Re: pci-disable-decode-of-io-memory-during-bar-sizing.patch

From: Linus Torvalds
Date: Tue Oct 30 2007 - 18:38:26 EST




On Tue, 30 Oct 2007, Linus Torvalds wrote:
>
> No. You really don't see the big picture. There's been tons of problems
> with MMCONFIG. Like the fact that other devices have their IO regions
> registered on top of it, because the MMCONFIG thing was done as a hidden
> resource. Or the fact that the area claimed was too small. Or too large.
> Or not listed at all.

Actually, I guess the bad case wasn't "not listed at all", but incorrectly
listed - so the probing would go to the wrong address, not find any
devices, and then promptly result in an unusable machine with no hardware
attached.

I _think_ (and hope) those machines were never released. But even now, on
my main machine, I get "MCFG area at f0000000 is not E820-reserved", and
probably the only reason the PCI layer doesn't overwrite it is because it
does show up as a PnP region, and I have pnp support enabled.

Basically, the resource allocation for mmconf has always been broken
(largely by *design* by Intel!). And by being broken, it has been
unreliable.

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