teach the x86 asm parser how to handle segment prefixes

in memory operands.  rdar://7874844


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@101661 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 22 insertions, 15 deletions

diff --git a/include/llvm/MC/MCParser/AsmParser.h b/include/llvm/MC/MCParser/AsmParser.h
index a50abd6b61..7a78906733 100644
--- a/include/llvm/MC/MCParser/AsmParser.h
+++ b/include/llvm/MC/MCParser/AsmParser.h
@@ -14,7 +14,6 @@
 #ifndef ASMPARSER_H
 #define ASMPARSER_H
 
-#include <vector>
 #include "llvm/MC/MCParser/AsmLexer.h"
 #include "llvm/MC/MCParser/AsmCond.h"
 #include "llvm/MC/MCParser/MCAsmParser.h"
@@ -22,6 +21,7 @@
 #include "llvm/MC/MCStreamer.h"
 #include "llvm/MC/MCAsmInfo.h"
 #include "llvm/ADT/StringMap.h"
+#include <vector>
 
 namespace llvm {
 class AsmCond;
diff --git a/lib/Target/X86/AsmParser/X86AsmParser.cpp b/lib/Target/X86/AsmParser/X86AsmParser.cpp
index 47873d14a9..da013505da 100644
--- a/lib/Target/X86/AsmParser/X86AsmParser.cpp
+++ b/lib/Target/X86/AsmParser/X86AsmParser.cpp
@@ -44,7 +44,7 @@ private:
   bool ParseRegister(unsigned &RegNo, SMLoc &StartLoc, SMLoc &EndLoc);
 
   X86Operand *ParseOperand();
-  X86Operand *ParseMemOperand();
+  X86Operand *ParseMemOperand(unsigned SegReg, SMLoc StartLoc);
 
   bool ParseDirectiveWord(unsigned Size, SMLoc L);
 
@@ -368,14 +368,22 @@ bool X86ATTAsmParser::ParseRegister(unsigned &RegNo,
 X86Operand *X86ATTAsmParser::ParseOperand() {
   switch (getLexer().getKind()) {
   default:
-    return ParseMemOperand();
+    // Parse a memory operand with no segment register.
+    return ParseMemOperand(0, Parser.getTok().getLoc());
   case AsmToken::Percent: {
-    // FIXME: if a segment register, this could either be just the seg reg, or
-    // the start of a memory operand.
+    // Read the register.
     unsigned RegNo;
     SMLoc Start, End;
     if (ParseRegister(RegNo, Start, End)) return 0;
-    return X86Operand::CreateReg(RegNo, Start, End);
+    
+    // If this is a segment register followed by a ':', then this is the start
+    // of a memory reference, otherwise this is a normal register reference.
+    if (getLexer().isNot(AsmToken::Colon))
+      return X86Operand::CreateReg(RegNo, Start, End);
+    
+    
+    getParser().Lex(); // Eat the colon.
+    return ParseMemOperand(RegNo, Start);
   }
   case AsmToken::Dollar: {
     // $42 -> immediate.
@@ -389,13 +397,10 @@ X86Operand *X86ATTAsmParser::ParseOperand() {
   }
 }
 
-/// ParseMemOperand: segment: disp(basereg, indexreg, scale)
-X86Operand *X86ATTAsmParser::ParseMemOperand() {
-  SMLoc MemStart = Parser.getTok().getLoc();
-  
-  // FIXME: If SegReg ':'  (e.g. %gs:), eat and remember.
-  unsigned SegReg = 0;
-  
+/// ParseMemOperand: segment: disp(basereg, indexreg, scale).  The '%ds:' prefix
+/// has already been parsed if present.
+X86Operand *X86ATTAsmParser::ParseMemOperand(unsigned SegReg, SMLoc MemStart) {
+ 
   // We have to disambiguate a parenthesized expression "(4+5)" from the start
   // of a memory operand with a missing displacement "(%ebx)" or "(,%eax)".  The
   // only way to do this without lookahead is to eat the '(' and see what is
diff --git a/test/MC/AsmParser/X86/x86_operands.s b/test/MC/AsmParser/X86/x86_operands.s
index edddd1fc44..bf958d8478 100644
--- a/test/MC/AsmParser/X86/x86_operands.s
+++ b/test/MC/AsmParser/X86/x86_operands.s
@@ -55,4 +55,6 @@
 # CHECK: call *4(%eax)
         call *4(%eax)
 
-        
+# CHECK: movl	%gs:8, %eax
+movl %gs:8, %eax
+
diff --git a/test/Makefile b/test/Makefile
index 3750fdb2f1..fc6e67b2e8 100644
--- a/test/Makefile
+++ b/test/Makefile
@@ -28,7 +28,7 @@ endif
 
 ifdef VERBOSE
 RUNTESTFLAGS := $(VERBOSE)
-LIT_ARGS := -v
+LIT_ARGS := -v -j16
 else
 LIT_ARGS := -s -v
 endif