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]
Message-ID: <20190604120623epcms5p3fc13e98047e7b44d6da144425213b4fe@epcms5p3>
Date:   Tue, 04 Jun 2019 17:36:23 +0530
From:   Vaneet Narang <v.narang@...sung.com>
To:     Andrew Morton <akpm@...ux-foundation.org>,
        Maninder Singh <maninder1.s@...sung.com>
CC:     "herbert@...dor.apana.org.au" <herbert@...dor.apana.org.au>,
        "davem@...emloft.net" <davem@...emloft.net>,
        "keescook@...omium.org" <keescook@...omium.org>,
        "gustavo@...eddedor.com" <gustavo@...eddedor.com>,
        "joe@...ches.com" <joe@...ches.com>,
        "linux-crypto@...r.kernel.org" <linux-crypto@...r.kernel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        AMIT SAHRAWAT <a.sahrawat@...sung.com>,
        PANKAJ MISHRA <pankaj.m@...sung.com>,
        Vaneet Narang <v.narang@...sung.com>
Subject: RE:(2) [PATCH 0/4] zstd: reduce stack usage

Hi Andrew,

>> This patch set reduces stack usage for zstd code, because target like ARM has
>> limited 8KB kernel stack, which is getting overflowed due to hight stack usage
>> of zstd code with call flow like:
 
>That's rather bad behaviour.  I assume the patchset actually fixes this?

Yes, patchset tries to reduce around 300 bytes of stack usage of zstd compression path. 
We faced high stack usage issue on switching compression algo from LZO/LZ4 to zstd algo.
zstd compression uses around 1200 bytes of stack which is huge as compared 
to LZO/LZ4 which uses negligible stack (< 200 bytes).

 
>I think I'll schedule the patchset for 5.2-rcX so that zstd is actually
>usable on arm in 5.2.  Does that sound OK? 
OK

Regards,
Vaneet Narang

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