[PATCH RFC v2] drm/amdgpu: Set/clear CPU_ACCESS flag on page fault and move to VRAM

[John Brooks]

When a BO is moved to VRAM, clear AMDGPU_BO_FLAG_CPU_ACCESS. This allows it
to potentially later move to invisible VRAM if the CPU does not access it
again.

Setting the CPU_ACCESS flag in amdgpu_bo_fault_reserve_notify() also means
that we can remove the loop to restrict lpfn to the end of visible VRAM,
because amdgpu_ttm_placement_init() will do it for us.

Signed-off-by: John Brooks <john at fastquake.com>
---

Whoops, I forgot to actually remove that loop.
Also, in the changelog: amdgpu_fault_reserve_notify -> amdgpu_bo_fault_reserve_notify

 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 15 +++++----------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    |  8 ++++++++
 2 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index fa8aeca..7164f8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -946,13 +946,16 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct amdgpu_bo *abo;
-	unsigned long offset, size, lpfn;
-	int i, r;
+	unsigned long offset, size;
+	int r;
 
 	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
 		return 0;
 
 	abo = container_of(bo, struct amdgpu_bo, tbo);
+
+	abo->flags |= AMDGPU_BO_FLAG_CPU_ACCESS;
+
 	if (bo->mem.mem_type != TTM_PL_VRAM)
 		return 0;
 
@@ -969,14 +972,6 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	/* hurrah the memory is not visible ! */
 	atomic64_inc(&adev->num_vram_cpu_page_faults);
 	amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM);
-	lpfn =	adev->mc.visible_vram_size >> PAGE_SHIFT;
-	for (i = 0; i < abo->placement.num_placement; i++) {
-		/* Force into visible VRAM */
-		if ((abo->placements[i].flags & TTM_PL_FLAG_VRAM) &&
-		    (!abo->placements[i].lpfn ||
-		     abo->placements[i].lpfn > lpfn))
-			abo->placements[i].lpfn = lpfn;
-	}
 	r = ttm_bo_validate(bo, &abo->placement, false, false);
 	if (unlikely(r == -ENOMEM)) {
 		amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index c9b131b..cc65cdd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -417,6 +417,7 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo,
 				struct ttm_mem_reg *new_mem)
 {
 	struct amdgpu_device *adev;
+	struct amdgpu_bo *abo;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	struct ttm_mem_reg tmp_mem;
 	struct ttm_placement placement;
@@ -424,6 +425,7 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo,
 	int r;
 
 	adev = amdgpu_ttm_adev(bo->bdev);
+	abo = container_of(bo, struct amdgpu_bo, tbo);
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
 	placement.num_placement = 1;
@@ -446,6 +448,12 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo,
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
+
+	/* The page fault handler will re-set this if the CPU accesses the BO
+	 * after it's moved.
+	 */
+	abo->flags &= ~AMDGPU_BO_FLAG_CPU_ACCESS;
+
 out_cleanup:
 	ttm_bo_mem_put(bo, &tmp_mem);
 	return r;
-- 
2.7.4