feat(asm): emit RISC-V GOOBJ with the shared emitter

Assisted-by: DeepSeek V4 Pro
2026-08-13 12:07:29 +02:00
parent 31ee8e7941
commit 9b5c878f9e
9 changed files with 358 additions and 383 deletions
@@ -0,0 +1,263 @@
+// 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"
+)
+
+// TestGOObjectRISCVStructure checks the emitted RISC-V object's relocations:
+// each AUIPC + second-instruction pair carries a single 8-byte
+// R_RISCV_PCREL_ITYPE/STYPE relocation, exactly as `go tool asm` models it
+// (rather than the ELF HI20/LO12 pair).
+func TestGOObjectRISCVStructure(t *testing.T) {
+	f, errs := parser.Parse("k_riscv64.s", `
+#include "textflag.h"
+
+TEXT ·sb(SB), NOSPLIT, $0-0
+	MOV $answer<>(SB), X10
+	MOV answer<>(SB), X11
+	MOV X12, answer<>(SB)
+	RET
+
+GLOBL answer<>(SB), RODATA, $8
+DATA answer<>+0(SB)/8, $42
+`)
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFileRISCV(f)
+	if err != nil {
+		t.Fatalf("AssembleFileRISCV: %v", err)
+	}
+	fn := img.Funcs[0]
+	if fn.Size != 26 {
+		t.Fatalf("function size = %d, want 26", fn.Size)
+	}
+	if len(fn.Relocs) != 3 {
+		t.Fatalf("relocs = %d, want 3", len(fn.Relocs))
+	}
+	wantKind := []RelocKind{RelRISCVPCRELIType, RelRISCVPCRELIType, RelRISCVPCRELSType}
+	wantOff := []int{0, 8, 16}
+	for i, r := range fn.Relocs {
+		if r.Kind != wantKind[i] || r.Off != wantOff[i] || r.After != r.Off+8 || r.Name != "answer" || r.Addend != 0 {
+			t.Errorf("reloc %d = {kind %v off %d after %d name %q addend %d}", i, r.Kind, r.Off, r.After, r.Name, r.Addend)
+		}
+	}
+
+	obj, err := img.GOObjectRISCV("testpkg", "k_riscv64.s")
+	if err != nil {
+		t.Fatalf("GOObjectRISCV: %v", err)
+	}
+	v := openGoobj(t, obj)
+
+	// Package defs: the static GLOBL, the FuncInfo, then the two DWARF
+	// symbols.
+	defs := v.syms(blkSymdef)
+	if len(defs) != 4 {
+		t.Fatalf("symdefs = %d, want 4", len(defs))
+	}
+	if defs[0].name != "answer" || defs[0].abi != 0xffff || defs[0].typ != kindSRODATA || defs[0].size != 8 {
+		t.Errorf("answer symbol = %+v", defs[0])
+	}
+	if defs[2].typ != kindSDWARFLINES || defs[3].typ != kindSDWARFFCN {
+		t.Errorf("dwarf symbols = %+v, %+v", defs[2], defs[3])
+	}
+
+	// The three code relocations, in definition order: ITYPE, ITYPE, STYPE,
+	// each 8 bytes wide against the GLOBL (package symbol 0).
+	relocIdx := v.blk(blkRelocIdx)
+	relocs := v.blk(blkReloc)
+	if len(relocs) != 5*23 {
+		t.Fatalf("relocs = %d bytes, want 5 entries", len(relocs))
+	}
+	// The function is the last non-package symbol; its relocs start after
+	// the DWARF symbols' (defs 2 and 3 each carry one).
+	le := binary.LittleEndian
+	first := int(le.Uint32(relocIdx[4*(4+4):]))
+	wantType := []uint16{relocRISCVPcrelItype, relocRISCVPcrelItype, relocRISCVPcrelStype}
+	wantOffAbs := []int{0, 8, 16}
+	for i := 0; i < 3; i++ {
+		e := relocs[(first+i)*23:]
+		if int32(le.Uint32(e[0:])) != int32(wantOffAbs[i]) || e[4] != 8 || le.Uint16(e[5:]) != wantType[i] ||
+			le.Uint32(e[15:]) != pkgIdxSelf || le.Uint32(e[19:]) != 0 {
+			t.Errorf("reloc %d = off %d size %d type %d pkg %d sym %d", i, int32(le.Uint32(e[0:])), e[4], le.Uint16(e[5:]), le.Uint32(e[15:]), le.Uint32(e[19:]))
+		}
+	}
+
+	// The function code: three AUIPC+second-instruction pairs with zero
+	// immediates, then the compressed return.
