[x86] Add basic support for .code16

This is not really expected to work right yet. Mostly because we will
still emit the OpSize (0x66) prefix in all the wrong places, along with
a number of other corner cases. Those will all be fixed in the subsequent
commits.

Patch from David Woodhouse.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@198584 91177308-0d34-0410-b5e6-96231b3b80d8

9 files changed, 346 insertions, 17 deletions

diff --git a/lib/Target/X86/AsmParser/X86AsmParser.cpp b/lib/Target/X86/AsmParser/X86AsmParser.cpp
index 0f8e9f7b4a..86ba185819 100644
--- a/lib/Target/X86/AsmParser/X86AsmParser.cpp
+++ b/lib/Target/X86/AsmParser/X86AsmParser.cpp
@@ -544,9 +544,21 @@ private:
     // FIXME: Can tablegen auto-generate this?
     return (STI.getFeatureBits() & X86::Mode64Bit) != 0;
   }
-  void SwitchMode() {
-    unsigned FB = ComputeAvailableFeatures(STI.ToggleFeature(X86::Mode64Bit));
+  bool is32BitMode() const {
+    // FIXME: Can tablegen auto-generate this?
+    return (STI.getFeatureBits() & X86::Mode32Bit) != 0;
+  }
+  bool is16BitMode() const {
+    // FIXME: Can tablegen auto-generate this?
+    return (STI.getFeatureBits() & X86::Mode16Bit) != 0;
+  }
+  void SwitchMode(uint64_t mode) {
+    uint64_t oldMode = STI.getFeatureBits() &
+        (X86::Mode64Bit | X86::Mode32Bit | X86::Mode16Bit);
+    unsigned FB = ComputeAvailableFeatures(STI.ToggleFeature(oldMode | mode));
     setAvailableFeatures(FB);
+    assert(mode == (STI.getFeatureBits() &
+                    (X86::Mode64Bit | X86::Mode32Bit | X86::Mode16Bit)));
   }
 
   bool isParsingIntelSyntax() {
@@ -1033,7 +1045,8 @@ struct X86Operand : public MCParsedAsmOperand {
 } // end anonymous namespace.
 
 bool X86AsmParser::isSrcOp(X86Operand &Op) {
-  unsigned basereg = is64BitMode() ? X86::RSI : X86::ESI;
+  unsigned basereg =
+      is64BitMode() ? X86::RSI : (is32BitMode() ? X86::ESI : X86::SI);
 
   return (Op.isMem() &&
     (Op.Mem.SegReg == 0 || Op.Mem.SegReg == X86::DS) &&
@@ -1043,7 +1056,8 @@ bool X86AsmParser::isSrcOp(X86Operand &Op) {
 }
 
 bool X86AsmParser::isDstOp(X86Operand &Op) {
-  unsigned basereg = is64BitMode() ? X86::RDI : X86::EDI;
+  unsigned basereg =
+      is64BitMode() ? X86::RDI : (is32BitMode() ? X86::EDI : X86::DI);
 
   return Op.isMem() &&
     (Op.Mem.SegReg == 0 || Op.Mem.SegReg == X86::ES) &&
@@ -1193,7 +1207,8 @@ X86AsmParser::CreateMemForInlineAsm(unsigned SegReg, const MCExpr *Disp,
     // operand to ensure proper matching.  Just pick a GPR based on the size of
     // a pointer.
     if (!Info.IsVarDecl) {
-      unsigned RegNo = is64BitMode() ? X86::RBX : X86::EBX;
+      unsigned RegNo =
+          is64BitMode() ? X86::RBX : (is32BitMode() ? X86::EBX : X86::BX);
       return X86Operand::CreateReg(RegNo, Start, End, /*AddressOf=*/true,
                                    SMLoc(), Identifier, Info.OpDecl);
     }
@@ -1612,7 +1627,8 @@ X86Operand *X86AsmParser::ParseIntelOffsetOfOperator() {
   // The offset operator will have an 'r' constraint, thus we need to create
   // register operand to ensure proper matching.  Just pick a GPR based on
   // the size of a pointer.
-  unsigned RegNo = is64BitMode() ? X86::RBX : X86::EBX;
+  unsigned RegNo =
+      is64BitMode() ? X86::RBX : (is32BitMode() ? X86::EBX : X86::BX);
   return X86Operand::CreateReg(RegNo, Start, End, /*GetAddress=*/true,
                                OffsetOfLoc, Identifier, Info.OpDecl);
 }
@@ -2679,18 +2695,24 @@ bool X86AsmParser::ParseDirectiveWord(unsigned Size, SMLoc L) {
 }
 
 /// ParseDirectiveCode
-///  ::= .code32 | .code64
+///  ::= .code16 | .code32 | .code64
 bool X86AsmParser::ParseDirectiveCode(StringRef IDVal, SMLoc L) {
-  if (IDVal == ".code32") {
+  if (IDVal == ".code16") {
+    Parser.Lex();
+    if (!is16BitMode()) {
+      SwitchMode(X86::Mode16Bit);
+      getParser().getStreamer().EmitAssemblerFlag(MCAF_Code16);
+    }
+  } else  if (IDVal == ".code32") {
     Parser.Lex();
-    if (is64BitMode()) {
-      SwitchMode();
+    if (!is32BitMode()) {
+      SwitchMode(X86::Mode32Bit);
       getParser().getStreamer().EmitAssemblerFlag(MCAF_Code32);
     }
   } else if (IDVal == ".code64") {
     Parser.Lex();
     if (!is64BitMode()) {
-      SwitchMode();
+      SwitchMode(X86::Mode64Bit);
       getParser().getStreamer().EmitAssemblerFlag(MCAF_Code64);
     }
   } else {
diff --git a/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp b/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp
index 293541a843..51b90b1c49 100644
--- a/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp
+++ b/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp
@@ -49,7 +49,12 @@ public:
 
   bool is32BitMode() const {
     // FIXME: Can tablegen auto-generate this?
-    return (STI.getFeatureBits() & X86::Mode64Bit) == 0;
+    return (STI.getFeatureBits() & X86::Mode32Bit) != 0;
+  }
+
+  bool is16BitMode() const {
+    // FIXME: Can tablegen auto-generate this?
+    return (STI.getFeatureBits() & X86::Mode16Bit) != 0;
   }
 
   unsigned GetX86RegNum(const MCOperand &MO) const {
@@ -1177,13 +1182,16 @@ void X86MCCodeEmitter::EmitOpcodePrefix(uint64_t TSFlags, unsigned &CurByte,
     assert(!Is64BitMemOperand(MI, MemOperand));
     need_address_override = Is16BitMemOperand(MI, MemOperand);
   } else {
-    need_address_override = false;
+    assert(is16BitMode());
+    assert(!Is64BitMemOperand(MI, MemOperand));
+    need_address_override = !Is16BitMemOperand(MI, MemOperand);
   }
 
   if (need_address_override)
     EmitByte(0x67, CurByte, OS);
 
   // Emit the operand size opcode prefix as needed.
+  // FIXME for is16BitMode().
   if (TSFlags & X86II::OpSize)
     EmitByte(0x66, CurByte, OS);
 
diff --git a/lib/Target/X86/MCTargetDesc/X86MCTargetDesc.cpp b/lib/Target/X86/MCTargetDesc/X86MCTargetDesc.cpp
index 403e50dbf8..09803f372f 100644
--- a/lib/Target/X86/MCTargetDesc/X86MCTargetDesc.cpp
+++ b/lib/Target/X86/MCTargetDesc/X86MCTargetDesc.cpp
@@ -47,9 +47,9 @@ std::string X86_MC::ParseX86Triple(StringRef TT) {
   Triple TheTriple(TT);
   std::string FS;
   if (TheTriple.getArch() == Triple::x86_64)
-    FS = "+64bit-mode";
+    FS = "+64bit-mode,-32bit-mode,-16bit-mode";
   else
-    FS = "-64bit-mode";
+    FS = "-64bit-mode,+32bit-mode,-16bit-mode";
   return FS;
 }
 
diff --git a/lib/Target/X86/X86.td b/lib/Target/X86/X86.td
index d55178ea12..e755faeb17 100644
--- a/lib/Target/X86/X86.td
+++ b/lib/Target/X86/X86.td
@@ -22,6 +22,10 @@ include "llvm/Target/Target.td"
 
 def Mode64Bit : SubtargetFeature<"64bit-mode", "In64BitMode", "true",
                                   "64-bit mode (x86_64)">;
+def Mode32Bit : SubtargetFeature<"32bit-mode", "In32BitMode", "true",
+                                  "32-bit mode (80386)">;
+def Mode16Bit : SubtargetFeature<"16bit-mode", "In16BitMode", "true",
+                                  "16-bit mode (i8086)">;
 
 //===----------------------------------------------------------------------===//
 // X86 Subtarget features
diff --git a/lib/Target/X86/X86InstrInfo.td b/lib/Target/X86/X86InstrInfo.td
index 707a313f14..9642a8926d 100644
--- a/lib/Target/X86/X86InstrInfo.td
+++ b/lib/Target/X86/X86InstrInfo.td
@@ -700,6 +700,12 @@ def Not64BitMode : Predicate<"!Subtarget->is64Bit()">,
                              AssemblerPredicate<"!Mode64Bit", "Not 64-bit mode">;
 def In64BitMode  : Predicate<"Subtarget->is64Bit()">,
                              AssemblerPredicate<"Mode64Bit", "64-bit mode">;
+def In16BitMode  : Predicate<"Subtarget->is16Bit()">,
+                             AssemblerPredicate<"Mode16Bit", "16-bit mode">;
+def Not16BitMode : Predicate<"!Subtarget->is16Bit()">,
+                             AssemblerPredicate<"!Mode16Bit", "Not 16-bit mode">;
+def In32BitMode  : Predicate<"Subtarget->is32Bit()">,
+                             AssemblerPredicate<"Mode32Bit", "32-bit mode">;
 def IsWin64      : Predicate<"Subtarget->isTargetWin64()">;
 def IsNaCl       : Predicate<"Subtarget->isTargetNaCl()">;
 def NotNaCl      : Predicate<"!Subtarget->isTargetNaCl()">;
diff --git a/lib/Target/X86/X86Subtarget.cpp b/lib/Target/X86/X86Subtarget.cpp
index 597fccb9fd..5ee986c9a8 100644
--- a/lib/Target/X86/X86Subtarget.cpp
+++ b/lib/Target/X86/X86Subtarget.cpp
@@ -482,6 +482,12 @@ void X86Subtarget::resetSubtargetFeatures(StringRef CPU, StringRef FS) {
   // target data structure which is shared with MC code emitter, etc.
   if (In64BitMode)
     ToggleFeature(X86::Mode64Bit);
+  else if (In32BitMode)
+    ToggleFeature(X86::Mode32Bit);
+  else if (In16BitMode)
+    ToggleFeature(X86::Mode16Bit);
+  else
+    llvm_unreachable("Not 16-bit, 32-bit or 64-bit mode!");
 
   DEBUG(dbgs() << "Subtarget features: SSELevel " << X86SSELevel
                << ", 3DNowLevel " << X863DNowLevel
@@ -551,7 +557,9 @@ X86Subtarget::X86Subtarget(const std::string &TT, const std::string &CPU,
   , PICStyle(PICStyles::None)
   , TargetTriple(TT)
   , StackAlignOverride(StackAlignOverride)
-  , In64BitMode(is64Bit) {
+  , In64BitMode(is64Bit)
+  , In32BitMode(!is64Bit)
+  , In16BitMode(false) {
   initializeEnvironment();
   resetSubtargetFeatures(CPU, FS);
 }
diff --git a/lib/Target/X86/X86Subtarget.h b/lib/Target/X86/X86Subtarget.h
index 93d251a679..f39389e08c 100644
--- a/lib/Target/X86/X86Subtarget.h
+++ b/lib/Target/X86/X86Subtarget.h
@@ -205,9 +205,15 @@ private:
   /// StackAlignOverride - Override the stack alignment.
   unsigned StackAlignOverride;
 
-  /// In64BitMode - True if compiling for 64-bit, false for 32-bit.
+  /// In64BitMode - True if compiling for 64-bit, false for 16-bit or 32-bit.
   bool In64BitMode;
 
+  /// In32BitMode - True if compiling for 32-bit, false for 16-bit or 64-bit.
+  bool In32BitMode;
+
+  /// In16BitMode - True if compiling for 16-bit, false for 32-bit or 64-bit.
+  bool In16BitMode;
+
 public:
   /// This constructor initializes the data members to match that
   /// of the specified triple.
@@ -244,6 +250,14 @@ public:
     return In64BitMode;
   }
 
+  bool is32Bit() const {
+    return In32BitMode;
+  }
+
+  bool is16Bit() const {
+    return In16BitMode;
+  }
+
   /// Is this x86_64 with the ILP32 programming model (x32 ABI)?
   bool isTarget64BitILP32() const {
     return In64BitMode && (TargetTriple.getEnvironment() == Triple::GNUX32 ||
diff --git a/test/MC/X86/address-size.s b/test/MC/X86/address-size.s
index 936cd579db..c9d04c4af3 100644
--- a/test/MC/X86/address-size.s
+++ b/test/MC/X86/address-size.s
@@ -17,3 +17,11 @@
 // CHECK: encoding: [0x67,0xc7,0x00,0x78,0x56,0x34,0x12]
 	movw	$0x1234, 0x5678(%bp)
 // CHECK: encoding: [0x67,0x66,0xc7,0x86,0x78,0x56,0x34,0x12]
+
+	.code16
+	movb	$0x0, (%si)
+// CHECK: encoding: [0xc6,0x04,0x00]
+	movb	$0x0, (%esi)
+// CHECK: encoding: [0x67,0xc6,0x06,0x00]
+	movb	$0x5a, (%di,%bp,1)
+// CHECK: encoding: [0xc6,0x03,0x5a]
diff --git a/test/MC/X86/x86-16.s b/test/MC/X86/x86-16.s
new file mode 100644
index 0000000000..36f3b1922f
--- /dev/null
+++ b/test/MC/X86/x86-16.s
@@ -0,0 +1,259 @@
+// RUN: llvm-mc -triple i386-unknown-unknown --show-encoding %s | FileCheck %s
+
+	.code16
+
+	pause
+// CHECK: pause
+// CHECK: encoding: [0xf3,0x90]
+	sfence
+// CHECK: sfence
+// CHECK: encoding: [0x0f,0xae,0xf8]
+	lfence
+// CHECK: lfence
+// CHECK: encoding: [0x0f,0xae,0xe8]
+	mfence
+	stgi
+// CHECK: stgi
+// CHECK: encoding: [0x0f,0x01,0xdc]
+	clgi
+// CHECK: clgi
+// CHECK: encoding: [0x0f,0x01,0xdd]
+
+	rdtscp
+// CHECK: rdtscp
+// CHECK:  encoding: [0x0f,0x01,0xf9]
+
+
+// CHECK: testb	%bl, %cl                # encoding: [0x84,0xcb]
+        testb %bl, %cl
+
+into
+// CHECK: into
+// CHECK:  encoding: [0xce]
+int3
+// CHECK: int3
+// CHECK:  encoding: [0xcc]
+int $4
+// CHECK: int $4
+// CHECK:  encoding: [0xcd,0x04]
+int $255
+// CHECK: int $255
+// CHECK:  encoding: [0xcd,0xff]
+
+// CHECK: fmul	%st(0)
+// CHECK:  encoding: [0xd8,0xc8]
+        fmul %st(0), %st
+
+// CHECK: fadd	%st(0)
+// CHECK:  encoding: [0xd8,0xc0]
+        fadd %st(0), %st
+
+// CHECK: fsub	%st(0)
+// CHECK:  encoding: [0xd8,0xe0]
+        fsub %st(0), %st
+
+// CHECK: fsubr	%st(0)
+// CHECK:  encoding: [0xd8,0xe8]
+        fsubr %st(0), %st
+
+// CHECK: fdivr	%st(0)
+// CHECK:  encoding: [0xd8,0xf8]
+        fdivr %st(0), %st
+
+// CHECK: fdiv	%st(0)
+// CHECK:  encoding: [0xd8,0xf0]
+        fdiv %st(0), %st
+
+// CHECK: wait
+// CHECK:  encoding: [0x9b]
+	fwait
+
+
+	setc	%bl
+	setnae	%bl
+	setnb	%bl
+	setnc	%bl
+	setna	%bl
+	setnbe	%bl
+	setpe	%bl
+	setpo	%bl
+	setnge	%bl
+	setnl	%bl
+	setng	%bl
+	setnle	%bl
+
+        setneb  %cl // CHECK: setne %cl
+	setcb	%bl // CHECK: setb %bl
+	setnaeb	%bl // CHECK: setb %bl
+
+
+// CHECK: lcalll	$31438, $31438
+// CHECK: lcalll	$31438, $31438
+// CHECK: ljmpl	$31438, $31438
+// CHECK: ljmpl	$31438, $31438
+
+calll	$0x7ace,$0x7ace
+lcalll	$0x7ace,$0x7ace
+jmpl	$0x7ace,$0x7ace
+ljmpl	$0x7ace,$0x7ace
+
+// CHECK: calll a
+ calll a
+
