io-uring.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Olivier Langlois <olivier@trillion01.com>
To: Tony Battersby <tonyb@cybernetics.com>,
	"Eric W. Biederman" <ebiederm@xmission.com>,
	Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	linux-fsdevel <linux-fsdevel@vger.kernel.org>,
	io-uring <io-uring@vger.kernel.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Jens Axboe <axboe@kernel.dk>,
	"Pavel Begunkov>" <asml.silence@gmail.com>
Subject: Re: [PATCH] coredump: Limit what can interrupt coredumps
Date: Wed, 11 Aug 2021 16:47:58 -0400	[thread overview]
Message-ID: <cbfa38bf5536fe37850823c68ea23f6c93dda154.camel@trillion01.com> (raw)
In-Reply-To: <8af373ec-9609-35a4-f185-f9bdc63d39b7@cybernetics.com>

On Tue, 2021-08-10 at 17:48 -0400, Tony Battersby wrote:
> > 
> I just ran into this problem also - coredumps from an io_uring
> program
> to a pipe are truncated.  But I am using kernel 5.10.57, which does
> NOT
> have commit 12db8b690010 ("entry: Add support for TIF_NOTIFY_SIGNAL")
> or
> commit 06af8679449d ("coredump: Limit what can interrupt
> coredumps"). 
> Kernel 5.4 works though, so I bisected the problem to commit
> f38c7e3abfba ("io_uring: ensure async buffered read-retry is setup
> properly") in kernel 5.9.  Note that my io_uring program uses only
> async
> buffered reads, which may be why this particular commit makes a
> difference to my program.
> 
> My io_uring program is a multi-purpose long-running program with many
> threads.  Most threads don't use io_uring but a few of them do. 
> Normally, my core dumps are piped to a program so that they can be
> compressed before being written to disk, but I can also test writing
> the
> core dumps directly to disk.  This is what I have found:
> 
> *) Unpatched 5.10.57: if a thread that doesn't use io_uring triggers
> a
> coredump, the core file is written correctly, whether it is written
> to
> disk or piped to a program, even if another thread is using io_uring
> at
> the same time.
> 
> *) Unpatched 5.10.57: if a thread that uses io_uring triggers a
> coredump, the core file is truncated, whether written directly to
> disk
> or piped to a program.
> 
> *) 5.10.57+backport 06af8679449d: if a thread that uses io_uring
> triggers a coredump, and the core is written directly to disk, then
> it
> is written correctly.
> 
> *) 5.10.57+backport 06af8679449d: if a thread that uses io_uring
> triggers a coredump, and the core is piped to a program, then it is
> truncated.
> 
> *) 5.10.57+revert f38c7e3abfba: core dumps are written correctly,
> whether written directly to disk or piped to a program.
> 
> Tony Battersby
> Cybernetics
> 
Tony,

this is super interesting details. I'm leaving for few days so I will
not be able to look into it until I am back but here is my
interpretation of your findings:

f38c7e3abfba makes it more likely that your task ends up in a fd read
wait queue. Previously the io_uring req queuing was failing and
returning EAGAIN. Now it ends up using io uring fast poll.

When the core dump gets written through a pipe, pipe_write must block
waiting for some event. If the task gets waken up by the io_uring wait
queue entry instead, it must somehow make pipe_write fails.

So the problem must be a mix of TIF_NOTIFY_SIGNAL and the fact that
io_uring wait queue entries aren't cleaned up while doing the core
dump.

I have a new modif to try out. I'll hopefully be able to submit a patch
to fix that once I come back (I cannot do it now or else, I'll never
leave ;-))



  reply	other threads:[~2021-08-11 20:48 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <192c9697e379bf084636a8213108be6c3b948d0b.camel@trillion01.com>
     [not found] ` <9692dbb420eef43a9775f425cb8f6f33c9ba2db9.camel@trillion01.com>
     [not found]   ` <87h7i694ij.fsf_-_@disp2133>
2021-06-09 20:33     ` [RFC] coredump: Do not interrupt dump for TIF_NOTIFY_SIGNAL Linus Torvalds
2021-06-09 20:48       ` Eric W. Biederman
2021-06-09 20:52         ` Linus Torvalds
2021-06-09 21:02       ` Olivier Langlois
2021-06-09 21:05         ` Eric W. Biederman
2021-06-09 21:26           ` Olivier Langlois
2021-06-09 21:56             ` Olivier Langlois
2021-06-10 14:26             ` Eric W. Biederman
2021-06-10 15:17               ` Olivier Langlois
2021-06-10 18:58               ` [CFT}[PATCH] coredump: Limit what can interrupt coredumps Eric W. Biederman
2021-06-10 19:10                 ` Linus Torvalds
2021-06-10 19:18                   ` Eric W. Biederman
2021-06-10 19:50                     ` Linus Torvalds
2021-06-10 20:11                       ` [PATCH] " Eric W. Biederman
2021-06-10 21:04                         ` Linus Torvalds
2021-06-12 14:36                         ` Olivier Langlois
2021-06-12 16:26                           ` Jens Axboe
2021-06-14 14:10                         ` Oleg Nesterov
2021-06-14 16:37                           ` Eric W. Biederman
2021-06-14 16:59                             ` Oleg Nesterov
2021-06-15 22:08                           ` Eric W. Biederman
2021-06-16 19:23                             ` Olivier Langlois
2021-06-16 20:00                               ` Eric W. Biederman
2021-06-18 20:05                                 ` Olivier Langlois
2021-08-05 13:06                             ` Olivier Langlois
2021-08-10 21:48                               ` Tony Battersby
2021-08-11 20:47                                 ` Olivier Langlois [this message]
2021-08-12  1:55                                 ` Jens Axboe
2021-08-12 13:53                                   ` Tony Battersby
2021-08-15 20:42                                   ` Olivier Langlois
2021-08-16 13:02                                     ` Pavel Begunkov
2021-08-16 13:06                                       ` Pavel Begunkov
2021-08-17 18:15                                     ` Jens Axboe
2021-08-17 18:24                                       ` Jens Axboe
2021-08-17 19:29                                         ` Tony Battersby
2021-08-17 19:59                                           ` Jens Axboe
2021-08-17 21:28                                             ` Jens Axboe
2021-08-17 21:39                                               ` Tony Battersby
2021-08-17 22:05                                                 ` Jens Axboe
2021-08-18 14:37                                                   ` Tony Battersby
2021-08-18 14:46                                                     ` Jens Axboe
2021-08-18  2:57                                               ` Jens Axboe
2021-08-18  2:58                                                 ` Jens Axboe
2021-08-21 10:08                                                 ` Olivier Langlois
2021-08-21 16:47                                                   ` Olivier Langlois
2021-08-21 16:51                                                     ` Jens Axboe
2021-08-21 17:21                                                       ` Olivier Langlois
2021-08-21  9:52                                         ` Olivier Langlois
2021-08-21  9:48                                       ` Olivier Langlois
2021-10-22 14:13     ` [RFC] coredump: Do not interrupt dump for TIF_NOTIFY_SIGNAL Pavel Begunkov
2021-12-24  1:34       ` Olivier Langlois
2021-12-24 10:37         ` Pavel Begunkov
2021-12-24 19:52           ` Eric W. Biederman
2021-12-28 11:24             ` Pavel Begunkov
2022-03-14 23:58               ` Eric W. Biederman
     [not found]                 ` <8218f1a245d054c940e25142fd00a5f17238d078.camel@trillion01.com>
2022-06-01  3:15                   ` Jens Axboe
2022-07-20 16:49                     ` [PATCH 0/2] coredump: Allow io_uring using apps to dump to pipes Eric W. Biederman
2022-07-20 16:50                       ` [PATCH 1/2] signal: Move stopping for the coredump from do_exit into get_signal Eric W. Biederman
2022-07-20 16:51                       ` [PATCH 2/2] coredump: Allow coredumps to pipes to work with io_uring Eric W. Biederman
2022-08-22 21:16                         ` Olivier Langlois
2022-08-23  3:35                           ` Olivier Langlois
2022-08-23 18:22                             ` Eric W. Biederman
2022-08-23 18:27                               ` Jens Axboe
2022-08-24 15:11                                 ` Eric W. Biederman
2022-08-24 15:51                                   ` Jens Axboe
2022-01-05 19:39           ` [RFC] coredump: Do not interrupt dump for TIF_NOTIFY_SIGNAL Olivier Langlois

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=cbfa38bf5536fe37850823c68ea23f6c93dda154.camel@trillion01.com \
    --to=olivier@trillion01.com \
    --cc=asml.silence@gmail.com \
    --cc=axboe@kernel.dk \
    --cc=ebiederm@xmission.com \
    --cc=io-uring@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=oleg@redhat.com \
    --cc=tonyb@cybernetics.com \
    --cc=torvalds@linux-foundation.org \
    --cc=viro@zeniv.linux.org.uk \
    /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).