ww/test/wcc/949_ptrarr_index_run.c

/*
 * 949_ptrarr_index_run — runtime + byte-id net for #61: indexing
 * through a pointer-to-array (`p[i]`, p: *[N]T) must stride by
 * size(T), the pointee array's ELEMENT, never by the whole-array
 * byte size.
 *
 * The family (one root class):
 *   A. wwstage value-route scaling — elemsizeofc's #270-2 nested-array
 *      block (selfhost/cmd/wcc/cgenutil.ww) fed a `*[N]T` pointee into
 *      the "outer stride = whole sub-array" rule that is only correct
 *      for [N][M]T / [][M]T. Every read/write/compound through `p[i]`
 *      scaled by N*size(T) (OOB for any i>=1), and the same wrong
 *      element belief reached the store-width chooser: a var-idx write
 *      emitted an N*8-byte aggregate copy sourced at the 8B rhs slot —
 *      OOB read of the frame neighborhood + OOB write at base+N*8*i,
 *      caller-frame smash. This is exactly lib/hash/siphash round()'s
 *      `v[0]=v0 .. v[3]=v3` corruption. cstage was runtime-correct
 *      (idx_eff, cgen.c:1163, peels TY_PTR→TY_ARRAY); wwstage aligned
 *      UP via the idxeffti/idxelemtn choke-point.
 *   B. `&p[i]` addr-of route — BOTH stages identically wrong
 *      (byte-id-BLIND): the TK_AMP &base[i] arm read bu->sub->size
 *      without the ptr peel, so &p[3]-&a[0] returned 3*N*size(T).
 *      Both stages converged on the idx_eff'd element size; only the
 *      RUNTIME rows here can pin this class — the 990-997 byte-id
 *      gates can never see a both-stages-identical miscompile.
 *
 * Each row carries (a) a cstage `ww build` + run asserting the exit
 * code and (b) a w6c vs w6c_ww `.s` cmp (rule-10 byte-id). Together
 * they pin BOTH stages: byte-id + cstage-runtime-correct implies
 * wwstage-runtime-correct. The matrix covers the elem widths the
 * scaling class is sensitive to ({1,2,4,8}B), const + var indices,
 * param / local / cast bases, read / write / compound routes,
 * neighbor-corruption guards, the &p[i] pointer-difference (B), and
 * the live consumer's mix-in-place shape (siphash round).
 *
 *   C. `(*p)[i]` explicit deref + index — BOTH stages SEGV'd
 *      identically (byte-id-blind): cgun's TK_STAR materialized an
 *      8-byte SCALAR load of a[0]'s value and the index used that
 *      VALUE as its base — a wild deref. Fixed in both stages at the
 *      deref choke-point: an ARRAY pointee takes the #185 *fn skip
 *      (an array value IS its address, #270-1a), so `*p` leaves AX =
 *      p's value and every index/addr-of/store route through
 *      `cgexpr(base)` materializes the array address for free. The
 *      deref_* rows pin read / write / compound at 8B and narrow
 *      widths (the narrow rows also pin the wwstage N_UN-base
 *      stamped-tinfo esz arm against the 8B default).
 */
#include <stdio.h>
#include <stdlib.h>
#include <string.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_exit; };

static const struct row rows[] = {
	/* A: read, const idx, param base, 8B elem (ken p2). Pre-fix
	 * wwstage strode 32 → read past the array. */
	{ "rd_u64_param_const",
	  "package main;\n"
	  "fn rd(p: *[4]u64) u64 = {\n"
	  "	return p[1];\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u64 = [100u64, 101u64, 102u64, 103u64];\n"
	  "	return rd(&a): i32;\n"
	  "};\n", 101 },
	/* A: read, var idx, 1B elem. */
	{ "rd_u8_param_var",
	  "package main;\n"
	  "fn rd(p: *[4]u8, i: i32) u8 = {\n"
	  "	return p[i];\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u8 = [10u8, 20u8, 30u8, 40u8];\n"
	  "	return rd(&a, 2): i32;\n"
	  "};\n", 30 },
	/* A: read, 2B elem. */
	{ "rd_u16_param",
	  "package main;\n"
	  "fn rd(p: *[4]u16) u16 = {\n"
	  "	return p[3];\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u16 = [11u16, 22u16, 33u16, 44u16];\n"
	  "	return rd(&a): i32;\n"
	  "};\n", 44 },
	/* A: read, 4B elem. */
	{ "rd_u32_param",
	  "package main;\n"
	  "fn rd(p: *[4]u32) u32 = {\n"
	  "	return p[2];\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u32 = [11u32, 22u32, 33u32, 44u32];\n"
	  "	return rd(&a): i32;\n"
	  "};\n", 33 },
	/* A: signed-narrow elem behind the ptr — pins the MOVSXD
	 * sign-extend the idxeffti'd elemissignedc picks (an undrilled
	 * read of the ptr tinfo classified the ARRAY: unsigned). */
	{ "rd_i32_signed",
	  "package main;\n"
	  "fn rd(p: *[4]i32) i32 = {\n"
	  "	return p[1];\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]i32 = [7, -5, 9, 1];\n"
	  "	return rd(&a) + 10;\n"
	  "};\n", 5 },
	/* A: write, const idx (ken p3) — scale-only half. */
	{ "wr_u64_param_const",
	  "package main;\n"
	  "fn wr(p: *[4]u64) void = {\n"
	  "	p[1] = 7u64;\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u64 = [1u64, 2u64, 3u64, 4u64];\n"
	  "	wr(&a);\n"
	  "	return (a[0] + a[1] + a[2]): i32;\n"
	  "};\n", 11 },
	/* A: write, VAR idx + param rhs (ken p10) — the corruption
	 * proof: pre-fix wwstage emitted a 32B aggregate copy sourced
	 * at &x (reading i, p, saved BP) to base+32*i → frame smash /
	 * SIGSEGV. Neighbor guards assert no byte outside a[1] moved. */
	{ "wr_u64_varidx_paramrhs",
	  "package main;\n"
	  "fn wr(p: *[4]u64, i: i32, x: u64) void = {\n"
	  "	p[i] = x;\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u64 = [10u64, 11u64, 12u64, 13u64];\n"
	  "	let i: i32 = 1;\n"
	  "	wr(&a, i, 77u64);\n"
	  "	if (a[0] != 10u64) { return 1; };\n"
	  "	if (a[1] != 77u64) { return 2; };\n"
	  "	if (a[2] != 12u64) { return 3; };\n"
	  "	if (a[3] != 13u64) { return 4; };\n"
	  "	return 0;\n"
	  "};\n", 0 },
	/* A: write, 1B elem, neighbor guards at the tightest width. */
	{ "wr_u8_neighbors",
	  "package main;\n"
	  "fn wr(p: *[4]u8) void = {\n"
	  "	p[1] = 9u8;\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u8 = [1u8, 2u8, 3u8, 4u8];\n"
	  "	wr(&a);\n"
	  "	return (a[0] + a[1] + a[2]): i32;\n"
	  "};\n", 13 },
	/* A: compound, const idx, 8B elem (ken p9b). */
	{ "compound_u64",
	  "package main;\n"
	  "fn add5(p: *[4]u64) void = {\n"
	  "	p[1] += 5u64;\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u64 = [100u64, 101u64, 102u64, 103u64];\n"
	  "	add5(&a);\n"
	  "	return a[1]: i32;\n"
	  "};\n", 106 },
	/* A: compound, var idx, 4B elem. */
	{ "compound_u32_varidx",
	  "package main;\n"
	  "fn addat(p: *[4]u32, i: i32) void = {\n"
	  "	p[i] += 7u32;\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u32 = [10u32, 20u32, 30u32, 40u32];\n"
	  "	addat(&a, 2);\n"
	  "	return a[2]: i32;\n"
	  "};\n", 37 },
	/* A: local-ptr base, no call boundary (ken p4). */
	{ "rd_localptr",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u64 = [100u64, 101u64, 102u64, 103u64];\n"
	  "	let p: *[4]u64 = &a;\n"
	  "	return p[2]: i32;\n"
	  "};\n", 102 },
	/* A: cast base (ken p6). */
	{ "rd_castbase",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let big: [4]u64 = [5u64, 6u64, 7u64, 8u64];\n"
	  "	let p: *[4]u64 = (&big): *[4]u64;\n"
	  "	return p[1]: i32;\n"
	  "};\n", 6 },
	/* A: nested *[2][3]u32 (ken p16) — the elemsizeofc N_TPTR
	 * carve-out must coexist with the #270-2 outer-stride rule for
	 * the pointee's OWN nesting: inner stride 4, outer 12. Read,
	 * write, neighbor guards; param + local ptr bases. */
	{ "nested_2d",
	  "package main;\n"
	  "fn rd(p: *[2][3]u32, i: i32, j: i32) u32 = { return p[i][j]; };\n"
	  "export fn main() i32 = {\n"
	  "	let a: [2][3]u32;\n"
	  "	a[0][0] = 0: u32; a[0][1] = 1: u32; a[0][2] = 2: u32;\n"
	  "	a[1][0] = 10: u32; a[1][1] = 11: u32; a[1][2] = 12: u32;\n"
	  "	if (rd(&a, 1, 2) != 12: u32) { return 1; };\n"
	  "	if (rd(&a, 0, 1) != 1: u32) { return 2; };\n"
	  "	let p: *[2][3]u32 = &a;\n"
	  "	p[1][0] = 99: u32;\n"
	  "	if (a[1][0] != 99: u32) { return 3; };\n"
	  "	if (a[1][1] != 11: u32) { return 4; };\n"
	  "	if (a[0][2] != 2: u32) { return 5; };\n"
	  "	return 0;\n"
	  "};\n", 0 },
	/* A: *[3]str — 3-word (ptr,len,cap) header elements; pins the
	 * read-side str-header gate on the idx_eff'd element. Pre-fix
	 * BOTH stages were runtime-wrong here, differently: cstage's
	 * u->sub gate missed the ptr base and dropped len/cap (ken
	 * p17). */
	{ "rd_str_elem",
	  "package main;\n"
	  "fn lenof(p: *[3]str, i: i32) i32 = { return p[i].len; };\n"
	  "export fn main() i32 = {\n"
	  "	let a: [3]str;\n"
	  "	a[0] = \"x\"; a[1] = \"yy\"; a[2] = \"zzz\";\n"
	  "	if (lenof(&a, 2) != 3) { return 1; };\n"
	  "	if (lenof(&a, 0) != 1) { return 2; };\n"
	  "	let p: *[3]str = &a;\n"
	  "	if (p[1].len != 2) { return 3; };\n"
	  "	return 0;\n"
	  "};\n", 0 },
	/* B: &p[i] pointer difference (ken p8b) — both stages emitted
	 * the whole-array stride (96) byte-IDENTICALLY pre-fix; only
	 * this runtime row can see the class. 3 * size(u64) = 24. */
	{ "amp_diff_u64",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u64 = [1u64, 2u64, 3u64, 4u64];\n"
	  "	let p: *[4]u64 = &a;\n"
	  "	let d: u64 = (&p[3]): u64 - (&a[0]): u64;\n"
	  "	return d: i32;\n"
	  "};\n", 24 },
	/* B: &p[i] difference at a narrow width. 3 * size(u16) = 6. */
	{ "amp_diff_u16",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u16 = [1u16, 2u16, 3u16, 4u16];\n"
	  "	let p: *[4]u16 = &a;\n"
	  "	let d: u64 = (&p[3]): u64 - (&a[0]): u64;\n"
	  "	return d: i32;\n"
	  "};\n", 6 },
	/* A: the live consumer's shape — siphash round() mutates all
	 * four lanes through the param ptr, each read feeding a later
	 * write. Pre-fix wwstage smashed the caller frame here. */
	{ "mix_inplace_round",
	  "package main;\n"
	  "fn mix(v: *[4]u64) void = {\n"
	  "	v[0] += v[1];\n"
	  "	v[2] += v[3];\n"
	  "	v[1] += v[0];\n"
	  "	v[3] += v[2];\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let v: [4]u64 = [1u64, 2u64, 3u64, 4u64];\n"
	  "	mix(&v);\n"
	  "	if (v[0] != 3u64)  { return 1; };\n"
	  "	if (v[1] != 5u64)  { return 2; };\n"
	  "	if (v[2] != 7u64)  { return 3; };\n"
	  "	if (v[3] != 11u64) { return 4; };\n"
	  "	return 0;\n"
	  "};\n", 0 },
	/* C: (*p)[i] read, 8B elem (ken p7 — SEGV'd both stages). */
	{ "deref_rd_u64",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u64 = [100u64, 101u64, 102u64, 103u64];\n"
	  "	let p: *[4]u64 = &a;\n"
	  "	return (*p)[1]: i32;\n"
	  "};\n", 101 },
	/* C: (*p)[i] read, 4B elem — pins the N_UN-base esz arm (the 8B
	 * default would mis-stride once the base materializes). */
	{ "deref_rd_u32",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u32 = [11u32, 22u32, 33u32, 44u32];\n"
	  "	let p: *[4]u32 = &a;\n"
	  "	return (*p)[2]: i32;\n"
	  "};\n", 33 },
	/* C: (*p)[i] read through a param base. */
	{ "deref_rd_param",
	  "package main;\n"
	  "fn rd(p: *[4]u64) u64 = {\n"
	  "	return (*p)[1];\n"
	  "};\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u64 = [100u64, 101u64, 102u64, 103u64];\n"
	  "	return rd(&a): i32;\n"
	  "};\n", 101 },
	/* C: (*p)[i] write, 8B elem. */
	{ "deref_wr_u64",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u64 = [1u64, 2u64, 3u64, 4u64];\n"
	  "	let p: *[4]u64 = &a;\n"
	  "	(*p)[1] = 7u64;\n"
	  "	return (a[0] + a[1] + a[2]): i32;\n"
	  "};\n", 11 },
	/* C: (*p)[i] write, 1B elem, neighbor guards. */
	{ "deref_wr_u8",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u8 = [1u8, 2u8, 3u8, 4u8];\n"
	  "	let p: *[4]u8 = &a;\n"
	  "	(*p)[1] = 9u8;\n"
	  "	return (a[0] + a[1] + a[2]): i32;\n"
	  "};\n", 13 },
	/* C: (*p)[i] compound. */
	{ "deref_compound_u64",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u64 = [100u64, 101u64, 102u64, 103u64];\n"
	  "	let p: *[4]u64 = &a;\n"
	  "	(*p)[1] += 5u64;\n"
	  "	return a[1]: i32;\n"
	  "};\n", 106 },
	{ NULL, NULL, 0 }
};

