diff --git a/llvm/lib/Transforms/Coroutines/CoroSplit.cpp b/llvm/lib/Transforms/Coroutines/CoroSplit.cpp
--- a/llvm/lib/Transforms/Coroutines/CoroSplit.cpp
+++ b/llvm/lib/Transforms/Coroutines/CoroSplit.cpp
@@ -1416,14 +1416,17 @@
 
     IRBuilder<> Builder(ReturnBB);
 
-    // Insert the call to the tail call function.
+    // Insert the call to the tail call function and inline it.
     auto *Fun = Suspend->getMustTailCallFunction();
     SmallVector<Value *, 8> Args(Suspend->operand_values());
     auto *TailCall = Builder.CreateCall(
         cast<FunctionType>(Fun->getType()->getPointerElementType()), Fun,
         ArrayRef<Value *>(Args).drop_front(3).drop_back(1));
-    TailCall->setTailCallKind(CallInst::TCK_MustTail);
+    TailCall->setTailCall();
     TailCall->setCallingConv(Fun->getCallingConv());
+    InlineFunctionInfo FnInfo;
+    auto InlineRes = InlineFunction(*TailCall, FnInfo);
+    assert(InlineRes.isSuccess() && "Expected inlining to succeed");
     Builder.CreateRetVoid();
 
     // Replace the lvm.coro.async.resume intrisic call.
diff --git a/llvm/test/Transforms/Coroutines/coro-async.ll b/llvm/test/Transforms/Coroutines/coro-async.ll
--- a/llvm/test/Transforms/Coroutines/coro-async.ll
+++ b/llvm/test/Transforms/Coroutines/coro-async.ll
@@ -28,8 +28,9 @@
 }>
 
 ; Function that implements the dispatch to the callee function.
-define swiftcc void @my_async_function.my_other_async_function_fp.apply(i8* %async.ctxt, %async.task* %task, %async.actor* %actor) {
-  musttail call swiftcc void @asyncSuspend(i8* %async.ctxt, %async.task* %task, %async.actor* %actor)
+define swiftcc void @my_async_function.my_other_async_function_fp.apply(i8* %fnPtr, i8* %async.ctxt, %async.task* %task, %async.actor* %actor) {
+  %callee = bitcast i8* %fnPtr to void(i8*, %async.task*, %async.actor*)*
+  tail call swiftcc void %callee(i8* %async.ctxt, %async.task* %task, %async.actor* %actor)
   ret void
 }
 
@@ -78,11 +79,12 @@
   %callee_context.caller_context.addr = getelementptr inbounds %async.ctxt, %async.ctxt* %callee_context.0, i32 0, i32 0
   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*
   %res = call {i8*, i8*, i8*} (i8*, i8*, ...) @llvm.coro.suspend.async(
                                                   i8* %resume.func_ptr,
                                                   i8* %resume_proj_fun,
-                                                  void (i8*, %async.task*, %async.actor*)* @my_async_function.my_other_async_function_fp.apply,
-                                                  i8* %callee_context, %async.task* %task, %async.actor *%actor)
+                                                  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)
 
   call void @llvm.coro.async.context.dealloc(i8* %callee_context)
   %continuation_task_arg = extractvalue {i8*, i8*, i8*} %res, 1
@@ -126,7 +128,7 @@
 ; CHECK:   store i8* bitcast (void (i8*, i8*, i8*)* @my_async_function.resume.0 to i8*), i8** [[RETURN_TO_CALLER_ADDR]]
 ; CHECK:   [[CALLER_CONTEXT_ADDR:%.*]] = bitcast i8* [[CALLEE_CTXT]] to i8**
 ; CHECK:   store i8* %async.ctxt, i8** [[CALLER_CONTEXT_ADDR]]
-; CHECK:   musttail call swiftcc void @asyncSuspend(i8* [[CALLEE_CTXT]], %async.task* %task, %async.actor* %actor)
+; CHECK:   tail call swiftcc void @asyncSuspend(i8* [[CALLEE_CTXT]], %async.task* %task, %async.actor* %actor)
 ; CHECK:   ret void
 ; CHECK: }
 
@@ -185,11 +187,12 @@
   %callee_context.caller_context.addr = getelementptr inbounds %async.ctxt, %async.ctxt* %callee_context.0, i32 0, i32 0
   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*
   %res = call {i8*, i8*, i8*} (i8*, i8*, ...) @llvm.coro.suspend.async(
                                                   i8* %resume.func_ptr,
                                                   i8* %resume_proj_fun,
-                                                  void (i8*, %async.task*, %async.actor*)* @my_async_function.my_other_async_function_fp.apply,
-                                                  i8* %callee_context, %async.task* %task, %async.actor *%actor)
+                                                  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)
 
   %continuation_task_arg = extractvalue {i8*, i8*, i8*} %res, 0
   %task.2 =  bitcast i8* %continuation_task_arg to %async.task*
@@ -202,11 +205,12 @@
   %callee_context.caller_context.addr.1 = getelementptr inbounds %async.ctxt, %async.ctxt* %callee_context.0.1, i32 0, i32 0
   store i8* %async.ctxt, i8** %callee_context.caller_context.addr.1
   %resume_proj_fun.2 = bitcast i8*(i8*)* @resume_context_projection to i8*
+  %callee.2 = bitcast void(i8*, %async.task*, %async.actor*)* @asyncSuspend to i8*
   %res.2 = call {i8*, i8*, i8*} (i8*, i8*, ...) @llvm.coro.suspend.async(
                                                   i8* %resume.func_ptr.1,
                                                   i8* %resume_proj_fun.2,
-                                                  void (i8*, %async.task*, %async.actor*)* @my_async_function.my_other_async_function_fp.apply,
-                                                  i8* %callee_context, %async.task* %task, %async.actor *%actor)
+                                                  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)
 
   call void @llvm.coro.async.context.dealloc(i8* %callee_context)
   %continuation_actor_arg = extractvalue {i8*, i8*, i8*} %res.2, 1
@@ -225,7 +229,7 @@
 ; CHECK: store i8* [[CALLEE_CTXT]],
 ; CHECK: store i8* bitcast (void (i8*, i8*, i8*)* @my_async_function2.resume.0 to i8*),
 ; CHECK: store i8* %async.ctxt,
-; CHECK: musttail call swiftcc void @asyncSuspend(i8* [[CALLEE_CTXT]], %async.task* %task, %async.actor* %actor)
+; CHECK: tail call swiftcc void @asyncSuspend(i8* [[CALLEE_CTXT]], %async.task* %task, %async.actor* %actor)
 ; CHECK: ret void
 
 ; CHECK-LABEL: define internal swiftcc void @my_async_function2.resume.0(i8* %0, i8* nocapture readnone %1, i8* nocapture readonly %2) {
@@ -235,7 +239,7 @@
 ; CHECK: [[CALLEE_CTXT_SPILL_ADDR2:%.*]] = bitcast i8* [[CALLEE_CTXT_SPILL_ADDR]] to i8**
 ; CHECK: store i8* bitcast (void (i8*, i8*, i8*)* @my_async_function2.resume.1 to i8*),
 ; CHECK: [[CALLLE_CTXT_RELOAD:%.*]] = load i8*, i8** [[CALLEE_CTXT_SPILL_ADDR2]]
-; CHECK: musttail call swiftcc void @asyncSuspend(i8* [[CALLEE_CTXT_RELOAD]]
+; CHECK: tail call swiftcc void @asyncSuspend(i8* [[CALLEE_CTXT_RELOAD]]
 ; CHECK: ret void
 
 ; CHECK-LABEL: define internal swiftcc void @my_async_function2.resume.1(i8* nocapture readnone %0, i8* %1, i8* nocapture readonly %2) {