From: David Laight <David.Laight@ACULAB.COM>
To: 'Peter Zijlstra' <peterz@infradead.org>,
Alexey Brodkin <Alexey.Brodkin@synopsys.com>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"tglx@linutronix.de" <tglx@linutronix.de>,
"linux-snps-arc@lists.infradead.org"
<linux-snps-arc@lists.infradead.org>,
"stable@vger.kernel.org" <stable@vger.kernel.org>,
"greg@kroah.com" <greg@kroah.com>,
"will.deacon@arm.com" <will.deacon@arm.com>,
"gregkh@linuxfoundation.org" <gregkh@linuxfoundation.org>,
"linux-arch@vger.kernel.org" <linux-arch@vger.kernel.org>,
"geert@linux-m68k.org" <geert@linux-m68k.org>
Subject: RE: [PATCH v3] devres: Explicitly align datai[] to 64-bit
Date: Mon, 9 Jul 2018 15:02:08 +0000 [thread overview]
Message-ID: <dd7f96e4b08644769865adb302eb7d53@AcuMS.aculab.com> (raw)
In-Reply-To: <20180709144925.GU2476@hirez.programming.kicks-ass.net>
From: Peter Zijlstra
> Sent: 09 July 2018 15:49
> On Mon, Jul 09, 2018 at 02:33:26PM +0000, Alexey Brodkin wrote:
> > > In fact, since alloc_dr() uses kmalloc() to allocate the entire thing,
> > > it is impossible to guarantee a larger alignment than kmalloc does.
> >
> > Well but 4-bytes [which is critical for atomic64_t] should be much less
> > than a sane cache line length so above should work.
>
> AFAICT ARCH_KMALLOC_MINALIGN ends up being 4 on x86_32 (it doesn't
> define ARCH_DMA_MINALIGN and doesn't seem to otherwise override the
> thing).
That seems broken.
I wonder what the minimal alignment really is?
I suspect some code expects (and gets) 8-byte alignment.
The min alignment might even be 16 or 32 bytes.
There aren't many x86 instructions that fault on mis-aligned addresses,
but there are a few.
Mostly related to the fpu - probably including the fpu save area.
David
WARNING: multiple messages have this Message-ID (diff)
From: David.Laight@ACULAB.COM (David Laight)
To: linux-snps-arc@lists.infradead.org
Subject: [PATCH v3] devres: Explicitly align datai[] to 64-bit
Date: Mon, 9 Jul 2018 15:02:08 +0000 [thread overview]
Message-ID: <dd7f96e4b08644769865adb302eb7d53@AcuMS.aculab.com> (raw)
In-Reply-To: <20180709144925.GU2476@hirez.programming.kicks-ass.net>
From: Peter Zijlstra
> Sent: 09 July 2018 15:49
> On Mon, Jul 09, 2018@02:33:26PM +0000, Alexey Brodkin wrote:
> > > In fact, since alloc_dr() uses kmalloc() to allocate the entire thing,
> > > it is impossible to guarantee a larger alignment than kmalloc does.
> >
> > Well but 4-bytes [which is critical for atomic64_t] should be much less
> > than a sane cache line length so above should work.
>
> AFAICT ARCH_KMALLOC_MINALIGN ends up being 4 on x86_32 (it doesn't
> define ARCH_DMA_MINALIGN and doesn't seem to otherwise override the
> thing).
That seems broken.
I wonder what the minimal alignment really is?
I suspect some code expects (and gets) 8-byte alignment.
The min alignment might even be 16 or 32 bytes.
There aren't many x86 instructions that fault on mis-aligned addresses,
but there are a few.
Mostly related to the fpu - probably including the fpu save area.
David
next prev parent reply other threads:[~2018-07-09 15:02 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-09 13:45 [PATCH v3] devres: Explicitly align datai[] to 64-bit Alexey Brodkin
2018-07-09 13:45 ` Alexey Brodkin
2018-07-09 13:54 ` Peter Zijlstra
2018-07-09 13:54 ` Peter Zijlstra
2018-07-09 13:54 ` Peter Zijlstra
2018-07-09 13:54 ` Peter Zijlstra
2018-07-09 13:54 ` Peter Zijlstra
2018-07-09 14:04 ` Mark Rutland
2018-07-09 14:04 ` Mark Rutland
2018-07-09 14:10 ` Geert Uytterhoeven
2018-07-09 14:10 ` Geert Uytterhoeven
2018-07-09 14:07 ` Alexey Brodkin
2018-07-09 14:07 ` Alexey Brodkin
2018-07-09 14:07 ` Peter Zijlstra
2018-07-09 14:07 ` Peter Zijlstra
2018-07-09 14:07 ` Peter Zijlstra
2018-07-09 14:10 ` Peter Zijlstra
2018-07-09 14:10 ` Peter Zijlstra
2018-07-09 14:10 ` Peter Zijlstra
2018-07-09 14:33 ` Alexey Brodkin
2018-07-09 14:33 ` Alexey Brodkin
2018-07-09 14:49 ` Peter Zijlstra
2018-07-09 14:49 ` Peter Zijlstra
2018-07-09 14:53 ` Alexey Brodkin
2018-07-09 14:53 ` Alexey Brodkin
2018-10-04 16:19 ` Alexey Brodkin
2018-10-04 16:19 ` Alexey Brodkin
2018-07-09 15:02 ` David Laight [this message]
2018-07-09 15:02 ` David Laight
2018-07-09 15:14 ` Peter Zijlstra
2018-07-09 15:14 ` Peter Zijlstra
2018-07-09 15:14 ` Peter Zijlstra
2018-07-09 15:29 ` Mark Rutland
2018-07-09 15:29 ` Mark Rutland
2018-07-09 15:34 ` Peter Zijlstra
2018-07-09 15:34 ` Peter Zijlstra
2018-07-09 15:34 ` Peter Zijlstra
2018-07-09 15:45 ` Peter Zijlstra
2018-07-09 15:45 ` Peter Zijlstra
2018-07-09 15:45 ` Peter Zijlstra
2018-07-09 15:48 ` Mark Rutland
2018-07-09 15:48 ` Mark Rutland
2018-07-09 16:10 ` David Laight
2018-07-09 16:10 ` David Laight
2018-07-09 20:28 ` Vineet Gupta
2018-07-09 20:28 ` Vineet Gupta
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=dd7f96e4b08644769865adb302eb7d53@AcuMS.aculab.com \
--to=david.laight@aculab.com \
--cc=Alexey.Brodkin@synopsys.com \
--cc=geert@linux-m68k.org \
--cc=greg@kroah.com \
--cc=gregkh@linuxfoundation.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-snps-arc@lists.infradead.org \
--cc=peterz@infradead.org \
--cc=stable@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=will.deacon@arm.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.