petrbalvin/gasm-sdk
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 36 Wiki Activity

fix(elf): relocation records, DWARF tables and per-architecture frame data

Browse Source 
Assisted-by: GLM 5.3
This commit is contained in:
petrbalvin
2026-09-19 23:49:13 +02:00
parent ebdf14939f
commit f3c8510a58
11 changed files with 1302 additions and 164 deletions
Download Patch File Download Diff File Expand all files Collapse all files
asm/elf.go
+49 -7
View File
@@ -42,8 +42,10 @@ const (
sttSection = 3 sttSection = 3
stInfoShift = 4 stInfoShift = 4
rX8664PC32 = 2 rX8664PC32 = 2
rX8664TPOFF32 = 20 // R_X86_64_TPOFF32 (debug/elf): the local-exec TLS offset the stack
// guard loads from FS. 20 is R_X86_64_TLSLD, a different relocation.
rX8664TPOFF32 = 23
) )
// elfSym is one symbol-table entry in construction. // elfSym is one symbol-table entry in construction.
@@ -219,7 +221,7 @@ func (img *Image) ELFObject() ([]byte, error) {
for _, r := range relas { for _, r := range relas {
var b [24]byte var b [24]byte
le.PutUint64(b[0:], r.off) le.PutUint64(b[0:], r.off)
le.PutUint64(b[8:], uint64(r.sym)<<32|rX8664PC32) le.PutUint64(b[8:], uint64(r.sym)<<32|uint64(r.typ))
le.PutUint64(b[16:], uint64(r.addend)) le.PutUint64(b[16:], uint64(r.addend))
out = append(out, b[:]...) out = append(out, b[:]...)
} }
@@ -228,15 +230,32 @@ func (img *Image) ELFObject() ([]byte, error) {
shstrOff := len(out) shstrOff := len(out)
out = append(out, stSections.bytes()...) out = append(out, stSections.bytes()...)
// DWARF debug sections (no relocations, the linker resolves DWARF fixups). // DWARF debug sections; the address placeholders they leave are carried
// as .rela.debug_info/.rela.debug_line entries the system linker applies.
dwAlign := func(n int) { dwAlign := func(n int) {
for len(out)%n != 0 { for len(out)%n != 0 {
out = append(out, 0) out = append(out, 0)
} }
} }
dw := appendDWARFSections(&out, img, "gasm.s", symIdx, dwAlign) dw := appendDWARFSections(&out, img, dwarfSourceName(img), symIdx, dwAlign, cfiAMD64)
dwarfStart := 0 // section index of .debug_abbrev, set when DWARF is present
if dw != nil { if dw != nil {
nSections += 4 // .debug_abbrev, .debug_info, .debug_line, .debug_line_str // Five DWARF sections: .debug_abbrev, .debug_info, .debug_line,
// .debug_line_str and .debug_frame (the CIE is unconditional, so
// the frame section is always present), plus the relocation
// sections below when they carry entries.
dwarfStart = nSections
nSections += 5
appendDWARFRelas(&out, dw, rX8664Abs64, dwAlign)
if dw.infoRelaCount > 0 {
nSections++
}
if dw.lineRelaCount > 0 {
nSections++
}
if dw.frameRelaCount > 0 {
nSections++
}
} }
align(8) align(8)
@@ -267,14 +286,37 @@ func (img *Image) ELFObject() ([]byte, error) {
} }
putSh(".shstrtab", shtStrtab, 0, shstrOff, len(stSections.bytes()), 0, 0, 1, 0) putSh(".shstrtab", shtStrtab, 0, shstrOff, len(stSections.bytes()), 0, 0, 1, 0)
// DWARF section headers. // DWARF section headers; their indices follow the write order.
if dw != nil { if dw != nil {
// secIdx is a running section index: each putSh below emits the
// next header, and the sh_info of a .rela section names the index
// of the section it relocates.
secIdx := dwarfStart
putSh(".debug_abbrev", shtProgbits, 0, dw.abbrevOff, dw.abbrevSize, 0, 0, 1, 0) putSh(".debug_abbrev", shtProgbits, 0, dw.abbrevOff, dw.abbrevSize, 0, 0, 1, 0)
secIdx++
putSh(".debug_info", shtProgbits, 0, dw.infoOff, dw.infoSize, 0, 0, 1, 0) putSh(".debug_info", shtProgbits, 0, dw.infoOff, dw.infoSize, 0, 0, 1, 0)
secInfoIdx := secIdx
secIdx++
if dw.infoRelaCount > 0 {
putSh(".rela.debug_info", shtRela, 0, dw.infoRelaOff, 24*dw.infoRelaCount, secSymtab, secInfoIdx, 8, 24)
secIdx++
}
putSh(".debug_line", shtProgbits, 0, dw.lineOff, dw.lineSize, 0, 0, 1, 0) putSh(".debug_line", shtProgbits, 0, dw.lineOff, dw.lineSize, 0, 0, 1, 0)
secLineIdx := secIdx
secIdx++
if dw.lineRelaCount > 0 {
putSh(".rela.debug_line", shtRela, 0, dw.lineRelaOff, 24*dw.lineRelaCount, secSymtab, secLineIdx, 8, 24)
secIdx++
}
putSh(".debug_line_str", shtProgbits, 0, dw.lineStrOff, dw.lineStrSize, 0, 0, 1, 0) putSh(".debug_line_str", shtProgbits, 0, dw.lineStrOff, dw.lineStrSize, 0, 0, 1, 0)
secIdx++
if dw.frameSize > 0 { if dw.frameSize > 0 {
putSh(".debug_frame", shtProgbits, 0, dw.frameOff, dw.frameSize, 0, 0, 8, 0) putSh(".debug_frame", shtProgbits, 0, dw.frameOff, dw.frameSize, 0, 0, 8, 0)
secFrameIdx := secIdx
secIdx++
if dw.frameRelaCount > 0 {
putSh(".rela.debug_frame", shtRela, 0, dw.frameRelaOff, 24*dw.frameRelaCount, secSymtab, secFrameIdx, 8, 24)
}
} }
} }
asm/elf_dwarf.go
+161 -74
View File
@@ -12,43 +12,74 @@ import (
// self-contained sections because the system linker only performs fixup // self-contained sections because the system linker only performs fixup
// relocations, not assembly. // relocations, not assembly.
// DWARF5 attribute, form and line-table constants (the values the
// toolchain uses, cmd/internal/dwarf/dwarf_defs.go; the DIE streams below
// are written against these forms).
const (
dwAtName = 0x03 // DW_AT_name
dwAtStmtList = 0x10 // DW_AT_stmt_list
dwAtLowPC = 0x11 // DW_AT_low_pc
dwAtHighPC = 0x12 // DW_AT_high_pc
dwAtDeclFile = 0x3a // DW_AT_decl_file
dwAtDeclLine = 0x3b // DW_AT_decl_line
dwAtExternal = 0x3f // DW_AT_external
dwAtFrameBase = 0x40 // DW_AT_frame_base
dwTagSubprog = 0x2e // DW_TAG_subprogram
dwTagCompUnit = 0x11 // DW_TAG_compile_unit
dwFormAddr = 0x01 // DW_FORM_addr
dwFormData8 = 0x07 // DW_FORM_data8
dwFormString = 0x08 // DW_FORM_string
dwFormData1 = 0x0b // DW_FORM_data1
dwFormUdata = 0x0f // DW_FORM_udata
dwFormSecOff = 0x17 // DW_FORM_sec_offset
dwFormExprloc = 0x18 // DW_FORM_exprloc
dwFormLineStrp = 0x1f // DW_FORM_line_strp
dwLnctPath = 0x01 // DW_LNCT_path
dwLnctDirIndex = 0x02 // DW_LNCT_directory_index
)
// dwarfAbbrevTable returns the .debug_abbrev content: a single compilation // dwarfAbbrevTable returns the .debug_abbrev content: a single compilation
// unit with DW_TAG_compile_unit and DW_TAG_subprogram entries. // unit with DW_TAG_compile_unit and DW_TAG_subprogram entries. The
// attribute/form pairs must match the DIE streams dwarfBuildInfoSection
// writes byte for byte, in the same order, or every consumer's parse of
// .debug_info desynchronises.
func dwarfAbbrevTable() []byte { func dwarfAbbrevTable() []byte {
var b []byte var b []byte
// Abbrev 1: DW_TAG_compile_unit // Abbrev 1: DW_TAG_compile_unit.
b = append(b, 1) // abbreviation code b = append(b, 1) // abbreviation code
b = append(b, 0x11) // DW_TAG_compile_unit b = appendUleb(b, dwTagCompUnit) // DW_TAG_compile_unit
b = append(b, 1) // DW_CHILDREN_yes b = append(b, 1) // DW_CHILDREN_yes
b = appendUleb(b, 0x1b) // DW_AT_low_pc b = appendUleb(b, dwAtLowPC) // DW_AT_low_pc
b = appendUleb(b, 0x01) // DW_FORM_addr b = appendUleb(b, dwFormAddr) // DW_FORM_addr
b = appendUleb(b, 0x29) // DW_AT_high_pc b = appendUleb(b, dwAtHighPC) // DW_AT_high_pc
b = appendUleb(b, 0x07) // DW_FORM_data8 b = appendUleb(b, dwFormData8) // DW_FORM_data8
b = appendUleb(b, 0x10) // DW_AT_stmt_list b = appendUleb(b, dwAtStmtList) // DW_AT_stmt_list
b = appendUleb(b, 0x25) // DW_FORM_sec_offset b = appendUleb(b, dwFormSecOff) // DW_FORM_sec_offset (4 bytes here)
b = appendUleb(b, 0x01) // DW_AT_name b = appendUleb(b, dwAtName) // DW_AT_name
b = appendUleb(b, 0x08) // DW_FORM_string b = appendUleb(b, dwFormString) // DW_FORM_string
b = appendUleb(b, 0) // end of attributes b = appendUleb(b, 0) // end of attributes: attr 0
b = appendUleb(b, 0) // ... paired with form 0
// Abbrev 2: DW_TAG_subprogram // Abbrev 2: DW_TAG_subprogram.
b = append(b, 2) // abbreviation code b = append(b, 2) // abbreviation code
b = append(b, 0x2e) // DW_TAG_subprogram b = appendUleb(b, dwTagSubprog) // DW_TAG_subprogram
b = append(b, 0) // DW_CHILDREN_no b = append(b, 0) // DW_CHILDREN_no
b = appendUleb(b, 0x03) // DW_AT_name b = appendUleb(b, dwAtName) // DW_AT_name
b = appendUleb(b, 0x08) // DW_FORM_string b = appendUleb(b, dwFormString) // DW_FORM_string
b = appendUleb(b, 0x11) // DW_AT_low_pc b = appendUleb(b, dwAtLowPC) // DW_AT_low_pc
b = appendUleb(b, 0x01) // DW_FORM_addr b = appendUleb(b, dwFormAddr) // DW_FORM_addr
b = appendUleb(b, 0x29) // DW_AT_high_pc b = appendUleb(b, dwAtHighPC) // DW_AT_high_pc
b = appendUleb(b, 0x07) // DW_FORM_data8 b = appendUleb(b, dwFormData8) // DW_FORM_data8
b = appendUleb(b, 0x3f) // DW_AT_frame_base b = appendUleb(b, dwAtFrameBase) // DW_AT_frame_base
b = appendUleb(b, 0x18) // DW_FORM_exprloc b = appendUleb(b, dwFormExprloc) // DW_FORM_exprloc
b = appendUleb(b, 0x3b) // DW_AT_decl_file b = appendUleb(b, dwAtDeclFile) // DW_AT_decl_file
b = appendUleb(b, 0x0b) // DW_FORM_data1 b = appendUleb(b, dwFormData1) // DW_FORM_data1
b = appendUleb(b, 0x37) // DW_AT_decl_line b = appendUleb(b, dwAtDeclLine) // DW_AT_decl_line
b = appendUleb(b, 0x0b) // DW_FORM_data1 b = appendUleb(b, dwFormData1) // DW_FORM_data1
b = appendUleb(b, 0x63) // DW_AT_external b = appendUleb(b, dwAtExternal) // DW_AT_external
b = appendUleb(b, 0x0b) // DW_FORM_flag b = appendUleb(b, 0x0c) // DW_FORM_flag (one byte, 0 or 1)
b = appendUleb(b, 0) // end of attributes b = appendUleb(b, 0) // end of attributes: attr 0
b = appendUleb(b, 0) // ... paired with form 0
// End of table. // End of table.
b = append(b, 0) b = append(b, 0)
@@ -68,6 +99,9 @@ type dwarfSections struct {
infoRelocs []dwarfReloc infoRelocs []dwarfReloc
// Relocations for .debug_line: (offset, symbol name, addend). // Relocations for .debug_line: (offset, symbol name, addend).
lineRelocs []dwarfReloc lineRelocs []dwarfReloc
// Relocations for .debug_frame: (offset, symbol name, addend), one per
// FDE initial_location.
frameRelocs []dwarfReloc
} }
type dwarfReloc struct { type dwarfReloc struct {
@@ -76,8 +110,9 @@ type dwarfReloc struct {
addend int64 addend int64
} }
// emitDWARF generates complete DWARF5 sections for the image. // emitDWARF generates complete DWARF5 sections for the image. cfi carries
func emitDWARF(img *Image, srcFile string) *dwarfSections { // the architecture's .debug_frame register conventions.
func emitDWARF(img *Image, srcFile string, cfi cfiArch) *dwarfSections {
ds := &dwarfSections{} ds := &dwarfSections{}
ds.debugAbbrev = dwarfAbbrevTable() ds.debugAbbrev = dwarfAbbrevTable()
@@ -86,19 +121,21 @@ func emitDWARF(img *Image, srcFile string) *dwarfSections {
lineStr.add(srcFile) lineStr.add(srcFile)
ds.debugLineStr = lineStr.bytes() ds.debugLineStr = lineStr.bytes()
// Build .debug_line. // Build .debug_line; the file table references the source name through
ds.debugLine = dwarfBuildLineSection(img, ds) // its offset in .debug_line_str.
ds.debugLine = dwarfBuildLineSection(img, uint32(lineStr.at(srcFile)), ds)
// Build .debug_info. // Build .debug_info.
ds.debugInfo = dwarfBuildInfoSection(img, srcFile, ds) ds.debugInfo = dwarfBuildInfoSection(img, srcFile, ds)
// Build .debug_frame. // Build .debug_frame.
ds.debugFrame = dwarfBuildFrameSection(img) ds.debugFrame = dwarfBuildFrameSection(img, cfi, ds)
return ds return ds
} }
// dwarfBuildLineSection builds a complete .debug_line section. // dwarfBuildLineSection builds a complete .debug_line section. srcStrOff is
func dwarfBuildLineSection(img *Image, ds *dwarfSections) []byte { // the source file name's offset in .debug_line_str.
func dwarfBuildLineSection(img *Image, srcStrOff uint32, ds *dwarfSections) []byte {
var b []byte var b []byte
le := binary.LittleEndian le := binary.LittleEndian
@@ -120,15 +157,25 @@ func dwarfBuildLineSection(img *Image, ds *dwarfSections) []byte {
// Standard opcode lengths (opcode 1..opcode_base-1). // Standard opcode lengths (opcode 1..opcode_base-1).
b = append(b, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0) b = append(b, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0)
// Directory table (DWARF5 format). // Directory table (DWARF5 §6.2.4): entry format descriptors followed by
b = append(b, 0) // one directory entry (index 0 = empty) // the entries. One directory, the compilation directory, whose path is
// File table. // the empty string at .debug_line_str offset 0.
b = appendUleb(b, 1) // file count b = append(b, 1) // directory_entry_format_count
// File 1: name index into .debug_line_str, dir index, time, size. b = appendUleb(b, dwLnctPath) // DW_LNCT_path
b = appendUleb(b, 0) // name (index 0 in line_str) b = appendUleb(b, dwFormLineStrp) // DW_FORM_line_strp
b = appendUleb(b, 0) // directory index b = appendUleb(b, 1) // directories_count
b = appendUleb(b, 0) // last modification time b = le.AppendUint32(b, 0) // .debug_line_str offset of ""
b = appendUleb(b, 0) // file size
// File table (DWARF5 §6.2.5). v5 indexes files from 0, so the source
// file is entry 0, matching the DW_AT_decl_file value 0 the DIEs carry.
b = append(b, 2) // file_name_entry_format_count
b = appendUleb(b, dwLnctPath) // DW_LNCT_path
b = appendUleb(b, dwFormLineStrp) // DW_FORM_line_strp
b = appendUleb(b, dwLnctDirIndex) // DW_LNCT_directory_index
b = appendUleb(b, dwFormUdata) // DW_FORM_udata
b = appendUleb(b, 1) // file_names_count
b = le.AppendUint32(b, srcStrOff) // .debug_line_str offset of the source name
b = appendUleb(b, 0) // directory index 0 (the compilation directory)
headerEnd := len(b) headerEnd := len(b)
@@ -176,8 +223,11 @@ func dwarfBuildLineSection(img *Image, ds *dwarfSections) []byte {
// Patch unit_length. // Patch unit_length.
le.PutUint32(b[headerStart:], uint32(len(b)-headerStart-4)) le.PutUint32(b[headerStart:], uint32(len(b)-headerStart-4))
// Patch header_length. // Patch header_length. In the v5 header it follows the one-byte
le.PutUint32(b[headerStart+6:], uint32(headerEnd-headerStart-10)) // address_size and segment_selector_size (offset 8, not the DWARF2-4
// offset 6), and counts from just past itself to the first program
// byte.
le.PutUint32(b[headerStart+8:], uint32(headerEnd-headerStart-12))
return b return b
} }
@@ -195,14 +245,16 @@ func dwarfBuildInfoSection(img *Image, srcFile string, ds *dwarfSections) []byte
// DW_TAG_compile_unit (abbrev 1). // DW_TAG_compile_unit (abbrev 1).
b = append(b, 1) // abbreviation code b = append(b, 1) // abbreviation code
// DW_AT_low_pc: address of .text start. // DW_AT_low_pc: address of .text start. A data-only image has no
infoRelocBase := len(b) // functions to relocate against; its CU covers no code, so the base
// stays zero (the DWARF "no base address" value) with no relocation.
b = le.AppendUint64(b, 0) // placeholder b = le.AppendUint64(b, 0) // placeholder
ds.infoRelocs = append(ds.infoRelocs, dwarfReloc{ if len(img.Funcs) > 0 {
off: uint64(infoRelocBase), ds.infoRelocs = append(ds.infoRelocs, dwarfReloc{
name: img.Funcs[0].Name, off: uint64(len(b) - 8),
addend: 0, name: img.Funcs[0].Name,
}) })
}
// DW_AT_high_pc: size of .text. // DW_AT_high_pc: size of .text.
b = le.AppendUint64(b, uint64(len(img.Code))) b = le.AppendUint64(b, uint64(len(img.Code)))
// DW_AT_stmt_list: offset into .debug_line (0). // DW_AT_stmt_list: offset into .debug_line (0).
@@ -229,8 +281,9 @@ func dwarfBuildInfoSection(img *Image, srcFile string, ds *dwarfSections) []byte
b = le.AppendUint64(b, uint64(fn.Size)) b = le.AppendUint64(b, uint64(fn.Size))
// DW_AT_frame_base: DW_OP_call_frame_cfa. // DW_AT_frame_base: DW_OP_call_frame_cfa.
b = append(b, 1, 0x9c) b = append(b, 1, 0x9c)
// DW_AT_decl_file: file index 1. // DW_AT_decl_file: the single file-table entry, index 0 (v5 indexes
b = append(b, 1) // files from 0).
b = append(b, 0)
// DW_AT_decl_line. // DW_AT_decl_line.
b = append(b, uint8(fn.Line)) b = append(b, uint8(fn.Line))
// DW_AT_external. // DW_AT_external.
@@ -253,32 +306,61 @@ func appendUleb(b []byte, v uint64) []byte {
return binary.AppendUvarint(b, v) return binary.AppendUvarint(b, v)
} }
// appendSleb appends v in signed LEB128, the encoding DWARF specifies:
// two's-complement sign extension, which is NOT Go's zigzag varint
// (binary.AppendVarint(-8) encodes 15, where DWARF wants 0x78).
func appendSleb(b []byte, v int64) []byte { func appendSleb(b []byte, v int64) []byte {
return binary.AppendVarint(b, v) for {
c := byte(v & 0x7f)
v >>= 7
if (v == 0 && c&0x40 == 0) || (v == -1 && c&0x40 != 0) {
return append(b, c)
}
b = append(b, c|0x80)
}
} }
// cfiArch carries the .debug_frame CIE parameters that differ per
// architecture: the DWARF register numbers of the stack pointer the initial
// CFA rule names and of the return address. The values are the ones the Go
// linker writes into its own CIE (cmd/link/internal/ld/dwarf.go uses
// Dwarfregsp and Dwarfreglr; the per-architecture constants live in
// cmd/link/internal/<arch>/l.go).
type cfiArch struct {
name string
cfaReg byte // the stack-pointer register the initial CFA rule names
raReg byte // the return-address register
}
var (
cfiAMD64 = cfiArch{"amd64", 7, 16} // RSP, RIP
cfiARM64 = cfiArch{"arm64", 31, 30} // SP (X31), LR (X30)
cfiRISCV64 = cfiArch{"riscv64", 2, 1} // X2 (sp), X1 (ra)
cfiLOONG64 = cfiArch{"loong64", 3, 1} // $r3 (sp), $r1 (ra)
)
// dwarfBuildFrameSection builds a .debug_frame section with CFI for stack // dwarfBuildFrameSection builds a .debug_frame section with CFI for stack
// unwinding. It emits one CIE and one FDE per function, encoding the // unwinding. It emits one CIE and one FDE per function, encoding the
// CFA (Canonical Frame Address) rule changes at each stack-adjustment // CFA (Canonical Frame Address) rule changes at each stack-adjustment
// boundary recorded in FuncLayout.Spadj. // boundary recorded in FuncLayout.Spadj.
func dwarfBuildFrameSection(img *Image) []byte { func dwarfBuildFrameSection(img *Image, cfi cfiArch, ds *dwarfSections) []byte {
var b []byte var b []byte
le := binary.LittleEndian le := binary.LittleEndian
// CIE (Common Information Entry). // CIE (Common Information Entry).
