From: Greg Thelen <gthelen@google.com>
Date: Wed, 24 Aug 2011 23:47:43 +0000 (+1000)
Subject: Both mem_cgroup_charge_statistics() and mem_cgroup_move_account() were
X-Git-Tag: next-20110914~1^2~14
X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=7ff851e4315db7ade6bed8282c7840dd8870cbe3;p=karo-tx-linux.git

Both mem_cgroup_charge_statistics() and mem_cgroup_move_account() were
unnecessarily disabling preemption when adjusting per-cpu counters:
    preempt_disable()
    __this_cpu_xxx()
    __this_cpu_yyy()
    preempt_enable()

This change does not disable preemption and thus CPU switch is possible
within these routines.  This does not cause a problem because the total
of all cpu counters is summed when reporting stats.  Now both
mem_cgroup_charge_statistics() and mem_cgroup_move_account() look like:
    this_cpu_xxx()
    this_cpu_yyy()

akpm: this is an optimisation for x86 and a deoptimisation for non-x86.
The non-x86 situation will be fixed as architectures implement their
atomic this_cpu_foo() operations.

Signed-off-by: Greg Thelen <gthelen@google.com>
Reported-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f367fadefe2f..54b35b35ea04 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -664,26 +664,22 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 					 bool file, int nr_pages)
 {
-	preempt_disable();
-
 	if (file)
-		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
+		this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
 				nr_pages);
 	else
-		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS],
+		this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS],
 				nr_pages);
 
 	/* pagein of a big page is an event. So, ignore page size */
-	if (nr_pages > 0)
-		__this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGIN]);
-	else {
-		__this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT]);
+	if (nr_pages > 0) {
+		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGIN]);
+	} else {
+		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT]);
 		nr_pages = -nr_pages; /* for event */
 	}
 
-	__this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT], nr_pages);
-
-	preempt_enable();
+	this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT], nr_pages);
 }
 
 unsigned long
@@ -2704,10 +2700,8 @@ static int mem_cgroup_move_account(struct page *page,
 
 	if (PageCgroupFileMapped(pc)) {
 		/* Update mapped_file data for mem_cgroup */
-		preempt_disable();
-		__this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
-		__this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
-		preempt_enable();
+		this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
+		this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
 	}
 	mem_cgroup_charge_statistics(from, PageCgroupCache(pc), -nr_pages);
 	if (uncharge)