Linux-Block Archive on lore.kernel.org
 help / color / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: linux-fsdevel@vger.kernel.org, linux-aio@kvack.org,
	linux-block@vger.kernel.org, linux-arch@vger.kernel.org
Cc: hch@lst.de, jmoyer@redhat.com, avi@scylladb.com,
	Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 07/15] io_uring: add submission side request cache
Date: Wed,  9 Jan 2019 19:43:56 -0700
Message-ID: <20190110024404.25372-8-axboe@kernel.dk> (raw)
In-Reply-To: <20190110024404.25372-1-axboe@kernel.dk>

We have to add each submitted polled request to the io_ring_ctx
poll_submitted list, which means we have to grab the poll_lock. We
already use the block plug to batch submissions if we're doing a batch
of IO submissions, extend that to cover the poll requests internally as
well.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 122 +++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 106 insertions(+), 16 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index c872bfb32a03..f7938156552f 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -113,6 +113,21 @@ struct sqe_submit {
 	unsigned index;
 };
 
+struct io_submit_state {
+	struct io_ring_ctx *ctx;
+
+	struct blk_plug plug;
+#ifdef CONFIG_BLOCK
+	struct blk_plug_cb plug_cb;
+#endif
+
+	/*
+	 * Polled iocbs that have been submitted, but not added to the ctx yet
+	 */
+	struct list_head req_list;
+	unsigned int req_count;
+};
+
 static struct kmem_cache *kiocb_cachep;
 
 static const struct file_operations io_scqring_fops;
@@ -480,21 +495,29 @@ static inline void io_rw_done(struct kiocb *req, ssize_t ret)
 }
 
 /*
- * After the iocb has been issued, it's safe to be found on the poll list.
- * Adding the kiocb to the list AFTER submission ensures that we don't
- * find it from a io_getevents() thread before the issuer is done accessing
- * the kiocb cookie.
+ * Called either at the end of IO submission, or through a plug callback
+ * because we're going to schedule. Moves out local batch of requests to
+ * the ctx poll list, so they can be found for polling + reaping.
  */
-static void io_iopoll_kiocb_issued(struct io_kiocb *kiocb)
+static void io_flush_state_reqs(struct io_ring_ctx *ctx,
+				 struct io_submit_state *state)
 {
+	spin_lock(&ctx->poll_lock);
+	list_splice_tail_init(&state->req_list, &ctx->poll_submitted);
+	spin_unlock(&ctx->poll_lock);
+	state->req_count = 0;
+}
+
+static void io_iopoll_iocb_add_list(struct io_kiocb *kiocb)
+{
+	const int front = test_bit(KIOCB_F_IOPOLL_COMPLETED, &kiocb->ki_flags);
+	struct io_ring_ctx *ctx = kiocb->ki_ctx;
+
 	/*
 	 * For fast devices, IO may have already completed. If it has, add
 	 * it to the front so we find it first. We can't add to the poll_done
 	 * list as that's unlocked from the completion side.
 	 */
-	const int front = test_bit(KIOCB_F_IOPOLL_COMPLETED, &kiocb->ki_flags);
-	struct io_ring_ctx *ctx = kiocb->ki_ctx;
-
 	spin_lock(&ctx->poll_lock);
 	if (front)
 		list_add(&kiocb->ki_list, &ctx->poll_submitted);
@@ -503,6 +526,33 @@ static void io_iopoll_kiocb_issued(struct io_kiocb *kiocb)
 	spin_unlock(&ctx->poll_lock);
 }
 
+static void io_iopoll_iocb_add_state(struct io_submit_state *state,
+				     struct io_kiocb *kiocb)
+{
+	if (test_bit(KIOCB_F_IOPOLL_COMPLETED, &kiocb->ki_flags))
+		list_add(&kiocb->ki_list, &state->req_list);
+	else
+		list_add_tail(&kiocb->ki_list, &state->req_list);
+
+	if (++state->req_count >= IO_IOPOLL_BATCH)
+		io_flush_state_reqs(state->ctx, state);
+}
+
+/*
+ * After the iocb has been issued, it's safe to be found on the poll list.
+ * Adding the kiocb to the list AFTER submission ensures that we don't
+ * find it from a io_getevents() thread before the issuer is done accessing
+ * the kiocb cookie.
+ */
+static void io_iopoll_kiocb_issued(struct io_submit_state *state,
+				   struct io_kiocb *kiocb)
+{
+	if (!state || !IS_ENABLED(CONFIG_BLOCK))
+		io_iopoll_iocb_add_list(kiocb);
+	else
+		io_iopoll_iocb_add_state(state, kiocb);
+}
+
 static ssize_t io_read(struct io_kiocb *kiocb, const struct io_uring_sqe *sqe)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
@@ -624,7 +674,8 @@ static int io_fsync(struct io_kiocb *kiocb, const struct io_uring_sqe *sqe,
 	return 0;
 }
 
-static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s)
+static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
+			 struct io_submit_state *state)
 {
 	const struct io_uring_sqe *sqe = s->sqe;
 	struct io_kiocb *req;
@@ -673,7 +724,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s)
 			ret = -EAGAIN;
 			goto out_put_req;
 		}
-		io_iopoll_kiocb_issued(req);
+		io_iopoll_kiocb_issued(state, req);
 	}
 	return 0;
 out_put_req:
@@ -681,6 +732,43 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s)
 	return ret;
 }
 
+#ifdef CONFIG_BLOCK
+static void io_state_unplug(struct blk_plug_cb *cb, bool from_schedule)
+{
+	struct io_submit_state *state;
+
+	state = container_of(cb, struct io_submit_state, plug_cb);
+	if (!list_empty(&state->req_list))
+		io_flush_state_reqs(state->ctx, state);
+}
+#endif
+
+/*
+ * Batched submission is done, ensure local IO is flushed out.
+ */
+static void io_submit_state_end(struct io_submit_state *state)
+{
+	blk_finish_plug(&state->plug);
+	if (!list_empty(&state->req_list))
+		io_flush_state_reqs(state->ctx, state);
+}
+
+/*
+ * Start submission side cache.
+ */
+static void io_submit_state_start(struct io_submit_state *state,
+				  struct io_ring_ctx *ctx)
+{
+	state->ctx = ctx;
+	INIT_LIST_HEAD(&state->req_list);
+	state->req_count = 0;
+#ifdef CONFIG_BLOCK
+	state->plug_cb.callback = io_state_unplug;
+	blk_start_plug(&state->plug);
+	list_add(&state->plug_cb.list, &state->plug.cb_list);
+#endif
+}
+
 static void io_inc_sqring(struct io_ring_ctx *ctx)
 {
 	struct io_sq_ring *ring = ctx->sq_ring;
@@ -715,11 +803,13 @@ static bool io_peek_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 
 static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 {
+	struct io_submit_state state, *statep = NULL;
 	int i, ret = 0, submit = 0;
-	struct blk_plug plug;
 
-	if (to_submit > IO_PLUG_THRESHOLD)
-		blk_start_plug(&plug);
+	if (to_submit > IO_PLUG_THRESHOLD) {
+		io_submit_state_start(&state, ctx);
+		statep = &state;
+	}
 
 	for (i = 0; i < to_submit; i++) {
 		struct sqe_submit s;
@@ -727,7 +817,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 		if (!io_peek_sqring(ctx, &s))
 			break;
 
-		ret = io_submit_sqe(ctx, &s);
+		ret = io_submit_sqe(ctx, &s, statep);
 		if (ret)
 			break;
 
@@ -735,8 +825,8 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 		io_inc_sqring(ctx);
 	}
 
-	if (to_submit > IO_PLUG_THRESHOLD)
-		blk_finish_plug(&plug);
+	if (statep)
+		io_submit_state_end(statep);
 
 	return submit ? submit : ret;
 }
-- 
2.17.1


  parent reply index

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-10  2:43 [PATCHSET v2] io_uring IO interface Jens Axboe
2019-01-10  2:43 ` [PATCH 01/15] fs: add an iopoll method to struct file_operations Jens Axboe
2019-01-10  2:43 ` [PATCH 02/15] block: wire up block device iopoll method Jens Axboe
2019-01-10  2:43 ` [PATCH 03/15] block: add bio_set_polled() helper Jens Axboe
2019-01-10  2:43 ` [PATCH 04/15] iomap: wire up the iopoll method Jens Axboe
2019-01-10  2:43 ` [PATCH 05/15] Add io_uring IO interface Jens Axboe
2019-01-11 18:19   ` Martin K. Petersen
2019-01-11 18:34     ` Jens Axboe
2019-01-13 16:22       ` Jens Axboe
2019-01-15 17:31         ` Martin K. Petersen
2019-01-10  2:43 ` [PATCH 06/15] io_uring: support for IO polling Jens Axboe
2019-01-10  2:43 ` Jens Axboe [this message]
2019-01-10  2:43 ` [PATCH 08/15] fs: add fget_many() and fput_many() Jens Axboe
2019-01-10  2:43 ` [PATCH 09/15] io_uring: use fget/fput_many() for file references Jens Axboe
2019-01-10  2:43 ` [PATCH 10/15] io_uring: batch io_kiocb allocation Jens Axboe
2019-01-10  2:44 ` [PATCH 11/15] block: implement bio helper to add iter bvec pages to bio Jens Axboe
2019-01-10  2:44 ` [PATCH 12/15] io_uring: add support for pre-mapped user IO buffers Jens Axboe
2019-01-10  2:44 ` [PATCH 13/15] io_uring: support kernel side submission Jens Axboe
2019-01-10  2:44 ` [PATCH 14/15] io_uring: add submission polling Jens Axboe
2019-01-10  2:44 ` [PATCH 15/15] io_uring: add io_uring_event cache hit information Jens Axboe
2019-01-10 23:12   ` Jeff Moyer
2019-01-10 23:47     ` Jens Axboe
2019-01-11  9:46 ` [PATCHSET v2] io_uring IO interface Roman Penyaev
2019-01-11 16:11   ` Ilya Dryomov
2019-01-11 16:21     ` Christoph Hellwig
2019-01-11 16:39     ` Roman Penyaev
2019-01-11 18:05   ` Jens Axboe

Reply instructions:

You may reply publically 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=20190110024404.25372-8-axboe@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=avi@scylladb.com \
    --cc=hch@lst.de \
    --cc=jmoyer@redhat.com \
    --cc=linux-aio@kvack.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.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

Linux-Block Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-block/0 linux-block/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-block linux-block/ https://lore.kernel.org/linux-block \
		linux-block@vger.kernel.org
	public-inbox-index linux-block

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-block


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git