Commit 57d44a35 authored by David Howells's avatar David Howells Committed by Jakub Kicinski
Browse files

unix: Convert unix_stream_sendpage() to use MSG_SPLICE_PAGES 



Convert unix_stream_sendpage() to use sendmsg() with MSG_SPLICE_PAGES
rather than directly splicing in the pages itself.

This allows ->sendpage() to be replaced by something that can handle
multiple multipage folios in a single transaction.

Signed-off-by: default avatarDavid Howells <dhowells@redhat.com>
cc: Kuniyuki Iwashima <kuniyu@amazon.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent a0dbf5f8

net/unix/af_unix.c

+7 −127
Original line number Diff line number Diff line
@@ -1839,24 +1839,6 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock, 
	}

}



static int maybe_init_creds(struct scm_cookie *scm,

			    struct socket *socket,

			    const struct sock *other)

{

	int err;

	struct msghdr msg = { .msg_controllen = 0 };



	err = scm_send(socket, &msg, scm, false);

	if (err)

		return err;



	if (unix_passcred_enabled(socket, other)) {

		scm->pid = get_pid(task_tgid(current));

		current_uid_gid(&scm->creds.uid, &scm->creds.gid);

	}

	return err;

}



static bool unix_skb_scm_eq(struct sk_buff *skb,

			    struct scm_cookie *scm)

{
@@ -2292,117 +2274,15 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, 
static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,

				    int offset, size_t size, int flags)

{

	int err;

	bool send_sigpipe = false;

	bool init_scm = true;

	struct scm_cookie scm;

	struct sock *other, *sk = socket->sk;

	struct sk_buff *skb, *newskb = NULL, *tail = NULL;



	if (flags & MSG_OOB)

		return -EOPNOTSUPP;



	other = unix_peer(sk);

	if (!other || sk->sk_state != TCP_ESTABLISHED)

		return -ENOTCONN;



	if (false) {

alloc_skb:

		unix_state_unlock(other);

		mutex_unlock(&unix_sk(other)->iolock);

		newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,

					      &err, 0);

		if (!newskb)

			goto err;

	}



	/* we must acquire iolock as we modify already present

	 * skbs in the sk_receive_queue and mess with skb->len

	 */

	err = mutex_lock_interruptible(&unix_sk(other)->iolock);

	if (err) {

		err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;

		goto err;

	}

	struct bio_vec bvec;

	struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES };



	if (sk->sk_shutdown & SEND_SHUTDOWN) {

		err = -EPIPE;

		send_sigpipe = true;

		goto err_unlock;

	}



	unix_state_lock(other);

	if (flags & MSG_SENDPAGE_NOTLAST)

		msg.msg_flags |= MSG_MORE;



	if (sock_flag(other, SOCK_DEAD) ||

	    other->sk_shutdown & RCV_SHUTDOWN) {

		err = -EPIPE;

		send_sigpipe = true;

		goto err_state_unlock;

	}



	if (init_scm) {

		err = maybe_init_creds(&scm, socket, other);

		if (err)

			goto err_state_unlock;

		init_scm = false;

	}



	skb = skb_peek_tail(&other->sk_receive_queue);

	if (tail && tail == skb) {

		skb = newskb;

	} else if (!skb || !unix_skb_scm_eq(skb, &scm)) {

		if (newskb) {

			skb = newskb;

		} else {

			tail = skb;

			goto alloc_skb;

		}

	} else if (newskb) {

		/* this is fast path, we don't necessarily need to

		 * call to kfree_skb even though with newskb == NULL

		 * this - does no harm

		 */

		consume_skb(newskb);

		newskb = NULL;

	}



	if (skb_append_pagefrags(skb, page, offset, size, MAX_SKB_FRAGS)) {

		tail = skb;

		goto alloc_skb;

	}



	skb->len += size;

	skb->data_len += size;

	skb->truesize += size;

	refcount_add(size, &sk->sk_wmem_alloc);



	if (newskb) {

		err = unix_scm_to_skb(&scm, skb, false);

		if (err)

			goto err_state_unlock;

		spin_lock(&other->sk_receive_queue.lock);

		__skb_queue_tail(&other->sk_receive_queue, newskb);

		spin_unlock(&other->sk_receive_queue.lock);

	}



	unix_state_unlock(other);

	mutex_unlock(&unix_sk(other)->iolock);



	other->sk_data_ready(other);

	scm_destroy(&scm);

	return size;



err_state_unlock:

	unix_state_unlock(other);

err_unlock:

	mutex_unlock(&unix_sk(other)->iolock);

err:

	kfree_skb(newskb);

	if (send_sigpipe && !(flags & MSG_NOSIGNAL))

		send_sig(SIGPIPE, current, 0);

	if (!init_scm)

		scm_destroy(&scm);

	return err;

	bvec_set_page(&bvec, page, size, offset);

	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);

	return unix_stream_sendmsg(socket, &msg, size);

}



static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg,