[WinEH] Fix 32-bit funclet epilogues in the presence of dynamic allocas

In particular, passing non-trivially copyable objects by value on win32
uses a dynamic alloca (inalloca). We would clobber ESP in the epilogue
and end up returning to outer space.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@249637 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86FrameLowering.cpp b/lib/Target/X86/X86FrameLowering.cpp
index fc314d76c644e555c791b9465fada96ae0c78545..7f05e5b3b1351e149a615ac350c1ee0131d5b4a8 100644 (file)
--- a/lib/Target/X86/X86FrameLowering.cpp
+++ b/lib/Target/X86/X86FrameLowering.cpp
@@ -1057,6 +1057,7 @@ void X86FrameLowering::emitEpilogue(MachineFunction &MF,
   bool IsWin64Prologue = MF.getTarget().getMCAsmInfo()->usesWindowsCFI();
   bool NeedsWinCFI =
       IsWin64Prologue && MF.getFunction()->needsUnwindTableEntry();
+  bool IsFunclet = isFuncletReturnInstr(MBBI);
 
   // Get the number of bytes to allocate from the FrameInfo.
   uint64_t StackSize = MFI->getStackSize();
@@ -1170,8 +1171,10 @@ void X86FrameLowering::emitEpilogue(MachineFunction &MF,
 
   // If dynamic alloca is used, then reset esp to point to the last callee-saved
   // slot before popping them off! Same applies for the case, when stack was
-  // realigned.
-  if (TRI->needsStackRealignment(MF) || MFI->hasVarSizedObjects()) {
+  // realigned. Don't do this if this was a funclet epilogue, since the funclets
+  // will not do realignment or dynamic stack allocation.
+  if ((TRI->needsStackRealignment(MF) || MFI->hasVarSizedObjects()) &&
+      !IsFunclet) {
     if (TRI->needsStackRealignment(MF))
       MBBI = FirstCSPop;
     unsigned SEHFrameOffset = calculateSetFPREG(SEHStackAllocAmt);

diff --git a/test/CodeGen/X86/cleanuppad-inalloca.ll b/test/CodeGen/X86/cleanuppad-inalloca.ll
new file mode 100644 (file)
index 0000000..8858f37
--- /dev/null
+++ b/test/CodeGen/X86/cleanuppad-inalloca.ll
@@ -0,0 +1,68 @@
+; RUN: llc < %s | FileCheck %s
+
+; Based on this C++:
+; struct A {
+;   int x;
+;   A();
+;   A(const A &a);
+;   ~A();
+; };
+; extern "C" void takes_two(A a1, A a2);
+; extern "C" void passes_two() { takes_two(A(), A()); }
+
+target datalayout = "e-m:x-p:32:32-i64:64-f80:32-n8:16:32-a:0:32-S32"
+target triple = "i686--windows-msvc"
+
+%struct.A = type { i32 }
+
+define void @passes_two() #0 personality i8* bitcast (i32 (...)* @__CxxFrameHandler3 to i8*) {
+entry:
+  %argmem = alloca inalloca <{ %struct.A, %struct.A }>, align 4
+  %0 = getelementptr inbounds <{ %struct.A, %struct.A }>, <{ %struct.A, %struct.A }>* %argmem, i32 0, i32 1
+  %call = call x86_thiscallcc %struct.A* @"\01??0A@@QAE@XZ"(%struct.A* %0)
+  %1 = getelementptr inbounds <{ %struct.A, %struct.A }>, <{ %struct.A, %struct.A }>* %argmem, i32 0, i32 0
+  %call1 = invoke x86_thiscallcc %struct.A* @"\01??0A@@QAE@XZ"(%struct.A* %1)
+          to label %invoke.cont unwind label %ehcleanup
+
+invoke.cont:                                      ; preds = %entry
+  call void @takes_two(<{ %struct.A, %struct.A }>* inalloca nonnull %argmem)
+  ret void
+
+ehcleanup:                                        ; preds = %entry
+  %2 = cleanuppad []
+  call x86_thiscallcc void @"\01??1A@@QAE@XZ"(%struct.A* %0)
+  cleanupret %2 unwind to caller
+}
+
+; CHECK: _passes_two:
+; CHECK: pushl %ebp
+; CHECK: movl %esp, %ebp
+; CHECK: subl ${{[0-9]+}}, %esp
+; CHECK: movl $8, %eax
+; CHECK: calll __chkstk
+; CHECK: calll "??0A@@QAE@XZ"
+; CHECK: calll "??0A@@QAE@XZ"
+; CHECK: calll _takes_two
+;      ESP must be restored via EBP due to "dynamic" alloca.
+; CHECK: leal -{{[0-9]+}}(%ebp), %esp
+; CHECK: popl %ebp
+; CHECK: retl
+
+; CHECK: "?dtor$2@?0?passes_two@4HA":
+; CHECK: pushl %ebp
+; CHECK: subl $8, %esp
+; CHECK: addl $12, %ebp
+; CHECK: {{movl|leal}} -{{[0-9]+}}(%ebp), %ecx
+; CHECK: calll "??1A@@QAE@XZ"
+; CHECK: addl $8, %esp
+; CHECK: retl
+
+declare void @takes_two(<{ %struct.A, %struct.A }>* inalloca) #0
+
+declare x86_thiscallcc %struct.A* @"\01??0A@@QAE@XZ"(%struct.A* returned) #0
+
+declare i32 @__CxxFrameHandler3(...)
+
+declare x86_thiscallcc void @"\01??1A@@QAE@XZ"(%struct.A*) #0
+
+attributes #0 = { "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }