[Drbd-dev] [PATCH net-next v2 13/17] drbd: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage()

[Drbd-dev] [PATCH net-next v2 13/17] drbd: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage()

[David Howells]

Use sendmsg() conditionally with MSG_SPLICE_PAGES in _drbd_send_page()
rather than calling sendpage() or _drbd_no_send_page().

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Philipp Reisner <philipp.reisner@linbit.com>
cc: Lars Ellenberg <lars.ellenberg@linbit.com>
cc: "Christoph Böhmwalder" <christoph.boehmwalder@linbit.com>
cc: Jens Axboe <axboe@kernel.dk>
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: drbd-dev@lists.linbit.com
cc: linux-block@vger.kernel.org
cc: netdev@vger.kernel.org
---

Notes:
    ver #2)
     - Wrap lines at 80.

 drivers/block/drbd/drbd_main.c | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 83987e7a5ef2..8a01a18a2550 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1540,7 +1540,8 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa
 		    int offset, size_t size, unsigned msg_flags)
 {
 	struct socket *socket = peer_device->connection->data.socket;
-	int len = size;
+	struct bio_vec bvec;
+	struct msghdr msg = { .msg_flags = msg_flags, };
 	int err = -EIO;
 
 	/* e.g. XFS meta- & log-data is in slab pages, which have a
@@ -1549,33 +1550,35 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa
 	 * put_page(); and would cause either a VM_BUG directly, or
 	 * __page_cache_release a page that would actually still be referenced
 	 * by someone, leading to some obscure delayed Oops somewhere else. */
-	if (drbd_disable_sendpage || !sendpage_ok(page))
-		return _drbd_no_send_page(peer_device, page, offset, size, msg_flags);
+	if (!drbd_disable_sendpage && sendpage_ok(page))
+		msg.msg_flags |= MSG_NOSIGNAL | MSG_SPLICE_PAGES;
+
+	bvec_set_page(&bvec, page, offset, size);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
 
-	msg_flags |= MSG_NOSIGNAL;
 	drbd_update_congested(peer_device->connection);
 	do {
 		int sent;
 
-		sent = socket->ops->sendpage(socket, page, offset, len, msg_flags);
+		sent = sock_sendmsg(socket, &msg);
 		if (sent <= 0) {
 			if (sent == -EAGAIN) {
 				if (we_should_drop_the_connection(peer_device->connection, socket))
 					break;
 				continue;
 			}
-			drbd_warn(peer_device->device, "%s: size=%d len=%d sent=%d\n",
-			     __func__, (int)size, len, sent);
+			drbd_warn(peer_device->device, "%s: size=%d len=%zu sent=%d\n",
+				  __func__, (int)size, msg_data_left(&msg),
+				  sent);
 			if (sent < 0)
 				err = sent;
 			break;
 		}
-		len    -= sent;
-		offset += sent;
-	} while (len > 0 /* THINK && device->cstate >= C_CONNECTED*/);
+	} while (msg_data_left(&msg)
+		 /* THINK && device->cstate >= C_CONNECTED*/);
 	clear_bit(NET_CONGESTED, &peer_device->connection->flags);
 
-	if (len == 0) {
+	if (!msg_data_left(&msg)) {
 		err = 0;
 		peer_device->device->send_cnt += size >> 9;
 	}

[Drbd-dev] [PATCH net-next v2 14/17] drdb: Send an entire bio in a single sendmsg

[David Howells]

Since _drdb_sendpage() is now using sendmsg to send the pages rather
sendpage, pass the entire bio in one go using a bvec iterator instead of
doing it piecemeal.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Philipp Reisner <philipp.reisner@linbit.com>
cc: Lars Ellenberg <lars.ellenberg@linbit.com>
cc: "Christoph Böhmwalder" <christoph.boehmwalder@linbit.com>
cc: Jens Axboe <axboe@kernel.dk>
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: drbd-dev@lists.linbit.com
cc: linux-block@vger.kernel.org
cc: netdev@vger.kernel.org
---

Notes:
    ver #2)
     - Use "unsigned int" rather than "unsigned".

 drivers/block/drbd/drbd_main.c | 77 +++++++++++-----------------------
 1 file changed, 25 insertions(+), 52 deletions(-)

