From: Trond Myklebust <trond.myklebust@fys.uio.no>
To: Andrew Morton <akpm@osdl.org>
Cc: Andreas Schwab <schwab@suse.de>,
76306.1226@compuserve.com, linux-kernel@vger.kernel.org,
ak@suse.de, mingo@redhat.com, torvalds@osdl.org
Subject: Re: set_bit() is broken on i386?
Date: Sat, 21 Jan 2006 14:26:22 -0500 [thread overview]
Message-ID: <1137871582.8715.31.camel@lade.trondhjem.org> (raw)
In-Reply-To: <20060120183857.188ef516.akpm@osdl.org>
On Fri, 2006-01-20 at 18:38 -0800, Andrew Morton wrote:
> We need to somehow tell the compiler "this assembly statement altered
> memory and you can't cache memory contents across it". That's what
> "memory" (ie: barrier()) does. I don't think there's a way of telling gcc
> _what_ memory was clobbered - just "all of memory".
We _can_ (and do) tell gcc that the unsigned long at address "addr"
will be clobbered. The problem here is that we're actually applying
set_bit() to a bit array that is larger than the single long, so we are
not necessarily clobbering "addr", but rather the long at addr + X.
Most non-386 architectures don't actually have this compiler reordering
problem since they tend to convert the index into the bit array into an
offset for addr + a remainder:
unsigned long *offset = addr + (nr / 8*sizeof(unsigned long));
unsigned long bit = (nr % 8*sizeof(unsigned long));
and then tell the compiler that the long at "offset" will be clobbered.
The remaining architectures appear to already have the general memory
clobber set in their asms (as far as I can see).
IOW: the 386 and x86_64 appear to be the problem cases here, and then
only when applied to large bit arrays.
Cheers
Trond
next prev parent reply other threads:[~2006-01-21 19:26 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-01-21 0:53 set_bit() is broken on i386? Chuck Ebbert
2006-01-21 1:15 ` Trond Myklebust
2006-01-21 1:49 ` Andreas Schwab
2006-01-21 2:38 ` Andrew Morton
2006-01-21 19:26 ` Trond Myklebust [this message]
2006-01-21 1:32 ` Valdis.Kletnieks
2006-01-21 2:01 ` Grzegorz Kulewski
2006-01-21 1:48 ` Andrew Morton
2006-01-21 1:38 Kenny Simpson
2006-01-21 1:46 Kenny Simpson
2006-01-21 2:07 Kenny Simpson
2006-01-21 7:43 Chuck Ebbert
2006-01-21 20:49 Chuck Ebbert
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=1137871582.8715.31.camel@lade.trondhjem.org \
--to=trond.myklebust@fys.uio.no \
--cc=76306.1226@compuserve.com \
--cc=ak@suse.de \
--cc=akpm@osdl.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=schwab@suse.de \
--cc=torvalds@osdl.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).