ww/test/wcc/758_cgalloc_str_field.c

/*
 * 758_cgalloc_str_field — cgalloc N_STRUCTLIT str-field store (task #22)
 * and the cgalloc CALL-site ffiresolve parity (task #25 / #24-part-A).
 *
 * Pre-fix (#22): wwstage cgalloc's per-field walk routed str-typed
 * fields through the generic `MOVQ (SP), BX ; MOVQ AX, foff(BX)` path,
 * which landed only AX (str.ptr) and clobbered BX (str.len) with the
 * heap base. str.len silently stayed zero (rt_malloc is MAP_ANON-backed,
 * so the slot was zero-init rather than garbage — but still wrong).
 * 990 and 995 byte-identity didn't catch this because nothing in the
 * bootstrapped selfhost source uses `alloc(T { strfield = "..." })!`.
 *
 * Fix (#22): a str-field-typed branch mirrors cmd/w6c/cgen.c:4184-4190
 * — route the heap base through CX so BX=len survives both stores
 * (ptr at foff+0, len at foff+8). Task #23 (slice/tagged/fn-pair
 * multi-word fields) is the broader follow-up; this row pins str.
 *
 * Pre-fix (#25): wwstage's cgalloc emitted a hardcoded `CALL
 * rt_malloc(SB)` while cstage routed the same site through
 * ffi_resolve("alloc"), so direct `w6c` vs `w6c_ww` on a fixture
 * without the @symbol decl in scope diverged (cstage: `CALL
 * alloc(SB)`; wwstage: `CALL rt_malloc(SB)`). The fix swaps both
 * cgenexpr.ww and cgenstmt.ww cgalloc CALL sites to
 * `ffiresolve(c, "malloc")`, aligning wwstage down to the leaner
 * cstage shape (CLAUDE.md rule 10). The `asm_rows` table below pins
 * the CALL line via single-file `w6c -o` / `w6c_ww -o`; `ww build`
 * combines lib/rt/malloc.ww into the fixture and would always supply
 * the @symbol decl, masking the regression.
 *
 * The runtime rows moved to the test/wcc/data/r75_alloc_{str_singleton,
 * i32_then_str,str_then_i32,two_str,f64_str_i32,str_readback} fixtures;
 * this carrier retains only the asm-line checks below.
 *
 * Full asm byte-identity is intentionally NOT checked here — the
 * `(BX)` (cstage txt.c omits zero displacement) vs `0(BX)` (wwstage
 * emitint(0) is unconditional) divergence still stands. The new str
 * branch follows the existing float / int branch shape and inherits
 * the same formatting; aligning all three with cstage is task #24
 * part B.
 */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.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;
}

/* asm_row — fixture for the ffiresolve CALL-line check. `want_sym`
 * is the unqualified symbol expected inside `CALL\t<sym>(SB)` from
 * both stages' .s output. Single-file `w6c` compile (no `ww build`
 * combine), so the @symbol decl is only in scope when the fixture
 * writes one — that's how `noscope_*` rows pin the pre-fix wwstage
 * hardcoded-`rt_malloc` divergence and `withsym_*` rows pin that
 * ffiresolve actually hits when the decl is present. */
struct asm_row { const char *label; const char *src; const char *want_sym; };

static const struct asm_row asm_rows[] = {
	/* Int-field, no @symbol in scope. ffiresolve("malloc") misses the
	 * ffi table and returns "malloc" unchanged on both stages. Pre-fix
	 * wwstage hardcoded `CALL rt_malloc(SB)` → diverged from cstage's
	 * ffi_resolve-mediated `CALL malloc(SB)`. */
	{ "noscope_intfield",
	  "package main;\n"
	  "type holder = struct { n: i32 };\n"
	  "fn dummy() *holder = { return alloc(holder { n = 42 })!; };\n",
	  "malloc" },
	/* Str-field, no @symbol in scope. Confirms the str-field branch
	 * (the #22 fix) still routes its CALL through ffiresolve, not a
	 * stray hardcoded literal copied alongside the #22 emit. */
	{ "noscope_strfield",
	  "package main;\n"
	  "type holder = struct { s: str };\n"
	  "fn dummy() *holder = { return alloc(holder { s = \"hi\" })!; };\n",
	  "malloc" },
	/* Two-step let-then-assign. cglet's CALL site (cgenstmt.ww:647)
	 * is the second cgalloc emit point; this row covers it. */
	{ "noscope_let_then_assign",
	  "package main;\n"
	  "type holder = struct { n: i32 };\n"
	  "fn dummy() *holder = {\n"
	  "    let p: *holder = alloc(holder { n = 0 })!;\n"
	  "    p.n = 7;\n"
	  "    return p;\n"
	  "};\n",
	  "malloc" },
	/* Explicit @symbol decl in scope. ffiresolve("malloc") → "rt_malloc"
	 * so both stages emit `CALL rt_malloc(SB)` — positive confirmation
	 * that the ffi table lookup hits, complementing the noscope rows. */
	{ "withsym_intfield",
	  "package main;\n"
	  "@symbol(\"rt_malloc\") export fn malloc(n: u64) *void;\n"
	  "type holder = struct { n: i32 };\n"
	  "fn dummy() *holder = { return alloc(holder { n = 42 })!; };\n",
	  "rt_malloc" },
};

/* asm_disp_row — pins the foff=0 displacement formatting (#24 part B).
 * cstage's txt.c prints `(REG)` for zero displacement (cmd/w6c/txt.c
 * prAdr D_INDIR); pre-fix wwstage emitted `0(REG)` via an unconditional
 * `emitint(fi.foff)`. Each row supplies a `want_line` that MUST appear
 * verbatim in BOTH stages' .s output. With the fix (4 emit sites routed
 * through `emitdispreg` SSoT) wwstage matches cstage; without it the
 * wwstage half fails because `0(REG)` is a different line. */
struct asm_disp_row { const char *label; const char *src; const char *want_line; };

static const struct asm_disp_row asm_disp_rows[] = {
	/* str at foff=0. Covers the str-field branch's first store
	 * (cgenexpr.ww cgalloc, MOVQ AX, (CX)). The companion +8 store
	 * always has a non-zero displacement so it's not the gate; the
	 * .ptr store is. */
	{ "alloc_str_at_offset0",
	  "package main;\n"
	  "type holder = struct { s: str };\n"
	  "fn dummy() *holder = { return alloc(holder { s = \"x\" })!; };\n",
	  /* #1/Phase 3: str IS []u8 (24B), so the alloc-str-field store
	   * routes the heap base through DX (CX now holds the cap) and
	   * writes 3 words (ptr/len/cap). Was `(CX)` in the 16B world. */
	  "\tMOVQ\tAX, (DX)\n" },
	/* str at non-zero foff. Pins that the displacement IS emitted
	 * (`8(CX)`) when foff != 0 — emitdispreg must not suppress
	 * non-zero offsets too. Pre-fix and post-fix both pass this; it
	 * guards against a future over-correction. */
	{ "alloc_str_at_nonzero_offset",
	  "package main;\n"
	  "type holder = struct { pad: i64, s: str };\n"
	  "fn dummy() *holder = {\n"
	  "    return alloc(holder { pad = 0, s = \"x\" })!;\n"
	  "};\n",
	  /* #1/Phase 3: DX base (str IS []u8, cap in CX); was `8(CX)`. */
	  "\tMOVQ\tAX, 8(DX)\n" },
	/* Generic 8-byte field at foff=0 (non-str, non-float path). Covers
	 * the `else` branch's `MOVQ AX, (BX)` store via fieldstoreop. */
	{ "alloc_int_at_offset0",
	  "package main;\n"
	  "type holder = struct { n: i64 };\n"
	  "fn dummy() *holder = { return alloc(holder { n = 42 })!; };\n",
	  "\tMOVQ\tAX, (BX)\n" },
	/* f64 at foff=0. Covers the float branch's `MOVSD X0, (BX)`
	 * store; mirrors the int row but routes through the MOVSD emit. */
	{ "alloc_f64_at_offset0",
	  "package main;\n"
	  "type holder = struct { f: f64 };\n"
	  "fn dummy() *holder = { return alloc(holder { f = 1.0f64 })!; };\n",
	  "\tMOVSD\tX0, (BX)\n" },
};

/* asm_call_check — compile via direct w6c / w6c_ww (no `ww build`),
 * extract the `CALL\t<sym>(SB)` line referencing alloc/rt_malloc from
 * each .s file, and verify (a) both stages emit the same line and
 * (b) the symbol matches r->want_sym. Returns 0 on success. */
static int
asm_call_check(const char *bin, const struct asm_row *r, int i)
{
	char src[64], cs[64], ws[64], cmd[1024];
	snprintf(src, sizeof src, "/tmp/wcas_asm_%d_%d.ww", getpid(), i);
	snprintf(cs,  sizeof cs,  "/tmp/wcas_asm_%d_%d_c.s", getpid(), i);
	snprintf(ws,  sizeof ws,  "/tmp/wcas_asm_%d_%d_w.s", getpid(), i);

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

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

	char want[64];
	snprintf(want, sizeof want, "\tCALL\t%s(SB)\n", r->want_sym);

	char cline[256] = {0}, wline[256] = {0};
	FILE *fc = fopen(cs, "rb");
	FILE *fw = fopen(ws, "rb");
	if (!fc || !fw) {
		fprintf(stderr, "asm[%s]: open .s failed\n", r->label);
		rc = -1;
	} else {
		char buf[256];
		while (fgets(buf, sizeof buf, fc)) {
			if (strstr(buf, "\tCALL\t")
			    && (strstr(buf, "alloc(SB)")
			    || strstr(buf, "rt_malloc(SB)"))) {
				strncpy(cline, buf, sizeof cline - 1);
				break;
			}
		}
		while (fgets(buf, sizeof buf, fw)) {
			if (strstr(buf, "\tCALL\t")
			    && (strstr(buf, "alloc(SB)")
			    || strstr(buf, "rt_malloc(SB)"))) {
				strncpy(wline, buf, sizeof wline - 1);
				break;
			}
		}
		if (cline[0] == '\0' || wline[0] == '\0') {
			fprintf(stderr,
			    "asm[%s]: no CALL alloc line found (c=%d w=%d)\n",
			    r->label, cline[0] != '\0', wline[0] != '\0');
			rc = -1;
		} else if (strcmp(cline, wline) != 0) {
			/* strncpy may leave no '\n'; both lines came from
			 * fgets so they include it. Strip for cleaner err. */
			char *p;
			if ((p = strchr(cline, '\n'))) *p = '\0';
			if ((p = strchr(wline, '\n'))) *p = '\0';
			fprintf(stderr,
			    "asm[%s]: cstage=<%s> wwstage=<%s>\n",
			    r->label, cline, wline);
			rc = -1;
		} else if (strcmp(cline, want) != 0) {
			char *p;
			if ((p = strchr(cline, '\n'))) *p = '\0';
			fprintf(stderr,
			    "asm[%s]: got=<%s> want=<\tCALL\t%s(SB)>\n",
			    r->label, cline, r->want_sym);
			rc = -1;
		}
	}
	if (fc) fclose(fc);
	if (fw) fclose(fw);

cleanup:;
	/* a failing compile can still leave a partial .s — ENOENT is the
	 * only tolerable unlink error on the never-created legs. */
	int cleanfail = 0;
	if (unlink(src) != 0 && errno != ENOENT) {
		perror(src);
		cleanfail = 1;
	}
	if (unlink(cs) != 0 && errno != ENOENT) {
		perror(cs);
		cleanfail = 1;
	}
	if (unlink(ws) != 0 && errno != ENOENT) {
		perror(ws);
		cleanfail = 1;
	}
	if (cleanfail && rc == 0)
		rc = -1;
	return rc;
}

