selfhost: mirror writable .data + R_X86_64_64 across the wwstage

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:
2026-05-12 13:03:03 +09:00
parent 003f707618
commit 1ac9980f7e
16 changed files with 1132 additions and 145 deletions

View File

@@ -38,8 +38,9 @@ export fn emitu32(a: *asm_, v: u32) void = {
};
export fn addreloc(a: *asm_, off: u64, kind: i32, s: *asym, add: i64) void = {
let r: *areloc = amalloc(a.a, 48u64): *areloc;
let r: *areloc = amalloc(a.a, 64u64): *areloc;
r.off = off;
r.section = 0; // .text
r.kind = kind;
r.asy = s;
r.addend = add;
@@ -47,6 +48,37 @@ export fn addreloc(a: *asm_, off: u64, kind: i32, s: *asym, add: i64) void = {
a.relocs = r;
};
// Record a relocation that lives in the .data section. Used by
// DATAR to patch a 64-bit slot with a symbol's runtime VA. obj.ww
// separates these into .rela.data when emitting the .o.
export fn addrelocdata(a: *asm_, off: u64, kind: i32, s: *asym, add: i64) void = {
let r: *areloc = amalloc(a.a, 64u64): *areloc;
r.off = off;
r.section = 1; // .data
r.kind = kind;
r.asy = s;
r.addend = add;
r.rnext = a.relocs;
a.relocs = r;
};
// Append one byte to the writable .data buffer. Mirrors emitbyte
// but targets a.data instead of a.text.
export fn emitdatabyte(a: *asm_, b: u8) void = {
if (a.datalen + 1u64 > a.datacap) {
let nc: u64 = a.datacap;
if (nc == 0u64) { nc = 256u64; };
nc = nc * 2u64;
let nb: *u8 = os.alloc(nc): *u8;
let i: u64 = 0u64;
for (i < a.datalen) { nb[i] = a.data[i]; i += 1u64; };
a.data = nb;
a.datacap = nc;
};
a.data[a.datalen] = b;
a.datalen += 1u64;
};
// ---- register codes ----------------------------------------------------
// Low 3 bits of register encoding.
@@ -270,6 +302,38 @@ export fn encode(a: *asm_) i32 = {
for (i < p.nbytes) { emitbyte(a, p.bytes[i]); i += 1u64; };
p = p.link; continue;
};
if (op == A_DATAW) {
// Writable variant: bytes go into .data instead of
// .text. obj.ww emits the extra section conditionally
// on datalen > 0 so .o output stays byte-identical
// for inputs that don't use DATAW.
let s: *asym = intern(a, p.to.asym);
s.defined = 1;
s.isdata = 1;
s.isglobal = 1;
s.addr = a.datalen;
let i: u64 = 0u64;
for (i < p.nbytes) { emitdatabyte(a, p.bytes[i]); i += 1u64; };
p = p.link; continue;
};
if (op == A_DATAR) {
// DATAR slot+off(SB), target(SB) — record an
// R_X86_64_64 relocation at slot+off in .data
// pointing at target. Slot must already be defined
// by a prior DATAW.
let holder: *asym = intern(a, p.from.asym);
if (holder.defined == 0) {
p = p.link; continue;
};
if (holder.isdata == 0) {
p = p.link; continue;
};
let target: *asym = intern(a, p.to.asym);
let reloff: u64 = holder.addr + p.from.offset: u64;
addrelocdata(a, reloff, 1 /* R_X86_64_64 */,
target, 0i64);
p = p.link; continue;
};
if (op == A_RET) {
emitbyte(a, 195u8); // 0xC3
p = p.link; continue;