linux/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c, branch v5.14

drm/amdgpu: Fill adev->unique_id with data from PF2VF msg

2021-05-20T02:33:58Z

Initialize unique_id from PF2VF under virtualization. V2: skip smu_get_unique_id() under virtualization Signed-off-by: Jiawei Gu Acked-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: Complete multimedia bandwidth interface

2021-05-20T02:29:58Z

- Update SRIOV PF2VF header with latest revision - Extend existing function in amdgpu_virt.c to read MM bandwidth config from PF2VF message - Add SRIOV Sienna Cichlid codec array and update the bandwidth with PF2VF message v2: squash in removal of unused variable (Alex) Signed-off-by: Bokun Zhang Reviewed-by: Monk liu Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: Add Aldebaran virtualization support

2021-05-10T22:06:43Z

1. add Aldebaran in virtualization detection list. 2. disable Aldebaran virtual display support as there is no GFX engine in Aldebaran. 3. skip TMR loading if Aldebaran is in virtualizatin mode as it shares the one host loaded. Signed-off-by: Zhigang Luo Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: indirect register access for nv12 sriov

2021-04-09T20:50:13Z

using the control bits got from host to control registers access. Signed-off-by: Peng Ju Zhou Reviewed-by: Emily.Deng Signed-off-by: Alex Deucher

drm/amdgpu: indirect register access for nv12 sriov

2021-04-09T20:50:09Z

get pf2vf msg info at it's earliest time so that guest driver can use these info to decide whether register indirect access enabled. Signed-off-by: Peng Ju Zhou Reviewed-by: Emily.Deng Signed-off-by: Alex Deucher

drm/amdgpu: detect sriov capability for aldebaran

2021-03-24T02:52:27Z

SRIOV pf/vf function identifier regsiter in aldebaran is the same as the one in arcturus Signed-off-by: Hawking Zhang Reviewed-by: Kevin Wang Reviewed-by: Le Ma Signed-off-by: Alex Deucher

drm/amd/amdgpu: add error handling to amdgpu_virt_read_pf2vf_data

2021-01-25T22:46:48Z

[Why] when vram lost happened in guest, try to write vram can lead to kernel stuck. [How] When the readback data is invalid, don't do write work, directly reschedule a new work. Signed-off-by: Jingwen Chen Reviewed-by: Monk Liu Signed-off-by: Alex Deucher

drm/amd/amdgpu: remove redundant flush_delayed_work

2021-01-20T21:38:17Z

When using cancel_delayed_work_sync, there's no need to flush_delayed_work first. This sequence can lead to a redundant loop of work executing. Signed-off-by: Jingwen Chen Reviewed-by: Monk Liu Signed-off-by: Alex Deucher

drm/amdgpu/sriov Stop data exchange for wholegpu reset

2021-01-14T04:47:39Z

[Why] When host trigger a whole gpu reset, guest will keep waiting till host finish reset. But there's a work queue in guest exchanging data between vf&pf which need to access frame buffer. During whole gpu reset, frame buffer is not accessable, and this causes the call trace. [How] After vf get reset notification from pf, stop data exchange. Signed-off-by: Jingwen Chen Signed-off-by: Jack Zhang Reviewed-by: Monk Liu Signed-off-by: Alex Deucher

Merge tag 'amd-drm-next-5.11-2020-12-09' of git://people.freedesktop.org/~agd5f/linux into drm-next

2020-12-10T06:55:53Z

amd-drm-next-5.11-2020-12-09: amdgpu: - SR-IOV fixes - Navy Flounder updates - Sienna Cichlid updates - Dimgrey Cavefish updates - Vangogh updates - Misc SMU fixes - Misc display fixes - Last big hunk of W=1 warning fixes - Cursor validation fixes - CI BACO updates From: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20201210045344.21566-1-alexander.deucher@amd.com Signed-off-by: Dave Airlie