C++/C#: Fix sync config file for value numbering sharing

MathiasVP · MathiasVP · commit d4c6f487bc88 · 2020-02-13T22:32:52.000+01:00
diff --git a/config/identical-files.json b/config/identical-files.json
@@ -222,10 +222,12 @@
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/internal/PrintSSA.qll",
     "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/PrintSSA.qll"
   ],
-  "C++ IR ValueNumberInternal": [
+  "IR ValueNumberInternal": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/gvn/internal/ValueNumberingInternal.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingInternal.qll",
-    "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/gvn/internal/ValueNumberingInternal.qll"
+    "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/gvn/internal/ValueNumberingInternal.qll",
+    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/gvn/internal/ValueNumberingInternal.qll",
+    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingInternal.qll"
   ],
   "C++ IR ValueNumber": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/gvn/ValueNumbering.qll",
diff --git a/cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/gvn/ValueNumbering.qll b/cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/gvn/ValueNumbering.qll
@@ -27,19 +27,19 @@ class ValueNumber extends TValueNumber {
   final Language::Location getLocation() {
     if
       exists(Instruction i |
-        i = getAnInstruction() and not i.getLocation() instanceof UnknownLocation
+        i = getAnInstruction() and not i.getLocation() instanceof Language::UnknownLocation
       )
     then
       result =
         min(Language::Location l |
-          l = getAnInstruction().getLocation() and not l instanceof UnknownLocation
+          l = getAnInstruction().getLocation() and not l instanceof Language::UnknownLocation
         |
           l
           order by
             l.getFile().getAbsolutePath(), l.getStartLine(), l.getStartColumn(), l.getEndLine(),
             l.getEndColumn()
         )
-    else result instanceof UnknownDefaultLocation
+    else result instanceof Language::UnknownDefaultLocation
   }
 
   /**
diff --git a/cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/gvn/internal/ValueNumberingImports.qll b/cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/gvn/internal/ValueNumberingImports.qll
@@ -1,4 +1,3 @@
 import semmle.code.cpp.ir.implementation.aliased_ssa.IR
 import semmle.code.cpp.ir.internal.Overlap
 import semmle.code.cpp.ir.internal.IRCppLanguage as Language
-import semmle.code.cpp.Location
diff --git a/cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/gvn/internal/ValueNumberingInternal.qll b/cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/gvn/internal/ValueNumberingInternal.qll
@@ -1,5 +1,4 @@
 private import ValueNumberingImports
-private import cpp
 
 newtype TValueNumber =
   TVariableAddressValueNumber(IRFunction irFunc, Language::AST ast) {
@@ -15,7 +14,7 @@ newtype TValueNumber =
   TStringConstantValueNumber(IRFunction irFunc, IRType type, string value) {
     stringConstantValueNumber(_, irFunc, type, value)
   } or
-  TFieldAddressValueNumber(IRFunction irFunc, Field field, TValueNumber objectAddress) {
+  TFieldAddressValueNumber(IRFunction irFunc, Language::Field field, TValueNumber objectAddress) {
     fieldAddressValueNumber(_, irFunc, field, objectAddress)
   } or
   TBinaryValueNumber(
@@ -34,7 +33,8 @@ newtype TValueNumber =
     unaryValueNumber(_, irFunc, opcode, type, operand)
   } or
   TInheritanceConversionValueNumber(
-    IRFunction irFunc, Opcode opcode, Class baseClass, Class derivedClass, TValueNumber operand
+    IRFunction irFunc, Opcode opcode, Language::Class baseClass, Language::Class derivedClass,
+    TValueNumber operand
   ) {
     inheritanceConversionValueNumber(_, irFunc, opcode, baseClass, derivedClass, operand)
   } or
diff --git a/cpp/ql/src/semmle/code/cpp/ir/implementation/raw/gvn/ValueNumbering.qll b/cpp/ql/src/semmle/code/cpp/ir/implementation/raw/gvn/ValueNumbering.qll
@@ -27,19 +27,19 @@ class ValueNumber extends TValueNumber {
   final Language::Location getLocation() {
     if
       exists(Instruction i |
-        i = getAnInstruction() and not i.getLocation() instanceof UnknownLocation
+        i = getAnInstruction() and not i.getLocation() instanceof Language::UnknownLocation
       )
     then
       result =
         min(Language::Location l |
-          l = getAnInstruction().getLocation() and not l instanceof UnknownLocation
+          l = getAnInstruction().getLocation() and not l instanceof Language::UnknownLocation
         |
           l
           order by
             l.getFile().getAbsolutePath(), l.getStartLine(), l.getStartColumn(), l.getEndLine(),
             l.getEndColumn()
         )
-    else result instanceof UnknownDefaultLocation
+    else result instanceof Language::UnknownDefaultLocation
   }
 
   /**
diff --git a/cpp/ql/src/semmle/code/cpp/ir/implementation/raw/gvn/internal/ValueNumberingImports.qll b/cpp/ql/src/semmle/code/cpp/ir/implementation/raw/gvn/internal/ValueNumberingImports.qll
@@ -1,4 +1,3 @@
 import semmle.code.cpp.ir.implementation.aliased_ssa.IR
 import semmle.code.cpp.ir.internal.Overlap
 import semmle.code.cpp.ir.internal.IRCppLanguage as Language
-import semmle.code.cpp.Location
diff --git a/cpp/ql/src/semmle/code/cpp/ir/implementation/raw/gvn/internal/ValueNumberingInternal.qll b/cpp/ql/src/semmle/code/cpp/ir/implementation/raw/gvn/internal/ValueNumberingInternal.qll
@@ -1,5 +1,4 @@
 private import ValueNumberingImports
-private import cpp
 
 newtype TValueNumber =
   TVariableAddressValueNumber(IRFunction irFunc, Language::AST ast) {
@@ -15,7 +14,7 @@ newtype TValueNumber =
   TStringConstantValueNumber(IRFunction irFunc, IRType type, string value) {
     stringConstantValueNumber(_, irFunc, type, value)
   } or
-  TFieldAddressValueNumber(IRFunction irFunc, Field field, TValueNumber objectAddress) {
+  TFieldAddressValueNumber(IRFunction irFunc, Language::Field field, TValueNumber objectAddress) {
     fieldAddressValueNumber(_, irFunc, field, objectAddress)
   } or
   TBinaryValueNumber(
@@ -34,7 +33,8 @@ newtype TValueNumber =
     unaryValueNumber(_, irFunc, opcode, type, operand)
   } or
   TInheritanceConversionValueNumber(
-    IRFunction irFunc, Opcode opcode, Class baseClass, Class derivedClass, TValueNumber operand
+    IRFunction irFunc, Opcode opcode, Language::Class baseClass, Language::Class derivedClass,
+    TValueNumber operand
   ) {
     inheritanceConversionValueNumber(_, irFunc, opcode, baseClass, derivedClass, operand)
   } or
diff --git a/cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/gvn/ValueNumbering.qll b/cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/gvn/ValueNumbering.qll
@@ -27,19 +27,19 @@ class ValueNumber extends TValueNumber {
   final Language::Location getLocation() {
     if
       exists(Instruction i |
-        i = getAnInstruction() and not i.getLocation() instanceof UnknownLocation
+        i = getAnInstruction() and not i.getLocation() instanceof Language::UnknownLocation
       )
     then
       result =
         min(Language::Location l |
-          l = getAnInstruction().getLocation() and not l instanceof UnknownLocation
+          l = getAnInstruction().getLocation() and not l instanceof Language::UnknownLocation
         |
           l
           order by
             l.getFile().getAbsolutePath(), l.getStartLine(), l.getStartColumn(), l.getEndLine(),
             l.getEndColumn()
         )
-    else result instanceof UnknownDefaultLocation
+    else result instanceof Language::UnknownDefaultLocation
   }
 
   /**
diff --git a/cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingImports.qll b/cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingImports.qll
@@ -1,4 +1,3 @@
 import semmle.code.cpp.ir.implementation.aliased_ssa.IR
 import semmle.code.cpp.ir.internal.Overlap
 import semmle.code.cpp.ir.internal.IRCppLanguage as Language
-import semmle.code.cpp.Location
diff --git a/cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingInternal.qll b/cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingInternal.qll
@@ -1,5 +1,4 @@
 private import ValueNumberingImports
-private import cpp
 
 newtype TValueNumber =
   TVariableAddressValueNumber(IRFunction irFunc, Language::AST ast) {
@@ -15,7 +14,7 @@ newtype TValueNumber =
   TStringConstantValueNumber(IRFunction irFunc, IRType type, string value) {
     stringConstantValueNumber(_, irFunc, type, value)
   } or
-  TFieldAddressValueNumber(IRFunction irFunc, Field field, TValueNumber objectAddress) {
+  TFieldAddressValueNumber(IRFunction irFunc, Language::Field field, TValueNumber objectAddress) {
     fieldAddressValueNumber(_, irFunc, field, objectAddress)
   } or
   TBinaryValueNumber(
@@ -34,7 +33,8 @@ newtype TValueNumber =
     unaryValueNumber(_, irFunc, opcode, type, operand)
   } or
   TInheritanceConversionValueNumber(
-    IRFunction irFunc, Opcode opcode, Class baseClass, Class derivedClass, TValueNumber operand
+    IRFunction irFunc, Opcode opcode, Language::Class baseClass, Language::Class derivedClass,
+    TValueNumber operand
   ) {
     inheritanceConversionValueNumber(_, irFunc, opcode, baseClass, derivedClass, operand)
   } or
diff --git a/cpp/ql/src/semmle/code/cpp/ir/internal/IRCppLanguage.qll b/cpp/ql/src/semmle/code/cpp/ir/internal/IRCppLanguage.qll
@@ -13,6 +13,10 @@ class Function = Cpp::Function;
 
 class Location = Cpp::Location;
 
+class UnknownLocation = Cpp::UnknownLocation;
+
+class UnknownDefaultLocation = Cpp::UnknownDefaultLocation;
+
 class File = Cpp::File;
 
 class AST = Cpp::Locatable;
diff --git a/csharp/ql/src/semmle/code/csharp/ir/implementation/raw/gvn/ValueNumbering.qll b/csharp/ql/src/semmle/code/csharp/ir/implementation/raw/gvn/ValueNumbering.qll
@@ -27,19 +27,19 @@ class ValueNumber extends TValueNumber {
   final Language::Location getLocation() {
     if
       exists(Instruction i |
-        i = getAnInstruction() and not i.getLocation() instanceof UnknownLocation
+        i = getAnInstruction() and not i.getLocation() instanceof Language::UnknownLocation
       )
     then
       result =
         min(Language::Location l |
-          l = getAnInstruction().getLocation() and not l instanceof UnknownLocation
+          l = getAnInstruction().getLocation() and not l instanceof Language::UnknownLocation
         |
           l
           order by
             l.getFile().getAbsolutePath(), l.getStartLine(), l.getStartColumn(), l.getEndLine(),
             l.getEndColumn()
         )
-    else result instanceof UnknownDefaultLocation
+    else result instanceof Language::UnknownDefaultLocation
   }
 
   /**
diff --git a/csharp/ql/src/semmle/code/csharp/ir/implementation/raw/gvn/internal/ValueNumberingImports.qll b/csharp/ql/src/semmle/code/csharp/ir/implementation/raw/gvn/internal/ValueNumberingImports.qll
@@ -1 +1,3 @@
 import semmle.code.csharp.ir.internal.Overlap
+import semmle.code.csharp.ir.internal.IRCSharpLanguage as Language
+import semmle.code.csharp.ir.implementation.unaliased_ssa.IR
diff --git a/csharp/ql/src/semmle/code/csharp/ir/implementation/raw/gvn/internal/ValueNumberingInternal.qll b/csharp/ql/src/semmle/code/csharp/ir/implementation/raw/gvn/internal/ValueNumberingInternal.qll
@@ -1,17 +1,10 @@
 private import ValueNumberingImports
-import semmle.code.csharp.ir.internal.IRCSharpLanguage as Language
-import semmle.code.csharp.ir.implementation.raw.IR
-private import semmle.code.csharp.Location
-
-class UnknownLocation = EmptyLocation;
-
-class UnknownDefaultLocation = EmptyLocation;
 
 newtype TValueNumber =
-  TVariableAddressValueNumber(IRFunction irFunc, IRVariable var) {
-    variableAddressValueNumber(_, irFunc, var)
+  TVariableAddressValueNumber(IRFunction irFunc, Language::AST ast) {
+    variableAddressValueNumber(_, irFunc, ast)
   } or
-  TInitializeParameterValueNumber(IRFunction irFunc, IRVariable var) {
+  TInitializeParameterValueNumber(IRFunction irFunc, Language::AST var) {
     initializeParameterValueNumber(_, irFunc, var)
   } or
   TInitializeThisValueNumber(IRFunction irFunc) { initializeThisValueNumber(_, irFunc) } or
@@ -45,6 +38,11 @@ newtype TValueNumber =
   ) {
     inheritanceConversionValueNumber(_, irFunc, opcode, baseClass, derivedClass, operand)
   } or
+  TLoadTotalOverlapValueNumber(
+    IRFunction irFunc, IRType type, TValueNumber memOperand, TValueNumber operand
+  ) {
+    loadTotalOverlapValueNumber(_, irFunc, type, memOperand, operand)
+  } or
   TUniqueValueNumber(IRFunction irFunc, Instruction instr) { uniqueValueNumber(instr, irFunc) }
 
