public inbox for [email protected]
 help / color / mirror / Atom feed
From: Kanchan Joshi <[email protected]>
To: Ming Lei <[email protected]>
Cc: Jens Axboe <[email protected]>, [email protected]
Subject: Re: [PATCH] io_uring: complete request via task work in case of DEFER_TASKRUN
Date: Fri, 14 Apr 2023 17:22:38 +0530	[thread overview]
Message-ID: <20230414115238.GB5049@green5> (raw)
In-Reply-To: <[email protected]>

[-- Attachment #1: Type: text/plain, Size: 1902 bytes --]

On Fri, Apr 14, 2023 at 03:53:13PM +0800, Ming Lei wrote:
>So far io_req_complete_post() only covers DEFER_TASKRUN by completing
>request via task work when the request is completed from IOWQ.
>
>However, uring command could be completed from any context, and if io
>uring is setup with DEFER_TASKRUN, the command is required to be
>completed from current context, otherwise wait on IORING_ENTER_GETEVENTS
>can't be wakeup, and may hang forever.
>
>The issue can be observed on removing ublk device, but turns out it is
>one generic issue for uring command & DEFER_TASKRUN, so solve it in
>io_uring core code.

Thanks for sharing, this has been fine for nvme-passthrough side though.
We usually test with DEFER_TASKRUN option, as both fio and t/io_uring
set the option.

>Link: https://lore.kernel.org/linux-block/[email protected]/
>Reported-by: Jens Axboe <[email protected]>
>Cc: Kanchan Joshi <[email protected]>
>Signed-off-by: Ming Lei <[email protected]>
>---
> io_uring/io_uring.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
>diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
>index 9083a8466ebf..9f6f92ed60b2 100644
>--- a/io_uring/io_uring.c
>+++ b/io_uring/io_uring.c
>@@ -1012,7 +1012,7 @@ static void __io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
>
> void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
> {
>-	if (req->ctx->task_complete && (issue_flags & IO_URING_F_IOWQ)) {
>+	if (req->ctx->task_complete && req->ctx->submitter_task != current) {
> 		req->io_task_work.func = io_req_task_complete;
> 		io_req_task_work_add(req);

In nvme-side, we always complete in task context, so this seems bit hard
to produce.
But this patch ensures that task-work is setup if it is needed, and
caller/driver did not get to set that explicitly. So looks fine to me.
FWIW, I do not see regression in nvme tests.

[-- Attachment #2: Type: text/plain, Size: 0 bytes --]



  reply	other threads:[~2023-04-14 11:53 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20230414075422epcas5p3ae5de53e643a448f19df82a7a1d5cd1c@epcas5p3.samsung.com>
2023-04-14  7:53 ` [PATCH] io_uring: complete request via task work in case of DEFER_TASKRUN Ming Lei
2023-04-14 11:52   ` Kanchan Joshi [this message]
2023-04-14 12:39   ` Jens Axboe
2023-04-14 13:01   ` Pavel Begunkov
2023-04-14 13:53     ` Ming Lei
2023-04-14 14:13       ` Kanchan Joshi
2023-04-14 14:53         ` Ming Lei
2023-04-14 15:07       ` Pavel Begunkov
2023-04-14 15:42         ` Ming Lei
2023-04-15 23:15           ` Pavel Begunkov
2023-04-16 10:05             ` Ming Lei

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=20230414115238.GB5049@green5 \
    [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