Re: BUG in drivers/dma/ioat/dma_v2.c:314

[David Woodhouse]

On Fri, 2010-07-09 at 14:28 -0700, Dan Williams wrote:
> It doesn't appear to from the dmesg below.  I agree, I would prefer to
> do a topology based check like this rather than cheating with 
> !cap_write_drain(), but it looks like cheating is the reliable option.

Actually, given that we know the chipset, can't we just read the VT BARs
directly from config space and check that the base address of the IOMMU
we get is the right one for the I/OAT device?

Something like...

   pci_read_config_dword( ("0:0.0") , 0x48, &vtbar );
   if (drhd->base_address != vtbar)
	WARN();


-- 
dwmw2

--
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/