Files
gasm-sdk/asm/goobj_test.go
T

514 lines
16 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
// SPDX-License-Identifier: BSD-3-Clause
package asm
import (
"bytes"
"encoding/binary"
"os"
"os/exec"
"path/filepath"
"strings"
"testing"
"sourcedock.dev/petrbalvin/gasm-devkit/parser"
)
// goobjView is a minimal parsed view of a GOOBJ payload, enough to check
// the emitter's output block by block.
type goobjView struct {
t *testing.T
b []byte
offs [blkEnd + 1]uint32
strOff uint32
}
func openGoobj(t *testing.T, data []byte) *goobjView {
t.Helper()
i := bytes.Index(data, []byte(goobjMagic))
if i < 0 {
t.Fatal("no GOOBJ magic in output")
}
v := &goobjView{t: t, b: data[i:], strOff: uint32(i + 96)}
for j := 0; j <= blkEnd; j++ {
v.offs[j] = binary.LittleEndian.Uint32(v.b[20+4*j:])
}
return v
}
func (v *goobjView) blk(i int) []byte { return v.b[v.offs[i]:v.offs[i+1]] }
func (v *goobjView) str(off, ln uint32) string {
return string(v.b[off : off+ln])
}
type goobjSymView struct {
name string
abi uint16
typ uint8
flag uint8
flag2 uint8
size uint32
align uint32
}
func (v *goobjView) syms(i int) []goobjSymView {
var out []goobjSymView
for x := v.blk(i); len(x) >= 21; x = x[21:] {
le := binary.LittleEndian
out = append(out, goobjSymView{
name: v.str(le.Uint32(x[4:]), le.Uint32(x[0:])),
abi: le.Uint16(x[8:]),
typ: x[10],
flag: x[11],
flag2: x[12],
size: le.Uint32(x[13:]),
align: le.Uint32(x[17:]),
})
}
return out
}
// TestGOObjectStructure checks the emitted object's blocks against the
// ground truth captured from go tool asm: the symbol tables, the FuncInfo
// contents, the pc-value tables, the relocation and the aux wiring.
func TestGOObjectStructure(t *testing.T) {
f, errs := parser.Parse("t_amd64.s", `
#include "textflag.h"
TEXT ·addq(SB), NOSPLIT, $0-24
MOVQ a+0(FP), AX
MOVQ b+8(FP), CX
ADDQ CX, AX
MOVQ AX, ret+16(FP)
RET
TEXT ·loadmask(SB), NOSPLIT, $0-8
VMOVDQU mask<>(SB), X0
VPMOVMSKB X0, AX
MOVQ AX, ret+0(FP)
RET
GLOBL mask<>(SB), RODATA, $16
DATA mask<>+0(SB)/8, $0x0807060504030201
DATA mask<>+8(SB)/8, $0x800f0e0d0c0b0a09
`)
if len(errs) > 0 {
t.Fatalf("parse: %v", errs)
}
img, err := AssembleFile(f)
if err != nil {
t.Fatalf("AssembleFile: %v", err)
}
obj, err := img.GOObject("testpkg", "t_amd64.s")
if err != nil {
t.Fatalf("GOObject: %v", err)
}
v := openGoobj(t, obj)
if flags := binary.LittleEndian.Uint32(v.b[16:]); flags != 4 {
t.Errorf("flags = %#x, want ObjFlagFromAssembly (4)", flags)
}
// Package defs: the static GLOBL, then per function the FuncInfo and the
// two DWARF symbols (debug_line program, subprogram DIE).
defs := v.syms(blkSymdef)
if len(defs) != 7 {
t.Fatalf("symdefs = %d, want 7", len(defs))
}
if defs[0].name != "mask" || defs[0].abi != 0xffff || defs[0].typ != kindSRODATA || defs[0].size != 16 || defs[0].flag2 != symFlag2Link {
t.Errorf("mask symbol = %+v", defs[0])
}
if defs[1].name != "" || defs[1].typ != kindSDATA || defs[1].size != 28 {
t.Errorf("addq funcinfo symbol = %+v", defs[1])
}
if defs[2].name != "" || defs[2].typ != kindSDWARFLINES || defs[2].size == 0 {
t.Errorf("addq lines symbol = %+v", defs[2])
}
if defs[3].name != "" || defs[3].typ != kindSDWARFFCN || defs[3].size == 0 {
t.Errorf("addq DIE symbol = %+v", defs[3])
}
if defs[4].name != "" || defs[4].typ != kindSDATA || defs[4].size != 28 {
t.Errorf("loadmask funcinfo symbol = %+v", defs[4])
}
// Non-package defs: four pc tables and the function, per function.
