Added a option to the disassembler to print immediates as hex.

This is for the lldb team so most of but not all of the values are
to be printed as hex with this option.  Some small values like the
scale in an X86 address were requested to printed in decimal
without the leading 0x.

There may be some tweaks need to places that may still be in
decimal that they want in hex.  Specially for arm.  I made my best
guess.  Any tweaks from here should be simple.

I also did the best I know now with help from the C++ gurus
creating the cleanest formatImm() utility function and containing
the changes.  But if someone has a better idea to make something
cleaner I'm all ears and game for changing the implementation.

rdar://8109283



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169393 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm-c/Disassembler.h

@@ -153,6 +153,8 @@ int LLVMSetDisasmOptions(LLVMDisasmContextRef DC, uint64_t Options);
 
 /* The option to produce marked up assembly. */
 #define LLVMDisassembler_Option_UseMarkup 1
+/* The option to print immediates as hex. */
+#define LLVMDisassembler_Option_PrintImmHex 2
 
 /**
  * Dispose of a disassembler context.

include/llvm/MC/MCInstPrinter.h

@@ -10,6 +10,8 @@
 #ifndef LLVM_MC_MCINSTPRINTER_H
 #define LLVM_MC_MCINSTPRINTER_H
 
+#include "llvm/Support/Format.h"
+
 namespace llvm {
 class MCInst;
 class raw_ostream;
@@ -36,13 +38,16 @@ class MCInstPrinter {
   /// True if we are printing marked up assembly.
   bool UseMarkup;
 
+  /// True if we are printing immediates as hex.
+  bool PrintImmHex;
+
   /// Utility function for printing annotations.
   void printAnnotation(raw_ostream &OS, StringRef Annot);
 public:
   MCInstPrinter(const MCAsmInfo &mai, const MCInstrInfo &mii,
                 const MCRegisterInfo &mri)
     : CommentStream(0), MAI(mai), MII(mii), MRI(mri), AvailableFeatures(0),
-      UseMarkup(0) {}
+      UseMarkup(0), PrintImmHex(0) {}
 
   virtual ~MCInstPrinter();
 
@@ -70,6 +75,12 @@ class MCInstPrinter {
   /// Utility functions to make adding mark ups simpler.
   StringRef markup(StringRef s) const;
   StringRef markup(StringRef a, StringRef b) const;
+
+  bool getPrintImmHex() const { return PrintImmHex; }
+  void setPrintImmHex(bool Value) { PrintImmHex = Value; }
+
+  /// Utility function to print immediates in decimal or hex.
+  format_object1<int64_t> formatImm(const int64_t Value) const;
 };
 
 } // namespace llvm

lib/MC/MCDisassembler/Disassembler.cpp

@@ -182,5 +182,11 @@ int LLVMSetDisasmOptions(LLVMDisasmContextRef DCR, uint64_t Options){
       IP->setUseMarkup(1);
       Options &= ~LLVMDisassembler_Option_UseMarkup;
   }
+  if (Options & LLVMDisassembler_Option_PrintImmHex){
+      LLVMDisasmContext *DC = (LLVMDisasmContext *)DCR;
+      MCInstPrinter *IP = DC->getIP();
+      IP->setPrintImmHex(1);
+      Options &= ~LLVMDisassembler_Option_PrintImmHex;
+  }
   return (Options == 0);
 }

lib/MC/MCInstPrinter.cpp

@@ -12,6 +12,7 @@
 #include "llvm/MC/MCAsmInfo.h"
 #include "llvm/MC/MCInstrInfo.h"
 #include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/Format.h"
 #include "llvm/Support/raw_ostream.h"
 using namespace llvm;
 
