Am 30.10.19 um 19:41 schrieb Alex Deucher:
To better clarify what is happening in this function.
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Reviewed-by: Christian König <christian.koenig@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index c8ce42200059..3c0bd6472a46 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1419,6 +1419,9 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
uint64_t incr, entry_end, pe_start;
struct amdgpu_bo *pt;
+ /* make sure that the page tables covering the address range are
+ * actually allocated
+ */
r = amdgpu_vm_alloc_pts(params->adev, params->vm, &cursor,
params->direct);
if (r)
@@ -1492,7 +1495,12 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
} while (frag_start < entry_end);
if (amdgpu_vm_pt_descendant(adev, &cursor)) {
- /* Free all child entries */
+ /* Free all child entries.
+ * Update the tables with the flags and addresses and free up subsequent
+ * tables in the case of huge pages or freed up areas.
+ * This is the maximum you can free, because all other page tables are not
+ * completely covered by the range and so potentially still in use.
+ */
while (cursor.pfn < frag_start) {
amdgpu_vm_free_pts(adev, params->vm, &cursor);
amdgpu_vm_pt_next(adev, &cursor);
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
