splice, net: Use sendmsg(MSG_SPLICE_PAGES) rather than ->sendpage()

Replace generic_splice_sendpage() + splice_from_pipe + pipe_to_sendpage()
with a net-specific handler, splice_to_socket(), that calls sendmsg() with
MSG_SPLICE_PAGES set instead of calling ->sendpage().

MSG_MORE is used to indicate if the sendmsg() is expected to be followed
with more data.

This allows multiple pipe-buffer pages to be passed in a single call in a
BVEC iterator, allowing the processing to be pushed down to a loop in the
protocol driver.  This helps pave the way for passing multipage folios down
too.

Protocols that haven't been converted to handle MSG_SPLICE_PAGES yet should
just ignore it and do a normal sendmsg() for now - although that may be a
bit slower as it may copy everything.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
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 2023-06-07 19:19:09 +01:00 committed by Jakub Kicinski
parent 81840b3b91
commit 2dc334f1a6
4 changed files with 131 additions and 57 deletions

View file

@ -57,6 +57,7 @@
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/file.h>
#include <linux/splice.h>
#include <linux/net.h>
#include <linux/interrupt.h>
#include <linux/thread_info.h>
@ -126,8 +127,6 @@ static long compat_sock_ioctl(struct file *file,
unsigned int cmd, unsigned long arg);
#endif
static int sock_fasync(int fd, struct file *filp, int on);
static ssize_t sock_sendpage(struct file *file, struct page *page,
int offset, size_t size, loff_t *ppos, int more);
static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags);
@ -162,8 +161,7 @@ static const struct file_operations socket_file_ops = {
.mmap = sock_mmap,
.release = sock_close,
.fasync = sock_fasync,
.sendpage = sock_sendpage,
.splice_write = generic_splice_sendpage,
.splice_write = splice_to_socket,
.splice_read = sock_splice_read,
.show_fdinfo = sock_show_fdinfo,
};
@ -1066,26 +1064,6 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
}
EXPORT_SYMBOL(kernel_recvmsg);
static ssize_t sock_sendpage(struct file *file, struct page *page,
int offset, size_t size, loff_t *ppos, int more)
{
struct socket *sock;
int flags;
int ret;
sock = file->private_data;
flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
/* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */
flags |= more;
ret = kernel_sendpage(sock, page, offset, size, flags);
if (trace_sock_send_length_enabled())
call_trace_sock_send_length(sock->sk, ret, 0);
return ret;
}
static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)