// tiny_destructors.c — Tiny の終了処理と統計ダンプを箱化
#include "tiny_destructors.h"

#include <stdio.h>
#include <string.h>

#include "box/tiny_hotheap_v2_box.h"
#include "box/tiny_front_stats_box.h"
#include "box/tiny_heap_box.h"
#include "box/tiny_route_env_box.h"
#include "box/tls_sll_box.h"
#include "front/tiny_heap_v2.h"
#include "hakmem_env_cache.h"
#include "hakmem_tiny_magazine.h"
#include "hakmem_tiny_stats_api.h"

static int g_flush_on_exit = 0;
static int g_ultra_debug_on_exit = 0;
static int g_path_debug_on_exit = 0;

// HotHeap v2 stats storage (defined in hakmem_tiny.c)
extern _Atomic uint64_t g_tiny_hotheap_v2_route_hits[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_alloc_calls[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_alloc_fast[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_alloc_lease[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_alloc_fallback_v1[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_alloc_refill[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_refill_with_current[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_refill_with_partial[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_alloc_route_fb[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_free_calls[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_free_fast[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_free_fallback_v1[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_cold_refill_fail[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_cold_retire_calls[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_retire_calls_v2[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_partial_pushes[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_partial_pops[TINY_HOTHEAP_MAX_CLASSES];
extern _Atomic uint64_t g_tiny_hotheap_v2_partial_peak[TINY_HOTHEAP_MAX_CLASSES];
extern TinyHotHeapV2PageStats g_tiny_hotheap_v2_page_stats[TINY_HOTHEAP_MAX_CLASSES];

extern _Atomic uint64_t g_tiny_alloc_ge1024[TINY_NUM_CLASSES];
extern _Atomic uint64_t g_tls_sll_invalid_head[TINY_NUM_CLASSES];
extern _Atomic uint64_t g_tls_sll_invalid_push[TINY_NUM_CLASSES];

static void hak_flush_tiny_exit(void) {
    if (g_flush_on_exit) {
        hak_tiny_magazine_flush_all();
        hak_tiny_trim();
    }
    if (g_ultra_debug_on_exit) {
        hak_tiny_ultra_debug_dump();
    }
    // Path debug dump (optional): HAKMEM_TINY_PATH_DEBUG=1
    hak_tiny_path_debug_dump();
    // Extended counters (optional): HAKMEM_TINY_COUNTERS_DUMP=1
    hak_tiny_debug_counters_dump();

    // DEBUG: Print SuperSlab accounting stats
    extern _Atomic uint64_t g_ss_active_dec_calls;
    extern _Atomic uint64_t g_hak_tiny_free_calls;
    extern _Atomic uint64_t g_ss_remote_push_calls;
    extern _Atomic uint64_t g_free_ss_enter;
    extern _Atomic uint64_t g_free_local_box_calls;
    extern _Atomic uint64_t g_free_remote_box_calls;
    extern uint64_t g_superslabs_allocated;
    extern uint64_t g_superslabs_freed;

    fprintf(stderr, "\n[EXIT DEBUG] SuperSlab Accounting:\n");
    fprintf(stderr, "  g_superslabs_allocated = %llu\n", (unsigned long long)g_superslabs_allocated);
    fprintf(stderr, "  g_superslabs_freed = %llu\n", (unsigned long long)g_superslabs_freed);
    fprintf(stderr, "  g_hak_tiny_free_calls = %llu\n",
            (unsigned long long)atomic_load_explicit(&g_hak_tiny_free_calls, memory_order_relaxed));
    fprintf(stderr, "  g_ss_remote_push_calls = %llu\n",
            (unsigned long long)atomic_load_explicit(&g_ss_remote_push_calls, memory_order_relaxed));
    fprintf(stderr, "  g_ss_active_dec_calls = %llu\n",
            (unsigned long long)atomic_load_explicit(&g_ss_active_dec_calls, memory_order_relaxed));
    extern _Atomic uint64_t g_free_wrapper_calls;
    fprintf(stderr, "  g_free_wrapper_calls = %llu\n",
            (unsigned long long)atomic_load_explicit(&g_free_wrapper_calls, memory_order_relaxed));
    fprintf(stderr, "  g_free_ss_enter = %llu\n",
            (unsigned long long)atomic_load_explicit(&g_free_ss_enter, memory_order_relaxed));
    fprintf(stderr, "  g_free_local_box_calls = %llu\n",
            (unsigned long long)atomic_load_explicit(&g_free_local_box_calls, memory_order_relaxed));
    fprintf(stderr, "  g_free_remote_box_calls = %llu\n",
            (unsigned long long)atomic_load_explicit(&g_free_remote_box_calls, memory_order_relaxed));
}

