1 files changed, 79 insertions, 86 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index cb32ce250db0..c8bc9b4ac328 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -61,6 +61,7 @@
 #include <net/nexthop.h>
 #include <net/lwtunnel.h>
 #include <net/ip_tunnels.h>
+#include <net/l3mdev.h>
 
 #include <asm/uaccess.h>
 
@@ -86,9 +87,9 @@ static void		ip6_dst_ifdown(struct dst_entry *,
 static int		 ip6_dst_gc(struct dst_ops *ops);
 
 static int		ip6_pkt_discard(struct sk_buff *skb);
-static int		ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb);
+static int		ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 static int		ip6_pkt_prohibit(struct sk_buff *skb);
-static int		ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb);
+static int		ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 static void		ip6_link_failure(struct sk_buff *skb);
 static void		ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 					   struct sk_buff *skb, u32 mtu);
@@ -142,6 +143,9 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
 	struct net_device *loopback_dev = net->loopback_dev;
 	int cpu;
 
+	if (dev == loopback_dev)
+		return;
+
 	for_each_possible_cpu(cpu) {
 		struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
 		struct rt6_info *rt;
@@ -151,14 +155,12 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
 			struct inet6_dev *rt_idev = rt->rt6i_idev;
 			struct net_device *rt_dev = rt->dst.dev;
 
-			if (rt_idev && (rt_idev->dev == dev || !dev) &&
-			    rt_idev->dev != loopback_dev) {
+			if (rt_idev->dev == dev) {
 				rt->rt6i_idev = in6_dev_get(loopback_dev);
 				in6_dev_put(rt_idev);
 			}
 
-			if (rt_dev && (rt_dev == dev || !dev) &&
-			    rt_dev != loopback_dev) {
+			if (rt_dev == dev) {
 				rt->dst.dev = loopback_dev;
 				dev_hold(rt->dst.dev);
 				dev_put(rt_dev);
@@ -247,12 +249,6 @@ static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
 {
 }
 
-static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst,
-					 unsigned long old)
-{
-	return NULL;
-}
-
 static struct dst_ops ip6_dst_blackhole_ops = {
 	.family			=	AF_INET6,
 	.destroy		=	ip6_dst_destroy,
@@ -261,7 +257,7 @@ static struct dst_ops ip6_dst_blackhole_ops = {
 	.default_advmss		=	ip6_default_advmss,
 	.update_pmtu		=	ip6_rt_blackhole_update_pmtu,
 	.redirect		=	ip6_rt_blackhole_redirect,
-	.cow_metrics		=	ip6_rt_blackhole_cow_metrics,
+	.cow_metrics		=	dst_cow_metrics_generic,
 	.neigh_lookup		=	ip6_neigh_lookup,
 };
 
@@ -308,7 +304,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
 		.obsolete	= DST_OBSOLETE_FORCE_CHK,
 		.error		= -EINVAL,
 		.input		= dst_discard,
-		.output		= dst_discard_sk,
+		.output		= dst_discard_out,
 	},
 	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
 	.rt6i_protocol  = RTPROT_KERNEL,
@@ -318,6 +314,15 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
 
 #endif
 
+static void rt6_info_init(struct rt6_info *rt)
+{
+	struct dst_entry *dst = &rt->dst;
+
+	memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
+	INIT_LIST_HEAD(&rt->rt6i_siblings);
+	INIT_LIST_HEAD(&rt->rt6i_uncached);
+}
+
 /* allocate dst with ip6_dst_ops */
 static struct rt6_info *__ip6_dst_alloc(struct net *net,
 					struct net_device *dev,
@@ -326,13 +331,9 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net,
 	struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
 					0, DST_OBSOLETE_FORCE_CHK, flags);
 
-	if (rt) {
-		struct dst_entry *dst = &rt->dst;
+	if (rt)
+		rt6_info_init(rt);
 
-		memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
-		INIT_LIST_HEAD(&rt->rt6i_siblings);
-		INIT_LIST_HEAD(&rt->rt6i_uncached);
-	}
 	return rt;
 }
 
@@ -421,31 +422,7 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 static int rt6_info_hash_nhsfn(unsigned int candidate_count,
 			       const struct flowi6 *fl6)
 {
-	unsigned int val = fl6->flowi6_proto;
-
-	val ^= ipv6_addr_hash(&fl6->daddr);
-	val ^= ipv6_addr_hash(&fl6->saddr);
-
-	/* Work only if this not encapsulated */
-	switch (fl6->flowi6_proto) {
-	case IPPROTO_UDP:
-	case IPPROTO_TCP:
-	case IPPROTO_SCTP:
-		val ^= (__force u16)fl6->fl6_sport;
-		val ^= (__force u16)fl6->fl6_dport;
-		break;
-
-	case IPPROTO_ICMPV6:
-		val ^= (__force u16)fl6->fl6_icmp_type;
-		val ^= (__force u16)fl6->fl6_icmp_code;
-		break;
-	}
-	/* RFC6438 recommands to use flowlabel */
-	val ^= (__force u32)fl6->flowlabel;
-
-	/* Perhaps, we need to tune, this function? */
-	val = val ^ (val >> 7) ^ (val >> 12);
-	return val % candidate_count;
+	return get_hash_from_flowi6(fl6) % candidate_count;
 }
 
