ipv6: prevent infinite loop in rt6_nlmsg_size()

While testing prior patch, I was able to trigger
an infinite loop in rt6_nlmsg_size() in the following place:

list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
			fib6_siblings) {
	rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
}

This is because fib6_del_route() and fib6_add_rt2node()
uses list_del_rcu(), which can confuse rcu readers,
because they might no longer see the head of the list.

Restart the loop if f6i->fib6_nsiblings is zero.

Fixes: d9ccb18 ("ipv6: Fix soft lockups in fib6_select_path under high next hop churn")
Signed-off-by: Eric Dumazet <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: edumazet

net/ipv6/ip6_fib.c

@@ -1265,7 +1265,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 							 &rt->fib6_siblings,
 							 fib6_siblings)
 					sibling->fib6_nsiblings--;
-				rt->fib6_nsiblings = 0;
+				WRITE_ONCE(rt->fib6_nsiblings, 0);
 				list_del_rcu(&rt->fib6_siblings);
 				rcu_read_lock();
 				rt6_multipath_rebalance(next_sibling);
@@ -2015,7 +2015,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 		list_for_each_entry_safe(sibling, next_sibling,
 					 &rt->fib6_siblings, fib6_siblings)
 			sibling->fib6_nsiblings--;
-		rt->fib6_nsiblings = 0;
+		WRITE_ONCE(rt->fib6_nsiblings, 0);
 		list_del_rcu(&rt->fib6_siblings);
 		rt6_multipath_rebalance(next_sibling);
 	}

net/ipv6/route.c

@@ -5670,32 +5670,34 @@ static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg)
 
 static size_t rt6_nlmsg_size(struct fib6_info *f6i)
 {
+	struct fib6_info *sibling;
+	struct fib6_nh *nh;
 	int nexthop_len;
 
 	if (f6i->nh) {
 		nexthop_len = nla_total_size(4); /* RTA_NH_ID */
 		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
 					 &nexthop_len);
-	} else {
-		struct fib6_nh *nh = f6i->fib6_nh;
-		struct fib6_info *sibling;
-
-		nexthop_len = 0;
-		if (f6i->fib6_nsiblings) {
-			rt6_nh_nlmsg_size(nh, &nexthop_len);
-
-			rcu_read_lock();
+		goto common;
+	}
 
-			list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
-						fib6_siblings) {
-				rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
-			}
+	rcu_read_lock();
+retry:
+	nh = f6i->fib6_nh;
+	nexthop_len = 0;
+	if (READ_ONCE(f6i->fib6_nsiblings)) {
+		rt6_nh_nlmsg_size(nh, &nexthop_len);
 
-			rcu_read_unlock();
+		list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
+					fib6_siblings) {
+			rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
+			if (!READ_ONCE(f6i->fib6_nsiblings))
+				goto retry;
 		}
-		nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
 	}
-
+	rcu_read_unlock();
+	nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
+common:
 	return NLMSG_ALIGN(sizeof(struct rtmsg))
 	       + nla_total_size(16) /* RTA_SRC */
 	       + nla_total_size(16) /* RTA_DST */