[X86] Fix intel syntax push parsing bug

[niravd]

Summary

Change erroneous parsing of push immediate instructions in intel syntax
to default to pointer size by rewriting into the ATT style for matching.

This fixes PR22028.

[majnemer]

lib/Target/X86/AsmParser/X86AsmParser.cpp

2799

auto *

2802

const auto *

[niravd]

use auto types

[rnk]

Looks terrible, please commit =(

Every time someone touches the X86 assembler I swear that this is the last straw, after this one fix we have to rewrite it from the ground up, but we just keep deferring it.

lib/Target/X86/AsmParser/X86AsmParser.cpp

2805–2808

IMO this is simpler:

char Tmp[] = "push ";
switch (getPointerWidth()) {
case 16: Tmp[4] = 'w'; break;
case 32: Tmp[4] = 'l'; break;
case 64: Tmp[4] = 'q'; break;
}

lib/Target/X86/AsmParser/X86AsmParser.cpp

bool X86AsmParser::MatchAndEmitIntelInstruction(SMLoc IDLoc, unsigned &Opcode,
                                                 MCStreamer &Out,
                                                 uint64_t &ErrorInfo,
                                                 bool MatchingInlineAsm) {
   assert(!Operands.empty() && "Unexpect empty operand list!");
   X86Operand &Op = static_cast<X86Operand &>(*Operands[0]);
   assert(Op.isToken() && "Leading operand should always be a mnemonic!");
   StringRef Mnemonic = Op.getToken();
   SMRange EmptyRange = None;
+  StringRef Base = Op.getToken();
 
   // First, handle aliases that expand to multiple instructions.
   MatchFPUWaitAlias(IDLoc, Op, Operands, Out, MatchingInlineAsm);
 
   MCInst Inst;
 
   // Find one unsized memory operand, if present.
   X86Operand *UnsizedMemOp = nullptr;
if (UnsizedMemOp) {
     for (const char *Instr : PtrSizedInstrs) {
       if (Mnemonic == Instr) {
         UnsizedMemOp->Mem.Size = getPointerWidth();
         break;
       }
     }
   }
 
+  SmallVector<unsigned, 8> Match;
+  uint64_t ErrorInfoMissingFeature = 0;
+
+  // If unsized push has immediate operand we should default the default pointer
+  // size for the size.
+  if (Mnemonic == "push" && Operands.size() == 2) {
+    X86Operand *X86Op = static_cast<X86Operand *>(Operands[1].get());
+    if (X86Op->isImm()) {
+      // If it's not a constant fall through and let remainder take care of it.
+      const MCConstantExpr *CE = dyn_cast<MCConstantExpr>(X86Op->getImm());
+      unsigned Size = getPointerWidth();
+      if (CE &&
+          (isIntN(Size, CE->getValue()) || isUIntN(Size, CE->getValue()))) {
+        SmallString<16> Tmp;
+        Tmp += Base;
+        Tmp += (is64BitMode())
+                   ? "q"
+                   : (is32BitMode()) ? "l" : (is16BitMode()) ? "w" : " ";
+        Op.setTokenValue(Tmp);
+        // Do match in ATT mode to allow explicit suffix usage.
+        Match.push_back(MatchInstruction(Operands, Inst, ErrorInfo,
+                                         MatchingInlineAsm,
+                                         false /*isParsingIntelSyntax()*/));
+        Op.setTokenValue(Base);
+      }
+    }
+  }
+
   // If an unsized memory operand is present, try to match with each memory
   // operand size.  In Intel assembly, the size is not part of the instruction
   // mnemonic.
-  SmallVector<unsigned, 8> Match;
-  uint64_t ErrorInfoMissingFeature = 0;
   if (UnsizedMemOp && UnsizedMemOp->isMemUnsized()) {
     static const unsigned MopSizes[] = {8, 16, 32, 64, 80, 128, 256, 512};
     for (unsigned Size : MopSizes) {
       UnsizedMemOp->Mem.Size = Size;
       uint64_t ErrorInfoIgnore;
       unsigned LastOpcode = Inst.getOpcode();
       unsigned M = MatchInstruction(Operands, Inst, ErrorInfoIgnore,
                                     MatchingInlineAsm, isParsingIntelSyntax());

test/MC/X86/pr22028.s

+// RUN: llvm-mc -triple i386-unknown-unknown-code16 -show-encoding %s | FileCheck --check-prefix=CHECK16 %s
+// RUN: llvm-mc -triple i386-unknown-unknown -show-encoding %s | FileCheck --check-prefix=CHECK %s
+// RUN: llvm-mc -triple i686-unknown-unknown -show-encoding %s | FileCheck --check-prefix=CHECK %s  
+  
+.intel_syntax
+  
+push 0
+push -1
+push 30
+push 257
+push 65536
+
+//CHECK16:  pushw $0                      # encoding: [0x6a,0x00]
+//CHECK16:  pushw $-1                 # encoding: [0x6a,0xff]
+//CHECK16:  pushw $30                     # encoding: [0x6a,0x1e]
+//CHECK16:  pushw $257                    # encoding: [0x68,0x01,0x01]
+//CHECK16:  pushl $65536                  # encoding: [0x66,0x68,0x00,0x00,0x01,0x00]
+
+//CHECK:  pushl $0                      # encoding: [0x6a,0x00]
+//CHECK:  pushl $-1                     # encoding: [0x6a,0xff]
+//CHECK:  pushl $30                     # encoding: [0x6a,0x1e]
+//CHECK:  pushl $257                    # encoding: [0x68,0x01,0x01,0x00,0x00]
+//CHECK:  pushl $65536                  # encoding: [0x68,0x00,0x00,0x01,0x00]