = skb; - arg.cb = cb; + err = -EINVAL; + memset(&fl, 0, sizeof(fl)); - w = (void*)cb->args[0]; - if (w == NULL) { - /* New dump: - * - * 1. hook callback destructor. - */ - cb->args[1] = (long)cb->done; - cb->done = fib6_dump_done; + if (tb[RTA_SRC]) { + if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) + goto errout; - /* - * 2. allocate and initialize walker. - */ - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (w == NULL) - return -ENOMEM; - RT6_TRACE("dump<%p", w); - memset(w, 0, sizeof(*w)); - w->root = &ip6_routing_table; - w->func = fib6_dump_node; - w->args = &arg; - cb->args[0] = (long)w; - read_lock_bh(&rt6_lock); - res = fib6_walk(w); - read_unlock_bh(&rt6_lock); - } else { - w->args = &arg; - read_lock_bh(&rt6_lock); - res = fib6_walk_continue(w); - read_unlock_bh(&rt6_lock); + ipv6_addr_copy(&fl.fl6_src, nla_data(tb[RTA_SRC])); } -#if RT6_DEBUG >= 3 - if (res <= 0 && skb->len == 0) - RT6_TRACE("%p>dump end\n", w); -#endif - res = res < 0 ? res : skb->len; - /* res < 0 is an error. (really, impossible) - res == 0 means that dump is complete, but skb still can contain data. - res > 0 dump is not complete, but frame is full. - */ - /* Destroy walker, if dump of this table is complete. */ - if (res <= 0) - fib6_dump_end(cb); - return res; -} - -int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) -{ - struct rtattr **rta = arg; - int iif = 0; - int err = -ENOBUFS; - struct sk_buff *skb; - struct flowi fl; - struct rt6_info *rt; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (skb == NULL) - goto out; + if (tb[RTA_DST]) { + if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr)) + goto errout; - /* Reserve room for dummy headers, this skb can pass - through good chunk of routing engine. - */ - skb->mac.raw = skb->data; - skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr)); + ipv6_addr_copy(&fl.fl6_dst, nla_data(tb[RTA_DST])); + } - memset(&fl, 0, sizeof(fl)); - if (rta[RTA_SRC-1]) - ipv6_addr_copy(&fl.fl6_src, - (struct in6_addr*)RTA_DATA(rta[RTA_SRC-1])); - if (rta[RTA_DST-1]) - ipv6_addr_copy(&fl.fl6_dst, - (struct in6_addr*)RTA_DATA(rta[RTA_DST-1])); + if (tb[RTA_IIF]) + iif = nla_get_u32(tb[RTA_IIF]); - if (rta[RTA_IIF-1]) - memcpy(&iif, RTA_DATA(rta[RTA_IIF-1]), sizeof(int)); + if (tb[RTA_OIF]) + fl.oif = nla_get_u32(tb[RTA_OIF]); if (iif) { struct net_device *dev; - dev = __dev_get_by_index(iif); + dev = __dev_get_by_index(net, iif); if (!dev) { err = -ENODEV; - goto out_free; + goto errout; } } - fl.oif = 0; - if (rta[RTA_OIF-1]) - memcpy(&fl.oif, RTA_DATA(rta[RTA_OIF-1]), sizeof(int)); + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (skb == NULL) { + err = -ENOBUFS; + goto errout; + } - rt = (struct rt6_info*)ip6_route_output(NULL, &fl); + /* Reserve room for dummy headers, this skb can pass + through good chunk of routing engine. + */ + skb_reset_mac_header(skb); + skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr)); - skb->dst = &rt->u.dst; + rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl); + skb_dst_set(skb, &rt->u.dst); - NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid; - err = rt6_fill_node(skb, rt, - &fl.fl6_dst, &fl.fl6_src, - iif, + err = rt6_fill_node(net, skb, rt, &fl.fl6_dst, &fl.fl6_src, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).pid, - nlh->nlmsg_seq, 0, 0); + nlh->nlmsg_seq, 0, 0, 0); if (err < 0) { - err = -EMSGSIZE; - goto out_free; + kfree_skb(skb); + goto errout; } - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); - if (err > 0) - err = 0; -out: + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid); +errout: return err; -out_free: - kfree_skb(skb); - goto out; } -void inet6_rt_notify(int event, struct rt6_info *rt, struct nlmsghdr *nlh, - struct netlink_skb_parms *req) +void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) { struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct rtmsg)+256); - u32 pid = current->pid; - u32 seq = 0; - - if (req) - pid = req->pid; - if (nlh) - seq = nlh->nlmsg_seq; - - skb = alloc_skb(size, gfp_any()); - if (!skb) { - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_ROUTE, ENOBUFS); - return; - } - if (rt6_fill_node(skb, rt, NULL, NULL, 0, event, pid, seq, 0, 0) < 0) { + struct net *net = info->nl_net; + u32 seq; + int err; + + err = -ENOBUFS; + seq = info->nlh != NULL ? info->nlh->nlmsg_seq : 