linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Matthew Wilcox <willy@infradead.org>
To: trondmy@kernel.org
Cc: Christoph Hellwig <hch@infradead.org>,
	"Darrick J. Wong" <djwong@kernel.org>,
	Jens Axboe <axboe@kernel.dk>,
	linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	Brian Foster <bfoster@redhat.com>
Subject: Re: [PATCH] iomap: Address soft lockup in iomap_finish_ioend()
Date: Fri, 31 Dec 2021 01:42:20 +0000	[thread overview]
Message-ID: <Yc5f/C1I+N8MPHcd@casper.infradead.org> (raw)
In-Reply-To: <20211230193522.55520-1-trondmy@kernel.org>

On Thu, Dec 30, 2021 at 02:35:22PM -0500, trondmy@kernel.org wrote:
>  Workqueue: xfs-conv/md127 xfs_end_io [xfs]
>  RIP: 0010:_raw_spin_unlock_irqrestore+0x11/0x20
>  Code: 7c ff 48 29 e8 4c 39 e0 76 cf 80 0b 08 eb 8c 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 e8 e6 db 7e ff 66 90 48 89 f7 57 9d <0f> 1f 44 00 00 c3 66 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 8b 07
>  RSP: 0018:ffffac51d26dfd18 EFLAGS: 00000202 ORIG_RAX: ffffffffffffff12
>  RAX: 0000000000000001 RBX: ffffffff980085a0 RCX: dead000000000200
>  RDX: ffffac51d3893c40 RSI: 0000000000000202 RDI: 0000000000000202
>  RBP: 0000000000000202 R08: ffffac51d3893c40 R09: 0000000000000000
>  R10: 00000000000000b9 R11: 00000000000004b3 R12: 0000000000000a20
>  R13: ffffd228f3e5a200 R14: ffff963cf7f58d10 R15: ffffd228f3e5a200
>  FS:  0000000000000000(0000) GS:ffff9625bfb00000(0000) knlGS:0000000000000000
>  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
>  CR2: 00007f5035487500 CR3: 0000000432810004 CR4: 00000000003706e0
>  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
>  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
>  Call Trace:
>   wake_up_page_bit+0x8a/0x110
>   iomap_finish_ioend+0xd7/0x1c0
>   iomap_finish_ioends+0x7f/0xb0

> +++ b/fs/iomap/buffered-io.c
> @@ -1052,9 +1052,11 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error)
>  			next = bio->bi_private;
>  
>  		/* walk each page on bio, ending page IO on them */
> -		bio_for_each_segment_all(bv, bio, iter_all)
> +		bio_for_each_segment_all(bv, bio, iter_all) {
>  			iomap_finish_page_writeback(inode, bv->bv_page, error,
>  					bv->bv_len);
> +			cond_resched();
> +		}
>  		bio_put(bio);
>  	}
>  	/* The ioend has been freed by bio_put() */

As I recall, iomap_finish_ioend() can be called in softirq (or even
hardirq?) context currently.  I think we've seen similar things before,
and the solution suggested at the time was to aggregate fewer writeback
pages into a single bio.

  parent reply	other threads:[~2021-12-31  1:42 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-12-30 19:35 [PATCH] iomap: Address soft lockup in iomap_finish_ioend() trondmy
2021-12-30 21:24 ` Jens Axboe
2021-12-30 22:25   ` Trond Myklebust
2021-12-30 22:27     ` Jens Axboe
2021-12-30 22:55       ` Trond Myklebust
2021-12-31  1:42 ` Matthew Wilcox [this message]
2021-12-31  6:16   ` Trond Myklebust
2022-01-01  3:55     ` Dave Chinner
2022-01-01 17:39       ` Trond Myklebust
2022-01-03 22:03         ` Dave Chinner
2022-01-04  0:04           ` Trond Myklebust
2022-01-04  1:22             ` Dave Chinner
2022-01-04  3:01               ` Trond Myklebust
2022-01-04  7:08               ` hch
2022-01-04 18:08                 ` Matthew Wilcox
2022-01-04 18:14                   ` hch
2022-01-04 19:22                     ` Darrick J. Wong
2022-01-04 21:52                       ` Dave Chinner
2022-01-04 23:12                         ` Darrick J. Wong
2022-01-05  2:10                           ` Dave Chinner
2022-01-05 13:56                             ` Brian Foster
2022-01-05 22:04                               ` Dave Chinner
2022-01-06 16:44                                 ` Brian Foster
2022-01-10  8:18                                   ` Dave Chinner
2022-01-10 17:45                                     ` Brian Foster
2022-01-10 18:11                                       ` hch
2022-01-11 14:33                                       ` Trond Myklebust
2022-01-05 13:42                           ` hch
2022-01-04 21:16                 ` Dave Chinner
2022-01-05 13:43                   ` hch
2022-01-05 22:34                     ` Dave Chinner
2022-01-05  2:09               ` Trond Myklebust
2022-01-05 20:45                 ` Trond Myklebust
2022-01-05 22:48                   ` Dave Chinner
2022-01-05 23:29                     ` Trond Myklebust
2022-01-06  0:01                     ` Darrick J. Wong
2022-01-09 23:09                       ` Dave Chinner
2022-01-06 18:36                     ` Trond Myklebust
2022-01-06 18:38                       ` Trond Myklebust
2022-01-06 20:07                       ` Brian Foster
2022-01-07  3:08                         ` Trond Myklebust
2022-01-07 15:15                           ` Brian Foster
2022-01-09 23:34                       ` Dave Chinner
2022-01-10 23:37                       ` Dave Chinner
2022-01-11  0:08                         ` Dave Chinner
2022-01-13 17:01                         ` Trond Myklebust
2022-01-17 17:24                           ` Trond Myklebust
2022-01-17 17:36                             ` Darrick J. Wong
2022-01-04 13:36         ` Brian Foster
2022-01-04 19:23           ` Darrick J. Wong
2022-01-05  2:31 ` [iomap] f5934dda54: BUG:sleeping_function_called_from_invalid_context_at_fs/iomap/buffered-io.c kernel test robot

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=Yc5f/C1I+N8MPHcd@casper.infradead.org \
    --to=willy@infradead.org \
    --cc=axboe@kernel.dk \
    --cc=bfoster@redhat.com \
    --cc=djwong@kernel.org \
    --cc=hch@infradead.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=trondmy@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
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;
as well as URLs for NNTP newsgroup(s).