diff options
| author | Huang Rui <ray.huang@amd.com> | 2020-02-11 18:26:07 +0800 |
|---|---|---|
| committer | Huang Rui <ray.huang@amd.com> | 2020-02-12 19:55:09 +0800 |
| commit | cf9eb78a89ccfe0a13f9d36d80604c731d5c18d2 (patch) | |
| tree | 3d37bff6f9c116ba0dc717053d0d794760715fab | |
| parent | fca0849af3bf0682d75d0a11e52e76592c5f42ef (diff) | |
| download | external_libdrm-cf9eb78a89ccfe0a13f9d36d80604c731d5c18d2.tar.gz external_libdrm-cf9eb78a89ccfe0a13f9d36d80604c731d5c18d2.tar.bz2 external_libdrm-cf9eb78a89ccfe0a13f9d36d80604c731d5c18d2.zip | |
amdgpu: use amdgpu_cs_submit_raw2 in amdgpu_cs_submit
So far, amdgpu_cs_submit_raw2 is mainly used for upper layer (Mesa), however,
amdgpu_cs_submit is used for current all unit tests. Our intention is that the
unit tests can actually verify the API which is really used.
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
| -rw-r--r-- | amdgpu/amdgpu_cs.c | 8 |
1 files changed, 5 insertions, 3 deletions
diff --git a/amdgpu/amdgpu_cs.c b/amdgpu/amdgpu_cs.c index aaa1f7b1..864a76a9 100644 --- a/amdgpu/amdgpu_cs.c +++ b/amdgpu/amdgpu_cs.c @@ -226,9 +226,11 @@ static int amdgpu_cs_submit_one(amdgpu_context_handle context, struct drm_amdgpu_cs_chunk_data *chunk_data; struct drm_amdgpu_cs_chunk_dep *dependencies = NULL; struct drm_amdgpu_cs_chunk_dep *sem_dependencies = NULL; + amdgpu_device_handle dev = context->dev; struct list_head *sem_list; amdgpu_semaphore_handle sem, tmp; uint32_t i, size, sem_count = 0; + uint64_t seq_no; bool user_fence; int r = 0; @@ -354,12 +356,12 @@ static int amdgpu_cs_submit_one(amdgpu_context_handle context, chunks[i].chunk_data = (uint64_t)(uintptr_t)sem_dependencies; } - r = drmCommandWriteRead(context->dev->fd, DRM_AMDGPU_CS, - &cs, sizeof(cs)); + r = amdgpu_cs_submit_raw2(dev, context, cs.in.bo_list_handle, cs.in.num_chunks, + chunks, &seq_no); if (r) goto error_unlock; - ibs_request->seq_no = cs.out.handle; + ibs_request->seq_no = seq_no; context->last_seq[ibs_request->ip_type][ibs_request->ip_instance][ibs_request->ring] = ibs_request->seq_no; error_unlock: pthread_mutex_unlock(&context->sequence_mutex); |