linux/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c, branch v4.14

drm/amdgpu: separate bo_va structure

2017-08-17T19:46:07Z

Split that into vm_bo_base and bo_va to allow other uses as well. Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: cleanup static CSA handling

2017-08-17T19:46:05Z

Move the CSA bo_va from the VM to the fpriv structure. Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu:kiq reg access need timeout(v2)

2017-05-24T21:40:17Z

this is to prevent fence forever waiting if FLR occured during register accessing. v2: use define instead of hardcode for the timeout msec Signed-off-by: Monk Liu Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: Move kiq ring lock out of virt structure

2017-05-24T21:40:12Z

The usage of kiq should not depend on the virtualization. Signed-off-by: Shaoyun Liu Reviewed-by:Andres Rodriquez Signed-off-by: Alex Deucher

drm/amdgpu/virt: bypass cg and pg setting for SRIOV

2017-05-24T21:40:03Z

GPU hypervisor cover all settings of CG and PG, so guest doesn't need to do anything. Bypass it. Signed-off-by: Frank Min Signed-off-by: Xiangliang Yu Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu/virt: add two functions for MM table

2017-04-28T21:32:58Z

Add two functions to allocate & free MM table memory. Signed-off-by: Xiangliang Yu Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu:no need to involv HDP in KIQ

2017-04-06T17:28:04Z

1,KIQ won't touch VRAM so no need to involv HDP flush/invalidate at all. 2,According to CP hw designer KIQ better not use any PM4 package lead to wait behave. Signed-off-by: Monk Liu Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: separate page table allocation from mapping

2017-03-30T03:54:00Z

This makes it easier to implement a replace operation. Signed-off-by: Christian König Reviewed-by: Junwei Zhang Signed-off-by: Alex Deucher

drm/amdgpu:add lock_reset for SRIOV

2017-03-30T03:52:46Z

this lock is used for sriov_gpu_reset, only get this mutex can run into sriov_gpu_reset. we have couple source triggers gpu_reset for SRIOV: 1) submit timedout and trigger reset voluntarily 2) invalid instruction detected by ENGINE and trigger reset voluntarily 2) hypervisor found world switch hang and trigger flr and notify guest to do reset. all need take care and we need a mutex to protect the consistency of reset routine. Signed-off-by: Monk Liu Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu:change kiq lock name

2017-03-30T03:52:45Z

Signed-off-by: Monk Liu Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher