2 files changed, 34 insertions, 4 deletions

diff --git a/clang/lib/CodeGen/CGCoroutine.cpp b/clang/lib/CodeGen/CGCoroutine.cpp
index c09c63f04b8..f6d06d0bdd0 100644
--- a/clang/lib/CodeGen/CGCoroutine.cpp
+++ b/clang/lib/CodeGen/CGCoroutine.cpp
@@ -284,6 +284,9 @@ void CodeGenFunction::EmitCoroutineBody(const CoroutineBodyStmt &S) {
   auto &TI = CGM.getContext().getTargetInfo();
   unsigned NewAlign = TI.getNewAlign() / TI.getCharWidth();
 
+  auto *EntryBB = Builder.GetInsertBlock();
+  auto *AllocBB = createBasicBlock("coro.alloc");
+  auto *InitBB = createBasicBlock("coro.init");
   auto *FinalBB = createBasicBlock("coro.final");
   auto *RetBB = createBasicBlock("coro.ret");
 
@@ -293,12 +296,20 @@ void CodeGenFunction::EmitCoroutineBody(const CoroutineBodyStmt &S) {
   createCoroData(*this, CurCoro, CoroId);
   CurCoro.Data->SuspendBB = RetBB;
 
+  // Backend is allowed to elide memory allocations, to help it, emit
+  // auto mem = coro.alloc() ? 0 : ... allocation code ...;
+  auto *CoroAlloc = Builder.CreateCall(
+      CGM.getIntrinsic(llvm::Intrinsic::coro_alloc), {CoroId});
+
+  Builder.CreateCondBr(CoroAlloc, AllocBB, InitBB);
+
+  EmitBlock(AllocBB);
   auto *AllocateCall = EmitScalarExpr(S.getAllocate());
+  auto *AllocOrInvokeContBB = Builder.GetInsertBlock();
 
   // Handle allocation failure if 'ReturnStmtOnAllocFailure' was provided.
   if (auto *RetOnAllocFailure = S.getReturnStmtOnAllocFailure()) {
     auto *RetOnFailureBB = createBasicBlock("coro.ret.on.failure");
-    auto *InitBB = createBasicBlock("coro.init");
 
     // See if allocation was successful.
     auto *NullPtr = llvm::ConstantPointerNull::get(Int8PtrTy);
@@ -308,9 +319,19 @@ void CodeGenFunction::EmitCoroutineBody(const CoroutineBodyStmt &S) {
     // If not, return OnAllocFailure object.
     EmitBlock(RetOnFailureBB);
     EmitStmt(RetOnAllocFailure);
-
-    EmitBlock(InitBB);
   }
+  else {
+    Builder.CreateBr(InitBB);
+  }
+
+  EmitBlock(InitBB);
+
+  // Pass the result of the allocation to coro.begin.
+  auto *Phi = Builder.CreatePHI(VoidPtrTy, 2);
+  Phi->addIncoming(NullPtr, EntryBB);
+  Phi->addIncoming(AllocateCall, AllocOrInvokeContBB);
+  Builder.CreateCall(
+      CGM.getIntrinsic(llvm::Intrinsic::coro_begin), {CoroId, Phi});
 
   CurCoro.Data->CleanupJD = getJumpDestInCurrentScope(RetBB);
   {
diff --git a/clang/test/CodeGenCoroutines/coro-alloc.cpp b/clang/test/CodeGenCoroutines/coro-alloc.cpp
index b551257f148..14e429ebc22 100644
--- a/clang/test/CodeGenCoroutines/coro-alloc.cpp
+++ b/clang/test/CodeGenCoroutines/coro-alloc.cpp
@@ -56,8 +56,17 @@ struct std::experimental::coroutine_traits<void, global_new_delete_tag> {
 // CHECK-LABEL: f0(
 extern "C" void f0(global_new_delete_tag) {
   // CHECK: %[[ID:.+]] = call token @llvm.coro.id(i32 16
+  // CHECK: %[[NeedAlloc:.+]] = call i1 @llvm.coro.alloc(token %[[ID]])
+  // CHECK: br i1 %[[NeedAlloc]], label %[[AllocBB:.+]], label %[[InitBB:.+]]
+
+  // CHECK: [[AllocBB]]:
   // CHECK: %[[SIZE:.+]] = call i64 @llvm.coro.size.i64()
-  // CHECK: call i8* @_Znwm(i64 %[[SIZE]])
+  // CHECK: %[[MEM:.+]] = call i8* @_Znwm(i64 %[[SIZE]])
+  // CHECK: br label %[[InitBB]]
+
+  // CHECK: [[InitBB]]:
+  // CHECK: %[[PHI:.+]] = phi i8* [ null, %{{.+}} ], [ %call, %[[AllocBB]] ]
+  // CHECK: call i8* @llvm.coro.begin(token %[[ID]], i8* %[[PHI]])
 
   // CHECK: %[[FRAME:.+]] = call i8* @llvm.coro.frame()
   // CHECK: %[[MEM:.+]] = call i8* @llvm.coro.free(token %[[ID]], i8* %[[FRAME]])