[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20211217075850.GC371207@leoy-ThinkPad-X240s>
Date: Fri, 17 Dec 2021 15:58:50 +0800
From: Leo Yan <leo.yan@...aro.org>
To: Catalin Marinas <catalin.marinas@....com>
Cc: Kees Cook <keescook@...omium.org>, Will Deacon <will@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Ard Biesheuvel <ardb@...nel.org>,
Sami Tolvanen <samitolvanen@...gle.com>,
Nicholas Piggin <npiggin@...il.com>,
James Morse <james.morse@....com>,
Marc Zyngier <maz@...nel.org>, Joey Gouly <joey.gouly@....com>,
Peter Collingbourne <pcc@...gle.com>,
Vincenzo Frascino <vincenzo.frascino@....com>,
"Peter Zijlstra (Intel)" <peterz@...radead.org>,
Stephane Eranian <eranian@...gle.com>,
James Clark <james.clark@....com>,
linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org
Subject: Re: [RFCv1 4/4] perf: arm_spe: Dynamically switch PID tracing to
contextidr
On Fri, Dec 10, 2021 at 03:59:18PM +0800, Leo Yan wrote:
[...]
> > You could also check there if the PID is in the root
> > namespace and avoid setting CONTEXTIDR (or write 0).
>
> This could introduce mess. Writing 0 can lead the decoder to take it
> as idle thread; if skip setting CONTEXTIDR, the tracer might use a
> stale stale PID number (the previous one ID number).
>
> Alternatively, if you accept to always set PID to CONTEXTIDR in
> contextidr_thread_switch(), it would be fine for me and we can only
> need to control PID packets in SPE and CoreSight drivers.
>
> Please let me know your opinion, thanks!
Gentle ping, Catalin. If anything is blur and you want me to clarify,
please let me know. Sorry if you are in holiday and if so we can
delay after holiday.
Thanks,
Leo
Powered by blists - more mailing lists