From 968823946949925bcc68163bed41b6a1da90a677 Mon Sep 17 00:00:00 2001
From: Reid Kleckner <reid@kleckner.net>
Date: Wed, 6 Aug 2014 17:57:23 +0000
Subject: [PATCH] Round up the size of byval arguments to MinAlign

Otherwise we can end up with an argument frame size that is not a
multiple of stack slot size, which is very awkward.

This fixes PR20547, which was a bug in x86_64 Sys V vararg handling.
However, it's much easier to test this with x86 callee-cleanup
functions, which previously ended in "retl $6" instead of "retl $8".

This does affect behavior of all backends, but it presumably fixes the
same bug in all of them.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@214980 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/CodeGen/CallingConvLower.cpp         |  1 +
 test/CodeGen/X86/byval-callee-cleanup.ll | 28 ++++++++++++++++++++++++++++
 2 files changed, 29 insertions(+)
 create mode 100644 test/CodeGen/X86/byval-callee-cleanup.ll

diff --git a/lib/CodeGen/CallingConvLower.cpp b/lib/CodeGen/CallingConvLower.cpp
index 50fc6a179b6..cfcc9eae14e 100644
--- a/lib/CodeGen/CallingConvLower.cpp
+++ b/lib/CodeGen/CallingConvLower.cpp
@@ -52,6 +52,7 @@ void CCState::HandleByVal(unsigned ValNo, MVT ValVT,
     Align = MinAlign;
   MF.getFrameInfo()->ensureMaxAlignment(Align);
   TM.getSubtargetImpl()->getTargetLowering()->HandleByVal(this, Size, Align);
+  Size = unsigned(RoundUpToAlignment(Size, MinAlign));
   unsigned Offset = AllocateStack(Size, Align);
   addLoc(CCValAssign::getMem(ValNo, ValVT, Offset, LocVT, LocInfo));
 }
diff --git a/test/CodeGen/X86/byval-callee-cleanup.ll b/test/CodeGen/X86/byval-callee-cleanup.ll
new file mode 100644
index 00000000000..61e2369a404
--- /dev/null
+++ b/test/CodeGen/X86/byval-callee-cleanup.ll
@@ -0,0 +1,28 @@
+; RUN: llc < %s -march=x86 | FileCheck %s
+
+; Previously we would forget to align to stack slot alignment after placing a
+; byval argument.  Subsequent arguments would align themselves, but if it was
+; the last argument, the argument size would not be a multiple of stack slot
+; size. This resulted in retl $6 in callee-cleanup functions, as well as subtle
+; varargs bugs.
+
+%struct.Six = type { [6 x i8] }
+
+define x86_stdcallcc void @f(%struct.Six* byval %a) {
+  ret void
+}
+; CHECK-LABEL: _f@8:
+; CHECK: retl $8
+
+define x86_thiscallcc void @g(i8* %this, %struct.Six* byval %a) {
+  ret void
+}
+; CHECK-LABEL: _g:
+; CHECK: retl $8
+
+define x86_fastcallcc void @h(i32 inreg %x, i32 inreg %y, %struct.Six* byval %a) {
+  ret void
+}
+; FIXME: This should be @h@8.
+; CHECK-LABEL: @h@16:
+; CHECK: retl $8
-- 
2.11.0