Add Page Box layer for C7 class optimization

- Implement tiny_page_box.c/h: per-thread page cache between UC and Shared Pool
- Integrate Page Box into Unified Cache refill path
- Remove legacy SuperSlab implementation (merged into smallmid)
- Add HAKMEM_TINY_PAGE_BOX_CLASSES env var for selective class enabling
- Update bench_random_mixed.c with Page Box statistics

Current status: Implementation safe, no regressions.
Page Box ON/OFF shows minimal difference - pool strategy needs tuning.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

bench_random_mixed.c

@@ -43,9 +43,40 @@ static inline uint32_t xorshift32(uint32_t* s){
 
 int main(int argc, char** argv){
   int cycles = (argc>1)? atoi(argv[1]) : 10000000; // total ops (10M for steady-state measurement)
-  int ws     = (argc>2)? atoi(argv[2]) : 8192;    // working-set slots
+  int ws     = (argc>2)? atoi(argv[2]) : 8192;     // working-set slots
   uint32_t seed = (argc>3)? (uint32_t)strtoul(argv[3],NULL,10) : 1234567u;
 
+  // サイズレンジ（Tiny-only / Non-Tiny-only の比較用）
+  // 既定: 16..1040 bytes（元の挙動と同等）
+  size_t min_size = 16u;
+  size_t max_size = 16u + 0x3FFu; // 16..1040 ≒ 16..1024
+
+  // 優先順位: argv[4]/argv[5] → ENV → 既定
+  if (argc > 4) {
+    long v = atol(argv[4]);
+    if (v > 0) min_size = (size_t)v;
+  } else {
+    const char* e = getenv("HAKMEM_BENCH_MIN_SIZE");
+    if (e && *e) {
+      long v = atol(e);
+      if (v > 0) min_size = (size_t)v;
+    }
+  }
+
+  if (argc > 5) {
+    long v = atol(argv[5]);
+    if (v > 0) max_size = (size_t)v;
+  } else {
+    const char* e = getenv("HAKMEM_BENCH_MAX_SIZE");
+    if (e && *e) {
+      long v = atol(e);
+      if (v > 0) max_size = (size_t)v;
+    }
+  }
+
+  if (min_size < 1) min_size = 1;
+  if (max_size < min_size) max_size = min_size;
+
   if (cycles <= 0) cycles = 1;
   if (ws <= 0) ws = 1024;
 
@@ -79,6 +110,8 @@ int main(int argc, char** argv){
         slots[idx] = NULL;
       } else {
         size_t sz = 16u + (r & 0x3FFu);
+        if (sz < min_size) sz = min_size;
+        if (sz > max_size) sz = max_size;
         void* p = malloc(sz);
         if (p) {
           ((unsigned char*)p)[0] = (unsigned char)r;
@@ -115,7 +148,9 @@ int main(int argc, char** argv){
         slots[idx] = NULL;
         warmup_frees++;
       } else {
-        size_t sz = 16u + (r & 0x3FFu); // 16..1040 bytes
+        size_t sz = 16u + (r & 0x3FFu); // 16..1040 bytes（後段でクランプ）
+        if (sz < min_size) sz = min_size;
+        if (sz > max_size) sz = max_size;
         void* p = malloc(sz);
         if (p) {
           ((unsigned char*)p)[0] = (unsigned char)r;
@@ -151,9 +186,11 @@ int main(int argc, char** argv){
       }
       slots[idx] = NULL;
       frees++;
-    } else {
-      // 16..1024 bytes (power-of-two-ish skew)
-      size_t sz = 16u + (r & 0x3FFu); // 16..1040 (approx 16..1024)
+      } else {
+        // 16..1024 bytes (power-of-two-ish skew, thenクランプ)
+        size_t sz = 16u + (r & 0x3FFu); // 16..1040 (approx 16..1024)
+        if (sz < min_size) sz = min_size;
+        if (sz > max_size) sz = max_size;
       if (0 && i > 28300) {  // DISABLED (Phase 2 perf)
         fprintf(stderr, "[MALLOC] i=%d sz=%zu idx=%d\n", i, sz, idx);
         fflush(stderr);