From:   David Howells <dhowells@redhat.com>
To:     Matthew Wilcox <willy@infradead.org>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>
Cc:     David Howells <dhowells@redhat.com>,
        Al Viro <viro@zeniv.linux.org.uk>,
        Christoph Hellwig <hch@infradead.org>,
        Jens Axboe <axboe@kernel.dk>, Jeff Layton <jlayton@kernel.org>,
        Christian Brauner <brauner@kernel.org>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        netdev@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [RFC PATCH 12/28] af_unix: Support MSG_SPLICE_PAGES
Date:   Thu, 16 Mar 2023 15:26:02 +0000
Message-Id: <20230316152618.711970-13-dhowells@redhat.com>
In-Reply-To: <20230316152618.711970-1-dhowells@redhat.com>
References: <20230316152618.711970-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Make AF_UNIX sendmsg() support MSG_SPLICE_PAGES, splicing in pages from the
source iterator if given and if ITER_BVEC and copying the data in
otherwise.

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

Signed-off-by: David Howells <dhowells@redhat.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: netdev@vger.kernel.org
---
 net/unix/af_unix.c | 84 +++++++++++++++++++++++++++++++++++++---------
 1 file changed, 68 insertions(+), 16 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 347122c3575e..6f3454db9c53 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2151,6 +2151,44 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 }
 #endif
 
+/*
+ * Extract pages from a BVEC-type iterator and add them to the socket buffer.
+ */
+static ssize_t unix_extract_bvec_to_skb(struct sk_buff *skb,
+					struct iov_iter *iter, ssize_t maxsize)
+{
+	const struct bio_vec *bv = iter->bvec;
+	unsigned long start = iter->iov_offset;
+	unsigned int i;
+	ssize_t ret = 0;
+
+	for (i = 0; i < iter->nr_segs; i++) {
+		size_t off, len;
+
+		len = bv[i].bv_len;
+		if (start >= len) {
+			start -= len;
+			continue;
+		}
+
+		len = min_t(size_t, maxsize, len - start);
+		off = bv[i].bv_offset + start;
+
+		if (skb_append_pagefrags(skb, bv->bv_page, off, len) < 0)
+			break;
+
+		ret += len;
+		maxsize -= len;
+		if (maxsize <= 0)
+			break;
+		start = 0;
+	}
+
+	if (ret > 0)
+		iov_iter_advance(iter, ret);
+	return ret;
+}
+
 static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 			       size_t len)
 {
@@ -2194,19 +2232,25 @@ 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;
 
@@ -2218,13 +2262,21 @@ 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)) {
+			size = unix_extract_bvec_to_skb(skb, &msg->msg_iter, size);
+			skb->data_len += size;
+			skb->len += size;
+			skb->truesize += size;
+			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);