Optimize C6 heavy and C7 ultra performance analysis with refined design refinements

- Update environment profile presets and visibility analysis
- Enhance small object and tiny segment v4 box implementations
- Refine C7 ultra and C6 heavy allocation strategies
- Add comprehensive performance metrics and design documentation

🤖 Generated with Claude Code

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

core/tiny_c7_ultra.c

@@ -3,11 +3,13 @@
 #include <stddef.h>
 #include <stdint.h>
 #include <stdbool.h>
+#include <string.h>
 #include "box/tiny_c7_ultra_box.h"
 #include "box/smallobject_hotbox_v3_box.h"
 #include "box/tiny_geometry_box.h"
 #include "tiny_region_id.h"
 #include "box/tiny_c7_ultra_segment_box.h"
+#include "box/tiny_front_v3_env_box.h"
 
 static __thread tiny_c7_ultra_tls_t g_tiny_c7_ultra_tls;
 
@@ -19,12 +21,24 @@ static inline void tiny_c7_ultra_clear(tiny_c7_ultra_tls_t* tls) {
     tls->freelist = NULL;
     tls->page_idx = 0;
     tls->page_meta = NULL;
+    tls->headers_initialized = false;
 }
 
 tiny_c7_ultra_tls_t* tiny_c7_ultra_tls_get(void) {
     return &g_tiny_c7_ultra_tls;
 }
 
+// freelist next をヘッダを壊さずに保持する（ヘッダ byte の直後に保存）
+static inline void ultra_store_next(void* base, void* next) {
+    memcpy((uint8_t*)base + 1, &next, sizeof(next));
+}
+
+static inline void* ultra_load_next(void* base) {
+    void* next = NULL;
+    memcpy(&next, (uint8_t*)base + 1, sizeof(next));
+    return next;
+}
+
 // セグメントから C7 ページを 1 枚借りて自前で carve する
 static bool tiny_c7_ultra_lease_page(tiny_c7_ultra_tls_t* tls) {
     tiny_c7_ultra_segment_t* seg = tls->seg;
@@ -40,6 +54,8 @@ static bool tiny_c7_ultra_lease_page(tiny_c7_ultra_tls_t* tls) {
     uint32_t capacity = (uint32_t)(seg->page_size / block_sz);
     if (capacity == 0) return false;
 
+    const bool header_light = tiny_front_v3_c7_ultra_header_light_enabled();
+
     // 空きページを 1 枚だけ拾う（UF-3 では最初の空きを線形探索）
     uint32_t chosen = seg->num_pages;
     for (uint32_t i = 0; i < seg->num_pages; i++) {
@@ -60,7 +76,11 @@ static bool tiny_c7_ultra_lease_page(tiny_c7_ultra_tls_t* tls) {
     void* head = NULL;
     for (int i = (int)capacity - 1; i >= 0; i--) {
         uint8_t* blk = base + ((size_t)i * block_sz);
-        *(void**)blk = head;
+        if (header_light) {
+            // header_light 時は carve で 1 度だけヘッダを書き込む
+            tiny_region_id_write_header(blk, 7);
+        }
+        ultra_store_next(blk, head);
         head = blk;
     }
     if (!head) {
@@ -78,17 +98,19 @@ static bool tiny_c7_ultra_lease_page(tiny_c7_ultra_tls_t* tls) {
     tls->freelist = head;
     tls->page_idx = chosen;
     tls->page_meta = page;
+    tls->headers_initialized = header_light;
     return true;
 }
 
 void* tiny_c7_ultra_alloc(size_t size) {
     (void)size;  // C7 専用のため未使用
     tiny_c7_ultra_tls_t* tls = tiny_c7_ultra_tls_get();
+    const bool header_light = tiny_front_v3_c7_ultra_header_light_enabled();
 
     // 1) freelist hit
     void* p = tls->freelist;
     if (__builtin_expect(p != NULL, 1)) {
-        void* next = *(void**)p;
+        void* next = ultra_load_next(p);
         tls->freelist = next;
         if (tls->page_meta) {
             tls->page_meta->freelist = next;
@@ -99,6 +121,9 @@ void* tiny_c7_ultra_alloc(size_t size) {
         if (tls->used < tls->capacity) {
             tls->used++;
         }
+        if (header_light && tls->headers_initialized) {
+            return (uint8_t*)p + 1;
+        }
         return tiny_region_id_write_header(p, 7);
     }
 
@@ -112,7 +137,7 @@ void* tiny_c7_ultra_alloc(size_t size) {
     if (__builtin_expect(p == NULL, 0)) {
         return so_alloc(7);
     }
-    void* next = *(void**)p;
+    void* next = ultra_load_next(p);
     tls->freelist = next;
     if (tls->page_meta) {
         tls->page_meta->freelist = next;
@@ -123,6 +148,9 @@ void* tiny_c7_ultra_alloc(size_t size) {
     if (tls->used < tls->capacity) {
         tls->used++;
     }
+    if (header_light && tls->headers_initialized) {
+        return (uint8_t*)p + 1;
+    }
     return tiny_region_id_write_header(p, 7);
 }
 
@@ -158,7 +186,7 @@ void tiny_c7_ultra_free(void* ptr) {
         return;
     }
 
-    *(void**)ptr = page->freelist;
+    ultra_store_next(ptr, page->freelist);
     page->freelist = ptr;
     if (page->used > 0) {
         page->used--;