[RFC PATCH v2 04/48] net: Declare MSG_SPLICE_PAGES internal sendmsg() flag

[David Howells]

Declare MSG_SPLICE_PAGES, an internal sendmsg() flag, that hints to a
network protocol that it should splice pages from the source iterator
rather than copying the data if it can.  This flag is added to a list that
is cleared by sendmsg and recvmsg syscalls on entry.

This is intended as a replacement for the ->sendpage() op, allowing a way
to splice in several multipage folios in one go.

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/linux/socket.h | 3 +++
 net/socket.c           | 7 +++++++
 2 files changed, 10 insertions(+)

diff --git a/include/linux/socket.h b/include/linux/socket.h
index 13c3a237b9c9..c2fa0f800999 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -327,6 +327,7 @@ struct ucred {
 					  */
 
 #define MSG_ZEROCOPY	0x4000000	/* Use user data in kernel path */
+#define MSG_SPLICE_PAGES 0x8000000	/* Splice the pages from the iterator in sendmsg() */
 #define MSG_FASTOPEN	0x20000000	/* Send data in TCP SYN */
 #define MSG_CMSG_CLOEXEC 0x40000000	/* Set close_on_exec for file
 					   descriptor received through
@@ -337,6 +338,8 @@ struct ucred {
 #define MSG_CMSG_COMPAT	0		/* We never have 32 bit fixups */
 #endif
 
+/* Flags to be cleared on entry by sendmsg, recvmsg, sendmmsg and recvmmsg syscalls */
+#define MSG_INTERNAL_FLAGS (MSG_SPLICE_PAGES)
 
 /* Setsockoptions(2) level. Thanks to BSD these must match IPPROTO_xxx */
 #define SOL_IP		0
diff --git a/net/socket.c b/net/socket.c
index 6bae8ce7059e..dfb912bbed62 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2139,6 +2139,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags,
 		msg.msg_name = (struct sockaddr *)&address;
 		msg.msg_namelen = addr_len;
 	}
+	flags &= ~MSG_INTERNAL_FLAGS;
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	msg.msg_flags = flags;
@@ -2192,6 +2193,7 @@ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
 	if (!sock)
 		goto out;
 
+	flags &= ~MSG_INTERNAL_FLAGS;
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	err = sock_recvmsg(sock, &msg, flags);
@@ -2579,6 +2581,7 @@ long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
 
 	if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT))
 		return -EINVAL;
+	flags &= ~MSG_INTERNAL_FLAGS;
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (!sock)
@@ -2627,6 +2630,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 	entry = mmsg;
 	compat_entry = (struct compat_mmsghdr __user *)mmsg;
 	err = 0;
+	flags &= ~MSG_INTERNAL_FLAGS;
 	flags |= MSG_BATCH;
 
 	while (datagrams < vlen) {
@@ -2775,6 +2779,7 @@ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg,
 			struct user_msghdr __user *umsg,
 			struct sockaddr __user *uaddr, unsigned int flags)
 {
+	flags &= ~MSG_INTERNAL_FLAGS;
 	return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0);
 }
 
@@ -2787,6 +2792,7 @@ long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
 
 	if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT))
 		return -EINVAL;
+	flags &= ~MSG_INTERNAL_FLAGS;
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (!sock)
@@ -2839,6 +2845,7 @@ static int do_recvmmsg(int fd, struct mmsghdr __user *mmsg,
 			goto out_put;
 		}
 	}
+	flags &= ~MSG_INTERNAL_FLAGS;
 
 	entry = mmsg;
 	compat_entry = (struct compat_mmsghdr __user *)mmsg;