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: Kuniyuki Iwashima --- net/unix/af_unix.c | 39 ++++++++++++++++++++++----------------- 1 file changed, 22 insertions(+), 17 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index be4c68876740..fa2081713dad 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2787,6 +2787,7 @@ 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; @@ -2794,30 +2795,34 @@ 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; - mutex_lock(&u->iolock); - skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err); - mutex_unlock(&u->iolock); - if (!skb) + err = sock_error(sk); + if (err) return err; -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (unlikely(skb == READ_ONCE(u->oob_skb))) { - bool drop = false; + mutex_lock(&u->iolock); + spin_lock(&queue->lock); - spin_lock(&sk->sk_receive_queue.lock); - if (likely(skb == u->oob_skb)) { - WRITE_ONCE(u->oob_skb, NULL); - drop = true; - } - spin_unlock(&sk->sk_receive_queue.lock); + skb = __skb_dequeue(queue); + if (!skb) { + spin_unlock(&queue->lock); + mutex_unlock(&u->iolock); + return -EAGAIN; + } - if (drop) { - kfree_skb_reason(skb, SKB_DROP_REASON_UNIX_SKIP_OOB); - return -EAGAIN; - } +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (skb == u->oob_skb) { + WRITE_ONCE(u->oob_skb, NULL); + spin_unlock(&queue->lock); + mutex_unlock(&u->iolock); + + 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); } -- 2.50.0.727.gbf7dc18ff4-goog