[AsmParser] Supprt non-consecutive global value numbers

llvm#78171 added support for
local value numbers to have gaps. This extends the support for
global value numbers (for globals and functions).

This means that it is now possible to delete an unnamed global
definition/declaration without breaking the IR.

This is a lot less common than unnamed local values, but it seems
like something we should support for consistency. (Unnamed globals
are also common in rustc IR).

Author: nikic

llvm/include/llvm/AsmParser/LLParser.h

@@ -15,6 +15,7 @@
 
 #include "LLLexer.h"
 #include "llvm/ADT/StringMap.h"
+#include "llvm/AsmParser/NumberedValues.h"
 #include "llvm/AsmParser/Parser.h"
 #include "llvm/IR/Attributes.h"
 #include "llvm/IR/FMF.h"
@@ -133,7 +134,7 @@ namespace llvm {
     // Global Value reference information.
     std::map<std::string, std::pair<GlobalValue*, LocTy> > ForwardRefVals;
     std::map<unsigned, std::pair<GlobalValue*, LocTy> > ForwardRefValIDs;
-    std::vector<GlobalValue*> NumberedVals;
+    NumberedValues<GlobalValue *> NumberedVals;
 
     // Comdat forward reference information.
     std::map<std::string, LocTy> ForwardRefComdats;
@@ -346,14 +347,15 @@ namespace llvm {
     bool parseGlobalType(bool &IsConstant);
     bool parseUnnamedGlobal();
     bool parseNamedGlobal();
-    bool parseGlobal(const std::string &Name, LocTy NameLoc, unsigned Linkage,
-                     bool HasLinkage, unsigned Visibility,
+    bool parseGlobal(const std::string &Name, unsigned NameID, LocTy NameLoc,
+                     unsigned Linkage, bool HasLinkage, unsigned Visibility,
                      unsigned DLLStorageClass, bool DSOLocal,
                      GlobalVariable::ThreadLocalMode TLM,
                      GlobalVariable::UnnamedAddr UnnamedAddr);
-    bool parseAliasOrIFunc(const std::string &Name, LocTy NameLoc, unsigned L,
-                           unsigned Visibility, unsigned DLLStorageClass,
-                           bool DSOLocal, GlobalVariable::ThreadLocalMode TLM,
+    bool parseAliasOrIFunc(const std::string &Name, unsigned NameID,
+                           LocTy NameLoc, unsigned L, unsigned Visibility,
+                           unsigned DLLStorageClass, bool DSOLocal,
+                           GlobalVariable::ThreadLocalMode TLM,
                            GlobalVariable::UnnamedAddr UnnamedAddr);
     bool parseComdat();
     bool parseStandaloneMetadata();
@@ -452,27 +454,13 @@ namespace llvm {
     bool parseFunctionType(Type *&Result);
     bool parseTargetExtType(Type *&Result);
 
-    class NumberedValues {
-      DenseMap<unsigned, Value *> Vals;
-      unsigned NextUnusedID = 0;
-
-    public:
-      unsigned getNext() const { return NextUnusedID; }
-      Value *get(unsigned ID) const { return Vals.lookup(ID); }
-      void add(unsigned ID, Value *V) {
-        assert(ID >= NextUnusedID && "Invalid value ID");
-        Vals.insert({ID, V});
-        NextUnusedID = ID + 1;
-      }
-    };
-
     // Function Semantic Analysis.
     class PerFunctionState {
       LLParser &P;
       Function &F;
       std::map<std::string, std::pair<Value*, LocTy> > ForwardRefVals;
       std::map<unsigned, std::pair<Value*, LocTy> > ForwardRefValIDs;
-      NumberedValues NumberedVals;
+      NumberedValues<Value *> NumberedVals;
 
       /// FunctionNumber - If this is an unnamed function, this is the slot
       /// number of it, otherwise it is -1.
@@ -614,8 +602,10 @@ namespace llvm {
                            SmallVectorImpl<unsigned> &UnnamedArgNums,
                            bool &IsVarArg);
     bool parseFunctionHeader(Function *&Fn, bool IsDefine,
+                             unsigned &FunctionNumber,
                              SmallVectorImpl<unsigned> &UnnamedArgNums);
-    bool parseFunctionBody(Function &Fn, ArrayRef<unsigned> UnnamedArgNums);
+    bool parseFunctionBody(Function &Fn, unsigned FunctionNumber,
+                           ArrayRef<unsigned> UnnamedArgNums);
     bool parseBasicBlock(PerFunctionState &PFS);
 
     enum TailCallType { TCT_None, TCT_Tail, TCT_MustTail };

llvm/include/llvm/AsmParser/NumberedValues.h

@@ -0,0 +1,34 @@
+//===-- NumberedValues.h - --------------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_ASMPARSER_NUMBEREDVALUES_H
+#define LLVM_ASMPARSER_NUMBEREDVALUES_H
+
+#include "llvm/ADT/DenseMap.h"
+
+namespace llvm {
+
+/// Mapping from value ID to value, which also remembers what the next unused
+/// ID is.
+template <class T> class NumberedValues {
+  DenseMap<unsigned, T> Vals;
+  unsigned NextUnusedID = 0;
+
+public:
+  unsigned getNext() const { return NextUnusedID; }
+  T get(unsigned ID) const { return Vals.lookup(ID); }
+  void add(unsigned ID, T V) {
+    assert(ID >= NextUnusedID && "Invalid value ID");
+    Vals.insert({ID, V});
+    NextUnusedID = ID + 1;
+  }
+};
+
+} // end namespace llvm
+
+#endif

llvm/include/llvm/AsmParser/SlotMapping.h

@@ -14,6 +14,7 @@
 #define LLVM_ASMPARSER_SLOTMAPPING_H
 
 #include "llvm/ADT/StringMap.h"
+#include "llvm/AsmParser/NumberedValues.h"
 #include "llvm/IR/TrackingMDRef.h"
 #include <map>
 #include <vector>
@@ -30,7 +31,7 @@ class Type;
 /// textual references to the values in the module can be parsed outside of the
 /// module's source.
 struct SlotMapping {
-  std::vector<GlobalValue *> GlobalValues;
+  NumberedValues<GlobalValue *> GlobalValues;
   std::map<unsigned, TrackingMDNodeRef> MetadataNodes;
   StringMap<Type *> NamedTypes;
   std::map<unsigned, Type *> Types;