kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h, branch v4.18.18

drm/amdgpu/vg20:increase 3 rings for AMDGPU_MAX_RINGS

2018-05-18T21:08:12+00:00

For Vega20, there are two UVD Hardware. One more UVD hardware adds one decode ring and two encode rings. So AMDGPU_MAX_RINGS need increase by 3. Signed-off-by: James Zhu Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: optionally do a writeback but don't invalidate TC for IB fences

2018-05-15T18:43:32+00:00

There is a new IB flag that enables this new behavior. Full invalidation is unnecessary for RELEASE_MEM and doesn't make sense when draw calls from two adjacent gfx IBs run in parallel. This will be the new default for Mesa. v2: bump the version Signed-off-by: Marek Olšák Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: add emit_reg_write_reg_wait ring callback

2018-05-15T18:43:13+00:00

This callback writes a value to a register and then reads back another register and waits for a value in a single operation. Provide a helper function using two operations for engines that don't support this opertion. Reviewed-by: Huang Rui Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: Add KFD eviction fence

2018-02-07T01:32:35+00:00

This fence is used by KFD to keep memory resident while user mode queues are enabled. Trying to evict memory will trigger the enable_signaling callback, which starts a KFD eviction, which involves preempting user mode queues before signaling the fence. There is one such fence per process. v2: * Grab a reference to mm_struct * Dereference fence after NULL check * Simplify fence release, no need to signal without anyone waiting * Added signed-off-by Harish, who is the original author of this code v3: * update MAINTAINERS file * change amd_kfd_ prefix to amdkfd_ * remove useless initialization of variable to NULL v4: * set amdkfd_fence_ops to be static * Suggested by: Fengguang Wu Signed-off-by: Harish Kasiviswanathan Signed-off-by: Felix Kuehling Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay

drm/amdgpu: Fix header file dependencies

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

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

drm/amdgpu: separate PASID mapping from VM flush v2

2018-02-19T19:20:18+00:00

Stuffing the PASID mapping into the VM flush isn't flexible enough since the PASID mapping changes not as often as we need a VM flush. v2: add missing use of gmc_v7_0_emit_pasid_mapping Signed-off-by: Christian König Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdgpu: cache the fence to wait for a VMID

2018-02-19T19:19:18+00:00

Beneficial when a lot of processes are waiting for VMIDs. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher

drm/amdgpu: add new emit_reg_wait callback

2018-02-19T19:19:08+00:00

Allows us to wait for a register value/mask on a ring. Signed-off-by: Christian König Reviewed-by: Felix Kuehling Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: remove now superflous *_hdp operation

2018-02-19T19:18:22+00:00

All HDP invalidation and most flush can now be replaced by the generic ASIC function. Signed-off-by: Christian König Acked-by: Chunming Zhou Signed-off-by: Alex Deucher

drm/amdgpu: forward pasid to backend flush implementations

2018-02-19T19:17:47+00:00

rd the pasid from the VM code to the emit_vm_flush function and update all implementations with the new parameter. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher