linux-kernel - Re: [PATCH 08/19] coresight: trbe: Use PERF_AUX_FLAG_PARTIAL instead of PERF_AUX_FLAG

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <20251210161958.GA724103@e132581.arm.com>
Date: Wed, 10 Dec 2025 16:19:58 +0000
From: Leo Yan <leo.yan@....com>
To: James Clark <james.clark@...aro.org>
Cc: Anshuman Khandual <anshuman.khandual@....com>,
	coresight@...ts.linaro.org, linux-arm-kernel@...ts.infradead.org,
	linux-kernel@...r.kernel.org, linux-perf-users@...r.kernel.org,
	Suzuki K Poulose <suzuki.poulose@....com>,
	Mike Leach <mike.leach@...aro.org>,
	Yeoreum Yun <yeoreum.yun@....com>, Will Deacon <will@...nel.org>,
	Mark Rutland <mark.rutland@....com>,
	Tamas Petz <tamas.petz@....com>,
	Tamas Zsoldos <tamas.zsoldos@....com>,
	Arnaldo Carvalho de Melo <acme@...nel.org>,
	Namhyung Kim <namhyung@...nel.org>, Jiri Olsa <jolsa@...nel.org>,
	Ian Rogers <irogers@...gle.com>,
	Adrian Hunter <adrian.hunter@...el.com>
Subject: Re: [PATCH 08/19] coresight: trbe: Use PERF_AUX_FLAG_PARTIAL instead
 of PERF_AUX_FLAG_COLLISION

On Tue, Dec 09, 2025 at 01:40:35PM +0000, James Clark wrote:

[...]

> > >   	if (!is_trbe_running(trbsr))
> > > -		perf_aux_output_flag(handle, PERF_AUX_FLAG_COLLISION);
> > > +		perf_aux_output_flag(handle, PERF_AUX_FLAG_PARTIAL);
> > 
> > This is interesting. So there is a no possibility for the records to be
> > overridden in the perf ring buffer and incomplete record is all that can
> > happen when TRBE is stopped, without stopping the ETE first ? Could both
> > of these scenarios might be possible as well ?
> > 
> 
> There's no chance of overwriting because that would be the TRUNCATED case
> and the event would get disabled. PARTIAL seems to be when there was an
> error that's recoverable in the driver only, but as in my other comment I
> don't think the extra complexity is necessary and always using TRUNCATED
> would be enough.

If I extend a bit, I would say that the TRUNCATED flag is used to prevent
buffer overwrites, while the other flags indicate why a record is
incomplete.

Thanks,
Leo