[OpenCL] Fix __enqueue_block for block with captures

The following test case causes issue with codegen of __enqueue_block

void (^block)(void) = ^{ callee(id, out); };

enqueue_kernel(queue, 0, ndrange, block);
Clang first does codegen for block expression in the first line and deletes its block info.
Clang then tries to do codegen for the same block expression again for the second line,
and fails because the block info is gone.

The fix is to do normal codegen for both lines. Introduce an API to OpenCL runtime to
record llvm block invoke function and llvm block literal emitted for each AST block
expression, and use the recorded information for generating the wrapper kernel.

The EmitBlockLiteral APIs are cleaned up to minimize changes to the normal codegen
of blocks.

Another minor issue is that some clean up AST expression is generated for block
with captures, which can be stripped by IgnoreImplicit.

Differential Revision: https://reviews.llvm.org/D43240

llvm-svn: 325264

1 files changed, 13 insertions, 15 deletions

diff --git a/clang/lib/CodeGen/CGBlocks.cpp b/clang/lib/CodeGen/CGBlocks.cpp
index d60b5fbb70d..bbef9292d2c 100644
--- a/clang/lib/CodeGen/CGBlocks.cpp
+++ b/clang/lib/CodeGen/CGBlocks.cpp
@@ -740,27 +740,19 @@ void CodeGenFunction::destroyBlockInfos(CGBlockInfo *head) {
 }
 
 /// Emit a block literal expression in the current function.
-llvm::Value *CodeGenFunction::EmitBlockLiteral(const BlockExpr *blockExpr,
-                                               llvm::Function **InvokeF) {
+llvm::Value *CodeGenFunction::EmitBlockLiteral(const BlockExpr *blockExpr) {
   // If the block has no captures, we won't have a pre-computed
   // layout for it.
   if (!blockExpr->getBlockDecl()->hasCaptures()) {
     // The block literal is emitted as a global variable, and the block invoke
     // function has to be extracted from its initializer.
     if (llvm::Constant *Block = CGM.getAddrOfGlobalBlockIfEmitted(blockExpr)) {
-      if (InvokeF) {
-        auto *GV = cast<llvm::GlobalVariable>(
-            cast<llvm::Constant>(Block)->stripPointerCasts());
-        auto *BlockInit = cast<llvm::ConstantStruct>(GV->getInitializer());
-        *InvokeF = cast<llvm::Function>(
-            BlockInit->getAggregateElement(2)->stripPointerCasts());
-      }
       return Block;
     }
     CGBlockInfo blockInfo(blockExpr->getBlockDecl(), CurFn->getName());
     computeBlockInfo(CGM, this, blockInfo);
     blockInfo.BlockExpression = blockExpr;
-    return EmitBlockLiteral(blockInfo, InvokeF);
+    return EmitBlockLiteral(blockInfo);
   }
 
   // Find the block info for this block and take ownership of it.
@@ -769,11 +761,10 @@ llvm::Value *CodeGenFunction::EmitBlockLiteral(const BlockExpr *blockExpr,
                                          blockExpr->getBlockDecl()));
 
   blockInfo->BlockExpression = blockExpr;
-  return EmitBlockLiteral(*blockInfo, InvokeF);
+  return EmitBlockLiteral(*blockInfo);
 }
 
-llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo,
-                                               llvm::Function **InvokeF) {
+llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo) {
   bool IsOpenCL = CGM.getContext().getLangOpts().OpenCL;
   auto GenVoidPtrTy =
       IsOpenCL ? CGM.getOpenCLRuntime().getGenericVoidPointerType() : VoidPtrTy;
@@ -788,8 +779,6 @@ llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo,
   BlockCGF.SanOpts = SanOpts;
   auto *InvokeFn = BlockCGF.GenerateBlockFunction(
       CurGD, blockInfo, LocalDeclMap, isLambdaConv, blockInfo.CanBeGlobal);
-  if (InvokeF)
-    *InvokeF = InvokeFn;
   auto *blockFn = llvm::ConstantExpr::getPointerCast(InvokeFn, GenVoidPtrTy);
 
   // If there is nothing to capture, we can emit this as a global block.
@@ -1024,6 +1013,11 @@ llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo,
   llvm::Value *result = Builder.CreatePointerCast(
       blockAddr.getPointer(), ConvertType(blockInfo.getBlockExpr()->getType()));
 
+  if (IsOpenCL) {
+    CGM.getOpenCLRuntime().recordBlockInfo(blockInfo.BlockExpression, InvokeFn,
+                                           result);
+  }
+
   return result;
 }
 
@@ -1287,6 +1281,10 @@ static llvm::Constant *buildGlobalBlock(CodeGenModule &CGM,
   llvm::Constant *Result =
       llvm::ConstantExpr::getPointerCast(literal, RequiredType);
   CGM.setAddrOfGlobalBlock(blockInfo.BlockExpression, Result);
+  if (CGM.getContext().getLangOpts().OpenCL)
+    CGM.getOpenCLRuntime().recordBlockInfo(
+        blockInfo.BlockExpression,
+        cast<llvm::Function>(blockFn->stripPointerCasts()), Result);
   return Result;
 }