[PATCH 07/10] drm/amdgpu: add concurrent baco reset support for XGMI
Andrey.Grodzovsky at amd.com
Mon Dec 9 15:52:14 UTC 2019
Thanks a lot Ma for trying - I think I have to have my own system to
debug this so I will keep trying enabling XGMI - i still think the is
the right and the generic solution for multiple nodes reset
synchronization and in fact the barrier should also be used for
synchronizing PSP mode 1 XGMI reset too.
On 12/9/19 6:34 AM, Ma, Le wrote:
> [AMD Official Use Only - Internal Distribution Only]
> Hi Andrey,
> I tried your patches on my 2P XGMI platform. The baco can work at most
> time, and randomly got following error:
> [ 1701.542298] amdgpu: [powerplay] Failed to send message 0x25,
> response 0x0
> This error usually means some sync issue exist for xgmi baco case.
> Feel free to debug your patches on my XGMI platform.
> Ma Le
> *From:*Grodzovsky, Andrey <Andrey.Grodzovsky at amd.com>
> *Sent:* Saturday, December 7, 2019 5:51 AM
> *To:* Ma, Le <Le.Ma at amd.com>; amd-gfx at lists.freedesktop.org; Zhou1,
> Tao <Tao.Zhou1 at amd.com>; Deucher, Alexander
> <Alexander.Deucher at amd.com>; Li, Dennis <Dennis.Li at amd.com>; Zhang,
> Hawking <Hawking.Zhang at amd.com>
> *Cc:* Chen, Guchun <Guchun.Chen at amd.com>
> *Subject:* Re: [PATCH 07/10] drm/amdgpu: add concurrent baco reset
> support for XGMI
> Hey Ma, attached a solution - it's just compiled as I still can't make
> my XGMI setup work (with bridge connected only one device is visible
> to the system while the other is not). Please try it on your system if
> you have a chance.
> On 12/4/19 10:14 PM, Ma, Le wrote:
> AFAIK it's enough for even single one node in the hive to to fail
> the enter the BACO state on time to fail the entire hive reset
> procedure, no ?
> [Le]: Yeah, agree that. Iâve been thinking that make all nodes
> entering baco simultaneously can reduce the possibility of node
> failure to enter/exit BACO risk. For example, in an XGMI hive with
> 8 nodes, the total time interval of 8 nodes enter/exit BACO on 8
> CPUs is less than the interval that 8 nodes enter BACO serially
> and exit BACO serially depending on one CPU with yield capability.
> This interval is usually strict for BACO feature itself. Anyway,
> we need more looping test later on any method we will choose.
> Any way - I see our discussion blocks your entire patch set - I
> think you can go ahead and commit yours way (I think you got an RB
> from Hawking) and I will look then and see if I can implement my
> method and if it works will just revert your patch.
> [Le]: OK, fine.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the amd-gfx