cgroups: add cgroup support for enabling controllers at boot time

The effects of cgroup_disable=foo are:

- foo isn't auto-mounted if you mount all cgroups in a single hierarchy
- foo isn't visible as an individually mountable subsystem

As a result there will only ever be one call to foo->create(), at init time;
all processes will stay in this group, and the group will never be mounted on
a visible hierarchy.  Any additional effects (e.g.  not allocating metadata)
are up to the foo subsystem.

This doesn't handle early_init subsystems (their "disabled" bit isn't set be,
but it could easily be extended to do so if any of the early_init systems
wanted it - I think it would just involve some nastier parameter processing
since it would occur before the command-line argument parser had been run.

Hugh said:

  Ballpark figures, I'm trying to get this question out rather than
  processing the exact numbers: CONFIG_CGROUP_MEM_RES_CTLR adds 15% overhead
  to the affected paths, booting with cgroup_disable=memory cuts that back to
  1% overhead (due to slightly bigger struct page).

  I'm no expert on distros, they may have no interest whatever in
  CONFIG_CGROUP_MEM_RES_CTLR=y; and the rest of us can easily build with or
  without it, or apply the cgroup_disable=memory patches.

Unix bench's execl test result on x86_64 was

== just after boot without mounting any cgroup fs.==
mem_cgorup=off : Execl Throughput       43.0     3150.1      732.6
mem_cgroup=on  : Execl Throughput       43.0     2932.6      682.0
==

[lizf@cn.fujitsu.com: fix boot option parsing]
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Sudhir Kumar <skumar@linux.vnet.ibm.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 42 insertions, 5 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 4cd1a5da80a4..32e9297ef747 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -375,6 +375,10 @@ and is between 256 and 4096 characters. It is defined in the file
 	ccw_timeout_log [S390]
 			See Documentation/s390/CommonIO for details.
 
+	cgroup_disable= [KNL] Disable a particular controller
+			Format: {name of the controller(s) to disable}
+				{Currently supported controllers - "memory"}
+
 	checkreqprot	[SELINUX] Set initial checkreqprot flag value.
 			Format: { "0" | "1" }
 			See security/selinux/Kconfig help text.
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 028ba3b523b1..a6a6035a4e1e 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -256,6 +256,7 @@ struct cgroup_subsys {
 	void (*bind)(struct cgroup_subsys *ss, struct cgroup *root);
 	int subsys_id;
 	int active;
+	int disabled;
 	int early_init;
 #define MAX_CGROUP_TYPE_NAMELEN 32
 	const char *name;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 53d86b4b0ce0..62f1a5231fe9 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -782,7 +782,14 @@ static int parse_cgroupfs_options(char *data,
 		if (!*token)
 			return -EINVAL;
 		if (!strcmp(token, "all")) {
-			opts->subsys_bits = (1 << CGROUP_SUBSYS_COUNT) - 1;
+			/* Add all non-disabled subsystems */
+			int i;
+			opts->subsys_bits = 0;
+			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+				struct cgroup_subsys *ss = subsys[i];
+				if (!ss->disabled)
+					opts->subsys_bits |= 1ul << i;
+			}
 		} else if (!strcmp(token, "noprefix")) {
 			set_bit(ROOT_NOPREFIX, &opts->flags);
 		} else if (!strncmp(token, "release_agent=", 14)) {
@@ -800,7 +807,8 @@ static int parse_cgroupfs_options(char *data,
 			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 				ss = subsys[i];
 				if (!strcmp(token, ss->name)) {
-					set_bit(i, &opts->subsys_bits);
+					if (!ss->disabled)
+						set_bit(i, &opts->subsys_bits);
 					break;
 				}
 			}
@@ -2600,13 +2608,13 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
 {
 	int i;
 
-	seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\n");
+	seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
 	mutex_lock(&cgroup_mutex);
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 		struct cgroup_subsys *ss = subsys[i];
-		seq_printf(m, "%s\t%lu\t%d\n",
+		seq_printf(m, "%s\t%lu\t%d\t%d\n",
 			   ss->name, ss->root->subsys_bits,
-			   ss->root->number_of_cgroups);
+			   ss->root->number_of_cgroups, !ss->disabled);
 	}
 	mutex_unlock(&cgroup_mutex);
 	return 0;
@@ -3010,3 +3018,27 @@ static void cgroup_release_agent(struct work_struct *work)
 	spin_unlock(&release_list_lock);
 	mutex_unlock(&cgroup_mutex);
 }
+
+static int __init cgroup_disable(char *str)
+{
+	int i;
+	char *token;
+
+	while ((token = strsep(&str, ",")) != NULL) {
+		if (!*token)
+			continue;
+
+		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+
+			if (!strcmp(token, ss->name)) {
+				ss->disabled = 1;
+				printk(KERN_INFO "Disabling %s control group"
+					" subsystem\n", ss->name);
+				break;
+			}
+		}
+	}
+	return 1;
+}
+__setup("cgroup_disable=", cgroup_disable);