The compaction freepage scanner implementation in isolate_freepages() starts
by taking the current cc->free_pfn value as the first pfn. In a for loop, it
scans from this first pfn to the end of the pageblock, and then subtracts
pageblock_nr_pages from the first pfn to obtain the first pfn for the next
for loop iteration.
This means that when cc->free_pfn starts at offset X rather than being aligned
on pageblock boundary, the scanner will start at offset X in all scanned
pageblock, ignoring potentially many free pages. Currently this can happen when
a) zone's end pfn is not pageblock aligned, or
b) through zone->compact_cached_free_pfn with CONFIG_HOLES_IN_ZONE enabled and
a hole spanning the beginning of a pageblock
This patch fixes the problem by aligning the initial pfn in isolate_freepages()
to pageblock boundary. This also allows to replace the end-of-pageblock
alignment within the for loop with a simple pageblock_nr_pages increment.
Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>
Reported-by: Heesub Shin <heesub.shin@xxxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@xxxxxxxxxxx>
Cc: Michal Nazarewicz <mina86@xxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
---
mm/compaction.c | 22 ++++++++++++----------
1 file changed, 12 insertions(+), 10 deletions(-)
diff --git a/mm/compaction.c b/mm/compaction.c
index 37f9762..627dc2e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -671,16 +671,20 @@ static void isolate_freepages(struct zone *zone,
struct compact_control *cc)
{
struct page *page;
- unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn;
+ unsigned long high_pfn, low_pfn, pfn, z_end_pfn;
int nr_freepages = cc->nr_freepages;
struct list_head *freelist = &cc->freepages;
/*
* Initialise the free scanner. The starting point is where we last
- * scanned from (or the end of the zone if starting). The low point
- * is the end of the pageblock the migration scanner is using.
+ * successfully isolated from, zone-cached value, or the end of the
+ * zone when isolating for the first time. We need this aligned to
+ * the pageblock boundary, because we do pfn -= pageblock_nr_pages
+ * in the for loop.
+ * The low boundary is the end of the pageblock the migration scanner
+ * is using.
*/
- pfn = cc->free_pfn;
+ pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
/*
@@ -700,6 +704,7 @@ static void isolate_freepages(struct zone *zone,
for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
pfn -= pageblock_nr_pages) {
unsigned long isolated;
+ unsigned long end_pfn;
/*
* This can iterate a massively long zone without finding any
@@ -734,13 +739,10 @@ static void isolate_freepages(struct zone *zone,
isolated = 0;
/*
- * As pfn may not start aligned, pfn+pageblock_nr_page
- * may cross a MAX_ORDER_NR_PAGES boundary and miss
- * a pfn_valid check. Ensure isolate_freepages_block()
- * only scans within a pageblock
+ * Take care when isolating in last pageblock of a zone which
+ * ends in the middle of a pageblock.
*/
- end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
- end_pfn = min(end_pfn, z_end_pfn);
+ end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn);
isolated = isolate_freepages_block(cc, pfn, end_pfn,
freelist, false);
nr_freepages += isolated;
--
1.8.4.5
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>