[PATCH net-next v5 13/19] ip, udp: Support MSG_SPLICE_PAGES

[David Howells]

Make IP/UDP sendmsg() support MSG_SPLICE_PAGES.  This causes pages to be
spliced from the source iterator.

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

Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
cc: Willem de Bruijn <willemdebruijn.kernel@xxxxxxxxx>
cc: David Ahern <dsahern@xxxxxxxxxx>
cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
cc: Eric Dumazet <edumazet@xxxxxxxxxx>
cc: Jakub Kicinski <kuba@xxxxxxxxxx>
cc: Paolo Abeni <pabeni@xxxxxxxxxx>
cc: Jens Axboe <axboe@xxxxxxxxx>
cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
cc: netdev@xxxxxxxxxxxxxxx
---
 net/ipv4/ip_output.c | 47 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 22a90a9392eb..c6c318eb3d37 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -957,6 +957,41 @@ csum_page(struct page *page, int offset, int copy)
 	return csum;
 }
 
+/*
+ * Add (or copy) data pages for MSG_SPLICE_PAGES.
+ */
+static int __ip_splice_pages(struct sock *sk, struct sk_buff *skb,
+			     void *from, int *pcopy)
+{
+	struct msghdr *msg = from;
+	struct page *page = NULL, **pages = &page;
+	ssize_t copy = *pcopy;
+	size_t off;
+	int err;
+
+	copy = iov_iter_extract_pages(&msg->msg_iter, &pages, copy, 1, 0, &off);
+	if (copy <= 0)
+		return copy ?: -EIO;
+
+	err = skb_append_pagefrags(skb, page, off, copy);
+	if (err < 0) {
+		iov_iter_revert(&msg->msg_iter, copy);
+		return err;
+	}
+
+	if (skb->ip_summed == CHECKSUM_NONE) {
+		__wsum csum;
+
+		csum = csum_page(page, off, copy);
+		skb->csum = csum_block_add(skb->csum, csum, skb->len);
+	}
+
+	skb_len_add(skb, copy);
+	refcount_add(copy, &sk->sk_wmem_alloc);
+	*pcopy = copy;
+	return 0;
+}
+
 static int __ip_append_data(struct sock *sk,
 			    struct flowi4 *fl4,
 			    struct sk_buff_head *queue,
@@ -1048,6 +1083,14 @@ static int __ip_append_data(struct sock *sk,
 				skb_zcopy_set(skb, uarg, &extra_uref);
 			}
 		}
+	} else if ((flags & MSG_SPLICE_PAGES) && length) {
+		if (inet->hdrincl)
+			return -EPERM;
+		if (rt->dst.dev->features & NETIF_F_SG)
+			/* We need an empty buffer to attach stuff to */
+			paged = true;
+		else
+			flags &= ~MSG_SPLICE_PAGES;
 	}
 
 	cork->length += length;
@@ -1207,6 +1250,10 @@ static int __ip_append_data(struct sock *sk,
 				err = -EFAULT;
 				goto error;
 			}
+		} else if (flags & MSG_SPLICE_PAGES) {
+			err = __ip_splice_pages(sk, skb, from, &copy);
+			if (err < 0)
+				goto error;
 		} else if (!zc) {
 			int i = skb_shinfo(skb)->nr_frags;