linux-kernel - Re: [RFC] tracing: Add support for critical section event tracing

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:   Fri, 30 Jun 2017 16:21:36 -0700
From:   Joel Fernandes <joelaf@...gle.com>
To:     Steven Rostedt <rostedt@...dmis.org>
Cc:     LKML <linux-kernel@...r.kernel.org>
Subject: Re: [RFC] tracing: Add support for critical section event tracing

Hi Steven,

On Jun 30, 2017 5:32 AM, "Steven Rostedt" <rostedt@...dmis.org> wrote:
[..]
>> Did you have any comments about this patch? It was sent a while ago
>> and if you can provide me your initial thoughts on it, I would
>> appreciate it. (Sorry to ping you about it during the busy merge
>> window time, but I was thinking if I can get any initial early
>> comments from you then I can get to work on it and finish in time well
>> before the next merge window).

> Sorry for missing that. It's still in my INBOX in the "to look at"
> markings ;-)

Cool, no problem :-)

> Actually, have you seen Tom Zanussi's patch series about histograms.
> "tracing: Inter-event (e.g. latency) support". He just recently posted
> another series.

I was at his talk during ELC. I will take a look at his new patches as
well today. Its quite a big series ;-)

> I'd like to get that in before looking at adding events into the
> critical sections. But that said, I'll still take a look at your patch.

I feel though that the inter event stuff is a bit independent of the
critical events. Other than the fact that the irqsoff tracer can
possibly be rewritten to use inter-events, I didn't see how the
critical events work depends on the inter event stuff, or blocks it as
such. Just checking if there is another reason that you see it can
conflict?

> Thanks for reminding me.

Thanks for making time for the review :-)

Regards,
Joel