mm: vmscan: clarify how swappiness, highest priority, memcg interact

A swappiness of 0 has a slightly different meaning for global reclaim
(may swap if file cache really low) and memory cgroup reclaim (never
swap, ever).

In addition, global reclaim at highest priority will scan all LRU lists
equal to their size and ignore other balancing heuristics.  UNLESS
swappiness forbids swapping, then the lists are balanced based on recent
reclaim effectiveness.  UNLESS file cache is running low, then anonymous
pages are force-scanned.

This (total mess of a) behaviour is implicit and not obvious from the
way the code is organized.  At least make it apparent in the code flow
and document the conditions.  It will be it easier to come up with sane
semantics later.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Satoru Moriya <satoru.moriya@hds.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Simon Jeons <simon.jeons@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/vmscan.c

@@ -1656,7 +1656,6 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
 	u64 fraction[2], denominator;
 	enum lru_list lru;
-	int noswap = 0;
 	bool force_scan = false;
 	struct zone *zone = lruvec_zone(lruvec);
 
@@ -1677,13 +1676,38 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 
 	/* If we have no swap space, do not bother scanning anon pages. */
 	if (!sc->may_swap || (nr_swap_pages <= 0)) {
-		noswap = 1;
 		fraction[0] = 0;
 		fraction[1] = 1;
 		denominator = 1;
 		goto out;
 	}
 
+	/*
+	 * Global reclaim will swap to prevent OOM even with no
+	 * swappiness, but memcg users want to use this knob to
+	 * disable swapping for individual groups completely when
+	 * using the memory controller's swap limit feature would be
+	 * too expensive.
+	 */
+	if (!global_reclaim(sc) && !vmscan_swappiness(sc)) {
+		fraction[0] = 0;
+		fraction[1] = 1;
+		denominator = 1;
+		goto out;
+	}
+
+	/*
+	 * Do not apply any pressure balancing cleverness when the
+	 * system is close to OOM, scan both anon and file equally
+	 * (unless the swappiness setting disagrees with swapping).
+	 */
+	if (!sc->priority && vmscan_swappiness(sc)) {
+		fraction[0] = 1;
+		fraction[1] = 1;
+		denominator = 1;
+		goto out;
+	}
+
 	anon  = get_lru_size(lruvec, LRU_ACTIVE_ANON) +
 		get_lru_size(lruvec, LRU_INACTIVE_ANON);
 	file  = get_lru_size(lruvec, LRU_ACTIVE_FILE) +
@@ -1765,13 +1789,10 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 		unsigned long scan;
 
 		size = get_lru_size(lruvec, lru);
-		if (sc->priority || noswap || !vmscan_swappiness(sc)) {
-			scan = size >> sc->priority;
-			if (!scan && force_scan)
-				scan = min(size, SWAP_CLUSTER_MAX);
-			scan = div64_u64(scan * fraction[file], denominator);
-		} else
-			scan = size;
+		scan = size >> sc->priority;
+		if (!scan && force_scan)
+			scan = min(size, SWAP_CLUSTER_MAX);
+		scan = div64_u64(scan * fraction[file], denominator);
 		nr[lru] = scan;
 	}
 }