cieStart := len(b) cieStart := len(b)
b = append(b, 0, 0, 0, 0) // length (placeholder) b = append(b, 0, 0, 0, 0) // length (placeholder)
b = le.AppendUint32(b, 0xFFFFFFFF) // CIE marker b = le.AppendUint32(b, 0xFFFFFFFF) // CIE marker
b = append(b, 3) // version (DWARF3, widely supported) b = append(b, 3) // version (DWARF3, widely supported)
b = append(b, 0) // augmentation (empty) b = append(b, 0) // augmentation (empty)
b = appendUleb(b, 1) // code alignment b = appendUleb(b, 1) // code alignment
b = appendSleb(b, -8) // data alignment (-8 for 64-bit) b = appendSleb(b, -8) // data alignment (-8 for 64-bit)
b = appendUleb(b, 16) // return address register (LR on arm64, RIP on amd64) b = appendUleb(b, uint64(cfi.raReg)) // return address register
// Initial CFA rule: DW_CFA_def_cfa (SP, 0) // Initial CFA rule: DW_CFA_def_cfa (SP, 0)
b = append(b, 0x0c) // DW_CFA_def_cfa b = append(b, 0x0c) // DW_CFA_def_cfa
b = appendUleb(b, 31) // register: SP (RSP=7 on amd64, SP=31 on arm64) b = appendUleb(b, uint64(cfi.cfaReg)) // the architecture's stack pointer
b = appendUleb(b, 0) // offset: 0 b = appendUleb(b, 0) // offset: 0
b = append(b, 0) // DW_CFA_nop (padding) b = append(b, 0) // DW_CFA_nop (padding)
// Patch CIE length. // Patch CIE length.
le.PutUint32(b[cieStart:], uint32(len(b)-cieStart-4)) le.PutUint32(b[cieStart:], uint32(len(b)-cieStart-4))
@@ -287,7 +369,12 @@ func dwarfBuildFrameSection(img *Image) []byte {
fdeStart := len(b) fdeStart := len(b)
b = append(b, 0, 0, 0, 0) // length (placeholder) b = append(b, 0, 0, 0, 0) // length (placeholder)
b = le.AppendUint32(b, uint32(cieStart)) // CIE pointer (offset from start) b = le.AppendUint32(b, uint32(cieStart)) // CIE pointer (offset from start)
// Initial location: function offset in .text (relocated by linker). // Initial location: function offset in .text, referenced through
// the function's symbol so the linker relocates it.
ds.frameRelocs = append(ds.frameRelocs, dwarfReloc{
off: uint64(fdeStart + 8),
name: fn.Name,
})
b = le.AppendUint64(b, uint64(fn.Offset)) b = le.AppendUint64(b, uint64(fn.Offset))
// Address range: function size. // Address range: function size.
b = le.AppendUint64(b, uint64(fn.Size)) b = le.AppendUint64(b, uint64(fn.Size))
asm/elf_dwarf_sections.go
+84 -24
View File
@@ -3,6 +3,17 @@
package asm package asm
import "encoding/binary"
// Absolute 64-bit relocation types for the DWARF address fixups, one per
// supported architecture (the numbers debug/elf carries).
const (
rX8664Abs64 = 1 // R_X86_64_64
rAARCH64Abs64 = 257 // R_AARCH64_ABS64
rRISCVAbs64 = 2 // R_RISCV_64
rLarchAbs64 = 2 // R_LARCH_64
)
// dwarfELFSections holds the laid-out DWARF sections ready for inclusion // dwarfELFSections holds the laid-out DWARF sections ready for inclusion
// in an ELF file. // in an ELF file.
type dwarfELFSections struct { type dwarfELFSections struct {
@@ -11,15 +22,23 @@ type dwarfELFSections struct {
lineOff, lineSize int lineOff, lineSize int
lineStrOff, lineStrSize int lineStrOff, lineStrSize int
frameOff, frameSize int frameOff, frameSize int
// Relocations for .debug_info address references. // .rela.debug_info and .rela.debug_line contents: file offsets and
// entry counts (zero count: the section is absent).
infoRelaOff, infoRelaCount int
lineRelaOff, lineRelaCount int
frameRelaOff, frameRelaCount int
// Relocations for .debug_info address references, offsets relative to
// the section start (what an r_offset in .rela.debug_info means).
infoRelocs []elfDwarfReloc infoRelocs []elfDwarfReloc
// Relocations for .debug_line address references. // Relocations for .debug_line address references, section-relative.
lineRelocs []elfDwarfReloc lineRelocs []elfDwarfReloc
// Relocations for .debug_frame FDE initial locations, section-relative.
frameRelocs []elfDwarfReloc
} }
type elfDwarfReloc struct { type elfDwarfReloc struct {
off uint64 off uint64 // offset within the target section
sym int // symbol index in .symtab sym int // symbol index in .symtab
addend int64 addend int64
} }
@@ -29,8 +48,9 @@ type elfDwarfReloc struct {
// //
// symIdx maps function names to their .symtab indices (needed for relocations // symIdx maps function names to their .symtab indices (needed for relocations
// against .text symbols). The map uses objectName format (pkg.name); the // against .text symbols). The map uses objectName format (pkg.name); the
// DWARF code uses bare function names, so we build a reverse lookup. // DWARF code uses bare function names, so we build a reverse lookup. cfi
func appendDWARFSections(out *[]byte, img *Image, srcFile string, symIdx map[string]int, align func(int)) *dwarfELFSections { // carries the architecture's .debug_frame register conventions.
func appendDWARFSections(out *[]byte, img *Image, srcFile string, symIdx map[string]int, align func(int), cfi cfiArch) *dwarfELFSections {
// Build a lookup from bare function name to symbol index. // Build a lookup from bare function name to symbol index.
nameToIdx := make(map[string]int, len(symIdx)) nameToIdx := make(map[string]int, len(symIdx))
for name, idx := range symIdx { for name, idx := range symIdx {
@@ -45,7 +65,7 @@ func appendDWARFSections(out *[]byte, img *Image, srcFile string, symIdx map[str
} }
nameToIdx[name] = idx nameToIdx[name] = idx
} }
ds := emitDWARF(img, srcFile) ds := emitDWARF(img, srcFile, cfi)
if ds == nil || len(ds.debugAbbrev) == 0 { if ds == nil || len(ds.debugAbbrev) == 0 {
return nil return nil
} }
@@ -68,15 +88,11 @@ func appendDWARFSections(out *[]byte, img *Image, srcFile string, symIdx map[str
align(1) align(1)
result.lineOff = len(*out) result.lineOff = len(*out)
result.lineSize = len(ds.debugLine) result.lineSize = len(ds.debugLine)
lineBase := len(*out)
*out = append(*out, ds.debugLine...) *out = append(*out, ds.debugLine...)
// Patch .debug_line relocations: replace placeholder addresses with
// actual .text offsets via symbol lookup.
for _, dr := range ds.lineRelocs { for _, dr := range ds.lineRelocs {
if idx, ok := nameToIdx[dr.name]; ok { if idx, ok := nameToIdx[dr.name]; ok {
result.lineRelocs = append(result.lineRelocs, elfDwarfReloc{ result.lineRelocs = append(result.lineRelocs, elfDwarfReloc{
off: uint64(lineBase) + dr.off, off: dr.off,
sym: idx, sym: idx,
addend: dr.addend, addend: dr.addend,
}) })
@@ -87,33 +103,77 @@ func appendDWARFSections(out *[]byte, img *Image, srcFile string, symIdx map[str
align(1) align(1)
result.infoOff = len(*out) result.infoOff = len(*out)
result.infoSize = len(ds.debugInfo) result.infoSize = len(ds.debugInfo)
infoBase := len(*out)
*out = append(*out, ds.debugInfo...) *out = append(*out, ds.debugInfo...)
// .debug_frame
if len(ds.debugFrame) > 0 {
align(1)
result.frameOff = len(*out)
result.frameSize = len(ds.debugFrame)
*out = append(*out, ds.debugFrame...)
}
// Patch .debug_info relocations.
for _, dr := range ds.infoRelocs { for _, dr := range ds.infoRelocs {
if idx, ok := nameToIdx[dr.name]; ok { if idx, ok := nameToIdx[dr.name]; ok {
result.infoRelocs = append(result.infoRelocs, elfDwarfReloc{ result.infoRelocs = append(result.infoRelocs, elfDwarfReloc{
off: uint64(infoBase) + dr.off, off: dr.off,
sym: idx, sym: idx,
addend: dr.addend, addend: dr.addend,
}) })
} }
} }
// .debug_frame: the section header declares alignment 8, so the data is
// padded to 8, matching it.
if len(ds.debugFrame) > 0 {
align(8)
result.frameOff = len(*out)
result.frameSize = len(ds.debugFrame)
*out = append(*out, ds.debugFrame...)
for _, dr := range ds.frameRelocs {
if idx, ok := nameToIdx[dr.name]; ok {
result.frameRelocs = append(result.frameRelocs, elfDwarfReloc{
off: dr.off,
sym: idx,
addend: dr.addend,
})
}
}
}
return result return result
} }
// appendDWARFRelas writes the .rela.debug_info and .rela.debug_line section
// bodies from the relocations appendDWARFSections recorded, with the
// architecture's absolute 64-bit relocation type, and records their file
// offsets and entry counts on dw. Called after the DWARF sections
// themselves so the r_offsets (section-relative) need no adjustment.
func appendDWARFRelas(out *[]byte, dw *dwarfELFSections, abs64 uint32, align func(int)) {
le := binary.LittleEndian
write := func(relas []elfDwarfReloc) (off, count int) {
if len(relas) == 0 {
return 0, 0
}
align(8)
off = 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(abs64))
le.PutUint64(b[16:], uint64(r.addend))
*out = append(*out, b[:]...)
}
return off, len(relas)
}
dw.infoRelaOff, dw.infoRelaCount = write(dw.infoRelocs)
dw.lineRelaOff, dw.lineRelaCount = write(dw.lineRelocs)
dw.frameRelaOff, dw.frameRelaCount = write(dw.frameRelocs)
}
// dwarfSourceName returns the source name the DWARF sections record: the
// image's source path when the assembler captured one, "gasm.s" otherwise.
func dwarfSourceName(img *Image) string {
if img.SourcePath != "" {
return img.SourcePath
}
return "gasm.s"
}
// dwarfSectionNames returns the DWARF section names for the string table. // dwarfSectionNames returns the DWARF section names for the string table.
var dwarfSectionNames = []string{ var dwarfSectionNames = []string{
".debug_abbrev", ".debug_info", ".debug_line", ".debug_line_str", ".debug_abbrev", ".debug_info", ".debug_line", ".debug_line_str",
".debug_frame", ".rela.debug_info", ".rela.debug_line", ".debug_frame", ".rela.debug_info", ".rela.debug_line",
".rela.debug_frame",
} }
asm/elf_dwarf_test.go
+303 -12
View File
@@ -4,11 +4,313 @@
package asm package asm
import ( import (
"bytes"
"encoding/binary"
"testing" "testing"
"sourcedock.dev/petrbalvin/gasm-devkit/parser" "sourcedock.dev/petrbalvin/gasm-devkit/parser"
) )
// ulebIter reads ULEB128 values, the .debug_abbrev and line-header
// encoding.
type ulebIter struct {
b []byte
i int
}
func (r *ulebIter) uleb(t *testing.T) uint64 {
t.Helper()
v, n := binary.Uvarint(r.b[r.i:])
if n <= 0 {
t.Fatalf("bad ULEB at %d", r.i)
}
r.i += n
return v
}
func (r *ulebIter) byteAt(t *testing.T) byte {
t.Helper()
if r.i >= len(r.b) {
t.Fatalf("read past end at %d", r.i)
}
c := r.b[r.i]
r.i++
return c
}
func (r *ulebIter) uint32At(t *testing.T) uint32 {
t.Helper()
v := binary.LittleEndian.Uint32(r.b[r.i:])
r.i += 4
return v
}
// sleb reads a signed LEB128, the DWARF encoding (sign-extended two's
// complement, not Go's zigzag varint).
