linux.git/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c, branch v4.16

drm/amdkfd: Deallocate SDMA queues correctly

2018-03-23T19:30:34+00:00

Deallocate SDMA queues during abnormal process termination and when
queue creation fails after the SDMA allocation.

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

drm/amdkfd: don't always call execute_queues_cpsch()

2018-01-02T18:10:50+00:00

When destroying an inactive queue, we don't need to call
execute_queues_cpsch.

Signed-off-by: Yong Zhao 
Reviewed-by: Oak Zeng 
Signed-off-by: Oded Gabbay

drm/amdkfd: Fix return value 0 when execute_queues_cpsch fails

2018-01-02T18:10:49+00:00

Signed-off-by: Yong Zhao 
Reviewed-by: Oak Zeng 
Signed-off-by: Oded Gabbay

drm/amdkfd: Add debugfs support to KFD

2017-11-27T23:29:49+00:00

This commit adds several debugfs entries for kfd:

kfd/hqds: dumps all HQDs on all GPUs for KFD-controlled compute and
    SDMA RLC queues

kfd/mqds: dumps all MQDs of all KFD processes on all GPUs

kfd/rls: dumps HWS runlists on all GPUs

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

drm/amdkfd: Delete a useless parameter from create_queue function pointer

2017-11-24T23:10:54+00:00

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

drm/amdkfd: Add support for user-mode trap handlers

2017-11-14T21:41:20+00:00

A second-level user mode trap handler can be installed. The CWSR trap
handler jumps to the secondary trap handler conditionally for any
conditions not handled by it. This can be used e.g. for debugging or
catching math exceptions.

When CWSR is disabled, the user mode trap handler is installed as
first level trap handler.

Signed-off-by: Shaoyun.liu 
Signed-off-by: Jay Cornwall 
Signed-off-by: Felix Kuehling 
Signed-off-by: Oded Gabbay

drm/amdkfd: Add CWSR support

2017-11-14T21:41:19+00:00

This hardware feature allows the GPU to preempt shader execution in
the middle of a compute wave, save the state and restore it later
to resume execution.

Memory for saving the state is allocated per queue in user mode and
the address and size passed to the create_queue ioctl. The size
depends on the number of waves that can be in flight simultaneously
on a given ASIC.

Signed-off-by: Shaoyun.liu 
Signed-off-by: Yong Zhao 
Signed-off-by: Felix Kuehling 
Signed-off-by: Oded Gabbay

drm/amdkfd: Minor cleanups

2017-11-01T23:21:33+00:00

These were missed previously when rebasing changes for upstreaming.

v2: Remove redundant sched_policy conditions

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

drm/amdkfd: Update queue_count before mapping queues

2017-11-01T23:21:32+00:00

map_queues_cpsch uses the queue_count to decide whether to upload
a new runlist. So update the counter before calling it.

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

drm/amdkfd: Cleanup DQM ASIC-specific ops

2017-11-01T23:21:31+00:00

Remove empty initialize function.

Rename register_process to update_qpd to avoid confusion with the
non-ASIC-specific register_process.

Shorten ops_asic_specific to asic_ops.

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