From e74a088d92e6010a1413a88865c85bb47a76f90c Mon Sep 17 00:00:00 2001
From: Eric Christopher <echristo@apple.com>
Date: Thu, 5 Aug 2010 23:57:43 +0000
Subject: [PATCH] Add an option to always emit realignment code for a
 particular module.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110404 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Target/X86/X86RegisterInfo.cpp    | 35 ++++++++++++++++++++++++++-
 test/CodeGen/X86/force-align-stack.ll | 21 ++++++++++++++++
 2 files changed, 55 insertions(+), 1 deletion(-)
 create mode 100644 test/CodeGen/X86/force-align-stack.ll

diff --git a/lib/Target/X86/X86RegisterInfo.cpp b/lib/Target/X86/X86RegisterInfo.cpp
index 9acdc168151..746e3fa7b5c 100644
--- a/lib/Target/X86/X86RegisterInfo.cpp
+++ b/lib/Target/X86/X86RegisterInfo.cpp
@@ -38,8 +38,15 @@
 #include "llvm/ADT/BitVector.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/CommandLine.h"
 using namespace llvm;
 
+static cl::opt<bool>
+ForceStackAlign("force-align-stack",
+                 cl::desc("Force align the stack to the minimum alignment"
+                           " needed for the function."),
+                 cl::init(false), cl::Hidden);
+
 X86RegisterInfo::X86RegisterInfo(X86TargetMachine &tm,
                                  const TargetInstrInfo &tii)
   : X86GenRegisterInfo(tm.getSubtarget<X86Subtarget>().is64Bit() ?
@@ -471,7 +478,11 @@ bool X86RegisterInfo::needsStackRealignment(const MachineFunction &MF) const {
   if (0 && requiresRealignment && MFI->hasVarSizedObjects())
     report_fatal_error(
       "Stack realignment in presense of dynamic allocas is not supported");
-
+    
+  // If we've requested that we force align the stack do so now.
+  if (ForceStackAlign)
+    return canRealignStack(MF);
+    
   return requiresRealignment && canRealignStack(MF);
 }
 
@@ -906,6 +917,17 @@ void X86RegisterInfo::emitPrologue(MachineFunction &MF) const {
   bool HasFP = hasFP(MF);
   DebugLoc DL;
 
+  // If we're forcing a stack realignment we can't rely on just the frame
+  // info, we need to know the ABI stack alignment as well in case we
+  // have a call out.  Otherwise just make sure we have some alignment - we'll
+  // go with the minimum SlotSize.
+  if (ForceStackAlign) {
+    if (MFI->hasCalls())
+      MaxAlign = (StackAlign > MaxAlign) ? StackAlign : MaxAlign;
+    else if (MaxAlign < SlotSize)
+      MaxAlign = SlotSize;
+  }
+
   // Add RETADDR move area to callee saved frame size.
   int TailCallReturnAddrDelta = X86FI->getTCReturnAddrDelta();
   if (TailCallReturnAddrDelta < 0)
@@ -1177,6 +1199,17 @@ void X86RegisterInfo::emitEpilogue(MachineFunction &MF,
   unsigned CSSize = X86FI->getCalleeSavedFrameSize();
   uint64_t NumBytes = 0;
 
+  // If we're forcing a stack realignment we can't rely on just the frame
+  // info, we need to know the ABI stack alignment as well in case we
+  // have a call out.  Otherwise just make sure we have some alignment - we'll
+  // go with the minimum.
+  if (ForceStackAlign) {
+    if (MFI->hasCalls())
+      MaxAlign = (StackAlign > MaxAlign) ? StackAlign : MaxAlign;
+    else
+      MaxAlign = MaxAlign ? MaxAlign : 4;
+  }
+
   if (hasFP(MF)) {
     // Calculate required stack adjustment.
     uint64_t FrameSize = StackSize - SlotSize;
diff --git a/test/CodeGen/X86/force-align-stack.ll b/test/CodeGen/X86/force-align-stack.ll
new file mode 100644
index 00000000000..ffcbf8a908c
--- /dev/null
+++ b/test/CodeGen/X86/force-align-stack.ll
@@ -0,0 +1,21 @@
+; RUN: llc < %s -relocation-model=static -force-align-stack | FileCheck %s
+; Tests to make sure that we always align the stack out to the minimum needed - 
+; in this case 16-bytes.
+target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128-n8:16:32"
+target triple = "i386-apple-darwin10.3"
+
+define void @a() nounwind ssp {
+entry:
+; CHECK: _a:
+; CHECK: andl    $-16, %esp
+  %z = alloca <16 x i8>                           ; <<16 x i8>*> [#uses=2]
+  %"alloca point" = bitcast i32 0 to i32          ; <i32> [#uses=0]
+  store <16 x i8> zeroinitializer, <16 x i8>* %z, align 16
+  call void @b(<16 x i8>* %z) nounwind
+  br label %return
+
+return:                                           ; preds = %entry
+  ret void
+}
+
+declare void @b(<16 x i8>*)
-- 
2.34.1