/* file_contains — true iff `path`'s contents contain `needle` as a
 * substring. Tab/newline-bearing needles match the literal byte sequence
 * the .s file holds, so `(CX)\n` does not collide with `0(CX)\n`. */
static int
file_contains(const char *path, const char *needle)
{
	FILE *f = fopen(path, "rb");
	if (!f) return 0;
	fseek(f, 0, SEEK_END);
	long sz = ftell(f);
	if (sz < 0 || sz > (1<<20)) { fclose(f); return 0; }
	fseek(f, 0, SEEK_SET);
	char *buf = (char*)malloc((size_t)sz + 1);
	if (!buf) { fclose(f); return 0; }
	size_t got = fread(buf, 1, (size_t)sz, f);
	buf[got] = '\0';
	fclose(f);
	int hit = strstr(buf, needle) != NULL;
	free(buf);
	return hit;
}

/* asm_disp_check — compile via direct w6c / w6c_ww and verify that the
 * literal `r->want_line` appears in BOTH stages' .s output. Pre-fix
 * wwstage substituted `0(REG)` for `(REG)` so the foff=0 rows fail on
 * the wwstage half; post-fix both halves carry the same text. */
static int
asm_disp_check(const char *bin, const struct asm_disp_row *r, int i)
{
	char src[64], cs[64], ws[64], cmd[1024];
	snprintf(src, sizeof src, "/tmp/wcas_disp_%d_%d.ww", getpid(), i);
	snprintf(cs,  sizeof cs,  "/tmp/wcas_disp_%d_%d_c.s", getpid(), i);
	snprintf(ws,  sizeof ws,  "/tmp/wcas_disp_%d_%d_w.s", getpid(), i);

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

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

	int chit = file_contains(cs, r->want_line);
	int whit = file_contains(ws, r->want_line);
	if (!chit || !whit) {
		fprintf(stderr,
		    "disp[%s]: want_line missing (cstage=%d wwstage=%d) "
		    "want=<%s>\n",
		    r->label, chit, whit, r->want_line);
		rc = -1;
	}

cleanup:;
	/* a failing compile can still leave a partial .s — ENOENT is the
	 * only tolerable unlink error on the never-created legs. */
	int cleanfail = 0;
	if (unlink(src) != 0 && errno != ENOENT) {
		perror(src);
		cleanfail = 1;
	}
	if (unlink(cs) != 0 && errno != ENOENT) {
		perror(cs);
		cleanfail = 1;
	}
	if (unlink(ws) != 0 && errno != ENOENT) {
		perror(ws);
		cleanfail = 1;
	}
	if (cleanfail && rc == 0)
		rc = -1;
	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;
	}

	int total = 0, fail = 0;

	/* Asm CALL-line check via direct w6c / w6c_ww. Gated on w6c_ww
	 * existence — when wwstage isn't built yet the cstage half alone
	 * can't catch the divergence. */
	char w6c_ww[1024];
	snprintf(w6c_ww, sizeof w6c_ww, "%s/w6c_ww", bin);
	if (access(w6c_ww, X_OK) == 0) {
		int an = (int)(sizeof asm_rows / sizeof asm_rows[0]);
		for (int i = 0; i < an; i++) {
			total++;
			if (asm_call_check(bin, &asm_rows[i], i) != 0)
				fail++;
		}
		int dn = (int)(sizeof asm_disp_rows / sizeof asm_disp_rows[0]);
		for (int i = 0; i < dn; i++) {
			total++;
			if (asm_disp_check(bin, &asm_disp_rows[i], i) != 0)
				fail++;
		}
	} else {
		fprintf(stderr,
		    "cgalloc_str_field: skip asm rows (no %s)\n", w6c_ww);
	}

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