Re: [PATCH 07/10] drm/amdgpu: add concurrent baco reset support for XGMI

Andrey Grodzovsky <Andrey.Grodzovsky@xxxxxxx> · Mon, 9 Dec 2019 10:52:14 -0500



    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.
    Andrey

    
    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.
         
        Regards,
        Ma Le
         
        
            From: Grodzovsky, Andrey
                <Andrey.Grodzovsky@xxxxxxx>
                

                Sent: Saturday, December 7, 2019 5:51 AM

                To: Ma, Le <Le.Ma@xxxxxxx>;
                amd-gfx@xxxxxxxxxxxxxxxxxxxxx; Zhou1, Tao
                <Tao.Zhou1@xxxxxxx>; Deucher, Alexander
                <Alexander.Deucher@xxxxxxx>; Li, Dennis
                <Dennis.Li@xxxxxxx>; Zhang, Hawking
                <Hawking.Zhang@xxxxxxx>

                Cc: Chen, Guchun <Guchun.Chen@xxxxxxx>

                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.
          
        Andrey
        
          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. I’ve 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.
          Andrey
        
      
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx