| Age | Commit message (Collapse) | Author | Files | Lines | |
|---|---|---|---|---|---|
| 2015-09-23 | drm/amdgpu: more scheduler cleanups v2 | Christian König | 1 | -1/+1 | |
| Embed the scheduler into the ring structure instead of allocating it. Use the ring name directly instead of the id. v2: rebased, whitespace cleanup Signed-off-by: Christian König <[email protected]> Reviewed-by: Junwei Zhang <[email protected]> Reviewed-by: Chunming Zhou<[email protected]> | |||||
| 2015-09-23 | drm/amdgpu: rename fence->scheduler to sched v2 | Christian König | 1 | -1/+1 | |
| Just to be consistent with the other members. v2: rename the ring member as well. Signed-off-by: Christian König <[email protected]> Reviewed-by: Junwei Zhang <[email protected]> (v1) Reviewed-by: Chunming Zhou<[email protected]> | |||||
| 2015-09-23 | drm/amdgpu: refine the scheduler job type conversion | Junwei Zhang | 1 | -3/+3 | |
| Use container_of rather than casting. Reviewed-by: Christian König <[email protected]> Reviewed-by: David Zhou <[email protected]> Signed-off-by: Junwei Zhang <[email protected]> | |||||
| 2015-09-23 | drm/amdgpu: refine the job naming for amdgpu_job and amdgpu_sched_job | Junwei Zhang | 1 | -18/+18 | |
| Use consistent naming across functions. Reviewed-by: Christian König <[email protected]> Reviewed-by: David Zhou <[email protected]> Signed-off-by: Junwei Zhang <[email protected]> | |||||
| 2015-09-23 | drm/amdgpu: remove process_job callback from the scheduler | Christian König | 1 | -22/+7 | |
| Just free the resources immediately after submitting the job. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Reviewed-by: Junwei Zhang <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> | |||||
| 2015-08-28 | drm/amdgpu: add scheduler dependency callback v2 | Christian König | 1 | -0/+7 | |
| This way the scheduler doesn't wait in it's work thread any more. v2: fix race conditions Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> | |||||
| 2015-08-26 | drm/amdgpu: remove extra parameters from scheduler callbacks | Christian König | 1 | -7/+4 | |
| Signed-off-by: Christian König <[email protected]> Acked-by: Alex Deucher <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> | |||||
| 2015-08-25 | drm/amdgpu: fix last_vm_update fence is not effetive for sched fence | Chunming Zhou | 1 | -0/+1 | |
| Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]> | |||||
| 2015-08-25 | drm/amdgpu: add owner for sched fence | Chunming Zhou | 1 | -2/+2 | |
| Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]> | |||||
| 2015-08-25 | drm/amdgpu: fix and cleanup amd_sched_entity_push_job | Christian König | 1 | -1/+1 | |
| Calling schedule() is probably the worse things we can do. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> | |||||
| 2015-08-25 | drm/amdgpu: remove v_seq handling from the scheduler v2 | Christian König | 1 | -1/+0 | |
| Simply not used any more. Only keep 32bit atomic for fence sequence numbering. v2: trivial rebase Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> (v1) Reviewed-by: Jammy Zhou <[email protected]> (v1) Reviewed-by: Chunming Zhou <[email protected]> (v1) | |||||
| 2015-08-20 | drm/amdgpu: free the job immediately after dispatching it | Christian König | 1 | -4/+3 | |
| Fixes a whole bunch of lockdep warnings. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> | |||||
| 2015-08-20 | drm/amdgpu: abstract amdgpu_job for scheduler | Chunming Zhou | 1 | -54/+34 | |
| Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: add reference for **fence | Chunming Zhou | 1 | -2/+2 | |
| fix fence is released when pass to **fence sometimes. add reference for it. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: remove amd_sched_wait_emit v2 | Christian König | 1 | -2/+0 | |
| Not used any more. v2: remove amd_sched_emit as well. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> | |||||
| 2015-08-17 | drm/amd: add scheduler fence implementation (v2) | Chunming Zhou | 1 | -17/+17 | |
| scheduler fence is based on kernel fence framework. v2: squash in Christian's build fix Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: use kernel submit helper in vm | Chunming Zhou | 1 | -2/+2 | |
| Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: use amd_sched_job in its backend ops | Chunming Zhou | 1 | -17/+17 | |
| Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: cleanup and fix scheduler fence handling v2 | Christian König | 1 | -18/+8 | |
| v2: rebased Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> (v1) Reviewed-by: Chunming Zhou <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: merge amd_sched_entity and amd_context_entity v2 | Christian König | 1 | -6/+6 | |
| Avoiding a couple of casts. v2: rename c_entity to entity as well Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: process sched job exactly triggered by fence signal | Chunming Zhou | 1 | -6/+13 | |
| Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]> | |||||
| 2015-08-17 | Revert "drm/amdgpu: return new seq_no for amd_sched_push_job" | Chunming Zhou | 1 | -2/+7 | |
| This reverts commit d1d33da8eb86b8ca41dd9ed95738030df5267b95. Reviewed-by: Christian K?nig <[email protected]> Conflicts: drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | |||||
| 2015-08-17 | drm/amdgpu: cleanup amdgpu_ctx inti/fini v2 | Christian König | 1 | -5/+3 | |
| Cleanup the kernel context handling. v2: rebased Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> (v1) | |||||
| 2015-08-17 | drm/amdgpu: move sched job process from isr to fence callback | Chunming Zhou | 1 | -0/+13 | |
| This way can avoid interrupt lost, and can process sched job exactly. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: add amd_sched_commit | Jammy Zhou | 1 | -3/+2 | |
| This function is to update last_emitted_v_seq and wake up the waiters. It should be called by driver in the run_job backend function Signed-off-by: Jammy Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: return new seq_no for amd_sched_push_job | Jammy Zhou | 1 | -7/+2 | |
| It is clean to update last_queued_v_seq in the scheduler module Signed-off-by: Jammy Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: some code refinement v2 | Jammy Zhou | 1 | -4/+5 | |
| Fix the code alignment, etc. v2: rebase the code Signed-off-by: Jammy Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: fix null pointer by previous cleanup | Chunming Zhou | 1 | -4/+0 | |
| Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: add kernel fence in ib_submit_kernel_helper | Chunming Zhou | 1 | -2/+6 | |
| every sbumission should be able to get a fence. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: clean up amd sched wait_ts and wait_signal | Christian König | 1 | -6/+0 | |
| Remove code not used at the moment. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: add helper function for kernel submission | Chunming Zhou | 1 | -0/+35 | |
| Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: fix seq in ctx_add_fence | Chunming Zhou | 1 | -2/+2 | |
| if enabling scheduler, then the queued seq is assigned when pushing job before emitting job. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: make sure the fence is emitted before ring to get it. | Chunming Zhou | 1 | -1/+4 | |
| Signed-off-by: Chunming Zhou <[email protected]> Acked-by: Christian K?nig <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> | |||||
| 2015-08-17 | drm/amdgpu: add backend implementation of gpu scheduler (v2) | Chunming Zhou | 1 | -0/+107 | |
| v2: fix rebase breakage Signed-off-by: Chunming Zhou <[email protected]> Acked-by: Christian K?nig <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> | |||||