a78224123e
Root Cause: 1. C7 stride was 1024B, unable to serve 1024B user requests (need 1025B with header) 2. New SuperSlabs start with meta->class_idx=0 (mmap zero-init) 3. superslab_init_slab() only sets class_idx if meta->class_idx==255 4. Multiple code paths used conditional assignment (if class_idx==255), leaving C7 slabs with class_idx=0 5. This caused C7 blocks to be misidentified as C0, leading to HDR_META_MISMATCH errors Changes: 1. Upgrade C7 stride: 1024B → 2048B (can now serve 1024B requests) 2. Update blocks_per_slab[7]: 64 → 32 (2048B stride / 64KB slab) 3. Update size-to-class LUT: entries 513-2048 now map to C7 4. Fix superslab_init_slab() fail-safe: only reinitialize if class_idx==255 (not 0) 5. Add explicit class_idx assignment in 6 initialization paths: - tiny_superslab_alloc.inc.h: superslab_refill() after init - hakmem_tiny_superslab.c: backend_shared after init (main path) - ss_unified_backend_box.c: unconditional assignment - ss_legacy_backend_box.c: explicit assignment - superslab_expansion_box.c: explicit assignment - ss_allocation_box.c: fail-safe condition fix Fix P0 refill bug: - Update obsolete array access after Phase 3d-B TLS SLL unification - g_tls_sll_head[cls] → g_tls_sll[cls].head - g_tls_sll_count[cls] → g_tls_sll[cls].count Results: - HDR_META_MISMATCH: eliminated (0 errors in 100K iterations) - 1024B allocations now routed to C7 (Tiny fast path) - NXT_MISALIGN warnings remain (legacy 1024B SuperSlabs, separate issue) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
212 lines
8.4 KiB
C++
212 lines
8.4 KiB
C++
// hakmem_tiny_config_box.inc
|
||
// Box: Tiny allocator configuration, debug counters, and return helpers.
|
||
// Extracted from hakmem_tiny.c to reduce file size and isolate config logic.
|
||
|
||
// ============================================================================
|
||
// Size class table (Box 3 dependency)
|
||
// ============================================================================
|
||
// Phase E1-CORRECT: ALL classes have 1-byte header
|
||
// These sizes represent TOTAL BLOCK SIZE (stride) = [Header 1B][Data N-1B]
|
||
// Usable data = stride - 1 (implicit)
|
||
const size_t g_tiny_class_sizes[TINY_NUM_CLASSES] = {
|
||
8, // Class 0: 8B total = [Header 1B][Data 7B]
|
||
16, // Class 1: 16B total = [Header 1B][Data 15B]
|
||
32, // Class 2: 32B total = [Header 1B][Data 31B]
|
||
64, // Class 3: 64B total = [Header 1B][Data 63B]
|
||
128, // Class 4: 128B total = [Header 1B][Data 127B]
|
||
256, // Class 5: 256B total = [Header 1B][Data 255B]
|
||
512, // Class 6: 512B total = [Header 1B][Data 511B]
|
||
2048 // Class 7: 2048B total = [Header 1B][Data 2047B] (upgraded for 1024B requests)
|
||
};
|
||
|
||
// ============================================================================
|
||
// Phase 16: Dynamic Tiny Max Size (ENV: HAKMEM_TINY_MAX_CLASS)
|
||
// Phase 17-1: Auto-adjust when Small-Mid enabled
|
||
// ============================================================================
|
||
|
||
// Forward declaration for Small-Mid check
|
||
extern bool smallmid_is_enabled(void);
|
||
|
||
// Get dynamic max size for Tiny allocator based on ENV configuration
|
||
// Default: 1023B (C0-C7), can be reduced to 255B (C0-C5)
|
||
// Phase 17-1: Auto-reduces to 255B when Small-Mid is enabled
|
||
size_t tiny_get_max_size(void) {
|
||
static int g_max_class = -1;
|
||
if (__builtin_expect(g_max_class == -1, 0)) {
|
||
const char* env = getenv("HAKMEM_TINY_MAX_CLASS");
|
||
if (env && *env) {
|
||
int max_class = atoi(env);
|
||
if (max_class >= 0 && max_class < TINY_NUM_CLASSES) {
|
||
g_max_class = max_class;
|
||
} else {
|
||
g_max_class = 7; // Default: all classes (C0-C7)
|
||
}
|
||
} else {
|
||
g_max_class = 7; // Default: all classes
|
||
}
|
||
}
|
||
|
||
// Phase 17-1: Auto-adjust when Small-Mid enabled
|
||
// Small-Mid handles 256B-1KB, so Tiny should only handle 0-255B
|
||
int effective_class = g_max_class;
|
||
if (smallmid_is_enabled() && effective_class > 5) {
|
||
effective_class = 5; // Limit to C0-C5 (0-255B)
|
||
}
|
||
|
||
// Map class to max usable size (stride - 1)
|
||
// C0=8B, C1=16B, C2=32B, C3=64B, C4=128B, C5=256B, C6=512B, C7=2048B
|
||
static const size_t class_to_max_size[TINY_NUM_CLASSES] = {
|
||
7, 15, 31, 63, 127, 255, 511, 2047
|
||
};
|
||
return class_to_max_size[effective_class];
|
||
}
|
||
|
||
// ============================================================================
|
||
// PRIORITY 1-4: Integrity Check Counters
|
||
// ============================================================================
|
||
_Atomic uint64_t g_integrity_check_class_bounds = 0;
|
||
_Atomic uint64_t g_integrity_check_freelist = 0;
|
||
_Atomic uint64_t g_integrity_check_canary = 0;
|
||
_Atomic uint64_t g_integrity_check_header = 0;
|
||
|
||
// Build-time gate for debug counters (path/ultra). Default OFF.
|
||
#ifndef HAKMEM_DEBUG_COUNTERS
|
||
#define HAKMEM_DEBUG_COUNTERS 0
|
||
#endif
|
||
|
||
int g_debug_fast0 = 0;
|
||
int g_debug_remote_guard = 0;
|
||
int g_remote_force_notify = 0;
|
||
// Tiny free safety (debug)
|
||
int g_tiny_safe_free = 0; // Default OFF for performance; env: HAKMEM_SAFE_FREE=1 でON
|
||
int g_tiny_safe_free_strict = 0; // env: HAKMEM_SAFE_FREE_STRICT=1
|
||
int g_tiny_force_remote = 0; // env: HAKMEM_TINY_FORCE_REMOTE=1
|
||
|
||
// Build-time gate: Minimal Tiny front (bench-only)
|
||
|
||
static inline int superslab_trace_enabled(void) {
|
||
static int g_ss_trace_flag = -1;
|
||
if (__builtin_expect(g_ss_trace_flag == -1, 0)) {
|
||
const char* tr = getenv("HAKMEM_TINY_SUPERSLAB_TRACE");
|
||
g_ss_trace_flag = (tr && atoi(tr) != 0) ? 1 : 0;
|
||
}
|
||
return g_ss_trace_flag;
|
||
}
|
||
// When enabled, physically excludes optional front tiers from the hot path
|
||
// (UltraFront/Quick/Frontend/HotMag/SS-try/BumpShadow), leaving:
|
||
// SLL → TLS Magazine → SuperSlab → (remaining slow path)
|
||
#ifndef HAKMEM_TINY_MINIMAL_FRONT
|
||
#define HAKMEM_TINY_MINIMAL_FRONT 1
|
||
#endif
|
||
// Strict front: compile-out optional front tiers but keep baseline structure intact
|
||
#ifndef HAKMEM_TINY_STRICT_FRONT
|
||
#define HAKMEM_TINY_STRICT_FRONT 0
|
||
#endif
|
||
|
||
// Bench-only fast path knobs (defaults)
|
||
#ifndef HAKMEM_TINY_BENCH_REFILL
|
||
#define HAKMEM_TINY_BENCH_REFILL 8
|
||
#endif
|
||
// Optional per-class overrides (bench-only)
|
||
#ifndef HAKMEM_TINY_BENCH_REFILL8
|
||
#define HAKMEM_TINY_BENCH_REFILL8 HAKMEM_TINY_BENCH_REFILL
|
||
#endif
|
||
#ifndef HAKMEM_TINY_BENCH_REFILL16
|
||
#define HAKMEM_TINY_BENCH_REFILL16 HAKMEM_TINY_BENCH_REFILL
|
||
#endif
|
||
#ifndef HAKMEM_TINY_BENCH_REFILL32
|
||
#define HAKMEM_TINY_BENCH_REFILL32 HAKMEM_TINY_BENCH_REFILL
|
||
#endif
|
||
#ifndef HAKMEM_TINY_BENCH_REFILL64
|
||
#define HAKMEM_TINY_BENCH_REFILL64 HAKMEM_TINY_BENCH_REFILL
|
||
#endif
|
||
|
||
// Bench-only warmup amounts (pre-fill TLS SLL on first alloc per class)
|
||
#ifndef HAKMEM_TINY_BENCH_WARMUP8
|
||
#define HAKMEM_TINY_BENCH_WARMUP8 64
|
||
#endif
|
||
#ifndef HAKMEM_TINY_BENCH_WARMUP16
|
||
#define HAKMEM_TINY_BENCH_WARMUP16 96
|
||
#endif
|
||
#ifndef HAKMEM_TINY_BENCH_WARMUP32
|
||
#define HAKMEM_TINY_BENCH_WARMUP32 160
|
||
#endif
|
||
#ifndef HAKMEM_TINY_BENCH_WARMUP64
|
||
#define HAKMEM_TINY_BENCH_WARMUP64 192
|
||
#endif
|
||
|
||
#ifdef HAKMEM_TINY_BENCH_FASTPATH
|
||
static __thread unsigned char g_tls_bench_warm_done[4];
|
||
#endif
|
||
|
||
#if HAKMEM_DEBUG_COUNTERS
|
||
#define HAK_PATHDBG_INC(arr, idx) do { if (g_path_debug_enabled) { (arr)[(idx)]++; } } while(0)
|
||
#define HAK_ULTRADBG_INC(arr, idx) do { (arr)[(idx)]++; } while(0)
|
||
#else
|
||
