[PATCH libdrm 2/2] drm/amdgpu: add new low overhead command submission API.

[Dave Airlie]

From: Dave Airlie <airlied at redhat.com>

This just sends chunks to the kernel API for a single command
stream.

This should provide a more future proof and extensible API
for command submission.

Signed-off-by: Dave Airlie <airlied at redhat.com>
---
 amdgpu/amdgpu.h    | 21 +++++++++++++++++++++
 amdgpu/amdgpu_cs.c | 30 ++++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+)

diff --git a/amdgpu/amdgpu.h b/amdgpu/amdgpu.h
index 183f974..b4a070d 100644
--- a/amdgpu/amdgpu.h
+++ b/amdgpu/amdgpu.h
@@ -1382,6 +1382,27 @@ int amdgpu_cs_import_syncobj(amdgpu_device_handle dev,
 			     int shared_fd,
 			     uint32_t *syncobj);
 
+/**
+ *  Submit raw command submission to kernel
+ *
+ * \param   dev	       - \c [in] device handle
+ * \param   context    - \c [in] context handle for context id
+ * \param   bo_list_handle - \c [in] request bo list handle (0 for none)
+ * \param   num_chunks - \c [in] number of CS chunks to submit
+ * \param   chunks     - \c [in] array of CS chunks
+ * \param   seq_no     - \c [out] output sequence number for submission.
+ *
+ * \return   0 on success\n
+ *          <0 - Negative POSIX Error code
+ *
+*/
+struct drm_amdgpu_cs_chunk;
+int amdgpu_cs_submit_raw(amdgpu_device_handle dev,
+			 amdgpu_context_handle context,
+			 uint32_t bo_list_handle,
+			 int num_chunks,
+			 struct drm_amdgpu_cs_chunk *chunks,
+			 uint64_t *seq_no);
 #ifdef __cplusplus
 }
 #endif
diff --git a/amdgpu/amdgpu_cs.c b/amdgpu/amdgpu_cs.c
index 722fd75..3c32070 100644
--- a/amdgpu/amdgpu_cs.c
+++ b/amdgpu/amdgpu_cs.c
@@ -634,3 +634,33 @@ int amdgpu_cs_import_syncobj(amdgpu_device_handle dev,
 
 	return drmSyncobjFDToHandle(dev->fd, shared_fd, handle);
 }
+
+int amdgpu_cs_submit_raw(amdgpu_device_handle dev,
+			 amdgpu_context_handle context,
+			 uint32_t bo_list_handle,
+			 int num_chunks,
+			 struct drm_amdgpu_cs_chunk *chunks,
+			 uint64_t *seq_no)
+{
+	union drm_amdgpu_cs cs = {0};
+	uint64_t *chunk_array;
+	int i, r;
+	if (num_chunks == 0)
+		return -EINVAL;
+
+	chunk_array = alloca(sizeof(uint64_t) * num_chunks);
+	for (i = 0; i < num_chunks; i++)
+		chunk_array[i] = (uint64_t)(uintptr_t)&chunks[i];
+	cs.in.chunks = (uint64_t)(uintptr_t)chunk_array;
+	cs.in.ctx_id = context->id;
+	cs.in.bo_list_handle = bo_list_handle;
+	cs.in.num_chunks = num_chunks;
+	r = drmCommandWriteRead(dev->fd, DRM_AMDGPU_CS,
+				&cs, sizeof(cs));
+	if (r)
+		return r;
+
+	if (seq_no)
+		*seq_no = cs.out.handle;
+	return 0;
+}
-- 
2.9.4