[CodeGen] Emit necessary .note sections for -fsplit-stack

[cherry]

Summary

According to https://gcc.gnu.org/wiki/SplitStacks, the linker expects a zero-sized .note.GNU-split-stack section if split-stack is used (and also .note.GNU-no-split-stack section if it also contains non-split-stack functions), so it can handle the cases where a split-stack function calls non-split-stack function.

This change adds the sections if needed.

Fixes PR #34670.

[rnk]

Looks good, thanks!

[cherry]

Thank you for the review!

include/llvm/CodeGen/MachineModuleInfo.h

class MachineModuleInfo : public ImmutablePass {
   bool UsesVAFloatArgument;
 
   /// True if the module calls the __morestack function indirectly, as is
   /// required under the large code model on x86. This is used to emit
   /// a definition of a symbol, __morestack_addr, containing the address. See
   /// comments in lib/Target/X86/X86FrameLowering.cpp for more details.
   bool UsesMorestackAddr;
 
+  /// True if the module contains split-stack functions. This is used to
+  /// emit .note.GNU-split-stack section as required by the linker for
+  /// special handling split-stack function calling no-split-stack function.
+  bool HasSplitStack;
+
+  /// True if the module contains no-split-stack functions. This is used to
+  /// emit .note.GNU-no-split-stack section when it also contains split-stack
+  /// functions.
+  bool HasNosplitStack;
+
   /// Maps IR Functions to their corresponding MachineFunctions.
   DenseMap<const Function*, std::unique_ptr<MachineFunction>> MachineFunctions;
   /// Next unique number available for a MachineFunction.
   unsigned NextFnNum = 0;
   const Function *LastRequest = nullptr; ///< Used for shortcut/cache.
   MachineFunction *LastResult = nullptr; ///< Used for shortcut/cache.
 
 public:
public:
   bool usesMorestackAddr() const {
     return UsesMorestackAddr;
   }
 
   void setUsesMorestackAddr(bool b) {
     UsesMorestackAddr = b;
   }
 
+  bool hasSplitStack() const {
+    return HasSplitStack;
+  }
+
+  void setHasSplitStack(bool b) {
+    HasSplitStack = b;
+  }
+
+  bool hasNosplitStack() const {
+    return HasNosplitStack;
+  }
+
+  void setHasNosplitStack(bool b) {
+    HasNosplitStack = b;
+  }
+
   /// Return the symbol to be used for the specified basic block when its
   /// address is taken.  This cannot be its normal LBB label because the block
   /// may be accessed outside its containing function.
   MCSymbol *getAddrLabelSymbol(const BasicBlock *BB) {
     return getAddrLabelSymbolToEmit(BB).front();
   }
 
   /// Return the symbol to be used for the specified basic block when its

lib/CodeGen/AsmPrinter/AsmPrinter.cpp

MCSymbol *AddrSymbol =
         OutContext.getOrCreateSymbol(StringRef("__morestack_addr"));
     OutStreamer->EmitLabel(AddrSymbol);
 
     unsigned PtrSize = MAI->getCodePointerSize();
     OutStreamer->EmitSymbolValue(GetExternalSymbolSymbol("__morestack"),
                                  PtrSize);
   }
 
+  // Emit .note.GNU-split-stack and .note.GNU-no-split-stack sections if
+  // split-stack is used.
+  if (TM.getTargetTriple().isOSBinFormatELF() && MMI->hasSplitStack()) {
+    OutStreamer->SwitchSection(
+        OutContext.getELFSection(".note.GNU-split-stack", ELF::SHT_PROGBITS, 0));
+    if (MMI->hasNosplitStack())
+      OutStreamer->SwitchSection(
+          OutContext.getELFSection(".note.GNU-no-split-stack", ELF::SHT_PROGBITS, 0));
+  }
+
   // If we don't have any trampolines, then we don't require stack memory
   // to be executable. Some targets have a directive to declare this.
   Function *InitTrampolineIntrinsic = M.getFunction("llvm.init.trampoline");
   if (!InitTrampolineIntrinsic || InitTrampolineIntrinsic->use_empty())
     if (MCSection *S = MAI->getNonexecutableStackSection(OutContext))
       OutStreamer->SwitchSection(S);
 
   // Allow the target to emit any magic that it wants at the end of the file,

lib/CodeGen/MachineModuleInfo.cpp

 }
 
 MachineModuleInfo::~MachineModuleInfo() = default;
 
 bool MachineModuleInfo::doInitialization(Module &M) {
   ObjFileMMI = nullptr;
   CurCallSite = 0;
   DbgInfoAvailable = UsesVAFloatArgument = UsesMorestackAddr = false;
+  HasSplitStack = HasNosplitStack = false;
   AddrLabelSymbols = nullptr;
   TheModule = &M;
   return false;
 }
 
 bool MachineModuleInfo::doFinalization(Module &M) {
   Personalities.clear();
 

lib/CodeGen/PrologEpilogInserter.cpp

void PEI::insertPrologEpilogCode(MachineFunction &Fn) {
 
   // Emit additional code that is required to support segmented stacks, if
   // we've been asked for it.  This, when linked with a runtime with support
   // for segmented stacks (libgcc is one), will result in allocating stack
   // space in small chunks instead of one large contiguous block.
   if (Fn.shouldSplitStack()) {
     for (MachineBasicBlock *SaveBlock : SaveBlocks)
       TFI.adjustForSegmentedStacks(Fn, *SaveBlock);
-  }
+    // Record that there are split-stack functions, so we will emit a
+    // special section to tell the linker.
+    Fn.getMMI().setHasSplitStack(true);
+  } else
+    Fn.getMMI().setHasNosplitStack(true);
 
   // Emit additional code that is required to explicitly handle the stack in
   // HiPE native code (if needed) when loaded in the Erlang/OTP runtime. The
   // approach is rather similar to that of Segmented Stacks, but it uses a
   // different conditional check and another BIF for allocating more stack
   // space.
   if (Fn.getFunction()->getCallingConv() == CallingConv::HiPE)
     for (MachineBasicBlock *SaveBlock : SaveBlocks)

test/CodeGen/X86/segmented-stacks.ll

 
 ; X32-DFlyBSD-LABEL: test_nostack:
 ; X32-DFlyBSD-NOT:   calll __morestack
 
 ; X64-DFlyBSD-LABEL: test_nostack:
 ; X64-DFlyBSD-NOT:   callq __morestack
 }
 
+define void @test_nosplitstck() {
+  ret void
+}
+
 attributes #0 = { "split-stack" }
 
 ; X64-Linux-Large: .rodata
 ; X64-Linux-Large-NEXT: __morestack_addr:
 ; X64-Linux-Large-NEXT: .quad __morestack
+
+; X32-Linux: .section ".note.GNU-split-stack","",@progbits
+; X32-Linux: .section ".note.GNU-no-split-stack","",@progbits
+
+; X64-Linux: .section ".note.GNU-split-stack","",@progbits
+; X64-Linux: .section ".note.GNU-no-split-stack","",@progbits
+
+; X64-FreeBSD: .section ".note.GNU-split-stack","",@progbits
+; X64-FreeBSD: .section ".note.GNU-no-split-stack","",@progbits
+
+; X32-DFlyBSD: .section ".note.GNU-split-stack","",@progbits
+; X32-DFlyBSD: .section ".note.GNU-no-split-stack","",@progbits
+
+; X64-DFlyBSD: .section ".note.GNU-split-stack","",@progbits
+; X64-DFlyBSD: .section ".note.GNU-no-split-stack","",@progbits