// tiny_unified_cache.h - Phase 23: Unified Frontend Cache (tcache-style)
//
// Goal: Flatten 4-5 layer frontend cascade into single-layer array cache
// Target: +50-100% performance (20.3M → 30-40M ops/s)
//
// Design (Task-sensei analysis):
//   - Replace: Ring → FastCache → SFC → TLS SLL (4 layers, 8-10 cache misses)
//   - With: Single unified array cache per class (1 layer, 2-3 cache misses)
//   - Fallback: Direct SuperSlab refill (skip intermediate layers)
//
// Performance:
//   - Alloc: 2-3 cache misses (TLS access + array access)
//   - Free: 2-3 cache misses (similar to System malloc tcache)
//   - vs Current: 8-10 cache misses → 2-3 cache misses (70% reduction)
//
// ENV Variables:
//   HAKMEM_TINY_UNIFIED_CACHE=1  # Enable Unified cache (default: 0, OFF)
//   HAKMEM_TINY_UNIFIED_C0=128   # C0 cache size (default: 128)
//   ...
//   HAKMEM_TINY_UNIFIED_C7=128   # C7 cache size (default: 128)

#ifndef HAK_FRONT_TINY_UNIFIED_CACHE_H
#define HAK_FRONT_TINY_UNIFIED_CACHE_H

#include <stdint.h>
#include <stdlib.h>
#include <stdio.h>
#include "../hakmem_build_flags.h"
#include "../hakmem_tiny_config.h"  // For TINY_NUM_CLASSES
#include "../box/tiny_front_config_box.h"  // Phase 8-Step1: Config macros

// ============================================================================
// Unified Cache Structure (per class)
// ============================================================================

typedef struct {
    void** slots;      // Dynamic array (allocated at init, power-of-2 size)
    uint16_t head;     // Pop index (consumer)
    uint16_t tail;     // Push index (producer)
    uint16_t capacity; // Cache size (power of 2 for fast modulo: & (capacity-1))
    uint16_t mask;     // Capacity - 1 (for fast modulo)
} TinyUnifiedCache;

// ============================================================================
// External TLS Variables (defined in tiny_unified_cache.c)
// ============================================================================

extern __thread TinyUnifiedCache g_unified_cache[TINY_NUM_CLASSES];

// ============================================================================
// Metrics (Phase 23, optional for debugging)
// ============================================================================

#if !HAKMEM_BUILD_RELEASE
extern __thread uint64_t g_unified_cache_hit[TINY_NUM_CLASSES];    // Alloc hits
extern __thread uint64_t g_unified_cache_miss[TINY_NUM_CLASSES];   // Alloc misses
extern __thread uint64_t g_unified_cache_push[TINY_NUM_CLASSES];   // Free pushes
extern __thread uint64_t g_unified_cache_full[TINY_NUM_CLASSES];   // Free full (fallback to SuperSlab)
#endif

// ============================================================================
// ENV Control (cached, lazy init)
// ============================================================================

// Phase 8-Step1-Fix: Forward declaration only (implementation in .c file)
// Enable flag (default: 0, OFF) - implemented in tiny_unified_cache.c
int unified_cache_enabled(void);

// Per-class capacity (default: Hot_2048 strategy - optimized for 256B workload)
// Phase 23 Capacity Optimization Result: Hot_2048 = 14.63M ops/s (+43% vs baseline)
// Hot classes (C2/C3: 128B/256B) get 2048 slots, others get 64 slots
static inline size_t unified_capacity(int class_idx) {
    static size_t g_cap[TINY_NUM_CLASSES] = {0};
    if (__builtin_expect(g_cap[class_idx] == 0, 0)) {
        char env_name[64];
        snprintf(env_name, sizeof(env_name), "HAKMEM_TINY_UNIFIED_C%d", class_idx);
        const char* e = getenv(env_name);

        // Default: Hot_2048 strategy (C2/C3=2048, others=64)
        size_t default_cap = 64;  // Cold classes
        if (class_idx == 2 || class_idx == 3) {
            default_cap = 2048;  // Hot classes (128B, 256B)
        }

        g_cap[class_idx] = (e && *e) ? (size_t)atoi(e) : default_cap;

        // Round up to power of 2 (for fast modulo)
        if (g_cap[class_idx] < 32) g_cap[class_idx] = 32;
        if (g_cap[class_idx] > 4096) g_cap[class_idx] = 4096;  // Increased limit for Hot_2048

        // Ensure power of 2
        size_t pow2 = 32;
        while (pow2 < g_cap[class_idx]) pow2 *= 2;
        g_cap[class_idx] = pow2;

#if !HAKMEM_BUILD_RELEASE
        fprintf(stderr, "[Unified-INIT] C%d capacity = %zu (power of 2)\n", class_idx, g_cap[class_idx]);
        fflush(stderr);
#endif
    }
    return g_cap[class_idx];
}

// ============================================================================
// Init/Shutdown Forward Declarations
// ============================================================================

void unified_cache_init(void);
void unified_cache_shutdown(void);
void unified_cache_print_stats(void);

// ============================================================================
// Phase 23-D: Self-Contained Refill (Box U1 + Box U2 integration)
// ============================================================================

// Batch refill from SuperSlab (called on cache miss)
// Returns: BASE pointer (first block), or NULL if failed
void* unified_cache_refill(int class_idx);

// ============================================================================
// Ultra-Fast Pop/Push (2-3 cache misses, tcache-style)
// ============================================================================

// Pop from unified cache (alloc fast path)
// Returns: BASE pointer (caller must convert to USER with +1)
static inline void* unified_cache_pop(int class_idx) {
    // Phase 8-Step1: Use config macro for dead code elimination in PGO mode
    // Fast path: Unified cache disabled → return NULL immediately
    #include "../box/tiny_front_config_box.h"
    if (__builtin_expect(!TINY_FRONT_UNIFIED_CACHE_ENABLED, 0)) return NULL;

    TinyUnifiedCache* cache = &g_unified_cache[class_idx];  // 1 cache miss (TLS)

    // Phase 8-Step3: Lazy init check (conditional in PGO mode)
    // PGO builds assume bench_fast_init() prewarmed cache → remove check (-1 branch)
    #if !HAKMEM_TINY_FRONT_PGO
    // Lazy init check (once per thread, per class)
    if (__builtin_expect(cache->slots == NULL, 0)) {
        unified_cache_init();  // First call in this thread
        // Re-check after init (may fail if allocation failed)
        if (cache->slots == NULL) return NULL;
    }
    #endif

    // Empty check
    if (__builtin_expect(cache->head == cache->tail, 0)) {
#if !HAKMEM_BUILD_RELEASE
        g_unified_cache_miss[class_idx]++;
#endif
        return NULL;  // Empty
    }

    // Pop from head (consumer)
    void* base = cache->slots[cache->head];  // 1 cache miss (array access)
    cache->head = (cache->head + 1) & cache->mask;  // Fast modulo (power of 2)

#if !HAKMEM_BUILD_RELEASE
    g_unified_cache_hit[class_idx]++;
#endif

    return base;  // Return BASE pointer (2-3 cache misses total)
}

// Push to unified cache (free fast path)
// Input: BASE pointer (caller must pass BASE, not USER)
// Returns: 1=SUCCESS, 0=FULL
static inline int unified_cache_push(int class_idx, void* base) {
    // Phase 8-Step1: Use config macro for dead code elimination in PGO mode
    // Fast path: Unified cache disabled → return 0 (not handled)
    if (__builtin_expect(!TINY_FRONT_UNIFIED_CACHE_ENABLED, 0)) return 0;

    TinyUnifiedCache* cache = &g_unified_cache[class_idx];  // 1 cache miss (TLS)

    // Phase 8-Step3: Lazy init check (conditional in PGO mode)
    // PGO builds assume bench_fast_init() prewarmed cache → remove check (-1 branch)
    #if !HAKMEM_TINY_FRONT_PGO
    // Lazy init check (once per thread, per class)
    if (__builtin_expect(cache->slots == NULL, 0)) {
        unified_cache_init();  // First call in this thread
        // Re-check after init (may fail if allocation failed)
        if (cache->slots == NULL) return 0;
    }
    #endif

    uint16_t next_tail = (cache->tail + 1) & cache->mask;

    // Full check (leave 1 slot empty to distinguish full/empty)
    if (__builtin_expect(next_tail == cache->head, 0)) {
#if !HAKMEM_BUILD_RELEASE
        g_unified_cache_full[class_idx]++;
#endif
        return 0;  // Full
    }

    // Push to tail (producer)
    cache->slots[cache->tail] = base;  // 1 cache miss (array write)
    cache->tail = next_tail;

#if !HAKMEM_BUILD_RELEASE
    g_unified_cache_push[class_idx]++;
#endif

    return 1;  // SUCCESS (2-3 cache misses total)
}

// ============================================================================
// Phase 23-D: Self-Contained Pop-or-Refill (tcache-style, single-layer)
// ============================================================================

// All-in-one: Pop from cache, or refill from SuperSlab on miss
// Returns: BASE pointer (caller converts to USER), or NULL if failed
// Design: Self-contained, bypasses all other frontend layers (Ring/FC/SFC/SLL)
static inline void* unified_cache_pop_or_refill(int class_idx) {
    // Phase 8-Step1: Use config macro for dead code elimination in PGO mode
    // Fast path: Unified cache disabled → return NULL (caller uses legacy cascade)
    if (__builtin_expect(!TINY_FRONT_UNIFIED_CACHE_ENABLED, 0)) return NULL;

    TinyUnifiedCache* cache = &g_unified_cache[class_idx];  // 1 cache miss (TLS)

    // Phase 8-Step3: Lazy init check (conditional in PGO mode)
    // PGO builds assume bench_fast_init() prewarmed cache → remove check (-1 branch)
    #if !HAKMEM_TINY_FRONT_PGO
    // Lazy init check (once per thread, per class)
    if (__builtin_expect(cache->slots == NULL, 0)) {
        unified_cache_init();
        if (cache->slots == NULL) return NULL;
    }
    #endif

    // Try pop from cache (fast path)
    if (__builtin_expect(cache->head != cache->tail, 1)) {
        void* base = cache->slots[cache->head];  // 1 cache miss (array access)
        cache->head = (cache->head + 1) & cache->mask;
#if !HAKMEM_BUILD_RELEASE
        g_unified_cache_hit[class_idx]++;
#endif
        return base;  // Hit! (2-3 cache misses total)
    }

    // Cache miss → Batch refill from SuperSlab
#if !HAKMEM_BUILD_RELEASE
    g_unified_cache_miss[class_idx]++;
#endif
    return unified_cache_refill(class_idx);  // Refill + return first block
}

#endif // HAK_FRONT_TINY_UNIFIED_CACHE_H