Hojun-Cho/ww
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

selfhost: mirror writable .data + R_X86_64_64 across the wwstage

Browse Source 
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.
This commit is contained in:
Hojun-Cho
2026-05-12 13:03:03 +09:00
parent 003f707618
commit 1ac9980f7e
16 changed files with 1132 additions and 145 deletions
Download Patch File Download Diff File Expand all files Collapse all files

117
selfhost/cmd/w6l/obj.ww
View File

@@ -123,6 +123,28 @@ fn emittext(l: *lnk, src: *u8, n: u64) void = {
l.textlen += n;
};
fn emitdata(l: *lnk, src: *u8, n: u64) void = {
if (l.datalen + n > l.datacap) {
let nc: u64 = l.datacap;
if (nc == 0u64) { nc = 256u64; };
for (nc < l.datalen + n) { nc = nc * 2u64; };
let nb: *u8 = os.alloc(nc): *u8;
let i: u64 = 0u64;
for (i < l.datalen) {
nb[i] = l.data[i];
i += 1u64;
};
l.data = nb;
l.datacap = nc;
};
let i: u64 = 0u64;
for (i < n) {
l.data[l.datalen + i] = src[i];
i += 1u64;
};
l.datalen += n;
};
// ---- C-string helpers --------------------------------------------------
fn cstrlen(p: *u8) u64 = {
@@ -213,6 +235,7 @@ fn elfglobals(a: *arena, buf: *u8, len: u64) *defent = {
let shstr: *u8 = buf + shstrshoff;
let idxtext: i32 = -1;
let idxdata: i32 = -1;
let idxsymtab: i32 = -1;
let i: u32 = 0u32;
for (i < shnum) {
@@ -222,6 +245,7 @@ fn elfglobals(a: *arena, buf: *u8, len: u64) *defent = {
let nm: *u8 = shstr + (shname: u64);
if (shtype == SHT_PROGBITS: u32) {
if (cstreq(nm, ".text")) { idxtext = i: i32; };
if (cstreq(nm, ".data")) { idxdata = i: i32; };
};
if (shtype == SHT_SYMTAB: u32) { idxsymtab = i: i32; };
i += 1u32;
@@ -247,10 +271,17 @@ fn elfglobals(a: *arena, buf: *u8, len: u64) *defent = {
let stinfo: u8 = buf[symp + SYM_INFO];
let stshndx: u16 = rdu16(buf, symp + SYM_SHNDX);
let bind: u32 = (stinfo: u32) >> 4u32;
// STB_GLOBAL = 1; defined in .text.
// STB_GLOBAL = 1; defined in .text or .data. Both are
// included so an archive member that owns a data global
// gets pulled in when something references it.
if (bind == 1u32) {
if (stshndx != 0u16) {
if ((stshndx: i32) == idxtext) {
let intext: bool = (stshndx: i32) == idxtext;
let indt: bool = false;
if (idxdata >= 0) {
indt = (stshndx: i32) == idxdata;
};
if (intext || indt) {
let nmp: *u8 = strtab + (stname: u64);
if (nmp[0u64] != 0u8) {
let nm: str = cstrtostr(a, nmp);
@@ -372,10 +403,12 @@ fn loadimage(l: *lnk, path: *u8, buf: *u8, len: u64) i32 = {
let shstrshoff: u64 = rdu64(buf, shoff + (shstrndx: u64) * SHDR_SIZE + SHDR_OFFSET);
let shstr: *u8 = buf + shstrshoff;
// find .text, .symtab, .rela.text
// find .text, .data, .symtab, .rela.text, .rela.data
let idxtext: i32 = -1;
let idxdata: i32 = -1;
let idxsymtab: i32 = -1;
let idxrela: i32 = -1;
let idxrelad: i32 = -1;
let i: u32 = 0u32;
for (i < shnum) {
let secoff: u64 = shoff + (i: u64) * SHDR_SIZE;
@@ -384,10 +417,12 @@ fn loadimage(l: *lnk, path: *u8, buf: *u8, len: u64) i32 = {
let nm: *u8 = shstr + (shname: u64);
if (shtype == SHT_PROGBITS: u32) {
if (cstreq(nm, ".text")) { idxtext = i: i32; };
if (cstreq(nm, ".data")) { idxdata = i: i32; };
};
if (shtype == SHT_SYMTAB: u32) { idxsymtab = i: i32; };
if (shtype == SHT_RELA: u32) {
if (cstreq(nm, ".rela.text")) { idxrela = i: i32; };
if (cstreq(nm, ".rela.data")) { idxrelad = i: i32; };
};
i += 1u32;
};
@@ -414,18 +449,34 @@ fn loadimage(l: *lnk, path: *u8, buf: *u8, len: u64) i32 = {
let stroff: u64 = rdu64(buf, strsh + SHDR_OFFSET);
let strtab: *u8 = buf + stroff;
let datasize: u64 = 0u64;
let dataoff: u64 = 0u64;
if (idxdata >= 0) {
let datash: u64 = shoff + (idxdata: u64) * SHDR_SIZE;
dataoff = rdu64(buf, datash + SHDR_OFFSET);
datasize = rdu64(buf, datash + SHDR_SIZE_F);
};
// Track this object.
let ob: *lobj = amalloc(l.a, 64u64): *lobj;
let ob: *lobj = amalloc(l.a, 96u64): *lobj;
ob.path = cstrtostr(l.a, path);
ob.buf = buf;
ob.len = len;
ob.textoff = l.textlen;
ob.textsize = textsize;
ob.dataoff = l.datalen;
ob.datasize = datasize;
ob.onext = l.objs;
l.objs = ob;
// Append .text bytes to the combined image.
emittext(l, buf + textoff, textsize);
// Append .data bytes (if present) to the combined .data buffer.
if (idxdata >= 0) {
if (datasize > 0u64) {
emitdata(l, buf + dataoff, datasize);
};
};
// Walk symbols. We don't keep a per-object map[] of *lsym. Instead
// the reloc loop re-walks symtab and re-interns by name. Simpler
@@ -441,7 +492,13 @@ fn loadimage(l: *lnk, path: *u8, buf: *u8, len: u64) i32 = {
let nm: str = cstrtostr(l.a, nmp);
let gs: *lsym = intern(l, nm);
if (stshndx != 0u16) {
if ((stshndx: i32) == idxtext) {
let intext: bool = (stshndx: i32) == idxtext;
let indt: bool = false;
if (idxdata >= 0) {
indt = (stshndx: i32) == idxdata;
};
if (intext) { if (indt) { indt = false; }; };
if (intext) {
if (gs.defined != 0) {
os.write(2, "w6l: duplicate symbol\n".ptr, 21u64);
l.errs += 1;
@@ -452,6 +509,18 @@ fn loadimage(l: *lnk, path: *u8, buf: *u8, len: u64) i32 = {
gs.val = ob.textoff + stvalue;
};
};
if (indt) {
if (gs.defined != 0) {
os.write(2, "w6l: duplicate symbol\n".ptr, 21u64);
l.errs += 1;
} else {
gs.defined = 1;
gs.indata = 1;
gs.owner = ob;
gs.idxinowner = si: i32;
gs.val = ob.dataoff + stvalue;
};
};
};
};
si += 1u64;
@@ -471,8 +540,9 @@ fn loadimage(l: *lnk, path: *u8, buf: *u8, len: u64) i32 = {
let raddend: u64 = rdu64(buf, rp + RELA_ADDEND);
let rsymidx: u32 = (rinfo >> 32u64): u32;
let rkind: i32 = ((rinfo & 4294967295u64): u32): i32;
let nr: *lrel = amalloc(l.a, 48u64): *lrel;
let nr: *lrel = amalloc(l.a, 64u64): *lrel;
nr.off = ob.textoff + roff;
nr.section = 0;
nr.kind = rkind;
nr.addend = raddend: i64;
// Look up the referenced sym by name (re-walk symtab).
@@ -491,5 +561,40 @@ fn loadimage(l: *lnk, path: *u8, buf: *u8, len: u64) i32 = {
};
};
// Data-reloc collection. Offsets land in .data, shifted by
// this object's data_off so they index the combined buffer.
if (idxrelad >= 0) {
let relash: u64 = shoff + (idxrelad: u64) * SHDR_SIZE;
let relaoff: u64 = rdu64(buf, relash + SHDR_OFFSET);
let relasize: u64 = rdu64(buf, relash + SHDR_SIZE_F);
let nrel: u64 = relasize / RELA_SIZE;
let ri: u64 = 0u64;
for (ri < nrel) {
let rp: u64 = relaoff + ri * RELA_SIZE;
let roff: u64 = rdu64(buf, rp + RELA_OFFSET);
let rinfo: u64 = rdu64(buf, rp + RELA_INFO);
let raddend: u64 = rdu64(buf, rp + RELA_ADDEND);
let rsymidx: u32 = (rinfo >> 32u64): u32;
let rkind: i32 = ((rinfo & 4294967295u64): u32): i32;
let nr: *lrel = amalloc(l.a, 64u64): *lrel;
nr.off = ob.dataoff + roff;
nr.section = 1;
nr.kind = rkind;
nr.addend = raddend: i64;
if ((rsymidx: u64) < nsyms) {
let sp: u64 = symoff + (rsymidx: u64) * SYM_SIZE;
let sname: u32 = rdu32(buf, sp + SYM_NAME);
let snm: *u8 = strtab + (sname: u64);
if (snm[0u64] != 0u8) {
let nm: str = cstrtostr(l.a, snm);
nr.sym = intern(l, nm);
};
};
nr.rnext = l.rels;
l.rels = nr;
ri += 1u64;
};
};
return 0;
};