void tiny_destructors_configure_from_env(void) {
    const char* tf = getenv("HAKMEM_TINY_FLUSH_ON_EXIT");
    if (tf && atoi(tf) != 0) {
        g_flush_on_exit = 1;
    }
    const char* ud = getenv("HAKMEM_TINY_ULTRA_DEBUG");
    if (ud && atoi(ud) != 0) {
        g_ultra_debug_on_exit = 1;
    }
    const char* pd = getenv("HAKMEM_TINY_PATH_DEBUG");
    if (pd) {
        g_path_debug_on_exit = 1;
    }
}

void tiny_destructors_register_exit(void) {
    if (g_flush_on_exit || g_ultra_debug_on_exit || g_path_debug_on_exit) {
        atexit(hak_flush_tiny_exit);
    }
}

static int tiny_heap_stats_dump_enabled(void) {
    static int g = -1;
    if (__builtin_expect(g == -1, 0)) {
        const char* eh = getenv("HAKMEM_TINY_HEAP_STATS_DUMP");
        const char* e = getenv("HAKMEM_TINY_C7_HEAP_STATS_DUMP");
        g = ((eh && *eh && *eh != '0') || (e && *e && *e != '0')) ? 1 : 0;
    }
    return g;
}

__attribute__((destructor))
static void tiny_heap_stats_dump(void) {
    if (!tiny_heap_stats_enabled() || !tiny_heap_stats_dump_enabled()) {
        return;
    }
    for (int cls = 0; cls < TINY_NUM_CLASSES; cls++) {
        TinyHeapClassStats snap = {
            .alloc_fast_current = atomic_load_explicit(&g_tiny_heap_stats[cls].alloc_fast_current, memory_order_relaxed),
            .alloc_slow_prepare = atomic_load_explicit(&g_tiny_heap_stats[cls].alloc_slow_prepare, memory_order_relaxed),
            .free_fast_local = atomic_load_explicit(&g_tiny_heap_stats[cls].free_fast_local, memory_order_relaxed),
            .free_slow_fallback = atomic_load_explicit(&g_tiny_heap_stats[cls].free_slow_fallback, memory_order_relaxed),
            .alloc_prepare_fail = atomic_load_explicit(&g_tiny_heap_stats[cls].alloc_prepare_fail, memory_order_relaxed),
            .alloc_fail = atomic_load_explicit(&g_tiny_heap_stats[cls].alloc_fail, memory_order_relaxed),
        };
        if (snap.alloc_fast_current == 0 && snap.alloc_slow_prepare == 0 &&
            snap.free_fast_local == 0 && snap.free_slow_fallback == 0 &&
            snap.alloc_prepare_fail == 0 && snap.alloc_fail == 0) {
            continue;
        }
        fprintf(stderr,
                "[HEAP_STATS cls=%d] alloc_fast_current=%llu alloc_slow_prepare=%llu free_fast_local=%llu free_slow_fallback=%llu alloc_prepare_fail=%llu alloc_fail=%llu\n",
                cls,
                (unsigned long long)snap.alloc_fast_current,
                (unsigned long long)snap.alloc_slow_prepare,
                (unsigned long long)snap.free_fast_local,
                (unsigned long long)snap.free_slow_fallback,
                (unsigned long long)snap.alloc_prepare_fail,
                (unsigned long long)snap.alloc_fail);
    }
    TinyC7PageStats ps = {
        .prepare_calls = atomic_load_explicit(&g_c7_page_stats.prepare_calls, memory_order_relaxed),
        .prepare_with_current_null = atomic_load_explicit(&g_c7_page_stats.prepare_with_current_null, memory_order_relaxed),
        .prepare_from_partial = atomic_load_explicit(&g_c7_page_stats.prepare_from_partial, memory_order_relaxed),
        .current_set_from_free = atomic_load_explicit(&g_c7_page_stats.current_set_from_free, memory_order_relaxed),
        .current_dropped_to_partial = atomic_load_explicit(&g_c7_page_stats.current_dropped_to_partial, memory_order_relaxed),
    };
    if (ps.prepare_calls || ps.prepare_with_current_null || ps.prepare_from_partial ||
        ps.current_set_from_free || ps.current_dropped_to_partial) {
        fprintf(stderr,
                "[C7_PAGE_STATS] prepare_calls=%llu prepare_with_current_null=%llu prepare_from_partial=%llu current_set_from_free=%llu current_dropped_to_partial=%llu\n",
                (unsigned long long)ps.prepare_calls,
                (unsigned long long)ps.prepare_with_current_null,
                (unsigned long long)ps.prepare_from_partial,
                (unsigned long long)ps.current_set_from_free,
                (unsigned long long)ps.current_dropped_to_partial);
        fflush(stderr);
    }
}

