*/
#include <linux/cgroup.h>
+#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/cgroupstats.h>
#include <linux/hash.h>
#include <linux/namei.h>
+#include <linux/smp_lock.h>
+#include <linux/pid_namespace.h>
#include <asm/atomic.h>
#include <linux/cgroup_subsys.h>
};
+#define MAX_CGROUP_ROOT_NAMELEN 64
+
/*
* A cgroupfs_root represents the root of a cgroup hierarchy,
* and may be associated with a superblock to form an active
/* Tracks how many cgroups are currently defined in hierarchy.*/
int number_of_cgroups;
- /* A list running through the mounted hierarchies */
+ /* A list running through the active hierarchies */
struct list_head root_list;
/* Hierarchy-specific flags */
/* The path to use for release notifications. */
char release_agent_path[PATH_MAX];
-};
+ /* The name for this hierarchy - may be empty */
+ char name[MAX_CGROUP_ROOT_NAMELEN];
+};
/*
* The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
*/
static struct cgroupfs_root rootnode;
+/*
+ * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when
+ * cgroup_subsys->use_id != 0.
+ */
+#define CSS_ID_MAX (65535)
+struct css_id {
+ /*
+ * The css to which this ID points. This pointer is set to valid value
+ * after cgroup is populated. If cgroup is removed, this will be NULL.
+ * This pointer is expected to be RCU-safe because destroy()
+ * is called after synchronize_rcu(). But for safe use, css_is_removed()
+ * css_tryget() should be used for avoiding race.
+ */
+ struct cgroup_subsys_state *css;
+ /*
+ * ID of this css.
+ */
+ unsigned short id;
+ /*
+ * Depth in hierarchy which this ID belongs to.
+ */
+ unsigned short depth;
+ /*
+ * ID is freed by RCU. (and lookup routine is RCU safe.)
+ */
+ struct rcu_head rcu_head;
+ /*
+ * Hierarchy of CSS ID belongs to.
+ */
+ unsigned short stack[0]; /* Array of Length (depth+1) */
+};
+
+
/* The list of hierarchy roots */
static LIST_HEAD(roots);
#define for_each_subsys(_root, _ss) \
list_for_each_entry(_ss, &_root->subsys_list, sibling)
-/* for_each_root() allows you to iterate across the active hierarchies */
-#define for_each_root(_root) \
+/* for_each_active_root() allows you to iterate across the active hierarchies */
+#define for_each_active_root(_root) \
list_for_each_entry(_root, &roots, root_list)
/* the list of cgroups eligible for automatic release. Protected by
static struct css_set init_css_set;
static struct cg_cgroup_link init_css_set_link;
+static int cgroup_subsys_init_idr(struct cgroup_subsys *ss);
+
/* css_set_lock protects the list of css_set objects, and the
* chain of tasks off each css_set. Nests outside task->alloc_lock
* due to cgroup_iter_start() */
rcu_read_lock();
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
- struct cgroup *cgrp = cg->subsys[i]->cgroup;
+ struct cgroup *cgrp = rcu_dereference(cg->subsys[i]->cgroup);
if (atomic_dec_and_test(&cgrp->count) &&
notify_on_release(cgrp)) {
if (taskexit)
return 0;
}
+/**
+ * link_css_set - a helper function to link a css_set to a cgroup
+ * @tmp_cg_links: cg_cgroup_link objects allocated by allocate_cg_links()
+ * @cg: the css_set to be linked
+ * @cgrp: the destination cgroup
+ */
+static void link_css_set(struct list_head *tmp_cg_links,
+ struct css_set *cg, struct cgroup *cgrp)
+{
+ struct cg_cgroup_link *link;
+
+ BUG_ON(list_empty(tmp_cg_links));
+ link = list_first_entry(tmp_cg_links, struct cg_cgroup_link,
+ cgrp_link_list);
+ link->cg = cg;
+ list_move(&link->cgrp_link_list, &cgrp->css_sets);
+ list_add(&link->cg_link_list, &cg->cg_links);
+}
+
/*
* find_css_set() takes an existing cgroup group and a
* cgroup object, and returns a css_set object that's
int i;
struct list_head tmp_cg_links;
- struct cg_cgroup_link *link;
struct hlist_head *hhead;
* only do it for the first subsystem in each
* hierarchy
*/
- if (ss->root->subsys_list.next == &ss->sibling) {
- BUG_ON(list_empty(&tmp_cg_links));
- link = list_entry(tmp_cg_links.next,
- struct cg_cgroup_link,
- cgrp_link_list);
- list_del(&link->cgrp_link_list);
- list_add(&link->cgrp_link_list, &cgrp->css_sets);
- link->cg = res;
- list_add(&link->cg_link_list, &res->cg_links);
- }
- }
- if (list_empty(&rootnode.subsys_list)) {
- link = list_entry(tmp_cg_links.next,
- struct cg_cgroup_link,
- cgrp_link_list);
- list_del(&link->cgrp_link_list);
- list_add(&link->cgrp_link_list, &dummytop->css_sets);
- link->cg = res;
- list_add(&link->cg_link_list, &res->cg_links);
+ if (ss->root->subsys_list.next == &ss->sibling)
+ link_css_set(&tmp_cg_links, res, cgrp);
}
+ if (list_empty(&rootnode.subsys_list))
+ link_css_set(&tmp_cg_links, res, dummytop);
BUG_ON(!list_empty(&tmp_cg_links));
static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode);
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp);
-static struct inode_operations cgroup_dir_inode_operations;
+static const struct inode_operations cgroup_dir_inode_operations;
static struct file_operations proc_cgroupstats_operations;
static struct backing_dev_info cgroup_backing_dev_info = {
+ .name = "cgroup",
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
+static int alloc_css_id(struct cgroup_subsys *ss,
+ struct cgroup *parent, struct cgroup *child);
+
static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
{
struct inode *inode = new_inode(sb);
* Call subsys's pre_destroy handler.
* This is called before css refcnt check.
*/
-static void cgroup_call_pre_destroy(struct cgroup *cgrp)
+static int cgroup_call_pre_destroy(struct cgroup *cgrp)
{
struct cgroup_subsys *ss;
+ int ret = 0;
+
for_each_subsys(cgrp->root, ss)
- if (ss->pre_destroy)
- ss->pre_destroy(ss, cgrp);
- return;
+ if (ss->pre_destroy) {
+ ret = ss->pre_destroy(ss, cgrp);
+ if (ret)
+ break;
+ }
+ return ret;
+}
+
+static void free_cgroup_rcu(struct rcu_head *obj)
+{
+ struct cgroup *cgrp = container_of(obj, struct cgroup, rcu_head);
+
+ kfree(cgrp);
}
static void cgroup_diput(struct dentry *dentry, struct inode *inode)
cgrp->root->number_of_cgroups--;
mutex_unlock(&cgroup_mutex);
- /* Drop the active superblock reference that we took when we
- * created the cgroup */
+ /*
+ * Drop the active superblock reference that we took when we
+ * created the cgroup
+ */
deactivate_super(cgrp->root->sb);
- kfree(cgrp);
+ call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
}
iput(inode);
}
remove_dir(dentry);
}
+/*
+ * A queue for waiters to do rmdir() cgroup. A tasks will sleep when
+ * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some
+ * reference to css->refcnt. In general, this refcnt is expected to goes down
+ * to zero, soon.
+ *
+ * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
+ */
+DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
+
+static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
+{
+ if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
+ wake_up_all(&cgroup_rmdir_waitq);
+}
+
+void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
+{
+ css_get(css);
+}
+
+void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
+{
+ cgroup_wakeup_rmdir_waiter(css->cgroup);
+ css_put(css);
+}
+
+
static int rebind_subsystems(struct cgroupfs_root *root,
unsigned long final_bits)
{
BUG_ON(cgrp->subsys[i]);
BUG_ON(!dummytop->subsys[i]);
BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
+ mutex_lock(&ss->hierarchy_mutex);
cgrp->subsys[i] = dummytop->subsys[i];
cgrp->subsys[i]->cgroup = cgrp;
- list_add(&ss->sibling, &root->subsys_list);
- rcu_assign_pointer(ss->root, root);
+ list_move(&ss->sibling, &root->subsys_list);
+ ss->root = root;
if (ss->bind)
ss->bind(ss, cgrp);
-
+ mutex_unlock(&ss->hierarchy_mutex);
} else if (bit & removed_bits) {
/* We're removing this subsystem */
BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]);
BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
+ mutex_lock(&ss->hierarchy_mutex);
if (ss->bind)
ss->bind(ss, dummytop);
dummytop->subsys[i]->cgroup = dummytop;
cgrp->subsys[i] = NULL;
- rcu_assign_pointer(subsys[i]->root, &rootnode);
- list_del(&ss->sibling);
+ subsys[i]->root = &rootnode;
+ list_move(&ss->sibling, &rootnode.subsys_list);
+ mutex_unlock(&ss->hierarchy_mutex);
} else if (bit & final_bits) {
/* Subsystem state should already exist */
BUG_ON(!cgrp->subsys[i]);
seq_puts(seq, ",noprefix");
if (strlen(root->release_agent_path))
seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+ if (strlen(root->name))
+ seq_printf(seq, ",name=%s", root->name);
mutex_unlock(&cgroup_mutex);
return 0;
}
unsigned long subsys_bits;
unsigned long flags;
char *release_agent;
+ char *name;
+
+ struct cgroupfs_root *new_root;
};
/* Convert a hierarchy specifier into a bitmask of subsystems and
struct cgroup_sb_opts *opts)
{
char *token, *o = data ?: "all";
+ unsigned long mask = (unsigned long)-1;
+
+#ifdef CONFIG_CPUSETS
+ mask = ~(1UL << cpuset_subsys_id);
+#endif
- opts->subsys_bits = 0;
- opts->flags = 0;
- opts->release_agent = NULL;
+ memset(opts, 0, sizeof(*opts));
while ((token = strsep(&o, ",")) != NULL) {
if (!*token)
/* Specifying two release agents is forbidden */
if (opts->release_agent)
return -EINVAL;
- opts->release_agent = kzalloc(PATH_MAX, GFP_KERNEL);
+ opts->release_agent =
+ kstrndup(token + 14, PATH_MAX, GFP_KERNEL);
if (!opts->release_agent)
return -ENOMEM;
- strncpy(opts->release_agent, token + 14, PATH_MAX - 1);
- opts->release_agent[PATH_MAX - 1] = 0;
+ } else if (!strncmp(token, "name=", 5)) {
+ int i;
+ const char *name = token + 5;
+ /* Can't specify an empty name */
+ if (!strlen(name))
+ return -EINVAL;
+ /* Must match [\w.-]+ */
+ for (i = 0; i < strlen(name); i++) {
+ char c = name[i];
+ if (isalnum(c))
+ continue;
+ if ((c == '.') || (c == '-') || (c == '_'))
+ continue;
+ return -EINVAL;
+ }
+ /* Specifying two names is forbidden */
+ if (opts->name)
+ return -EINVAL;
+ opts->name = kstrndup(name,
+ MAX_CGROUP_ROOT_NAMELEN,
+ GFP_KERNEL);
+ if (!opts->name)
+ return -ENOMEM;
} else {
struct cgroup_subsys *ss;
int i;
}
}
+ /*
+ * Option noprefix was introduced just for backward compatibility
+ * with the old cpuset, so we allow noprefix only if mounting just
+ * the cpuset subsystem.
