[PATCH] mm, reclaim: cleanup should_continue_reclaim()

[Vlastimil Babka]

After commit "mm, reclaim: make should_continue_reclaim perform dryrun
detection", closer look at the function shows, that nr_reclaimed == 0 means
the function will always return false. And since non-zero nr_reclaimed implies
non_zero nr_scanned, testing nr_scanned serves no purpose, and so does the
testing for __GFP_RETRY_MAYFAIL.

This patch thus cleans up the function to test only !nr_reclaimed upfront, and
remove the __GFP_RETRY_MAYFAIL test and nr_scanned parameter completely.
Comment is also updated, explaining that approximating "full LRU list has been
scanned" with nr_scanned == 0 didn't really work.

Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>
---
 mm/vmscan.c | 43 ++++++++++++++-----------------------------
 1 file changed, 14 insertions(+), 29 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index ad498b76e492..db3c9e06a888 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2582,7 +2582,6 @@ static bool in_reclaim_compaction(struct scan_control *sc)
  */
 static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 					unsigned long nr_reclaimed,
-					unsigned long nr_scanned,
 					struct scan_control *sc)
 {
 	unsigned long pages_for_compaction;
@@ -2593,28 +2592,18 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 	if (!in_reclaim_compaction(sc))
 		return false;
 
-	/* Consider stopping depending on scan and reclaim activity */
-	if (sc->gfp_mask & __GFP_RETRY_MAYFAIL) {
-		/*
-		 * For __GFP_RETRY_MAYFAIL allocations, stop reclaiming if the
-		 * full LRU list has been scanned and we are still failing
-		 * to reclaim pages. This full LRU scan is potentially
-		 * expensive but a __GFP_RETRY_MAYFAIL caller really wants to succeed
-		 */
-		if (!nr_reclaimed && !nr_scanned)
-			return false;
-	} else {
-		/*
-		 * For non-__GFP_RETRY_MAYFAIL allocations which can presumably
-		 * fail without consequence, stop if we failed to reclaim
-		 * any pages from the last SWAP_CLUSTER_MAX number of
-		 * pages that were scanned. This will return to the
-		 * caller faster at the risk reclaim/compaction and
-		 * the resulting allocation attempt fails
-		 */
-		if (!nr_reclaimed)
-			return false;
-	}
+	/*
+	 * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX
+	 * number of pages that were scanned. This will return to the caller
+	 * with the risk reclaim/compaction and the resulting allocation attempt
+	 * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL
+	 * allocations through requiring that the full LRU list has been scanned
+	 * first, by assuming that zero delta of sc->nr_scanned means full LRU
+	 * scan, but that approximation was wrong, and there were corner cases
+	 * where always a non-zero amount of pages were scanned.
+	 */
+	if (!nr_reclaimed)
+		return false;
 
 	/* If compaction would go ahead or the allocation would succeed, stop */
 	for (z = 0; z <= sc->reclaim_idx; z++) {
@@ -2641,11 +2630,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 	if (get_nr_swap_pages() > 0)
 		inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
 
-	return inactive_lru_pages > pages_for_compaction &&
-		/*
-		 * avoid dryrun with plenty of inactive pages
-		 */
-		nr_scanned && nr_reclaimed;
+	return inactive_lru_pages > pages_for_compaction;
 }
 
 static bool pgdat_memcg_congested(pg_data_t *pgdat, struct mem_cgroup *memcg)
@@ -2810,7 +2795,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			wait_iff_congested(BLK_RW_ASYNC, HZ/10);
 
 	} while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
-					 sc->nr_scanned - nr_scanned, sc));
+					 sc));
 
 	/*
 	 * Kswapd gives up on balancing particular nodes after too
-- 
2.22.0