[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAFA6WYMD4TRR5psUyhu2jhZ2XBMUfav3D7_eH1HE8VJfXc7Fuw@mail.gmail.com>
Date: Mon, 7 Aug 2023 18:16:24 +0530
From: Sumit Garg <sumit.garg@...aro.org>
To: Mark Rutland <mark.rutland@....com>
Cc: Doug Anderson <dianders@...omium.org>,
Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will@...nel.org>,
Daniel Thompson <daniel.thompson@...aro.org>,
Marc Zyngier <maz@...nel.org>,
linux-perf-users@...r.kernel.org, ito-yuichi@...itsu.com,
Chen-Yu Tsai <wens@...e.org>, Ard Biesheuvel <ardb@...nel.org>,
Stephen Boyd <swboyd@...omium.org>,
Peter Zijlstra <peterz@...radead.org>,
Thomas Gleixner <tglx@...utronix.de>,
linux-arm-kernel@...ts.infradead.org,
kgdb-bugreport@...ts.sourceforge.net,
Masayoshi Mizuma <msys.mizuma@...il.com>,
"Rafael J . Wysocki" <rafael.j.wysocki@...el.com>,
Lecopzer Chen <lecopzer.chen@...iatek.com>,
Andrey Konovalov <andreyknvl@...il.com>,
Ben Dooks <ben-linux@...ff.org>,
Frederic Weisbecker <frederic@...nel.org>,
"Gautham R. Shenoy" <gautham.shenoy@....com>,
Ingo Molnar <mingo@...nel.org>,
Jason Wessel <jason.wessel@...driver.com>,
Josh Poimboeuf <jpoimboe@...nel.org>,
Masahiro Yamada <masahiroy@...nel.org>,
Valentin Schneider <vschneid@...hat.com>,
Wei Li <liwei391@...wei.com>, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v9 0/7] arm64: Add debug IPI for backtraces / kgdb; try to
use NMI for it
On Mon, 7 Aug 2023 at 16:11, Mark Rutland <mark.rutland@....com> wrote:
>
> Hi Doug,
>
> Apologies for the delay.
>
> On Mon, Jul 24, 2023 at 08:55:44AM -0700, Doug Anderson wrote:
> > On Thu, Jun 1, 2023 at 2:37 PM Douglas Anderson <dianders@...omium.org> wrote:
> > I'm looking for some ideas on what to do to move this patch series
> > forward. Thanks to Daniel, the kgdb patch is now in Linus's tree which
> > hopefully makes this simpler to land. I guess there is still the
> > irqchip dependency that will need to be sorted out, though...
> >
> > Even if folks aren't in agreement about whether this is ready to be
> > enabled in production, I don't think anything here is super
> > objectionable or controversial, is it? Can we land it? If you feel
> > like it needs extra review, would it help if I tried to drum up some
> > extra people to provide review feedback?
>
> Ignoring the soundness issues I mentioned before (which I'm slowly chipping
> away at, and you're likely lucky enough to avoid in practice)...
>
> Having looked over the series, I think the GICv3 bit isn't quite right, but is
> easy enough to fix. I've commented on the patch with what I think we should
> have there.
Thanks for catching this and I agree with your proposed fix.
>
> The only major thing otherwise from my PoV is the structure of the debug IPI
> framework. I'm not keen on that being a separate body of code and I think it
> should live in smp.c along with the other IPIs.
That's a fair point.
> I'd also strongly prefer if we
> could have separate IPI_CPU_BACKTRACE and IPI_CPU_KGDB IPIs,
With current logic of single debug IPI, it is not required for a user
to enable KGDB in order to use that IPI for backtrace. The original
motivation for this logic was that the IPIs are a scarce resource on
arm64 as per comments from Marc. So I am fine either way to keep them
separate or unified.
> and I think we can
> do that either by unifying IPI_CPU_STOP && IPI_CPU_CRASH_STOP or by reclaiming
> IPI_WAKEUP by reusing a different IPI for the parking protocol (e.g.
> IPI_RESCHEDULE).
That sounds like a good cleanup.
>
> I think it'd be nice if the series could enable NMIs for backtrace and the
> CPU_{,CRASH_}STOP cases, with KGDB being the bonus atop. That way it'd be
> clearly beneficial for anyone trying to debug lockups even if they're not a
> KGDB user.
>
It's good to see other use-cases of IPIs turned into NMIs.
-Sumit
> > Also: in case it's interesting to anyone, I've been doing benchmarks
> > on sc7180-trogdor devices in preparation for enabling this. On that
> > platform, I did manage to see about 4% reduction in a set of hackbench
> > numbers when fully enabling pseudo-NMI. However, when I instead ran
> > Speedometer 2.1 I saw no difference. See:
> >
> > https://issuetracker.google.com/issues/197061987
>
> Thanks for the pointer!
>
> I know that there are a couple of things that we could do to slightly improve
> local_irq_*() when using pNMIs, though I suspect that the bulk of the cost
> there will come from the necessary synchronization.
>
> Thanks,
> Mark.
Powered by blists - more mailing lists