#include "hakmem_shared_pool_internal.h"
#include "hakmem_debug_master.h"
#include "box/ss_slab_meta_box.h"
#include "box/ss_hot_cold_box.h"
#include "box/ss_tier_box.h"              // P-Tier: Utilization-aware tiering
#include "hakmem_env_cache.h"  // Priority-2: ENV cache
#include "superslab/superslab_inline.h"  // superslab_ref_get guard for TLS pins
#include "box/ss_release_guard_box.h"    // Box: SuperSlab Release Guard
#include "box/ss_slab_reset_box.h"       // Box: Reset slab metadata on reuse path
#include "box/ss_stats_box.h"            // Observability: Superslab/slab counters
#include "box/ss_budget_box.h"           // Budget guard (global/class caps)

#include <stdlib.h>
#include <stdio.h>
#include <stdatomic.h>

static inline void c7_release_log_once(SuperSlab* ss, int slab_idx) {
#if HAKMEM_BUILD_RELEASE
    static _Atomic uint32_t rel_c7_release_logs = 0;
    uint32_t n = atomic_fetch_add_explicit(&rel_c7_release_logs, 1, memory_order_relaxed);
    if (n < 8) {
        TinySlabMeta* meta = &ss->slabs[slab_idx];
        fprintf(stderr,
                "[REL_C7_RELEASE] ss=%p slab=%d used=%u cap=%u carved=%u\n",
                (void*)ss,
                slab_idx,
                (unsigned)meta->used,
                (unsigned)meta->capacity,
                (unsigned)meta->carved);
    }
#else
    static _Atomic uint32_t dbg_c7_release_logs = 0;
    uint32_t n = atomic_fetch_add_explicit(&dbg_c7_release_logs, 1, memory_order_relaxed);
    if (n < 8) {
        TinySlabMeta* meta = &ss->slabs[slab_idx];
        fprintf(stderr,
                "[DBG_C7_RELEASE] ss=%p slab=%d used=%u cap=%u carved=%u\n",
                (void*)ss,
                slab_idx,
                (unsigned)meta->used,
                (unsigned)meta->capacity,
                (unsigned)meta->carved);
    }
#endif
}

void
shared_pool_release_slab(SuperSlab* ss, int slab_idx)
{
    // Phase 12: SP-SLOT Box - Slot-based Release
    //
    // Flow:
    //   1. Validate inputs and check meta->used == 0
    //   2. Find SharedSSMeta for this SuperSlab
    //   3. Mark slot ACTIVE → EMPTY
    //   4. Push to per-class free list (enables same-class reuse)
    //   5. If all slots EMPTY → superslab_free() → LRU cache

    if (!ss) {
        return;
    }
    if (slab_idx < 0 || slab_idx >= SLABS_PER_SUPERSLAB_MAX) {
        return;
    }

    // Phase 9-2 FIX: Promote Legacy SuperSlabs to Shared Pool on first recycle
    // If we are recycling a slot from a Legacy SS, we must remove it from the
    // Legacy list (g_superslab_heads) to prevent Legacy Backend from allocating
    // from it simultaneously (Double Allocation Race).
    // This effectively transfers ownership to Shared Pool.
    extern void remove_superslab_from_legacy_head(SuperSlab* ss);
    remove_superslab_from_legacy_head(ss);

    // BUGFIX: Re-check used count after removal. Legacy Backend might have
    // allocated from this slab while we were waiting for the lock in remove().
    TinySlabMeta* slab_meta = &ss->slabs[slab_idx];
    if (atomic_load_explicit(&slab_meta->used, memory_order_acquire) != 0) {
        // Legacy Backend stole this slab. It's now an orphan (removed from list).
        // We abort recycling. It will be recycled when Legacy frees it later.
        return;
    }

    // Debug logging
#if !HAKMEM_BUILD_RELEASE
    // Priority-2: Use cached ENV
    int dbg = HAK_ENV_SS_FREE_DEBUG();
#else
    static const int dbg = 0;
#endif
    (void)dbg;

    // P0 instrumentation: count lock acquisitions
    lock_stats_init();
    if (g_lock_stats_enabled == 1) {
        atomic_fetch_add(&g_lock_stats_enabled, 1);
        atomic_fetch_add(&g_lock_release_slab_count, 1);
    }

    pthread_mutex_lock(&g_shared_pool.alloc_lock);

    // TinySlabMeta* slab_meta = &ss->slabs[slab_idx]; // Already declared above
    if (slab_meta->used != 0) {
        // Not actually empty (double check under lock)
        if (g_lock_stats_enabled == 1) {
            atomic_fetch_add(&g_lock_release_count, 1);
        }
        pthread_mutex_unlock(&g_shared_pool.alloc_lock);
        return;
    }

    uint8_t class_idx = slab_meta->class_idx;
    if (class_idx == 7) {
        c7_release_log_once(ss, slab_idx);
    }

    // Guard: if SuperSlab is pinned (TLS/remote references), defer release to avoid
    // class_map=255 while pointers are still in-flight.
    uint32_t ss_refs_guard = superslab_ref_get(ss);
    if (ss_refs_guard != 0) {
#if !HAKMEM_BUILD_RELEASE
        if (dbg == 1) {
            fprintf(stderr,
                    "[SP_SLOT_RELEASE_SKIP_PINNED] ss=%p slab_idx=%d class=%d refcount=%u\n",
                    (void*)ss, slab_idx, class_idx, (unsigned)ss_refs_guard);
        }
#endif
        if (g_lock_stats_enabled == 1) {
            atomic_fetch_add(&g_lock_release_count, 1);
        }
        pthread_mutex_unlock(&g_shared_pool.alloc_lock);
        return;
    }

    #if !HAKMEM_BUILD_RELEASE
    if (dbg == 1) {
        fprintf(stderr, "[SP_SLOT_RELEASE] ss=%p slab_idx=%d class=%d used=0 (marking EMPTY)\n",
                (void*)ss, slab_idx, class_idx);
    }
    #endif

    if (class_idx == 7) {
        ss_slab_reset_meta_for_tiny(ss, slab_idx, class_idx);
#if HAKMEM_BUILD_RELEASE
        static _Atomic uint32_t rel_c7_reset_logs = 0;
        uint32_t rn = atomic_fetch_add_explicit(&rel_c7_reset_logs, 1, memory_order_relaxed);
        if (rn < 4) {
            TinySlabMeta* m = &ss->slabs[slab_idx];
            fprintf(stderr,
                    "[REL_C7_RELEASE_RESET] ss=%p slab=%d used=%u cap=%u carved=%u freelist=%p\n",
                    (void*)ss,
                    slab_idx,
                    (unsigned)m->used,
                    (unsigned)m->capacity,
                    (unsigned)m->carved,
                    m->freelist);
        }
#else
        static _Atomic uint32_t dbg_c7_reset_logs = 0;
        uint32_t rn = atomic_fetch_add_explicit(&dbg_c7_reset_logs, 1, memory_order_relaxed);
        if (rn < 4) {
            TinySlabMeta* m = &ss->slabs[slab_idx];
            fprintf(stderr,
                    "[DBG_C7_RELEASE_RESET] ss=%p slab=%d used=%u cap=%u carved=%u freelist=%p\n",
                    (void*)ss,
                    slab_idx,
                    (unsigned)m->used,
                    (unsigned)m->capacity,
                    (unsigned)m->carved,
                    m->freelist);
        }
#endif
    }

    // Find SharedSSMeta for this SuperSlab
    SharedSSMeta* sp_meta = NULL;
    uint32_t count = atomic_load_explicit(&g_shared_pool.ss_meta_count, memory_order_relaxed);
    for (uint32_t i = 0; i < count; i++) {
        // RACE FIX: Load pointer atomically
        SuperSlab* meta_ss = atomic_load_explicit(&g_shared_pool.ss_metadata[i].ss, memory_order_relaxed);
        if (meta_ss == ss) {
            sp_meta = &g_shared_pool.ss_metadata[i];
            break;
        }
    }

    if (!sp_meta) {
        // SuperSlab not in SP-SLOT system yet - create metadata
        sp_meta = sp_meta_find_or_create(ss);
        if (!sp_meta) {
            pthread_mutex_unlock(&g_shared_pool.alloc_lock);
            return;  // Failed to create metadata
        }
    }

    // Mark slot as EMPTY (ACTIVE → EMPTY)
    uint32_t slab_bit = (1u << slab_idx);
    SlotState slot_state = atomic_load_explicit(
        &sp_meta->slots[slab_idx].state,
        memory_order_acquire);
    if (slot_state != SLOT_ACTIVE && (ss->slab_bitmap & slab_bit)) {
        // Legacy path import: rebuild slot states from SuperSlab bitmap/class_map
        sp_meta_sync_slots_from_ss(sp_meta, ss);
        slot_state = atomic_load_explicit(
            &sp_meta->slots[slab_idx].state,
            memory_order_acquire);
    }

    if (slot_state != SLOT_ACTIVE || sp_slot_mark_empty(sp_meta, slab_idx) != 0) {
        if (g_lock_stats_enabled == 1) {
            atomic_fetch_add(&g_lock_release_count, 1);
        }
        pthread_mutex_unlock(&g_shared_pool.alloc_lock);
        return;  // Slot wasn't ACTIVE
    }

    // Update SuperSlab metadata
    uint32_t bit = (1u << slab_idx);
    if (ss->slab_bitmap & bit) {
        ss->slab_bitmap &= ~bit;
        slab_meta->class_idx = 255;  // UNASSIGNED
        // P1.1: Mark class_map as UNASSIGNED when releasing slab
        ss->class_map[slab_idx] = 255;
        // Reset slab metadata to a pristine state for all classes (C0–C7)
        ss_slab_reset_meta_for_tiny(ss, slab_idx, -1);

        if (ss->active_slabs > 0) {
            ss->active_slabs--;
            if (ss->active_slabs == 0 && g_shared_pool.active_count > 0) {
                g_shared_pool.active_count--;
            }
        }
        if (class_idx < TINY_NUM_CLASSES_SS &&
            g_shared_pool.class_active_slots[class_idx] > 0) {
            g_shared_pool.class_active_slots[class_idx]--;
        }
    }

    // P0-4: Push to lock-free per-class free list (enables reuse by same class)
    // Note: push BEFORE releasing mutex (slot state already updated under lock)
    if (class_idx < TINY_NUM_CLASSES_SS) {
        sp_freelist_push_lockfree(class_idx, sp_meta, slab_idx);

        #if !HAKMEM_BUILD_RELEASE
        if (dbg == 1) {
            fprintf(stderr, "[SP_SLOT_FREELIST_LOCKFREE] class=%d pushed slot (ss=%p slab=%d) active_slots=%u/%u\n",
                    class_idx, (void*)ss, slab_idx,
                    sp_meta->active_slots, sp_meta->total_slots);
        }
        #endif
    }

    // P-Tier: Check tier transition after releasing slab
    // This may transition HOT → DRAINING if utilization dropped below threshold
    // or DRAINING → FREE if utilization reached 0
    ss_tier_check_transition(ss);

    // P-Tier Step B: Eager FREE eviction
    // If tier transitioned to FREE (total_active_blocks == 0), immediately try to
    // release the SuperSlab regardless of active_slots. This prevents registry bloat.
    SSTier current_tier = ss_tier_get(ss);
    if (current_tier == SS_TIER_FREE) {
        // Double-check: total_active_blocks should be 0 for FREE tier
        uint32_t active_blocks = atomic_load_explicit(&ss->total_active_blocks, memory_order_acquire);
        if (active_blocks == 0 && ss_release_guard_superslab_can_free(ss)) {
            #if !HAKMEM_BUILD_RELEASE
            if (dbg == 1) {
                fprintf(stderr, "[SP_TIER_FREE_EAGER] ss=%p tier=FREE active_slots=%u -> immediate free\n",
                        (void*)ss, sp_meta->active_slots);
            }
            #endif

            // Force all remaining slots to EMPTY state for clean metadata
            for (uint32_t i = 0; i < sp_meta->total_slots; i++) {
                SlotState st = atomic_load_explicit(&sp_meta->slots[i].state, memory_order_relaxed);
                if (st == SLOT_ACTIVE) {
                    atomic_store_explicit(&sp_meta->slots[i].state, SLOT_EMPTY, memory_order_relaxed);
                }
            }
            sp_meta->active_slots = 0;

            if (g_lock_stats_enabled == 1) {
                atomic_fetch_add(&g_lock_release_count, 1);
            }

            // Clear meta->ss before unlocking (race prevention)
            atomic_store_explicit(&sp_meta->ss, NULL, memory_order_release);

            pthread_mutex_unlock(&g_shared_pool.alloc_lock);

            // Free SuperSlab immediately (bypasses normal active_slots==0 check)
            extern void superslab_free(SuperSlab* ss);
            ss_stats_on_ss_free_class(class_idx);
            ss_budget_on_free(class_idx);
            superslab_free(ss);
            return;
        }
    }

    // Check if SuperSlab is now completely empty (all slots EMPTY or UNUSED)
    if (sp_meta->active_slots == 0) {
        #if !HAKMEM_BUILD_RELEASE
        if (dbg == 1) {
            fprintf(stderr, "[SP_SLOT_COMPLETELY_EMPTY] ss=%p active_slots=0 (calling superslab_free)\n",
                    (void*)ss);
        }
        #endif

        if (g_lock_stats_enabled == 1) {
            atomic_fetch_add(&g_lock_release_count, 1);
        }

        // RACE FIX: Set meta->ss to NULL BEFORE unlocking mutex
        // This prevents Stage 2 from accessing freed SuperSlab
        atomic_store_explicit(&sp_meta->ss, NULL, memory_order_release);

        pthread_mutex_unlock(&g_shared_pool.alloc_lock);

        // Remove from legacy backend list (moved to top of function)
        // extern void remove_superslab_from_legacy_head(SuperSlab* ss);
        // remove_superslab_from_legacy_head(ss);

        // Free SuperSlab:
        // 1. Try LRU cache (hak_ss_lru_push) - lazy deallocation
        // 2. Or munmap if LRU is full - eager deallocation
        
        // BUGFIX: Double check total_active_blocks and refcount. Legacy Backend might have
        // allocated from ANOTHER slab in this SS just before we removed it.
        // If so, we must NOT free the SS.
        if (ss_release_guard_superslab_can_free(ss)) {
            extern void superslab_free(SuperSlab* ss);
            ss_stats_on_ss_free_class(class_idx);
            ss_budget_on_free(class_idx);
            superslab_free(ss);
        } else {
            #if !HAKMEM_BUILD_RELEASE
            if (dbg == 1) {
                uint32_t active_blocks = atomic_load_explicit(&ss->total_active_blocks, memory_order_acquire);
                uint32_t ss_refs = superslab_ref_get(ss);
                fprintf(stderr,
                        "[SP_SLOT_RELEASE] SKIP free ss=%p: total_active_blocks=%u refcount=%u\n",
                        (void*)ss,
                        (unsigned)active_blocks,
                        (unsigned)ss_refs);
            }
            #endif
        }
        return;
    }

    if (g_lock_stats_enabled == 1) {
        atomic_fetch_add(&g_lock_release_count, 1);
    }
    pthread_mutex_unlock(&g_shared_pool.alloc_lock);
}