On 02/10/2010 02:03 PM, Bjorn Helgaas wrote: > On Friday 05 February 2010 12:29:25 pm Bjorn Helgaas wrote: >> On Friday 05 February 2010 12:08:47 pm Yinghai Lu wrote: >>> On 02/05/2010 09:46 AM, Bjorn Helgaas wrote: > >>>> How many AMD boxes need amd_bus.c? I assume it's mostly or even only >>>> those with multiple host bridges? Do you have any idea how many of >>>> those shipped prior to 2010, and whether there are _CRS defects that >>>> we're avoiding by using amd_bus.c? >>> yes. >>> >>> Sun have 8 or more those kinds systems. and mostly have those problem. >>> >>> HP have simlair systems too. >> >> Were there bug reports from machines in the field, or is your claim >> that there are problems based on your experience with prototype >> machines? >> >> Frankly, I'm dubious that there are AMD machines in the field with >> this sort of _CRS defect, because I don't think machines like that >> could run Windows. > > Let me approach this from another angle. I'm thinking about turning > on "pci=use_crs" for anything from 2008 or newer, instead of 2010, > because it should fix bugs like this: > https://bugs.launchpad.net/ubuntu/+source/linux/+bug/341681 that system only has one HT chain? current we didn't enable that one AMD chain. so for unassigned resources is decided by pci_search_gap from e820? sent patches that will enable amd_bus.c for one chain. but that is still on hpa/ingo's to review list. > > If we did that, would it break any AMD multi-host machines in the field? not sure. > > I think using 2008 would essentially disable amd_bus.c unless the user > booted with "pci=nocrs" or we added blacklist entries. amd_bus.c will still print out reading out from HW. that would be amusing to compare result from HW and from ACPI. will resubmit another patch with intel multi IOH's, that will be used to print out reading out from HW reading out. YH -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
