// superslab_slab.c - Slab initialization and management
// Purpose: Slab lifecycle and bitmap management within SuperSlabs
// License: MIT
// Date: 2025-11-28

#include "hakmem_tiny_superslab_internal.h"
#include "box/slab_recycling_box.h"
#include "hakmem_env_cache.h"  // Priority-2: ENV cache (eliminate syscalls)
#include <stdio.h>

// ============================================================================
// Remote Drain (MPSC queue to freelist conversion)
// ============================================================================

// Drain remote MPSC stack into freelist (ownership already verified by caller)
void _ss_remote_drain_to_freelist_unsafe(SuperSlab* ss, int slab_idx, TinySlabMeta* meta)
{
    if (!ss || slab_idx < 0 || slab_idx >= ss_slabs_capacity(ss) || !meta) return;

    static _Atomic uint32_t g_remote_drain_diag_once = 0;
    static int g_remote_drain_diag_en = -1;

    // Atomically take the whole remote list
    uintptr_t head = atomic_exchange_explicit(&ss->remote_heads[slab_idx], 0,
                                              memory_order_acq_rel);
    if (head == 0) return;

    // Convert remote stack (offset 0 next) into freelist encoding via Box API
    // and splice in front of current freelist preserving relative order.
    void* prev = meta->freelist;
    int cls = (int)meta->class_idx;
    uint16_t drained_count = 0; // Phase 9-2: Batched used decrement

    HAK_CHECK_CLASS_IDX(cls, "_ss_remote_drain_to_freelist_unsafe");
    if (__builtin_expect(cls < 0 || cls >= TINY_NUM_CLASSES, 0)) {
        static _Atomic int g_remote_drain_cls_oob = 0;
        if (atomic_fetch_add_explicit(&g_remote_drain_cls_oob, 1, memory_order_relaxed) == 0) {
            fprintf(stderr,
                    "[REMOTE_DRAIN_CLASS_OOB] ss=%p slab_idx=%d meta=%p cls=%d head=%#lx\n",
                    (void*)ss, slab_idx, (void*)meta, cls, (unsigned long)head);
        }
        return;
    }
    uintptr_t cur = head;
    while (cur != 0) {
        uintptr_t next = *(uintptr_t*)cur;  // remote-next stored at offset 0
        // Priority-2: Use cached ENV (eliminate lazy-init static overhead)
        if (__builtin_expect(g_remote_drain_diag_en == -1, 0)) {
#if !HAKMEM_BUILD_RELEASE
            g_remote_drain_diag_en = HAK_ENV_TINY_SLL_DIAG();
#else
            g_remote_drain_diag_en = 0;
#endif
        }
        if (__builtin_expect(g_remote_drain_diag_en, 0)) {
            uintptr_t addr = (uintptr_t)next;
            if (addr != 0 && (addr < 4096 || addr > 0x00007fffffffffffULL)) {
                uint32_t shot = atomic_fetch_add_explicit(&g_remote_drain_diag_once, 1, memory_order_relaxed);
                if (shot < 8) {
                    fprintf(stderr,
                            "[REMOTE_DRAIN_NEXT_INVALID] cls=%d slab=%d cur=%p next=%p head=%#lx prev=%p count=%u\n",
                            cls,
                            slab_idx,
                            (void*)cur,
                            (void*)next,
                            (unsigned long)head,
                            prev,
                            (unsigned)meta->used);
                }
            }
#if HAKMEM_TINY_HEADER_CLASSIDX
            int hdr_cls = tiny_region_id_read_header((uint8_t*)cur + 1);
            if (hdr_cls >= 0 && hdr_cls != cls) {
                uint32_t shot = atomic_fetch_add_explicit(&g_remote_drain_diag_once, 1, memory_order_relaxed);
                if (shot < 8) {
                    fprintf(stderr,
                            "[REMOTE_DRAIN_HDR_MISMATCH] cls=%d slab=%d cur=%p hdr_cls=%d meta_cls=%d head=%#lx\n",
                            cls, slab_idx, (void*)cur, hdr_cls, (int)meta->class_idx, (unsigned long)head);
                }
            }
#endif
        }
#if HAKMEM_TINY_HEADER_CLASSIDX
        // Cross-check header vs meta before writing next (even if diag is off)
        {
            int hdr_cls_pre = tiny_region_id_read_header((uint8_t*)cur + 1);
            if (hdr_cls_pre >= 0 && hdr_cls_pre != cls) {
                static _Atomic uint32_t g_hdr_meta_mismatch_rd = 0;
                uint32_t n = atomic_fetch_add_explicit(&g_hdr_meta_mismatch_rd, 1, memory_order_relaxed);
                if (n < 16) {
                    fprintf(stderr,
                            "[REMOTE_DRAIN_HDR_META_MISMATCH] cls=%d slab=%d cur=%p hdr_cls=%d meta_cls=%d\n",
                            cls, slab_idx, (void*)cur, hdr_cls_pre, (int)meta->class_idx);
                }
            }
        }
#endif
        // Restore header for header-classes (class 1-6) which were clobbered by remote push
#if HAKMEM_TINY_HEADER_CLASSIDX
        if (cls != 0) {
            uint8_t expected = (uint8_t)(HEADER_MAGIC | (cls & HEADER_CLASS_MASK));
            *(uint8_t*)(uintptr_t)cur = expected;
        }
#endif
        // Rewrite next pointer to Box representation for this class
        tiny_next_write(cls, (void*)cur, prev);
        prev = (void*)cur;
        cur = next;
        drained_count++;
    }
    meta->freelist = prev;
    // Reset remote count after full drain
    atomic_store_explicit(&ss->remote_counts[slab_idx], 0, memory_order_release);

    // Phase 9-2: Batched decrement of used count (Atomic)
    // Remote frees don't decrement used until they land in freelist.
    if (drained_count > 0) {
        uint16_t old_used = atomic_fetch_sub_explicit(&meta->used, drained_count, memory_order_release);
        // If used became 0 (old_used == drained_count), try to recycle
        if (old_used == drained_count) {
             SLAB_TRY_RECYCLE(ss, slab_idx, meta);
        }
    }

    // Update freelist/nonempty visibility bits
    uint32_t bit = (1u << slab_idx);
    atomic_fetch_or_explicit(&ss->freelist_mask, bit, memory_order_release);
    atomic_fetch_or_explicit(&ss->nonempty_mask, bit, memory_order_release);
}

// ============================================================================
// Slab Initialization within SuperSlab
// ============================================================================

void superslab_init_slab(SuperSlab* ss, int slab_idx, size_t block_size, uint32_t owner_tid)
{
    if (!ss || slab_idx < 0 || slab_idx >= ss_slabs_capacity(ss)) {
        return;
    }

    // Phase E1-CORRECT unified geometry:
    // - block_size is the TOTAL stride for this class (g_tiny_class_sizes[cls])
    // - usable bytes are determined by slab index (slab0 vs others)
    // - capacity = usable / stride for ALL classes (including former C7)
    size_t usable_size = (slab_idx == 0)
                           ? SUPERSLAB_SLAB0_USABLE_SIZE
                           : SUPERSLAB_SLAB_USABLE_SIZE;
    size_t stride = block_size;
    uint16_t capacity = (uint16_t)(usable_size / stride);

#if !HAKMEM_BUILD_RELEASE
    if (slab_idx == 0) {
        fprintf(stderr,
                "[SUPERSLAB_INIT] slab 0: usable_size=%zu stride=%zu capacity=%u\n",
                usable_size, stride, (unsigned)capacity);
    }
#endif

    TinySlabMeta* meta = &ss->slabs[slab_idx];
    meta->freelist = NULL;          // NULL = linear allocation mode
    meta->used = 0;
    meta->active = 0;               // P1.3: blocks in use by user (starts at 0)
    meta->tls_cached = 0;           // P2.2: blocks cached in TLS SLL (starts at 0)
    meta->capacity = capacity;
    meta->carved = 0;
    // LARSON FIX: Use bits 8-15 instead of 0-7 since pthread TIDs are aligned to 256 bytes
    meta->owner_tid_low = (uint8_t)((owner_tid >> 8) & 0xFFu);
    // Fail-safe: stamp class_idx from geometry (stride → class).
    // This ensures legacy/shared/legacy-refill paths all end with a correct class.
    for (int i = 0; i < TINY_NUM_CLASSES; i++) {
        if (g_tiny_class_sizes[i] == stride) {
            meta->class_idx = (uint8_t)i;
            // P1.1: Update class_map for out-of-band lookup on free path
            ss->class_map[slab_idx] = (uint8_t)i;
            break;
        }
    }

#if HAKMEM_BUILD_RELEASE
    static _Atomic int rel_c7_init_logged = 0;
    if (meta->class_idx == 7 &&
        atomic_load_explicit(&rel_c7_init_logged, memory_order_relaxed) == 0) {
        fprintf(stderr,
                "[REL_C7_INIT] ss=%p slab=%d cls=%u cap=%u used=%u carved=%u stride=%zu\n",
                (void*)ss,
                slab_idx,
                (unsigned)meta->class_idx,
                (unsigned)meta->capacity,
                (unsigned)meta->used,
                (unsigned)meta->carved,
                stride);
        atomic_store_explicit(&rel_c7_init_logged, 1, memory_order_relaxed);
    }
#else
    static __thread int dbg_c7_init_logged = 0;
    if (meta->class_idx == 7 && dbg_c7_init_logged == 0) {
        fprintf(stderr,
                "[DBG_C7_INIT] ss=%p slab=%d cls=%u cap=%u used=%u carved=%u stride=%zu\n",
                (void*)ss,
                slab_idx,
                (unsigned)meta->class_idx,
                (unsigned)meta->capacity,
                (unsigned)meta->used,
                (unsigned)meta->carved,
                stride);
        dbg_c7_init_logged = 1;
    }
#endif

    superslab_activate_slab(ss, slab_idx);
}

// ============================================================================
// Slab Bitmap Management
// ============================================================================

void superslab_activate_slab(SuperSlab* ss, int slab_idx) {
    if (!ss || slab_idx < 0 || slab_idx >= ss_slabs_capacity(ss)) {
        return;
    }
    uint32_t mask = 1u << slab_idx;
    if ((ss->slab_bitmap & mask) == 0) {
        ss->slab_bitmap |= mask;
        ss->active_slabs++;

        // Phase 3d-C: Update hot/cold indices after activating new slab
        ss_update_hot_cold_indices(ss);
    }
}

void superslab_deactivate_slab(SuperSlab* ss, int slab_idx) {
    if (!ss || slab_idx < 0 || slab_idx >= ss_slabs_capacity(ss)) {
        return;
    }
    uint32_t mask = 1u << slab_idx;
    if (ss->slab_bitmap & mask) {
        ss->slab_bitmap &= ~mask;
        ss->active_slabs--;
    }
}

int superslab_find_free_slab(SuperSlab* ss) {
    if (!ss) return -1;
    if ((int)ss->active_slabs >= ss_slabs_capacity(ss)) {
        return -1;  // No free slabs
    }
    // Find first 0 bit in bitmap
    int cap = ss_slabs_capacity(ss);
    for (int i = 0; i < cap; i++) {
        if ((ss->slab_bitmap & (1u << i)) == 0) {
            return i;
        }
    }
    return -1;
}