Respect llvm.used in Internalize.

The language reference says that:

"If a symbol appears in the @llvm.used list, then the compiler,
assembler, and linker are required to treat the symbol as if there is
a reference to the symbol that it cannot see"

Since even the linker cannot see the reference, we must assume that
the reference can be using the symbol table. For example, a user can add
__attribute__((used)) to a debug helper function like dump and use it from
a debugger.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187103 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 41 insertions, 21 deletions

diff --git a/lib/Transforms/IPO/GlobalOpt.cpp b/lib/Transforms/IPO/GlobalOpt.cpp
index 20af15e..64cd515 100644
--- a/lib/Transforms/IPO/GlobalOpt.cpp
+++ b/lib/Transforms/IPO/GlobalOpt.cpp
@@ -38,6 +38,7 @@
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Target/TargetLibraryInfo.h"
+#include "llvm/Transforms/Utils/ModuleUtils.h"
 #include <algorithm>
 using namespace llvm;
 
@@ -3040,24 +3041,6 @@ bool GlobalOpt::OptimizeGlobalCtorsList(GlobalVariable *&GCL) {
   return true;
 }
 
-/// \brief Given "llvm.used" or "llvm.compiler.used" as a global name, collect
-/// the initializer elements of that global in Set and return the global itself.
-static GlobalVariable *
-collectUsedGlobalVariables(Module &M, const char *Name,
-                           SmallPtrSet<GlobalValue *, 8> &Set) {
-  GlobalVariable *GV = M.getGlobalVariable(Name);
-  if (!GV || !GV->hasInitializer())
-    return GV;
-
-  const ConstantArray *Init = cast<ConstantArray>(GV->getInitializer());
-  for (unsigned I = 0, E = Init->getNumOperands(); I != E; ++I) {
-    Value *Op = Init->getOperand(I);
-    GlobalValue *G = cast<GlobalValue>(Op->stripPointerCastsNoFollowAliases());
-    Set.insert(G);
-  }
-  return GV;
-}
-
 static int compareNames(const void *A, const void *B) {
   const GlobalValue *VA = *reinterpret_cast<GlobalValue* const*>(A);
   const GlobalValue *VB = *reinterpret_cast<GlobalValue* const*>(B);
@@ -3107,9 +3090,8 @@ class LLVMUsed {
 
 public:
   LLVMUsed(Module &M) {
-    UsedV = collectUsedGlobalVariables(M, "llvm.used", Used);
-    CompilerUsedV =
-        collectUsedGlobalVariables(M, "llvm.compiler.used", CompilerUsed);
+    UsedV = collectUsedGlobalVariables(M, Used, false);
+    CompilerUsedV = collectUsedGlobalVariables(M, CompilerUsed, true);
   }
   typedef SmallPtrSet<GlobalValue *, 8>::iterator iterator;
   iterator usedBegin() { return Used.begin(); }
diff --git a/lib/Transforms/IPO/Internalize.cpp b/lib/Transforms/IPO/Internalize.cpp
index 4bfab5b..d56a06f 100644
--- a/lib/Transforms/IPO/Internalize.cpp
+++ b/lib/Transforms/IPO/Internalize.cpp
@@ -15,6 +15,7 @@
 
 #define DEBUG_TYPE "internalize"
 #include "llvm/Transforms/IPO.h"
+#include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/CallGraph.h"
 #include "llvm/IR/Module.h"
@@ -22,6 +23,7 @@
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
+#include "llvm/Transforms/Utils/ModuleUtils.h"
 #include <fstream>
 #include <set>
 using namespace llvm;
@@ -117,6 +119,24 @@ bool InternalizePass::runOnModule(Module &M) {
   // type of call-back in CodeGen.
   ExternalNames.insert("__stack_chk_fail");
 
+  SmallPtrSet<GlobalValue *, 8> Used;
+  collectUsedGlobalVariables(M, Used, false);
+
+  // We must assume that globals in llvm.used have a reference that not even
+  // the linker can see, so we don't internalize them.
+  // For llvm.compiler.used the situation is a bit fuzzy. The assembler and
+  // linker can drop those symbols. If this pass is running as part of LTO,
+  // one might think that it could just drop llvm.compiler.used. The problem
+  // is that even in LTO llvm doesn't see every reference. For example,
+  // we don't see references from function local inline assembly. To be
+  // conservative, we internalize symbols in llvm.compiler.used, but we
+  // keep llvm.compiler.used so that the symbol is not deleted by llvm.
+  for (SmallPtrSet<GlobalValue *, 8>::iterator I = Used.begin(), E = Used.end();
+       I != E; ++I) {
+    GlobalValue *V = *I;
+    ExternalNames.insert(V->getName());
+  }
+
   // Mark all functions not in the api as internal.
   // FIXME: maybe use private linkage?
   for (Module::iterator I = M.begin(), E = M.end(); I != E; ++I)
diff --git a/lib/Transforms/Utils/ModuleUtils.cpp b/lib/Transforms/Utils/ModuleUtils.cpp
index d090b48..ff6e6f9 100644
--- a/lib/Transforms/Utils/ModuleUtils.cpp
+++ b/lib/Transforms/Utils/ModuleUtils.cpp
@@ -12,6 +12,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/Transforms/Utils/ModuleUtils.h"
+#include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/IRBuilder.h"
@@ -62,3 +63,20 @@ void llvm::appendToGlobalCtors(Module &M, Function *F, int Priority) {
 void llvm::appendToGlobalDtors(Module &M, Function *F, int Priority) {
   appendToGlobalArray("llvm.global_dtors", M, F, Priority);
 }
+
+GlobalVariable *
+llvm::collectUsedGlobalVariables(Module &M, SmallPtrSet<GlobalValue *, 8> &Set,
+                                 bool CompilerUsed) {
+  const char *Name = CompilerUsed ? "llvm.compiler.used" : "llvm.used";
+  GlobalVariable *GV = M.getGlobalVariable(Name);
+  if (!GV || !GV->hasInitializer())
+    return GV;
+
+  const ConstantArray *Init = cast<ConstantArray>(GV->getInitializer());
+  for (unsigned I = 0, E = Init->getNumOperands(); I != E; ++I) {
+    Value *Op = Init->getOperand(I);
+    GlobalValue *G = cast<GlobalValue>(Op->stripPointerCastsNoFollowAliases());
+    Set.insert(G);
+  }
+  return GV;
+}