From: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx> Subject: mm, page_alloc: check once if a zone has isolated pageblocks When bulk freeing pages from the per-cpu lists the zone is checked for isolated pageblocks on every release. This patch checks it once per drain. [mgorman@xxxxxxxxxxxxxxxxxxx: fix locking radce, per Vlastimil] Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx> Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx> Cc: Vlastimil Babka <vbabka@xxxxxxx> Cc: Jesper Dangaard Brouer <brouer@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/page_alloc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff -puN mm/page_alloc.c~mm-page_alloc-check-once-if-a-zone-has-isolated-pageblocks mm/page_alloc.c --- a/mm/page_alloc.c~mm-page_alloc-check-once-if-a-zone-has-isolated-pageblocks +++ a/mm/page_alloc.c @@ -831,8 +831,10 @@ static void free_pcppages_bulk(struct zo int batch_free = 0; int to_free = count; unsigned long nr_scanned; + bool isolated_pageblocks; spin_lock(&zone->lock); + isolated_pageblocks = has_isolate_pageblock(zone); nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); if (nr_scanned) __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); @@ -870,7 +872,7 @@ static void free_pcppages_bulk(struct zo /* MIGRATE_ISOLATE page should not go to pcplists */ VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); /* Pageblock could have been isolated meanwhile */ - if (unlikely(has_isolate_pageblock(zone))) + if (unlikely(isolated_pageblocks)) mt = get_pageblock_migratetype(page); __free_one_page(page, page_to_pfn(page), zone, 0, mt); _ -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
