From: Peter Zijlstra <peterz@infradead.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "Ingo Molnar" <mingo@kernel.org>,
"Linux Kernel Mailing List" <linux-kernel@vger.kernel.org>,
"Frédéric Weisbecker" <fweisbec@gmail.com>,
"Oleg Nesterov" <oleg@redhat.com>,
"Mike Galbraith" <umgwanakikbuti@gmail.com>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Steven Rostedt" <rostedt@goodmis.org>
Subject: Re: [RFC][PATCH v2 12/11] sched: Add preempt_count invariant check
Date: Tue, 29 Sep 2015 13:55:39 +0200 [thread overview]
Message-ID: <20150929115539.GE3816@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <CA+55aFzFiMf1vDLmQztJoL7QjtQeE4tbO-CY=XgzVfHUD6MgtA@mail.gmail.com>
On Tue, Sep 29, 2015 at 07:55:49AM -0400, Linus Torvalds wrote:
> On Tue, Sep 29, 2015 at 6:56 AM, Peter Zijlstra <peterz@infradead.org> wrote:
> >
> > + * Initial preempt_count value; reflects the preempt_count schedule invariant
> > + * which states that during schedule preempt_count() == 2.
>
> Is this actually *true*?
>
> preempt_count() is two only if preemption is enabled. But spinlocks do
> not actually update the preemption count if there is no preemption, so
> these kinds of checks and comments that aren't even inside #ifdef
> CONFIG_PREEMPT seem to be actively misleading.
>
> I do believe that the preempt count is stable - but the actual value
> would seem to depend on config options.
Right, 2*PREEMPT_DISABLE_OFFSET is the 'right' number. That ends up
being 0 for !PREEMPT_COUNT configs.
I'll update the Changelog to be more accurate on this.
next prev parent reply other threads:[~2015-09-29 12:01 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-29 9:28 [RFC][PATCH 00/11] sched: Killing PREEMPT_ACTIVE Peter Zijlstra
2015-09-29 9:28 ` [RFC][PATCH 01/11] sched: Simplify INIT_PREEMPT_COUNT Peter Zijlstra
2015-09-29 10:30 ` [tip:sched/core] sched/core: " tip-bot for Peter Zijlstra
2015-09-29 13:19 ` [RFC][PATCH 01/11] sched: " Frederic Weisbecker
2015-09-29 14:43 ` Steven Rostedt
2015-09-29 14:47 ` Peter Zijlstra
[not found] ` <20150929103729.00899e69@gandalf.local.home>
[not found] ` <20150929143559.GL3816@twins.programming.kicks-ass.net>
2015-09-29 15:00 ` Steven Rostedt
2015-09-29 15:05 ` Peter Zijlstra
2015-09-29 9:28 ` [RFC][PATCH 02/11] sched: Create preempt_count invariant Peter Zijlstra
2015-09-29 10:30 ` [tip:sched/core] sched/core: " tip-bot for Peter Zijlstra
2015-09-29 12:55 ` [RFC][PATCH 02/11] sched: " Frederic Weisbecker
2015-09-29 13:02 ` Peter Zijlstra
2015-09-29 14:40 ` Steven Rostedt
2015-09-29 13:11 ` Thomas Gleixner
2015-09-29 14:09 ` Peter Zijlstra
2015-09-29 9:28 ` [RFC][PATCH 03/11] sched: Robustify preemption leak checks Peter Zijlstra
2015-09-29 10:31 ` [tip:sched/core] sched/core: " tip-bot for Peter Zijlstra
2015-09-29 13:13 ` [RFC][PATCH 03/11] sched: " Thomas Gleixner
2015-09-29 13:25 ` Frederic Weisbecker
2015-09-29 14:24 ` Peter Zijlstra
2015-09-29 14:32 ` Frederic Weisbecker
2015-09-29 15:07 ` Steven Rostedt
2015-09-29 15:17 ` Peter Zijlstra
2015-09-29 9:28 ` [RFC][PATCH 04/11] sched: Rework TASK_DEAD preemption exception Peter Zijlstra
2015-09-29 13:13 ` Thomas Gleixner
2015-09-29 13:41 ` Frederic Weisbecker
2015-09-29 15:10 ` Steven Rostedt
2015-09-29 9:28 ` [RFC][PATCH 05/11] sched: Add preempt argument to __schedule() Peter Zijlstra
2015-09-29 13:14 ` Thomas Gleixner
2015-09-29 13:18 ` Frederic Weisbecker
2015-09-29 15:28 ` Steven Rostedt
2015-09-29 15:30 ` Steven Rostedt
2015-09-29 15:29 ` Peter Zijlstra
2015-09-29 9:28 ` [RFC][PATCH 06/11] sched: Fix trace_sched_switch() Peter Zijlstra
2015-09-29 13:15 ` Thomas Gleixner
2015-09-29 15:38 ` Steven Rostedt
2015-09-29 15:48 ` Peter Zijlstra
2015-09-29 16:30 ` Steven Rostedt
2015-09-29 9:28 ` [RFC][PATCH 07/11] sched: Stop setting PREEMPT_ACTIVE Peter Zijlstra
2015-09-29 13:16 ` Thomas Gleixner
2015-09-29 15:41 ` Steven Rostedt
2015-09-29 16:25 ` Peter Zijlstra
2015-09-29 9:28 ` [RFC][PATCH 08/11] sched: Simplify preempt_count tests Peter Zijlstra
2015-09-29 13:17 ` Thomas Gleixner
2015-09-29 15:42 ` Steven Rostedt
2015-09-29 9:28 ` [RFC][PATCH 09/11] sched, x86: Kill saved_preempt_count Peter Zijlstra
2015-09-29 13:18 ` Thomas Gleixner
2015-09-29 15:44 ` Steven Rostedt
2015-09-29 15:46 ` Peter Zijlstra
2015-09-29 9:28 ` [RFC][PATCH 10/11] sched: Kill PREEMPT_ACTIVE Peter Zijlstra
2015-09-29 13:18 ` Thomas Gleixner
2015-09-29 15:45 ` Steven Rostedt
2015-09-29 9:28 ` [RFC][PATCH 11/11] sched: More notrace Peter Zijlstra
2015-09-29 13:19 ` Thomas Gleixner
2015-09-29 15:58 ` Steven Rostedt
2015-09-29 10:27 ` [RFC][PATCH 12/11] sched: Add preempt_count invariant check Peter Zijlstra
2015-09-29 10:32 ` Peter Zijlstra
2015-09-29 10:56 ` [RFC][PATCH v2 " Peter Zijlstra
2015-09-29 11:55 ` Linus Torvalds
2015-09-29 11:55 ` Peter Zijlstra [this message]
2015-09-29 10:34 ` [RFC][PATCH 00/11] sched: Killing PREEMPT_ACTIVE Ingo Molnar
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=20150929115539.GE3816@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=fweisbec@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=umgwanakikbuti@gmail.com \
/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
all inboxes | Powered by JetHome®