+ */
+ if (test_bit(ROOT_NOPREFIX, &opts->flags) &&
+ (opts->subsys_bits & mask))
+ return -EINVAL;
+
/* We can't have an empty hierarchy */
- if (!opts->subsys_bits)
+ if (!opts->subsys_bits && !opts->name)
return -EINVAL;
return 0;
struct cgroup *cgrp = &root->top_cgroup;
struct cgroup_sb_opts opts;
+ lock_kernel();
mutex_lock(&cgrp->dentry->d_inode->i_mutex);
mutex_lock(&cgroup_mutex);
goto out_unlock;
}
+ /* Don't allow name to change at remount */
+ if (opts.name && strcmp(opts.name, root->name)) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
ret = rebind_subsystems(root, opts.subsys_bits);
+ if (ret)
+ goto out_unlock;
/* (re)populate subsystem files */
- if (!ret)
- cgroup_populate_dir(cgrp);
+ cgroup_populate_dir(cgrp);
if (opts.release_agent)
strcpy(root->release_agent_path, opts.release_agent);
out_unlock:
- if (opts.release_agent)
- kfree(opts.release_agent);
+ kfree(opts.release_agent);
+ kfree(opts.name);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+ unlock_kernel();
return ret;
}
-static struct super_operations cgroup_ops = {
+static const struct super_operations cgroup_ops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
.show_options = cgroup_show_options,
INIT_LIST_HEAD(&cgrp->children);
INIT_LIST_HEAD(&cgrp->css_sets);
INIT_LIST_HEAD(&cgrp->release_list);
+ INIT_LIST_HEAD(&cgrp->pids_list);
init_rwsem(&cgrp->pids_mutex);
}
+
static void init_cgroup_root(struct cgroupfs_root *root)
{
struct cgroup *cgrp = &root->top_cgroup;
static int cgroup_test_super(struct super_block *sb, void *data)
{
- struct cgroupfs_root *new = data;
+ struct cgroup_sb_opts *opts = data;
struct cgroupfs_root *root = sb->s_fs_info;
- /* First check subsystems */
- if (new->subsys_bits != root->subsys_bits)
- return 0;
+ /* If we asked for a name then it must match */
+ if (opts->name && strcmp(opts->name, root->name))
+ return 0;
- /* Next check flags */
- if (new->flags != root->flags)
+ /* If we asked for subsystems then they must match */
+ if (opts->subsys_bits && (opts->subsys_bits != root->subsys_bits))
return 0;
return 1;
}
+static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
+{
+ struct cgroupfs_root *root;
+
+ /* Empty hierarchies aren't supported */
+ if (!opts->subsys_bits)
+ return NULL;
+
+ root = kzalloc(sizeof(*root), GFP_KERNEL);
+ if (!root)
+ return ERR_PTR(-ENOMEM);
+
+ init_cgroup_root(root);
+ root->subsys_bits = opts->subsys_bits;
+ root->flags = opts->flags;
+ if (opts->release_agent)
+ strcpy(root->release_agent_path, opts->release_agent);
+ if (opts->name)
+ strcpy(root->name, opts->name);
+ return root;
+}
+
static int cgroup_set_super(struct super_block *sb, void *data)
{
int ret;
- struct cgroupfs_root *root = data;
+ struct cgroup_sb_opts *opts = data;
+
+ /* If we don't have a new root, we can't set up a new sb */
+ if (!opts->new_root)
+ return -EINVAL;
+
+ BUG_ON(!opts->subsys_bits);
ret = set_anon_super(sb, NULL);
if (ret)
return ret;
- sb->s_fs_info = root;
- root->sb = sb;
+ sb->s_fs_info = opts->new_root;
+ opts->new_root->sb = sb;
sb->s_blocksize = PAGE_CACHE_SIZE;
sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
void *data, struct vfsmount *mnt)
{
struct cgroup_sb_opts opts;
+ struct cgroupfs_root *root;
int ret = 0;
struct super_block *sb;
- struct cgroupfs_root *root;
- struct list_head tmp_cg_links;
+ struct cgroupfs_root *new_root;
/* First find the desired set of subsystems */
ret = parse_cgroupfs_options(data, &opts);
- if (ret) {
- if (opts.release_agent)
- kfree(opts.release_agent);
- return ret;
- }
-
- root = kzalloc(sizeof(*root), GFP_KERNEL);
- if (!root) {
- if (opts.release_agent)
- kfree(opts.release_agent);
- return -ENOMEM;
- }
+ if (ret)
+ goto out_err;
- init_cgroup_root(root);
- root->subsys_bits = opts.subsys_bits;
- root->flags = opts.flags;
- if (opts.release_agent) {
- strcpy(root->release_agent_path, opts.release_agent);
- kfree(opts.release_agent);
+ /*
+ * Allocate a new cgroup root. We may not need it if we're
+ * reusing an existing hierarchy.
+ */
+ new_root = cgroup_root_from_opts(&opts);
+ if (IS_ERR(new_root)) {
+ ret = PTR_ERR(new_root);
+ goto out_err;
}
+ opts.new_root = new_root;
- sb = sget(fs_type, cgroup_test_super, cgroup_set_super, root);
-
+ /* Locate an existing or new sb for this hierarchy */
+ sb = sget(fs_type, cgroup_test_super, cgroup_set_super, &opts);
if (IS_ERR(sb)) {
- kfree(root);
- return PTR_ERR(sb);
+ ret = PTR_ERR(sb);
+ kfree(opts.new_root);
+ goto out_err;
}
- if (sb->s_fs_info != root) {
- /* Reusing an existing superblock */
- BUG_ON(sb->s_root == NULL);
- kfree(root);
- root = NULL;
- } else {
- /* New superblock */
- struct cgroup *cgrp = &root->top_cgroup;
+ root = sb->s_fs_info;
+ BUG_ON(!root);
+ if (root == opts.new_root) {
+ /* We used the new root structure, so this is a new hierarchy */
+ struct list_head tmp_cg_links;
+ struct cgroup *root_cgrp = &root->top_cgroup;
struct inode *inode;
+ struct cgroupfs_root *existing_root;
int i;
BUG_ON(sb->s_root != NULL);
mutex_lock(&inode->i_mutex);
mutex_lock(&cgroup_mutex);
+ if (strlen(root->name)) {
+ /* Check for name clashes with existing mounts */
+ for_each_active_root(existing_root) {
+ if (!strcmp(existing_root->name, root->name)) {
+ ret = -EBUSY;
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&inode->i_mutex);
+ goto drop_new_super;
+ }
+ }
+ }
+
/*
* We're accessing css_set_count without locking
* css_set_lock here, but that's OK - it can only be
if (ret == -EBUSY) {
mutex_unlock(&cgroup_mutex);
mutex_unlock(&inode->i_mutex);
- goto free_cg_links;
+ free_cg_links(&tmp_cg_links);
+ goto drop_new_super;
}
/* EBUSY should be the only error here */
list_add(&root->root_list, &roots);
root_count++;
- sb->s_root->d_fsdata = &root->top_cgroup;
+ sb->s_root->d_fsdata = root_cgrp;
root->top_cgroup.dentry = sb->s_root;
/* Link the top cgroup in this hierarchy into all
struct hlist_node *node;
struct css_set *cg;
- hlist_for_each_entry(cg, node, hhead, hlist) {
- struct cg_cgroup_link *link;
-
- BUG_ON(list_empty(&tmp_cg_links));
- link = list_entry(tmp_cg_links.next,
- struct cg_cgroup_link,
- cgrp_link_list);
- list_del(&link->cgrp_link_list);
- link->cg = cg;
- list_add(&link->cgrp_link_list,
- &root->top_cgroup.css_sets);
- list_add(&link->cg_link_list, &cg->cg_links);
- }
+ hlist_for_each_entry(cg, node, hhead, hlist)
+ link_css_set(&tmp_cg_links, cg, root_cgrp);
}
write_unlock(&css_set_lock);
free_cg_links(&tmp_cg_links);
- BUG_ON(!list_empty(&cgrp->sibling));
- BUG_ON(!list_empty(&cgrp->children));
+ BUG_ON(!list_empty(&root_cgrp->sibling));
+ BUG_ON(!list_empty(&root_cgrp->children));
BUG_ON(root->number_of_cgroups != 1);
- cgroup_populate_dir(cgrp);
- mutex_unlock(&inode->i_mutex);
+ cgroup_populate_dir(root_cgrp);
mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&inode->i_mutex);
+ } else {
+ /*
+ * We re-used an existing hierarchy - the new root (if
+ * any) is not needed
+ */
+ kfree(opts.new_root);
}
- return simple_set_mnt(mnt, sb);
+ simple_set_mnt(mnt, sb);
+ kfree(opts.release_agent);
+ kfree(opts.name);
+ return 0;
- free_cg_links:
- free_cg_links(&tmp_cg_links);
drop_new_super:
- up_write(&sb->s_umount);
- deactivate_super(sb);
+ deactivate_locked_super(sb);
+ out_err:
+ kfree(opts.release_agent);
+ kfree(opts.name);
+
return ret;
}
list_del(&root->root_list);
root_count--;
}
+
mutex_unlock(&cgroup_mutex);
- kfree(root);
kill_litter_super(sb);
+ kfree(root);
}
static struct file_system_type cgroup_fs_type = {
* @buf: the buffer to write the path into
* @buflen: the length of the buffer
*
- * Called with cgroup_mutex held. Writes path of cgroup into buf.
- * Returns 0 on success, -errno on error.
+ * Called with cgroup_mutex held or else with an RCU-protected cgroup
+ * reference. Writes path of cgroup into buf. Returns 0 on success,
+ * -errno on error.
*/
int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
{
char *start;
+ struct dentry *dentry = rcu_dereference(cgrp->dentry);
- if (cgrp == dummytop) {
+ if (!dentry || cgrp == dummytop) {
/*
* Inactive subsystems have no dentry for their root
* cgroup
*--start = '\0';
for (;;) {
- int len = cgrp->dentry->d_name.len;
+ int len = dentry->d_name.len;
if ((start -= len) < buf)
return -ENAMETOOLONG;
memcpy(start, cgrp->dentry->d_name.name, len);
cgrp = cgrp->parent;
if (!cgrp)
break;
+ dentry = rcu_dereference(cgrp->dentry);
if (!cgrp->parent)
continue;
if (--start < buf)
int retval = 0;
struct cgroup_subsys *ss;
struct cgroup *oldcgrp;
- struct css_set *cg = tsk->cgroups;
+ struct css_set *cg;
struct css_set *newcg;
struct cgroupfs_root *root = cgrp->root;
int subsys_id;
}
}
+ task_lock(tsk);
+ cg = tsk->cgroups;
+ get_css_set(cg);
+ task_unlock(tsk);
/*
* Locate or allocate a new css_set for this task,
* based on its final set of cgroups
*/
newcg = find_css_set(cg, cgrp);
+ put_css_set(cg);
if (!newcg)
return -ENOMEM;
set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
synchronize_rcu();
put_css_set(cg);
+
+ /*
+ * wake up rmdir() waiter. the rmdir should fail since the cgroup
+ * is no longer empty.
+ */
+ cgroup_wakeup_rmdir_waiter(cgrp);
return 0;
}
.release = cgroup_file_release,
};
-static struct inode_operations cgroup_dir_inode_operations = {
+static const struct inode_operations cgroup_dir_inode_operations = {
.lookup = simple_lookup,
.mkdir = cgroup_mkdir,
.rmdir = cgroup_rmdir,
.rename = cgroup_rename,
};
-static int cgroup_create_file(struct dentry *dentry, int mode,
+static int cgroup_create_file(struct dentry *dentry, mode_t mode,
struct super_block *sb)
{
- static struct dentry_operations cgroup_dops = {
+ static const struct dentry_operations cgroup_dops = {
.d_iput = cgroup_diput,
};
* @mode: mode to set on new directory.
*/
static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
- int mode)
+ mode_t mode)
{
struct dentry *parent;
int error = 0;
if (!error) {
dentry->d_fsdata = cgrp;
inc_nlink(parent->d_inode);
- cgrp->dentry = dentry;
+ rcu_assign_pointer(cgrp->dentry, dentry);
dget(dentry);
}
dput(dentry);
return error;
}
+/**
+ * cgroup_file_mode - deduce file mode of a control file
+ * @cft: the control file in question
+ *
+ * returns cft->mode if ->mode is not 0
+ * returns S_IRUGO|S_IWUSR if it has both a read and a write handler
+ * returns S_IRUGO if it has only a read handler
+ * returns S_IWUSR if it has only a write hander
+ */
+static mode_t cgroup_file_mode(const struct cftype *cft)
+{
+ mode_t mode = 0;
+
+ if (cft->mode)
+ return cft->mode;
+
+ if (cft->read || cft->read_u64 || cft->read_s64 ||
+ cft->read_map || cft->read_seq_string)
+ mode |= S_IRUGO;
+
+ if (cft->write || cft->write_u64 || cft->write_s64 ||
+ cft->write_string || cft->trigger)
+ mode |= S_IWUSR;
+
+ return mode;
+}
+
int cgroup_add_file(struct cgroup *cgrp,
struct cgroup_subsys *subsys,
const struct cftype *cft)
struct dentry *dir = cgrp->dentry;
struct dentry *dentry;
int error;
+ mode_t mode;
char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));
dentry = lookup_one_len(name, dir, strlen(name));
if (!IS_ERR(dentry)) {
- error = cgroup_create_file(dentry, 0644 | S_IFREG,
+ mode = cgroup_file_mode(cft);
+ error = cgroup_create_file(dentry, mode | S_IFREG,
cgrp->root->sb);
if (!error)
dentry->d_fsdata = (void *)cft;
*/
static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp)
{
- int n = 0;
+ int n = 0, pid;
struct cgroup_iter it;
struct task_struct *tsk;
cgroup_iter_start(cgrp, &it);
while ((tsk = cgroup_iter_next(cgrp, &it))) {
if (unlikely(n == npids))
break;
- pidarray[n++] = task_pid_vnr(tsk);
+ pid = task_pid_vnr(tsk);
+ if (pid > 0)
+ pidarray[n++] = pid;
}
cgroup_iter_end(cgrp, &it);
return n;
ret = 0;
cgrp = dentry->d_fsdata;
- rcu_read_lock();
cgroup_iter_start(cgrp, &it);
while ((tsk = cgroup_iter_next(cgrp, &it))) {
}
cgroup_iter_end(cgrp, &it);
- rcu_read_unlock();
err:
return ret;
}
+/*
+ * Cache pids for all threads in the same pid namespace that are
+ * opening the same "tasks" file.
+ */
+struct cgroup_pids {
+ /* The node in cgrp->pids_list */
+ struct list_head list;
+ /* The cgroup those pids belong to */
+ struct cgroup *cgrp;
+ /* The namepsace those pids belong to */
+ struct pid_namespace *ns;
+ /* Array of process ids in the cgroup */
+ pid_t *tasks_pids;
+ /* How many files are using the this tasks_pids array */
+ int use_count;
+ /* Length of the current tasks_pids array */
+ int length;
+};
+
static int cmppid(const void *a, const void *b)
{
return *(pid_t *)a - *(pid_t *)b;
}
-
/*
* seq_file methods for the "tasks" file. The seq_file position is the
* next pid to display; the seq_file iterator is a pointer to the pid
* after a seek to the start). Use a binary-search to find the
* next pid to display, if any
*/
- struct cgroup *cgrp = s->private;
+ struct cgroup_pids *cp = s->private;
+ struct cgroup *cgrp = cp->cgrp;
int index = 0, pid = *pos;
int *iter;
down_read(&cgrp->pids_mutex);
if (pid) {
- int end = cgrp->pids_length;
+ int end = cp->length;
while (index < end) {
int mid = (index + end) / 2;
- if (cgrp->tasks_pids[mid] == pid) {
+ if (cp->tasks_pids[mid] == pid) {
index = mid;
break;
- } else if (cgrp->tasks_pids[mid] <= pid)
+ } else if (cp->tasks_pids[mid] <= pid)
index = mid + 1;
else
end = mid;
}
}
/* If we're off the end of the array, we're done */
- if (index >= cgrp->pids_length)
+ if (index >= cp->length)
return NULL;
/* Update the abstract position to be the actual pid that we found */
- iter = cgrp->tasks_pids + index;
+ iter = cp->tasks_pids + index;
*pos = *iter;
return iter;
}
static void cgroup_tasks_stop(struct seq_file *s, void *v)
{
- struct cgroup *cgrp = s->private;
+ struct cgroup_pids *cp = s->private;
+ struct cgroup *cgrp = cp->cgrp;
up_read(&cgrp->pids_mutex);
}
static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct cgroup *cgrp = s->private;
+ struct cgroup_pids *cp = s->private;
int *p = v;
- int *end = cgrp->tasks_pids + cgrp->pids_length;
+ int *end = cp->tasks_pids + cp->length;
/*
* Advance to the next pid in the array. If this goes off the
return seq_printf(s, "%d\n", *(int *)v);
}
-static struct seq_operations cgroup_tasks_seq_operations = {
+static const struct seq_operations cgroup_tasks_seq_operations = {
.start = cgroup_tasks_start,
.stop = cgroup_tasks_stop,
.next = cgroup_tasks_next,
.show = cgroup_tasks_show,
};
-static void release_cgroup_pid_array(struct cgroup *cgrp)
+static void release_cgroup_pid_array(struct cgroup_pids *cp)
{
+ struct cgroup *cgrp = cp->cgrp;
+
down_write(&cgrp->pids_mutex);
- BUG_ON(!cgrp->pids_use_count);
- if (!--cgrp->pids_use_count) {
- kfree(cgrp->tasks_pids);
- cgrp->tasks_pids = NULL;
- cgrp->pids_length = 0;
+ BUG_ON(!cp->use_count);
+ if (!--cp->use_count) {
+ list_del(&cp->list);
+ put_pid_ns(cp->ns);
+ kfree(cp->tasks_pids);
+ kfree(cp);
}
up_write(&cgrp->pids_mutex);
}
static int cgroup_tasks_release(struct inode *inode, struct file *file)
{
- struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
+ struct seq_file *seq;
+ struct cgroup_pids *cp;
if (!(file->f_mode & FMODE_READ))
return 0;
- release_cgroup_pid_array(cgrp);
+ seq = file->private_data;
+ cp = seq->private;
+
+ release_cgroup_pid_array(cp);
return seq_release(inode, file);
}
static int cgroup_tasks_open(struct inode *unused, struct file *file)
{
struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
+ struct pid_namespace *ns = current->nsproxy->pid_ns;
+ struct cgroup_pids *cp;
pid_t *pidarray;
int npids;
int retval;
* array if necessary
*/
down_write(&cgrp->pids_mutex);
- kfree(cgrp->tasks_pids);
- cgrp->tasks_pids = pidarray;
- cgrp->pids_length = npids;
- cgrp->pids_use_count++;
+
+ list_for_each_entry(cp, &cgrp->pids_list, list) {
+ if (ns == cp->ns)
+ goto found;
+ }
+
+ cp = kzalloc(sizeof(*cp), GFP_KERNEL);
+ if (!cp) {
+ up_write(&cgrp->pids_mutex);
+ kfree(pidarray);
+ return -ENOMEM;
+ }
+ cp->cgrp = cgrp;
+ cp->ns = ns;
+ get_pid_ns(ns);
+ list_add(&cp->list, &cgrp->pids_list);
+found:
+ kfree(cp->tasks_pids);
+ cp->tasks_pids = pidarray;
+ cp->length = npids;
+ cp->use_count++;
up_write(&cgrp->pids_mutex);
file->f_op = &cgroup_tasks_operations;
retval = seq_open(file, &cgroup_tasks_seq_operations);
if (retval) {
- release_cgroup_pid_array(cgrp);
+ release_cgroup_pid_array(cp);
return retval;
}
- ((struct seq_file *)file->private_data)->private = cgrp;
+ ((struct seq_file *)file->private_data)->private = cp;
return 0;
}
.write_u64 = cgroup_tasks_write,
.release = cgroup_tasks_release,
.private = FILE_TASKLIST,
+ .mode = S_IRUGO | S_IWUSR,
},
{
if (ss->populate && (err = ss->populate(ss, cgrp)) < 0)
return err;
}
+ /* This cgroup is ready now */
+ for_each_subsys(cgrp->root, ss) {
+ struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+ /*
+ * Update id->css pointer and make this css visible from
+ * CSS ID functions. This pointer will be dereferened
+ * from RCU-read-side without locks.
