#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
-#include <linux/backing-dev.h>
#include <linux/slab.h>
-#include <linux/magic.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/sort.h>
#include <linux/delayacct.h>
#include <linux/cgroupstats.h>
#include <linux/hashtable.h>
-#include <linux/namei.h>
#include <linux/pid_namespace.h>
#include <linux/idr.h>
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
*/
#define CGROUP_PIDLIST_DESTROY_DELAY HZ
+#define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \
+ MAX_CFTYPE_NAME + 2)
+
/*
* cgroup_tree_mutex nests above cgroup_mutex and protects cftypes, file
* creation/removal and hierarchy changing operations including cgroup
/* hierarchy ID allocation and mapping, protected by cgroup_mutex */
static DEFINE_IDR(cgroup_hierarchy_idr);
-static struct cgroup_name root_cgroup_name = { .name = "/" };
-
/*
* Assign a monotonically increasing serial number to cgroups. It
* guarantees cgroups with bigger numbers are newer than those with smaller
static struct cftype cgroup_base_files[];
+static void cgroup_put(struct cgroup *cgrp);
+static int rebind_subsystems(struct cgroupfs_root *root,
+ unsigned long added_mask, unsigned removed_mask);
static void cgroup_destroy_css_killed(struct cgroup *cgrp);
static int cgroup_destroy_locked(struct cgroup *cgrp);
static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
bool is_add);
-static int cgroup_file_release(struct inode *inode, struct file *file);
static void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
/**
return test_bit(CGRP_DEAD, &cgrp->flags);
}
+struct cgroup_subsys_state *seq_css(struct seq_file *seq)
+{
+ struct kernfs_open_file *of = seq->private;
+ struct cgroup *cgrp = of->kn->parent->priv;
+ struct cftype *cft = seq_cft(seq);
+
+ /*
+ * This is open and unprotected implementation of cgroup_css().
+ * seq_css() is only called from a kernfs file operation which has
+ * an active reference on the file. Because all the subsystem
+ * files are drained before a css is disassociated with a cgroup,
+ * the matching css from the cgroup's subsys table is guaranteed to
+ * be and stay valid until the enclosing operation is complete.
+ */
+ if (cft->ss)
+ return rcu_dereference_raw(cgrp->subsys[cft->ss->id]);
+ else
+ return &cgrp->dummy_css;
+}
+EXPORT_SYMBOL_GPL(seq_css);
+
/**
* cgroup_is_descendant - test ancestry
* @cgrp: the cgroup to be tested
#define for_each_active_root(root) \
list_for_each_entry((root), &cgroup_roots, root_list)
-static inline struct cgroup *__d_cgrp(struct dentry *dentry)
-{
- return dentry->d_fsdata;
-}
-
-static inline struct cfent *__d_cfe(struct dentry *dentry)
-{
- return dentry->d_fsdata;
-}
-
-static inline struct cftype *__d_cft(struct dentry *dentry)
-{
- return __d_cfe(dentry)->type;
-}
-
/**
* cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
* @cgrp: the cgroup to be checked for liveness
return cset;
}
+static struct cgroupfs_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
+{
+ struct cgroup *top_cgrp = kf_root->kn->priv;
+
+ return top_cgrp->root;
+}
+
+static int cgroup_init_root_id(struct cgroupfs_root *root, int start, int end)
+{
+ int id;
+
+ lockdep_assert_held(&cgroup_mutex);
+
+ id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, start, end,
+ GFP_KERNEL);
+ if (id < 0)
+ return id;
+
+ root->hierarchy_id = id;
+ return 0;
+}
+
+static void cgroup_exit_root_id(struct cgroupfs_root *root)
+{
+ lockdep_assert_held(&cgroup_mutex);
+
+ if (root->hierarchy_id) {
+ idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id);
+ root->hierarchy_id = 0;
+ }
+}
+
+static void cgroup_free_root(struct cgroupfs_root *root)
+{
+ if (root) {
+ /* hierarhcy ID shoulid already have been released */
+ WARN_ON_ONCE(root->hierarchy_id);
+
+ idr_destroy(&root->cgroup_idr);
+ kfree(root);
+ }
+}
+
+static void cgroup_get_root(struct cgroupfs_root *root)
+{
+ /*
+ * The caller must ensure that @root is alive, which can be
+ * achieved by holding a ref on one of the member cgroups or
+ * following a registered reference to @root while holding
+ * cgroup_tree_mutex.
+ */
+ WARN_ON_ONCE(atomic_read(&root->refcnt) <= 0);
+ atomic_inc(&root->refcnt);
+}
+
+static void cgroup_put_root(struct cgroupfs_root *root)
+{
+ struct cgroup *cgrp = &root->top_cgroup;
+ struct cgrp_cset_link *link, *tmp_link;
+ int ret;
+
+ /*
+ * @root's refcnt reaching zero and its deregistration should be
+ * atomic w.r.t. cgroup_tree_mutex. This ensures that
+ * cgroup_get_root() is safe to invoke if @root is registered.
+ */
+ mutex_lock(&cgroup_tree_mutex);
+ if (!atomic_dec_and_test(&root->refcnt)) {
+ mutex_unlock(&cgroup_tree_mutex);
+ return;
+ }
+ mutex_lock(&cgroup_mutex);
+
+ BUG_ON(atomic_read(&root->nr_cgrps) != 1);
+ BUG_ON(!list_empty(&cgrp->children));
+
+ /* Rebind all subsystems back to the default hierarchy */
+ if (root->flags & CGRP_ROOT_SUBSYS_BOUND) {
+ ret = rebind_subsystems(root, 0, root->subsys_mask);
+ /* Shouldn't be able to fail ... */
+ BUG_ON(ret);
+ }
+
+ /*
+ * Release all the links from cset_links to this hierarchy's
+ * root cgroup
+ */
+ write_lock(&css_set_lock);
+
+ list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
+ list_del(&link->cset_link);
+ list_del(&link->cgrp_link);
+ kfree(link);
+ }
+ write_unlock(&css_set_lock);
+
+ if (!list_empty(&root->root_list)) {
+ list_del(&root->root_list);
+ cgroup_root_count--;
+ }
+
+ cgroup_exit_root_id(root);
+
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
+
+ kernfs_destroy_root(root->kf_root);
+ cgroup_free_root(root);
+}
+
/*
* Return the cgroup for "task" from the given hierarchy. Must be
* called with cgroup_mutex held.
