Commit 35f9c09f authored by Eric Dumazet's avatar Eric Dumazet Committed by David S. Miller
Browse files

tcp: tcp_sendpages() should call tcp_push() once 



commit 2f533844 (tcp: allow splice() to build full TSO packets) added
a regression for splice() calls using SPLICE_F_MORE.

We need to call tcp_flush() at the end of the last page processed in
tcp_sendpages(), or else transmits can be deferred and future sends
stall.

Add a new internal flag, MSG_SENDPAGE_NOTLAST, acting like MSG_MORE, but
with different semantic.

For all sendpage() providers, its a transparent change. Only
sock_sendpage() and tcp_sendpages() can differentiate the two different
flags provided by pipe_to_sendpage()

Reported-by: default avatarTom Herbert <therbert@google.com>
Cc: Nandita Dukkipati <nanditad@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: H.K. Jerry Chu <hkchu@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: default avatarEric Dumazet <eric.dumazet@gmail&gt;com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 78d50217

fs/splice.c

+4 −1
Original line number Diff line number Diff line
@@ -30,6 +30,7 @@ 
#include <linux/uio.h>

#include <linux/security.h>

#include <linux/gfp.h>

#include <linux/socket.h>



/*

 * Attempt to steal a page from a pipe buffer. This should perhaps go into
@@ -690,7 +691,9 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe, 
	if (!likely(file->f_op && file->f_op->sendpage))

		return -EINVAL;



	more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;

	more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0;

	if (sd->len < sd->total_len)

		more |= MSG_SENDPAGE_NOTLAST;

	return file->f_op->sendpage(file, buf->page, buf->offset,

				    sd->len, &pos, more);

}

include/linux/socket.h

+1 −1
Original line number Diff line number Diff line
@@ -265,7 +265,7 @@ struct ucred { 
#define MSG_NOSIGNAL	0x4000	/* Do not generate SIGPIPE */

#define MSG_MORE	0x8000	/* Sender will send more */

#define MSG_WAITFORONE	0x10000	/* recvmmsg(): block until 1+ packets avail */



#define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */

#define MSG_EOF         MSG_FIN



#define MSG_CMSG_CLOEXEC 0x40000000	/* Set close_on_exit for file

net/ipv4/tcp.c

+1 −1
Original line number Diff line number Diff line
@@ -860,7 +860,7 @@ wait_for_memory: 
	}



out:

	if (copied && !(flags & MSG_MORE))

	if (copied && !(flags & MSG_SENDPAGE_NOTLAST))

		tcp_push(sk, flags, mss_now, tp->nonagle);

	return copied;

net/socket.c

+3 −3
Original line number Diff line number Diff line
@@ -811,9 +811,9 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, 


	sock = file->private_data;



	flags = !(file->f_flags & O_NONBLOCK) ? 0 : MSG_DONTWAIT;

	if (more)

		flags |= MSG_MORE;

	flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;

	/* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */

	flags |= more;



	return kernel_sendpage(sock, page, offset, size, flags);

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE