tcp: tcp_sendpages() should call tcp_push() once

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>

4 files changed, 9 insertions, 6 deletions

diff --git a/fs/splice.c b/fs/splice.c
index 5f883de7ef3a..f8476841eb04 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -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);
 }
diff --git a/include/linux/socket.h b/include/linux/socket.h
index da2d3e2543f3..b84bbd48b874 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -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
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2ff6f45a76f4..5d54ed30e821 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -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;
 
diff --git a/net/socket.c b/net/socket.c
index 484cc6953fc6..851edcd6b098 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -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);
 }