public inbox for [email protected]
 help / color / mirror / Atom feed
From: Dylan Yudaken <[email protected]>
To: "[email protected]" <[email protected]>,
	"[email protected]" <[email protected]>
Cc: Stefan Roesch <[email protected]>
Subject: Re: [PATCH for-next] io_uring: ensure local task_work marks task as running
Date: Wed, 21 Sep 2022 20:12:21 +0000	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

On Wed, 2022-09-21 at 13:18 -0600, Jens Axboe wrote:
> io_uring will run task_work from contexts that have been prepared for
> waiting, and in doing so it'll implicitly set the task running again
> to avoid issues with blocking conditions. The new deferred local
> task_work doesn't do that, which can result in spews on this being
> an invalid condition:
> 
> 

[  112.917576] do not call blocking ops when !TASK_RUNNING; state=1
> set at [<00000000ad64af64>] prepare_to_wait_exclusive+0x3f/0xd0
> [  112.983088] WARNING: CPU: 1 PID: 190 at kernel/sched/core.c:9819
> __might_sleep+0x5a/0x60
> [  112.987240] Modules linked in:
> [  112.990504] CPU: 1 PID: 190 Comm: io_uring Not tainted 6.0.0-rc6+
> #1617
> [  113.053136] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
> BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014
> [  113.133650] RIP: 0010:__might_sleep+0x5a/0x60
> [  113.136507] Code: ee 48 89 df 5b 31 d2 5d e9 33 ff ff ff 48 8b 90
> 30 0b 00 00 48 c7 c7 90 de 45 82 c6 05 20 8b 79 01 01 48 89 d1 e8 3a
> 49 77 00 <0f> 0b eb d1 66 90 0f 1f 44 00 00 9c 58 f6 c4 02 74 35 65
> 8b 05 ed
> [  113.223940] RSP: 0018:ffffc90000537ca0 EFLAGS: 00010286
> [  113.232903] RAX: 0000000000000000 RBX: ffffffff8246782c RCX:
> ffffffff8270bcc8
> IOPS=133.15K, BW=520MiB/s, IOS/call=32/31
> [  113.353457] RDX: ffffc90000537b50 RSI: 00000000ffffdfff RDI:
> 0000000000000001
> [  113.358970] RBP: 00000000000003bc R08: 0000000000000000 R09:
> c0000000ffffdfff
> [  113.361746] R10: 0000000000000001 R11: ffffc90000537b48 R12:
> ffff888103f97280
> [  113.424038] R13: 0000000000000000 R14: 0000000000000001 R15:
> 0000000000000001
> [  113.428009] FS:  00007f67ae7fc700(0000) GS:ffff88842fc80000(0000)
> knlGS:0000000000000000
> [  113.432794] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [  113.503186] CR2: 00007f67b8b9b3b0 CR3: 0000000102b9b005 CR4:
> 0000000000770ee0
> [  113.507291] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
> 0000000000000000
> [  113.512669] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
> 0000000000000400
> [  113.574374] PKRU: 55555554
> [  113.576800] Call Trace:
> [  113.578325]  <TASK>
> [  113.579799]  set_page_dirty_lock+0x1b/0x90
> [  113.582411]  __bio_release_pages+0x141/0x160
> [  113.673078]  ? set_next_entity+0xd7/0x190
> [  113.675632]  blk_rq_unmap_user+0xaa/0x210
> [  113.678398]  ? timerqueue_del+0x2a/0x40
> [  113.679578]  nvme_uring_task_cb+0x94/0xb0
> [  113.683025]  __io_run_local_work+0x8a/0x150
> [  113.743724]  ? io_cqring_wait+0x33d/0x500
> [  113.746091]  io_run_local_work.part.76+0x2e/0x60
> [  113.750091]  io_cqring_wait+0x2e7/0x500
> [  113.752395]  ?
> trace_event_raw_event_io_uring_req_failed+0x180/0x180
> [  113.823533]  __x64_sys_io_uring_enter+0x131/0x3c0
> [  113.827382]  ? switch_fpu_return+0x49/0xc0
> [  113.830753]  do_syscall_64+0x34/0x80
> [  113.832620]  entry_SYSCALL_64_after_hwframe+0x5e/0xc8
> 
> Ensure that we mark current as TASK_RUNNING for deferred task_work
> as well.
> 
> Fixes: c0e0d6ba25f1 ("io_uring: add IORING_SETUP_DEFER_TASKRUN")
> Reported-by: Stefan Roesch <[email protected]>
> Signed-off-by: Jens Axboe <[email protected]>
> 
> ---
> 
> diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
> index 3875ea897cdf..f359e24b46c3 100644
> --- a/io_uring/io_uring.c
> +++ b/io_uring/io_uring.c
> @@ -1215,6 +1215,7 @@ int io_run_local_work(struct io_ring_ctx *ctx)
>         if (llist_empty(&ctx->work_llist))
>                 return 0;
>  
> +       __set_current_state(TASK_RUNNING);
>         locked = mutex_trylock(&ctx->uring_lock);
>         ret = __io_run_local_work(ctx, locked);
>         if (locked)
> 


Reviewed-by: Dylan Yudaken <[email protected]>


      reply	other threads:[~2022-09-21 20:12 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-21 19:18 [PATCH for-next] io_uring: ensure local task_work marks task as running Jens Axboe
2022-09-21 20:12 ` Dylan Yudaken [this message]

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=7122df71330d01191fc5d8e211e4f3d15fd32cba.camel@fb.com \
    [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