* update of a tasks cgroup pointer by cgroup_attach_task()
*/
-/*
- * A couple of forward declarations required, due to cyclic reference loop:
- * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
- * cgroup_add_file -> cgroup_create_file -> cgroup_dir_inode_operations
- * -> cgroup_mkdir.
- */
-
-static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
-static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask);
-static const struct inode_operations cgroup_dir_inode_operations;
+static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
static const 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 struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
+static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
+ char *buf)
{
- struct inode *inode = new_inode(sb);
-
- if (inode) {
- inode->i_ino = get_next_ino();
- inode->i_mode = mode;
- inode->i_uid = current_fsuid();
- inode->i_gid = current_fsgid();
- inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
- }
- return inode;
+ if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) &&
+ !(cgrp->root->flags & CGRP_ROOT_NOPREFIX))
+ snprintf(buf, CGROUP_FILE_NAME_MAX, "%s.%s",
+ cft->ss->name, cft->name);
+ else
+ strncpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
+ return buf;
}
-static struct cgroup_name *cgroup_alloc_name(struct dentry *dentry)
+/**
+ * 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 umode_t cgroup_file_mode(const struct cftype *cft)
{
- struct cgroup_name *name;
+ umode_t mode = 0;
- name = kmalloc(sizeof(*name) + dentry->d_name.len + 1, GFP_KERNEL);
- if (!name)
- return NULL;
- strcpy(name->name, dentry->d_name.name);
- return name;
+ if (cft->mode)
+ return cft->mode;
+
+ if (cft->read_u64 || cft->read_s64 || cft->seq_show)
+ mode |= S_IRUGO;
+
+ if (cft->write_u64 || cft->write_s64 || cft->write_string ||
+ cft->trigger)
+ mode |= S_IWUSR;
+
+ return mode;
}
static void cgroup_free_fn(struct work_struct *work)
{
struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work);
- mutex_lock(&cgroup_mutex);
- cgrp->root->number_of_cgroups--;
- mutex_unlock(&cgroup_mutex);
+ atomic_dec(&cgrp->root->nr_cgrps);
/*
- * We get a ref to the parent's dentry, and put the ref when
- * this cgroup is being freed, so it's guaranteed that the
- * parent won't be destroyed before its children.
+ * We get a ref to the parent, and put the ref when this cgroup is
+ * being freed, so it's guaranteed that the parent won't be
+ * destroyed before its children.
*/
- dput(cgrp->parent->dentry);
+ cgroup_put(cgrp->parent);
- /*
- * Drop the active superblock reference that we took when we
- * created the cgroup. This will free cgrp->root, if we are
- * holding the last reference to @sb.
- */
- deactivate_super(cgrp->root->sb);
+ /* put the root reference that we took when we created the cgroup */
+ cgroup_put_root(cgrp->root);
cgroup_pidlist_destroy_all(cgrp);
- simple_xattrs_free(&cgrp->xattrs);
-
- kfree(rcu_dereference_raw(cgrp->name));
+ kernfs_put(cgrp->kn);
kfree(cgrp);
}
queue_work(cgroup_destroy_wq, &cgrp->destroy_work);
}
-static void cgroup_diput(struct dentry *dentry, struct inode *inode)
+static void cgroup_get(struct cgroup *cgrp)
{
- /* is dentry a directory ? if so, kfree() associated cgroup */
- if (S_ISDIR(inode->i_mode)) {
- struct cgroup *cgrp = dentry->d_fsdata;
-
- BUG_ON(!(cgroup_is_dead(cgrp)));
-
- /*
- * XXX: cgrp->id is only used to look up css's. As cgroup
- * and css's lifetimes will be decoupled, it should be made
- * per-subsystem and moved to css->id so that lookups are
- * successful until the target css is released.
- */
- mutex_lock(&cgroup_mutex);
- idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
- mutex_unlock(&cgroup_mutex);
- cgrp->id = -1;
-
- call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
- } else {
- struct cfent *cfe = __d_cfe(dentry);
- struct cgroup *cgrp = dentry->d_parent->d_fsdata;
-
- WARN_ONCE(!list_empty(&cfe->node) &&
- cgrp != &cgrp->root->top_cgroup,
- "cfe still linked for %s\n", cfe->type->name);
- simple_xattrs_free(&cfe->xattrs);
- kfree(cfe);
- }
- iput(inode);
+ WARN_ON_ONCE(cgroup_is_dead(cgrp));
+ WARN_ON_ONCE(atomic_read(&cgrp->refcnt) <= 0);
+ atomic_inc(&cgrp->refcnt);
}
-static void remove_dir(struct dentry *d)
+static void cgroup_put(struct cgroup *cgrp)
{
- struct dentry *parent = dget(d->d_parent);
+ if (!atomic_dec_and_test(&cgrp->refcnt))
+ return;
+ if (WARN_ON_ONCE(!cgroup_is_dead(cgrp)))
+ return;
+
+ /*
+ * XXX: cgrp->id is only used to look up css's. As cgroup and
+ * css's lifetimes will be decoupled, it should be made
+ * per-subsystem and moved to css->id so that lookups are
+ * successful until the target css is released.
+ */
+ mutex_lock(&cgroup_mutex);
+ idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+ mutex_unlock(&cgroup_mutex);
+ cgrp->id = -1;
- d_delete(d);
- simple_rmdir(parent->d_inode, d);
- dput(parent);
+ call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
}
static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
{
- struct cfent *cfe;
+ char name[CGROUP_FILE_NAME_MAX];
- lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
lockdep_assert_held(&cgroup_tree_mutex);
-
- /*
- * If we're doing cleanup due to failure of cgroup_create(),
- * the corresponding @cfe may not exist.