 /**
@@ -61,12 +59,18 @@ newtype TValueNumber =
  * The use of `p.x` on line 3 is linked to the definition of `p` on line 1 as well, but is not
  * congruent to that definition because `p.x` accesses only a subset of the memory defined by `p`.
  */
-private class CongruentCopyInstruction extends CopyInstruction {
+class CongruentCopyInstruction extends CopyInstruction {
   CongruentCopyInstruction() {
     this.getSourceValueOperand().getDefinitionOverlap() instanceof MustExactlyOverlap
   }
 }
 
+class LoadTotalOverlapInstruction extends LoadInstruction {
+  LoadTotalOverlapInstruction() {
+    this.getSourceValueOperand().getDefinitionOverlap() instanceof MustTotallyOverlap
+  }
+}
+
 /**
  * Holds if this library knows how to assign a value number to the specified instruction, other than
  * a `unique` value number that is never shared by multiple instructions.
@@ -91,20 +95,28 @@ private predicate numberableInstruction(Instruction instr) {
   instr instanceof PointerArithmeticInstruction
   or
   instr instanceof CongruentCopyInstruction
+  or
+  instr instanceof LoadTotalOverlapInstruction
 }
 
 private predicate variableAddressValueNumber(
-  VariableAddressInstruction instr, IRFunction irFunc, IRVariable var
+  VariableAddressInstruction instr, IRFunction irFunc, Language::AST ast
 ) {
   instr.getEnclosingIRFunction() = irFunc and
-  instr.getIRVariable() = var
+  // The underlying AST element is used as value-numbering key instead of the
+  // `IRVariable` to work around a problem where a variable or expression with
+  // multiple types gives rise to multiple `IRVariable`s.
+  instr.getIRVariable().getAST() = ast
 }
 
 private predicate initializeParameterValueNumber(
-  InitializeParameterInstruction instr, IRFunction irFunc, IRVariable var
+  InitializeParameterInstruction instr, IRFunction irFunc, Language::AST var
 ) {
   instr.getEnclosingIRFunction() = irFunc and
-  instr.getIRVariable() = var
+  // The underlying AST element is used as value-numbering key instead of the
+  // `IRVariable` to work around a problem where a variable or expression with
+  // multiple types gives rise to multiple `IRVariable`s.
+  instr.getIRVariable().getAST() = var
 }
 
 private predicate initializeThisValueNumber(InitializeThisInstruction instr, IRFunction irFunc) {
@@ -166,6 +178,7 @@ private predicate unaryValueNumber(
   instr.getEnclosingIRFunction() = irFunc and
   not instr instanceof InheritanceConversionInstruction and
   not instr instanceof CopyInstruction and
+  not instr instanceof FieldAddressInstruction and
   instr.getOpcode() = opcode and
   instr.getResultIRType() = type and
   tvalueNumber(instr.getUnary()) = operand
@@ -182,6 +195,16 @@ private predicate inheritanceConversionValueNumber(
   tvalueNumber(instr.getUnary()) = operand
 }
 
+private predicate loadTotalOverlapValueNumber(
+  LoadTotalOverlapInstruction instr, IRFunction irFunc, IRType type, TValueNumber memOperand,
+  TValueNumber operand
+) {
+  instr.getEnclosingIRFunction() = irFunc and
+  instr.getResultIRType() = type and
+  tvalueNumber(instr.getAnOperand().(MemoryOperand).getAnyDef()) = memOperand and
+  tvalueNumberOfOperand(instr.getAnOperand().(AddressOperand)) = operand
+}
+
 /**
  * Holds if `instr` should be assigned a unique value number because this library does not know how
  * to determine if two instances of that instruction are equivalent.
@@ -205,6 +228,12 @@ TValueNumber tvalueNumber(Instruction instr) {
   )
 }
 
