// smallobject_cold_iface_v7.c - SmallObject ColdIface v7 implementation (Phase v7-5b)
//
// Purpose:
//   - Page refill: acquire page from segment, carve freelist
//   - Page retire: release empty page back to segment, publish stats
//
// v7-5a optimizations:
//   - Header written at alloc time (not carve - freelist overlaps block[0])
//   - Stats collected at retire time (not on hot path)
//
// v7-5b additions:
//   - C5 support (256B blocks) alongside C6 (512B blocks)
//   - Same segment shared between C5/C6, page_meta.class_idx distinguishes

#include <stdlib.h>
#include <string.h>
#include <stdint.h>
#include <stdio.h>
#include <unistd.h>
#include "box/smallobject_cold_iface_v7_box.h"
#include "box/smallsegment_v7_box.h"
#include "box/region_id_v6_box.h"
#include "box/smallobject_policy_v7_box.h"  // v7-7: Learner integration
#include "tiny_region_id.h"  // v7-5a: For HEADER_MAGIC, HEADER_CLASS_MASK

#ifndef likely
#define likely(x)   __builtin_expect(!!(x), 1)
#define unlikely(x) __builtin_expect(!!(x), 0)
#endif

// ============================================================================
// V7 Stats (for debugging/OBSERVE)
// ============================================================================

static uint64_t g_v7_alloc_count = 0;
static uint64_t g_v7_free_count = 0;
static uint64_t g_v7_refill_count = 0;
static uint64_t g_v7_retire_count = 0;

// Destructor to print stats at exit
__attribute__((destructor))
static void small_v7_stats_report(void) {
    if (g_v7_alloc_count > 0 || g_v7_free_count > 0) {
        fprintf(stderr, "[SMALL_V7] alloc=%lu free=%lu refill=%lu retire=%lu\n",
                (unsigned long)g_v7_alloc_count, (unsigned long)g_v7_free_count,
                (unsigned long)g_v7_refill_count, (unsigned long)g_v7_retire_count);
    }
}

void small_v7_stat_alloc(void) { __sync_fetch_and_add(&g_v7_alloc_count, 1); }
void small_v7_stat_free(void) { __sync_fetch_and_add(&g_v7_free_count, 1); }
void small_v7_stat_refill(void) { __sync_fetch_and_add(&g_v7_refill_count, 1); }
void small_v7_stat_retire(void) { __sync_fetch_and_add(&g_v7_retire_count, 1); }

// ============================================================================
// TLS Heap Context
// ============================================================================

static __thread SmallHeapCtx_v7 g_small_heap_ctx_v7;
static __thread int g_small_heap_ctx_v7_init = 0;

SmallHeapCtx_v7* small_heap_ctx_v7(void) {
    if (unlikely(!g_small_heap_ctx_v7_init)) {
        // Initialize context
        memset(&g_small_heap_ctx_v7, 0, sizeof(g_small_heap_ctx_v7));

        for (int i = 0; i < HAK_SMALL_NUM_CLASSES_V7; i++) {
            g_small_heap_ctx_v7.cls[i].class_idx = (uint16_t)i;
            g_small_heap_ctx_v7.cls[i].current = NULL;
            g_small_heap_ctx_v7.cls[i].partial_head = NULL;
            g_small_heap_ctx_v7.cls[i].full_head = NULL;
            g_small_heap_ctx_v7.cls[i].local_freelist = NULL;
            g_small_heap_ctx_v7.cls[i].local_freelist_count = 0;
            g_small_heap_ctx_v7.cls[i].local_freelist_cap = 0;
            g_small_heap_ctx_v7.cls[i].flags = 0;
        }

        g_small_heap_ctx_v7.segment = NULL;

        // Phase v7-3: Initialize TLS fast hints and cache
        g_small_heap_ctx_v7.tls_seg_base = 0;
        g_small_heap_ctx_v7.tls_seg_end = 0;
        g_small_heap_ctx_v7.last_page_base = 0;
        g_small_heap_ctx_v7.last_page_end = 0;
        g_small_heap_ctx_v7.last_page_meta = NULL;

        g_small_heap_ctx_v7_init = 1;
    }

    return &g_small_heap_ctx_v7;
}

// ============================================================================
// Segment Acquisition (lazy)
// ============================================================================

static SmallSegment_v7* cold_v7_ensure_segment(SmallHeapCtx_v7* ctx) {
    if (likely(ctx->segment != NULL)) {
        return ctx->segment;
    }

    // Acquire segment for this thread
    uint32_t tid = (uint32_t)getpid();
    SmallSegment_v7* seg = small_segment_alloc_v7(tid);

    if (unlikely(!seg)) {
        return NULL;
    }

    ctx->segment = seg;

    // Phase v7-3: Set TLS segment fast hints
    ctx->tls_seg_base = seg->base;
    ctx->tls_seg_end = seg->base + SMALL_SEGMENT_V7_SIZE;

    // Register with RegionIdBox for ptr->region lookup
    // This enables region_id_lookup_v6() to recognize v7 pointers
    region_id_register_v6(
        (void*)seg->base,
        SMALL_SEGMENT_V7_SIZE,
        REGION_KIND_SMALL_V7,
        seg
    );

    return seg;
}

// ============================================================================
// Page Refill
// ============================================================================

SmallPageMeta_v7* small_cold_v7_refill_page(SmallHeapCtx_v7* ctx, uint32_t class_idx) {
    if (unlikely(!ctx)) {
        return NULL;
    }

    // v7-5b: C5 (256B) and C6 (512B) supported
    size_t block_size = small_v7_block_size(class_idx);
    if (unlikely(block_size == 0)) {
        return NULL;  // Unsupported class
    }

    // Ensure we have a segment
    SmallSegment_v7* seg = cold_v7_ensure_segment(ctx);
    if (unlikely(!seg)) {
        return NULL;
    }

    // Take a page from segment's free stack
    SmallPageMeta_v7* page = small_segment_take_page_v7(seg, class_idx);
    if (unlikely(!page)) {
        return NULL;  // No free pages
    }

    // Calculate page base address
    uintptr_t page_offset = (uintptr_t)page->page_idx * SMALL_PAGE_V7_SIZE;
    uintptr_t page_base = seg->base + page_offset;
    uint8_t* base = (uint8_t*)page_base;

    // Calculate capacity
    uint32_t capacity = SMALL_PAGE_V7_SIZE / block_size;
    page->capacity = capacity;
    page->used = 0;

    // Build intrusive freelist (last to first for cache locality on pop)
    // freelist points to BASE pointers (block start)
    //
    // Note: Cannot write header at carve time because freelist next pointer
    // is stored at block[0..7], which overlaps with header byte at block[0].
    // Header must be written at alloc time after popping from freelist.
    void* freelist = NULL;
    for (int i = (int)capacity - 1; i >= 0; i--) {
        uint8_t* block = base + ((size_t)i * block_size);

        // Link: block->next = freelist
        void* next = freelist;
        memcpy(block, &next, sizeof(void*));
        freelist = block;
    }

    page->free_list = freelist;

    // Set as current page for this class
    SmallClassHeap_v7* heap = &ctx->cls[class_idx];
    heap->current = page;

    // v7-7: Feed refill to Learner for workload detection
    small_learner_v7_record_refill(class_idx, capacity);

    return page;
}

// ============================================================================
// Page Retire
// ============================================================================

void small_cold_v7_retire_page(SmallHeapCtx_v7* ctx, SmallPageMeta_v7* page) {
    if (unlikely(!ctx || !page)) {
        return;
    }

    // Only retire pages that are fully empty
    if (page->used != 0) {
        return;
    }

    SmallSegment_v7* seg = page->segment;
    if (unlikely(!seg)) {
        return;
    }

    // Publish stats before retiring
    SmallPageStatsV7 stats = {
        .class_idx = (uint8_t)page->class_idx,
        .reserved0 = 0,
        .page_idx = page->page_idx,
        .capacity = page->capacity,
        .alloc_count = page->alloc_count,
        .free_count = page->free_count,
        .remote_free_count = page->remote_free_count,
        .peak_live = page->peak_live,
        .remote_burst_max = page->remote_burst_max,
        .lifetime_ms = 0  // TODO: Calculate from epoch
    };
    small_cold_v7_publish_stats(&stats);

    // Clear current if this was the current page
    SmallClassHeap_v7* heap = &ctx->cls[page->class_idx];
    if (heap->current == page) {
        heap->current = NULL;
    }

    // Release page back to segment
    small_segment_release_page_v7(seg, page);
}

// ============================================================================
// Stats Publishing (v7-7: Learner integration)
// ============================================================================

void small_cold_v7_publish_stats(const SmallPageStatsV7* stats) {
    if (!stats) return;

    // v7-7: Feed stats to Learner for dynamic route switching
    // Note: v7-5a removed alloc_count from hot path, use capacity as traffic proxy
    small_learner_v7_record_retire(stats->class_idx, stats->capacity);
}