[PATCH 4/4] drm/amdgpu: Implement VRAM wipe on release

[Kuehling, Felix]

Wipe VRAM memory containing sensitive data when moving or releasing
BOs. Clearing the memory is pipelined to minimize any impact on
subsequent memory allocation latency. Use of a poison value should
help debug future use-after-free bugs.

When moving BOs, the existing ttm_bo_pipelined_move ensures that the
memory won't be reused before being wiped.

When releasing BOs, the BO is fenced with the memory fill operation,
which results in queuing the BO for a delayed delete.

v2: Move amdgpu_amdkfd_unreserve_memory_limit into
amdgpu_bo_release_notify so that KFD can use memory that's still
being cleared in the background

Signed-off-by: Felix Kuehling <Felix.Kuehling at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 39 ++++++++++++++++++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.h |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 17 ++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h    |  2 ++
 4 files changed, 56 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 989b7b55cb2e..f95f7a6509cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -80,9 +80,6 @@ static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo)
 	if (bo->pin_count > 0)
 		amdgpu_bo_subtract_pin_size(bo);
 
-	if (bo->kfd_bo)
-		amdgpu_amdkfd_unreserve_memory_limit(bo);
-
 	amdgpu_bo_kunmap(bo);
 
 	if (bo->gem_base.import_attach)
@@ -1211,6 +1208,42 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 	trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
 }
 
+/**
+ * amdgpu_bo_move_notify - notification about a BO being released
+ * @bo: pointer to a buffer object
+ *
+ * Wipes VRAM buffers whose contents should not be leaked before the
+ * memory is released.
+ */
+void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
+{
+	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *abo;
+	int r;
+
+	if (!amdgpu_bo_is_amdgpu_bo(bo))
+		return;
+
+	abo = ttm_to_amdgpu_bo(bo);
+
+	if (abo->kfd_bo)
+		amdgpu_amdkfd_unreserve_memory_limit(abo);
+
+	if (bo->mem.mem_type != TTM_PL_VRAM || !bo->mem.mm_node ||
+	    !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE))
+		return;
+
+	reservation_object_lock(bo->resv, NULL);
+
+	r = amdgpu_fill_buffer(abo, AMDGPU_POISON, bo->resv, &fence);
+	if (!WARN_ON(r)) {
+		amdgpu_bo_fence(abo, fence, false);
+		dma_fence_put(fence);
+	}
+
+	reservation_object_unlock(bo->resv);
+}
+
 /**
  * amdgpu_bo_fault_reserve_notify - notification about a memory fault
  * @bo: pointer to a buffer object
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index d60593cc436e..e302384fe003 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -265,6 +265,7 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 			   bool evict,
 			   struct ttm_mem_reg *new_mem);
+void amdgpu_bo_release_notify(struct ttm_buffer_object *bo);
 int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
 void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,
 		     bool shared);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index eca2321e7a97..801f912a8578 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -439,6 +439,22 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 	if (r)
 		goto error;
 
+	/* clear the space being freed */
+	if (old_mem->mem_type == TTM_PL_VRAM &&
+	    (ttm_to_amdgpu_bo(bo)->flags &
+	     AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) {
+		struct dma_fence *wipe_fence = NULL;
+
+		r = amdgpu_fill_buffer(ttm_to_amdgpu_bo(bo), AMDGPU_POISON,
+				       NULL, &wipe_fence);
+		if (r) {
+			goto error;
+		} else if (wipe_fence) {
+			dma_fence_put(fence);
+			fence = wipe_fence;
+		}
+	}
+
 	/* Always block for VM page tables before committing the new location */
 	if (bo->type == ttm_bo_type_kernel)
 		r = ttm_bo_move_accel_cleanup(bo, fence, true, new_mem);
@@ -1594,6 +1610,7 @@ static struct ttm_bo_driver amdgpu_bo_driver = {
 	.move = &amdgpu_bo_move,
 	.verify_access = &amdgpu_verify_access,
 	.move_notify = &amdgpu_bo_move_notify,
+	.release_notify = &amdgpu_bo_release_notify,
 	.fault_reserve_notify = &amdgpu_bo_fault_reserve_notify,
 	.io_mem_reserve = &amdgpu_ttm_io_mem_reserve,
 	.io_mem_free = &amdgpu_ttm_io_mem_free,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index caa76c693700..bccb8c49e597 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -38,6 +38,8 @@
 #define AMDGPU_GTT_MAX_TRANSFER_SIZE	512
 #define AMDGPU_GTT_NUM_TRANSFER_WINDOWS	2
 
+#define AMDGPU_POISON	0xd0bed0be
+
 struct amdgpu_mman {
 	struct ttm_bo_device		bdev;
 	bool				mem_global_referenced;
-- 
2.17.1