+	code := img.Code[fn.Offset : fn.Offset+fn.Size]
+	want := append(wordLE(riscvUType(riscvEnc{0x17, 0x0, 0x00}, 10, 0)), wordLE(riscvIType(riscvEnc{0x13, 0x0, 0x00}, 10, 10, 0))...)
+	want = append(want, wordLE(riscvUType(riscvEnc{0x17, 0x0, 0x00}, 11, 0))...)
+	want = append(want, wordLE(riscvIType(riscvEnc{0x03, 0x3, 0x00}, 11, 11, 0))...)
+	want = append(want, wordLE(riscvUType(riscvEnc{0x17, 0x0, 0x00}, 31, 0))...)
+	want = append(want, wordLE(riscvSType(riscvEnc{0x23, 0x3, 0x00}, 31, 12, 0))...)
+	want = append(want, 0x82, 0x80) // C.JR ra
+	if !bytes.Equal(code, want) {
+		t.Errorf("code = % x\nwant % x", code, want)
+	}
+
+	// The same bytes must survive into the object's data block intact: the
+	// linker patches only the immediate fields of the AUIPC pairs, so the
+	// opcode/register bits of every instruction must not be zeroed.
+	dataIdx := v.blk(blkDataIdx)
+	dataBlk := v.blk(blkData)
+	dOff := int(le.Uint32(dataIdx[8*4:])) // the function is the last symbol
+	emitted := dataBlk[dOff : dOff+fn.Size]
+	if !bytes.Equal(emitted, want) {
+		t.Errorf("emitted data = % x\nwant % x", emitted, want)
+	}
+}
+
+// TestGOObjectRISCVLink cross-compiles a Go program with the gasm-produced
+// object substituted into the package archive, proving cmd/link accepts the
+// emitted RISC-V GOOBJ.  The binary is not executed (no riscv64 host or
+// qemu).  Skipped when no Go toolchain is available.
+func TestGOObjectRISCVLink(t *testing.T) {
+	goBin, err := exec.LookPath("go")
+	if err != nil {
+		t.Skip("no Go toolchain available")
+	}
+	dir := t.TempDir()
+	asmSrc := `#include "textflag.h"
+TEXT ·add(SB), NOSPLIT, $0-24
+	MOV a+0(FP), X10
+	MOV b+8(FP), X11
+	ADD X11, X10, X10
+	MOV X10, ret+16(FP)
+	RET
+`
+	if err := os.WriteFile(filepath.Join(dir, "main_riscv64.s"), []byte(asmSrc), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	mainSrc := `package main
+
+func add(a, b int64) int64
+
+func main() {
+	if add(20, 22) != 42 {
+		panic("bad add")
+	}
+}
+`
+	if err := os.WriteFile(filepath.Join(dir, "main.go"), []byte(mainSrc), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(dir, "go.mod"), []byte("module rvlink\n\ngo 1.21\n"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+
+	build := exec.Command(goBin, "build", "-x", "-work", "-o", filepath.Join(dir, "prog"), ".")