#define HAK_PATHDBG_INC(arr, idx) do { (void)(idx); } while(0)
|
||
#define HAK_ULTRADBG_INC(arr, idx) do { (void)(idx); } while(0)
|
||
#endif
|
||
// Simple scalar debug increment (no-op when HAKMEM_DEBUG_COUNTERS=0)
|
||
#if HAKMEM_DEBUG_COUNTERS
|
||
#define HAK_DBG_INC(var) do { (var)++; } while(0)
|
||
#else
|
||
#define HAK_DBG_INC(var) do { (void)0; } while(0)
|
||
#endif
|
||
// Return helper: record tiny alloc stat (guarded) then return pointer
|
||
static inline void tiny_debug_track_alloc_ret(int cls, void* ptr);
|
||
|
||
// ========== HAK_RET_ALLOC: Single Definition Point ==========
|
||
// Choose implementation based on HAKMEM_TINY_HEADER_CLASSIDX
|
||
// - Phase 7 enabled: Write header and return user pointer
|
||
// - Phase 7 disabled: Legacy behavior (stats + route + return)
|
||
|
||
#if HAKMEM_TINY_HEADER_CLASSIDX
|
||
#if HAKMEM_BUILD_RELEASE
|
||
// Phase E1-CORRECT: ALL classes have 1-byte headers (including C7)
|
||
// Ultra-fast inline macro (3-4 instructions)
|
||
#define HAK_RET_ALLOC(cls, base_ptr) do { \
|
||
*(uint8_t*)(base_ptr) = HEADER_MAGIC | ((cls) & HEADER_CLASS_MASK); \
|
||
return (void*)((uint8_t*)(base_ptr) + 1); \
|
||
} while(0)
|
||
#else
|
||
// Debug: Keep full validation via tiny_region_id_write_header()
|
||
#define HAK_RET_ALLOC(cls, ptr) return tiny_region_id_write_header((ptr), (cls))
|
||
#endif
|
||
#else
|
||
// Legacy: Stats and routing before return
|
||
#ifdef HAKMEM_ENABLE_STATS
|
||
// Optional: sampling（ビルド時に有効化）。ホットパスは直接インライン呼び出し（間接分岐なし）。
|
||
#ifdef HAKMEM_TINY_STAT_SAMPLING
|
||
static __thread unsigned g_tls_stat_accum_alloc[TINY_NUM_CLASSES];
|
||
static int g_stat_rate_lg = 0; // 0=毎回、それ以外=2^lgごと
|
||
static inline __attribute__((always_inline)) void hkm_stat_alloc(int cls) {
|
||
if (__builtin_expect(g_stat_rate_lg == 0, 1)) { stats_record_alloc(cls); return; }
|
||
unsigned m = (1u << g_stat_rate_lg) - 1u;
|
||
if (((++g_tls_stat_accum_alloc[cls]) & m) == 0u) stats_record_alloc(cls);
|
||
}
|
||
#else
|
||
static inline __attribute__((always_inline)) void hkm_stat_alloc(int cls) { stats_record_alloc(cls); }
|
||
#endif
|
||
#define HAK_RET_ALLOC(cls, ptr) do { \
|
||
tiny_debug_track_alloc_ret((cls), (ptr)); \
|
||
hkm_stat_alloc((cls)); \
|
||
ROUTE_COMMIT((cls), 0x7F); \
|
||
return (ptr); \
|
||
} while(0)
|
||
#else
|
||
#define HAK_RET_ALLOC(cls, ptr) do { \
|
||
tiny_debug_track_alloc_ret((cls), (ptr)); \
|
||
ROUTE_COMMIT((cls), 0x7F); \
|
||
return (ptr); \
|
||
} while(0)
|
||
#endif
|
||
#endif // HAKMEM_TINY_HEADER_CLASSIDX
|
||
|
||
// Free-side stats: compile-time zero when stats disabled
|
||
#ifdef HAKMEM_ENABLE_STATS
|
||
#define HAK_STAT_FREE(cls) do { stats_record_free((cls)); } while(0)
|
||
#else
|
||
#define HAK_STAT_FREE(cls) do { } while(0)
|
||
#endif
|
||
|