[RFC PATCH 19/28] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage

[RFC PATCH 19/28] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage

[David Howells]

Use sendmsg() and MSG_SPLICE_PAGES rather than sendpage in ceph when
transmitting data.  For the moment, this can only transmit one page at a
time because of the architecture of net/ceph/, but if
write_partial_message_data() can be given a bvec[] at a time by the
iteration code, this would allow pages to be sent in a batch.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Ilya Dryomov <idryomov@gmail.com>
cc: Xiubo Li <xiubli@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: ceph-devel@vger.kernel.org
cc: netdev@vger.kernel.org
---
 net/ceph/messenger_v1.c | 58 ++++++++++++++---------------------------
 1 file changed, 19 insertions(+), 39 deletions(-)

diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index d664cb1593a7..b2d801a49122 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -74,37 +74,6 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
 	return r;
 }
 
-/*
- * @more: either or both of MSG_MORE and MSG_SENDPAGE_NOTLAST
- */
-static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
-			     int offset, size_t size, int more)
-{
-	ssize_t (*sendpage)(struct socket *sock, struct page *page,
-			    int offset, size_t size, int flags);
-	int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more;
-	int ret;
-
-	/*
-	 * sendpage cannot properly handle pages with page_count == 0,
-	 * we need to fall back to sendmsg if that's the case.
-	 *
-	 * Same goes for slab pages: skb_can_coalesce() allows
-	 * coalescing neighboring slab objects into a single frag which
-	 * triggers one of hardened usercopy checks.
-	 */
-	if (sendpage_ok(page))
-		sendpage = sock->ops->sendpage;
-	else
-		sendpage = sock_no_sendpage;
-
-	ret = sendpage(sock, page, offset, size, flags);
-	if (ret == -EAGAIN)
-		ret = 0;
-
-	return ret;
-}
-
 static void con_out_kvec_reset(struct ceph_connection *con)
 {
 	BUG_ON(con->v1.out_skip);
@@ -464,7 +433,6 @@ static int write_partial_message_data(struct ceph_connection *con)
 	struct ceph_msg *msg = con->out_msg;
 	struct ceph_msg_data_cursor *cursor = &msg->cursor;
 	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
-	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
 	u32 crc;
 
 	dout("%s %p msg %p\n", __func__, con, msg);
@@ -482,6 +450,10 @@ static int write_partial_message_data(struct ceph_connection *con)
 	 */
 	crc = do_datacrc ? le32_to_cpu(msg->footer.data_crc) : 0;
 	while (cursor->total_resid) {
+		struct bio_vec bvec;
+		struct msghdr msghdr = {
+			.msg_flags = MSG_SPLICE_PAGES | MSG_SENDPAGE_NOTLAST,
+		};
 		struct page *page;
 		size_t page_offset;
 		size_t length;
@@ -494,9 +466,12 @@ static int write_partial_message_data(struct ceph_connection *con)
 
 		page = ceph_msg_data_next(cursor, &page_offset, &length);
 		if (length == cursor->total_resid)
-			more = MSG_MORE;
-		ret = ceph_tcp_sendpage(con->sock, page, page_offset, length,
-					more);
+			msghdr.msg_flags |= MSG_MORE;
+
+		bvec_set_page(&bvec, page, length, page_offset);
+		iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, length);
+
+		ret = sock_sendmsg(con->sock, &msghdr);
 		if (ret <= 0) {
 			if (do_datacrc)
 				msg->footer.data_crc = cpu_to_le32(crc);
@@ -526,7 +501,10 @@ static int write_partial_message_data(struct ceph_connection *con)
  */
 static int write_partial_skip(struct ceph_connection *con)
 {
-	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
+	struct bio_vec bvec;
+	struct msghdr msghdr = {
+		.msg_flags = MSG_SPLICE_PAGES | MSG_SENDPAGE_NOTLAST | MSG_MORE,
+	};
 	int ret;
 
 	dout("%s %p %d left\n", __func__, con, con->v1.out_skip);
@@ -534,9 +512,11 @@ static int write_partial_skip(struct ceph_connection *con)
 		size_t size = min(con->v1.out_skip, (int)PAGE_SIZE);
 
 		if (size == con->v1.out_skip)
-			more = MSG_MORE;
-		ret = ceph_tcp_sendpage(con->sock, ceph_zero_page, 0, size,
-					more);
+			msghdr.msg_flags &= ~MSG_SENDPAGE_NOTLAST;
+		bvec_set_page(&bvec, ZERO_PAGE(0), size, 0);
+		iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, size);
+
+		ret = sock_sendmsg(con->sock, &msghdr);
 		if (ret <= 0)
 			goto out;
 		con->v1.out_skip -= ret;