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 8a01a18a2550..beba74ae093b 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1520,28 +1520,15 @@ static void drbd_update_congested(struct drbd_connection *connection)
  * As a workaround, we disable sendpage on pages
  * with page_count == 0 or PageSlab.
  */
-static int _drbd_no_send_page(struct drbd_peer_device *peer_device, struct page *page,
-			      int offset, size_t size, unsigned msg_flags)
-{
-	struct socket *socket;
-	void *addr;
-	int err;
-
-	socket = peer_device->connection->data.socket;
-	addr = kmap(page) + offset;
-	err = drbd_send_all(peer_device->connection, socket, addr, size, msg_flags);
-	kunmap(page);
-	if (!err)
-		peer_device->device->send_cnt += size >> 9;
-	return err;
-}
-
-static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *page,
-		    int offset, size_t size, unsigned msg_flags)
+static int _drbd_send_pages(struct drbd_peer_device *peer_device,
+			    struct iov_iter *iter, unsigned int msg_flags)
 {
 	struct socket *socket = peer_device->connection->data.socket;
-	struct bio_vec bvec;
-	struct msghdr msg = { .msg_flags = msg_flags, };
+	struct msghdr msg = {
+		.msg_flags	= msg_flags | MSG_NOSIGNAL,
+		.msg_iter	= *iter,
+	};
+	size_t size = iov_iter_count(iter);
 	int err = -EIO;
 
 	/* e.g. XFS meta- & log-data is in slab pages, which have a
@@ -1550,11 +1537,8 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa
 	 * put_page(); and would cause either a VM_BUG directly, or
 	 * __page_cache_release a page that would actually still be referenced
 	 * by someone, leading to some obscure delayed Oops somewhere else. */
-	if (!drbd_disable_sendpage && sendpage_ok(page))
-		msg.msg_flags |= MSG_NOSIGNAL | MSG_SPLICE_PAGES;
-
-	bvec_set_page(&bvec, page, offset, size);
-	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
+	if (drbd_disable_sendpage)
+		msg.msg_flags &= ~(MSG_NOSIGNAL | MSG_SPLICE_PAGES);
 
 	drbd_update_congested(peer_device->connection);
 	do {
@@ -1587,39 +1571,22 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa
 
 static int _drbd_send_bio(struct drbd_peer_device *peer_device, struct bio *bio)
 {
-	struct bio_vec bvec;
-	struct bvec_iter iter;
+	struct iov_iter iter;
 
-	/* hint all but last page with MSG_MORE */
-	bio_for_each_segment(bvec, bio, iter) {
-		int err;
+	iov_iter_bvec(&iter, ITER_SOURCE, bio->bi_io_vec, bio->bi_vcnt,
+		      bio->bi_iter.bi_size);
 
-		err = _drbd_no_send_page(peer_device, bvec.bv_page,
-					 bvec.bv_offset, bvec.bv_len,
-					 bio_iter_last(bvec, iter)
-					 ? 0 : MSG_MORE);
-		if (err)
-			return err;
-	}
-	return 0;
+	return _drbd_send_pages(peer_device, &iter, 0);
 }
 
 static int _drbd_send_zc_bio(struct drbd_peer_device *peer_device, struct bio *bio)
 {
-	struct bio_vec bvec;
-	struct bvec_iter iter;
+	struct iov_iter iter;
 
-	/* hint all but last page with MSG_MORE */
-	bio_for_each_segment(bvec, bio, iter) {
-		int err;
+	iov_iter_bvec(&iter, ITER_SOURCE, bio->bi_io_vec, bio->bi_vcnt,
+		      bio->bi_iter.bi_size);
 
-		err = _drbd_send_page(peer_device, bvec.bv_page,
-				      bvec.bv_offset, bvec.bv_len,
-				      bio_iter_last(bvec, iter) ? 0 : MSG_MORE);
-		if (err)
-			return err;
-	}
-	return 0;
+	return _drbd_send_pages(peer_device, &iter, MSG_SPLICE_PAGES);
 }
 
 static int _drbd_send_zc_ee(struct drbd_peer_device *peer_device,
@@ -1631,10 +1598,16 @@ static int _drbd_send_zc_ee(struct drbd_peer_device *peer_device,
 
 	/* hint all but last page with MSG_MORE */
 	page_chain_for_each(page) {
+		struct iov_iter iter;
+		struct bio_vec bvec;
 		unsigned l = min_t(unsigned, len, PAGE_SIZE);
 
-		err = _drbd_send_page(peer_device, page, 0, l,
-				      page_chain_next(page) ? MSG_MORE : 0);
+		bvec_set_page(&bvec, page, 0, l);
+		iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, l);
+
+		err = _drbd_send_pages(peer_device, &iter,
+				       MSG_SPLICE_PAGES |
+				       (page_chain_next(page) ? MSG_MORE : 0));
 		if (err)
 			return err;
 		len -= l;