2 messages, 2 authors, 2008-05-27 · open the first message on its own page
From: Roland Dreier <hidden>
Date: 2008-05-27 04:08:22
> either via sparse or some fancy lockdep like "device store" thing? > If we can't test for it and it doesn't show up on x86 ... it'll just be > an eterrnal chase. Ben's point is that it will start showing up on x86 because newer compilers are reordering things... - R.
From: Arjan van de Ven <hidden>
Date: 2008-05-27 04:27:25
On Mon, 26 May 2008 21:08:10 -0700 Roland Dreier [off-list ref] wrote:
> either via sparse or some fancy lockdep like "device store" thing? > If we can't test for it and it doesn't show up on x86 ... it'll > just be an eterrnal chase. Ben's point is that it will start showing up on x86 because newer compilers are reordering things... - R.
I know a basic reorder will show up there. A simple "barrier()" in readl/writel solves it for x86. Understandably, Ben doesn't really like that answer ;-) -- If you want to reach me at my work email, use arjan@linux.intel.com For development, discussion and tips for power savings, visit http://www.lesswatts.org