@@ -50,3 +51,11 @@ StringRef MCInstPrinter::markup(StringRef a, StringRef b) const {
   else
     return b;
 }
+
+/// Utility function to print immediates in decimal or hex.
+format_object1<int64_t> MCInstPrinter::formatImm(const int64_t Value) const {
+  if (getPrintImmHex())
+    return format("0x%llx", Value);
+  else
+    return format("%lld", Value);
+}

lib/Target/ARM/InstPrinter/ARMInstPrinter.cpp

@@ -293,7 +293,7 @@ void ARMInstPrinter::printOperand(const MCInst *MI, unsigned OpNo,
     printRegName(O, Reg);
   } else if (Op.isImm()) {
     O << markup("<imm:")
-      << '#' << Op.getImm()
+      << '#' << formatImm(Op.getImm())
       << markup(">");
   } else {
     assert(Op.isExpr() && "unknown operand kind in printOperand");
@@ -319,7 +319,7 @@ void ARMInstPrinter::printThumbLdrLabelOperand(const MCInst *MI, unsigned OpNum,
     O << *MO1.getExpr();
   else if (MO1.isImm()) {
     O << markup("<mem:") << "[pc, "
-      << markup("<imm:") << "#" << MO1.getImm()
+      << markup("<imm:") << "#" << formatImm(MO1.getImm())
       << markup(">]>", "]");
   }
   else
@@ -911,15 +911,15 @@ void ARMInstPrinter::printAdrLabelOperand(const MCInst *MI, unsigned OpNum,
 void ARMInstPrinter::printThumbS4ImmOperand(const MCInst *MI, unsigned OpNum,
                                             raw_ostream &O) {
   O << markup("<imm:")
-    << "#" << MI->getOperand(OpNum).getImm() * 4
+    << "#" << formatImm(MI->getOperand(OpNum).getImm() * 4)
     << markup(">");
 }
 
 void ARMInstPrinter::printThumbSRImm(const MCInst *MI, unsigned OpNum,
                                      raw_ostream &O) {
   unsigned Imm = MI->getOperand(OpNum).getImm();
   O << markup("<imm:")
-    << "#" << (Imm == 0 ? 32 : Imm)
+    << "#" << formatImm((Imm == 0 ? 32 : Imm))
     << markup(">");
 }
 
@@ -976,7 +976,7 @@ void ARMInstPrinter::printThumbAddrModeImm5SOperand(const MCInst *MI,
   if (unsigned ImmOffs = MO2.getImm()) {
     O << ", "
       << markup("<imm:")
-      << "#" << ImmOffs * Scale
+      << "#" << formatImm(ImmOffs * Scale)
       << markup(">");
   }
   O << "]" << markup(">");
@@ -1127,7 +1127,7 @@ void ARMInstPrinter::printT2AddrModeImm0_1020s4Operand(const MCInst *MI,
   if (MO2.getImm()) {
     O << ", "
       << markup("<imm:")
-      << "#" << MO2.getImm() * 4
+      << "#" << formatImm(MO2.getImm() * 4)
       << markup(">");
   }
   O << "]" << markup(">");
@@ -1217,7 +1217,7 @@ void ARMInstPrinter::printImmPlusOneOperand(const MCInst *MI, unsigned OpNum,
                                             raw_ostream &O) {
   unsigned Imm = MI->getOperand(OpNum).getImm();
   O << markup("<imm:")
-    << "#" << Imm + 1
+    << "#" << formatImm(Imm + 1)
     << markup(">");
 }
 

lib/Target/X86/InstPrinter/X86ATTInstPrinter.cpp

@@ -131,7 +131,7 @@ void X86ATTInstPrinter::printPCRelImm(const MCInst *MI, unsigned OpNo,
                                       raw_ostream &O) {
   const MCOperand &Op = MI->getOperand(OpNo);
   if (Op.isImm())
-    O << Op.getImm();
+    O << formatImm(Op.getImm());
   else {
     assert(Op.isExpr() && "unknown pcrel immediate operand");
     // If a symbolic branch target was added as a constant expression then print
@@ -157,7 +157,7 @@ void X86ATTInstPrinter::printOperand(const MCInst *MI, unsigned OpNo,
   } else if (Op.isImm()) {
     // Print X86 immediates as signed values.
     O << markup("<imm:")
-      << '$' << (int64_t)Op.getImm()
+      << '$' << formatImm((int64_t)Op.getImm())
       << markup(">");
 
