[dpdk-dev] vf init issue with patch igb_uio: issue FLR during open and release of device file

[Ferruh Yigit]

On 9/15/2017 10:18 AM, Yang, Qiming wrote:
>> -----Original Message-----
>> From: Thomas Monjalon [mailto:thomas at monjalon.net]
>> Sent: Friday, September 15, 2017 4:43 PM
>> To: Yang, Qiming <qiming.yang at intel.com>
>> Cc: dev at dpdk.org; Tan, Jianfeng <jianfeng.tan at intel.com>; Thotton, Shijith
>> <Shijith.Thotton at cavium.com>; Hu, Xuekun <xuekun.hu at intel.com>; Yigit,
>> Ferruh <ferruh.yigit at intel.com>; Patil, Harish <Harish.Patil at cavium.com>;
>> Gregory Etelson <gregory at weka.io>; stable at dpdk.org
>> Subject: Re: [dpdk-dev] vf init issue with patch igb_uio: issue FLR during open
>> and release of device file
>>
>> Hi
>>
>> 15/09/2017 10:04, Yang, Qiming:
>>> Hi, Thomas
>>> We meet a urgent issue because of Shijith's patch.
>>> When use DPDK version 17.08, DPDK VF driver and kernel PF driver, i40e, ixgbe
>> and qede(Harish said) VF all meet initial failure.
>>
>> This patch has been integrated in DPDK 17.08-rc2 (2 months ago).
>> Why a so obvious issue is discovered only now?
>>
>>> This issue only occurred when use 17.08 igb_uio, vfio-pci and 17.05 igb_uio all
>> works well.
>>> Considering this issue will block our vf driver develop and test work, could we
>> revert this patch first and find another appropriate way?
>>
>> We need to be sure the revert is the right solution because it will be backported
>> to the stable 17.08 release.
>>
>> Shijith suggests to "try removing pci_reset_function from igbuio_pci_open."
>> Can we try this first?
>> Are we sure the bug is not in new firmwares?
> 
> I have tried to remove pci_reset_function, it works in my environment, but it doesn't work in someone's enviroment.
> And removing this function won't it changes the original purpose of his patch?  So I'm not sure it is a good solution.

Yes, removing that will be functionally almost same with revert.

> This bug is not a firmware version related issue, we can reproduce stably with older firmware.

I also think this is not related to the firmware.
But I don't see why works with one version of the Linux PF driver, but
not other.

> 
> Qiming
>