Merge branch 'main' of https://github.com/microsoft/codeql

.github/workflows/go-tests-other-os.yml

@@ -7,15 +7,17 @@ on:
       - .github/workflows/go-tests-other-os.yml
       - .github/actions/**
       - codeql-workspace.yml
+env:
+  GO_VERSION: '~1.21.0'
 jobs:
   test-mac:
     name: Test MacOS
     runs-on: macos-latest
     steps:
-      - name: Set up Go 1.20
+      - name: Set up Go ${{ env.GO_VERSION }}
         uses: actions/setup-go@v4
         with:
-          go-version: '1.20'
+          go-version: ${{ env.GO_VERSION }}
         id: go
 
       - name: Check out code
@@ -47,10 +49,10 @@ jobs:
     name: Test Windows
     runs-on: windows-latest-xl
     steps:
-      - name: Set up Go 1.20
+      - name: Set up Go ${{ env.GO_VERSION }}
         uses: actions/setup-go@v4
         with:
-          go-version: '1.20'
+          go-version: ${{ env.GO_VERSION }}
         id: go
 
       - name: Check out code

.github/workflows/go-tests.yml

@@ -15,15 +15,17 @@ on:
       - .github/workflows/go-tests.yml
       - .github/actions/**
       - codeql-workspace.yml
+env:
+  GO_VERSION: '~1.21.0'
 jobs:
   test-linux:
     name: Test Linux (Ubuntu)
     runs-on: ubuntu-latest-xl
     steps:
-      - name: Set up Go 1.20
+      - name: Set up Go ${{ env.GO_VERSION }}
         uses: actions/setup-go@v4
         with:
-          go-version: '1.20'
+          go-version: ${{ env.GO_VERSION }}
         id: go
 
       - name: Check out code

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",
@@ -33,16 +32,6 @@
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplForPathname.qll",
     "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImpl1.qll"
   ],
-  "TaintTracking Java/C++/C#/Go/Python/Ruby/Swift": [
-    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking1/TaintTracking.qll",
-    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/tainttracking1/TaintTracking.qll",
-    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking1/TaintTracking.qll",
-    "go/ql/lib/semmle/go/dataflow/internal/tainttracking1/TaintTracking.qll",
-    "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking1/TaintTracking.qll",
-    "python/ql/lib/semmle/python/dataflow/new/internal/tainttracking1/TaintTracking.qll",
-    "ruby/ql/lib/codeql/ruby/dataflow/internal/tainttracking1/TaintTracking.qll",
-    "swift/ql/lib/codeql/swift/dataflow/internal/tainttracking1/TaintTracking.qll"
-  ],
   "TaintTracking Legacy Configuration Java/C++/C#/Go/Python/Ruby/Swift": [
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
@@ -484,10 +473,6 @@
     "ruby/ql/lib/codeql/ruby/security/internal/SensitiveDataHeuristics.qll",
     "swift/ql/lib/codeql/swift/security/internal/SensitiveDataHeuristics.qll"
   ],
-  "CFG": [
-    "csharp/ql/lib/semmle/code/csharp/controlflow/internal/ControlFlowGraphImplShared.qll",
-    "swift/ql/lib/codeql/swift/controlflow/internal/ControlFlowGraphImplShared.qll"
-  ],
   "TypeTracker": [
     "python/ql/lib/semmle/python/dataflow/new/internal/TypeTracker.qll",
     "ruby/ql/lib/codeql/ruby/typetracking/TypeTracker.qll"

cpp/autobuilder/Semmle.Autobuild.Cpp.Tests/BuildScripts.cs

@@ -327,7 +327,7 @@ namespace Semmle.Autobuild.Cpp.Tests
         {
             Actions.RunProcess[@"cmd.exe /C nuget restore C:\Project\test.sln -DisableParallelProcessing"] = 1;
             Actions.RunProcess[@"cmd.exe /C C:\Project\.nuget\nuget.exe restore C:\Project\test.sln -DisableParallelProcessing"] = 0;
-            Actions.RunProcess[@"cmd.exe /C CALL ^""C:\Program Files ^(x86^)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat^"" && set Platform=&& type NUL && msbuild C:\Project\test.sln /t:rebuild /p:Platform=""x86"" /p:Configuration=""Release"""] = 0;
+            Actions.RunProcess[@"cmd.exe /C CALL ^""C:\Program^ Files^ ^(x86^)\Microsoft^ Visual^ Studio^ 14.0\VC\vcvarsall.bat^"" && set Platform=&& type NUL && msbuild C:\Project\test.sln /t:rebuild /p:Platform=""x86"" /p:Configuration=""Release"""] = 0;
             Actions.RunProcessOut[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe -prerelease -legacy -property installationPath"] = "";
             Actions.RunProcess[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe -prerelease -legacy -property installationPath"] = 1;
             Actions.RunProcess[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe -prerelease -legacy -property installationVersion"] = 0;

cpp/ql/lib/change-notes/2023-08-24-no-taint-argv-indirections.md

@@ -0,0 +1,4 @@
+---
+category: minorAnalysis
+---
+* Only the 2 level indirection of `argv` (corresponding to `**argv`) is consided for `FlowSource`.

cpp/ql/lib/qlpack.yml

@@ -1,5 +1,5 @@
 name: codeql/cpp-all
-version: 0.9.0
+version: 0.9.1-dev
 groups: cpp
 dbscheme: semmlecode.cpp.dbscheme
 extractor: cpp

cpp/ql/lib/semmle/code/cpp/dataflow/TaintTracking.qll

@@ -25,6 +25,10 @@ import semmle.code.cpp.dataflow.DataFlow2
  * global (inter-procedural) taint-tracking analyses.
  */
 deprecated module TaintTracking {
-  import semmle.code.cpp.dataflow.internal.tainttracking1.TaintTracking
+  import semmle.code.cpp.dataflow.internal.tainttracking1.TaintTrackingParameter::Public
+  private import semmle.code.cpp.dataflow.internal.DataFlowImplSpecific
+  private import semmle.code.cpp.dataflow.internal.TaintTrackingImplSpecific
+  private import codeql.dataflow.TaintTracking
+  import TaintFlowMake<CppOldDataFlow, CppOldTaintTracking>
   import semmle.code.cpp.dataflow.internal.tainttracking1.TaintTrackingImpl
 }

cpp/ql/lib/semmle/code/cpp/dataflow/internal/TaintTrackingImplSpecific.qll

@@ -0,0 +1,10 @@
+/**
+ * Provides C++-specific definitions for use in the taint tracking library.
+ */
+
+private import codeql.dataflow.TaintTracking
+private import DataFlowImplSpecific
+
+module CppOldTaintTracking implements InputSig<CppOldDataFlow> {
+  import TaintTrackingUtil
+}

cpp/ql/lib/semmle/code/cpp/dataflow/internal/TaintTrackingUtil.qll

@@ -39,7 +39,7 @@ predicate defaultAdditionalTaintStep(DataFlow::Node src, DataFlow::Node sink) {
  * of `c` at sinks and inputs to additional taint steps.
  */
 bindingset[node]
-predicate defaultImplicitTaintRead(DataFlow::Node node, DataFlow::Content c) { none() }
+predicate defaultImplicitTaintRead(DataFlow::Node node, DataFlow::ContentSet c) { none() }
 
 /**
  * Holds if `node` should be a sanitizer in all global taint flow configurations

cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking1/TaintTracking.qll

@@ -1,75 +0,0 @@
-/**
- * Provides classes for performing local (intra-procedural) and
- * global (inter-procedural) taint-tracking analyses.
- */
-
-import TaintTrackingParameter::Public
-private import TaintTrackingParameter::Private
-
-private module AddTaintDefaults<DataFlowInternal::FullStateConfigSig Config> implements
-  DataFlowInternal::FullStateConfigSig
-{
-  import Config
-
-  predicate isBarrier(DataFlow::Node node) {
-    Config::isBarrier(node) or defaultTaintSanitizer(node)
-  }
-
-  predicate isAdditionalFlowStep(DataFlow::Node node1, DataFlow::Node node2) {
-    Config::isAdditionalFlowStep(node1, node2) or
-    defaultAdditionalTaintStep(node1, node2)
-  }
-
-  predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
-    Config::allowImplicitRead(node, c)
-    or
-    (
-      Config::isSink(node) or
-      Config::isSink(node, _) or
-      Config::isAdditionalFlowStep(node, _) or
-      Config::isAdditionalFlowStep(node, _, _, _)
-    ) and
-    defaultImplicitTaintRead(node, c)
-  }
-}
-
-/**
- * Constructs a global taint tracking computation.
- */
-module Global<DataFlow::ConfigSig Config> implements DataFlow::GlobalFlowSig {
-  private module Config0 implements DataFlowInternal::FullStateConfigSig {
-    import DataFlowInternal::DefaultState<Config>
-    import Config
-  }
-
-  private module C implements DataFlowInternal::FullStateConfigSig {
-    import AddTaintDefaults<Config0>
-  }
-
-  import DataFlowInternal::Impl<C>
-}
-
-/** DEPRECATED: Use `Global` instead. */
-deprecated module Make<DataFlow::ConfigSig Config> implements DataFlow::GlobalFlowSig {
-  import Global<Config>
-}
-
-/**
- * Constructs a global taint tracking computation using flow state.
- */
-module GlobalWithState<DataFlow::StateConfigSig Config> implements DataFlow::GlobalFlowSig {
-  private module Config0 implements DataFlowInternal::FullStateConfigSig {
-    import Config
-  }
-
-  private module C implements DataFlowInternal::FullStateConfigSig {
-    import AddTaintDefaults<Config0>
-  }
-
-  import DataFlowInternal::Impl<C>
-}
-
-/** DEPRECATED: Use `GlobalWithState` instead. */
-deprecated module MakeWithState<DataFlow::StateConfigSig Config> implements DataFlow::GlobalFlowSig {
-  import GlobalWithState<Config>
-}

cpp/ql/lib/semmle/code/cpp/dataflow/new/TaintTracking.qll

@@ -23,6 +23,10 @@ import semmle.code.cpp.dataflow.new.DataFlow2
  * global (inter-procedural) taint-tracking analyses.
  */
 module TaintTracking {
-  import semmle.code.cpp.ir.dataflow.internal.tainttracking1.TaintTracking
+  import semmle.code.cpp.ir.dataflow.internal.tainttracking1.TaintTrackingParameter::Public
+  private import semmle.code.cpp.ir.dataflow.internal.DataFlowImplSpecific
+  private import semmle.code.cpp.ir.dataflow.internal.TaintTrackingImplSpecific
+  private import codeql.dataflow.TaintTracking
+  import TaintFlowMake<CppDataFlow, CppTaintTracking>
   import semmle.code.cpp.ir.dataflow.internal.tainttracking1.TaintTrackingImpl
 }

cpp/ql/lib/semmle/code/cpp/ir/dataflow/TaintTracking.qll

@@ -19,6 +19,10 @@ import semmle.code.cpp.ir.dataflow.DataFlow
 import semmle.code.cpp.ir.dataflow.DataFlow2
 
 module TaintTracking {
-  import semmle.code.cpp.ir.dataflow.internal.tainttracking1.TaintTracking
+  import semmle.code.cpp.ir.dataflow.internal.tainttracking1.TaintTrackingParameter::Public
+  private import semmle.code.cpp.ir.dataflow.internal.DataFlowImplSpecific
+  private import semmle.code.cpp.ir.dataflow.internal.TaintTrackingImplSpecific
+  private import codeql.dataflow.TaintTracking
+  import TaintFlowMake<CppDataFlow, CppTaintTracking>
   import semmle.code.cpp.ir.dataflow.internal.tainttracking1.TaintTrackingImpl
 }

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)
 }
 
@@ -1534,6 +1520,25 @@ private module Cached {
     )
   }
 
+  /**
+   * Holds if `operand.getDef() = instr`, but there exists a `StoreInstruction` that
+   * writes to an address that is equivalent to the value computed by `instr` in
+   * between `instr` and `operand`, and therefore there should not be flow from `*instr`
+   * to `*operand`.
+   */
+  pragma[nomagic]
+  private predicate isStoredToBetween(Instruction instr, Operand operand) {
+    simpleOperandLocalFlowStep(pragma[only_bind_into](instr), pragma[only_bind_into](operand)) and
+    exists(StoreInstruction store, IRBlock block, int storeIndex, int instrIndex, int operandIndex |
+      store.getDestinationAddress() = instr and
+      block.getInstruction(storeIndex) = store and
+      block.getInstruction(instrIndex) = instr and
+      block.getInstruction(operandIndex) = operand.getUse() and
+      instrIndex < storeIndex and
+      storeIndex < operandIndex
+    )
+  }
+
   private predicate indirectionInstructionFlow(
     RawIndirectInstruction nodeFrom, IndirectOperand nodeTo
   ) {
@@ -1543,7 +1548,8 @@ private module Cached {
       simpleOperandLocalFlowStep(pragma[only_bind_into](instr), pragma[only_bind_into](operand))
     |
       hasOperandAndIndex(nodeTo, operand, pragma[only_bind_into](indirectionIndex)) and
-      hasInstructionAndIndex(nodeFrom, instr, pragma[only_bind_into](indirectionIndex))
+      hasInstructionAndIndex(nodeFrom, instr, pragma[only_bind_into](indirectionIndex)) and
+      not isStoredToBetween(instr, operand)
     )
   }
 

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

@@ -10,32 +10,35 @@ 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) {
+    TMkSourceVariable(SsaInternals0::SourceVariable base, int ind) {
-      ind = [0 .. getMaxIndirectionForIRVariable(baseVar.getIRVariable())]
+      ind = [0 .. countIndirectionsForCppType(base.getLanguageType()) + 1]
-    } or
-    TCallVariable(AllocationInstruction call, int ind) {
-      ind = [0 .. countIndirectionsForCppType(getResultLanguageType(call))]
     }
 
-  abstract class SourceVariable extends TSourceVariable {
+  class SourceVariable extends TSourceVariable {
+    SsaInternals0::SourceVariable base;
     int ind;
 
-    bindingset[ind]
+    SourceVariable() { this = TMkSourceVariable(base, ind) }
-    SourceVariable() { any() }
+
+    /** 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
@@ -43,65 +46,19 @@ private module SourceVariables {
      */
     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();
+    DataFlowType getType() {
+      if this.isGLValue()
+      then result = base.getType()
+      else result = getTypeImpl(base.getType(), ind - 1)
     }
-
-  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)
-    }
-  }
-
-  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) }
   }
 }
 
@@ -137,8 +94,9 @@ predicate hasRawIndirectInstruction(Instruction instr, int indirectionIndex) {
 
 cached
 private newtype TDefOrUseImpl =
-  TDefImpl(Operand address, int indirectionIndex) {
+  TDefImpl(BaseSourceVariableInstruction base, Operand address, int indirectionIndex) {
-    exists(Instruction base | isDef(_, _, address, base, _, 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) {
+  TUseImpl(BaseSourceVariableInstruction base, Operand operand, int indirectionIndex) {
-    isUse(_, operand, _, _, indirectionIndex) and
+    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;
 
-  override BaseSourceVariableInstruction getBase() { isDef(_, _, address, result, _, _) }
+  DirectDef() { this = TDefImpl(base, address, ind) }
 
-  override int getIndirection() { isDef(_, _, address, _, result, ind) }
+  override BaseSourceVariableInstruction getBase() { result = base }
 
-  override Node0Impl getValue() { isDef(_, result, address, _, _, _) }
+  override int getIndirection() { isDef(_, _, address, base, result, ind) }
 
-  override predicate isCertain() { isDef(true, _, address, _, _, ind) }
+  override Node0Impl getValue() { isDef(_, result, address, base, _, _) }
+
+  override predicate isCertain() { isDef(true, _, address, base, _, ind) }
 }
 
 private class IteratorDef extends DefImpl, TIteratorDef {
@@ -359,6 +319,7 @@ abstract class UseImpl extends DefOrUseImpl {
 
 abstract private class OperandBasedUse extends UseImpl {
   Operand operand;
+  BaseSourceVariableInstruction base;
 
   bindingset[ind]
   OperandBasedUse() { any() }
@@ -366,7 +327,6 @@ abstract private class OperandBasedUse extends UseImpl {
   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 |
@@ -382,34 +342,29 @@ abstract private class OperandBasedUse extends UseImpl {
         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) }
+  DirectUse() { this = TUseImpl(base, operand, ind) }
 
-  override int getIndirection() { isUse(_, operand, _, result, ind) }
+  override int getIndirection() { isUse(_, operand, base, result, ind) }
 
-  override BaseSourceVariableInstruction getBase() { isUse(_, operand, result, _, ind) }
+  override predicate isCertain() { isUse(true, operand, base, _, ind) }
-
-  override predicate isCertain() { isUse(true, operand, _, _, 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(base, operand, result, ind) }
-
-  override int getIndirection() { isIteratorUse(container, operand, result, ind) }
-
-  override BaseSourceVariableInstruction getBase() { result = container }
 
   override predicate isCertain() { none() }
 

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

@@ -6,6 +6,7 @@ private import DataFlowImplCommon as DataFlowImplCommon
 private import DataFlowUtil
 private import semmle.code.cpp.models.interfaces.PointerWrapper
 private import DataFlowPrivate
+private import semmle.code.cpp.ir.ValueNumbering
 
 /**
  * Holds if `operand` is an operand that is not used by the dataflow library.
@@ -146,14 +147,6 @@ 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 +361,22 @@ 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 +385,19 @@ 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 {
+class BaseCallVariable extends AbstractBaseSourceVariable, TBaseCallVariable {
-  AllocationInstruction call;
+  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 +497,7 @@ 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 }
 }
 
