Use pushq / popq instead of subq $8, %rsp / addq $8, %rsp to adjust stack in

prologue and epilogue if the adjustment is 8. Similarly, use pushl / popl if
the adjustment is 4 in 32-bit mode.

In the epilogue, takes care to pop to a caller-saved register that's not live
at the exit (either return or tailcall instruction).
rdar://8771137


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122783 91177308-0d34-0410-b5e6-96231b3b80d8

9 files changed, 258 insertions, 181 deletions

diff --git a/lib/Target/X86/X86FrameInfo.cpp b/lib/Target/X86/X86FrameInfo.cpp
index c47b0fa697..5219861058 100644
--- a/lib/Target/X86/X86FrameInfo.cpp
+++ b/lib/Target/X86/X86FrameInfo.cpp
@@ -25,6 +25,7 @@
 #include "llvm/Target/TargetData.h"
 #include "llvm/Target/TargetOptions.h"
 #include "llvm/Support/CommandLine.h"
+#include "llvm/ADT/SmallSet.h"
 
 using namespace llvm;
 
@@ -75,12 +76,70 @@ static unsigned getADDriOpcode(unsigned is64Bit, int64_t Imm) {
   }
 }
 
+/// findDeadCallerSavedReg - Return a caller-saved register that isn't live
+/// when it reaches the "return" instruction. We can then pop a stack object
+/// to this register without worry about clobbering it.
+static unsigned findDeadCallerSavedReg(MachineBasicBlock &MBB,
+                                       MachineBasicBlock::iterator &MBBI,
+                                       const TargetRegisterInfo &TRI,
+                                       bool Is64Bit) {
+  const MachineFunction *MF = MBB.getParent();
+  const Function *F = MF->getFunction();
+  if (!F || MF->getMMI().callsEHReturn())
+    return 0;
+
+  static const unsigned CallerSavedRegs32Bit[] = {
+    X86::EAX, X86::EDX, X86::ECX
+  };
+
+  static const unsigned CallerSavedRegs64Bit[] = {
+    X86::RAX, X86::RDX, X86::RCX, X86::RSI, X86::RDI,
+    X86::R8,  X86::R9,  X86::R10, X86::R11
+  };
+
+  unsigned Opc = MBBI->getOpcode();
+  switch (Opc) {
+  default: return 0;
+  case X86::RET:
+  case X86::RETI:
+  case X86::TCRETURNdi:
+  case X86::TCRETURNri:
+  case X86::TCRETURNmi:
+  case X86::TCRETURNdi64:
+  case X86::TCRETURNri64:
+  case X86::TCRETURNmi64:
+  case X86::EH_RETURN:
+  case X86::EH_RETURN64: {
+    SmallSet<unsigned, 8> Uses;
+    for (unsigned i = 0, e = MBBI->getNumOperands(); i != e; ++i) {
+      MachineOperand &MO = MBBI->getOperand(i);
+      if (!MO.isReg() || MO.isDef())
+        continue;
+      unsigned Reg = MO.getReg();
+      if (!Reg)
+        continue;
+      for (const unsigned *AsI = TRI.getOverlaps(Reg); *AsI; ++AsI)
+        Uses.insert(*AsI);
+    }
+
+    const unsigned *CS = Is64Bit ? CallerSavedRegs64Bit : CallerSavedRegs32Bit;
+    for (; *CS; ++CS)
+      if (!Uses.count(*CS))
+        return *CS;
+  }
+  }
+
+  return 0;
+}
+
+
 /// emitSPUpdate - Emit a series of instructions to increment / decrement the
 /// stack pointer by a constant value.
 static
 void emitSPUpdate(MachineBasicBlock &MBB, MachineBasicBlock::iterator &MBBI,
-                  unsigned StackPtr, int64_t NumBytes, bool Is64Bit,
-                  const TargetInstrInfo &TII) {
+                  unsigned StackPtr, int64_t NumBytes,
+                  bool Is64Bit, const TargetInstrInfo &TII,
+                  const TargetRegisterInfo &TRI) {
   bool isSub = NumBytes < 0;
   uint64_t Offset = isSub ? -NumBytes : NumBytes;
   unsigned Opc = isSub ?
@@ -91,10 +150,26 @@ void emitSPUpdate(MachineBasicBlock &MBB, MachineBasicBlock::iterator &MBBI,
 
   while (Offset) {
     uint64_t ThisVal = (Offset > Chunk) ? Chunk : Offset;
+    if (ThisVal == (Is64Bit ? 8 : 4)) {
+      // Use push / pop instead.
+      unsigned Reg = isSub
+        ? (Is64Bit ? X86::RAX : X86::EAX)
+        : findDeadCallerSavedReg(MBB, MBBI, TRI, Is64Bit);
+      if (Reg) {
+        Opc = isSub
+          ? (Is64Bit ? X86::PUSH64r : X86::PUSH32r)
+          : (Is64Bit ? X86::POP64r  : X86::POP32r);
+        BuildMI(MBB, MBBI, DL, TII.get(Opc))
+          .addReg(Reg, getDefRegState(!isSub) | getUndefRegState(isSub));
+        Offset -= ThisVal;
+        continue;
+      }
+    }
+
     MachineInstr *MI =
       BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr)
-        .addReg(StackPtr)
-        .addImm(ThisVal);
+      .addReg(StackPtr)
+      .addImm(ThisVal);
     MI->getOperand(3).setIsDead(); // The EFLAGS implicit def is dead.
     Offset -= ThisVal;
   }
@@ -531,9 +606,11 @@ void X86FrameInfo::emitPrologue(MachineFunction &MF) const {
     BuildMI(MBB, MBBI, DL, TII.get(X86::WINCALL64pcrel32))
       .addExternalSymbol("__chkstk")
       .addReg(StackPtr, RegState::Define | RegState::Implicit);
-    emitSPUpdate(MBB, MBBI, StackPtr, -(int64_t)NumBytes, Is64Bit, TII);
+    emitSPUpdate(MBB, MBBI, StackPtr, -(int64_t)NumBytes, Is64Bit,
+                 TII, *RegInfo);
   } else if (NumBytes)
-    emitSPUpdate(MBB, MBBI, StackPtr, -(int64_t)NumBytes, Is64Bit, TII);
+    emitSPUpdate(MBB, MBBI, StackPtr, -(int64_t)NumBytes, Is64Bit,
+                 TII, *RegInfo);
 
   if ((NumBytes || PushedRegs) && needsFrameMoves) {
     // Mark end of stack pointer adjustment.
@@ -651,7 +728,7 @@ void X86FrameInfo::emitEpilogue(MachineFunction &MF,
     // We cannot use LEA here, because stack pointer was realigned. We need to
     // deallocate local frame back.
     if (CSSize) {
-      emitSPUpdate(MBB, MBBI, StackPtr, NumBytes, Is64Bit, TII);
+      emitSPUpdate(MBB, MBBI, StackPtr, NumBytes, Is64Bit, TII, *RegInfo);
       MBBI = prior(LastCSPop);
     }
 
@@ -672,7 +749,7 @@ void X86FrameInfo::emitEpilogue(MachineFunction &MF,
     }
   } else if (NumBytes) {
     // Adjust stack pointer back: ESP += numbytes.
-    emitSPUpdate(MBB, MBBI, StackPtr, NumBytes, Is64Bit, TII);
+    emitSPUpdate(MBB, MBBI, StackPtr, NumBytes, Is64Bit, TII, *RegInfo);
   }
 
   // We're returning from function via eh_return.
@@ -707,7 +784,7 @@ void X86FrameInfo::emitEpilogue(MachineFunction &MF,
     if (Offset) {
       // Check for possible merge with preceeding ADD instruction.
       Offset += mergeSPUpdates(MBB, MBBI, StackPtr, true);
-      emitSPUpdate(MBB, MBBI, StackPtr, Offset, Is64Bit, TII);
+      emitSPUpdate(MBB, MBBI, StackPtr, Offset, Is64Bit, TII, *RegInfo);
     }
 
     // Jump to label or value in register.
@@ -751,7 +828,7 @@ void X86FrameInfo::emitEpilogue(MachineFunction &MF,
 
     // Check for possible merge with preceeding ADD instruction.
     delta += mergeSPUpdates(MBB, MBBI, StackPtr, true);
-    emitSPUpdate(MBB, MBBI, StackPtr, delta, Is64Bit, TII);
+    emitSPUpdate(MBB, MBBI, StackPtr, delta, Is64Bit, TII, *RegInfo);
   }
 }
 
diff --git a/lib/Target/X86/X86InstrControl.td b/lib/Target/X86/X86InstrControl.td
index 79a6e4ae52..62ab53eb09 100644
--- a/lib/Target/X86/X86InstrControl.td
+++ b/lib/Target/X86/X86InstrControl.td
@@ -26,7 +26,7 @@ let isTerminator = 1, isReturn = 1, isBarrier = 1,
                     [(X86retflag timm:$amt)]>;
   def RETIW  : Ii16<0xC2, RawFrm, (outs), (ins i16imm:$amt, variable_ops),
                     "retw\t$amt",
-                    [(X86retflag timm:$amt)]>, OpSize;
+                    []>, OpSize;
   def LRETL  : I   <0xCB, RawFrm, (outs), (ins),
                     "lretl", []>;
   def LRETQ  : RI  <0xCB, RawFrm, (outs), (ins),
diff --git a/test/CodeGen/X86/2009-09-10-SpillComments.ll b/test/CodeGen/X86/2009-09-10-SpillComments.ll
index f9ca861c55..adac203360 100644
--- a/test/CodeGen/X86/2009-09-10-SpillComments.ll
+++ b/test/CodeGen/X86/2009-09-10-SpillComments.ll
@@ -2,9 +2,9 @@
 
 ; This test shouldn't require spills.
 
-; CHECK: subq  $8, %rsp
+; CHECK: pushq
 ; CHECK-NOT: $rsp
-; CHECK: addq  $8, %rsp
+; CHECK: popq
 
 	%struct..0anon = type { i32 }
 	%struct.rtvec_def = type { i32, [1 x %struct..0anon] }
diff --git a/test/CodeGen/X86/2010-07-02-asm-alignstack.ll b/test/CodeGen/X86/2010-07-02-asm-alignstack.ll
index cb47d208dd..0bbb24f6ec 100644
--- a/test/CodeGen/X86/2010-07-02-asm-alignstack.ll
+++ b/test/CodeGen/X86/2010-07-02-asm-alignstack.ll
@@ -3,7 +3,7 @@
 define void @foo() nounwind ssp {
 entry:
 ; CHECK: foo
-; CHECK: subq $8, %rsp
+; CHECK: pushq
 ; CHECK: int $3
   call void asm sideeffect alignstack "# top of block", "~{dirflag},~{fpsr},~{flags},~{edi},~{esi},~{edx},~{ecx},~{eax}"() nounwind
   call void asm sideeffect alignstack ".file \22small.c\22", "~{dirflag},~{fpsr},~{flags}"() nounwind
@@ -18,7 +18,7 @@ return:                                           ; preds = %entry
 define void @bar() nounwind ssp {
 entry:
 ; CHECK: bar
-; CHECK-NOT: subq $8, %rsp
+; CHECK-NOT: pushq
 ; CHECK: int $3
   call void asm sideeffect "# top of block", "~{dirflag},~{fpsr},~{flags},~{edi},~{esi},~{edx},~{ecx},~{eax}"() nounwind
   call void asm sideeffect ".file \22small.c\22", "~{dirflag},~{fpsr},~{flags}"() nounwind
diff --git a/test/CodeGen/X86/abi-isel.ll b/test/CodeGen/X86/abi-isel.ll
index 38868ff8dd..3ef312cb65 100644
--- a/test/CodeGen/X86/abi-isel.ll
+++ b/test/CodeGen/X86/abi-isel.ll
@@ -1,16 +1,16 @@
-; RUN: llc < %s -asm-verbose=0 -mtriple=i686-unknown-linux-gnu -march=x86 -relocation-model=static -code-model=small -post-RA-scheduler=false | FileCheck %s -check-prefix=LINUX-32-STATIC
-; RUN: llc < %s -asm-verbose=0 -mtriple=i686-unknown-linux-gnu -march=x86 -relocation-model=static -code-model=small -post-RA-scheduler=false | FileCheck %s -check-prefix=LINUX-32-PIC
+; RUN: llc < %s -asm-verbose=0 -mtriple=i686-unknown-linux-gnu -march=x86 -relocation-model=static -code-model=small | FileCheck %s -check-prefix=LINUX-32-STATIC
+; RUN: llc < %s -asm-verbose=0 -mtriple=i686-unknown-linux-gnu -march=x86 -relocation-model=static -code-model=small | FileCheck %s -check-prefix=LINUX-32-PIC
 
-; RUN: llc < %s -asm-verbose=0 -mtriple=x86_64-unknown-linux-gnu -march=x86-64 -relocation-model=static -code-model=small -post-RA-scheduler=false | FileCheck %s -check-prefix=LINUX-64-STATIC
-; RUN: llc < %s -asm-verbose=0 -mtriple=x86_64-unknown-linux-gnu -march=x86-64 -relocation-model=pic -code-model=small -post-RA-scheduler=false | FileCheck %s -check-prefix=LINUX-64-PIC
+; RUN: llc < %s -asm-verbose=0 -mtriple=x86_64-unknown-linux-gnu -march=x86-64 -relocation-model=static -code-model=small | FileCheck %s -check-prefix=LINUX-64-STATIC
+; RUN: llc < %s -asm-verbose=0 -mtriple=x86_64-unknown-linux-gnu -march=x86-64 -relocation-model=pic -code-model=small | FileCheck %s -check-prefix=LINUX-64-PIC
 
-; RUN: llc < %s -asm-verbose=0 -mtriple=i686-apple-darwin -march=x86 -relocation-model=static -code-model=small -post-RA-scheduler=false | FileCheck %s -check-prefix=DARWIN-32-STATIC
-; RUN: llc < %s -asm-verbose=0 -mtriple=i686-apple-darwin -march=x86 -relocation-model=dynamic-no-pic -code-model=small -post-RA-scheduler=false | FileCheck %s -check-prefix=DARWIN-32-DYNAMIC
-; RUN: llc < %s -asm-verbose=0 -mtriple=i686-apple-darwin -march=x86 -relocation-model=pic -code-model=small -post-RA-scheduler=false | FileCheck %s -check-prefix=DARWIN-32-PIC
+; RUN: llc < %s -asm-verbose=0 -mtriple=i686-apple-darwin -march=x86 -relocation-model=static -code-model=small | FileCheck %s -check-prefix=DARWIN-32-STATIC
+; RUN: llc < %s -asm-verbose=0 -mtriple=i686-apple-darwin -march=x86 -relocation-model=dynamic-no-pic -code-model=small | FileCheck %s -check-prefix=DARWIN-32-DYNAMIC
+; RUN: llc < %s -asm-verbose=0 -mtriple=i686-apple-darwin -march=x86 -relocation-model=pic -code-model=small | FileCheck %s -check-prefix=DARWIN-32-PIC
 
-; RUN: llc < %s -asm-verbose=0 -mtriple=x86_64-apple-darwin -march=x86-64 -relocation-model=static -code-model=small -post-RA-scheduler=false | FileCheck %s -check-prefix=DARWIN-64-STATIC
-; RUN: llc < %s -asm-verbose=0 -mtriple=x86_64-apple-darwin -march=x86-64 -relocation-model=dynamic-no-pic -code-model=small -post-RA-scheduler=false | FileCheck %s -check-prefix=DARWIN-64-DYNAMIC
-; RUN: llc < %s -asm-verbose=0 -mtriple=x86_64-apple-darwin -march=x86-64 -relocation-model=pic -code-model=small -post-RA-scheduler=false | FileCheck %s -check-prefix=DARWIN-64-PIC
+; RUN: llc < %s -asm-verbose=0 -mtriple=x86_64-apple-darwin -march=x86-64 -relocation-model=static -code-model=small | FileCheck %s -check-prefix=DARWIN-64-STATIC
+; RUN: llc < %s -asm-verbose=0 -mtriple=x86_64-apple-darwin -march=x86-64 -relocation-model=dynamic-no-pic -code-model=small | FileCheck %s -check-prefix=DARWIN-64-DYNAMIC
+; RUN: llc < %s -asm-verbose=0 -mtriple=x86_64-apple-darwin -march=x86-64 -relocation-model=pic -code-model=small | FileCheck %s -check-prefix=DARWIN-64-PIC
 
 @src = external global [131072 x i32]
 @dst = external global [131072 x i32]
@@ -8375,7 +8375,7 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: lcallee:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	x
 ; LINUX-32-STATIC-NEXT: 	calll	x
 ; LINUX-32-STATIC-NEXT: 	calll	x
@@ -8383,11 +8383,11 @@ entry:
 ; LINUX-32-STATIC-NEXT: 	calll	x
 ; LINUX-32-STATIC-NEXT: 	calll	x
 ; LINUX-32-STATIC-NEXT: 	calll	x
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: lcallee:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	x
 ; LINUX-32-PIC-NEXT: 	calll	x
 ; LINUX-32-PIC-NEXT: 	calll	x
@@ -8395,11 +8395,11 @@ entry:
 ; LINUX-32-PIC-NEXT: 	calll	x
 ; LINUX-32-PIC-NEXT: 	calll	x
 ; LINUX-32-PIC-NEXT: 	calll	x
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: lcallee:
-; LINUX-64-PIC: 	subq	$8, %rsp
+; LINUX-64-PIC: 	pushq
 ; LINUX-64-PIC-NEXT: 	callq	x@PLT
 ; LINUX-64-PIC-NEXT: 	callq	x@PLT
 ; LINUX-64-PIC-NEXT: 	callq	x@PLT
@@ -8407,7 +8407,7 @@ entry:
 ; LINUX-64-PIC-NEXT: 	callq	x@PLT
 ; LINUX-64-PIC-NEXT: 	callq	x@PLT
 ; LINUX-64-PIC-NEXT: 	callq	x@PLT
-; LINUX-64-PIC-NEXT: 	addq	$8, %rsp
+; LINUX-64-PIC-NEXT: 	popq
 ; LINUX-64-PIC-NEXT: 	ret
 
 ; DARWIN-32-STATIC: _lcallee:
@@ -8447,7 +8447,7 @@ entry:
 ; DARWIN-32-PIC-NEXT: 	ret
 
 ; DARWIN-64-STATIC: _lcallee:
-; DARWIN-64-STATIC: 	subq	$8, %rsp
+; DARWIN-64-STATIC: 	pushq
 ; DARWIN-64-STATIC-NEXT: 	callq	_x
 ; DARWIN-64-STATIC-NEXT: 	callq	_x
 ; DARWIN-64-STATIC-NEXT: 	callq	_x
@@ -8455,11 +8455,11 @@ entry:
 ; DARWIN-64-STATIC-NEXT: 	callq	_x
 ; DARWIN-64-STATIC-NEXT: 	callq	_x
 ; DARWIN-64-STATIC-NEXT: 	callq	_x
-; DARWIN-64-STATIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-STATIC-NEXT: 	popq
 ; DARWIN-64-STATIC-NEXT: 	ret
 
 ; DARWIN-64-DYNAMIC: _lcallee:
-; DARWIN-64-DYNAMIC: 	subq	$8, %rsp
+; DARWIN-64-DYNAMIC: 	pushq
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_x
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_x
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_x
@@ -8467,11 +8467,11 @@ entry:
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_x
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_x
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_x
-; DARWIN-64-DYNAMIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-DYNAMIC-NEXT: 	popq
 ; DARWIN-64-DYNAMIC-NEXT: 	ret
 
 ; DARWIN-64-PIC: _lcallee:
-; DARWIN-64-PIC: 	subq	$8, %rsp
+; DARWIN-64-PIC: 	pushq
 ; DARWIN-64-PIC-NEXT: 	callq	_x
 ; DARWIN-64-PIC-NEXT: 	callq	_x
 ; DARWIN-64-PIC-NEXT: 	callq	_x
@@ -8479,7 +8479,7 @@ entry:
 ; DARWIN-64-PIC-NEXT: 	callq	_x
 ; DARWIN-64-PIC-NEXT: 	callq	_x
 ; DARWIN-64-PIC-NEXT: 	callq	_x
-; DARWIN-64-PIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-PIC-NEXT: 	popq
 ; DARWIN-64-PIC-NEXT: 	ret
 }
 
@@ -8506,7 +8506,7 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: dcallee:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	y
 ; LINUX-32-STATIC-NEXT: 	calll	y
 ; LINUX-32-STATIC-NEXT: 	calll	y
@@ -8514,11 +8514,11 @@ entry:
 ; LINUX-32-STATIC-NEXT: 	calll	y
 ; LINUX-32-STATIC-NEXT: 	calll	y
 ; LINUX-32-STATIC-NEXT: 	calll	y
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: dcallee:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	y
 ; LINUX-32-PIC-NEXT: 	calll	y
 ; LINUX-32-PIC-NEXT: 	calll	y
@@ -8526,11 +8526,11 @@ entry:
 ; LINUX-32-PIC-NEXT: 	calll	y
 ; LINUX-32-PIC-NEXT: 	calll	y
 ; LINUX-32-PIC-NEXT: 	calll	y
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: dcallee:
-; LINUX-64-PIC: 	subq	$8, %rsp
+; LINUX-64-PIC: 	pushq
 ; LINUX-64-PIC-NEXT: 	callq	y@PLT
 ; LINUX-64-PIC-NEXT: 	callq	y@PLT
 ; LINUX-64-PIC-NEXT: 	callq	y@PLT
@@ -8538,7 +8538,7 @@ entry:
 ; LINUX-64-PIC-NEXT: 	callq	y@PLT
 ; LINUX-64-PIC-NEXT: 	callq	y@PLT
 ; LINUX-64-PIC-NEXT: 	callq	y@PLT
-; LINUX-64-PIC-NEXT: 	addq	$8, %rsp
+; LINUX-64-PIC-NEXT: 	popq
 ; LINUX-64-PIC-NEXT: 	ret
 
 ; DARWIN-32-STATIC: _dcallee:
@@ -8578,7 +8578,7 @@ entry:
 ; DARWIN-32-PIC-NEXT: 	ret
 
 ; DARWIN-64-STATIC: _dcallee:
-; DARWIN-64-STATIC: 	subq	$8, %rsp
+; DARWIN-64-STATIC: 	pushq
 ; DARWIN-64-STATIC-NEXT: 	callq	_y
 ; DARWIN-64-STATIC-NEXT: 	callq	_y
 ; DARWIN-64-STATIC-NEXT: 	callq	_y
@@ -8586,11 +8586,11 @@ entry:
 ; DARWIN-64-STATIC-NEXT: 	callq	_y
 ; DARWIN-64-STATIC-NEXT: 	callq	_y
 ; DARWIN-64-STATIC-NEXT: 	callq	_y
-; DARWIN-64-STATIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-STATIC-NEXT: 	popq
 ; DARWIN-64-STATIC-NEXT: 	ret
 
 ; DARWIN-64-DYNAMIC: _dcallee:
-; DARWIN-64-DYNAMIC: 	subq	$8, %rsp
+; DARWIN-64-DYNAMIC: 	pushq
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_y
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_y
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_y
@@ -8598,11 +8598,11 @@ entry:
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_y
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_y
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_y
-; DARWIN-64-DYNAMIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-DYNAMIC-NEXT: 	popq
 ; DARWIN-64-DYNAMIC-NEXT: 	ret
 
 ; DARWIN-64-PIC: _dcallee:
-; DARWIN-64-PIC: 	subq	$8, %rsp
+; DARWIN-64-PIC: 	pushq
 ; DARWIN-64-PIC-NEXT: 	callq	_y
 ; DARWIN-64-PIC-NEXT: 	callq	_y
 ; DARWIN-64-PIC-NEXT: 	callq	_y
@@ -8610,7 +8610,7 @@ entry:
 ; DARWIN-64-PIC-NEXT: 	callq	_y
 ; DARWIN-64-PIC-NEXT: 	callq	_y
 ; DARWIN-64-PIC-NEXT: 	callq	_y
-; DARWIN-64-PIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-PIC-NEXT: 	popq
 ; DARWIN-64-PIC-NEXT: 	ret
 }
 
@@ -8770,24 +8770,24 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: caller:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	callee
 ; LINUX-32-STATIC-NEXT: 	calll	callee
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: caller:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	callee
 ; LINUX-32-PIC-NEXT: 	calll	callee
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: caller:
-; LINUX-64-PIC: 	subq	$8, %rsp
+; LINUX-64-PIC: 	pushq
 ; LINUX-64-PIC-NEXT: 	callq	callee@PLT
 ; LINUX-64-PIC-NEXT: 	callq	callee@PLT
-; LINUX-64-PIC-NEXT: 	addq	$8, %rsp
+; LINUX-64-PIC-NEXT: 	popq
 ; LINUX-64-PIC-NEXT: 	ret
 
 ; DARWIN-32-STATIC: _caller:
@@ -8812,24 +8812,24 @@ entry:
 ; DARWIN-32-PIC-NEXT: 	ret
 
