/*
 * 717_struct_byval_param — wwstage param-spill ABI for user-defined
 * by-value struct parameters of size ≤ 16B. Sister to #9 (which
 * fixed an OVER-allocation in the match-scrutinee spill path);
 * this is the UNDER-allocation in the cgfn param-spill path.
 *
 * Pre-fix (#11): wwstage cgfnparams dispatched on TK_ELLIPSIS,
 * float, tagged, slice, str — then a catch-all 8B scalar arm.
 * User-defined struct params (TY_STRUCT after collectstructs)
 * had no branch and fell through to the 8B arm. For
 * `fn cmp(a: inst, b: inst)` with `inst = struct { sec: i64,
 * nsec: i64 }` cstage allocated `TEXT cmp,$32` and spilled all
 * four argregs DI/SI/DX/CX; wwstage allocated `TEXT cmp,$16`
 * and spilled only DI/SI — the second-half value words of each
 * arg (DX/CX) were never stored, and `b.sec`/`b.nsec` reads
 * trailed into the saved-BP word. Built-in `str` (also 16B,
 * ptr+len) routed correctly through the isstrtype arm, so the
 * bug was a TY_STRUCT type-dispatch miss, not a missing path.
 *
 * Fix (#11, wwstage-only per rule 10): add structparamsize in
 * cgenutil.ww (mirror cstage cgen.c struct_arg_size: returns the
 * struct's totsize for sizes in (0, 16], else 0). Add a struct
 * arm in cgfnparams between the str arm and the 8B catch-all,
 * matching cstage's struct_eb = (size > 8) ? 2 : 1 — including
 * the partial-fit stitch arm (idx=5, nw=2: one reg, one stack
 * tail). Mirror the same isstr branch in cgfn's pre-scan so the
 * frame reservation and emit stay lockstep.
 *
 * What this test pins:
 *   - Asm byte-identity between cstage and wwstage for 2×16B
 *     struct params, 1×16B struct + 1×8B struct (mixed
 *     eightbyte counts), 1×16B struct + 1×str (regression guard
 *     for the already-working str path), and 6 i64 + 1 16B
 *     struct (partial-fit stitch case).
 *   - Runtime end-to-end: each row's main returns a deterministic
 *     exit code derived from the received struct's fields. A
 *     regression in the spill ABI (e.g. CX→slot+8 missing) shows
 *     up as a `got != want` exit-code mismatch.
 *
 * NOT covered:
 *   - Structs > 16B by-value param: cstage's struct_arg_size
 *     itself gates on size <= 16, so a 24B-struct param also
 *     under-allocates in cstage (falls through to the 8B arm).
 *     Both stages agree on the wrong behaviour, so it's bug-
 *     compatible byte-identical; that's a separate task.
 *   - Single-field i32-or-smaller struct: still 8B totsize after
 *     wwstage's registerstruct rounds up, equivalent to a scalar
 *     i64 in the spill path. The 1-field i64 row exercises the
 *     nw=1 branch.
 */
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/stat.h>
#include <sys/wait.h>
#include "wwtestpkg.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[] = {
	/* 1. Canonical 2×16B struct shape (the original probe). The
	 * comparator reads b.sec — that's the second-arg slot+0, which
	 * pre-fix sat unwritten and aliased the caller's saved BP. */
	{ "two_16B_struct_cmp",
	  "type inst = struct { sec: i64, nsec: i64 };\n"
	  "fn cmp(a: inst, b: inst) i32 = {\n"
	  "    if (a.sec < b.sec) { return -1; };\n"
	  "    if (a.sec > b.sec) { return 1; };\n"
	  "    if (a.nsec < b.nsec) { return -1; };\n"
	  "    if (a.nsec > b.nsec) { return 1; };\n"
	  "    return 0;\n"
	  "};\n"
	  "fn main() i32 = {\n"
	  "    let x: inst = inst { sec = 5i64, nsec = 200i64 };\n"
	  "    let y: inst = inst { sec = 5i64, nsec = 100i64 };\n"
	  "    let r: i32 = cmp(x, y);\n"
	  "    if (r > 0) { return 7; };\n"
	  "    return 0;\n"
	  "};\n",
	  7 },
	/* 2. 16B struct + 8B struct (mixed eightbyte counts). a uses
	 * DI/SI (2 eb), b uses DX (1 eb). Returns a.sec + a.nsec + b.v
	 * = 10 + 20 + 30 = 60. */
	{ "mixed_16B_8B_struct",
	  "type two = struct { sec: i64, nsec: i64 };\n"
	  "type one = struct { v: i64 };\n"
	  "fn sum(a: two, b: one) i32 = {\n"
	  "    return (a.sec + a.nsec + b.v): i32;\n"
	  "};\n"
	  "fn main() i32 = {\n"
	  "    let x: two = two { sec = 10i64, nsec = 20i64 };\n"
	  "    let y: one = one { v = 30i64 };\n"
	  "    return sum(x, y);\n"
	  "};\n",
	  60 },
	/* 3. 16B struct + 16B str (regression guard). The pre-fix
	 * wwstage already handled str via the isstrtype arm; this row
	 * pins that the new struct arm doesn't shadow it. struct in
	 * DI/SI, str in DX/CX. Returns a.sec + s.len = 42 + 3 = 45. */
	{ "struct_plus_str",
	  "type two = struct { sec: i64, nsec: i64 };\n"
	  "fn pick(a: two, s: str) i32 = {\n"
	  "    return (a.sec + (s.len: i64)): i32;\n"
	  "};\n"
	  "fn main() i32 = {\n"
	  "    let x: two = two { sec = 42i64, nsec = 0i64 };\n"
	  "    return pick(x, \"abc\");\n"
	  "};\n",
	  45 },
	/* 4. Partial-fit stitch: 5 i64 args consume DI/SI/DX/CX/R8;
	 * the 16B struct hits idx=5 with regs_left=1, nw=2 — one
	 * half (struct word 0) lands in R9, the second half spills
	 * onto the caller's stack at +16(BP). Wwstage's struct arm
	 * stitches both into a contiguous local slot. Returns
	 * sum(s0..s4) + x.a + x.b = 1+2+3+4+5+11+22 = 48. */
	{ "partial_fit_5i64_plus_16B",
	  "type pair = struct { a: i64, b: i64 };\n"
	  "fn manyfn(s0: i64, s1: i64, s2: i64, s3: i64, s4: i64,\n"
	  "         x: pair) i32 = {\n"
	  "    return (s0 + s1 + s2 + s3 + s4 + x.a + x.b): i32;\n"
	  "};\n"
	  "fn main() i32 = {\n"
	  "    let p: pair = pair { a = 11i64, b = 22i64 };\n"
	  "    return manyfn(1i64, 2i64, 3i64, 4i64, 5i64, p);\n"
	  "};\n",
	  48 },
};

