fix(goobj): external package and symbol indices and arm64 pair relocations

Assisted-by: GLM 5.3

asm/goobj_resolve.go

@@ -40,8 +40,11 @@ func exportPath(importPath string) (string, error) {
 //
 // refs maps package import paths to the symbol names referenced from that
 // package.  The returned pkgIdx maps each import path to its position in
-// the blkPkgIdx table (0-based), and symIdx gives each symbol's index within
-// its package.
+// the blkPkgIdx table, which reserves index 0 for the dummy invalid
+// package (cmd/internal/obj/sym.go: "0 is invalid index"; the loader's
+// reader loop starts at 1), so package i sits at block index i+1 and its
+// relocations carry i+1.  symIdx gives each symbol's index within its
+// package.
 func resolveExternalGOOBJ(refs map[string][]string) (pkgIdx map[string]int, symIdx map[string]int, err error) {
 	pkgIdx = make(map[string]int, len(refs))
 	symIdx = make(map[string]int)
@@ -50,7 +53,9 @@ func resolveExternalGOOBJ(refs map[string][]string) (pkgIdx map[string]int, symI
 	packages := sortedPkgRefs(refs)
 
 	for i, pkg := range packages {
-		pkgIdx[pkg.path] = i
+		// Block index 0 is the dummy invalid package; the first real
+		// package starts at 1.
+		pkgIdx[pkg.path] = i + 1
 		exp, err := exportPath(pkg.path)
 		if err != nil {
 			return nil, nil, err
@@ -145,40 +150,65 @@ func parseArDecimal(b []byte) int {
 }
 
 // goobjFile is a parsed GOOBJ file: the string table and the symbol-definition
-// block.
+// blocks.  The hashed blocks are kept raw: their symbols carry no names, only
+// the loader needs their counts.
 type goobjFile struct {
-	strTab []byte // string table, at headerSize + n
-	symdef []byte // blkSymdef raw block
-	npdef  []byte // blkNonpkgdef raw block
+	strTab   []byte // string table, at headerSize + n
+	symdef   []byte // blkSymdef raw block
+	hashed64 []byte // blkHashed64def raw block
+	hashed   []byte // blkHasheddef raw block
+	npdef    []byte // blkNonpkgdef raw block
 }
 
-// symbols returns all symbol names in definition order by scanning the
-// symdef and nonpkgdef blocks and resolving each name through the string
-// table.  Package definitions (blkSymdef) use fully-qualified names like
-// "runtime.morestack"; non-package definitions (blkNonpkgdef) use bare
-// names like "morestack".  This combined list matches the index the
-// linker expects for cross-package references.
+// loaderIndexBase returns the index the first nonpkgdef symbol occupies in the
+// loader's per-object symbol array.  cmd/link lays the definition blocks out as
+// symdef, hashed64def, hasheddef, nonpkgdef, nonpkgref (loader.go: preloadSyms
+// fills r.syms in exactly that order, and resolve() indexes PkgIdxNone and
+// cross-package SymIdx into it), so a symbol found in blkNonpkgdef carries the
+// three leading blocks' symbol counts as its base.
+func (f *goobjFile) loaderIndexBase() int {
+	return len(f.symdef)/recSymSize + len(f.hashed64)/recSymSize + len(f.hashed)/recSymSize
+}
+
+// symbols returns the names of the symdef and nonpkgdef blocks in
+// definition order.  Package definitions (blkSymdef) use fully-qualified
+// names like "runtime.morestack"; non-package definitions (blkNonpkgdef)
+// use bare names like "morestack".  For lookups by index prefer
+// findSymbol: it adds the hashed blocks' count the loader's array
+// interleaves between the two.
 func (f *goobjFile) symbols() []string {
 	return append(f.defNames(), f.npdefNames()...)
 }
 
-// findSymbol returns the index of a symbol within the combined symbol list,
-// or -1 if not found.  It first tries the fully-qualified name (pkg.name),
-// then the bare name.
+// findSymbol returns the index of a symbol within the loader's per-object
+// symbol array, or -1 if not found.  It first tries the fully-qualified
+// name (pkg.name), then the bare name (assembly objects store dotless
+// names, e.g. runtime's "gogo", for symbols other packages reach through
+// a linkname).
 func (f *goobjFile) findSymbol(pkg, name string) int {
+	base := f.loaderIndexBase()
 	qualified := pkg + "." + name
-	syms := f.symbols()
-	for i, s := range syms {
+	for i, s := range f.defNames() {
 		if s == qualified {
 			return i
 		}
 	}
-	// Try bare name (for non-package definitions).
-	for i, s := range syms {
+	for i, s := range f.npdefNames() {
+		if s == qualified {
+			return base + i
+		}
+	}
+	// Try bare name (for dotless assembly definitions).
+	for i, s := range f.defNames() {
 		if s == name {
 			return i
 		}
 	}
+	for i, s := range f.npdefNames() {
+		if s == name {
+			return base + i
+		}
+	}
 	return -1
 }
 
@@ -192,12 +222,16 @@ func (f *goobjFile) npdefNames() []string {
 	return f.readSymNames(f.npdef)
 }
 
+// recSymSize is the size of one Sym record in the definition blocks
+// (goobj.SymSize: stringRefSize + 2 + 1 + 1 + 1 + 4 + 4).
+const recSymSize = 21
+
 // readSymNames reads symbol names from a symdef/nonpkgdef block.  Each record
 // is 21 bytes: nameLen (u32), nameOff (u32), abi (u16), typ, flag, flag2,
 // size (u32), align (u32).  nameOff is an absolute offset into the string
 // table.
 func (f *goobjFile) readSymNames(block []byte) []string {
-	const recSize = 21
+	const recSize = recSymSize
 	if len(block) < recSize {
 		return nil
 	}
@@ -247,16 +281,18 @@ func parseGOOBJ(data []byte) (*goobjFile, error) {
 	//   [16:20] flags
 	//   [20:96] 19 × uint32 offsets
 	var offs [blkEnd + 1]uint32
-	for i := 0; i <= blkEnd; i++ {
+	for i := range blkEnd + 1 {
 		offs[i] = binary.LittleEndian.Uint32(payload[20+4*i:])
 	}
 	// The string table lives at headerSize.
 	strTabStart := uint32(goobjHeaderSize)
 
 	f := &goobjFile{
-		strTab: payload[strTabStart:offs[0]],
-		symdef: blockSlice(payload, offs, blkSymdef, blkSymdef+1),
-		npdef:  blockSlice(payload, offs, blkNonpkgdef, blkNonpkgdef+1),
+		strTab:   payload[strTabStart:offs[0]],
+		symdef:   blockSlice(payload, offs, blkSymdef, blkSymdef+1),
+		hashed64: blockSlice(payload, offs, blkHashed64def, blkHashed64def+1),
+		hashed:   blockSlice(payload, offs, blkHasheddef, blkHasheddef+1),
+		npdef:    blockSlice(payload, offs, blkNonpkgdef, blkNonpkgdef+1),
 	}
 	return f, nil
 }
@@ -306,22 +342,26 @@ func resolveExternalSymbols(externals []string) (pkgTable []string, pkgIdxMap ma
 		return nil, nil, nil, err
 	}
 
-	// Build the package table in pkgIdx order.
+	// Build the package table in pkgIdx order.  The indices are 1-based
+	// (0 is the dummy invalid package, written by the emitter itself), so
+	// the table without the dummy is indexed one below.
 	pkgTable = make([]string, len(pkgIdx1))
 	for pkg, idx := range pkgIdx1 {
-		pkgTable[idx] = pkg
+		pkgTable[idx-1] = pkg
 	}
 
 	return pkgTable, pkgIdx1, symIdx1, nil
 }
 
 // splitQualified splits a qualified Go symbol name (pkgpath·name) into its
-// package path and local name.  The separator is the middle dot (U+00B7).
-// If no separator is found, the symbol is assumed to be in the current
-// package (empty pkg).
+// package path and local name.  The separator is the middle dot (U+00B7),
+// whose UTF-8 encoding is two bytes, so the search must be string-based:
+// IndexByte would match only the second byte and leave the lead byte on
+// the package path.  If no separator is found, the symbol is assumed to be
+// in the current package (empty pkg).
 func splitQualified(full string) (pkg, name string) {
-	if idx := strings.IndexByte(full, '\u00b7'); idx >= 0 {
-		return full[:idx], full[idx+len("\u00b7"):]
+	if before, after, ok := strings.Cut(full, "\u00b7"); ok {
+		return before, after
 	}
 	if before, after, ok := strings.Cut(full, "."); ok {
 		return before, after