[AlwaysInliner] Enable call site inlining to make flatten attribute working again (#53360)

Problem: Migration to new PM broke flatten attribute.

This is one use case why LLVM should support inlining call-site with alwaysinline.  The flatten attribute is nowdays broken, so we should either land patch like this one or remove everything related to  flatten attribute from Clang.

Second use case is something like "per call site inlining intrinsics" to control inlining even more; mentioned in
https://lists.llvm.org/pipermail/cfe-dev/2018-September/059232.html

Fixes llvm/llvm-project#53360

Reviewed By: aeubanks

Differential Revision: https://reviews.llvm.org/D117965

Author: davidbolvansky

clang/test/CodeGen/flatten.c

@@ -1,9 +1,3 @@
-// UNSUPPORTED: experimental-new-pass-manager
-// Currently, different code seems to be intentionally generated under the new
-// PM since we alwaysinline functions and not callsites under new PM.
-// Under new PM, f() will not be inlined from g() since f is not marked as
-// alwaysinline.
-
 // RUN: %clang_cc1 -triple=x86_64-linux-gnu %s -emit-llvm -o - | FileCheck %s
 
 void f(void) {}

clang/test/CodeGenCXX/flatten.cpp

@@ -1,7 +1,3 @@
-// UNSUPPORTED: experimental-new-pass-manager
-// See the comment for CodeGen/flatten.c on why this is unsupported with the new
-// PM.
-
 // RUN: %clang_cc1 -triple=x86_64-linux-gnu -std=c++11 %s -emit-llvm -o - | FileCheck %s
 
 void f(void) {}

llvm/lib/Transforms/IPO/AlwaysInliner.cpp

@@ -54,13 +54,13 @@ PreservedAnalyses AlwaysInlinerPass::run(Module &M,
     if (F.isPresplitCoroutine())
       continue;
 
-    if (!F.isDeclaration() && F.hasFnAttribute(Attribute::AlwaysInline) &&
-        isInlineViable(F).isSuccess()) {
+    if (!F.isDeclaration() && isInlineViable(F).isSuccess()) {
       Calls.clear();
 
       for (User *U : F.users())
         if (auto *CB = dyn_cast<CallBase>(U))
-          if (CB->getCalledFunction() == &F)
+          if (CB->getCalledFunction() == &F &&
+              CB->hasFnAttr(Attribute::AlwaysInline))
             Calls.insert(CB);
 
       for (CallBase *CB : Calls) {

llvm/test/Transforms/Coroutines/coro-retcon-once-private.ll

@@ -3,9 +3,7 @@
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.12.0"
 
-; CHECK: define internal { i8*, i32 } @f(i8* %buffer, i32* %array)
-; CHECK-NEXT: entry:
-; CHECK-NEXT:  unreachable
+; CHECK-NOT: define {{.*}} @f(i8* %buffer, i32* %array)
 
 define internal {i8*, i32} @f(i8* %buffer, i32* %array) {
 entry:

llvm/test/Transforms/Inline/always-inline.ll

@@ -1,14 +1,11 @@
-; RUN: opt < %s -inline-threshold=0 -always-inline -enable-new-pm=0 -S | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-CALL
+; RUN: opt < %s -inline-threshold=0 -always-inline -enable-new-pm=0 -S | FileCheck %s --check-prefix=CHECK
 ;
 ; Ensure the threshold has no impact on these decisions.
-; RUN: opt < %s -inline-threshold=20000000 -always-inline -enable-new-pm=0 -S | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-CALL
-; RUN: opt < %s -inline-threshold=-20000000 -always-inline -enable-new-pm=0 -S | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-CALL
+; RUN: opt < %s -inline-threshold=20000000 -always-inline -enable-new-pm=0 -S | FileCheck %s --check-prefix=CHECK
+; RUN: opt < %s -inline-threshold=-20000000 -always-inline -enable-new-pm=0 -S | FileCheck %s --check-prefix=CHECK
 ;
 ; The new pass manager doesn't re-use any threshold based infrastructure for
-; the always inliner, but test that we get the correct result. The new PM
-; always inliner also doesn't support inlining call-site alwaysinline
-; annotations. It isn't clear that this is a reasonable use case for
-; 'alwaysinline'.
+; the always inliner, but test that we get the correct result.
 ; RUN: opt < %s -inline-threshold=0 -passes=always-inline -S | FileCheck %s --check-prefix=CHECK
 ; RUN: opt < %s -inline-threshold=20000000 -passes=always-inline -S | FileCheck %s --check-prefix=CHECK
 ; RUN: opt < %s -inline-threshold=-20000000 -passes=always-inline -S | FileCheck %s --check-prefix=CHECK
@@ -26,12 +23,6 @@ define i32 @outer1() {
    ret i32 %r
 }
 
-; The always inliner can't DCE arbitrary internal functions. PR2945
-define internal i32 @pr2945() nounwind {
-; CHECK-LABEL: @pr2945(
-  ret i32 0
-}
-
 define internal void @inner2(i32 %N) alwaysinline {
 ; CHECK-NOT: @inner2(
   %P = alloca i32, i32 %N
@@ -146,10 +137,9 @@ define i32 @inner7() {
   ret i32 1
 }
 define i32 @outer7() {
-; CHECK-CALL-LABEL: @outer7(
-; CHECK-CALL-NOT: call
-; CHECK-CALL: ret
-
+; CHECK-LABEL: @outer7(
+; CHECK-NOT: call
+; CHECK: ret
    %r = call i32 @inner7() alwaysinline
    ret i32 %r
 }