 static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
@@ -498,10 +475,10 @@ static inline struct rt6_info *rt6_device_match(struct net *net,
 			if (dev->flags & IFF_LOOPBACK) {
 				if (!sprt->rt6i_idev ||
 				    sprt->rt6i_idev->dev->ifindex != oif) {
-					if (flags & RT6_LOOKUP_F_IFACE && oif)
+					if (flags & RT6_LOOKUP_F_IFACE)
 						continue;
-					if (local && (!oif ||
-						      local->rt6i_idev->dev->ifindex == oif))
+					if (local &&
+					    local->rt6i_idev->dev->ifindex == oif)
 						continue;
 				}
 				local = sprt;
@@ -538,7 +515,7 @@ static void rt6_probe_deferred(struct work_struct *w)
 		container_of(w, struct __rt6_probe_work, work);
 
 	addrconf_addr_solict_mult(&work->target, &mcaddr);
-	ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL, NULL);
+	ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, NULL);
 	dev_put(work->dev);
 	kfree(work);
 }
@@ -1068,6 +1045,9 @@ static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 	saved_fn = fn;
 
+	if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
+		oif = 0;
+
 redo_rt6_select:
 	rt = rt6_select(fn, oif, strict);
 	if (rt->rt6i_nsiblings)
@@ -1165,7 +1145,7 @@ void ip6_route_input(struct sk_buff *skb)
 	int flags = RT6_LOOKUP_F_HAS_SADDR;
 	struct ip_tunnel_info *tun_info;
 	struct flowi6 fl6 = {
-		.flowi6_iif = skb->dev->ifindex,
+		.flowi6_iif = l3mdev_fib_oif(skb->dev),
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
 		.flowlabel = ip6_flowinfo(iph),
@@ -1189,15 +1169,22 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table
 struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
 				    struct flowi6 *fl6)
 {
+	struct dst_entry *dst;
 	int flags = 0;
+	bool any_src;
+
+	dst = l3mdev_rt6_dst_by_oif(net, fl6);
+	if (dst)
+		return dst;
 
 	fl6->flowi6_iif = LOOPBACK_IFINDEX;
 
+	any_src = ipv6_addr_any(&fl6->saddr);
 	if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) ||
-	    fl6->flowi6_oif)
+	    (fl6->flowi6_oif && any_src))
 		flags |= RT6_LOOKUP_F_IFACE;
 
-	if (!ipv6_addr_any(&fl6->saddr))
+	if (!any_src)
 		flags |= RT6_LOOKUP_F_HAS_SADDR;
 	else if (sk)
 		flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs);
@@ -1213,24 +1200,20 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 
 	rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, DST_OBSOLETE_NONE, 0);
 	if (rt) {
-		new = &rt->dst;
-
-		memset(new + 1, 0, sizeof(*rt) - sizeof(*new));
+		rt6_info_init(rt);
 
+		new = &rt->dst;
 		new->__use = 1;
 		new->input = dst_discard;
-		new->output = dst_discard_sk;
+		new->output = dst_discard_out;
 
-		if (dst_metrics_read_only(&ort->dst))
-			new->_metrics = ort->dst._metrics;
-		else
-			dst_copy_metrics(new, &ort->dst);
+		dst_copy_metrics(new, &ort->dst);
 		rt->rt6i_idev = ort->rt6i_idev;
 		if (rt->rt6i_idev)
 			in6_dev_hold(rt->rt6i_idev);
 
 		rt->rt6i_gateway = ort->rt6i_gateway;
-		rt->rt6i_flags = ort->rt6i_flags;
+		rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU;
 		rt->rt6i_metric = 0;
 
 		memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
@@ -1748,21 +1731,21 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
 	return -EINVAL;
 }
 
-int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret)
+static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
 {
-	int err;
 	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;
+	int err = -EINVAL;
 
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
-		return -EINVAL;
+		goto out;
 #ifndef CONFIG_IPV6_SUBTREES
 	if (cfg->fc_src_len)
-		return -EINVAL;
+		goto out;
 #endif
 	if (cfg->fc_ifindex) {
 		err = -ENODEV;
@@ -1877,7 +1860,7 @@ int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret)
 		switch (cfg->fc_type) {
 		case RTN_BLACKHOLE:
 			rt->dst.error = -EINVAL;
-			rt->dst.output = dst_discard_sk;
+			rt->dst.output = dst_discard_out;
 			rt->dst.input = dst_discard;
 			break;
 		case RTN_PROHIBIT:
@@ -1982,9 +1965,7 @@ install_route:
 
 	cfg->fc_nlinfo.nl_net = dev_net(dev);
 
-	*rt_ret = rt;
-
-	return 0;
+	return rt;
 out:
 	if (dev)
 		dev_put(dev);
@@ -1993,20 +1974,21 @@ out:
 	if (rt)
 		dst_free(&rt->dst);
 
