Like ttm_bo_validate(), ttm_bo_init() might need to move BO and
the number of bytes moved by TTM should be reported. This can help
the throttle buffer migration mechanism to make a better decision.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 3 +--
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 ++++++
3 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 402a8954c6d8..5227e4d1d5db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1720,6 +1720,7 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data);
int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type,
u32 ip_instance, u32 ring,
struct amdgpu_ring **out_ring);
+void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes);
void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain);
bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 6e948e4986ec..dade2fa9593a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -351,8 +351,7 @@ static u64 amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev)
* submission. This can result in a debt that can stop buffer migrations
* temporarily.
*/
-static void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev,
- u64 num_bytes)
+void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes)
{
spin_lock(&adev->mm_stats.lock);
adev->mm_stats.accum_us -= bytes_to_us(adev, num_bytes);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 531e16ce256e..28c4615a6128 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -323,6 +323,7 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
struct amdgpu_bo *bo;
enum ttm_bo_type type;
unsigned long page_align;
+ u64 initial_bytes_moved;
size_t acc_size;
int r;
@@ -399,10 +400,15 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
locked = ww_mutex_trylock(&bo->tbo.ttm_resv.lock);
WARN_ON(!locked);
}
+
+ initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
r = ttm_bo_init(&adev->mman.bdev, &bo->tbo, size, type,
&bo->placement, page_align, !kernel, NULL,
acc_size, sg, resv ? resv : &bo->tbo.ttm_resv,
&amdgpu_ttm_bo_destroy);
+ amdgpu_cs_report_moved_bytes(adev,
+ initial_bytes_moved - atomic64_read(&adev->num_bytes_moved));
+
if (unlikely(r != 0)) {
ww_mutex_unlock(&bo->tbo.resv->lock);
return r;
--
2.11.1