+	build.Dir = dir
+	build.Env = append(os.Environ(), "GOARCH=riscv64")
+	buildLog, err := build.CombinedOutput()
+	if err != nil {
+		t.Fatalf("baseline build: %v\n%s", err, buildLog)
+	}
+	var pkgArch, work, linkLine, asmObj string
+	for _, line := range strings.Split(string(buildLog), "\n") {
+		switch {
+		case strings.HasPrefix(line, "WORK="):
+			work = strings.TrimPrefix(line, "WORK=")
+		case strings.Contains(line, "/asm ") && strings.Contains(line, "main_riscv64.s") && !strings.Contains(line, "-gensymabis"):
+			asmObj = fieldAfter(line, "-o")
+		case strings.Contains(line, "pack r") && strings.Contains(line, "_pkg_.a"):
+			pkgArch = strings.TrimSpace(strings.SplitN(line, "pack r", 2)[1])
+			pkgArch = strings.Fields(strings.SplitN(pkgArch, "#", 2)[0])[0]
+		case strings.Contains(line, "/link ") && strings.Contains(line, "-importcfg"):
+			linkLine = line
+		}
+	}
+	if pkgArch == "" || linkLine == "" || asmObj == "" {
+		t.Skip("could not locate the archive, asm output or link line in the build log")
+	}
+	pkgArch = strings.ReplaceAll(pkgArch, "$WORK", work)
+	asmMember := filepath.Base(strings.ReplaceAll(asmObj, "$WORK", work))
+
+	pf, perrs := parser.Parse(filepath.Join(dir, "main_riscv64.s"), asmSrc)
+	if len(perrs) > 0 {
+		t.Fatalf("parse: %v", perrs)
+	}
+	pimg, err := AssembleFileRISCV(pf)
+	if err != nil {
+		t.Fatalf("AssembleFileRISCV: %v", err)
+	}
+	obj, err := pimg.GOObjectRISCV("main", filepath.Join(dir, "main_riscv64.s"))
+	if err != nil {
+		t.Fatalf("GOObjectRISCV: %v", err)
+	}
+
+	membersDir := filepath.Join(dir, "members")
+	if err := os.MkdirAll(membersDir, 0o755); err != nil {
+		t.Fatal(err)
+	}
+	extract := exec.Command(goBin, "tool", "pack", "x", pkgArch)
+	extract.Dir = membersDir
+	extract.Env = append(os.Environ(), "GOARCH=riscv64")
+	if out, err := extract.CombinedOutput(); err != nil {
+		t.Fatalf("pack x: %v\n%s", err, out)
+	}
+	member := filepath.Join(membersDir, asmMember)
+	if err := os.Chmod(member, 0o644); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(member, obj, 0o644); err != nil {
+		t.Fatal(err)
+	}
+	listCmd := exec.Command(goBin, "tool", "pack", "t", pkgArch)
+	listCmd.Env = append(os.Environ(), "GOARCH=riscv64")
+	listOut, err := listCmd.CombinedOutput()
+	if err != nil {
+		t.Fatalf("pack t: %v\n%s", err, listOut)
+	}
+	newArch := filepath.Join(dir, "pkg.a")
+	args := []string{"tool", "pack", "c", newArch}
+	seen := map[string]bool{}
+	for _, m := range strings.Fields(string(listOut)) {
+		if seen[m] {
+			continue
+		}
+		seen[m] = true
+		if err := os.Chmod(filepath.Join(membersDir, m), 0o644); err != nil {
+			t.Fatal(err)
+		}
+		args = append(args, filepath.Join(membersDir, m))
+	}
+	pack := exec.Command(goBin, args...)
+	pack.Dir = membersDir
+	pack.Env = append(os.Environ(), "GOARCH=riscv64")
+	if out, err := pack.CombinedOutput(); err != nil {
+		t.Fatalf("pack c: %v\n%s", err, out)
+	}
+
+	linkLine = strings.ReplaceAll(linkLine, "$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
+	goExp, _ := exec.Command(goBin, "env", "GOEXPERIMENT").Output()
+	link.Env = append(os.Environ(), "GOEXPERIMENT="+strings.TrimSpace(string(goExp)), "GOARCH=riscv64")
+	if out, err := link.CombinedOutput(); err != nil {
+		t.Fatalf("link with gasm object: %v\n%s", err, out)
+	}
+
+	nm := exec.Command(goBin, "tool", "nm", filepath.Join(dir, "app2"))
+	nm.Env = append(os.Environ(), "GOARCH=riscv64")
+	nmOut, err := nm.CombinedOutput()
+	if err != nil {
+		t.Fatalf("nm gasm-linked binary: %v\n%s", err, nmOut)
+	}
+	if !strings.Contains(string(nmOut), "main.add") {
+		t.Errorf("main.add not found in linked binary:\n%s", nmOut)
+	}
+}