hakmem/core/front/tiny_heap_v2.h

// tiny_heap_v2.h - Tiny per-thread heap (experimental Box)
// Purpose:
//   - Provide a very simple per-thread front for tiny allocations.
//   - Currently targets small classes (C0–C3) and is gated by ENV:
//       HAKMEM_TINY_HEAP_V2=1
//   - Backend remains existing FastCache + Superslab refill.
//
// Design (first pass):
//   - Per-thread, per-class small magazine (L0) in front of FastCache.
//   - On alloc:
//       1) Pop from magazine.
//       2) If empty, refill magazine from FastCache (and backend via tiny_alloc_fast_refill).
//   - On free: still goes through existing free path (hak_tiny_free_fast_v2),
//     which ultimately feeds TLS SLL / drain / Superslab.
//
// This Box is intentionally minimal; performance tuning (sizes, class set)
// is left for later phases.

#ifndef HAK_FRONT_TINY_HEAP_V2_H
#define HAK_FRONT_TINY_HEAP_V2_H

#include "../hakmem_tiny.h"

// Phase 13-B: Magazine capacity (same as Phase 13-A)
#ifndef TINY_HEAP_V2_MAG_CAP
#define TINY_HEAP_V2_MAG_CAP 16
#endif

// TinyHeapV2 Magazine (per-thread, per-class)
typedef struct {
    void* items[TINY_HEAP_V2_MAG_CAP];
    int   top;
} TinyHeapV2Mag;

// TinyHeapV2 Statistics (per-thread, per-class)
typedef struct {
    uint64_t alloc_calls;
    uint64_t mag_hits;
    uint64_t refill_calls;
    uint64_t refill_blocks;
    uint64_t backend_oom;
} TinyHeapV2Stats;

// External TLS variables (defined in hakmem_tiny.c)
extern __thread TinyHeapV2Mag g_tiny_heap_v2_mag[TINY_NUM_CLASSES];
extern __thread TinyHeapV2Stats g_tiny_heap_v2_stats[TINY_NUM_CLASSES];

// Enable flag (cached)
static inline int tiny_heap_v2_enabled(void) {
    static int g_enable = -1;
    static int g_first_call = 1;
    if (__builtin_expect(g_enable == -1, 0)) {
        const char* e = getenv("HAKMEM_TINY_HEAP_V2");
        g_enable = (e && *e && *e != '0') ? 1 : 0;
        fprintf(stderr, "[HeapV2-INIT] tiny_heap_v2_enabled() called: ENV='%s' → %d\n",
                e ? e : "(null)", g_enable);
        fflush(stderr);
    }
    if (g_first_call && g_enable) {
        fprintf(stderr, "[HeapV2-FIRST] Returning enabled=%d\n", g_enable);
        fflush(stderr);
        g_first_call = 0;
    }
    return g_enable;
}

// Class-specific enable mask (cached)
// ENV: HAKMEM_TINY_HEAP_V2_CLASS_MASK (bitmask: bit 0=C0, bit 1=C1, bit 2=C2, bit 3=C3)
// Default: 0xF (all classes C0-C3 enabled)
// Example: 0x2 = C1 only, 0x8 = C3 only, 0x6 = C1+C2
static inline int tiny_heap_v2_class_enabled(int class_idx) {
    static int g_class_mask = -1;
    if (__builtin_expect(g_class_mask == -1, 0)) {
        const char* e = getenv("HAKMEM_TINY_HEAP_V2_CLASS_MASK");
        if (e && *e) {
            // Parse hex or decimal
            char* endptr;
            long val = strtol(e, &endptr, 0);  // 0 = auto-detect base (0x for hex, else decimal)
            g_class_mask = (int)val;
        } else {
            g_class_mask = 0xF;  // Default: C0-C3 all enabled
        }
    }

    if (class_idx < 0 || class_idx >= 8) return 0;
    return (g_class_mask & (1 << class_idx)) != 0;
}

// Leftover mode flag (cached)
// ENV: HAKMEM_TINY_HEAP_V2_LEFTOVER_MODE
// - 0 (default): L0 gets blocks first ("stealing" design, +18% @ 32B)
// - 1: L1 primary owner, L0 gets leftovers ("leftover" design, Box-clean but -5% @ 16B)
//
// Decision (Phase 13-B): Default to Mode 0 (Stealing) for performance
// Rationale (ChatGPT analysis):
//   - Learning layer primarily observes Superslab/Pool statistics
//   - L0 stealing doesn't corrupt Superslab carving/drain signals
//   - If needed, add TinyHeapV2 hit/miss counters to learning layer later
//   - Performance gain (+18% @ 32B) justifies less-strict Box boundary
static inline int tiny_heap_v2_leftover_mode(void) {
    static int g_leftover_mode = -1;
    if (__builtin_expect(g_leftover_mode == -1, 0)) {
        const char* e = getenv("HAKMEM_TINY_HEAP_V2_LEFTOVER_MODE");
        g_leftover_mode = (e && *e && *e != '0') ? 1 : 0;
    }
    return g_leftover_mode;
}

// NOTE: This header MUST be included AFTER tiny_alloc_fast.inc.h!
// It uses fastcache_pop, tiny_alloc_fast_refill, hak_tiny_size_to_class which are
// static inline functions defined in tiny_alloc_fast.inc.h and related headers.

// Phase 13-A Step 1: NO REFILL (avoid circular dependency)
// TinyHeapV2 is a "lucky hit" L0 cache that doesn't refill itself.
// Refill will come from existing front layers later (outside TinyHeapV2).
// This function is currently a no-op stub for future use.
static inline int tiny_heap_v2_refill_mag(int class_idx) {
    (void)class_idx;
    // NO-OP: Do not refill to avoid circular dependency with FastCache
    return 0;
}

// Phase 13-A Step 2: Try to push a block into TinyHeapV2 magazine
// Called from free path to supply magazine with "leftover" blocks.
// Returns: 1 if pushed successfully, 0 if magazine is full
static inline int tiny_heap_v2_try_push(int class_idx, void* base) {
    // 1. Check if class is enabled
    if (class_idx < 0 || class_idx > 3) return 0;
    if (!tiny_heap_v2_class_enabled(class_idx)) return 0;

    TinyHeapV2Mag* mag = &g_tiny_heap_v2_mag[class_idx];

    // 2. Check if magazine has room
    if (mag->top >= TINY_HEAP_V2_MAG_CAP) {
        return 0;  // Magazine full
    }

    // 3. Push BASE pointer into magazine
    mag->items[mag->top++] = base;

    // DEBUG: Log push events
    static int g_push_dbg = -1;
    if (g_push_dbg == -1) {
        const char* e = getenv("HAKMEM_TINY_HEAP_V2_DEBUG");
        g_push_dbg = (e && *e && *e != '0') ? 1 : 0;
    }
    if (g_push_dbg) {
        static __thread int g_push_count[TINY_NUM_CLASSES] = {0};
        if (g_push_count[class_idx] < 5) {
            fprintf(stderr, "[HeapV2-PUSH] C%d push #%d, base=%p, mag->top=%d\n",
                    class_idx, g_push_count[class_idx]++, base, mag->top);
        }
    }

    return 1;  // Success
}

// Tiny heap v2 alloc – returns BASE pointer or NULL.
// Phase 13-A Step 1: Minimal "lucky hit" L0 cache (NO REFILL)
// Strategy: Pop from magazine if available, else return NULL immediately.
// Caller is responsible for header write via HAK_RET_ALLOC (BASE → USER conversion).
// Contract:
//   - Only handles class 0-3 (8-64B) based on CLASS_MASK
//   - Returns BASE pointer (not USER pointer!)
//   - Returns NULL if magazine empty (caller falls back to existing path)
//
// PERFORMANCE FIX: Accept class_idx as parameter to avoid redundant size→class conversion
static inline void* tiny_heap_v2_alloc_by_class(int class_idx) {
    // FAST PATH: Caller already validated class_idx (0-3), skip redundant checks

    #if !HAKMEM_BUILD_RELEASE
    // Debug: Class-specific enable mask (only in debug builds)
    if (__builtin_expect(!tiny_heap_v2_class_enabled(class_idx), 0)) {
        return NULL;  // Class disabled via HAKMEM_TINY_HEAP_V2_CLASS_MASK
    }
    #endif

    TinyHeapV2Mag* mag = &g_tiny_heap_v2_mag[class_idx];

    // Pop from magazine if available (lucky hit!)
    if (__builtin_expect(mag->top > 0, 1)) {  // Expect HIT (likely, 99% hit rate)
        g_tiny_heap_v2_stats[class_idx].alloc_calls++;
        g_tiny_heap_v2_stats[class_idx].mag_hits++;
        void* base = mag->items[--mag->top];
        return base;  // BASE pointer (caller will convert to USER)
    }

    // Magazine empty: return NULL immediately (NO REFILL)
    return NULL;
}

// Print statistics (called at program exit if HAKMEM_TINY_HEAP_V2_STATS=1)
// Declaration only (implementation in hakmem_tiny.c for external linkage)
void tiny_heap_v2_print_stats(void);

#endif // HAK_FRONT_TINY_HEAP_V2_H