From: Steven Rostedt <rostedt@goodmis.org>
To: Marco Elver <elver@google.com>
Cc: "Paul E. McKenney" <paulmck@kernel.org>,
Anders Roxell <anders.roxell@linaro.org>,
Andrew Morton <akpm@linux-foundation.org>,
Alexander Potapenko <glider@google.com>,
Dmitry Vyukov <dvyukov@google.com>, Jann Horn <jannh@google.com>,
Mark Rutland <mark.rutland@arm.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Linux-MM <linux-mm@kvack.org>,
kasan-dev <kasan-dev@googlegroups.com>,
rcu@vger.kernel.org, Peter Zijlstra <peterz@infradead.org>,
Tejun Heo <tj@kernel.org>, Lai Jiangshan <jiangshanlai@gmail.com>
Subject: Re: [PATCH] kfence: Avoid stalling work queue task without allocations
Date: Mon, 23 Nov 2020 11:36:59 -0500 [thread overview]
Message-ID: <20201123113659.3d1fd866@gandalf.local.home> (raw)
In-Reply-To: <20201123112812.19e918b3@gandalf.local.home>
On Mon, 23 Nov 2020 11:28:12 -0500
Steven Rostedt <rostedt@goodmis.org> wrote:
> I noticed:
>
>
> [ 237.650900] enabling event benchmark_event
>
> In both traces. Could you disable CONFIG_TRACEPOINT_BENCHMARK and see if
> the issue goes away. That event kicks off a thread that spins in a tight
> loop for some time and could possibly cause some issues.
>
> It still shouldn't break things, we can narrow it down if it is the culprit.
And it probably is the issue because that thread will never sleep! It runs
a loop of:
static int benchmark_event_kthread(void *arg)
{
/* sleep a bit to make sure the tracepoint gets activated */
msleep(100);
while (!kthread_should_stop()) {
trace_do_benchmark();
/*
* We don't go to sleep, but let others run as well.
* This is basically a "yield()" to let any task that
* wants to run, schedule in, but if the CPU is idle,
* we'll keep burning cycles.
*
* Note the tasks_rcu_qs() version of cond_resched() will
* notify synchronize_rcu_tasks() that this thread has
* passed a quiescent state for rcu_tasks. Otherwise
* this thread will never voluntarily schedule which would
* block synchronize_rcu_tasks() indefinitely.
*/
cond_resched_tasks_rcu_qs();
}
return 0;
}
Did something change, where that "cond_resched_tasks_rcu_qs()" doesn't let
things progress on ARM64?
I noticed that you have PREEMPT enabled so this will only be preempted when
its schedule time runs out and something else wants to run. How would that
affect other threads?
-- Steve
next prev parent reply other threads:[~2020-11-23 16:37 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-10 13:53 [PATCH] kfence: Avoid stalling work queue task without allocations Marco Elver
2020-11-10 14:25 ` Dmitry Vyukov
2020-11-10 14:53 ` Marco Elver
2020-11-10 23:23 ` Anders Roxell
2020-11-11 8:29 ` Marco Elver
2020-11-11 13:38 ` Marco Elver
2020-11-11 18:05 ` Steven Rostedt
2020-11-11 18:23 ` Paul E. McKenney
2020-11-11 18:34 ` Marco Elver
2020-11-11 19:21 ` Paul E. McKenney
2020-11-11 20:21 ` Marco Elver
2020-11-12 0:11 ` Paul E. McKenney
2020-11-12 12:49 ` Marco Elver
2020-11-12 16:14 ` Marco Elver
2020-11-12 17:54 ` Paul E. McKenney
2020-11-12 18:12 ` Marco Elver
2020-11-12 20:00 ` Paul E. McKenney
2020-11-13 11:06 ` Marco Elver
2020-11-13 17:20 ` Paul E. McKenney
2020-11-13 17:57 ` Paul E. McKenney
2020-11-17 10:52 ` Marco Elver
2020-11-17 18:29 ` Paul E. McKenney
2020-11-18 22:56 ` Marco Elver
2020-11-18 23:38 ` Paul E. McKenney
2020-11-19 12:53 ` Marco Elver
2020-11-19 15:14 ` Paul E. McKenney
2020-11-19 17:02 ` Marco Elver
2020-11-19 18:48 ` Paul E. McKenney
2020-11-19 19:38 ` linux-next: stall warnings and deadlock on Arm64 (was: [PATCH] kfence: Avoid stalling...) Marco Elver
2020-11-19 21:35 ` Paul E. McKenney
2020-11-19 22:53 ` Will Deacon
2020-11-20 10:30 ` Mark Rutland
2020-11-20 14:03 ` Marco Elver
2020-11-23 19:32 ` Mark Rutland
2020-11-24 14:03 ` Marco Elver
2020-11-24 15:01 ` Paul E. McKenney
2020-11-24 19:43 ` Mark Rutland
2020-11-24 20:32 ` Steven Rostedt
2020-11-24 19:30 ` Mark Rutland
2020-11-25 9:45 ` Marco Elver
2020-11-25 10:28 ` Mark Rutland
2020-11-20 14:19 ` Marco Elver
2020-11-20 14:39 ` Paul E. McKenney
2020-11-20 15:22 ` Mark Rutland
2020-11-20 17:38 ` Paul E. McKenney
2020-11-20 18:02 ` Mark Rutland
2020-11-20 18:57 ` Paul E. McKenney
2020-11-20 15:26 ` Steven Rostedt
2020-11-20 18:17 ` Marco Elver
2020-11-20 18:57 ` Steven Rostedt
2020-11-20 19:16 ` Steven Rostedt
2020-11-20 19:22 ` Marco Elver
2020-11-20 19:27 ` [PATCH] kfence: Avoid stalling work queue task without allocations Steven Rostedt
2020-11-23 15:27 ` Marco Elver
2020-11-23 16:28 ` Steven Rostedt
2020-11-23 16:36 ` Steven Rostedt [this message]
2020-11-23 18:53 ` Marco Elver
2020-11-23 18:42 ` Steven Rostedt
2020-11-24 2:59 ` Boqun Feng
2020-11-24 3:44 ` Paul E. McKenney
2020-11-11 18:21 ` Paul E. McKenney
2020-11-11 15:01 ` Anders Roxell
2020-11-11 15:22 ` Marco Elver
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=20201123113659.3d1fd866@gandalf.local.home \
--to=rostedt@goodmis.org \
--cc=akpm@linux-foundation.org \
--cc=anders.roxell@linaro.org \
--cc=dvyukov@google.com \
--cc=elver@google.com \
--cc=glider@google.com \
--cc=jannh@google.com \
--cc=jiangshanlai@gmail.com \
--cc=kasan-dev@googlegroups.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mark.rutland@arm.com \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=rcu@vger.kernel.org \
--cc=tj@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).