nps := v.syms(blkNonpkgdef)
if len(nps) != 10 {
t.Fatalf("nonpkgdefs = %d, want 10", len(nps))
}
fn := nps[4]
if fn.name != "testpkg.addq" || fn.typ != kindSTEXT || fn.flag != symFlagNoSplit || fn.size != 19 {
t.Errorf("addq symbol = %+v", fn)
}
for i, s := range []int{0, 1, 2, 3, 5, 6, 7, 8} {
if nps[s].typ != kindSRODATA || nps[s].align != 1 || nps[s].name != "" {
t.Errorf("pc table %d = %+v", i, nps[s])
}
}
// FuncInfo: args 24, FuncFlag Asm, one file, no inline tree.
le := binary.LittleEndian
data := v.blk(blkData)
didx := v.blk(blkDataIdx)
fi := data[16:44]
if le.Uint32(fi[0:]) != 24 || le.Uint32(fi[4:]) != 0 || fi[8] != 0 || fi[9] != funcFlagAsm ||
le.Uint32(fi[16:]) != 1 || le.Uint32(fi[20:]) != 0 || le.Uint32(fi[24:]) != 0 {
t.Errorf("funcinfo bytes %x", fi)
}
// The pc-value tables of addq (non-package indices 0–3, so global
// indices 7–10): pcsp a flat zero over the whole function, pcinline a
// flat -1, both with the pc delta in MinLC (1) units.
pcsp := data[le.Uint32(didx[4*7:]):]
if got := pcsp[:3]; !bytes.Equal(got, []byte{0x02, 19, 0x00}) {
t.Errorf("pcsp = %x, want 021300", got)
}
pcinl := data[le.Uint32(didx[4*10:]):]
if got := pcinl[:3]; !bytes.Equal(got, []byte{0x00, 19, 0x00}) {
t.Errorf("pcinline = %x, want 001300", got)
}
// Relocations: the four DWARF address references (two per function, in
// definition order), then the loadmask code's R_PCREL against the
// GLOBL, with the field in the function code left zero. The loadmask
// code's offset comes from the data index (7 defs + 9 non-package).
relocs := v.blk(blkReloc)
if len(relocs) != 5*23 {
t.Fatalf("relocs = %d bytes, want 5 entries", len(relocs))
}
// addq's DWARF references (defs 2 and 3) against the function, which
// is non-package index 4.
lr := relocs[:23]
if int32(le.Uint32(lr[0:])) != 3 || lr[4] != 8 || le.Uint16(lr[5:]) != relocAddr ||
le.Uint32(lr[15:]) != pkgIdxNone || le.Uint32(lr[19:]) != 4 {
t.Errorf("addq lines reloc = %x", lr)
}
dr := relocs[23:46]
if dr[4] != 4 || le.Uint16(dr[5:]) != relocDWTXTADDRU4() ||
le.Uint32(dr[15:]) != pkgIdxNone || le.Uint32(dr[19:]) != 4 {
t.Errorf("addq DIE reloc = %x", dr)
}
cr := relocs[4*23:]
off := int32(le.Uint32(cr[0:]))
if off != 4 || cr[4] != 4 || le.Uint16(cr[5:]) != relocPCRel ||
le.Uint64(cr[7:]) != 0 || le.Uint32(cr[15:]) != pkgIdxSelf || le.Uint32(cr[19:]) != 0 {
t.Errorf("loadmask reloc = %x", cr)
}
lm := le.Uint32(didx[4*16:])
code := data[lm : lm+18]
if !bytes.Equal(code[4:8], []byte{0, 0, 0, 0}) {
t.Errorf("relocated field = %x, want zeroed", code[4:8])
}
// Aux wiring: FuncInfo, the two DWARF symbols (package symbols), then
// the four pc tables (non-package symbols).
auxs := v.blk(blkAux)
if len(auxs) != 2*7*9 {
t.Fatalf("aux = %d bytes, want 14 entries", len(auxs))
}
wantAux := []struct {
typ uint8
pkg uint32
idx uint32
}{
{auxFuncInfo, pkgIdxSelf, 1},
{auxDwarfInfo, pkgIdxSelf, 3},
{auxDwarfLines, pkgIdxSelf, 2},
{auxPcsp, pkgIdxNone, 0},
{auxPcfile, pkgIdxNone, 1},
{auxPcline, pkgIdxNone, 2},
{auxPcinline, pkgIdxNone, 3},
{auxFuncInfo, pkgIdxSelf, 4},
{auxDwarfInfo, pkgIdxSelf, 6},
{auxDwarfLines, pkgIdxSelf, 5},
{auxPcsp, pkgIdxNone, 5},
{auxPcfile, pkgIdxNone, 6},
{auxPcline, pkgIdxNone, 7},
{auxPcinline, pkgIdxNone, 8},
}
for i, w := range wantAux {
e := auxs[i*9:]
if e[0] != w.typ || le.Uint32(e[1:]) != w.pkg || le.Uint32(e[5:]) != w.idx {
t.Errorf("aux[%d] = {%d,%d,%d}, want {%d,%d,%d}", i, e[0], le.Uint32(e[1:]), le.Uint32(e[5:]), w.typ, w.pkg, w.idx)
}
}
}
// decodePCValues decodes a pc-value table into (pc, value) steps. The
// table ends with a final unsigned pc delta covering the rest of the
// function, followed by a zero byte that carries no value delta.
func decodePCValues(b []byte) (pcs, vals []int64) {
val, n := binary.Varint(b)
b = b[n:]
val-- // the first delta is against the implicit -1
var pc int64
pcs = append(pcs, pc)
vals = append(vals, val)
for {
pcd, n := binary.Uvarint(b)
b = b[n:]
if pcd == 0 { // zero pc delta terminates the table
break
}
pc += int64(pcd)
if len(b) == 1 && b[0] == 0 { // final coverage, no value change
break
}
vd, n := binary.Varint(b)
b = b[n:]
val += vd
pcs = append(pcs, pc)
vals = append(vals, val)
}
return pcs, vals
}
// TestGOObjectPcspFrame checks the pcsp table of a frame-pointer function:
// the prologue raises the stack delta to 8+frame, the RET's epilogue
// restores it to zero.
func TestGOObjectPcspFrame(t *testing.T) {
f, errs := parser.Parse("frame_amd64.s", `
#include "textflag.h"
TEXT ·framed(SB), NOSPLIT, $8-0
MOVQ BP, AX
RET
`)
if len(errs) > 0 {
t.Fatalf("parse: %v", errs)
}
img, err := AssembleFile(f)
if err != nil {
t.Fatalf("AssembleFile: %v", err)
}
fn := img.Funcs[0]
pcs, vals := decodePCValues(pcspTable(fn, 1))
// Prologue: PUSHQ BP (1 byte, +8), MOVQ SP, BP (3 bytes, no change),
// SUBQ $8, SP (4 bytes, +16 in total); the RET's epilogue unwinds
// ADDQ $8, SP (+8) then POPQ BP (0).
wantPCs := []int64{0, 1, 8}
wantVals := []int64{0, 8, 16}
if len(pcs) < len(wantPCs) {
t.Fatalf("pcsp pcs = %v vals = %v", pcs, vals)
}
for i := range wantPCs {
if pcs[i] != wantPCs[i] || vals[i] != wantVals[i] {
t.Errorf("pcsp[%d] = (%d,%d), want (%d,%d) — all: %v %v", i, pcs[i], vals[i], wantPCs[i], wantVals[i], pcs, vals)
}
}
// The last two steps unwind the epilogue to zero.
n := len(pcs)
if vals[n-1] != 0 || vals[n-2] != 8 {
t.Errorf("epilogue steps = %v %v, want …8, 0", pcs, vals)
}
// The table covers the whole function.
if last := pcs[n-1]; last >= int64(fn.Size) {
t.Errorf("last pc %d beyond function size %d", last, fn.Size)
}
}
// TestGOObjectExternalRejected checks that a reference to a symbol no GLOBL
// defines is reported: GOOBJ emission resolves only file-local symbols so
// far.
func TestGOObjectExternalRejected(t *testing.T) {
f, errs := parser.Parse("ext_amd64.s", `
#include "textflag.h"
TEXT ·useext(SB), NOSPLIT, $0-8
MOVQ elsewhere(SB), AX
MOVQ AX, ret+0(FP)
RET
`)
if len(errs) > 0 {
t.Fatalf("parse: %v", errs)
}
img, err := AssembleFile(f)
if err != nil {
t.Fatalf("AssembleFile: %v", err)
}
if _, err := img.GOObject("p", "ext_amd64.s"); err == nil || !strings.Contains(err.Error(), "external") {
t.Errorf("error = %v, want an external-symbol error", err)
}
}
// TestGOObjectLinkAndRun is the end-to-end check: assemble the test
// functions to a GOOBJ, swap it into a go build in place of the toolchain's
// assembly object, link, and run — the output must match the baseline
// binary the Go assembler produced. Skipped when no Go toolchain is
// available.
func TestGOObjectLinkAndRun(t *testing.T) {
goBin, err := exec.LookPath("go")
if err != nil {
t.Skip("no Go toolchain available")
}
dir := t.TempDir()
const asmSrc = `
#include "textflag.h"
TEXT ·addq(SB), NOSPLIT, $0-24
MOVQ a+0(FP), AX
MOVQ b+8(FP), CX
ADDQ CX, AX
MOVQ AX, ret+16(FP)
RET
TEXT ·loadmask(SB), NOSPLIT, $0-8
VMOVDQU mask<>(SB), X0
VPMOVMSKB X0, AX
MOVQ AX, ret+0(FP)
RET
GLOBL mask<>(SB), RODATA, $16
DATA mask<>+0(SB)/8, $0x0807060504030201
DATA mask<>+8(SB)/8, $0x800f0e0d0c0b0a09
`
const mainSrc = `package main
func addq(a, b int64) int64
func loadmask() int64
func main() {
println(addq(41, 1))
println(loadmask())
}
`
if err := os.WriteFile(filepath.Join(dir, "main_amd64.s"), []byte(asmSrc), 0o644); err != nil {
t.Fatal(err)
}
if err := os.WriteFile(filepath.Join(dir, "main.go"), []byte(mainSrc), 0o644); err != nil {
t.Fatal(err)
}
if err := os.WriteFile(filepath.Join(dir, "go.mod"), []byte("module goobjtest\n\ngo 1.27\n"), 0o644); err != nil {
t.Fatal(err)
}
// Baseline build with the toolchain's assembler; keep the work
// directory and the commands the build used.
cmd := exec.Command(goBin, "build", "-x", "-work", "-o", "app", ".")
cmd.Dir = dir
buildLog, err := cmd.CombinedOutput()
if err != nil {
t.Fatalf("baseline build: %v\n%s", err, buildLog)
}
var work string
var asmObj, pkgArch, linkLine string
for line := range strings.SplitSeq(string(buildLog), "\n") {
switch {
case strings.HasPrefix(line, "WORK="):
work = strings.TrimPrefix(line, "WORK=")
case strings.Contains(line, "/asm ") && strings.Contains(line, "-o ") && strings.Contains(line, "main_amd64.s") && !strings.Contains(line, "-gensymabis"):
asmObj = fieldAfter(line, "-o")
case strings.Contains(line, "pack r") && strings.Contains(line, "_pkg_.a"):
pkgArch = strings.TrimSpace(strings.SplitN(line, "pack r", 2)[1])
pkgArch = strings.Fields(strings.SplitN(pkgArch, "#", 2)[0])[0]
case strings.Contains(line, "/link ") && strings.Contains(line, "-importcfg"):
linkLine = line
}
}
if work == "" || asmObj == "" || pkgArch == "" || linkLine == "" {
t.Fatalf("could not locate the build steps:\n%s", buildLog)
}
asmObj = strings.ReplaceAll(asmObj, "$WORK", work)
pkgArch = strings.ReplaceAll(pkgArch, "$WORK", work)
// The baseline's answer.
