gasm-sdk/asm/elfarm64_test.go

// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
// SPDX-License-Identifier: BSD-3-Clause

package asm

import (
	"bytes"
	"debug/elf"
	"encoding/binary"
	"testing"

	"sourcedock.dev/petrbalvin/gasm-devkit/parser"
)

// TestELFAARCH64Object checks the structure of the emitted AArch64 ELF64
// relocatable object: sections, the symbol table (bindings, types, values,
// sizes) and the .rela.text relocation pair for the static-symbol load,
// parsed back with debug/elf.
func TestELFAARCH64Object(t *testing.T) {
	f, errs := parser.Parse("k_arm64.s", `
#include "textflag.h"

TEXT ·add(SB), NOSPLIT, $0-24
	MOVD a+0(FP), R4
	MOVD b+8(FP), R5
	ADD R5, R4, R4
	MOVD R4, ret+16(FP)
	RET

TEXT ·getanswer(SB), NOSPLIT, $0-8
	MOVD answer<>(SB), R4
	MOVD $answer<>(SB), R5
	MOVD R4, ret+0(FP)
	RET

GLOBL answer<>(SB), RODATA, $8
DATA answer<>+0(SB)/8, $42
`)
	if len(errs) > 0 {
		t.Fatalf("parse: %v", errs)
	}
	img, err := AssembleFileARM64(f)
	if err != nil {
		t.Fatalf("AssembleFileARM64: %v", err)
	}
	obj, err := img.ELFAARCH64Object()
	if err != nil {
		t.Fatalf("ELFAARCH64Object: %v", err)
	}
	ef, err := elf.NewFile(bytes.NewReader(obj))
	if err != nil {
		t.Fatalf("parse emitted object: %v", err)
	}
	defer ef.Close()

	if ef.Type != elf.ET_REL || ef.Machine != elf.EM_AARCH64 {
		t.Errorf("type/machine = %v/%v, want ET_REL/EM_AARCH64", ef.Type, ef.Machine)
	}

	text := ef.Section(".text")
	data := ef.Section(".data")
	if text == nil || data == nil {
		t.Fatal("missing .text or .data section")
	}
	if text.Size == 0 {
		t.Error(".text section is empty")
	}

	syms, err := ef.Symbols()
	if err != nil {
		t.Fatalf("symbols: %v", err)
	}

	foundAdd, foundGetanswer, foundAnswer := false, false, false
	for _, s := range syms {
		switch s.Name {
		case "add":
			foundAdd = true
			if elf.SymType(s.Info&0xf) != elf.STT_FUNC || elf.SymBind(s.Info>>4) != elf.STB_GLOBAL {
				t.Errorf("add: info=0x%02x, want STT_FUNC|STB_GLOBAL", s.Info)
			}
		case "getanswer":
			foundGetanswer = true
			if elf.SymType(s.Info&0xf) != elf.STT_FUNC || elf.SymBind(s.Info>>4) != elf.STB_GLOBAL {
				t.Errorf("getanswer: info=0x%02x, want STT_FUNC|STB_GLOBAL", s.Info)
			}
		case "answer":
			foundAnswer = true
			if elf.SymType(s.Info&0xf) != elf.STT_OBJECT || elf.SymBind(s.Info>>4) != elf.STB_LOCAL {
				t.Errorf("answer: info=0x%02x, want STT_OBJECT|STB_LOCAL", s.Info)
			}
		}
	}
	if !foundAdd {
		t.Error("symbol 'add' not found")
	}
	if !foundGetanswer {
		t.Error("symbol 'getanswer' not found")
	}
	if !foundAnswer {
		t.Error("symbol 'answer' not found")
	}

	// Check that .rela.text exists (getanswer has SB reference).
	relaText := ef.Section(".rela.text")
	if relaText == nil {
		t.Fatal("missing .rela.text section")
	}

	// The SB references of getanswer form two ADRP pairs: the load
	// (MOVD answer<>(SB), R4) is ADRP+LDR carrying HI21 at the ADRP and
	// LDST64_ABS_LO12_NC at the LDR word, and the address-of
	// (MOVD $answer<>(SB), R5) is ADRP+ADD carrying HI21 and
	// ADD_ABS_LO12_NC.  cmd/link's own conversion emits exactly this
	// sectoff / sectoff+4 pairing; a second HI21 at the ADD or LDR word
	// corrupts the pair.
	raw, err := relaText.Data()
	if err != nil {
		t.Fatal(err)
	}
	if len(raw)%24 != 0 || len(raw)/24 != 4 {
		t.Fatalf(".rela.text has %d bytes, want four 24-byte entries", len(raw))
	}
	wantRela := []struct {
		typ elf.R_AARCH64
		off uint64 // relative to the getanswer function start
	}{
		{elf.R_AARCH64_ADR_PREL_PG_HI21, 0},
		{elf.R_AARCH64_LDST64_ABS_LO12_NC, 4},
		{elf.R_AARCH64_ADR_PREL_PG_HI21, 8},
		{elf.R_AARCH64_ADD_ABS_LO12_NC, 12},
	}
	getanswer := byNameElf(t, ef, "getanswer")
	for i, w := range wantRela {
		e := raw[i*24 : (i+1)*24]
		off := binary.LittleEndian.Uint64(e[0:])
		info := binary.LittleEndian.Uint64(e[8:])
		typ := elf.R_AARCH64(info & 0xffffffff)
		sym := int(info >> 32)
		if typ != w.typ || off != getanswer.Value+w.off {
			t.Errorf("reloc %d: type %v off %d, want %v at %d", i, typ, off, w.typ, getanswer.Value+w.off)
		}
		if sym != 3 { // NULL, .text, .data, then the first local: answer
			t.Errorf("reloc %d: symbol index %d, want 3 (answer)", i, sym)
		}
	}
}

// byNameElf returns the symbol table entry for name from the raw .symtab,
// which carries every entry including the null and section symbols in order.
func byNameElf(t *testing.T, ef *elf.File, name string) elf.Symbol {
	t.Helper()
	syms, err := ef.Symbols()
	if err != nil {
		t.Fatalf("symbols: %v", err)
	}
	for _, s := range syms {
		if s.Name == name {
			return s
		}
	}
	t.Fatalf("symbol %q not found", name)
	return elf.Symbol{}
}

// TestELFAARCH64ObjectNoRelocations checks the ELF output when there are no
// static-symbol references (no .rela.text section).
func TestELFAARCH64ObjectNoRelocations(t *testing.T) {
	f, errs := parser.Parse("k_arm64.s", `
#include "textflag.h"

TEXT ·add(SB), NOSPLIT, $0-24
	MOVD a+0(FP), R4
	MOVD b+8(FP), R5
	ADD R5, R4, R4
	MOVD R4, ret+16(FP)
	RET
`)
	if len(errs) > 0 {
		t.Fatalf("parse: %v", errs)
	}
	img, err := AssembleFileARM64(f)
	if err != nil {
		t.Fatalf("AssembleFileARM64: %v", err)
	}
	obj, err := img.ELFAARCH64Object()
	if err != nil {
		t.Fatalf("ELFAARCH64Object: %v", err)
	}
	ef, err := elf.NewFile(bytes.NewReader(obj))
	if err != nil {
		t.Fatalf("parse emitted object: %v", err)
	}
	defer ef.Close()

	if ef.Section(".rela.text") != nil {
		t.Error("unexpected .rela.text section when there are no relocations")
	}
}