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,
        Mark Fasheh <mark@fasheh.com>,
        Joel Becker <jlbec@evilplan.org>,
        Joseph Qi <joseph.qi@linux.alibaba.com>,
        ocfs2-devel@oss.oracle.com
Subject: [RFC PATCH v2 45/48] ocfs2: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage()
Date:   Wed, 29 Mar 2023 15:13:51 +0100
Message-Id: <20230329141354.516864-46-dhowells@redhat.com>
In-Reply-To: <20230329141354.516864-1-dhowells@redhat.com>
References: <20230329141354.516864-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Fix ocfs2 to use the page fragment allocator rather than kzalloc in order
to allocate the buffers for the handshake message and keepalive request and
reply messages.  Slab pages should not be given to sendpage, but fragments
can be.

Switch from using sendpage() to using sendmsg() + MSG_SPLICE_PAGES so that
sendpage can be phased out.

Signed-off-by: David Howells <dhowells@redhat.com>

cc: Mark Fasheh <mark@fasheh.com>
cc: Joel Becker <jlbec@evilplan.org>
cc: Joseph Qi <joseph.qi@linux.alibaba.com>
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: ocfs2-devel@oss.oracle.com
cc: netdev@vger.kernel.org
---
 fs/ocfs2/cluster/tcp.c | 107 ++++++++++++++++++++++-------------------
 1 file changed, 58 insertions(+), 49 deletions(-)

diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index aecbd712a00c..e568ad2f34bf 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -110,9 +110,6 @@ static struct work_struct o2net_listen_work;
 static struct o2hb_callback_func o2net_hb_up, o2net_hb_down;
 #define O2NET_HB_PRI 0x1
 
-static struct o2net_handshake *o2net_hand;
-static struct o2net_msg *o2net_keep_req, *o2net_keep_resp;
-
 static int o2net_sys_err_translations[O2NET_ERR_MAX] =
 		{[O2NET_ERR_NONE]	= 0,
 		 [O2NET_ERR_NO_HNDLR]	= -ENOPROTOOPT,
@@ -930,19 +927,22 @@ static int o2net_send_tcp_msg(struct socket *sock, struct kvec *vec,
 }
 
 static void o2net_sendpage(struct o2net_sock_container *sc,
-			   void *kmalloced_virt,
-			   size_t size)
+			   void *virt, size_t size)
 {
 	struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
+	struct msghdr msg = {};
+	struct bio_vec bv;
 	ssize_t ret;
 
+	bvec_set_virt(&bv, virt, size);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, size);
+
 	while (1) {
+		msg.msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES;
 		mutex_lock(&sc->sc_send_lock);
-		ret = sc->sc_sock->ops->sendpage(sc->sc_sock,
-						 virt_to_page(kmalloced_virt),
-						 offset_in_page(kmalloced_virt),
-						 size, MSG_DONTWAIT);
+		ret = sock_sendmsg(sc->sc_sock, &msg);
 		mutex_unlock(&sc->sc_send_lock);
+
 		if (ret == size)
 			break;
 		if (ret == (ssize_t)-EAGAIN) {
@@ -1168,6 +1168,7 @@ static int o2net_process_message(struct o2net_sock_container *sc,
 				 struct o2net_msg *hdr)
 {
 	struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
+	struct o2net_msg *keep_resp;
 	int ret = 0, handler_status;
 	enum  o2net_system_error syserr;
 	struct o2net_msg_handler *nmh = NULL;
@@ -1186,8 +1187,16 @@ static int o2net_process_message(struct o2net_sock_container *sc,
 					   be32_to_cpu(hdr->status));
 			goto out;
 		case O2NET_MSG_KEEP_REQ_MAGIC:
-			o2net_sendpage(sc, o2net_keep_resp,
-				       sizeof(*o2net_keep_resp));
+			keep_resp = page_frag_alloc(NULL, sizeof(*keep_resp),
+						    GFP_KERNEL);
+			if (!keep_resp) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			memset(keep_resp, 0, sizeof(*keep_resp));
+			keep_resp->magic = cpu_to_be16(O2NET_MSG_KEEP_RESP_MAGIC);
+			o2net_sendpage(sc, keep_resp, sizeof(*keep_resp));
+			folio_put(virt_to_folio(keep_resp));
 			goto out;
 		case O2NET_MSG_KEEP_RESP_MAGIC:
 			goto out;
@@ -1439,15 +1448,22 @@ static void o2net_rx_until_empty(struct work_struct *work)
 	sc_put(sc);
 }
 
-static void o2net_initialize_handshake(void)
+static struct o2net_handshake *o2net_initialize_handshake(void)
 {
-	o2net_hand->o2hb_heartbeat_timeout_ms = cpu_to_be32(
-		O2HB_MAX_WRITE_TIMEOUT_MS);
-	o2net_hand->o2net_idle_timeout_ms = cpu_to_be32(o2net_idle_timeout());
-	o2net_hand->o2net_keepalive_delay_ms = cpu_to_be32(
-		o2net_keepalive_delay());
-	o2net_hand->o2net_reconnect_delay_ms = cpu_to_be32(
-		o2net_reconnect_delay());
+	struct o2net_handshake *hand;
+
+	hand = page_frag_alloc(NULL, sizeof(*hand), GFP_KERNEL);
+	if (!hand)
+		return NULL;
+
+	memset(hand, 0, sizeof(*hand));
+	hand->protocol_version		= cpu_to_be64(O2NET_PROTOCOL_VERSION);
+	hand->connector_id		= cpu_to_be64(1);
+	hand->o2hb_heartbeat_timeout_ms	= cpu_to_be32(O2HB_MAX_WRITE_TIMEOUT_MS);
+	hand->o2net_idle_timeout_ms	= cpu_to_be32(o2net_idle_timeout());
+	hand->o2net_keepalive_delay_ms	= cpu_to_be32(o2net_keepalive_delay());
+	hand->o2net_reconnect_delay_ms	= cpu_to_be32(o2net_reconnect_delay());
+	return hand;
 }
 
 /* ------------------------------------------------------------ */
@@ -1456,16 +1472,22 @@ static void o2net_initialize_handshake(void)
  * rx path will see the response and mark the sc valid */
 static void o2net_sc_connect_completed(struct work_struct *work)
 {
+	struct o2net_handshake *hand;
 	struct o2net_sock_container *sc =
 		container_of(work, struct o2net_sock_container,
 			     sc_connect_work);
 
+	hand = o2net_initialize_handshake();
+	if (!hand)
+		goto out;
+
 	mlog(ML_MSG, "sc sending handshake with ver %llu id %llx\n",
               (unsigned long long)O2NET_PROTOCOL_VERSION,
-	      (unsigned long long)be64_to_cpu(o2net_hand->connector_id));
+	      (unsigned long long)be64_to_cpu(hand->connector_id));
 
-	o2net_initialize_handshake();
-	o2net_sendpage(sc, o2net_hand, sizeof(*o2net_hand));
+	o2net_sendpage(sc, hand, sizeof(*hand));
+	folio_put(virt_to_folio(hand));
+out:
 	sc_put(sc);
 }
 
@@ -1475,8 +1497,15 @@ static void o2net_sc_send_keep_req(struct work_struct *work)
 	struct o2net_sock_container *sc =
 		container_of(work, struct o2net_sock_container,
 			     sc_keepalive_work.work);
+	struct o2net_msg *keep_req;
 
-	o2net_sendpage(sc, o2net_keep_req, sizeof(*o2net_keep_req));
+	keep_req = page_frag_alloc(NULL, sizeof(*keep_req), GFP_KERNEL);
+	if (keep_req) {
+		memset(keep_req, 0, sizeof(*keep_req));
+		keep_req->magic = cpu_to_be16(O2NET_MSG_KEEP_REQ_MAGIC);
+		o2net_sendpage(sc, keep_req, sizeof(*keep_req));
+		folio_put(virt_to_folio(keep_req));
+	}
 	sc_put(sc);
 }
 
@@ -1780,6 +1809,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
 	struct socket *new_sock = NULL;
 	struct o2nm_node *node = NULL;
 	struct o2nm_node *local_node = NULL;
+	struct o2net_handshake *hand;
 	struct o2net_sock_container *sc = NULL;
 	struct o2net_node *nn;
 	unsigned int nofs_flag;
@@ -1882,8 +1912,11 @@ static int o2net_accept_one(struct socket *sock, int *more)
 	o2net_register_callbacks(sc->sc_sock->sk, sc);
 	o2net_sc_queue_work(sc, &sc->sc_rx_work);
 
-	o2net_initialize_handshake();
-	o2net_sendpage(sc, o2net_hand, sizeof(*o2net_hand));
+	hand = o2net_initialize_handshake();
+	if (hand) {
+		o2net_sendpage(sc, hand, sizeof(*hand));
+		folio_put(virt_to_folio(hand));
+	}
 
 out:
 	if (new_sock)
@@ -2090,21 +2123,8 @@ int o2net_init(void)
 	unsigned long i;
 
 	o2quo_init();
-
 	o2net_debugfs_init();
 
-	o2net_hand = kzalloc(sizeof(struct o2net_handshake), GFP_KERNEL);
-	o2net_keep_req = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
-	o2net_keep_resp = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
-	if (!o2net_hand || !o2net_keep_req || !o2net_keep_resp)
-		goto out;
-
-	o2net_hand->protocol_version = cpu_to_be64(O2NET_PROTOCOL_VERSION);
-	o2net_hand->connector_id = cpu_to_be64(1);
-
-	o2net_keep_req->magic = cpu_to_be16(O2NET_MSG_KEEP_REQ_MAGIC);
-	o2net_keep_resp->magic = cpu_to_be16(O2NET_MSG_KEEP_RESP_MAGIC);
-
 	for (i = 0; i < ARRAY_SIZE(o2net_nodes); i++) {
 		struct o2net_node *nn = o2net_nn_from_num(i);
 
@@ -2122,21 +2142,10 @@ int o2net_init(void)
 	}
 
 	return 0;
-
-out:
-	kfree(o2net_hand);
-	kfree(o2net_keep_req);
-	kfree(o2net_keep_resp);
-	o2net_debugfs_exit();
-	o2quo_exit();
-	return -ENOMEM;
 }
 
 void o2net_exit(void)
 {
 	o2quo_exit();
-	kfree(o2net_hand);
-	kfree(o2net_keep_req);
-	kfree(o2net_keep_resp);
 	o2net_debugfs_exit();
 }