[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <7c86c4470803210618j46d0dceay16757a90b9c7c48b@mail.gmail.com>
Date: Fri, 21 Mar 2008 14:18:44 +0100
From: "stephane eranian" <eranian@...glemail.com>
To: "Ingo Molnar" <mingo@...e.hu>
Cc: "Markus Metzger" <markus.t.metzger@...el.com>, ak@...e.de,
hpa@...or.com, linux-kernel@...r.kernel.org, tglx@...utronix.de,
markus.t.metzger@...il.com, suresh.b.siddha@...el.com,
roland@...hat.com, akpm@...ux-foundation.org,
mtk.manpages@...il.com
Subject: Re: [patch] x86, ptrace: support pebs in ds.c and disable ptrace and ds support
Ingo,
The PEBS support does not extend all the way to ptrace.
It does not make sense anyway.
I am fine with not using ptrace to expose BTS. But this needs
to be exposed to user level somehow. It is useful for many debugging
tools.
On Fri, Mar 21, 2008 at 1:53 PM, Ingo Molnar <mingo@...e.hu> wrote:
>
> * Markus Metzger <markus.t.metzger@...el.com> wrote:
>
> > Polish the ds.h interface and add support for PEBS.
> >
> > Guard DS support and the ptrace interface to BTS by CONFIG macros;
> > disabled per default.
> >
> > Ds.c is meant to be the resource allocator for per-thread and per-cpu
> > BTS and PEBS recording.
> > It is used by ptrace to provide execution tracing of debugged tasks.
> > It will be used by utrace for the same purpose.
> > It will be used by profilers (e.g. perfmon2).
> > It may be used by kernel debuggers to provide a kernel execution trace.
>
> we could apply this if Roland Acks it - but i guess a precondition for
> that is to not include more ptrace extensions and to also start working
> on utrace support for it. Ptrace is something we want to reduce usage
> of, not extend.
>
> Ingo
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists