bpf: net: Avoid copying sk_user_data of reuseport_array during sk_clone

It makes little sense for copying sk_user_data of reuseport_array during
sk_clone_lock().  This patch reuses the SK_USER_DATA_NOCOPY bit introduced in
commit f1ff5ce2cd5e ("net, sk_msg: Clear sk_user_data pointer on clone if tagged").
It is used to mark the sk_user_data is not supposed to be copied to its clone.

Although the cloned sk's sk_user_data will not be used/freed in
bpf_sk_reuseport_detach(), this change can still allow the cloned
sk's sk_user_data to be used by some other means.

Freeing the reuseport_array's sk_user_data does not require a rcu grace
period.  Thus, the existing rcu_assign_sk_user_data_nocopy() is not
used.

Fixes: 5dc4c4b7d4e8 ("bpf: Introduce BPF_MAP_TYPE_REUSEPORT_SOCKARRAY")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20200709061104.4018798-1-kafai@fb.com

1 files changed, 9 insertions, 4 deletions

diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 21cde24386db..a95bc8d7e812 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -20,11 +20,14 @@ static struct reuseport_array *reuseport_array(struct bpf_map *map)
 /* The caller must hold the reuseport_lock */
 void bpf_sk_reuseport_detach(struct sock *sk)
 {
-	struct sock __rcu **socks;
+	uintptr_t sk_user_data;
 
 	write_lock_bh(&sk->sk_callback_lock);
-	socks = sk->sk_user_data;
-	if (socks) {
+	sk_user_data = (uintptr_t)sk->sk_user_data;
+	if (sk_user_data) {
+		struct sock __rcu **socks;
+
+		socks = (void *)(sk_user_data & SK_USER_DATA_PTRMASK);
 		WRITE_ONCE(sk->sk_user_data, NULL);
 		/*
 		 * Do not move this NULL assignment outside of
@@ -252,6 +255,7 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
 	struct sock *free_osk = NULL, *osk, *nsk;
 	struct sock_reuseport *reuse;
 	u32 index = *(u32 *)key;
+	uintptr_t sk_user_data;
 	struct socket *socket;
 	int err, fd;
 
@@ -305,7 +309,8 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
 	if (err)
 		goto put_file_unlock;
 
-	WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]);
+	sk_user_data = (uintptr_t)&array->ptrs[index] | SK_USER_DATA_NOCOPY;
+	WRITE_ONCE(nsk->sk_user_data, (void *)sk_user_data);
 	rcu_assign_pointer(array->ptrs[index], nsk);
 	free_osk = osk;
 	err = 0;