[OpenCL] Add missing address spaces in IR generation of blocks

Modify ObjC blocks impl wrt address spaces as follows:

- keep default private address space for blocks generated
as local variables (with captures);

- add global address space for global block literals (no captures);

- make the block invoke function and enqueue_kernel prototype with
the generic AS block pointer parameter to accommodate both 
private and global AS cases from above;

- add block handling into default AS because it's implemented as
a special pointer type (BlockPointer) in the frontend and therefore
it is used as a pointer everywhere. This is also needed to accommodate
both private and global AS blocks for the two cases above.

- removes ObjC RT specific symbols (NSConcreteStackBlock and
NSConcreteGlobalBlock) in the OpenCL mode.

Review: https://reviews.llvm.org/D28814
llvm-svn: 293286

5 files changed, 115 insertions, 44 deletions

diff --git a/clang/lib/AST/Expr.cpp b/clang/lib/AST/Expr.cpp
index 14f31d0c6b8..366e5bf404f 100644
--- a/clang/lib/AST/Expr.cpp
+++ b/clang/lib/AST/Expr.cpp
@@ -1571,8 +1571,9 @@ bool CastExpr::CastConsistency() const {
     goto CheckNoBasePath;
 
   case CK_AddressSpaceConversion:
-    assert(getType()->isPointerType());
-    assert(getSubExpr()->getType()->isPointerType());
+    assert(getType()->isPointerType() || getType()->isBlockPointerType());
+    assert(getSubExpr()->getType()->isPointerType() ||
+           getSubExpr()->getType()->isBlockPointerType());
     assert(getType()->getPointeeType().getAddressSpace() !=
            getSubExpr()->getType()->getPointeeType().getAddressSpace());
   // These should not have an inheritance path.
diff --git a/clang/lib/CodeGen/CGBlocks.cpp b/clang/lib/CodeGen/CGBlocks.cpp
index b250b9a32b1..53288a69e2d 100644
--- a/clang/lib/CodeGen/CGBlocks.cpp
+++ b/clang/lib/CodeGen/CGBlocks.cpp
@@ -718,7 +718,12 @@ llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo) {
 
   // Otherwise, we have to emit this as a local block.
 
-  llvm::Constant *isa = CGM.getNSConcreteStackBlock();
+  llvm::Constant *isa =
+      (!CGM.getContext().getLangOpts().OpenCL)
+          ? CGM.getNSConcreteStackBlock()
+          : CGM.getNullPointer(cast<llvm::PointerType>(
+                                   CGM.getNSConcreteStackBlock()->getType()),
+                               QualType(getContext().VoidPtrTy));
   isa = llvm::ConstantExpr::getBitCast(isa, VoidPtrTy);
 
   // Build the block descriptor.
@@ -906,9 +911,8 @@ llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo) {
 
   // Cast to the converted block-pointer type, which happens (somewhat
   // unfortunately) to be a pointer to function type.
-  llvm::Value *result =
-    Builder.CreateBitCast(blockAddr.getPointer(),
-                          ConvertType(blockInfo.getBlockExpr()->getType()));
+  llvm::Value *result = Builder.CreatePointerCast(
+      blockAddr.getPointer(), ConvertType(blockInfo.getBlockExpr()->getType()));
 
   return result;
 }
@@ -976,21 +980,41 @@ RValue CodeGenFunction::EmitBlockCallExpr(const CallExpr *E,
   llvm::Value *BlockPtr = EmitScalarExpr(E->getCallee());
 
   // Get a pointer to the generic block literal.
+  // For OpenCL we generate generic AS void ptr to be able to reuse the same
+  // block definition for blocks with captures generated as private AS local
+  // variables and without captures generated as global AS program scope
+  // variables.
+  unsigned AddrSpace = 0;
+  if (getLangOpts().OpenCL)
+    AddrSpace = getContext().getTargetAddressSpace(LangAS::opencl_generic);
+
   llvm::Type *BlockLiteralTy =
-    llvm::PointerType::getUnqual(CGM.getGenericBlockLiteralType());
+      llvm::PointerType::get(CGM.getGenericBlockLiteralType(), AddrSpace);
 
   // Bitcast the callee to a block literal.
-  BlockPtr = Builder.CreateBitCast(BlockPtr, BlockLiteralTy, "block.literal");
+  BlockPtr =
+      Builder.CreatePointerCast(BlockPtr, BlockLiteralTy, "block.literal");
 
   // Get the function pointer from the literal.
   llvm::Value *FuncPtr =
     Builder.CreateStructGEP(CGM.getGenericBlockLiteralType(), BlockPtr, 3);
 
-  BlockPtr = Builder.CreateBitCast(BlockPtr, VoidPtrTy);
 
   // Add the block literal.
   CallArgList Args;
-  Args.add(RValue::get(BlockPtr), getContext().VoidPtrTy);
+
+  QualType VoidPtrQualTy = getContext().VoidPtrTy;
+  llvm::Type *GenericVoidPtrTy = VoidPtrTy;
+  if (getLangOpts().OpenCL) {
+    GenericVoidPtrTy = Builder.getInt8PtrTy(
+        getContext().getTargetAddressSpace(LangAS::opencl_generic));
+    VoidPtrQualTy =
+        getContext().getPointerType(getContext().getAddrSpaceQualType(
+            getContext().VoidTy, LangAS::opencl_generic));
+  }
+
+  BlockPtr = Builder.CreatePointerCast(BlockPtr, GenericVoidPtrTy);
+  Args.add(RValue::get(BlockPtr), VoidPtrQualTy);
 
   QualType FnType = BPT->getPointeeType();
 
@@ -1097,7 +1121,12 @@ static llvm::Constant *buildGlobalBlock(CodeGenModule &CGM,
   auto fields = builder.beginStruct();
 
   // isa
-  fields.add(CGM.getNSConcreteGlobalBlock());
+  fields.add(
+      (!CGM.getContext().getLangOpts().OpenCL)
+          ? CGM.getNSConcreteGlobalBlock()
+          : CGM.getNullPointer(cast<llvm::PointerType>(
+                                   CGM.getNSConcreteGlobalBlock()->getType()),
+                               QualType(CGM.getContext().VoidPtrTy)));
 
   // __flags
   BlockFlags flags = BLOCK_IS_GLOBAL | BLOCK_HAS_SIGNATURE;
@@ -1114,16 +1143,19 @@ static llvm::Constant *buildGlobalBlock(CodeGenModule &CGM,
   // Descriptor
   fields.add(buildBlockDescriptor(CGM, blockInfo));
 
-  llvm::Constant *literal =
-    fields.finishAndCreateGlobal("__block_literal_global",
-                                 blockInfo.BlockAlign,
-                                 /*constant*/ true);
+  unsigned AddrSpace = 0;
+  if (CGM.getContext().getLangOpts().OpenCL)
+    AddrSpace = CGM.getContext().getTargetAddressSpace(LangAS::opencl_global);
+
+  llvm::Constant *literal = fields.finishAndCreateGlobal(
+      "__block_literal_global", blockInfo.BlockAlign,
+      /*constant*/ true, llvm::GlobalVariable::InternalLinkage, AddrSpace);
 
   // Return a constant of the appropriately-casted type.
   llvm::Type *RequiredType =
     CGM.getTypes().ConvertType(blockInfo.getBlockExpr()->getType());
   llvm::Constant *Result =
-      llvm::ConstantExpr::getBitCast(literal, RequiredType);
+      llvm::ConstantExpr::getPointerCast(literal, RequiredType);
   CGM.setAddrOfGlobalBlock(blockInfo.BlockExpression, Result);
   return Result;
 }
@@ -1155,9 +1187,13 @@ void CodeGenFunction::setBlockContextParameter(const ImplicitParamDecl *D,
 
   // Instead of messing around with LocalDeclMap, just set the value
   // directly as BlockPointer.
-  BlockPointer = Builder.CreateBitCast(arg,
-                                       BlockInfo->StructureType->getPointerTo(),
-                                       "block");
+  BlockPointer = Builder.CreatePointerCast(
+      arg,
+      BlockInfo->StructureType->getPointerTo(
+          getContext().getLangOpts().OpenCL
+              ? getContext().getTargetAddressSpace(LangAS::opencl_generic)
+              : 0),
+      "block");
 }
 
 Address CodeGenFunction::LoadBlockStruct() {
@@ -1196,6 +1232,15 @@ CodeGenFunction::GenerateBlockFunction(GlobalDecl GD,
   // The first argument is the block pointer.  Just take it as a void*
   // and cast it later.
   QualType selfTy = getContext().VoidPtrTy;
+
+  // For OpenCL passed block pointer can be private AS local variable or
+  // global AS program scope variable (for the case with and without captures).
+  // Generic AS is used therefore to be able to accomodate both private and
+  // generic AS in one implementation.
+  if (getLangOpts().OpenCL)
+    selfTy = getContext().getPointerType(getContext().getAddrSpaceQualType(
+        getContext().VoidTy, LangAS::opencl_generic));
+
   IdentifierInfo *II = &CGM.getContext().Idents.get(".block_descriptor");
 
   ImplicitParamDecl selfDecl(getContext(), const_cast<BlockDecl*>(blockDecl),
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index b3d02f1f51c..b1feefe9f0d 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -2493,6 +2493,8 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
 
     llvm::Type *QueueTy = ConvertType(getContext().OCLQueueTy);
     llvm::Type *RangeTy = ConvertType(getContext().OCLNDRangeTy);
+    llvm::Type *GenericVoidPtrTy = Builder.getInt8PtrTy(
+        getContext().getTargetAddressSpace(LangAS::opencl_generic));
 
     llvm::Value *Queue = EmitScalarExpr(E->getArg(0));
     llvm::Value *Flags = EmitScalarExpr(E->getArg(1));
@@ -2502,12 +2504,12 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
       // The most basic form of the call with parameters:
       // queue_t, kernel_enqueue_flags_t, ndrange_t, block(void)
       Name = "__enqueue_kernel_basic";
-      llvm::Type *ArgTys[] = {QueueTy, Int32Ty, RangeTy, Int8PtrTy};
+      llvm::Type *ArgTys[] = {QueueTy, Int32Ty, RangeTy, GenericVoidPtrTy};
       llvm::FunctionType *FTy = llvm::FunctionType::get(
           Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys, 4), false);
 
-      llvm::Value *Block =
-          Builder.CreateBitCast(EmitScalarExpr(E->getArg(3)), Int8PtrTy);
+      llvm::Value *Block = Builder.CreatePointerCast(
+          EmitScalarExpr(E->getArg(3)), GenericVoidPtrTy);
 
       return RValue::get(Builder.CreateCall(
           CGM.CreateRuntimeFunction(FTy, Name), {Queue, Flags, Range, Block}));
@@ -2518,14 +2520,14 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
     if (E->getArg(3)->getType()->isBlockPointerType()) {
       // No events passed, but has variadic arguments.
       Name = "__enqueue_kernel_vaargs";
-      llvm::Value *Block =
-          Builder.CreateBitCast(EmitScalarExpr(E->getArg(3)), Int8PtrTy);
+      llvm::Value *Block = Builder.CreatePointerCast(
+          EmitScalarExpr(E->getArg(3)), GenericVoidPtrTy);
       // Create a vector of the arguments, as well as a constant value to
       // express to the runtime the number of variadic arguments.
       std::vector<llvm::Value *> Args = {Queue, Flags, Range, Block,
                                          ConstantInt::get(IntTy, NumArgs - 4)};
-      std::vector<llvm::Type *> ArgTys = {QueueTy, IntTy, RangeTy, Int8PtrTy,
-                                          IntTy};
+      std::vector<llvm::Type *> ArgTys = {QueueTy, IntTy, RangeTy,
+                                          GenericVoidPtrTy, IntTy};
 
       // Each of the following arguments specifies the size of the corresponding
       // argument passed to the enqueued block.
@@ -2555,12 +2557,12 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
       // Convert to generic address space.
       EventList = Builder.CreatePointerCast(EventList, EventPtrTy);
       ClkEvent = Builder.CreatePointerCast(ClkEvent, EventPtrTy);
-      llvm::Value *Block =
-          Builder.CreateBitCast(EmitScalarExpr(E->getArg(6)), Int8PtrTy);
+      llvm::Value *Block = Builder.CreatePointerCast(
+          EmitScalarExpr(E->getArg(6)), GenericVoidPtrTy);
 
-      std::vector<llvm::Type *> ArgTys = {QueueTy,  Int32Ty,    RangeTy,
-                                          Int32Ty,  EventPtrTy, EventPtrTy,
-                                          Int8PtrTy};
+      std::vector<llvm::Type *> ArgTys = {
+          QueueTy,    Int32Ty,    RangeTy,         Int32Ty,
+          EventPtrTy, EventPtrTy, GenericVoidPtrTy};
 
