drm/amdgpu: use bulk moves for efficient VM LRU handling (v6)

I continue to work for bulk moving that based on the proposal by Christian.

Background:
amdgpu driver will move all PD/PT and PerVM BOs into idle list. Then move all of
them on the end of LRU list one by one. Thus, that cause so many BOs moved to
the end of the LRU, and impact performance seriously.

Then Christian provided a workaround to not move PD/PT BOs on LRU with below
patch:
Commit 0bbf32026cf5ba41e9922b30e26e1bed1ecd38ae ("drm/amdgpu: band aid
validating VM PTs")

However, the final solution should bulk move all PD/PT and PerVM BOs on the LRU
instead of one by one.

Whenever amdgpu_vm_validate_pt_bos() is called and we have BOs which need to be
validated we move all BOs together to the end of the LRU without dropping the
lock for the LRU.

While doing so we note the beginning and end of this block in the LRU list.

Now when amdgpu_vm_validate_pt_bos() is called and we don't have anything to do,
we don't move every BO one by one, but instead cut the LRU list into pieces so
that we bulk move everything to the end in just one operation.

Test data:
+--------------+-----------------+-----------+---------------------------------------+
|              |The Talos        |Clpeak(OCL)|BusSpeedReadback(OCL)                  |
|              |Principle(Vulkan)|           |                                       |
+------------------------------------------------------------------------------------+
|              |                 |           |0.319 ms(1k) 0.314 ms(2K) 0.308 ms(4K) |
| Original     |  147.7 FPS      |  76.86 us |0.307 ms(8K) 0.310 ms(16K)             |
+------------------------------------------------------------------------------------+
| Orignial + WA|                 |           |0.254 ms(1K) 0.241 ms(2K)              |
|(don't move   |  162.1 FPS      |  42.15 us |0.230 ms(4K) 0.223 ms(8K) 0.204 ms(16K)|
|PT BOs on LRU)|                 |           |                                       |
+------------------------------------------------------------------------------------+
| Bulk move    |  163.1 FPS      |  40.52 us |0.244 ms(1K) 0.252 ms(2K) 0.213 ms(4K) |
|              |                 |           |0.214 ms(8K) 0.225 ms(16K)             |
+--------------+-----------------+-----------+---------------------------------------+

After test them with above three benchmarks include vulkan and opencl. We can
see the visible improvement than original, and even better than original with
workaround.

v2: move all BOs include idle, relocated, and moved list to the end of LRU and
put them together.
v3: remove unused parameter and use list_for_each_entry instead of the one with
save entry.
v4: move the amdgpu_vm_move_to_lru_tail after command submission, at that time,
all bo will be back on idle list.
v5: remove amdgpu_vm_move_to_lru_tail_by_list(), use bulk_moveable instread of
validated, and move ttm_bo_bulk_move_lru_tail() also into
amdgpu_vm_move_to_lru_tail().
v6: clean up and fix return value.

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>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
Acked-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c

@@ -1259,6 +1259,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	union drm_amdgpu_cs *cs = data;
 	struct amdgpu_cs_parser parser = {};
 	bool reserved_buffers = false;
+	struct amdgpu_fpriv *fpriv;
 	int i, r;
 
 	if (!adev->accel_working)
@@ -1303,6 +1304,8 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 	r = amdgpu_cs_submit(&parser, cs);
 
+	fpriv = filp->driver_priv;
+	amdgpu_vm_move_to_lru_tail(adev, &fpriv->vm);
 out:
 	amdgpu_cs_parser_fini(&parser, r, reserved_buffers);
 	return r;

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

@@ -267,6 +267,47 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 	list_add(&entry->tv.head, validated);
 }
 
