summaryrefslogtreecommitdiffstats
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
authorVlastimil Babka <vbabka@suse.cz>2014-06-04 16:07:22 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2014-06-04 16:54:00 -0700
commit5bcc9f86ef09a933255ee66bd899d4601785dad5 (patch)
treea451b94983b961c29e1d697a731ff68799144425 /mm/page_alloc.c
parent9b857d26d08f00971997cd21aa491e27e0c84ce3 (diff)
downloadop-kernel-dev-5bcc9f86ef09a933255ee66bd899d4601785dad5.zip
op-kernel-dev-5bcc9f86ef09a933255ee66bd899d4601785dad5.tar.gz
mm/page_alloc: prevent MIGRATE_RESERVE pages from being misplaced
For the MIGRATE_RESERVE pages, it is useful when they do not get misplaced on free_list of other migratetype, otherwise they might get allocated prematurely and e.g. fragment the MIGRATE_RESEVE pageblocks. While this cannot be avoided completely when allocating new MIGRATE_RESERVE pageblocks in min_free_kbytes sysctl handler, we should prevent the misplacement where possible. Currently, it is possible for the misplacement to happen when a MIGRATE_RESERVE page is allocated on pcplist through rmqueue_bulk() as a fallback for other desired migratetype, and then later freed back through free_pcppages_bulk() without being actually used. This happens because free_pcppages_bulk() uses get_freepage_migratetype() to choose the free_list, and rmqueue_bulk() calls set_freepage_migratetype() with the *desired* migratetype and not the page's original MIGRATE_RESERVE migratetype. This patch fixes the problem by moving the call to set_freepage_migratetype() from rmqueue_bulk() down to __rmqueue_smallest() and __rmqueue_fallback() where the actual page's migratetype (e.g. from which free_list the page is taken from) is used. Note that this migratetype might be different from the pageblock's migratetype due to freepage stealing decisions. This is OK, as page stealing never uses MIGRATE_RESERVE as a fallback, and also takes care to leave all MIGRATE_CMA pages on the correct freelist. Therefore, as an additional benefit, the call to get_pageblock_migratetype() from rmqueue_bulk() when CMA is enabled, can be removed completely. This relies on the fact that MIGRATE_CMA pageblocks are created only during system init, and the above. The related is_migrate_isolate() check is also unnecessary, as memory isolation has other ways to move pages between freelists, and drain pcp lists containing pages that should be isolated. The buffered_rmqueue() can also benefit from calling get_freepage_migratetype() instead of get_pageblock_migratetype(). Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reported-by: Yong-Taek Lee <ytk.lee@samsung.com> Reported-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Suggested-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Suggested-by: Mel Gorman <mgorman@suse.de> Acked-by: Minchan Kim <minchan@kernel.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: "Wang, Yalin" <Yalin.Wang@sonymobile.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c23
1 files changed, 13 insertions, 10 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9f13bcf..ab46f79 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -931,6 +931,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
rmv_page_order(page);
area->nr_free--;
expand(zone, page, order, current_order, area, migratetype);
+ set_freepage_migratetype(page, migratetype);
return page;
}
@@ -1057,7 +1058,9 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page,
/*
* When borrowing from MIGRATE_CMA, we need to release the excess
- * buddy pages to CMA itself.
+ * buddy pages to CMA itself. We also ensure the freepage_migratetype
+ * is set to CMA so it is returned to the correct freelist in case
+ * the page ends up being not actually allocated from the pcp lists.
*/
if (is_migrate_cma(fallback_type))
return fallback_type;
@@ -1125,6 +1128,12 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
expand(zone, page, order, current_order, area,
new_type);
+ /* The freepage_migratetype may differ from pageblock's
+ * migratetype depending on the decisions in
+ * try_to_steal_freepages. This is OK as long as it does
+ * not differ for MIGRATE_CMA type.
+ */
+ set_freepage_migratetype(page, new_type);
trace_mm_page_alloc_extfrag(page, order, current_order,
start_migratetype, migratetype, new_type);
@@ -1175,7 +1184,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
int migratetype, int cold)
{
- int mt = migratetype, i;
+ int i;
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
@@ -1196,14 +1205,8 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
list_add(&page->lru, list);
else
list_add_tail(&page->lru, list);
- if (IS_ENABLED(CONFIG_CMA)) {
- mt = get_pageblock_migratetype(page);
- if (!is_migrate_cma(mt) && !is_migrate_isolate(mt))
- mt = migratetype;
- }
- set_freepage_migratetype(page, mt);
list = &page->lru;
- if (is_migrate_cma(mt))
+ if (is_migrate_cma(get_freepage_migratetype(page)))
__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
-(1 << order));
}
@@ -1572,7 +1575,7 @@ again:
if (!page)
goto failed;
__mod_zone_freepage_state(zone, -(1 << order),
- get_pageblock_migratetype(page));
+ get_freepage_migratetype(page));
}
__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
OpenPOWER on IntegriCloud