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

w6c+selfhost: tagged-arr element ABI + full selfhost mirror

Browse Source 
Closes the remaining tagged-union gaps after the prior two commits:

  1. Tagged element in an array/slice (cstage). N_INDEX load now reads
     slot words into AX/DX/CX, matching the tagged-return ABI so match
     / call-arg / let-init paths consume `arr[i]` uniformly. N_INDEX
     store routes through a scratch slot + cg_widen_tagged_store +
     byte-copy to &arr[i], so the full widening machinery (scalar /
     str / struct payload / tagged subset / nullable fold) lights up
     for element writes too.

  2. Selfhost mirror — the cgen widen helpers (struct payload,
     tagged-subset, spread-flatten) C cgen has had for two commits
     finally land in selfhost:

       cgwidentaggedstore  — single writer for nullable / tagged ident /
                             tagged via AX:DX:CX / struct (lit + ident) /
                             str / scalar source shapes.
       cgwidentagremap     — CMPQ-chain tag remap for variant-subset.
       rhsstructpayload    — struct-name predicate; filters `!void` /
                             `!i32` aliases that share N_STRUCTLIT shape
                             but aren't structs.
       rhstaggedident,
       rhstaggedabicall    — source-shape predicates.
       flatvariantidx      — spread-aware variant index lookup. Walks
                             `(...inner | T)` entries by resolving the
                             alias and inlining the inner's variants so
                             wwstage's tag order matches the check.c
                             flattening cstage does at type resolution.

     cglet tagged init, cgassign tagged-ident reassign, cgreturn struct
     / subset payload, pushargsrev struct payload, cgindex tagged
     element load, cgassign N_INDEX tagged element store all delegate
     to these. cgmatch picks up scrutt from N_INDEX bases (element
     type) and uses flatvariantidx for case dispatch.

  3. Selfhost frame accounting: scanlocals reserves a 24B @tagscr slot
     when the body contains a tagged-arr store, a struct-payload
     tagged return, or a struct-payload call arg — dedup'd via
     scanseenmark so multiple sites share one slot. N_LET stubs now
     carry tnode so walk-time type checks see the array element type.
     slotsize TARRAY learned to size tagged / struct / ptr / aliased
     elements (was 8B-default for anything not N_TNAME-primitive,
     undersizing tagged-element arrays).

     Scalar / str call-arg widening keeps its direct-push fast path
     (no scratch), so wwstage's asm on selfhost source remains
     byte-identical to cstage's — 993/995 still pass.

700_e2e: 9 new rows — scalar/str/struct/subset/nullable variants in
arrays and slices, plus pass-arg / let-init / return / match shapes.
This commit is contained in:
Hojun-Cho
2026-05-13 06:29:52 +09:00
parent 9133251269
commit 6fd0160c0f
8 changed files with 2859 additions and 357 deletions
Download Patch File Download Diff File Expand all files Collapse all files

249
selfhost/cmd/wcc/cgenexpr.ww
View File

@@ -112,7 +112,7 @@ fn cgexpr(c: *cgen, n: *node) void = {
// tagged-union type expression `tagged`. -1 if `tagged` isn't an
// nkind.N_TTAGGED or no variant matches. Mirrors the lookup that cgmatch
// does inline; pulled out so `is` / `as` can reuse it.
fn cgtagvariantidx(tagged: *node, vt: *node) i32 = {
fn cgtagvariantidx(c: *cgen, tagged: *node, vt: *node) i32 = {
if (tagged == nil) { return -1; };
if (vt == nil) { return -1; };
if (tagged.kind != nkind.N_TTAGGED) { return -1; };
@@ -120,16 +120,7 @@ fn cgtagvariantidx(tagged: *node, vt: *node) i32 = {
want.ptr = nil; want.len = 0;
if (vt.kind == nkind.N_TNAME) { want = vt.str; };
if (want.len == 0) { return -1; };
let v: *node = tagged.list;
let idx: i32 = 0;
for (v != nil) {
if (v.kind == nkind.N_TNAME) {
if (streq(v.str, want)) { return idx; };
};
v = v.next;
idx += 1;
};
return -1;
return flatvariantidx(c, tagged, want);
};
// cgtryprop — `e?` propagates the error variant up the stack.
@@ -246,7 +237,7 @@ fn cgtypetest(c: *cgen, n: *node) void = {
};
};
};
let want: i32 = cgtagvariantidx(scrutt, n.rhs);
let want: i32 = cgtagvariantidx(c, scrutt, n.rhs);
if (want < 0) { want = 0; };
emitline("\tMOVQ\t");
emitoff(scrutoff: i64);
@@ -334,7 +325,7 @@ fn cgtypeassert(c: *cgen, n: *node) void = {
};
};
};
let want: i32 = cgtagvariantidx(scrutt, n.rhs);
let want: i32 = cgtagvariantidx(c, scrutt, n.rhs);
if (want < 0) { want = 0; };
let okl: str = mklabel(c, "asrt_ok");
emitline("\tMOVQ\t");
@@ -566,6 +557,43 @@ fn cgindex(c: *cgen, n: *node) void = {
esz = indexbaseesz(c, base);
};};
};
// Tagged-union element: load slot words into (AX=tag, DX=val0,
// CX=val1) matching the tagged-return ABI so call-arg / let /
// match consumers see the same shape as a tagged-returning fn.
// Slot size = esz (8/16/24); nullable folded element is one
// word, which the fallthrough below handles via MOVQ AX.
let elem_tagged: bool = false;
let elem_slot_sz: i32 = esz;
if (base != nil) {
if (base.kind == nkind.N_IDENT) {
let bl: *local = baselocal;
let etn: *node = nil;
if (bl != nil) {
let btn: *node = bl.tnode;
if (btn != nil) {
let bk: nkind = btn.kind;
if (bk == nkind.N_TARRAY) { etn = btn.lhs; };
if (bk == nkind.N_TSLICE) { etn = btn.lhs; };
if (bk == nkind.N_TPTR) { etn = btn.lhs; };
};
} else {
let tn: *node = letvartnode(c, base.str);
if (tn != nil) {
let bk: nkind = tn.kind;
if (bk == nkind.N_TARRAY) { etn = tn.lhs; };
if (bk == nkind.N_TSLICE) { etn = tn.lhs; };
if (bk == nkind.N_TPTR) { etn = tn.lhs; };
};
};
if (istaggedtype(c, etn)) {
if (!isnullabletype(etn)) {
elem_tagged = true;
elem_slot_sz = slotsize(c, etn);
esz = elem_slot_sz;
};
};
};
};
cgexpr(c, idx);
if (esz > 1) {
emitline("\tMOVQ\t$");
@@ -584,6 +612,16 @@ fn cgindex(c: *cgen, n: *node) void = {
emitline("(SB), BX\n");
};
emitline("\tADDQ\tAX, BX\n");
if (elem_tagged) {
if (elem_slot_sz > 16) {
emitline("\tMOVQ\t16(BX), CX\n");
};
if (elem_slot_sz > 8) {
emitline("\tMOVQ\t8(BX), DX\n");
};
emitline("\tMOVQ\t(BX), AX\n");
return;
};
if (esz == 16) {
emitline("\tMOVQ\t8(BX), CX\n");
emitline("\tMOVQ\t(BX), AX\n");
@@ -612,6 +650,16 @@ fn cgindex(c: *cgen, n: *node) void = {
emitline("(BP), BX\n");
};
emitline("\tADDQ\tAX, BX\n");
if (elem_tagged) {
if (elem_slot_sz > 16) {
emitline("\tMOVQ\t16(BX), CX\n");
};
if (elem_slot_sz > 8) {
emitline("\tMOVQ\t8(BX), DX\n");
};
