[dpdk-dev] [PATCH v4 08/14] virtio: pci: extend virtio pci rw api for vfio interface

Santosh Shukla sshukla at mvista.com
Mon Jan 18 14:09:12 CET 2016


On Mon, Jan 18, 2016 at 12:47 PM, Yuanhan Liu
<yuanhan.liu at linux.intel.com> wrote:
> On Mon, Jan 18, 2016 at 12:15:40PM +0530, Santosh Shukla wrote:
>> I am testing for virtio 1.0 and 0.95 for arm including your patch,
>> soon we;ll post the patch series that is rebased on / dependent on
>> below patchset:
>> - virtio 1.0
>> - vfio-noiommu
>> - KDRV check by huawei
>>
>> IMO, we should start merging the dependent patches as because I'll
>
> Yep, agreed. That's why I was keep pushing Huawei for ACK and
> validation team for testing, although I have tested that. :)
>
>> have to rebase, then do regression across the platform at least for
>> x86/arm64 and it's quite a work now.
>>
>> Beside that I have few question specific to vfio in virtio pmd driver;
>> - vfio don't need resource_init functionality as it uses struct
>> rte_pci_dev but it need parsing so to make sure
>>     1. user has setted no_iommu mode
>>     2. virtio pci device attached to vfio-no-iommu driver or not.
>>
>> So for 1) I am thinking to add RTE_KDRV_VFIO_NOIOMMU mode and a helper
>> function like pci_vfio_is_iommu(), such that  pc_xxx_scan() function
>> updates dev->kdrv with RTE_KDRV_VFIO_NOIOMMU at driver probe time.
>
> That sounds better to me. And that's also what I want to comment on
> your another patch [09/14], that we should try to avoid getting UIO/VFIO
> stuff inside virtio pmd driver, unless it's a must. (yes, I know
> UIO is already an example here, but I don't like it, and badly, I don't
> have the time to check if I can remove it.)
>

Understood, So I'm moving possible required driver/parsing check in
eal_pci.c rather keeping it in virtio, as those parsing/driver
dependency checks are generic, has nothing to do with virtio.

>>
>> case 2) would check for _noiommu mode and then would verify that
>> driver is attached or not?
>
> Sorry, very limited VFIO and noiommu knowledge, and I can't answer, so
> far.
>
>         --yliu
>>
>> above two case applicable to both virtio spec 1.0 and 0.95. I have
>> done changes for those two case for v5 patch series,l any comment
>> welcome before I push patch for review.
>>
>> Thanks.


More information about the dev mailing list