Messages in this thread | | | Subject | Re: BUG in drivers/dma/ioat/dma_v2.c:314 | From | David Woodhouse <> | Date | Sat, 10 Jul 2010 01:09:14 +0100 |
| |
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
| |