mm, compaction: abort free scanner if split fails

[ Upstream commit 284f69fb49e2e385203f52441b324b9a68461d6b ]

[ Upstream commit a4f04f2c6955aff5e2c08dcb40aca247ff4d7370 ]

If the memory compaction free scanner cannot successfully split a free
page (only possible due to per-zone low watermark), terminate the free
scanner rather than continuing to scan memory needlessly.  If the
watermark is insufficient for a free page of order <= cc->order, then
terminate the scanner since all future splits will also likely fail.

This prevents the compaction freeing scanner from scanning all memory on
very large zones (very noticeable for zones > 128GB, for instance) when
all splits will likely fail while holding zone->lock.

compaction_alloc() iterating a 128GB zone has been benchmarked to take
over 400ms on some systems whereas any free page isolated and ready to
be split ends up failing in split_free_page() because of the low
watermark check and thus the iteration continues.

The next time compaction occurs, the freeing scanner will likely start
at the end of the zone again since no success was made previously and we
get the same lengthy iteration until the zone is brought above the low
watermark.  All thp page faults can take >400ms in such a state without
this fix.

Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1606211820350.97086@chino.kir.corp.google.com
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>

1 files changed, 20 insertions, 10 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 347e998dbd16..9f8b1dd5303c 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -420,18 +420,23 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
+		if (!isolated)
+			break;
+
 		total_isolated += isolated;
+		cc->nr_freepages += isolated;
 		for (i = 0; i < isolated; i++) {
 			list_add(&page->lru, freelist);
 			page++;
 		}
-
-		/* If a page was split, advance to the end of it */
-		if (isolated) {
-			blockpfn += isolated - 1;
-			cursor += isolated - 1;
-			continue;
+		if (!strict && cc->nr_migratepages <= cc->nr_freepages) {
+			blockpfn += isolated;
+			break;
 		}
+		/* Advance to the end of split page */
+		blockpfn += isolated - 1;
+		cursor += isolated - 1;
+		continue;
 
 isolate_fail:
 		if (strict)
@@ -441,6 +446,9 @@ isolate_fail:
 
 	}
 
+	if (locked)
+		spin_unlock_irqrestore(&cc->zone->lock, flags);
+
 	/*
 	 * There is a tiny chance that we have read bogus compound_order(),
 	 * so be careful to not go outside of the pageblock.
@@ -461,9 +469,6 @@ isolate_fail:
 	if (strict && blockpfn < end_pfn)
 		total_isolated = 0;
 
-	if (locked)
-		spin_unlock_irqrestore(&cc->zone->lock, flags);
-
 	/* Update the pageblock-skip if the whole pageblock was scanned */
 	if (blockpfn == end_pfn)
 		update_pageblock_skip(cc, valid_page, total_isolated, false);
@@ -889,7 +894,12 @@ static void isolate_freepages(struct compact_control *cc)
 
 		/* Found a block suitable for isolating free pages from. */
 		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
-					block_end_pfn, freelist, false);
+						block_end_pfn, freelist, false);
+		/* If isolation failed early, do not continue needlessly */
+		if (!isolated && isolate_start_pfn < block_end_pfn &&
+		    cc->nr_migratepages > cc->nr_freepages)
+			break;
+
 		nr_freepages += isolated;
 
 		/*