       std::vector<llvm::Value *> Args = {Queue,     Flags,    Range, NumEvents,
                                          EventList, ClkEvent, Block};
@@ -2596,20 +2598,24 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
   // OpenCL v2.0 s6.13.17.6 - Kernel query functions need bitcast of block
   // parameter.
   case Builtin::BIget_kernel_work_group_size: {
+    llvm::Type *GenericVoidPtrTy = Builder.getInt8PtrTy(
+        getContext().getTargetAddressSpace(LangAS::opencl_generic));
     Value *Arg = EmitScalarExpr(E->getArg(0));
-    Arg = Builder.CreateBitCast(Arg, Int8PtrTy);
-    return RValue::get(
-        Builder.CreateCall(CGM.CreateRuntimeFunction(
-                               llvm::FunctionType::get(IntTy, Int8PtrTy, false),
-                               "__get_kernel_work_group_size_impl"),
-                           Arg));
+    Arg = Builder.CreatePointerCast(Arg, GenericVoidPtrTy);
+    return RValue::get(Builder.CreateCall(
+        CGM.CreateRuntimeFunction(
+            llvm::FunctionType::get(IntTy, GenericVoidPtrTy, false),
+            "__get_kernel_work_group_size_impl"),
+        Arg));
   }
   case Builtin::BIget_kernel_preferred_work_group_size_multiple: {
+    llvm::Type *GenericVoidPtrTy = Builder.getInt8PtrTy(
+        getContext().getTargetAddressSpace(LangAS::opencl_generic));
     Value *Arg = EmitScalarExpr(E->getArg(0));
-    Arg = Builder.CreateBitCast(Arg, Int8PtrTy);
+    Arg = Builder.CreatePointerCast(Arg, GenericVoidPtrTy);
     return RValue::get(Builder.CreateCall(
         CGM.CreateRuntimeFunction(
-            llvm::FunctionType::get(IntTy, Int8PtrTy, false),
+            llvm::FunctionType::get(IntTy, GenericVoidPtrTy, false),
             "__get_kernel_preferred_work_group_multiple_impl"),
         Arg));
   }
diff --git a/clang/lib/Sema/SemaExpr.cpp b/clang/lib/Sema/SemaExpr.cpp
index 43242390597..ca57a413e91 100644
--- a/clang/lib/Sema/SemaExpr.cpp
+++ b/clang/lib/Sema/SemaExpr.cpp
@@ -7405,7 +7405,13 @@ checkBlockPointerTypesForAssignment(Sema &S, QualType LHSType,
   Sema::AssignConvertType ConvTy = Sema::Compatible;
 
   // For blocks we enforce that qualifiers are identical.
-  if (lhptee.getLocalQualifiers() != rhptee.getLocalQualifiers())
+  Qualifiers LQuals = lhptee.getLocalQualifiers();
+  Qualifiers RQuals = rhptee.getLocalQualifiers();
+  if (S.getLangOpts().OpenCL) {
+    LQuals.removeAddressSpace();
+    RQuals.removeAddressSpace();
+  }
+  if (LQuals != RQuals)
     ConvTy = Sema::CompatiblePointerDiscardsQualifiers;
 
   if (!S.Context.typesAreBlockPointerCompatible(LHSType, RHSType))
@@ -7630,7 +7636,12 @@ Sema::CheckAssignmentConstraints(QualType LHSType, ExprResult &RHS,
     // U^ -> void*
     if (RHSType->getAs<BlockPointerType>()) {
       if (LHSPointer->getPointeeType()->isVoidType()) {
-        Kind = CK_BitCast;
+        unsigned AddrSpaceL = LHSPointer->getPointeeType().getAddressSpace();
+        unsigned AddrSpaceR = RHSType->getAs<BlockPointerType>()
+                                  ->getPointeeType()
+                                  .getAddressSpace();
+        Kind =
+            AddrSpaceL != AddrSpaceR ? CK_AddressSpaceConversion : CK_BitCast;
         return Compatible;
       }
     }
@@ -7642,7 +7653,13 @@ Sema::CheckAssignmentConstraints(QualType LHSType, ExprResult &RHS,
   if (isa<BlockPointerType>(LHSType)) {
     // U^ -> T^
     if (RHSType->isBlockPointerType()) {
-      Kind = CK_BitCast;
+      unsigned AddrSpaceL = LHSType->getAs<BlockPointerType>()
+                                ->getPointeeType()
+                                .getAddressSpace();
+      unsigned AddrSpaceR = RHSType->getAs<BlockPointerType>()
+                                ->getPointeeType()
+                                .getAddressSpace();
+      Kind = AddrSpaceL != AddrSpaceR ? CK_AddressSpaceConversion : CK_BitCast;
       return checkBlockPointerTypesForAssignment(*this, LHSType, RHSType);
     }
 
diff --git a/clang/lib/Sema/SemaType.cpp b/clang/lib/Sema/SemaType.cpp
index e4995bd2206..92a2ecc2275 100644
--- a/clang/lib/Sema/SemaType.cpp
+++ b/clang/lib/Sema/SemaType.cpp
@@ -6942,8 +6942,10 @@ static void processTypeAttrs(TypeProcessingState &state, QualType &type,
       (TAL == TAL_DeclSpec || TAL == TAL_DeclChunk)) {
     Declarator &D = state.getDeclarator();
     if (state.getCurrentChunkIndex() > 0 &&
-        D.getTypeObject(state.getCurrentChunkIndex() - 1).Kind ==
-            DeclaratorChunk::Pointer) {
+        (D.getTypeObject(state.getCurrentChunkIndex() - 1).Kind ==
+             DeclaratorChunk::Pointer ||
+         D.getTypeObject(state.getCurrentChunkIndex() - 1).Kind ==
+             DeclaratorChunk::BlockPointer)) {
       type = state.getSema().Context.getAddrSpaceQualType(
           type, LangAS::opencl_generic);
     } else if (state.getCurrentChunkIndex() == 0 &&