ModuleUtils: Stop using comdat members to generate unique module ids.

[pcc]

Summary

It is possible for two modules to define the same set of external
symbols without causing a duplicate symbol error at link time,
as long as each of the symbols is a comdat member. So we cannot
use them as part of a unique id for the module.

[rnk]

Looks good.

llvm/trunk/include/llvm/Transforms/Utils/ModuleUtils.h

 ///
 /// After this routine finishes, the only remaining `Function`s in \p
 /// DeadComdatFunctions are those where every member of the comdat is listed
 /// and thus removing them is safe (provided *all* are removed).
 void filterDeadComdatFunctions(
     Module &M, SmallVectorImpl<Function *> &DeadComdatFunctions);
 
 /// \brief Produce a unique identifier for this module by taking the MD5 sum of
-/// the names of the module's strong external symbols.
+/// the names of the module's strong external symbols that are not comdat
+/// members.
 ///
 /// This identifier is normally guaranteed to be unique, or the program would
 /// fail to link due to multiply defined symbols.
 ///
 /// If the module has no strong external symbols (such a module may still have a
 /// semantic effect if it performs global initialization), we cannot produce a
 /// unique identifier for this module, so we return the empty string.
 std::string getUniqueModuleId(Module *M);
 
 } // End llvm namespace
 
 #endif //  LLVM_TRANSFORMS_UTILS_MODULEUTILS_H

llvm/trunk/lib/Transforms/Utils/ModuleUtils.cpp

void llvm::filterDeadComdatFunctions(
   });
 }
 
 std::string llvm::getUniqueModuleId(Module *M) {
   MD5 Md5;
   bool ExportsSymbols = false;
   auto AddGlobal = [&](GlobalValue &GV) {
     if (GV.isDeclaration() || GV.getName().startswith("llvm.") ||
-        !GV.hasExternalLinkage())
+        !GV.hasExternalLinkage() || GV.hasComdat())
       return;
     ExportsSymbols = true;
     Md5.update(GV.getName());
     Md5.update(ArrayRef<uint8_t>{0});
   };
 
   for (auto &F : *M)
     AddGlobal(F);

llvm/trunk/test/Transforms/ThinLTOBitcodeWriter/filter-alias.ll

 ; RUN: opt -thinlto-bc -o %t %s
 ; RUN: llvm-modextract -n 0 -o - %t | llvm-dis | FileCheck --check-prefix=CHECK0 %s
 ; RUN: llvm-modextract -n 1 -o - %t | llvm-dis | FileCheck --check-prefix=CHECK1 %s
 ; CHECK0: @al = external global i8*
 ; CHECK1: @al = unnamed_addr alias i8*,
 
 target datalayout = "e-m:w-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-pc-windows-msvc19.0.24215"
 
 $al = comdat any
 
 @anon = private unnamed_addr constant { [1 x i8*] } { [1 x i8*] [i8* null] }, comdat($al), !type !0
 
 @al = external unnamed_addr alias i8*, getelementptr inbounds ({ [1 x i8*] }, { [1 x i8*] }* @anon, i32 0, i32 0, i32 1)
 
+@foo = global i32 1
+
 !0 = !{i64 8, !"?AVA@@"}

llvm/trunk/test/Transforms/ThinLTOBitcodeWriter/unsplittable.ll

 declare void @sink(i8*)
 
 ; CHECK: define internal void @f()
 define internal void @f() {
   call void @sink(i8* @g)
   ret void
 }
 
+$h = comdat any
+; CHECK: define void @h() comdat
+define void @h() comdat {
+  ret void
+}
+
 !0 = !{i32 0, !"typeid"}