diff mbox series

[v3,2/5] drm/ttm: revise ttm_bo_move_to_lru_tail to support bulk moves

Message ID 1534154331-11810-3-git-send-email-ray.huang@amd.com (mailing list archive)
State New, archived
Headers show
Series drm/ttm,amdgpu: Introduce LRU bulk move functionality | expand

Commit Message

Huang Rui Aug. 13, 2018, 9:58 a.m. UTC
From: Christian König <christian.koenig@amd.com>

When move a BO to the end of LRU, it need remember the BO positions.
Make sure all moved bo in between "first" and "last". And they will be bulk
moving together.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Tested-by: Mike Lothian <mike@fireburn.co.uk>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c |  8 ++++----
 drivers/gpu/drm/ttm/ttm_bo.c           | 26 +++++++++++++++++++++++++-
 include/drm/ttm/ttm_bo_api.h           |  6 +++++-
 3 files changed, 34 insertions(+), 6 deletions(-)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 015613b..9c84770 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -297,9 +297,9 @@  int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 				break;
 
 			spin_lock(&glob->lru_lock);
-			ttm_bo_move_to_lru_tail(&bo->tbo);
+			ttm_bo_move_to_lru_tail(&bo->tbo, NULL);
 			if (bo->shadow)
-				ttm_bo_move_to_lru_tail(&bo->shadow->tbo);
+				ttm_bo_move_to_lru_tail(&bo->shadow->tbo, NULL);
 			spin_unlock(&glob->lru_lock);
 		}
 
@@ -319,9 +319,9 @@  int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		if (!bo->parent)
 			continue;
 
-		ttm_bo_move_to_lru_tail(&bo->tbo);
+		ttm_bo_move_to_lru_tail(&bo->tbo, NULL);
 		if (bo->shadow)
-			ttm_bo_move_to_lru_tail(&bo->shadow->tbo);
+			ttm_bo_move_to_lru_tail(&bo->shadow->tbo, NULL);
 	}
 	spin_unlock(&glob->lru_lock);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 7c48472..7117b6b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -214,12 +214,36 @@  void ttm_bo_del_sub_from_lru(struct ttm_buffer_object *bo)
 }
 EXPORT_SYMBOL(ttm_bo_del_sub_from_lru);
 
-void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo)
+static void ttm_bo_bulk_move_set_pos(struct ttm_lru_bulk_move_pos *pos,
+				     struct ttm_buffer_object *bo)
+{
+	if (!pos->first)
+		pos->first = bo;
+	pos->last = bo;
+}
+
+void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo,
+			     struct ttm_lru_bulk_move *bulk)
 {
 	reservation_object_assert_held(bo->resv);
 
 	ttm_bo_del_from_lru(bo);
 	ttm_bo_add_to_lru(bo);
+
+	if (bulk && !(bo->mem.placement & TTM_PL_FLAG_NO_EVICT)) {
+		switch (bo->mem.mem_type) {
+		case TTM_PL_TT:
+			ttm_bo_bulk_move_set_pos(&bulk->tt[bo->priority], bo);
+			break;
+
+		case TTM_PL_VRAM:
+			ttm_bo_bulk_move_set_pos(&bulk->vram[bo->priority], bo);
+			break;
+		}
+		if (bo->ttm && !(bo->ttm->page_flags &
+				 (TTM_PAGE_FLAG_SG | TTM_PAGE_FLAG_SWAPPED)))
+			ttm_bo_bulk_move_set_pos(&bulk->swap[bo->priority], bo);
+	}
 }
 EXPORT_SYMBOL(ttm_bo_move_to_lru_tail);
 
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index a01ba20..0d4eb81 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -51,6 +51,8 @@  struct ttm_placement;
 
 struct ttm_place;
 
+struct ttm_lru_bulk_move;
+
 /**
  * struct ttm_bus_placement
  *
@@ -405,12 +407,14 @@  void ttm_bo_del_from_lru(struct ttm_buffer_object *bo);
  * ttm_bo_move_to_lru_tail
  *
  * @bo: The buffer object.
+ * @bulk: optional bulk move structure to remember BO positions
  *
  * Move this BO to the tail of all lru lists used to lookup and reserve an
  * object. This function must be called with struct ttm_bo_global::lru_lock
  * held, and is used to make a BO less likely to be considered for eviction.
  */
-void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo);
+void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo,
+			     struct ttm_lru_bulk_move *bulk);
 
 /**
  * ttm_bo_lock_delayed_workqueue