Merge branch 'splice-net-replace-sendpage-with-sendmsg-msg_splice_pages-part-1'

David Howells says:

====================
splice, net: Replace sendpage with sendmsg(MSG_SPLICE_PAGES), part 1

Here's the first tranche of patches towards providing a MSG_SPLICE_PAGES
internal sendmsg flag that is intended to replace the ->sendpage() op with
calls to sendmsg().  MSG_SPLICE_PAGES is a hint that tells the protocol
that it should splice the pages supplied if it can and copy them if not.

This will allow splice to pass multiple pages in a single call and allow
certain parts of higher protocols (e.g. sunrpc, iwarp) to pass an entire
message in one go rather than having to send them piecemeal.  This should
also make it easier to handle the splicing of multipage folios.

A helper, skb_splice_from_iter() is provided to do the work of splicing or
copying data from an iterator.  If a page is determined to be unspliceable
(such as being in the slab), then the helper will give an error.

Note that this facility is not made available to userspace and does not
provide any sort of callback.

This set consists of the following parts:

 (1) Define the MSG_SPLICE_PAGES flag and prevent sys_sendmsg() from being
     able to set it.

 (2) Add an extra argument to skb_append_pagefrags() so that something
     other than MAX_SKB_FRAGS can be used (sysctl_max_skb_frags for
     example).

 (3) Add the skb_splice_from_iter() helper to handle splicing pages into
     skbuffs for MSG_SPLICE_PAGES that can be shared by TCP, IP/UDP and
     AF_UNIX.

 (4) Implement MSG_SPLICE_PAGES support in TCP.

 (5) Make do_tcp_sendpages() just wrap sendmsg() and then fold it in to its
     various callers.

 (6) Implement MSG_SPLICE_PAGES support in IP and make udp_sendpage() just
     a wrapper around sendmsg().

 (7) Implement MSG_SPLICE_PAGES support in IP6/UDP6.

 (8) Implement MSG_SPLICE_PAGES support in AF_UNIX.

 (9) Make AF_UNIX copy unspliceable pages.

Link: https://lore.kernel.org/r/20230316152618.711970-1-dhowells@redhat.com/ # v1
Link: https://lore.kernel.org/r/20230329141354.516864-1-dhowells@redhat.com/ # v2
Link: https://lore.kernel.org/r/20230331160914.1608208-1-dhowells@redhat.com/ # v3
Link: https://lore.kernel.org/r/20230405165339.3468808-1-dhowells@redhat.com/ # v4
Link: https://lore.kernel.org/r/20230406094245.3633290-1-dhowells@redhat.com/ # v5
Link: https://lore.kernel.org/r/20230411160902.4134381-1-dhowells@redhat.com/ # v6
Link: https://lore.kernel.org/r/20230515093345.396978-1-dhowells@redhat.com/ # v7
Link: https://lore.kernel.org/r/20230518113453.1350757-1-dhowells@redhat.com/ # v8
====================

Link: https://lore.kernel.org/r/20230522121125.2595254-1-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 40 insertions, 143 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index cc695c9f09ec..115436ce1f8a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -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)
 {
@@ -2200,19 +2182,25 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 	while (sent < len) {
 		size = len - sent;
 
-		/* Keep two messages in the pipe so it schedules better */
-		size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64);
+		if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {
+			skb = sock_alloc_send_pskb(sk, 0, 0,
+						   msg->msg_flags & MSG_DONTWAIT,
+						   &err, 0);
+		} else {
+			/* Keep two messages in the pipe so it schedules better */
+			size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64);
 
-		/* allow fallback to order-0 allocations */
-		size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ);
+			/* allow fallback to order-0 allocations */
+			size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ);
 
-		data_len = max_t(int, 0, size - SKB_MAX_HEAD(0));
+			data_len = max_t(int, 0, size - SKB_MAX_HEAD(0));
 
-		data_len = min_t(size_t, size, PAGE_ALIGN(data_len));
+			data_len = min_t(size_t, size, PAGE_ALIGN(data_len));
 
-		skb = sock_alloc_send_pskb(sk, size - data_len, data_len,
-					   msg->msg_flags & MSG_DONTWAIT, &err,
-					   get_order(UNIX_SKB_FRAGS_SZ));
+			skb = sock_alloc_send_pskb(sk, size - data_len, data_len,
+						   msg->msg_flags & MSG_DONTWAIT, &err,
+						   get_order(UNIX_SKB_FRAGS_SZ));
+		}
 		if (!skb)
 			goto out_err;
 
@@ -2224,13 +2212,24 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		}
 		fds_sent = true;
 
-		skb_put(skb, size - data_len);
-		skb->data_len = data_len;
-		skb->len = size;
-		err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
-		if (err) {
-			kfree_skb(skb);
-			goto out_err;
+		if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {
+			err = skb_splice_from_iter(skb, &msg->msg_iter, size,
+						   sk->sk_allocation);
+			if (err < 0) {
+				kfree_skb(skb);
+				goto out_err;
+			}
+			size = err;
+			refcount_add(size, &sk->sk_wmem_alloc);
+		} else {
+			skb_put(skb, size - data_len);
+			skb->data_len = data_len;
+			skb->len = size;
+			err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
+			if (err) {
+				kfree_skb(skb);
+				goto out_err;
+			}
 		}
 
 		unix_state_lock(other);
@@ -2275,117 +2274,15 @@ out_err:
 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;
-	}
-
-	if (sk->sk_shutdown & SEND_SHUTDOWN) {
-		err = -EPIPE;
-		send_sigpipe = true;
-		goto err_unlock;
-	}
-
-	unix_state_lock(other);
-
-	if (sock_flag(other, SOCK_DEAD) ||
-	    other->sk_shutdown & RCV_SHUTDOWN) {
-		err = -EPIPE;
-		send_sigpipe = true;
-		goto err_state_unlock;
-	}
+	struct bio_vec bvec;
+	struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES };
 
-	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 (flags & MSG_SENDPAGE_NOTLAST)
+		msg.msg_flags |= MSG_MORE;
 
-	if (skb_append_pagefrags(skb, page, offset, size)) {
-		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,