From b841b901c452d92610f739a36e54978453528876 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 22 May 2023 13:11:10 +0100 Subject: 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 Reviewed-by: Willem de Bruijn cc: Jens Axboe cc: Matthew Wilcox Signed-off-by: Jakub Kicinski --- net/socket.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/socket.c') 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) -- cgit From 2dc334f1a63a8839b88483a3e73c0f27c9c1791c Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 7 Jun 2023 19:19:09 +0100 Subject: 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 Reviewed-by: Jakub Kicinski cc: Jens Axboe cc: Matthew Wilcox Signed-off-by: Jakub Kicinski --- net/socket.c | 26 ++------------------------ 1 file changed, 2 insertions(+), 24 deletions(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 3df96e9ba4e2..c4d9104418c8 100644 --- a/net/socket.c +++ b/net/socket.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include #include @@ -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) -- cgit From 2bfc66850952b6921b2033b09729ec59eabbc81d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 7 Jun 2023 19:19:10 +0100 Subject: splice, net: Add a splice_eof op to file-ops and socket-ops Add an optional method, ->splice_eof(), to allow splice to indicate the premature termination of a splice to struct file_operations and struct proto_ops. This is called if sendfile() or splice() encounters all of the following conditions inside splice_direct_to_actor(): (1) the user did not set SPLICE_F_MORE (splice only), and (2) an EOF condition occurred (->splice_read() returned 0), and (3) we haven't read enough to fulfill the request (ie. len > 0 still), and (4) we have already spliced at least one byte. A further patch will modify the behaviour of SPLICE_F_MORE to always be passed to the actor if either the user set it or we haven't yet read sufficient data to fulfill the request. Suggested-by: Linus Torvalds Link: https://lore.kernel.org/r/CAHk-=wh=V579PDYvkpnTobCLGczbgxpMgGmmhqiTyE34Cpi5Gg@mail.gmail.com/ Signed-off-by: David Howells Reviewed-by: Jakub Kicinski cc: Jens Axboe cc: Christoph Hellwig cc: Al Viro cc: Matthew Wilcox cc: Jan Kara cc: Jeff Layton cc: David Hildenbrand cc: Christian Brauner cc: Chuck Lever cc: Boris Pismenny cc: John Fastabend cc: linux-mm@kvack.org Signed-off-by: Jakub Kicinski --- net/socket.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index c4d9104418c8..b778fc03c6e0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -130,6 +130,7 @@ static int sock_fasync(int fd, struct file *filp, int on); static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +static void sock_splice_eof(struct file *file); #ifdef CONFIG_PROC_FS static void sock_show_fdinfo(struct seq_file *m, struct file *f) @@ -163,6 +164,7 @@ static const struct file_operations socket_file_ops = { .fasync = sock_fasync, .splice_write = splice_to_socket, .splice_read = sock_splice_read, + .splice_eof = sock_splice_eof, .show_fdinfo = sock_show_fdinfo, }; @@ -1076,6 +1078,14 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, return sock->ops->splice_read(sock, ppos, pipe, len, flags); } +static void sock_splice_eof(struct file *file) +{ + struct socket *sock = file->private_data; + + if (sock->ops->splice_eof) + sock->ops->splice_eof(sock); +} + static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; -- cgit From dc97391e661009eab46783030d2404c9b6e6f2e7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 23 Jun 2023 23:55:12 +0100 Subject: sock: Remove ->sendpage*() in favour of sendmsg(MSG_SPLICE_PAGES) Remove ->sendpage() and ->sendpage_locked(). sendmsg() with MSG_SPLICE_PAGES should be used instead. This allows multiple pages and multipage folios to be passed through. Signed-off-by: David Howells Acked-by: Marc Kleine-Budde # for net/can cc: Jens Axboe cc: Matthew Wilcox cc: linux-afs@lists.infradead.org cc: mptcp@lists.linux.dev cc: rds-devel@oss.oracle.com cc: tipc-discussion@lists.sourceforge.net cc: virtualization@lists.linux-foundation.org Link: https://lore.kernel.org/r/20230623225513.2732256-16-dhowells@redhat.com Signed-off-by: Jakub Kicinski --- net/socket.c | 48 ------------------------------------------------ 1 file changed, 48 deletions(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index b778fc03c6e0..8c3c8b29995a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3552,54 +3552,6 @@ int kernel_getpeername(struct socket *sock, struct sockaddr *addr) } EXPORT_SYMBOL(kernel_getpeername); -/** - * kernel_sendpage - send a &page through a socket (kernel space) - * @sock: socket - * @page: page - * @offset: page offset - * @size: total size in bytes - * @flags: flags (MSG_DONTWAIT, ...) - * - * Returns the total amount sent in bytes or an error. - */ - -int kernel_sendpage(struct socket *sock, struct page *page, int offset, - size_t size, int flags) -{ - if (sock->ops->sendpage) { - /* Warn in case the improper page to zero-copy send */ - WARN_ONCE(!sendpage_ok(page), "improper page for zero-copy send"); - return sock->ops->sendpage(sock, page, offset, size, flags); - } - return sock_no_sendpage(sock, page, offset, size, flags); -} -EXPORT_SYMBOL(kernel_sendpage); - -/** - * kernel_sendpage_locked - send a &page through the locked sock (kernel space) - * @sk: sock - * @page: page - * @offset: page offset - * @size: total size in bytes - * @flags: flags (MSG_DONTWAIT, ...) - * - * Returns the total amount sent in bytes or an error. - * Caller must hold @sk. - */ - -int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, - size_t size, int flags) -{ - struct socket *sock = sk->sk_socket; - - if (sock->ops->sendpage_locked) - return sock->ops->sendpage_locked(sk, page, offset, size, - flags); - - return sock_no_sendpage_locked(sk, page, offset, size, flags); -} -EXPORT_SYMBOL(kernel_sendpage_locked); - /** * kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space) * @sock: socket -- cgit