From da44c36d644294924b715c8ced5440949ae9f6a5 Mon Sep 17 00:00:00 2001
From: Kai Nacke <kai.nacke@redstar.de>
Date: Fri, 13 Dec 2013 05:37:05 +0000
Subject: [PATCH] Change stack probing code for MingW.
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

Since gcc 4.6 the compiler uses ___chkstk_ms which has the same semantics as the
MS CRT function __chkstk. This simplifies the prologue generation a bit.

Reviewed by Rafael Espíndola.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@197205 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Target/X86/X86FrameLowering.cpp        | 16 +++++++---------
 test/CodeGen/X86/win64_alloca_dynalloca.ll |  6 +++---
 test/CodeGen/X86/win_chkstk.ll             |  6 +++---
 3 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/lib/Target/X86/X86FrameLowering.cpp b/lib/Target/X86/X86FrameLowering.cpp
index 142e60b4836..0c5209cf3ee 100644
--- a/lib/Target/X86/X86FrameLowering.cpp
+++ b/lib/Target/X86/X86FrameLowering.cpp
@@ -608,14 +608,12 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
   // virtual memory manager are allocated in correct sequence.
   if (NumBytes >= 4096 && STI.isOSWindows() && !STI.isTargetMacho()) {
     const char *StackProbeSymbol;
-    bool isSPUpdateNeeded = false;
 
     if (Is64Bit) {
-      if (STI.isTargetCygMing())
-        StackProbeSymbol = "___chkstk";
-      else {
+      if (STI.isTargetCygMing()) {
+        StackProbeSymbol = "___chkstk_ms";
+      } else {
         StackProbeSymbol = "__chkstk";
-        isSPUpdateNeeded = true;
       }
     } else if (STI.isTargetCygMing())
       StackProbeSymbol = "_alloca";
@@ -657,15 +655,15 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
       .addReg(X86::EFLAGS, RegState::Define | RegState::Implicit)
       .setMIFlag(MachineInstr::FrameSetup);
 
-    // MSVC x64's __chkstk does not adjust %rsp itself.
-    // It also does not clobber %rax so we can reuse it when adjusting %rsp.
-    if (isSPUpdateNeeded) {
+    if (Is64Bit) {
+      // MSVC x64's __chkstk and cygwin/mingw's ___chkstk_ms do not adjust %rsp
+      // themself. It also does not clobber %rax so we can reuse it when
+      // adjusting %rsp.
       BuildMI(MBB, MBBI, DL, TII.get(X86::SUB64rr), StackPtr)
         .addReg(StackPtr)
         .addReg(X86::RAX)
         .setMIFlag(MachineInstr::FrameSetup);
     }
-
     if (isEAXAlive) {
         // Restore EAX
         MachineInstr *MI = addRegOffset(BuildMI(MF, DL, TII.get(X86::MOV32rm),
diff --git a/test/CodeGen/X86/win64_alloca_dynalloca.ll b/test/CodeGen/X86/win64_alloca_dynalloca.ll
index aff53057a95..a6b6536f906 100644
--- a/test/CodeGen/X86/win64_alloca_dynalloca.ll
+++ b/test/CodeGen/X86/win64_alloca_dynalloca.ll
@@ -12,11 +12,11 @@ entry:
 
   %buf0 = alloca i8, i64 4096, align 1
 
-; ___chkstk must adjust %rsp.
+; ___chkstk_ms does not adjust %rsp.
 ; M64: movq  %rsp, %rbp
 ; M64:       $4096, %rax
-; M64: callq ___chkstk
-; M64-NOT:   %rsp
+; M64: callq ___chkstk_ms
+; M64: subq  %rax, %rsp
 
 ; __chkstk does not adjust %rsp.
 ; W64: movq  %rsp, %rbp
diff --git a/test/CodeGen/X86/win_chkstk.ll b/test/CodeGen/X86/win_chkstk.ll
index 3f522ea5682..0c02c1a11d1 100644
--- a/test/CodeGen/X86/win_chkstk.ll
+++ b/test/CodeGen/X86/win_chkstk.ll
@@ -17,7 +17,7 @@ entry:
 ; WIN_X32:    calll __chkstk
 ; WIN_X64:    callq __chkstk
 ; MINGW_X32:  calll __alloca
-; MINGW_X64:  callq ___chkstk
+; MINGW_X64:  callq ___chkstk_ms
 ; LINUX-NOT:  call __chkstk
   %array4096 = alloca [4096 x i8], align 16       ; <[4096 x i8]*> [#uses=0]
   ret i32 0
@@ -36,7 +36,7 @@ entry:
 ; WIN_X64:       ret
 
 ; MINGW_X64:     # BB#0:
-; MINGW_X64-NOT: callq _alloca
+; MINGW_X64-NOT: callq ___chkstk_ms
 ; MINGW_X64:     ret
 
 ; LINUX:         # BB#0:
@@ -53,7 +53,7 @@ entry:
 ; WIN_X32:    calll __chkstk
 ; WIN_X64:    callq __chkstk
 ; MINGW_X32:  calll __alloca
-; MINGW_X64:  callq ___chkstk
+; MINGW_X64:  callq ___chkstk_ms
 ; LINUX-NOT:  call __chkstk
   %array4096 = alloca [4096 x i8], align 16       ; <[4096 x i8]*> [#uses=0]
   ret i32 0
-- 
2.34.1