[llvm] [X86] Fix incorrect NOP insertion between fused instructions that breaks macro fusion (PR #155316)

[Aleksandr Popov via llvm-commits]

https://github.com/aleks-tmb updated https://github.com/llvm/llvm-project/pull/155316

>From d18a854d72aeea1a8ea0d1bb63aa497f15fcc65a Mon Sep 17 00:00:00 2001
From: Aleksander Popov <a.popov.tmb at gmail.com>
Date: Mon, 25 Aug 2025 23:50:49 +0200
Subject: [PATCH] [X86] Fix incorrect NOP insertion between fused instructions
 that breaks macro fusion

Fixes #155045
---
 .../Target/X86/MCTargetDesc/X86AsmBackend.cpp | 12 ++++++++++-
 llvm/test/MC/X86/align-branch-fused.s         | 20 ++++++++++++++++++-
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp b/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
index 56a4cc3d65c2e..ce2ff75a8f77d 100644
--- a/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
+++ b/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
@@ -485,7 +485,17 @@ void X86AsmBackend::emitInstructionBegin(MCObjectStreamer &OS,
   if (!CanPadInst)
     return;
 
-  if (PendingBA && PendingBA->getNext() == OS.getCurrentFragment()) {
+  if (PendingBA) {
+    auto *NextFragment = PendingBA->getNext();
+    assert(NextFragment && "NextFragment should not be null");
+    if (NextFragment == OS.getCurrentFragment())
+      return;
+    // We eagerly create an empty fragment when inserting a fragment
+    // with a variable-size tail.
+    if (NextFragment->getKind() == MCFragment::FT_Relaxable &&
+        NextFragment->getNext() == OS.getCurrentFragment())
+      return;
+
     // Macro fusion actually happens and there is no other fragment inserted
     // after the previous instruction.
     //
diff --git a/llvm/test/MC/X86/align-branch-fused.s b/llvm/test/MC/X86/align-branch-fused.s
index 7530967a890c6..5b4a144e30921 100644
--- a/llvm/test/MC/X86/align-branch-fused.s
+++ b/llvm/test/MC/X86/align-branch-fused.s
@@ -1,7 +1,10 @@
-# RUN: llvm-mc -filetype=obj -triple x86_64 --x86-align-branch-boundary=32 --x86-align-branch=fused+jcc %s | llvm-objdump -d --no-show-raw-insn - | FileCheck %s
+# RUN: rm -rf %t && split-file %s %t && cd %t
+# RUN: llvm-mc -filetype=obj -triple x86_64 --x86-align-branch-boundary=32 --x86-align-branch=fused+jcc foo.s | llvm-objdump -d --no-show-raw-insn - | FileCheck foo.s
+# RUN: llvm-mc -filetype=obj -triple x86_64 --x86-align-branch-boundary=32 --x86-align-branch=fused+jcc -x86-pad-max-prefix-size=1 bar.s | llvm-objdump -d --no-show-raw-insn - | FileCheck bar.s
 
   # Exercise cases where fused instructions need to be aligned.
 
+#--- foo.s
   .text
   .globl  foo
 foo:
@@ -40,3 +43,18 @@ foo:
   cmp  %rax, %rbp
   jne foo
   int3
+
+# Exercise the case where fused instructions need to be aligned,
+# ensuring fusion is not broken by a NOP
+
+#--- bar.s
+  .text
+	.globl	bar
+bar:
+  .nops 27
+# CHECK:      20:       testq   %rcx, %rcx
+# CHECK:      23:       je
+	testq	%rcx, %rcx
+	je	.EXIT
+.EXIT:
+	ret