linux.git/drivers/gpu/drm/amd/amdkfd/kfd_process.c, branch v4.18

drm/amdkfd: Implement doorbell allocation for SOC15

2018-04-10T21:33:05+00:00

Allocate doorbells according to the doorbell routing information on
SOC15 ASICs (Vega10 and later). On older ASICs we continue to use the
queue_id as the doorbell ID to maintain compatibility with the Thunk.

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

drm/amdkfd: Clean up KFD_MMAP_ offset handling

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

Use bit-rotate for better clarity and remove _MASK from the #defines as
these represent mmap types.

Centralize all the parsing of the mmap offset in kfd_mmap and add device
parameter to doorbell and reserved_mem map functions.

Encode gpu_id into upper bits of vm_pgoff. This frees up the lower bits
for encoding the the doorbell ID on Vega10.

Signed-off-by: Harish Kasiviswanathan 
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: Use ordered workqueue to restore processes

2018-03-23T19:30:36+00:00

Restoring multiple processes concurrently can lead to live-locks
where each process prevents the other from validating all its BOs.

v2: fix duplicate check of same variable

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

drm/amdkfd: Add TC flush on VMID deallocation for Hawaii

2018-03-15T21:27:50+00:00

On GFX7 the CP does not perform a TC flush when queues are unmapped.
To avoid TC eviction from accessing an invalid VMID, flush it
explicitly before releasing a VMID.

v2: Fix unnecessary list_for_each_entry_safe
v3: Moved allocation to kfd_process_device_init_vm

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

drm/amdkfd: Allocate CWSR trap handler memory for dGPUs

2018-03-15T21:27:49+00:00

Add helpers for allocating GPUVM memory in kernel mode and use them
to allocate memory for the CWSR trap handler.

v2: Use dev instead of pdd->dev in kfd_process_free_gpuvm
v3:
* Cleaned up and simplified kfd_process_alloc_gpuvm
* Moved allocation for dGPU to kfd_process_device_init_vm

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

drm/amdkfd: Add per-process IDR for buffer handles

2018-03-15T21:27:48+00:00

Also used for cleaning up on process termination.

v2: Refactored cleanup on process termination

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

drm/amdkfd: Create KFD VMs on demand

2018-03-15T21:27:44+00:00

Instead of creating all VMs on process creation, create them when
a process is bound to a device. This will later allow registering
an existing VM from a DRM render node FD at runtime, before the
process is bound to the device. This way the render node VM can be
used for KFD instead of creating our own redundant VM.

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

drm/amdkfd: Implement KFD process eviction/restore

2018-02-07T01:32:45+00:00

When the TTM memory manager in KGD evicts BOs, all user mode queues
potentially accessing these BOs must be evicted temporarily. Once
user mode queues are evicted, the eviction fence is signaled,
allowing the migration of the BO to proceed.

A delayed worker is scheduled to restore all the BOs belonging to
the evicted process and restart its queues.

During suspend/resume of the GPU we also evict all processes to allow
KGD to save BOs in system memory, since VRAM will be lost.

v2:
* Account for eviction when updating of q->is_active in MQD manager

Signed-off-by: Harish Kasiviswanathan 
Signed-off-by: Felix Kuehling 
Acked-by: Oded Gabbay 
Signed-off-by: Oded Gabbay

drm/amdkfd: Add GPUVM virtual address space to PDD

2018-02-07T01:32:44+00:00

Create/destroy the GPUVM context during PDD creation/destruction.
Get VM page table base and program it during process registration
(HWS) or VMID allocation (non-HWS).

v2:
* Used dev instead of pdd->dev in kfd_flush_tlb

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