-	*rt_ret = NULL;
-
-	return err;
+	return ERR_PTR(err);
 }
 
 int ip6_route_add(struct fib6_config *cfg)
 {
 	struct mx6_config mxc = { .mx = NULL, };
-	struct rt6_info *rt = NULL;
+	struct rt6_info *rt;
 	int err;
 
-	err = ip6_route_info_create(cfg, &rt);
-	if (err)
+	rt = ip6_route_info_create(cfg);
+	if (IS_ERR(rt)) {
+		err = PTR_ERR(rt);
+		rt = NULL;
 		goto out;
+	}
 
 	err = ip6_convert_metrics(&mxc, cfg);
 	if (err)
@@ -2098,7 +2080,6 @@ static int ip6_route_del(struct fib6_config *cfg)
 
 static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb)
 {
-	struct net *net = dev_net(skb->dev);
 	struct netevent_redirect netevent;
 	struct rt6_info *rt, *nrt = NULL;
 	struct ndisc_options ndopts;
@@ -2159,7 +2140,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	}
 
 	rt = (struct rt6_info *) dst;
-	if (rt == net->ipv6.ip6_null_entry) {
+	if (rt->rt6i_flags & RTF_REJECT) {
 		net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n");
 		return;
 	}
@@ -2288,7 +2269,6 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 					   unsigned int pref)
 {
 	struct fib6_config cfg = {
-		.fc_table	= RT6_TABLE_INFO,
 		.fc_metric	= IP6_RT_PRIO_USER,
 		.fc_ifindex	= ifindex,
 		.fc_dst_len	= prefixlen,
@@ -2299,6 +2279,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 		.fc_nlinfo.nl_net = net,
 	};
 
+	cfg.fc_table = l3mdev_fib_table_by_index(net, ifindex) ? : RT6_TABLE_INFO;
 	cfg.fc_dst = *prefix;
 	cfg.fc_gateway = *gwaddr;
 
@@ -2339,7 +2320,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
 				     unsigned int pref)
 {
 	struct fib6_config cfg = {
-		.fc_table	= RT6_TABLE_DFLT,
+		.fc_table	= l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT,
 		.fc_metric	= IP6_RT_PRIO_USER,
 		.fc_ifindex	= dev->ifindex,
 		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
@@ -2386,7 +2367,8 @@ static void rtmsg_to_fib6_config(struct net *net,
 {
 	memset(cfg, 0, sizeof(*cfg));
 
-	cfg->fc_table = RT6_TABLE_MAIN;
+	cfg->fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ?
+			 : RT6_TABLE_MAIN;
 	cfg->fc_ifindex = rtmsg->rtmsg_ifindex;
 	cfg->fc_metric = rtmsg->rtmsg_metric;
 	cfg->fc_expires = rtmsg->rtmsg_info;
@@ -2470,7 +2452,7 @@ 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 sock *sk, struct sk_buff *skb)
+static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	skb->dev = skb_dst(skb)->dev;
 	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
@@ -2481,7 +2463,7 @@ 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 sock *sk, struct sk_buff *skb)
+static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	skb->dev = skb_dst(skb)->dev;
 	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
@@ -2495,6 +2477,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 				    const struct in6_addr *addr,
 				    bool anycast)
 {
+	u32 tb_id;
 	struct net *net = dev_net(idev->dev);
 	struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev,
 					    DST_NOCOUNT);
@@ -2517,7 +2500,8 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 	rt->rt6i_gateway  = *addr;
 	rt->rt6i_dst.addr = *addr;
 	rt->rt6i_dst.plen = 128;
-	rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
+	tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL;
+	rt->rt6i_table = fib6_get_table(net, tb_id);
 	rt->dst.flags |= DST_NOCACHE;
 
 	atomic_set(&rt->dst.__refcnt, 1);
@@ -2622,7 +2606,8 @@ void rt6_ifdown(struct net *net, struct net_device *dev)
 
 	fib6_clean_all(net, fib6_ifdown, &adn);
 	icmp6_clean_all(fib6_ifdown, &adn);
-	rt6_uncached_list_flush_dev(net, dev);
+	if (dev)
+		rt6_uncached_list_flush_dev(net, dev);
 }
 
 struct rt6_mtu_change_arg {
@@ -2895,9 +2880,12 @@ static int ip6_route_multipath_add(struct fib6_config *cfg)
 				r_cfg.fc_encap_type = nla_get_u16(nla);
 		}
 
-		err = ip6_route_info_create(&r_cfg, &rt);
-		if (err)
+		rt = ip6_route_info_create(&r_cfg);
+		if (IS_ERR(rt)) {
+			err = PTR_ERR(rt);
+			rt = NULL;
 			goto cleanup;
+		}
 
 		err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
 		if (err) {
@@ -3276,6 +3264,11 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	} else {
 		fl6.flowi6_oif = oif;
 
+		if (netif_index_is_l3_master(net, oif)) {
+			fl6.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC |
+					   FLOWI_FLAG_SKIP_NH_OIF;
+		}
+
 		rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
 	}