 ; DARWIN-64-STATIC: _caller:
-; DARWIN-64-STATIC: 	subq	$8, %rsp
+; DARWIN-64-STATIC: 	pushq
 ; DARWIN-64-STATIC-NEXT: 	callq	_callee
 ; DARWIN-64-STATIC-NEXT: 	callq	_callee
-; DARWIN-64-STATIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-STATIC-NEXT: 	popq
 ; DARWIN-64-STATIC-NEXT: 	ret
 
 ; DARWIN-64-DYNAMIC: _caller:
-; DARWIN-64-DYNAMIC: 	subq	$8, %rsp
+; DARWIN-64-DYNAMIC: 	pushq
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_callee
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_callee
-; DARWIN-64-DYNAMIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-DYNAMIC-NEXT: 	popq
 ; DARWIN-64-DYNAMIC-NEXT: 	ret
 
 ; DARWIN-64-PIC: _caller:
-; DARWIN-64-PIC: 	subq	$8, %rsp
+; DARWIN-64-PIC: 	pushq
 ; DARWIN-64-PIC-NEXT: 	callq	_callee
 ; DARWIN-64-PIC-NEXT: 	callq	_callee
-; DARWIN-64-PIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-PIC-NEXT: 	popq
 ; DARWIN-64-PIC-NEXT: 	ret
 }
 
@@ -8844,24 +8844,24 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: dcaller:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	dcallee
 ; LINUX-32-STATIC-NEXT: 	calll	dcallee
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: dcaller:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	dcallee
 ; LINUX-32-PIC-NEXT: 	calll	dcallee
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: dcaller:
-; LINUX-64-PIC: 	subq	$8, %rsp
+; LINUX-64-PIC: 	pushq
 ; LINUX-64-PIC-NEXT: 	callq	dcallee
 ; LINUX-64-PIC-NEXT: 	callq	dcallee
-; LINUX-64-PIC-NEXT: 	addq	$8, %rsp
+; LINUX-64-PIC-NEXT: 	popq
 ; LINUX-64-PIC-NEXT: 	ret
 
 ; DARWIN-32-STATIC: _dcaller:
@@ -8886,24 +8886,24 @@ entry:
 ; DARWIN-32-PIC-NEXT: 	ret
 
 ; DARWIN-64-STATIC: _dcaller:
-; DARWIN-64-STATIC: 	subq	$8, %rsp
+; DARWIN-64-STATIC: 	pushq
 ; DARWIN-64-STATIC-NEXT: 	callq	_dcallee
 ; DARWIN-64-STATIC-NEXT: 	callq	_dcallee
-; DARWIN-64-STATIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-STATIC-NEXT: 	popq
 ; DARWIN-64-STATIC-NEXT: 	ret
 
 ; DARWIN-64-DYNAMIC: _dcaller:
-; DARWIN-64-DYNAMIC: 	subq	$8, %rsp
+; DARWIN-64-DYNAMIC: 	pushq
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_dcallee
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_dcallee
-; DARWIN-64-DYNAMIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-DYNAMIC-NEXT: 	popq
 ; DARWIN-64-DYNAMIC-NEXT: 	ret
 
 ; DARWIN-64-PIC: _dcaller:
-; DARWIN-64-PIC: 	subq	$8, %rsp
+; DARWIN-64-PIC: 	pushq
 ; DARWIN-64-PIC-NEXT: 	callq	_dcallee
 ; DARWIN-64-PIC-NEXT: 	callq	_dcallee
-; DARWIN-64-PIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-PIC-NEXT: 	popq
 ; DARWIN-64-PIC-NEXT: 	ret
 }
 
@@ -8918,24 +8918,24 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: lcaller:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	lcallee
 ; LINUX-32-STATIC-NEXT: 	calll	lcallee
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: lcaller:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	lcallee
 ; LINUX-32-PIC-NEXT: 	calll	lcallee
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: lcaller:
-; LINUX-64-PIC: 	subq	$8, %rsp
+; LINUX-64-PIC: 	pushq
 ; LINUX-64-PIC-NEXT: 	callq	lcallee@PLT
 ; LINUX-64-PIC-NEXT: 	callq	lcallee@PLT
-; LINUX-64-PIC-NEXT: 	addq	$8, %rsp
+; LINUX-64-PIC-NEXT: 	popq
 ; LINUX-64-PIC-NEXT: 	ret
 
 ; DARWIN-32-STATIC: _lcaller:
@@ -8960,24 +8960,24 @@ entry:
 ; DARWIN-32-PIC-NEXT: 	ret
 
 ; DARWIN-64-STATIC: _lcaller:
-; DARWIN-64-STATIC: 	subq	$8, %rsp
+; DARWIN-64-STATIC: 	pushq
 ; DARWIN-64-STATIC-NEXT: 	callq	_lcallee
 ; DARWIN-64-STATIC-NEXT: 	callq	_lcallee
-; DARWIN-64-STATIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-STATIC-NEXT: 	popq
 ; DARWIN-64-STATIC-NEXT: 	ret
 
 ; DARWIN-64-DYNAMIC: _lcaller:
-; DARWIN-64-DYNAMIC: 	subq	$8, %rsp
+; DARWIN-64-DYNAMIC: 	pushq
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_lcallee
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_lcallee
-; DARWIN-64-DYNAMIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-DYNAMIC-NEXT: 	popq
 ; DARWIN-64-DYNAMIC-NEXT: 	ret
 
 ; DARWIN-64-PIC: _lcaller:
-; DARWIN-64-PIC: 	subq	$8, %rsp
+; DARWIN-64-PIC: 	pushq
 ; DARWIN-64-PIC-NEXT: 	callq	_lcallee
 ; DARWIN-64-PIC-NEXT: 	callq	_lcallee
-; DARWIN-64-PIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-PIC-NEXT: 	popq
 ; DARWIN-64-PIC-NEXT: 	ret
 }
 
@@ -8990,21 +8990,21 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: tailcaller:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	callee
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: tailcaller:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	callee
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: tailcaller:
-; LINUX-64-PIC: 	subq	$8, %rsp
+; LINUX-64-PIC: 	pushq
 ; LINUX-64-PIC-NEXT: 	callq	callee@PLT
-; LINUX-64-PIC-NEXT: 	addq	$8, %rsp
+; LINUX-64-PIC-NEXT: 	popq
 ; LINUX-64-PIC-NEXT: 	ret
 
 ; DARWIN-32-STATIC: _tailcaller:
@@ -9026,21 +9026,21 @@ entry:
 ; DARWIN-32-PIC-NEXT: 	ret
 
 ; DARWIN-64-STATIC: _tailcaller:
-; DARWIN-64-STATIC: 	subq	$8, %rsp
+; DARWIN-64-STATIC: 	pushq
 ; DARWIN-64-STATIC-NEXT: 	callq	_callee
-; DARWIN-64-STATIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-STATIC-NEXT: 	popq
 ; DARWIN-64-STATIC-NEXT: 	ret
 
 ; DARWIN-64-DYNAMIC: _tailcaller:
-; DARWIN-64-DYNAMIC: 	subq	$8, %rsp
+; DARWIN-64-DYNAMIC: 	pushq
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_callee
-; DARWIN-64-DYNAMIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-DYNAMIC-NEXT: 	popq
 ; DARWIN-64-DYNAMIC-NEXT: 	ret
 
 ; DARWIN-64-PIC: _tailcaller:
-; DARWIN-64-PIC: 	subq	$8, %rsp
+; DARWIN-64-PIC: 	pushq
 ; DARWIN-64-PIC-NEXT: 	callq	_callee
-; DARWIN-64-PIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-PIC-NEXT: 	popq
 ; DARWIN-64-PIC-NEXT: 	ret
 }
 
@@ -9053,21 +9053,21 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: dtailcaller:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	dcallee
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: dtailcaller:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	dcallee
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: dtailcaller:
-; LINUX-64-PIC: 	subq	$8, %rsp
+; LINUX-64-PIC: 	pushq
 ; LINUX-64-PIC-NEXT: 	callq	dcallee
-; LINUX-64-PIC-NEXT: 	addq	$8, %rsp
+; LINUX-64-PIC-NEXT: 	popq
 ; LINUX-64-PIC-NEXT: 	ret
 
 ; DARWIN-32-STATIC: _dtailcaller:
@@ -9089,21 +9089,21 @@ entry:
 ; DARWIN-32-PIC-NEXT: 	ret
 
 ; DARWIN-64-STATIC: _dtailcaller:
-; DARWIN-64-STATIC: 	subq	$8, %rsp
+; DARWIN-64-STATIC: 	pushq
 ; DARWIN-64-STATIC-NEXT: 	callq	_dcallee
-; DARWIN-64-STATIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-STATIC-NEXT: 	popq
 ; DARWIN-64-STATIC-NEXT: 	ret
 
 ; DARWIN-64-DYNAMIC: _dtailcaller:
-; DARWIN-64-DYNAMIC: 	subq	$8, %rsp
+; DARWIN-64-DYNAMIC: 	pushq
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_dcallee
-; DARWIN-64-DYNAMIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-DYNAMIC-NEXT: 	popq
 ; DARWIN-64-DYNAMIC-NEXT: 	ret
 
 ; DARWIN-64-PIC: _dtailcaller:
-; DARWIN-64-PIC: 	subq	$8, %rsp
+; DARWIN-64-PIC: 	pushq
 ; DARWIN-64-PIC-NEXT: 	callq	_dcallee
-; DARWIN-64-PIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-PIC-NEXT: 	popq
 ; DARWIN-64-PIC-NEXT: 	ret
 }
 
@@ -9116,21 +9116,21 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: ltailcaller:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	lcallee
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: ltailcaller:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	lcallee
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: ltailcaller:
-; LINUX-64-PIC: 	subq	$8, %rsp
+; LINUX-64-PIC: 	pushq
 ; LINUX-64-PIC-NEXT: 	callq	lcallee@PLT
-; LINUX-64-PIC-NEXT: 	addq	$8, %rsp
+; LINUX-64-PIC-NEXT: 	popq
 ; LINUX-64-PIC-NEXT: 	ret
 
 ; DARWIN-32-STATIC: _ltailcaller:
@@ -9152,21 +9152,21 @@ entry:
 ; DARWIN-32-PIC-NEXT: 	ret
 
 ; DARWIN-64-STATIC: _ltailcaller:
-; DARWIN-64-STATIC: 	subq	$8, %rsp
+; DARWIN-64-STATIC: 	pushq
 ; DARWIN-64-STATIC-NEXT: 	callq	_lcallee
-; DARWIN-64-STATIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-STATIC-NEXT: 	popq
 ; DARWIN-64-STATIC-NEXT: 	ret
 
 ; DARWIN-64-DYNAMIC: _ltailcaller:
-; DARWIN-64-DYNAMIC: 	subq	$8, %rsp
+; DARWIN-64-DYNAMIC: 	pushq
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	_lcallee
-; DARWIN-64-DYNAMIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-DYNAMIC-NEXT: 	popq
 ; DARWIN-64-DYNAMIC-NEXT: 	ret
 
 ; DARWIN-64-PIC: _ltailcaller:
-; DARWIN-64-PIC: 	subq	$8, %rsp
+; DARWIN-64-PIC: 	pushq
 ; DARWIN-64-PIC-NEXT: 	callq	_lcallee
-; DARWIN-64-PIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-PIC-NEXT: 	popq
 ; DARWIN-64-PIC-NEXT: 	ret
 }
 
@@ -9183,17 +9183,17 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: icaller:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	*ifunc
 ; LINUX-32-STATIC-NEXT: 	calll	*ifunc
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: icaller:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	*ifunc
 ; LINUX-32-PIC-NEXT: 	calll	*ifunc
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: icaller:
@@ -9272,17 +9272,17 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: dicaller:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	*difunc
 ; LINUX-32-STATIC-NEXT: 	calll	*difunc
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: dicaller:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	*difunc
 ; LINUX-32-PIC-NEXT: 	calll	*difunc
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: dicaller:
@@ -9320,24 +9320,24 @@ entry:
 ; DARWIN-32-PIC-NEXT: 	ret
 
 ; DARWIN-64-STATIC: _dicaller:
-; DARWIN-64-STATIC: 	subq	$8, %rsp
+; DARWIN-64-STATIC: 	pushq
 ; DARWIN-64-STATIC-NEXT: 	callq	*_difunc(%rip)
 ; DARWIN-64-STATIC-NEXT: 	callq	*_difunc(%rip)
-; DARWIN-64-STATIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-STATIC-NEXT: 	popq
 ; DARWIN-64-STATIC-NEXT: 	ret
 
 ; DARWIN-64-DYNAMIC: _dicaller:
-; DARWIN-64-DYNAMIC: 	subq	$8, %rsp
+; DARWIN-64-DYNAMIC: 	pushq
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	*_difunc(%rip)
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	*_difunc(%rip)
-; DARWIN-64-DYNAMIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-DYNAMIC-NEXT: 	popq
 ; DARWIN-64-DYNAMIC-NEXT: 	ret
 
 ; DARWIN-64-PIC: _dicaller:
-; DARWIN-64-PIC: 	subq	$8, %rsp
+; DARWIN-64-PIC: 	pushq
 ; DARWIN-64-PIC-NEXT: 	callq	*_difunc(%rip)
 ; DARWIN-64-PIC-NEXT: 	callq	*_difunc(%rip)
-; DARWIN-64-PIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-PIC-NEXT: 	popq
 ; DARWIN-64-PIC-NEXT: 	ret
 }
 
@@ -9354,24 +9354,24 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: licaller:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	*lifunc
 ; LINUX-32-STATIC-NEXT: 	calll	*lifunc
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: licaller:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	*lifunc
 ; LINUX-32-PIC-NEXT: 	calll	*lifunc
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: licaller:
-; LINUX-64-PIC: 	subq	$8, %rsp
+; LINUX-64-PIC: 	pushq
 ; LINUX-64-PIC-NEXT: 	callq	*lifunc(%rip)
 ; LINUX-64-PIC-NEXT: 	callq	*lifunc(%rip)
-; LINUX-64-PIC-NEXT: 	addq	$8, %rsp
+; LINUX-64-PIC-NEXT: 	popq
 ; LINUX-64-PIC-NEXT: 	ret
 
 ; DARWIN-32-STATIC: _licaller:
@@ -9401,24 +9401,24 @@ entry:
 ; DARWIN-32-PIC-NEXT: 	ret
 
 ; DARWIN-64-STATIC: _licaller:
-; DARWIN-64-STATIC: 	subq	$8, %rsp
+; DARWIN-64-STATIC: 	pushq
 ; DARWIN-64-STATIC-NEXT: 	callq	*_lifunc(%rip)
 ; DARWIN-64-STATIC-NEXT: 	callq	*_lifunc(%rip)
-; DARWIN-64-STATIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-STATIC-NEXT: 	popq
 ; DARWIN-64-STATIC-NEXT: 	ret
 
 ; DARWIN-64-DYNAMIC: _licaller:
-; DARWIN-64-DYNAMIC: 	subq	$8, %rsp
+; DARWIN-64-DYNAMIC: 	pushq
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	*_lifunc(%rip)
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	*_lifunc(%rip)
-; DARWIN-64-DYNAMIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-DYNAMIC-NEXT: 	popq
 ; DARWIN-64-DYNAMIC-NEXT: 	ret
 
 ; DARWIN-64-PIC: _licaller:
-; DARWIN-64-PIC: 	subq	$8, %rsp
+; DARWIN-64-PIC: 	pushq
 ; DARWIN-64-PIC-NEXT: 	callq	*_lifunc(%rip)
 ; DARWIN-64-PIC-NEXT: 	callq	*_lifunc(%rip)
-; DARWIN-64-PIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-PIC-NEXT: 	popq
 ; DARWIN-64-PIC-NEXT: 	ret
 }
 
@@ -9435,17 +9435,17 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: itailcaller:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	*ifunc
 ; LINUX-32-STATIC-NEXT: 	calll	*ifunc
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: itailcaller:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	*ifunc
 ; LINUX-32-PIC-NEXT: 	calll	*ifunc
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: itailcaller:
@@ -9521,22 +9521,22 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: ditailcaller:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	*difunc
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: ditailcaller:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	*difunc
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: ditailcaller:
-; LINUX-64-PIC: 	subq	$8, %rsp
+; LINUX-64-PIC: 	pushq
 ; LINUX-64-PIC-NEXT: 	movq	difunc@GOTPCREL(%rip), %rax
 ; LINUX-64-PIC-NEXT: 	callq	*(%rax)
-; LINUX-64-PIC-NEXT: 	addq	$8, %rsp
+; LINUX-64-PIC-NEXT: 	popq
 ; LINUX-64-PIC-NEXT: 	ret
 
 ; DARWIN-32-STATIC: _ditailcaller:
@@ -9561,20 +9561,20 @@ entry:
 ; DARWIN-32-PIC-NEXT: 	ret
 
 ; DARWIN-64-STATIC: _ditailcaller:
-; DARWIN-64-STATIC: 	subq	$8, %rsp
+; DARWIN-64-STATIC: 	pushq
 ; DARWIN-64-STATIC-NEXT: 	callq	*_difunc(%rip)
-; DARWIN-64-STATIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-STATIC-NEXT: 	popq
 ; DARWIN-64-STATIC-NEXT: 	ret
 
 ; DARWIN-64-DYNAMIC: _ditailcaller:
-; DARWIN-64-DYNAMIC: 	subq	$8, %rsp
+; DARWIN-64-DYNAMIC: 	pushq
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	*_difunc(%rip)
-; DARWIN-64-DYNAMIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-DYNAMIC-NEXT: 	popq
 ; DARWIN-64-DYNAMIC-NEXT: 	ret
 
 ; DARWIN-64-PIC: _ditailcaller:
 ; DARWIN-64-PIC: 	callq	*_difunc(%rip)
-; DARWIN-64-PIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-PIC-NEXT: 	popq
 ; DARWIN-64-PIC-NEXT: 	ret
 }
 
@@ -9588,21 +9588,21 @@ entry:
 ; LINUX-64-STATIC: ret
 
 ; LINUX-32-STATIC: litailcaller:
-; LINUX-32-STATIC: 	subl	$4, %esp
+; LINUX-32-STATIC: 	pushl
 ; LINUX-32-STATIC-NEXT: 	calll	*lifunc
-; LINUX-32-STATIC-NEXT: 	addl	$4, %esp
+; LINUX-32-STATIC-NEXT: 	popl
 ; LINUX-32-STATIC-NEXT: 	ret
 
 ; LINUX-32-PIC: litailcaller:
-; LINUX-32-PIC: 	subl	$4, %esp
+; LINUX-32-PIC: 	pushl
 ; LINUX-32-PIC-NEXT: 	calll	*lifunc
-; LINUX-32-PIC-NEXT: 	addl	$4, %esp
+; LINUX-32-PIC-NEXT: 	popl
 ; LINUX-32-PIC-NEXT: 	ret
 
 ; LINUX-64-PIC: litailcaller:
-; LINUX-64-PIC: 	subq	$8, %rsp
+; LINUX-64-PIC: 	pushq
 ; LINUX-64-PIC-NEXT: 	callq	*lifunc(%rip)
-; LINUX-64-PIC-NEXT: 	addq	$8, %rsp
+; LINUX-64-PIC-NEXT: 	popq
 ; LINUX-64-PIC-NEXT: 	ret
 
 ; DARWIN-32-STATIC: _litailcaller:
@@ -9627,20 +9627,20 @@ entry:
 ; DARWIN-32-PIC-NEXT: 	ret
 
 ; DARWIN-64-STATIC: _litailcaller:
-; DARWIN-64-STATIC: 	subq	$8, %rsp
+; DARWIN-64-STATIC: 	pushq
 ; DARWIN-64-STATIC-NEXT: 	callq	*_lifunc(%rip)
-; DARWIN-64-STATIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-STATIC-NEXT: 	popq
 ; DARWIN-64-STATIC-NEXT: 	ret
 
 ; DARWIN-64-DYNAMIC: _litailcaller:
-; DARWIN-64-DYNAMIC: 	subq	$8, %rsp
+; DARWIN-64-DYNAMIC: 	pushq
 ; DARWIN-64-DYNAMIC-NEXT: 	callq	*_lifunc(%rip)
-; DARWIN-64-DYNAMIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-DYNAMIC-NEXT: 	popq
 ; DARWIN-64-DYNAMIC-NEXT: 	ret
 
 ; DARWIN-64-PIC: _litailcaller:
-; DARWIN-64-PIC: 	subq	$8, %rsp
+; DARWIN-64-PIC: 	pushq
 ; DARWIN-64-PIC-NEXT: 	callq	*_lifunc(%rip)
-; DARWIN-64-PIC-NEXT: 	addq	$8, %rsp
+; DARWIN-64-PIC-NEXT: 	popq
 ; DARWIN-64-PIC-NEXT: 	ret
 }
diff --git a/test/CodeGen/X86/licm-symbol.ll b/test/CodeGen/X86/licm-symbol.ll
index 08306c2950..c3d1938e9d 100644
--- a/test/CodeGen/X86/licm-symbol.ll
+++ b/test/CodeGen/X86/licm-symbol.ll
@@ -3,7 +3,7 @@
 ; MachineLICM should be able to hoist the sF reference out of the loop.
 
 ; CHECK: pushl %esi
-; CHECK: subl  $4, %esp
+; CHECK: pushl
 ; CHECK: movl  $176, %esi
 ; CHECK: addl  L___sF$non_lazy_ptr, %esi
 ; CHECK: .align  4, 0x90
diff --git a/test/CodeGen/X86/tail-opts.ll b/test/CodeGen/X86/tail-opts.ll
index f546ac44e2..9291695f4d 100644
--- a/test/CodeGen/X86/tail-opts.ll
+++ b/test/CodeGen/X86/tail-opts.ll
@@ -273,7 +273,7 @@ declare fastcc %union.tree_node* @default_conversion(%union.tree_node*) nounwind
 ; CHECK: foo:
 ; CHECK:        callq func
 ; CHECK-NEXT: .LBB4_2:
-; CHECK-NEXT:   addq $8, %rsp
+; CHECK-NEXT:   popq
 ; CHECK-NEXT:   ret
 
 define void @foo(i1* %V) nounwind {
diff --git a/test/CodeGen/X86/tailcall-largecode.ll b/test/CodeGen/X86/tailcall-largecode.ll
index c7070f2abd..c3f4278aec 100644
--- a/test/CodeGen/X86/tailcall-largecode.ll
+++ b/test/CodeGen/X86/tailcall-largecode.ll
@@ -17,7 +17,7 @@ define fastcc i32 @indirect_manyargs(i32(i32,i32,i32,i32,i32,i32,i32)* %target)
 ; Adjust the stack to enter the function.  (The amount of the
 ; adjustment may change in the future, in which case the location of
 ; the stack argument and the return adjustment will change too.)
-;  CHECK: subq $8, %rsp
+;  CHECK: pushq
 ; Put the call target into R11, which won't be clobbered while restoring
 ; callee-saved registers and won't be used for passing arguments.
 ;  CHECK: movq %rdi, %rax
@@ -31,7 +31,7 @@ define fastcc i32 @indirect_manyargs(i32(i32,i32,i32,i32,i32,i32,i32)* %target)
 ;  CHECK: movl $5, %r8d
 ;  CHECK: movl $6, %r9d
 ; Adjust the stack to "return".
-;  CHECK: addq $8, %rsp
+;  CHECK: popq
 ; And tail-call to the target.
 ;  CHECK: jmpq *%rax  # TAILCALL
   %res = tail call fastcc i32 %target(i32 1, i32 2, i32 3, i32 4, i32 5,
@@ -46,7 +46,7 @@ define fastcc i32 @direct_manyargs() {
 ; Adjust the stack to enter the function.  (The amount of the
 ; adjustment may change in the future, in which case the location of
 ; the stack argument and the return adjustment will change too.)
-;  CHECK: subq $8, %rsp
+;  CHECK: pushq
 ; Pass the stack argument.
 ;  CHECK: movl $7, 16(%rsp)
 ; Pass the register arguments, in the right registers.
@@ -62,7 +62,7 @@ define fastcc i32 @direct_manyargs() {
 ; arguments.
 ;  CHECK: movabsq $manyargs_callee, %rax
 ; Adjust the stack to "return".
-;  CHECK: addq $8, %rsp
+;  CHECK: popq
 ; And tail-call to the target.
 ;  CHECK: jmpq *%rax  # TAILCALL
   %res = tail call fastcc i32 @manyargs_callee(i32 1, i32 2, i32 3, i32 4,
diff --git a/test/CodeGen/X86/tlv-2.ll b/test/CodeGen/X86/tlv-2.ll
index 883801d854..5f29a60bef 100644
--- a/test/CodeGen/X86/tlv-2.ll
+++ b/test/CodeGen/X86/tlv-2.ll
@@ -26,7 +26,7 @@ entry:
   ; CHECK: movq    _d@TLVP(%rip), %rdi
   ; CHECK: callq   *(%rdi)
   ; CHECK: movl    $4, (%rax)
-  ; CHECK: addq    $8, %rsp
+  ; CHECK: popq
   
   ret void
 }