emitline("\tMOVQ\t(BX), AX\n");
return;
};
// str element (16B): load (ptr, len) into (AX, BX) so
// the value flows through the str-rhs convention.
if (esz == 16) {
@@ -633,6 +681,19 @@ fn cgindex(c: *cgen, n: *node) void = {
cgexpr(c, base);
emitline("\tPOPQ\tBX\n");
emitline("\tADDQ\tBX, AX\n");
if (elem_tagged) {
// AX holds the element address. Copy to BX (loading slot+0
// into AX clobbers it), then read slot words.
emitline("\tMOVQ\tAX, BX\n");
if (elem_slot_sz > 16) {
emitline("\tMOVQ\t16(BX), CX\n");
};
if (elem_slot_sz > 8) {
emitline("\tMOVQ\t8(BX), DX\n");
};
emitline("\tMOVQ\t(BX), AX\n");
return;
};
if (esz == 16) {
emitline("\tMOVQ\t8(AX), BX\n");
emitline("\tMOVQ\t(AX), AX\n");
@@ -747,15 +808,16 @@ fn cgmatch(c: *cgen, n: *node) void = {
scrutt = resolvetagged(c, lc.tnode);
};
} else {
// Non-ident scrutinee (call result, ?, etc.). Spill into a
// 24B `@match_spill` scratch slot and dispatch off it.
// Tagged returns follow the AX:DX:CX convention, so store
// all three words at +0/+8/+16; nullable returns are
// single-word (AX = ptr) and only read +0, so the extra
// stores are harmless. For N_CALL we recover the return
// type via fnretlookup so nullable dispatch can pick the
// pointer-vs-null discriminator. Mirrors C cgen's
// @match_spill path in cmd/w6c/cgen.c N_MATCH.
// Non-ident scrutinee (call result, arr[i], ?, etc.).
// Spill into a 24B `@match_spill` scratch slot and
// dispatch off it. Tagged returns (N_CALL) follow the
// AX:DX:CX convention; tagged-element loads (N_INDEX)
// after the cgindex fix produce the same triple.
// Nullable returns are single-word (AX = ptr); only +0
// is read, so the extra stores are harmless. We
// recover the scrutinee type from fnretlookup (N_CALL)
// or the base local's array element type (N_INDEX) so
// dispatch can compute variant indices.
scrutoff = localalloc(c, "@match_spill", 24, nil);
if (scrut.kind == nkind.N_CALL) {
let callee: *node = scrut.lhs;
@@ -770,6 +832,27 @@ fn cgmatch(c: *cgen, n: *node) void = {
};
};
};
if (scrut.kind == nkind.N_INDEX) {
let ibase: *node = scrut.lhs;
if (ibase != nil) {
if (ibase.kind == nkind.N_IDENT) {
let bl: *local = localfindnode(c, ibase.str);
let btn: *node = nil;
if (bl != nil) { btn = bl.tnode; }
else { btn = letvartnode(c, ibase.str); };
if (btn != nil) {
let bk: nkind = btn.kind;
let etn: *node = nil;
if (bk == nkind.N_TARRAY) { etn = btn.lhs; };
if (bk == nkind.N_TSLICE) { etn = btn.lhs; };
if (bk == nkind.N_TPTR) { etn = btn.lhs; };
if (etn != nil) {
scrutt = resolvetagged(c, etn);
};
};
};
};
};
cgexpr(c, scrut);
emitline("\tMOVQ\tAX, ");
emitoff(scrutoff: i64);
@@ -832,23 +915,8 @@ fn cgmatch(c: *cgen, n: *node) void = {
let patname: str;
patname.ptr = nil; patname.len = 0;
if (pat.kind == nkind.N_TNAME) { patname = pat.str; };
let v: *node = scrutt.list;
let idx: i32 = 0;
let found: bool = false;
for (v != nil) {
if (v.kind == nkind.N_TNAME) {
if (variantnamematch(v.str, patname)) {
want = idx;
found = true;
v = nil;
};
};
if (v != nil) {
v = v.next;
idx += 1;
};
};
if (!found) { want = 0; };
let r: i32 = flatvariantidx(c, scrutt, patname);
if (r >= 0) { want = r; };
};
};
emitline("\tMOVQ\t");
@@ -2156,6 +2224,25 @@ fn cgassign(c: *cgen, n: *node) void = {
};
};
};
// Tagged-union local reassignment: `r = expr;` where r has a
// tagged-union type. Delegate to cgwidentaggedstore (same path
// as cglet's tagged-init). Covers nullable fold, tagged source,
