Merge pull request github#3482 from MathiasVP/getlim-taint-source

C++: Add GetDelim as taint step

Author: jbj

cpp/ql/src/semmle/code/cpp/models/Models.qll

@@ -14,3 +14,4 @@ private import implementations.Strdup
 private import implementations.Strftime
 private import implementations.StdString
 private import implementations.Swap
+private import implementations.GetDelim

cpp/ql/src/semmle/code/cpp/models/implementations/GetDelim.qll

@@ -0,0 +1,40 @@
+import semmle.code.cpp.models.interfaces.Taint
+import semmle.code.cpp.models.interfaces.Alias
+import semmle.code.cpp.models.interfaces.SideEffect
+import semmle.code.cpp.models.interfaces.FlowSource
+
+/**
+ * The standard functions `getdelim`, `getwdelim` and the glibc variant `__getdelim`.
+ */
+class GetDelimFunction extends TaintFunction, AliasFunction, SideEffectFunction, RemoteFlowFunction {
+  GetDelimFunction() { hasGlobalName(["getdelim", "getwdelim", "__getdelim"]) }
+
+  override predicate hasTaintFlow(FunctionInput i, FunctionOutput o) {
+    i.isParameter(3) and o.isParameterDeref(0)
+  }
+
+  override predicate parameterNeverEscapes(int index) { index = [0, 1, 3] }
+
+  override predicate parameterEscapesOnlyViaReturn(int index) { none() }
+
+  override predicate parameterIsAlwaysReturned(int index) { none() }
+
+  override predicate hasOnlySpecificReadSideEffects() { any() }
+
+  override predicate hasOnlySpecificWriteSideEffects() { any() }
+
+  override predicate hasSpecificWriteSideEffect(ParameterIndex i, boolean buffer, boolean mustWrite) {
+    i = [0, 1] and
+    buffer = false and
+    mustWrite = false
+  }
+
+  override predicate hasSpecificReadSideEffect(ParameterIndex i, boolean buffer) {
+    i = 3 and buffer = false
+  }
+
+  override predicate hasRemoteFlowSource(FunctionOutput output, string description) {
+    output.isParameterDeref(0) and
+    description = "String read by " + this.getName()
+  }
+}

cpp/ql/test/library-tests/dataflow/taint-tests/localTaint.expected

@@ -591,3 +591,13 @@
 | taint.cpp:463:6:463:6 | 0 | taint.cpp:471:7:471:7 | y |  |
 | taint.cpp:468:7:468:7 | ref arg x | taint.cpp:470:7:470:7 | x |  |
 | taint.cpp:468:10:468:10 | ref arg y | taint.cpp:471:7:471:7 | y |  |
+| taint.cpp:480:26:480:32 | source1 | taint.cpp:483:28:483:34 | source1 |  |
+| taint.cpp:481:15:481:21 | 0 | taint.cpp:483:12:483:15 | line |  |
+| taint.cpp:481:15:481:21 | 0 | taint.cpp:485:7:485:10 | line |  |
+| taint.cpp:482:9:482:9 | n | taint.cpp:483:19:483:19 | n |  |
+| taint.cpp:483:11:483:15 | ref arg & ... | taint.cpp:483:12:483:15 | line [inner post update] |  |
+| taint.cpp:483:11:483:15 | ref arg & ... | taint.cpp:485:7:485:10 | line |  |
+| taint.cpp:483:12:483:15 | line | taint.cpp:483:11:483:15 | & ... |  |
+| taint.cpp:483:18:483:19 | ref arg & ... | taint.cpp:483:19:483:19 | n [inner post update] |  |
+| taint.cpp:483:19:483:19 | n | taint.cpp:483:18:483:19 | & ... |  |
+| taint.cpp:483:28:483:34 | source1 | taint.cpp:483:11:483:15 | ref arg & ... | TAINT |

cpp/ql/test/library-tests/dataflow/taint-tests/taint.cpp

@@ -470,3 +470,17 @@ void test_swop() {
 	sink(x); // clean [FALSE POSITIVE]
 	sink(y); // tainted
 }
+
+// --- getdelim ---
+
+struct FILE;
+
+int getdelim(char ** lineptr, size_t * n, int delimiter, FILE *stream);
+
+void test_getdelim(FILE* source1) {
+	char* line = nullptr;
+	size_t n;
+	getdelim(&line, &n, '\n', source1);
+
+	sink(line);
+}

cpp/ql/test/library-tests/dataflow/taint-tests/taint.expected

@@ -67,3 +67,4 @@
 | taint.cpp:465:7:465:7 | x | taint.cpp:462:6:462:11 | call to source |
 | taint.cpp:470:7:470:7 | x | taint.cpp:462:6:462:11 | call to source |
 | taint.cpp:471:7:471:7 | y | taint.cpp:462:6:462:11 | call to source |
+| taint.cpp:485:7:485:10 | line | taint.cpp:480:26:480:32 | source1 |

cpp/ql/test/library-tests/dataflow/taint-tests/test_ir.expected

@@ -28,3 +28,4 @@
 | taint.cpp:430:9:430:14 | member | taint.cpp:428:13:428:18 | call to source |
 | taint.cpp:465:7:465:7 | x | taint.cpp:462:6:462:11 | call to source |
 | taint.cpp:470:7:470:7 | x | taint.cpp:462:6:462:11 | call to source |
+| taint.cpp:485:7:485:10 | line | taint.cpp:480:26:480:32 | source1 |