Re: [PATCH] drm/amdgpu: avoid restore process run into dead loop.

[Felix Kuehling]

Am 2023-03-02 um 13:15 schrieb Gang Ba:

In restore process worker, pinned BO cause update PTE fail, then
the function re-schedule the restore_work. This will generate dead loop.

Signed-off-by: Gang Ba <g...@amd.com>

Reviewed-by: Felix Kuehling <felix.kuehl...@amd.com>

---
  drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 5 ++++-
  1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 4b46b936a804..a38be83e486e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2586,7 +2586,7 @@ int amdgpu_amdkfd_gpuvm_export_ipc_obj(struct 
amdgpu_device *adev, void *vm,
        struct dma_buf *dmabuf;
        int r;

- if (!adev|| !vm || !mem)

+       if (!adev || !vm || !mem)
                return -EINVAL;

mutex_lock(&mem->lock);

@@ -3170,6 +3170,9 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, 
struct dma_fence **ef)
                        if (!attachment->is_mapped)
                                continue;

+ if (attachment->bo_va->base.bo->tbo.pin_count)

+                               continue;
+
                        kfd_mem_dmaunmap_attachment(mem, attachment);
                        ret = update_gpuvm_pte(mem, attachment, &sync_obj);
                        if (ret) {