mm/page_alloc: convert zone_pcp_update() to rely on memory barriers instead of stop_machine()

zone_pcp_update()'s goal is to adjust the ->high and ->mark members of a
percpu pageset based on a zone's ->managed_pages.  We don't need to drain
the entire percpu pageset just to modify these fields.

This lets us avoid calling setup_pageset() (and the draining required to
call it) and instead allows simply setting the fields' values (with some
attention paid to memory barriers to prevent the relationship between
->batch and ->high from being thrown off).

This does change the behavior of zone_pcp_update() as the percpu pagesets
will not be drained when zone_pcp_update() is called (they will end up
being shrunk, not completely drained, later when a 0-order page is freed
in free_hot_cold_page()).

Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Cc: Gilad Ben-Yossef <gilad@benyossef.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 9 insertions, 24 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 97b8f861e63..8125263be60 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6085,33 +6085,18 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
 #endif
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-static int __meminit __zone_pcp_update(void *data)
-{
-	struct zone *zone = data;
-	int cpu;
-	unsigned long batch = zone_batchsize(zone), flags;
-
-	for_each_possible_cpu(cpu) {
-		struct per_cpu_pageset *pset;
-		struct per_cpu_pages *pcp;
-
-		pset = per_cpu_ptr(zone->pageset, cpu);
-		pcp = &pset->pcp;
-
-		local_irq_save(flags);
-		if (pcp->count > 0)
-			free_pcppages_bulk(zone, pcp->count, pcp);
-		drain_zonestat(zone, pset);
-		setup_pageset(pset, batch);
-		local_irq_restore(flags);
-	}
-	return 0;
-}
-
+/*
+ * The zone indicated has a new number of managed_pages; batch sizes and percpu
+ * page high values need to be recalulated.
+ */
 void __meminit zone_pcp_update(struct zone *zone)
 {
+	unsigned cpu;
+	unsigned long batch;
 	mutex_lock(&pcp_batch_high_lock);
-	stop_machine(__zone_pcp_update, zone, NULL);
+	batch = zone_batchsize(zone);
+	for_each_possible_cpu(cpu)
+		pageset_set_batch(per_cpu_ptr(zone->pageset, cpu), batch);
 	mutex_unlock(&pcp_batch_high_lock);
 }
 #endif