tcp: allow splice() to build full TSO packets

[ This combines upstream commit
  2f53384424251c06038ae612e56231b96ab610ee and the follow-on bug fix
  commit 35f9c09fe9c72eb8ca2b8e89a593e1c151f28fc2 ]

vmsplice()/splice(pipe, socket) call do_tcp_sendpages() one page at a
time, adding at most 4096 bytes to an skb. (assuming PAGE_SIZE=4096)

The call to tcp_push() at the end of do_tcp_sendpages() forces an
immediate xmit when pipe is not already filled, and tso_fragment() try
to split these skb to MSS multiples.

4096 bytes are usually split in a skb with 2 MSS, and a remaining
sub-mss skb (assuming MTU=1500)

This makes slow start suboptimal because many small frames are sent to
qdisc/driver layers instead of big ones (constrained by cwnd and packets
in flight of course)

In fact, applications using sendmsg() (adding an additional memory copy)
instead of vmsplice()/splice()/sendfile() are a bit faster because of
this anomaly, especially if serving small files in environments with
large initial [c]wnd.

Call tcp_push() only if MSG_MORE is not set in the flags parameter.

This bit is automatically provided by splice() internals but for the
last page, or on all pages if user specified SPLICE_F_MORE splice()
flag.

In some workloads, this can reduce number of sent logical packets by an
order of magnitude, making zero-copy TCP actually faster than
one-copy :)

Reported-by: Tom 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: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>

diff --git a/fs/splice.c b/fs/splice.c
index bb92b7c5cdcb1bdf2b000db663cecdcdaaa6f656..f5d5a2b98563d6e0ff46f012fd1baef4701334fa 100644 (file)
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -30,6 +30,7 @@
 #include <linux/syscalls.h>
 #include <linux/uio.h>
 #include <linux/security.h>
+#include <linux/socket.h>
 
 /*
  * Attempt to steal a page from a pipe buffer. This should perhaps go into
@@ -637,7 +638,9 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe,
 
        ret = buf->ops->confirm(pipe, buf);
        if (!ret) {
-               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;
                if (file->f_op && file->f_op->sendpage)
                        ret = file->f_op->sendpage(file, buf->page, buf->offset,
                                                   sd->len, &pos, more);

diff --git a/include/linux/socket.h b/include/linux/socket.h
index 3273a0c5043b96321bf6dda00bc44d4d4c254003..3124c518d0471b66c081433652f5437bd7b59af6 100644 (file)
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -246,7 +246,7 @@ struct ucred {
 #define MSG_ERRQUEUE   0x2000  /* Fetch message from error queue */
 #define MSG_NOSIGNAL   0x4000  /* Do not generate SIGPIPE */
 #define MSG_MORE       0x8000  /* Sender will send more */
-
+#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

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b9644d82665319c5b84a2f9cb3caa595a7ab19fa..6232462ffcb826ef92285ab148b96c70f0110fb7 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -847,7 +847,7 @@ wait_for_memory:
        }
 
 out:
-       if (copied)
+       if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
                tcp_push(sk, flags, mss_now, tp->nonagle);
        return copied;
 

diff --git a/net/socket.c b/net/socket.c
index d449812d6208d337d0d927d47401ca62346632ea..bf9fc68a554cf6b884cae123364cbecfb9655672 100644 (file)
--- a/net/socket.c
+++ b/net/socket.c
@@ -732,9 +732,9 @@ 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);
 }