feat(asm): resolve external GOOBJ symbols from archive data

asm/goobj.go

@@ -213,16 +213,50 @@ func (img *Image) GOObject(pkgPath, srcPath string) ([]byte, error) {
 		})
 	}
 
+	// Resolve external symbol references (cross-package).  Build the
+	// package index table and determine each external symbol's SymIdx
+	// by reading the target package's export data.
+	var extPkgTable []string
+	var extPkgIdx map[string]int
+	var extSymIdx map[string]int
+	if len(img.Externals) > 0 {
+		var err error
+		extPkgTable, extPkgIdx, extSymIdx, err = resolveExternalSymbols(img.Externals)
+		if err != nil {
+			return nil, fmt.Errorf("GOOBJ emission: resolving external symbols: %w", err)
+		}
+	}
+
 	// Relocations, per defined symbol in definition order (package defs,
-	// then non-package defs).  Only file-local GLOBL references resolve;
-	// external symbols need the import machinery of a later increment.
+	// then non-package defs).
 	nsyms := len(defs) + len(nps)
 	symRelocs := make([][]byte, nsyms) // flat 23-byte records
 	for i, fn := range img.Funcs {
 		si := len(defs) + fnNpIdx[i]
 		for _, r := range fn.Relocs {
 			if r.External {
-				return nil, fmt.Errorf("GOOBJ emission: external symbol %q is not supported yet", r.Name)
+				// Split package-qualified name: "runtime·morestack" → runtime, morestack.
+				pkg, name := splitQualified(r.Name)
+				if pkg == "" {
+					return nil, fmt.Errorf("GOOBJ emission: external symbol %q has no package prefix", r.Name)
+				}
+				pIdx, ok := extPkgIdx[pkg]
+				if !ok {
+					return nil, fmt.Errorf("GOOBJ emission: package %q not resolved", pkg)
+				}
+				sIdx, ok := extSymIdx[pkg+"·"+name]
+				if !ok {
+					return nil, fmt.Errorf("GOOBJ emission: symbol %s·%s not resolved", pkg, name)
+				}
+				var rec [23]byte
+				binary.LittleEndian.PutUint32(rec[0:], uint32(int32(r.Off)))
+				rec[4] = 4 // field width
+				binary.LittleEndian.PutUint16(rec[5:], relocPCRel)
+				binary.LittleEndian.PutUint64(rec[7:], uint64(r.Addend))
+				binary.LittleEndian.PutUint32(rec[15:], uint32(pIdx))
+				binary.LittleEndian.PutUint32(rec[19:], uint32(sIdx))
+				symRelocs[si] = append(symRelocs[si], rec[:]...)
+				continue
 			}
 			di, ok := defIdx[r.Name]
 			if !ok {
@@ -291,7 +325,16 @@ func (img *Image) GOObject(pkgPath, srcPath string) ([]byte, error) {
 	for _, s := range nps {
 		npdefBlk = s.sym.append(npdefBlk, strOff)
 	}
-	pkgIdxBlk := stringRef(nil, "") // index 0: the dummy invalid package
+
+	// Package index table: index 0 is the dummy invalid package.
+	// External packages follow, in pkgIdx order.
+	for _, pkg := range extPkgTable {
+		addStr(pkg)
+	}
+	pkgIdxBlk := stringRef(nil, "") // index 0: dummy
+	for _, pkg := range extPkgTable {
+		pkgIdxBlk = stringRef(pkgIdxBlk, pkg)
+	}
 	fileBlk := stringRef(nil, srcPath)
 
 	var relocBlk, auxBlk, dataBlk []byte

asm/goobj_resolve.go

@@ -0,0 +1,348 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+package asm
+
+import (
+	"bytes"
+	"encoding/binary"
+	"fmt"
+	"os"
+	"os/exec"
+	"strings"
+)
+
+// readGOOBJSymbols reads the GOOBJ symbol definitions from a compiled Go
+// package's export file.  The file is an ar archive containing a __.PKGDEF
+// member whose payload is the "go object ...\n!\n" preamble followed by the
+// GOOBJ data.  The function returns the symbol names in definition order
+// (the order they appear in blkSymdef), which matches the SymIdx the linker
+// expects for cross-package references.
+func readGOOBJSymbols(exportPath string) ([]string, error) {
+	data, err := os.ReadFile(exportPath)
+	if err != nil {
+		return nil, err
+	}
+	goobj, err := extractGOOBJ(data)
+	if err != nil {
+		return nil, fmt.Errorf("%s: %w", exportPath, err)
+	}
+	return goobj.symbols(), nil
+}
+
+// exportPath returns the export file path for a given import path by running
+// "go list -export".  The result is cached so repeated calls for the same
+// package are fast.
+func exportPath(importPath string) (string, error) {
+	cmd := exec.Command("go", "list", "-json", "-export", importPath)
+	out, err := cmd.Output()
+	if err != nil {
+		return "", fmt.Errorf("go list %s: %w", importPath, err)
+	}
+	// Quick JSON extraction: find "Export": "…"
+	const key = `"Export": "`
+	i := bytes.Index(out, []byte(key))
+	if i < 0 {
+		return "", fmt.Errorf("go list %s: no Export field", importPath)
+	}
+	start := i + len(key)
+	end := bytes.IndexByte(out[start:], '"')
+	if end < 0 {
+		return "", fmt.Errorf("go list %s: malformed Export field", importPath)
+	}
+	return string(out[start : start+end]), nil
+}
+
+// resolveExternalGOOBJ resolves a set of external symbol references into
+// (package index, symbol index) pairs suitable for GOOBJ emission.
+//
+// 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.
+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)
+
+	// Assign package indices in sorted order for determinism.
+	packages := sortedPkgRefs(refs)
+
+	for i, pkg := range packages {
+		pkgIdx[pkg.path] = i
+		exp, err := exportPath(pkg.path)
+		if err != nil {
+			return nil, nil, err
+		}
+		data, err := os.ReadFile(exp)
+		if err != nil {
+			return nil, nil, err
+		}
+		gobj, err := extractGOOBJ(data)
+		if err != nil {
+			return nil, nil, fmt.Errorf("%s: %w", pkg.path, err)
+		}
+		for _, name := range pkg.syms {
+			idx := gobj.findSymbol(pkg.path, name)
+			if idx < 0 {
+				return nil, nil, fmt.Errorf("symbol %s·%s not found in export data of %s", pkg.path, name, pkg.path)
+			}
+			symIdx[pkg.path+"·"+name] = idx
+		}
+	}
+	return pkgIdx, symIdx, nil
+}
+
+type pkgRef struct {
+	path string
+	syms []string
+}
+
+func sortedPkgRefs(refs map[string][]string) []pkgRef {
+	var pkgs []pkgRef
+	for pkg, syms := range refs {
+		pkgs = append(pkgs, pkgRef{pkg, syms})
+	}
+	// Simple insertion sort — the list is tiny (usually 1–3 packages).
+	for i := 1; i < len(pkgs); i++ {
+		for j := i; j > 0 && pkgs[j-1].path > pkgs[j].path; j-- {
+			pkgs[j-1], pkgs[j] = pkgs[j], pkgs[j-1]
+		}
+	}
+	return pkgs
+}
+
+// extractGOOBJ finds the GOOBJ data in an ar archive and returns a parsed
+// goobjFile.  The archive member _go_.o contains the "go object …\n!\n"
+// preamble followed by the GOOBJ payload; __.PKGDEF is the compiler export
+// data (type information) and is not the GOOBJ object.
+func extractGOOBJ(data []byte) (*goobjFile, error) {
+	if len(data) < 8 || string(data[:8]) != "!<arch>\n" {
+		return nil, fmt.Errorf("not an ar archive")
+	}
+	pos := 8
+	for pos+60 <= len(data) {
+		hdr := data[pos : pos+60]
+		pos += 60
+
+		// Parse ar header fields.
+		name := strings.TrimRight(string(hdr[:16]), " /")
+		size := parseArDecimal(hdr[48:58])
+		if size < 0 {
+			return nil, fmt.Errorf("invalid ar header: bad size")
+		}
+		if pos+size > len(data) {
+			return nil, fmt.Errorf("ar entry %q extends past end of file", name)
+		}
+		body := data[pos : pos+size]
+		pos += size
+		// ar pads to even bytes.
+		if pos%2 != 0 {
+			pos++
+		}
+
+		if name == "_go_.o" {
+			return parseGOOBJ(body)
+		}
+	}
+	return nil, fmt.Errorf("archive contains no _go_.o member")
+}
+
+// parseArDecimal parses a decimal number from a space-padded field.
+func parseArDecimal(b []byte) int {
+	v := 0
+	for _, c := range b {
+		if c == ' ' {
+			continue
+		}
+		if c < '0' || c > '9' {
+			return -1
+		}
+		v = v*10 + int(c-'0')
+	}
+	return v
+}
+
+// goobjFile is a parsed GOOBJ file: the string table and the symbol-definition
