1 files changed, 52 insertions, 53 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1f4b935a0e57..219701caba1e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -87,7 +87,8 @@ struct dst_entry	*ip6_dst_check(struct dst_entry *dst, u32 cookie);
 static unsigned int	 ip6_default_advmss(const struct dst_entry *dst);
 INDIRECT_CALLABLE_SCOPE
 unsigned int		ip6_mtu(const struct dst_entry *dst);
-static struct dst_entry *ip6_negative_advice(struct dst_entry *);
+static void		ip6_negative_advice(struct sock *sk,
+					    struct dst_entry *dst);
 static void		ip6_dst_destroy(struct dst_entry *);
 static void		ip6_dst_ifdown(struct dst_entry *,
 				       struct net_device *dev);
@@ -130,7 +131,6 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
 struct uncached_list {
 	spinlock_t		lock;
 	struct list_head	head;
-	struct list_head	quarantine;
 };
 
 static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list);
@@ -188,8 +188,7 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev)
 				handled = true;
 			}
 			if (handled)
-				list_move(&rt->dst.rt_uncached,
-					  &ul->quarantine);
+				list_del_init(&rt->dst.rt_uncached);
 		}
 		spin_unlock_bh(&ul->lock);
 	}
@@ -226,7 +225,7 @@ static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst,
 					      struct sk_buff *skb,
 					      const void *daddr)
 {
-	const struct rt6_info *rt = container_of(dst, struct rt6_info, dst);
+	const struct rt6_info *rt = dst_rt6_info(dst);
 
 	return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any),
 				dst->dev, skb, daddr);
@@ -234,8 +233,8 @@ static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst,
 
 static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr)
 {
+	const struct rt6_info *rt = dst_rt6_info(dst);
 	struct net_device *dev = dst->dev;
-	struct rt6_info *rt = (struct rt6_info *)dst;
 
 	daddr = choose_neigh_daddr(rt6_nexthop(rt, &in6addr_any), NULL, daddr);
 	if (!daddr)
@@ -354,7 +353,7 @@ EXPORT_SYMBOL(ip6_dst_alloc);
 
 static void ip6_dst_destroy(struct dst_entry *dst)
 {
-	struct rt6_info *rt = (struct rt6_info *)dst;
+	struct rt6_info *rt = dst_rt6_info(dst);
 	struct fib6_info *from;
 	struct inet6_dev *idev;
 
@@ -367,13 +366,13 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 		in6_dev_put(idev);
 	}
 
-	from = xchg((__force struct fib6_info **)&rt->from, NULL);
+	from = unrcu_pointer(xchg(&rt->from, NULL));
 	fib6_info_release(from);
 }
 
 static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
 {
-	struct rt6_info *rt = (struct rt6_info *)dst;
+	struct rt6_info *rt = dst_rt6_info(dst);
 	struct inet6_dev *idev = rt->rt6i_idev;
 
 	if (idev && idev->dev != blackhole_netdev) {
@@ -637,6 +636,8 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
 	rcu_read_lock();
 	last_probe = READ_ONCE(fib6_nh->last_probe);
 	idev = __in6_dev_get(dev);
+	if (!idev)
+		goto out;
 	neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
 	if (neigh) {
 		if (READ_ONCE(neigh->nud_state) & NUD_VALID)
@@ -1288,7 +1289,7 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
 
 	dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup);
 	if (dst->error == 0)
-		return (struct rt6_info *) dst;
+		return dst_rt6_info(dst);
 
 	dst_release(dst);
 
@@ -1408,6 +1409,7 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 		struct rt6_info *prev, **p;
 
 		p = this_cpu_ptr(res->nh->rt6i_pcpu);
+		/* Paired with READ_ONCE() in __fib6_drop_pcpu_from() */
 		prev = xchg(p, NULL);
 		if (prev) {
 			dst_dev_put(&prev->dst);
@@ -1436,7 +1438,7 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net,
 	if (res->f6i->fib6_destroying) {
 		struct fib6_info *from;
 
-		from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
+		from = unrcu_pointer(xchg(&pcpu_rt->from, NULL));
 		fib6_info_release(from);
 	}
 
@@ -1465,7 +1467,7 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
 	/* purge completely the exception to allow releasing the held resources:
 	 * some [sk] cache may keep the dst around for unlimited time
 	 */
-	from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL);
+	from = unrcu_pointer(xchg(&rt6_ex->rt6i->from, NULL));
 	fib6_info_release(from);
 	dst_dev_put(&rt6_ex->rt6i->dst);
 
@@ -2372,7 +2374,7 @@ static u32 rt6_multipath_custom_hash_outer(const struct net *net,
 		hash_keys.ports.dst = keys.ports.dst;
 
 	*p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION);
-	return flow_hash_from_keys(&hash_keys);
+	return fib_multipath_hash_from_keys(net, &hash_keys);
 }
 
 static u32 rt6_multipath_custom_hash_inner(const struct net *net,
@@ -2421,7 +2423,7 @@ static u32 rt6_multipath_custom_hash_inner(const struct net *net,
 	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT)
 		hash_keys.ports.dst = keys.ports.dst;
 
-	return flow_hash_from_keys(&hash_keys);
+	return fib_multipath_hash_from_keys(net, &hash_keys);
 }
 
 static u32 rt6_multipath_custom_hash_skb(const struct net *net,
@@ -2460,7 +2462,7 @@ static u32 rt6_multipath_custom_hash_fl6(const struct net *net,
 	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
 		hash_keys.ports.dst = fl6->fl6_dport;
 
-	return flow_hash_from_keys(&hash_keys);
+	return fib_multipath_hash_from_keys(net, &hash_keys);
 }
 
 /* if skb is set it will be used and fl6 can be NULL */
@@ -2482,7 +2484,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 			hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
 			hash_keys.basic.ip_proto = fl6->flowi6_proto;
 		}
-		mhash = flow_hash_from_keys(&hash_keys);
+		mhash = fib_multipath_hash_from_keys(net, &hash_keys);
 		break;
 	case 1:
 		if (skb) {
@@ -2514,7 +2516,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 			hash_keys.ports.dst = fl6->fl6_dport;
 			hash_keys.basic.ip_proto = fl6->flowi6_proto;
 		}
-		mhash = flow_hash_from_keys(&hash_keys);
+		mhash = fib_multipath_hash_from_keys(net, &hash_keys);
 		break;
 	case 2:
 		memset(&hash_keys, 0, sizeof(hash_keys));
@@ -2551,7 +2553,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 			hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
 			hash_keys.basic.ip_proto = fl6->flowi6_proto;
 		}
-		mhash = flow_hash_from_keys(&hash_keys);
+		mhash = fib_multipath_hash_from_keys(net, &hash_keys);
 		break;
 	case 3:
 		if (skb)
@@ -2647,7 +2649,7 @@ struct dst_entry *ip6_route_output_flags(struct net *net,
 
 	rcu_read_lock();
 	dst = ip6_route_output_flags_noref(net, sk, fl6, flags);
-	rt6 = (struct rt6_info *)dst;
+	rt6 = dst_rt6_info(dst);
 	/* For dst cached in uncached_list, refcnt is already taken. */
 	if (list_empty(&rt6->dst.rt_uncached) && !dst_hold_safe(dst)) {
 		dst = &net->ipv6.ip6_null_entry->dst;
@@ -2661,7 +2663,7 @@ EXPORT_SYMBOL_GPL(ip6_route_output_flags);
 
 struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
 {
-	struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig;
+	struct rt6_info *rt, *ort = dst_rt6_info(dst_orig);
 	struct net_device *loopback_dev = net->loopback_dev;
 	struct dst_entry *new = NULL;
 
@@ -2744,7 +2746,7 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst,
 	struct fib6_info *from;
 	struct rt6_info *rt;
 
-	rt = container_of(dst, struct rt6_info, dst);
+	rt = dst_rt6_info(dst);
 
 	if (rt->sernum)
 		return rt6_is_valid(rt) ? dst : NULL;
@@ -2770,24 +2772,24 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst,
 }
 EXPORT_INDIRECT_CALLABLE(ip6_dst_check);
 
-static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
+static void ip6_negative_advice(struct sock *sk,
+				struct dst_entry *dst)
 {
-	struct rt6_info *rt = (struct rt6_info *) dst;
+	struct rt6_info *rt = dst_rt6_info(dst);
 
-	if (rt) {
-		if (rt->rt6i_flags & RTF_CACHE) {
-			rcu_read_lock();
-			if (rt6_check_expired(rt)) {
-				rt6_remove_exception_rt(rt);
-				dst = NULL;
-			}
-			rcu_read_unlock();
-		} else {
-			dst_release(dst);
-			dst = NULL;
+	if (rt->rt6i_flags & RTF_CACHE) {
+		rcu_read_lock();
+		if (rt6_check_expired(rt)) {
+			/* counteract the dst_release() in sk_dst_reset() */
+			dst_hold(dst);
+			sk_dst_reset(sk);
+
+			rt6_remove_exception_rt(rt);
 		}
+		rcu_read_unlock();
+		return;
 	}
-	return dst;
+	sk_dst_reset(sk);
 }
 
 static void ip6_link_failure(struct sk_buff *skb)
@@ -2796,7 +2798,7 @@ static void ip6_link_failure(struct sk_buff *skb)
 
 	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
 
-	rt = (struct rt6_info *) skb_dst(skb);
+	rt = dst_rt6_info(skb_dst(skb));
 	if (rt) {
 		rcu_read_lock();
 		if (rt->rt6i_flags & RTF_CACHE) {
@@ -2852,7 +2854,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 				 bool confirm_neigh)
 {
 	const struct in6_addr *daddr, *saddr;
-	struct rt6_info *rt6 = (struct rt6_info *)dst;
+	struct rt6_info *rt6 = dst_rt6_info(dst);
 
 	/* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU)
 	 * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it.
@@ -3601,7 +3603,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 	if (!dev)
 		goto out;
 
-	if (idev->cnf.disable_ipv6) {
+	if (!idev || idev->cnf.disable_ipv6) {
 		NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device");
 		err = -EACCES;
 		goto out;
@@ -3760,7 +3762,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	if (!rt)
 		goto out;
 
-	rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len,
+	rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len,
 					       extack);
 	if (IS_ERR(rt->fib6_metrics)) {
 		err = PTR_ERR(rt->fib6_metrics);
@@ -4174,7 +4176,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 		}
 	}
 
-	rt = (struct rt6_info *) dst;
+	rt = dst_rt6_info(dst);
 	if (rt->rt6i_flags & RTF_REJECT) {
 		net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n");
 		return;
@@ -4445,7 +4447,7 @@ static void rtmsg_to_fib6_config(struct net *net,
 		.fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ?
 			 : RT6_TABLE_MAIN,
 		.fc_ifindex = rtmsg->rtmsg_ifindex,
-		.fc_metric = rtmsg->rtmsg_metric ? : IP6_RT_PRIO_USER,
+		.fc_metric = rtmsg->rtmsg_metric,
 		.fc_expires = rtmsg->rtmsg_info,
 		.fc_dst_len = rtmsg->rtmsg_dst_len,
 		.fc_src_len = rtmsg->rtmsg_src_len,
@@ -4475,6 +4477,9 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg)
 	rtnl_lock();
 	switch (cmd) {
 	case SIOCADDRT:
+		/* Only do the default setting of fc_metric in route adding */
+		if (cfg.fc_metric == 0)
+			cfg.fc_metric = IP6_RT_PRIO_USER;
 		err = ip6_route_add(&cfg, GFP_KERNEL, NULL);
 		break;
 	case SIOCDELRT:
@@ -5608,7 +5613,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			 int iif, int type, u32 portid, u32 seq,
 			 unsigned int flags)
 {
-	struct rt6_info *rt6 = (struct rt6_info *)dst;
+	struct rt6_info *rt6 = dst_rt6_info(dst);
 	struct rt6key *rt6_dst, *rt6_src;
 	u32 *pmetrics, table, rt6_flags;
 	unsigned char nh_flags = 0;
@@ -5682,7 +5687,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 				goto nla_put_failure;
 	} else if (dest) {
 		struct in6_addr saddr_buf;
-		if (ip6_route_get_saddr(net, rt, dest, 0, &saddr_buf) == 0 &&
+		if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 &&
 		    nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf))
 			goto nla_put_failure;
 	}
@@ -6111,7 +6116,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	}
 
 
-	rt = container_of(dst, struct rt6_info, dst);
+	rt = dst_rt6_info(dst);
 	if (rt->dst.error) {
 		err = rt->dst.error;
 		ip6_rt_put(rt);
@@ -6329,7 +6334,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v)
 
 #ifdef CONFIG_SYSCTL
 
-static int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
+static int ipv6_sysctl_rtcache_flush(const struct ctl_table *ctl, int write,
 			      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net;
@@ -6338,12 +6343,12 @@ static int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
 	if (!write)
 		return -EINVAL;
 
-	net = (struct net *)ctl->extra1;
-	delay = net->ipv6.sysctl.flush_delay;
 	ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
 	if (ret)
 		return ret;
 
+	net = (struct net *)ctl->extra1;
+	delay = net->ipv6.sysctl.flush_delay;
 	fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0);
 	return 0;
 }
@@ -6428,7 +6433,6 @@ static struct ctl_table ipv6_route_table_template[] = {
 		.extra1		=	SYSCTL_ZERO,
 		.extra2		=	SYSCTL_ONE,
 	},
-	{ }
 };
 
 struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
@@ -6452,10 +6456,6 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
 		table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss;
 		table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
 		table[10].data = &net->ipv6.sysctl.skip_notify_on_dev_down;
-
-		/* Don't export sysctls to unprivileged users */
-		if (net->user_ns != &init_user_ns)
-			table[1].procname = NULL;
 	}
 
 	return table;
@@ -6756,7 +6756,6 @@ int __init ip6_route_init(void)
 		struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
 
 		INIT_LIST_HEAD(&ul->head);
-		INIT_LIST_HEAD(&ul->quarantine);
 		spin_lock_init(&ul->lock);
 	}