[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <0bcb26fb-f04d-7ba7-1118-37022466ccc5@arm.com>
Date: Mon, 1 Nov 2021 15:42:50 +0000
From: German Gomez <german.gomez@....com>
To: Leo Yan <leo.yan@...aro.org>
Cc: Namhyung Kim <namhyung@...nel.org>,
James Clark <james.clark@....com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Jiri Olsa <jolsa@...hat.com>, Ingo Molnar <mingo@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
LKML <linux-kernel@...r.kernel.org>,
Andi Kleen <ak@...ux.intel.com>,
Ian Rogers <irogers@...gle.com>,
Stephane Eranian <eranian@...gle.com>,
Adrian Hunter <adrian.hunter@...el.com>
Subject: Re: [RFC] perf arm-spe: Track task context switch for cpu-mode events
On 01/11/2021 15:36, German Gomez wrote:
> [...]
> Not really. It will only peek at the first decoded packet without
Slight correction for clarity: s/decoded packet/decoded record/. I would
be peeking at the first record in the auxtrace queue. The context packet
is stored in the context_id field of the record.
> dropping it. I couldn't think of a corner case where the decoder might
> miss a context packet for the first records (I also haven't seen any -1
> values so far).
>
Powered by blists - more mailing lists