tcp: tcp_sendpages() should call tcp_push() once

commit 35f9c09fe9c72eb8ca2b8e89a593e1c151f28fc2 upstream.

commit 2f533844242 (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: 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: Paul Gortmaker <paul.gortmaker@windriver.com>

diff --git a/fs/splice.c b/fs/splice.c
index cc617b09e4c226175f610d2de56ece6e04777404..3bec7c63be642f2a0dd3b99f8ea5e9e762370263 100644 (file)
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -31,6 +31,7 @@
 #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
@@ -638,7 +639,9 @@ 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 354cc5617f8b87304b97eebeec2c4b3e8a52428a..7cfb4f881644b607a6b7855dbf140db35a88660d 100644 (file)
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -256,7 +256,7 @@ 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

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cea0a9223c5da309189f477266dc95b95d06215b..df671c76f1960745ba91d8ae67a0bc74ec510f83 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -849,7 +849,7 @@ 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;
 

diff --git a/net/socket.c b/net/socket.c
index c63ebf4e31b5eee010a30a3d700c4c591482561c..c802797e3a4abddddbe733e094e1443f3a76cbdb 100644 (file)
--- a/net/socket.c
+++ b/net/socket.c
@@ -746,9 +746,9 @@ 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);
 }