static int
slurp_eq(const char *a, const char *b)
{
	FILE *fa = fopen(a, "rb");
	FILE *fb = fopen(b, "rb");
	if (!fa || !fb) { if (fa) fclose(fa); if (fb) fclose(fb); return -1; }
	int rc = 0;
	for (;;) {
		int ca = fgetc(fa);
		int cb = fgetc(fb);
		if (ca != cb) { rc = -1; break; }
		if (ca == EOF) break;
	}
	fclose(fa); fclose(fb);
	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 w6c[1100], w6c_ww[1100];
	snprintf(w6c, sizeof w6c, "%s/w6c", bin);
	snprintf(w6c_ww, sizeof w6c_ww, "%s/w6c_ww", bin);
	if (access(w6c_ww, X_OK) != 0) {
		fprintf(stderr, "ptrarr_index: w6c_ww missing — cannot run "
		    "the cs==ww byte-id gate\n");
		return 1;
	}

	int n = 0, fail = 0;
	for (int i = 0; rows[i].src; i++, n++) {
		char src[64];
		snprintf(src, sizeof src, "/tmp/wwpai_%d_%d.ww", getpid(), i);
		FILE *f = fopen(src, "wb");
		if (f == NULL) { fail++; continue; }
		fputs(rows[i].src, f);
		fclose(f);

		/* (a) cstage build + run. */
		char tmpdir[64];
		snprintf(tmpdir, sizeof tmpdir, "/tmp/wwpai_%d_d_%d",
		    getpid(), i);
		mkdir(tmpdir, 0755);

		char cmd[2048];
		snprintf(cmd, sizeof cmd, "cd %s && %s/ww build %s",
		    tmpdir, bin, src);
		if (runwait(cmd) != 0) {
			fprintf(stderr, "row[%s]: cstage build failed\n",
			    rows[i].label);
			fail++;
			unlink(src); rmdir(tmpdir);
			continue;
		}

		char outbin[128];
		const char *base = strrchr(src, '/');
		base = base ? base + 1 : src;
		snprintf(outbin, sizeof outbin, "%s/%s", tmpdir, base);
		char *dot = strrchr(outbin, '.');
		if (dot && strcmp(dot, ".ww") == 0) *dot = '\0';

		int got = runwait(outbin);
		if (got != rows[i].want_exit) {
			fprintf(stderr, "row[%s]: cstage exit %d, want %d\n",
			    rows[i].label, got, rows[i].want_exit);
			fail++;
		}
		unlink(outbin); rmdir(tmpdir);

		/* (b) cs==ww byte-id gate. */
		char cs_s[64], ws_s[64];
		snprintf(cs_s, sizeof cs_s, "/tmp/wwpai_%d_%d_cs.s",
		    getpid(), i);
		snprintf(ws_s, sizeof ws_s, "/tmp/wwpai_%d_%d_ww.s",
		    getpid(), i);

		snprintf(cmd, sizeof cmd, "%s -o %s %s 2>/dev/null",
		    w6c, cs_s, src);
		if (runwait(cmd) != 0) {
			fprintf(stderr, "row[%s]: w6c failed\n", rows[i].label);
			fail++; unlink(src); continue;
		}
		snprintf(cmd, sizeof cmd, "%s -o %s %s 2>/dev/null",
		    w6c_ww, ws_s, src);
		if (runwait(cmd) != 0) {
			fprintf(stderr, "row[%s]: w6c_ww failed\n",
			    rows[i].label);
			fail++; unlink(src); unlink(cs_s); continue;
		}
		if (slurp_eq(cs_s, ws_s) != 0) {
			fprintf(stderr,
			    "row[%s]: cstage/wwstage .s DIFFER (rule-10 "
			    "byte-id violation)\n", rows[i].label);
			fail++;
		}
		unlink(src); unlink(cs_s); unlink(ws_s);
	}

	if (fail) {
		fprintf(stderr, "%d/%d ptrarr-index tests failed\n", fail, n);
		return 1;
	}
	printf("ptrarr_index: %d/%d ok (cstage run + cs==ww byte-id)\n",
	    n, n);
	return 0;
}