// 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 v6.18, mm/vmscan.c:6802-6866.
 * Full function definition; surrounding kernel context is required.
 * Source: https://github.com/torvalds/linux/blob/v6.18/mm/vmscan.c#L6802
 * License text: GPL-2.0.txt (in this directory).
 */
static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
{
	int i;
	unsigned long mark = -1;
	struct zone *zone;

	/*
	 * Check watermarks bottom-up as lower zones are more likely to
	 * meet watermarks.
	 */
	for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) {
		enum zone_stat_item item;
		unsigned long free_pages;

		if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)
			mark = promo_wmark_pages(zone);
		else
			mark = high_wmark_pages(zone);

		/*
		 * In defrag_mode, watermarks must be met in whole
		 * blocks to avoid polluting allocator fallbacks.
		 *
		 * However, kswapd usually cannot accomplish this on
		 * its own and needs kcompactd support. Once it's
		 * reclaimed a compaction gap, and kswapd_shrink_node
		 * has dropped order, simply ensure there are enough
		 * base pages for compaction, wake kcompactd & sleep.
		 */
		if (defrag_mode && order)
			item = NR_FREE_PAGES_BLOCKS;
		else
			item = NR_FREE_PAGES;

		/*
		 * When there is a high number of CPUs in the system,
		 * the cumulative error from the vmstat per-cpu cache
		 * can blur the line between the watermarks. In that
		 * case, be safe and get an accurate snapshot.
		 *
		 * TODO: NR_FREE_PAGES_BLOCKS moves in steps of
		 * pageblock_nr_pages, while the vmstat pcp threshold
		 * is limited to 125. On many configurations that
		 * counter won't actually be per-cpu cached. But keep
		 * things simple for now; revisit when somebody cares.
		 */
		free_pages = zone_page_state(zone, item);
		if (zone->percpu_drift_mark && free_pages < zone->percpu_drift_mark)
			free_pages = zone_page_state_snapshot(zone, item);

		if (__zone_watermark_ok(zone, order, mark, highest_zoneidx,
					0, free_pages))
			return true;
	}

	/*
	 * If a node has no managed zone within highest_zoneidx, it does not
	 * need balancing by definition. This can happen if a zone-restricted
	 * allocation tries to wake a remote kswapd.
	 */
	if (mark == -1)
		return true;

	return false;
}