+// block.
+type goobjFile struct {
+	strTab []byte // string table, at headerSize + n
+	symdef []byte // blkSymdef 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.
+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.
+func (f *goobjFile) findSymbol(pkg, name string) int {
+	qualified := pkg + "." + name
+	syms := f.symbols()
+	for i, s := range syms {
+		if s == qualified {
+			return i
+		}
+	}
+	// Try bare name (for non-package definitions).
+	for i, s := range syms {
+		if s == name {
+			return i
+		}
+	}
+	return -1
+}
+
+// defNames returns names from blkSymdef only.
+func (f *goobjFile) defNames() []string {
+	return f.readSymNames(f.symdef)
+}
+
+// npdefNames returns names from blkNonpkgdef.
+func (f *goobjFile) npdefNames() []string {
+	return f.readSymNames(f.npdef)
+}
+
+// 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
+	if len(block) < recSize {
+		return nil
+	}
+	n := len(block) / recSize
+	names := make([]string, 0, n)
+	for i := 0; i < n; i++ {
+		rec := block[i*recSize : (i+1)*recSize]
+		nameLen := binary.LittleEndian.Uint32(rec[0:4])
+		nameOff := binary.LittleEndian.Uint32(rec[4:8])
+		// nameOff is an absolute offset into the GOOBJ payload.  The string
+		// table we have starts at goobjHeaderSize, so we subtract that.
+		if nameOff < goobjHeaderSize {
+			continue
+		}
+		relOff := nameOff - goobjHeaderSize
+		if relOff >= uint32(len(f.strTab)) || relOff+nameLen > uint32(len(f.strTab)) {
+			continue
+		}
+		names = append(names, string(f.strTab[relOff:relOff+nameLen]))
+	}
+	return names
+}
+
+const goobjHeaderSize = 8 + 8 + 4 + 4*(blkEnd+1) // magic + fingerprint + flags + 19 block offsets
+
+// parseGOOBJ parses a raw GOOBJ payload (the data after the "\n!\n" preamble).
+func parseGOOBJ(data []byte) (*goobjFile, error) {
+	// Find the "\n!\n" separator.
+	sep := []byte("\n!\n")
+	i := bytes.Index(data, sep)
+	if i < 0 {
+		// Maybe the data has no preamble (e.g. a raw .o file).
+		i = -3 // treat as if preamble starts before the data
+	}
+	payload := data[i+len(sep):]
+
+	if len(payload) < goobjHeaderSize {
+		return nil, fmt.Errorf("GOOBJ payload too short (%d bytes)", len(payload))
+	}
+	if string(payload[:8]) != goobjMagic {
+		return nil, fmt.Errorf("bad GOOBJ magic: %q", payload[:8])
+	}
+
+	// Read block offsets.  The header layout is:
+	//   [0:8]   magic
+	//   [8:16]  fingerprint
+	//   [16:20] flags
+	//   [20:96] 19 × uint32 offsets
+	var offs [blkEnd + 1]uint32
+	for i := 0; i <= blkEnd; i++ {
+		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),
+	}
+	return f, nil
+}
+
+// blockSlice extracts a block from the payload using its offset pair.
+func blockSlice(payload []byte, offs [blkEnd + 1]uint32, start, end int) []byte {
+	if start < 0 || end > blkEnd || offs[end] < offs[start] {
+		return nil
+	}
+	beg := offs[start]
+	fin := offs[end]
+	if int(fin) > len(payload) || int(beg) > int(fin) {
+		return nil
+	}
+	return payload[beg:fin]
+}
+
+// resolveExternalSymbols is the high-level entry point for GOOBJ emission.
+// Given a list of external symbol names (e.g. ["runtime·morestack",
+// "runtime·g0"]), it returns the package-index table entries and a map from
+// full symbol name to GOOBJ {pkgIdx, symIdx}.
+//
+// The package table entries should be written into blkPkgIdx, and the
+// returned indices should replace pkgIdxSelf / placeholder values in the
+// relocation records.
+func resolveExternalSymbols(externals []string) (pkgTable []string, pkgIdxMap map[string]int, symIdxMap map[string]int, err error) {
+	// Group references by package.
+	refs := make(map[string]map[string]bool)
+	for _, full := range externals {
+		pkg, name := splitQualified(full)
+		if refs[pkg] == nil {
+			refs[pkg] = make(map[string]bool)
+		}
+		refs[pkg][name] = true
+	}
+
+	// Convert maps to slices.
+	r := make(map[string][]string, len(refs))
+	for pkg, names := range refs {
+		for name := range names {
+			r[pkg] = append(r[pkg], name)
+		}
+	}
+
+	pkgIdx1, symIdx1, err := resolveExternalGOOBJ(r)
+	if err != nil {
+		return nil, nil, nil, err
+	}
+
+	// Build the package table in pkgIdx order.
+	pkgTable = make([]string, len(pkgIdx1))
+	for pkg, idx := range pkgIdx1 {
+		pkgTable[idx] = 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).
+func splitQualified(full string) (pkg, name string) {
+	if idx := strings.IndexByte(full, '\u00b7'); idx >= 0 {
+		return full[:idx], full[idx+len("\u00b7"):]
+	}
+	if idx := strings.IndexByte(full, '.'); idx >= 0 {
+		return full[:idx], full[idx+1:]
+	}
+	return "", full
+}

asm/goobj_resolve_test.go

@@ -0,0 +1,66 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+package asm
+
+import (
+	"os"
+	"os/exec"
+	"testing"
+)
+
+// TestReadRuntimeSymbols verifies the GOOBJ reader can extract and find
+// symbols from the runtime package's compiled archive.
+func TestReadRuntimeSymbols(t *testing.T) {
+	exp, err := exportPath("runtime")
+	if err != nil {
+		t.Skipf("cannot find runtime export: %v (need Go toolchain)", err)
+	}
+	data, err := os.ReadFile(exp)
+	if err != nil {
+		t.Skipf("cannot read runtime export: %v", err)
+	}
+	gobj, err := extractGOOBJ(data)
+	if err != nil {
+		t.Fatalf("extractGOOBJ: %v", err)
+	}
+
+	t.Logf("runtime: %d symbols", len(gobj.symbols()))
+
+	// Verify we can find well-known runtime symbols.
+	for _, tc := range []struct{ pkg, name string }{
+		{"runtime", "g0"},
+		{"runtime", "morestack"},
+		{"runtime", "newstack"},
+	} {
+		idx := gobj.findSymbol(tc.pkg, tc.name)
+		if idx < 0 {
+			t.Errorf("findSymbol(%q, %q) = -1", tc.pkg, tc.name)
+		} else {
+			t.Logf("findSymbol(%q, %q) = %d", tc.pkg, tc.name, idx)
+		}
+	}
+}
+
+// TestResolveExternalSymbols verifies end-to-end resolution of external
+// symbol references.
+func TestResolveExternalSymbols(t *testing.T) {
+	if _, err := exec.LookPath("go"); err != nil {
+		t.Skip("go toolchain not available")
+	}
+
+	refs := map[string][]string{
+		"runtime": {"g0"},
+	}
+	pkgIdx, symIdx, err := resolveExternalGOOBJ(refs)
+	if err != nil {
+		t.Fatalf("resolveExternalGOOBJ: %v", err)
+	}
+	if len(pkgIdx) != 1 || pkgIdx["runtime"] != 0 {
+		t.Errorf("pkgIdx = %v, want runtime→0", pkgIdx)
+	}
+	if _, ok := symIdx["runtime·g0"]; !ok {
+		t.Errorf("symIdx missing runtime·g0, got %v", symIdx)
+	}
+	t.Logf("runtime·g0 → SymIdx=%d", symIdx["runtime·g0"])
+}

asm/goobjriscv.go

@@ -113,16 +113,47 @@ func (img *Image) GOObjectRISCV(pkgPath, srcPath string) ([]byte, error) {
 		})
 	}
 
+	// Resolve external symbol references (cross-package).
+	var extPkgTable []string
+	var extPkgIdx map[string]int
+	var extSymIdx map[string]int
+	if len(img.Externals) > 0 {
+		var err error
+		extPkgTable, extPkgIdx, extSymIdx, err = resolveExternalSymbols(img.Externals)
+		if err != nil {
+			return nil, fmt.Errorf("GOOBJ emission: resolving external symbols: %w", err)
+		}
+	}
+
 	// Relocations, per defined symbol in definition order (package defs,
-	// then non-package defs).  Only file-local GLOBL references resolve;
-	// external symbols need the import machinery of a later increment.
+	// then non-package defs).
 	nsyms := len(defs) + len(nps)
 	symRelocs := make([][]byte, nsyms) // flat 23-byte records
 	for i, fn := range img.Funcs {
 		si := len(defs) + fnNpIdx[i]
 		for _, r := range fn.Relocs {
 			if r.External {
-				return nil, fmt.Errorf("GOOBJ emission: external symbol %q is not supported yet", r.Name)
+				pkg, name := splitQualified(r.Name)
+				if pkg == "" {
+					return nil, fmt.Errorf("GOOBJ emission: external symbol %q has no package prefix", r.Name)
+				}
+				pIdx, ok := extPkgIdx[pkg]
+				if !ok {
+					return nil, fmt.Errorf("GOOBJ emission: package %q not resolved", pkg)
+				}
+				sIdx, ok := extSymIdx[pkg+"·"+name]
+				if !ok {
+					return nil, fmt.Errorf("GOOBJ emission: symbol %s·%s not resolved", pkg, name)
+				}
+				var rec [23]byte
+				binary.LittleEndian.PutUint32(rec[0:], uint32(int32(r.Off)))
+				rec[4] = 4 // field width
+				binary.LittleEndian.PutUint16(rec[5:], relocRISCVPcrelHi20)
+				binary.LittleEndian.PutUint64(rec[7:], uint64(r.Addend))
+				binary.LittleEndian.PutUint32(rec[15:], uint32(pIdx))
+				binary.LittleEndian.PutUint32(rec[19:], uint32(sIdx))
+				symRelocs[si] = append(symRelocs[si], rec[:]...)
+				continue
 			}
 			di, ok := defIdx[r.Name]
 			if !ok {
@@ -179,6 +210,20 @@ func (img *Image) GOObjectRISCV(pkgPath, srcPath string) ([]byte, error) {
 	for _, s := range nps {
 		addStr(s.sym.name)
 	}
+	for _, pkg := range extPkgTable {
+		addStr(pkg)
+	}
+
+	// Package index block: index 0 is the dummy invalid package, followed by
+	// external packages.
+	var pkgIdxBlk bytes.Buffer
+	pkgIdxBlk.Write(binary.LittleEndian.AppendUint32(nil, 0)) // len("")
+	pkgIdxBlk.Write(binary.LittleEndian.AppendUint32(nil, 0)) // offset of ""
+	for _, pkg := range extPkgTable {
+		off := strOff[pkg]
+		pkgIdxBlk.Write(binary.LittleEndian.AppendUint32(nil, uint32(len(pkg))))
+		pkgIdxBlk.Write(binary.LittleEndian.AppendUint32(nil, off))
+	}
 
 	// Symbol definition records (21 bytes each).
 	var symdef, nonpkgdef []byte
@@ -258,24 +303,24 @@ func (img *Image) GOObjectRISCV(pkgPath, srcPath string) ([]byte, error) {
 	// Blocks in order: autolib, pkgidx, file, symdef, hashed64def, hasheddef,
 	// nonpkgdef, nonpkgref, refflags, hash64, hash, relocidx, auxidx, dataidx,
 	// reloc, aux, data, refname.
-	writeBlock(nil)       // autolib
-	writeBlock(nil)       // pkgidx
-	writeBlock(fileBlk)   // file
-	writeBlock(symdef)    // symdef
-	writeBlock(nil)       // hashed64def
-	writeBlock(nil)       // hasheddef
-	writeBlock(nonpkgdef) // nonpkgdef
-	writeBlock(nil)       // nonpkgref
-	writeBlock(nil)       // refflags
-	writeBlock(nil)       // hash64
-	writeBlock(nil)       // hash
-	writeBlock(relocIdx)  // relocidx
-	writeBlock(auxIdx)    // auxidx
-	writeBlock(dataIdx)   // dataidx
-	writeBlock(relocBlk)  // reloc
-	writeBlock(auxBlk)    // aux
-	writeBlock(dataBlk)   // data
-	writeBlock(nil)       // refname
+	writeBlock(nil)               // autolib
+	writeBlock(pkgIdxBlk.Bytes()) // pkgidx
+	writeBlock(fileBlk)           // file
+	writeBlock(symdef)            // symdef
+	writeBlock(nil)               // hashed64def
+	writeBlock(nil)               // hasheddef
+	writeBlock(nonpkgdef)         // nonpkgdef
+	writeBlock(nil)               // nonpkgref
+	writeBlock(nil)               // refflags
+	writeBlock(nil)               // hash64
+	writeBlock(nil)               // hash
+	writeBlock(relocIdx)          // relocidx
+	writeBlock(auxIdx)            // auxidx
+	writeBlock(dataIdx)           // dataidx
+	writeBlock(relocBlk)          // reloc
+	writeBlock(auxBlk)            // aux
+	writeBlock(dataBlk)           // data
+	writeBlock(nil)               // refname
 
 	// Fill in the block offsets.
 	le := binary.LittleEndian