Commit d0aac854 authored by Kuniyuki Iwashima's avatar Kuniyuki Iwashima Committed by Jakub Kicinski
Browse files

af_unix: Don't use skb_recv_datagram() in unix_stream_read_skb(). 



unix_stream_read_skb() calls skb_recv_datagram() with MSG_DONTWAIT,
which is mostly equivalent to sock_error(sk) + skb_dequeue().

In the following patch, we will add a new field to cache the number
of bytes in the receive queue.  Then, we want to avoid introducing
atomic ops in the fast path, so we will reuse the receive queue lock.

As a preparation for the change, let's not use skb_recv_datagram()
in unix_stream_read_skb().

Note that sock_error() is now moved out of the u->iolock mutex as
the mutex does not synchronise the peer's close() at all.

Signed-off-by: default avatarKuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250702223606.1054680-4-kuniyu@google.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 772f0104

net/unix/af_unix.c

+22 −17
Original line number Diff line number Diff line
@@ -2786,6 +2786,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, 


static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor)

{

	struct sk_buff_head *queue = &sk->sk_receive_queue;

	struct unix_sock *u = unix_sk(sk);

	struct sk_buff *skb;

	int err;
@@ -2793,30 +2794,34 @@ static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) 
	if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED))

		return -ENOTCONN;



	err = sock_error(sk);

	if (err)

		return err;



	mutex_lock(&u->iolock);

	skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err);

	spin_lock(&queue->lock);



	skb = __skb_dequeue(queue);

	if (!skb) {

		spin_unlock(&queue->lock);

		mutex_unlock(&u->iolock);

	if (!skb)

		return err;

		return -EAGAIN;

	}



#if IS_ENABLED(CONFIG_AF_UNIX_OOB)

	if (unlikely(skb == READ_ONCE(u->oob_skb))) {

		bool drop = false;



		spin_lock(&sk->sk_receive_queue.lock);

		if (likely(skb == u->oob_skb)) {

	if (skb == u->oob_skb) {

		WRITE_ONCE(u->oob_skb, NULL);

			drop = true;

		}

		spin_unlock(&sk->sk_receive_queue.lock);

		spin_unlock(&queue->lock);

		mutex_unlock(&u->iolock);



		if (drop) {

		kfree_skb_reason(skb, SKB_DROP_REASON_UNIX_SKIP_OOB);

		return -EAGAIN;

	}

	}

#endif



	spin_unlock(&queue->lock);

	mutex_unlock(&u->iolock);



	return recv_actor(sk, skb);

}