Re: [libvirt] Questions about function virPCIDeviceIsBehindSwitchLackingACS in virpci.c

Hi,   In function virPCIDeviceIsBehindSwitchLackingACS, I noticed that(line 8):   1    if (virPCIDeviceGetParent(dev, &parent) < 0) 2        return -1; 3    if (!parent) { 4        /* if we have no parent, and this is the root bus, ACS doesn't come 5         * into play since devices on the root bus can't P2P without going 6         * through the root IOMMU. 7         */ 8        if (dev->address.bus == 0) { 9            return 0; 10        } else { 11            virReportError(VIR_ERR_INTERNAL_ERROR, 12                           _("Failed to find parent device for %s"), 13                           dev->name); 14            return -1; 15        } 16    }   Why we just return 0 only if device’s bus is 0? In my server, I can see a root bus which bus number is greater than 0, see the results(just a part) after I run lspci -t:   +-[0000:80]-+-02.0-[81-83]--+-00.0 |           |               \-00.1 |           +-05.0 |           +-05.1 |           +-05.2 |           \-05.4 +-[0000:7f]-+-08.0 |           +-08.2 |           +-08.3 |           + . . . |           \-1f.2 \-[0000:00]-+-00.0              +-01.0-[01]----00.0              +-02.0-[02]--+-00.0              |            +-00.1              |            +-00.2              |            \-00.3              +-02.2-[03]--              +-03.0-[04-0b]----00.0-[05-0b]--+-08.0-[06-08]----00.0              |                               \-10.0-[09-0b]----00.0              +-05.0              +-05.1              +-05.2              +-05.4              +-11.0              +-11.4              +-16.0              +-16.1              +-1a.0   If I assign the device 0000:81:00.0 to a VM, I get “Failed to find parent device”. I think I should get no error with return value 0 just like bus number is 0, because bus 80 is the root bus as well in my case.   In the <<Intel C610 Series Chipset and Intel X99 Chipset Platform Controller Hub(PCH)>> Datasheet, I found that(Chapter 9.1): For some server platforms, it may be desirable to have multiple PCHs in the system Which means some PCH’s may reside on a bus greater than 0.   So, is this a bug?