cgroup: replace __DEVEL__sane_behavior with cgroup2 fs type
With major controllers - cpu, memory and io - shaping up for the
unified hierarchy, cgroup2 is about ready to be, gradually, released
into the wild. Replace __DEVEL__sane_behavior flag which was used to
select the unified hierarchy with a separate filesystem type "cgroup2"
so that unified hierarchy can be mounted as follows.
mount -t cgroup2 none $MOUNT_POINT
The cgroup2 fs has its own magic number - 0x63677270 ("cgrp").
v2: Assign a different magic number to cgroup2 fs.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
diff --git a/Documentation/cgroups/unified-hierarchy.txt b/Documentation/cgroups/unified-hierarchy.txt
index 781b1d4..c1f0e87 100644
--- a/Documentation/cgroups/unified-hierarchy.txt
+++ b/Documentation/cgroups/unified-hierarchy.txt
@@ -94,11 +94,9 @@
2-1. Mounting
-Currently, unified hierarchy can be mounted with the following mount
-command. Note that this is still under development and scheduled to
-change soon.
+Unified hierarchy can be mounted with the following mount command.
- mount -t cgroup -o __DEVEL__sane_behavior cgroup $MOUNT_POINT
+ mount -t cgroup2 none $MOUNT_POINT
All controllers which support the unified hierarchy and are not bound
to other hierarchies are automatically bound to unified hierarchy and
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 869fd4a..80e2ae6 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -66,7 +66,6 @@
/* cgroup_root->flags */
enum {
- CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), /* __DEVEL__sane_behavior specified */
CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */
CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */
};
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index accb036..b283d56 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -54,6 +54,7 @@
#define SMB_SUPER_MAGIC 0x517B
#define CGROUP_SUPER_MAGIC 0x27e0eb
+#define CGROUP2_SUPER_MAGIC 0x63677270
#define STACK_END_MAGIC 0x57AC6E9D
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b316deb..af08862 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -211,6 +211,7 @@
/* Ditto for the can_fork callback. */
static unsigned long have_canfork_callback __read_mostly;
+static struct file_system_type cgroup2_fs_type;
static struct cftype cgroup_dfl_base_files[];
static struct cftype cgroup_legacy_base_files[];
@@ -1641,10 +1642,6 @@
all_ss = true;
continue;
}
- if (!strcmp(token, "__DEVEL__sane_behavior")) {
- opts->flags |= CGRP_ROOT_SANE_BEHAVIOR;
- continue;
- }
if (!strcmp(token, "noprefix")) {
opts->flags |= CGRP_ROOT_NOPREFIX;
continue;
@@ -1711,15 +1708,6 @@
return -ENOENT;
}
- if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
- pr_warn("sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
- if (nr_opts != 1) {
- pr_err("sane_behavior: no other mount options allowed\n");
- return -EINVAL;
- }
- return 0;
- }
-
/*
* If the 'all' option was specified select all the subsystems,
* otherwise if 'none', 'name=' and a subsystem name options were
@@ -1998,6 +1986,7 @@
int flags, const char *unused_dev_name,
void *data)
{
+ bool is_v2 = fs_type == &cgroup2_fs_type;
struct super_block *pinned_sb = NULL;
struct cgroup_subsys *ss;
struct cgroup_root *root;
@@ -2014,6 +2003,17 @@
if (!use_task_css_set_links)
cgroup_enable_task_cg_lists();
+ if (is_v2) {
+ if (data) {
+ pr_err("cgroup2: unknown option \"%s\"\n", (char *)data);
+ return ERR_PTR(-EINVAL);
+ }
+ cgrp_dfl_root_visible = true;
+ root = &cgrp_dfl_root;
+ cgroup_get(&root->cgrp);
+ goto out_mount;
+ }
+
mutex_lock(&cgroup_mutex);
/* First find the desired set of subsystems */
@@ -2021,15 +2021,6 @@
if (ret)
goto out_unlock;
- /* look for a matching existing root */
- if (opts.flags & CGRP_ROOT_SANE_BEHAVIOR) {
- cgrp_dfl_root_visible = true;
- root = &cgrp_dfl_root;
- cgroup_get(&root->cgrp);
- ret = 0;
- goto out_unlock;
- }
-
/*
* Destruction of cgroup root is asynchronous, so subsystems may
* still be dying after the previous unmount. Let's drain the
@@ -2140,9 +2131,10 @@
if (ret)
return ERR_PTR(ret);
-
+out_mount:
dentry = kernfs_mount(fs_type, flags, root->kf_root,
- CGROUP_SUPER_MAGIC, &new_sb);
+ is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC,
+ &new_sb);
if (IS_ERR(dentry) || !new_sb)
cgroup_put(&root->cgrp);
@@ -2185,6 +2177,12 @@
.kill_sb = cgroup_kill_sb,
};
+static struct file_system_type cgroup2_fs_type = {
+ .name = "cgroup2",
+ .mount = cgroup_mount,
+ .kill_sb = cgroup_kill_sb,
+};
+
/**
* task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
* @task: target task
@@ -5315,6 +5313,7 @@
WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup"));
WARN_ON(register_filesystem(&cgroup_fs_type));
+ WARN_ON(register_filesystem(&cgroup2_fs_type));
WARN_ON(!proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations));
return 0;