> From: Ravi Kerur [mailto:rkerur@xxxxxxxxx] > Sent: Friday, February 9, 2018 9:26 PM > To: Alex Williamson <alex.williamson@xxxxxxxxxx> > Cc: kvm@xxxxxxxxxxxxxxx; Peter Xu <peterx@xxxxxxxxxx>; Burakov, Anatoly > <anatoly.burakov@xxxxxxxxx> > Subject: Re: DMAR errors with VT-d and vfio/vfio-pci on IXGBE vf interface > assigned to guest > > CC'ing Anatoly(DPDK/vIOMMU engineer). More information inline. Thanks > Alex for your prompt response. > > > On Fri, Feb 9, 2018 at 12:02 PM, Alex Williamson > <alex.williamson@xxxxxxxxxx> wrote: > > On Fri, 9 Feb 2018 10:31:57 -0800 > > Ravi Kerur <rkerur@xxxxxxxxx> wrote: > > > >> Hi, > >> > >> I am running into an issue when DPDK is started with intel_iommu=on > >> via GRUB command. Problem is not seen with regular kernel driver, > >> error messages show when DPDK is started and happens for both PF and > >> VF interfaces. Discussing with DPDK folks it is not a DPDK issue > >> hence sending an email to this list. Hi Ravi, My apologies, I can see that I wasn't as clear as I should have been. I didn't mean to imply that it wasn't a DPDK issue - it may still very well be one, as Alex has already noted in another email. My replies were specifically concerning IOMMU support. That is, provided the drivers are doing their job correctly, nothing in DPDK's VFIO support will make or break things between releases, as I'm not aware of any major changes going into IOMMU support for DPDK in that time frame. It is still possible for drivers themselves to change between releases in a way that would cause issues, it's just that I'm not that plugged in to DPDK driver development to know enough about it and provide a definitive answer on that front. To avoid spamming another list with irrelevant info, I'll provide you some testing suggestions on DPDK mailing list so that we can hopefully get to the bottom of this. Thanks, Anatoly
