More closely follow libgcc, which has code after the `ret' instruction to

release the stack segment and reset the stack pointer. Place the code in its own
MBB to make the verifier happy.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@141859 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86FrameLowering.cpp b/lib/Target/X86/X86FrameLowering.cpp
index 757cef2d7f7dc708edf63f482cb1c8a9213e3179..07e0d0ed2639b93a4776d05ff2e6e78e43ac38ef 100644 (file)
--- a/lib/Target/X86/X86FrameLowering.cpp
+++ b/lib/Target/X86/X86FrameLowering.cpp
@@ -1336,15 +1336,28 @@ X86FrameLowering::adjustForSegmentedStacks(MachineFunction &MF) const {
   if (Is64Bit)
     IsNested = HasNestArgument(&MF);
 
+  // The MOV R10, RAX needs to be in a different block, since the RET we emit in
+  // allocMBB needs to be last (terminating) instruction.
+  MachineBasicBlock *restoreR10MBB = NULL;
+  if (IsNested)
+    restoreR10MBB = MF.CreateMachineBasicBlock();
+
   for (MachineBasicBlock::livein_iterator i = prologueMBB.livein_begin(),
          e = prologueMBB.livein_end(); i != e; i++) {
     allocMBB->addLiveIn(*i);
     checkMBB->addLiveIn(*i);
+
+    if (IsNested)
+      restoreR10MBB->addLiveIn(*i);
   }
 
-  if (IsNested)
+  if (IsNested) {
     allocMBB->addLiveIn(X86::R10);
+    restoreR10MBB->addLiveIn(X86::RAX);
+  }
 
+  if (IsNested)
+    MF.push_front(restoreR10MBB);
   MF.push_front(allocMBB);
   MF.push_front(checkMBB);
 
@@ -1414,13 +1427,19 @@ X86FrameLowering::adjustForSegmentedStacks(MachineFunction &MF) const {
   if (!Is64Bit)
     BuildMI(allocMBB, DL, TII.get(X86::ADD32ri), X86::ESP).addReg(X86::ESP)
       .addImm(8);
+  BuildMI(allocMBB, DL, TII.get(X86::RET));
 
-  if (Is64Bit && IsNested)
-    BuildMI(allocMBB, DL, TII.get(X86::MOV64rr), X86::R10).addReg(X86::RAX);
+  if (IsNested)
+    BuildMI(restoreR10MBB, DL, TII.get(X86::MOV64rr), X86::R10)
+      .addReg(X86::RAX);
 
-  BuildMI(allocMBB, DL, TII.get(X86::RET));
+  if (IsNested) {
+    allocMBB->addSuccessor(restoreR10MBB);
+    restoreR10MBB->addSuccessor(&prologueMBB);
+  } else {
+    allocMBB->addSuccessor(&prologueMBB);
+  }
 
-  allocMBB->addSuccessor(&prologueMBB);
   checkMBB->addSuccessor(allocMBB);
   checkMBB->addSuccessor(&prologueMBB);
 

diff --git a/test/CodeGen/X86/segmented-stacks.ll b/test/CodeGen/X86/segmented-stacks.ll
index 37f082c730a833f0428f72031cef6e15549d96de..ecdb00d5d1efad54c62071644945677ad845af2c 100644 (file)
--- a/test/CodeGen/X86/segmented-stacks.ll
+++ b/test/CodeGen/X86/segmented-stacks.ll
@@ -81,7 +81,7 @@ define i32 @test_nested(i32 * nest %closure, i32 %other) {
 ; X64-NEXT: movabsq $0, %r10
 ; X64-NEXT: movabsq $0, %r11
 ; X64-NEXT: callq __morestack
-; X64-NEXT: movq %rax, %r10
 ; X64-NEXT: ret
+; X64:      movq %rax, %r10
 
 }