Emit an error is asm parser parsed X86_64 only registers, e.g. %rax, %sil.

This can happen in cases where TableGen generated asm matcher cannot check
whether a register operand is in the right register class. e.g. mem operands.

rdar://8204588


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@136292 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/ARM/AsmParser/ARMAsmParser.cpp

@@ -161,11 +161,6 @@ public:
 };
 } // end anonymous namespace
 
-namespace llvm {
-  // FIXME: TableGen this?
-  extern MCRegisterClass ARMMCRegisterClasses[]; // In ARMGenRegisterInfo.inc.
-}
-
 namespace {
 
 /// ARMOperand - Instances of this class represent a parsed ARM machine

lib/Target/ARM/MCTargetDesc/ARMMCCodeEmitter.cpp

@@ -1152,11 +1152,6 @@ getMsbOpValue(const MCInst &MI, unsigned Op,
   return msb;
 }
 
-namespace llvm {
-  // FIXME: TableGen this?
-  extern MCRegisterClass ARMMCRegisterClasses[]; // In ARMGenRegisterInfo.inc.
-}
-
 unsigned ARMMCCodeEmitter::
 getRegisterListOpValue(const MCInst &MI, unsigned Op,
                        SmallVectorImpl<MCFixup> &Fixups) const {

lib/Target/X86/AsmParser/X86AsmParser.cpp

@@ -13,6 +13,7 @@
 #include "llvm/MC/MCStreamer.h"
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCInst.h"
+#include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/MC/MCSubtargetInfo.h"
 #include "llvm/MC/MCParser/MCAsmLexer.h"
 #include "llvm/MC/MCParser/MCAsmParser.h"
@@ -400,19 +401,25 @@ bool X86ATTAsmParser::ParseRegister(unsigned &RegNo,
   if (Tok.isNot(AsmToken::Identifier))
     return Error(Tok.getLoc(), "invalid register name");
 
-  // FIXME: Validate register for the current architecture; we have to do
-  // validation later, so maybe there is no need for this here.
   RegNo = MatchRegisterName(Tok.getString());
 
   // If the match failed, try the register name as lowercase.
   if (RegNo == 0)
     RegNo = MatchRegisterName(LowercaseString(Tok.getString()));
 
-  // FIXME: This should be done using Requires<In32BitMode> and
-  // Requires<In64BitMode> so "eiz" usage in 64-bit instructions
-  // can be also checked.
-  if (RegNo == X86::RIZ && !is64BitMode())
-    return Error(Tok.getLoc(), "riz register in 64-bit mode only");
+  if (!is64BitMode()) {
+    // FIXME: This should be done using Requires<In32BitMode> and
+    // Requires<In64BitMode> so "eiz" usage in 64-bit instructions can be also
+    // checked.
+    // FIXME: Check AH, CH, DH, BH cannot be used in an instruction requiring a
+    // REX prefix.
+    if (RegNo == X86::RIZ ||
+        X86MCRegisterClasses[X86::GR64RegClassID].contains(RegNo) ||
+        X86II::isX86_64NonExtLowByteReg(RegNo) ||
+        X86II::isX86_64ExtendedReg(RegNo))
+      return Error(Tok.getLoc(), "register %"
+                   + Tok.getString() + " is only available in 64-bit mode");
+  }
 
   // Parse "%st" as "%st(0)" and "%st(1)", which is multiple tokens.
   if (RegNo == 0 && (Tok.getString() == "st" || Tok.getString() == "ST")) {
@@ -490,7 +497,7 @@ X86Operand *X86ATTAsmParser::ParseOperand() {
     SMLoc Start, End;
     if (ParseRegister(RegNo, Start, End)) return 0;
     if (RegNo == X86::EIZ || RegNo == X86::RIZ) {
-      Error(Start, "eiz and riz can only be used as index registers");
+      Error(Start, "%eiz and %riz can only be used as index registers");
       return 0;
     }
 

lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp

@@ -155,11 +155,6 @@ static MCFixupKind getImmFixupKind(uint64_t TSFlags) {
   return MCFixup::getKindForSize(Size, isPCRel);
 }
 
