linux-kernel - Re: [GIT PULL] perf tools changes for v6.10

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: Windows password security audit tool. GUI, reports in PDF.

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

Date: Sun, 26 May 2024 09:11:41 -0700
From: Linus Torvalds <torvalds@...ux-foundation.org>
To: Ian Rogers <irogers@...gle.com>
Cc: Namhyung Kim <namhyung@...nel.org>, Arnaldo Carvalho de Melo <acme@...nel.org>, Leo Yan <leo.yan@...ux.dev>, 
	Mark Rutland <mark.rutland@....com>, Ingo Molnar <mingo@...nel.org>, 
	Thomas Gleixner <tglx@...utronix.de>, Jiri Olsa <jolsa@...nel.org>, 
	Adrian Hunter <adrian.hunter@...el.com>, Clark Williams <williams@...hat.com>, 
	Kate Carcia <kcarcia@...hat.com>, linux-kernel@...r.kernel.org, 
	linux-perf-users@...r.kernel.org, Anne Macedo <retpolanne@...teo.net>, 
	Bhaskar Chowdhury <unixbhaskar@...il.com>, Ethan Adams <j.ethan.adams@...il.com>, 
	James Clark <james.clark@....com>, Kan Liang <kan.liang@...ux.intel.com>, 
	Thomas Richter <tmricht@...ux.ibm.com>, Tycho Andersen <tycho@...ho.pizza>, 
	Yang Jihong <yangjihong@...edance.com>
Subject: Re: [GIT PULL] perf tools changes for v6.10

On Sat, 25 May 2024 at 23:22, Ian Rogers <irogers@...gle.com> wrote:
>
> What to do with events with no PMU like data_read?

Are they actually ambiguous?

> The rule for looking up an event with no PMU specified is to try it on
> every PMU - the rule is about as old as perf itself.

Well, clearly you then violated that rule with your change. Or you
ended up changing the rule to look them up in the wrong order.

I'm not interested in theoretical breakages. I'm interested in actual
_real_ and _clear_ breakages, and that commit of yours introduced
them.

Maybe the fix is to make sure the events are always looked up in the
right order, with core events always getting priority.

That said, in the *particular* case that I hit, it's even worse than
that. It's not just that the wrong event was looked up - it looked up
an event that DIDN'T EVEN WORK for the workload.

So it's doubly broken.

I don't understand why you then bring up a "what about" issue that is
entirely irrelevant and would presumably never have shown the issue in
the first place because it wasn't probably wasn't ambiguous, and that
actually did work as an event source.

Reality matters. What-about-isms don't.

              Linus