[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20201030083358.4c771278@oasis.local.home>
Date: Fri, 30 Oct 2020 08:33:58 -0400
From: Steven Rostedt <rostedt@...dmis.org>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Thomas Gleixner <tglx@...utronix.de>,
LKML <linux-kernel@...r.kernel.org>,
Ingo Molnar <mingo@...nel.org>, kan.liang@...ux.intel.com,
like.xu@...ux.intel.com, Andy Lutomirski <luto@...capital.net>
Subject: Re: [PATCH] perf/arch: Remove perf_sample_data::regs_user_copy
On Fri, 30 Oct 2020 11:59:17 +0100
Peter Zijlstra <peterz@...radead.org> wrote:
> On Fri, Oct 30, 2020 at 11:26:01AM +0100, Thomas Gleixner wrote:
> > What's worse is perf_sample_data which is 384 bytes and is 64 bytes aligned.
>
> Here; this shrinks it to 192 bytes. Combined with the static dummy this
> should reduce stack usage by 360 bytes.
>
> ---
> Subject: perf/arch: Remove perf_sample_data::regs_user_copy
>
> struct perf_sample_data lives on-stack, we should be careful about it's
> size. Furthermore, the pt_regs copy in there is only because x86_64 is a
> trainwreck, solve it differently.
>
> Halves sizeof(perf_sample_data).
>
>
I tested with just this patch and it doesn't crash when running
function tracing and perf simultaneously.
-- Steve
Powered by blists - more mailing lists