ARM IAS: support .inst directive

This adds support for the .inst directive.  This is an ARM specific directive to
indicate an instruction encoded as a constant expression.  The major difference
between .word, .short, or .byte and .inst is that the latter will be
disassembled as an instruction since it does not get flagged as data.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@197657 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/MC/MCStreamer.h

@@ -95,6 +95,7 @@ class ARMTargetStreamer : public MCTargetStreamer {
   virtual void emitFPU(unsigned FPU) = 0;
   virtual void emitArch(unsigned Arch) = 0;
   virtual void finishAttributeSection() = 0;
+  virtual void emitInst(uint32_t Inst, char Suffix = '\0') = 0;
 };
 
 /// MCStreamer - Streaming machine code generation interface.  This interface

lib/Target/ARM/AsmParser/ARMAsmParser.cpp

@@ -19,6 +19,7 @@
 #include "llvm/ADT/OwningPtr.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringExtras.h"
 #include "llvm/ADT/StringSwitch.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/MC/MCAsmInfo.h"
@@ -150,6 +151,7 @@ class ARMAsmParser : public MCTargetAsmParser {
   bool parseDirectiveSetFP(SMLoc L);
   bool parseDirectivePad(SMLoc L);
   bool parseDirectiveRegSave(SMLoc L, bool IsVector);
+  bool parseDirectiveInst(SMLoc L, char Suffix = '\0');
 
   StringRef splitMnemonic(StringRef Mnemonic, unsigned &PredicationCode,
                           bool &CarrySetting, unsigned &ProcessorIMod,
@@ -7809,6 +7811,12 @@ bool ARMAsmParser::ParseDirective(AsmToken DirectiveID) {
     return parseDirectiveRegSave(DirectiveID.getLoc(), false);
   else if (IDVal == ".vsave")
     return parseDirectiveRegSave(DirectiveID.getLoc(), true);
+  else if (IDVal == ".inst")
+    return parseDirectiveInst(DirectiveID.getLoc());
+  else if (IDVal == ".inst.n")
+    return parseDirectiveInst(DirectiveID.getLoc(), 'n');
+  else if (IDVal == ".inst.w")
+    return parseDirectiveInst(DirectiveID.getLoc(), 'w');
   return true;
 }
 
@@ -8288,6 +8296,78 @@ bool ARMAsmParser::parseDirectiveRegSave(SMLoc L, bool IsVector) {
   return false;
 }
 
+/// parseDirectiveInst
+///  ::= .inst opcode [, ...]
+///  ::= .inst.n opcode [, ...]
+///  ::= .inst.w opcode [, ...]
+bool ARMAsmParser::parseDirectiveInst(SMLoc Loc, char Suffix) {
+  int Width;
+
+  if (isThumb()) {
+    switch (Suffix) {
+    case 'n':
+      Width = 2;
+      break;
+    case 'w':
+      Width = 4;
+      break;
+    default:
+      Parser.eatToEndOfStatement();
+      return Error(Loc, "cannot determine Thumb instruction size, "
+                        "use inst.n/inst.w instead");
+    }
+  } else {
+    if (Suffix) {
+      Parser.eatToEndOfStatement();
+      return Error(Loc, "width suffixes are invalid in ARM mode");
+    }
+    Width = 4;
+  }
+
+  if (getLexer().is(AsmToken::EndOfStatement)) {
+    Parser.eatToEndOfStatement();
+    return Error(Loc, "expected expression following directive");
+  }
+
+  for (;;) {
+    const MCExpr *Expr;
+
+    if (getParser().parseExpression(Expr))
+      return Error(Loc, "expected expression");
+
+    const MCConstantExpr *Value = dyn_cast_or_null<MCConstantExpr>(Expr);
+    if (!Value)
+      return Error(Loc, "expected constant expression");
+
+    switch (Width) {
+    case 2:
+      if (Value->getValue() > 0xffff)
+        return Error(Loc, "inst.n operand is too big, use inst.w instead");
+      break;
+    case 4:
+      if (Value->getValue() > 0xffffffff)
+        return Error(Loc,
+                 StringRef(Suffix ? "inst.w" : "inst") + " operand is too big");
+      break;
+    default:
+      llvm_unreachable("only supported widths are 2 and 4");
+    }
+
+    getTargetStreamer().emitInst(Value->getValue(), Suffix);
+
+    if (getLexer().is(AsmToken::EndOfStatement))
+      break;
+
+    if (getLexer().isNot(AsmToken::Comma))
+      return Error(Loc, "unexpected token in directive");
+
+    Parser.Lex();
+  }
+
+  Parser.Lex();
+  return false;
+}
+
 /// Force static initialization.
 extern "C" void LLVMInitializeARMAsmParser() {
   RegisterMCAsmParser<ARMAsmParser> X(TheARMTarget);

lib/Target/ARM/MCTargetDesc/ARMELFStreamer.cpp

@@ -20,8 +20,10 @@
 #include "ARMUnwindOp.h"
 #include "ARMUnwindOpAsm.h"
 #include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/StringExtras.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/MC/MCAsmBackend.h"
+#include "llvm/MC/MCAsmInfo.h"
 #include "llvm/MC/MCAssembler.h"
 #include "llvm/MC/MCCodeEmitter.h"
 #include "llvm/MC/MCContext.h"
@@ -121,6 +123,7 @@ class ARMTargetAsmStreamer : public ARMTargetStreamer {
   virtual void emitTextAttribute(unsigned Attribute, StringRef String);
   virtual void emitArch(unsigned Arch);
   virtual void emitFPU(unsigned FPU);
+  virtual void emitInst(uint32_t Inst, char Suffix = '\0');
   virtual void finishAttributeSection();
 
 public:
@@ -190,6 +193,13 @@ void ARMTargetAsmStreamer::emitFPU(unsigned FPU) {
 void ARMTargetAsmStreamer::finishAttributeSection() {
 }
 
+void ARMTargetAsmStreamer::emitInst(uint32_t Inst, char Suffix) {
+  OS << "\t.inst";
+  if (Suffix)
+    OS << "." << Suffix;
+  OS << "\t0x" << utohexstr(Inst) << "\n";
+}
+
 class ARMTargetELFStreamer : public ARMTargetStreamer {
 private:
   // This structure holds all attributes, accounting for
@@ -295,6 +305,7 @@ class ARMTargetELFStreamer : public ARMTargetStreamer {
   virtual void emitTextAttribute(unsigned Attribute, StringRef String);
   virtual void emitArch(unsigned Arch);
   virtual void emitFPU(unsigned FPU);
+  virtual void emitInst(uint32_t Inst, char Suffix = '\0');
   virtual void finishAttributeSection();
 
   size_t calculateContentSize() const;
@@ -367,6 +378,44 @@ class ARMELFStreamer : public MCELFStreamer {
     MCELFStreamer::EmitInstruction(Inst);
   }
 
+  virtual void emitInst(uint32_t Inst, char Suffix) {
+    unsigned Size;
+    char Buffer[4];
+    const bool LittleEndian = getContext().getAsmInfo()->isLittleEndian();
+
+    switch (Suffix) {
+    case '\0':
+      Size = 4;
+
+      assert(!IsThumb);
+      EmitARMMappingSymbol();
+      for (unsigned II = 0, IE = Size; II != IE; II++) {
+        const unsigned I = LittleEndian ? (Size - II - 1) : II;
+        Buffer[Size - II - 1] = uint8_t(Inst >> I * CHAR_BIT);
+      }
+
+      break;
+    case 'n':
+    case 'w':
+      Size = (Suffix == 'n' ? 2 : 4);
+
+      assert(IsThumb);
+      EmitThumbMappingSymbol();
+      for (unsigned II = 0, IE = Size; II != IE; II = II + 2) {
+        const unsigned I0 = LittleEndian ? II + 0 : (Size - II - 1);
+        const unsigned I1 = LittleEndian ? II + 1 : (Size - II - 2);
+        Buffer[Size - II - 2] = uint8_t(Inst >> I0 * CHAR_BIT);
+        Buffer[Size - II - 1] = uint8_t(Inst >> I1 * CHAR_BIT);
+      }
+
+      break;
+    default:
+      llvm_unreachable("Invalid Suffix");
+    }
+
+    MCELFStreamer::EmitBytes(StringRef(Buffer, Size));
+  }
+
   /// This is one of the functions used to emit data into an ELF section, so the
   /// ARM streamer overrides it to add the appropriate mapping symbol ($d) if
   /// necessary.
@@ -791,6 +840,9 @@ void ARMTargetELFStreamer::finishAttributeSection() {
   Contents.clear();
   FPU = ARM::INVALID_FPU;
 }
+void ARMTargetELFStreamer::emitInst(uint32_t Inst, char Suffix) {
+  getStreamer().emitInst(Inst, Suffix);
+}
 
 void ARMELFStreamer::FinishImpl() {
   MCTargetStreamer &TS = getTargetStreamer();

test/MC/ARM/inst-arm-suffixes.s

@@ -0,0 +1,15 @@
+@ RUN: not llvm-mc %s -triple armv7-linux-gnueabi -filetype asm -o - 2>&1 \
+@ RUN:   | FileCheck -check-prefix CHECK-ERROR %s
+
+	.syntax unified
+	.arm
+
+	.align 2
+	.global suffixes_invalid_in_arm
+	.type suffixes_invalid_in_arm,%function
+suffixes_invalid_in_arm:
+	.inst.n 2
+@ CHECK-ERROR: width suffixes are invalid in ARM mode
+	.inst.w 4
+@ CHECK-ERROR: width suffixes are invalid in ARM mode
+

test/MC/ARM/inst-constant-required.s

@@ -0,0 +1,15 @@
+@ RUN: not llvm-mc %s -triple=armv7-linux-gnueabi -filetype asm -o - 2>&1 \
+@ RUN:   | FileCheck -check-prefix CHECK-ERROR %s
+
+	.syntax unified
+	.arm
+
+	.align 2
+	.global constant_expression_required
+	.type constant_expression_required,%function
+constant_expression_required:
+.Label:
+	movs r0, r0
+	.inst .Label
+@ CHECK-ERROR: expected constant expression
+

test/MC/ARM/inst-directive-emit.s

@@ -0,0 +1,20 @@
+@ RUN: llvm-mc %s -triple armv7-linux-gnueabi -filetype asm -o - | FileCheck %s
+
+	.syntax unified
+	.thumb
+
+	.align 2
+	.global emit_asm
+	.type emit_asm,%function
+emit_asm:
+	.inst.w 0xf2400000, 0xf2c00000
+
+@ CHECK: 	.text
+@ CHECK: 	.code	16
+@ CHECK: 	.align	2
+@ CHECK: 	.globl	emit_asm
+@ CHECK: 	.type	emit_asm,%function
+@ CHECK: emit_asm:
+@ CHECK: 	inst.w 0xF2400000
+@ CHECK: 	inst.w 0xF2C00000
+

test/MC/ARM/inst-directive.s

@@ -0,0 +1,81 @@
+@ RUN: llvm-mc %s -triple=armv7-linux-gnueabi -filetype=obj -o - \
+@ RUN:   | llvm-readobj -s -sd | FileCheck %s
+
+	.syntax unified
+
+@-------------------------------------------------------------------------------
+@ arm_inst
+@-------------------------------------------------------------------------------
+	.arm
+
+	.section	.inst.arm_inst
+
+	.align	2
+	.global	arm_inst
+	.type	arm_inst,%function
+arm_inst:
+	.inst 0xdefe
+
+@ CHECK: Section {
+@ CHECK:   Name: .inst.arm_inst
+@ CHECK:   SectionData (
+@ CHECK-NEXT:     0000: FEDE0000
+@ CHECK-NEXT:   )
+
+@-------------------------------------------------------------------------------
+@ thumb_inst_n
+@-------------------------------------------------------------------------------
+	.thumb
+
+	.section	.inst.thumb_inst_n
+
+	.align	2
+	.global	thumb_inst_n
+	.type	thumb_inst_n,%function
+thumb_inst_n:
+	.inst.n 0xdefe
+
+@ CHECK: Section {
+@ CHECK:   Name: .inst.thumb_inst_n
+@ CHECK:   SectionData (
+@ CHECK-NEXT:     0000: FEDE
+@ CHECK-NEXT:   )
+
+@-------------------------------------------------------------------------------
+@ thumb_inst_w
+@-------------------------------------------------------------------------------
+	.thumb
+
+	.section	.inst.thumb_inst_w
+
+	.align	2
+	.global	thumb_inst_w
+	.type	thumb_inst_w,%function
+thumb_inst_w:
+	.inst.w 0x00000000
+
+@ CHECK: Section {
+@ CHECK:   Name: .inst.thumb_inst_w
+@ CHECK:   SectionData (
+@ CHECK-NEXT:     0000: 00000000
+@ CHECK-NEXT:   )
+
+@-------------------------------------------------------------------------------
+@ thumb_inst_w
+@-------------------------------------------------------------------------------
+	.thumb
+
+	.section	.inst.thumb_inst_inst
+
+	.align	2
+	.global	thumb_inst_inst
+	.type	thumb_inst_inst,%function
+thumb_inst_inst:
+	.inst.w 0xf2400000, 0xf2c00000
+
+@ CHECK: Section {
+@ CHECK:   Name: .inst.thumb_inst_inst
+@ CHECK:   SectionData (
+@ CHECK-NEXT:     0000: 40F20000 C0F20000
+@ CHECK-NEXT:   )
+

test/MC/ARM/inst-overflow.s

@@ -0,0 +1,14 @@
+@ RUN: not llvm-mc %s -triple armv7-linux-gnueabi -filetype asm -o - 2>&1 \
+@ RUN:   | FileCheck -check-prefix CHECK-ERROR %s
+
+	.syntax unified
+	.arm
+
+	.align 2
+	.global constant_overflow
+	.type constant_overflow,%function
+constant_overflow:
+	.inst 1 << 32
+@ CHECK-ERROR: inst operand is too big
+
+

test/MC/ARM/inst-thumb-overflow-2.s

@@ -0,0 +1,13 @@
+@ RUN: not llvm-mc %s -triple armv7-linux-gnueabi -filetype asm -o - 2>&1 \
+@ RUN:   | FileCheck -check-prefix CHECK-ERRORS %s
+
+	.syntax unified
+	.thumb
+
+	.align 2
+	.global constant_overflow
+	.type constant_overflow,%function
+constant_overflow:
+	.inst.w 1 << 32
+@ CHECK-ERRORS: inst.w operand is too big
+

test/MC/ARM/inst-thumb-overflow.s

@@ -0,0 +1,13 @@
+@ RUN: not llvm-mc %s -triple armv7-linux-gnueabi -filetype asm -o - 2>&1 \
+@ RUN:   | FileCheck -check-prefix CHECK-ERROR %s
+
+	.syntax unified
+	.thumb
+
+	.align 2
+	.global constant_overflow
+	.type constant_overflow,%function
+constant_overflow:
+	.inst.n 1 << 31
+@ CHECK-ERROR: inst.n operand is too big, use inst.w instead
+