// 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:5936-6047.
 * Full function definition; surrounding kernel context is required.
 * Source: https://github.com/torvalds/linux/blob/v6.12/mm/vmscan.c#L5936
 * License text: GPL-2.0.txt (in this directory).
 */
static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
{
	unsigned long nr_reclaimed, nr_scanned, nr_node_reclaimed;
	struct lruvec *target_lruvec;
	bool reclaimable = false;

	if (lru_gen_enabled() && root_reclaim(sc)) {
		lru_gen_shrink_node(pgdat, sc);
		return;
	}

	target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);

again:
	memset(&sc->nr, 0, sizeof(sc->nr));

	nr_reclaimed = sc->nr_reclaimed;
	nr_scanned = sc->nr_scanned;

	prepare_scan_control(pgdat, sc);

	shrink_node_memcgs(pgdat, sc);

	flush_reclaim_state(sc);

	nr_node_reclaimed = sc->nr_reclaimed - nr_reclaimed;

	/* Record the subtree's reclaim efficiency */
	if (!sc->proactive)
		vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
			   sc->nr_scanned - nr_scanned, nr_node_reclaimed);

	if (nr_node_reclaimed)
		reclaimable = true;

	if (current_is_kswapd()) {
		/*
		 * If reclaim is isolating dirty pages under writeback,
		 * it implies that the long-lived page allocation rate
		 * is exceeding the page laundering rate. Either the
		 * global limits are not being effective at throttling
		 * processes due to the page distribution throughout
		 * zones or there is heavy usage of a slow backing
		 * device. The only option is to throttle from reclaim
		 * context which is not ideal as there is no guarantee
		 * the dirtying process is throttled in the same way
		 * balance_dirty_pages() manages.
		 *
		 * Once a node is flagged PGDAT_WRITEBACK, kswapd will
		 * count the number of pages under pages flagged for
		 * immediate reclaim and stall if any are encountered
		 * in the nr_immediate check below.
		 */
		if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken)
			set_bit(PGDAT_WRITEBACK, &pgdat->flags);

		/* Allow kswapd to start writing pages during reclaim.*/
		if (sc->nr.unqueued_dirty == sc->nr.file_taken)
			set_bit(PGDAT_DIRTY, &pgdat->flags);

		/*
		 * If kswapd scans pages marked for immediate
		 * reclaim and under writeback (nr_immediate), it
		 * implies that pages are cycling through the LRU
		 * faster than they are written so forcibly stall
		 * until some pages complete writeback.
		 */
		if (sc->nr.immediate)
			reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
	}

	/*
	 * Tag a node/memcg as congested if all the dirty pages were marked
	 * for writeback and immediate reclaim (counted in nr.congested).
	 *
	 * Legacy memcg will stall in page writeback so avoid forcibly
	 * stalling in reclaim_throttle().
	 */
	if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested) {
		if (cgroup_reclaim(sc) && writeback_throttling_sane(sc))
			set_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags);

		if (current_is_kswapd())
			set_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags);
	}

	/*
	 * Stall direct reclaim for IO completions if the lruvec is
	 * node is congested. Allow kswapd to continue until it
	 * starts encountering unqueued dirty pages or cycling through
	 * the LRU too quickly.
	 */
	if (!current_is_kswapd() && current_may_throttle() &&
	    !sc->hibernation_mode &&
	    (test_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags) ||
	     test_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags)))
		reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED);

	if (should_continue_reclaim(pgdat, nr_node_reclaimed, sc))
		goto again;

	/*
	 * Kswapd gives up on balancing particular nodes after too
	 * many failures to reclaim anything from them and goes to
	 * sleep. On reclaim progress, reset the failure counter. A
	 * successful direct reclaim run will revive a dormant kswapd.
	 */
	if (reclaimable)
		pgdat->kswapd_failures = 0;
	else if (sc->cache_trim_mode)
		sc->cache_trim_mode_failed = 1;
}