lkml.org 
[lkml]   [2006]   [Sep]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: Opinion on ordering of writel vs. stores to RAM
From
Date
On Mon, 2006-09-11 at 11:08 -0700, Jesse Barnes wrote:
> On Sunday, September 10, 2006 6:00 pm, Benjamin Herrenschmidt wrote:
> > > If we accept this, I don't think we're much better off than we are
> > > currently (not that I have a problem with that). That is, many
> > > drivers
> > > would still need to be fixed up.
> >
> > Not necessarily if you introduce the trick of doing the mmiowb() in
> > spin_unlock when a per-cpu flag has been set previously by writel... not
> > sure if it's worth tho.
>
> True, though again this would add a branch to writeX.

No, it adds a cacheable store to writeX and a branch to spin_unlock

> Sure, that's where one would typically use it, but it really is a memory
> barrier...

I prefer having separate semantics for it so people understand it better
but I may be wrong :)

> That's because it *is* a barrier. I don't think it's any harder to understand
> then regular memory barriers for example. It's just that you'd typically use
> it in conjunction with locks to ensure proper device access.

That's why I prefer defining it as a MMIO + lock barrier.

> Ok, that's fine, though I think you'd only want the very weak semantics (as
> provided by your __raw* routines) on write combined memory typically?

Well, that and memory with no side effects (like frame buffers)

> > I'm very much against your terminology. It's -not- an IO to IO barrier.
> > It's an IO to lock barrier. Really. IO to IO is something else. ordering
> > of IOs between CPUs has absolutely no meaning outside of the context of
> > locked regions in any case.
>
> But it *is* MMIO vs. MMIO. There's confusion because your __raw* routines
> don't even guarantee same CPU ordering, while mmiowb() is solely intended for
> inter-CPU ordering.
>
> But as you say, the most common (maybe only) use model for it is to make sure
> critical sections protecting device access behave correctly, so I don't have
> a problem tying it to locks somehow.

Ben.


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2006-09-11 23:35    [W:0.064 / U:0.096 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site