hakmem/core/hakmem_tiny_superslab.h

// hakmem_tiny_superslab.h - SuperSlab allocator for Tiny Pool (Phase 6.22)
// Purpose: mimalloc-inspired 2MB aligned slab allocation for fast pointer→slab lookup
// License: MIT
// Date: 2025-10-24
// Phase 6-2.8: Refactored into modular headers (types, inline)

#ifndef HAKMEM_TINY_SUPERSLAB_H
#define HAKMEM_TINY_SUPERSLAB_H

#include <stdint.h>
#include <stddef.h>
#include <stdbool.h>
#include <stdatomic.h>
#include <stdlib.h>
#include <time.h>  // Phase 8.3: For clock_gettime() in hak_now_ns()
#include <signal.h>
#include <stdio.h>  // For fprintf() debugging
#include <pthread.h>

// Phase 6-2.8: Modular headers (types, inline functions)
#include "superslab/superslab_types.h"
#include "superslab/superslab_inline.h"

// Legacy includes (for backward compatibility)
#include "tiny_debug_ring.h"
#include "tiny_remote.h"
#include "hakmem_tiny_superslab_constants.h"  // Phase 6-2.5: Centralized layout constants
#include "hakmem_build_flags.h"

// Debug instrumentation flags (defined in hakmem_tiny.c)
extern int g_debug_remote_guard;
extern int g_tiny_safe_free_strict;
extern _Atomic uint64_t g_ss_active_dec_calls;

uint32_t tiny_remote_drain_threshold(void);

// Monotonic clock in nanoseconds (header inline to avoid TU dependencies)
static inline uint64_t hak_now_ns(void) {
    struct timespec ts;
    clock_gettime(CLOCK_MONOTONIC, &ts);
    return (uint64_t)ts.tv_sec * 1000000000ull + (uint64_t)ts.tv_nsec;
}

// ============================================================================
// Tiny block stride helper (Phase 7 header-aware)
// ============================================================================
// Returns the effective per-block stride used for linear carving within slabs.
// When header-based class indexing is enabled, classes 0-6 reserve an extra
// byte per block for the header. Class 7 (1024B) remains headerless by design.
static inline size_t tiny_block_stride_for_class(int class_idx) {
    // Local size table (avoid extern dependency for inline function)
    // CRITICAL: C7 upgraded from 1024B to 2048B stride (Phase C7-Upgrade)
    static const size_t class_sizes[8] = {8, 16, 32, 64, 128, 256, 512, 2048};
    size_t bs = class_sizes[class_idx];
#if HAKMEM_TINY_HEADER_CLASSIDX
    // Phase E1-CORRECT: ALL classes have 1-byte header
    bs += 1;
#endif
#if !HAKMEM_BUILD_RELEASE
    // One-shot debug: confirm stride behavior at runtime for class 0
    static _Atomic int g_stride_dbg = 0;
    if (class_idx == 0) {
        int exp = 0;
        if (atomic_compare_exchange_strong(&g_stride_dbg, &exp, 1)) {
            fprintf(stderr, "[STRIDE_DBG] HEADER_CLASSIDX=%d class=%d stride=%zu\n",
                    (int)HAKMEM_TINY_HEADER_CLASSIDX, class_idx, bs);
        }
    }
#endif
    return bs;
}

/*
 * Phase 12 (Shared SuperSlab Pool: Stage A - Minimal Box API wrapper)
 *
 * Goals at this stage:
 *  - Introduce a single, well-defined Box/Phase12 API that the tiny front-end
 *    (slow path / refill) uses to obtain blocks from the SuperSlab layer.
 *  - Keep existing per-class SuperslabHead/g_superslab_heads and
 *    superslab_allocate() implementation intact as the internal backend.
 *  - Do NOT change behavior or allocation strategy yet; we only:
 *      - centralize the "allocate from superslab for tiny class" logic, and
 *      - isolate callers from internal Superslab details.
 *
 * This allows:
 *  - hak_tiny_alloc_slow() / refill code to stop depending on legacy internals,
 *    so later commits can switch the backend to the shared SuperSlab pool
 *    (hakmem_shared_pool.{h,c}) without touching front-end call sites.
 *
 * Stage A API (introduced here):
 *  - void* hak_tiny_alloc_superslab_box(int class_idx);
 *      - Returns a single tiny block for given class_idx, or NULL on failure.
 *      - BOX CONTRACT:
 *          - Callers pass validated class_idx (0 <= idx < TINY_NUM_CLASSES).
 *          - Returns a BASE pointer already suitable for Box/TLS-SLL/header rules.
 *          - No direct access to SuperSlab/TinySlabMeta from callers.
 *
 * NOTE:
 *  - At this stage, hak_tiny_alloc_superslab_box() is a thin inline wrapper
 *    that forwards to the existing per-class SuperslabHead backend.
 *  - Later Stage B/C patches may switch its implementation to shared_pool_*()
 *    without changing any callers.
 */
void* hak_tiny_alloc_superslab_box(int class_idx);

// Initialize a slab within SuperSlab
void superslab_init_slab(SuperSlab* ss, int slab_idx, size_t block_size, uint32_t owner_tid);

// Mark a slab as active
void superslab_activate_slab(SuperSlab* ss, int slab_idx);

// Mark a slab as inactive
void superslab_deactivate_slab(SuperSlab* ss, int slab_idx);

// Find first free slab index (-1 if none)
int superslab_find_free_slab(SuperSlab* ss);

// Free a SuperSlab (unregister and return to pool or munmap)
void superslab_free(SuperSlab* ss);

// Statistics
void superslab_print_stats(SuperSlab* ss);

// Phase 8.3: ACE statistics
void superslab_ace_print_stats(void);

// ============================================================================
// Phase 8.3: ACE (Adaptive Cache Engine) - SuperSlab adaptive sizing
// ============================================================================

// ACE tick function (called periodically, ~150ms interval)
// Observes metrics and decides promotion (1MB→2MB) or demotion (2MB→1MB)
void hak_tiny_superslab_ace_tick(int class_idx, uint64_t now_ns);

// Phase 8.4: ACE Observer (called from Learner thread - zero hot-path overhead)
void hak_tiny_superslab_ace_observe_all(void);

// ============================================================================
// Partial SuperSlab adopt/publish (per-class single-slot)
// ============================================================================

// Publish a SuperSlab with available freelist for other threads to adopt.
void ss_partial_publish(int class_idx, SuperSlab* ss);

// Adopt published SuperSlab for the class (returns NULL if none).
SuperSlab* ss_partial_adopt(int class_idx);

// ============================================================================
// SuperSlab adopt gate (publish/adopt wiring helper)
// ============================================================================

// Environment-aware switch that keeps free/alloc sides in sync. Default:
//   - Disabled until cross-thread free is observed.
//   - `HAKMEM_TINY_SS_ADOPT=1` forces ON, `=0` forces OFF.
int tiny_adopt_gate_should_publish(void);
int tiny_adopt_gate_should_adopt(void);
void tiny_adopt_gate_on_remote_seen(int class_idx);

// ============================================================================
// External variable declarations
// ============================================================================

extern _Atomic int g_ss_remote_seen;  // set to 1 on first remote free observed
extern int g_remote_force_notify;

#endif // HAKMEM_TINY_SUPERSLAB_H