On Fri, Jun 2, 2017 at 3:31 AM, Daniel Kim <d...@playmechanix.com> wrote:
> On Fri, May 12, 2017 at 6:12 PM, Daniel Kim <d...@playmechanix.com> wrote:
>> I believe I do have IOMMU enabled. At least the dmesg output seems to
>> imply that I do:
>> [ 1.141948] iommu: Adding device 0000:00:02.0 to group 0
>> [ 1.142033] iommu: Adding device 0000:00:10.0 to group 1
>> [ 1.142074] iommu: Adding device 0000:00:10.1 to group 1
>> [ 1.142119] iommu: Adding device 0000:00:11.0 to group 2
>> [ 1.142172] iommu: Adding device 0000:00:12.0 to group 3
>> [ 1.142184] iommu: Adding device 0000:00:12.2 to group 3
>> [ 1.142234] iommu: Adding device 0000:00:13.0 to group 4
>> [ 1.142247] iommu: Adding device 0000:00:13.2 to group 4
>> [ 1.142303] iommu: Adding device 0000:00:14.0 to group 5
>> [ 1.142315] iommu: Adding device 0000:00:14.2 to group 5
>> [ 1.142328] iommu: Adding device 0000:00:14.3 to group 5
>> [ 1.142373] iommu: Adding device 0000:00:14.4 to group 6
>> [ 1.142417] iommu: Adding device 0000:00:14.5 to group 7
>> [ 1.142529] iommu: Adding device 0000:00:15.0 to group 8
>> [ 1.142570] iommu: Adding device 0000:00:15.2 to group 8
>> [ 1.142639] iommu: Adding device 0000:00:18.0 to group 9
>> [ 1.142653] iommu: Adding device 0000:00:18.1 to group 9
>> [ 1.142668] iommu: Adding device 0000:00:18.2 to group 9
>> [ 1.142682] iommu: Adding device 0000:00:18.3 to group 9
>> [ 1.142695] iommu: Adding device 0000:00:18.4 to group 9
>> [ 1.142712] iommu: Adding device 0000:00:18.5 to group 9
>> [ 1.142725] iommu: Adding device 0000:01:00.0 to group 0
>> [ 1.142733] iommu: Adding device 0000:01:00.1 to group 0
>> [ 1.142840] iommu: Adding device 0000:04:00.0 to group 8
>> [ 1.143305] AMD-Vi: Found IOMMU at 0000:00:00.2 cap 0x40
>>
>> The last kernel I used where the NIC mostly worked was 4.4.0 (x86-64).
>> Even when it worked, it had this issue we've experienced since v3.13
>> where the NIC would suddenly become unresponsive. It won't be
>> considered disconnected from the network, but RX/TX packets, errors,
>> dropped, etc. values displayed with ifconfig would show a number that
>> looked suspiciously close to 32-bit INT_MAX.
>>
>> Since v4.8, I can trigger it much faster and it now prints out a call
>> stack and other messages into dmesg.
>
> I'd like to follow up on this since I haven't heard of any updates for
> awhile. Is there anything I can do on my end to help?
We are analyzing the Logs. Please wait for some more time.
If needed, we will send a debug patch to collect more information.
