// hakmem_batch.h - madvise Batching for TLB Optimization (Box Theory)
//
// Priority 3 optimization from ChatGPT Pro feedback:
// Batch MADV_DONTNEED calls to reduce TLB flush overhead
//
// Why batching matters:
// - mimalloc is 2× faster on VM scenario partly due to batched madvise
// - Each madvise() call triggers TLB flush (expensive!)
// - Batching 4MB worth of blocks reduces TLB flushes by 50-100×
//
// Expected Gain: +20-30% on VM scenario

#pragma once
#include <stddef.h>
#include <stdint.h>

// Configuration
#define BATCH_THRESHOLD (8 * 1024 * 1024)  // 8MB: flush batch when reached (Phase 6.11: increased from 1MB for 2MB allocations)
#define BATCH_MIN_SIZE (64 * 1024)         // 64KB: only batch large blocks
#define BATCH_MAX_BLOCKS 256               // Max blocks in batch

// Batch state
typedef struct {
    void* blocks[BATCH_MAX_BLOCKS];        // Pointers to blocks
    size_t sizes[BATCH_MAX_BLOCKS];        // Sizes of blocks
    int count;                             // Number of blocks in batch
    size_t total_bytes;                    // Total bytes in batch
} DontneedBatch;

// Batching API (Box Interface)
void hak_batch_init(void);
void hak_batch_shutdown(void);

// Add block to batch (returns 1 if flushed, 0 if buffered)
int hak_batch_add(void* ptr, size_t size);

// Force flush all batched blocks
void hak_batch_flush(void);

// Statistics
void hak_batch_print_stats(void);

// Query
size_t hak_batch_get_pending_bytes(void);
int hak_batch_get_pending_count(void);

// Page-level DONTNEED batching (for managed pool pages): enqueue whole pages
// Flush performs MADV_DONTNEED only (no munmap), safe with retained VA pointers.
int hak_batch_add_page(void* page, size_t size);