- */
- list_for_each_entry(cfe, &cgrp->files, node) {
- struct dentry *d = cfe->dentry;
-
- if (cft && cfe->type != cft)
- continue;
-
- dget(d);
- d_delete(d);
- simple_unlink(cgrp->dentry->d_inode, d);
- list_del_init(&cfe->node);
- dput(d);
-
- break;
- }
+ kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
}
/**
int i;
for_each_subsys(ss, i) {
- struct cftype_set *set;
+ struct cftype *cfts;
if (!test_bit(i, &subsys_mask))
continue;
- list_for_each_entry(set, &ss->cftsets, node)
- cgroup_addrm_files(cgrp, set->cfts, false);
+ list_for_each_entry(cfts, &ss->cfts, node)
+ cgroup_addrm_files(cgrp, cfts, false);
}
}
-/*
- * NOTE : the dentry must have been dget()'ed
- */
-static void cgroup_d_remove_dir(struct dentry *dentry)
-{
- struct dentry *parent;
-
- parent = dentry->d_parent;
- spin_lock(&parent->d_lock);
- spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- list_del_init(&dentry->d_u.d_child);
- spin_unlock(&dentry->d_lock);
- spin_unlock(&parent->d_lock);
- remove_dir(dentry);
-}
-
static int rebind_subsystems(struct cgroupfs_root *root,
unsigned long added_mask, unsigned removed_mask)
{
* now matches the bound subsystems.
*/
root->flags |= CGRP_ROOT_SUBSYS_BOUND;
+ kernfs_activate(cgrp->kn);
return 0;
}
-static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
+static int cgroup_show_options(struct seq_file *seq,
+ struct kernfs_root *kf_root)
{
- struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
+ struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
struct cgroup_subsys *ss;
int ssid;
char *name;
/* User explicitly requested empty subsystem */
bool none;
-
- struct cgroupfs_root *new_root;
-
};
/*
pr_err("cgroup: sane_behavior: clone_children is not allowed\n");
return -EINVAL;
}
+
+ if (opts->flags & CGRP_ROOT_XATTR)
+ pr_warning("cgroup: sane_behavior: xattr is always available, flag unnecessary\n");
}
/*
return 0;
}
-static int cgroup_remount(struct super_block *sb, int *flags, char *data)
+static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
{
int ret = 0;
- struct cgroupfs_root *root = sb->s_fs_info;
- struct cgroup *cgrp = &root->top_cgroup;
+ struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
struct cgroup_sb_opts opts;
unsigned long added_mask, removed_mask;
return -EINVAL;
}
- mutex_lock(&cgrp->dentry->d_inode->i_mutex);
mutex_lock(&cgroup_tree_mutex);
mutex_lock(&cgroup_mutex);
}
/* remounting is not allowed for populated hierarchies */
- if (root->number_of_cgroups > 1) {
+ if (!list_empty(&root->top_cgroup.children)) {
ret = -EBUSY;
goto out_unlock;
}
kfree(opts.name);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgroup_tree_mutex);
- mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
return ret;
}
-static const struct super_operations cgroup_ops = {
- .statfs = simple_statfs,
- .drop_inode = generic_delete_inode,
- .show_options = cgroup_show_options,
- .remount_fs = cgroup_remount,
-};
-
static void init_cgroup_housekeeping(struct cgroup *cgrp)
{
+ atomic_set(&cgrp->refcnt, 1);
INIT_LIST_HEAD(&cgrp->sibling);
INIT_LIST_HEAD(&cgrp->children);
- INIT_LIST_HEAD(&cgrp->files);
INIT_LIST_HEAD(&cgrp->cset_links);
INIT_LIST_HEAD(&cgrp->release_list);
INIT_LIST_HEAD(&cgrp->pidlists);
mutex_init(&cgrp->pidlist_mutex);
cgrp->dummy_css.cgroup = cgrp;
- simple_xattrs_init(&cgrp->xattrs);
}
static void init_cgroup_root(struct cgroupfs_root *root)
{
struct cgroup *cgrp = &root->top_cgroup;
+ atomic_set(&root->refcnt, 1);
INIT_LIST_HEAD(&root->root_list);
- root->number_of_cgroups = 1;
+ atomic_set(&root->nr_cgrps, 1);
cgrp->root = root;
- RCU_INIT_POINTER(cgrp->name, &root_cgroup_name);
init_cgroup_housekeeping(cgrp);
idr_init(&root->cgroup_idr);
}
-static int cgroup_init_root_id(struct cgroupfs_root *root, int start, int end)
-{
- int id;
-
- lockdep_assert_held(&cgroup_mutex);
-
- id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, start, end,
- GFP_KERNEL);
- if (id < 0)
- return id;
-
- root->hierarchy_id = id;
- return 0;
-}
-
-static void cgroup_exit_root_id(struct cgroupfs_root *root)
-{
- lockdep_assert_held(&cgroup_mutex);
-
- if (root->hierarchy_id) {
- idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id);
- root->hierarchy_id = 0;
- }
-}
-
-static int cgroup_test_super(struct super_block *sb, void *data)
-{
- struct cgroup_sb_opts *opts = data;
- struct cgroupfs_root *root = sb->s_fs_info;
-
- /* If we asked for a name then it must match */
- if (opts->name && strcmp(opts->name, root->name))
- return 0;
-
- /*
- * If we asked for subsystems (or explicitly for no
- * subsystems) then they must match
- */
- if ((opts->subsys_mask || opts->none)
- && (opts->subsys_mask != root->subsys_mask))
- return 0;
-
- return 1;
-}
-
static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
{
struct cgroupfs_root *root;
if (!opts->subsys_mask && !opts->none)
- return NULL;
+ return ERR_PTR(-EINVAL);
root = kzalloc(sizeof(*root), GFP_KERNEL);
if (!root)
return root;
}
-static void cgroup_free_root(struct cgroupfs_root *root)
-{
- if (root) {
- /* hierarhcy ID shoulid already have been released */
- WARN_ON_ONCE(root->hierarchy_id);
-
- idr_destroy(&root->cgroup_idr);
- kfree(root);
- }
-}
-
-static int cgroup_set_super(struct super_block *sb, void *data)
+static int cgroup_setup_root(struct cgroupfs_root *root)
{
- int ret;
- struct cgroup_sb_opts *opts = data;
+ LIST_HEAD(tmp_links);
+ struct cgroup *root_cgrp = &root->top_cgroup;
+ struct css_set *cset;
+ int i, ret;
- /* If we don't have a new root, we can't set up a new sb */