@@ -868,7 +865,7 @@ private module Cached {
    * to a specific address.
    */
   private predicate isCertainAddress(Operand operand) {
-    operand.getDef() instanceof VariableAddressInstruction
+    valueNumberOfOperand(operand).getAnInstruction() instanceof VariableAddressInstruction
     or
     operand.getType() instanceof Cpp::ReferenceType
   }

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

@@ -0,0 +1,10 @@
+/**
+ * Provides C++-specific definitions for use in the taint tracking library.
+ */
+
+private import codeql.dataflow.TaintTracking
+private import DataFlowImplSpecific
+
+module CppTaintTracking implements InputSig<CppDataFlow> {
+  import TaintTrackingUtil
+}

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

@@ -112,7 +112,7 @@ predicate defaultAdditionalTaintStep(DataFlow::Node src, DataFlow::Node sink) {
  * of `c` at sinks and inputs to additional taint steps.
  */
 bindingset[node]
-predicate defaultImplicitTaintRead(DataFlow::Node node, DataFlow::Content c) { none() }
+predicate defaultImplicitTaintRead(DataFlow::Node node, DataFlow::ContentSet c) { none() }
 
 /**
  * Holds if `node` should be a sanitizer in all global taint flow configurations

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/ssa0/SsaInternals.qll

@@ -15,15 +15,12 @@ private import semmle.code.cpp.ir.dataflow.internal.DataFlowUtil
 private import semmle.code.cpp.ir.dataflow.internal.SsaInternalsCommon
 
 private module SourceVariables {
-  class SourceVariable instanceof BaseSourceVariable {
+  class SourceVariable extends BaseSourceVariable {
-    string toString() { result = BaseSourceVariable.super.toString() }
+    /**
-
+     * Gets the base source variable of this `SourceVariable`.
+     */
     BaseSourceVariable getBaseVariable() { result = this }
   }
-
-  class SourceIRVariable = BaseIRVariable;
-
-  class CallVariable = BaseCallVariable;
 }
 
 import SourceVariables

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/tainttracking1/TaintTracking.qll

@@ -1,75 +0,0 @@
-/**
- * Provides classes for performing local (intra-procedural) and
- * global (inter-procedural) taint-tracking analyses.
- */
-
-import TaintTrackingParameter::Public
-private import TaintTrackingParameter::Private
-
-private module AddTaintDefaults<DataFlowInternal::FullStateConfigSig Config> implements
-  DataFlowInternal::FullStateConfigSig
-{
-  import Config
-
-  predicate isBarrier(DataFlow::Node node) {
-    Config::isBarrier(node) or defaultTaintSanitizer(node)
-  }
-
-  predicate isAdditionalFlowStep(DataFlow::Node node1, DataFlow::Node node2) {
-    Config::isAdditionalFlowStep(node1, node2) or
-    defaultAdditionalTaintStep(node1, node2)
-  }
-
-  predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
-    Config::allowImplicitRead(node, c)
-    or
-    (
-      Config::isSink(node) or
-      Config::isSink(node, _) or
-      Config::isAdditionalFlowStep(node, _) or
-      Config::isAdditionalFlowStep(node, _, _, _)
-    ) and
-    defaultImplicitTaintRead(node, c)
-  }
-}
-
-/**
- * Constructs a global taint tracking computation.
- */
-module Global<DataFlow::ConfigSig Config> implements DataFlow::GlobalFlowSig {
-  private module Config0 implements DataFlowInternal::FullStateConfigSig {
-    import DataFlowInternal::DefaultState<Config>
-    import Config
-  }
-
-  private module C implements DataFlowInternal::FullStateConfigSig {
-    import AddTaintDefaults<Config0>
-  }
-
-  import DataFlowInternal::Impl<C>
-}
-
-/** DEPRECATED: Use `Global` instead. */
-deprecated module Make<DataFlow::ConfigSig Config> implements DataFlow::GlobalFlowSig {
-  import Global<Config>
-}
-
-/**
- * Constructs a global taint tracking computation using flow state.
- */
-module GlobalWithState<DataFlow::StateConfigSig Config> implements DataFlow::GlobalFlowSig {
-  private module Config0 implements DataFlowInternal::FullStateConfigSig {
-    import Config
-  }
-
-  private module C implements DataFlowInternal::FullStateConfigSig {
-    import AddTaintDefaults<Config0>
-  }
-
-  import DataFlowInternal::Impl<C>
-}
-
-/** DEPRECATED: Use `GlobalWithState` instead. */
-deprecated module MakeWithState<DataFlow::StateConfigSig Config> implements DataFlow::GlobalFlowSig {
-  import GlobalWithState<Config>
-}

cpp/ql/lib/semmle/code/cpp/rangeanalysis/new/internal/semantic/analysis/RangeAnalysisStage.qll

@@ -574,16 +574,6 @@ module RangeStage<
     )
   }
 
-  /** Holds if `e >= 1` as determined by sign analysis. */
-  private predicate strictlyPositiveIntegralExpr(SemExpr e) {
-    semStrictlyPositive(e) and getTrackedType(e) instanceof SemIntegerType
-  }
-
-  /** Holds if `e <= -1` as determined by sign analysis. */
-  private predicate strictlyNegativeIntegralExpr(SemExpr e) {
-    semStrictlyNegative(e) and getTrackedType(e) instanceof SemIntegerType
-  }
-
   /**
    * Holds if `e1 + delta` is a valid bound for `e2`.
    * - `upper = true`  : `e2 <= e1 + delta`
@@ -597,27 +587,6 @@ module RangeStage<
     delta = D::fromInt(0) and
     (upper = true or upper = false)
     or
-    exists(SemExpr x, SemSubExpr sub |
-      e2 = sub and
-      sub.getLeftOperand() = e1 and
-      sub.getRightOperand() = x
-    |
-      // `x instanceof ConstantIntegerExpr` is covered by valueFlowStep
-      not x instanceof SemConstantIntegerExpr and
-      if strictlyPositiveIntegralExpr(x)
-      then upper = true and delta = D::fromInt(-1)
-      else
-        if semPositive(x)
-        then upper = true and delta = D::fromInt(0)
-        else
-          if strictlyNegativeIntegralExpr(x)
-          then upper = false and delta = D::fromInt(1)
-          else
-            if semNegative(x)
-            then upper = false and delta = D::fromInt(0)
-            else none()
-    )
-    or
     e2.(SemRemExpr).getRightOperand() = e1 and
     semPositive(e1) and
     delta = D::fromInt(-1) and
@@ -1137,6 +1106,23 @@ module RangeStage<
         b = bRight and origdelta = odRight and reason = rRight and bLeft instanceof SemZeroBound
       )
       or
+      exists(D::Delta dLeft, D::Delta dRight, boolean fbeLeft, boolean fbeRight |
+        boundedSubOperandLeft(e, upper, b, dLeft, fbeLeft, origdelta, reason) and
+        boundedSubOperandRight(e, upper, dRight, fbeRight) and
+        // when `upper` is `true` we have:
+        // left <= b + dLeft
+        // right >= 0 + dRight
+        // left - right <= b + dLeft - (0 + dRight)
+        //               = b + (dLeft - dRight)
+        // and when `upper` is `false` we have:
+        // left >= b + dLeft
+        // right <= 0 + dRight
+        // left - right >= b + dLeft - (0 + dRight)
+        //               = b + (dLeft - dRight)
+        delta = D::fromFloat(D::toFloat(dLeft) - D::toFloat(dRight)) and
+        fromBackEdge = fbeLeft.booleanOr(fbeRight)
+      )
+      or
       exists(
         SemRemExpr rem, D::Delta d_max, D::Delta d1, D::Delta d2, boolean fbe1, boolean fbe2,
         D::Delta od1, D::Delta od2, SemReason r1, SemReason r2
@@ -1201,6 +1187,37 @@ module RangeStage<
     )
   }
 
+  /**
+   * Holds if `sub = left - right` and `left <= b + delta` if `upper` is `true`
+   * and `left >= b + delta` is `upper` is `false`.
+   */
+  pragma[nomagic]
+  private predicate boundedSubOperandLeft(
+    SemSubExpr sub, boolean upper, SemBound b, D::Delta delta, boolean fromBackEdge,
+    D::Delta origdelta, SemReason reason
+  ) {
+    // `semValueFlowStep` already handles the case where one of the operands is a constant.
+    not semValueFlowStep(sub, _, _) and
+    bounded(sub.getLeftOperand(), b, delta, upper, fromBackEdge, origdelta, reason)
+  }
+
+  /**
+   * Holds if `sub = left - right` and `right <= 0 + delta` if `upper` is `false`
+   * and `right >= 0 + delta` is `upper` is `true`.
+   *
+   * Note that the boolean value of `upper` is flipped compared to many other predicates in
+   * this file. This ensures a clean join at the call-site.
+   */
+  pragma[nomagic]
+  private predicate boundedSubOperandRight(
+    SemSubExpr sub, boolean upper, D::Delta delta, boolean fromBackEdge
+  ) {
+    // `semValueFlowStep` already handles the case where one of the operands is a constant.
+    not semValueFlowStep(sub, _, _) and
+    bounded(sub.getRightOperand(), any(SemZeroBound zb), delta, upper.booleanNot(), fromBackEdge, _,
+      _)
+  }
+
   pragma[nomagic]
   private predicate boundedRemExpr(
     SemRemExpr rem, boolean upper, D::Delta delta, boolean fromBackEdge, D::Delta origdelta,

cpp/ql/lib/semmle/code/cpp/security/FlowSources.qll

@@ -53,7 +53,7 @@ private class ArgvSource extends LocalFlowSource {
     exists(Function main, Parameter argv |
       main.hasGlobalName("main") and
       main.getParameter(1) = argv and
-      this.asParameter(_) = argv
+      this.asParameter(2) = argv
     )
   }
 

cpp/ql/lib/semmle/code/cpp/security/InvalidPointerDereference/AllocationToInvalidPointer.qll

@@ -96,7 +96,7 @@ predicate hasSize(HeuristicAllocationExpr alloc, DataFlow::Node n, int state) {
  * but because there's a strict comparison that compares `n` against the size of the allocation this
  * snippet is fine.
  */
-module SizeBarrier {
+private module SizeBarrier {
   private module SizeBarrierConfig implements DataFlow::ConfigSig {
     predicate isSource(DataFlow::Node source) {
       // The sources is the same as in the sources for the second
@@ -104,35 +104,60 @@ module SizeBarrier {
       hasSize(_, source, _)
     }
 
+    /**
+     * Holds if `small <= large + k` holds if `g` evaluates to `testIsTrue`.
+     */
     additional predicate isSink(
-      DataFlow::Node left, DataFlow::Node right, IRGuardCondition g, int k, boolean testIsTrue
+      DataFlow::Node small, DataFlow::Node large, IRGuardCondition g, int k, boolean testIsTrue
     ) {
-      // The sink is any "large" side of a relational comparison. i.e., the `right` expression
+      // The sink is any "large" side of a relational comparison. i.e., the `large` expression
-      // in a guard such as `left < right + k`.
+      // in a guard such as `small <= large + k`.
-      g.comparesLt(left.asOperand(), right.asOperand(), k, true, testIsTrue)
+      g.comparesLt(small.asOperand(), large.asOperand(), k + 1, true, testIsTrue)
     }
 
     predicate isSink(DataFlow::Node sink) { isSink(_, sink, _, _, _) }
   }
 
-  private import DataFlow::Global<SizeBarrierConfig>
+  module SizeBarrierFlow = DataFlow::Global<SizeBarrierConfig>;
 
-  private int getAFlowStateForNode(DataFlow::Node node) {
+  private int getASizeAddend(DataFlow::Node node) {
     exists(DataFlow::Node source |
-      flow(source, node) and
+      SizeBarrierFlow::flow(source, node) and
       hasSize(_, source, result)
     )
   }
 
+  /**
+   * Holds if `small <= large + k` holds if `g` evaluates to `edge`.
+   */
   private predicate operandGuardChecks(
-    IRGuardCondition g, Operand left, Operand right, int state, boolean edge
+    IRGuardCondition g, Operand small, DataFlow::Node large, int k, boolean edge
   ) {
-    exists(DataFlow::Node nLeft, DataFlow::Node nRight, int k |
+    SizeBarrierFlow::flowTo(large) and
-      nRight.asOperand() = right and
+    SizeBarrierConfig::isSink(DataFlow::operandNode(small), large, g, k, edge)
-      nLeft.asOperand() = left and
+  }
-      SizeBarrierConfig::isSink(nLeft, nRight, g, k, edge) and
+
-      state = getAFlowStateForNode(nRight) and
+  /**
-      k <= state
+   * Gets an instruction `instr` that is guarded by a check such as `instr <= small + delta` where
+   * `small <= _ + k` and `small` is the "small side" of of a relational comparison that checks
+   * whether `small <= size` where `size` is the size of an allocation.
+   */
+  Instruction getABarrierInstruction0(int delta, int k) {
+    exists(
+      IRGuardCondition g, ValueNumber value, Operand small, boolean edge, DataFlow::Node large
+    |
+      // We know:
+      // 1. result <= value + delta (by `bounded`)
+      // 2. value <= large + k (by `operandGuardChecks`).
+      // So:
+      // result <= value + delta (by 1.)
+      //        <= large + k + delta (by 2.)
+      small = value.getAUse() and
+      operandGuardChecks(pragma[only_bind_into](g), pragma[only_bind_into](small), large,
+        pragma[only_bind_into](k), pragma[only_bind_into](edge)) and
+      bounded(result, value.getAnInstruction(), delta) and
+      g.controls(result.getBlock(), edge) and
+      k < getASizeAddend(large)
     )
   }
 
@@ -140,13 +165,14 @@ module SizeBarrier {
    * Gets an instruction that is guarded by a guard condition which ensures that
    * the value of the instruction is upper-bounded by size of some allocation.
    */
+  bindingset[state]
+  pragma[inline_late]
   Instruction getABarrierInstruction(int state) {
-    exists(IRGuardCondition g, ValueNumber value, Operand use, boolean edge |
+    exists(int delta, int k |
-      use = value.getAUse() and
+      state > k + delta and
-      operandGuardChecks(pragma[only_bind_into](g), pragma[only_bind_into](use), _,
+      // result <= "size of allocation" + delta + k
-        pragma[only_bind_into](state), pragma[only_bind_into](edge)) and
+      //        < "size of allocation" + state
-      result = value.getAnInstruction() and
+      result = getABarrierInstruction0(delta, k)
-      g.controls(result.getBlock(), edge)
     )
   }
 
@@ -155,14 +181,16 @@ module SizeBarrier {
    * the value of the node is upper-bounded by size of some allocation.
    */
   DataFlow::Node getABarrierNode(int state) {
-    result.asOperand() = getABarrierInstruction(state).getAUse()
+    exists(DataFlow::Node source, int delta, int k |
+      SizeBarrierFlow::flow(source, result) and
+      hasSize(_, source, state) and
+      result.asInstruction() = SizeBarrier::getABarrierInstruction0(delta, k) and
+      state > k + delta
+      // so now we have:
+      // result <= "size of allocation" + delta + k
+      //        < "size of allocation" + state
+    )
   }
-
-  /**
-   * Gets the block of a node that is guarded (see `getABarrierInstruction` or
-   * `getABarrierNode` for the definition of what it means to be guarded).
-   */
-  IRBlock getABarrierBlock(int state) { result.getAnInstruction() = getABarrierInstruction(state) }
 }
 
 private module InterestingPointerAddInstruction {

cpp/ql/lib/semmle/code/cpp/security/InvalidPointerDereference/InvalidPointerToDereference.qll

@@ -66,11 +66,14 @@
  * module. Since the node we are tracking is not necessarily _equal_ to the pointer-arithmetic instruction, but rather satisfies
  * `node.asInstruction() <= pai + deltaDerefSourceAndPai`, we need to account for the delta when checking if a guard is sufficiently
  * strong to infer that a future dereference is safe. To do this, we check that the guard guarantees that a node `n` satisfies
- * `n < node + k` where `node` is a node we know is equal to the value of the dereference source (i.e., it satisfies
+ * `n < node + k` where `node` is a node such that `node <= pai`. Thus, we know that any node `m` such that `m <= n + delta` where
- * `node.asInstruction() <= pai + deltaDerefSourceAndPai`) and `k <= deltaDerefSourceAndPai`. Combining this we have
+ * `delta + k <= 0` will be safe because:
- * `n < node + k <= node + deltaDerefSourceAndPai <= pai + 2*deltaDerefSourceAndPai` (TODO: Oops. This math doesn't quite work out.
+ * ```
- * I think this is because we need to redefine the `BarrierConfig` to start flow at the pointer-arithmetic instruction instead of
+ * m <= n + delta
- * at the dereference source. When combined with TODO above it's easy to show that this guard ensures that the dereference is safe).
+ *   <  node + k + delta
+ *   <= pai + k + delta
+ *   <= pai
+ * ```
  */
 
 private import cpp
@@ -82,16 +85,19 @@ private import RangeAnalysisUtil
 
 private module InvalidPointerToDerefBarrier {
   private module BarrierConfig implements DataFlow::ConfigSig {
-    predicate isSource(DataFlow::Node source) {
+    additional predicate isSource(DataFlow::Node source, PointerArithmeticInstruction pai) {
-      // The sources is the same as in the sources for `InvalidPointerToDerefConfig`.
+      invalidPointerToDerefSource(_, pai, _, _) and
-      invalidPointerToDerefSource(_, _, source, _)
+      // source <= pai
+      bounded2(source.asInstruction(), pai, any(int d | d <= 0))
     }
 
+    predicate isSource(DataFlow::Node source) { isSource(source, _) }
+
     additional predicate isSink(
-      DataFlow::Node left, DataFlow::Node right, IRGuardCondition g, int k, boolean testIsTrue
+      DataFlow::Node small, DataFlow::Node large, IRGuardCondition g, int k, boolean testIsTrue
     ) {
       // The sink is any "large" side of a relational comparison.
-      g.comparesLt(left.asOperand(), right.asOperand(), k, true, testIsTrue)
+      g.comparesLt(small.asOperand(), large.asOperand(), k, true, testIsTrue)
     }
 
     predicate isSink(DataFlow::Node sink) { isSink(_, sink, _, _, _) }
@@ -99,59 +105,82 @@ private module InvalidPointerToDerefBarrier {
 
   private module BarrierFlow = DataFlow::Global<BarrierConfig>;
 
-  private int getInvalidPointerToDerefSourceDelta(DataFlow::Node node) {
+  /**
-    exists(DataFlow::Node source |
+   * Holds if `g` ensures that `small < large + k` if `g` evaluates to `edge`.
-      BarrierFlow::flow(source, node) and
+   *
-      invalidPointerToDerefSource(_, _, source, result)
+   * Additionally, it also holds that `large <= pai`. Thus, when `g` evaluates to `edge`
-    )
+   * it holds that `small < pai + k`.
-  }
+   */
-
   private predicate operandGuardChecks(
-    IRGuardCondition g, Operand left, Operand right, int state, boolean edge
+    PointerArithmeticInstruction pai, IRGuardCondition g, Operand small, int k, boolean edge
   ) {
-    exists(DataFlow::Node nLeft, DataFlow::Node nRight, int k |
+    exists(DataFlow::Node source, DataFlow::Node nSmall, DataFlow::Node nLarge |
-      nRight.asOperand() = right and
+      nSmall.asOperand() = small and
-      nLeft.asOperand() = left and
+      BarrierConfig::isSource(source, pai) and
-      BarrierConfig::isSink(nLeft, nRight, g, k, edge) and
+      BarrierFlow::flow(source, nLarge) and
-      state = getInvalidPointerToDerefSourceDelta(nRight) and
+      BarrierConfig::isSink(nSmall, nLarge, g, k, edge)
-      k <= state
     )
   }
 
-  Instruction getABarrierInstruction(int state) {
+  /**
-    exists(IRGuardCondition g, ValueNumber value, Operand use, boolean edge |
+   * Gets an instruction `instr` such that `instr < pai`.
+   */
+  Instruction getABarrierInstruction(PointerArithmeticInstruction pai) {
+    exists(IRGuardCondition g, ValueNumber value, Operand use, boolean edge, int delta, int k |
       use = value.getAUse() and
-      operandGuardChecks(pragma[only_bind_into](g), pragma[only_bind_into](use), _, state,
+      // value < pai + k
-        pragma[only_bind_into](edge)) and
+      operandGuardChecks(pai, pragma[only_bind_into](g), pragma[only_bind_into](use),
-      result = value.getAnInstruction() and
+        pragma[only_bind_into](k), pragma[only_bind_into](edge)) and
-      g.controls(result.getBlock(), edge)
+      // result <= value + delta
+      bounded(result, value.getAnInstruction(), delta) and
+      g.controls(result.getBlock(), edge) and
+      delta + k <= 0
+      // combining the above we have: result < pai + k + delta <= pai
     )
   }
 
-  DataFlow::Node getABarrierNode() { result.asOperand() = getABarrierInstruction(_).getAUse() }
+  DataFlow::Node getABarrierNode(PointerArithmeticInstruction pai) {
+    result.asOperand() = getABarrierInstruction(pai).getAUse()
+  }
 
-  pragma[nomagic]
+  /**
-  IRBlock getABarrierBlock(int state) { result.getAnInstruction() = getABarrierInstruction(state) }
+   * Gets an address operand whose definition `instr` satisfies `instr < pai`.
+   */
+  AddressOperand getABarrierAddressOperand(PointerArithmeticInstruction pai) {
+    result.getDef() = getABarrierInstruction(pai)
+  }
 }
 
 /**
  * A configuration to track flow from a pointer-arithmetic operation found
  * by `AllocToInvalidPointerConfig` to a dereference of the pointer.
  */
-private module InvalidPointerToDerefConfig implements DataFlow::ConfigSig {
+private module InvalidPointerToDerefConfig implements DataFlow::StateConfigSig {
-  predicate isSource(DataFlow::Node source) { invalidPointerToDerefSource(_, _, source, _) }
+  class FlowState extends PointerArithmeticInstruction {
+    FlowState() { invalidPointerToDerefSource(_, this, _, _) }
+  }
+
+  predicate isSource(DataFlow::Node source, FlowState pai) {
+    invalidPointerToDerefSource(_, pai, source, _)
+  }
 
   pragma[inline]
-  predicate isSink(DataFlow::Node sink) { isInvalidPointerDerefSink(sink, _, _, _) }
+  predicate isSink(DataFlow::Node sink) { isInvalidPointerDerefSink(sink, _, _, _, _) }
+
+  predicate isSink(DataFlow::Node sink, FlowState pai) { none() }
 
   predicate isBarrier(DataFlow::Node node) {
     node = any(DataFlow::SsaPhiNode phi | not phi.isPhiRead()).getAnInput(true)
-    or
+  }
-    node = InvalidPointerToDerefBarrier::getABarrierNode()
+
+  predicate isBarrier(DataFlow::Node node, FlowState pai) {
+    // `node = getABarrierNode(pai)` ensures that node < pai, so this node is safe to dereference.
+    // Note that this is the only place where the `FlowState` is used in this configuration.
+    node = InvalidPointerToDerefBarrier::getABarrierNode(pai)
   }
 }
 
-private import DataFlow::Global<InvalidPointerToDerefConfig>
+private import DataFlow::GlobalWithState<InvalidPointerToDerefConfig>
 
 /**
  * Holds if `allocSource` is dataflow node that represents an allocation that flows to the
@@ -165,19 +194,14 @@ private predicate invalidPointerToDerefSource(
   DataFlow::Node allocSource, PointerArithmeticInstruction pai, DataFlow::Node derefSource,
   int deltaDerefSourceAndPai
 ) {
-  exists(int rhsSizeDelta |
   // Note that `deltaDerefSourceAndPai` is not necessarily equal to `rhsSizeDelta`:
   // `rhsSizeDelta` is the constant offset added to the size of the allocation, and
   // `deltaDerefSourceAndPai` is the constant difference between the pointer-arithmetic instruction
   // and the instruction computing the address for which we will search for a dereference.
-    AllocToInvalidPointer::pointerAddInstructionHasBounds(allocSource, pai, _, rhsSizeDelta) and
+  AllocToInvalidPointer::pointerAddInstructionHasBounds(allocSource, pai, _, _) and
+  // derefSource <= pai + deltaDerefSourceAndPai
   bounded2(derefSource.asInstruction(), pai, deltaDerefSourceAndPai) and
-    deltaDerefSourceAndPai >= 0 and
+  deltaDerefSourceAndPai >= 0
-    // TODO: This condition will go away once #13725 is merged, and then we can make `SizeBarrier`
-    // private to `AllocationToInvalidPointer.qll`.
-    not derefSource.getBasicBlock() =
-      AllocToInvalidPointer::SizeBarrier::getABarrierBlock(rhsSizeDelta)
-  )
 }
 
 /**
@@ -187,15 +211,14 @@ private predicate invalidPointerToDerefSource(
  */
 pragma[inline]
 private predicate isInvalidPointerDerefSink(
-  DataFlow::Node sink, Instruction i, string operation, int deltaDerefSinkAndDerefAddress
+  DataFlow::Node sink, AddressOperand addr, Instruction i, string operation,
+  int deltaDerefSinkAndDerefAddress
 ) {
-  exists(AddressOperand addr, Instruction s, IRBlock b |
+  exists(Instruction s |
     s = sink.asInstruction() and
     bounded(addr.getDef(), s, deltaDerefSinkAndDerefAddress) and
     deltaDerefSinkAndDerefAddress >= 0 and
-    i.getAnOperand() = addr and
+    i.getAnOperand() = addr
-    b = i.getBlock() and
-    not b = InvalidPointerToDerefBarrier::getABarrierBlock(deltaDerefSinkAndDerefAddress)
   |
     i instanceof StoreInstruction and
     operation = "write"
@@ -221,9 +244,11 @@ private Instruction getASuccessor(Instruction instr) {
   instr.getBlock().getASuccessor+() = result.getBlock()
 }
 
-private predicate paiForDereferenceSink(PointerArithmeticInstruction pai, DataFlow::Node derefSink) {
+private predicate paiForDereferenceSink(
+  PointerArithmeticInstruction pai, DataFlow::Node derefSink, int deltaDerefSourceAndPai
+) {
   exists(DataFlow::Node derefSource |
-    invalidPointerToDerefSource(_, pai, derefSource, _) and
+    invalidPointerToDerefSource(_, pai, derefSource, deltaDerefSourceAndPai) and
     flow(derefSource, derefSink)
   )
 }
@@ -235,13 +260,15 @@ private predicate paiForDereferenceSink(PointerArithmeticInstruction pai, DataFl
  */
 private predicate derefSinkToOperation(
   DataFlow::Node derefSink, PointerArithmeticInstruction pai, DataFlow::Node operation,
-  string description, int deltaDerefSinkAndDerefAddress
+  string description, int deltaDerefSourceAndPai, int deltaDerefSinkAndDerefAddress
 ) {
-  exists(Instruction operationInstr |
+  exists(Instruction operationInstr, AddressOperand addr |
-    paiForDereferenceSink(pai, pragma[only_bind_into](derefSink)) and
+    paiForDereferenceSink(pai, pragma[only_bind_into](derefSink), deltaDerefSourceAndPai) and
-    isInvalidPointerDerefSink(derefSink, operationInstr, description, deltaDerefSinkAndDerefAddress) and
+    isInvalidPointerDerefSink(derefSink, addr, operationInstr, description,
+      deltaDerefSinkAndDerefAddress) and
     operationInstr = getASuccessor(derefSink.asInstruction()) and
-    operation.asInstruction() = operationInstr
+    operation.asInstruction() = operationInstr and
+    not addr = InvalidPointerToDerefBarrier::getABarrierAddressOperand(pai)
   )
 }
 
@@ -260,7 +287,8 @@ predicate operationIsOffBy(
   exists(int deltaDerefSourceAndPai, int deltaDerefSinkAndDerefAddress |
     invalidPointerToDerefSource(allocation, pai, derefSource, deltaDerefSourceAndPai) and
     flow(derefSource, derefSink) and
-    derefSinkToOperation(derefSink, pai, operation, description, deltaDerefSinkAndDerefAddress) and
+    derefSinkToOperation(derefSink, pai, operation, description, deltaDerefSourceAndPai,
+      deltaDerefSinkAndDerefAddress) and
     delta = deltaDerefSourceAndPai + deltaDerefSinkAndDerefAddress
   )
 }

cpp/ql/lib/semmle/code/cpp/security/InvalidPointerDereference/RangeAnalysisUtil.qll

@@ -18,7 +18,7 @@ private Instruction getABoundIn(SemBound b, IRFunction func) {
  * Holds if `i <= b + delta`.
  */
 pragma[inline]
-private predicate boundedImpl(Instruction i, Instruction b, int delta) {
+private predicate boundedImplCand(Instruction i, Instruction b, int delta) {
   exists(SemBound bound, IRFunction func |
     semBounded(getSemanticExpr(i), bound, delta, true, _) and
     b = getABoundIn(bound, func) and
@@ -26,6 +26,15 @@ private predicate boundedImpl(Instruction i, Instruction b, int delta) {
   )
 }
 
+/**
+ * Holds if `i <= b + delta` and `delta` is the smallest integer that satisfies
+ * this condition.
+ */
+pragma[inline]
+private predicate boundedImpl(Instruction i, Instruction b, int delta) {
+  delta = min(int cand | boundedImplCand(i, b, cand))
+}
+
 /**
  * Holds if `i <= b + delta`.
  *

cpp/ql/src/Likely Bugs/Format/NonConstantFormat.ql

@@ -105,8 +105,6 @@ predicate isNonConst(DataFlow::Node node, boolean isIndirect) {
     or
     e instanceof NewArrayExpr
     or
-    e instanceof AssignExpr
-    or
     exists(Variable v | v = e.(VariableAccess).getTarget() |
       v.getType().(ArrayType).getBaseType() instanceof CharType and
       exists(AssignExpr ae |

cpp/ql/src/Security/CWE/CWE-089/SqlTainted.ql

@@ -14,9 +14,11 @@
 
 import cpp
 import semmle.code.cpp.security.Security
+import semmle.code.cpp.security.FlowSources
 import semmle.code.cpp.security.FunctionWithWrappers
-import semmle.code.cpp.ir.dataflow.internal.DefaultTaintTrackingImpl
+import semmle.code.cpp.ir.IR
-import TaintedWithPath
+import semmle.code.cpp.ir.dataflow.TaintTracking
+import SqlTainted::PathGraph
 
 class SqlLikeFunction extends FunctionWithWrappers {
   SqlLikeFunction() { sqlArgument(this.getName(), _) }
@@ -24,31 +26,43 @@ class SqlLikeFunction extends FunctionWithWrappers {
   override predicate interestingArg(int arg) { sqlArgument(this.getName(), arg) }
 }
 
-class Configuration extends TaintTrackingConfiguration {
+Expr asSinkExpr(DataFlow::Node node) {
-  override predicate isSink(Element tainted) {
+  result = node.asIndirectArgument()
-    exists(SqlLikeFunction runSql | runSql.outermostWrapperFunctionCall(tainted, _))
+  or
+  // We want the conversion so we only get one node for the expression
+  result = node.asConvertedExpr()
 }
 
-  override predicate isBarrier(Expr e) {
+module SqlTaintedConfig implements DataFlow::ConfigSig {
-    super.isBarrier(e)
+  predicate isSource(DataFlow::Node node) { node instanceof FlowSource }
-    or
+
-    e.getUnspecifiedType() instanceof IntegralType
+  predicate isSink(DataFlow::Node node) {
-    or
+    exists(SqlLikeFunction runSql | runSql.outermostWrapperFunctionCall(asSinkExpr(node), _))
+  }
+
+  predicate isBarrier(DataFlow::Node node) {
+    node.asExpr().getUnspecifiedType() instanceof IntegralType
+  }
+
+  predicate isBarrierIn(DataFlow::Node node) {
     exists(SqlBarrierFunction sql, int arg, FunctionInput input |
-      e = sql.getACallToThisFunction().getArgument(arg) and
+      node.asIndirectArgument() = sql.getACallToThisFunction().getArgument(arg) and
       input.isParameterDeref(arg) and
       sql.barrierSqlArgument(input, _)
     )
   }
 }
 
+module SqlTainted = TaintTracking::Global<SqlTaintedConfig>;
+
 from
-  SqlLikeFunction runSql, Expr taintedArg, Expr taintSource, PathNode sourceNode, PathNode sinkNode,
+  SqlLikeFunction runSql, Expr taintedArg, FlowSource taintSource, SqlTainted::PathNode sourceNode,
-  string taintCause, string callChain
+  SqlTainted::PathNode sinkNode, string callChain
 where
   runSql.outermostWrapperFunctionCall(taintedArg, callChain) and
-  taintedWithPath(taintSource, taintedArg, sourceNode, sinkNode) and
+  SqlTainted::flowPath(sourceNode, sinkNode) and
-  isUserInput(taintSource, taintCause)
+  taintedArg = asSinkExpr(sinkNode.getNode()) and
+  taintSource = sourceNode.getNode()
 select taintedArg, sourceNode, sinkNode,
   "This argument to a SQL query function is derived from $@ and then passed to " + callChain + ".",
-  taintSource, "user input (" + taintCause + ")"
+  taintSource, "user input (" + taintSource.getSourceType() + ")"

cpp/ql/src/change-notes/2023-08-24-no-taint-argv-indirections.md

@@ -0,0 +1,4 @@
+---
+category: minorAnalysis
+---
+* Some queries that had repeated results corresponding to different levels of indirection for `argv` now only have a single result.

cpp/ql/src/change-notes/2023-08-24-remove-non-constant-assign-sources.md

@@ -0,0 +1,4 @@
+---
+category: minorAnalysis
+---
+* The `cpp/non-constant-format` query no longer considers an assignment on the right-hand side of another assignment to be a source of non-constant format strings. As a result, the query may now produce fewer results.

cpp/ql/src/experimental/Security/CWE/CWE-078/WordexpTainted.ql

@@ -40,7 +40,7 @@ module WordexpTaintConfig implements DataFlow::ConfigSig {
 
   predicate isSink(DataFlow::Node sink) {
     exists(FunctionCall fc | fc.getTarget() instanceof WordexpFunction |
-      fc.getArgument(0) = sink.asExpr() and
+      fc.getArgument(0) = sink.asIndirectArgument(1) and
       not isCommandSubstitutionDisabled(fc)
     )
   }

cpp/ql/src/qlpack.yml

@@ -1,5 +1,5 @@
 name: codeql/cpp-queries
-version: 0.7.2
+version: 0.7.3-dev
 groups: 
   - cpp
   - queries

cpp/ql/test/experimental/query-tests/Security/CWE/CWE-078/WordexpTainted.expected

@@ -1,16 +1,8 @@
 edges
-| test.cpp:22:27:22:30 | argv | test.cpp:29:13:29:20 | filePath |
+| test.cpp:22:27:22:30 | argv indirection | test.cpp:29:13:29:20 | filePath indirection |
-| test.cpp:22:27:22:30 | argv | test.cpp:29:13:29:20 | filePath |
-| test.cpp:22:27:22:30 | argv indirection | test.cpp:29:13:29:20 | filePath |
-| test.cpp:22:27:22:30 | argv indirection | test.cpp:29:13:29:20 | filePath |
 nodes
-| test.cpp:22:27:22:30 | argv | semmle.label | argv |
 | test.cpp:22:27:22:30 | argv indirection | semmle.label | argv indirection |
-| test.cpp:29:13:29:20 | filePath | semmle.label | filePath |
+| test.cpp:29:13:29:20 | filePath indirection | semmle.label | filePath indirection |
-| test.cpp:29:13:29:20 | filePath | semmle.label | filePath |
 subpaths
 #select
-| test.cpp:29:13:29:20 | filePath | test.cpp:22:27:22:30 | argv | test.cpp:29:13:29:20 | filePath | Using user-supplied data in a `wordexp` command, without disabling command substitution, can make code vulnerable to command injection. |
+| test.cpp:29:13:29:20 | filePath indirection | test.cpp:22:27:22:30 | argv indirection | test.cpp:29:13:29:20 | filePath indirection | Using user-supplied data in a `wordexp` command, without disabling command substitution, can make code vulnerable to command injection. |
-| test.cpp:29:13:29:20 | filePath | test.cpp:22:27:22:30 | argv | test.cpp:29:13:29:20 | filePath | Using user-supplied data in a `wordexp` command, without disabling command substitution, can make code vulnerable to command injection. |
-| test.cpp:29:13:29:20 | filePath | test.cpp:22:27:22:30 | argv indirection | test.cpp:29:13:29:20 | filePath | Using user-supplied data in a `wordexp` command, without disabling command substitution, can make code vulnerable to command injection. |
-| test.cpp:29:13:29:20 | filePath | test.cpp:22:27:22:30 | argv indirection | test.cpp:29:13:29:20 | filePath | Using user-supplied data in a `wordexp` command, without disabling command substitution, can make code vulnerable to command injection. |

cpp/ql/test/experimental/query-tests/Security/CWE/CWE-193/constant-size/ConstantSizeArrayOffByOne.expected

@@ -69,12 +69,6 @@ edges
 | test.cpp:322:19:322:27 | ... + ... | test.cpp:325:24:325:26 | end |
 | test.cpp:324:23:324:26 | temp | test.cpp:324:23:324:32 | ... + ... |
 | test.cpp:324:23:324:32 | ... + ... | test.cpp:325:15:325:19 | temp2 |
-| test.cpp:351:9:351:11 | arr | test.cpp:351:9:351:14 | access to array |
-| test.cpp:351:9:351:11 | arr | test.cpp:351:18:351:25 | access to array |
-| test.cpp:351:18:351:20 | arr | test.cpp:351:9:351:14 | access to array |
-| test.cpp:351:18:351:20 | arr | test.cpp:351:18:351:25 | access to array |
-| test.cpp:351:29:351:31 | arr | test.cpp:351:9:351:14 | access to array |
-| test.cpp:351:29:351:31 | arr | test.cpp:351:18:351:25 | access to array |
 nodes
 | test.cpp:34:5:34:24 | access to array | semmle.label | access to array |
 | test.cpp:34:10:34:12 | buf | semmle.label | buf |
@@ -167,11 +161,6 @@ nodes
 | test.cpp:325:15:325:19 | temp2 | semmle.label | temp2 |
 | test.cpp:325:24:325:26 | end | semmle.label | end |
 | test.cpp:325:24:325:26 | end | semmle.label | end |
-| test.cpp:351:9:351:11 | arr | semmle.label | arr |
-| test.cpp:351:9:351:14 | access to array | semmle.label | access to array |
-| test.cpp:351:18:351:20 | arr | semmle.label | arr |
-| test.cpp:351:18:351:25 | access to array | semmle.label | access to array |
-| test.cpp:351:29:351:31 | arr | semmle.label | arr |
 subpaths
 #select
 | test.cpp:35:5:35:22 | PointerAdd: access to array | test.cpp:35:10:35:12 | buf | test.cpp:35:5:35:22 | access to array | This pointer arithmetic may have an off-by-1 error allowing it to overrun $@ at this $@. | test.cpp:15:9:15:11 | buf | buf | test.cpp:35:5:35:26 | Store: ... = ... | write |
@@ -194,6 +183,3 @@ subpaths
 | test.cpp:322:19:322:27 | PointerAdd: ... + ... | test.cpp:322:19:322:22 | temp | test.cpp:325:24:325:26 | end | This pointer arithmetic may have an off-by-1 error allowing it to overrun $@ at this $@. | test.cpp:314:10:314:13 | temp | temp | test.cpp:330:13:330:24 | Store: ... = ... | write |
 | test.cpp:322:19:322:27 | PointerAdd: ... + ... | test.cpp:322:19:322:22 | temp | test.cpp:325:24:325:26 | end | This pointer arithmetic may have an off-by-1 error allowing it to overrun $@ at this $@. | test.cpp:314:10:314:13 | temp | temp | test.cpp:331:13:331:24 | Store: ... = ... | write |
 | test.cpp:322:19:322:27 | PointerAdd: ... + ... | test.cpp:322:19:322:22 | temp | test.cpp:325:24:325:26 | end | This pointer arithmetic may have an off-by-1 error allowing it to overrun $@ at this $@. | test.cpp:314:10:314:13 | temp | temp | test.cpp:333:13:333:24 | Store: ... = ... | write |
-| test.cpp:351:18:351:25 | PointerAdd: access to array | test.cpp:351:9:351:11 | arr | test.cpp:351:18:351:25 | access to array | This pointer arithmetic may have an off-by-1 error allowing it to overrun $@ at this $@. | test.cpp:348:9:348:11 | arr | arr | test.cpp:351:18:351:25 | Load: access to array | read |
-| test.cpp:351:18:351:25 | PointerAdd: access to array | test.cpp:351:18:351:20 | arr | test.cpp:351:18:351:25 | access to array | This pointer arithmetic may have an off-by-1 error allowing it to overrun $@ at this $@. | test.cpp:348:9:348:11 | arr | arr | test.cpp:351:18:351:25 | Load: access to array | read |
-| test.cpp:351:18:351:25 | PointerAdd: access to array | test.cpp:351:29:351:31 | arr | test.cpp:351:18:351:25 | access to array | This pointer arithmetic may have an off-by-1 error allowing it to overrun $@ at this $@. | test.cpp:348:9:348:11 | arr | arr | test.cpp:351:18:351:25 | Load: access to array | read |

cpp/ql/test/experimental/query-tests/Security/CWE/CWE-193/constant-size/test.cpp

@@ -348,7 +348,7 @@ int positiveRange(int x) {
     int arr[128];
 
     for(int i=127-offset; i>= 0; i--) {
-        arr[i] = arr[i+1] + arr[i+offset]; // GOOD [FALSE POSITIVE]
+        arr[i] = arr[i+1] + arr[i+offset]; // GOOD
     }
     return arr[0];
 }

cpp/ql/test/experimental/query-tests/Security/CWE/CWE-193/pointer-deref/InvalidPointerDeref.expected

@@ -129,7 +129,6 @@ edges
 | test.cpp:271:14:271:21 | ... + ... | test.cpp:271:14:271:21 | ... + ... |
 | test.cpp:271:14:271:21 | ... + ... | test.cpp:274:5:274:10 | ... = ... |
 | test.cpp:271:14:271:21 | ... + ... | test.cpp:274:5:274:10 | ... = ... |
-| test.cpp:304:15:304:26 | new[] | test.cpp:308:5:308:29 | ... = ... |
 | test.cpp:355:14:355:27 | new[] | test.cpp:356:15:356:23 | ... + ... |
 | test.cpp:355:14:355:27 | new[] | test.cpp:356:15:356:23 | ... + ... |
 | test.cpp:355:14:355:27 | new[] | test.cpp:357:24:357:30 | ... + ... |
@@ -214,20 +213,26 @@ edges
 | test.cpp:543:14:543:27 | new[] | test.cpp:548:5:548:19 | ... = ... |
 | test.cpp:554:14:554:27 | new[] | test.cpp:559:5:559:19 | ... = ... |
 | test.cpp:642:14:642:31 | new[] | test.cpp:647:5:647:19 | ... = ... |
-| test.cpp:652:14:652:27 | new[] | test.cpp:656:3:656:6 | ... ++ |
-| test.cpp:652:14:652:27 | new[] | test.cpp:656:3:656:6 | ... ++ |
-| test.cpp:652:14:652:27 | new[] | test.cpp:662:3:662:11 | ... = ... |
-| test.cpp:656:3:656:6 | ... ++ | test.cpp:656:3:656:6 | ... ++ |
-| test.cpp:656:3:656:6 | ... ++ | test.cpp:662:3:662:11 | ... = ... |
-| test.cpp:656:3:656:6 | ... ++ | test.cpp:662:3:662:11 | ... = ... |
-| test.cpp:667:14:667:31 | new[] | test.cpp:675:7:675:23 | ... = ... |
 | test.cpp:695:13:695:26 | new[] | test.cpp:698:5:698:10 | ... += ... |
+| test.cpp:695:13:695:26 | new[] | test.cpp:698:5:698:10 | ... += ... |
+| test.cpp:698:5:698:10 | ... += ... | test.cpp:698:5:698:10 | ... += ... |
 | test.cpp:698:5:698:10 | ... += ... | test.cpp:701:15:701:16 | * ... |
 | test.cpp:705:18:705:18 | q | test.cpp:705:18:705:18 | q |
 | test.cpp:705:18:705:18 | q | test.cpp:706:12:706:13 | * ... |
 | test.cpp:705:18:705:18 | q | test.cpp:706:12:706:13 | * ... |
 | test.cpp:711:13:711:26 | new[] | test.cpp:714:11:714:11 | q |
 | test.cpp:714:11:714:11 | q | test.cpp:705:18:705:18 | q |
+| test.cpp:730:12:730:28 | new[] | test.cpp:732:16:732:26 | ... + ... |
+| test.cpp:730:12:730:28 | new[] | test.cpp:732:16:732:26 | ... + ... |
+| test.cpp:730:12:730:28 | new[] | test.cpp:733:5:733:12 | ... = ... |
+| test.cpp:732:16:732:26 | ... + ... | test.cpp:732:16:732:26 | ... + ... |
+| test.cpp:732:16:732:26 | ... + ... | test.cpp:733:5:733:12 | ... = ... |
+| test.cpp:732:16:732:26 | ... + ... | test.cpp:733:5:733:12 | ... = ... |
+| test.cpp:754:18:754:31 | new[] | test.cpp:767:16:767:29 | access to array |
+| test.cpp:754:18:754:31 | new[] | test.cpp:767:16:767:29 | access to array |
+| test.cpp:754:18:754:31 | new[] | test.cpp:772:16:772:29 | access to array |
+| test.cpp:754:18:754:31 | new[] | test.cpp:772:16:772:29 | access to array |
+| test.cpp:781:14:781:27 | new[] | test.cpp:786:18:786:27 | access to array |
 nodes
 | test.cpp:4:15:4:20 | call to malloc | semmle.label | call to malloc |
 | test.cpp:5:15:5:22 | ... + ... | semmle.label | ... + ... |
@@ -320,8 +325,6 @@ nodes
 | test.cpp:271:14:271:21 | ... + ... | semmle.label | ... + ... |
 | test.cpp:271:14:271:21 | ... + ... | semmle.label | ... + ... |
 | test.cpp:274:5:274:10 | ... = ... | semmle.label | ... = ... |
-| test.cpp:304:15:304:26 | new[] | semmle.label | new[] |
-| test.cpp:308:5:308:29 | ... = ... | semmle.label | ... = ... |
 | test.cpp:355:14:355:27 | new[] | semmle.label | new[] |
 | test.cpp:356:15:356:23 | ... + ... | semmle.label | ... + ... |
 | test.cpp:356:15:356:23 | ... + ... | semmle.label | ... + ... |
@@ -371,20 +374,26 @@ nodes
 | test.cpp:559:5:559:19 | ... = ... | semmle.label | ... = ... |
 | test.cpp:642:14:642:31 | new[] | semmle.label | new[] |
 | test.cpp:647:5:647:19 | ... = ... | semmle.label | ... = ... |
-| test.cpp:652:14:652:27 | new[] | semmle.label | new[] |
-| test.cpp:656:3:656:6 | ... ++ | semmle.label | ... ++ |
-| test.cpp:656:3:656:6 | ... ++ | semmle.label | ... ++ |
-| test.cpp:662:3:662:11 | ... = ... | semmle.label | ... = ... |
-| test.cpp:667:14:667:31 | new[] | semmle.label | new[] |
-| test.cpp:675:7:675:23 | ... = ... | semmle.label | ... = ... |
 | test.cpp:695:13:695:26 | new[] | semmle.label | new[] |
 | test.cpp:698:5:698:10 | ... += ... | semmle.label | ... += ... |
+| test.cpp:698:5:698:10 | ... += ... | semmle.label | ... += ... |
 | test.cpp:701:15:701:16 | * ... | semmle.label | * ... |
 | test.cpp:705:18:705:18 | q | semmle.label | q |
 | test.cpp:705:18:705:18 | q | semmle.label | q |
 | test.cpp:706:12:706:13 | * ... | semmle.label | * ... |
 | test.cpp:711:13:711:26 | new[] | semmle.label | new[] |
 | test.cpp:714:11:714:11 | q | semmle.label | q |
+| test.cpp:730:12:730:28 | new[] | semmle.label | new[] |
+| test.cpp:732:16:732:26 | ... + ... | semmle.label | ... + ... |
+| test.cpp:732:16:732:26 | ... + ... | semmle.label | ... + ... |
+| test.cpp:733:5:733:12 | ... = ... | semmle.label | ... = ... |
+| test.cpp:754:18:754:31 | new[] | semmle.label | new[] |
+| test.cpp:767:16:767:29 | access to array | semmle.label | access to array |
+| test.cpp:767:16:767:29 | access to array | semmle.label | access to array |
+| test.cpp:772:16:772:29 | access to array | semmle.label | access to array |
+| test.cpp:772:16:772:29 | access to array | semmle.label | access to array |
+| test.cpp:781:14:781:27 | new[] | semmle.label | new[] |
+| test.cpp:786:18:786:27 | access to array | semmle.label | access to array |
 subpaths
 #select
 | test.cpp:6:14:6:15 | * ... | test.cpp:4:15:4:20 | call to malloc | test.cpp:6:14:6:15 | * ... | This read might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:4:15:4:20 | call to malloc | call to malloc | test.cpp:5:19:5:22 | size | size |
@@ -406,7 +415,6 @@ subpaths
 | test.cpp:254:9:254:16 | ... = ... | test.cpp:248:24:248:30 | call to realloc | test.cpp:254:9:254:16 | ... = ... | This write might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:248:24:248:30 | call to realloc | call to realloc | test.cpp:254:11:254:11 | i | i |
 | test.cpp:264:13:264:14 | * ... | test.cpp:260:13:260:24 | new[] | test.cpp:264:13:264:14 | * ... | This read might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:260:13:260:24 | new[] | new[] | test.cpp:261:19:261:21 | len | len |
 | test.cpp:274:5:274:10 | ... = ... | test.cpp:270:13:270:24 | new[] | test.cpp:274:5:274:10 | ... = ... | This write might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:270:13:270:24 | new[] | new[] | test.cpp:271:19:271:21 | len | len |
-| test.cpp:308:5:308:29 | ... = ... | test.cpp:304:15:304:26 | new[] | test.cpp:308:5:308:29 | ... = ... | This write might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:304:15:304:26 | new[] | new[] | test.cpp:308:8:308:10 | ... + ... | ... + ... |
 | test.cpp:358:14:358:26 | * ... | test.cpp:355:14:355:27 | new[] | test.cpp:358:14:358:26 | * ... | This read might be out of bounds, as the pointer might be equal to $@ + $@ + 1. | test.cpp:355:14:355:27 | new[] | new[] | test.cpp:356:20:356:23 | size | size |
 | test.cpp:359:14:359:32 | * ... | test.cpp:355:14:355:27 | new[] | test.cpp:359:14:359:32 | * ... | This read might be out of bounds, as the pointer might be equal to $@ + $@ + 2. | test.cpp:355:14:355:27 | new[] | new[] | test.cpp:356:20:356:23 | size | size |
 | test.cpp:384:13:384:16 | * ... | test.cpp:377:14:377:27 | new[] | test.cpp:384:13:384:16 | * ... | This read might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:377:14:377:27 | new[] | new[] | test.cpp:378:20:378:23 | size | size |
@@ -418,7 +426,11 @@ subpaths
 | test.cpp:548:5:548:19 | ... = ... | test.cpp:543:14:543:27 | new[] | test.cpp:548:5:548:19 | ... = ... | This write might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:543:14:543:27 | new[] | new[] | test.cpp:548:8:548:14 | src_pos | src_pos |
 | test.cpp:559:5:559:19 | ... = ... | test.cpp:554:14:554:27 | new[] | test.cpp:559:5:559:19 | ... = ... | This write might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:554:14:554:27 | new[] | new[] | test.cpp:559:8:559:14 | src_pos | src_pos |
 | test.cpp:647:5:647:19 | ... = ... | test.cpp:642:14:642:31 | new[] | test.cpp:647:5:647:19 | ... = ... | This write might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:642:14:642:31 | new[] | new[] | test.cpp:647:8:647:14 | src_pos | src_pos |
-| test.cpp:662:3:662:11 | ... = ... | test.cpp:652:14:652:27 | new[] | test.cpp:662:3:662:11 | ... = ... | This write might be out of bounds, as the pointer might be equal to $@ + $@ + 1. | test.cpp:652:14:652:27 | new[] | new[] | test.cpp:653:19:653:22 | size | size |
-| test.cpp:675:7:675:23 | ... = ... | test.cpp:667:14:667:31 | new[] | test.cpp:675:7:675:23 | ... = ... | This write might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:667:14:667:31 | new[] | new[] | test.cpp:675:10:675:18 | ... ++ | ... ++ |
 | test.cpp:701:15:701:16 | * ... | test.cpp:695:13:695:26 | new[] | test.cpp:701:15:701:16 | * ... | This read might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:695:13:695:26 | new[] | new[] | test.cpp:696:19:696:22 | size | size |
 | test.cpp:706:12:706:13 | * ... | test.cpp:711:13:711:26 | new[] | test.cpp:706:12:706:13 | * ... | This read might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:711:13:711:26 | new[] | new[] | test.cpp:712:19:712:22 | size | size |
+| test.cpp:733:5:733:12 | ... = ... | test.cpp:730:12:730:28 | new[] | test.cpp:733:5:733:12 | ... = ... | This write might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:730:12:730:28 | new[] | new[] | test.cpp:732:21:732:25 | ... + ... | ... + ... |
+| test.cpp:767:16:767:29 | access to array | test.cpp:754:18:754:31 | new[] | test.cpp:767:16:767:29 | access to array | This read might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:754:18:754:31 | new[] | new[] | test.cpp:767:22:767:28 | ... + ... | ... + ... |
+| test.cpp:767:16:767:29 | access to array | test.cpp:754:18:754:31 | new[] | test.cpp:767:16:767:29 | access to array | This read might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:754:18:754:31 | new[] | new[] | test.cpp:772:22:772:28 | ... + ... | ... + ... |
+| test.cpp:772:16:772:29 | access to array | test.cpp:754:18:754:31 | new[] | test.cpp:772:16:772:29 | access to array | This read might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:754:18:754:31 | new[] | new[] | test.cpp:767:22:767:28 | ... + ... | ... + ... |
+| test.cpp:772:16:772:29 | access to array | test.cpp:754:18:754:31 | new[] | test.cpp:772:16:772:29 | access to array | This read might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:754:18:754:31 | new[] | new[] | test.cpp:772:22:772:28 | ... + ... | ... + ... |
+| test.cpp:786:18:786:27 | access to array | test.cpp:781:14:781:27 | new[] | test.cpp:786:18:786:27 | access to array | This read might be out of bounds, as the pointer might be equal to $@ + $@. | test.cpp:781:14:781:27 | new[] | new[] | test.cpp:786:20:786:26 | ... + ... | ... + ... |

cpp/ql/test/experimental/query-tests/Security/CWE/CWE-193/pointer-deref/test.cpp

@@ -305,7 +305,7 @@ void test21() {
 
   for (int i = 0; i < n; i += 2) {
     xs[i] = test21_get(i); // GOOD
-    xs[i+1] = test21_get(i+1); // $ alloc=L304 alloc=L304-1 deref=L308 // GOOD [FALSE POSITIVE]
+    xs[i+1] = test21_get(i+1); // GOOD
   }
 }
 
@@ -659,7 +659,7 @@ void test32(unsigned size) {
   xs++;
   if (xs >= end)
     return;
-  xs[0] = 0; // $ deref=L656->L662+1 deref=L657->L662+1 GOOD [FALSE POSITIVE]
+  xs[0] = 0; // GOOD
 }
 
 void test33(unsigned size, unsigned src_pos)
@@ -672,7 +672,7 @@ void test33(unsigned size, unsigned src_pos)
   while (dst_pos < size - 1) {
     dst_pos++;
     if (true)
-      xs[dst_pos++] = 0; // $ alloc=L667+1 deref=L675 // GOOD [FALSE POSITIVE]
+      xs[dst_pos++] = 0; // GOOD
   }
 }
 
@@ -714,3 +714,77 @@ void test35(unsigned long size, char* q)
     deref(q);
   }
 }
+
+void test21_simple(bool b) {
+  int n = 0;
+  if (b) n = 2;
+
+  int* xs = new int[n];
+
+  for (int i = 0; i < n; i += 2) {
+    xs[i+1] = 0; // GOOD
+  }
+}
+
+void test36(unsigned size, unsigned n) {
+  int* p = new int[size + 2];
+  if(n < size + 1) {
+    int* end = p + (n + 2); // $ alloc=L730+2
+    *end = 0; // $ deref=L733 // BAD
+  }
+}
+
+void test37(unsigned long n)
+{
+  int *p = new int[n];
+  for (unsigned long i = n; i != 0u; i--)
+  {
+    p[n - i] = 0; // GOOD
+  }
+}
+
+unsigned get(char);
+void exit(int);
+
+void error(const char * msg) {
+  exit(1);
+}
+
+void test38(unsigned size) {
+  char * alloc = new char[size];
+
+  unsigned pos = 0;
+  while (pos < size) {
+    char kind = alloc[pos];
+    unsigned n = get(alloc[pos]);
+    if (pos + n >= size) {
+      error("");
+    }
+    switch (kind) {
+    case '0':
+      if (n != 1)
+        error("");
+      char x = alloc[pos + 1]; // $ alloc=L754 deref=L767 // GOOD [FALSE POSITIVE]
+      break;
+    case '1':
+      if (n != 2)
+        error("");
+      char a = alloc[pos + 1]; // $ alloc=L754 deref=L772 // GOOD [FALSE POSITIVE]
+      char b = alloc[pos + 2];
+      break;
+    }
+    pos += 1 + n;
+  }
+}
+
+void test38_simple(unsigned size, unsigned pos, unsigned numParams) {
+  char * p = new char[size];
+
+  if (pos < size) {
+    if (pos + numParams < size) {
+      if (numParams == 1) {
+        char x = p[pos + 1]; // $ alloc=L781 deref=L786 // GOOD [FALSE POSITIVE]
+      }
+    }
+  }
+}

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

@@ -732,7 +732,7 @@ void test_does_not_write_source_to_dereference()
 {
   int x;
   does_not_write_source_to_dereference(&x);
-  sink(x); // $ ast,ir=733:7 SPURIOUS: ast,ir=726:11
+  sink(x); // $ ast=733:7 ir SPURIOUS: ast=726:11
 }
 
 void sometimes_calls_sink_eq(int x, int n) {

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

@@ -134,7 +134,7 @@ void pointer_test() {
 	sink(*p3); // $ ast,ir
 
 	*p3 = 0;
-	sink(*p3); // $ SPURIOUS: ast,ir
+	sink(*p3); // $ SPURIOUS: ast
 }
 
 // --- return values ---

cpp/ql/test/library-tests/floats/float128/errors.expected

@@ -1,3 +0,0 @@
-| file://:0:0:0:0 | There was an error during this compilation |
-| float128.cpp:1:39:1:39 | 128-bit floating-point types are not supported in this configuration |
-| float128.cpp:2:30:2:30 | 128-bit floating-point types are not supported in this configuration |

cpp/ql/test/library-tests/floats/float128/errors.ql

@@ -1,4 +0,0 @@
-import cpp
-
-from Diagnostic d
-select d

cpp/ql/test/library-tests/floats/float128/float128.cpp

@@ -1,5 +1,5 @@
-typedef _Complex float __attribute__((mode(TC))) _Complex128; // [COMPILER ERROR AND ERROR-TYPE DUE TO __float128 BEING DISABLED]
+typedef _Complex float __attribute__((mode(TC))) _Complex128;
-typedef float __attribute__((mode(TF))) _Float128; // [COMPILER ERROR AND ERROR-TYPE DUE TO __float128 BEING DISABLED]
+typedef float __attribute__((mode(TF))) _Float128;
 
 int main() {
   __float128 f = 1.0f;
@@ -25,4 +25,3 @@ __float128 id(__float128 q)
 {
   return q;
 }
-// semmle-extractor-options: --expect_errors

cpp/ql/test/library-tests/floats/float128/usertypes.expected

@@ -1,5 +1,5 @@
-| float128.cpp:1:50:1:60 | _Complex128 | file://:0:0:0:0 | <error-type> |
+| float128.cpp:1:50:1:60 | _Complex128 | file://:0:0:0:0 | float __complex__ |
-| float128.cpp:2:41:2:49 | _Float128 | file://:0:0:0:0 | <error-type> |
+| float128.cpp:2:41:2:49 | _Float128 | file://:0:0:0:0 | __float128 |
 | float128.cpp:13:29:13:54 | __is_floating_point_helper<T> | float128.cpp:10:8:10:17 | false_type |
 | float128.cpp:14:19:14:51 | __is_floating_point_helper<float> | float128.cpp:11:8:11:16 | true_type |
 | float128.cpp:15:19:15:52 | __is_floating_point_helper<double> | float128.cpp:11:8:11:16 | true_type |

cpp/ql/test/library-tests/ir/ir/PrintAST.expected

@@ -1798,6 +1798,23 @@ ir.c:
 #   10|                 Type = [CTypedefType] MyCoords
 #   10|                 ValueCategory = lvalue
 #   11|     getStmt(3): [ReturnStmt] return ...
+#   13| [TopLevelFunction] void CStyleCast(void*)
+#   13|   <params>: 
+#   13|     getParameter(0): [Parameter] src
+#   13|         Type = [VoidPointerType] void *
+#   14|   getEntryPoint(): [BlockStmt] { ... }
+#   15|     getStmt(0): [DeclStmt] declaration
+#   15|       getDeclarationEntry(0): [VariableDeclarationEntry] definition of dst
+#   15|           Type = [CharPointerType] char *
+#   15|         getVariable().getInitializer(): [Initializer] initializer for dst
+#   15|           getExpr(): [VariableAccess] src
+#   15|               Type = [VoidPointerType] void *
+#   15|               ValueCategory = prvalue(load)
+#   15|           getExpr().getFullyConverted(): [CStyleCast] (char *)...
+#   15|               Conversion = [PointerConversion] pointer conversion
+#   15|               Type = [CharPointerType] char *
+#   15|               ValueCategory = prvalue
+#   16|     getStmt(1): [ReturnStmt] return ...
 ir.cpp:
 #    1| [TopLevelFunction] void Constants()
 #    1|   <params>: 

cpp/ql/test/library-tests/ir/ir/ir.c

@@ -9,3 +9,10 @@ void MyCoordsTest(int pos) {
   coords.x = coords.y = pos + 1;
   coords.x = getX(&coords);
 }
+
+void CStyleCast(void *src)
+{
+    char *dst = (char*)src;
+}
+
+// semmle-extractor-options: --microsoft

cpp/ql/test/library-tests/ir/ir/operand_locations.expected

@@ -978,6 +978,20 @@
 | ir.c:10:19:10:25 | ChiTotal | total:m9_13 |
 | ir.c:10:19:10:25 | SideEffect | ~m9_13 |
 | ir.c:10:20:10:25 | Unary | r10_2 |
+| ir.c:13:6:13:15 | ChiPartial | partial:m13_3 |
+| ir.c:13:6:13:15 | ChiTotal | total:m13_2 |
+| ir.c:13:6:13:15 | SideEffect | m13_3 |
+| ir.c:13:23:13:25 | Address | &:r13_5 |
+| ir.c:13:23:13:25 | Address | &:r13_5 |
+| ir.c:13:23:13:25 | Address | &:r13_7 |
+| ir.c:13:23:13:25 | Address | &:r13_7 |
+| ir.c:13:23:13:25 | Load | m13_6 |
+| ir.c:13:23:13:25 | SideEffect | m13_8 |
+| ir.c:15:11:15:13 | Address | &:r15_1 |
+| ir.c:15:17:15:26 | StoreValue | r15_4 |
+| ir.c:15:24:15:26 | Address | &:r15_2 |
+| ir.c:15:24:15:26 | Load | m13_6 |
+| ir.c:15:24:15:26 | Unary | r15_3 |
 | ir.cpp:1:6:1:14 | ChiPartial | partial:m1_3 |
 | ir.cpp:1:6:1:14 | ChiTotal | total:m1_2 |
 | ir.cpp:1:6:1:14 | SideEffect | m1_3 |

cpp/ql/test/library-tests/ir/ir/raw_ir.expected

@@ -766,6 +766,26 @@ ir.c:
 #    7|     v7_7(void)                                 = AliasedUse                   : ~m?
 #    7|     v7_8(void)                                 = ExitFunction                 : 
 
+#   13| void CStyleCast(void*)
+#   13|   Block 0
+#   13|     v13_1(void)          = EnterFunction              : 
+#   13|     mu13_2(unknown)      = AliasedDefinition          : 
+#   13|     mu13_3(unknown)      = InitializeNonLocal         : 
+#   13|     r13_4(glval<void *>) = VariableAddress[src]       : 
+#   13|     mu13_5(void *)       = InitializeParameter[src]   : &:r13_4
+#   13|     r13_6(void *)        = Load[src]                  : &:r13_4, ~m?
+#   13|     mu13_7(unknown)      = InitializeIndirection[src] : &:r13_6
+#   15|     r15_1(glval<char *>) = VariableAddress[dst]       : 
+#   15|     r15_2(glval<void *>) = VariableAddress[src]       : 
+#   15|     r15_3(void *)        = Load[src]                  : &:r15_2, ~m?
+#   15|     r15_4(char *)        = Convert                    : r15_3
+#   15|     mu15_5(char *)       = Store[dst]                 : &:r15_1, r15_4
+#   16|     v16_1(void)          = NoOp                       : 
+#   13|     v13_8(void)          = ReturnIndirection[src]     : &:r13_6, ~m?
+#   13|     v13_9(void)          = ReturnVoid                 : 
+#   13|     v13_10(void)         = AliasedUse                 : ~m?
+#   13|     v13_11(void)         = ExitFunction               : 
+
 ir.cpp:
 #    1| void Constants()
 #    1|   Block 0

cpp/ql/test/library-tests/ir/range-analysis/test.cpp

@@ -95,3 +95,25 @@ void gotoLoop(bool b1, bool b2)
     }
   }
 }
+
+void test_sub(int x, int y, int n) {
+  if(x > 0 && x < 500) {
+    if(y > 0 && y < 10) {
+      range(x - y); // $ range=<=498 range=>=-8
+    }
+
+    if(n > 0 && n < 100) {
+      for (int i = 0; i < n; i++)
+      {
+        range(n - i); // $ range=">=Phi: i-97" range=<=99 range=>=-97
+        range(i - n); // $ range="<=Phi: i-1" range=">=Phi: i-99" range=<=97 range=>=-99 
+      }
+
+      for (int i = n; i != 0; i--)
+      {
+        range(n - i); // $ SPURIOUS: overflow=+
+        range(i - n); // $ range=">=Phi: i-99"
+      }
+    }
+  }
+}

cpp/ql/test/query-tests/Likely Bugs/Format/NonConstantFormat/test.cpp

@@ -156,3 +156,10 @@ void fmt_via_strcpy(char *data) {
     strcpy(data, "some string");
     printf(data); // BAD
 }
+
+void fmt_with_assignment() {
+  const char *x, *y;
+
+  x = y = "a";
+  printf(y); // GOOD
+}

cpp/ql/test/query-tests/Security/CWE/CWE-022/semmle/tests/TaintedPath.expected

@@ -1,16 +1,10 @@
 edges
-| test.c:8:27:8:30 | argv | test.c:17:11:17:18 | fileName indirection |
-| test.c:8:27:8:30 | argv indirection | test.c:17:11:17:18 | fileName indirection |
 | test.c:8:27:8:30 | argv indirection | test.c:17:11:17:18 | fileName indirection |
 | test.c:8:27:8:30 | argv indirection | test.c:32:11:32:18 | fileName indirection |
-| test.c:8:27:8:30 | argv indirection | test.c:32:11:32:18 | fileName indirection |
-| test.c:8:27:8:30 | argv indirection | test.c:57:10:57:16 | access to array indirection |
 | test.c:8:27:8:30 | argv indirection | test.c:57:10:57:16 | access to array indirection |
 | test.c:37:17:37:24 | scanf output argument | test.c:38:11:38:18 | fileName indirection |
 | test.c:43:17:43:24 | scanf output argument | test.c:44:11:44:18 | fileName indirection |
 nodes
-| test.c:8:27:8:30 | argv | semmle.label | argv |
-| test.c:8:27:8:30 | argv indirection | semmle.label | argv indirection |
 | test.c:8:27:8:30 | argv indirection | semmle.label | argv indirection |
 | test.c:17:11:17:18 | fileName indirection | semmle.label | fileName indirection |
 | test.c:32:11:32:18 | fileName indirection | semmle.label | fileName indirection |
@@ -21,12 +15,8 @@ nodes
 | test.c:57:10:57:16 | access to array indirection | semmle.label | access to array indirection |
 subpaths
 #select
-| test.c:17:11:17:18 | fileName | test.c:8:27:8:30 | argv | test.c:17:11:17:18 | fileName indirection | This argument to a file access function is derived from $@ and then passed to fopen(filename). | test.c:8:27:8:30 | argv | user input (a command-line argument) |
 | test.c:17:11:17:18 | fileName | test.c:8:27:8:30 | argv indirection | test.c:17:11:17:18 | fileName indirection | This argument to a file access function is derived from $@ and then passed to fopen(filename). | test.c:8:27:8:30 | argv indirection | user input (a command-line argument) |
-| test.c:17:11:17:18 | fileName | test.c:8:27:8:30 | argv indirection | test.c:17:11:17:18 | fileName indirection | This argument to a file access function is derived from $@ and then passed to fopen(filename). | test.c:8:27:8:30 | argv indirection | user input (a command-line argument) |
-| test.c:32:11:32:18 | fileName | test.c:8:27:8:30 | argv indirection | test.c:32:11:32:18 | fileName indirection | This argument to a file access function is derived from $@ and then passed to fopen(filename). | test.c:8:27:8:30 | argv indirection | user input (a command-line argument) |
 | test.c:32:11:32:18 | fileName | test.c:8:27:8:30 | argv indirection | test.c:32:11:32:18 | fileName indirection | This argument to a file access function is derived from $@ and then passed to fopen(filename). | test.c:8:27:8:30 | argv indirection | user input (a command-line argument) |
 | test.c:38:11:38:18 | fileName | test.c:37:17:37:24 | scanf output argument | test.c:38:11:38:18 | fileName indirection | This argument to a file access function is derived from $@ and then passed to fopen(filename). | test.c:37:17:37:24 | scanf output argument | user input (value read by scanf) |
 | test.c:44:11:44:18 | fileName | test.c:43:17:43:24 | scanf output argument | test.c:44:11:44:18 | fileName indirection | This argument to a file access function is derived from $@ and then passed to fopen(filename). | test.c:43:17:43:24 | scanf output argument | user input (value read by scanf) |
 | test.c:57:10:57:16 | access to array | test.c:8:27:8:30 | argv indirection | test.c:57:10:57:16 | access to array indirection | This argument to a file access function is derived from $@ and then passed to read(fileName), which calls fopen(filename). | test.c:8:27:8:30 | argv indirection | user input (a command-line argument) |
-| test.c:57:10:57:16 | access to array | test.c:8:27:8:30 | argv indirection | test.c:57:10:57:16 | access to array indirection | This argument to a file access function is derived from $@ and then passed to read(fileName), which calls fopen(filename). | test.c:8:27:8:30 | argv indirection | user input (a command-line argument) |

cpp/ql/test/query-tests/Security/CWE/CWE-078/semmle/ExecTainted/ExecTainted.expected

@@ -1,6 +1,5 @@
 edges
 | test.cpp:15:27:15:30 | argv indirection | test.cpp:22:45:22:52 | userName indirection |
-| test.cpp:15:27:15:30 | argv indirection | test.cpp:22:45:22:52 | userName indirection |
 | test.cpp:22:13:22:20 | sprintf output argument | test.cpp:23:12:23:19 | command1 indirection |
 | test.cpp:22:45:22:52 | userName indirection | test.cpp:22:13:22:20 | sprintf output argument |
 | test.cpp:47:21:47:26 | call to getenv indirection | test.cpp:50:35:50:43 | envCflags indirection |
@@ -71,7 +70,6 @@ edges
 | test.cpp:220:19:220:26 | filename indirection | test.cpp:220:19:220:26 | filename indirection |
 nodes
 | test.cpp:15:27:15:30 | argv indirection | semmle.label | argv indirection |
-| test.cpp:15:27:15:30 | argv indirection | semmle.label | argv indirection |
 | test.cpp:22:13:22:20 | sprintf output argument | semmle.label | sprintf output argument |
 | test.cpp:22:45:22:52 | userName indirection | semmle.label | userName indirection |
 | test.cpp:23:12:23:19 | command1 indirection | semmle.label | command1 indirection |
@@ -154,7 +152,6 @@ subpaths
 | test.cpp:196:26:196:33 | filename indirection | test.cpp:186:47:186:54 | filename indirection | test.cpp:188:11:188:17 | strncat output argument | test.cpp:196:10:196:16 | concat output argument |
 #select
 | test.cpp:23:12:23:19 | command1 | test.cpp:15:27:15:30 | argv indirection | test.cpp:23:12:23:19 | command1 indirection | This argument to an OS command is derived from $@, dangerously concatenated into $@, and then passed to system(string). | test.cpp:15:27:15:30 | argv indirection | user input (a command-line argument) | test.cpp:22:13:22:20 | sprintf output argument | sprintf output argument |
-| test.cpp:23:12:23:19 | command1 | test.cpp:15:27:15:30 | argv indirection | test.cpp:23:12:23:19 | command1 indirection | This argument to an OS command is derived from $@, dangerously concatenated into $@, and then passed to system(string). | test.cpp:15:27:15:30 | argv indirection | user input (a command-line argument) | test.cpp:22:13:22:20 | sprintf output argument | sprintf output argument |
 | test.cpp:51:10:51:16 | command | test.cpp:47:21:47:26 | call to getenv indirection | test.cpp:51:10:51:16 | command indirection | This argument to an OS command is derived from $@, dangerously concatenated into $@, and then passed to system(string). | test.cpp:47:21:47:26 | call to getenv indirection | user input (an environment variable) | test.cpp:50:11:50:17 | sprintf output argument | sprintf output argument |
 | test.cpp:65:10:65:16 | command | test.cpp:62:9:62:16 | fread output argument | test.cpp:65:10:65:16 | command indirection | This argument to an OS command is derived from $@, dangerously concatenated into $@, and then passed to system(string). | test.cpp:62:9:62:16 | fread output argument | user input (string read by fread) | test.cpp:64:11:64:17 | strncat output argument | strncat output argument |
 | test.cpp:85:32:85:38 | command | test.cpp:82:9:82:16 | fread output argument | test.cpp:85:32:85:38 | command indirection | This argument to an OS command is derived from $@, dangerously concatenated into $@, and then passed to execl. | test.cpp:82:9:82:16 | fread output argument | user input (string read by fread) | test.cpp:84:11:84:17 | strncat output argument | strncat output argument |

cpp/ql/test/query-tests/Security/CWE/CWE-089/SqlTainted/SqlTainted.expected

@@ -1,25 +1,12 @@
 edges
-| test.c:15:20:15:23 | argv | test.c:21:18:21:23 | query1 |
+| test.c:14:27:14:30 | argv indirection | test.c:21:18:21:23 | query1 indirection |
-| test.c:15:20:15:23 | argv | test.c:21:18:21:23 | query1 |
+| test.cpp:39:27:39:30 | argv indirection | test.cpp:43:27:43:33 | access to array indirection |
-| test.c:15:20:15:23 | argv | test.c:21:18:21:23 | query1 |
-| test.c:15:20:15:23 | argv | test.c:21:18:21:23 | query1 |
-| test.cpp:43:27:43:30 | argv | test.cpp:43:27:43:33 | access to array |
-| test.cpp:43:27:43:30 | argv | test.cpp:43:27:43:33 | access to array |
-| test.cpp:43:27:43:30 | argv | test.cpp:43:27:43:33 | access to array |
-| test.cpp:43:27:43:30 | argv | test.cpp:43:27:43:33 | access to array |
-| test.cpp:43:27:43:30 | argv | test.cpp:43:27:43:33 | access to array |
-| test.cpp:43:27:43:30 | argv | test.cpp:43:27:43:33 | access to array |
-subpaths
 nodes
-| test.c:15:20:15:23 | argv | semmle.label | argv |
+| test.c:14:27:14:30 | argv indirection | semmle.label | argv indirection |
-| test.c:15:20:15:23 | argv | semmle.label | argv |
+| test.c:21:18:21:23 | query1 indirection | semmle.label | query1 indirection |
-| test.c:21:18:21:23 | query1 | semmle.label | query1 |
+| test.cpp:39:27:39:30 | argv indirection | semmle.label | argv indirection |
-| test.c:21:18:21:23 | query1 | semmle.label | query1 |
+| test.cpp:43:27:43:33 | access to array indirection | semmle.label | access to array indirection |
-| test.cpp:43:27:43:30 | argv | semmle.label | argv |
+subpaths
-| test.cpp:43:27:43:30 | argv | semmle.label | argv |
-| test.cpp:43:27:43:33 | access to array | semmle.label | access to array |
-| test.cpp:43:27:43:33 | access to array | semmle.label | access to array |
-| test.cpp:43:27:43:33 | access to array | semmle.label | access to array |
 #select
-| test.c:21:18:21:23 | query1 | test.c:15:20:15:23 | argv | test.c:21:18:21:23 | query1 | This argument to a SQL query function is derived from $@ and then passed to mysql_query(sqlArg). | test.c:15:20:15:23 | argv | user input (argv) |
+| test.c:21:18:21:23 | query1 | test.c:14:27:14:30 | argv indirection | test.c:21:18:21:23 | query1 indirection | This argument to a SQL query function is derived from $@ and then passed to mysql_query(sqlArg). | test.c:14:27:14:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:43:27:43:33 | access to array | test.cpp:43:27:43:30 | argv | test.cpp:43:27:43:33 | access to array | This argument to a SQL query function is derived from $@ and then passed to pqxx::work::exec1((unnamed parameter 0)). | test.cpp:43:27:43:30 | argv | user input (argv) |
+| test.cpp:43:27:43:33 | access to array | test.cpp:39:27:39:30 | argv indirection | test.cpp:43:27:43:33 | access to array indirection | This argument to a SQL query function is derived from $@ and then passed to pqxx::work::exec1((unnamed parameter 0)). | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |

cpp/ql/test/query-tests/Security/CWE/CWE-119/semmle/tests/OverflowDestination.expected

@@ -1,10 +1,6 @@
 edges
 | main.cpp:6:27:6:30 | argv indirection | main.cpp:7:33:7:36 | argv indirection |
-| main.cpp:6:27:6:30 | argv indirection | main.cpp:7:33:7:36 | argv indirection |
 | main.cpp:7:33:7:36 | argv indirection | overflowdestination.cpp:23:45:23:48 | argv indirection |
-| main.cpp:7:33:7:36 | argv indirection | overflowdestination.cpp:23:45:23:48 | argv indirection |
-| overflowdestination.cpp:23:45:23:48 | argv indirection | overflowdestination.cpp:30:17:30:20 | arg1 indirection |
-| overflowdestination.cpp:23:45:23:48 | argv indirection | overflowdestination.cpp:30:17:30:20 | arg1 indirection |
 | overflowdestination.cpp:23:45:23:48 | argv indirection | overflowdestination.cpp:30:17:30:20 | arg1 indirection |
 | overflowdestination.cpp:23:45:23:48 | argv indirection | overflowdestination.cpp:30:17:30:20 | arg1 indirection |
 | overflowdestination.cpp:43:8:43:10 | fgets output argument | overflowdestination.cpp:46:15:46:17 | src indirection |
@@ -24,10 +20,7 @@ edges
 | overflowdestination.cpp:76:30:76:32 | src indirection | overflowdestination.cpp:57:52:57:54 | src indirection |
 nodes
 | main.cpp:6:27:6:30 | argv indirection | semmle.label | argv indirection |
-| main.cpp:6:27:6:30 | argv indirection | semmle.label | argv indirection |
 | main.cpp:7:33:7:36 | argv indirection | semmle.label | argv indirection |
-| main.cpp:7:33:7:36 | argv indirection | semmle.label | argv indirection |
-| overflowdestination.cpp:23:45:23:48 | argv indirection | semmle.label | argv indirection |
 | overflowdestination.cpp:23:45:23:48 | argv indirection | semmle.label | argv indirection |
 | overflowdestination.cpp:30:17:30:20 | arg1 indirection | semmle.label | arg1 indirection |
 | overflowdestination.cpp:30:17:30:20 | arg1 indirection | semmle.label | arg1 indirection |
@@ -51,8 +44,6 @@ subpaths
 #select
 | overflowdestination.cpp:30:2:30:8 | call to strncpy | main.cpp:6:27:6:30 | argv indirection | overflowdestination.cpp:30:17:30:20 | arg1 indirection | To avoid overflow, this operation should be bounded by destination-buffer size, not source-buffer size. |
 | overflowdestination.cpp:30:2:30:8 | call to strncpy | main.cpp:6:27:6:30 | argv indirection | overflowdestination.cpp:30:17:30:20 | arg1 indirection | To avoid overflow, this operation should be bounded by destination-buffer size, not source-buffer size. |
-| overflowdestination.cpp:30:2:30:8 | call to strncpy | main.cpp:6:27:6:30 | argv indirection | overflowdestination.cpp:30:17:30:20 | arg1 indirection | To avoid overflow, this operation should be bounded by destination-buffer size, not source-buffer size. |
-| overflowdestination.cpp:30:2:30:8 | call to strncpy | main.cpp:6:27:6:30 | argv indirection | overflowdestination.cpp:30:17:30:20 | arg1 indirection | To avoid overflow, this operation should be bounded by destination-buffer size, not source-buffer size. |
 | overflowdestination.cpp:46:2:46:7 | call to memcpy | overflowdestination.cpp:43:8:43:10 | fgets output argument | overflowdestination.cpp:46:15:46:17 | src indirection | To avoid overflow, this operation should be bounded by destination-buffer size, not source-buffer size. |
 | overflowdestination.cpp:53:2:53:7 | call to memcpy | overflowdestination.cpp:73:8:73:10 | fgets output argument | overflowdestination.cpp:53:15:53:17 | src indirection | To avoid overflow, this operation should be bounded by destination-buffer size, not source-buffer size. |
 | overflowdestination.cpp:53:2:53:7 | call to memcpy | overflowdestination.cpp:73:8:73:10 | fgets output argument | overflowdestination.cpp:53:15:53:17 | src indirection | To avoid overflow, this operation should be bounded by destination-buffer size, not source-buffer size. |

cpp/ql/test/query-tests/Security/CWE/CWE-120/semmle/tests/BadlyBoundedWrite.expected

@@ -1,2 +1,6 @@
+| tests2.cpp:59:3:59:10 | call to snprintf | This 'call to snprintf' operation is limited to 13 bytes but the destination is only 0 bytes. |
+| tests2.cpp:59:3:59:10 | call to snprintf | This 'call to snprintf' operation is limited to 13 bytes but the destination is only 2 bytes. |
+| tests2.cpp:63:3:63:10 | call to snprintf | This 'call to snprintf' operation is limited to 13 bytes but the destination is only 0 bytes. |
+| tests2.cpp:63:3:63:10 | call to snprintf | This 'call to snprintf' operation is limited to 13 bytes but the destination is only 3 bytes. |
 | tests.c:43:3:43:10 | call to snprintf | This 'call to snprintf' operation is limited to 111 bytes but the destination is only 110 bytes. |
 | tests.c:46:3:46:10 | call to snprintf | This 'call to snprintf' operation is limited to 111 bytes but the destination is only 110 bytes. |

cpp/ql/test/query-tests/Security/CWE/CWE-120/semmle/tests/VeryLikelyOverrunWrite.expected

@@ -1,10 +1,10 @@
-| tests2.cpp:17:3:17:8 | call to wcscpy | This 'call to wcscpy' operation requires 12 bytes but the destination is only 8 bytes. |
+| tests2.cpp:18:3:18:8 | call to wcscpy | This 'call to wcscpy' operation requires 12 bytes but the destination is only 8 bytes. |
-| tests2.cpp:22:3:22:8 | call to wcscpy | This 'call to wcscpy' operation requires 16 bytes but the destination is only 12 bytes. |
+| tests2.cpp:23:3:23:8 | call to wcscpy | This 'call to wcscpy' operation requires 16 bytes but the destination is only 12 bytes. |
-| tests2.cpp:27:3:27:8 | call to wcscpy | This 'call to wcscpy' operation requires 20 bytes but the destination is only 16 bytes. |
+| tests2.cpp:28:3:28:8 | call to wcscpy | This 'call to wcscpy' operation requires 20 bytes but the destination is only 16 bytes. |
-| tests2.cpp:31:3:31:8 | call to wcscpy | This 'call to wcscpy' operation requires 24 bytes but the destination is only 20 bytes. |
+| tests2.cpp:32:3:32:8 | call to wcscpy | This 'call to wcscpy' operation requires 24 bytes but the destination is only 20 bytes. |
-| tests2.cpp:36:3:36:8 | call to wcscpy | This 'call to wcscpy' operation requires 28 bytes but the destination is only 24 bytes. |
+| tests2.cpp:37:3:37:8 | call to wcscpy | This 'call to wcscpy' operation requires 28 bytes but the destination is only 24 bytes. |
-| tests2.cpp:41:3:41:8 | call to wcscpy | This 'call to wcscpy' operation requires 32 bytes but the destination is only 28 bytes. |
+| tests2.cpp:42:3:42:8 | call to wcscpy | This 'call to wcscpy' operation requires 32 bytes but the destination is only 28 bytes. |
-| tests2.cpp:46:3:46:8 | call to wcscpy | This 'call to wcscpy' operation requires 36 bytes but the destination is only 32 bytes. |
+| tests2.cpp:47:3:47:8 | call to wcscpy | This 'call to wcscpy' operation requires 36 bytes but the destination is only 32 bytes. |
 | tests.c:54:3:54:9 | call to sprintf | This 'call to sprintf' operation requires 11 bytes but the destination is only 10 bytes. |
 | tests.c:58:3:58:9 | call to sprintf | This 'call to sprintf' operation requires 11 bytes but the destination is only 10 bytes. |
 | tests.c:62:17:62:24 | buffer10 | This 'scanf string argument' operation requires 11 bytes but the destination is only 10 bytes. |

cpp/ql/test/query-tests/Security/CWE/CWE-120/semmle/tests/tests2.cpp

@@ -6,6 +6,7 @@ void *realloc(void *ptr, size_t size);
 void *calloc(size_t nmemb, size_t size); 
 void free(void *ptr);
 wchar_t *wcscpy(wchar_t *s1, const wchar_t *s2); 
+int snprintf(char *s, size_t n, const char *format, ...);
 
 // --- Semmle tests ---
 
@@ -46,3 +47,18 @@ void tests2() {
   wcscpy(buffer, L"12345678"); // BAD: buffer overflow
   delete [] buffer;
 }
+
+char* dest1 = "a";
+char* dest2 = "abcdefghijklmnopqrstuvwxyz";
+
+void test3() {
+  const char src[] = "abcdefghijkl";
+  dest1 = (char*)malloc(sizeof(src));
+  if (!dest1)
+    return;
+  snprintf(dest1, sizeof(src), "%s", src); // GOOD [FALSE POSITIVE]
+  dest2 = (char*)malloc(3);
+  if (!dest2)
+    return;
+  snprintf(dest2, sizeof(src), "%s", src); // BAD (but with duplicate alerts)
+}

cpp/ql/test/query-tests/Security/CWE/CWE-129/semmle/ImproperArrayIndexValidation/ImproperArrayIndexValidation.expected

@@ -1,12 +1,6 @@
 edges
-| test1.c:7:26:7:29 | argv | test1.c:9:9:9:9 | i |
-| test1.c:7:26:7:29 | argv | test1.c:11:9:11:9 | i |
-| test1.c:7:26:7:29 | argv | test1.c:13:9:13:9 | i |
-| test1.c:7:26:7:29 | argv indirection | test1.c:9:9:9:9 | i |
 | test1.c:7:26:7:29 | argv indirection | test1.c:9:9:9:9 | i |
 | test1.c:7:26:7:29 | argv indirection | test1.c:11:9:11:9 | i |
-| test1.c:7:26:7:29 | argv indirection | test1.c:11:9:11:9 | i |
-| test1.c:7:26:7:29 | argv indirection | test1.c:13:9:13:9 | i |
 | test1.c:7:26:7:29 | argv indirection | test1.c:13:9:13:9 | i |
 | test1.c:9:9:9:9 | i | test1.c:16:16:16:16 | i |
 | test1.c:11:9:11:9 | i | test1.c:32:16:32:16 | i |
@@ -15,8 +9,6 @@ edges
 | test1.c:32:16:32:16 | i | test1.c:33:11:33:11 | i |
 | test1.c:48:16:48:16 | i | test1.c:53:15:53:15 | j |
 nodes
-| test1.c:7:26:7:29 | argv | semmle.label | argv |
-| test1.c:7:26:7:29 | argv indirection | semmle.label | argv indirection |
 | test1.c:7:26:7:29 | argv indirection | semmle.label | argv indirection |
 | test1.c:9:9:9:9 | i | semmle.label | i |
 | test1.c:11:9:11:9 | i | semmle.label | i |
@@ -29,12 +21,6 @@ nodes
 | test1.c:53:15:53:15 | j | semmle.label | j |
 subpaths
 #select
-| test1.c:18:16:18:16 | i | test1.c:7:26:7:29 | argv | test1.c:18:16:18:16 | i | An array indexing expression depends on $@ that might be outside the bounds of the array. | test1.c:7:26:7:29 | argv | a command-line argument |
 | test1.c:18:16:18:16 | i | test1.c:7:26:7:29 | argv indirection | test1.c:18:16:18:16 | i | An array indexing expression depends on $@ that might be outside the bounds of the array. | test1.c:7:26:7:29 | argv indirection | a command-line argument |
-| test1.c:18:16:18:16 | i | test1.c:7:26:7:29 | argv indirection | test1.c:18:16:18:16 | i | An array indexing expression depends on $@ that might be outside the bounds of the array. | test1.c:7:26:7:29 | argv indirection | a command-line argument |
-| test1.c:33:11:33:11 | i | test1.c:7:26:7:29 | argv | test1.c:33:11:33:11 | i | An array indexing expression depends on $@ that might be outside the bounds of the array. | test1.c:7:26:7:29 | argv | a command-line argument |
 | test1.c:33:11:33:11 | i | test1.c:7:26:7:29 | argv indirection | test1.c:33:11:33:11 | i | An array indexing expression depends on $@ that might be outside the bounds of the array. | test1.c:7:26:7:29 | argv indirection | a command-line argument |
-| test1.c:33:11:33:11 | i | test1.c:7:26:7:29 | argv indirection | test1.c:33:11:33:11 | i | An array indexing expression depends on $@ that might be outside the bounds of the array. | test1.c:7:26:7:29 | argv indirection | a command-line argument |
-| test1.c:53:15:53:15 | j | test1.c:7:26:7:29 | argv | test1.c:53:15:53:15 | j | An array indexing expression depends on $@ that might be outside the bounds of the array. | test1.c:7:26:7:29 | argv | a command-line argument |
-| test1.c:53:15:53:15 | j | test1.c:7:26:7:29 | argv indirection | test1.c:53:15:53:15 | j | An array indexing expression depends on $@ that might be outside the bounds of the array. | test1.c:7:26:7:29 | argv indirection | a command-line argument |
 | test1.c:53:15:53:15 | j | test1.c:7:26:7:29 | argv indirection | test1.c:53:15:53:15 | j | An array indexing expression depends on $@ that might be outside the bounds of the array. | test1.c:7:26:7:29 | argv indirection | a command-line argument |

cpp/ql/test/query-tests/Security/CWE/CWE-190/semmle/TaintedAllocationSize/TaintedAllocationSize.expected

@@ -1,21 +1,9 @@
 edges
-| test.cpp:39:27:39:30 | argv | test.cpp:43:38:43:44 | tainted |
-| test.cpp:39:27:39:30 | argv | test.cpp:44:38:44:63 | ... * ... |
-| test.cpp:39:27:39:30 | argv | test.cpp:46:38:46:63 | ... + ... |
-| test.cpp:39:27:39:30 | argv | test.cpp:49:32:49:35 | size |
-| test.cpp:39:27:39:30 | argv | test.cpp:50:26:50:29 | size |
-| test.cpp:39:27:39:30 | argv | test.cpp:53:35:53:60 | ... * ... |
-| test.cpp:39:27:39:30 | argv indirection | test.cpp:43:38:43:44 | tainted |
 | test.cpp:39:27:39:30 | argv indirection | test.cpp:43:38:43:44 | tainted |
 | test.cpp:39:27:39:30 | argv indirection | test.cpp:44:38:44:63 | ... * ... |
-| test.cpp:39:27:39:30 | argv indirection | test.cpp:44:38:44:63 | ... * ... |
-| test.cpp:39:27:39:30 | argv indirection | test.cpp:46:38:46:63 | ... + ... |
 | test.cpp:39:27:39:30 | argv indirection | test.cpp:46:38:46:63 | ... + ... |
 | test.cpp:39:27:39:30 | argv indirection | test.cpp:49:32:49:35 | size |
-| test.cpp:39:27:39:30 | argv indirection | test.cpp:49:32:49:35 | size |
 | test.cpp:39:27:39:30 | argv indirection | test.cpp:50:26:50:29 | size |
-| test.cpp:39:27:39:30 | argv indirection | test.cpp:50:26:50:29 | size |
-| test.cpp:39:27:39:30 | argv indirection | test.cpp:53:35:53:60 | ... * ... |
 | test.cpp:39:27:39:30 | argv indirection | test.cpp:53:35:53:60 | ... * ... |
 | test.cpp:124:18:124:23 | call to getenv | test.cpp:128:24:128:41 | ... * ... |
 | test.cpp:124:18:124:31 | call to getenv indirection | test.cpp:128:24:128:41 | ... * ... |
@@ -47,8 +35,6 @@ edges
 | test.cpp:353:18:353:31 | call to getenv indirection | test.cpp:355:35:355:38 | size |
 | test.cpp:353:18:353:31 | call to getenv indirection | test.cpp:356:35:356:38 | size |
 nodes
-| test.cpp:39:27:39:30 | argv | semmle.label | argv |
-| test.cpp:39:27:39:30 | argv indirection | semmle.label | argv indirection |
 | test.cpp:39:27:39:30 | argv indirection | semmle.label | argv indirection |
 | test.cpp:43:38:43:44 | tainted | semmle.label | tainted |
 | test.cpp:44:38:44:63 | ... * ... | semmle.label | ... * ... |
@@ -92,23 +78,11 @@ nodes
 | test.cpp:356:35:356:38 | size | semmle.label | size |
 subpaths
 #select
-| test.cpp:43:31:43:36 | call to malloc | test.cpp:39:27:39:30 | argv | test.cpp:43:38:43:44 | tainted | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv | user input (a command-line argument) |
 | test.cpp:43:31:43:36 | call to malloc | test.cpp:39:27:39:30 | argv indirection | test.cpp:43:38:43:44 | tainted | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:43:31:43:36 | call to malloc | test.cpp:39:27:39:30 | argv indirection | test.cpp:43:38:43:44 | tainted | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:44:31:44:36 | call to malloc | test.cpp:39:27:39:30 | argv | test.cpp:44:38:44:63 | ... * ... | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv | user input (a command-line argument) |
 | test.cpp:44:31:44:36 | call to malloc | test.cpp:39:27:39:30 | argv indirection | test.cpp:44:38:44:63 | ... * ... | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:44:31:44:36 | call to malloc | test.cpp:39:27:39:30 | argv indirection | test.cpp:44:38:44:63 | ... * ... | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:46:31:46:36 | call to malloc | test.cpp:39:27:39:30 | argv | test.cpp:46:38:46:63 | ... + ... | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv | user input (a command-line argument) |
 | test.cpp:46:31:46:36 | call to malloc | test.cpp:39:27:39:30 | argv indirection | test.cpp:46:38:46:63 | ... + ... | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:46:31:46:36 | call to malloc | test.cpp:39:27:39:30 | argv indirection | test.cpp:46:38:46:63 | ... + ... | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:49:25:49:30 | call to malloc | test.cpp:39:27:39:30 | argv | test.cpp:49:32:49:35 | size | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv | user input (a command-line argument) |
 | test.cpp:49:25:49:30 | call to malloc | test.cpp:39:27:39:30 | argv indirection | test.cpp:49:32:49:35 | size | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:49:25:49:30 | call to malloc | test.cpp:39:27:39:30 | argv indirection | test.cpp:49:32:49:35 | size | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:50:17:50:30 | new[] | test.cpp:39:27:39:30 | argv | test.cpp:50:26:50:29 | size | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv | user input (a command-line argument) |
 | test.cpp:50:17:50:30 | new[] | test.cpp:39:27:39:30 | argv indirection | test.cpp:50:26:50:29 | size | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:50:17:50:30 | new[] | test.cpp:39:27:39:30 | argv indirection | test.cpp:50:26:50:29 | size | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:53:21:53:27 | call to realloc | test.cpp:39:27:39:30 | argv | test.cpp:53:35:53:60 | ... * ... | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv | user input (a command-line argument) |
-| test.cpp:53:21:53:27 | call to realloc | test.cpp:39:27:39:30 | argv indirection | test.cpp:53:35:53:60 | ... * ... | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |
 | test.cpp:53:21:53:27 | call to realloc | test.cpp:39:27:39:30 | argv indirection | test.cpp:53:35:53:60 | ... * ... | This allocation size is derived from $@ and might overflow. | test.cpp:39:27:39:30 | argv indirection | user input (a command-line argument) |
 | test.cpp:128:17:128:22 | call to malloc | test.cpp:124:18:124:23 | call to getenv | test.cpp:128:24:128:41 | ... * ... | This allocation size is derived from $@ and might overflow. | test.cpp:124:18:124:23 | call to getenv | user input (an environment variable) |
 | test.cpp:128:17:128:22 | call to malloc | test.cpp:124:18:124:31 | call to getenv indirection | test.cpp:128:24:128:41 | ... * ... | This allocation size is derived from $@ and might overflow. | test.cpp:124:18:124:31 | call to getenv indirection | user input (an environment variable) |

cpp/ql/test/query-tests/Security/CWE/CWE-311/semmle/tests/CleartextBufferWrite.expected

@@ -1,12 +1,9 @@
 edges
 | test.cpp:53:27:53:30 | argv indirection | test.cpp:58:25:58:29 | input indirection |
 | test.cpp:53:27:53:30 | argv indirection | test.cpp:58:25:58:29 | input indirection |
-| test.cpp:53:27:53:30 | argv indirection | test.cpp:58:25:58:29 | input indirection |
-| test.cpp:53:27:53:30 | argv indirection | test.cpp:58:25:58:29 | input indirection |
 nodes
 | test2.cpp:110:3:110:6 | call to gets indirection | semmle.label | call to gets indirection |
 | test.cpp:53:27:53:30 | argv indirection | semmle.label | argv indirection |
-| test.cpp:53:27:53:30 | argv indirection | semmle.label | argv indirection |
 | test.cpp:58:25:58:29 | input indirection | semmle.label | input indirection |
 | test.cpp:58:25:58:29 | input indirection | semmle.label | input indirection |
 subpaths
@@ -14,5 +11,3 @@ subpaths
 | test2.cpp:110:3:110:6 | call to gets | test2.cpp:110:3:110:6 | call to gets indirection | test2.cpp:110:3:110:6 | call to gets indirection | This write into buffer 'password' may contain unencrypted data from $@. | test2.cpp:110:3:110:6 | call to gets indirection | user input (string read by gets) |
 | test.cpp:58:3:58:9 | call to sprintf | test.cpp:53:27:53:30 | argv indirection | test.cpp:58:25:58:29 | input indirection | This write into buffer 'passwd' may contain unencrypted data from $@. | test.cpp:53:27:53:30 | argv indirection | user input (a command-line argument) |
 | test.cpp:58:3:58:9 | call to sprintf | test.cpp:53:27:53:30 | argv indirection | test.cpp:58:25:58:29 | input indirection | This write into buffer 'passwd' may contain unencrypted data from $@. | test.cpp:53:27:53:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:58:3:58:9 | call to sprintf | test.cpp:53:27:53:30 | argv indirection | test.cpp:58:25:58:29 | input indirection | This write into buffer 'passwd' may contain unencrypted data from $@. | test.cpp:53:27:53:30 | argv indirection | user input (a command-line argument) |
-| test.cpp:58:3:58:9 | call to sprintf | test.cpp:53:27:53:30 | argv indirection | test.cpp:58:25:58:29 | input indirection | This write into buffer 'passwd' may contain unencrypted data from $@. | test.cpp:53:27:53:30 | argv indirection | user input (a command-line argument) |

csharp/.vscode/extensions.json

@@ -1,9 +1,11 @@
 {
     "recommendations": [
-        "github.vscode-codeql",
-        "ms-dotnettools.csharp",
         "formulahendry.dotnet-test-explorer",
-        "hbenl.vscode-test-explorer"
+        "gaoshan0621.csharp-format-usings",
+        "github.vscode-codeql",
+        "hbenl.vscode-test-explorer",
+        "ms-dotnettools.csharp",
+        "ms-dotnettools.csdevkit"
     ],
     "unwantedRecommendations": []
 }

csharp/.vscode/settings.json

@@ -7,5 +7,8 @@
         "editor.defaultFormatter": "ms-dotnettools.csharp"
     },
     "omnisharp.enableEditorConfigSupport": true,
-    "omnisharp.enableRoslynAnalyzers": true
+    "omnisharp.enableRoslynAnalyzers": true,
+    "csharpFormatUsings.splitGroups": false,
+    "csharpFormatUsings.sortOrder": "Xunit System Microsoft Semmle.Util Semmle",
+    "dotnet.defaultSolution": "CSharp.sln"
 }

csharp/.vscode/tasks.json

@@ -1,53 +0,0 @@
-{
-    "version": "2.0.0",
-    "tasks": [
-        {
-            "label": "dotnet build",
-            "command": "dotnet",
-            "type": "shell",
-            "args": [
-                "build",
-                // Ask dotnet build to generate full paths for file names.
-                "/property:GenerateFullPaths=true",
-                // Do not generate summary otherwise it leads to duplicate errors in Problems panel
-                "/consoleloggerparameters:NoSummary"
-            ],
-            "group": "build",
-            "presentation": {
-                "reveal": "always"
-            },
-            "problemMatcher": "$msCompile"
-        },
-        {
-            "label": "dotnet rebuild",
-            "command": "dotnet",
-            "type": "shell",
-            "args": [
-                "build",
-                "--no-incremental",
-                "/property:GenerateFullPaths=true",
-                "/consoleloggerparameters:NoSummary"
-            ],
-            "group": "build",
-            "presentation": {
-                "reveal": "always"
-            },
-            "problemMatcher": "$msCompile"
-        },
-        {
-            "label": "dotnet test",
-            "command": "dotnet",
-            "type": "shell",
-            "args": [
-                "test",
-                "/property:GenerateFullPaths=true",
-                "/consoleloggerparameters:NoSummary"
-            ],
-            "group": "test",
-            "presentation": {
-                "reveal": "always"
-            },
-            "problemMatcher": "$msCompile"
-        }
-    ]
-}

csharp/CSharp.sln

@@ -11,6 +11,8 @@ Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Semmle.Extraction.CSharp",
 EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Semmle.Extraction.CIL", "extractor\Semmle.Extraction.CIL\Semmle.Extraction.CIL.csproj", "{399A1579-68F0-40F4-9A23-F241BA697F9C}"
 EndProject
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Semmle.Extraction.CSharp.DependencyFetching", "extractor\Semmle.Extraction.CSharp.DependencyFetching\Semmle.Extraction.CSharp.DependencyFetching.csproj", "{541D1AC5-E42C-4AB2-A1A4-C2355CE2A2EF}"
+EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Semmle.Extraction.CSharp.Standalone", "extractor\Semmle.Extraction.CSharp.Standalone\Semmle.Extraction.CSharp.Standalone.csproj", "{D00E7D25-0FA0-48EC-B048-CD60CE1B30D8}"
 EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Semmle.Extraction.CIL.Driver", "extractor\Semmle.Extraction.CIL.Driver\Semmle.Extraction.CIL.Driver.csproj", "{EFA400B3-C1CE-446F-A4E2-8B44E61EF47C}"
@@ -49,6 +51,10 @@ Global
 		{399A1579-68F0-40F4-9A23-F241BA697F9C}.Debug|Any CPU.Build.0 = Debug|Any CPU
 		{399A1579-68F0-40F4-9A23-F241BA697F9C}.Release|Any CPU.ActiveCfg = Release|Any CPU
 		{399A1579-68F0-40F4-9A23-F241BA697F9C}.Release|Any CPU.Build.0 = Release|Any CPU
+		{541D1AC5-E42C-4AB2-A1A4-C2355CE2A2EF}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{541D1AC5-E42C-4AB2-A1A4-C2355CE2A2EF}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{541D1AC5-E42C-4AB2-A1A4-C2355CE2A2EF}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{541D1AC5-E42C-4AB2-A1A4-C2355CE2A2EF}.Release|Any CPU.Build.0 = Release|Any CPU
 		{D00E7D25-0FA0-48EC-B048-CD60CE1B30D8}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
 		{D00E7D25-0FA0-48EC-B048-CD60CE1B30D8}.Debug|Any CPU.Build.0 = Debug|Any CPU
 		{D00E7D25-0FA0-48EC-B048-CD60CE1B30D8}.Release|Any CPU.ActiveCfg = Release|Any CPU

csharp/autobuilder/Semmle.Autobuild.CSharp.Tests/BuildScripts.cs

@@ -725,7 +725,7 @@ namespace Semmle.Autobuild.CSharp.Tests
         [Fact]
         public void TestWindowsCmdIgnoreErrors()
         {
-            actions.RunProcess["cmd.exe /C ^\"build.cmd --skip-tests^\""] = 3;
+            actions.RunProcess["cmd.exe /C ^\"build.cmd^ --skip-tests^\""] = 3;
             actions.RunProcess[@"cmd.exe /C C:\codeql\tools\java\bin\java -jar C:\codeql\csharp\tools\extractor-asp.jar ."] = 0;
             actions.RunProcess[@"cmd.exe /C C:\codeql\tools\codeql index --xml --extensions config"] = 0;
             actions.FileExists["csharp.log"] = true;
@@ -744,9 +744,9 @@ namespace Semmle.Autobuild.CSharp.Tests
         public void TestWindowCSharpMsBuild()
         {
             actions.RunProcess[@"cmd.exe /C C:\Project\.nuget\nuget.exe restore C:\Project\test1.sln -DisableParallelProcessing"] = 0;
-            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program Files ^(x86^)\\Microsoft Visual Studio 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test1.sln /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
+            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program^ Files^ ^(x86^)\\Microsoft^ Visual^ Studio^ 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test1.sln /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
             actions.RunProcess[@"cmd.exe /C C:\Project\.nuget\nuget.exe restore C:\Project\test2.sln -DisableParallelProcessing"] = 0;
-            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program Files ^(x86^)\\Microsoft Visual Studio 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test2.sln /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
+            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program^ Files^ ^(x86^)\\Microsoft^ Visual^ Studio^ 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test2.sln /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
             actions.FileExists["csharp.log"] = true;
             actions.FileExists[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe"] = false;
             actions.FileExists[@"C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat"] = false;
@@ -775,9 +775,9 @@ namespace Semmle.Autobuild.CSharp.Tests
         public void TestWindowCSharpMsBuildMultipleSolutions()
         {
             actions.RunProcess[@"cmd.exe /C nuget restore C:\Project\test1.csproj -DisableParallelProcessing"] = 0;
-            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program Files ^(x86^)\\Microsoft Visual Studio 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test1.csproj /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
+            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program^ Files^ ^(x86^)\\Microsoft^ Visual^ Studio^ 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test1.csproj /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
             actions.RunProcess[@"cmd.exe /C nuget restore C:\Project\test2.csproj -DisableParallelProcessing"] = 0;
-            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program Files ^(x86^)\\Microsoft Visual Studio 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test2.csproj /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
+            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program^ Files^ ^(x86^)\\Microsoft^ Visual^ Studio^ 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test2.csproj /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
             actions.FileExists["csharp.log"] = true;
             actions.FileExists[@"C:\Project\test1.csproj"] = true;
             actions.FileExists[@"C:\Project\test2.csproj"] = true;
@@ -820,7 +820,7 @@ namespace Semmle.Autobuild.CSharp.Tests
         public void TestWindowCSharpMsBuildFailed()
         {
             actions.RunProcess[@"cmd.exe /C nuget restore C:\Project\test1.sln -DisableParallelProcessing"] = 0;
-            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program Files ^(x86^)\\Microsoft Visual Studio 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test1.sln /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 1;
+            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program^ Files^ ^(x86^)\\Microsoft^ Visual^ Studio^ 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test1.sln /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 1;
             actions.FileExists["csharp.log"] = true;
             actions.FileExists[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe"] = false;
             actions.FileExists[@"C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat"] = false;
@@ -846,8 +846,8 @@ namespace Semmle.Autobuild.CSharp.Tests
         [Fact]
         public void TestSkipNugetMsBuild()
         {
-            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program Files ^(x86^)\\Microsoft Visual Studio 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test1.sln /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
+            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program^ Files^ ^(x86^)\\Microsoft^ Visual^ Studio^ 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test1.sln /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
-            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program Files ^(x86^)\\Microsoft Visual Studio 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test2.sln /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
+            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program^ Files^ ^(x86^)\\Microsoft^ Visual^ Studio^ 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\test2.sln /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
             actions.FileExists["csharp.log"] = true;
             actions.FileExists[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe"] = false;
             actions.FileExists[@"C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat"] = false;
@@ -1037,7 +1037,7 @@ namespace Semmle.Autobuild.CSharp.Tests
         {
             actions.RunProcess[@"cmd.exe /C nuget restore C:\Project\dirs.proj -DisableParallelProcessing"] = 1;
             actions.RunProcess[@"cmd.exe /C C:\Project\.nuget\nuget.exe restore C:\Project\dirs.proj -DisableParallelProcessing"] = 0;
-            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program Files ^(x86^)\\Microsoft Visual Studio 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\dirs.proj /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
+            actions.RunProcess["cmd.exe /C CALL ^\"C:\\Program^ Files^ ^(x86^)\\Microsoft^ Visual^ Studio^ 12.0\\VC\\vcvarsall.bat^\" && set Platform=&& type NUL && msbuild C:\\Project\\dirs.proj /t:Windows /p:Platform=\"x86\" /p:Configuration=\"Debug\" /P:Fu=Bar"] = 0;
             actions.FileExists["csharp.log"] = true;
             actions.FileExists[@"C:\Project\a\test.csproj"] = true;
             actions.FileExists[@"C:\Project\dirs.proj"] = true;

csharp/autobuilder/Semmle.Autobuild.Shared/CommandBuilder.cs

@@ -55,7 +55,7 @@ namespace Semmle.Autobuild.Shared
         }
 
         private static readonly char[] specialChars = { ' ', '\t', '\n', '\v', '\"' };
-        private static readonly char[] cmdMetacharacter = { '(', ')', '%', '!', '^', '\"', '<', '>', '&', '|' };
+        private static readonly char[] cmdMetacharacter = { '(', ')', '%', '!', '^', '\"', '<', '>', '&', '|', ' ' };
 
         /// <summary>
         /// Appends the given argument to the command line.

csharp/codeql-extractor.yml

@@ -1,4 +1,6 @@
 name: "csharp"
+aliases:
+  - "c#"
 display_name: "C#"
 version: 1.22.1
 column_kind: "utf16"

csharp/extractor/Semmle.Extraction.CIL.Driver/ExtractorOptions.cs

@@ -1,13 +1,12 @@
 using System.Collections.Generic;
-using System.Linq;
-using System.IO;
-using System.Reflection.PortableExecutable;
-using System.Reflection.Metadata;
-using System.Reflection;
-using System.Runtime.InteropServices;
 using System.Globalization;
+using System.IO;
+using System.Linq;
+using System.Reflection;
+using System.Reflection.Metadata;
+using System.Reflection.PortableExecutable;
+using System.Runtime.InteropServices;
 using Semmle.Util;
-using Semmle.Util.Logging;
 
 namespace Semmle.Extraction.CIL.Driver
 {

csharp/extractor/Semmle.Extraction.CIL.Driver/Program.cs

@@ -1,8 +1,8 @@
 using System;
+using System.Diagnostics;
 using System.Linq;
 using System.Threading.Tasks;
 using Semmle.Util.Logging;
-using System.Diagnostics;
 
 namespace Semmle.Extraction.CIL.Driver
 {

csharp/extractor/Semmle.Extraction.CIL/Analyser.cs

@@ -1,6 +1,6 @@
-using Semmle.Util.Logging;
 using System;
 using Semmle.Util;
+using Semmle.Util.Logging;
 using Semmle.Extraction.CIL.Entities;
 
 namespace Semmle.Extraction.CIL

csharp/extractor/Semmle.Extraction.CIL/Context.Factories.cs

@@ -1,8 +1,7 @@
-using Semmle.Extraction.CIL.Entities;
+using System;
-using System;
 using System.Collections.Generic;
-using System.IO;
 using System.Reflection.Metadata;
+using Semmle.Extraction.CIL.Entities;
 
 namespace Semmle.Extraction.CIL
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/Assembly.cs

@@ -1,8 +1,7 @@
-using System.Reflection;
+using System.Collections.Generic;
 using System.Globalization;
-using System.Collections.Generic;
+using System.Reflection;
 using Semmle.Extraction.Entities;
-using System.IO;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/Attribute.cs

@@ -1,5 +1,4 @@
-using System;
+using System.Collections.Generic;
-using System.Collections.Generic;
 using System.Linq;
 using System.Reflection.Metadata;
 

csharp/extractor/Semmle.Extraction.CIL/Entities/Base/LabelledEntity.cs

@@ -1,6 +1,5 @@
 using System;
 using System.Collections.Generic;
-using System.IO;
 
 namespace Semmle.Extraction.CIL
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/ConstructedType.cs

@@ -1,7 +1,7 @@
 using System;
-using System.Linq;
 using System.Collections.Generic;
 using System.IO;
+using System.Linq;
 using Semmle.Util;
 
 namespace Semmle.Extraction.CIL.Entities

csharp/extractor/Semmle.Extraction.CIL/Entities/DefinitionField.cs

@@ -1,7 +1,7 @@
 using System;
 using System.Collections.Generic;
-using System.Reflection.Metadata;
 using System.Reflection;
+using System.Reflection.Metadata;
 using System.Reflection.Metadata.Ecma335;
 
 namespace Semmle.Extraction.CIL.Entities

csharp/extractor/Semmle.Extraction.CIL/Entities/DefinitionMethod.cs

@@ -1,7 +1,7 @@
-using System.Reflection.Metadata;
 using System.Collections.Generic;
-using System.Reflection;
 using System.Linq;
+using System.Reflection;
+using System.Reflection.Metadata;
 using System.Reflection.Metadata.Ecma335;
 
 namespace Semmle.Extraction.CIL.Entities

csharp/extractor/Semmle.Extraction.CIL/Entities/Event.cs

@@ -1,5 +1,4 @@
 using System.Collections.Generic;
-using System.IO;
 using System.Reflection.Metadata;
 
 namespace Semmle.Extraction.CIL.Entities

csharp/extractor/Semmle.Extraction.CIL/Entities/File.cs

@@ -1,5 +1,4 @@
 using System.Collections.Generic;
-using System.IO;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/Folder.cs

@@ -1,5 +1,4 @@
 using System.Collections.Generic;
-using System.IO;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/ITypeSignature.cs

@@ -1,5 +1,3 @@
-using System.IO;
-
 namespace Semmle.Extraction.CIL.Entities
 {
     internal interface ITypeSignature

csharp/extractor/Semmle.Extraction.CIL/Entities/LocalVariable.cs

@@ -1,5 +1,4 @@
 using System.Collections.Generic;
-using System.IO;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/MemberReferenceMethod.cs

@@ -1,6 +1,6 @@
-using System.Reflection.Metadata;
 using System.Collections.Generic;
 using System.Linq;
+using System.Reflection.Metadata;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/Method.cs

@@ -1,8 +1,7 @@
 using System;
-using System.Reflection.Metadata;
 using System.Collections.Generic;
 using System.Linq;
-using System.IO;
+using System.Reflection.Metadata;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/MethodSpecificationMethod.cs

@@ -1,9 +1,8 @@
 using System;
-using System.Collections.Immutable;
-using System.Reflection.Metadata;
 using System.Collections.Generic;
+using System.Collections.Immutable;
 using System.Linq;
-using System.IO;
+using System.Reflection.Metadata;
 using Semmle.Util;
 
 namespace Semmle.Extraction.CIL.Entities

csharp/extractor/Semmle.Extraction.CIL/Entities/MethodTypeParameter.cs

@@ -1,6 +1,5 @@
 using System;
 using System.Collections.Generic;
-using System.IO;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/NamedTypeIdWriter.cs

@@ -1,5 +1,4 @@
 using System.Linq;
-using System.IO;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/Namespace.cs

@@ -1,6 +1,5 @@
 using System;
 using System.Collections.Generic;
-using System.IO;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/NoMetadataHandleType.FullyQualifiedNameParser.cs

@@ -1,4 +1,3 @@
-using System;
 using System.Collections.Generic;
 using System.Linq;
 using Semmle.Util;

csharp/extractor/Semmle.Extraction.CIL/Entities/Parameter.cs

@@ -1,5 +1,4 @@
 using System.Collections.Generic;
-using System.IO;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/PrimitiveType.cs

@@ -1,7 +1,7 @@
 using System;
-using System.Reflection.Metadata;
 using System.Collections.Generic;
 using System.IO;
+using System.Reflection.Metadata;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/Property.cs

@@ -1,7 +1,6 @@
 using System.Collections.Generic;
 using System.Reflection.Metadata;
 using System.Reflection.Metadata.Ecma335;
-using System.IO;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/SignatureDecoder.cs

@@ -1,6 +1,5 @@
-using System.Reflection.Metadata;
 using System.Collections.Immutable;
-using System.IO;
+using System.Reflection.Metadata;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/SourceLocation.cs

@@ -1,5 +1,4 @@
 using System.Collections.Generic;
-using System.IO;
 using Semmle.Extraction.PDB;
 
 namespace Semmle.Extraction.CIL.Entities

csharp/extractor/Semmle.Extraction.CIL/Entities/Type.cs

@@ -1,8 +1,8 @@
-using System.Reflection.Metadata;
+using System.Collections.Generic;
-using System.Collections.Generic;
-using System.IO;
 using System.Diagnostics.CodeAnalysis;
+using System.IO;
 using System.Linq;
+using System.Reflection.Metadata;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/TypeContainer.cs

@@ -1,5 +1,4 @@
 using System.Collections.Generic;
-using System.IO;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/TypeDefinitionType.cs

@@ -1,10 +1,10 @@
 using System;
-using System.Linq;
 using System.Collections.Generic;
-using System.Reflection;
 using System.IO;
-using System.Reflection.Metadata.Ecma335;
+using System.Linq;
+using System.Reflection;
 using System.Reflection.Metadata;
+using System.Reflection.Metadata.Ecma335;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/TypeParameter.cs

@@ -1,9 +1,9 @@
 using System;
-using System.Reflection.Metadata;
-using System.Linq;
 using System.Collections.Generic;
-using System.Reflection;
 using System.IO;
+using System.Linq;
+using System.Reflection;
+using System.Reflection.Metadata;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/TypeReferenceType.cs

@@ -1,8 +1,8 @@
 using System;
-using System.Reflection.Metadata;
-using System.Linq;
 using System.Collections.Generic;
 using System.IO;
+using System.Linq;
+using System.Reflection.Metadata;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/TypeSignatureDecoder.cs

@@ -1,7 +1,7 @@
 using System;
-using System.Reflection.Metadata;
 using System.Collections.Immutable;
 using System.Linq;
+using System.Reflection.Metadata;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/Entities/TypeTypeParameter.cs

@@ -1,6 +1,5 @@
-using System.Linq;
 using System.Collections.Generic;
-using System.IO;
+using System.Linq;
 
 namespace Semmle.Extraction.CIL.Entities
 {

csharp/extractor/Semmle.Extraction.CIL/PDB/MdProvider.cs

@@ -1,6 +1,6 @@
 using System;
-using Microsoft.DiaSymReader;
 using System.Reflection;
+using Microsoft.DiaSymReader;
 
 #pragma warning disable IDE0060, CA1822