// superslab_stats.c - Statistics and debugging for SuperSlab allocator
// Purpose: Tracking and reporting allocation statistics
// License: MIT
// Date: 2025-11-28

#include "hakmem_tiny_superslab_internal.h"
#include "box/ss_os_acquire_box.h"
#include <stdbool.h>
#include <stdlib.h>

// ============================================================================
// Global Statistics
// ============================================================================

pthread_mutex_t g_superslab_lock = PTHREAD_MUTEX_INITIALIZER;
uint64_t g_superslabs_allocated = 0;  // Non-static for debugging
uint64_t g_superslabs_freed = 0;      // Phase 7.6: Non-static for test access
uint64_t g_bytes_allocated = 0;  // Non-static for debugging

// Debug counters
_Atomic uint64_t g_ss_active_dec_calls = 0;
_Atomic uint64_t g_hak_tiny_free_calls = 0;
_Atomic uint64_t g_ss_remote_push_calls = 0;
// Free path instrumentation (lightweight, for OOM/route diagnosis)
_Atomic uint64_t g_free_ss_enter = 0;          // hak_tiny_free_superslab() entries
_Atomic uint64_t g_free_local_box_calls = 0;   // same-thread freelist pushes
_Atomic uint64_t g_free_remote_box_calls = 0;  // cross-thread remote pushes
// Per-class counters for gating/metrics (Tiny classes = 8)
uint64_t g_ss_alloc_by_class[8] = {0};
uint64_t g_ss_freed_by_class[8] = {0};

// Global counters for debugging (non-static for external access)
_Atomic uint64_t g_ss_mmap_count = 0;
_Atomic uint64_t g_final_fallback_mmap_count = 0;
_Atomic uint64_t g_ss_os_alloc_calls = 0;
_Atomic uint64_t g_ss_os_free_calls = 0;
_Atomic uint64_t g_ss_os_madvise_calls = 0;
_Atomic uint64_t g_ss_os_madvise_fail_enomem = 0;
_Atomic uint64_t g_ss_os_madvise_fail_other = 0;
_Atomic uint64_t g_ss_os_huge_alloc_calls = 0;
_Atomic uint64_t g_ss_os_huge_fail_calls = 0;
_Atomic bool     g_ss_madvise_disabled = false;

// Superslab/slab observability (Tiny-only; relaxed updates)
_Atomic uint64_t g_ss_live_by_class[8]   = {0};
_Atomic uint64_t g_ss_empty_events[8]    = {0};
_Atomic uint64_t g_slab_live_events[8]   = {0};

// ============================================================================
// Statistics Functions
// ============================================================================

void ss_stats_os_alloc(uint8_t size_class, size_t ss_size) {
    pthread_mutex_lock(&g_superslab_lock);
    g_superslabs_allocated++;
    if (size_class < 8) {
        g_ss_alloc_by_class[size_class]++;
    }
    g_bytes_allocated += ss_size;
    pthread_mutex_unlock(&g_superslab_lock);
}

void ss_stats_cache_reuse(void) {
    pthread_mutex_lock(&g_superslab_lock);
    g_superslabs_reused++;
    pthread_mutex_unlock(&g_superslab_lock);
}

void ss_stats_cache_store(void) {
    pthread_mutex_lock(&g_superslab_lock);
    g_superslabs_cached++;
    pthread_mutex_unlock(&g_superslab_lock);
}

void ss_stats_on_ss_alloc_class(int class_idx) {
    if (class_idx >= 0 && class_idx < 8) {
        atomic_fetch_add_explicit(&g_ss_live_by_class[class_idx], 1, memory_order_relaxed);
    }
}

void ss_stats_on_ss_free_class(int class_idx) {
    if (class_idx >= 0 && class_idx < 8) {
        uint64_t prev = atomic_load_explicit(&g_ss_live_by_class[class_idx], memory_order_relaxed);
        if (prev > 0) {
            atomic_fetch_sub_explicit(&g_ss_live_by_class[class_idx], 1, memory_order_relaxed);
        }
    }
}

void ss_stats_on_ss_scan(int class_idx, int slab_live, int is_empty) {
    if (class_idx < 0 || class_idx >= 8) {
        return;
    }
    if (slab_live > 0) {
        atomic_fetch_add_explicit(&g_slab_live_events[class_idx],
                                  (uint64_t)slab_live,
                                  memory_order_relaxed);
    }
    if (is_empty) {
        atomic_fetch_add_explicit(&g_ss_empty_events[class_idx], 1, memory_order_relaxed);
    }
}