func (r *ulebIter) sleb(t *testing.T) int64 {
t.Helper()
var v int64
var shift uint
for {
c := r.byteAt(t)
v |= int64(c&0x7f) << shift
shift += 7
if c&0x80 == 0 {
if c&0x40 != 0 {
v |= -1 << shift
}
return v
}
}
}
// dwarfAttr is one attribute/form pair of an abbreviation.
type dwarfAttr struct{ attr, form uint64 }
// dwarfAbbrev is one parsed abbreviation declaration.
type dwarfAbbrev struct {
code uint64
tag uint64
children bool
attrs []dwarfAttr
}
// parseAbbrevs walks a .debug_abbrev table: abbreviation code, tag,
// children flag, then attr/form ULEB pairs terminated by a double zero.
func parseAbbrevs(t *testing.T, b []byte) map[uint64]dwarfAbbrev {
t.Helper()
out := map[uint64]dwarfAbbrev{}
r := &ulebIter{b: b}
for {
code := r.uleb(t)
if code == 0 {
return out
}
ab := dwarfAbbrev{code: code, tag: r.uleb(t)}
ab.children = r.byteAt(t) == 1
for {
attr := r.uleb(t)
form := r.uleb(t)
if attr == 0 && form == 0 {
break
}
if attr == 0 || form == 0 {
t.Fatalf("abbrev %d: half-terminated attr/form pair (%d, %d)", code, attr, form)
}
ab.attrs = append(ab.attrs, dwarfAttr{attr, form})
}
out[code] = ab
}
}
func eqAttrs(t *testing.T, ab dwarfAbbrev, want []dwarfAttr) {
t.Helper()
if len(ab.attrs) != len(want) {
t.Fatalf("abbrev %d attrs = %v, want %v", ab.code, ab.attrs, want)
}
for i, w := range want {
if ab.attrs[i] != w {
t.Fatalf("abbrev %d attr %d = (%#x, %#x), want (%#x, %#x)", ab.code, i, ab.attrs[i].attr, ab.attrs[i].form, w.attr, w.form)
}
}
}
// TestDwarfAbbrevTable walks the abbreviation table as a consumer does and
// checks the attribute/form sets against the constants the toolchain uses
// (cmd/internal/dwarf/dwarf_defs.go). A wrong constant here renames an
// attribute (0x1b is comp_dir, not low_pc; 0x29 and 0x37 are bounds and
// count) and a wrong form desynchronises the DIE parse: 0x25 is strx1, one
// byte, where the writer emits four for a section offset.
func TestDwarfAbbrevTable(t *testing.T) {
abbrev := dwarfAbbrevTable()
if len(abbrev) == 0 {
t.Fatal("empty abbrev table")
}
// Must end with a zero byte (end of table).
if abbrev[len(abbrev)-1] != 0 {
t.Fatalf("abbrev table last byte = %d, want 0", abbrev[len(abbrev)-1])
}
abs := parseAbbrevs(t, abbrev)
if len(abs) != 2 {
t.Fatalf("abbreviations = %d, want 2", len(abs))
}
cu, ok := abs[1]
if !ok {
t.Fatal("missing abbreviation 1 (compile unit)")
}
if cu.tag != dwTagCompUnit || !cu.children {
t.Errorf("abbrev 1: tag %#x children %v, want compile unit with children", cu.tag, cu.children)
}
eqAttrs(t, cu, []dwarfAttr{
{dwAtLowPC, dwFormAddr},
{dwAtHighPC, dwFormData8},
{dwAtStmtList, dwFormSecOff},
{dwAtName, dwFormString},
})
sp, ok := abs[2]
if !ok {
t.Fatal("missing abbreviation 2 (subprogram)")
}
if sp.tag != dwTagSubprog || sp.children {
t.Errorf("abbrev 2: tag %#x children %v, want subprogram without children", sp.tag, sp.children)
}
eqAttrs(t, sp, []dwarfAttr{
{dwAtName, dwFormString},
{dwAtLowPC, dwFormAddr},
{dwAtHighPC, dwFormData8},
{dwAtFrameBase, dwFormExprloc},
{dwAtDeclFile, dwFormData1},
{dwAtDeclLine, dwFormData1},
{dwAtExternal, 0x0c}, // DW_FORM_flag
})
}
// TestDwarfLineHeaderV5 parses the .debug_line header under DWARF5 rules:
// the directory and file tables are format-descriptor lists, not the
// DWARF2-4 shape of null-terminated strings, and the file entry references
// the source name through .debug_line_str.
func TestDwarfLineHeaderV5(t *testing.T) {
src := `#include "textflag.h"
TEXT ·add(SB), NOSPLIT, $0-24
MOVQ a+0(FP), AX
MOVQ b+8(FP), BX
ADDQ BX, AX
MOVQ AX, ret+16(FP)
RET
`
f, errs := parser.Parse("test_amd64.s", src)
if len(errs) > 0 {
t.Fatalf("parse: %v", errs)
}
img, err := AssembleFile(f)
if err != nil {
t.Fatalf("assemble: %v", err)
}
ds := emitDWARF(img, "test_amd64.s", cfiAMD64)
r := &ulebIter{b: ds.debugLine}
r.uint32At(t) // unit_length
if v := binary.LittleEndian.Uint16(ds.debugLine[4:]); v != 5 {
t.Fatalf("version = %d, want 5", v)
}
r.i = 6
r.byteAt(t) // address_size
r.byteAt(t) // segment_selector_size
r.uint32At(t) // header_length
r.byteAt(t) // minimum_instruction_length
r.byteAt(t) // maximum_ops_per_instruction
r.byteAt(t) // default_is_stmt
r.byteAt(t) // line_base
r.byteAt(t) // line_range
opcodeBase := r.byteAt(t)
for range int(opcodeBase) - 1 {
r.byteAt(t) // standard opcode lengths
}
// Directory table (DWARF5 §6.2.4).
if n := r.byteAt(t); n != 1 {
t.Fatalf("directory_entry_format_count = %d, want 1", n)
}
if lnct := r.uleb(t); lnct != dwLnctPath {
t.Errorf("directory content type = %#x, want DW_LNCT_path", lnct)
}
if form := r.uleb(t); form != dwFormLineStrp {
t.Errorf("directory form = %#x, want DW_FORM_line_strp", form)
}
if n := r.uleb(t); n != 1 {
t.Fatalf("directories_count = %d, want 1", n)
}
if off := r.uint32At(t); off != 0 {
t.Errorf("compilation directory line_strp = %d, want 0 (the empty string)", off)
}
// File table (DWARF5 §6.2.5).
if n := r.byteAt(t); n != 2 {
t.Fatalf("file_name_entry_format_count = %d, want 2", n)
}
if lnct := r.uleb(t); lnct != dwLnctPath {
t.Errorf("file content type = %#x, want DW_LNCT_path", lnct)
}
if form := r.uleb(t); form != dwFormLineStrp {
t.Errorf("file path form = %#x, want DW_FORM_line_strp", form)
}
if lnct := r.uleb(t); lnct != dwLnctDirIndex {
t.Errorf("file content type = %#x, want DW_LNCT_directory_index", lnct)
}
if form := r.uleb(t); form != dwFormUdata {
t.Errorf("file dir-index form = %#x, want DW_FORM_udata", form)
}
if n := r.uleb(t); n != 1 {
t.Fatalf("file_names_count = %d, want 1", n)
}
strOff := r.uint32At(t)
if dirIdx := r.uleb(t); dirIdx != 0 {
t.Errorf("file directory index = %d, want 0", dirIdx)
}
// The file entry's line_strp must resolve to the source name.
end := int(strOff) + len("test_amd64.s")
if int(strOff) >= len(ds.debugLineStr) || !bytes.Equal(ds.debugLineStr[strOff:end], []byte("test_amd64.s")) {
t.Errorf("file entry line_strp %d does not name the source: %q", strOff, ds.debugLineStr)
}
// The fixed header fields: address_size 8 and a header_length that
// points just past the file table (the patch site is offset 8 in the
// v5 header, and the field counts from its own end).
if ds.debugLine[6] != 8 || ds.debugLine[7] != 0 {
t.Errorf("address_size/segment_selector = %d/%d, want 8/0", ds.debugLine[6], ds.debugLine[7])
}
if hl := binary.LittleEndian.Uint32(ds.debugLine[8:]); hl != uint32(r.i-12) {
t.Errorf("header_length = %d, want %d (the byte after the file table is %d)", hl, r.i-12, r.i)
}
}
// TestDwarfFrameCIEArch checks the shared CIE carries each architecture's
// stack-pointer and return-address registers: the values the Go linker
// writes (cmd/link/internal/<arch>/l.go dwarfRegSP/dwarfRegLR).
func TestDwarfFrameCIEArch(t *testing.T) {
for _, tc := range []struct {
name string
cfi cfiArch
}{
{"amd64", cfiAMD64},
{"arm64", cfiARM64},
{"riscv64", cfiRISCV64},
{"loong64", cfiLOONG64},
} {
frame := dwarfBuildFrameSection(&Image{}, tc.cfi, &dwarfSections{})
r := &ulebIter{b: frame}
r.uint32At(t) // length
if cid := r.uint32At(t); cid != 0xFFFFFFFF {
t.Errorf("%s: CIE id = %#x, want 0xffffffff", tc.name, cid)
}
if v := r.byteAt(t); v != 3 {
t.Errorf("%s: CIE version = %d, want 3", tc.name, v)
}
if aug := r.byteAt(t); aug != 0 {
t.Errorf("%s: CIE augmentation = %d, want 0", tc.name, aug)
}
if ca := r.uleb(t); ca != 1 {
t.Errorf("%s: code alignment = %d, want 1", tc.name, ca)
}
if da := r.sleb(t); da != -8 {
t.Errorf("%s: data alignment = %d, want -8 (signed LEB128, not zigzag)", tc.name, da)
}
if ra := r.uleb(t); ra != uint64(tc.cfi.raReg) {
t.Errorf("%s: return-address register = %d, want %d", tc.name, ra, tc.cfi.raReg)
}
if op := r.byteAt(t); op != 0x0c {
t.Errorf("%s: expected DW_CFA_def_cfa, got opcode %#x", tc.name, op)
}
if cfa := r.uleb(t); cfa != uint64(tc.cfi.cfaReg) {
t.Errorf("%s: CFA register = %d, want %d", tc.name, cfa, tc.cfi.cfaReg)
}
if off := r.uleb(t); off != 0 {
t.Errorf("%s: CFA offset = %d, want 0", tc.name, off)
}
}
}
func TestEmitDWARF(t *testing.T) { func TestEmitDWARF(t *testing.T) {
src := `#include "textflag.h" src := `#include "textflag.h"
TEXT ·add(SB), NOSPLIT, $0-24 TEXT ·add(SB), NOSPLIT, $0-24
@@ -27,7 +329,7 @@ TEXT ·add(SB), NOSPLIT, $0-24
t.Fatalf("assemble: %v", err) t.Fatalf("assemble: %v", err)
} }
ds := emitDWARF(img, "test_amd64.s") ds := emitDWARF(img, "test_amd64.s", cfiAMD64)
// .debug_abbrev must not be empty and must start with abbrev code 1. // .debug_abbrev must not be empty and must start with abbrev code 1.
if len(ds.debugAbbrev) == 0 { if len(ds.debugAbbrev) == 0 {
@@ -68,14 +370,3 @@ TEXT ·add(SB), NOSPLIT, $0-24
t.Fatal("no .debug_info relocations") t.Fatal("no .debug_info relocations")
} }
} }
func TestDwarfAbbrevTable(t *testing.T) {
abbrev := dwarfAbbrevTable()
if len(abbrev) == 0 {
t.Fatal("empty abbrev table")
}
// Must end with a zero byte (end of table).
if abbrev[len(abbrev)-1] != 0 {
t.Fatalf("abbrev table last byte = %d, want 0", abbrev[len(abbrev)-1])
}
}
asm/elf_test.go
+442
View File
@@ -12,6 +12,7 @@ import (
"path/filepath" "path/filepath"
"testing" "testing"
"sourcedock.dev/petrbalvin/gasm-devkit/ast"
"sourcedock.dev/petrbalvin/gasm-devkit/parser" "sourcedock.dev/petrbalvin/gasm-devkit/parser"
) )
@@ -211,6 +212,75 @@ func TestELFObject(t *testing.T) {
} }
} }
// TestELFObjectTLSGuardReloc checks that a non-NOSPLIT function's stack
// guard carries an R_X86_64_TPOFF32 relocation against the null symbol in
// .rela.text. The serialisation must honour the record's type field: a
// hardcoded R_X86_64_PC32 mislinks the TLS load as an ordinary
// PC-relative reference.
func TestELFObjectTLSGuardReloc(t *testing.T) {
f, errs := parser.Parse("g_amd64.s", `
#include "textflag.h"
TEXT ·grow(SB), $0
CALL ·other(SB)
RET
TEXT ·other(SB), NOSPLIT, $0
RET
`)
if len(errs) > 0 {
t.Fatalf("parse: %v", errs)
}
img, err := AssembleFile(f)
if err != nil {
t.Fatalf("AssembleFile: %v", err)
}
var haveTLS bool
for _, fn := range img.Funcs {
for _, r := range fn.Relocs {
if r.Kind == RelTLSLE {
haveTLS = true
}
}
}
if !haveTLS {
t.Fatal("test source produced no RelTLSLE relocation")
}
obj, err := img.ELFObject()
if err != nil {
t.Fatalf("ELFObject: %v", err)
}
ef, err := elf.NewFile(bytes.NewReader(obj))
if err != nil {
t.Fatalf("parse emitted object: %v", err)
}
defer ef.Close()
relaSec := ef.Section(".rela.text")
if relaSec == nil {
t.Fatal("missing .rela.text")
}
raw, err := relaSec.Data()
if err != nil {
t.Fatal(err)
}
found := false
for i := 0; i+24 <= len(raw); i += 24 {
e := raw[i:]
info := binary.LittleEndian.Uint64(e[8:])
typ := info & 0xffffffff
sym := int(info >> 32)
if typ == uint64(elf.R_X86_64_TPOFF32) {
found = true
if sym != 0 {
t.Errorf("TPOFF32 relocation against symbol %d, want 0 (the null symbol)", sym)
}
}
}
if !found {
t.Errorf("no R_X86_64_TPOFF32 relocation in .rela.text (%d bytes)", len(raw))
}
}
// TestELFObjectNoRelocations checks a file with no static-symbol references // TestELFObjectNoRelocations checks a file with no static-symbol references
// emits a valid object without a .rela.text section. // emits a valid object without a .rela.text section.
func TestELFObjectNoRelocations(t *testing.T) { func TestELFObjectNoRelocations(t *testing.T) {
@@ -253,6 +323,238 @@ TEXT ·nop(SB), NOSPLIT, $0
} }
} }
// elfSectionHeaderCount returns the e_shnum the ELF header declares.
func elfSectionHeaderCount(t *testing.T, obj []byte) int {
t.Helper()
return int(binary.LittleEndian.Uint16(obj[60:]))
}
// checkELFSectionAccounting verifies the number of section headers the
// writer physically laid out equals e_shnum: every DWARF section written
// after .shstrtab must be counted, or the last ones (always .debug_frame)
// are invisible to every consumer, debug/elf included.
func checkELFSectionAccounting(t *testing.T, obj []byte) {
t.Helper()
shoff := int(binary.LittleEndian.Uint64(obj[40:]))
shentsize := int(binary.LittleEndian.Uint16(obj[58:]))
shnum := elfSectionHeaderCount(t, obj)
if shentsize != 64 {
t.Fatalf("e_shentsize = %d, want 64", shentsize)
}
if (len(obj)-shoff)%shentsize != 0 {
t.Fatalf("section header table is not a whole number of entries: shoff=%d len=%d", shoff, len(obj))
}
if present := (len(obj) - shoff) / shentsize; present != shnum {
t.Errorf("e_shnum = %d but %d section headers are laid out", shnum, present)
}
}
// TestELFDWARFSectionAccounting runs the header accounting check over all
// four architecture emitters, and additionally checks the .debug_frame
// section is visible (its data aligned as its header declares).
func TestELFDWARFSectionAccounting(t *testing.T) {
parse := func(name, src string) *ast.File {
f, errs := parser.Parse(name, src)
if len(errs) > 0 {
t.Fatalf("parse %s: %v", name, errs)
}
return f
}
cases := []struct {
name string
img *Image
emit func(*Image) ([]byte, error)
}{
{"amd64", elfTestImage(t), (*Image).ELFObject},
{"arm64", mustImage(t, func() (*Image, error) {
return AssembleFileARM64(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
`))
}), (*Image).ELFAARCH64Object},
{"riscv64", mustImage(t, func() (*Image, error) {
return AssembleFileRISCV(parse("k_riscv64.s", `
#include "textflag.h"
TEXT ·sb(SB), NOSPLIT, $0-0
MOV $answer<>(SB), X10
RET
GLOBL answer<>(SB), RODATA, $8
DATA answer<>+0(SB)/8, $42
`))
}), (*Image).ELFRISCVObject},
{"loong64", mustImage(t, func() (*Image, error) {
return AssembleFileLOONG64(parse("k_loong64.s", `
#include "textflag.h"
TEXT ·add(SB), NOSPLIT, $0-24
MOVV a+0(FP), R4
MOVV b+8(FP), R5
ADDV R5, R4, R4
MOVV R4, ret+16(FP)
RET
`))
}), (*Image).ELFLOONG64Object},
}
for _, tc := range cases {
obj, err := tc.emit(tc.img)
if err != nil {
t.Fatalf("%s: emit: %v", tc.name, err)
}
checkELFSectionAccounting(t, obj)
ef, err := elf.NewFile(bytes.NewReader(obj))
if err != nil {
t.Fatalf("%s: parse emitted object: %v", tc.name, err)
}
frame := ef.Section(".debug_frame")
if frame == nil {
t.Errorf("%s: .debug_frame invisible to debug/elf (e_shnum too small?)", tc.name)
ef.Close()
continue
}
if frame.Offset%8 != 0 || frame.Addralign != 8 {
t.Errorf("%s: .debug_frame offset %d align %d, want offset%%8==0 align 8", tc.name, frame.Offset, frame.Addralign)
}
ef.Close()
}
}
func mustImage(t *testing.T, f func() (*Image, error)) *Image {
t.Helper()
img, err := f()
if err != nil {
t.Fatal(err)
}
return img
}
// TestELFDWARFRelocations checks the .rela.debug_info and .rela.debug_line
// sections exist and carry absolute 64-bit relocations against the
// function symbols, with r_offsets inside their target sections.
func TestELFDWARFRelocations(t *testing.T) {
img := elfTestImage(t)
obj, err := img.ELFObject()
if err != nil {
t.Fatalf("ELFObject: %v", err)
}
ef, err := elf.NewFile(bytes.NewReader(obj))
if err != nil {
t.Fatalf("parse emitted object: %v", err)
}
defer ef.Close()
// The DWARF must record the assembled file's path (threaded through
// Image.SourcePath), not a placeholder name.
info, err := ef.Section(".debug_info").Data()
if err != nil {
t.Fatal(err)
}
if img.SourcePath != "t_amd64.s" || !bytes.Contains(info, []byte(img.SourcePath)) {
t.Errorf("DWARF compilation unit does not name the source %q", img.SourcePath)
}
for _, tc := range []struct {
rela string
target string
want uint32
}{
{".rela.debug_info", ".debug_info", rX8664Abs64},
{".rela.debug_line", ".debug_line", rX8664Abs64},
{".rela.debug_frame", ".debug_frame", rX8664Abs64},
} {
rs := ef.Section(tc.rela)
if rs == nil {
t.Fatalf("missing %s", tc.rela)
}
if rs.Type != elf.SHT_RELA {
t.Errorf("%s: type %v, want SHT_RELA", tc.rela, rs.Type)
}
target := ef.Section(tc.target)
if target == nil {
t.Fatalf("missing %s", tc.target)
}
if rs.Link == 0 || ef.Sections[rs.Info] != target {
t.Errorf("%s: link %d info %d, want the symtab and %s", tc.rela, rs.Link, rs.Info, tc.target)
}
b, err := rs.Data()
if err != nil {
t.Fatal(err)
}
// .debug_line has one address per function; .debug_info adds the
// compile unit's own low_pc.
want := len(img.Funcs)
if tc.target == ".debug_info" {
want++
}
if len(b)/24 != want {
t.Errorf("%s: %d entries, want %d", tc.rela, len(b)/24, want)
}
for i := 0; i+24 <= len(b); i += 24 {
r_offset := binary.LittleEndian.Uint64(b[i:])
info := binary.LittleEndian.Uint64(b[i+8:])
typ := uint32(info)
sym := int(info >> 32)
if typ != tc.want {
t.Errorf("%s entry %d: type %d, want R_X86_64_64 (%d)", tc.rela, i/24, typ, tc.want)
}
if r_offset >= uint64(target.Size) {
t.Errorf("%s entry %d: r_offset %d outside %s (%d bytes)", tc.rela, i/24, r_offset, tc.target, target.Size)
}
if sym == 0 {
t.Errorf("%s entry %d: against the null symbol", tc.rela, i/24)
}
}
}
}
// TestELFDataOnly checks a source with GLOBL data and no TEXT emits a valid
// ELF object: the DWARF compilation unit of a code-less image has no
// function to relocate against and must not reach for one.
func TestELFDataOnly(t *testing.T) {
f, errs := parser.Parse("d0_amd64.s", `
GLOBL table<>(SB), RODATA, $8
DATA table<>+0(SB)/8, $12345
`)
if len(errs) > 0 {
t.Fatalf("parse: %v", errs)
}
img, err := AssembleFile(f)
if err != nil {
t.Fatalf("AssembleFile: %v", err)
}
obj, err := img.ELFObject()
if err != nil {
t.Fatalf("ELFObject: %v", err)
}
checkELFSectionAccounting(t, obj)
ef, err := elf.NewFile(bytes.NewReader(obj))
if err != nil {
t.Fatalf("parse emitted object: %v", err)
}
defer ef.Close()
syms, err := ef.Symbols()
if err != nil {
t.Fatal(err)
}
found := false
for _, s := range syms {
if s.Name == "table" && s.Size == 8 {
found = true
}
}
if !found {
t.Errorf("data symbol table missing: %v", syms)
}
if ef.Section(".rela.debug_info") != nil || ef.Section(".rela.debug_line") != nil {
t.Error("data-only image must not emit DWARF address relocations")
}
}
// TestELFLinkAndRun is the end-to-end check: assemble the test functions, // TestELFLinkAndRun is the end-to-end check: assemble the test functions,
// link the emitted object with a C driver that defines the external symbol, // link the emitted object with a C driver that defines the external symbol,
// and run the result. Skipped when no C compiler is available. // and run the result. Skipped when no C compiler is available.
@@ -307,4 +609,144 @@ int main(void) {
if got := string(run); got != "42 42 7\n" { if got := string(run); got != "42 42 7\n" {
t.Errorf("output %q, want \"42 42 7\\n\"", got) t.Errorf("output %q, want \"42 42 7\\n\"", got)
} }
// The DWARF addresses must have resolved at link time: the .debug_info
// placeholders were carried by .rela.debug_info, so every subprogram's
// low_pc must now equal its linked symbol address.
bin, err := os.ReadFile(appPath)
if err != nil {
t.Fatal(err)
}
lef, err := elf.NewFile(bytes.NewReader(bin))
if err != nil {
t.Fatalf("parse linked binary: %v", err)
}
defer lef.Close()
syms, err := lef.Symbols()
if err != nil {
t.Fatal(err)
}
addrByName := map[string]uint64{}
for _, s := range syms {
if elf.ST_TYPE(s.Info) == elf.STT_FUNC && s.Value != 0 {
addrByName[s.Name] = s.Value
}
}
lowPCs := dwarfSubprogramLowPCs(t, lef)
if len(lowPCs) == 0 {
t.Fatal("no subprogram DW_AT_low_pc parsed from the linked binary")
}
for name, pc := range lowPCs {
addr, ok := addrByName[name]
if !ok {
t.Errorf("subprogram %q not in the linked symbol table", name)
continue
}
if pc != addr {
t.Errorf("subprogram %q: DW_AT_low_pc = %#x, linked address %#x (DWARF relocation unresolved)", name, pc, addr)
}
}
}
// dwarfSubprogramLowPCs walks the linked binary's .debug_info with its own
// .debug_abbrev and returns each DW_TAG_subprogram's DW_AT_low_pc by name.
func dwarfSubprogramLowPCs(t *testing.T, ef *elf.File) map[string]uint64 {
t.Helper()
abbrevSec := ef.Section(".debug_abbrev")
infoSec := ef.Section(".debug_info")
if abbrevSec == nil || infoSec == nil {
t.Fatal("linked binary lacks .debug_abbrev or .debug_info")
}
abbrev, err := abbrevSec.Data()
if err != nil {
t.Fatal(err)
}
info, err := infoSec.Data()
if err != nil {
t.Fatal(err)
}
abs := parseAbbrevs(t, abbrev)
le := binary.LittleEndian
out := map[string]uint64{}
r := &ulebIter{b: info}
r.uint32At(t) // unit_length
if v := le.Uint16(info[4:]); v != 5 {
t.Fatalf(".debug_info version %d, want 5", v)
}
r.i = 6
r.byteAt(t) // unit_type
r.byteAt(t) // address_size
r.uint32At(t) // debug_abbrev_offset
var name string
var lowPC uint64
for r.i < len(r.b) {
code := r.uleb(t)
if code == 0 {
continue // end of the CU's children
}
ab, ok := abs[code]
if !ok {
t.Fatalf("unknown abbreviation code %d", code)
}
name, lowPC = "", 0
for _, a := range ab.attrs {
switch a.attr {
case dwAtName:
readFormKeep(t, r, a.form, &name, nil)
case dwAtLowPC:
readFormKeep(t, r, a.form, nil, &lowPC)
default:
readFormSkip(t, r, a.form)
}
}
if ab.tag == dwTagSubprog && name != "" {
out[name] = lowPC
}
}
return out
}
// readFormKeep reads one DIE attribute value, keeping a string or an
// address into the pointer it was given (nil keeps nothing).
func readFormKeep(t *testing.T, r *ulebIter, form uint64, name *string, addr *uint64) {
t.Helper()
switch form {
case dwFormString:
end := r.i
for end < len(r.b) && r.b[end] != 0 {
end++
}
if name != nil {
*name = string(r.b[r.i:end])
}
r.i = end + 1
case dwFormAddr:
if addr != nil {
*addr = binary.LittleEndian.Uint64(r.b[r.i:])
}
r.i += 8
default:
readFormSkip(t, r, form)
}
}
func readFormSkip(t *testing.T, r *ulebIter, form uint64) {
t.Helper()
switch form {
case dwFormString:
for r.i < len(r.b) && r.b[r.i] != 0 {
r.i++
}
r.i++
case dwFormAddr, dwFormData8:
r.i += 8
case dwFormSecOff:
r.i += 4
case dwFormExprloc:
r.i += int(r.uleb(t))
case dwFormData1, 0x0c:
r.i++
default:
t.Fatalf("unsupported form %#x", form)
}
} }
asm/elfarm64.go
+74 -22
View File
@@ -81,10 +81,15 @@ func (img *Image) ELFAARCH64Object() ([]byte, error) {
} }
// Build relocations. Each SB reference is an ADRP pair: // Build relocations. Each SB reference is an ADRP pair:
// ADRP Rd, 0 → R_AARCH64_ADR_PREL_PG_HI21 // ADRP Rd, 0 → R_AARCH64_ADR_PREL_PG_HI21 at the ADRP
// ADD → R_AARCH64_ADD_ABS_LO12_NC // ADD → R_AARCH64_ADD_ABS_LO12_NC at the ADD word
// LDR/STR X → R_AARCH64_LDST64_ABS_LO12_NC // LDR/STR X → R_AARCH64_LDST64_ABS_LO12_NC at the LDR/STR word
// BL → R_AARCH64_CALL26 // BL → R_AARCH64_CALL26
// cmd/link's own conversion emits the HI21 at sectoff and the LO12 at
// sectoff+4 (cmd/link/internal/arm64/asm.go), so the ADD or load word
// carries the page-offset relocation, never a second HI21. The
// assembler records two RelArm64Addr relocs per ADRP+ADD pair (one per
// word), so the second of the pair is consumed here.
// Addends stay raw: ADR_PREL_PG_HI21 and the ABS_LO12_NC forms resolve // Addends stay raw: ADR_PREL_PG_HI21 and the ABS_LO12_NC forms resolve
// against S+A, and CALL26 branches take the branch instruction's own // against S+A, and CALL26 branches take the branch instruction's own
// place as the PC-relative base, so subtracting the field width (the // place as the PC-relative base, so subtracting the field width (the
@@ -97,28 +102,34 @@ func (img *Image) ELFAARCH64Object() ([]byte, error) {
} }
var relas []elfRela var relas []elfRela
for _, fn := range img.Funcs { for _, fn := range img.Funcs {
for _, r := range fn.Relocs { for i := 0; i < len(fn.Relocs); i++ {
r := fn.Relocs[i]
idx, ok := symIdx[r.Name] idx, ok := symIdx[r.Name]
if !ok { if !ok {
return nil, fmt.Errorf("relocation references unknown symbol %q", r.Name) return nil, fmt.Errorf("relocation references unknown symbol %q", r.Name)
} }
var typ uint32 switch r.Kind {
switch { case RelArm64Branch:
case r.Kind == RelArm64Branch: relas = append(relas, elfRela{
typ = rArm64Call26 off: uint64(fn.Offset + r.Off), typ: rArm64Call26, sym: idx, addend: r.Addend,
case r.Kind == RelArm64LDST64 && r.Off%4 == 4: })
typ = rArm64Ldst64Lo12NC case RelArm64Addr:
case r.Kind == RelArm64Addr && r.Off%4 == 4: // ADRP+ADD: the pair's second reloc (at Off+4) is the
typ = rArm64AddAbsLo12NC // assembler's twin of the same pair; skip it.
relas = append(relas,
elfRela{off: uint64(fn.Offset + r.Off), typ: rArm64PrelPgHi21, sym: idx, addend: r.Addend},
elfRela{off: uint64(fn.Offset + r.Off + 4), typ: rArm64AddAbsLo12NC, sym: idx, addend: r.Addend},
)
i++
case RelArm64LDST64:
// ADRP+LDR/STR: one assembler reloc covers the pair.
relas = append(relas,
elfRela{off: uint64(fn.Offset + r.Off), typ: rArm64PrelPgHi21, sym: idx, addend: r.Addend},
elfRela{off: uint64(fn.Offset + r.Off + 4), typ: rArm64Ldst64Lo12NC, sym: idx, addend: r.Addend},
)
default: default:
typ = rArm64PrelPgHi21 return nil, fmt.Errorf("relocation kind %v unsupported in ELF emission", r.Kind)
} }
relas = append(relas, elfRela{
off: uint64(fn.Offset + r.Off),
typ: typ,
sym: idx,
addend: r.Addend,
})
} }
} }
@@ -193,15 +204,32 @@ func (img *Image) ELFAARCH64Object() ([]byte, error) {
shstrOff := len(out) shstrOff := len(out)
out = append(out, stSections.bytes()...) out = append(out, stSections.bytes()...)
// DWARF debug sections. // DWARF debug sections; the address placeholders they leave are carried
// as .rela.debug_info/.rela.debug_line entries the system linker applies.
dwAlign := func(n int) { dwAlign := func(n int) {
for len(out)%n != 0 { for len(out)%n != 0 {
out = append(out, 0) out = append(out, 0)
} }
} }
dw := appendDWARFSections(&out, img, "gasm.s", symIdx, dwAlign) dw := appendDWARFSections(&out, img, dwarfSourceName(img), symIdx, dwAlign, cfiARM64)
dwarfStart := 0 // section index of .debug_abbrev, set when DWARF is present
if dw != nil { if dw != nil {
nSections += 4 // Five DWARF sections: .debug_abbrev, .debug_info, .debug_line,
// .debug_line_str and .debug_frame (the CIE is unconditional, so
// the frame section is always present), plus the relocation
// sections below when they carry entries.
dwarfStart = nSections
nSections += 5
appendDWARFRelas(&out, dw, rAARCH64Abs64, dwAlign)
if dw.infoRelaCount > 0 {
nSections++
}
if dw.lineRelaCount > 0 {
nSections++
}
if dw.frameRelaCount > 0 {
nSections++
}
} }
align(8) align(8)
@@ -230,13 +258,37 @@ func (img *Image) ELFAARCH64Object() ([]byte, error) {
putSh(".rela.text", shtRela, 0, relaOff, 24*len(relas), secSymtab, secText, 8, 24) 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) putSh(".shstrtab", shtStrtab, 0, shstrOff, len(stSections.bytes()), 0, 0, 1, 0)
// DWARF section headers; their indices follow the write order.
if dw != nil { if dw != nil {
// secIdx is a running section index: each putSh below emits the
// next header, and the sh_info of a .rela section names the index
// of the section it relocates.
secIdx := dwarfStart
putSh(".debug_abbrev", shtProgbits, 0, dw.abbrevOff, dw.abbrevSize, 0, 0, 1, 0) putSh(".debug_abbrev", shtProgbits, 0, dw.abbrevOff, dw.abbrevSize, 0, 0, 1, 0)
secIdx++
putSh(".debug_info", shtProgbits, 0, dw.infoOff, dw.infoSize, 0, 0, 1, 0) putSh(".debug_info", shtProgbits, 0, dw.infoOff, dw.infoSize, 0, 0, 1, 0)
secInfoIdx := secIdx
secIdx++
if dw.infoRelaCount > 0 {
putSh(".rela.debug_info", shtRela, 0, dw.infoRelaOff, 24*dw.infoRelaCount, secSymtab, secInfoIdx, 8, 24)
secIdx++
}
putSh(".debug_line", shtProgbits, 0, dw.lineOff, dw.lineSize, 0, 0, 1, 0) putSh(".debug_line", shtProgbits, 0, dw.lineOff, dw.lineSize, 0, 0, 1, 0)
secLineIdx := secIdx
secIdx++
if dw.lineRelaCount > 0 {
putSh(".rela.debug_line", shtRela, 0, dw.lineRelaOff, 24*dw.lineRelaCount, secSymtab, secLineIdx, 8, 24)
secIdx++
}
putSh(".debug_line_str", shtProgbits, 0, dw.lineStrOff, dw.lineStrSize, 0, 0, 1, 0) putSh(".debug_line_str", shtProgbits, 0, dw.lineStrOff, dw.lineStrSize, 0, 0, 1, 0)
secIdx++
if dw.frameSize > 0 { if dw.frameSize > 0 {
putSh(".debug_frame", shtProgbits, 0, dw.frameOff, dw.frameSize, 0, 0, 8, 0) putSh(".debug_frame", shtProgbits, 0, dw.frameOff, dw.frameSize, 0, 0, 8, 0)
secFrameIdx := secIdx
secIdx++
if dw.frameRelaCount > 0 {
putSh(".rela.debug_frame", shtRela, 0, dw.frameRelaOff, 24*dw.frameRelaCount, secSymtab, secFrameIdx, 8, 24)
}
} }
} }
asm/elfarm64_test.go
+58 -1
View File
@@ -6,6 +6,7 @@ package asm
import ( import (
"bytes" "bytes"
"debug/elf" "debug/elf"
"encoding/binary"
"testing" "testing"
"sourcedock.dev/petrbalvin/gasm-devkit/parser" "sourcedock.dev/petrbalvin/gasm-devkit/parser"
@@ -28,6 +29,7 @@ TEXT ·add(SB), NOSPLIT, $0-24
TEXT ·getanswer(SB), NOSPLIT, $0-8 TEXT ·getanswer(SB), NOSPLIT, $0-8
MOVD answer<>(SB), R4 MOVD answer<>(SB), R4
MOVD $answer<>(SB), R5
MOVD R4, ret+0(FP) MOVD R4, ret+0(FP)
RET RET
@@ -102,8 +104,63 @@ DATA answer<>+0(SB)/8, $42
// Check that .rela.text exists (getanswer has SB reference). // Check that .rela.text exists (getanswer has SB reference).
relaText := ef.Section(".rela.text") relaText := ef.Section(".rela.text")
if relaText == nil { if relaText == nil {
t.Error("missing .rela.text section") 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 // TestELFAARCH64ObjectNoRelocations checks the ELF output when there are no
asm/elfloong64.go
+49 -3
View File
@@ -13,6 +13,12 @@ import (
const ( const (
emLOONGARCH = 258 // EM_LOONGARCH emLOONGARCH = 258 // EM_LOONGARCH
// EF_LOONGARCH_ABI_DOUBLE_FLOAT | EF_LOONGARCH_OBJABI_V1: the flags the
// Go toolchain writes (cmd/link/internal/ld/elf.go: Flags = 0x43 for
// Loong64). System linkers refuse to merge ET_REL objects whose float
// ABI differs, so 0 (soft-float) would make the object unlinkable.
efLarchAbiDoubleObjV1 = 0x43
// LoongArch relocation types (the ELF psABI). // LoongArch relocation types (the ELF psABI).
rLarchPCALAHI20 = 71 // R_LARCH_PCALA_HI20 (pcalau12i) rLarchPCALAHI20 = 71 // R_LARCH_PCALA_HI20 (pcalau12i)
rLarchPCALALO12 = 72 // R_LARCH_PCALA_LO12 (addi.d/ld/st) rLarchPCALALO12 = 72 // R_LARCH_PCALA_LO12 (addi.d/ld/st)
@@ -187,9 +193,25 @@ func (img *Image) ELFLOONG64Object() ([]byte, error) {
out = append(out, 0) out = append(out, 0)
} }
} }
dw := appendDWARFSections(&out, img, "gasm.s", symIdx, dwAlign) dw := appendDWARFSections(&out, img, dwarfSourceName(img), symIdx, dwAlign, cfiLOONG64)
dwarfStart := 0 // section index of .debug_abbrev, set when DWARF is present
if dw != nil { if dw != nil {
nSections += 4 // Five DWARF sections: .debug_abbrev, .debug_info, .debug_line,
// .debug_line_str and .debug_frame (the CIE is unconditional, so
// the frame section is always present), plus the relocation
// sections below when they carry entries.
dwarfStart = nSections
nSections += 5
appendDWARFRelas(&out, dw, rLarchAbs64, dwAlign)
if dw.infoRelaCount > 0 {
nSections++
}
if dw.lineRelaCount > 0 {
nSections++
}
if dw.frameRelaCount > 0 {
nSections++
}
} }
align(8) align(8)
@@ -218,13 +240,37 @@ func (img *Image) ELFLOONG64Object() ([]byte, error) {
putSh(".rela.text", shtRela, 0, relaOff, 24*len(relas), secSymtab, secText, 8, 24) 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) putSh(".shstrtab", shtStrtab, 0, shstrOff, len(stSections.bytes()), 0, 0, 1, 0)
// DWARF section headers; their indices follow the write order.
if dw != nil { if dw != nil {
// secIdx is a running section index: each putSh below emits the
// next header, and the sh_info of a .rela section names the index
// of the section it relocates.
secIdx := dwarfStart
putSh(".debug_abbrev", shtProgbits, 0, dw.abbrevOff, dw.abbrevSize, 0, 0, 1, 0) putSh(".debug_abbrev", shtProgbits, 0, dw.abbrevOff, dw.abbrevSize, 0, 0, 1, 0)
secIdx++
putSh(".debug_info", shtProgbits, 0, dw.infoOff, dw.infoSize, 0, 0, 1, 0) putSh(".debug_info", shtProgbits, 0, dw.infoOff, dw.infoSize, 0, 0, 1, 0)
secInfoIdx := secIdx
secIdx++
if dw.infoRelaCount > 0 {
putSh(".rela.debug_info", shtRela, 0, dw.infoRelaOff, 24*dw.infoRelaCount, secSymtab, secInfoIdx, 8, 24)
secIdx++
}
putSh(".debug_line", shtProgbits, 0, dw.lineOff, dw.lineSize, 0, 0, 1, 0) putSh(".debug_line", shtProgbits, 0, dw.lineOff, dw.lineSize, 0, 0, 1, 0)
secLineIdx := secIdx
secIdx++
if dw.lineRelaCount > 0 {
putSh(".rela.debug_line", shtRela, 0, dw.lineRelaOff, 24*dw.lineRelaCount, secSymtab, secLineIdx, 8, 24)
secIdx++
}
putSh(".debug_line_str", shtProgbits, 0, dw.lineStrOff, dw.lineStrSize, 0, 0, 1, 0) putSh(".debug_line_str", shtProgbits, 0, dw.lineStrOff, dw.lineStrSize, 0, 0, 1, 0)
secIdx++
if dw.frameSize > 0 { if dw.frameSize > 0 {
putSh(".debug_frame", shtProgbits, 0, dw.frameOff, dw.frameSize, 0, 0, 8, 0) putSh(".debug_frame", shtProgbits, 0, dw.frameOff, dw.frameSize, 0, 0, 8, 0)
secFrameIdx := secIdx
secIdx++
if dw.frameRelaCount > 0 {
putSh(".rela.debug_frame", shtRela, 0, dw.frameRelaOff, 24*dw.frameRelaCount, secSymtab, secFrameIdx, 8, 24)
}
} }
} }
@@ -237,7 +283,7 @@ func (img *Image) ELFLOONG64Object() ([]byte, error) {
le.PutUint64(hdr[24:], 0) le.PutUint64(hdr[24:], 0)
le.PutUint64(hdr[32:], 0) le.PutUint64(hdr[32:], 0)
le.PutUint64(hdr[40:], uint64(shoff)) le.PutUint64(hdr[40:], uint64(shoff))
le.PutUint32(hdr[48:], 0) le.PutUint32(hdr[48:], efLarchAbiDoubleObjV1)
le.PutUint16(hdr[52:], 64) le.PutUint16(hdr[52:], 64)
le.PutUint16(hdr[54:], 0) le.PutUint16(hdr[54:], 0)
le.PutUint16(hdr[56:], 0) le.PutUint16(hdr[56:], 0)
asm/elfloong64_test.go
+5
View File
@@ -55,6 +55,11 @@ DATA answer<>+0(SB)/8, $42
if ef.Type != elf.ET_REL || ef.Machine != elf.EM_LOONGARCH { if ef.Type != elf.ET_REL || ef.Machine != elf.EM_LOONGARCH {
t.Errorf("type/machine = %v/%v, want ET_REL/EM_LOONGARCH", ef.Type, ef.Machine) t.Errorf("type/machine = %v/%v, want ET_REL/EM_LOONGARCH", ef.Type, ef.Machine)
} }
// The double-float ABI plus OBJABI_V1 flags the Go toolchain writes;
// system linkers refuse ABI-mismatched merges.
if flags := binary.LittleEndian.Uint32(obj[48:]); flags != efLarchAbiDoubleObjV1 {
t.Errorf("e_flags = %#x, want %#x (double-float, OBJABI_V1)", flags, efLarchAbiDoubleObjV1)
}
text := ef.Section(".text") text := ef.Section(".text")
data := ef.Section(".data") data := ef.Section(".data")
asm/elfriscv.go
+60 -11
View File
@@ -13,8 +13,13 @@ import (
const ( const (
emRISCV = 243 // EM_RISCV emRISCV = 243 // EM_RISCV
// EF_RISCV_FLOAT_ABI_DOUBLE: the double-precision float ABI the Go
// toolchain targets (cmd/link/internal/ld/elf.go writes Flags = 0x4 for
// RISCV64). System linkers refuse to merge ET_REL objects whose float
// ABI differs, so 0 (soft-float) would make the object unlinkable.
efRISCVFloatAbiDouble = 0x4
// RISC-V relocation types. // RISC-V relocation types.
rRISCV32 = 1
rRISCVJAL = 17 // R_RISCV_JAL rRISCVJAL = 17 // R_RISCV_JAL
rRISCVPCRELHI20 = 23 // R_RISCV_PCREL_HI20 rRISCVPCRELHI20 = 23 // R_RISCV_PCREL_HI20
rRISCVPCRELLO12I = 24 // R_RISCV_PCREL_LO12_I rRISCVPCRELLO12I = 24 // R_RISCV_PCREL_LO12_I
@@ -83,9 +88,14 @@ func (img *Image) ELFRISCVObject() ([]byte, error) {
// Build relocations. Each SB reference is an AUIPC + second-instruction // Build relocations. Each SB reference is an AUIPC + second-instruction
// pair carrying a single relocation kind; the ELF writer expands it into // pair carrying a single relocation kind; the ELF writer expands it into
// the R_RISCV_PCREL_HI20 + R_RISCV_PCREL_LO12_I/S pair the psABI expects. // the R_RISCV_PCREL_HI20 + R_RISCV_PCREL_LO12_I/S pair the psABI expects.