     if (CommentStream && (Op.getImm() > 255 || Op.getImm() < -256))
@@ -189,7 +189,7 @@ void X86ATTInstPrinter::printMemReference(const MCInst *MI, unsigned Op,
   if (DispSpec.isImm()) {
     int64_t DispVal = DispSpec.getImm();
     if (DispVal || (!IndexReg.getReg() && !BaseReg.getReg()))
-      O << DispVal;
+      O << formatImm(DispVal);
   } else {
     assert(DispSpec.isExpr() && "non-immediate displacement for LEA?");
     O << *DispSpec.getExpr();
@@ -207,7 +207,7 @@ void X86ATTInstPrinter::printMemReference(const MCInst *MI, unsigned Op,
       if (ScaleVal != 1) {
         O << ','
 	  << markup("<imm:")
-          << ScaleVal
+          << ScaleVal // never printed in hex.
 	  << markup(">");
       }
     }

test/MC/Disassembler/ARM/hex-immediates.txt

@@ -0,0 +1,5 @@
+# RUN: llvm-mc -triple=thumbv7-apple-darwin -mcpu=cortex-a8 -hdis < %s | FileCheck %s
+# CHECK: ldr	r4, [pc, #0x20]
+0x08 0x4c
+# CHECK: sub	sp, #0x84
+0xa1 0xb0

test/MC/Disassembler/X86/hex-immediates.txt

@@ -0,0 +1,10 @@
+# RUN: llvm-mc --hdis %s -triple=x86_64-apple-darwin9 2>&1 | FileCheck %s
+
+# CHECK: movabsq	$0x7fffffffffffffff, %rcx
+0x48 0xb9 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0x7f
+# CHECK: leaq	0x3e2(%rip), %rdi
+0x48 0x8d 0x3d 0xe2 0x03 0x00 0x00
+# CHECK: subq	$0x40, %rsp
+0x48 0x83 0xec 0x40
+# CHECK: leal	(,%r14,4), %eax
+0x42 0x8d 0x04 0xb5 0x00 0x00 0x00 0x00

tools/llvm-mc/llvm-mc.cpp

@@ -162,7 +162,8 @@ enum ActionType {
   AC_Assemble,
   AC_Disassemble,
   AC_EDisassemble,
-  AC_MDisassemble
+  AC_MDisassemble,
+  AC_HDisassemble
 };
 
 static cl::opt<ActionType>
@@ -178,6 +179,9 @@ Action(cl::desc("Action to perform:"),
                              "Enhanced disassembly of strings of hex bytes"),
                   clEnumValN(AC_MDisassemble, "mdis",
                              "Marked up disassembly of strings of hex bytes"),
+                  clEnumValN(AC_HDisassemble, "hdis",
+                             "Disassemble strings of hex bytes printing "
+                             "immediates as hex"),
                   clEnumValEnd));
 
 static const Target *GetTarget(const char *ProgName) {
@@ -437,6 +441,7 @@ int main(int argc, char **argv) {
   }
 
   int Res = 1;
+  bool disassemble = false;
   switch (Action) {
   case AC_AsLex:
     Res = AsLexInput(SrcMgr, *MAI, Out.get());
@@ -446,15 +451,22 @@ int main(int argc, char **argv) {
     break;
   case AC_MDisassemble:
     IP->setUseMarkup(1);
-    // Fall through to do disassembly.
+    disassemble = true;
+    break;
+  case AC_HDisassemble:
+    IP->setPrintImmHex(1);
+    disassemble = true;
+    break;
   case AC_Disassemble:
-    Res = Disassembler::disassemble(*TheTarget, TripleName, *STI, *Str,
-                                    *Buffer, SrcMgr, Out->os());
+    disassemble = true;
     break;
   case AC_EDisassemble:
     Res =  Disassembler::disassembleEnhanced(TripleName, *Buffer, SrcMgr, Out->os());
     break;
   }
+  if (disassemble)
+    Res = Disassembler::disassemble(*TheTarget, TripleName, *STI, *Str,
+                                    *Buffer, SrcMgr, Out->os());
 
   // Keep output if no errors.
   if (Res == 0) Out->keep();