/* AILang reference-counting runtime — Iter 18b.
 *
 * This is the allocator + counter primitives for `ail build --memory=rc`.
 * It establishes the memory layout (8-byte refcount header preceding
 * every allocation) and the three runtime entry points the codegen will
 * eventually call: ailang_rc_alloc / ailang_rc_inc / ailang_rc_dec.
 *
 * Iter 18b deliberately stops at the *layout* and the *alloc*. The
 * codegen routes `Term::Ctor` / `Term::Lam` env / closure-pair sites
 * through `ailang_rc_alloc` instead of `GC_malloc` / `bump_malloc`, but
 * does NOT yet emit `inc` or `dec` calls anywhere. Programs running
 * under `--memory=rc` therefore leak every allocation — the same
 * behaviour as the pre-Boehm era. This is intentional: the next iter
 * (18c) ships uniqueness inference and the codegen pass that emits
 * inc/dec. 18b is purely about plumbing the allocator and validating
 * that compiled programs still produce correct output under the new
 * allocator.
 *
 * Layout:
 *
 *   high address ┐
 *                │  payload (size bytes, 8-byte aligned)
 *                ┤  ← returned pointer (`p`)
 *                │  uint64_t refcount    ← header (8 bytes)
 *   low address  ┘  ← ailang_rc_alloc's internal allocation
 *
 * The returned pointer points to the *payload*. The header is at
 * `p - 8`. Codegen treats the returned pointer exactly like a
 * `GC_malloc`-returned pointer; it stores the ADT tag at offset 0,
 * fields from offset 8, env-cells from offset 0 in lambda envs, etc.
 *
 * Single-threaded: counter ops are non-atomic. AILang has no
 * concurrency primitives yet; when it acquires them, atomic-vs-non-
 * atomic becomes a separate decision per allocation kind (see
 * Decision 10's "Does not commit to atomic refcounts" clause).
 */

#include <stddef.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

/* Header lives in the 8 bytes preceding every payload. */
typedef uint64_t ailang_rc_header_t;

#define HEADER_SIZE ((size_t)sizeof(ailang_rc_header_t))

static inline ailang_rc_header_t *header_of(void *payload) {
    return (ailang_rc_header_t *)((uint8_t *)payload - HEADER_SIZE);
}

/* Allocate `size` bytes of payload, prefixed by an 8-byte refcount
 * header initialised to 1. Returns a pointer to the payload.
 *
 * Aborts on out-of-memory; AILang has no exception machinery yet, and
 * Boehm's behaviour on OOM is also "abort", so this matches.
 *
 * Zero-initialises the payload to match `GC_malloc`'s contract — codegen
 * may rely on uninitialised fields reading as zero in some paths. */
void *ailang_rc_alloc(size_t size) {
    void *block = malloc(HEADER_SIZE + size);
    if (block == NULL) {
        fprintf(stderr,
                "ailang_rc_alloc: out of memory (requested payload %zu bytes)\n",
                size);
        abort();
    }
    ailang_rc_header_t *hdr = (ailang_rc_header_t *)block;
    *hdr = 1;
    void *payload = (uint8_t *)block + HEADER_SIZE;
    memset(payload, 0, size);
    return payload;
}

/* Refcount += 1. No-op on null (codegen never asks for inc on a known-
 * null pointer, but defensive — top-level fn-value pointers may be
 * null-env closure pairs in static memory which must not be incremented). */
void ailang_rc_inc(void *payload) {
    if (payload == NULL) {
        return;
    }
    /* Heuristic for "static, do not touch": the static closure-pair env
     * pointers (Iter 8b) live in the LLVM data segment, not in heap
     * memory we allocated. We cannot trivially distinguish them at
     * runtime without a flag bit; for Iter 18b, we accept that inc on
     * static memory is undefined behaviour. Iter 18c's codegen will
     * elide inc/dec for known-static pointers, so this path will not
     * be reached for them in practice. */
    ailang_rc_header_t *hdr = header_of(payload);
    *hdr += 1;
}

/* Refcount -= 1. If it reaches zero, frees the underlying block.
 *
 * Iter 18b deliberately does NOT recursively dec child references.
 * That requires per-type traversal info (which fields are pointer-
 * typed, which are unboxed), which is added in Iter 18c when the
 * codegen learns to emit per-ctor `dec` cascades. For now, free-on-
 * zero just frees the box; any boxed children leak.
 *
 * Iter 18b never emits `dec` calls from codegen, so this fn is
 * effectively dead code in 18b. It exists so the runtime ABI is
 * complete and 18c can wire codegen up against a stable surface. */
void ailang_rc_dec(void *payload) {
    if (payload == NULL) {
        return;
    }
    ailang_rc_header_t *hdr = header_of(payload);
    if (*hdr == 0) {
        fprintf(stderr,
                "ailang_rc_dec: refcount underflow at %p (already zero)\n",
                payload);
        abort();
    }
    *hdr -= 1;
    if (*hdr == 0) {
        free(hdr);
    }
}

/* ---------------------------------------------------------------------------
 * Iter 18e: drop worklist.
 *
 * Backs the `(drop-iterative)` data attribute. When a type is annotated
 * `(drop-iterative)`, codegen emits `drop_<m>_<T>` with an iterative-with-
 * worklist body in place of the recursive cascade. The worklist is a
 * heap-allocated stretchy buffer of `void*` pointers — one entry per
 * not-yet-processed cell. Each entry is mono-typed to T (the annotated
 * ADT being dropped); fields of T whose type is `T` itself are pushed,
 * fields whose type is a different ADT call that ADT's drop fn directly.
 * (See `Emitter::emit_iterative_drop_fn_for_type` in the codegen for the
 * IR shape and the same-type / different-type dispatch.)
 *
 * Strategy: heap-allocated buffer, doubled on overflow. We chose this
 * over a stack-allocated small buffer (overcomplicates the IR seam — the
 * codegen body would need to track "which buffer is live") and over Lean
 * 4's "thread the worklist through one of the cell's own pointer slots"
 * technique (requires the codegen to know which slot of each ctor is
 * "free to repurpose" — non-trivial since AILang ctors are heterogeneous
 * and slot 0 is always the tag). The runtime-helper approach keeps the
 * IR-level body of `drop_<m>_<T>` small: three calls (new / push / pop /
 * free) drive the loop.
 *
 * Precedent: Lean 4's `lean_dec_ref_cold` and Roc's iterative-free path
 * both use a worklist to break tail recursion in their drop cascades.
 * Lean threads the worklist through field slots (the "in-place" variant);
 * we use a separate heap buffer because AILang's ctor layout makes slot
 * repurposing fragile. The semantic invariant matches: every cell whose
 * refcount reaches zero is dec'd exactly once, regardless of cascade
 * depth, without consuming proportional C stack space.
 *
 * Single-threaded; non-atomic. Same scope as the rest of `runtime/rc.c`.
 * --------------------------------------------------------------------------- */

typedef struct {
    void **data;     /* heap buffer of `cap` pointers; null once freed */
    size_t len;      /* number of live entries (always <= cap) */
    size_t cap;      /* current capacity in slots */
} ailang_drop_worklist_t;

/* Initial capacity. 16 slots * 8 bytes = 128 bytes — small enough that
 * very-shallow drops don't waste memory, large enough that 16-deep
 * cascades (very common) never realloc. Doubled on overflow. */
#define DROP_WORKLIST_INIT_CAP ((size_t)16)

void *ailang_drop_worklist_new(void) {
    ailang_drop_worklist_t *wl = malloc(sizeof(ailang_drop_worklist_t));
    if (wl == NULL) {
        fprintf(stderr,
                "ailang_drop_worklist_new: out of memory (header)\n");
        abort();
    }
    wl->data = malloc(DROP_WORKLIST_INIT_CAP * sizeof(void *));
    if (wl->data == NULL) {
        fprintf(stderr,
                "ailang_drop_worklist_new: out of memory (initial buffer)\n");
        abort();
    }
    wl->len = 0;
    wl->cap = DROP_WORKLIST_INIT_CAP;
    return (void *)wl;
}

/* Push `payload` onto the worklist. Skips null payloads — pushed nulls
 * would dispatch on `load i64, ptr null` at pop time and segfault, so
 * we filter here. The check is symmetric with `ailang_rc_dec`'s null
 * guard (a null payload is a no-op everywhere in the rc runtime). */
void ailang_drop_worklist_push(void *wl_opaque, void *payload) {
    if (payload == NULL) {
        return;
    }
    ailang_drop_worklist_t *wl = (ailang_drop_worklist_t *)wl_opaque;
    if (wl->len == wl->cap) {
        size_t new_cap = wl->cap * 2;
        void **new_data = realloc(wl->data, new_cap * sizeof(void *));
        if (new_data == NULL) {
            fprintf(stderr,
                    "ailang_drop_worklist_push: out of memory (grow to %zu slots)\n",
                    new_cap);
            abort();
        }
        wl->data = new_data;
        wl->cap = new_cap;
    }
    wl->data[wl->len] = payload;
    wl->len += 1;
}

/* Pop one payload from the worklist. Returns NULL when the worklist is
 * empty. Since `push` filters nulls, a returned null is unambiguous and
 * can be used by the IR body as the loop-exit sentinel. */
void *ailang_drop_worklist_pop(void *wl_opaque) {
    ailang_drop_worklist_t *wl = (ailang_drop_worklist_t *)wl_opaque;
    if (wl->len == 0) {
        return NULL;
    }
    wl->len -= 1;
    return wl->data[wl->len];
}

/* Free the worklist itself. Called once at the end of the iterative
 * drop loop. Does NOT free any payloads still in the buffer — the IR
 * body must drain the buffer first via repeated `pop` calls before
 * calling free. */
void ailang_drop_worklist_free(void *wl_opaque) {
    if (wl_opaque == NULL) {
        return;
    }
    ailang_drop_worklist_t *wl = (ailang_drop_worklist_t *)wl_opaque;
    free(wl->data);
    free(wl);
}