- if (!opts->new_root)
- return -EINVAL;
+ lockdep_assert_held(&cgroup_tree_mutex);
+ lockdep_assert_held(&cgroup_mutex);
- BUG_ON(!opts->subsys_mask && !opts->none);
+ ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
+ if (ret < 0)
+ goto out;
+ root_cgrp->id = ret;
- ret = set_anon_super(sb, NULL);
+ /*
+ * We're accessing css_set_count without locking css_set_lock here,
+ * but that's OK - it can only be increased by someone holding
+ * cgroup_lock, and that's us. The worst that can happen is that we
+ * have some link structures left over
+ */
+ ret = allocate_cgrp_cset_links(css_set_count, &tmp_links);
if (ret)
- return ret;
-
- 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;
- sb->s_magic = CGROUP_SUPER_MAGIC;
- sb->s_op = &cgroup_ops;
-
- return 0;
-}
-
-static int cgroup_get_rootdir(struct super_block *sb)
-{
- static const struct dentry_operations cgroup_dops = {
- .d_iput = cgroup_diput,
- .d_delete = always_delete_dentry,
- };
-
- struct inode *inode =
- cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);
-
- if (!inode)
- return -ENOMEM;
-
- inode->i_fop = &simple_dir_operations;
- inode->i_op = &cgroup_dir_inode_operations;
- /* directories start off with i_nlink == 2 (for "." entry) */
- inc_nlink(inode);
- sb->s_root = d_make_root(inode);
- if (!sb->s_root)
- return -ENOMEM;
- /* for everything else we want ->d_op set */
- sb->s_d_op = &cgroup_dops;
- return 0;
-}
-
-static int cgroup_setup_root(struct cgroupfs_root *root)
-{
- LIST_HEAD(tmp_links);
- struct super_block *sb = root->sb;
- struct cgroup *root_cgrp = &root->top_cgroup;
- struct cgroupfs_root *existing_root;
- struct css_set *cset;
- struct inode *inode;
- const struct cred *cred;
- int i, ret;
-
- lockdep_assert_held(&cgroup_tree_mutex);
- lockdep_assert_held(&cgroup_mutex);
- BUG_ON(sb->s_root != NULL);
-
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&cgroup_tree_mutex);
-
- ret = cgroup_get_rootdir(sb);
- if (ret) {
- mutex_lock(&cgroup_tree_mutex);
- mutex_lock(&cgroup_mutex);
- return ret;
- }
- inode = sb->s_root->d_inode;
-
- mutex_lock(&inode->i_mutex);
- mutex_lock(&cgroup_tree_mutex);
- mutex_lock(&cgroup_mutex);
-
- ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
- if (ret < 0)
- goto out_unlock;
- root_cgrp->id = ret;
-
- /* check for name clashes with existing mounts */
- ret = -EBUSY;
- if (strlen(root->name))
- for_each_active_root(existing_root)
- if (!strcmp(existing_root->name, root->name))
- goto out_unlock;
-
- /*
- * We're accessing css_set_count without locking css_set_lock here,
- * but that's OK - it can only be increased by someone holding
- * cgroup_lock, and that's us. The worst that can happen is that we
- * have some link structures left over
- */
- ret = allocate_cgrp_cset_links(css_set_count, &tmp_links);
- if (ret)
- goto out_unlock;
+ goto out;
/* ID 0 is reserved for dummy root, 1 for unified hierarchy */
ret = cgroup_init_root_id(root, 2, 0);
if (ret)
- goto out_unlock;
-
- sb->s_root->d_fsdata = root_cgrp;
- root_cgrp->dentry = sb->s_root;
+ goto out;
- /*
- * We're inside get_sb() and will call lookup_one_len() to create
- * the root files, which doesn't work if SELinux is in use. The
- * following cred dancing somehow works around it. See 2ce9738ba
- * ("cgroupfs: use init_cred when populating new cgroupfs mount")
- * for more details.
- */
- cred = override_creds(&init_cred);
+ root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops,
+ KERNFS_ROOT_CREATE_DEACTIVATED,
+ root_cgrp);
+ if (IS_ERR(root->kf_root)) {
+ ret = PTR_ERR(root->kf_root);
+ goto exit_root_id;
+ }
+ root_cgrp->kn = root->kf_root->kn;
ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true);
if (ret)
- goto rm_base_files;
+ goto destroy_root;
ret = rebind_subsystems(root, root->subsys_mask, 0);
if (ret)
- goto rm_base_files;
-
- revert_creds(cred);
+ goto destroy_root;
/*
* There must be no failure case after here, since rebinding takes
write_unlock(&css_set_lock);
BUG_ON(!list_empty(&root_cgrp->children));
- BUG_ON(root->number_of_cgroups != 1);
+ BUG_ON(atomic_read(&root->nr_cgrps) != 1);
+ kernfs_activate(root_cgrp->kn);
ret = 0;
- goto out_unlock;
+ goto out;
-rm_base_files:
- cgroup_addrm_files(&root->top_cgroup, cgroup_base_files, false);
- revert_creds(cred);
+destroy_root:
+ kernfs_destroy_root(root->kf_root);
+ root->kf_root = NULL;
+exit_root_id:
cgroup_exit_root_id(root);
-out_unlock:
- mutex_unlock(&inode->i_mutex);
+out:
free_cgrp_cset_links(&tmp_links);
return ret;
}
int flags, const char *unused_dev_name,
void *data)
{
- struct super_block *sb = NULL;
- struct cgroupfs_root *root = NULL;
+ struct cgroupfs_root *root;
struct cgroup_sb_opts opts;
- struct cgroupfs_root *new_root;
+ struct dentry *dentry;
int ret;
mutex_lock(&cgroup_tree_mutex);
if (ret)
goto out_unlock;
- /*
- * 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_unlock;
- }
- opts.new_root = new_root;
+ /* look for a matching existing root */
+ for_each_active_root(root) {
+ bool name_match = false;
- /* Locate an existing or new sb for this hierarchy */
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&cgroup_tree_mutex);
- sb = sget(fs_type, cgroup_test_super, cgroup_set_super, 0, &opts);
- mutex_lock(&cgroup_tree_mutex);
- mutex_lock(&cgroup_mutex);
- if (IS_ERR(sb)) {
- ret = PTR_ERR(sb);
- cgroup_free_root(opts.new_root);
- goto out_unlock;
- }
+ /*
+ * If we asked for a name then it must match. Also, if
+ * name matches but sybsys_mask doesn't, we should fail.
