Re: [Patch net] kcm: fix a race condition in kcm_recvmsg()

[Cong Wang <xiyou.wangcong@gmail.com>]

On Sat, Oct 22, 2022 at 07:30:44PM -0700, Cong Wang wrote:
> From: Cong Wang <cong.wang@bytedance.com>
> 
> sk->sk_receive_queue is protected by skb queue lock, but for KCM
> sockets its RX path takes mux->rx_lock to protect more than just
> skb queue, so grabbing skb queue lock is not necessary when
> mux->rx_lock is already held. But kcm_recvmsg() still only grabs
> the skb queue lock, so race conditions still exist.
> 
> Close this race condition by taking mux->rx_lock in kcm_recvmsg()
> too. This way is much simpler than enforcing skb queue lock
> everywhere.
> 

After a second thought, this actually could introduce a performance
regression as struct kcm_mux can be shared by multiple KCM sockets.

So, I am afraid we have to use the skb queue lock, fortunately I found
an easier way (comparing to Paolo's) to solve the skb peek race.

Zhengchao, could you please test the following patch?

Thanks!

---------------->

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index a5004228111d..890a2423f559 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -222,7 +222,7 @@ static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head)
 	struct sk_buff *skb;
 	struct kcm_sock *kcm;
 
-	while ((skb = __skb_dequeue(head))) {
+	while ((skb = skb_dequeue(head))) {
 		/* Reset destructor to avoid calling kcm_rcv_ready */
 		skb->destructor = sock_rfree;
 		skb_orphan(skb);
@@ -1085,53 +1085,17 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	return err;
 }
 
-static struct sk_buff *kcm_wait_data(struct sock *sk, int flags,
-				     long timeo, int *err)
-{
-	struct sk_buff *skb;
-
-	while (!(skb = skb_peek(&sk->sk_receive_queue))) {
-		if (sk->sk_err) {
-			*err = sock_error(sk);
-			return NULL;
-		}
-
-		if (sock_flag(sk, SOCK_DONE))
-			return NULL;
-
-		if ((flags & MSG_DONTWAIT) || !timeo) {
-			*err = -EAGAIN;
-			return NULL;
-		}
-
-		sk_wait_data(sk, &timeo, NULL);
-
-		/* Handle signals */
-		if (signal_pending(current)) {
-			*err = sock_intr_errno(timeo);
-			return NULL;
-		}
-	}
-
-	return skb;
-}
-
 static int kcm_recvmsg(struct socket *sock, struct msghdr *msg,
 		       size_t len, int flags)
 {
 	struct sock *sk = sock->sk;
 	struct kcm_sock *kcm = kcm_sk(sk);
 	int err = 0;
-	long timeo;
 	struct strp_msg *stm;
 	int copied = 0;
 	struct sk_buff *skb;
 
-	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
-
-	lock_sock(sk);
-
-	skb = kcm_wait_data(sk, flags, timeo, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto out;
 
@@ -1162,14 +1126,11 @@ static int kcm_recvmsg(struct socket *sock, struct msghdr *msg,
 			/* Finished with message */
 			msg->msg_flags |= MSG_EOR;
 			KCM_STATS_INCR(kcm->stats.rx_msgs);
-			skb_unlink(skb, &sk->sk_receive_queue);
-			kfree_skb(skb);
 		}
 	}
 
 out:
-	release_sock(sk);
-
+	skb_free_datagram(sk, skb);
 	return copied ? : err;
 }
 
@@ -1179,7 +1140,6 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos,
 {
 	struct sock *sk = sock->sk;
 	struct kcm_sock *kcm = kcm_sk(sk);
-	long timeo;
 	struct strp_msg *stm;
 	int err = 0;
 	ssize_t copied;
@@ -1187,11 +1147,7 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos,
 
 	/* Only support splice for SOCKSEQPACKET */
 
-	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
-
-	lock_sock(sk);
-
-	skb = kcm_wait_data(sk, flags, timeo, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto err_out;
 
@@ -1219,13 +1175,11 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos,
 	 * finish reading the message.
 	 */
 
-	release_sock(sk);
-
+	skb_free_datagram(sk, skb);
 	return copied;
 
 err_out:
-	release_sock(sk);
-
+	skb_free_datagram(sk, skb);
 	return err;
 }