From: Andy Lutomirski <luto@kernel.org>
To: Joel Fernandes <joel@joelfernandes.org>
Cc: Thomas Gleixner <tglx@linutronix.de>,
"Paul E. McKenney" <paulmck@kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
rcu@vger.kernel.org, Andrew Lutomirski <luto@kernel.org>,
X86 ML <x86@kernel.org>,
Frederic Weisbecker <frederic@kernel.org>,
Steven Rostedt <rostedt@goodmis.org>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Will Deacon <will@kernel.org>,
Peter Zijlstra <peterz@infradead.org>
Subject: Re: [PATCH x86/entry: Force rcu_irq_enter() when in idle task
Date: Tue, 16 Jun 2020 09:52:09 -0700 [thread overview]
Message-ID: <CALCETrViTVCaqmF1wQCAdPR7k9ZYOvRDdzjkVBMwrVH6nh3zMg@mail.gmail.com> (raw)
In-Reply-To: <20200616143018.GD12037@google.com>
On Tue, Jun 16, 2020 at 7:30 AM Joel Fernandes <joel@joelfernandes.org> wrote:
>
> On Tue, Jun 16, 2020 at 10:40:04AM +0200, Thomas Gleixner wrote:
> > Joel,
> >
> > Joel Fernandes <joel@joelfernandes.org> writes:
> > > On Fri, Jun 12, 2020 at 03:55:00PM +0200, Thomas Gleixner wrote:
> > >> This is also correct vs. user mode entries in NOHZ full scenarios because
> > >> user mode entries bring RCU out of EQS and force the RCU irq nesting state
> > >
> > > I had to re-read this sentence a couple of times. The 'user mode entries'
> > > sounds like 'entry into user mode'. It would be good to reword it to 'IRQ
> > > entry in user mode'.
> >
> > :)
> >
> > > My knowledge predates the rcu-watching reworks so apologies on the below
> > > question but I still didn't fully follow why when the idle task behaves
> > > differently from being in user mode. Even with user mode we should have:
> > >
> > > <user mode> (in EQS)
> > > <irq entry> <---------- exits EQS so now rcu is watching
> > > <softirq entry in the exit path>
> > > <timer tick irq entry> <-- the buggy !watching logic prevents rcu_irq_enter
> > > -> report QS since tick thinks it is first level.
> > >
> > > Is there a subtlety here I'm missing? I checked the RCU code and I did not
> > > see anywhere that rcu_user_enter() makes it behave differently. Both
> > > rcu_user_enter() and rcu_idle_enter() call rcu_eqs_enter().
> >
> > The interrupt hit user mode entry does:
> >
> > idtentry_enter_cond_rcu()
> > if (user_mode(regs))
> > enter_from_user_mode()
> > user_exit_irqoff()
> > __context_tracking_exit(CONTEXT_USER)
> > rcu_user_exit()
> > rcu_eqs_exit(1)
> > ...
> > WRITE_ONCE(rdp->dynticks_nmi_nesting,
> > DYNTICK_IRQ_NONIDLE);
> >
> > i.e. for interrupts which enter from user mode we are not invoking
> > rcu_irq_enter() at all.
> >
> > The return from interrupt path has nothing to do with that because
> > that's an entry in kernel mode.
>
> Hi Thomas,
> Ah, IRQ entry in user mode triggers the context-tracking path. Makes sense now, thanks.
>
> This will help me when I have to propose to get rid of dynticks_nmi_nesting again :)
>
Propose away, but just keep in mind that horrible architectures like
x86 really can nest non-maskable interrupts that hit kernel code more
than one deep.
--Andy
next prev parent reply other threads:[~2020-06-16 16:52 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-11 23:53 [PATCH RFC] x86/entry: Ask RCU if it needs rcu_irq_{enter,exit}() Paul E. McKenney
2020-06-11 23:54 ` Paul E. McKenney
2020-06-12 5:30 ` Andy Lutomirski
2020-06-12 12:40 ` Thomas Gleixner
2020-06-12 13:55 ` [PATCH x86/entry: Force rcu_irq_enter() when in idle task Thomas Gleixner
2020-06-12 14:26 ` Frederic Weisbecker
2020-06-12 14:47 ` Thomas Gleixner
2020-06-12 15:32 ` Andy Lutomirski
2020-06-12 17:49 ` Paul E. McKenney
2020-06-12 19:19 ` Paul E. McKenney
2020-06-12 19:25 ` Thomas Gleixner
2020-06-12 19:28 ` Andy Lutomirski
2020-06-12 19:34 ` Thomas Gleixner
2020-06-12 21:56 ` Paul E. McKenney
2020-06-12 19:50 ` [tip: x86/entry] " tip-bot2 for Thomas Gleixner
2020-06-15 20:16 ` [PATCH " Joel Fernandes
2020-06-16 8:40 ` Thomas Gleixner
2020-06-16 14:30 ` Joel Fernandes
2020-06-16 16:52 ` Andy Lutomirski [this message]
2020-06-12 9:27 ` [PATCH RFC] x86/entry: Ask RCU if it needs rcu_irq_{enter,exit}() Thomas Gleixner
2020-06-12 13:57 ` Paul E. McKenney
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=CALCETrViTVCaqmF1wQCAdPR7k9ZYOvRDdzjkVBMwrVH6nh3zMg@mail.gmail.com \
--to=luto@kernel.org \
--cc=frederic@kernel.org \
--cc=joel@joelfernandes.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=rcu@vger.kernel.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=will@kernel.org \
--cc=x86@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).