Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   David Howells <dhowells@redhat.com>
To:     Matthew Wilcox <willy@infradead.org>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>
Cc:     David Howells <dhowells@redhat.com>,
        Al Viro <viro@zeniv.linux.org.uk>,
        Christoph Hellwig <hch@infradead.org>,
        Jens Axboe <axboe@kernel.dk>, Jeff Layton <jlayton@kernel.org>,
        Christian Brauner <brauner@kernel.org>,
        Chuck Lever III <chuck.lever@oracle.com>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        netdev@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        Ilya Dryomov <idryomov@gmail.com>,
        Xiubo Li <xiubli@redhat.com>, ceph-devel@vger.kernel.org
Subject: [PATCH v3 45/55] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage()
Date:   Fri, 31 Mar 2023 17:09:04 +0100
Message-Id: <20230331160914.1608208-46-dhowells@redhat.com>
In-Reply-To: <20230331160914.1608208-1-dhowells@redhat.com>
References: <20230331160914.1608208-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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;