baseOut, err := exec.Command(filepath.Join(dir, "app")).CombinedOutput()
if err != nil {
t.Fatalf("run baseline: %v\n%s", err, baseOut)
}
// Assemble the same source with gasm and swap the object in.
pf, perrs := parser.Parse(filepath.Join(dir, "main_amd64.s"), asmSrc)
if len(perrs) > 0 {
t.Fatalf("parse: %v", perrs)
}
img, err := AssembleFile(pf)
if err != nil {
t.Fatalf("AssembleFile: %v", err)
}
obj, err := img.GOObject("main", filepath.Join(dir, "main_amd64.s"))
if err != nil {
t.Fatalf("GOObject: %v", err)
}
// Rebuild the package archive with our object in place of the
// toolchain's (go tool pack has no replace-in-place that dedupes, so
// extract, substitute and repack). The archive member holding the
// assembler's output is named after the asm object file, e.g.
// main_amd64.o.
extract := exec.Command(goBin, "tool", "pack", "x", pkgArch)
membersDir := filepath.Join(dir, "members")
if err := os.MkdirAll(membersDir, 0o755); err != nil {
t.Fatal(err)
}
extract.Dir = membersDir
if out, err := extract.CombinedOutput(); err != nil {
t.Fatalf("pack x: %v\n%s", err, out)
}
member := filepath.Join(membersDir, filepath.Base(asmObj))
if err := os.Chmod(member, 0o644); err != nil {
t.Fatal(err)
}
if err := os.WriteFile(member, obj, 0o644); err != nil {
t.Fatal(err)
}
listCmd := exec.Command(goBin, "tool", "pack", "t", pkgArch)
listOut, err := listCmd.CombinedOutput()
if err != nil {
t.Fatalf("pack t: %v\n%s", err, listOut)
}
newArch := filepath.Join(dir, "pkg.a")
args := []string{"tool", "pack", "c", newArch}
seen := map[string]bool{}
for m := range strings.FieldsSeq(string(listOut)) {
if seen[m] {
continue
}
seen[m] = true
if err := os.Chmod(filepath.Join(membersDir, m), 0o644); err != nil {
t.Fatal(err)
}
args = append(args, filepath.Join(membersDir, m))
}
pack := exec.Command(goBin, args...)
pack.Dir = membersDir
if out, err := pack.CombinedOutput(); err != nil {
t.Fatalf("pack c: %v\n%s", err, out)
}
// Link with our archive. The link line carries a GOROOT assignment
// and $WORK placeholders; run it through the shell with the
// GOEXPERIMENT the toolchain expects (the linker compares the object
// header against its own, experiments included).
goExp, _ := exec.Command(goBin, "env", "GOEXPERIMENT").Output()
linkLine = strings.ReplaceAll(linkLine, "$WORK", work)
linkLine = strings.ReplaceAll(linkLine, filepath.Join(work, "b001", "_pkg_.a"), newArch)
linkLine = strings.ReplaceAll(linkLine, filepath.Join(work, "b001", "exe", "a.out"), filepath.Join(dir, "app2"))
link := exec.Command("sh", "-c", linkLine)
link.Dir = dir
link.Env = append(os.Environ(), "GOEXPERIMENT="+strings.TrimSpace(string(goExp)))
if out, err := link.CombinedOutput(); err != nil {
t.Fatalf("link with gasm object: %v\n%s", err, out)
}
got, err := exec.Command(filepath.Join(dir, "app2")).CombinedOutput()
if err != nil {
t.Fatalf("run gasm-linked binary: %v\n%s", err, got)
}
if !bytes.Equal(got, baseOut) {
t.Errorf("gasm-linked output %q, want baseline %q", got, baseOut)
}
}
// fieldAfter returns the whitespace-delimited field following the first
// occurrence of flag in line.
func fieldAfter(line, flag string) string {
fields := strings.Fields(line)
for i, f := range fields {
if f == flag && i+1 < len(fields) {
return fields[i+1]
}
}
return ""
}