+ */
+ if (css->id)
+ rcu_assign_pointer(css->id->css, css);
+ }
return 0;
}
struct cgroup *cgrp)
{
css->cgroup = cgrp;
- atomic_set(&css->refcnt, 0);
+ atomic_set(&css->refcnt, 1);
css->flags = 0;
+ css->id = NULL;
if (cgrp == dummytop)
set_bit(CSS_ROOT, &css->flags);
BUG_ON(cgrp->subsys[ss->subsys_id]);
cgrp->subsys[ss->subsys_id] = css;
}
+static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
+{
+ /* We need to take each hierarchy_mutex in a consistent order */
+ int i;
+
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss->root == root)
+ mutex_lock(&ss->hierarchy_mutex);
+ }
+}
+
+static void cgroup_unlock_hierarchy(struct cgroupfs_root *root)
+{
+ int i;
+
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss->root == root)
+ mutex_unlock(&ss->hierarchy_mutex);
+ }
+}
+
/*
* cgroup_create - create a cgroup
* @parent: cgroup that will be parent of the new cgroup
* Must be called with the mutex on the parent inode held
*/
static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
- int mode)
+ mode_t mode)
{
struct cgroup *cgrp;
struct cgroupfs_root *root = parent->root;
goto err_destroy;
}
init_cgroup_css(css, ss, cgrp);
+ if (ss->use_id)
+ if (alloc_css_id(ss, parent, cgrp))
+ goto err_destroy;
+ /* At error, ->destroy() callback has to free assigned ID. */
}
+ cgroup_lock_hierarchy(root);
list_add(&cgrp->sibling, &cgrp->parent->children);
+ cgroup_unlock_hierarchy(root);
root->number_of_cgroups++;
err = cgroup_create_dir(cgrp, dentry, mode);
err_remove:
+ cgroup_lock_hierarchy(root);
list_del(&cgrp->sibling);
+ cgroup_unlock_hierarchy(root);
root->number_of_cgroups--;
err_destroy:
{
/* Check the reference count on each subsystem. Since we
* already established that there are no tasks in the
- * cgroup, if the css refcount is also 0, then there should
+ * cgroup, if the css refcount is also 1, then there should
* be no outstanding references, so the subsystem is safe to
* destroy. We scan across all subsystems rather than using
* the per-hierarchy linked list of mounted subsystems since
* matter, since it can only happen if the cgroup
* has been deleted and hence no longer needs the
* release agent to be called anyway. */
- if (css && atomic_read(&css->refcnt))
+ if (css && (atomic_read(&css->refcnt) > 1))
return 1;
}
return 0;
}
+/*
+ * Atomically mark all (or else none) of the cgroup's CSS objects as
+ * CSS_REMOVED. Return true on success, or false if the cgroup has
+ * busy subsystems. Call with cgroup_mutex held
+ */
+
+static int cgroup_clear_css_refs(struct cgroup *cgrp)
+{
+ struct cgroup_subsys *ss;
+ unsigned long flags;
+ bool failed = false;
+ local_irq_save(flags);
+ for_each_subsys(cgrp->root, ss) {
+ struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+ int refcnt;
+ while (1) {
+ /* We can only remove a CSS with a refcnt==1 */
+ refcnt = atomic_read(&css->refcnt);
+ if (refcnt > 1) {
+ failed = true;
+ goto done;
+ }
+ BUG_ON(!refcnt);
+ /*
+ * Drop the refcnt to 0 while we check other
+ * subsystems. This will cause any racing
+ * css_tryget() to spin until we set the
+ * CSS_REMOVED bits or abort
+ */
+ if (atomic_cmpxchg(&css->refcnt, refcnt, 0) == refcnt)
+ break;
+ cpu_relax();
+ }
+ }
+ done:
+ for_each_subsys(cgrp->root, ss) {
+ struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+ if (failed) {
+ /*
+ * Restore old refcnt if we previously managed
+ * to clear it from 1 to 0
+ */
+ if (!atomic_read(&css->refcnt))
+ atomic_set(&css->refcnt, 1);
+ } else {
+ /* Commit the fact that the CSS is removed */
+ set_bit(CSS_REMOVED, &css->flags);
+ }
+ }
+ local_irq_restore(flags);
+ return !failed;
+}
+
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
{
struct cgroup *cgrp = dentry->d_fsdata;
struct dentry *d;
struct cgroup *parent;
+ DEFINE_WAIT(wait);
+ int ret;
/* the vfs holds both inode->i_mutex already */
-
+again:
mutex_lock(&cgroup_mutex);
if (atomic_read(&cgrp->count) != 0) {
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgroup_mutex);
/*
+ * In general, subsystem has no css->refcnt after pre_destroy(). But
+ * in racy cases, subsystem may have to get css->refcnt after
+ * pre_destroy() and it makes rmdir return with -EBUSY. This sometimes
+ * make rmdir return -EBUSY too often. To avoid that, we use waitqueue
+ * for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir
+ * and subsystem's reference count handling. Please see css_get/put
+ * and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation.
+ */
+ set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+
+ /*
* Call pre_destroy handlers of subsys. Notify subsystems
* that rmdir() request comes.
*/
- cgroup_call_pre_destroy(cgrp);
+ ret = cgroup_call_pre_destroy(cgrp);
+ if (ret) {
+ clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+ return ret;
+ }
mutex_lock(&cgroup_mutex);
parent = cgrp->parent;
-
- if (atomic_read(&cgrp->count)
- || !list_empty(&cgrp->children)
- || cgroup_has_css_refs(cgrp)) {
+ if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
+ clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
mutex_unlock(&cgroup_mutex);
return -EBUSY;
}
+ prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
+ if (!cgroup_clear_css_refs(cgrp)) {
+ mutex_unlock(&cgroup_mutex);
+ /*
+ * Because someone may call cgroup_wakeup_rmdir_waiter() before
+ * prepare_to_wait(), we need to check this flag.
