[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250923081634.24ef8132@batman.local.home>
Date: Tue, 23 Sep 2025 08:16:34 -0400
From: Steven Rostedt <rostedt@...nel.org>
To: Peter Zijlstra <peterz@...radead.org>
Cc: linux-kernel@...r.kernel.org, linux-trace-kernel@...r.kernel.org,
x86@...nel.org, Masami Hiramatsu <mhiramat@...nel.org>, Mark Rutland
<mark.rutland@....com>, Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Andrew Morton <akpm@...ux-foundation.org>, Thomas Gleixner
<tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>, Borislav Petkov
<bp@...en8.de>, Dave Hansen <dave.hansen@...ux.intel.com>, Linus Torvalds
<torvalds@...ux-foundation.org>, Josh Poimboeuf <jpoimboe@...nel.org>
Subject: Re: [PATCH v2 2/2] unwind deferred/x86: Do not defer stack tracing
for compat tasks
On Tue, 23 Sep 2025 12:45:15 +0200
Peter Zijlstra <peterz@...radead.org> wrote:
> Changelog seems to forget mentioning *why* we can't unwind compat.
>
> I'm sure I've seen compat FP unwind support at some point in this
> series. Did that go missing somewhere?
>
> Also, these two patches are in the wrong order, first you enable things,
> including compat tasks, and then you go 'whoopsie, no compats'.
Sure, we can swap it. Yes, we had patches to support it, but they
were a bit complicated and when I tested them, they didn't work. But
then I also noticed that the current stack tracing didn't work on
compat either. Instead of adding complicated code that wasn't working
on my machine, I decided to remove the patches. But after I did that, I
realized I needed to make sure it wasn't even tried, which is this
patch.
I'm not sure who needs profiling on compat code, and I figured we can
not add the new deferred work to it if it's not needed. If in the
future we need it, we can add it then.
-- Steve
Powered by blists - more mailing lists