RE: [PATCH] drm/amdgpu: perform mode2 reset for sdma fed error on gfx v11_0_3

2023-05-17 Thread Zhang, Hawking
; Yang, Stanley Subject: RE: [PATCH] drm/amdgpu: perform mode2 reset for sdma fed error on gfx v11_0_3 [AMD Official Use Only - General] reset_context is a local variable in amdgpu_ras_do_recovery, if gpu_reset_flag is not used, read regRLC_RLCS_FED_STATUS_0 register and check sdma fed error

RE: [PATCH] drm/amdgpu: perform mode2 reset for sdma fed error on gfx v11_0_3

2023-05-16 Thread Chai, Thomas
-Original Message- From: Zhang, Hawking Sent: Wednesday, May 17, 2023 11:41 AM To: Chai, Thomas ; amd-gfx@lists.freedesktop.org Cc: Zhou1, Tao ; Li, Candice ; Yang, Stanley Subject: RE: [PATCH] drm/amdgpu: perform mode2 reset for sdma fed error on gfx v11_0_3 [AMD Official Use Only

RE: [PATCH] drm/amdgpu: perform mode2 reset for sdma fed error on gfx v11_0_3

2023-05-16 Thread Zhang, Hawking
[AMD Official Use Only - General] Shall we just force the mode-2 reset if it is non-fatal error mode? Is the gpu_reset_flag really necessary in such case? reset_context.method = AMD_RESET_METHOD_MODE2; Ideally, driver decides either perform reset or other error handling approach (i.e. unmap qu