// ============================================================================
// Diagnostics
// ============================================================================

void log_superslab_oom_once(size_t ss_size, size_t alloc_size, int err) {
    (void)ss_size; (void)alloc_size; (void)err;
    static int logged = 0;
    if (logged) return;
    logged = 1;

    // CRITICAL FIX: Increment lock depth FIRST before any LIBC calls
    // fopen/fclose/getrlimit/fprintf all may call malloc internally
    // Must bypass HAKMEM wrapper to avoid header mismatch crash
    extern __thread int g_hakmem_lock_depth;
    g_hakmem_lock_depth++;  // Force wrapper to use __libc_malloc

    struct rlimit rl = {0};
    if (getrlimit(RLIMIT_AS, &rl) != 0) {
        rl.rlim_cur = RLIM_INFINITY;
        rl.rlim_max = RLIM_INFINITY;
    }

    unsigned long vm_size_kb = 0;
    unsigned long vm_rss_kb = 0;
    FILE* status = fopen("/proc/self/status", "r");
    if (status) {
        char line[256];
        while (fgets(line, sizeof(line), status)) {
            if (strncmp(line, "VmSize:", 7) == 0) {
                (void)sscanf(line + 7, "%lu", &vm_size_kb);
            } else if (strncmp(line, "VmRSS:", 6) == 0) {
                (void)sscanf(line + 6, "%lu", &vm_rss_kb);
            }
        }
        fclose(status);
    }
    // CRITICAL FIX: Do NOT decrement lock_depth yet!
    // fprintf() below may call malloc for buffering

    char rl_cur_buf[32];
    char rl_max_buf[32];
    if (rl.rlim_cur == RLIM_INFINITY) {
        strcpy(rl_cur_buf, "inf");
    } else {
        snprintf(rl_cur_buf, sizeof(rl_cur_buf), "%llu", (unsigned long long)rl.rlim_cur);
    }
    if (rl.rlim_max == RLIM_INFINITY) {
        strcpy(rl_max_buf, "inf");
    } else {
        snprintf(rl_max_buf, sizeof(rl_max_buf), "%llu", (unsigned long long)rl.rlim_max);
    }

#if !HAKMEM_BUILD_RELEASE
    fprintf(stderr,
            "[SS OOM] mmap failed: err=%d ss_size=%zu alloc_size=%zu "
            "alloc=%llu freed=%llu bytes=%llu "
            "RLIMIT_AS(cur=%s max=%s) VmSize=%lu kB VmRSS=%lu kB\n",
            err,
            ss_size,
            alloc_size,
            (unsigned long long)g_superslabs_allocated,
            (unsigned long long)g_superslabs_freed,
            (unsigned long long)g_bytes_allocated,
            rl_cur_buf,
            rl_max_buf,
            vm_size_kb,
            vm_rss_kb);
#endif

    g_hakmem_lock_depth--;  // Now safe to restore (all libc calls complete)
}

// ============================================================================
// Statistics / Debugging
// ============================================================================

void superslab_print_stats(SuperSlab* ss) {
    if (!ss || ss->magic != SUPERSLAB_MAGIC) {
        printf("Invalid SuperSlab\n");
        return;
    }

    printf("=== SuperSlab Stats ===\n");
    printf("Address: %p\n", (void*)ss);
    // Phase 12: per-SS size_class removed; classes are per-slab via meta->class_idx.
    printf("Active slabs: %u / %d\n", ss->active_slabs, ss_slabs_capacity(ss));
    printf("Bitmap: 0x%08X\n", ss->slab_bitmap);
    printf("\nPer-slab details:\n");
    for (int i = 0; i < ss_slabs_capacity(ss); i++) {
        if (ss->slab_bitmap & (1u << i)) {
            TinySlabMeta* meta = &ss->slabs[i];
            printf("  Slab %2d: used=%u/%u freelist=%p class=%u owner_tid_low=%u\n",
                   i, meta->used, meta->capacity, meta->freelist,
                   (unsigned)meta->class_idx, (unsigned)meta->owner_tid_low);
        }
    }
    printf("\n");
}

// Global statistics
void superslab_print_global_stats(void) {
    pthread_mutex_lock(&g_superslab_lock);
    printf("=== Global SuperSlab Stats ===\n");
    printf("SuperSlabs allocated: %lu\n", g_superslabs_allocated);
    printf("SuperSlabs freed: %lu\n", g_superslabs_freed);
    printf("SuperSlabs active: %lu\n", g_superslabs_allocated - g_superslabs_freed);
    printf("Total bytes allocated: %lu MB\n", g_bytes_allocated / (1024 * 1024));
    pthread_mutex_unlock(&g_superslab_lock);
}

// ============================================================================ 
// OS call counters (optional, ENV gated)
// ============================================================================ 

static int ss_os_stats_env_enabled(void) {
    static int g = -1;
    if (__builtin_expect(g == -1, 0)) {
        const char* e = getenv("HAKMEM_SS_OS_STATS");
        g = (e && *e && *e != '0') ? 1 : 0;
    }
    return g;
}

static void ss_os_stats_dump(void) __attribute__((destructor, used));
static void ss_os_stats_dump(void) {
    if (!ss_os_stats_env_enabled()) {
        return;
    }
    fprintf(stderr,
            "[SS_OS_STATS] alloc=%llu free=%llu madvise=%llu madvise_enomem=%llu madvise_other=%llu madvise_disabled=%d "
            "mmap_total=%llu fallback_mmap=%llu huge_alloc=%llu huge_fail=%llu\n",
            (unsigned long long)atomic_load_explicit(&g_ss_os_alloc_calls, memory_order_relaxed),
            (unsigned long long)atomic_load_explicit(&g_ss_os_free_calls, memory_order_relaxed),
            (unsigned long long)atomic_load_explicit(&g_ss_os_madvise_calls, memory_order_relaxed),
            (unsigned long long)atomic_load_explicit(&g_ss_os_madvise_fail_enomem, memory_order_relaxed),
            (unsigned long long)atomic_load_explicit(&g_ss_os_madvise_fail_other, memory_order_relaxed),
            atomic_load_explicit(&g_ss_madvise_disabled, memory_order_relaxed) ? 1 : 0,
            (unsigned long long)atomic_load_explicit(&g_ss_mmap_count, memory_order_relaxed),
            (unsigned long long)atomic_load_explicit(&g_final_fallback_mmap_count, memory_order_relaxed),
            (unsigned long long)atomic_load_explicit(&g_ss_os_huge_alloc_calls, memory_order_relaxed),
            (unsigned long long)atomic_load_explicit(&g_ss_os_huge_fail_calls, memory_order_relaxed));
}

void ss_stats_dump_if_requested(void) {
    const char* env = getenv("HAKMEM_SS_STATS_DUMP");
    if (!env || !*env || *env == '0') {
        return;
    }
    fprintf(stderr, "[SS_STATS] class live empty_events slab_live_events\n");
    for (int c = 0; c < 8; c++) {
        uint64_t live = atomic_load_explicit(&g_ss_live_by_class[c], memory_order_relaxed);
        uint64_t empty = atomic_load_explicit(&g_ss_empty_events[c], memory_order_relaxed);
        uint64_t slab_live = atomic_load_explicit(&g_slab_live_events[c], memory_order_relaxed);
        if (live || empty || slab_live) {
            fprintf(stderr, "  C%d: live=%llu empty=%llu slab_live=%llu\n",
                    c,
                    (unsigned long long)live,
                    (unsigned long long)empty,
                    (unsigned long long)slab_live);
        }
    }
}