Hojun-Cho
1ac9980f7e
Bring the wwstage toolchain to parity with C-side DATAW / DATAR /
.data / .rela.data support. With this, w6c_ww + w6a_ww + w6l_ww can
compile, assemble and link `let g: str = "lit";` (and the scalar /
str / slice / struct globals that landed earlier) end-to-end, with
output that's byte-identical to the C-side pipeline.
w6a (types.ww / parse.ww / asm.ww / obj.ww):
- A_DATAW + A_DATAR opcodes; parser learns `name+disp(SB)`;
A_DATAR records an R_X86_64_64 reloc in .data via the new
addrelocdata helper; areloc gains a `section` flag and asym
an `isdata` flag; obj.ww splits relocs into .rela.text /
.rela.data, emits .data PROGBITS + .rela.data conditionally,
and shuffles section indices the same way cmd/w6a/obj.c does
so byte output stays identical when no DATAW/DATAR are used.
w6l (sym.ww / obj.ww / pass.ww / out.ww / dynout.ww / main.ww):
- lrel grows `section`; lsym grows `indata`; lobj tracks
dataoff / datasize; lnk grows combined .data buffer;
- obj.ww loads .data and .rela.data, registers data symbols
with indata=1 and val shifted by the input's data_off, and
the archive scanner includes both .text and .data globals;
- pass.ww adds R_X86_64_64 (patch 8 bytes in .text or .data
with sym_va + addend); relocate's signature becomes
(textva, datava);
- out.ww emits a second PT_LOAD (R+W) when datalen > 0, with
.data at the page-aligned offset after .text;
- dynout.ww refuses .data + -l/-L cleanly (matches the C-side
error message);
- main.ww computes text_va / data_va and passes both to
relocate.
wcc cgen (cgen.ww / cgendecl.ww):
- letpreintern walks top-level str-lets and interns the strlit
BEFORE emitdatasection emits its DATA row, so emitletdataw
can later look up the same label;
- emitletdataw's 16B branch detects non-empty strlit init and
emits the 8-zero + 8-LE-len DATAW plus a DATAR slot+0,strlit
reloc, mirroring cmd/w6c/cgen.c.
Verified: `wwdump_ww -c` byte-matches `w6c` on a `let g: str =
"hello world\n";` fixture; `w6a_ww` and `w6l_ww` produce a
binary byte-identical to the C-side pipeline that runs and
prints "hello world". Bootstrap fixed-point holds (ww2 == ww3 ==
ww4), 26/26 tests green.
112 lines
2.8 KiB
Plaintext
112 lines
2.8 KiB
Plaintext
// selfhost/cmd/w6l/sym.ww — port of cmd/w6l/sym.c.
|
|
//
|
|
// Linker symbol table. Singly-linked list, usually a few hundred
|
|
// entries; hashing isn't worth it yet.
|
|
|
|
use mem;
|
|
|
|
type lsym = struct {
|
|
name: str,
|
|
val: u64, // offset within combined .text (or .data when
|
|
// indata=1) once linked
|
|
defined: i32, // 1 if some lobj defines this symbol
|
|
indata: i32, // 1 if defined in .data (writable globals)
|
|
owner: *lobj,
|
|
idxinowner: i32,
|
|
// Dynamic-linking fields. Set by resolve when an undefined sym
|
|
// is provided by some loaded lso. pltidx and dynsymidx default
|
|
// to -1 (set explicitly by resolve, not by amalloc-zeroing).
|
|
isdyn: i32,
|
|
dynlib: *lso,
|
|
dynversion: str, // matched export's version; len 0 if none
|
|
pltidx: i32,
|
|
dynsymidx: i32,
|
|
snext: *lsym,
|
|
};
|
|
|
|
type lrel = struct {
|
|
off: u64, // offset within the relocation's section
|
|
section: i32, // 0 = .text, 1 = .data
|
|
kind: i32, // R_X86_64_*
|
|
sym: *lsym,
|
|
addend: i64,
|
|
rnext: *lrel,
|
|
};
|
|
|
|
type lobj = struct {
|
|
path: str,
|
|
buf: *u8, // object bytes
|
|
len: u64,
|
|
textoff: u64, // offset of .text in combined output
|
|
textsize: u64,
|
|
dataoff: u64, // offset of .data in combined output
|
|
datasize: u64, // bytes contributed to combined .data (0 if none)
|
|
onext: *lobj,
|
|
};
|
|
|
|
// lexport — one entry per GLOBAL/WEAK symbol exported by a loaded .so.
|
|
// Stored as a chain in the order the .so's dynsym presents them, so
|
|
// soprovides_v's first-match semantics agree with the C version.
|
|
type lexport = struct {
|
|
name: str,
|
|
version: str, // len 0 for unversioned globals
|
|
enext: *lexport,
|
|
};
|
|
|
|
type lso = struct {
|
|
path: str, // full filesystem path used to load
|
|
soname: str, // DT_SONAME, or basename if missing
|
|
exports: *lexport, // dynsym-order chain of exported names
|
|
sonext: *lso,
|
|
};
|
|
|
|
type lnk = struct {
|
|
a: *arena,
|
|
objs: *lobj,
|
|
sos: *lso,
|
|
syms: *lsym,
|
|
rels: *lrel,
|
|
text: *u8, // combined .text
|
|
textcap: u64,
|
|
textlen: u64,
|
|
// Combined .data (writable). Empty unless any input .o has a
|
|
// .data PROGBITS section.
|
|
data: *u8,
|
|
datacap: u64,
|
|
datalen: u64,
|
|
errs: i32,
|
|
dynn: i32, // number of syms routed through PLT
|
|
};
|
|
|
|
fn streq(a: str, b: str) bool = {
|
|
if (a.len != b.len) { return false; };
|
|
let i: i32 = 0;
|
|
for (i < a.len) {
|
|
if (a[i] != b[i]) { return false; };
|
|
i += 1;
|
|
};
|
|
return true;
|
|
};
|
|
|
|
export fn intern(l: *lnk, name: str) *lsym = {
|
|
let s: *lsym = l.syms;
|
|
for (s != nil) {
|
|
if (streq(s.name, name)) { return s; };
|
|
s = s.snext;
|
|
};
|
|
let n: *lsym = amalloc(l.a, 96u64): *lsym;
|
|
n.name = name;
|
|
n.snext = l.syms;
|
|
l.syms = n;
|
|
return n;
|
|
};
|
|
|
|
export fn lookup(l: *lnk, name: str) *lsym = {
|
|
let s: *lsym = l.syms;
|
|
for (s != nil) {
|
|
if (streq(s.name, name)) { return s; };
|
|
s = s.snext;
|
|
};
|
|
return nil;
|
|
};
|