diff options
| author | shaoyunl <shaoyun.liu@amd.com> | 2021-02-16 20:50:42 +0300 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2021-03-24 06:10:38 +0300 |
| commit | e3c1b0712fdb039d9139ac0910be9a658c9cb65e (patch) | |
| tree | c36c46491fe9ace02e73059e3dbbab0fb1059fa5 /drivers/gpu/drm/amd/amdgpu/amdgpu.h | |
| parent | 655ce9cb13b5967558d81dd644868473ecfb5ee4 (diff) | |
| download | linux-e3c1b0712fdb039d9139ac0910be9a658c9cb65e.tar.xz | |
drm/amdgpu: Reset the devices in the XGMI hive duirng probe
In passthrough configuration, hypervisior will trigger the SBR(Secondary bus reset) to the devices
without sync to each other. This could cause device hang since for XGMI configuration, all the devices
within the hive need to be reset at a limit time slot. This serial of patches try to solve this issue
by co-operate with new SMU which will only do minimum house keeping to response the SBR request but don't
do the real reset job and leave it to driver. Driver need to do the whole sw init and minimum HW init
to bring up the SMU and trigger the reset(possibly BACO) on all the ASICs at the same time
Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
Acked-by: Andrey Grodzovsky andrey.grodzovsky@amd.com
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu.h')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu.h | 13 |
1 files changed, 13 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index d660deec20f0..ddf79ef0ccee 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -124,6 +124,10 @@ struct amdgpu_mgpu_info uint32_t num_gpu; uint32_t num_dgpu; uint32_t num_apu; + + /* delayed reset_func for XGMI configuration if necessary */ + struct delayed_work delayed_reset_work; + bool pending_reset; }; struct amdgpu_watchdog_timer @@ -1128,6 +1132,15 @@ void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev, bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type); bool amdgpu_device_has_dc_support(struct amdgpu_device *adev); +int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, + struct amdgpu_job *job, + bool *need_full_reset_arg); + +int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive, + struct list_head *device_list_handle, + bool *need_full_reset_arg, + bool skip_hw_reset); + int emu_soc_asic_init(struct amdgpu_device *adev); /* |