0; + + skb = nlmsg_new(rt6_nlmsg_size(), gfp_any()); + if (skb == NULL) + goto errout; + + err = rt6_fill_node(net, skb, rt, NULL, NULL, 0, + event, info->pid, seq, 0, 0, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_ROUTE, EINVAL); - return; + goto errout; + } + rtnl_notify(skb, net, info->pid, RTNLGRP_IPV6_ROUTE, + info->nlh, gfp_any()); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); +} + +static int ip6_route_dev_notify(struct notifier_block *this, + unsigned long event, void *data) +{ + struct net_device *dev = (struct net_device *)data; + struct net *net = dev_net(dev); + + if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) { + net->ipv6.ip6_null_entry->u.dst.dev = dev; + net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + net->ipv6.ip6_prohibit_entry->u.dst.dev = dev; + net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev); + net->ipv6.ip6_blk_hole_entry->u.dst.dev = dev; + net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev); +#endif } - NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_ROUTE; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_ROUTE, gfp_any()); + + return NOTIFY_OK; } /* @@ -1883,254 +2448,352 @@ struct rt6_proc_arg static int rt6_info_route(struct rt6_info *rt, void *p_arg) { - struct rt6_proc_arg *arg = (struct rt6_proc_arg *) p_arg; - int i; - - if (arg->skip < arg->offset / RT6_INFO_LEN) { - arg->skip++; - return 0; - } - - if (arg->len >= arg->length) - return 0; + struct seq_file *m = p_arg; - for (i=0; i<16; i++) { - sprintf(arg->buffer + arg->len, "%02x", - rt->rt6i_dst.addr.s6_addr[i]); - arg->len += 2; - } - arg->len += sprintf(arg->buffer + arg->len, " %02x ", - rt->rt6i_dst.plen); + seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen); #ifdef CONFIG_IPV6_SUBTREES - for (i=0; i<16; i++) { - sprintf(arg->buffer + arg->len, "%02x", - rt->rt6i_src.addr.s6_addr[i]); - arg->len += 2; - } - arg->len += sprintf(arg->buffer + arg->len, " %02x ", - rt->rt6i_src.plen); + seq_printf(m, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen); #else - sprintf(arg->buffer + arg->len, - "00000000000000000000000000000000 00 "); - arg->len += 36; + seq_puts(m, "00000000000000000000000000000000 00 "); #endif if (rt->rt6i_nexthop) { - for (i=0; i<16; i++) { - sprintf(arg->buffer + arg->len, "%02x", - rt->rt6i_nexthop->primary_key[i]); - arg->len += 2; - } + seq_printf(m, "%pi6", rt->rt6i_nexthop->primary_key); } else { - sprintf(arg->buffer + arg->len, - "00000000000000000000000000000000"); - arg->len += 32; - } - arg->len += sprintf(arg->buffer + arg->len, - " %08x %08x %08x %08x %8s\n", - rt->rt6i_metric, atomic_read(&rt->u.dst.__refcnt), - rt->u.dst.__use, rt->rt6i_flags, - rt->rt6i_dev ? rt->rt6i_dev->name : ""); + seq_puts(m, "00000000000000000000000000000000"); + } + seq_printf(m, " %08x %08x %08x %08x %8s\n", + rt->rt6i_metric, atomic_read(&rt->u.dst.__refcnt), + rt->u.dst.__use, rt->rt6i_flags, + rt->rt6i_dev ? rt->rt6i_dev->name : ""); return 0; } -static int rt6_proc_info(char *buffer, char **start, off_t offset, int length) +static int ipv6_route_show(struct seq_file *m, void *v) { - struct rt6_proc_arg arg; - arg.buffer = buffer; - arg.offset = offset; - arg.length = length; - arg.skip = 0; - arg.len = 0; - - read_lock_bh(&rt6_lock); - fib6_clean_tree(&ip6_routing_table, rt6_info_route, 0, &arg); - read_unlock_bh(&rt6_lock); - - *start = buffer; - if (offset) - *start += offset % RT6_INFO_LEN; - - arg.len -= offset % RT6_INFO_LEN; - - if (arg.len > length) - arg.len = length; - if (arg.len < 0) - arg.len = 0; + struct net *net = (struct net *)m->private; + fib6_clean_all(net, rt6_info_route, 0, m); + return 0; +} - return arg.len; +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, +}; + static int rt6_stats_seq_show(struct seq_file *seq, void *v) { + struct net *net = (struct net *)seq->private; seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n", - rt6_stats.fib_nodes, rt6_stats.fib_route_nodes, - rt6_stats.fib_rt_alloc, rt6_stats.fib_rt_entries, - rt6_stats.fib_rt_cache, - atomic_read(&ip6_dst_ops.entries), - rt6_stats.fib_discarded_routes); + net->ipv6.rt6_stats->fib_nodes, + net->ipv6.rt6_stats->fib_route_nodes, + net->ipv6.rt6_stats->fib_rt_alloc, + net->ipv6.rt6_stats->fib_rt_entries, + net->ipv6.rt6_stats->fib_rt_cache, + atomic_read(&net->ipv6.ip6_dst_ops.entries), + net->ipv6.rt6_stats->fib_discarded_routes); return 0; } static int rt6_stats_seq_open(struct inode *inode, struct file *file) { - return single_open(file, rt6_stats_seq_show, NULL); + return single_open_net(inode, file, rt6_stats_seq_show); } -static struct file_operations rt6_stats_seq_fops = { +static const struct file_operations rt6_stats_seq_fops = { .owner = THIS_MODULE, .open = rt6_stats_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL -static int flush_delay; - static -int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp, +int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct net *net = current->nsproxy->net_ns; + int delay = net->ipv6.sysctl.flush_delay; if (write) { - proc_dointvec(ctl, write, filp, buffer, lenp, ppos); - fib6_run_gc(flush_delay <= 0 ? ~0UL : (unsigned long)flush_delay); + proc_dointvec(ctl, write, buffer, lenp, ppos); + fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); return 0; } else return -EINVAL; } -ctl_table ipv6_route_table[] = { - { - .ctl_name = NET_IPV6_ROUTE_FLUSH, +ctl_table ipv6_route_table_template[] = { + { .procname = "flush", - .data = &flush_delay, + .data = &init_net.ipv6.sysctl.flush_delay, .maxlen = sizeof(int), .mode = 0200, - .proc_handler = &ipv6_sysctl_rtcache_flush + .proc_handler = ipv6_sysctl_rtcache_flush }, { - .ctl_name = NET_IPV6_ROUTE_GC_THRESH, .procname = "gc_thresh", - .data = &ip6_dst_ops.gc_thresh, + .data = &ip6_dst_ops_template.gc_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ROUTE_MAX_SIZE, .procname = "max_size", - .data = &ip6_rt_max_size, + .data = &init_net.ipv6.sysctl.ip6_rt_max_size, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL, .procname = "gc_min_interval", - .data = &ip6_rt_gc_min_interval, + .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_TIMEOUT, .procname = "gc_timeout", - .data = &ip6_rt_gc_timeout, + .data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_INTERVAL, .procname = "gc_interval", - .data = &ip6_rt_gc_interval, + .data = &init_net.ipv6.sysctl.ip6_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_ELASTICITY, .procname = "gc_elasticity", - .data = &ip6_rt_gc_elasticity, + .data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_MTU_EXPIRES, .procname = "mtu_expires", - .data = &ip6_rt_mtu_expires, + .data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_MIN_ADVMSS, .procname = "min_adv_mss", - .data = &ip6_rt_min_advmss, + .data = &init_net.ipv6.sysctl.ip6_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS, .procname = "gc_min_interval_ms", - .data = &ip6_rt_gc_min_interval, + .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_ms_jiffies, - .strategy = &sysctl_ms_jiffies, + .proc_handler = proc_dointvec_ms_jiffies, }, - { .ctl_name = 0 } + { } }; -#endif +struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) +{ + struct ctl_table *table; + + table = kmemdup(ipv6_route_table_template, + sizeof(ipv6_route_table_template), + GFP_KERNEL); + + if (table) { + table[0].data = &net->ipv6.sysctl.flush_delay; + table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh; + table[2].data = &net->ipv6.sysctl.ip6_rt_max_size; + table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; + table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout; + table[5].data = &net->ipv6.sysctl.ip6_rt_gc_interval; + table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity; + 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; + } -void __init ip6_route_init(void) -{ - struct proc_dir_entry *p; + return table; +} +#endif - ip6_dst_ops.kmem_cachep = kmem_cache_create("ip6_dst_cache", - sizeof(struct rt6_info), - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - if (!ip6_dst_ops.kmem_cachep) - panic("cannot create ip6_dst_cache"); +static int __net_init ip6_route_net_init(struct net *net) +{ + int ret = -ENOMEM; + + memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template, + sizeof(net->ipv6.ip6_dst_ops)); + + net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, + sizeof(*net->ipv6.ip6_null_entry), + GFP_KERNEL); + if (!net->ipv6.ip6_null_entry) + goto out_ip6_dst_ops; + net->ipv6.ip6_null_entry->u.dst.path = + (struct dst_entry *)net->ipv6.ip6_null_entry; + net->ipv6.ip6_null_entry->u.dst.ops = &net->ipv6.ip6_dst_ops; + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, + sizeof(*net->ipv6.ip6_prohibit_entry), + GFP_KERNEL); + if (!net->ipv6.ip6_prohibit_entry) + goto out_ip6_null_entry; + net->ipv6.ip6_prohibit_entry->u.dst.path = + (struct dst_entry *)net->ipv6.ip6_prohibit_entry; + net->ipv6.ip6_prohibit_entry->u.dst.ops = &net->ipv6.ip6_dst_ops; + + net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, + sizeof(*net->ipv6.ip6_blk_hole_entry), + GFP_KERNEL); + if (!net->ipv6.ip6_blk_hole_entry) + goto out_ip6_prohibit_entry; + net->ipv6.ip6_blk_hole_entry->u.dst.path = + (struct dst_entry *)net->ipv6.ip6_blk_hole_entry; + net->ipv6.ip6_blk_hole_entry->u.dst.ops = &net->ipv6.ip6_dst_ops; +#endif - fib6_init(); -#ifdef CONFIG_PROC_FS - p = proc_net_create("ipv6_route", 0, rt6_proc_info); - if (p) - p->owner = THIS_MODULE; + net->ipv6.sysctl.flush_delay = 0; + net->ipv6.sysctl.ip6_rt_max_size = 4096; + net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2; + net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ; + net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ; + net->ipv6.sysctl.ip6_rt_gc_elasticity = 9; + net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ; + net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; - proc_net_fops_create("rt6_stats", S_IRUGO, &rt6_stats_seq_fops); +#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); #endif -#ifdef CONFIG_XFRM - xfrm6_init(); + net->ipv6.ip6_rt_gc_expire = 30*HZ; + + ret = 0; +out: + return ret; + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES +out_ip6_prohibit_entry: + kfree(net->ipv6.ip6_prohibit_entry); +out_ip6_null_entry: + kfree(net->ipv6.ip6_null_entry); #endif +out_ip6_dst_ops: + goto out; } -void ip6_route_cleanup(void) +static void __net_exit ip6_route_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS - proc_net_remove("ipv6_route"); - proc_net_remove("rt6_stats"); + proc_net_remove(net, "ipv6_route"); + proc_net_remove(net, "rt6_stats"); #endif -#ifdef CONFIG_XFRM - xfrm6_fini(); + kfree(net->ipv6.ip6_null_entry); +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + kfree(net->ipv6.ip6_prohibit_entry); + kfree(net->ipv6.ip6_blk_hole_entry); #endif - rt6_ifdown(NULL); +} + +static struct pernet_operations ip6_route_net_ops = { + .init = ip6_route_net_init, + .exit = ip6_route_net_exit, +}; + +static struct notifier_block ip6_route_dev_notifier = { + .notifier_call = ip6_route_dev_notify, + .priority = 0, +}; + +int __init ip6_route_init(void) +{ + int ret; + + ret = -ENOMEM; + ip6_dst_ops_template.kmem_cachep = + kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!ip6_dst_ops_template.kmem_cachep) + goto out; + + ret = register_pernet_subsys(&ip6_route_net_ops); + if (ret) + goto out_kmem_cache; + + ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; + + /* Registering of the loopback is done before this portion of code, + * the loopback reference in rt6_info will not be taken, do it + * manually for init_net */ + init_net.ipv6.ip6_null_entry->u.dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); + #ifdef CONFIG_IPV6_MULTIPLE_TABLES + init_net.ipv6.ip6_prohibit_entry->u.dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); + init_net.ipv6.ip6_blk_hole_entry->u.dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); + #endif + ret = fib6_init(); + if (ret) + goto out_register_subsys; + + ret = xfrm6_init(); + if (ret) + goto out_fib6_init; + + ret = fib6_rules_init(); + if (ret) + goto xfrm6_init; + + ret = -ENOBUFS; + if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL) || + __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL) || + __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL)) + goto fib6_rules_init; + + ret = register_netdevice_notifier(&ip6_route_dev_notifier); + if (ret) + goto fib6_rules_init; + +out: + return ret; + +fib6_rules_init: + fib6_rules_cleanup(); +xfrm6_init: + xfrm6_fini(); +out_fib6_init: + fib6_gc_cleanup(); +out_register_subsys: + unregister_pernet_subsys(&ip6_route_net_ops); +out_kmem_cache: + kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); + goto out; +} + +void ip6_route_cleanup(void) +{ + unregister_netdevice_notifier(&ip6_route_dev_notifier); + fib6_rules_cleanup(); + xfrm6_fini(); fib6_gc_cleanup(); - kmem_cache_destroy(ip6_dst_ops.kmem_cachep); + unregister_pernet_subsys(&ip6_route_net_ops); + kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); }