[PATCH bpf v2 2/2] bpf: Unconditionally take socket references in lookup helpers

Michal Luczaj <[email protected]>
Newsgroups org.kernel.vger.netdev,org.kernel.vger.bpf,org.kernel.vger.linux-kernel
Message-ID <[email protected]>
Lookup helpers gate whether to acquire a socket reference on
sk_is_refcounted(), a check re-evaluated at release. An established socket
refcounted at acquire time can gain SOCK_RCU_FREE via
connect(AF_UNSPEC)+listen() before release runs; the release-side re-check
then reads sk_is_refcounted() == false and skips the put. The reference
leaks.

Make acquire and release unconditional and symmetric: always take a
reference, always put it. Adapt sk_select_reuseport().

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]>
---
TC bpf_sk_assign() has the same issue; it takes a reference only when
sk_is_refcounted() is true at assign time, but sock_pfree() (the skb
destructor it installs) re-checks sk_is_refcounted() independently at
release time. The same connect(AF_UNSPEC)+listen() transition leaks the
socket here too. I'd welcome suggestions on the right way to handle this.
---
 net/core/filter.c   | 27 ++++++++++++++++++---------
 net/core/sock_map.c |  4 ++--
 2 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index fede810ef37f..d71e069f669a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7032,6 +7032,14 @@ 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;
 }
 
@@ -7090,11 +7098,16 @@ 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 RCU-free, but take a reference anyway;
+		 * bpf_sk_release() puts.
+		 */
+		if (sk2 && !refcount_inc_not_zero(&sk2->sk_refcnt))
+			sk2 = NULL;
 		sk = sk2;
 	}
 
@@ -7279,7 +7292,7 @@ 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;
 }
@@ -11571,11 +11584,13 @@ 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) {
@@ -11605,13 +11620,7 @@ 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 9efbd8ca7db8..92a006fd3368 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -392,7 +392,7 @@ static void *sock_map_lookup(struct bpf_map *map, void *key)
 	sk = __sock_map_lookup_elem(map, *(u32 *)key);
 	if (!sk)
 		return NULL;
-	if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt))
+	if (!refcount_inc_not_zero(&sk->sk_refcnt))
 		return NULL;
 	return sk;
 }
@@ -1218,7 +1218,7 @@ static void *sock_hash_lookup(struct bpf_map *map, void *key)
 	sk = __sock_hash_lookup_elem(map, key);
 	if (!sk)
 		return NULL;
-	if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt))
+	if (!refcount_inc_not_zero(&sk->sk_refcnt))
 		return NULL;
 	return sk;
 }

-- 
2.55.0
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.