Merge branch 'inet-exceptions-less-predictable'

Eric Dumazet says:

====================
inet: make exception handling less predictible

This second round of patches is addressing Keyu Man recommendations
to make linux hosts more robust against a class of brute force attacks.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 34 insertions, 17 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 1e3b187970708..1b6c8fad62772 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -587,18 +587,25 @@ static void fnhe_flush_routes(struct fib_nh_exception *fnhe)
 	}
 }
 
-static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash)
+static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash)
 {
-	struct fib_nh_exception *fnhe, *oldest;
+	struct fib_nh_exception __rcu **fnhe_p, **oldest_p;
+	struct fib_nh_exception *fnhe, *oldest = NULL;
 
-	oldest = rcu_dereference(hash->chain);
-	for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe;
-	     fnhe = rcu_dereference(fnhe->fnhe_next)) {
-		if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp))
+	for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) {
+		fnhe = rcu_dereference_protected(*fnhe_p,
+						 lockdep_is_held(&fnhe_lock));
+		if (!fnhe)
+			break;
+		if (!oldest ||
+		    time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) {
 			oldest = fnhe;
+			oldest_p = fnhe_p;
+		}
 	}
 	fnhe_flush_routes(oldest);
-	return oldest;
+	*oldest_p = oldest->fnhe_next;
+	kfree_rcu(oldest, rcu);
 }
 
 static u32 fnhe_hashfun(__be32 daddr)
@@ -677,16 +684,21 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
 		if (rt)
 			fill_route_from_fnhe(rt, fnhe);
 	} else {
-		if (depth > FNHE_RECLAIM_DEPTH)
-			fnhe = fnhe_oldest(hash);
-		else {
-			fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC);
-			if (!fnhe)
-				goto out_unlock;
-
-			fnhe->fnhe_next = hash->chain;
-			rcu_assign_pointer(hash->chain, fnhe);
+		/* Randomize max depth to avoid some side channels attacks. */
+		int max_depth = FNHE_RECLAIM_DEPTH +
+				prandom_u32_max(FNHE_RECLAIM_DEPTH);
+
+		while (depth > max_depth) {
+			fnhe_remove_oldest(hash);
+			depth--;
 		}
+
+		fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC);
+		if (!fnhe)
+			goto out_unlock;
+
+		fnhe->fnhe_next = hash->chain;
+
 		fnhe->fnhe_genid = genid;
 		fnhe->fnhe_daddr = daddr;
 		fnhe->fnhe_gw = gw;
@@ -694,6 +706,8 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
 		fnhe->fnhe_mtu_locked = lock;
 		fnhe->fnhe_expires = max(1UL, expires);
 
+		rcu_assign_pointer(hash->chain, fnhe);
+
 		/* Exception created; mark the cached routes for the nexthop
 		 * stale, so anyone caching it rechecks if this exception
 		 * applies to them.
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f34137d5bf859..dbc2240239777 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1657,6 +1657,7 @@ static int rt6_insert_exception(struct rt6_info *nrt,
 	struct in6_addr *src_key = NULL;
 	struct rt6_exception *rt6_ex;
 	struct fib6_nh *nh = res->nh;
+	int max_depth;
 	int err = 0;
 
 	spin_lock_bh(&rt6_exception_lock);
@@ -1711,7 +1712,9 @@ static int rt6_insert_exception(struct rt6_info *nrt,
 	bucket->depth++;
 	net->ipv6.rt6_stats->fib_rt_cache++;
 
-	if (bucket->depth > FIB6_MAX_DEPTH)
+	/* Randomize max depth to avoid some side channels attacks. */
+	max_depth = FIB6_MAX_DEPTH + prandom_u32_max(FIB6_MAX_DEPTH);
+	while (bucket->depth > max_depth)
 		rt6_exception_remove_oldest(bucket);
 
 out: