ww/test/wcc/702_dot_explicit_deref.c

/*
 * 702_dot_explicit_deref — silent miscompile of `(*p).f` (task #16).
 *
 * Pre-existing landmine surfaced by worker-cgnassign during #5
 * (whole-struct N_ASSIGN). Both cstage cgen.c N_ASSIGN N_DOT and
 * wwstage cgenexpr.ww cgassign single-dot dispatch gated on
 * `n->lhs->lhs->kind == N_IDENT`. The parser produces N_UN(STAR,
 * IDENT(p)) for `(*p).f`, so the store fell off the dispatch and
 * silently emitted nothing. Read-side N_DOT had the same gap —
 * the pointer-auto-deref load branch required N_IDENT and fell
 * through to cgexpr on the N_UN, which derefs the pointer as a
 * scalar (load 8B from p into AX, then the field part is dropped).
 *
 * Not exercised by current selfhost source (auto-deref `p.f` was
 * used throughout) so 995_self_rebuild didn't catch it. Latent for
 * any future user code that types out the explicit deref.
 *
 * The fix in both stages is a base/lhs retarget: when the parser
 * shape is N_UN(STAR, IDENT(p)), substitute the inner IDENT so
 * the existing via_ptr / pointer-auto-deref branch fires the same
 * as `p.f`. v1 scope is bare-IDENT inner only; `(*expr).f` with a
 * non-IDENT pointer expression (`(*arr[i]).f`, `(*g.p).f`) still
 * drops silently, tracked as a follow-up — needs cgexpr(inner) →
 * reg + RHS-spill scheduling, which is a different design.
 *
 * Each row pins:
 *   - cstage value correctness (process exit code).
 *   - wwstage value correctness (when ww_ww exists).
 *   - cstage vs wwstage byte-identical .s output (catches drift).
 */
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/stat.h>
#include <sys/wait.h>

static int
runwait(const char *cmd)
{
	int rc = system(cmd);
	if (rc == -1) return -1;
	if (WIFEXITED(rc)) return WEXITSTATUS(rc);
	return -1;
}

struct row { const char *label; const char *src; int want; };

static const struct row rows[] = {
	/* Write side, scalar i64 field via explicit deref.
	 * Pre-fix: cgassign single-dot dispatch fell off (base.kind
	 * was N_UN, not N_IDENT) and emitted no store. f stayed 0. */
	{ "write_i64",
	  "type pt = struct { x: i64, y: i64 };\n"
	  "fn main() i32 = {\n"
	  "    let s: pt = pt { x = 0i64, y = 0i64 };\n"
	  "    let p: *pt = &s;\n"
	  "    (*p).x = 7i64;\n"
	  "    (*p).y = 35i64;\n"
	  "    return (s.x + s.y): i32;\n"
	  "};\n",
	  42 },
	/* Write side, narrow i32 field. Pins fldstoreop sizing on
	 * the via_ptr path — MOVL not MOVQ (which would stomp 4 bytes
	 * past the field). */
	{ "write_i32",
	  "type box = struct { a: i32, b: i32, c: i32 };\n"
	  "fn main() i32 = {\n"
	  "    let s: box = box { a = 0, b = 0, c = 0 };\n"
	  "    let p: *box = &s;\n"
	  "    (*p).a = 5;\n"
	  "    (*p).b = 11;\n"
	  "    (*p).c = 19;\n"
	  "    return s.a + s.b + s.c;\n"
	  "};\n",
	  35 },
	/* Write side, str field. Pins the str-typed field branch in
	 * the via_ptr path (cgexpr → AX=ptr/BX=len, store both halves
	 * at +0/+8 — not just AX). Initialiser uses `let v: box;`
	 * (zero-fill) instead of a struct literal because N_LET
	 * N_STRUCTLIT silently drops the .len half of a str-typed
	 * field — a separate pre-existing bug, out of scope here. */
	{ "write_str",
	  "type box = struct { s: str, n: i64 };\n"
	  "fn main() i32 = {\n"
	  "    let v: box;\n"
	  "    let p: *box = &v;\n"
	  "    (*p).s = \"hi\";\n"
	  "    (*p).n = 40i64;\n"
	  "    return (v.s.len: i64 + v.n): i32;\n"
	  "};\n",
	  42 },
	/* Read side, scalar i64 field via explicit deref.
	 * Pre-fix: case N_DOT's pointer-auto-deref branch required
	 * N_IDENT and fell through to `cgexpr(c, n->lhs, ...)` —
	 * derefed the pointer as if loading a scalar, so AX held the
	 * first qword of the struct (s.x = 50). Field offset for .y
	 * (+8) was dropped → returned 50 instead of 80. */
	{ "read_i64",
	  "type pt = struct { x: i64, y: i64 };\n"
	  "fn main() i32 = {\n"
	  "    let s: pt = pt { x = 50i64, y = 80i64 };\n"
	  "    let p: *pt = &s;\n"
	  "    return (*p).y: i32;\n"
	  "};\n",
	  80 },
	/* Read side, narrow i32 field. Pins fldloadop sizing — MOVL
	 * with sign-extend, not raw MOVQ. */
	{ "read_i32",
	  "type box = struct { a: i32, b: i32, c: i32 };\n"
	  "fn main() i32 = {\n"
	  "    let s: box = box { a = 1, b = 2, c = 3 };\n"
	  "    let p: *box = &s;\n"
	  "    return (*p).a + (*p).b + (*p).c;\n"
	  "};\n",
	  6 },
	/* Read side, str field. Pins the str-typed field load path —
	 * AX=ptr, BX=len. .len is the receive-side check. Initialiser
	 * uses write-by-field (same str-in-structlit-init bug avoided
	 * as in write_str). */
	{ "read_str_len",
	  "type box = struct { s: str };\n"
	  "fn main() i32 = {\n"
	  "    let v: box;\n"
	  "    v.s = \"hello\";\n"
	  "    let p: *box = &v;\n"
	  "    return (*p).s.len: i32;\n"
	  "};\n",
	  5 },
	/* Mixed: write via (*p).f then read via (*p).f. End-to-end
	 * round-trip pins both sides agreeing on the same offset and
	 * width. */
	{ "roundtrip",
	  "type pt = struct { x: i32, y: i32, z: i32 };\n"
	  "fn main() i32 = {\n"
	  "    let s: pt = pt { x = 0, y = 0, z = 0 };\n"
	  "    let p: *pt = &s;\n"
	  "    (*p).x = 4;\n"
	  "    (*p).y = 7;\n"
	  "    (*p).z = 13;\n"
	  "    return (*p).x + (*p).y + (*p).z;\n"
	  "};\n",
	  24 },
};

/* run_driver — compile r->src via the given driver and exec; return
 * the process exit code. Mirror of 701's helper. */
static int
run_driver(const char *driver, const struct row *r, int i)
{
	char tmpdir[64], src[128], outbin[128], rmcmd[160], cmd[1024];
	snprintf(tmpdir, sizeof tmpdir, "/tmp/wded_%d_d_%d", getpid(), i);
	mkdir(tmpdir, 0755);
	snprintf(src,    sizeof src,    "%s/wded_%d_%d.ww", tmpdir, getpid(), i);
	snprintf(outbin, sizeof outbin, "%s/wded_%d_%d",    tmpdir, getpid(), i);
	snprintf(rmcmd,  sizeof rmcmd,  "rm -rf %s", tmpdir);

