If the BO has been moved the PT should be updated, otherwise the VAs
might point to invalid PT.

This fixes random GPU hangs when replacing sparse mappings from the
userspace, while OP_MAP/OP_UNMAP works fine because always valid BOs
are correctly handled there.

Cc: sta...@vger.kernel.org
Signed-off-by: Samuel Pitoiset <samuel.pitoi...@gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 143d11afe0e5..eff73c428b12 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1771,18 +1771,30 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device 
*adev,
 
        /* Insert partial mapping before the range */
        if (!list_empty(&before->list)) {
+               struct amdgpu_bo *bo = before->bo_va->base.bo;
+
                amdgpu_vm_it_insert(before, &vm->va);
                if (before->flags & AMDGPU_PTE_PRT)
                        amdgpu_vm_prt_get(adev);
+
+               if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv &&
+                   !before->bo_va->base.moved)
+                       amdgpu_vm_bo_moved(&before->bo_va->base);
        } else {
                kfree(before);
        }
 
        /* Insert partial mapping after the range */
        if (!list_empty(&after->list)) {
+               struct amdgpu_bo *bo = after->bo_va->base.bo;
+
                amdgpu_vm_it_insert(after, &vm->va);
                if (after->flags & AMDGPU_PTE_PRT)
                        amdgpu_vm_prt_get(adev);
+
+               if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv &&
+                   !after->bo_va->base.moved)
+                       amdgpu_vm_bo_moved(&after->bo_va->base);
        } else {
                kfree(after);
        }
-- 
2.41.0

Reply via email to