+/**
+ * Gets the value number assigned to the exact definition of `op`, if any.
+ * Returns at most one result.
+ */
+TValueNumber tvalueNumberOfOperand(Operand op) { result = tvalueNumber(op.getDef()) }
+
 /**
  * Gets the value number assigned to `instr`, if any, unless that instruction is assigned a unique
  * value number.
@@ -213,12 +242,12 @@ private TValueNumber nonUniqueValueNumber(Instruction instr) {
   exists(IRFunction irFunc |
     irFunc = instr.getEnclosingIRFunction() and
     (
-      exists(IRVariable var |
-        variableAddressValueNumber(instr, irFunc, var) and
-        result = TVariableAddressValueNumber(irFunc, var)
+      exists(Language::AST ast |
+        variableAddressValueNumber(instr, irFunc, ast) and
+        result = TVariableAddressValueNumber(irFunc, ast)
       )
       or
-      exists(IRVariable var |
+      exists(Language::AST var |
         initializeParameterValueNumber(instr, irFunc, var) and
         result = TInitializeParameterValueNumber(irFunc, var)
       )
@@ -268,6 +297,11 @@ private TValueNumber nonUniqueValueNumber(Instruction instr) {
           TPointerArithmeticValueNumber(irFunc, opcode, type, elementSize, leftOperand, rightOperand)
       )
       or
+      exists(IRType type, TValueNumber memOperand, TValueNumber operand |
+        loadTotalOverlapValueNumber(instr, irFunc, type, memOperand, operand) and
+        result = TLoadTotalOverlapValueNumber(irFunc, type, memOperand, operand)
+      )
+      or
       // The value number of a copy is just the value number of its source value.
       result = tvalueNumber(instr.(CongruentCopyInstruction).getSourceValue())
     )
diff --git a/csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/gvn/ValueNumbering.qll b/csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/gvn/ValueNumbering.qll
@@ -27,19 +27,19 @@ class ValueNumber extends TValueNumber {
   final Language::Location getLocation() {
     if
       exists(Instruction i |
-        i = getAnInstruction() and not i.getLocation() instanceof UnknownLocation
+        i = getAnInstruction() and not i.getLocation() instanceof Language::UnknownLocation
       )
     then
       result =
         min(Language::Location l |
-          l = getAnInstruction().getLocation() and not l instanceof UnknownLocation
+          l = getAnInstruction().getLocation() and not l instanceof Language::UnknownLocation
         |
           l
           order by
             l.getFile().getAbsolutePath(), l.getStartLine(), l.getStartColumn(), l.getEndLine(),
             l.getEndColumn()
         )
-    else result instanceof UnknownDefaultLocation
+    else result instanceof Language::UnknownDefaultLocation
   }
 
   /**
diff --git a/csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingImports.qll b/csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingImports.qll
@@ -1 +1,3 @@
 import semmle.code.csharp.ir.internal.Overlap
+import semmle.code.csharp.ir.internal.IRCSharpLanguage as Language
+import semmle.code.csharp.ir.implementation.unaliased_ssa.IR
diff --git a/csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingInternal.qll b/csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingInternal.qll
diff --git a/csharp/ql/src/semmle/code/csharp/ir/internal/IRCSharpLanguage.qll b/csharp/ql/src/semmle/code/csharp/ir/internal/IRCSharpLanguage.qll

Original file line number	Diff line number	Diff line change
`@@ -27,19 +27,19 @@ class ValueNumber extends TValueNumber {`
`27`	`27`	`final Language::Location getLocation() {`
`28`	`28`	`if`
`29`	`29`	`exists(Instruction i \|`
`30`		`- i = getAnInstruction() and not i.getLocation() instanceof UnknownLocation`
	`30`	`+ i = getAnInstruction() and not i.getLocation() instanceof Language::UnknownLocation`
`31`	`31`	`)`
`32`	`32`	`then`
`33`	`33`	`result =`
`34`	`34`	`min(Language::Location l \|`
`35`		`- l = getAnInstruction().getLocation() and not l instanceof UnknownLocation`
	`35`	`+ l = getAnInstruction().getLocation() and not l instanceof Language::UnknownLocation`
`36`	`36`	`\|`
`37`	`37`	`l`
`38`	`38`	`order by`
`39`	`39`	`l.getFile().getAbsolutePath(), l.getStartLine(), l.getStartColumn(), l.getEndLine(),`
`40`	`40`	`l.getEndColumn()`
`41`	`41`	`)`
`42`		`- else result instanceof UnknownDefaultLocation`
	`42`	`+ else result instanceof Language::UnknownDefaultLocation`
`43`	`43`	`}`
`44`	`44`
`45`	`45`	`/**`