From: "Darrick J. Wong" <darrick.wong@oracle.com>
To: Eric Biggers <ebiggers@kernel.org>
Cc: Arnd Bergmann <arnd@kernel.org>, "Theodore Ts'o" <tytso@mit.edu>,
Russell King - ARM Linux admin <linux@armlinux.org.uk>,
Will Deacon <will@kernel.org>,
linux-toolchains@vger.kernel.org,
Mark Rutland <mark.rutland@arm.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Andreas Dilger <adilger.kernel@dilger.ca>,
Ext4 Developers List <linux-ext4@vger.kernel.org>,
Linux ARM <linux-arm-kernel@lists.infradead.org>
Subject: Re: Aarch64 EXT4FS inode checksum failures - seems to be weak memory ordering issues
Date: Thu, 7 Jan 2021 15:53:28 -0800 [thread overview]
Message-ID: <20210107235328.GI6908@magnolia> (raw)
In-Reply-To: <X/eK5xIMK5yZ2/tl@gmail.com>
On Thu, Jan 07, 2021 at 02:27:51PM -0800, Eric Biggers wrote:
> On Thu, Jan 07, 2021 at 10:48:05PM +0100, Arnd Bergmann wrote:
> > On Thu, Jan 7, 2021 at 5:27 PM Theodore Ts'o <tytso@mit.edu> wrote:
> > >
> > > On Thu, Jan 07, 2021 at 01:37:47PM +0000, Russell King - ARM Linux admin wrote:
> > > > > The gcc bugzilla mentions backports into gcc-linaro, but I do not see
> > > > > them in my git history.
> > > >
> > > > So, do we raise the minimum gcc version for the kernel as a whole to 5.1
> > > > or just for aarch64?
> > >
> > > Russell, Arnd, thanks so much for tracking down the root cause of the
> > > bug!
> >
> > There is one more thing that I wondered about when looking through
> > the ext4 code: Should it just call the crc32c_le() function directly
> > instead of going through the crypto layer? It seems that with Ard's
> > rework from 2018, that can just call the underlying architecture specific
> > implementation anyway.
> >
>
> It looks like that would work, although note that crc32c_le() uses the shash API
> too, so it isn't any more "direct" than what ext4 does now.
Yes.
> Also, a potential issue is that the implementation of crc32c that crc32c_le()
> uses might be chosen too early if the architecture-specific implementation of
> crc32c is compiled as a module (e.g. crc32c-intel.ko).
This was the primary reason I chose to do it this way for ext4.
The other is that ext4 didn't use crc32c before metadata_csum, so
there's no point in pulling in the crypto layer if you're only going to
use older ext2 or ext3 filesystems. That was 2010, maybe people have
stopped doing that?
> There are two ways this
> could be fixed -- either by making it a proper library API like blake2s() that
> can call the architecture-specific code directly, or by reconfiguring things
> when a new crypto module is loaded (like what lib/crc-t10dif.c does).
Though I would like to see the library functions gain the ability to use
whatever is the fastest mechanism available once we can be reasonably
certain that all the platform-specific drivers have been loaded.
That said, IIRC most distros compile all of them into their
(increasingly large) vmlinuz files so maybe this isn't much of practical
concern?
--D
>
> Until one of those is done, switching to crc32c_le() might cause performance
> regressions.
>
> - Eric
next prev parent reply other threads:[~2021-01-07 23:54 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-05 15:47 Aarch64 EXT4FS inode checksum failures - seems to be weak memory ordering issues Russell King - ARM Linux admin
2021-01-05 18:27 ` Darrick J. Wong
2021-01-05 19:50 ` Russell King - ARM Linux admin
2021-01-06 11:53 ` Mark Rutland
2021-01-06 12:13 ` Russell King - ARM Linux admin
2021-01-06 13:52 ` Russell King - ARM Linux admin
2021-01-06 17:20 ` Will Deacon
2021-01-06 17:46 ` Russell King - ARM Linux admin
2021-01-06 21:04 ` Arnd Bergmann
2021-01-06 22:00 ` Arnd Bergmann
2021-01-06 22:32 ` Russell King - ARM Linux admin
2021-01-07 11:18 ` Russell King - ARM Linux admin
2021-01-07 12:45 ` Russell King - ARM Linux admin
2021-01-07 13:16 ` Arnd Bergmann
2021-01-07 13:37 ` Russell King - ARM Linux admin
2021-01-07 16:27 ` Theodore Ts'o
2021-01-07 17:00 ` Florian Weimer
2021-01-07 21:48 ` Arnd Bergmann
2021-01-07 22:14 ` Russell King - ARM Linux admin
2021-01-07 22:41 ` Eric Biggers
2021-01-08 8:21 ` Ard Biesheuvel
2021-01-07 22:27 ` Eric Biggers
2021-01-07 23:53 ` Darrick J. Wong [this message]
2021-01-08 8:05 ` Arnd Bergmann
2021-01-08 9:13 ` Peter Zijlstra
2021-01-08 10:31 ` Pavel Machek
2021-01-07 21:20 ` Arnd Bergmann
2021-01-08 9:21 ` Peter Zijlstra
2021-01-08 9:26 ` Will Deacon
2021-01-08 20:02 ` Linus Torvalds
2021-01-08 20:22 ` Arnd Bergmann
2021-01-08 21:20 ` Nick Desaulniers
2021-01-08 20:29 ` Russell King - ARM Linux admin
2021-01-12 13:20 ` Lukas Wunner
2021-01-12 13:31 ` Florian Weimer
2021-01-12 13:46 ` David Laight
2021-01-12 17:28 ` Linus Torvalds
2021-01-14 13:13 ` Lukas Wunner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210107235328.GI6908@magnolia \
--to=darrick.wong@oracle.com \
--cc=adilger.kernel@dilger.ca \
--cc=arnd@kernel.org \
--cc=ebiggers@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-toolchains@vger.kernel.org \
--cc=linux@armlinux.org.uk \
--cc=mark.rutland@arm.com \
--cc=tytso@mit.edu \
--cc=will@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).