drm/amdgpu: add gang submit frontend v6

Allows submitting jobs as gang which needs to run on multiple engines at the
same time.

All members of the gang get the same implicit, explicit and VM dependencies. So
no gang member will start running until everything else is ready.

The last job is considered the gang leader (usually a submission to the GFX
ring) and used for signaling output dependencies.

Each job is remembered individually as user of a buffer object, so there is no
joining of work at the end.

v2: rebase and fix review comments from Andrey and Yogesh
v3: use READ instead of BOOKKEEP for now because of VM unmaps, set gang
    leader only when necessary
v4: fix order of pushing jobs and adding fences found by Trigger.
v5: fix job index calculation and adding IBs to jobs
v6: fix typo found by Alex

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 7 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h
index 30ecc4917f81..cbaa19b2b8a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h
@@ -27,6 +27,8 @@
 #include "amdgpu_bo_list.h"
 #include "amdgpu_ring.h"
 
+#define AMDGPU_CS_GANG_SIZE	4
+
 struct amdgpu_bo_va_mapping;
 
 struct amdgpu_cs_chunk {
@@ -50,9 +52,11 @@ struct amdgpu_cs_parser {
 	unsigned		nchunks;
 	struct amdgpu_cs_chunk	*chunks;
 
-	/* scheduler job object */
-	struct amdgpu_job	*job;
-	struct drm_sched_entity	*entity;
+	/* scheduler job objects */
+	unsigned int		gang_size;
+	struct drm_sched_entity	*entities[AMDGPU_CS_GANG_SIZE];
+	struct amdgpu_job	*jobs[AMDGPU_CS_GANG_SIZE];
+	struct amdgpu_job	*gang_leader;
 
 	/* buffer objects */
 	struct ww_acquire_ctx		ticket;