+// CHECK:	incb	%al # encoding: [0xfe,0xc0]
+	incb %al
+
+// CHECK:	decb	%al # encoding: [0xfe,0xc8]
+	decb %al
+
+// CHECK: pshufw $14, %mm4, %mm0 # encoding: [0x0f,0x70,0xc4,0x0e]
+pshufw $14, %mm4, %mm0
+
+// CHECK: pshufw $90, %mm4, %mm0 # encoding: [0x0f,0x70,0xc4,0x5a]
+pshufw $90, %mm4, %mm0
+
+// CHECK: aaa
+// CHECK:  encoding: [0x37]
+        	aaa
+
+// CHECK: aad	$1
+// CHECK:  encoding: [0xd5,0x01]
+        	aad	$1
+
+// CHECK: aad
+// CHECK:  encoding: [0xd5,0x0a]
+        	aad	$0xA
+
+// CHECK: aad
+// CHECK:  encoding: [0xd5,0x0a]
+        	aad
+
+// CHECK: aam	$2
+// CHECK:  encoding: [0xd4,0x02]
+        	aam	$2
+
+// CHECK: aam
+// CHECK:  encoding: [0xd4,0x0a]
+        	aam	$0xA
+
+// CHECK: aam
+// CHECK:  encoding: [0xd4,0x0a]
+        	aam
+
+// CHECK: aas
+// CHECK:  encoding: [0x3f]
+        	aas
+
+// CHECK: daa
+// CHECK:  encoding: [0x27]
+        	daa
+
+// CHECK: das
+// CHECK:  encoding: [0x2f]
+        	das
+
+// CHECK: arpl	%bx, %bx
+// CHECK:  encoding: [0x63,0xdb]
+        	arpl	%bx,%bx
+
+// CHECK: arpl	%bx, 6(%ecx)
+// CHECK:  encoding: [0x67,0x63,0x59,0x06]
+        	arpl	%bx,6(%ecx)
+
+// CHECK: fcompi	%st(2)
+// CHECK:  encoding: [0xdf,0xf2]
+        	fcompi	%st(2), %st
+
+// CHECK: fcompi	%st(2)
+// CHECK:  encoding: [0xdf,0xf2]
+        	fcompi	%st(2)
+
+// CHECK: fcompi
+// CHECK:  encoding: [0xdf,0xf1]
+        	fcompi
+
+// CHECK: fucompi	%st(2)
+// CHECK:  encoding: [0xdf,0xea]
+        	fucompi	%st(2),%st
+
+// CHECK: fucompi	%st(2)
+// CHECK:  encoding: [0xdf,0xea]
+        	fucompi	%st(2)
+
+// CHECK: fucompi
+// CHECK:  encoding: [0xdf,0xe9]
+        	fucompi
+
+// CHECK: wait
+// CHECK:  encoding: [0x9b]
+        	fclex
+
+// CHECK: fnclex
+// CHECK:  encoding: [0xdb,0xe2]
+        	fnclex
+
+// CHECK: ud2
+// CHECK:  encoding: [0x0f,0x0b]
+        	ud2
+
+// CHECK: ud2
+// CHECK:  encoding: [0x0f,0x0b]
+        	ud2a
+
+// CHECK: ud2b
+// CHECK:  encoding: [0x0f,0xb9]
+        	ud2b
+
+// CHECK: loope 0
+// CHECK: encoding: [0xe1,A]
+	loopz 0
+
+// CHECK: loopne 0
+// CHECK: encoding: [0xe0,A]
+	loopnz 0
+
+// CHECK: outsb # encoding: [0x6e]
+// CHECK: outsb
+// CHECK: outsb
+	outsb
+	outsb	%ds:(%si), %dx
+	outsb	(%si), %dx
+
+// CHECK: insb # encoding: [0x6c]
+// CHECK: insb
+	insb
+	insb	%dx, %es:(%di)
+
+// CHECK: movsb # encoding: [0xa4]
+// CHECK: movsb
+// CHECK: movsb
+	movsb
+	movsb	%ds:(%si), %es:(%di)
+	movsb	(%si), %es:(%di)
+
+// CHECK: lodsb # encoding: [0xac]
+// CHECK: lodsb
+// CHECK: lodsb
+// CHECK: lodsb
+// CHECK: lodsb
+	lodsb
+	lodsb	%ds:(%si), %al
+	lodsb	(%si), %al
+	lods	%ds:(%si), %al
+	lods	(%si), %al
+
+// CHECK: stosb # encoding: [0xaa]
+// CHECK: stosb
+// CHECK: stosb
+	stosb
+	stosb	%al, %es:(%di)
+	stos	%al, %es:(%di)
+
+// CHECK: fsubp
+// CHECK: encoding: [0xde,0xe1]
+fsubp %st,%st(1)
+
+// CHECK: fsubp	%st(2)
+// CHECK: encoding: [0xde,0xe2]
+fsubp   %st, %st(2)
+