mm, vmscan: simplify the logic deciding whether kswapd sleeps

kswapd goes through some complex steps trying to figure out if it should
stay awake based on the classzone_idx and the requested order.  It is
unnecessarily complex and passes in an invalid classzone_idx to
balance_pgdat().  What matters most of all is whether a larger order has
been requsted and whether kswapd successfully reclaimed at the previous
order.  This patch irons out the logic to check just that and the end
result is less headache inducing.

Link: http://lkml.kernel.org/r/1467970510-21195-10-git-send-email-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 50 insertions, 51 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index a52167e..905c604 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2762,7 +2762,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
 	/* kswapd must be awake if processes are being throttled */
 	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
-		pgdat->classzone_idx = min(pgdat->classzone_idx,
+		pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
 						(enum zone_type)ZONE_NORMAL);
 		wake_up_interruptible(&pgdat->kswapd_wait);
 	}
@@ -3042,11 +3042,11 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 		if (!populated_zone(zone))
 			continue;
 
-		if (zone_balanced(zone, order, classzone_idx))
-			return true;
+		if (!zone_balanced(zone, order, classzone_idx))
+			return false;
 	}
 
-	return false;
+	return true;
 }
 
 /*
@@ -3238,8 +3238,8 @@ out:
 	return sc.order;
 }
 
-static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
-				int classzone_idx, int balanced_classzone_idx)
+static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
+				unsigned int classzone_idx)
 {
 	long remaining = 0;
 	DEFINE_WAIT(wait);
@@ -3250,8 +3250,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
 	prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 
 	/* Try to sleep for a short interval */
-	if (prepare_kswapd_sleep(pgdat, order, remaining,
-						balanced_classzone_idx)) {
+	if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) {
 		/*
 		 * Compaction records what page blocks it recently failed to
 		 * isolate pages from and skips them in the future scanning.
@@ -3264,9 +3263,20 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
 		 * We have freed the memory, now we should compact it to make
 		 * allocation of the requested order possible.
 		 */
-		wakeup_kcompactd(pgdat, order, classzone_idx);
+		wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
 
 		remaining = schedule_timeout(HZ/10);
+
+		/*
+		 * If woken prematurely then reset kswapd_classzone_idx and
+		 * order. The values will either be from a wakeup request or
+		 * the previous request that slept prematurely.
+		 */
+		if (remaining) {
+			pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
+			pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order);
+		}
+
 		finish_wait(&pgdat->kswapd_wait, &wait);
 		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 	}
@@ -3275,8 +3285,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
 	 * After a short sleep, check if it was a premature sleep. If not, then
 	 * go fully to sleep until explicitly woken up.
 	 */
-	if (prepare_kswapd_sleep(pgdat, order, remaining,
-						balanced_classzone_idx)) {
+	if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) {
 		trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
 
 		/*
@@ -3317,9 +3326,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
  */
 static int kswapd(void *p)
 {
-	unsigned long order, new_order;
-	int classzone_idx, new_classzone_idx;
-	int balanced_classzone_idx;
+	unsigned int alloc_order, reclaim_order, classzone_idx;
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
 
@@ -3349,38 +3356,20 @@ static int kswapd(void *p)
 	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 	set_freezable();
 
-	order = new_order = 0;
-	classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
-	balanced_classzone_idx = classzone_idx;
+	pgdat->kswapd_order = alloc_order = reclaim_order = 0;
+	pgdat->kswapd_classzone_idx = classzone_idx = 0;
 	for ( ; ; ) {
 		bool ret;
 
-		/*
-		 * While we were reclaiming, there might have been another
-		 * wakeup, so check the values.
-		 */
-		new_order = pgdat->kswapd_max_order;
-		new_classzone_idx = pgdat->classzone_idx;
-		pgdat->kswapd_max_order =  0;
-		pgdat->classzone_idx = pgdat->nr_zones - 1;
+kswapd_try_sleep:
+		kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order,
+					classzone_idx);
 
-		if (order < new_order || classzone_idx > new_classzone_idx) {
-			/*
-			 * Don't sleep if someone wants a larger 'order'
-			 * allocation or has tigher zone constraints
-			 */
-			order = new_order;
-			classzone_idx = new_classzone_idx;
-		} else {
-			kswapd_try_to_sleep(pgdat, order, classzone_idx,
-						balanced_classzone_idx);
-			order = pgdat->kswapd_max_order;
-			classzone_idx = pgdat->classzone_idx;
-			new_order = order;
-			new_classzone_idx = classzone_idx;
-			pgdat->kswapd_max_order = 0;
-			pgdat->classzone_idx = pgdat->nr_zones - 1;
-		}
+		/* Read the new order and classzone_idx */
+		alloc_order = reclaim_order = pgdat->kswapd_order;
+		classzone_idx = pgdat->kswapd_classzone_idx;
+		pgdat->kswapd_order = 0;
+		pgdat->kswapd_classzone_idx = 0;
 
 		ret = try_to_freeze();
 		if (kthread_should_stop())
@@ -3390,12 +3379,24 @@ static int kswapd(void *p)
 		 * We can speed up thawing tasks if we don't call balance_pgdat
 		 * after returning from the refrigerator
 		 */
-		if (!ret) {
-			trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
+		if (ret)
+			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, alloc_order);
+		reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
+		if (reclaim_order < alloc_order)
+			goto kswapd_try_sleep;
 
-			/* return value ignored until next patch */
-			balance_pgdat(pgdat, order, classzone_idx);
-		}
+		alloc_order = reclaim_order = pgdat->kswapd_order;
+		classzone_idx = pgdat->kswapd_classzone_idx;
 	}
 
 	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
@@ -3418,10 +3419,8 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
 		return;
 	pgdat = zone->zone_pgdat;
-	if (pgdat->kswapd_max_order < order) {
-		pgdat->kswapd_max_order = order;
-		pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
-	}
+	pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
+	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
 	if (zone_balanced(zone, order, 0))