// tiny_ultra_tls_box.c - Phase TLS-UNIFY-2a + TLS-UNIFY-3: Unified ULTRA TLS implementation
//
// Phase 1: Thin wrapper delegating to per-class TLS (completed)
// Phase 2a: Unified struct with array magazines for C4-C6 (completed)
//           C7 remains in separate TinyC7Ultra box.
// Phase 3: C6 intrusive LIFO (current) - ENV gated
//

#include "tiny_ultra_tls_box.h"
#include "tiny_c7_ultra_box.h"
#include "free_path_stats_box.h"
#include "tiny_c6_ultra_intrusive_env_box.h"   // Phase 3: ENV gate
#include "tiny_c6_intrusive_freelist_box.h"   // Phase 3: L1 box
#include "../superslab/superslab_inline.h"    // For ss_fast_lookup
#include "../tiny_debug_ring.h"               // For ring visualization

#ifndef likely
#define likely(x)   __builtin_expect(!!(x), 1)
#define unlikely(x) __builtin_expect(!!(x), 0)
#endif

// ============================================================================
// Phase TLS-UNIFY-2a: Unified TLS context for C4-C6
// ============================================================================

static __thread TinyUltraTlsCtx g_ultra_tls_ctx = {0};

TinyUltraTlsCtx* tiny_ultra_tls_ctx(void) {
    return &g_ultra_tls_ctx;
}

// ============================================================================
// Phase TLS-UNIFY-2a: Pop from unified TLS (C4-C6) or C7 separate box
// ============================================================================

void* tiny_ultra_tls_pop(uint8_t class_idx) {
    TinyUltraTlsCtx* ctx = &g_ultra_tls_ctx;

    switch (class_idx) {
        case 4:
            if (likely(ctx->c4_count > 0)) {
                return ctx->c4_freelist[--ctx->c4_count];
            }
            return NULL;

        case 5:
            if (likely(ctx->c5_count > 0)) {
                return ctx->c5_freelist[--ctx->c5_count];
            }
            return NULL;

        case 6:
            if (tiny_c6_ultra_intrusive_enabled()) {
                // Phase 3: intrusive LIFO
                void* base = c6_ifl_pop(&ctx->c6_head);
                if (base) {
                    ctx->c6_count--;
                    FREE_PATH_STAT_INC(c6_ifl_pop);
                    tiny_debug_ring_record(TINY_RING_EVENT_C6_IFL_POP, 6,
                                           (uintptr_t)base, ctx->c6_count);
                } else {
                    tiny_debug_ring_record(TINY_RING_EVENT_C6_IFL_EMPTY, 6,
                                           0, ctx->c6_count);
                }
                return base;
            } else {
                // Fallback: array magazine
                if (likely(ctx->c6_count > 0)) {
                    return ctx->c6_freelist[--ctx->c6_count];
                }
                return NULL;
            }

        case 7: {
            // C7 uses separate TinyC7Ultra box (not unified)
            tiny_c7_ultra_tls_t* c7ctx = tiny_c7_ultra_tls_get();
            if (likely(c7ctx->count > 0)) {
                return c7ctx->freelist[--c7ctx->count];
            }
            return NULL;
        }

        default:
            return NULL;
    }
}

// ============================================================================
// Phase TLS-UNIFY-2a: Push to unified TLS (C4-C6) or C7 separate box
// ============================================================================

// Forward declaration for slow path
extern void so_free(int class_idx, void* ptr);

// Slow path: flush half of TLS cache and push to segment
static void tiny_ultra_tls_push_slow(uint8_t class_idx, void* base) {
    // Convert BASE to USER pointer for so_free
    void* user_ptr = (uint8_t*)base + 1;
    so_free(class_idx, user_ptr);
}

void tiny_ultra_tls_push(uint8_t class_idx, void* base) {
    TinyUltraTlsCtx* ctx = &g_ultra_tls_ctx;
    uintptr_t addr = (uintptr_t)base;

