[PATCH bpf v3 1/2] bpf: Unconditionally take socket references in lookup helpers

Lookup helpers gate the reference acquisition on sk_is_refcounted(), and
the release side re-evaluates the same check. An established socket can be
refcounted at acquire time and later gain SOCK_RCU_FREE via
connect(AF_UNSPEC) + listen() before release. The release re-check then
sees sk_is_refcounted() == false and skips the put, leaking the reference.

Make acquire and release unconditional and symmetric: always take a
reference, always put it. Adapt sk_select_reuseport(). Drop the
misplaced/outdated comment above __bpf_skc_lookup().

Fixes: 6acc9b432e67 ("bpf: Add helper to retrieve socket in BPF")
Fixes: 64d85290d79c ("bpf: Allow bpf_map_lookup_elem for SOCKMAP and SOCKHASH")
Reported-by: Sashiko <[email protected]>
Closes: https://lore.kernel.org/bpf/[email protected]/
Signed-off-by: Michal Luczaj <[email protected]>
Reviewed-by: Emil Tsalapatis <[email protected]>
---
 net/core/filter.c   | 30 ++++++++++++++++++------------
 net/core/sock_map.c |  8 ++------
 2 files changed, 20 insertions(+), 18 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 61940e753552..66d83a198ea2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7205,12 +7205,17 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 		WARN_ONCE(1, "Found non-RCU, unreferenced socket!");
 		sk = NULL;
 	}
+
+	/*
+	 * Always take a reference, even if the lookup skipped one;
+	 * bpf_sk_release() always puts one.
+	 */
+	if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt))
+		sk = NULL;
+
 	return sk;
 }
 
-/* bpf_skc_lookup performs the core lookup for different types of sockets,
- * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE.
- */
 static struct sock *
 __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		 struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
@@ -7263,11 +7268,16 @@ bpf_sk_lookup_full_sk(struct sock *sk)
 	 */
 	if (sk2 != sk) {
 		sock_gen_put(sk);
-		/* Ensure there is no need to bump sk2 refcnt. */
 		if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) {
 			WARN_ONCE(1, "Found non-RCU, unreferenced socket!");
 			return NULL;
 		}
+		/*
+		 * sk2 is not refcounted, but take a reference anyway;
+		 * bpf_sk_release() puts.
+		 */
+		if (sk2 && !refcount_inc_not_zero(&sk2->sk_refcnt))
+			sk2 = NULL;
 		sk = sk2;
 	}
 
@@ -7448,7 +7458,7 @@ static const struct bpf_func_proto bpf_tc_sk_lookup_udp_proto = {
 
 BPF_CALL_1(bpf_sk_release, struct sock *, sk)
 {
-	if (sk && sk_is_refcounted(sk))
+	if (sk)
 		sock_gen_put(sk);
 	return 0;
 }
@@ -11736,11 +11746,13 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
 	bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY;
 	struct sock_reuseport *reuse;
 	struct sock *selected_sk;
-	int err;
+	int err = 0;
 
 	selected_sk = map->ops->map_lookup_elem(map, key);
 	if (!selected_sk)
 		return -ENOENT;
+	if (!is_sockarray)
+		sock_put(selected_sk);
 
 	reuse = rcu_dereference(selected_sk->sk_reuseport_cb);
 	if (!reuse) {
@@ -11770,13 +11782,7 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
 	}
 
 	reuse_kern->selected_sk = selected_sk;
-
-	return 0;
 error:
-	/* Lookup in sock_map can return TCP ESTABLISHED sockets. */
-	if (sk_is_refcounted(selected_sk))
-		sock_put(selected_sk);
-
 	return err;
 }
 
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index ca49bc7f8687..ae18dc4d60f9 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -390,9 +390,7 @@ static void *sock_map_lookup(struct bpf_map *map, void *key)
 	struct sock *sk;
 
 	sk = __sock_map_lookup_elem(map, *(u32 *)key);
-	if (!sk)
-		return NULL;
-	if (sk_is_refcounted(sk))
+	if (sk)
 		sock_hold(sk);
 	return sk;
 }
@@ -1216,9 +1214,7 @@ static void *sock_hash_lookup(struct bpf_map *map, void *key)
 	struct sock *sk;
 
 	sk = __sock_hash_lookup_elem(map, key);
-	if (!sk)
-		return NULL;
-	if (sk_is_refcounted(sk))
+	if (sk)
 		sock_hold(sk);
 	return sk;
 }

-- 
2.55.0