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

cstage+selfhost+test: zero unused ABI words in cgreturn variant-widen (#18)

Browse Source 
cgreturn's variant-widen arm only filled the registers each variant's
payload needed: scalar variants left CX and R8 stale; str variant
left R8 stale. The receiver (cg_widen_tagged_store non-N_IDENT
branch) writes all four ABI words to the dst slot unconditionally,
so caller-side residue in CX/R8 (the array-index IMULQ being the
canonical primer) landed at slot+16 and slot+24.

Worker-fmtparser surfaced this through fprintf's loop body where
array indexing primed CX and a 24B-return helper failed to clear
it; bug isn't loop-specific — straight-line repro at /tmp/wcrs_repro/
repro8.ww confirms.

Patch: emit `MOVQ $0, CX` after the variant's register shuffle when
the slot exceeds 16B and the variant doesn't fill CX; same for R8
when the slot exceeds 24B. Symmetric across cstage cgen.c and
wwstage cgenstmt.ww. Order: zero-MOVQs precede `MOVQ $tag, AX` so
AX-as-staging stays safe. Inline comment at cg_widen_tagged_store
non-N_IDENT branch documents the producer-zero contract.

Test 707 (cgreturn_variant_zero): 6 rows × both stages = 12 fixtures.
Covers scalar/bool/str returns after array-index priming in
straight-line / single-loop body / nested-loop body / mixed-variant
loop. Asm byte-identity check intentionally omitted; wwstage
taggedvariantindex divergence on str/bool N_IDENT is filed as task
#20. 995_self_rebuild covers the broader cross-stage drift surface.

ww2 == ww3 == ww4 byte-identical post-fix. 67/67 green.

Deferred (followups filed): #20 wwstage taggedvariantindex,
#21 [N]str/[N]bool array-literal non-pointer-half writes, #22
consolidate variant-widen into uniform scratch-slot path.
This commit is contained in:
Hojun-Cho
2026-05-16 01:37:15 +09:00
parent 6b6d7dd283
commit 166431a2da
6 changed files with 383 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
selfhost/cmd/w6c/main.combined.ww
View File

@@ -14663,6 +14663,14 @@ fn cgreturn(c: *cgen, n: *node) void = {
return;
};
let idx: i32 = taggedvariantindex(c, c.fnret, rhs);
// Tagged-return ABI: AX=tag, DX=word0, CX=word1,
// R8=word2. Receiver (cgwidentaggedstore call-source
// arm) writes AX/DX/CX/R8 unconditionally sized by the
// dst slot; unused ABI words must be zeroed here so a
// stale CX/R8 from the caller (e.g. a slice-stride
// IMULQ before the call) does not land in slot+16 /
// slot+24. (Task #18.)
let rsz: i32 = slotsize(c, c.fnret);
if (nodeisslice(c, rhs)) {
// cgexpr leaves (AX=ptr, BX=len, CX=cap).
// Shuffle into return ABI: DX=ptr, CX=len,
@@ -14673,8 +14681,20 @@ fn cgreturn(c: *cgen, n: *node) void = {
} else { if (nodeisstr(c, rhs)) {
emitline("\tMOVQ\tBX, CX\n");
emitline("\tMOVQ\tAX, DX\n");
// str fills DX,CX. Zero R8 if dst covers slot+24.
if (rsz > 24) {
emitline("\tMOVQ\t$0, R8\n");
};
} else {
emitline("\tMOVQ\tAX, DX\n");
// scalar fills DX only. Zero CX / R8 if dst
// covers slot+16 / slot+24.
if (rsz > 16) {
emitline("\tMOVQ\t$0, CX\n");
};
if (rsz > 24) {
emitline("\tMOVQ\t$0, R8\n");
};
};};
emitline("\tMOVQ\t$");
if (idx < 0) { idx = 0; };

20
selfhost/cmd/wcc/cgenstmt.ww
View File

@@ -230,6 +230,14 @@ fn cgreturn(c: *cgen, n: *node) void = {
return;
};
let idx: i32 = taggedvariantindex(c, c.fnret, rhs);
// Tagged-return ABI: AX=tag, DX=word0, CX=word1,
// R8=word2. Receiver (cgwidentaggedstore call-source
// arm) writes AX/DX/CX/R8 unconditionally sized by the
// dst slot; unused ABI words must be zeroed here so a
// stale CX/R8 from the caller (e.g. a slice-stride
// IMULQ before the call) does not land in slot+16 /
// slot+24. (Task #18.)
let rsz: i32 = slotsize(c, c.fnret);
if (nodeisslice(c, rhs)) {
// cgexpr leaves (AX=ptr, BX=len, CX=cap).
// Shuffle into return ABI: DX=ptr, CX=len,
@@ -240,8 +248,20 @@ fn cgreturn(c: *cgen, n: *node) void = {
} else { if (nodeisstr(c, rhs)) {
emitline("\tMOVQ\tBX, CX\n");
emitline("\tMOVQ\tAX, DX\n");
// str fills DX,CX. Zero R8 if dst covers slot+24.
if (rsz > 24) {
emitline("\tMOVQ\t$0, R8\n");
};
} else {
emitline("\tMOVQ\tAX, DX\n");
// scalar fills DX only. Zero CX / R8 if dst
// covers slot+16 / slot+24.
if (rsz > 16) {
emitline("\tMOVQ\t$0, CX\n");
};
if (rsz > 24) {
emitline("\tMOVQ\t$0, R8\n");
};
};};
emitline("\tMOVQ\t$");
if (idx < 0) { idx = 0; };

20
selfhost/cmd/wwdump/main.combined.ww
View File

@@ -14663,6 +14663,14 @@ fn cgreturn(c: *cgen, n: *node) void = {
return;
};
let idx: i32 = taggedvariantindex(c, c.fnret, rhs);
// Tagged-return ABI: AX=tag, DX=word0, CX=word1,
// R8=word2. Receiver (cgwidentaggedstore call-source
// arm) writes AX/DX/CX/R8 unconditionally sized by the
// dst slot; unused ABI words must be zeroed here so a
// stale CX/R8 from the caller (e.g. a slice-stride
// IMULQ before the call) does not land in slot+16 /
// slot+24. (Task #18.)
let rsz: i32 = slotsize(c, c.fnret);
if (nodeisslice(c, rhs)) {
// cgexpr leaves (AX=ptr, BX=len, CX=cap).
// Shuffle into return ABI: DX=ptr, CX=len,
@@ -14673,8 +14681,20 @@ fn cgreturn(c: *cgen, n: *node) void = {
} else { if (nodeisstr(c, rhs)) {
emitline("\tMOVQ\tBX, CX\n");
emitline("\tMOVQ\tAX, DX\n");
// str fills DX,CX. Zero R8 if dst covers slot+24.
if (rsz > 24) {
emitline("\tMOVQ\t$0, R8\n");
};
} else {
emitline("\tMOVQ\tAX, DX\n");
// scalar fills DX only. Zero CX / R8 if dst
// covers slot+16 / slot+24.
if (rsz > 16) {
emitline("\tMOVQ\t$0, CX\n");
};
if (rsz > 24) {
emitline("\tMOVQ\t$0, R8\n");
};
};};
emitline("\tMOVQ\t$");
if (idx < 0) { idx = 0; };