// The HI20 carries the symbol addend; the LO12 addend is zero, matching // The HI20 carries the symbol and its addend. The LO12's symbol must
// cmd/link's own ELF conversion (the LO12 resolves against the HI20's // denote the AUIPC site the HI20 relocates (psABI §8.4.9: the pair is
// AUIPC location). // resolved against the label of the AUIPC, not the target symbol;
// cmd/link generates one local text symbol per AUIPC for exactly this,
// cmd/link/internal/riscv64/asm.go). The .text section symbol with the
// AUIPC's section-relative offset as addend gives S + A = the AUIPC
// address, which is that label.
const secSymText = 1 // syms[1], the .text section symbol
type elfRela struct { type elfRela struct {
off uint64 off uint64
typ uint32 typ uint32
@@ -99,21 +109,20 @@ func (img *Image) ELFRISCVObject() ([]byte, error) {
if !ok { if !ok {
return nil, fmt.Errorf("relocation references unknown symbol %q", r.Name) return nil, fmt.Errorf("relocation references unknown symbol %q", r.Name)
} }
auipc := int64(fn.Offset + r.Off)
switch r.Kind { switch r.Kind {
case RelRISCVPCRELIType: case RelRISCVPCRELIType:
relas = append(relas, relas = append(relas,
elfRela{off: uint64(fn.Offset + r.Off), typ: rRISCVPCRELHI20, sym: idx, addend: r.Addend}, elfRela{off: uint64(fn.Offset + r.Off), typ: rRISCVPCRELHI20, sym: idx, addend: r.Addend},
elfRela{off: uint64(fn.Offset + r.Off + 4), typ: rRISCVPCRELLO12I, sym: idx, addend: 0}, elfRela{off: uint64(fn.Offset + r.Off + 4), typ: rRISCVPCRELLO12I, sym: secSymText, addend: auipc},
) )
case RelRISCVPCRELSType: case RelRISCVPCRELSType:
relas = append(relas, relas = append(relas,
elfRela{off: uint64(fn.Offset + r.Off), typ: rRISCVPCRELHI20, sym: idx, addend: r.Addend}, elfRela{off: uint64(fn.Offset + r.Off), typ: rRISCVPCRELHI20, sym: idx, addend: r.Addend},
elfRela{off: uint64(fn.Offset + r.Off + 4), typ: rRISCVPCRELLO12S, sym: idx, addend: 0}, elfRela{off: uint64(fn.Offset + r.Off + 4), typ: rRISCVPCRELLO12S, sym: secSymText, addend: auipc},
) )
case RelRISCVJal: case RelRISCVJal:
relas = append(relas, elfRela{off: uint64(fn.Offset + r.Off), typ: rRISCVJAL, sym: idx, addend: r.Addend}) relas = append(relas, elfRela{off: uint64(fn.Offset + r.Off), typ: rRISCVJAL, sym: idx, addend: r.Addend})
case RelPCRelAbs:
relas = append(relas, elfRela{off: uint64(fn.Offset + r.Off), typ: rRISCV32, sym: idx, addend: r.Addend})
default: default:
return nil, fmt.Errorf("relocation kind %v unsupported in ELF emission", r.Kind) return nil, fmt.Errorf("relocation kind %v unsupported in ELF emission", r.Kind)
} }
@@ -196,9 +205,25 @@ func (img *Image) ELFRISCVObject() ([]byte, error) {
out = append(out, 0) out = append(out, 0)
} }
} }
dw := appendDWARFSections(&out, img, "gasm.s", symIdx, dwAlign) dw := appendDWARFSections(&out, img, dwarfSourceName(img), symIdx, dwAlign, cfiRISCV64)
dwarfStart := 0 // section index of .debug_abbrev, set when DWARF is present
if dw != nil { if dw != nil {
nSections += 4 // Five DWARF sections: .debug_abbrev, .debug_info, .debug_line,
// .debug_line_str and .debug_frame (the CIE is unconditional, so
// the frame section is always present), plus the relocation
// sections below when they carry entries.
dwarfStart = nSections
nSections += 5
appendDWARFRelas(&out, dw, rRISCVAbs64, dwAlign)
if dw.infoRelaCount > 0 {
nSections++
}
if dw.lineRelaCount > 0 {
nSections++
}
if dw.frameRelaCount > 0 {
nSections++
}
} }
align(8) align(8)
@@ -227,13 +252,37 @@ func (img *Image) ELFRISCVObject() ([]byte, error) {
putSh(".rela.text", shtRela, 0, relaOff, 24*len(relas), secSymtab, secText, 8, 24) 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) putSh(".shstrtab", shtStrtab, 0, shstrOff, len(stSections.bytes()), 0, 0, 1, 0)
// DWARF section headers; their indices follow the write order.
if dw != nil { if dw != nil {
// secIdx is a running section index: each putSh below emits the
// next header, and the sh_info of a .rela section names the index
// of the section it relocates.
secIdx := dwarfStart
putSh(".debug_abbrev", shtProgbits, 0, dw.abbrevOff, dw.abbrevSize, 0, 0, 1, 0) putSh(".debug_abbrev", shtProgbits, 0, dw.abbrevOff, dw.abbrevSize, 0, 0, 1, 0)
secIdx++
putSh(".debug_info", shtProgbits, 0, dw.infoOff, dw.infoSize, 0, 0, 1, 0) putSh(".debug_info", shtProgbits, 0, dw.infoOff, dw.infoSize, 0, 0, 1, 0)
secInfoIdx := secIdx
secIdx++
if dw.infoRelaCount > 0 {
putSh(".rela.debug_info", shtRela, 0, dw.infoRelaOff, 24*dw.infoRelaCount, secSymtab, secInfoIdx, 8, 24)
secIdx++
}
putSh(".debug_line", shtProgbits, 0, dw.lineOff, dw.lineSize, 0, 0, 1, 0) putSh(".debug_line", shtProgbits, 0, dw.lineOff, dw.lineSize, 0, 0, 1, 0)
secLineIdx := secIdx
secIdx++
if dw.lineRelaCount > 0 {
putSh(".rela.debug_line", shtRela, 0, dw.lineRelaOff, 24*dw.lineRelaCount, secSymtab, secLineIdx, 8, 24)
secIdx++
}
putSh(".debug_line_str", shtProgbits, 0, dw.lineStrOff, dw.lineStrSize, 0, 0, 1, 0) putSh(".debug_line_str", shtProgbits, 0, dw.lineStrOff, dw.lineStrSize, 0, 0, 1, 0)
secIdx++
if dw.frameSize > 0 { if dw.frameSize > 0 {
putSh(".debug_frame", shtProgbits, 0, dw.frameOff, dw.frameSize, 0, 0, 8, 0) putSh(".debug_frame", shtProgbits, 0, dw.frameOff, dw.frameSize, 0, 0, 8, 0)
secFrameIdx := secIdx
secIdx++
if dw.frameRelaCount > 0 {
putSh(".rela.debug_frame", shtRela, 0, dw.frameRelaOff, 24*dw.frameRelaCount, secSymtab, secFrameIdx, 8, 24)
}
} }
} }
@@ -246,7 +295,7 @@ func (img *Image) ELFRISCVObject() ([]byte, error) {
le.PutUint64(hdr[24:], 0) le.PutUint64(hdr[24:], 0)
le.PutUint64(hdr[32:], 0) le.PutUint64(hdr[32:], 0)
le.PutUint64(hdr[40:], uint64(shoff)) le.PutUint64(hdr[40:], uint64(shoff))
le.PutUint32(hdr[48:], 0) le.PutUint32(hdr[48:], efRISCVFloatAbiDouble)
le.PutUint16(hdr[52:], 64) le.PutUint16(hdr[52:], 64)
le.PutUint16(hdr[54:], 0) le.PutUint16(hdr[54:], 0)
le.PutUint16(hdr[56:], 0) le.PutUint16(hdr[56:], 0)
asm/link.go
+17 -10
View File
@@ -25,6 +25,10 @@ type Image struct {
Symbols map[string]int // static symbol → byte offset within the image Symbols map[string]int // static symbol → byte offset within the image
DataSyms []DataSymbol // GLOBL symbols, in layout order DataSyms []DataSymbol // GLOBL symbols, in layout order
Externals []string // referenced but undefined symbols, sorted Externals []string // referenced but undefined symbols, sorted
// SourcePath is the assembled file's path, recorded in the DWARF
// sections in place of a placeholder name. Empty when the image was
// not built from a named file.
SourcePath string
} }
// FuncLayout describes one assembled function within an Image. // FuncLayout describes one assembled function within an Image.
@@ -81,12 +85,9 @@ func (fl *FuncLayout) LineAt(offset int) int {
return 0 return 0
} }
// RelocKind Reloc is one static-symbol reference within a function body: the disp32 // RelocKind discriminates the relocation a static-symbol reference needs;
// field at Off (function-relative) must reach the symbol plus Addend, // the encoders record one per SB reference, and the object-file emitters map
// measured from After, the address just past the instruction. An External // it to their format's relocation type.
// relocation names a symbol no GLOBL in the file defines; the object-file
// emitters carry it into the output's relocation table.
// RelocKind discriminates the type of relocation needed.
type RelocKind int type RelocKind int
const ( const (
@@ -96,7 +97,6 @@ const (
RelRISCVPCRELIType // R_RISCV_PCREL_ITYPE (AUIPC + I-type pair) RelRISCVPCRELIType // R_RISCV_PCREL_ITYPE (AUIPC + I-type pair)
RelRISCVPCRELSType // R_RISCV_PCREL_STYPE (AUIPC + S-type pair) RelRISCVPCRELSType // R_RISCV_PCREL_STYPE (AUIPC + S-type pair)
RelRISCVJal // R_RISCV_JAL (J-type call) RelRISCVJal // R_RISCV_JAL (J-type call)
RelPCRelAbs // 32-bit absolute (R_RISCV_32)
RelLoong64AddrHi // R_LOONG64_ADDR_HI (pcalau12i) RelLoong64AddrHi // R_LOONG64_ADDR_HI (pcalau12i)
RelLoong64AddrLo // R_LOONG64_ADDR_LO (addi.d/ld/st) RelLoong64AddrLo // R_LOONG64_ADDR_LO (addi.d/ld/st)
RelArm64Addr // R_ADDRARM64 (ADRP + ADD pair) RelArm64Addr // R_ADDRARM64 (ADRP + ADD pair)
@@ -106,6 +106,13 @@ const (
) )
type Reloc struct { type Reloc struct {
// Off is the function-relative offset of the field the linker patches
// and After the address just past the instruction, the base the
// assembler measures PC-relative displacements from. Name plus
// Addend select the target: the symbol plus the byte offset. An
// External relocation names a symbol no GLOBL in the file defines;
// the object-file emitters carry it into the output's relocation
// table.
Off int Off int
After int After int
Name string Name string
@@ -150,7 +157,7 @@ func AssembleFile(f *ast.File) (*Image, error) {
} }
link := &linkInfo{symbols: known, allowExternal: true} link := &linkInfo{symbols: known, allowExternal: true}
img := &Image{Symbols: map[string]int{}} img := &Image{Symbols: map[string]int{}, SourcePath: f.Path}
textOff := map[string]int{} textOff := map[string]int{}
type asmFunc struct { type asmFunc struct {
name string name string
@@ -267,7 +274,7 @@ func AssembleFileRISCV(f *ast.File) (*Image, error) {
return nil, err return nil, err
} }
img := &Image{Symbols: map[string]int{}} img := &Image{Symbols: map[string]int{}, SourcePath: f.Path}
for _, d := range f.Decls { for _, d := range f.Decls {
t, ok := d.(*ast.Text) t, ok := d.(*ast.Text)
if !ok { if !ok {
@@ -339,7 +346,7 @@ func AssembleFileLOONG64(f *ast.File) (*Image, error) {
return nil, err return nil, err
} }
img := &Image{Symbols: map[string]int{}} img := &Image{Symbols: map[string]int{}, SourcePath: f.Path}
for _, d := range f.Decls { for _, d := range f.Decls {
t, ok := d.(*ast.Text) t, ok := d.(*ast.Text)
if !ok { if !ok {