Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: io-uring@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 12/12] io_uring: support true async buffered reads, if file provides it
Date: Sat, 23 May 2020 12:57:55 -0600
Message-ID: <20200523185755.8494-13-axboe@kernel.dk> (raw)
In-Reply-To: <20200523185755.8494-1-axboe@kernel.dk>

If the file is flagged with FMODE_BUF_RASYNC, then we don't have to punt
the buffered read to an io-wq worker. Instead we can rely on page
unlocking callbacks to support retry based async IO. This is a lot more
efficient than doing async thread offload.

The retry is done similarly to how we handle poll based retry. From
the unlock callback, we simply queue the retry to a task_work based
handler.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 99 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 99 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index e95481c552ff..dd532d2634c2 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -498,6 +498,8 @@ struct io_async_rw {
 	struct iovec			*iov;
 	ssize_t				nr_segs;
 	ssize_t				size;
+	struct wait_page_queue		wpq;
+	struct callback_head		task_work;
 };
 
 struct io_async_ctx {
@@ -2568,6 +2570,99 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	return 0;
 }
 
+static void io_async_buf_cancel(struct callback_head *cb)
+{
+	struct io_async_rw *rw;
+	struct io_ring_ctx *ctx;
+	struct io_kiocb *req;
+
+	rw = container_of(cb, struct io_async_rw, task_work);
+	req = rw->wpq.wait.private;
+	ctx = req->ctx;
+
+	spin_lock_irq(&ctx->completion_lock);
+	io_cqring_fill_event(req, -ECANCELED);
+	io_commit_cqring(ctx);
+	spin_unlock_irq(&ctx->completion_lock);
+
+	io_cqring_ev_posted(ctx);
+	req_set_fail_links(req);
+	io_double_put_req(req);
+}
+
+static void io_async_buf_retry(struct callback_head *cb)
+{
+	struct io_async_rw *rw;
+	struct io_ring_ctx *ctx;
+	struct io_kiocb *req;
+
+	rw = container_of(cb, struct io_async_rw, task_work);
+	req = rw->wpq.wait.private;
+	ctx = req->ctx;
+
+	__set_current_state(TASK_RUNNING);
+	mutex_lock(&ctx->uring_lock);
+	__io_queue_sqe(req, NULL);
+	mutex_unlock(&ctx->uring_lock);
+}
+
+static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
+			     int sync, void *arg)
+{
+	struct wait_page_queue *wpq;
+	struct io_kiocb *req = wait->private;
+	struct io_async_rw *rw = &req->io->rw;
+	struct wait_page_key *key = arg;
+	struct task_struct *tsk;
+	int ret;
+
+	wpq = container_of(wait, struct wait_page_queue, wait);
+
+	ret = wake_page_match(wpq, key);
+	if (ret != 1)
+		return ret;
+
+	list_del_init(&wait->entry);
+
+	init_task_work(&rw->task_work, io_async_buf_retry);
+	/* submit ref gets dropped, acquire a new one */
+	refcount_inc(&req->refs);
+	tsk = req->task;
+	ret = task_work_add(tsk, &rw->task_work, true);
+	if (unlikely(ret)) {
+		/* queue just for cancelation */
+		init_task_work(&rw->task_work, io_async_buf_cancel);
+		tsk = io_wq_get_task(req->ctx->io_wq);
+		task_work_add(tsk, &rw->task_work, true);
+	}
+	wake_up_process(tsk);
+	return 1;
+}
+
+static bool io_rw_should_retry(struct io_kiocb *req)
+{
+	struct kiocb *kiocb = &req->rw.kiocb;
+	int ret;
+
+	/* already tried, or we're doing O_DIRECT */
+	if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_WAITQ))
+		return false;
+	/*
+	 * just use poll if we can, and don't attempt if the fs doesn't
+	 * support callback based unlocks
+	 */
+	if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC))
+		return false;
+
+	ret = kiocb_wait_page_queue_init(kiocb, &req->io->rw.wpq,
+						io_async_buf_func, req);
+	if (ret)
+		return false;
+	get_task_struct(current);
+	req->task = current;
+	return true;
+}
+
 static int io_read(struct io_kiocb *req, bool force_nonblock)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
@@ -2601,6 +2696,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock)
 	if (!ret) {
 		ssize_t ret2;
 
+retry:
 		if (req->file->f_op->read_iter)
 			ret2 = call_read_iter(req->file, kiocb, &iter);
 		else
@@ -2619,6 +2715,9 @@ static int io_read(struct io_kiocb *req, bool force_nonblock)
 			if (!(req->flags & REQ_F_NOWAIT) &&
 			    !file_can_poll(req->file))
 				req->flags |= REQ_F_MUST_PUNT;
+			if (io_rw_should_retry(req))
+				goto retry;
+			kiocb->ki_flags &= ~IOCB_WAITQ;
 			return -EAGAIN;
 		}
 	}
-- 
2.26.2


  parent reply index

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-23 18:57 [PATCHSET v2 0/12] Add support for async buffered reads Jens Axboe
2020-05-23 18:57 ` [PATCH 01/12] block: read-ahead submission should imply no-wait as well Jens Axboe
2020-05-23 18:57 ` [PATCH 02/12] mm: allow read-ahead with IOCB_NOWAIT set Jens Axboe
2020-05-23 18:57 ` [PATCH 03/12] mm: abstract out wake_page_match() from wake_page_function() Jens Axboe
2020-05-23 18:57 ` [PATCH 04/12] mm: add support for async page locking Jens Axboe
2020-05-23 18:57 ` [PATCH 05/12] mm: support async buffered reads in generic_file_buffered_read() Jens Axboe
2020-05-24 14:05   ` Trond Myklebust
2020-05-24 16:30     ` Jens Axboe
2020-05-24 16:40       ` Jens Axboe
2020-05-24 17:11         ` Trond Myklebust
2020-05-24 17:12           ` Jens Axboe
2020-05-23 18:57 ` [PATCH 06/12] fs: add FMODE_BUF_RASYNC Jens Axboe
2020-05-23 18:57 ` [PATCH 07/12] ext4: flag as supporting buffered async reads Jens Axboe
2020-05-23 18:57 ` [PATCH 08/12] block: flag block devices as supporting IOCB_WAITQ Jens Axboe
2020-05-23 18:57 ` [PATCH 09/12] xfs: flag files as supporting buffered async reads Jens Axboe
2020-05-23 18:57 ` [PATCH 10/12] btrfs: " Jens Axboe
2020-05-23 18:57 ` [PATCH 11/12] mm: add kiocb_wait_page_queue_init() helper Jens Axboe
2020-05-23 18:57 ` Jens Axboe [this message]
2020-05-25  7:29   ` [PATCH 12/12] io_uring: support true async buffered reads, if file provides it Pavel Begunkov
2020-05-25 19:59     ` Jens Axboe
2020-05-26  7:44       ` Pavel Begunkov
2020-05-26 13:50         ` Jens Axboe
2020-05-26  7:38   ` Pavel Begunkov
2020-05-26 13:47     ` Jens Axboe
2020-05-23 19:20 ` [PATCHSET v2 0/12] Add support for async buffered reads Jens Axboe
2020-05-24  9:46   ` Chris Panayis
2020-05-24 19:24     ` Jens Axboe
2020-05-24 19:21 [PATCHSET v4 " Jens Axboe
2020-05-24 19:22 ` [PATCH 12/12] io_uring: support true async buffered reads, if file provides it Jens Axboe
2020-05-26 19:51 [PATCHSET v5 0/12] Add support for async buffered reads Jens Axboe
2020-05-26 19:51 ` [PATCH 12/12] io_uring: support true async buffered reads, if file provides it Jens Axboe

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=20200523185755.8494-13-axboe@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=io-uring@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.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-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/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-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org
	public-inbox-index linux-fsdevel

Example config snippet for mirrors

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


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