public inbox for [email protected]
 help / color / mirror / Atom feed
From: Jens Axboe <[email protected]>
To: [email protected]
Cc: [email protected], [email protected],
	[email protected], [email protected],
	Jens Axboe <[email protected]>
Subject: [PATCH 12/12] io_uring: support true async buffered reads, if file provides it
Date: Tue, 26 May 2020 13:51:23 -0600	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

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 <[email protected]>
---
 fs/io_uring.c | 130 ++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 126 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index e6865afa8467..95df63b0b2ce 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -79,6 +79,7 @@
 #include <linux/fs_struct.h>
 #include <linux/splice.h>
 #include <linux/task_work.h>
+#include <linux/pagemap.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -498,6 +499,8 @@ 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 +2571,119 @@ 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;
+
+	/* never retry for NOWAIT, we just complete with -EAGAIN */
+	if (req->flags & REQ_F_NOWAIT)
+		return false;
+
+	/* 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;
+
+	/*
+	 * If request type doesn't require req->io to defer in general,
+	 * we need to allocate it here
+	 */
+	if (!req->io && __io_alloc_async_ctx(req))
+		return false;
+
+	ret = kiocb_wait_page_queue_init(kiocb, &req->io->rw.wpq,
+						io_async_buf_func, req);
+	if (!ret) {
+		get_task_struct(current);
+		req->task = current;
+		return true;
+	}
+
+	return false;
+}
+
+static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter)
+{
+	if (req->file->f_op->read_iter)
+		return call_read_iter(req->file, &req->rw.kiocb, iter);
+	return loop_rw_iter(READ, req->file, &req->rw.kiocb, iter);
+}
+
 static int io_read(struct io_kiocb *req, bool force_nonblock)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
@@ -2601,10 +2717,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock)
 	if (!ret) {
 		ssize_t ret2;
 
-		if (req->file->f_op->read_iter)
-			ret2 = call_read_iter(req->file, kiocb, &iter);
-		else
-			ret2 = loop_rw_iter(READ, req->file, kiocb, &iter);
+		ret2 = io_iter_do_read(req, &iter);
 
 		/* Catch -EAGAIN return for forced non-blocking submission */
 		if (!force_nonblock || ret2 != -EAGAIN) {
@@ -2619,6 +2732,15 @@ 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 we can retry, do so with the callbacks armed */
+			if (io_rw_should_retry(req)) {
+				ret2 = io_iter_do_read(req, &iter);
+				if (ret2 != -EAGAIN) {
+					kiocb_done(kiocb, ret2);
+					goto out_free;
+				}
+			}
+			kiocb->ki_flags &= ~IOCB_WAITQ;
 			return -EAGAIN;
 		}
 	}
-- 
2.26.2


  parent reply	other threads:[~2020-05-26 19:51 UTC|newest]

Thread overview: 71+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-26 19:51 [PATCHSET v5 0/12] Add support for async buffered reads Jens Axboe
2020-05-26 19:51 ` [PATCH 01/12] block: read-ahead submission should imply no-wait as well Jens Axboe
2020-05-26 19:51 ` [PATCH 02/12] mm: allow read-ahead with IOCB_NOWAIT set Jens Axboe
2020-05-26 20:45   ` Johannes Weiner
2020-05-26 19:51 ` [PATCH 03/12] mm: abstract out wake_page_match() from wake_page_function() Jens Axboe
2020-05-26 21:02   ` Johannes Weiner
2020-06-01 14:16   ` Matthew Wilcox
2020-05-26 19:51 ` [PATCH 04/12] mm: add support for async page locking Jens Axboe
2020-05-26 21:59   ` Johannes Weiner
2020-05-26 22:01     ` Jens Axboe
2020-05-27 16:02       ` Johannes Weiner
2020-06-01 14:26   ` Matthew Wilcox
2020-06-01 17:15     ` Jens Axboe
2020-05-26 19:51 ` [PATCH 05/12] mm: support async buffered reads in generic_file_buffered_read() Jens Axboe
2020-05-26 22:00   ` Johannes Weiner
2020-05-26 19:51 ` [PATCH 06/12] fs: add FMODE_BUF_RASYNC Jens Axboe
2020-05-26 19:51 ` [PATCH 07/12] ext4: flag as supporting buffered async reads Jens Axboe
2020-05-26 19:51 ` [PATCH 08/12] block: flag block devices as supporting IOCB_WAITQ Jens Axboe
2020-05-26 19:51 ` [PATCH 09/12] xfs: flag files as supporting buffered async reads Jens Axboe
2020-05-28 17:53   ` Darrick J. Wong
2020-05-28 19:23     ` Jens Axboe
2020-05-26 19:51 ` [PATCH 10/12] btrfs: " Jens Axboe
2020-05-26 19:57   ` Chris Mason
2020-05-26 19:51 ` [PATCH 11/12] mm: add kiocb_wait_page_queue_init() helper Jens Axboe
2020-05-26 22:01   ` Johannes Weiner
2020-05-26 19:51 ` Jens Axboe [this message]
     [not found] ` <CA+icZUWfX+QmroE6j74C7o-BdfMF5=6PdYrA=5W_JCKddqkJgQ@mail.gmail.com>
2020-05-28 17:06   ` [PATCHSET v5 0/12] Add support for async buffered reads Jens Axboe
2020-05-28 17:12     ` Sedat Dilek
2020-05-28 17:14       ` Jens Axboe
2020-05-28 18:20         ` Sedat Dilek
2020-05-29 10:02     ` Sedat Dilek
2020-05-29 11:22       ` Sedat Dilek
2020-05-30 13:36         ` Sedat Dilek
2020-05-30 18:57           ` Sedat Dilek
2020-05-31  1:57             ` Jens Axboe
     [not found]               ` <CA+icZUXxmOA-5+dukCgxfSp4eVHB+QaAHO6tsgq0iioQs3Af-w@mail.gmail.com>
2020-05-31  7:12                 ` Sedat Dilek
2020-06-01 13:35                   ` Sedat Dilek
2020-06-01 14:04                     ` Jens Axboe
2020-06-01 14:13                       ` Sedat Dilek
2020-06-01 14:14                         ` Jens Axboe
2020-06-01 14:35                           ` Jens Axboe
2020-06-01 14:43                             ` Sedat Dilek
2020-06-01 14:46                               ` Jens Axboe
2020-06-01 14:51                                 ` Sedat Dilek
2020-06-01 20:18                                 ` Sedat Dilek
     [not found] ` <[email protected]>
2020-06-04  1:04   ` Jens Axboe
2020-06-04  1:30     ` Andres Freund
2020-06-05 19:56       ` Andres Freund
2020-06-05 14:42     ` Jens Axboe
2020-06-05 20:20       ` Andres Freund
2020-06-05 20:21         ` Jens Axboe
2020-06-05 20:36         ` Andres Freund
2020-06-05 20:53           ` Jens Axboe
2020-06-05 21:13             ` Jens Axboe
2020-06-05 21:21               ` Jens Axboe
2020-06-05 22:30                 ` Andres Freund
2020-06-05 22:36                   ` Andres Freund
2020-06-05 22:49                     ` Jens Axboe
2020-06-05 22:54                       ` Andres Freund
2020-06-05 22:56                         ` Jens Axboe
2020-06-05 23:02                           ` Andres Freund
2020-06-06  0:33                 ` Sedat Dilek
2020-06-06 16:04                   ` Jens Axboe
  -- strict thread matches above, loose matches on Subject: below --
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
2020-05-23 18:57 [PATCHSET v2 0/12] Add support for async buffered reads Jens Axboe
2020-05-23 18:57 ` [PATCH 12/12] io_uring: support true async buffered reads, if file provides it Jens Axboe
2020-05-25  7:29   ` 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

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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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