<div dir="ltr"><div>Hi Alex,</div><div><br></div><div>Yes, my dmesg did report this issue related to RMRR. <br></div><div><br></div><div>Based on your suggestion, I ran the hp-script-utils steps mentioned at <a href="https://support.hpe.com/hpsc/doc/public/display?docId=emr_na-c04781229">https://support.hpe.com/hpsc/doc/public/display?docId=emr_na-c04781229</a>. I disabled RMRR for all 3 of my available PCI slots.</div><div><br></div><div>I swapped NIC's in and out of different PCI slots until I found one magical slot which just works. I inserted my 4-port Intel 82580 NIC (branded HP 365T), and then successfully started a VM on one of the 4 available ports. None of the NIC's I tried would work in the first two slots I tried. <br></div></div><br><div class="gmail_quote"><div dir="ltr">On Mon, Aug 6, 2018 at 5:09 PM Alex Williamson <<a href="mailto:alex.williamson@redhat.com">alex.williamson@redhat.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">On Mon, 6 Aug 2018 17:04:24 -0600<br>
Alex Williamson <<a href="mailto:alex.williamson@redhat.com" target="_blank">alex.williamson@redhat.com</a>> wrote:<br>
<br>
> On Mon, 6 Aug 2018 16:39:51 -0600<br>
> Quincy Wofford <<a href="mailto:quincy.wofford@gmail.com" target="_blank">quincy.wofford@gmail.com</a>> wrote:<br>
> <br>
> > I'm attempting PCI-passthrough from host to guest on an HP ProLiant 380P,<br>
> > which has an updated, yet rather old BIOS (2015), but it does support VT-d.<br>
> > I'm running CentOS 7, kernel 3.10.0-862.9.1.el7.x86_64.<br>
> > <br>
> > I have an Intel 82580 NIC installed with 4 ports. Each of these ports is in<br>
> > its own IOMMU group (I enabled SR-IOV at the BIOS, which might be the<br>
> > reason they show up separately)<br>
> > <br>
> > After detaching and adding a 'hostdev' device with the appropriate pci<br>
> > address, I attempt to start my VM. I get " failed to set iommu for<br>
> > container: Operation not permitted". As recommended here (<br>
> > <a href="http://vfio.blogspot.com/2014/08/vfiovga-faq.html" rel="noreferrer" target="_blank">http://vfio.blogspot.com/2014/08/vfiovga-faq.html</a>) I parsed dmesg in an<br>
> > attempt to find:<br>
> > <br>
> > -------------------<br>
> > No interrupt remapping support. Use the module param<br>
> > "allow_unsafe_interrupts" to enable VFIO IOMMU support on this platform<br>
> > -------------------<br>
> > ...but nothing similar exists in my logs.<br>
> > <br>
> > Since this device is showing up in its own IOMMU group, I assume ACS<br>
> > override won't get me any further. In any case, it is not an option for me<br>
> > to leave ACS override on. I can turn it on for testing, the server is not<br>
> > currently in production.<br>
> > <br>
> > Below you will find links to relevant configs:<br>
> > <br>
> > virsh edit monitor: <a href="https://pastebin.com/kzCR0E5t" rel="noreferrer" target="_blank">https://pastebin.com/kzCR0E5t</a><br>
> > nodedev-list --tree: <a href="https://pastebin.com/AfYJKZX9" rel="noreferrer" target="_blank">https://pastebin.com/AfYJKZX9</a><br>
> > nodedev-dumpxml pci_0000_04_00_1: <a href="https://pastebin.com/VUurQ05Y" rel="noreferrer" target="_blank">https://pastebin.com/VUurQ05Y</a><br>
> > virsh start monitor: <a href="https://pastebin.com/6ANCL5pJ" rel="noreferrer" target="_blank">https://pastebin.com/6ANCL5pJ</a> <br>
> <br>
> dmesg likely has the answer, probably reports:<br>
> <br>
> "Device is ineligible for IOMMU domain attach due to platform RMRR<br>
> requirement. Contact your platform vendor."<br>
> <br>
> You can read more about it here:<br>
> <br>
> <a href="https://access.redhat.com/sites/default/files/attachments/rmrr-wp1.pdf" rel="noreferrer" target="_blank">https://access.redhat.com/sites/default/files/attachments/rmrr-wp1.pdf</a><br>
> <br>
> The quick summary is that the hardware vendor has imposed a mapping<br>
> requirement for the device that is incompatible with device<br>
> assignment. AIUI HP for disabling these mappings for some systems,<br>
> hopefully yours is one. Good luck,<br>
<br>
Oops, missed half the thought there. Depending on the generation of<br>
your Proliant, HP may have instructions for disabling the interfering<br>
reserved memory ranges. Thanks,<br>
<br>
Alex<br>
</blockquote></div>