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: <Z31gdpNdwHYG2xY3@infradead.org>
Date: Tue, 7 Jan 2025 09:12:22 -0800
From: Christoph Hellwig <hch@...radead.org>
To: Amir Goldstein <amir73il@...il.com>
Cc: Chi Zhiling <chizhiling@....com>, Dave Chinner <david@...morbit.com>,
	djwong@...nel.org, cem@...nel.org, linux-xfs@...r.kernel.org,
	linux-kernel@...r.kernel.org, Chi Zhiling <chizhiling@...inos.cn>,
	John Garry <john.g.garry@...cle.com>
Subject: Re: [PATCH] xfs: Remove i_rwsem lock in buffered read

On Tue, Jan 07, 2025 at 01:13:17PM +0100, Amir Goldstein wrote:
> The issue with atomicity of buffered I/O is the xfs has traditionally
> provided atomicity of write vs. read (a.k.a no torn writes), which is
> not required by POSIX standard (because POSIX was not written with
> threads in mind) and is not respected by any other in-tree filesystem.

That is true for original Posix, but once Posix Threads joined the game
the behavior was and still is required.  See "2.9.7 Thread Interactions
with Regular File Operations" here:

https://pubs.opengroup.org/onlinepubs/9699919799/functions/V2_chap02.html

Now most Linux filesystems ignored that and got away with ignoring
the requirement, but it still exists.

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