[PATCH net-next v4 18/20] ip6, udp6: Support MSG_SPLICE_PAGES

[David Howells]

Make IP6/UDP6 sendmsg() support MSG_SPLICE_PAGES.  This causes pages to be
spliced from the source iterator if possible, copying the data if not.

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 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
---
 include/net/ip.h      |  1 +
 net/ipv4/ip_output.c  |  4 ++--
 net/ipv6/ip6_output.c | 12 ++++++++++++
 3 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 7627a4df893b..8a50341007bf 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -211,6 +211,7 @@ int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 		    __u8 tos);
 void ip_init(void);
+int __ip_splice_pages(struct sock *sk, struct sk_buff *skb, void *from, int *pcopy);
 int ip_append_data(struct sock *sk, struct flowi4 *fl4,
 		   int getfrag(void *from, char *to, int offset, int len,
 			       int odd, struct sk_buff *skb),
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e34c86b1b59a..241a78d82766 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -960,8 +960,7 @@ csum_page(struct page *page, int offset, int copy)
 /*
  * 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)
+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;
@@ -1010,6 +1009,7 @@ static int __ip_splice_pages(struct sock *sk, struct sk_buff *skb,
 	*pcopy = copy;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__ip_splice_pages);
 
 static int __ip_append_data(struct sock *sk,
 			    struct flowi4 *fl4,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 0b6140f0179d..82846d18cf22 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1589,6 +1589,14 @@ static int __ip6_append_data(struct sock *sk,
 				skb_zcopy_set(skb, uarg, &extra_uref);
 			}
 		}
+	} else if ((flags & MSG_SPLICE_PAGES) && length) {
+		if (inet_sk(sk)->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;
 	}
 
 	/*
@@ -1778,6 +1786,10 @@ static int __ip6_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;