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 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 <[email protected]>
Reviewed-by: Willem de Bruijn <[email protected]>
cc: "David S. Miller" <[email protected]>
cc: Eric Dumazet <[email protected]>
cc: Jakub Kicinski <[email protected]>
cc: Paolo Abeni <[email protected]>
cc: Jens Axboe <[email protected]>
cc: Matthew Wilcox <[email protected]>
cc: [email protected]
cc: [email protected]
---
Notes:
ver #7)
- In ____sys_sendmsg(), clear internal flags before setting msg_flags.
- Clear internal flags in uring io_send{,_zc}().
include/linux/socket.h | 3 +++
io_uring/net.c | 2 ++
net/socket.c | 2 ++
3 files changed, 7 insertions(+)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 13c3a237b9c9..bd1cc3238851 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 and sendmmsg syscalls */
+#define MSG_INTERNAL_SENDMSG_FLAGS (MSG_SPLICE_PAGES)
/* Setsockoptions(2) level. Thanks to BSD these must match IPPROTO_xxx */
#define SOL_IP 0
diff --git a/io_uring/net.c b/io_uring/net.c
index 89e839013837..f7cbb3c7a575 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -389,6 +389,7 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
if (flags & MSG_WAITALL)
min_ret = iov_iter_count(&msg.msg_iter);
+ flags &= ~MSG_INTERNAL_SENDMSG_FLAGS;
msg.msg_flags = flags;
ret = sock_sendmsg(sock, &msg);
if (ret < min_ret) {
@@ -1136,6 +1137,7 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags)
msg_flags |= MSG_DONTWAIT;
if (msg_flags & MSG_WAITALL)
min_ret = iov_iter_count(&msg.msg_iter);
+ msg_flags &= ~MSG_INTERNAL_SENDMSG_FLAGS;
msg.msg_flags = msg_flags;
msg.msg_ubuf = &io_notif_to_data(zc->notif)->uarg;
diff --git a/net/socket.c b/net/socket.c
index b7e01d0fe082..3df96e9ba4e2 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2138,6 +2138,7 @@ 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_SENDMSG_FLAGS;
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
msg.msg_flags = flags;
@@ -2483,6 +2484,7 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys,
msg_sys->msg_control = ctl_buf;
msg_sys->msg_control_is_user = false;
}
+ flags &= ~MSG_INTERNAL_SENDMSG_FLAGS;
msg_sys->msg_flags = flags;
if (sock->file->f_flags & O_NONBLOCK)