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]
Message-ID: <6135e1e118724e5ea3a1f7640b705cb5@AcuMS.aculab.com>
Date:   Mon, 13 Mar 2023 09:25:20 +0000
From:   David Laight <David.Laight@...LAB.COM>
To:     'Theodore Ts'o' <tytso@....edu>, Yangtao Li <frank.li@...o.com>
CC:     "adilger.kernel@...ger.ca" <adilger.kernel@...ger.ca>,
        "linux-ext4@...r.kernel.org" <linux-ext4@...r.kernel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "viro@...iv.linux.org.uk" <viro@...iv.linux.org.uk>
Subject: RE: [PATCH] ext4: convert to DIV_ROUND_UP() in
 mpage_process_page_bufs()

...
> On 32-bit platforms --- i386 in particular --- the 64-bit division
> results in an out-of-line call to a helper function that is not
> supplied in the kernel compilation environment, so not only is it
> slower, it Just Doesn't Work.

Even on some 64-bit systems a 64bit divide can be significantly
slower than a 32-bit divide - even with the same arguments.
IIRC Intel x86-64 a 64-bit divide (128-bit dividend) is about
twice the clocks of a 32-bit one. On AMD cpu they are much the same.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