gasm-sdk/asm/elfriscv.go

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

package asm

import (
	"encoding/binary"
	"fmt"
)

// RISC-V ELF64 relocatable object emission.

const (
	emRISCV = 243 // EM_RISCV

	// RISC-V relocation types.
	rRISCV32         = 1
	rRISCVPCRELHI20  = 23 // R_RISCV_PCREL_HI20
	rRISCVPCRELLO12I = 24 // R_RISCV_PCREL_LO12_I
	rRISCVPCRELLO12S = 25 // R_RISCV_PCREL_LO12_S
)

// ELFRISCVObject returns the image as an ELF64 relocatable object file for
// RISC-V (EM_RISCV, 64-bit, little-endian).  The structure mirrors the amd64
// ELF emission: .text, .data, .symtab, .strtab and optional .rela.text.
func (img *Image) ELFRISCVObject() ([]byte, error) {
	le := binary.LittleEndian

	const (
		secText = 1
		secData = 2
	)

	// Build symbol table.
	var locals, globals []elfSym
	for _, fn := range img.Funcs {
		s := elfSym{
			name:  objectName(fn.Pkg, fn.Name),
			info:  sttFunc,
			shndx: secText,
			value: uint64(fn.Offset),
			size:  uint64(fn.Size),
		}
		if fn.Static {
			locals = append(locals, s)
		} else {
			s.info |= stbGlobal << stInfoShift
			globals = append(globals, s)
		}
	}
	for _, d := range img.DataSyms {
		s := elfSym{
			name:  objectName(d.Pkg, d.Name),
			info:  sttObject,
			shndx: secData,
			value: uint64(d.Offset),
			size:  uint64(d.Size),
		}
		if d.Static {
			locals = append(locals, s)
		} else {
			s.info |= stbGlobal << stInfoShift
			globals = append(globals, s)
		}
	}
	for _, name := range img.Externals {
		globals = append(globals, elfSym{name: name, info: stbGlobal << stInfoShift})
	}
	syms := []elfSym{
		{},
		{name: ".text", info: sttSection, shndx: secText},
		{name: ".data", info: sttSection, shndx: secData},
	}
	syms = append(syms, locals...)
	shInfo := len(syms)
	syms = append(syms, globals...)
	symIdx := map[string]int{}
	for i, s := range syms {
		symIdx[s.name] = i
	}

	// Build relocations.  Each SB reference produces a pair:
	//   AUIPC rd, 0  → R_RISCV_PCREL_HI20
	//   ADDI/LD/SD   → R_RISCV_PCREL_LO12_I or _S
	// For now we record them as individual entries; at link time
	// the linker must pair HI20 with its matching LO12.
	type elfRela struct {
		off    uint64
		typ    uint32
		sym    int
		addend int64
	}
	var relas []elfRela
	for _, fn := range img.Funcs {
		for _, r := range fn.Relocs {
			idx, ok := symIdx[r.Name]
			if !ok {
				return nil, fmt.Errorf("relocation references unknown symbol %q", r.Name)
			}
			// Determine relocation type from the relocation kind.
			typ := uint32(rRISCVPCRELHI20) // default: AUIPC
			switch r.Kind {
			case RelPCRelLO12:
				typ = rRISCVPCRELLO12I
			case RelPCRelLO12S:
				typ = rRISCVPCRELLO12S
			case RelPCRelAbs:
				typ = rRISCV32
			}
			relas = append(relas, elfRela{
				off:    uint64(fn.Offset + r.Off),
				typ:    typ,
				sym:    idx,
				addend: r.Addend - int64(r.After-r.Off),
			})
		}
	}

	// String tables.
	stNames := newElfStrtab()
	for _, s := range syms {
		stNames.add(s.name)
	}
	stSections := newElfStrtab()
	for _, n := range []string{".text", ".data", ".symtab", ".strtab", ".rela.text", ".shstrtab"} {
		stSections.add(n)
	}

	hasRela := len(relas) > 0
	nSections := 6
	if hasRela {
		nSections = 7
	}
	secSymtab, secStrtab := 3, 4
	secShstr := nSections - 1

	// Layout.
	var out []byte
	out = append(out, make([]byte, 64)...)

	align := func(n int) {
		for len(out)%n != 0 {
			out = append(out, 0)
		}
	}

	align(16)
	textOff := len(out)
	out = append(out, img.Code...)

	align(16)
	dataOff := len(out)
	out = append(out, img.Data...)

	align(8)
	symtabOff := len(out)
	for _, s := range syms {
		var b [24]byte
		le.PutUint32(b[0:], uint32(stNames.at(s.name)))
		b[4] = s.info
		b[5] = 0
		le.PutUint16(b[6:], s.shndx)
		le.PutUint64(b[8:], s.value)
		le.PutUint64(b[16:], s.size)
		out = append(out, b[:]...)
	}

	strtabOff := len(out)
	out = append(out, stNames.bytes()...)

	var relaOff int
	if hasRela {
		align(8)
		relaOff = len(out)
		for _, r := range relas {
			var b [24]byte
			le.PutUint64(b[0:], r.off)
			le.PutUint64(b[8:], uint64(r.sym)<<32|uint64(r.typ))
			le.PutUint64(b[16:], uint64(r.addend))
			out = append(out, b[:]...)
		}
	}

	shstrOff := len(out)
	out = append(out, stSections.bytes()...)

	align(8)
	shoff := len(out)

	putSh := func(name string, typ int, flags uint64, off, size int, link, info int, alignV, entsize uint64) {
		var b [64]byte
		le.PutUint32(b[0:], uint32(stSections.at(name)))
		le.PutUint32(b[4:], uint32(typ))
		le.PutUint64(b[8:], flags)
		le.PutUint64(b[16:], 0)
		le.PutUint64(b[24:], uint64(off))
		le.PutUint64(b[32:], uint64(size))
		le.PutUint32(b[40:], uint32(link))
		le.PutUint32(b[44:], uint32(info))
		le.PutUint64(b[48:], alignV)
		le.PutUint64(b[56:], entsize)
		out = append(out, b[:]...)
	}
	putSh("", shtNull, 0, 0, 0, 0, 0, 0, 0)
	putSh(".text", shtProgbits, shfAlloc|shfExecInstr, textOff, len(img.Code), 0, 0, 16, 0)
	putSh(".data", shtProgbits, shfAlloc|shfWrite, dataOff, len(img.Data), 0, 0, 16, 0)
	putSh(".symtab", shtSymtab, 0, symtabOff, 24*len(syms), secStrtab, shInfo, 8, 24)
	putSh(".strtab", shtStrtab, 0, strtabOff, len(stNames.bytes()), 0, 0, 1, 0)
	if hasRela {
		putSh(".rela.text", shtRela, 0, relaOff, 24*len(relas), secSymtab, secText, 8, 24)
	}
	putSh(".shstrtab", shtStrtab, 0, shstrOff, len(stSections.bytes()), 0, 0, 1, 0)

	// ELF header.
	hdr := out[:64]
	copy(hdr[0:], []byte{0x7f, 'E', 'L', 'F', elfClass64, elfDataLSB, elfVersion, 0})
	le.PutUint16(hdr[16:], etREL)
	le.PutUint16(hdr[18:], emRISCV)
	le.PutUint32(hdr[20:], elfVersion)
	le.PutUint64(hdr[24:], 0)
	le.PutUint64(hdr[32:], 0)
	le.PutUint64(hdr[40:], uint64(shoff))
	le.PutUint32(hdr[48:], 0)
	le.PutUint16(hdr[52:], 64)
	le.PutUint16(hdr[54:], 0)
	le.PutUint16(hdr[56:], 0)
	le.PutUint16(hdr[58:], 64)
	le.PutUint16(hdr[60:], uint16(nSections))
	le.PutUint16(hdr[62:], uint16(secShstr))

	return out, nil
}