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/wcsbp_%d_d_%d", getpid(), i);
	mkdir(tmpdir, 0755);
	snprintf(src,    sizeof src,    "%s/wcsbp_%d_%d.ww", tmpdir, getpid(), i);
	snprintf(outbin, sizeof outbin, "%s/wcsbp_%d_%d",    tmpdir, getpid(), i);
	snprintf(rmcmd,  sizeof rmcmd,  "rm -rf %s", tmpdir);

	FILE *f = fopen(src, "wb");
	if (!f) { runwait(rmcmd); return -1; }
	wwtest_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 — pin the spill prologue + frame size by
 * diffing the w6c vs w6c_ww text output. The whole point of #11
 * is that wwstage's frame stops under-bloating for user-defined
 * struct params, so the bytes must match. */
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/wcsbp_asm_%d_%d.ww", getpid(), i);
	snprintf(cs,  sizeof cs,  "/tmp/wcsbp_asm_%d_%d_c.s", getpid(), i);
	snprintf(ws,  sizeof ws,  "/tmp/wcsbp_asm_%d_%d_w.s", getpid(), i);

	FILE *f = fopen(src, "wb");
	if (!f) return -1;
	wwtest_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, "struct_byval_param: 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,
				    "struct_byval_param[%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,
		    "struct_byval_param: %d/%d fixtures failed\n",
		    fail, total);
		return 1;
	}
	printf("struct_byval_param: %d/%d ok\n", total, total);
	return 0;
}