linux-kernel - Re: [PATCH 3/3] x86/ftrace: Use text

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

Date:   Fri, 11 Oct 2019 09:11:45 -0400
From:   Steven Rostedt <rostedt@...dmis.org>
To:     Daniel Bristot de Oliveira <bristot@...hat.com>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        linux-kernel@...r.kernel.org, x86@...nel.org,
        Nadav Amit <nadav.amit@...il.com>,
        Andy Lutomirski <luto@...nel.org>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        Song Liu <songliubraving@...com>,
        Masami Hiramatsu <mhiramat@...nel.org>
Subject: Re: [PATCH 3/3] x86/ftrace: Use text_poke()

On Fri, 11 Oct 2019 09:37:10 +0200
Daniel Bristot de Oliveira <bristot@...hat.com> wrote:

> But, yes, we will need [ as an optimization ] to sort the address right before
> inserting them in the batch. Still, having the ftrace_pages ordered seems to be
> a good thing, as in many cases, the ftrace_pages are disjoint sets.

I think it would be fine if we run the batches according to the ftrace
page groups. Which will be guaranteed to be sorted. I try to keep the
groups to a minimum, thus it shouldn't be too many ipi busts.

Although, my new work may actually make more page groups by trying to
cut down on the dyn_ftrace size by using offsets. If a function extends
outside the offset range, a new page group will need to be created.

-- Steve