gasm-sdk/asm/goobj_dwarf.go

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

package asm

import (
	"encoding/binary"
)

// This file generates the per-function DWARF symbols the linker's DWARF
// pass requires of an assembly object, byte-identical to what cmd/asm
// emits: the .debug_line state-machine program (SDWARFLINES) and the
// subprogram DIE (SDWARFFCN).  The linker copies the DIE and line-program
// bytes verbatim into .debug_info and .debug_line, fixing up their
// relocations, so the formats here must match cmd/internal/dwarf's
// DW_ABRV_FUNCTION and generateDebugLinesSymbol exactly.
//
// DWARF5 is assumed throughout (the toolchain's default on Linux and the
// other non-Darwin targets gasm supports).

// Line-program parameters (cmd/internal/obj/dwarf.go).
const (
	dwLineBase   = -4
	dwLineRange  = 10
	dwOpcodeBase = 11
	dwPCRange    = (255 - dwOpcodeBase) / dwLineRange
)

// goobjReloc is one relocation attached to an emitter-generated symbol
// (the DWARF lines/info symbols), in goobj's on-disk encoding fields.
type goobjReloc struct {
	off int32
	siz uint8
	typ uint16
	add int64
	pkg uint32
	sym uint32
}

// goobjDwarfLines builds the function's .debug_line state-machine program:
// an LNE_set_address extended opcode establishing the function's start
// address (carrying the R_ADDR relocation), one row per source line
// change across the function's instructions, an advance to the end of the
// function and an end-of-sequence opcode.  The linker appends these bytes
// after the unit's line header, so they must start with the address and
// leave the state machine terminated.
func goobjDwarfLines(fn FuncLayout, fnNpIdx int) ([]byte, []goobjReloc) {
	// Rows: the prologue, if any, then the body instructions (fn.Lines
	// covers the body only).  The first body offset > 0 means a prologue
	// precedes it; the toolchain reports the prologue on the TEXT line.
	pts := make([]LineEntry, 0, len(fn.Lines)+1)
	if len(fn.Lines) == 0 || fn.Lines[0].Offset > 0 {
		pts = append(pts, LineEntry{Offset: 0, Line: fn.Line})
	}
	pts = append(pts, fn.Lines...)

	out := []byte{0, 9, 2, 0, 0, 0, 0, 0, 0, 0, 0} // LNE_set_address, address zeroed
	relocs := []goobjReloc{{
		off: 3, siz: 8, typ: relocAddr,
		pkg: pkgIdxNone, sym: uint32(fnNpIdx),
	}}

	// The state machine starts at line 1, pc 0 (function-relative); the
	// implicit initial pc is the function entry, so the first pc delta is
	// against 0.
	line := int64(1)
	pc := uint64(0)
	for _, p := range pts {
		if p.Line == 0 || uint64(p.Offset) < pc {
			continue
		}
		// Rows mark source-line changes only; the pc delta is measured from
		// the previous row, not the previous instruction.
		if int64(p.Line) == line {
			continue
		}
		deltaPC := uint64(p.Offset) - pc
		deltaLC := int64(p.Line) - line
		out = dwPutPCLCDelta(out, deltaPC, deltaLC)
		line, pc = int64(p.Line), uint64(p.Offset)
	}

	// Cover the rest of the function and close the sequence.
	if end := uint64(fn.Size) - pc; end > 0 {
		out = append(out, 2) // DW_LNS_advance_pc
		out = binary.AppendUvarint(out, end)
	}
	out = append(out, 0, 1, 1) // LNE_end_sequence
	return out, relocs
}

// dwPutPCLCDelta encodes one (pcDelta, lineDelta) step as the shortest
// special opcode plus any standard-opcode remainder, exactly like
// cmd/internal/obj's putpclcdelta.
func dwPutPCLCDelta(b []byte, deltaPC uint64, deltaLC int64) []byte {
	opcode := dwSelectOpcode(deltaPC, deltaLC)
	deltaPC -= uint64((opcode - dwOpcodeBase) / dwLineRange)
	deltaLC -= (opcode-dwOpcodeBase)%dwLineRange + dwLineBase

