Fix __attribute__((annotate("")) with non-zero globals AS

[arichardson]

Summary

The existing code attempting to bitcast from a value in the default
globals AS to i8 addrspace(0)* was triggering an assertion failure for me.
I found this while compiling poppler for CHERI-RISC-V (we use AS200 for
all globals). The test case uses AMDGPU since that is one of the in-tree
targets with a non-zero default globals address space.
The new test previously triggered a "Invalid constantexpr bitcast!"
assertion an now correctly generates code with addrspace(1) pointers.

[arichardson]

ping?

[arichardson]

rebase

[rjmccall]

Sorry for the delay; LGTM.

clang/lib/CodeGen/CodeGenModule.cpp

IntAlignInBytes =
     C.toCharUnitsFromBits(C.getTargetInfo().getIntAlign()).getQuantity();
   CharTy =
     llvm::IntegerType::get(LLVMContext, C.getTargetInfo().getCharWidth());
   IntTy = llvm::IntegerType::get(LLVMContext, C.getTargetInfo().getIntWidth());
   IntPtrTy = llvm::IntegerType::get(LLVMContext,
     C.getTargetInfo().getMaxPointerWidth());
   Int8PtrTy = Int8Ty->getPointerTo(0);
   Int8PtrPtrTy = Int8PtrTy->getPointerTo(0);
-  AllocaInt8PtrTy = Int8Ty->getPointerTo(
-      M.getDataLayout().getAllocaAddrSpace());
+  const llvm::DataLayout &DL = M.getDataLayout();
+  AllocaInt8PtrTy = Int8Ty->getPointerTo(DL.getAllocaAddrSpace());
+  GlobalsInt8PtrTy = Int8Ty->getPointerTo(DL.getDefaultGlobalsAddressSpace());
   ASTAllocaAddressSpace = getTargetCodeGenInfo().getASTAllocaAddressSpace();
 
   RuntimeCC = getTargetCodeGenInfo().getABIInfo().getRuntimeCC();
 
   if (LangOpts.ObjC)
     createObjCRuntime();
   if (LangOpts.OpenCL)
     createOpenCLRuntime();
llvm::Constant *CodeGenModule::EmitAnnotationLineNo(SourceLocation L) {
   unsigned LineNo = PLoc.isValid() ? PLoc.getLine() :
     SM.getExpansionLineNumber(L);
   return llvm::ConstantInt::get(Int32Ty, LineNo);
 }
 
 llvm::Constant *CodeGenModule::EmitAnnotationArgs(const AnnotateAttr *Attr) {
   ArrayRef<Expr *> Exprs = {Attr->args_begin(), Attr->args_size()};
   if (Exprs.empty())
-    return llvm::ConstantPointerNull::get(Int8PtrTy);
+    return llvm::ConstantPointerNull::get(GlobalsInt8PtrTy);
 
   llvm::FoldingSetNodeID ID;
   for (Expr *E : Exprs) {
     ID.Add(cast<clang::ConstantExpr>(E)->getAPValueResult());
   }
   llvm::Constant *&Lookup = AnnotationArgs[ID.ComputeHash()];
   if (Lookup)
     return Lookup;
 
   llvm::SmallVector<llvm::Constant *, 4> LLVMArgs;
   LLVMArgs.reserve(Exprs.size());
   ConstantEmitter ConstEmiter(*this);
   llvm::transform(Exprs, std::back_inserter(LLVMArgs), [&](const Expr *E) {
     const auto *CE = cast<clang::ConstantExpr>(E);
     return ConstEmiter.emitAbstract(CE->getBeginLoc(), CE->getAPValueResult(),
                                     CE->getType());
   });
   auto *Struct = llvm::ConstantStruct::getAnon(LLVMArgs);
   auto *GV = new llvm::GlobalVariable(getModule(), Struct->getType(), true,
                                       llvm::GlobalValue::PrivateLinkage, Struct,
                                       ".args");
   GV->setSection(AnnotationSection);
   GV->setUnnamedAddr(llvm::GlobalValue::UnnamedAddr::Global);
-  auto *Bitcasted = llvm::ConstantExpr::getBitCast(GV, Int8PtrTy);
+  auto *Bitcasted = llvm::ConstantExpr::getBitCast(GV, GlobalsInt8PtrTy);
 
   Lookup = Bitcasted;
   return Bitcasted;
 }
 
 llvm::Constant *CodeGenModule::EmitAnnotateAttr(llvm::GlobalValue *GV,
                                                 const AnnotateAttr *AA,
                                                 SourceLocation L) {
   // Get the globals for file name, annotation, and the line number.
   llvm::Constant *AnnoGV = EmitAnnotationString(AA->getAnnotation()),
                  *UnitGV = EmitAnnotationUnit(L),
                  *LineNoCst = EmitAnnotationLineNo(L),
                  *Args = EmitAnnotationArgs(AA);
 
-  llvm::Constant *ASZeroGV = GV;
-  if (GV->getAddressSpace() != 0) {
-    ASZeroGV = llvm::ConstantExpr::getAddrSpaceCast(
-                   GV, GV->getValueType()->getPointerTo(0));
+  llvm::Constant *GVInGlobalsAS = GV;
+  if (GV->getAddressSpace() !=
+      getDataLayout().getDefaultGlobalsAddressSpace()) {
+    GVInGlobalsAS = llvm::ConstantExpr::getAddrSpaceCast(
+        GV, GV->getValueType()->getPointerTo(
+                getDataLayout().getDefaultGlobalsAddressSpace()));
   }
 
   // Create the ConstantStruct for the global annotation.
   llvm::Constant *Fields[] = {
-      llvm::ConstantExpr::getBitCast(ASZeroGV, Int8PtrTy),
-      llvm::ConstantExpr::getBitCast(AnnoGV, Int8PtrTy),
-      llvm::ConstantExpr::getBitCast(UnitGV, Int8PtrTy),
+      llvm::ConstantExpr::getBitCast(GVInGlobalsAS, GlobalsInt8PtrTy),
+      llvm::ConstantExpr::getBitCast(AnnoGV, GlobalsInt8PtrTy),
+      llvm::ConstantExpr::getBitCast(UnitGV, GlobalsInt8PtrTy),
       LineNoCst,
       Args,
   };
   return llvm::ConstantStruct::getAnon(Fields);
 }
 
 void CodeGenModule::AddGlobalAnnotations(const ValueDecl *D,
                                          llvm::GlobalValue *GV) {

clang/lib/CodeGen/CodeGenTypeCache.h

struct CodeGenTypeCache {
   };
 
   /// void* in alloca address space
   union {
     llvm::PointerType *AllocaVoidPtrTy;
     llvm::PointerType *AllocaInt8PtrTy;
   };
 
+  /// void* in default globals address space
+  union {
+    llvm::PointerType *GlobalsVoidPtrTy;
+    llvm::PointerType *GlobalsInt8PtrTy;
+  };
+
   /// The size and alignment of the builtin C type 'int'.  This comes
   /// up enough in various ABI lowering tasks to be worth pre-computing.
   union {
     unsigned char IntSizeInBytes;
     unsigned char IntAlignInBytes;
   };
   CharUnits getIntSize() const {
     return CharUnits::fromQuantity(IntSizeInBytes);

clang/test/CodeGen/annotations-global.c

 // RUN: %clang_cc1 %s -emit-llvm -o %t1
 // RUN: FileCheck --check-prefix=FOO %s < %t1
 // RUN: FileCheck --check-prefix=A %s < %t1
 // RUN: FileCheck --check-prefix=BAR %s < %t1
 // RUN: FileCheck --check-prefix=FOOS %s < %t1
 // RUN: FileCheck --check-prefix=ADDRSPACE %s < %t1
+// RUN: %clang_cc1 %s -triple r600 -emit-llvm -o - | FileCheck %s --check-prefix AS1-GLOBALS
 // END.
 
 static __attribute((annotate("sfoo_0"))) __attribute((annotate("sfoo_1"))) char sfoo;
 __attribute((annotate("foo_0"))) __attribute((annotate("foo_1"))) char foo;
 
 void __attribute((annotate("ann_a_0"))) __attribute((annotate("ann_a_1"))) __attribute((annotate("ann_a_2"))) __attribute((annotate("ann_a_3"))) a(char *a);
 void __attribute((annotate("ann_a_0"))) __attribute((annotate("ann_a_1"))) a(char *a) {
   __attribute__((annotate("bar_0"))) __attribute__((annotate("bar_1"))) static char bar;

 // BAR: target triple
 // BAR: private unnamed_addr constant [6 x i8] c"bar_{{.}}\00", section "llvm.metadata"
 // BAR: private unnamed_addr constant [6 x i8] c"bar_{{.}}\00", section "llvm.metadata"
 // BAR-NOT: bar_
 // BAR: @llvm.global.annotations = appending global [11 x { i8*, i8*, i8*, i32, i8* }] {{.*}}i8* @a.bar{{.*}}i8* @a.bar{{.*}}, section "llvm.metadata"
 
 // ADDRSPACE: target triple
 // ADDRSPACE: @llvm.global.annotations = appending global {{.*}} addrspacecast (i8 addrspace(1)* @addrspace1_var to i8*), {{.*}}
+
+// AS1-GLOBALS: target datalayout = "{{.+}}-A5-G1"
+// AS1-GLOBALS: @llvm.global.annotations = appending addrspace(1) global [11 x { i8 addrspace(1)*, i8 addrspace(1)*, i8 addrspace(1)*, i32, i8 addrspace(1)* }]
+// AS1-GLOBALS-SAME: { i8 addrspace(1)* @a.bar,
+// AS1-GLOBALS-SAME: { i8 addrspace(1)* @addrspace1_var,