[PATCH v3 07/55] tcp: Support MSG_SPLICE_PAGES

[David Howells]

Make TCP's 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: Eric Dumazet <edumazet@xxxxxxxxxx>
cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
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/tcp.c | 67 ++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 60 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 288693981b00..910b327c236e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1220,7 +1220,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 	int flags, err, copied = 0;
 	int mss_now = 0, size_goal, copied_syn = 0;
 	int process_backlog = 0;
-	bool zc = false;
+	int zc = 0;
 	long timeo;
 
 	flags = msg->msg_flags;
@@ -1231,17 +1231,22 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 		if (msg->msg_ubuf) {
 			uarg = msg->msg_ubuf;
 			net_zcopy_get(uarg);
-			zc = sk->sk_route_caps & NETIF_F_SG;
+			if (sk->sk_route_caps & NETIF_F_SG)
+				zc = 1;
 		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
 			uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb));
 			if (!uarg) {
 				err = -ENOBUFS;
 				goto out_err;
 			}
-			zc = sk->sk_route_caps & NETIF_F_SG;
-			if (!zc)
+			if (sk->sk_route_caps & NETIF_F_SG)
+				zc = 1;
+			else
 				uarg_to_msgzc(uarg)->zerocopy = 0;
 		}
+	} else if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES) && size) {
+		if (sk->sk_route_caps & NETIF_F_SG)
+			zc = 2;
 	}
 
 	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
@@ -1304,7 +1309,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 		goto do_error;
 
 	while (msg_data_left(msg)) {
-		int copy = 0;
+		ssize_t copy = 0;
 
 		skb = tcp_write_queue_tail(sk);
 		if (skb)
@@ -1345,7 +1350,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 		if (copy > msg_data_left(msg))
 			copy = msg_data_left(msg);
 
-		if (!zc) {
+		if (zc == 0) {
 			bool merge = true;
 			int i = skb_shinfo(skb)->nr_frags;
 			struct page_frag *pfrag = sk_page_frag(sk);
@@ -1390,7 +1395,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 				page_ref_inc(pfrag->page);
 			}
 			pfrag->offset += copy;
-		} else {
+		} else if (zc == 1)  {
 			/* First append to a fragless skb builds initial
 			 * pure zerocopy skb
 			 */
@@ -1411,6 +1416,54 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 			if (err < 0)
 				goto do_error;
 			copy = err;
+		} else if (zc == 2) {
+			/* Splice in data. */
+			struct page *page = NULL, **pages = &page;
+			size_t off = 0, part;
+			bool can_coalesce;
+			int i = skb_shinfo(skb)->nr_frags;
+
+			copy = iov_iter_extract_pages(&msg->msg_iter, &pages,
+						      copy, 1, 0, &off);
+			if (copy <= 0) {
+				err = copy ?: -EIO;
+				goto do_error;
+			}
+
+			can_coalesce = skb_can_coalesce(skb, i, page, off);
+			if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
+				tcp_mark_push(tp, skb);
+				iov_iter_revert(&msg->msg_iter, copy);
+				goto new_segment;
+			}
+			if (tcp_downgrade_zcopy_pure(sk, skb)) {
+				iov_iter_revert(&msg->msg_iter, copy);
+				goto wait_for_space;
+			}
+
+			part = tcp_wmem_schedule(sk, copy);
+			iov_iter_revert(&msg->msg_iter, copy - part);
+			if (!part)
+				goto wait_for_space;
+			copy = part;
+
+			if (can_coalesce) {
+				skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+			} else {
+				get_page(page);
+				skb_fill_page_desc_noacc(skb, i, page, off, copy);
+			}
+			page = NULL;
+
+			if (!(flags & MSG_NO_SHARED_FRAGS))
+				skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
+
+			skb->len += copy;
+			skb->data_len += copy;
+			skb->truesize += copy;
+			sk_wmem_queued_add(sk, copy);
+			sk_mem_charge(sk, copy);
+
 		}
 
 		if (!copied)