+ * Remember whether name matched.
+ */
+ if (opts.name) {
+ if (strcmp(opts.name, root->name))
+ continue;
+ name_match = true;
+ }
- root = sb->s_fs_info;
- BUG_ON(!root);
- if (root == opts.new_root) {
- ret = cgroup_setup_root(root);
- if (ret)
- goto out_unlock;
- } else {
/*
- * We re-used an existing hierarchy - the new root (if
- * any) is not needed
+ * If we asked for subsystems (or explicitly for no
+ * subsystems) then they must match.
*/
- cgroup_free_root(opts.new_root);
+ if ((opts.subsys_mask || opts.none) &&
+ (opts.subsys_mask != root->subsys_mask)) {
+ if (!name_match)
+ continue;
+ ret = -EBUSY;
+ goto out_unlock;
+ }
if ((root->flags ^ opts.flags) & CGRP_ROOT_OPTION_MASK) {
if ((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) {
pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n");
}
}
+
+ cgroup_get_root(root);
+ goto out_unlock;
}
- ret = 0;
+ /* no such thing, create a new one */
+ root = cgroup_root_from_opts(&opts);
+ if (IS_ERR(root)) {
+ ret = PTR_ERR(root);
+ goto out_unlock;
+ }
+
+ ret = cgroup_setup_root(root);
+ if (ret)
+ cgroup_free_root(root);
+
out_unlock:
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgroup_tree_mutex);
- if (ret && !IS_ERR_OR_NULL(sb))
- deactivate_locked_super(sb);
-
kfree(opts.release_agent);
kfree(opts.name);
- if (!ret)
- return dget(sb->s_root);
- else
+ if (ret)
return ERR_PTR(ret);
+
+ dentry = kernfs_mount(fs_type, flags, root->kf_root);
+ if (IS_ERR(dentry))
+ cgroup_put_root(root);
+ return dentry;
}
static void cgroup_kill_sb(struct super_block *sb)
{
- struct cgroupfs_root *root = sb->s_fs_info;
- struct cgroup *cgrp = &root->top_cgroup;
- struct cgrp_cset_link *link, *tmp_link;
- int ret;
-
- BUG_ON(!root);
-
- BUG_ON(root->number_of_cgroups != 1);
- BUG_ON(!list_empty(&cgrp->children));
-
- mutex_lock(&cgrp->dentry->d_inode->i_mutex);
- mutex_lock(&cgroup_tree_mutex);
- mutex_lock(&cgroup_mutex);
-
- /* Rebind all subsystems back to the default hierarchy */
- if (root->flags & CGRP_ROOT_SUBSYS_BOUND) {
- ret = rebind_subsystems(root, 0, root->subsys_mask);
- /* Shouldn't be able to fail ... */
- BUG_ON(ret);
- }
-
- /*
- * Release all the links from cset_links to this hierarchy's
- * root cgroup
- */
- write_lock(&css_set_lock);
+ struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
+ struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
- list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
- list_del(&link->cset_link);
- list_del(&link->cgrp_link);
- kfree(link);
- }
- write_unlock(&css_set_lock);
-
- if (!list_empty(&root->root_list)) {
- list_del(&root->root_list);
- cgroup_root_count--;
- }
-
- cgroup_exit_root_id(root);
-
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&cgroup_tree_mutex);
- mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
-
- simple_xattrs_free(&cgrp->xattrs);
-
- kill_litter_super(sb);
- cgroup_free_root(root);
+ cgroup_put_root(root);
+ kernfs_kill_sb(sb);
}
static struct file_system_type cgroup_fs_type = {
static struct kobject *cgroup_kobj;
-/**
- * cgroup_path - generate the path of a cgroup
- * @cgrp: the cgroup in question
- * @buf: the buffer to write the path into
- * @buflen: the length of the buffer
- *
- * Writes path of cgroup into buf. Returns 0 on success, -errno on error.
- *
- * We can't generate cgroup path using dentry->d_name, as accessing
- * dentry->name must be protected by irq-unsafe dentry->d_lock or parent
- * inode's i_mutex, while on the other hand cgroup_path() can be called
- * with some irq-safe spinlocks held.
- */
-int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
-{
- int ret = -ENAMETOOLONG;
- char *start;
-
- if (!cgrp->parent) {
- if (strlcpy(buf, "/", buflen) >= buflen)
- return -ENAMETOOLONG;
- return 0;
- }
-
- start = buf + buflen - 1;
- *start = '\0';
-
- rcu_read_lock();
- do {
- const char *name = cgroup_name(cgrp);
- int len;
-
- len = strlen(name);
- if ((start -= len) < buf)
- goto out;
- memcpy(start, name, len);
-
- if (--start < buf)
- goto out;
- *start = '/';
-
- cgrp = cgrp->parent;
- } while (cgrp->parent);
- ret = 0;
- memmove(buf, start, buf + buflen - start);
-out:
- rcu_read_unlock();
- return ret;
-}
-EXPORT_SYMBOL_GPL(cgroup_path);
-
/**
* task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
* @task: target task
* function grabs cgroup_mutex and shouldn't be used inside locks used by
* cgroup controller callbacks.
