Re: [Regression] "iommu/amd: Relax locking in dma_ops path" makes tg3 ethernet transmit queue timeout

From: Kai-Heng Feng
Date: Mon May 18 2020 - 11:32:12 EST




> On May 18, 2020, at 22:05, Kai-Heng Feng <kai.heng.feng@xxxxxxxxxxxxx> wrote:
>
>
>
>> On May 18, 2020, at 21:32, Joerg Roedel <jroedel@xxxxxxx> wrote:
>>
>> On Mon, May 18, 2020 at 05:06:45PM +0800, Kai-Heng Feng wrote:
>>> Particularly, as soon as the spinlock is removed, the issue can be reproduced.
>>> Function domain_flush_complete() doesn't seem to affect the status.
>>>
>>> However, the .map_page callback was removed by be62dbf554c5
>>> ("iommu/amd: Convert AMD iommu driver to the dma-iommu api"), so
>>> there's no easy revert for this issue.
>>>
>>> This is still reproducible as of today's mainline kernel, v5.7-rc6.
>>
>> Is there any error message from the IOMMU driver?
>>
>
> As of mainline kernel, there's no error message from IOMMU driver.
> There are some complains from v4.15-rc1:
> https://pastebin.ubuntu.com/p/qn4TXkFxsc/

Just tested v5.7-rc6, the issue disappears as soon as kernel boots with "iommu=off".

Kai-Heng

>
> Kai-Heng