// smallobject_hotbox_v4.c - SmallObject HotHeap v4 (C5/C6/C7 opt-in)
//
// Phase v4-3.1: C7 は v4 独自の freelist/current/partial で完結。C6/C5 は強ゲート付きで同形パスを使う。

#include <stdlib.h>
#include <string.h>

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

#include "box/smallobject_hotbox_v4_box.h"
#include "box/smallobject_hotbox_v4_env_box.h"
#include "box/smallobject_hotbox_v4_stats_box.h"
#include "box/smallobject_cold_iface_v4.h"
#include "box/smallobject_hotbox_v3_env_box.h"
#include "box/tiny_heap_box.h"
#include "box/smallsegment_v4_box.h"
#include "box/smallsegment_v4_env_box.h"
#include "box/tiny_cold_iface_v1.h"
#include "box/tiny_geometry_box.h"
#include "tiny_region_id.h"

// ============================================================================
// Stats storage (Phase v4-mid-5)
// ============================================================================
small_heap_v4_class_stats_t g_small_heap_v4_stats[8];

// ============================================================================
// v4 Segment Configuration (Phase v4-mid-0+)
// ============================================================================

#define SMALL_SEGMENT_V4_SIZE (2 * 1024 * 1024)  // 2 MiB segment
#define SMALL_SEGMENT_V4_PAGE_SIZE (64 * 1024)   // 64 KiB page
#define SMALL_SEGMENT_V4_MAGIC 0xDEADBEEF
#define SMALL_SEGMENT_V4_PAGE_SHIFT 16            // log2(64KiB)

// TLS context
static __thread small_heap_ctx_v4 g_ctx_v4;

// Phase v4-mid-6: C6 TLS Fastlist
static __thread SmallC6FastState g_small_c6_fast;

static inline SmallC6FastState* small_c6_fast_state(void) {
    return &g_small_c6_fast;
}

// Internal segment structure (internal use only, not exposed via public box API)
typedef struct small_segment_v4_internal {
    int class_idx;
    size_t segment_size;
    tiny_heap_ctx_t* tiny_ctx;
} small_segment_v4_internal;

static __thread small_segment_v4_internal g_segments_v4[SMALLOBJECT_NUM_CLASSES];

small_heap_ctx_v4* small_heap_ctx_v4_get(void) {
    return &g_ctx_v4;
}

static small_page_v4* v4_page_from_lease(tiny_heap_page_t* lease, int class_idx, small_segment_v4* seg);

// -----------------------------------------------------------------------------
// helpers
// -----------------------------------------------------------------------------

static inline int v4_class_supported(int class_idx) {
    return class_idx == 7 || class_idx == 6 || class_idx == 5;
}

static size_t smallsegment_v4_default_size(void) {
    const char* env = smallsegment_v4_size_env();
    if (env && *env) {
        size_t v = strtoull(env, NULL, 0);
        if (v > (size_t)(64 * 1024)) {
            return v;
        }
    }
    return (size_t)(2 * 1024 * 1024);  // default 2MiB segment単位（将来の実装用）
}

small_segment_v4* smallsegment_v4_acquire(int class_idx) {
    if (!v4_class_supported(class_idx)) return NULL;
    small_segment_v4_internal* seg = &g_segments_v4[class_idx];
    seg->class_idx = class_idx;
    if (!seg->segment_size) {
        seg->segment_size = smallsegment_v4_default_size();
    }
    if (!seg->tiny_ctx) {
        seg->tiny_ctx = tiny_heap_ctx_for_thread();
    }
    return (small_segment_v4*)seg;
}

void* smallsegment_v4_alloc_page(small_segment_v4* seg, int class_idx) {
    if (!seg || !v4_class_supported(class_idx)) return NULL;
    // Internal use only: cast to internal type to access tiny_ctx
    small_segment_v4_internal* int_seg = (small_segment_v4_internal*)seg;
    if (!int_seg->tiny_ctx) {
        int_seg->tiny_ctx = tiny_heap_ctx_for_thread();
    }
    tiny_heap_ctx_t* tctx = int_seg->tiny_ctx ? int_seg->tiny_ctx : tiny_heap_ctx_for_thread();
    if (!tctx) return NULL;

    tiny_heap_page_t* lease = tiny_heap_prepare_page(tctx, class_idx);
    if (!lease) return NULL;
    int_seg->tiny_ctx = tctx;
    return v4_page_from_lease(lease, class_idx, seg);
}

void smallsegment_v4_release_if_empty(small_segment_v4* seg, void* page_ptr, int class_idx) {
    small_page_v4* page = (small_page_v4*)page_ptr;
    if (!page || !v4_class_supported(class_idx)) return;
    tiny_heap_ctx_t* tctx = tiny_heap_ctx_for_thread();
    tiny_heap_page_t* lease = (tiny_heap_page_t*)page->slab_ref;
    if (tctx && lease) {
        tiny_heap_page_becomes_empty(tctx, class_idx, lease);
    }
    free(page);
}

static inline void v4_page_push_partial(small_class_heap_v4* h, small_page_v4* page) {
    if (!h || !page) return;
    page->next = h->partial_head;
    h->partial_head = page;
    h->partial_count++;
}

static inline small_page_v4* v4_page_pop_partial(small_class_heap_v4* h) {
    if (!h) return NULL;
    small_page_v4* p = h->partial_head;
    if (p) {
        h->partial_head = p->next;
        p->next = NULL;
        if (h->partial_count > 0) {
            h->partial_count--;
        }
    }
    return p;
}

static inline void v4_page_push_full(small_class_heap_v4* h, small_page_v4* page) {
    if (!h || !page) return;
    page->next = h->full_head;
    h->full_head = page;
}

static inline uint32_t v4_partial_limit(int class_idx) {
    // C7 は refill/retire を抑えるため少し広めに保持
    return (class_idx == 7) ? 2u : 1u;
}

static inline int v4_ptr_in_page(const small_page_v4* page, const uint8_t* ptr) {
    if (!page || !ptr) return 0;
    uint8_t* base = page->base;
    size_t span = (size_t)page->block_size * (size_t)page->capacity;
    if (ptr < base || ptr >= base + span) return 0;
    size_t off = (size_t)(ptr - base);
    return (off % page->block_size) == 0;
}

static inline void* v4_build_freelist(uint8_t* base, uint16_t capacity, size_t stride) {
    void* head = NULL;
    for (int i = capacity - 1; i >= 0; i--) {
        uint8_t* blk = base + ((size_t)i * stride);
        void* next = head;
        head = blk;
        memcpy(blk, &next, sizeof(void*));
    }
    return head;
}

typedef enum {
    V4_LOC_NONE = 0,
    V4_LOC_CURRENT,
    V4_LOC_PARTIAL,
    V4_LOC_FULL,
} v4_loc_t;

static small_page_v4* v4_find_page(small_class_heap_v4* h, const uint8_t* ptr, v4_loc_t* loc, small_page_v4** prev_out) {
    if (loc) *loc = V4_LOC_NONE;
    if (prev_out) *prev_out = NULL;
    if (!h || !ptr) return NULL;

    if (h->current && v4_ptr_in_page(h->current, ptr)) {
        if (loc) *loc = V4_LOC_CURRENT;
        return h->current;
    }
    small_page_v4* prev = NULL;
    for (small_page_v4* p = h->partial_head; p; prev = p, p = p->next) {
        if (v4_ptr_in_page(p, ptr)) {
            if (loc) *loc = V4_LOC_PARTIAL;
            if (prev_out) *prev_out = prev;
            return p;
        }
    }
    for (small_page_v4* p = h->full_head; p; prev = p, p = p->next) {
        if (v4_ptr_in_page(p, ptr)) {
            if (loc) *loc = V4_LOC_FULL;
            if (prev_out) *prev_out = prev;
            return p;
        }
    }
    return NULL;
}

int smallobject_hotbox_v4_can_own(int class_idx, void* ptr) {
    if (__builtin_expect(!v4_class_supported(class_idx), 0)) return 0;
    if (!small_heap_v4_class_enabled((uint8_t)class_idx)) return 0;
    if (!ptr) return 0;
    small_heap_ctx_v4* ctx = small_heap_ctx_v4_get();
    if (!ctx) return 0;
    small_class_heap_v4* h = &ctx->cls[class_idx];
    return v4_find_page(h, (const uint8_t*)ptr, NULL, NULL) != NULL;
}

// -----------------------------------------------------------------------------
// Cold iface (C5/C6/C7, Tiny v1 経由)
// -----------------------------------------------------------------------------

static small_page_v4* v4_page_from_lease(tiny_heap_page_t* lease, int class_idx, small_segment_v4* seg) {
    if (!lease) return NULL;
    small_page_v4* page = (small_page_v4*)malloc(sizeof(small_page_v4));
    if (!page) return NULL;
    memset(page, 0, sizeof(*page));
    page->class_idx = (uint8_t)class_idx;
    page->capacity = lease->capacity;
    page->used = 0;
    page->block_size = (uint32_t)tiny_stride_for_class((int)class_idx);
    page->base = lease->base;
    page->slab_ref = lease;
    page->segment = seg;
    page->freelist = v4_build_freelist(lease->base, lease->capacity, page->block_size);
    if (!page->freelist) {
        free(page);
        return NULL;
    }
    page->next = NULL;
    page->flags = 0;
    return page;
}

static small_page_v4* cold_refill_page_v4(small_heap_ctx_v4* hot_ctx, uint32_t class_idx) {
    if (__builtin_expect(!v4_class_supported((int)class_idx), 0)) return NULL;
    (void)hot_ctx;

    if (smallsegment_v4_enabled()) {
        small_segment_v4* seg = smallsegment_v4_acquire((int)class_idx);
        return (small_page_v4*)smallsegment_v4_alloc_page(seg, (int)class_idx);
    }

    tiny_heap_ctx_t* tctx = tiny_heap_ctx_for_thread();
    if (!tctx) return NULL;

    // Phase v4-mid-6: Get a fresh page from TinyHeap
    tiny_heap_page_t* lease = tiny_heap_prepare_page(tctx, (int)class_idx);
    if (!lease) return NULL;

    // Clear TinyHeap's current so next call gets fresh page
    tiny_heap_class_t* hcls = tiny_heap_class(tctx, (int)class_idx);
    if (hcls) {
        tiny_heap_class_unlink(hcls, lease);
    }

    return v4_page_from_lease(lease, (int)class_idx, NULL);
}

static void cold_retire_page_v4(small_heap_ctx_v4* hot_ctx, uint32_t class_idx, small_page_v4* page) {
    (void)hot_ctx;
    if (!page) return;
    if (smallsegment_v4_enabled()) {
        small_segment_v4* seg = (small_segment_v4*)page->segment;
        smallsegment_v4_release_if_empty(seg, page, (int)class_idx);
        return;
    }
    tiny_heap_ctx_t* tctx = tiny_heap_ctx_for_thread();
    tiny_heap_page_t* lease = (tiny_heap_page_t*)page->slab_ref;
    if (tctx && lease) {
        tiny_heap_page_becomes_empty(tctx, (int)class_idx, lease);
    }
    free(page);
}

// Direct function implementations (phase v4-mid-0: cold_refill/retire を直接呼び出す)
small_page_v4* small_cold_v4_refill_page(small_heap_ctx_v4* ctx, uint32_t class_idx) {
    return cold_refill_page_v4(ctx, class_idx);
}

void small_cold_v4_retire_page(small_heap_ctx_v4* ctx, small_page_v4* page) {
    if (!page) return;
    cold_retire_page_v4(ctx, (uint32_t)page->class_idx, page);
}

bool small_cold_v4_remote_push(small_page_v4* page, void* ptr, uint32_t tid) {
    (void)page; (void)ptr; (void)tid;
    return false;  // stub: not yet implemented
}

void small_cold_v4_remote_drain(small_heap_ctx_v4* ctx) {
    (void)ctx;
    // stub: not yet implemented
}

// ============================================================================
// smallsegment_v4_page_meta_of: Pointer → Page metadata lookup
// ============================================================================
// Phase v4-mid-1: Implement mask+shift O(1) lookup for Fail-Fast validation.
//
// Algorithm:
//   1. Compute segment base: addr & ~(SMALL_SEGMENT_V4_SIZE - 1)
//   2. Verify magic number
//   3. Compute page_idx: (addr - seg_base) >> SMALL_SEGMENT_V4_PAGE_SHIFT
//   4. Return &seg->page_meta[page_idx] or NULL

small_page_v4* smallsegment_v4_page_meta_of(small_segment_v4* seg, void* ptr) {
    if (!seg || !ptr) {
        return NULL;
    }

    uintptr_t addr = (uintptr_t)ptr;
    uintptr_t seg_base = addr & ~(SMALL_SEGMENT_V4_SIZE - 1);

    // Verify segment pointer and magic
    SmallSegment* s = (SmallSegment*)seg_base;
    if (!s || s->magic != SMALL_SEGMENT_V4_MAGIC) {
        return NULL;
    }

    // Compute page index and bounds check
    size_t page_idx = (addr - seg_base) >> SMALL_SEGMENT_V4_PAGE_SHIFT;
    if (page_idx >= s->num_pages) {
        return NULL;
    }

    // Return page metadata (computed as flexible array offset)
    // Note: For now, just return a non-NULL marker.
    // Actual page_meta[] array will be implemented in Phase v4-mid-2.
    return (SmallPageMeta*)(1);  // Non-NULL sentinel for now
}

// -----------------------------------------------------------------------------
// alloc/free
// -----------------------------------------------------------------------------

static small_page_v4* small_alloc_slow_v4(small_heap_ctx_v4* ctx, int class_idx) {
    small_class_heap_v4* h = &ctx->cls[class_idx];
    const uint32_t partial_limit = v4_partial_limit(class_idx);
    small_page_v4* cur = h->current;
    if (cur && cur->freelist) {
        return cur;  // usable current
    }
    if (cur && !cur->freelist) {
        // current をいったん partial/full に退避（partial を優先）
        if (h->partial_count < partial_limit) {
            v4_page_push_partial(h, cur);
        } else {
            v4_page_push_full(h, cur);
        }
        h->current = NULL;
    }

    // partial から 1 ページだけ復帰
    small_page_v4* from_partial = v4_page_pop_partial(h);
    if (from_partial) {
        h->current = from_partial;
        return from_partial;
    }

    // Call direct Cold function (not vtable)
    small_page_v4* page = small_cold_v4_refill_page(ctx, (uint32_t)class_idx);
    if (!page) return NULL;
    h->current = page;
    return page;
}

void* small_heap_alloc_fast_v4(small_heap_ctx_v4* ctx, int class_idx) {
    // Phase v4-mid-5: Add stats instrumentation
    small_heap_v4_stat_alloc_call(class_idx);

    // Phase v4-mid-6: C6 Fastlist Path
    if (class_idx == 6 && small_heap_v4_fastlist_enabled()) {
        SmallC6FastState* s = &g_small_c6_fast;
        if (likely(s->freelist)) {
            void* b = s->freelist;
            s->freelist = *(void**)b;
            s->used++;
            small_heap_v4_stat_alloc_success(class_idx);
            return tiny_region_id_write_header(b, class_idx);
        }
        // Fastlist empty: sync used back to meta before slow path
        if (s->meta) {
            s->meta->used = (uint16_t)s->used;
        }
    }

    // Phase v4-mid-2: C6-only full SmallHeapCtx v4 implementation
    if (__builtin_expect(!v4_class_supported(class_idx), 0)) {
        small_heap_v4_stat_alloc_fallback_pool(class_idx);
        return NULL;  // C5/C6/C7 以外は未対応
    }
    if (!small_heap_v4_class_enabled((uint8_t)class_idx)) {
        small_heap_v4_stat_alloc_fallback_pool(class_idx);
        return NULL;
    }

    small_class_heap_v4* h = &ctx->cls[class_idx];
    small_page_v4* page = h->current;

    // Try current page freelist
    if (page && page->freelist) {
        void* blk = page->freelist;
        void* next = NULL;
        memcpy(&next, blk, sizeof(void*));
        page->freelist = next;
        page->used++;
        small_heap_v4_stat_alloc_success(class_idx);
        return tiny_region_id_write_header(blk, class_idx);
    }

    // Current exhausted or NULL, try slow path (partial/refill)
    page = small_alloc_slow_v4(ctx, class_idx);
    if (!page || !page->freelist) {
        small_heap_v4_stat_alloc_null_page(class_idx);
        small_heap_v4_stat_alloc_fallback_pool(class_idx);
        return NULL;
    }

    // Phase v4-mid-6: Promote to C6 Fastlist
    if (class_idx == 6 && small_heap_v4_fastlist_enabled()) {
        if (!page) {
             // Should not happen
        } else if (!page->freelist) {
             return NULL;
        } else {
             SmallC6FastState* s = &g_small_c6_fast;
             s->meta = page;
             s->page_base = page->base;
             s->capacity = page->capacity;
             s->used = page->used;
             s->freelist = page->freelist;
             page->freelist = NULL; // Steal freelist ownership

             // Retry fast path
             if (likely(s->freelist)) {
                 void* b = s->freelist;
                 s->freelist = *(void**)b;
                 s->used++;
                 small_heap_v4_stat_alloc_success(class_idx);
                 return tiny_region_id_write_header(b, class_idx);
             }
        }
    }

    // Allocate from newly acquired/promoted page
    void* blk = page->freelist;
    void* next = NULL;
    memcpy(&next, blk, sizeof(void*));
    page->freelist = next;
    page->used++;

    small_heap_v4_stat_alloc_success(class_idx);
    return tiny_region_id_write_header(blk, class_idx);
}

static void v4_unlink_from_list(small_class_heap_v4* h, v4_loc_t loc, small_page_v4* prev, small_page_v4* page) {
    if (!h || !page) return;
    switch (loc) {
        case V4_LOC_CURRENT:
            h->current = NULL;
            break;
        case V4_LOC_PARTIAL:
            if (prev) prev->next = page->next;
            else h->partial_head = page->next;
            if (h->partial_count > 0) {
                h->partial_count--;
            }
            break;
        case V4_LOC_FULL:
            if (prev) prev->next = page->next;
            else h->full_head = page->next;
            break;
        default:
            break;
    }
    page->next = NULL;
}

extern void hak_pool_free(void* ptr, size_t size, uintptr_t site_id);

void small_heap_free_fast_v4(small_heap_ctx_v4* ctx, int class_idx, void* ptr) {
    // Phase v4-mid-5: Add stats instrumentation
    small_heap_v4_stat_free_call(class_idx);

    // Phase v4-mid-6: C6 Fastlist Path
    if (class_idx == 6 && small_heap_v4_fastlist_enabled()) {
        SmallC6FastState* s = &g_small_c6_fast;
        if (s->page_base && (uintptr_t)ptr >= (uintptr_t)s->page_base) {
             // Use actual block size from meta
             uint32_t bsize = (s->meta) ? s->meta->block_size : 512;
             size_t span = (size_t)s->capacity * bsize;
             if ((uintptr_t)ptr < (uintptr_t)s->page_base + span) {
                 *(void**)ptr = s->freelist;
                 s->freelist = ptr;
                 s->used--;
                 small_heap_v4_stat_free_page_found(class_idx);
                 return;
             }
        }
    }

    // Phase v4-mid-2: C6-only full SmallHeapCtx v4 implementation
    if (__builtin_expect(!v4_class_supported(class_idx), 0)) {
        return;
    }
    if (!small_heap_v4_class_enabled((uint8_t)class_idx)) return;
    if (!ptr) return;

    // Phase v4-mid-6: ptr is already BASE (caller converts USER→BASE before calling us)
    // See malloc_tiny_fast.h L254: base = ptr - 1, then L354/L282 passes base
    void* base_ptr = ptr;

    small_class_heap_v4* h = &ctx->cls[class_idx];
    small_page_v4* prev = NULL;
    v4_loc_t loc = V4_LOC_NONE;

    // Try to find page in current/partial/full lists (using BASE pointer)
    small_page_v4* page = v4_find_page(h, (const uint8_t*)base_ptr, &loc, &prev);

    // Phase v4-mid-2: If page not found in v4 heap, try page_meta_of() for segment lookup
    if (!page) {
        small_heap_v4_stat_free_page_not_found(class_idx);
        // Try to find via segment mask+shift (requires segment to be initialized)
        // For now, this is a fallback for future segment-based allocation
        // Fallback to pool v1 (avoid recursion via free())
        hak_pool_free(base_ptr, 0, 0);
        return;
    }

    small_heap_v4_stat_free_page_found(class_idx);

    const uint32_t partial_limit = v4_partial_limit(class_idx);

    // freelist push (use BASE pointer, not USER pointer)
    void* head = page->freelist;
    memcpy(base_ptr, &head, sizeof(void*));
    page->freelist = base_ptr;
    if (page->used > 0) {
        page->used--;
    }

    if (page->used == 0) {
        if (loc != V4_LOC_CURRENT) {
            v4_unlink_from_list(h, loc, prev, page);
        }
        if (!h->current) {
            h->current = page;
            page->next = NULL;
            return;
        }
        if (h->current == page) {
            page->next = NULL;
            return;
        }
        if (h->partial_count < partial_limit) {
            v4_page_push_partial(h, page);
            return;
        }
        // Call direct Cold function (not vtable)
        small_cold_v4_retire_page(ctx, page);
        return;
    }

    if (!h->current) {
        // このページを current に据える
        if (loc != V4_LOC_CURRENT) {
            v4_unlink_from_list(h, loc, prev, page);
        }
        h->current = page;
        page->next = NULL;
    } else if (loc == V4_LOC_FULL && page->freelist) {
        // full → partial に戻す（current があっても partial 上限までは復帰）
        v4_unlink_from_list(h, loc, prev, page);
        if (h->partial_count < partial_limit) {
            v4_page_push_partial(h, page);
        } else {
            v4_page_push_full(h, page);  // 上限超なら戻す
        }
    }
}

// ============================================================================
// Stats dump (Phase v4-mid-5)
// ============================================================================
void small_heap_v4_stats_dump(void) {
    if (!small_heap_v4_stats_enabled()) {
        return;
    }

    fprintf(stderr, "\n========================================\n");
    fprintf(stderr, "[SMALL_HEAP_V4_STATS] Summary\n");
    fprintf(stderr, "========================================\n");

    for (int c = 0; c < 8; c++) {
        uint64_t alloc_calls = atomic_load_explicit(&g_small_heap_v4_stats[c].alloc_calls, memory_order_relaxed);
        uint64_t alloc_success = atomic_load_explicit(&g_small_heap_v4_stats[c].alloc_success, memory_order_relaxed);
        uint64_t alloc_null_page = atomic_load_explicit(&g_small_heap_v4_stats[c].alloc_null_page, memory_order_relaxed);
        uint64_t alloc_fallback = atomic_load_explicit(&g_small_heap_v4_stats[c].alloc_fallback_pool, memory_order_relaxed);
        uint64_t free_calls = atomic_load_explicit(&g_small_heap_v4_stats[c].free_calls, memory_order_relaxed);
        uint64_t free_found = atomic_load_explicit(&g_small_heap_v4_stats[c].free_page_found, memory_order_relaxed);
        uint64_t free_not_found = atomic_load_explicit(&g_small_heap_v4_stats[c].free_page_not_found, memory_order_relaxed);

        if (alloc_calls > 0 || free_calls > 0) {
            fprintf(stderr, "\nClass C%d:\n", c);
            fprintf(stderr, "  Alloc: calls=%lu success=%lu null_page=%lu fallback_pool=%lu\n",
                    (unsigned long)alloc_calls, (unsigned long)alloc_success,
                    (unsigned long)alloc_null_page, (unsigned long)alloc_fallback);
            fprintf(stderr, "  Free:  calls=%lu page_found=%lu page_not_found=%lu\n",
                    (unsigned long)free_calls, (unsigned long)free_found,
                    (unsigned long)free_not_found);
        }
    }

    fprintf(stderr, "========================================\n\n");
    fflush(stderr);
}

// Automatic dump at program exit
static void small_heap_v4_stats_atexit(void) __attribute__((destructor));
static void small_heap_v4_stats_atexit(void) {
    small_heap_v4_stats_dump();
}