[PATCH 6.6.y] amdkfd: Fix memory availability double accounting of kfd pinned objects

[Sasha Levin <sashal@kernel.org>]

From: Daniel Phillips <daniel.phillips@amd.com>

[ Upstream commit 16df12d7158fb55f20d6e985abd1996cbabab9f8 ]

Pinned objects that are not kfd objects reduce the total vram available
to kfd, so we subtract the total size of pinned objects from kdf vram
availability. However this double counts objects pinned by kfd itself,
because they are counted both as used and pinned. So track the total
size of objects pinned by kfd and add it back to kfd availability to
remove the double accounting.

Signed-off-by: Daniel Phillips <daniel.phillips@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit b8257bdb26ca5d9a75f4b81f629422f17afa221b)
Cc: stable@vger.kernel.org
[ sashal: Adjusted context for the missing out label and the simpler VRAM calculation without APU branching or RAS accounting. ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h       |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 11 +++++++++++
 2 files changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 8fc55a6671841..1be8c4a676096 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -100,6 +100,7 @@ struct amdgpu_kfd_dev {
 	struct kfd_dev *dev;
 	int64_t vram_used[MAX_XCP];
 	uint64_t vram_used_aligned[MAX_XCP];
+	atomic64_t vram_pinned;
 	bool init_complete;
 	struct work_struct reset_work;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index b2c5f99b2e57a..8237772ca9426 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1432,6 +1432,11 @@ static int amdgpu_amdkfd_gpuvm_pin_bo(struct amdgpu_bo *bo, u32 domain)
 		pr_err("Error in Pinning BO to domain: %d\n", domain);
 
 	amdgpu_bo_sync_wait(bo, AMDGPU_FENCE_OWNER_KFD, false);
+
+	if (!ret && bo->tbo.resource->mem_type == TTM_PL_VRAM)
+		atomic64_add(amdgpu_bo_size(bo),
+			&amdgpu_ttm_adev(bo->tbo.bdev)->kfd.vram_pinned);
+
 	amdgpu_bo_unreserve(bo);
 
 	return ret;
@@ -1454,6 +1459,11 @@ static void amdgpu_amdkfd_gpuvm_unpin_bo(struct amdgpu_bo *bo)
 		return;
 
 	amdgpu_bo_unpin(bo);
+
+	if (bo->tbo.resource->mem_type == TTM_PL_VRAM)
+		atomic64_sub(amdgpu_bo_size(bo),
+			&amdgpu_ttm_adev(bo->tbo.bdev)->kfd.vram_pinned);
+
 	amdgpu_bo_unreserve(bo);
 }
 
@@ -1610,6 +1620,7 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev,
 	vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id)
 		- adev->kfd.vram_used_aligned[xcp_id]
 		- atomic64_read(&adev->vram_pin_size)
+		+ atomic64_read(&adev->kfd.vram_pinned)
 		- reserved_for_pt;
 
 	if (adev->gmc.is_app_apu) {
-- 
2.53.0