    switch (class_idx) {
        case 4: {
            // Learn segment on first C4 free
            if (unlikely(ctx->c4_seg_base == 0)) {
                SuperSlab* ss = ss_fast_lookup(base);
                if (ss != NULL) {
                    ctx->c4_seg_base = (uintptr_t)ss;
                    ctx->c4_seg_end  = ctx->c4_seg_base + (1u << ss->lg_size);
                }
            }
            // Check segment range and capacity
            if (likely(ctx->c4_seg_base != 0 &&
                       addr >= ctx->c4_seg_base &&
                       addr < ctx->c4_seg_end &&
                       ctx->c4_count < TINY_ULTRA_C4_CAP)) {
                ctx->c4_freelist[ctx->c4_count++] = base;
                FREE_PATH_STAT_INC(c4_ultra_free_fast);
                return;
            }
            tiny_ultra_tls_push_slow(class_idx, base);
            break;
        }

        case 5: {
            // Learn segment on first C5 free
            if (unlikely(ctx->c5_seg_base == 0)) {
                SuperSlab* ss = ss_fast_lookup(base);
                if (ss != NULL) {
                    ctx->c5_seg_base = (uintptr_t)ss;
                    ctx->c5_seg_end  = ctx->c5_seg_base + (1u << ss->lg_size);
                }
            }
            if (likely(ctx->c5_seg_base != 0 &&
                       addr >= ctx->c5_seg_base &&
                       addr < ctx->c5_seg_end &&
                       ctx->c5_count < TINY_ULTRA_C5_CAP)) {
                ctx->c5_freelist[ctx->c5_count++] = base;
                FREE_PATH_STAT_INC(c5_ultra_free_fast);
                return;
            }
            tiny_ultra_tls_push_slow(class_idx, base);
            break;
        }

        case 6: {
            // Learn segment on first C6 free (common for both modes)
            if (unlikely(ctx->c6_seg_base == 0)) {
                SuperSlab* ss = ss_fast_lookup(base);
                if (ss != NULL) {
                    ctx->c6_seg_base = (uintptr_t)ss;
                    ctx->c6_seg_end  = ctx->c6_seg_base + (1u << ss->lg_size);
                }
            }
            // Check segment range and capacity (common)
            if (likely(ctx->c6_seg_base != 0 &&
                       addr >= ctx->c6_seg_base &&
                       addr < ctx->c6_seg_end &&
                       ctx->c6_count < TINY_ULTRA_C6_CAP)) {
                if (tiny_c6_ultra_intrusive_enabled()) {
                    // Phase 3: intrusive LIFO
                    c6_ifl_push(&ctx->c6_head, base);
                    ctx->c6_count++;
                    FREE_PATH_STAT_INC(c6_ifl_push);
                    FREE_PATH_STAT_INC(c6_ultra_free_fast);
                    tiny_debug_ring_record(TINY_RING_EVENT_C6_IFL_PUSH, 6,
                                           (uintptr_t)base, ctx->c6_count);
                } else {
                    // Fallback: array magazine
                    ctx->c6_freelist[ctx->c6_count++] = base;
                    FREE_PATH_STAT_INC(c6_ultra_free_fast);
                }
                return;
            }
            // Slow path (range out or cap exceeded)
            if (tiny_c6_ultra_intrusive_enabled()) {
                FREE_PATH_STAT_INC(c6_ifl_fallback);
            }
            tiny_ultra_tls_push_slow(class_idx, base);
            break;
        }

        case 7: {
            // C7 uses separate TinyC7Ultra box (not unified)
            tiny_c7_ultra_tls_t* c7ctx = tiny_c7_ultra_tls_get();
            if (unlikely(c7ctx->seg_base == 0)) {
                SuperSlab* ss = ss_fast_lookup(base);
                if (ss != NULL) {
                    c7ctx->seg_base = (uintptr_t)ss;
                    c7ctx->seg_end  = c7ctx->seg_base + (1u << ss->lg_size);
                }
            }
            if (likely(c7ctx->seg_base != 0 &&
                       addr >= c7ctx->seg_base &&
                       addr < c7ctx->seg_end &&
                       c7ctx->count < TINY_C7_ULTRA_CAP)) {
                c7ctx->freelist[c7ctx->count++] = base;
                FREE_PATH_STAT_INC(c7_ultra_fast);
                return;
            }
            // Slow path for C7
            void* user_ptr = (uint8_t*)base + 1;
            so_free(7, user_ptr);
            break;
        }

        default:
            break;
    }
}