// SPDX-License-Identifier: GPL-2.0
/*
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Swap reorganised 29.12.95, Stephen Tweedie.
 *  kswapd added: 7.1.96  sct
 *  Removed kswapd_ctl limits, and swap out as many pages as needed
 *  to bring the system back to freepages.high: 2.4.97, Rik van Riel.
 *  Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com).
 *  Multiqueue VM started 5.8.00, Rik van Riel.
 */

/* Extracted unchanged from Linux v6.12, mm/vmscan.c:7165-7241.
 * Full function definition; surrounding kernel context is required.
 * Source: https://github.com/torvalds/linux/blob/v6.12/mm/vmscan.c#L7165
 * License text: GPL-2.0.txt (in this directory).
 */
static int kswapd(void *p)
{
	unsigned int alloc_order, reclaim_order;
	unsigned int highest_zoneidx = MAX_NR_ZONES - 1;
	pg_data_t *pgdat = (pg_data_t *)p;
	struct task_struct *tsk = current;
	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);

	if (!cpumask_empty(cpumask))
		set_cpus_allowed_ptr(tsk, cpumask);

	/*
	 * Tell the memory management that we're a "memory allocator",
	 * and that if we need more memory we should get access to it
	 * regardless (see "__alloc_pages()"). "kswapd" should
	 * never get caught in the normal page freeing logic.
	 *
	 * (Kswapd normally doesn't need memory anyway, but sometimes
	 * you need a small amount of memory in order to be able to
	 * page out something else, and this flag essentially protects
	 * us from recursively trying to free more memory as we're
	 * trying to free the first piece of memory in the first place).
	 */
	tsk->flags |= PF_MEMALLOC | PF_KSWAPD;
	set_freezable();

	WRITE_ONCE(pgdat->kswapd_order, 0);
	WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES);
	atomic_set(&pgdat->nr_writeback_throttled, 0);
	for ( ; ; ) {
		bool was_frozen;

		alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
		highest_zoneidx = kswapd_highest_zoneidx(pgdat,
							highest_zoneidx);

kswapd_try_sleep:
		kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order,
					highest_zoneidx);

		/* Read the new order and highest_zoneidx */
		alloc_order = READ_ONCE(pgdat->kswapd_order);
		highest_zoneidx = kswapd_highest_zoneidx(pgdat,
							highest_zoneidx);
		WRITE_ONCE(pgdat->kswapd_order, 0);
		WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES);

		if (kthread_freezable_should_stop(&was_frozen))
			break;

		/*
		 * We can speed up thawing tasks if we don't call balance_pgdat
		 * after returning from the refrigerator
		 */
		if (was_frozen)
			continue;

		/*
		 * Reclaim begins at the requested order but if a high-order
		 * reclaim fails then kswapd falls back to reclaiming for
		 * order-0. If that happens, kswapd will consider sleeping
		 * for the order it finished reclaiming at (reclaim_order)
		 * but kcompactd is woken to compact for the original
		 * request (alloc_order).
		 */
		trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx,
						alloc_order);
		reclaim_order = balance_pgdat(pgdat, alloc_order,
						highest_zoneidx);
		if (reclaim_order < alloc_order)
			goto kswapd_try_sleep;
	}

	tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD);

	return 0;
}