Implement the ldr-pseudo opcode for ARM assembly

The ldr-pseudo opcode is a convenience for loading 32-bit constants.
It is converted into a pc-relative load from a constant pool. For
example,

  ldr r0, =0x10001
  ldr r1, =bar

will generate this output in the final assembly

  ldr r0, .Ltmp0
  ldr r1, .Ltmp1
  ...
  .Ltmp0: .long 0x10001
  .Ltmp1: .long bar

Sketch of the LDR pseudo implementation:
  Keep a map from Section => ConstantPool

  When parsing ldr r0, =val
    parse val as an MCExpr
    get ConstantPool for current Section
    Label = CreateTempSymbol()
    remember val in ConstantPool at next free slot
    add operand to ldr that is MCSymbolRef of Label

  On finishParse() callback
    Write out all non-empty constant pools
    for each Entry in ConstantPool
      Emit Entry.Label
      Emit Entry.Value

Possible improvements to be added in a later patch:
  1. Does not convert load of small constants to mov
     (e.g. ldr r0, =0x1 => mov r0, 0x1)
  2. Does reuse constant pool entries for same constant

The implementation was tested for ARM, Thumb1, and Thumb2 targets on
linux and darwin.

llvm-svn: 197708

1 files changed, 93 insertions, 1 deletions

diff --git a/llvm/lib/Target/ARM/AsmParser/ARMAsmParser.cpp b/llvm/lib/Target/ARM/AsmParser/ARMAsmParser.cpp
index 6c9e445346b..8ebf1e41ebf 100644
--- a/llvm/lib/Target/ARM/AsmParser/ARMAsmParser.cpp
+++ b/llvm/lib/Target/ARM/AsmParser/ARMAsmParser.cpp
@@ -36,6 +36,7 @@
 #include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/MC/MCStreamer.h"
 #include "llvm/MC/MCSubtargetInfo.h"
+#include "llvm/MC/MCSymbol.h"
 #include "llvm/Support/ELF.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/SourceMgr.h"
@@ -50,11 +51,69 @@ class ARMOperand;
 
 enum VectorLaneTy { NoLanes, AllLanes, IndexedLane };
 
+// A class to keep track of assembler-generated constant pools that are use to
+// implement the ldr-pseudo.
+class ConstantPool {
+  typedef SmallVector<std::pair<MCSymbol *, const MCExpr *>, 4> EntryVecTy;
+  EntryVecTy Entries;
+
+public:
+  // Initialize a new empty constant pool
+  ConstantPool() { }
+
+  // Add a new entry to the constant pool in the next slot.
+  // \param Value is the new entry to put in the constant pool.
+  //
+  // \returns a MCExpr that references the newly inserted value
+  const MCExpr *addEntry(const MCExpr *Value, MCContext &Context) {
+    MCSymbol *CPEntryLabel = Context.CreateTempSymbol();
+
+    Entries.push_back(std::make_pair(CPEntryLabel, Value));
+    return MCSymbolRefExpr::Create(CPEntryLabel, Context);
+  }
+
+  // Emit the contents of the constant pool using the provided streamer.
+  void emitEntries(MCStreamer &Streamer) const {
+    Streamer.EmitCodeAlignment(4); // align to 4-byte address
+    Streamer.EmitDataRegion(MCDR_DataRegion);
+    for (EntryVecTy::const_iterator I = Entries.begin(), E = Entries.end();
+         I != E; ++I) {
+      Streamer.EmitLabel(I->first);
+      Streamer.EmitValue(I->second, 4);
+    }
+    Streamer.EmitDataRegion(MCDR_DataRegionEnd);
+  }
+};
+
+// Map type used to keep track of per-Section constant pools used by the
+// ldr-pseudo opcode. The map associates a section to its constant pool. The
+// constant pool is a vector of (label, value) pairs. When the ldr
+// pseudo is parsed we insert a new (label, value) pair into the constant pool
+// for the current section and add MCSymbolRefExpr to the new label as
+// an opcode to the ldr. After we have parsed all the user input we
+// output the (label, value) pairs in each constant pool at the end of the
+// section.
+typedef std::map<const MCSection *, ConstantPool> ConstantPoolMapTy;
+
 class ARMAsmParser : public MCTargetAsmParser {
   MCSubtargetInfo &STI;
   MCAsmParser &Parser;
   const MCInstrInfo &MII;
   const MCRegisterInfo *MRI;
+  ConstantPoolMapTy ConstantPools;
+
+  // Assembler created constant pools for ldr pseudo
+  ConstantPool *getConstantPool(const MCSection *Section) {
+    ConstantPoolMapTy::iterator CP = ConstantPools.find(Section);
+    if (CP == ConstantPools.end())
+      return 0;
+
+    return &CP->second;
+  }
+
+  ConstantPool &getOrCreateConstantPool(const MCSection *Section) {
+    return ConstantPools[Section];
+  }
 
   ARMTargetStreamer &getTargetStreamer() {
     MCTargetStreamer &TS = getParser().getStreamer().getTargetStreamer();
@@ -296,7 +355,7 @@ public:
                                MCStreamer &Out, unsigned &ErrorInfo,
                                bool MatchingInlineAsm);
   void onLabelParsed(MCSymbol *Symbol);
-
+  void finishParse();
 };
 } // end anonymous namespace
 
@@ -4656,6 +4715,24 @@ bool ARMAsmParser::parseOperand(SmallVectorImpl<MCParsedAsmOperand*> &Operands,
     Operands.push_back(ARMOperand::CreateImm(ExprVal, S, E));
     return false;
   }
+  case AsmToken::Equal: {
+    if (Mnemonic != "ldr") // only parse for ldr pseudo (e.g. ldr r0, =val)
+      return Error(Parser.getTok().getLoc(), "unexpected token in operand");
+
+    const MCSection *Section =
+        getParser().getStreamer().getCurrentSection().first;
+    assert(Section);
+    Parser.Lex(); // Eat '='
+    const MCExpr *SubExprVal;
+    if (getParser().parseExpression(SubExprVal))
+      return true;
+    E = SMLoc::getFromPointer(Parser.getTok().getLoc().getPointer() - 1);
+
+    const MCExpr *CPLoc =
+        getOrCreateConstantPool(Section).addEntry(SubExprVal, getContext());
+    Operands.push_back(ARMOperand::CreateImm(CPLoc, S, E));
+    return false;
+  }
   }
 }
 
@@ -8396,3 +8473,18 @@ unsigned ARMAsmParser::validateTargetOperandClass(MCParsedAsmOperand *AsmOp,
   }
   return Match_InvalidOperand;
 }
+
+void ARMAsmParser::finishParse() {
+  // Dump contents of assembler constant pools.
+  MCStreamer &Streamer = getParser().getStreamer();
+  for (ConstantPoolMapTy::iterator CPI = ConstantPools.begin(),
+                                   CPE = ConstantPools.end();
+       CPI != CPE; ++CPI) {
+    const MCSection *Section = CPI->first;
+    ConstantPool &CP = CPI->second;
+
+    // Dump assembler constant pools at the end of the section.
+    Streamer.SwitchSection(Section);
+    CP.emitEntries(Streamer);
+  }
+}