__attribute__((destructor))
static void tiny_front_class_stats_dump(void) {
    if (!tiny_front_class_stats_dump_enabled()) {
        return;
    }
    for (int cls = 0; cls < TINY_NUM_CLASSES; cls++) {
        uint64_t a = atomic_load_explicit(&g_tiny_front_alloc_class[cls], memory_order_relaxed);
        uint64_t f = atomic_load_explicit(&g_tiny_front_free_class[cls], memory_order_relaxed);
        if (a == 0 && f == 0) {
            continue;
        }
        fprintf(stderr, "[FRONT_CLASS cls=%d] alloc=%llu free=%llu\n",
                cls, (unsigned long long)a, (unsigned long long)f);
    }
}

__attribute__((destructor))
static void tiny_c7_delta_debug_destructor(void) {
    if (tiny_c7_meta_light_enabled() && tiny_c7_delta_debug_enabled()) {
        tiny_c7_heap_debug_dump_deltas();
    }
    if (tiny_heap_meta_light_enabled_for_class(6) && tiny_c6_delta_debug_enabled()) {
        tiny_c6_heap_debug_dump_deltas();
    }
}

__attribute__((destructor))
static void tiny_hotheap_v2_stats_dump(void) {
    if (!tiny_hotheap_v2_stats_enabled()) {
        return;
    }
    for (uint8_t ci = 0; ci < TINY_HOTHEAP_MAX_CLASSES; ci++) {
        uint64_t alloc_calls = atomic_load_explicit(&g_tiny_hotheap_v2_alloc_calls[ci], memory_order_relaxed);
        uint64_t route_hits = atomic_load_explicit(&g_tiny_hotheap_v2_route_hits[ci], memory_order_relaxed);
        uint64_t alloc_fast = atomic_load_explicit(&g_tiny_hotheap_v2_alloc_fast[ci], memory_order_relaxed);
        uint64_t alloc_lease = atomic_load_explicit(&g_tiny_hotheap_v2_alloc_lease[ci], memory_order_relaxed);
        uint64_t alloc_fb = atomic_load_explicit(&g_tiny_hotheap_v2_alloc_fallback_v1[ci], memory_order_relaxed);
        uint64_t free_calls = atomic_load_explicit(&g_tiny_hotheap_v2_free_calls[ci], memory_order_relaxed);
        uint64_t free_fast = atomic_load_explicit(&g_tiny_hotheap_v2_free_fast[ci], memory_order_relaxed);
        uint64_t free_fb = atomic_load_explicit(&g_tiny_hotheap_v2_free_fallback_v1[ci], memory_order_relaxed);
        uint64_t cold_refill_fail = atomic_load_explicit(&g_tiny_hotheap_v2_cold_refill_fail[ci], memory_order_relaxed);
        uint64_t cold_retire_calls = atomic_load_explicit(&g_tiny_hotheap_v2_cold_retire_calls[ci], memory_order_relaxed);
        uint64_t retire_calls_v2 = atomic_load_explicit(&g_tiny_hotheap_v2_retire_calls_v2[ci], memory_order_relaxed);
        uint64_t partial_pushes = atomic_load_explicit(&g_tiny_hotheap_v2_partial_pushes[ci], memory_order_relaxed);
        uint64_t partial_pops = atomic_load_explicit(&g_tiny_hotheap_v2_partial_pops[ci], memory_order_relaxed);
        uint64_t partial_peak = atomic_load_explicit(&g_tiny_hotheap_v2_partial_peak[ci], memory_order_relaxed);
        uint64_t refill_with_cur = atomic_load_explicit(&g_tiny_hotheap_v2_refill_with_current[ci], memory_order_relaxed);
        uint64_t refill_with_partial = atomic_load_explicit(&g_tiny_hotheap_v2_refill_with_partial[ci], memory_order_relaxed);

        TinyHotHeapV2PageStats ps = {
            .prepare_calls = atomic_load_explicit(&g_tiny_hotheap_v2_page_stats[ci].prepare_calls, memory_order_relaxed),
            .prepare_with_current_null = atomic_load_explicit(&g_tiny_hotheap_v2_page_stats[ci].prepare_with_current_null, memory_order_relaxed),
            .prepare_from_partial = atomic_load_explicit(&g_tiny_hotheap_v2_page_stats[ci].prepare_from_partial, memory_order_relaxed),
            .free_made_current = atomic_load_explicit(&g_tiny_hotheap_v2_page_stats[ci].free_made_current, memory_order_relaxed),
            .page_retired = atomic_load_explicit(&g_tiny_hotheap_v2_page_stats[ci].page_retired, memory_order_relaxed),
        };

        if (!(alloc_calls || alloc_fast || alloc_lease || alloc_fb || free_calls || free_fast || free_fb ||
              ps.prepare_calls || ps.prepare_with_current_null || ps.prepare_from_partial ||
              ps.free_made_current || ps.page_retired || retire_calls_v2 || partial_pushes || partial_pops || partial_peak)) {
            continue;
        }

        tiny_route_kind_t route_kind = tiny_route_for_class(ci);
        fprintf(stderr,
                "[HOTHEAP_V2_STATS cls=%u route=%d] route_hits=%llu alloc_calls=%llu alloc_fast=%llu alloc_lease=%llu alloc_refill=%llu refill_cur=%llu refill_partial=%llu alloc_fb_v1=%llu alloc_route_fb=%llu cold_refill_fail=%llu cold_retire_calls=%llu retire_v2=%llu free_calls=%llu free_fast=%llu free_fb_v1=%llu prep_calls=%llu prep_null=%llu prep_from_partial=%llu free_made_current=%llu page_retired=%llu partial_push=%llu partial_pop=%llu partial_peak=%llu\n",
                (unsigned)ci,
                (int)route_kind,
                (unsigned long long)route_hits,
                (unsigned long long)alloc_calls,
                (unsigned long long)alloc_fast,
                (unsigned long long)alloc_lease,
                (unsigned long long)atomic_load_explicit(&g_tiny_hotheap_v2_alloc_refill[ci], memory_order_relaxed),
                (unsigned long long)refill_with_cur,
                (unsigned long long)refill_with_partial,
                (unsigned long long)alloc_fb,
                (unsigned long long)atomic_load_explicit(&g_tiny_hotheap_v2_alloc_route_fb[ci], memory_order_relaxed),
                (unsigned long long)cold_refill_fail,
                (unsigned long long)cold_retire_calls,
                (unsigned long long)retire_calls_v2,
                (unsigned long long)free_calls,
                (unsigned long long)free_fast,
                (unsigned long long)free_fb,
                (unsigned long long)ps.prepare_calls,
                (unsigned long long)ps.prepare_with_current_null,
                (unsigned long long)ps.prepare_from_partial,
                (unsigned long long)ps.free_made_current,
                (unsigned long long)ps.page_retired,
                (unsigned long long)partial_pushes,
                (unsigned long long)partial_pops,
                (unsigned long long)partial_peak);
    }
}

static void tiny_heap_v2_stats_atexit(void) __attribute__((destructor));
static void tiny_heap_v2_stats_atexit(void) {
    tiny_heap_v2_print_stats();
}

static void tiny_alloc_1024_diag_atexit(void) __attribute__((destructor));
static void tiny_alloc_1024_diag_atexit(void) {
    // Priority-2: Use cached ENV
    if (!HAK_ENV_TINY_ALLOC_1024_METRIC()) return;
    fprintf(stderr, "\n[ALLOC_GE1024] per-class counts (size>=1024)\n");
    for (int cls = 0; cls < TINY_NUM_CLASSES; cls++) {
        uint64_t v = atomic_load_explicit(&g_tiny_alloc_ge1024[cls], memory_order_relaxed);
        if (v) {
            fprintf(stderr, " C%d=%llu", cls, (unsigned long long)v);
        }
    }
    fprintf(stderr, "\n");
}

static void tiny_tls_sll_diag_atexit(void) __attribute__((destructor));
static void tiny_tls_sll_diag_atexit(void) {
#if !HAKMEM_BUILD_RELEASE
    // Priority-2: Use cached ENV
    if (!HAK_ENV_TINY_SLL_DIAG()) return;
    fprintf(stderr, "\n[TLS_SLL_DIAG] invalid head/push counts per class\n");
    for (int cls = 0; cls < TINY_NUM_CLASSES; cls++) {
        uint64_t ih = atomic_load_explicit(&g_tls_sll_invalid_head[cls], memory_order_relaxed);
        uint64_t ip = atomic_load_explicit(&g_tls_sll_invalid_push[cls], memory_order_relaxed);
        if (ih || ip) {
            fprintf(stderr, " C%d: invalid_head=%llu invalid_push=%llu\n",
                    cls, (unsigned long long)ih, (unsigned long long)ip);
        }
    }
#endif
}