linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: trd@45mercystreet.com (Toby Douglass)
To: linux-arm-kernel@lists.infradead.org
Subject: GCC built-in atomic operations and memory barriers
Date: Fri, 06 Nov 2009 20:17:47 +0100	[thread overview]
Message-ID: <4AF4765B.5080303@45mercystreet.com> (raw)
In-Reply-To: <4AF1FBA4.4070307@xenomai.org>

Gilles Chanteperdrix wrote:
> Russell King - ARM Linux wrote:
>> The kernel API is the syscall interface and associated data structures.
>> It does not include everything you can find in kernel headers.
> 
> Are the functions found in the vectors page part of the kernel API?
> Because if that is so, then they provide a way to implement cmpxchg and
> barriers in user-space.

GCC (I had overlooked this) has a function, __sync_synchronize(), which 
provides a full memory barrier.  I do not know how it is implemented on 
ARM, but the CAS I wrote certainly would not work (and did not work) 
without a memory barrier and with this function inserted, does work.

The GCC atomic CAS for ARM appears to call the OS's compare-exchange 
function, which certainly is broken, by lacking memory barriers, on the 
Linux I am developing on.

Either way, I now have my own platform independent ARM __asm__ for LL/CS 
CAS, with memory barriers, so I'm happy.  Also, I got my OpenGL wrapper 
DLL working last night :-)

  reply	other threads:[~2009-11-06 19:17 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-11-04 18:09 GCC built-in atomic operations and memory barriers Toby Douglass
2009-11-04 19:05 ` Russell King - ARM Linux
2009-11-04 20:12   ` Toby Douglass
2009-11-04 21:03     ` Russell King - ARM Linux
2009-11-06 19:10       ` Toby Douglass
2009-11-04 22:09   ` Gilles Chanteperdrix
2009-11-06 19:17     ` Toby Douglass [this message]
2009-11-21 15:21     ` CAS implementation may be broken Toby Douglass
2009-11-23 15:08       ` Russell King - ARM Linux
2009-11-23 19:10         ` Toby Douglass
2009-11-23 20:06           ` Russell King - ARM Linux
2009-11-23 20:34             ` Toby Douglass
2009-11-23 15:13       ` Catalin Marinas
2009-11-24 15:15         ` Toby Douglass
2009-11-24 15:36           ` Russell King - ARM Linux
2009-11-24 16:20             ` Toby Douglass
2009-11-24 16:27             ` Catalin Marinas
2009-11-24 17:14             ` Toby Douglass
2009-11-25  1:24           ` Jamie Lokier
2009-11-26 16:14             ` Toby Douglass
2009-11-27  1:37               ` Jamie Lokier
2009-11-24 15:33         ` Toby Douglass
2009-11-23 15:34       ` Catalin Marinas
2009-11-23 16:40         ` Toby Douglass
2009-11-23 22:28       ` Jamie Lokier
2009-11-23 23:13         ` Russell King - ARM Linux
2009-11-24  1:32           ` Jamie Lokier
2009-11-24 11:19             ` Catalin Marinas
2009-11-24 22:24               ` Toby Douglass
2009-11-25 11:11                 ` Catalin Marinas
2009-11-25 18:57                   ` Toby Douglass
2009-11-24 22:34               ` Toby Douglass
2009-11-24 22:56                 ` Russell King - ARM Linux
2009-11-25  0:34                   ` Toby Douglass
2009-11-24  9:38           ` Toby Douglass
2009-11-24 15:59         ` Catalin Marinas
2009-11-24 16:34         ` Toby Douglass

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=4AF4765B.5080303@45mercystreet.com \
    --to=trd@45mercystreet.com \
    --cc=linux-arm-kernel@lists.infradead.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).