Merge branch 'main' into post-release-prep/codeql-cli-2.14.2

Author: henrymercer

config/identical-files.json

@@ -22,7 +22,6 @@
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl5.qll",
     "go/ql/lib/semmle/go/dataflow/internal/DataFlowImpl1.qll",
     "go/ql/lib/semmle/go/dataflow/internal/DataFlowImpl2.qll",
-    "go/ql/lib/semmle/go/dataflow/internal/DataFlowImplForStringsNewReplacer.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl1.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl2.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl3.qll",
@@ -572,4 +571,4 @@
     "python/ql/lib/semmle/python/security/internal/EncryptionKeySizes.qll",
     "java/ql/lib/semmle/code/java/security/internal/EncryptionKeySizes.qll"
   ]
-}
+}

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowPrivate.qll

@@ -1078,7 +1078,7 @@ private IRVariable getIRVariableForParameterNode(ParameterNode p) {
 
 /** Holds if `v` is the source variable corresponding to the parameter represented by `p`. */
 pragma[nomagic]
-private predicate parameterNodeHasSourceVariable(ParameterNode p, Ssa::SourceIRVariable v) {
+private predicate parameterNodeHasSourceVariable(ParameterNode p, Ssa::SourceVariable v) {
   v.getIRVariable() = getIRVariableForParameterNode(p) and
   exists(Position pos | p.isParameterOf(_, pos) |
     pos instanceof DirectPosition and

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowUtil.qll

@@ -781,26 +781,12 @@ class IndirectArgumentOutNode extends Node, TIndirectArgumentOutNode, PartialDef
   override Expr getDefinedExpr() { result = operand.getDef().getUnconvertedResultExpression() }
 }
 
-pragma[nomagic]
-predicate indirectReturnOutNodeOperand0(CallInstruction call, Operand operand, int indirectionIndex) {
-  Ssa::hasRawIndirectInstruction(call, indirectionIndex) and
-  operandForFullyConvertedCall(operand, call)
-}
-
-pragma[nomagic]
-predicate indirectReturnOutNodeInstruction0(
-  CallInstruction call, Instruction instr, int indirectionIndex
-) {
-  Ssa::hasRawIndirectInstruction(call, indirectionIndex) and
-  instructionForFullyConvertedCall(instr, call)
-}
-
 /**
  * Holds if `node` is an indirect operand with columns `(operand, indirectionIndex)`, and
  * `operand` represents a use of the fully converted value of `call`.
  */
 private predicate hasOperand(Node node, CallInstruction call, int indirectionIndex, Operand operand) {
-  indirectReturnOutNodeOperand0(call, operand, indirectionIndex) and
+  operandForFullyConvertedCall(operand, call) and
   hasOperandAndIndex(node, operand, indirectionIndex)
 }
 
@@ -813,7 +799,7 @@ private predicate hasOperand(Node node, CallInstruction call, int indirectionInd
 private predicate hasInstruction(
   Node node, CallInstruction call, int indirectionIndex, Instruction instr
 ) {
-  indirectReturnOutNodeInstruction0(call, instr, indirectionIndex) and
+  instructionForFullyConvertedCall(instr, call) and
   hasInstructionAndIndex(node, instr, indirectionIndex)
 }
 

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/SsaInternals.qll

@@ -10,99 +10,56 @@ private import ssa0.SsaInternals as SsaInternals0
 import SsaInternalsCommon
 
 private module SourceVariables {
-  int getMaxIndirectionForIRVariable(IRVariable var) {
-    exists(Type type, boolean isGLValue |
-      var.getLanguageType().hasType(type, isGLValue) and
-      if isGLValue = true
-      then result = 1 + getMaxIndirectionsForType(type)
-      else result = getMaxIndirectionsForType(type)
-    )
-  }
-
   cached
   private newtype TSourceVariable =
-    TSourceIRVariable(BaseIRVariable baseVar, int ind) {
-      ind = [0 .. getMaxIndirectionForIRVariable(baseVar.getIRVariable())]
-    } or
-    TCallVariable(AllocationInstruction call, int ind) {
-      ind = [0 .. countIndirectionsForCppType(getResultLanguageType(call))]
+    TMkSourceVariable(SsaInternals0::SourceVariable base, int ind) {
+      ind = [0 .. countIndirectionsForCppType(base.getLanguageType()) + 1]
     }
 
-  abstract class SourceVariable extends TSourceVariable {
+  class SourceVariable extends TSourceVariable {
+    SsaInternals0::SourceVariable base;
     int ind;
 
-    bindingset[ind]
-    SourceVariable() { any() }
+    SourceVariable() { this = TMkSourceVariable(base, ind) }
+
+    /** Gets the IR variable associated with this `SourceVariable`, if any. */
+    IRVariable getIRVariable() { result = base.(BaseIRVariable).getIRVariable() }
+
+    /**
+     * Gets the base source variable (i.e., the variable without any
+     * indirections) of this source variable.
+     */
+    SsaInternals0::SourceVariable getBaseVariable() { result = base }
 
     /** Gets a textual representation of this element. */
-    abstract string toString();
+    string toString() {
+      ind = 0 and
+      result = this.getBaseVariable().toString()
+      or
+      ind > 0 and
+      result = this.getBaseVariable().toString() + " indirection"
+    }
 
     /**
      * Gets the number of loads performed on the base source variable
      * to reach the value of this source variable.
      */
     int getIndirection() { result = ind }
 
-    /**
-     * Gets the base source variable (i.e., the variable without any
-     * indirections) of this source variable.
-     */
-    abstract BaseSourceVariable getBaseVariable();
-
     /** Holds if this variable is a glvalue. */
-    predicate isGLValue() { none() }
+    predicate isGLValue() { ind = 0 }
 
     /**
      * Gets the type of this source variable. If `isGLValue()` holds, then
      * the type of this source variable should be thought of as "pointer
      * to `getType()`".
      */
-    abstract DataFlowType getType();
-  }
-
-  class SourceIRVariable extends SourceVariable, TSourceIRVariable {
-    BaseIRVariable var;
-
-    SourceIRVariable() { this = TSourceIRVariable(var, ind) }
-
-    IRVariable getIRVariable() { result = var.getIRVariable() }
-
-    override BaseIRVariable getBaseVariable() { result.getIRVariable() = this.getIRVariable() }
-
-    override string toString() {
-      ind = 0 and
-      result = this.getIRVariable().toString()
-      or
-      ind > 0 and
-      result = this.getIRVariable().toString() + " indirection"
-    }
-
-    override predicate isGLValue() { ind = 0 }
-
-    override DataFlowType getType() {
-      if ind = 0 then result = var.getType() else result = getTypeImpl(var.getType(), ind - 1)
+    DataFlowType getType() {
+      if this.isGLValue()
+      then result = base.getType()
+      else result = getTypeImpl(base.getType(), ind - 1)
     }
   }
-
-  class CallVariable extends SourceVariable, TCallVariable {
-    AllocationInstruction call;
-
-    CallVariable() { this = TCallVariable(call, ind) }
-
-    AllocationInstruction getCall() { result = call }
-
-    override BaseCallVariable getBaseVariable() { result.getCallInstruction() = call }
-
-    override string toString() {
-      ind = 0 and
-      result = "Call"
-      or
-      ind > 0 and
-      result = "Call indirection"
-    }
-
-    override DataFlowType getType() { result = getTypeImpl(call.getResultType(), ind) }
-  }
 }
 
 import SourceVariables
@@ -137,8 +94,9 @@ predicate hasRawIndirectInstruction(Instruction instr, int indirectionIndex) {
 
 cached
 private newtype TDefOrUseImpl =
-  TDefImpl(Operand address, int indirectionIndex) {
-    exists(Instruction base | isDef(_, _, address, base, _, indirectionIndex) |
+  TDefImpl(BaseSourceVariableInstruction base, Operand address, int indirectionIndex) {
+    isDef(_, _, address, base, _, indirectionIndex) and
+    (
       // We only include the definition if the SSA pruning stage
       // concluded that the definition is live after the write.
       any(SsaInternals0::Def def).getAddressOperand() = address
@@ -148,8 +106,8 @@ private newtype TDefOrUseImpl =
       base.(VariableAddressInstruction).getAstVariable() instanceof GlobalLikeVariable
     )
   } or
-  TUseImpl(Operand operand, int indirectionIndex) {
-    isUse(_, operand, _, _, indirectionIndex) and
+  TUseImpl(BaseSourceVariableInstruction base, Operand operand, int indirectionIndex) {
+    isUse(_, operand, base, _, indirectionIndex) and
     not isDef(_, _, operand, _, _, _)
   } or
   TGlobalUse(GlobalLikeVariable v, IRFunction f, int indirectionIndex) {
@@ -236,7 +194,7 @@ abstract private class DefOrUseImpl extends TDefOrUseImpl {
 