	FILE *f = fopen(src, "wb");
	if (!f) { runwait(rmcmd); return -1; }
	fputs(r->src, f);
	fclose(f);

	snprintf(cmd, sizeof cmd, "%s build -o %s %s", driver, outbin, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "row[%s]: build via %s failed\n",
		    r->label, driver);
		runwait(rmcmd);
		return -1;
	}

	int got = runwait(outbin);

	runwait(rmcmd);
	return got;
}

/* asm_byte_identical — generate .s via cstage's w6c and wwstage's
 * w6c_ww and diff. Mirror of 701. */
static int
asm_byte_identical(const char *bin, const struct row *r, int i)
{
	char src[64], cs[64], ws[64], cmd[1024];
	snprintf(src, sizeof src, "/tmp/wded_asm_%d_%d.ww", getpid(), i);
	snprintf(cs,  sizeof cs,  "/tmp/wded_asm_%d_%d_c.s", getpid(), i);
	snprintf(ws,  sizeof ws,  "/tmp/wded_asm_%d_%d_w.s", getpid(), i);

	FILE *f = fopen(src, "wb");
	if (!f) return -1;
	fputs(r->src, f);
	fclose(f);

	snprintf(cmd, sizeof cmd, "%s/w6c -o %s %s 2>/dev/null", bin, cs, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "row[%s]: w6c errored\n", r->label);
		unlink(src);
		return -1;
	}
	snprintf(cmd, sizeof cmd, "%s/w6c_ww -o %s %s 2>/dev/null",
	    bin, ws, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "row[%s]: w6c_ww errored\n", r->label);
		unlink(src); unlink(cs);
		return -1;
	}

	FILE *fc = fopen(cs, "rb");
	FILE *fw = fopen(ws, "rb");
	int rc = 0;
	if (!fc || !fw) {
		rc = -1;
	} else {
		for (;;) {
			int a = fgetc(fc);
			int b = fgetc(fw);
			if (a != b) { rc = -1; break; }
			if (a == EOF) break;
		}
	}
	if (fc) fclose(fc);
	if (fw) fclose(fw);
	if (rc != 0)
		fprintf(stderr, "row[%s]: cstage vs wwstage asm differs\n",
		    r->label);
	unlink(src); unlink(cs); unlink(ws);
	return rc;
}

int
main(void)
{
	const char *bin = getenv("BIN");
	if (!bin) bin = "out/bin";
	char absbin[1024];
	if (bin[0] != '/') {
		char cwd[1024];
		if (getcwd(cwd, sizeof cwd) == NULL) return 1;
		snprintf(absbin, sizeof absbin, "%s/%s", cwd, bin);
		bin = absbin;
	}

	char cdrv[1024];
	snprintf(cdrv, sizeof cdrv, "%s/ww", bin);
	char wdrv[1024];
	snprintf(wdrv, sizeof wdrv, "%s/ww_ww", bin);

	struct { const char *name; const char *path; int gated_on_existence; }
	drivers[] = {
		{ "cstage",  cdrv, 0 },
		{ "wwstage", wdrv, 1 },
		{ NULL, NULL, 0 },
	};

	int n = (int)(sizeof rows / sizeof rows[0]);
	int total = 0, fail = 0;

	for (int d = 0; drivers[d].name; d++) {
		if (drivers[d].gated_on_existence
		    && access(drivers[d].path, X_OK) != 0) {
			fprintf(stderr, "dot_explicit_deref: skip %s (no %s)\n",
			    drivers[d].name, drivers[d].path);
			continue;
		}
		for (int i = 0; i < n; i++) {
			int got = run_driver(drivers[d].path, &rows[i], i);
			total++;
			if (got != rows[i].want) {
				fprintf(stderr,
				    "dot_explicit_deref[%s][%s]: exit=%d want=%d\n",
				    drivers[d].name, rows[i].label,
				    got, rows[i].want);
				fail++;
			}
		}
	}

	if (access(wdrv, X_OK) == 0) {
		for (int i = 0; i < n; i++) {
			total++;
			if (asm_byte_identical(bin, &rows[i], i) != 0)
				fail++;
		}
	}

	if (fail) {
		fprintf(stderr,
		    "dot_explicit_deref: %d/%d fixtures failed\n",
		    fail, total);
		return 1;
	}
	printf("dot_explicit_deref: %d/%d ok\n", total, total);
	return 0;
}