hakmem/core/hakmem_tiny_slow.inc

// hakmem_tiny_slow.inc
// Slow path allocation implementation

// Slow path allocation function
// Phase 6-1.7: Export for box refactor (Box 5 needs access from hakmem.c)
#ifdef HAKMEM_TINY_PHASE6_BOX_REFACTOR
void* __attribute__((cold, noinline)) hak_tiny_alloc_slow(size_t size, int class_idx) {
#else
static void* __attribute__((cold, noinline)) hak_tiny_alloc_slow(size_t size, int class_idx) {
#endif
    (void)size; // size is already validated by caller

    if (class_idx < 0 || class_idx >= TINY_NUM_CLASSES) {
        return NULL;
    }

    // Try refilling from HotMag
    if (g_hotmag_enable && class_idx <= 3) {
        TinyHotMag* hm = &g_tls_hot_mag[class_idx];
        hotmag_try_refill(class_idx, hm);
        void* ptr = hotmag_pop(class_idx);
        if (ptr) { HAK_RET_ALLOC(class_idx, ptr); }
    }

    // Try TLS SLL via Box (Phase12 正式経路)
    // C7 は headerless: 既存仕様通り TLS/SLL をスキップ
    if (g_tls_sll_enable && class_idx != 7) {
        // Box: 単一APIで TLS SLL を扱う（内部で head/count/next を管理）
        void* ptr = NULL;
        if (tls_sll_pop(class_idx, &ptr)) {
            return ptr;
        }
    }

    // Try TLS list (legacy small-mag) via既存API（構造体直接触らない）
    if (g_tls_list_enable && class_idx != 7) {
        TinyTLSList* tls = &g_tls_lists[class_idx];

        // Fail-Fast: guard against poisoned head (remote sentinel)
        if (__builtin_expect((uintptr_t)tls->head == TINY_REMOTE_SENTINEL, 0)) {
            tls->head = NULL;
            tls->count = 0;
        }

        if (tls->count > 0) {
            void* ptr = tls_list_pop(tls, class_idx);
            if (ptr) {
                HAK_RET_ALLOC(class_idx, ptr);
            }
        }

        // Try refilling TLS list from TLS-cached Superslab slab
        uint32_t want = tls->refill_low > 0 ? tls->refill_low : 32;
        if (tls_refill_from_tls_slab(class_idx, tls, want) > 0) {
            void* ptr = tls_list_pop(tls, class_idx);
            if (ptr) {
                HAK_RET_ALLOC(class_idx, ptr);
            }
        }
    }

    // Background coalescing/aggregation (ENV gated, very lightweight)
    do {
        // BG Remote Drain (coalescer)
        static int bg_en = -1, bg_period = -1, bg_budget = -1;
        static __thread uint32_t bg_tick[8];
        if (__builtin_expect(bg_en == -1, 0)) {
            const char* e = getenv("HAKMEM_TINY_BG_REMOTE");
            bg_en = (e && *e && *e != '0') ? 1 : 0;
            const char* p = getenv("HAKMEM_TINY_BG_REMOTE_PERIOD");
            bg_period = p ? atoi(p) : 1024;
            if (bg_period <= 0) bg_period = 1024;
            const char* b = getenv("HAKMEM_TINY_BG_REMOTE_BATCH");
            bg_budget = b ? atoi(b) : 4;
            if (bg_budget < 0) bg_budget = 0; if (bg_budget > 64) bg_budget = 64;
        }
        if (bg_en) {
            if ((++bg_tick[class_idx] % (uint32_t)bg_period) == 0u) {
                extern void tiny_remote_bg_drain_step(int class_idx, int budget);
                tiny_remote_bg_drain_step(class_idx, bg_budget);
            }
        }
        // Ready Aggregator (mailbox → ready push)
        static int rdy_en = -1, rdy_period = -1, rdy_budget = -1;
        static __thread uint32_t rdy_tick[8];
        if (__builtin_expect(rdy_en == -1, 0)) {
            const char* e = getenv("HAKMEM_TINY_BG_READY");
            rdy_en = (e && *e && *e != '0') ? 1 : 0;
            const char* p = getenv("HAKMEM_TINY_BG_READY_PERIOD");
            rdy_period = p ? atoi(p) : 1024;
            if (rdy_period <= 0) rdy_period = 1024;
            const char* b = getenv("HAKMEM_TINY_BG_READY_BUDGET");
            rdy_budget = b ? atoi(b) : 1;
            if (rdy_budget < 0) rdy_budget = 0; if (rdy_budget > 8) rdy_budget = 8;
        }
        if (rdy_en) {
            if ((++rdy_tick[class_idx] % (uint32_t)rdy_period) == 0u) {
                extern void tiny_ready_bg_aggregate_step(int class_idx, int mail_budget);
                tiny_ready_bg_aggregate_step(class_idx, rdy_budget);
            }
        }
    } while (0);

    // Final fallback: allocate from superslab via Box API wrapper (Stage A)
    // NOTE:
    //  - hak_tiny_alloc_superslab_box() is a thin façade over the legacy
    //    per-class SuperslabHead backend in Phase 12 Stage A.
    //  - Callers (slow path) no longer depend on internal Superslab layout.
    void* ss_ptr = hak_tiny_alloc_superslab_box(class_idx);
    if (ss_ptr) { HAK_RET_ALLOC(class_idx, ss_ptr); }
    tiny_alloc_dump_tls_state(class_idx, "slow_fail", &g_tls_slabs[class_idx]);
    // Optional one-shot debug when final slow path fails
    static int g_alloc_dbg = -1; if (__builtin_expect(g_alloc_dbg == -1, 0)) { const char* e=getenv("HAKMEM_TINY_ALLOC_DEBUG"); g_alloc_dbg = (e && atoi(e)!=0)?1:0; }
    if (g_alloc_dbg) {
        static _Atomic int printed[8]; int exp=0;
        if (atomic_compare_exchange_strong(&printed[class_idx], &exp, 1)) {
            fprintf(stderr, "[ALLOC-SLOW] hak_tiny_alloc_superslab returned NULL class=%d size=%zu\n", class_idx, size);
        }
    }
    return ss_ptr;
}