[RFC PATCH 24/28] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage()

[David Howells]

Use sendmsg() and MSG_SPLICE_PAGES rather than sendpage in ceph when
transmitting data.  For the moment, this can only transmit one page at a
time because of the architecture of net/ceph/, but if
write_partial_message_data() can be given a bvec[] at a time by the
iteration code, this would allow pages to be sent in a batch.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Ilya Dryomov <idryomov@gmail.com>
cc: Xiubo Li <xiubli@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: ceph-devel@vger.kernel.org
cc: netdev@vger.kernel.org
---
 net/ceph/messenger_v2.c | 89 +++++++++--------------------------------
 1 file changed, 18 insertions(+), 71 deletions(-)

diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index 301a991dc6a6..1637a0c21126 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -117,91 +117,38 @@ static int ceph_tcp_recv(struct ceph_connection *con)
 	return ret;
 }
 
-static int do_sendmsg(struct socket *sock, struct iov_iter *it)
-{
-	struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS };
-	int ret;
-
-	msg.msg_iter = *it;
-	while (iov_iter_count(it)) {
-		ret = sock_sendmsg(sock, &msg);
-		if (ret <= 0) {
-			if (ret == -EAGAIN)
-				ret = 0;
-			return ret;
-		}
-
-		iov_iter_advance(it, ret);
-	}
-
-	WARN_ON(msg_data_left(&msg));
-	return 1;
-}
-
-static int do_try_sendpage(struct socket *sock, struct iov_iter *it)
-{
-	struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS };
-	struct bio_vec bv;
-	int ret;
-
-	if (WARN_ON(!iov_iter_is_bvec(it)))
-		return -EINVAL;
-
-	while (iov_iter_count(it)) {
-		/* iov_iter_iovec() for ITER_BVEC */
-		bvec_set_page(&bv, it->bvec->bv_page,
-			      min(iov_iter_count(it),
-				  it->bvec->bv_len - it->iov_offset),
-			      it->bvec->bv_offset + it->iov_offset);
-
-		/*
-		 * sendpage cannot properly handle pages with
-		 * page_count == 0, we need to fall back to sendmsg if
-		 * that's the case.
-		 *
-		 * Same goes for slab pages: skb_can_coalesce() allows
-		 * coalescing neighboring slab objects into a single frag
-		 * which triggers one of hardened usercopy checks.
-		 */
-		if (sendpage_ok(bv.bv_page)) {
-			ret = sock->ops->sendpage(sock, bv.bv_page,
-						  bv.bv_offset, bv.bv_len,
-						  CEPH_MSG_FLAGS);
-		} else {
-			iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, bv.bv_len);
-			ret = sock_sendmsg(sock, &msg);
-		}
-		if (ret <= 0) {
-			if (ret == -EAGAIN)
-				ret = 0;
-			return ret;
-		}
-
-		iov_iter_advance(it, ret);
-	}
-
-	return 1;
-}
-
 /*
  * Write as much as possible.  The socket is expected to be corked,
  * so we don't bother with MSG_MORE/MSG_SENDPAGE_NOTLAST here.
  *
  * Return:
- *   1 - done, nothing (else) to write
+ *  >0 - done, nothing (else) to write
  *   0 - socket is full, need to wait
  *  <0 - error
  */
 static int ceph_tcp_send(struct ceph_connection *con)
 {
+	struct msghdr msg = {
+		.msg_iter	= con->v2.out_iter,
+		.msg_flags	= CEPH_MSG_FLAGS,
+	};
 	int ret;
 
+	if (WARN_ON(!iov_iter_is_bvec(&con->v2.out_iter)))
+		return -EINVAL;
+
+	if (con->v2.out_iter_sendpage)
+		msg.msg_flags |= MSG_SPLICE_PAGES;
+
 	dout("%s con %p have %zu try_sendpage %d\n", __func__, con,
 	     iov_iter_count(&con->v2.out_iter), con->v2.out_iter_sendpage);
-	if (con->v2.out_iter_sendpage)
-		ret = do_try_sendpage(con->sock, &con->v2.out_iter);
-	else
-		ret = do_sendmsg(con->sock, &con->v2.out_iter);
+
+	ret = sock_sendmsg(con->sock, &msg);
+	if (ret > 0)
+		iov_iter_advance(&con->v2.out_iter, ret);
+	else if (ret == -EAGAIN)
+		ret = 0;
+
 	dout("%s con %p ret %d left %zu\n", __func__, con, ret,
 	     iov_iter_count(&con->v2.out_iter));
 	return ret;