[linux kernel] do_try_to_free_pages函数解析

/*

• This is the main entry point to direct page reclaim.
• If a full scan of the inactive list fails to free enough memory then we
• are “out of memory” and something needs to be killed.
• If the caller is !__GFP_FS then the probability of a failure is reasonably
• high - the zone may be full of dirty or under-writeback pages, which this
• caller can’t do much about. We kick the writeback threads and take explicit
• naps in the hope that some of these pages can be written. But if the
• allocating task holds filesystem locks which prevent writeout this might not
• work, and the allocation attempt will fail.

returns: 0, if no pages reclaimed

• else, the number of pages reclaimed

*/

static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
					  struct scan_control *sc)
{
	int initial_priority = sc->priority;
	pg_data_t *last_pgdat;
	struct zoneref *z;
	struct zone *zone;
retry:
	delayacct_freepages_start();

	if (global_reclaim(sc))
		__count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1);

	do {
		vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
				sc->priority);
		sc->nr_scanned = 0;
		shrink_zones(zonelist, sc);

		if (sc->nr_reclaimed >= sc->nr_to_reclaim)
			break;

		if (sc->compaction_ready)
			break;

		/*
		 * If we're getting trouble reclaiming, start doing
		 * writepage even in laptop mode.
		 */
		if (sc->priority < DEF_PRIORITY - 2)
			sc->may_writepage = 1;
	} while (--sc->priority >= 0);

	last_pgdat = NULL;
	for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx,
					sc->nodemask) {
		if (zone->zone_pgdat == last_pgdat)
			continue;
		last_pgdat = zone->zone_pgdat;
		snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat);
		set_memcg_congestion(last_pgdat, sc->target_mem_cgroup, false);
	}

	delayacct_freepages_end();

	if (sc->nr_reclaimed)
		return sc->nr_reclaimed;

	/* Aborted reclaim to try compaction? don't OOM, then */
	if (sc->compaction_ready)
		return 1;

	/* Untapped cgroup reserves?  Don't OOM, retry. */
	if (sc->memcg_low_skipped) {
		sc->priority = initial_priority;
		sc->memcg_low_reclaim = 1;
		sc->memcg_low_skipped = 0;
		goto retry;
	}

	return 0;
}

最终会调用shrink_zones进行内存回收。