+/**
+ * amdgpu_vm_move_to_lru_tail - move all BOs to the end of LRU
+ *
+ * @adev: amdgpu device pointer
+ * @vm: vm providing the BOs
+ *
+ * Move all BOs to the end of LRU and remember their positions to put them
+ * together.
+ */
+void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
+				struct amdgpu_vm *vm)
+{
+	struct ttm_bo_global *glob = adev->mman.bdev.glob;
+	struct amdgpu_vm_bo_base *bo_base;
+
+	if (vm->bulk_moveable) {
+		spin_lock(&glob->lru_lock);
+		ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move);
+		spin_unlock(&glob->lru_lock);
+		return;
+	}
+
+	memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move));
+
+	spin_lock(&glob->lru_lock);
+	list_for_each_entry(bo_base, &vm->idle, vm_status) {
+		struct amdgpu_bo *bo = bo_base->bo;
+
+		if (!bo->parent)
+			continue;
+
+		ttm_bo_move_to_lru_tail(&bo->tbo, &vm->lru_bulk_move);
+		if (bo->shadow)
+			ttm_bo_move_to_lru_tail(&bo->shadow->tbo,
+						&vm->lru_bulk_move);
+	}
+	spin_unlock(&glob->lru_lock);
+
+	vm->bulk_moveable = true;
+}
+
 /**
  * amdgpu_vm_validate_pt_bos - validate the page table BOs
  *
@@ -284,10 +325,11 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			      int (*validate)(void *p, struct amdgpu_bo *bo),
 			      void *param)
 {
-	struct ttm_bo_global *glob = adev->mman.bdev.glob;
 	struct amdgpu_vm_bo_base *bo_base, *tmp;
 	int r = 0;
 
+	vm->bulk_moveable &= list_empty(&vm->evicted);
+
 	list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) {
 		struct amdgpu_bo *bo = bo_base->bo;
 
@@ -295,14 +337,6 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		if (r)
 			break;
 
-		if (bo->parent) {
-			spin_lock(&glob->lru_lock);
-			ttm_bo_move_to_lru_tail(&bo->tbo, NULL);
-			if (bo->shadow)
-				ttm_bo_move_to_lru_tail(&bo->shadow->tbo, NULL);
-			spin_unlock(&glob->lru_lock);
-		}
-
 		if (bo->tbo.type != ttm_bo_type_kernel) {
 			spin_lock(&vm->moved_lock);
 			list_move(&bo_base->vm_status, &vm->moved);
@@ -312,19 +346,6 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		}
 	}
 
-	spin_lock(&glob->lru_lock);
-	list_for_each_entry(bo_base, &vm->idle, vm_status) {
-		struct amdgpu_bo *bo = bo_base->bo;
-
-		if (!bo->parent)
-			continue;
-
-		ttm_bo_move_to_lru_tail(&bo->tbo, NULL);
-		if (bo->shadow)
-			ttm_bo_move_to_lru_tail(&bo->shadow->tbo, NULL);
-	}
-	spin_unlock(&glob->lru_lock);
-
 	return r;
 }
 
@@ -2590,6 +2611,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		return r;
 
 	vm->pte_support_ats = false;
+	vm->bulk_moveable = true;
 
 	if (vm_context == AMDGPU_VM_CONTEXT_COMPUTE) {
 		vm->use_cpu_for_update = !!(adev->vm_manager.vm_update_mode &

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h

@@ -29,6 +29,7 @@
 #include <linux/rbtree.h>
 #include <drm/gpu_scheduler.h>
 #include <drm/drm_file.h>
+#include <drm/ttm/ttm_bo_driver.h>
 
 #include "amdgpu_sync.h"
 #include "amdgpu_ring.h"
@@ -247,6 +248,11 @@ struct amdgpu_vm {
 
 	/* Some basic info about the task */
 	struct amdgpu_task_info task_info;
+
+	/* Store positions of group of BOs */
+	struct ttm_lru_bulk_move lru_bulk_move;
+	/* mark whether can do the bulk move */
+	bool			bulk_moveable;
 };
 
 struct amdgpu_vm_manager {
@@ -354,8 +360,11 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev);
 
 void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
-			 struct amdgpu_task_info *task_info);
+			     struct amdgpu_task_info *task_info);
 
 void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);
 
+void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
+				struct amdgpu_vm *vm);
+
 #endif