Re: [PATCH] Define wc_wmb, a write barrier for PCI write combining

[Benjamin LaHaise <bcrl@kvack.org>]

On Wed, Mar 01, 2006 at 12:05:07PM -0800, Bryan O'Sullivan wrote:
> This section also makes it clear yet again that wmb() is absolutely not
> sufficient to get program store order semantics in the presence of WC;
> you *have* to use an explicit synchronising instruction of some kind.

The semantics your code seems to care about are not those of a memory 
barrier (which deals with ordering), but of a flush of the write combining 
buffers.  That's an important high level distinction as they are implemented 
differently across architectures.  Please rename the macro something like 
flush_wc() and document it as such, at which point I remove my objection.

		-ben
-- 
"Ladies and gentlemen, I'm sorry to interrupt, but the police are here 
and they've asked us to stop the party."  Don't Email: <dont@kvack.org>.