   /**
    * Gets the instruction that computes the base of this definition or use.
-   * This is always a `VariableAddressInstruction` or an `AllocationInstruction`.
+   * This is always a `VariableAddressInstruction` or an `CallInstruction`.
    */
   abstract BaseSourceVariableInstruction getBase();
 
@@ -308,15 +266,17 @@ abstract class DefImpl extends DefOrUseImpl {
 }
 
 private class DirectDef extends DefImpl, TDefImpl {
-  DirectDef() { this = TDefImpl(address, ind) }
+  BaseSourceVariableInstruction base;
+
+  DirectDef() { this = TDefImpl(base, address, ind) }
 
-  override BaseSourceVariableInstruction getBase() { isDef(_, _, address, result, _, _) }
+  override BaseSourceVariableInstruction getBase() { result = base }
 
-  override int getIndirection() { isDef(_, _, address, _, result, ind) }
+  override int getIndirection() { isDef(_, _, address, base, result, ind) }
 
-  override Node0Impl getValue() { isDef(_, result, address, _, _, _) }
+  override Node0Impl getValue() { isDef(_, result, address, base, _, _) }
 
-  override predicate isCertain() { isDef(true, _, address, _, _, ind) }
+  override predicate isCertain() { isDef(true, _, address, base, _, ind) }
 }
 
 private class IteratorDef extends DefImpl, TIteratorDef {
@@ -359,57 +319,52 @@ abstract class UseImpl extends DefOrUseImpl {
 
 abstract private class OperandBasedUse extends UseImpl {
   Operand operand;
+  BaseSourceVariableInstruction base;
 
   bindingset[ind]
   OperandBasedUse() { any() }
 
   final override predicate hasIndexInBlock(IRBlock block, int index) {
     // See the comment in `ssa0`'s `OperandBasedUse` for an explanation of this
     // predicate's implementation.
-    exists(BaseSourceVariableInstruction base | base = this.getBase() |
-      if base.getAst() = any(Cpp::PostfixCrementOperation c).getOperand()
-      then
-        exists(Operand op, int indirectionIndex, int indirection |
-          indirectionIndex = this.getIndirectionIndex() and
-          indirection = this.getIndirection() and
-          op =
-            min(Operand cand, int i |
-              isUse(_, cand, base, indirection, indirectionIndex) and
-              block.getInstruction(i) = cand.getUse()
-            |
-              cand order by i
-            ) and
-          block.getInstruction(index) = op.getUse()
-        )
-      else operand.getUse() = block.getInstruction(index)
-    )
+    if base.getAst() = any(Cpp::PostfixCrementOperation c).getOperand()
+    then
+      exists(Operand op, int indirectionIndex, int indirection |
+        indirectionIndex = this.getIndirectionIndex() and
+        indirection = this.getIndirection() and
+        op =
+          min(Operand cand, int i |
+            isUse(_, cand, base, indirection, indirectionIndex) and
+            block.getInstruction(i) = cand.getUse()
+          |
+            cand order by i
+          ) and
+        block.getInstruction(index) = op.getUse()
+      )
+    else operand.getUse() = block.getInstruction(index)
   }
 
+  final override BaseSourceVariableInstruction getBase() { result = base }
+
   final Operand getOperand() { result = operand }
 
   final override Cpp::Location getLocation() { result = operand.getLocation() }
 }
 
 private class DirectUse extends OperandBasedUse, TUseImpl {
-  DirectUse() { this = TUseImpl(operand, ind) }
-
-  override int getIndirection() { isUse(_, operand, _, result, ind) }
+  DirectUse() { this = TUseImpl(base, operand, ind) }
 
-  override BaseSourceVariableInstruction getBase() { isUse(_, operand, result, _, ind) }
+  override int getIndirection() { isUse(_, operand, base, result, ind) }
 
-  override predicate isCertain() { isUse(true, operand, _, _, ind) }
+  override predicate isCertain() { isUse(true, operand, base, _, ind) }
 
   override Node getNode() { nodeHasOperand(result, operand, ind) }
 }
 
 private class IteratorUse extends OperandBasedUse, TIteratorUse {
-  BaseSourceVariableInstruction container;
+  IteratorUse() { this = TIteratorUse(operand, base, ind) }
 
-  IteratorUse() { this = TIteratorUse(operand, container, ind) }
-
-  override int getIndirection() { isIteratorUse(container, operand, result, ind) }
-
-  override BaseSourceVariableInstruction getBase() { result = container }
+  override int getIndirection() { isIteratorUse(base, operand, result, ind) }
 
   override predicate isCertain() { none() }
 

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/SsaInternalsCommon.qll

@@ -146,14 +146,6 @@ int countIndirectionsForCppType(LanguageType langType) {
   )
 }
 
-/**
- * A `CallInstruction` that calls an allocation function such
- * as `malloc` or `operator new`.
- */
-class AllocationInstruction extends CallInstruction {
-  AllocationInstruction() { this.getStaticCallTarget() instanceof Cpp::AllocationFunction }
-}
-
 private predicate isIndirectionType(Type t) { t instanceof Indirection }
 
 private predicate hasUnspecifiedBaseType(Indirection t, Type base) {
@@ -368,17 +360,22 @@ newtype TBaseSourceVariable =
   // Each IR variable gets its own source variable
   TBaseIRVariable(IRVariable var) or
   // Each allocation gets its own source variable
-  TBaseCallVariable(AllocationInstruction call)
+  TBaseCallVariable(CallInstruction call) { not call.getResultIRType() instanceof IRVoidType }
 
-abstract class BaseSourceVariable extends TBaseSourceVariable {
+abstract private class AbstractBaseSourceVariable extends TBaseSourceVariable {
   /** Gets a textual representation of this element. */
   abstract string toString();
 
   /** Gets the type of this base source variable. */
-  abstract DataFlowType getType();
+  final DataFlowType getType() { this.getLanguageType().hasUnspecifiedType(result, _) }
+
+  /** Gets the `CppType` of this base source variable. */
+  abstract CppType getLanguageType();
 }
 
-class BaseIRVariable extends BaseSourceVariable, TBaseIRVariable {
+final class BaseSourceVariable = AbstractBaseSourceVariable;
+
+class BaseIRVariable extends AbstractBaseSourceVariable, TBaseIRVariable {
   IRVariable var;
 
   IRVariable getIRVariable() { result = var }
@@ -387,19 +384,19 @@ class BaseIRVariable extends BaseSourceVariable, TBaseIRVariable {
 
   override string toString() { result = var.toString() }
 
-  override DataFlowType getType() { result = var.getType() }
+  override CppType getLanguageType() { result = var.getLanguageType() }
 }
 
-class BaseCallVariable extends BaseSourceVariable, TBaseCallVariable {
-  AllocationInstruction call;
+class BaseCallVariable extends AbstractBaseSourceVariable, TBaseCallVariable {
+  CallInstruction call;
 
   BaseCallVariable() { this = TBaseCallVariable(call) }
 
-  AllocationInstruction getCallInstruction() { result = call }
+  CallInstruction getCallInstruction() { result = call }
 
   override string toString() { result = call.toString() }
 
-  override DataFlowType getType() { result = call.getResultType() }
+  override CppType getLanguageType() { result = getResultLanguageType(call) }
 }
 
 /**
@@ -499,8 +496,7 @@ private class BaseIRVariableInstruction extends BaseSourceVariableInstruction,
   override BaseIRVariable getBaseSourceVariable() { result.getIRVariable() = this.getIRVariable() }
 }
 
-private class BaseAllocationInstruction extends BaseSourceVariableInstruction, AllocationInstruction
-{
+private class BaseCallInstruction extends BaseSourceVariableInstruction, CallInstruction {
   override BaseCallVariable getBaseSourceVariable() { result.getCallInstruction() = this }
 }