public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
To: Andi Kleen <ak@suse.de>
Cc: patches@x86-64.org, Jeremy Fitzhardinge <jeremy@goop.org>,
	Zachary Amsden <zach@vmware.com>,
	Rusty Russell <rusty@rustcorp.com.au>,
	linux-kernel@vger.kernel.org,
	"S. P. Prasanna" <prasanna@in.ibm.com>,
	Chris Wright <chrisw@sous-sol.org>
Subject: Non atomic unaligned writes
Date: Sun, 19 Aug 2007 20:55:22 -0400	[thread overview]
Message-ID: <20070820005522.GA5069@Krystal> (raw)
In-Reply-To: <200707192246.58047.ak@suse.de>

* Andi Kleen (ak@suse.de) wrote:
> Normally there are not that many NMIs or MCEs at boot, but it would
> be still good to avoid the very rare crash by auditing the code first
> [better than try to debug it on some production system later]
> 
> > > - smp lock patching only ever changes a single byte (lock prefix) of
> > > a single instruction
> > > - kprobes only ever change a single byte
> > >
> > > For the immediate value patching it also cannot happen because
> > > you'll never modify multiple instructions and all immediate values
> > > can be changed atomically. 
> > >   
> > 
> > Are misaligned/cross-cache-line updates atomic?
> 
> In theory yes, in practice there can be errata of course. There tend 
> to be a couple with self modifying code, especially cross modifying
> (from another CPU) -- but you don't do that.
> 
> -Andi

I must disagree with Andi on this point. Considering the quoted
paragraph below, misaligned/cross-cache-line updates are not atomic.
This is why I align the immediate values in such a way that the
immediate value within the mov instruction is itself aligned.

Intel System Programming Guide

7.1.1 Guaranteed Atomic Operations

The Intel386™, Intel486™, Pentium®, and P6 family processors guarantee
that the following basic memory operations will always be carried out
atomically:
• Reading or writing a byte.
• Reading or writing a word aligned on a 16-bit boundary.
• Reading or writing a doubleword aligned on a 32-bit boundary.
The P6 family processors guarantee that the following additional memory
operations will always be carried out atomically:
• Reading or writing a quadword aligned on a 64-bit boundary. (This
operation is also guaranteed on the Pentium® processor.)
• 16-bit accesses to uncached memory locations that fit within a 32-bit
data bus.
• 16-, 32-, and 64-bit accesses to cached memory that fit within a
32-Byte cache line.

Accesses to cacheable memory that are split across bus widths, cache
lines, and page boundaries are not guaranteed to be atomic by the
Intel486™, Pentium®, or P6 family processors. The P6 family processors
provide bus control signals that permit external memory subsystems to
make split accesses atomic; however, nonaligned data accesses will
seriously impact the performance of the processor and should be avoided
where possible.

Mathieu


-- 
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68

  parent reply	other threads:[~2007-08-20  1:00 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-07-19  9:05 new text patching for review Andi Kleen
2007-07-19 13:38 ` Mathieu Desnoyers
2007-07-19 13:46   ` Andi Kleen
2007-07-19 17:35     ` Mathieu Desnoyers
2007-07-19 21:14       ` Andi Kleen
2007-07-19 20:30         ` Jeremy Fitzhardinge
2007-07-19 20:46           ` [patches] " Andi Kleen
2007-07-19 20:51             ` Jeremy Fitzhardinge
2007-07-19 21:06               ` Andi Kleen
2007-07-19 21:08                 ` Jeremy Fitzhardinge
2007-07-19 23:53             ` Mathieu Desnoyers
2007-08-20  0:55             ` Mathieu Desnoyers [this message]
2007-08-20  5:03               ` Non atomic unaligned writes Arjan van de Ven
2007-08-20 10:23               ` Andi Kleen
2007-07-19 23:51           ` new text patching for review Mathieu Desnoyers
2007-07-19 23:49         ` Mathieu Desnoyers
2007-07-20  1:15           ` Zachary Amsden
2007-07-20  7:37             ` Andi Kleen
2007-07-20 15:17             ` Mathieu Desnoyers
2007-07-21  6:19               ` Andi Kleen
2007-07-20  8:28           ` Andi Kleen
2007-07-20 14:36             ` Mathieu Desnoyers
2007-07-20  0:37 ` Zachary Amsden
2007-07-20  8:23   ` Andi Kleen
2007-08-10 19:00 ` Mathieu Desnoyers

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=20070820005522.GA5069@Krystal \
    --to=mathieu.desnoyers@polymtl.ca \
    --cc=ak@suse.de \
    --cc=chrisw@sous-sol.org \
    --cc=jeremy@goop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=patches@x86-64.org \
    --cc=prasanna@in.ibm.com \
    --cc=rusty@rustcorp.com.au \
    --cc=zach@vmware.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox