From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
To: "linux-mm@kvack.org" <linux-mm@kvack.org>
Cc: Linux Kernel <linux-kernel@vger.kernel.org>,
Michal Hocko <mhocko@suse.cz>,
Johannes Weiner <hannes@cmpxchg.org>,
Andrew Morton <akpm@linux-foundation.org>,
Han Ying <yinghan@google.com>,
Glauber Costa <glommer@parallels.com>,
Konstantin Khlebnikov <khlebnikov@openvz.org>,
Suleiman Souhlal <suleiman@google.com>
Subject: [RFC][PATCH 2/6] memcg: add pc_set_mem_cgroup_and_flags()
Date: Wed, 28 Mar 2012 19:51:17 +0900 [thread overview]
Message-ID: <4F72ED25.60307@jp.fujitsu.com> (raw)
In-Reply-To: <4F72EB84.7080000@jp.fujitsu.com>
Consolidate a code for setting pc->mem_cgroup and USED bit which requires smp_wmb().
And remove a macro PCGF_NOCOPY_AT_SPLIT which isn't helpful to read code, now.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---
include/linux/page_cgroup.h | 18 ++++++++++++++++++
mm/memcontrol.c | 18 ++++--------------
2 files changed, 22 insertions(+), 14 deletions(-)
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 92768cb..2707809 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -1,6 +1,8 @@
#ifndef __LINUX_PAGE_CGROUP_H
#define __LINUX_PAGE_CGROUP_H
+#include <linux/smp.h>
+
enum {
/* flags for mem_cgroup */
PCG_LOCK, /* Lock for pc->mem_cgroup and following bits. */
@@ -94,6 +96,22 @@ pc_set_mem_cgroup(struct page_cgroup *pc, struct mem_cgroup *memcg)
pc->mem_cgroup = memcg;
}
+static inline void
+pc_set_mem_cgroup_and_flags(struct page_cgroup *pc, struct mem_cgroup *memcg,
+ unsigned long flags)
+{
+ pc->mem_cgroup = memcg;
+ /*
+ * We access a page_cgroup asynchronously without lock_page_cgroup().
+ * Especially when a page_cgroup is taken from a page, pc's mem_cgroup
+ * is accessed after testing USED bit. To make pc's mem_cgroup visible
+ * before USED bit, we need memory barrier here.
+ * See mem_cgroup_add_lru_list(), etc.
+ */
+ smp_wmb();
+ pc->flags = flags;
+}
+
#else /* CONFIG_CGROUP_MEM_RES_CTLR */
struct page_cgroup;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8077460..d366b60 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2511,16 +2511,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
}
}
- pc_set_mem_cgroup(pc, memcg);
- /*
- * We access a page_cgroup asynchronously without lock_page_cgroup().
- * Especially when a page_cgroup is taken from a page, pc's mem_cgroup
- * is accessed after testing USED bit. To make pc's mem_cgroup visible
- * before USED bit, we need memory barrier here.
- * See mem_cgroup_add_lru_list(), etc.
- */
- smp_wmb();
- SetPageCgroupUsed(pc);
+ pc_set_mem_cgroup_and_flags(pc, memcg, BIT(PCG_USED) | BIT(PCG_LOCK));
if (lrucare) {
if (was_on_lru) {
@@ -2549,7 +2540,6 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MIGRATION))
/*
* Because tail pages are not marked as "used", set it. We're under
* zone->lru_lock, 'splitting on pmd' and compound_lock.
@@ -2565,11 +2555,11 @@ void mem_cgroup_split_huge_fixup(struct page *head)
if (mem_cgroup_disabled())
return;
+ if (!PageCgroupUsed(head_pc))
+ return;
for (i = 1; i < HPAGE_PMD_NR; i++) {
pc = head_pc + i;
- pc_set_mem_cgroup(pc, memcg);
- smp_wmb();/* see __commit_charge() */
- pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
+ pc_set_mem_cgroup_and_flags(pc, memcg, BIT(PCG_USED));
}
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
--
1.7.4.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2012-03-28 10:53 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-03-28 10:44 [RFC][PATCH 0/6 v2] reducing page_cgroup size KAMEZAWA Hiroyuki
2012-03-28 10:47 ` [RFC][PATCH 1/6] memcg: add methods to access pc->mem_cgroup KAMEZAWA Hiroyuki
2012-03-28 10:51 ` KAMEZAWA Hiroyuki [this message]
2012-04-17 21:17 ` [RFC][PATCH 2/6] memcg: add pc_set_mem_cgroup_and_flags() Ying Han
2012-04-18 7:23 ` KAMEZAWA Hiroyuki
2012-04-18 18:18 ` Ying Han
2012-03-28 10:57 ` [RFC][PATCH 3/6] memcg: add PageCgroupReset() KAMEZAWA Hiroyuki
2012-04-17 21:25 ` Ying Han
2012-04-18 7:34 ` KAMEZAWA Hiroyuki
2012-03-28 10:59 ` [RFC][[PATCH 4/6] memcg: remove mem_cgroup pointer from page_cgroup KAMEZAWA Hiroyuki
2012-03-28 11:00 ` [RFC][PATCH 5/6] memcg: remove unnecessary memory barrier KAMEZAWA Hiroyuki
2012-03-28 11:06 ` [RFC][PATCH 6/6] memcg: config for integrate page_cgroup into memmap KAMEZAWA Hiroyuki
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4F72ED25.60307@jp.fujitsu.com \
--to=kamezawa.hiroyu@jp.fujitsu.com \
--cc=akpm@linux-foundation.org \
--cc=glommer@parallels.com \
--cc=hannes@cmpxchg.org \
--cc=khlebnikov@openvz.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.cz \
--cc=suleiman@google.com \
--cc=yinghan@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox