X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=kernel%2Fnet%2Fipv4%2Froute.c;h=02c62299d717b9f6c38a5227e3b3ae376e0015b6;hb=e09b41010ba33a20a87472ee821fa407a5b8da36;hp=f45f2a12f37b25b7270560498423df9488405b1d;hpb=f93b97fd65072de626c074dbe099a1fff05ce060;p=kvmfornfv.git diff --git a/kernel/net/ipv4/route.c b/kernel/net/ipv4/route.c index f45f2a12f..02c62299d 100644 --- a/kernel/net/ipv4/route.c +++ b/kernel/net/ipv4/route.c @@ -91,6 +91,7 @@ #include #include #include +#include #include #include #include @@ -102,6 +103,7 @@ #include #include #include +#include #include #include #ifdef CONFIG_SYSCTL @@ -109,6 +111,8 @@ #include #endif #include +#include +#include #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) @@ -125,6 +129,7 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; +static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; /* * Interface to generic destination cache. */ @@ -457,12 +462,9 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, } #define IP_IDENTS_SZ 2048u -struct ip_ident_bucket { - atomic_t id; - u32 stamp32; -}; -static struct ip_ident_bucket *ip_idents __read_mostly; +static atomic_t *ip_idents __read_mostly; +static u32 *ip_tstamps __read_mostly; /* In order to protect privacy, we add a perturbation to identifiers * if one generator is seldom used. This makes hard for an attacker @@ -470,15 +472,16 @@ static struct ip_ident_bucket *ip_idents __read_mostly; */ u32 ip_idents_reserve(u32 hash, int segs) { - struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ; - u32 old = ACCESS_ONCE(bucket->stamp32); + u32 *p_tstamp = ip_tstamps + hash % IP_IDENTS_SZ; + atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ; + u32 old = ACCESS_ONCE(*p_tstamp); u32 now = (u32)jiffies; u32 delta = 0; - if (old != now && cmpxchg(&bucket->stamp32, old, now) == old) + if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = prandom_u32_max(now - old); - return atomic_add_return(segs + delta, &bucket->id) - segs; + return atomic_add_return(segs + delta, p_id) - segs; } EXPORT_SYMBOL(ip_idents_reserve); @@ -749,11 +752,11 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow if (!(n->nud_state & NUD_VALID)) { neigh_event_send(n, NULL); } else { - if (fib_lookup(net, fl4, &res) == 0) { + if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, 0); + 0, jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -836,6 +839,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) struct inet_peer *peer; struct net *net; int log_martians; + int vif; rcu_read_lock(); in_dev = __in_dev_get_rcu(rt->dst.dev); @@ -844,10 +848,11 @@ void ip_rt_send_redirect(struct sk_buff *skb) return; } log_martians = IN_DEV_LOG_MARTIANS(in_dev); + vif = l3mdev_master_ifindex_rcu(rt->dst.dev); rcu_read_unlock(); net = dev_net(rt->dst.dev); - peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1); + peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif, 1); if (!peer) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt_nexthop(rt, ip_hdr(skb)->daddr)); @@ -936,7 +941,8 @@ static int ip_error(struct sk_buff *skb) break; } - peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1); + peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, + l3mdev_master_ifindex(skb->dev), 1); send = true; if (peer) { @@ -977,7 +983,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) return; rcu_read_lock(); - if (fib_lookup(dev_net(dst->dev), fl4, &res) == 0) { + if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, 0, mtu, @@ -1147,7 +1153,7 @@ static void ipv4_link_failure(struct sk_buff *skb) dst_set_expires(&rt->dst, 0); } -static int ip_rt_bug(struct sock *sk, struct sk_buff *skb) +static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb) { pr_debug("%s: %pI4 -> %pI4, %s\n", __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, @@ -1188,7 +1194,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) fl4.flowi4_mark = skb->mark; rcu_read_lock(); - if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0) + if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0) src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res); else src = inet_select_addr(rt->dst.dev, @@ -1405,6 +1411,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif + rt->dst.lwtstate = lwtstate_get(nh->nh_lwtstate); if (unlikely(fnhe)) cached = rt_bind_exception(rt, fnhe, daddr); else if (!(rt->dst.flags & DST_NOCACHE)) @@ -1432,12 +1439,34 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, } static struct rtable *rt_dst_alloc(struct net_device *dev, + unsigned int flags, u16 type, bool nopolicy, bool noxfrm, bool will_cache) { - return dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, - (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | - (nopolicy ? DST_NOPOLICY : 0) | - (noxfrm ? DST_NOXFRM : 0)); + struct rtable *rt; + + rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, + (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | + (nopolicy ? DST_NOPOLICY : 0) | + (noxfrm ? DST_NOXFRM : 0)); + + if (rt) { + rt->rt_genid = rt_genid_ipv4(dev_net(dev)); + rt->rt_flags = flags; + rt->rt_type = type; + rt->rt_is_input = 0; + rt->rt_iif = 0; + rt->rt_pmtu = 0; + rt->rt_gateway = 0; + rt->rt_uses_gateway = 0; + rt->rt_table_id = 0; + INIT_LIST_HEAD(&rt->rt_uncached); + + rt->dst.output = ip_output; + if (flags & RTCF_LOCAL) + rt->dst.input = ip_local_deliver; + } + + return rt; } /* called in rcu_read_lock() section */ @@ -1446,6 +1475,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, { struct rtable *rth; struct in_device *in_dev = __in_dev_get_rcu(dev); + unsigned int flags = RTCF_MULTICAST; u32 itag = 0; int err; @@ -1458,9 +1488,8 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, skb->protocol != htons(ETH_P_IP)) goto e_inval; - if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) - if (ipv4_is_loopback(saddr)) - goto e_inval; + if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev)) + goto e_inval; if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr)) @@ -1471,7 +1500,10 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (err < 0) goto e_err; } - rth = rt_dst_alloc(dev_net(dev)->loopback_dev, + if (our) + flags |= RTCF_LOCAL; + + rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false); if (!rth) goto e_nobufs; @@ -1480,20 +1512,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->dst.tclassid = itag; #endif rth->dst.output = ip_rt_bug; - - rth->rt_genid = rt_genid_ipv4(dev_net(dev)); - rth->rt_flags = RTCF_MULTICAST; - rth->rt_type = RTN_MULTICAST; rth->rt_is_input= 1; - rth->rt_iif = 0; - rth->rt_pmtu = 0; - rth->rt_gateway = 0; - rth->rt_uses_gateway = 0; - INIT_LIST_HEAD(&rth->rt_uncached); - if (our) { - rth->dst.input= ip_local_deliver; - rth->rt_flags |= RTCF_LOCAL; - } #ifdef CONFIG_IP_MROUTE if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) @@ -1538,6 +1557,36 @@ static void ip_handle_martian_source(struct net_device *dev, #endif } +static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) +{ + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe, __rcu **fnhe_p; + u32 hval = fnhe_hashfun(daddr); + + spin_lock_bh(&fnhe_lock); + + hash = rcu_dereference_protected(nh->nh_exceptions, + lockdep_is_held(&fnhe_lock)); + hash += hval; + + fnhe_p = &hash->chain; + fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); + while (fnhe) { + if (fnhe->fnhe_daddr == daddr) { + rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( + fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + fnhe_flush_routes(fnhe); + kfree_rcu(fnhe, rcu); + break; + } + fnhe_p = &fnhe->fnhe_next; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, + lockdep_is_held(&fnhe_lock)); + } + + spin_unlock_bh(&fnhe_lock); +} + /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1548,7 +1597,6 @@ static int __mkroute_input(struct sk_buff *skb, struct rtable *rth; int err; struct in_device *out_dev; - unsigned int flags = 0; bool do_cache; u32 itag = 0; @@ -1592,18 +1640,27 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe) + if (fnhe) { rth = rcu_dereference(fnhe->fnhe_rth_input); - else - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(&FIB_RES_NH(*res), daddr); + fnhe = NULL; + } else { + goto rt_cache; + } + } + + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); +rt_cache: if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; } } - rth = rt_dst_alloc(out_dev->dev, + rth = rt_dst_alloc(out_dev->dev, 0, res->type, IN_DEV_CONF_GET(in_dev, NOPOLICY), IN_DEV_CONF_GET(out_dev, NOXFRM), do_cache); if (!rth) { @@ -1611,21 +1668,22 @@ static int __mkroute_input(struct sk_buff *skb, goto cleanup; } - rth->rt_genid = rt_genid_ipv4(dev_net(rth->dst.dev)); - rth->rt_flags = flags; - rth->rt_type = res->type; rth->rt_is_input = 1; - rth->rt_iif = 0; - rth->rt_pmtu = 0; - rth->rt_gateway = 0; - rth->rt_uses_gateway = 0; - INIT_LIST_HEAD(&rth->rt_uncached); + if (res->table) + rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; - rth->dst.output = ip_output; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag); + if (lwtunnel_output_redirect(rth->dst.lwtstate)) { + rth->dst.lwtstate->orig_output = rth->dst.output; + rth->dst.output = lwtunnel_output; + } + if (lwtunnel_input_redirect(rth->dst.lwtstate)) { + rth->dst.lwtstate->orig_input = rth->dst.input; + rth->dst.input = lwtunnel_input; + } skb_dst_set(skb, &rth->dst); out: err = 0; @@ -1633,6 +1691,48 @@ out: return err; } +#ifdef CONFIG_IP_ROUTE_MULTIPATH + +/* To make ICMP packets follow the right flow, the multipath hash is + * calculated from the inner IP addresses in reverse order. + */ +static int ip_multipath_icmp_hash(struct sk_buff *skb) +{ + const struct iphdr *outer_iph = ip_hdr(skb); + struct icmphdr _icmph; + const struct icmphdr *icmph; + struct iphdr _inner_iph; + const struct iphdr *inner_iph; + + if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0)) + goto standard_hash; + + icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph), + &_icmph); + if (!icmph) + goto standard_hash; + + if (icmph->type != ICMP_DEST_UNREACH && + icmph->type != ICMP_REDIRECT && + icmph->type != ICMP_TIME_EXCEEDED && + icmph->type != ICMP_PARAMETERPROB) { + goto standard_hash; + } + + inner_iph = skb_header_pointer(skb, + outer_iph->ihl * 4 + sizeof(_icmph), + sizeof(_inner_iph), &_inner_iph); + if (!inner_iph) + goto standard_hash; + + return fib_multipath_hash(inner_iph->daddr, inner_iph->saddr); + +standard_hash: + return fib_multipath_hash(outer_iph->saddr, outer_iph->daddr); +} + +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ + static int ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, const struct flowi4 *fl4, @@ -1640,8 +1740,15 @@ static int ip_mkroute_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, u32 tos) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res->fi && res->fi->fib_nhs > 1) - fib_select_multipath(res); + if (res->fi && res->fi->fib_nhs > 1) { + int h; + + if (unlikely(ip_hdr(skb)->protocol == IPPROTO_ICMP)) + h = ip_multipath_icmp_hash(skb); + else + h = fib_multipath_hash(saddr, daddr); + fib_select_multipath(res, h); + } #endif /* create a routing cache entry */ @@ -1664,6 +1771,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, { struct fib_result res; struct in_device *in_dev = __in_dev_get_rcu(dev); + struct ip_tunnel_info *tun_info; struct flowi4 fl4; unsigned int flags = 0; u32 itag = 0; @@ -1681,10 +1789,18 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, by fib_lookup. */ + tun_info = skb_tunnel_info(skb); + if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) + fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id; + else + fl4.flowi4_tun_key.tun_id = 0; + skb_dst_drop(skb); + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; res.fi = NULL; + res.table = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; @@ -1712,13 +1828,14 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, * Now we are ready to route packet. */ fl4.flowi4_oif = 0; - fl4.flowi4_iif = dev->ifindex; + fl4.flowi4_iif = l3mdev_fib_oif_rcu(dev); fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; + fl4.flowi4_flags = 0; fl4.daddr = daddr; fl4.saddr = saddr; - err = fib_lookup(net, &fl4, &res); + err = fib_lookup(net, &fl4, &res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) err = -EHOSTUNREACH; @@ -1732,7 +1849,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &itag); if (err < 0) - goto martian_source_keep_err; + goto martian_source; goto local_input; } @@ -1754,7 +1871,7 @@ brd_input: err = fib_validate_source(skb, saddr, 0, tos, 0, dev, in_dev, &itag); if (err < 0) - goto martian_source_keep_err; + goto martian_source; } flags |= RTCF_BROADCAST; res.type = RTN_BROADCAST; @@ -1774,26 +1891,19 @@ local_input: } } - rth = rt_dst_alloc(net->loopback_dev, + rth = rt_dst_alloc(net->loopback_dev, flags | RTCF_LOCAL, res.type, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache); if (!rth) goto e_nobufs; - rth->dst.input= ip_local_deliver; rth->dst.output= ip_rt_bug; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif - - rth->rt_genid = rt_genid_ipv4(net); - rth->rt_flags = flags|RTCF_LOCAL; - rth->rt_type = res.type; rth->rt_is_input = 1; - rth->rt_iif = 0; - rth->rt_pmtu = 0; - rth->rt_gateway = 0; - rth->rt_uses_gateway = 0; - INIT_LIST_HEAD(&rth->rt_uncached); + if (res.table) + rth->rt_table_id = res.table->tb_id; + RT_CACHE_STAT_INC(in_slow_tot); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; @@ -1814,6 +1924,7 @@ no_route: RT_CACHE_STAT_INC(in_no_route); res.type = RTN_UNREACHABLE; res.fi = NULL; + res.table = NULL; goto local_input; /* @@ -1836,8 +1947,6 @@ e_nobufs: goto out; martian_source: - err = -EINVAL; -martian_source_keep_err: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); goto out; } @@ -1945,19 +2054,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res, struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); - if (fnhe) + if (fnhe) { prth = &fnhe->fnhe_rth_output; - else { - if (unlikely(fl4->flowi4_flags & - FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { - do_cache = false; - goto add; + rth = rcu_dereference(*prth); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(nh, fl4->daddr); + fnhe = NULL; + } else { + goto rt_cache; } - prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); } + + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; + } + prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); rth = rcu_dereference(*prth); + +rt_cache: if (rt_cache_valid(rth)) { dst_hold(&rth->dst); return rth; @@ -1965,29 +2084,19 @@ static struct rtable *__mkroute_output(const struct fib_result *res, } add: - rth = rt_dst_alloc(dev_out, + rth = rt_dst_alloc(dev_out, flags, type, IN_DEV_CONF_GET(in_dev, NOPOLICY), IN_DEV_CONF_GET(in_dev, NOXFRM), do_cache); if (!rth) return ERR_PTR(-ENOBUFS); - rth->dst.output = ip_output; - - rth->rt_genid = rt_genid_ipv4(dev_net(dev_out)); - rth->rt_flags = flags; - rth->rt_type = type; - rth->rt_is_input = 0; rth->rt_iif = orig_oif ? : 0; - rth->rt_pmtu = 0; - rth->rt_gateway = 0; - rth->rt_uses_gateway = 0; - INIT_LIST_HEAD(&rth->rt_uncached); + if (res->table) + rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(out_slow_tot); - if (flags & RTCF_LOCAL) - rth->dst.input = ip_local_deliver; if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { if (flags & RTCF_LOCAL && !(dev_out->flags & IFF_LOOPBACK)) { @@ -2006,6 +2115,8 @@ add: } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0); + if (lwtunnel_output_redirect(rth->dst.lwtstate)) + rth->dst.output = lwtunnel_output; return rth; } @@ -2014,7 +2125,8 @@ add: * Major route resolver routine. */ -struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) +struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, + int mp_hash) { struct net_device *dev_out = NULL; __u8 tos = RT_FL_TOS(fl4); @@ -2022,6 +2134,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) struct fib_result res; struct rtable *rth; int orig_oif; + int err = -ENETUNREACH; res.tclassid = 0; res.fi = NULL; @@ -2097,7 +2210,8 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) goto out; } if (ipv4_is_local_multicast(fl4->daddr) || - ipv4_is_lbcast(fl4->daddr)) { + ipv4_is_lbcast(fl4->daddr) || + fl4->flowi4_proto == IPPROTO_IGMP) { if (!fl4->saddr) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); @@ -2111,6 +2225,10 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } + + rth = l3mdev_get_rtable(dev_out, fl4); + if (rth) + goto out; } if (!fl4->daddr) { @@ -2124,10 +2242,12 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) goto make_route; } - if (fib_lookup(net, fl4, &res)) { + err = fib_lookup(net, fl4, &res, 0); + if (err) { res.fi = NULL; res.table = NULL; - if (fl4->flowi4_oif) { + if (fl4->flowi4_oif && + !netif_index_is_l3_master(net, fl4->flowi4_oif)) { /* Apparently, routing tables are wrong. Assume, that the destination is on link. @@ -2152,7 +2272,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) res.type = RTN_UNICAST; goto make_route; } - rth = ERR_PTR(-ENETUNREACH); + rth = ERR_PTR(err); goto out; } @@ -2169,18 +2289,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) goto make_route; } -#ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0) - fib_select_multipath(&res); - else -#endif - if (!res.prefixlen && - res.table->tb_num_default > 1 && - res.type == RTN_UNICAST && !fl4->flowi4_oif) - fib_select_default(&res); - - if (!fl4->saddr) - fl4->saddr = FIB_RES_PREFSRC(net, res); + fib_select_path(net, &res, fl4, mp_hash); dev_out = FIB_RES_DEV(res); fl4->flowi4_oif = dev_out->ifindex; @@ -2193,7 +2302,7 @@ out: rcu_read_unlock(); return rth; } -EXPORT_SYMBOL_GPL(__ip_route_output_key); +EXPORT_SYMBOL_GPL(__ip_route_output_key_hash); static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) { @@ -2245,7 +2354,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or new->__use = 1; new->input = dst_discard; - new->output = dst_discard_sk; + new->output = dst_discard_out; new->dev = ort->dst.dev; if (new->dev) @@ -2262,7 +2371,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_uses_gateway = ort->rt_uses_gateway; INIT_LIST_HEAD(&rt->rt_uncached); - dst_free(new); } @@ -2272,7 +2380,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or } struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, - struct sock *sk) + const struct sock *sk) { struct rtable *rt = __ip_route_output_key(net, flp4); @@ -2288,7 +2396,7 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, } EXPORT_SYMBOL_GPL(ip_route_output_flow); -static int rt_fill_info(struct net *net, __be32 dst, __be32 src, +static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, struct flowi4 *fl4, struct sk_buff *skb, u32 portid, u32 seq, int event, int nowait, unsigned int flags) { @@ -2308,8 +2416,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = fl4->flowi4_tos; - r->rtm_table = RT_TABLE_MAIN; - if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN)) + r->rtm_table = table_id; + if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; @@ -2414,6 +2522,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) int err; int mark; struct sk_buff *skb; + u32 table_id = RT_TABLE_MAIN; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy); if (err < 0) @@ -2449,6 +2558,9 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; + if (netif_index_is_l3_master(net, fl4.flowi4_oif)) + fl4.flowi4_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF; + if (iif) { struct net_device *dev; @@ -2483,7 +2595,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; - err = rt_fill_info(net, dst, src, &fl4, skb, + if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) + table_id = rt->rt_table_id; + + err = rt_fill_info(net, dst, src, table_id, &fl4, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0); if (err < 0) @@ -2504,7 +2619,6 @@ void ip_rt_multicast_event(struct in_device *in_dev) } #ifdef CONFIG_SYSCTL -static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; @@ -2742,6 +2856,10 @@ int __init ip_rt_init(void) prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents)); + ip_tstamps = kcalloc(IP_IDENTS_SZ, sizeof(*ip_tstamps), GFP_KERNEL); + if (!ip_tstamps) + panic("IP: failed to allocate ip_tstamps\n"); + for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);