[coro] Fix rematerializable instruction sinking to coro.suspend blocks

There is a constraint that coro.suspend instructions need to be in their
own blocks. The coro split pass initially creates IR that obeys this constraint
(which is later checked). Sinking rematerializable instructions into these
blocks breaks that constraint.

Instead rematerialize in the predecessor block to the suspend's single
predecessor block.

Differential Revision: https://reviews.llvm.org/D104051

Author: aschwaighofer

llvm/lib/Transforms/Coroutines/CoroFrame.cpp

@@ -1964,11 +1964,16 @@ static void rewriteMaterializableInstructions(IRBuilder<> &IRB,
     for (Instruction *U : E.second) {
       // If we have not seen this block, materialize the value.
       if (CurrentBlock != U->getParent()) {
-        CurrentBlock = U->getParent();
+
+        bool IsInCoroSuspendBlock = isa<AnyCoroSuspendInst>(U);
+        CurrentBlock = IsInCoroSuspendBlock
+                           ? U->getParent()->getSinglePredecessor()
+                           : U->getParent();
         CurrentMaterialization = cast<Instruction>(Def)->clone();
         CurrentMaterialization->setName(Def->getName());
         CurrentMaterialization->insertBefore(
-            &*CurrentBlock->getFirstInsertionPt());
+            IsInCoroSuspendBlock ? CurrentBlock->getTerminator()
+                                 : &*CurrentBlock->getFirstInsertionPt());
       }
       if (auto *PN = dyn_cast<PHINode>(U)) {
         assert(PN->getNumIncomingValues() == 1 &&

llvm/test/Transforms/Coroutines/coro-async.ll

@@ -1,5 +1,5 @@
 ; RUN: opt < %s -enable-coroutines -passes='default<O2>' -S | FileCheck --check-prefixes=CHECK %s
-
+; RUN: opt < %s -enable-coroutines -O0 -S
 target datalayout = "p:64:64:64"
 
 %async.task = type { i64 }
@@ -212,11 +212,12 @@ entry:
   store i8* %async.ctxt, i8** %callee_context.caller_context.addr
   %resume_proj_fun = bitcast i8*(i8*)* @resume_context_projection to i8*
   %callee = bitcast void(i8*, %async.task*, %async.actor*)* @asyncSuspend to i8*
+  %task.casted = bitcast i8* %arg0 to %async.task*
   %res = call {i8*, i8*, i8*} (i32, i8*, i8*, ...) @llvm.coro.suspend.async(i32 2,
                                                   i8* %resume.func_ptr,
                                                   i8* %resume_proj_fun,
                                                   void (i8*, i8*, %async.task*, %async.actor*)* @my_async_function.my_other_async_function_fp.apply,
-                                                  i8* %callee, i8* %callee_context, %async.task* %task, %async.actor *%actor), !dbg !9
+                                                  i8* %callee, i8* %callee_context, %async.task* %task.casted, %async.actor *%actor), !dbg !9
 
   %continuation_task_arg = extractvalue {i8*, i8*, i8*} %res, 0
   %task.2 =  bitcast i8* %continuation_task_arg to %async.task*
@@ -234,7 +235,7 @@ entry:
                                                   i8* %resume.func_ptr.1,
                                                   i8* %resume_proj_fun.2,
                                                   void (i8*, i8*, %async.task*, %async.actor*)* @my_async_function.my_other_async_function_fp.apply,
-                                                  i8* %callee.2, i8* %callee_context, %async.task* %task, %async.actor *%actor)
+                                                  i8* %callee.2, i8* %callee_context, %async.task* %task.casted, %async.actor *%actor)
 
   call void @llvm.coro.async.context.dealloc(i8* %callee_context)
   %continuation_actor_arg = extractvalue {i8*, i8*, i8*} %res.2, 1
@@ -542,6 +543,7 @@ declare swiftcc void @asyncReturn(i8*, %async.task*, %async.actor*)
 declare swiftcc void @asyncSuspend(i8*, %async.task*, %async.actor*)
 declare i8* @llvm.coro.async.resume()
 declare void @llvm.coro.async.size.replace(i8*, i8*)
+declare i8* @hide(i8*)
 
 !llvm.dbg.cu = !{!2}
 !llvm.module.flags = !{!0}