*
- * Returns 0 on success, fails with -%ENAMETOOLONG if @buflen is too short.
+ * Return value is the same as kernfs_path().
*/
-int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
+char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
{
struct cgroupfs_root *root;
struct cgroup *cgrp;
- int hierarchy_id = 1, ret = 0;
-
- if (buflen < 2)
- return -ENAMETOOLONG;
+ int hierarchy_id = 1;
+ char *path = NULL;
mutex_lock(&cgroup_mutex);
if (root) {
cgrp = task_cgroup_from_root(task, root);
- ret = cgroup_path(cgrp, buf, buflen);
+ path = cgroup_path(cgrp, buf, buflen);
} else {
/* if no hierarchy exists, everyone is in "/" */
- memcpy(buf, "/", 2);
+ if (strlcpy(buf, "/", buflen) < buflen)
+ path = buf;
}
mutex_unlock(&cgroup_mutex);
- return ret;
+ return path;
}
EXPORT_SYMBOL_GPL(task_cgroup_path);
static int cgroup_release_agent_write(struct cgroup_subsys_state *css,
struct cftype *cft, const char *buffer)
{
- BUILD_BUG_ON(sizeof(css->cgroup->root->release_agent_path) < PATH_MAX);
- if (strlen(buffer) >= PATH_MAX)
- return -EINVAL;
+ struct cgroupfs_root *root = css->cgroup->root;
+
+ BUILD_BUG_ON(sizeof(root->release_agent_path) < PATH_MAX);
if (!cgroup_lock_live_group(css->cgroup))
return -ENODEV;
spin_lock(&release_agent_path_lock);
- strcpy(css->cgroup->root->release_agent_path, buffer);
+ strlcpy(root->release_agent_path, buffer,
+ sizeof(root->release_agent_path));
spin_unlock(&release_agent_path_lock);
mutex_unlock(&cgroup_mutex);
return 0;
return 0;
}
-/* A buffer size big enough for numbers or short strings */
-#define CGROUP_LOCAL_BUFFER_SIZE 64
-
-static ssize_t cgroup_file_write(struct file *file, const char __user *userbuf,
- size_t nbytes, loff_t *ppos)
+static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
+ size_t nbytes, loff_t off)
{
- struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cgroup_subsys_state *css = cfe->css;
- size_t max_bytes = cft->max_write_len ?: CGROUP_LOCAL_BUFFER_SIZE - 1;
- char *buf;
+ struct cgroup *cgrp = of->kn->parent->priv;
+ struct cftype *cft = of->kn->priv;
+ struct cgroup_subsys_state *css;
int ret;
- if (nbytes >= max_bytes)
- return -E2BIG;
-
- buf = kmalloc(nbytes + 1, GFP_KERNEL);
- if (!buf)
- return -ENOMEM;
-
- if (copy_from_user(buf, userbuf, nbytes)) {
- ret = -EFAULT;
- goto out_free;
- }
-
- buf[nbytes] = '\0';
+ /*
+ * kernfs guarantees that a file isn't deleted with operations in
+ * flight, which means that the matching css is and stays alive and
+ * doesn't need to be pinned. The RCU locking is not necessary
+ * either. It's just for the convenience of using cgroup_css().
+ */
+ rcu_read_lock();
+ css = cgroup_css(cgrp, cft->ss);
+ rcu_read_unlock();
if (cft->write_string) {
ret = cft->write_string(css, cft, strstrip(buf));
} else {
ret = -EINVAL;
}
-out_free:
- kfree(buf);
+
return ret ?: nbytes;
}
-/*
- * seqfile ops/methods for returning structured data. Currently just
- * supports string->u64 maps, but can be extended in future.
- */
-
static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
{
- struct cftype *cft = seq_cft(seq);
-
- if (cft->seq_start) {
- return cft->seq_start(seq, ppos);
- } else {
- /*
- * The same behavior and code as single_open(). Returns
- * !NULL if pos is at the beginning; otherwise, NULL.
- */
- return NULL + !*ppos;
- }
+ return seq_cft(seq)->seq_start(seq, ppos);
}
static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos)
{
- struct cftype *cft = seq_cft(seq);
-
- if (cft->seq_next) {
- return cft->seq_next(seq, v, ppos);
- } else {
- /*
- * The same behavior and code as single_open(), always
- * terminate after the initial read.
- */
- ++*ppos;
- return NULL;
- }
+ return seq_cft(seq)->seq_next(seq, v, ppos);
}
static void cgroup_seqfile_stop(struct seq_file *seq, void *v)
{
- struct cftype *cft = seq_cft(seq);
-
- if (cft->seq_stop)
- cft->seq_stop(seq, v);
+ seq_cft(seq)->seq_stop(seq, v);
}
static int cgroup_seqfile_show(struct seq_file *m, void *arg)
{
struct cftype *cft = seq_cft(m);
- struct cgroup_subsys_state *css = seq_css(m);
-
- if (cft->seq_show)
- return cft->seq_show(m, arg);
-
- if (cft->read_u64)
- seq_printf(m, "%llu\n", cft->read_u64(css, cft));
- else if (cft->read_s64)
- seq_printf(m, "%lld\n", cft->read_s64(css, cft));
- else
- return -EINVAL;
- return 0;
-}
-
-static struct seq_operations cgroup_seq_operations = {
- .start = cgroup_seqfile_start,
- .next = cgroup_seqfile_next,
- .stop = cgroup_seqfile_stop,
- .show = cgroup_seqfile_show,
-};
-
-static int cgroup_file_open(struct inode *inode, struct file *file)
-{
- struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cgroup *cgrp = __d_cgrp(cfe->dentry->d_parent);
- struct cgroup_subsys_state *css;
- struct cgroup_open_file *of;
- int err;
-
- err = generic_file_open(inode, file);
- if (err)
- return err;
-
- /*
- * If the file belongs to a subsystem, pin the css. Will be
- * unpinned either on open failure or release. This ensures that
- * @css stays alive for all file operations.
