debug/pe: introduce File.COFFSymbols and (*COFFSymbol).FullName

Reloc.SymbolTableIndex is an index into symbol table. But
Reloc.SymbolTableIndex cannot be used as index into File.Symbols,
because File.Symbols slice has Aux lines removed as it is built.

We cannot change the way File.Symbols works, so I propose we
introduce new File.COFFSymbols that does not have that limitation.

Also unlike File.Symbols, File.COFFSymbols will consist of
COFFSymbol. COFFSymbol matches PE COFF specification exactly,
and it is simpler to use.

Updates #15345

Change-Id: Icbc265853a472529cd6d64a76427b27e5459e373
Reviewed-on: https://go-review.googlesource.com/22336Reviewed-by: David Crawshaw <crawshaw@golang.org>
Run-TryBot: Alex Brainman <alex.brainman@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>

src/debug/pe/file.go

@@ -19,7 +19,8 @@ type File struct {
 	FileHeader
 	OptionalHeader interface{} // of type *OptionalHeader32 or *OptionalHeader64
 	Sections       []*Section
-	Symbols        []*Symbol
+	Symbols        []*Symbol    // COFF symbols with auxiliary symbol records removed
+	COFFSymbols    []COFFSymbol // all COFF symbols (including auxiliary symbol records)
 	StringTable    StringTable
 
 	closer io.Closer
@@ -94,48 +95,14 @@ func NewFile(r io.ReaderAt) (*File, error) {
 		return nil, err
 	}
 
-	var ss []byte
-	if f.FileHeader.NumberOfSymbols > 0 {
-		// Get COFF string table, which is located at the end of the COFF symbol table.
-		sr.Seek(int64(f.FileHeader.PointerToSymbolTable+COFFSymbolSize*f.FileHeader.NumberOfSymbols), io.SeekStart)
-		var l uint32
-		if err := binary.Read(sr, binary.LittleEndian, &l); err != nil {
-			return nil, err
-		}
-		ss = make([]byte, l)
-		if _, err := r.ReadAt(ss, int64(f.FileHeader.PointerToSymbolTable+COFFSymbolSize*f.FileHeader.NumberOfSymbols)); err != nil {
-			return nil, err
-		}
-
-		// Process COFF symbol table.
-		sr.Seek(int64(f.FileHeader.PointerToSymbolTable), io.SeekStart)
-		aux := uint8(0)
-		for i := 0; i < int(f.FileHeader.NumberOfSymbols); i++ {
-			cs := new(COFFSymbol)
-			if err := binary.Read(sr, binary.LittleEndian, cs); err != nil {
-				return nil, err
-			}
-			if aux > 0 {
-				aux--
-				continue
-			}
-			var name string
-			if cs.Name[0] == 0 && cs.Name[1] == 0 && cs.Name[2] == 0 && cs.Name[3] == 0 {
-				si := int(binary.LittleEndian.Uint32(cs.Name[4:]))
-				name, _ = getString(ss, si)
-			} else {
-				name = cstring(cs.Name[:])
-			}
-			aux = cs.NumberOfAuxSymbols
-			s := &Symbol{
-				Name:          name,
-				Value:         cs.Value,
-				SectionNumber: cs.SectionNumber,
-				Type:          cs.Type,
-				StorageClass:  cs.StorageClass,
-			}
-			f.Symbols = append(f.Symbols, s)
-		}
+	// Read symbol table.
+	f.COFFSymbols, err = readCOFFSymbols(&f.FileHeader, sr)
+	if err != nil {
+		return nil, err
+	}
+	f.Symbols, err = removeAuxSymbols(f.COFFSymbols, f.StringTable)
+	if err != nil {
+		return nil, err
 	}
 
 	// Read optional header.

src/debug/pe/section.go

@@ -39,6 +39,8 @@ func (sh *SectionHeader32) fullName(st StringTable) (string, error) {
 	return st.String(uint32(i))
 }
 
+// TODO(brainman): copy all IMAGE_REL_* consts from ldpe.go here
+
 // Reloc represents a PE COFF relocation.
 // Each section contains its own relocation list.
 type Reloc struct {

src/debug/pe/symbol.go

@@ -4,8 +4,15 @@
 
 package pe
 
+import (
+	"encoding/binary"
+	"fmt"
+	"io"
+)
+
 const COFFSymbolSize = 18
 
+// COFFSymbol represents single COFF symbol table record.
 type COFFSymbol struct {
 	Name               [8]uint8
 	Value              uint32
@@ -15,6 +22,70 @@ type COFFSymbol struct {
 	NumberOfAuxSymbols uint8
 }
 
+func readCOFFSymbols(fh *FileHeader, r io.ReadSeeker) ([]COFFSymbol, error) {
+	if fh.NumberOfSymbols <= 0 {
+		return nil, nil
+	}
+	_, err := r.Seek(int64(fh.PointerToSymbolTable), io.SeekStart)
+	if err != nil {
+		return nil, fmt.Errorf("fail to seek to symbol table: %v", err)
+	}
+	syms := make([]COFFSymbol, fh.NumberOfSymbols)
+	err = binary.Read(r, binary.LittleEndian, syms)
+	if err != nil {
+		return nil, fmt.Errorf("fail to read symbol table: %v", err)
+	}
+	return syms, nil
+}
+
+// isSymNameOffset checks symbol name if it is encoded as offset into string table.
+func isSymNameOffset(name [8]byte) (bool, uint32) {
+	if name[0] == 0 && name[1] == 0 && name[2] == 0 && name[3] == 0 {
+		return true, binary.LittleEndian.Uint32(name[4:])
+	}
+	return false, 0
+}
+
+// FullName finds real name of symbol sym. Normally name is stored
+// in sym.Name, but if it is longer then 8 characters, it is stored
+// in COFF string table st instead.
+func (sym *COFFSymbol) FullName(st StringTable) (string, error) {
+	if ok, offset := isSymNameOffset(sym.Name); ok {
+		return st.String(offset)
+	}
+	return cstring(sym.Name[:]), nil
+}
+
+func removeAuxSymbols(allsyms []COFFSymbol, st StringTable) ([]*Symbol, error) {
+	if len(allsyms) == 0 {
+		return nil, nil
+	}
+	syms := make([]*Symbol, 0)
+	aux := uint8(0)
+	for _, sym := range allsyms {
+		if aux > 0 {
+			aux--
+			continue
+		}
+		name, err := sym.FullName(st)
+		if err != nil {
+			return nil, err
+		}
+		aux = sym.NumberOfAuxSymbols
+		s := &Symbol{
+			Name:          name,
+			Value:         sym.Value,
+			SectionNumber: sym.SectionNumber,
+			Type:          sym.Type,
+			StorageClass:  sym.StorageClass,
+		}
+		syms = append(syms, s)
+	}
+	return syms, nil
+}
+
+// Symbol is similar to COFFSymbol with Name field replaced
+// by Go string. Symbol also does not have NumberOfAuxSymbols.
 type Symbol struct {
 	Name          string
 	Value         uint32