net: Declare MSG_SPLICE_PAGES internal sendmsg() flag

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 <dhowells@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
David Howells 2023-05-22 13:11:10 +01:00 committed by Jakub Kicinski
parent 57910a47ff
commit b841b901c4
3 changed files with 7 additions and 0 deletions

View File

@ -327,6 +327,7 @@ struct ucred {
*/ */
#define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #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_FASTOPEN 0x20000000 /* Send data in TCP SYN */
#define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file #define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file
descriptor received through descriptor received through
@ -337,6 +338,8 @@ struct ucred {
#define MSG_CMSG_COMPAT 0 /* We never have 32 bit fixups */ #define MSG_CMSG_COMPAT 0 /* We never have 32 bit fixups */
#endif #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 */ /* Setsockoptions(2) level. Thanks to BSD these must match IPPROTO_xxx */
#define SOL_IP 0 #define SOL_IP 0

View File

@ -389,6 +389,7 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
if (flags & MSG_WAITALL) if (flags & MSG_WAITALL)
min_ret = iov_iter_count(&msg.msg_iter); min_ret = iov_iter_count(&msg.msg_iter);
flags &= ~MSG_INTERNAL_SENDMSG_FLAGS;
msg.msg_flags = flags; msg.msg_flags = flags;
ret = sock_sendmsg(sock, &msg); ret = sock_sendmsg(sock, &msg);
if (ret < min_ret) { if (ret < min_ret) {
@ -1136,6 +1137,7 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags)
msg_flags |= MSG_DONTWAIT; msg_flags |= MSG_DONTWAIT;
if (msg_flags & MSG_WAITALL) if (msg_flags & MSG_WAITALL)
min_ret = iov_iter_count(&msg.msg_iter); min_ret = iov_iter_count(&msg.msg_iter);
msg_flags &= ~MSG_INTERNAL_SENDMSG_FLAGS;
msg.msg_flags = msg_flags; msg.msg_flags = msg_flags;
msg.msg_ubuf = &io_notif_to_data(zc->notif)->uarg; msg.msg_ubuf = &io_notif_to_data(zc->notif)->uarg;

View File

@ -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_name = (struct sockaddr *)&address;
msg.msg_namelen = addr_len; msg.msg_namelen = addr_len;
} }
flags &= ~MSG_INTERNAL_SENDMSG_FLAGS;
if (sock->file->f_flags & O_NONBLOCK) if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT; flags |= MSG_DONTWAIT;
msg.msg_flags = flags; 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 = ctl_buf;
msg_sys->msg_control_is_user = false; msg_sys->msg_control_is_user = false;
} }
flags &= ~MSG_INTERNAL_SENDMSG_FLAGS;
msg_sys->msg_flags = flags; msg_sys->msg_flags = flags;
if (sock->file->f_flags & O_NONBLOCK) if (sock->file->f_flags & O_NONBLOCK)