memcg: mem+swap controller Kconfig

Config and control variable for mem+swap controller.

This patch adds CONFIG_CGROUP_MEM_RES_CTLR_SWAP
(memory resource controller swap extension.)

For accounting swap, it's obvious that we have to use additional memory to
remember "who uses swap".  This adds more overhead.  So, it's better to
offer "choice" to users.  This patch adds 2 choices.

This patch adds 2 parameters to enable swap extension or not.
  - CONFIG
  - boot option

Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 57 insertions, 0 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 532eacbbed62..fb849020aea9 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1562,6 +1562,9 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nosoftlockup	[KNL] Disable the soft-lockup detector.
 
+	noswapaccount	[KNL] Disable accounting of swap in memory resource
+			controller. (See Documentation/controllers/memory.txt)
+
 	nosync		[HW,M68K] Disables sync negotiation for all devices.
 
 	notsc		[BUGS=X86-32] Disable Time Stamp Counter
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b095f5f6ecf7..41b46cc9d1f1 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -77,6 +77,9 @@ extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
 extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
 					int priority, enum lru_list lru);
 
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+extern int do_swap_account;
+#endif
 
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
 struct mem_cgroup;
diff --git a/init/Kconfig b/init/Kconfig
index 7cbe1f43ca22..a724a149bf3f 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -428,6 +428,23 @@ config CGROUP_MEM_RES_CTLR
 config MM_OWNER
 	bool
 
+config CGROUP_MEM_RES_CTLR_SWAP
+	bool "Memory Resource Controller Swap Extension(EXPERIMENTAL)"
+	depends on CGROUP_MEM_RES_CTLR && SWAP && EXPERIMENTAL
+	help
+	  Add swap management feature to memory resource controller. When you
+	  enable this, you can limit mem+swap usage per cgroup. In other words,
+	  when you disable this, memory resource controller has no cares to
+	  usage of swap...a process can exhaust all of the swap. This extension
+	  is useful when you want to avoid exhaustion swap but this itself
+	  adds more overheads and consumes memory for remembering information.
+	  Especially if you use 32bit system or small memory system, please
+	  be careful about enabling this. When memory resource controller
+	  is disabled by boot option, this will be automatically disabled and
+	  there will be no overhead from this. Even when you set this config=y,
+	  if boot option "noswapaccount" is set, swap will not be accounted.
+
+
 endmenu
 
 config SYSFS_DEPRECATED
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7288e9d85ca7..59dd8c116372 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -41,6 +41,15 @@
 struct cgroup_subsys mem_cgroup_subsys __read_mostly;
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */
+int do_swap_account __read_mostly;
+static int really_do_swap_account __initdata = 1; /* for remember boot option*/
+#else
+#define do_swap_account		(0)
+#endif
+
+
 /*
  * Statistics for memory cgroup.
  */
@@ -1404,6 +1413,18 @@ static void mem_cgroup_free(struct mem_cgroup *mem)
 }
 
 
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+static void __init enable_swap_cgroup(void)
+{
+	if (!mem_cgroup_subsys.disabled && really_do_swap_account)
+		do_swap_account = 1;
+}
+#else
+static void __init enable_swap_cgroup(void)
+{
+}
+#endif
+
 static struct cgroup_subsys_state *
 mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 {
@@ -1419,6 +1440,9 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	for_each_node_state(node, N_POSSIBLE)
 		if (alloc_mem_cgroup_per_zone_info(mem, node))
 			goto free_out;
+	/* root ? */
+	if (cont->parent == NULL)
+		enable_swap_cgroup();
 
 	return &mem->css;
 free_out:
@@ -1490,3 +1514,13 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.attach = mem_cgroup_move_task,
 	.early_init = 0,
 };
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+
+static int __init disable_swap_account(char *s)
+{
+	really_do_swap_account = 0;
+	return 1;
+}
+__setup("noswapaccount", disable_swap_account);
+#endif