socket, bpf: fix possible use after free

Starting from linux-4.4, 3WHS no longer takes the listener lock.

Since this time, we might hit a use-after-free in sk_filter_charge(),
if the filter we got in the memcpy() of the listener content
just happened to be replaced by a thread changing listener BPF filter.

To fix this, we need to make sure the filter refcount is not already
zero before incrementing it again.

Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/core/filter.c b/net/core/filter.c
index 82edad58d066857aeee562661098effa3b3e6961..74b8c91fb5f4461da58c73568976bc9834c4612b 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -989,10 +989,14 @@ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 
 bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
-       bool ret = __sk_filter_charge(sk, fp);
-       if (ret)
-               refcount_inc(&fp->refcnt);
-       return ret;
+       if (!refcount_inc_not_zero(&fp->refcnt))
+               return false;
+
+       if (!__sk_filter_charge(sk, fp)) {
+               sk_filter_release(fp);
+               return false;
+       }
+       return true;
 }
 
 static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)

diff --git a/net/core/sock.c b/net/core/sock.c
index 7d55c05f449d306b43fd850a61ce8ffd44174f7f..23953b741a41fbcf4a6ffb0dd5bf05bd5266b99d 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1684,13 +1684,16 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 
                sock_reset_flag(newsk, SOCK_DONE);
 
-               filter = rcu_dereference_protected(newsk->sk_filter, 1);
+               rcu_read_lock();
+               filter = rcu_dereference(sk->sk_filter);
                if (filter != NULL)
                        /* though it's an empty new sock, the charging may fail
                         * if sysctl_optmem_max was changed between creation of
                         * original socket and cloning
                         */
                        is_charged = sk_filter_charge(newsk, filter);
+               RCU_INIT_POINTER(newsk->sk_filter, filter);
+               rcu_read_unlock();
 
                if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
                        /* We need to make sure that we don't uncharge the new