+ */
+ if (test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))
+ schedule();
+ finish_wait(&cgroup_rmdir_waitq, &wait);
+ clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+ if (signal_pending(current))
+ return -EINTR;
+ goto again;
+ }
+ /* NO css_tryget() can success after here. */
+ finish_wait(&cgroup_rmdir_waitq, &wait);
+ clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
spin_lock(&release_list_lock);
set_bit(CGRP_REMOVED, &cgrp->flags);
if (!list_empty(&cgrp->release_list))
list_del(&cgrp->release_list);
spin_unlock(&release_list_lock);
- /* delete my sibling from parent->children */
+
+ cgroup_lock_hierarchy(cgrp->root);
+ /* delete this cgroup from parent->children */
list_del(&cgrp->sibling);
+ cgroup_unlock_hierarchy(cgrp->root);
+
spin_lock(&cgrp->dentry->d_lock);
d = dget(cgrp->dentry);
spin_unlock(&d->d_lock);
printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);
/* Create the top cgroup state for this subsystem */
+ list_add(&ss->sibling, &rootnode.subsys_list);
ss->root = &rootnode;
css = ss->create(ss, dummytop);
/* We don't handle early failures gracefully */
* need to invoke fork callbacks here. */
BUG_ON(!list_empty(&init_task.tasks));
+ mutex_init(&ss->hierarchy_mutex);
+ lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
ss->active = 1;
}
INIT_HLIST_NODE(&init_css_set.hlist);
css_set_count = 1;
init_cgroup_root(&rootnode);
- list_add(&rootnode.root_list, &roots);
root_count = 1;
init_task.cgroups = &init_css_set;
struct cgroup_subsys *ss = subsys[i];
if (!ss->early_init)
cgroup_init_subsys(ss);
+ if (ss->use_id)
+ cgroup_subsys_init_idr(ss);
}
/* Add init_css_set to the hash table */
mutex_lock(&cgroup_mutex);
- for_each_root(root) {
+ for_each_active_root(root) {
struct cgroup_subsys *ss;
struct cgroup *cgrp;
int subsys_id;
int count = 0;
- /* Skip this hierarchy if it has no active subsystems */
- if (!root->actual_subsys_bits)
- continue;
seq_printf(m, "%lu:", root->subsys_bits);
for_each_subsys(root, ss)
seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
+ if (strlen(root->name))
+ seq_printf(m, "%sname=%s", count ? "," : "",
+ root->name);
seq_putc(m, ':');
get_first_subsys(&root->top_cgroup, NULL, &subsys_id);
cgrp = task_cgroup(tsk, subsys_id);
mutex_unlock(&cgroup_mutex);
return 0;
}
- cg = tsk->cgroups;
- parent = task_cgroup(tsk, subsys->subsys_id);
/* Pin the hierarchy */
- if (!atomic_inc_not_zero(&parent->root->sb->s_active)) {
+ if (!atomic_inc_not_zero(&root->sb->s_active)) {
/* We race with the final deactivate_super() */
mutex_unlock(&cgroup_mutex);
return 0;
}
/* Keep the cgroup alive */
+ task_lock(tsk);
+ parent = task_cgroup(tsk, subsys->subsys_id);
+ cg = tsk->cgroups;
get_css_set(cg);
+ task_unlock(tsk);
+
mutex_unlock(&cgroup_mutex);
/* Now do the VFS work to create a cgroup */
mutex_unlock(&inode->i_mutex);
put_css_set(cg);
- deactivate_super(parent->root->sb);
+ deactivate_super(root->sb);
/* The cgroup is still accessible in the VFS, but
* we're not going to try to rmdir() it at this
* point. */
mutex_lock(&cgroup_mutex);
put_css_set(cg);
mutex_unlock(&cgroup_mutex);
- deactivate_super(parent->root->sb);
+ deactivate_super(root->sb);
return ret;
}
/**
- * cgroup_is_descendant - see if @cgrp is a descendant of current task's cgrp
+ * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp
* @cgrp: the cgroup in question
+ * @task: the task in question
*
- * See if @cgrp is a descendant of the current task's cgroup in
- * the appropriate hierarchy.
+ * See if @cgrp is a descendant of @task's cgroup in the appropriate
+ * hierarchy.
*
* If we are sending in dummytop, then presumably we are creating
* the top cgroup in the subsystem.
*
* Called only by the ns (nsproxy) cgroup.
*/
-int cgroup_is_descendant(const struct cgroup *cgrp)
+int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task)
{
int ret;
struct cgroup *target;
return 1;
get_first_subsys(cgrp, NULL, &subsys_id);
- target = task_cgroup(current, subsys_id);
+ target = task_cgroup(task, subsys_id);
while (cgrp != target && cgrp!= cgrp->top_cgroup)
cgrp = cgrp->parent;
ret = (cgrp == target);
{
struct cgroup *cgrp = css->cgroup;
rcu_read_lock();
- if (atomic_dec_and_test(&css->refcnt) && notify_on_release(cgrp)) {
- set_bit(CGRP_RELEASABLE, &cgrp->flags);
- check_for_release(cgrp);
+ if (atomic_dec_return(&css->refcnt) == 1) {
+ if (notify_on_release(cgrp)) {
+ set_bit(CGRP_RELEASABLE, &cgrp->flags);
+ check_for_release(cgrp);
+ }
+ cgroup_wakeup_rmdir_waiter(cgrp);
}
rcu_read_unlock();
}
return 1;
}
__setup("cgroup_disable=", cgroup_disable);
+
+/*
+ * Functons for CSS ID.
+ */
+
+/*
+ *To get ID other than 0, this should be called when !cgroup_is_removed().
+ */
+unsigned short css_id(struct cgroup_subsys_state *css)
+{
+ struct css_id *cssid = rcu_dereference(css->id);
+
+ if (cssid)
+ return cssid->id;
+ return 0;
+}
+
+unsigned short css_depth(struct cgroup_subsys_state *css)
+{
+ struct css_id *cssid = rcu_dereference(css->id);
+
+ if (cssid)
+ return cssid->depth;
+ return 0;
+}
+
+bool css_is_ancestor(struct cgroup_subsys_state *child,
+ const struct cgroup_subsys_state *root)
+{
+ struct css_id *child_id = rcu_dereference(child->id);
+ struct css_id *root_id = rcu_dereference(root->id);
+
+ if (!child_id || !root_id || (child_id->depth < root_id->depth))
+ return false;
+ return child_id->stack[root_id->depth] == root_id->id;
+}
+
+static void __free_css_id_cb(struct rcu_head *head)
+{
+ struct css_id *id;
+
+ id = container_of(head, struct css_id, rcu_head);
+ kfree(id);
+}
+
+void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
+{
+ struct css_id *id = css->id;
+ /* When this is called before css_id initialization, id can be NULL */
+ if (!id)
+ return;
+
+ BUG_ON(!ss->use_id);
+
+ rcu_assign_pointer(id->css, NULL);
+ rcu_assign_pointer(css->id, NULL);
+ spin_lock(&ss->id_lock);
+ idr_remove(&ss->idr, id->id);
+ spin_unlock(&ss->id_lock);
+ call_rcu(&id->rcu_head, __free_css_id_cb);
+}
+
+/*
+ * This is called by init or create(). Then, calls to this function are
+ * always serialized (By cgroup_mutex() at create()).
+ */
+
+static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
+{
+ struct css_id *newid;
+ int myid, error, size;
+
+ BUG_ON(!ss->use_id);
+
+ size = sizeof(*newid) + sizeof(unsigned short) * (depth + 1);
+ newid = kzalloc(size, GFP_KERNEL);
+ if (!newid)
+ return ERR_PTR(-ENOMEM);
+ /* get id */
+ if (unlikely(!idr_pre_get(&ss->idr, GFP_KERNEL))) {
+ error = -ENOMEM;
+ goto err_out;
+ }
+ spin_lock(&ss->id_lock);
+ /* Don't use 0. allocates an ID of 1-65535 */
+ error = idr_get_new_above(&ss->idr, newid, 1, &myid);
+ spin_unlock(&ss->id_lock);
+
+ /* Returns error when there are no free spaces for new ID.*/
+ if (error) {
+ error = -ENOSPC;
+ goto err_out;
+ }
+ if (myid > CSS_ID_MAX)
+ goto remove_idr;
+
+ newid->id = myid;
+ newid->depth = depth;
+ return newid;
+remove_idr:
+ error = -ENOSPC;
+ spin_lock(&ss->id_lock);
+ idr_remove(&ss->idr, myid);
+ spin_unlock(&ss->id_lock);
+err_out:
+ kfree(newid);
+ return ERR_PTR(error);
+
+}
+
+static int __init cgroup_subsys_init_idr(struct cgroup_subsys *ss)
+{
+ struct css_id *newid;
+ struct cgroup_subsys_state *rootcss;
+
+ spin_lock_init(&ss->id_lock);
+ idr_init(&ss->idr);
+
+ rootcss = init_css_set.subsys[ss->subsys_id];
+ newid = get_new_cssid(ss, 0);
+ if (IS_ERR(newid))
+ return PTR_ERR(newid);
+
+ newid->stack[0] = newid->id;
+ newid->css = rootcss;
+ rootcss->id = newid;
+ return 0;
+}
+
+static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent,
+ struct cgroup *child)
+{
+ int subsys_id, i, depth = 0;
+ struct cgroup_subsys_state *parent_css, *child_css;
+ struct css_id *child_id, *parent_id = NULL;
+
+ subsys_id = ss->subsys_id;
+ parent_css = parent->subsys[subsys_id];
+ child_css = child->subsys[subsys_id];
+ depth = css_depth(parent_css) + 1;
+ parent_id = parent_css->id;
+
+ child_id = get_new_cssid(ss, depth);
+ if (IS_ERR(child_id))
+ return PTR_ERR(child_id);
+
+ for (i = 0; i < depth; i++)
+ child_id->stack[i] = parent_id->stack[i];
+ child_id->stack[depth] = child_id->id;
+ /*
+ * child_id->css pointer will be set after this cgroup is available
+ * see cgroup_populate_dir()
+ */
+ rcu_assign_pointer(child_css->id, child_id);
+
+ return 0;
+}
+
+/**
+ * css_lookup - lookup css by id
+ * @ss: cgroup subsys to be looked into.
+ * @id: the id
+ *
+ * Returns pointer to cgroup_subsys_state if there is valid one with id.
+ * NULL if not. Should be called under rcu_read_lock()
+ */
+struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id)
+{
+ struct css_id *cssid = NULL;
+
+ BUG_ON(!ss->use_id);
+ cssid = idr_find(&ss->idr, id);
+
+ if (unlikely(!cssid))
+ return NULL;
+
+ return rcu_dereference(cssid->css);
+}
+
+/**
+ * css_get_next - lookup next cgroup under specified hierarchy.
+ * @ss: pointer to subsystem
+ * @id: current position of iteration.
+ * @root: pointer to css. search tree under this.
+ * @foundid: position of found object.
+ *
+ * Search next css under the specified hierarchy of rootid. Calling under
+ * rcu_read_lock() is necessary. Returns NULL if it reaches the end.
+ */
+struct cgroup_subsys_state *
+css_get_next(struct cgroup_subsys *ss, int id,
+ struct cgroup_subsys_state *root, int *foundid)
+{
+ struct cgroup_subsys_state *ret = NULL;
+ struct css_id *tmp;
+ int tmpid;
+ int rootid = css_id(root);
+ int depth = css_depth(root);
+
+ if (!rootid)
+ return NULL;
+
+ BUG_ON(!ss->use_id);
+ /* fill start point for scan */
+ tmpid = id;
+ while (1) {
+ /*
+ * scan next entry from bitmap(tree), tmpid is updated after
+ * idr_get_next().
+ */
+ spin_lock(&ss->id_lock);
+ tmp = idr_get_next(&ss->idr, &tmpid);
+ spin_unlock(&ss->id_lock);
+
+ if (!tmp)
+ break;
+ if (tmp->depth >= depth && tmp->stack[depth] == rootid) {
+ ret = rcu_dereference(tmp->css);
+ if (ret) {
+ *foundid = tmpid;
+ break;
+ }
+ }
+ /* continue to scan from next id */
+ tmpid = tmpid + 1;
+ }
+ return ret;
+}
+