[IR] Disallow llvm.global_ctors and llvm.global_dtors of the 2-field form in textual format

The 3-field form was introduced by D3499 in 2014 and the legacy 2-field
form was planned to be removed in LLVM 4.0

For the textual format, this patch migrates the existing 2-field form to
use the 3-field form and deletes the compatibility code.
test/Verifier/global-ctors-2.ll checks we have a friendly error message.

For bitcode, lib/IR/AutoUpgrade UpgradeGlobalVariables will upgrade the
2-field form (add i8* null as the third field).

Reviewed By: rnk, dexonsmith

Differential Revision: https://reviews.llvm.org/D61547

llvm-svn: 360742

5 files changed, 56 insertions, 46 deletions

diff --git a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
index d3b8c4da5f4..28872566863 100644
--- a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -2794,8 +2794,14 @@ Error BitcodeReader::globalCleanup() {
   }
 
   // Look for global variables which need to be renamed.
+  std::vector<std::pair<GlobalVariable *, GlobalVariable *>> UpgradedVariables;
   for (GlobalVariable &GV : TheModule->globals())
-    UpgradeGlobalVariable(&GV);
+    if (GlobalVariable *Upgraded = UpgradeGlobalVariable(&GV))
+      UpgradedVariables.emplace_back(&GV, Upgraded);
+  for (auto &Pair : UpgradedVariables) {
+    Pair.first->eraseFromParent();
+    TheModule->getGlobalList().push_back(Pair.second);
+  }
 
   // Force deallocation of memory for these vectors to favor the client that
   // want lazy deserialization.
diff --git a/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp b/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
index be874aca6d4..3d2e5e5ea00 100644
--- a/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
@@ -1966,7 +1966,7 @@ struct Structor {
 /// priority.
 void AsmPrinter::EmitXXStructorList(const DataLayout &DL, const Constant *List,
                                     bool isCtor) {
-  // Should be an array of '{ int, void ()* }' structs.  The first value is the
+  // Should be an array of '{ i32, void ()*, i8* }' structs.  The first value is the
   // init priority.
   if (!isa<ConstantArray>(List)) return;
 
@@ -1974,12 +1974,10 @@ void AsmPrinter::EmitXXStructorList(const DataLayout &DL, const Constant *List,
   const ConstantArray *InitList = dyn_cast<ConstantArray>(List);
   if (!InitList) return; // Not an array!
   StructType *ETy = dyn_cast<StructType>(InitList->getType()->getElementType());
-  // FIXME: Only allow the 3-field form in LLVM 4.0.
-  if (!ETy || ETy->getNumElements() < 2 || ETy->getNumElements() > 3)
-    return; // Not an array of two or three elements!
-  if (!isa<IntegerType>(ETy->getTypeAtIndex(0U)) ||
-      !isa<PointerType>(ETy->getTypeAtIndex(1U))) return; // Not (int, ptr).
-  if (ETy->getNumElements() == 3 && !isa<PointerType>(ETy->getTypeAtIndex(2U)))
+  if (!ETy || ETy->getNumElements() != 3 ||
+      !isa<IntegerType>(ETy->getTypeAtIndex(0U)) ||
+      !isa<PointerType>(ETy->getTypeAtIndex(1U)) ||
+      !isa<PointerType>(ETy->getTypeAtIndex(2U)))
     return; // Not (int, ptr, ptr).
 
   // Gather the structors in a form that's convenient for sorting by priority.
@@ -1995,7 +1993,7 @@ void AsmPrinter::EmitXXStructorList(const DataLayout &DL, const Constant *List,
     Structor &S = Structors.back();
     S.Priority = Priority->getLimitedValue(65535);
     S.Func = CS->getOperand(1);
-    if (ETy->getNumElements() == 3 && !CS->getOperand(2)->isNullValue())
+    if (!CS->getOperand(2)->isNullValue())
       S.ComdatKey =
           dyn_cast<GlobalValue>(CS->getOperand(2)->stripPointerCasts());
   }
diff --git a/llvm/lib/IR/AutoUpgrade.cpp b/llvm/lib/IR/AutoUpgrade.cpp
index c0fd3cd7cbd..e6a096a8855 100644
--- a/llvm/lib/IR/AutoUpgrade.cpp
+++ b/llvm/lib/IR/AutoUpgrade.cpp
@@ -805,9 +805,35 @@ bool llvm::UpgradeIntrinsicFunction(Function *F, Function *&NewFn) {
   return Upgraded;
 }
 
-bool llvm::UpgradeGlobalVariable(GlobalVariable *GV) {
-  // Nothing to do yet.
-  return false;
+GlobalVariable *llvm::UpgradeGlobalVariable(GlobalVariable *GV) {
+  if (!(GV->hasName() && (GV->getName() == "llvm.global_ctors" ||
+                          GV->getName() == "llvm.global_dtors")) ||
+      !GV->hasInitializer())
+    return nullptr;
+  ArrayType *ATy = dyn_cast<ArrayType>(GV->getValueType());
+  if (!ATy)
+    return nullptr;
+  StructType *STy = dyn_cast<StructType>(ATy->getElementType());
+  if (!STy || STy->getNumElements() != 2)
+    return nullptr;
+
+  LLVMContext &C = GV->getContext();
+  IRBuilder<> IRB(C);
+  auto EltTy = StructType::get(STy->getElementType(0), STy->getElementType(1),
+                               IRB.getInt8PtrTy());
+  Constant *Init = GV->getInitializer();
+  unsigned N = Init->getNumOperands();
+  std::vector<Constant *> NewCtors(N);
+  for (unsigned i = 0; i != N; ++i) {
+    auto Ctor = cast<Constant>(Init->getOperand(i));
+    NewCtors[i] = ConstantStruct::get(
+        EltTy, Ctor->getAggregateElement(0u), Ctor->getAggregateElement(1),
+        Constant::getNullValue(IRB.getInt8PtrTy()));
+  }
+  Constant *NewInit = ConstantArray::get(ArrayType::get(EltTy, N), NewCtors);
+
+  return new GlobalVariable(NewInit->getType(), false, GV->getLinkage(),
+                            NewInit, GV->getName());
 }
 
