linux-stable.git/drivers/gpu/drm/amd/include/kgd_kfd_interface.h, branch linux-4.19.y

drm/amdkfd: Change the control stack MTYPE from UC to NC on GFX9

2018-09-20T15:25:17+00:00

CWSR fails on Raven if the control stack is MTYPE_UC, which is used
for regular GART mappings. As a workaround we map it using MTYPE_NC.

The MEC firmware expects the control stack at one page offset from the
start of the MQD so it is part of the MQD allocation on GFXv9. AMDGPU
added a memory allocation flag just for this purpose.

Acked-by: Alex Deucher 
Signed-off-by: Yong Zhao 
Reviewed-by: Felix Kuehling 
Signed-off-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdgpu: Add kfd2kgd.set_compute_idle interface

2018-07-16T23:10:36+00:00

This allows automatic switching to the compute power profile depending
on compute activity.

Signed-off-by: Felix Kuehling 
Reviewed-by: Eric Huang 
Reviewed-by: Alex Deucher 
Signed-off-by: Oded Gabbay

drm/amd: Add gpu reset interfaces between amdgpu and amdkfd

2018-07-12T02:32:52+00:00

Signed-off-by: Shaoyun Liu 
Reviewed-by: Felix Kuehling 
Signed-off-by: Felix Kuehling 
Acked-by: Christian König 
Signed-off-by: Oded Gabbay

drm/amdkfd: fix zero reading of VMID and PASID for Hawaii

2018-07-12T02:32:51+00:00

Upon VM Fault, the VMID and PASID written by HW are zeros in
Hawaii. Instead of reading from ih_ring_entry, read directly
from the registers. This workaround fix the soft hang issues
caused by mishandled VM Fault in Hawaii.

Signed-off-by: Lan Xiao 
Signed-off-by: Felix Kuehling 
Acked-by: Christian König 
Signed-off-by: Oded Gabbay

drm/amdgpu: save vm fault information for amdkfd

2018-07-12T02:32:49+00:00

amdgpu save the vm fault related information for KFD usage and keep the
copy until KFD read it.

Signed-off-by: shaoyun liu 
Signed-off-by: Felix Kuehling 
Acked-by: Christian König 
Signed-off-by: Oded Gabbay

drm/amdgpu: Add doorbell routing info to kgd2kfd_shared_resources

2018-04-10T21:33:02+00:00

This is needed for Vega10 and later ASICs to let KFD know which
doorbells can be used for SDMA and CP queues respectively.

Signed-off-by: Felix Kuehling 
Reviewed-by: Oded Gabbay 
Signed-off-by: Oded Gabbay

drm/amdgpu: Remove unused interface from kfd2kgd interface

2018-04-10T21:32:58+00:00

Signed-off-by: Felix Kuehling 
Reviewed-by: Oded Gabbay 
Signed-off-by: Oded Gabbay

drm/amdkfd: Add quiesce_mm and resume_mm to kgd2kfd_calls

2018-03-23T19:32:32+00:00

These interfaces allow KGD to stop and resume all GPU user mode queue
access to a process address space. This is needed for handling MMU
notifiers of userptrs mapped for GPU access in KFD VMs.

Signed-off-by: Felix Kuehling 
Reviewed-by: Oded Gabbay 
Signed-off-by: Oded Gabbay

drm/amdkfd: Add ioctls for GPUVM memory management

2018-03-15T21:27:51+00:00

v2:
* Fix error handling after kfd_bind_process_to_device in
  kfd_ioctl_map_memory_to_gpu
v3:
* Add ioctl to acquire VM from a DRM FD
v4:
* Return number of successful map/unmap operations in failure cases
* Facilitate partial retry after failed map/unmap
* Added comments with parameter descriptions to new APIs
* Defined AMDKFD_IOC_FREE_MEMORY_OF_GPU write-only

Signed-off-by: Felix Kuehling 
Acked-by: Christian König 
Signed-off-by: Oded Gabbay

drm/amdgpu: Add kfd2kgd interface to acquire an existing VM

2018-03-15T21:27:43+00:00

This allows acquiring an existing VM from a render node FD to use it
for a compute process.

Such VMs get destroyed when the original file descriptor is released.
Added a callback from amdgpu_vm_fini to handle KFD VM destruction
correctly in this case.

v2:
* Removed vm->vm_context check in amdgpu_amdkfd_gpuvm_destroy_cb,
  check vm->process_info earlier instead

Signed-off-by: Felix Kuehling 
Acked-by: Christian König 
Signed-off-by: Oded Gabbay