linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
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	[thread overview]
Message-ID: <20230329141354.516864-46-dhowells@redhat.com> (raw)
In-Reply-To: <20230329141354.516864-1-dhowells@redhat.com>

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();
 }


  parent reply	other threads:[~2023-03-29 14:23 UTC|newest]

Thread overview: 79+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-03-29 14:13 [RFC PATCH v2 00/48] splice, net: Replace sendpage with sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-29 14:13 ` [RFC PATCH v2 01/48] netfs: Fix netfs_extract_iter_to_sg() for ITER_UBUF/IOVEC David Howells
2023-03-29 14:13 ` [RFC PATCH v2 02/48] iov_iter: Remove last_offset member David Howells
2023-03-29 14:13 ` [RFC PATCH v2 03/48] iov_iter: Add an iterator-of-iterators David Howells
2023-03-29 14:13 ` [RFC PATCH v2 04/48] net: Declare MSG_SPLICE_PAGES internal sendmsg() flag David Howells
2023-03-30 14:28   ` Willem de Bruijn
2023-03-30 15:07   ` David Howells
2023-03-30 17:51     ` Willem de Bruijn
2023-03-29 14:13 ` [RFC PATCH v2 05/48] mm: Move the page fragment allocator from page_alloc.c into its own file David Howells
2023-03-29 14:13 ` [RFC PATCH v2 06/48] mm: Make the page_frag_cache allocator use multipage folios David Howells
2023-03-29 14:13 ` [RFC PATCH v2 07/48] mm: Make the page_frag_cache allocator use per-cpu David Howells
2023-03-29 14:13 ` [RFC PATCH v2 08/48] tcp: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 09/48] tcp: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 10/48] tcp: Convert do_tcp_sendpages() to use MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 11/48] tcp_bpf: Inline do_tcp_sendpages as it's now a wrapper around tcp_sendmsg David Howells
2023-03-29 14:13 ` [RFC PATCH v2 12/48] espintcp: Inline do_tcp_sendpages() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 13/48] tls: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 14/48] siw: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 15/48] tcp: Fold do_tcp_sendpages() into tcp_sendpage_locked() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 16/48] ip, udp: Support MSG_SPLICE_PAGES David Howells
2023-03-30 14:20   ` Willem de Bruijn
2023-03-30 14:39   ` David Howells
2023-03-30 17:46     ` Willem de Bruijn
2023-03-30 15:11   ` David Howells
2023-03-30 17:55     ` Willem de Bruijn
2023-03-30 19:49     ` David Howells
2023-03-29 14:13 ` [RFC PATCH v2 17/48] ip, udp: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 18/48] udp: Convert udp_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 19/48] af_unix: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 20/48] af_unix: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 21/48] crypto: af_alg: Pin pages rather than ref'ing if appropriate David Howells
2023-03-29 14:13 ` [RFC PATCH v2 22/48] crypto: af_alg: Use netfs_extract_iter_to_sg() to create scatterlists David Howells
2023-03-29 14:13 ` [RFC PATCH v2 23/48] crypto: af_alg: Indent the loop in af_alg_sendmsg() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 24/48] crypto: af_alg: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 25/48] crypto: af_alg: Convert af_alg_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 26/48] crypto: af_alg/hash: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 27/48] splice, net: Use sendmsg(MSG_SPLICE_PAGES) rather than ->sendpage() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 28/48] splice: Reimplement splice_to_socket() to pass multiple bufs to sendmsg() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 29/48] Remove file->f_op->sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 30/48] siw: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage to transmit David Howells
2023-03-29 15:18   ` Bernard Metzler
2023-03-29 15:32   ` David Howells
2023-03-29 14:13 ` [RFC PATCH v2 31/48] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 32/48] iscsi: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 33/48] iscsi: Assume "sendpage" is okay in iscsi_tcp_segment_map() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 34/48] tcp_bpf: Make tcp_bpf_sendpage() go through tcp_bpf_sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-29 14:13 ` [RFC PATCH v2 35/48] net: Use sendmsg(MSG_SPLICE_PAGES) not sendpage in skb_send_sock() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 36/48] algif: Remove hash_sendpage*() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 37/48] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage() David Howells
2023-03-30  1:45   ` Xiubo Li
2023-03-30  6:48   ` David Howells
2023-03-31 13:05     ` Xiubo Li
2023-04-03  3:27     ` Xiubo Li
2023-04-03  8:32     ` David Howells
2023-04-10  0:38       ` Xiubo Li
2023-03-29 14:13 ` [RFC PATCH v2 38/48] rds: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 39/48] dlm: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 40/48] sunrpc: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage David Howells
2023-03-29 15:28   ` Chuck Lever III
2023-03-29 19:58   ` David Howells
2023-03-30  9:29   ` David Howells
2023-03-30  9:41   ` David Howells
2023-03-30 13:16     ` Chuck Lever III
2023-03-30 13:01   ` David Howells
2023-03-30 13:16   ` David Howells
2023-03-30 13:27     ` Chuck Lever III
2023-03-30 14:26     ` David Howells
2023-03-30 16:36       ` Chuck Lever III
2023-04-14 14:41         ` Daire Byrne
2023-03-29 14:13 ` [RFC PATCH v2 41/48] sunrpc: Rely on TCP sendmsg + MSG_SPLICE_PAGES to copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 42/48] nvme: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 43/48] kcm: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 44/48] smc: Drop smc_sendpage() in favour of smc_sendmsg() + MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` David Howells [this message]
2023-03-29 14:13 ` [RFC PATCH v2 46/48] drbd: Use sendmsg(MSG_SPLICE_PAGES) rather than sendmsg() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 47/48] drdb: Send an entire bio in a single sendmsg David Howells
2023-03-29 14:13 ` [RFC PATCH v2 48/48] sock: Remove ->sendpage*() in favour of sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-29 14:23   ` Hannes Reinecke
2023-03-29 14:39   ` David Howells

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230329141354.516864-46-dhowells@redhat.com \
    --to=dhowells@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=brauner@kernel.org \
    --cc=chuck.lever@oracle.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=hch@infradead.org \
    --cc=jlayton@kernel.org \
    --cc=jlbec@evilplan.org \
    --cc=joseph.qi@linux.alibaba.com \
    --cc=kuba@kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mark@fasheh.com \
    --cc=netdev@vger.kernel.org \
    --cc=ocfs2-devel@oss.oracle.com \
    --cc=pabeni@redhat.com \
    --cc=torvalds@linux-foundation.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).