Index: compiler-rt/trunk/lib/fuzzer/dataflow/DataFlow.cpp
===================================================================
--- compiler-rt/trunk/lib/fuzzer/dataflow/DataFlow.cpp
+++ compiler-rt/trunk/lib/fuzzer/dataflow/DataFlow.cpp
@@ -63,6 +63,9 @@
 } // extern "C"
 
 static size_t InputLen;
+static size_t InputLabelBeg;
+static size_t InputLabelEnd;
+static size_t InputSizeLabel;
 static size_t NumFuncs;
 static const uintptr_t *FuncsBeg;
 static __thread size_t CurrentFunc;
@@ -95,8 +98,10 @@
     return;
   LabelSeen[L] = true;
   assert(L);
-  if (L <= InputLen + 1) {
-    Bytes[L - 1] = '1';
+  if (L < InputSizeLabel) {
+    Bytes[L + InputLabelBeg - 1] = '1';
+  } else if (L == InputSizeLabel) {
+    Bytes[InputLen] = '1';
   } else {
     auto *DLI = dfsan_get_label_info(L);
     SetBytesForLabel(DLI->l1, Bytes);
@@ -124,9 +129,9 @@
   if (argc == 1)
     return PrintFunctions();
   assert(argc == 4 || argc == 5);
-  size_t Beg = atoi(argv[1]);
-  size_t End = atoi(argv[2]);
-  assert(Beg < End);
+  InputLabelBeg = atoi(argv[1]);
+  InputLabelEnd = atoi(argv[2]);
+  assert(InputLabelBeg < InputLabelEnd);
 
   const char *Input = argv[3];
   fprintf(stderr, "INFO: reading '%s'\n", Input);
@@ -143,14 +148,16 @@
 
   fprintf(stderr, "INFO: running '%s'\n", Input);
   for (size_t I = 1; I <= InputLen; I++) {
-    dfsan_label L = dfsan_create_label("", nullptr);
-    assert(L == I);
     size_t Idx = I - 1;
-    if (Idx >= Beg && Idx < End)
+    if (Idx >= InputLabelBeg && Idx < InputLabelEnd) {
+      dfsan_label L = dfsan_create_label("", nullptr);
+      assert(L == I - InputLabelBeg);
       dfsan_set_label(L, Buf + Idx, 1);
+    }
   }
   dfsan_label SizeL = dfsan_create_label("", nullptr);
-  assert(SizeL == InputLen + 1);
+  InputSizeLabel = SizeL;
+  assert(InputSizeLabel == InputLabelEnd - InputLabelBeg + 1);
   dfsan_set_label(SizeL, &InputLen, sizeof(InputLen));
 
   LLVMFuzzerTestOneInput(Buf, InputLen);
Index: compiler-rt/trunk/lib/fuzzer/scripts/collect_data_flow.py
===================================================================
--- compiler-rt/trunk/lib/fuzzer/scripts/collect_data_flow.py
+++ compiler-rt/trunk/lib/fuzzer/scripts/collect_data_flow.py
@@ -65,8 +65,8 @@
     tmpfile = os.path.join(tmpdir, str(r[0]) + "-" + str(r[1]))
     ret = subprocess.call([exe, str(r[0]), str(r[1]), inp, tmpfile])
     if ret and r[1] - r[0] >= 2:
-      q.append([r[0], (r[1] + r[0]) / 2])
-      q.append([(r[1] + r[0]) / 2, r[1]])
+      q.append([r[0], (r[1] + r[0]) // 2])
+      q.append([(r[1] + r[0]) // 2, r[1]])
     else:
       outputs.append(tmpfile)
       print("******* Success: ", r)
Index: compiler-rt/trunk/test/fuzzer/dataflow.test
===================================================================
--- compiler-rt/trunk/test/fuzzer/dataflow.test
+++ compiler-rt/trunk/test/fuzzer/dataflow.test
@@ -82,3 +82,14 @@
 USE_DATA_FLOW_TRACE-DAG: a8eefe2fd5d6b32028f355fafa3e739a6bf5edc => |000001|
 USE_DATA_FLOW_TRACE-DGA: d28cb407e8e1a702c72d25473f0553d3ec172262 => |0000011|
 USE_DATA_FLOW_TRACE: INFO: DataFlowTrace: 6 trace files, 3 functions, 2 traces with focus function
+
+# Test that we can run collect_data_flow on a long input (>2**16 bytes)
+RUN: rm -rf %t/OUT
+RUN: printf "%0.sA" {1..150001} > %t/IN/very_long_input
+RUN: %libfuzzer_src/scripts/collect_data_flow.py %t-ThreeFunctionsTestDF %t/IN/very_long_input %t/OUT | FileCheck %s --check-prefix=COLLECT_TRACE_FOR_LONG_INPUT
+RUN: rm %t/IN/very_long_input
+COLLECT_TRACE_FOR_LONG_INPUT: ******* Trying:{{[ ]+}}[0, 150001]
+COLLECT_TRACE_FOR_LONG_INPUT: ******* Trying:{{[ ]+}}[75000, 150001]
+COLLECT_TRACE_FOR_LONG_INPUT: ******* Trying:{{[ ]+}}[112500, 150001]
+COLLECT_TRACE_FOR_LONG_INPUT: ******* Success:{{[ ]+}}[{{[0123456789]+}}, 150001]
+COLLECT_TRACE_FOR_LONG_INPUT: ******* Success:{{[ ]+}}[0, {{[0123456789]+}}]