Phase 21-1-B: Ring cache Alloc/Free 統合 - C2/C3 hot path integration

**統合内容**:
- Alloc path (tiny_alloc_fast.inc.h): Ring pop → HeapV2/UltraHot/SLL fallback
- Free path (tiny_free_fast_v2.inc.h): Ring push → HeapV2/SLL fallback
- Lazy init: 最初の alloc/free 時に自動初期化（thread-safe）

**設計**:
- Lazy init パターン（ENV control と同様）
- ring_cache_pop/push 内で slots == NULL チェック → ring_cache_init() 呼び出し
- Include 構造: ファイルトップレベルに #include 追加（関数内 include 禁止）

**Makefile 修正**:
- TINY_BENCH_OBJS_BASE に core/front/tiny_ring_cache.o 追加
- Link エラー修正: 4箇所の object list に追加

**動作確認**:
- Ring OFF (default): 83K ops/s (1K iterations) ✅
- Ring ON (HAKMEM_TINY_HOT_RING_ENABLE=1): 78K ops/s ✅
- クラッシュなし、正常動作確認

**次のステップ**: Phase 21-1-C (Refill/Cascade 実装)

core/front/tiny_ring_cache.h

@@ -130,6 +130,14 @@ static inline int ring_cascade_enabled(void) {
     return g_enable;
 }
 
+// ============================================================================
+// Init/Shutdown Forward Declarations (needed by pop/push)
+// ============================================================================
+
+void ring_cache_init(void);
+void ring_cache_shutdown(void);
+void ring_cache_print_stats(void);
+
 // ============================================================================
 // Ultra-Fast Pop/Push (1-2 instructions)
 // ============================================================================
@@ -137,8 +145,19 @@ static inline int ring_cascade_enabled(void) {
 // Pop from ring (alloc fast path)
 // Returns: BASE pointer (caller must convert to USER with +1)
 static inline void* ring_cache_pop(int class_idx) {
+    // Fast path: Ring disabled or wrong class → return NULL immediately
+    if (__builtin_expect(!ring_cache_enabled(), 0)) return NULL;
+    if (__builtin_expect(class_idx != 2 && class_idx != 3, 0)) return NULL;
+
     TinyRingCache* ring = (class_idx == 2) ? &g_ring_cache_c2 : &g_ring_cache_c3;
 
+    // Lazy init check (once per thread)
+    if (__builtin_expect(ring->slots == NULL, 0)) {
+        ring_cache_init();  // First call in this thread
+        // Re-check after init (may fail if allocation failed)
+        if (ring->slots == NULL) return NULL;
+    }
+
     // Empty check
     if (__builtin_expect(ring->head == ring->tail, 0)) {
         return NULL;  // Empty
@@ -155,8 +174,19 @@ static inline void* ring_cache_pop(int class_idx) {
 // Input: BASE pointer (caller must pass BASE, not USER)
 // Returns: 1=SUCCESS, 0=FULL
 static inline int ring_cache_push(int class_idx, void* base) {
+    // Fast path: Ring disabled or wrong class → return 0 (not handled)
+    if (__builtin_expect(!ring_cache_enabled(), 0)) return 0;
+    if (__builtin_expect(class_idx != 2 && class_idx != 3, 0)) return 0;
+
     TinyRingCache* ring = (class_idx == 2) ? &g_ring_cache_c2 : &g_ring_cache_c3;
 
+    // Lazy init check (once per thread)
+    if (__builtin_expect(ring->slots == NULL, 0)) {
+        ring_cache_init();  // First call in this thread
+        // Re-check after init (may fail if allocation failed)
+        if (ring->slots == NULL) return 0;
+    }
+
     uint16_t next_tail = (ring->tail + 1) & ring->mask;
 
     // Full check (leave 1 slot empty to distinguish full/empty)
@@ -178,12 +208,4 @@ static inline int ring_cache_push(int class_idx, void* base) {
 // Forward declaration (defined in tiny_ring_cache.c)
 int ring_refill_from_sll(int class_idx, int target_count);
 
-// ============================================================================
-// Init/Shutdown (called from hakmem_tiny.c)
-// ============================================================================
-
-void ring_cache_init(void);
-void ring_cache_shutdown(void);
-void ring_cache_print_stats(void);
-
 #endif // HAK_FRONT_TINY_RING_CACHE_H