-namespace llvm {
-  // FIXME: TableGen this?
-  extern MCRegisterClass X86MCRegisterClasses[]; // In X86GenRegisterInfo.inc.
-}
-
 /// Is32BitMemOperand - Return true if the specified instruction with a memory
 /// operand should emit the 0x67 prefix byte in 64-bit mode due to a 32-bit
 /// memory operand.  Op specifies the operand # of the memoperand.

test/MC/X86/3DNow.s

@@ -1,18 +1,18 @@
-// RUN: llvm-mc -triple i386-unknown-unknown --show-encoding %s | FileCheck %s
+// RUN: llvm-mc -triple x86_64-unknown-unknown --show-encoding %s | FileCheck %s
 
 // PR8283
 
 // CHECK: pavgusb %mm2, %mm1  # encoding: [0x0f,0x0f,0xca,0xbf]
 pavgusb	%mm2, %mm1
 
-// CHECK: pavgusb 9(%esi,%edx), %mm3 # encoding: [0x0f,0x0f,0x5c,0x16,0x09,0xbf]
+// CHECK: pavgusb 9(%esi,%edx), %mm3 # encoding: [0x67,0x0f,0x0f,0x5c,0x16,0x09,0xbf]
 pavgusb	9(%esi,%edx), %mm3
 
         
 // CHECK: pf2id %mm2, %mm1  # encoding: [0x0f,0x0f,0xca,0x1d]
 pf2id	%mm2, %mm1
 
-// CHECK: pf2id 9(%esi,%edx), %mm3 # encoding: [0x0f,0x0f,0x5c,0x16,0x09,0x1d]
+// CHECK: pf2id 9(%esi,%edx), %mm3 # encoding: [0x67,0x0f,0x0f,0x5c,0x16,0x09,0x1d]
 pf2id	9(%esi,%edx), %mm3
 
 // CHECK: pfacc %mm2, %mm1  # encoding: [0x0f,0x0f,0xca,0xae]

test/MC/X86/x86-32-coverage.s

@@ -19571,8 +19571,8 @@
 // CHECK: 	aeskeygenassist	$125, (%edx,%eax,4), %xmm2
                 aeskeygenassist $125, (%edx,%eax,4), %xmm2
 
-// CHECK:   blendvps	(%rax), %xmm1   # encoding: [0x66,0x0f,0x38,0x14,0x08]
-            blendvps (%rax), %xmm1
+// CHECK:   blendvps	(%eax), %xmm1   # encoding: [0x66,0x0f,0x38,0x14,0x08]
+            blendvps (%eax), %xmm1
 // CHECK:   blendvps	%xmm2, %xmm1    # encoding: [0x66,0x0f,0x38,0x14,0xca]
             blendvps %xmm2, %xmm1
 

test/MC/X86/x86_errors.s

@@ -1,5 +1,12 @@
 // RUN: not llvm-mc -triple x86_64-unknown-unknown %s 2> %t.err
-// RUN: FileCheck < %t.err %s
+// RUN: FileCheck --check-prefix=64 < %t.err %s
 
-// CHECK: error: ambiguous instructions require an explicit suffix (could be 'cmpb', 'cmpw', 'cmpl', or 'cmpq')
+// RUN: not llvm-mc -triple i386-unknown-unknown %s 2> %t.err
+// RUN: FileCheck --check-prefix=32 < %t.err %s
+// rdar://8204588
+
+// 64: error: ambiguous instructions require an explicit suffix (could be 'cmpb', 'cmpw', 'cmpl', or 'cmpq')
 cmp $0, 0(%eax)
+
+// 32: error: register %rax is only available in 64-bit mode
+addl $0, 0(%rax)

utils/TableGen/RegisterInfoEmitter.cpp

@@ -40,6 +40,9 @@ RegisterInfoEmitter::runEnums(raw_ostream &OS,
 
   OS << "namespace llvm {\n\n";
 
+  OS << "class MCRegisterClass;\n"
+     << "extern MCRegisterClass " << Namespace << "MCRegisterClasses[];\n\n";
+
   if (!Namespace.empty())
     OS << "namespace " << Namespace << " {\n";
   OS << "enum {\n  NoRegister,\n";