[PATCH v1 13/20] drm/amdgpu: use multiple entities in amdgpu_move_blit

[Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>]

Thanks to "drm/ttm: rework pipelined eviction fence handling", ttm
can deal correctly with moves and evictions being executed from
different contexts.

Create several entities and use them in a round-robin fashion.

Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 14 +++++++++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h |  1 +
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 839ea8c7f6be..c3a88574f143 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -401,6 +401,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct amdgpu_bo *abo = ttm_to_amdgpu_bo(bo);
+	struct amdgpu_ttm_entity *entity;
 	struct amdgpu_copy_mem src, dst;
 	struct dma_fence *fence = NULL;
 	int r;
@@ -412,8 +413,12 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 	src.offset = 0;
 	dst.offset = 0;
 
+	int e = atomic_inc_return(&adev->mman.next_move_entity) %
+				  adev->mman.num_move_entities;
+	entity = &adev->mman.move_entities[e];
+
 	r = amdgpu_ttm_copy_mem_to_mem(adev,
-				       &adev->mman.move_entities[0],
+				       entity,
 				       &src, &dst,
 				       new_mem->size,
 				       amdgpu_bo_encrypted(abo),
@@ -426,7 +431,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 	    (abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) {
 		struct dma_fence *wipe_fence = NULL;
 
-		r = amdgpu_fill_buffer(&adev->mman.move_entities[0],
+		r = amdgpu_fill_buffer(entity,
 				       abo, 0, &wipe_fence, fence,
 				       AMDGPU_KERNEL_JOB_ID_MOVE_BLIT);
 		if (r) {
@@ -2179,10 +2184,12 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
 	uint64_t size;
 	int r, i, j;
-	u32 num_clear_entities, num_move_entities, windows, w;
+	u32 num_clear_entities, num_move_entities;
+	u32 windows, w;
 
 	num_clear_entities = adev->sdma.num_instances;
 	num_move_entities = MIN(adev->sdma.num_instances, TTM_FENCES_MAX_SLOT_COUNT);
+	man->pipelined_eviction.n_fences = num_move_entities;
 	windows = adev->gmc.is_app_apu ? 0 : (2 * num_move_entities + num_clear_entities);
 
 	if (!adev->mman.initialized || amdgpu_in_reset(adev) ||
@@ -2205,6 +2212,7 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 		}
 
 		adev->mman.num_move_entities = num_move_entities;
+		atomic_set(&adev->mman.next_move_entity, 0);
 		for (i = 0; i < num_move_entities; i++) {
 			r = drm_sched_entity_init(&adev->mman.move_entities[i].base,
 						  DRM_SCHED_PRIORITY_NORMAL, &sched,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 3fc31c7c6bfe..c3df9d24fb96 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -76,6 +76,7 @@ struct amdgpu_mman {
 	atomic_t next_clear_entity;
 	u32 num_clear_entities;
 	struct amdgpu_ttm_entity move_entities[TTM_FENCES_MAX_SLOT_COUNT];
+	atomic_t next_move_entity;
 	u32 num_move_entities;
 
 	struct amdgpu_vram_mgr vram_mgr;
-- 
2.43.0