commit d1cfdc9f8d34d5c6f318466bf154bfac4f1039ee
author Michael Butler <butlermichael@google.com> Wed May 27 23:06:31 2020 -0700
committer Slava Shklyaev <slavash@google.com> Fri Jun 12 12:44:20 2020 +0100
tree f6f7a4507e56d5340690939819dd3432840b2e3b
parent 10bf3a28fb8ea69ec614bdc41d0d81077f419dd3

Verify non-optional tensors have values in CpuExecutor

This change adds additional validation for non-optional tensors for the
following operations:
* EMBEDDING_LOOKUP
* HASHTABLE_LOOKUP
* LSH_PROJECTION
* BIDIRECTIONAL_SEQUENCE_LSTM
* LSTM
* RANDOM_MULTINOMIAL
* RNN
* SVDF
* SPLIT

Some operations such as SVDF unpack the scalar values without checking
if the value is present, leading to a failed CHECK. This CL adds
protections to use default values in these cases, and relies on a
corresponding Prepare method to cause these cases to fail validation.

Bug: 157516274
Test: mma
Test: CtsNNAPITestCases
Test: NeuralNetworksTest_static
Test: libneuralnetworks_fuzzer
Change-Id: I6bb804ec40205c9741b04231022894c714ad28ec
Merged-In: I6bb804ec40205c9741b04231022894c714ad28ec
(cherry picked from commit ac18d190b96c493961cf1d57e327806afbe319bb)

common/operations/LSTM.cpp

diff --git a/common/operations/LSTM.cpp b/common/operations/LSTM.cpp
index 6020353..ba5d46a 100644
--- a/common/operations/LSTM.cpp
+++ b/common/operations/LSTM.cpp
@@ -83,16 +83,20 @@
     output_state_in_ = GetInput(operation, operands, kOutputStateInTensor);
     cell_state_in_ = GetInput(operation, operands, kCellStateInTensor);
 
-    params_.activation = static_cast<TfLiteFusedActivation>(
-            getScalarData<int32_t>(*GetInput(operation, operands, kActivationParam)));
+    const auto& activationOperand = *GetInput(operation, operands, kActivationParam);
+    params_.activation = static_cast<TfLiteFusedActivation>(getScalarDataWithDefault<int32_t>(
+            activationOperand, TfLiteFusedActivation::kTfLiteActNone));
+
+    const auto& cellClipOperand = *GetInput(operation, operands, kCellClipParam);
+    const auto& projClipOperand = *GetInput(operation, operands, kProjClipParam);
     if (input_->type == OperandType::TENSOR_FLOAT32) {
-        params_.cell_clip = getScalarData<float>(*GetInput(operation, operands, kCellClipParam));
-        params_.proj_clip = getScalarData<float>(*GetInput(operation, operands, kProjClipParam));
+        params_.cell_clip = getScalarDataWithDefault<float>(cellClipOperand, 0.0f);
+        params_.proj_clip = getScalarDataWithDefault<float>(projClipOperand, 0.0f);
     } else {
-        params_.cell_clip = static_cast<float>(
-                getScalarData<_Float16>(*GetInput(operation, operands, kCellClipParam)));
-        params_.proj_clip = static_cast<float>(
-                getScalarData<_Float16>(*GetInput(operation, operands, kProjClipParam)));
+        params_.cell_clip =
+                static_cast<float>(getScalarDataWithDefault<_Float16>(cellClipOperand, 0.0f));
+        params_.proj_clip =
+                static_cast<float>(getScalarDataWithDefault<_Float16>(projClipOperand, 0.0f));
     }
 
     // We check the version of LSTM by checking the number of the inputs to the
@@ -302,8 +306,42 @@
     // Check we have all the inputs and outputs we need.
     NN_CHECK(NumInputsWithValues(operation, operands) >= 15 &&
              NumInputsWithValues(operation, operands) <= 27);
+    constexpr int requiredInputs[] = {
+            kInputTensor,
+            kInputToForgetWeightsTensor,
+            kInputToCellWeightsTensor,
+            kInputToOutputWeightsTensor,
+            kRecurrentToForgetWeightsTensor,
+            kRecurrentToCellWeightsTensor,
+            kRecurrentToOutputWeightsTensor,
+            kForgetGateBiasTensor,
+            kCellGateBiasTensor,
+            kOutputGateBiasTensor,
+            kOutputStateInTensor,
+            kCellStateInTensor,
+            kActivationParam,
+            kCellClipParam,
+            kProjClipParam,
+    };
+    for (const int requiredInput : requiredInputs) {
+        NN_RET_CHECK(!IsNullInput(GetInput(operation, operands, requiredInput)))
+                << "required input " << requiredInput << " is omitted";
+    }
     NN_CHECK_EQ(NumOutputs(operation), 4);
 
+    // Check that the scalar operands' buffers are large enough.
+    const auto& activationOperand = *GetInput(operation, operands, kActivationParam);
+    NN_RET_CHECK(activationOperand.length >= sizeof(int32_t));
+    const auto& cellClipOperand = *GetInput(operation, operands, kCellClipParam);
+    const auto& projClipOperand = *GetInput(operation, operands, kProjClipParam);
+    if (input_->type == OperandType::TENSOR_FLOAT32) {
+        NN_RET_CHECK(cellClipOperand.length >= sizeof(float));
+        NN_RET_CHECK(projClipOperand.length >= sizeof(float));
+    } else {
+        NN_RET_CHECK(cellClipOperand.length >= sizeof(_Float16));
+        NN_RET_CHECK(projClipOperand.length >= sizeof(_Float16));
+    }
+
     // Inferring batch size, number of outputs and number of cells from the
     // input tensors.
     NN_CHECK(NumDimensions(input_) > 1);