From 00f06b246a3056bbaa901a90a5a93c9f81ab8e36 Mon Sep 17 00:00:00 2001
From: John Brooks <john@fastquake.com>
Date: Tue, 27 Jun 2017 22:33:18 -0400
Subject: drm/amdgpu: Throttle visible VRAM moves separately
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The BO move throttling code is designed to allow VRAM to fill quickly if it
is relatively empty. However, this does not take into account situations
where the visible VRAM is smaller than total VRAM, and total VRAM may not
be close to full but the visible VRAM segment is under pressure. In such
situations, visible VRAM would experience unrestricted swapping and
performance would drop.
Add a separate counter specifically for moves involving visible VRAM, and
check it before moving BOs there.
v2: Only perform calculations for separate counter if visible VRAM is
smaller than total VRAM. (Michel Dänzer)
v3: [Michel Dänzer]
* Use BO's location rather than the AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED
flag to determine whether to account a move for visible VRAM in most
cases.
* Use a single
if (adev->mc.visible_vram_size < adev->mc.real_vram_size) {
block in amdgpu_cs_get_threshold_for_moves.
Fixes: 95844d20ae02 (drm/amdgpu: throttle buffer migrations at CS using a fixed MBps limit (v2))
Signed-off-by: John Brooks <john@fastquake.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
(limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_object.c')
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index a85e75327456..e429829ae93d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -322,7 +322,7 @@ 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;
+ u64 initial_bytes_moved, bytes_moved;
size_t acc_size;
int r;
@@ -398,8 +398,14 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, type,
&bo->placement, page_align, !kernel, NULL,
acc_size, sg, resv, &amdgpu_ttm_bo_destroy);
- amdgpu_cs_report_moved_bytes(adev,
- atomic64_read(&adev->num_bytes_moved) - initial_bytes_moved);
+ bytes_moved = atomic64_read(&adev->num_bytes_moved) -
+ initial_bytes_moved;
+ if (adev->mc.visible_vram_size < adev->mc.real_vram_size &&
+ bo->tbo.mem.mem_type == TTM_PL_VRAM &&
+ bo->tbo.mem.start < adev->mc.visible_vram_size >> PAGE_SHIFT)
+ amdgpu_cs_report_moved_bytes(adev, bytes_moved, bytes_moved);
+ else
+ amdgpu_cs_report_moved_bytes(adev, bytes_moved, 0);
if (unlikely(r != 0))
return r;
--
cgit