From: Oleg Nesterov <oleg@redhat.com>
To: Nicholas Piggin <npiggin@gmail.com>
Cc: Frederic Weisbecker <frederic@kernel.org>,
Tejun Heo <tj@kernel.org>, Leonardo Bras <leobras@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Lai Jiangshan <jiangshanlai@gmail.com>,
linux-kernel@vger.kernel.org, Junyao Zhao <junzhao@redhat.com>,
Chris von Recklinghausen <crecklin@redhat.com>
Subject: Re: Nohz_full on boot CPU is broken (was: Re: [PATCH v2 1/1] wq: Avoid using isolated cpus' timers on queue_delayed_work)
Date: Wed, 10 Apr 2024 15:55:19 +0200 [thread overview]
Message-ID: <20240410135518.GA25421@redhat.com> (raw)
In-Reply-To: <D0G5OX8W9NH9.1HE33RVAROAJK@gmail.com>
Hi Nicholas,
On 04/10, Nicholas Piggin wrote:
>
> Thanks for this. Taking a while to page this back in, the intention is
> for housekeeping to be done by boot CPU until house keeper is awake, so
> returning smp_processor_id() seems like the right thing to do here for
> ephemeral jobs like timers and work, provided that CPU / mask is not
> stored somewhere long term by the caller.
>
> For things that set an affinity like kthread, sched, maybe managed
> irqs, and such.
>
> There are not many callers of housekeeping_any_cpu() so that's easy
> enough to verify. But similar like housekeeping_cpumask() and others
> could be an issue or at least a foot-gun, I'm not sure how well I
> convinced myself of those.
>
> Could you test like this?
>
> WARN_ON_ONCE(system_state == SYSTEM_RUNNING ||
> type != HK_TYPE_TIMER);
>
> With a comment to say other ephemeral mask types could be exempted if
> needed.
Sorry, I don't understand... Let me repeat, I know absolutely nothing
about nonhz/etc. I didn't even try to really fix the problem(s), I am
only trying to find a minimal/simple workaround to fix the problem we
hit in Red Hat.
This is what I was going to send:
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -46,7 +46,15 @@ int housekeeping_any_cpu(enum hk_type type)
if (cpu < nr_cpu_ids)
return cpu;
- return cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
+ cpu = cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
+ if (likely(cpu < nr_cpu_ids))
+ return cpu;
+ /*
+ * Unless we have another problem this can only happen
+ * at boot time before start_secondary() brings the 1st
+ * housekeeping CPU up.
+ */
+ WARN_ON_ONCE(system_state == SYSTEM_RUNNING);
}
}
return smp_processor_id();
Yes, this fixes the symptom, not the problem. And yes, "another problem"
mentioned in the comment is very possible, say "maxcpus" kernel-parameter
can be less than the first housekeeping cpu. But in this case the user
should blame himself (and I am not sure the kernel will boot).
I don't understand why do you suggest to add "|| type != HK_TYPE_TIMER",
currently all the callers of housekeeping_any_cpu() use type == HK_TIMER.
But OK, I can add this check. I guess for the case it finds another user
with type != HK_TYPE_TIMER which can't use smp_processor_id() even at
boot time or stores the returned CPU for the long term.
Will you agree with the change above or what do you suggest instead as
a simple workaround?
> It would also be nice to warn for cases that would be bugs if the boot
> CPU was not in the HK mask. Could that be done by having a
> housekeepers_online() call after smp_init() (maybe at the start of
> sched_init_smp()) that could verify there is at least one online, and
> set a flag that could be used to create warnings.
Again, I am not sure I understand, but I too thought that something like
housekeeping_check(void)
{
for_each_set_bit(type, &housekeeping.flags, HK_TYPE_MAX) {
if (!cpumask_intersects(cpu_online, housekeeping.cpumasks[type]))
panic();
}
after bringup_nonboot_cpus(setup_max_cpus).
But I am not sure this is correct and this is another (although related) issue.
Oleg.
next prev parent reply other threads:[~2024-04-10 13:56 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-30 1:00 [PATCH v2 1/1] wq: Avoid using isolated cpus' timers on queue_delayed_work Leonardo Bras
2024-01-30 1:22 ` Tejun Heo
2024-01-30 2:58 ` Leonardo Bras
2024-04-02 10:58 ` Oleg Nesterov
2024-04-03 19:12 ` Tejun Heo
2024-04-03 20:38 ` Oleg Nesterov
2024-04-05 14:04 ` Oleg Nesterov
2024-04-05 15:38 ` Tejun Heo
2024-04-05 22:03 ` Frederic Weisbecker
2024-04-05 21:52 ` Nohz_full on boot CPU is broken (was: Re: [PATCH v2 1/1] wq: Avoid using isolated cpus' timers on queue_delayed_work) Frederic Weisbecker
2024-04-07 13:09 ` Oleg Nesterov
2024-04-07 13:52 ` Oleg Nesterov
2024-04-09 12:05 ` Frederic Weisbecker
2024-04-09 12:04 ` Frederic Weisbecker
2024-04-09 13:07 ` Oleg Nesterov
2024-04-09 13:59 ` Frederic Weisbecker
2024-04-10 4:26 ` Nicholas Piggin
2024-04-10 13:55 ` Oleg Nesterov [this message]
2024-04-11 13:41 ` Oleg Nesterov
2024-04-11 14:39 ` [PATCH] sched/isolation: fix boot crash when the boot CPU is nohz_full Oleg Nesterov
2024-04-11 16:59 ` Oleg Nesterov
2024-04-13 14:17 ` [PATCH] sched/isolation: fix boot crash when maxcpus < first-housekeeping-cpu Oleg Nesterov
2024-04-18 14:54 ` Phil Auld
2024-04-18 15:40 ` Frederic Weisbecker
2024-04-24 20:05 ` [tip: sched/urgent] sched/isolation: Fix boot crash when maxcpus < first housekeeping CPU tip-bot2 for Oleg Nesterov
2024-04-28 8:13 ` Ingo Molnar
2024-04-28 13:16 ` Oleg Nesterov
2024-04-28 8:24 ` tip-bot2 for Oleg Nesterov
2024-04-15 21:37 ` [PATCH] sched/isolation: fix boot crash when the boot CPU is nohz_full Frederic Weisbecker
2024-04-18 14:50 ` Phil Auld
2024-04-22 18:50 ` Oleg Nesterov
2024-04-24 14:42 ` Phil Auld
2024-04-24 20:05 ` [tip: sched/urgent] sched/isolation: {revent " tip-bot2 for Oleg Nesterov
2024-04-24 20:41 ` Phil Auld
2024-04-28 8:14 ` Ingo Molnar
2024-04-29 11:50 ` Phil Auld
2024-04-28 8:24 ` [tip: sched/urgent] sched/isolation: Prevent " tip-bot2 for Oleg Nesterov
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=20240410135518.GA25421@redhat.com \
--to=oleg@redhat.com \
--cc=crecklin@redhat.com \
--cc=frederic@kernel.org \
--cc=jiangshanlai@gmail.com \
--cc=junzhao@redhat.com \
--cc=leobras@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=npiggin@gmail.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--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).