 // Handles upgrading SSE2/AVX2/AVX512BW PSLLDQ intrinsics by converting them
diff --git a/llvm/lib/IR/Verifier.cpp b/llvm/lib/IR/Verifier.cpp
index 1ba64f33380..f7004cf4eae 100644
--- a/llvm/lib/IR/Verifier.cpp
+++ b/llvm/lib/IR/Verifier.cpp
@@ -641,18 +641,18 @@ void Verifier::visitGlobalVariable(const GlobalVariable &GV) {
       PointerType *FuncPtrTy =
           FunctionType::get(Type::getVoidTy(Context), false)->
           getPointerTo(DL.getProgramAddressSpace());
-      // FIXME: Reject the 2-field form in LLVM 4.0.
       Assert(STy &&
                  (STy->getNumElements() == 2 || STy->getNumElements() == 3) &&
                  STy->getTypeAtIndex(0u)->isIntegerTy(32) &&
                  STy->getTypeAtIndex(1) == FuncPtrTy,
              "wrong type for intrinsic global variable", &GV);
-      if (STy->getNumElements() == 3) {
-        Type *ETy = STy->getTypeAtIndex(2);
-        Assert(ETy->isPointerTy() &&
-                   cast<PointerType>(ETy)->getElementType()->isIntegerTy(8),
-               "wrong type for intrinsic global variable", &GV);
-      }
+      Assert(STy->getNumElements() == 3,
+             "the third field of the element type is mandatory, "
+             "specify i8* null to migrate from the obsoleted 2-field form");
+      Type *ETy = STy->getTypeAtIndex(2);
+      Assert(ETy->isPointerTy() &&
+                 cast<PointerType>(ETy)->getElementType()->isIntegerTy(8),
+             "wrong type for intrinsic global variable", &GV);
     }
   }
 
diff --git a/llvm/lib/Transforms/Utils/ModuleUtils.cpp b/llvm/lib/Transforms/Utils/ModuleUtils.cpp
index b076e7503c6..c84beceee19 100644
--- a/llvm/lib/Transforms/Utils/ModuleUtils.cpp
+++ b/llvm/lib/Transforms/Utils/ModuleUtils.cpp
@@ -27,44 +27,24 @@ static void appendToGlobalArray(const char *Array, Module &M, Function *F,
   // Get the current set of static global constructors and add the new ctor
   // to the list.
   SmallVector<Constant *, 16> CurrentCtors;
-  StructType *EltTy;
+  StructType *EltTy = StructType::get(
+      IRB.getInt32Ty(), PointerType::getUnqual(FnTy), IRB.getInt8PtrTy());
   if (GlobalVariable *GVCtor = M.getNamedGlobal(Array)) {
-    ArrayType *ATy = cast<ArrayType>(GVCtor->getValueType());
-    StructType *OldEltTy = cast<StructType>(ATy->getElementType());
-    // Upgrade a 2-field global array type to the new 3-field format if needed.
-    if (Data && OldEltTy->getNumElements() < 3)
-      EltTy = StructType::get(IRB.getInt32Ty(), PointerType::getUnqual(FnTy),
-                              IRB.getInt8PtrTy());
-    else
-      EltTy = OldEltTy;
     if (Constant *Init = GVCtor->getInitializer()) {
       unsigned n = Init->getNumOperands();
       CurrentCtors.reserve(n + 1);
-      for (unsigned i = 0; i != n; ++i) {
-        auto Ctor = cast<Constant>(Init->getOperand(i));
-        if (EltTy != OldEltTy)
-          Ctor =
-              ConstantStruct::get(EltTy, Ctor->getAggregateElement((unsigned)0),
-                                  Ctor->getAggregateElement(1),
-                                  Constant::getNullValue(IRB.getInt8PtrTy()));
-        CurrentCtors.push_back(Ctor);
-      }
+      for (unsigned i = 0; i != n; ++i)
+        CurrentCtors.push_back(cast<Constant>(Init->getOperand(i)));
     }
     GVCtor->eraseFromParent();
-  } else {
-    // Use the new three-field struct if there isn't one already.
-    EltTy = StructType::get(IRB.getInt32Ty(), PointerType::getUnqual(FnTy),
-                            IRB.getInt8PtrTy());
   }
 
-  // Build a 2 or 3 field global_ctor entry.  We don't take a comdat key.
+  // Build a 3 field global_ctor entry.  We don't take a comdat key.
   Constant *CSVals[3];
   CSVals[0] = IRB.getInt32(Priority);
   CSVals[1] = F;
-  // FIXME: Drop support for the two element form in LLVM 4.0.
-  if (EltTy->getNumElements() >= 3)
-    CSVals[2] = Data ? ConstantExpr::getPointerCast(Data, IRB.getInt8PtrTy())
-                     : Constant::getNullValue(IRB.getInt8PtrTy());
+  CSVals[2] = Data ? ConstantExpr::getPointerCast(Data, IRB.getInt8PtrTy())
+                   : Constant::getNullValue(IRB.getInt8PtrTy());
   Constant *RuntimeCtorInit =
       ConstantStruct::get(EltTy, makeArrayRef(CSVals, EltTy->getNumElements()));