on darwin empty functions need to codegen into something of non-zero length,

otherwise labels get incorrectly merged.  We handled this by emitting a 
".byte 0", but this isn't correct on thumb/arm targets where the text segment
needs to be a multiple of 2/4 bytes.  Handle this by emitting a noop.  This
is more gross than it should be because arm/ppc are not fully mc'ized yet.

This fixes rdar://7908505

llvm-svn: 102400

include/llvm/Target/TargetInstrInfo.h

@@ -24,6 +24,7 @@ class LiveVariables;
 class MCAsmInfo;
 class MachineMemOperand;
 class MDNode;
+class MCInst;
 class SDNode;
 class SelectionDAG;
 class TargetRegisterClass;
@@ -490,6 +491,13 @@ public:
   virtual void insertNoop(MachineBasicBlock &MBB, 
                           MachineBasicBlock::iterator MI) const;
   
+  
+  /// getNoopForMachoTarget - Return the noop instruction to use for a noop.
+  virtual void getNoopForMachoTarget(MCInst &NopInst) const {
+    // Default to just using 'nop' string.
+  }
+  
+  
   /// isPredicated - Returns true if the instruction is already predicated.
   ///
   virtual bool isPredicated(const MachineInstr *MI) const {

lib/CodeGen/AsmPrinter/AsmPrinter.cpp

@@ -585,9 +585,15 @@ void AsmPrinter::EmitFunctionBody() {
   
   // If the function is empty and the object file uses .subsections_via_symbols,
   // then we need to emit *something* to the function body to prevent the
-  // labels from collapsing together.  Just emit a 0 byte.
-  if (MAI->hasSubsectionsViaSymbols() && !HasAnyRealCode)
-    OutStreamer.EmitIntValue(0, 1, 0/*addrspace*/);
+  // labels from collapsing together.  Just emit a noop.
+  if (MAI->hasSubsectionsViaSymbols() && !HasAnyRealCode) {
+    MCInst Noop;
+    TM.getInstrInfo()->getNoopForMachoTarget(Noop);
+    if (Noop.getOpcode())
+      OutStreamer.EmitInstruction(Noop);
+    else  // Target not mc-ized yet.
+      OutStreamer.EmitRawText(StringRef("\tnop\n"));
+  }
   
   // Emit target-specific gunk after the function body.
   EmitFunctionBodyEnd();

lib/Target/X86/X86InstrInfo.cpp

@@ -27,6 +27,7 @@
 #include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/CodeGen/LiveVariables.h"
 #include "llvm/CodeGen/PseudoSourceValue.h"
+#include "llvm/MC/MCInst.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/ErrorHandling.h"
@@ -3766,3 +3767,9 @@ void X86InstrInfo::SetSSEDomain(MachineInstr *MI, unsigned Domain) const {
   assert(table && "Cannot change domain");
   MI->setDesc(get(table[Domain-1]));
 }
+
+/// getNoopForMachoTarget - Return the noop instruction to use for a noop.
+void X86InstrInfo::getNoopForMachoTarget(MCInst &NopInst) const {
+  NopInst.setOpcode(X86::NOOP);
+}
+

lib/Target/X86/X86InstrInfo.h

@@ -693,6 +693,8 @@ public:
                                        int64_t Offset1, int64_t Offset2,
                                        unsigned NumLoads) const;
 
+  virtual void getNoopForMachoTarget(MCInst &NopInst) const;
+
   virtual
   bool ReverseBranchCondition(SmallVectorImpl<MachineOperand> &Cond) const;
 

test/CodeGen/PowerPC/2008-01-25-EmptyFunction.ll

@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=ppc32 | grep .byte
+; RUN: llc < %s -march=ppc32 | grep nop
 target triple = "powerpc-apple-darwin8"
 
 

test/CodeGen/X86/2008-01-25-EmptyFunction.ll

@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 | grep {.byte	0}
+; RUN: llc < %s -march=x86 | grep nop
 target triple = "i686-apple-darwin8"