linux-kernel - Re: [PATCH] mm/slub: use stackdepot to save stack trace in objects

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:   Tue, 13 Jul 2021 14:03:39 +0200
From:   Geert Uytterhoeven <geert@...ux-m68k.org>
To:     glittao@...il.com, Yogesh Lal <ylal@...eaurora.org>
Cc:     Christoph Lameter <cl@...ux.com>,
        Pekka Enberg <penberg@...nel.org>,
        David Rientjes <rientjes@...gle.com>,
        Joonsoo Kim <iamjoonsoo.kim@....com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Vlastimil Babka <vbabka@...e.cz>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Linux MM <linux-mm@...ck.org>
Subject: Re: [PATCH] mm/slub: use stackdepot to save stack trace in objects

Hi Oliver, Yogesh,

On Wed, Apr 14, 2021 at 8:08 PM <glittao@...il.com> wrote:
> From: Oliver Glitta <glittao@...il.com>
>
> Many stack traces are similar so there are many similar arrays.
> Stackdepot saves each unique stack only once.
>
> Replace field addrs in struct track with depot_stack_handle_t handle.
> Use stackdepot to save stack trace.
>
> The benefits are smaller memory overhead and possibility to aggregate
> per-cache statistics in the future using the stackdepot handle
> instead of matching stacks manually.
>
> Signed-off-by: Oliver Glitta <glittao@...il.com>

Thanks for your patch, which is now commit 788691464c294553 ("mm/slub:
use stackdepot to save stack trace in objects") in v5.14-rc1.

> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -1891,6 +1891,7 @@ config SLUB_DEBUG
>         default y
>         bool "Enable SLUB debugging support" if EXPERT
>         depends on SLUB && SYSFS
> +       select STACKDEPOT if STACKTRACE_SUPPORT
>         help
>           SLUB has extensive debug support features. Disabling these can
>           result in significant savings in code size. This also disables

This change increases memory consumption by 4 MiB (or more, see below).

Looking at lib/Kconfig:

|   config STACK_HASH_ORDER
|           int "stack depot hash size (12 => 4KB, 20 => 1024KB)"

The sizes reported here are not correct, as the actual memory consumption
is not STACK_HAS_ORDER bytes, but STACK_HAS_ORDER pointers.
Hence they're off by a factor of 4 or 8.

|           range 12 20
|           default 20

Does this really have to default to the maximum value?

|           depends on STACKDEPOT
|           help
|            Select the hash size as a power of 2 for the stackdepot hash table.
|            Choose a lower value to reduce the memory impact.

Gr{oetje,eeting}s,

                        Geert

-- 
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@...ux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds