#ifndef TINY_ULTRA_FAST_INC_H
#define TINY_ULTRA_FAST_INC_H

// ============================================================================
// HAKMEM Ultra Fast Path
// ============================================================================
// Phase E5: System malloc並みの超軽量fast path
//
// 目的:
//   - FastCache/SFC/統計/プロファイリングを全てOFF
//   - TLS SLL 1層のみのシンプル実装
//   - 8-10命令でalloc/freeを完結
//
// 期待:
//   - System malloc並みの性能 (90M+ ops/s)
//   - 「賢い機能」のコストを定量化
// ============================================================================

#include "hakmem_tiny.h"

// External TLS arrays (defined in hakmem_tiny.c)
// Phase 3d-B: TLS Cache Merge - Unified structure (type in hakmem_tiny.h)
extern __thread TinyTLSSLL g_tls_sll[TINY_NUM_CLASSES];

// ============================================================================
// Ultra-Fast Allocation (8-10 instructions)
// ============================================================================
static inline void* tiny_alloc_ultra_fast(size_t size) {
    // 1. Size to class (direct calculation, no LUT)
    // HAKMEM Tiny classes (from g_tiny_class_sizes):
    // C0=8B, C1=16B, C2=32B, C3=64B, C4=128B, C5=256B, C6=512B, C7=1024B
    if (size == 0) size = 1;
    if (size > 1024) return NULL;  // Tiny範囲外

    // Direct mapping: use BSR-style or simple branching
    int cl;
    if (size <= 8) cl = 0;
    else if (size <= 16) cl = 1;
    else if (size <= 32) cl = 2;
    else if (size <= 64) cl = 3;
    else if (size <= 128) cl = 4;
    else if (size <= 256) cl = 5;
    else if (size <= 512) cl = 6;
    else cl = 7;  // size <= 1024

    // 2. TLS SLL pop (3-4 instructions)
    // Phase 3d-B: Use unified struct (head+count in same cache line)
    void* ptr = g_tls_sll[cl].head;  // 1 load
    if (!ptr) return NULL;  // 1 branch (miss → slow path)

    void* next = *(void**)ptr;  // 1 load (next pointer)
    g_tls_sll[cl].head = next;  // 1 store
    g_tls_sll[cl].count--;      // 1 decrement

    // 3. Return USER pointer (ptr is BASE, +1 for header)
    //    Phase 7 header-based fast free requires this
    return (char*)ptr + 1;
}

// ============================================================================
// Ultra-Fast Free (6-8 instructions)
// ============================================================================
static inline int tiny_free_ultra_fast(void* ptr) {
    if (!ptr) return 0;

    // 1. Read header to get class_idx (Phase 7 header-based)
    uint8_t header = *((uint8_t*)ptr - 1);
    uint8_t class_idx = header & 0x0F;

    // 2. Bounds check (safety - minimal overhead)
    if (class_idx >= TINY_NUM_CLASSES) return 0;  // Route to slow path

    // 3. Convert USER → BASE
    void* base = (char*)ptr - 1;

    // 4. TLS SLL push (3-4 instructions)
    // Phase 3d-B: Use unified struct (head+count in same cache line)
    void* head = g_tls_sll[class_idx].head;  // 1 load
    *(void**)base = head;                     // 1 store (link)
    g_tls_sll[class_idx].head = base;         // 1 store
    g_tls_sll[class_idx].count++;             // 1 increment

    return 1;  // Success
}

// ============================================================================
// Ultra Mode Entry Point - TLS SLL Only (no fallback)
// ============================================================================
// NOTE: Ultra mode expects TLS SLL to be warm. If miss, returns NULL.
// Caller (wrapper) will fallback to full tiny_alloc_fast path.

static inline void* tiny_alloc_fast_ultra(size_t size) {
    // Try ultra-fast path (TLS SLL only)
    return tiny_alloc_ultra_fast(size);
}

static inline void tiny_free_fast_ultra(void* ptr) {
    // Try ultra-fast free (TLS SLL push only)
    tiny_free_ultra_fast(ptr);
}

#endif // TINY_ULTRA_FAST_INC_H