// struct payload, str payload, scalar payload, with tag remap.
if (lhs != nil) {
if (lhs.kind == nkind.N_IDENT) {
if (n.op == tkind.TK_ASSIGN) {
let lc: *local = localfindnode(c, lhs.str);
if (lc != nil) {
if (istaggedtype(c, lc.tnode)) {
let lsz: i32 = slotsize(c, lc.tnode);
cgwidentaggedstore(c, lc.tnode,
n.rhs, lc.off, lsz);
return;
};
};
};
};
};
// `*p = v` — deref-assign. Element width comes from the
// pointer's declared type. Mirrors C cgen: eval rhs (AX,
// and BX if str), push, eval pointer, pop value, store.
@@ -2256,12 +2343,20 @@ fn cgassign(c: *cgen, n: *node) void = {
let isglobalptr: bool = false;
let globalname: str;
globalname.ptr = nil; globalname.len = 0;
let elemtn: *node = nil;
if (base != nil) {
if (base.kind == nkind.N_IDENT) {
let bn: str = base.str;
baselocal = localfindnode(c, bn);
if (baselocal != nil) {
esz = elemsizeof(baselocal.tnode);
let btn: *node = baselocal.tnode;
if (btn != nil) {
let bk: nkind = btn.kind;
if (bk == nkind.N_TARRAY) { elemtn = btn.lhs; };
if (bk == nkind.N_TSLICE) { elemtn = btn.lhs; };
if (bk == nkind.N_TPTR) { elemtn = btn.lhs; };
};
} else {
let tn: *node = letvartnode(c, bn);
if (tn != nil) {
@@ -2269,11 +2364,13 @@ fn cgassign(c: *cgen, n: *node) void = {
isglobalarr = true;
globalname = bn;
esz = elemsizeof(tn);
elemtn = tn.lhs;
};
if (tn.kind == nkind.N_TPTR) {
isglobalptr = true;
globalname = bn;
esz = elemsizeof(tn);
elemtn = tn.lhs;
};
};
};
@@ -2281,6 +2378,80 @@ fn cgassign(c: *cgen, n: *node) void = {
esz = indexbaseesz(c, base);
};};
};
// Tagged-union element: materialize source in a shared
// scratch slot via cgwidentaggedstore (handles struct /
// str / scalar / subset / nullable variants uniformly),
// then compute &arr[i] and byte-copy. The scratch
// (@tagscr) is reused across all tagged-arr stores in
// the function and counted once in scanlocals.
if (elemtn != nil) {
if (istaggedtype(c, elemtn)) {
let slot_sz: i32 = slotsize(c, elemtn);
let scroff: i32 = localadd(c, "@tagscr",
24, nil);
// Pre-zero scratch (matches push helper).
emitline("\tXORQ\tAX, AX\n");
let zz: i32 = 0;
for (zz < slot_sz) {
emitline("\tMOVQ\tAX, ");
emitoff((scroff + zz): i64);
emitline("(BP)\n");
zz += 8;
};
cgwidentaggedstore(c, elemtn, n.rhs,
scroff, slot_sz);
cgexpr(c, idx);
if (slot_sz > 1) {
emitline("\tMOVQ\t$");
emitint(slot_sz: i64);
emitline(", CX\n");
emitline("\tIMULQ\tCX, AX\n");
};
if (isglobalarr) {
emitline("\tLEAQ\t");
emitsymname(c, globalname);
emitline("(SB), BX\n");
} else { if (isglobalptr) {
emitline("\tMOVQ\t");
emitsymname(c, globalname);
emitline("(SB), BX\n");
} else { if (baselocal != nil) {
let tn: *node = baselocal.tnode;
let isarr: bool = false;
if (tn != nil) {
if (tn.kind == nkind.N_TARRAY) {
isarr = true;
};
};
if (isarr) {
emitline("\tLEAQ\t");
emitoff(baselocal.off: i64);
emitline("(BP), BX\n");
} else {
emitline("\tMOVQ\t");
emitoff(baselocal.off: i64);
emitline("(BP), BX\n");
};
} else {
emitline("\tPUSHQ\tAX\n");
cgexpr(c, base);
emitline("\tMOVQ\tAX, BX\n");
emitline("\tPOPQ\tAX\n");
};};};
emitline("\tADDQ\tAX, BX\n");
let cc: i32 = 0;
for (cc < slot_sz) {
emitline("\tMOVQ\t");
emitoff((scroff + cc): i64);
emitline("(BP), AX\n");
emitline("\tMOVQ\tAX, ");
emitoff(cc: i64);
emitline("(BX)\n");
cc += 8;
};
return;
};
};
cgexpr(c, n.rhs); // value → AX
if (esz == 16) { emitline("\tPUSHQ\tBX\n"); };
emitline("\tPUSHQ\tAX\n");