All of lore.kernel.org
 help / color / mirror / Atom feed
* pci-gart_64.c: could we get better explanation?
@ 2008-05-26 18:47 Pavel Machek
  2008-05-26 19:51 ` Benjamin Herrenschmidt
  0 siblings, 1 reply; 4+ messages in thread
From: Pavel Machek @ 2008-05-26 18:47 UTC (permalink / raw)
  To: kernel list, Ingo Molnar, Dave Jones, Andi Kleen; +Cc: Benjamin Herrenschmidt

Hi!

+++ b/arch/x86/kernel/pci-gart_64.c
@@ -774,6 +778,7 @@ #endif
 
        /*
         * Try to workaround a bug (thanks to BenH)
         * Set unmapped entries to a scratch page instead of 0.
         * Any prefetches that hit unmapped entries won't get an bus abort

Could someone explain? Which bug is being worked around? CPUs
prefetching over NULL?
								Pavel
-- 
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: pci-gart_64.c: could we get better explanation?
  2008-05-26 18:47 pci-gart_64.c: could we get better explanation? Pavel Machek
@ 2008-05-26 19:51 ` Benjamin Herrenschmidt
  2008-06-25 22:25   ` Pavel Machek
  0 siblings, 1 reply; 4+ messages in thread
From: Benjamin Herrenschmidt @ 2008-05-26 19:51 UTC (permalink / raw)
  To: Pavel Machek; +Cc: kernel list, Ingo Molnar, Dave Jones, Andi Kleen


On Mon, 2008-05-26 at 20:47 +0200, Pavel Machek wrote:
> Hi!
> 
> +++ b/arch/x86/kernel/pci-gart_64.c
> @@ -774,6 +778,7 @@ #endif
>  
>         /*
>          * Try to workaround a bug (thanks to BenH)
>          * Set unmapped entries to a scratch page instead of 0.
>          * Any prefetches that hit unmapped entries won't get an bus abort
> 
> Could someone explain? Which bug is being worked around? CPUs
> prefetching over NULL?

P2P bridge prefetching on DMA reads.

Ben.



^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: pci-gart_64.c: could we get better explanation?
  2008-05-26 19:51 ` Benjamin Herrenschmidt
@ 2008-06-25 22:25   ` Pavel Machek
  2008-06-26 13:17     ` Ingo Molnar
  0 siblings, 1 reply; 4+ messages in thread
From: Pavel Machek @ 2008-06-25 22:25 UTC (permalink / raw)
  To: Benjamin Herrenschmidt
  Cc: kernel list, Ingo Molnar, Dave Jones, Andi Kleen,
	Trivial patch monkey

On Tue 2008-05-27 05:51:39, Benjamin Herrenschmidt wrote:
> 
> On Mon, 2008-05-26 at 20:47 +0200, Pavel Machek wrote:
> > Hi!
> > 
> > +++ b/arch/x86/kernel/pci-gart_64.c
> > @@ -774,6 +778,7 @@ #endif
> >  
> >         /*
> >          * Try to workaround a bug (thanks to BenH)
> >          * Set unmapped entries to a scratch page instead of 0.
> >          * Any prefetches that hit unmapped entries won't get an bus abort
> > 
> > Could someone explain? Which bug is being worked around? CPUs
> > prefetching over NULL?
> 
> P2P bridge prefetching on DMA reads.

---

Add better explanation to pci-gart.

Signed-off-by: Pavel Machek <pavel@suse.cz>

diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 838a1d3..e72e583 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -800,10 +800,10 @@ #endif
 	wbinvd();
 
 	/*
-	 * Try to workaround a bug (thanks to BenH)
+	 * Try to workaround a bug (thanks to BenH):
 	 * Set unmapped entries to a scratch page instead of 0.
 	 * Any prefetches that hit unmapped entries won't get an bus abort
-	 * then.
+	 * then. (P2P bridge may be prefetching on DMA reads).
 	 */
 	scratch = get_zeroed_page(GFP_KERNEL);
 	if (!scratch)

-- 
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html

^ permalink raw reply related	[flat|nested] 4+ messages in thread

* Re: pci-gart_64.c: could we get better explanation?
  2008-06-25 22:25   ` Pavel Machek
@ 2008-06-26 13:17     ` Ingo Molnar
  0 siblings, 0 replies; 4+ messages in thread
From: Ingo Molnar @ 2008-06-26 13:17 UTC (permalink / raw)
  To: Pavel Machek
  Cc: Benjamin Herrenschmidt, kernel list, Dave Jones, Andi Kleen,
	Trivial patch monkey


* Pavel Machek <pavel@suse.cz> wrote:

> Add better explanation to pci-gart.

applied to tip/x86/gart - thanks Pavel.

	Ingo

^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2008-06-26 13:18 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2008-05-26 18:47 pci-gart_64.c: could we get better explanation? Pavel Machek
2008-05-26 19:51 ` Benjamin Herrenschmidt
2008-06-25 22:25   ` Pavel Machek
2008-06-26 13:17     ` Ingo Molnar

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.