	// The remainder: standard opcodes first, then the special opcode
	// (which emits the row).
	if deltaPC != 0 {
		switch {
		case deltaPC <= uint64(dwPCRange):
			opcode -= dwLineRange * int64(uint64(dwPCRange)-deltaPC)
			b = append(b, 8) // DW_LNS_const_add_pc
		case (1<<14) <= deltaPC && deltaPC < (1<<16):
			b = append(b, 9) // DW_LNS_fixed_advance_pc
			b = binary.LittleEndian.AppendUint16(b, uint16(deltaPC))
		default:
			b = append(b, 2) // DW_LNS_advance_pc
			b = binary.AppendUvarint(b, deltaPC)
		}
	}
	if deltaLC != 0 {
		b = append(b, 3) // DW_LNS_advance_line
		b = binary.AppendVarint(b, deltaLC)
	}
	return append(b, byte(opcode))
}

// dwSelectOpcode picks the special opcode for (deltaPC, deltaLC) per
// cmd/internal/obj's putpclcdelta selection logic.
func dwSelectOpcode(deltaPC uint64, deltaLC int64) int64 {
	switch {
	case deltaLC < dwLineBase:
		if deltaPC >= uint64(dwPCRange) {
			return dwOpcodeBase + dwLineRange*dwPCRange
		}
		return dwOpcodeBase + dwLineRange*int64(deltaPC)
	case deltaLC < dwLineBase+dwLineRange:
		if deltaPC >= uint64(dwPCRange) {
			op := int64(dwOpcodeBase) + (deltaLC - dwLineBase) + dwLineRange*dwPCRange
			if op > 255 {
				op -= dwLineRange
			}
			return op
		}
		return int64(dwOpcodeBase) + (deltaLC - dwLineBase) + dwLineRange*int64(deltaPC)
	default:
		if deltaPC <= uint64(dwPCRange) {
			op := min(int64(dwOpcodeBase)+(dwLineRange-1)+dwLineRange*int64(deltaPC), 255)
			return op
		}
		switch deltaPC - uint64(dwPCRange) {
		case uint64(dwPCRange), (1 << 7) - 1, (1 << 16) - 1, (1 << 21) - 1,
			(1 << 28) - 1, (1 << 35) - 1, (1 << 42) - 1, (1 << 49) - 1,
			(1 << 56) - 1, (1 << 63) - 1:
			return 255
		default:
			// 250: the toolchain's "249" comment is stale.
			return dwOpcodeBase + dwLineRange*dwPCRange - 1
		}
	}
}

// goobjDwarfInfo builds the function's DWARF5 subprogram DIE (abbrev
// DW_ABRV_FUNCTION): name, low_pc as a .debug_addr index (the
// R_DWTXTADDR_U4 relocation), high_pc as the size, the call-frame-CFA
// frame base, the decl file/line and the external flag.  name is the
// symbol's object name (package-qualified unless static).
func goobjDwarfInfo(fn FuncLayout, name string, fnNpIdx int) ([]byte, []goobjReloc) {
	out := []byte{3} // DW_ABRV_FUNCTION
	out = append(out, name...)
	out = append(out, 0)

	addrx := len(out)
	out = append(out, 0, 0, 0, 0) // DW_AT_low_pc: addrx slot, zeroed
	out = binary.AppendUvarint(out, uint64(fn.Size))
	out = append(out, 1, 0x9c) // DW_AT_frame_base: block1, DW_OP_call_frame_cfa
	out = binary.LittleEndian.AppendUint32(out, 1)
	out = binary.AppendUvarint(out, uint64(fn.Line))
	if fn.Static {
		out = append(out, 0)
	} else {
		out = append(out, 1) // DW_AT_external
	}
	out = append(out, 0) // end of children

	relocs := []goobjReloc{{
		off: int32(addrx), siz: 4, typ: relocDWTXTADDRU4(),
		pkg: pkgIdxNone, sym: uint32(fnNpIdx),
	}}
	return out, relocs
}