- */
- rcu_read_lock();
- css = cgroup_css(cgrp, cft->ss);
- if (cft->ss && !css_tryget(css))
- css = NULL;
- rcu_read_unlock();
-
- if (!css)
- return -ENODEV;
-
- /*
- * @cfe->css is used by read/write/close to determine the
- * associated css. @file->private_data would be a better place but
- * that's already used by seqfile. Multiple accessors may use it
- * simultaneously which is okay as the association never changes.
- */
- WARN_ON_ONCE(cfe->css && cfe->css != css);
- cfe->css = css;
-
- of = __seq_open_private(file, &cgroup_seq_operations,
- sizeof(struct cgroup_open_file));
- if (of) {
- of->cfe = cfe;
- return 0;
- }
-
- if (css->ss)
- css_put(css);
- return -ENOMEM;
-}
-
-static int cgroup_file_release(struct inode *inode, struct file *file)
-{
- struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cgroup_subsys_state *css = cfe->css;
-
- if (css->ss)
- css_put(css);
- return seq_release_private(inode, file);
-}
-
-/*
- * cgroup_rename - Only allow simple rename of directories in place.
- */
-static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
-{
- int ret;
- struct cgroup_name *name, *old_name;
- struct cgroup *cgrp;
-
- /*
- * It's convinient to use parent dir's i_mutex to protected
- * cgrp->name.
- */
- lockdep_assert_held(&old_dir->i_mutex);
-
- if (!S_ISDIR(old_dentry->d_inode->i_mode))
- return -ENOTDIR;
- if (new_dentry->d_inode)
- return -EEXIST;
- if (old_dir != new_dir)
- return -EIO;
-
- cgrp = __d_cgrp(old_dentry);
-
- /*
- * This isn't a proper migration and its usefulness is very
- * limited. Disallow if sane_behavior.
- */
- if (cgroup_sane_behavior(cgrp))
- return -EPERM;
-
- name = cgroup_alloc_name(new_dentry);
- if (!name)
- return -ENOMEM;
-
- ret = simple_rename(old_dir, old_dentry, new_dir, new_dentry);
- if (ret) {
- kfree(name);
- return ret;
- }
-
- old_name = rcu_dereference_protected(cgrp->name, true);
- rcu_assign_pointer(cgrp->name, name);
-
- kfree_rcu(old_name, rcu_head);
- return 0;
-}
-
-static struct simple_xattrs *__d_xattrs(struct dentry *dentry)
-{
- if (S_ISDIR(dentry->d_inode->i_mode))
- return &__d_cgrp(dentry)->xattrs;
- else
- return &__d_cfe(dentry)->xattrs;
-}
-
-static inline int xattr_enabled(struct dentry *dentry)
-{
- struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
- return root->flags & CGRP_ROOT_XATTR;
-}
-
-static bool is_valid_xattr(const char *name)
-{
- if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
- !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN))
- return true;
- return false;
-}
-
-static int cgroup_setxattr(struct dentry *dentry, const char *name,
- const void *val, size_t size, int flags)
-{
- if (!xattr_enabled(dentry))
- return -EOPNOTSUPP;
- if (!is_valid_xattr(name))
- return -EINVAL;
- return simple_xattr_set(__d_xattrs(dentry), name, val, size, flags);
-}
-
-static int cgroup_removexattr(struct dentry *dentry, const char *name)
-{
- if (!xattr_enabled(dentry))
- return -EOPNOTSUPP;
- if (!is_valid_xattr(name))
- return -EINVAL;
- return simple_xattr_remove(__d_xattrs(dentry), name);
-}
-
-static ssize_t cgroup_getxattr(struct dentry *dentry, const char *name,
- void *buf, size_t size)
-{
- if (!xattr_enabled(dentry))
- return -EOPNOTSUPP;
- if (!is_valid_xattr(name))
- return -EINVAL;
- return simple_xattr_get(__d_xattrs(dentry), name, buf, size);
-}
-
-static ssize_t cgroup_listxattr(struct dentry *dentry, char *buf, size_t size)
-{
- if (!xattr_enabled(dentry))
- return -EOPNOTSUPP;
- return simple_xattr_list(__d_xattrs(dentry), buf, size);
-}
-
-static const struct file_operations cgroup_file_operations = {
- .read = seq_read,
- .write = cgroup_file_write,
- .llseek = generic_file_llseek,
- .open = cgroup_file_open,
- .release = cgroup_file_release,
-};
-
-static const struct inode_operations cgroup_file_inode_operations = {
- .setxattr = cgroup_setxattr,
- .getxattr = cgroup_getxattr,
- .listxattr = cgroup_listxattr,
- .removexattr = cgroup_removexattr,
-};
-
-static const struct inode_operations cgroup_dir_inode_operations = {
- .lookup = simple_lookup,
- .mkdir = cgroup_mkdir,
- .rmdir = cgroup_rmdir,
- .rename = cgroup_rename,
- .setxattr = cgroup_setxattr,
- .getxattr = cgroup_getxattr,
- .listxattr = cgroup_listxattr,
- .removexattr = cgroup_removexattr,
-};
-
-static int cgroup_create_file(struct dentry *dentry, umode_t mode,
- struct super_block *sb)
-{
- struct inode *inode;
-
- if (!dentry)
- return -ENOENT;
- if (dentry->d_inode)
- return -EEXIST;
-
- inode = cgroup_new_inode(mode, sb);
- if (!inode)
- return -ENOMEM;
-
- if (S_ISDIR(mode)) {
- inode->i_op = &cgroup_dir_inode_operations;
- inode->i_fop = &simple_dir_operations;
+ struct cgroup_subsys_state *css = seq_css(m);
- /* start off with i_nlink == 2 (for "." entry) */
- inc_nlink(inode);
- inc_nlink(dentry->d_parent->d_inode);
+ if (cft->seq_show)
+ return cft->seq_show(m, arg);
- /*
- * Control reaches here with cgroup_mutex held.
- * @inode->i_mutex should nest outside cgroup_mutex but we
- * want to populate it immediately without releasing
- * cgroup_mutex. As @inode isn't visible to anyone else
- * yet, trylock will always succeed without affecting
- * lockdep checks.
- */
- WARN_ON_ONCE(!mutex_trylock(&inode->i_mutex));
- } else if (S_ISREG(mode)) {
- inode->i_size = 0;
- inode->i_fop = &cgroup_file_operations;
- inode->i_op = &cgroup_file_inode_operations;
- }
- d_instantiate(dentry, inode);
- dget(dentry); /* Extra count - pin the dentry in core */
+ if (cft->read_u64)
+ seq_printf(m, "%llu\n", cft->read_u64(css, cft));
+ else if (cft->read_s64)
+ seq_printf(m, "%lld\n", cft->read_s64(css, cft));
+ else
+ return -EINVAL;
return 0;
}
-/**
- * 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 struct kernfs_ops cgroup_kf_single_ops = {
+ .atomic_write_len = PAGE_SIZE,
+ .write = cgroup_file_write,
+ .seq_show = cgroup_seqfile_show,
+};
+
+static struct kernfs_ops cgroup_kf_ops = {
+ .atomic_write_len = PAGE_SIZE,
+ .write = cgroup_file_write,
+ .seq_start = cgroup_seqfile_start,
+ .seq_next = cgroup_seqfile_next,
+ .seq_stop = cgroup_seqfile_stop,
+ .seq_show = cgroup_seqfile_show,
+};
+
+/*
+ * cgroup_rename - Only allow simple rename of directories in place.
*/
-static umode_t cgroup_file_mode(const struct cftype *cft)
+static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
+ const char *new_name_str)
{
- umode_t mode = 0;
+ struct cgroup *cgrp = kn->priv;
+ int ret;
- if (cft->mode)
- return cft->mode;
+ if (kernfs_type(kn) != KERNFS_DIR)
+ return -ENOTDIR;
+ if (kn->parent != new_parent)
+ return -EIO;
- if (cft->read_u64 || cft->read_s64 || cft->seq_show)
- mode |= S_IRUGO;
+ /*
+ * This isn't a proper migration and its usefulness is very
+ * limited. Disallow if sane_behavior.
+ */
+ if (cgroup_sane_behavior(cgrp))
+ return -EPERM;
- if (cft->write_u64 || cft->write_s64 || cft->write_string ||
- cft->trigger)
- mode |= S_IWUSR;
+ mutex_lock(&cgroup_tree_mutex);
+ mutex_lock(&cgroup_mutex);
- return mode;
+ ret = kernfs_rename(kn, new_parent, new_name_str);
+
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
+ return ret;
}
static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft)
{
- struct dentry *dir = cgrp->dentry;
- struct cgroup *parent = __d_cgrp(dir);
- struct dentry *dentry;
- struct cfent *cfe;
- int error;
- umode_t mode;
- char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
-
- if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) &&
- !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) {
- strcpy(name, cft->ss->name);
- strcat(name, ".");
- }
- strcat(name, cft->name);
-
- BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));
+ char name[CGROUP_FILE_NAME_MAX];
+ struct kernfs_node *kn;
+ struct lock_class_key *key = NULL;
- cfe = kzalloc(sizeof(*cfe), GFP_KERNEL);
- if (!cfe)
- return -ENOMEM;
-
- dentry = lookup_one_len(name, dir, strlen(name));
- if (IS_ERR(dentry)) {
- error = PTR_ERR(dentry);
- goto out;
- }
-
- cfe->type = (void *)cft;
- cfe->dentry = dentry;
- dentry->d_fsdata = cfe;
- simple_xattrs_init(&cfe->xattrs);
-
- mode = cgroup_file_mode(cft);
- error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb);
- if (!error) {
- list_add_tail(&cfe->node, &parent->files);
- cfe = NULL;
- }
- dput(dentry);
-out:
- kfree(cfe);
- return error;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ key = &cft->lockdep_key;
+#endif
+ kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name),
+ cgroup_file_mode(cft), 0, cft->kf_ops, cft,
+ NULL, false, key);
+ if (IS_ERR(kn))
+ return PTR_ERR(kn);
+ return 0;
}
/**
struct cftype *cft;
int ret;
- lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
lockdep_assert_held(&cgroup_tree_mutex);
for (cft = cfts; cft->name[0] != '\0'; cft++) {
return 0;
}
-static void cgroup_cfts_prepare(void)
- __acquires(&cgroup_mutex)
-{
- /*
- * Thanks to the entanglement with vfs inode locking, we can't walk
- * the existing cgroups under cgroup_mutex and create files.
- * Instead, we use css_for_each_descendant_pre() and drop RCU read
- * lock before calling cgroup_addrm_files().
- */
- mutex_lock(&cgroup_tree_mutex);
- mutex_lock(&cgroup_mutex);
-}
-
-static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
- __releases(&cgroup_mutex)
+static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add)
{
LIST_HEAD(pending);
struct cgroup_subsys *ss = cfts[0].ss;
struct cgroup *root = &ss->root->top_cgroup;
- struct super_block *sb = ss->root->sb;
- struct dentry *prev = NULL;
- struct inode *inode;
struct cgroup_subsys_state *css;
- u64 update_before;
int ret = 0;
- mutex_unlock(&cgroup_mutex);
+ lockdep_assert_held(&cgroup_tree_mutex);
- /* %NULL @cfts indicates abort and don't bother if @ss isn't attached */
- if (!cfts || ss->root == &cgroup_dummy_root ||
- !atomic_inc_not_zero(&sb->s_active)) {
- mutex_unlock(&cgroup_tree_mutex);
+ /* don't bother if @ss isn't attached */
+ if (ss->root == &cgroup_dummy_root)
return 0;
- }
-
- /*
- * All cgroups which are created after we drop cgroup_mutex will
- * have the updated set of files, so we only need to update the
- * cgroups created before the current @cgroup_serial_nr_next.
- */
- update_before = cgroup_serial_nr_next;
/* add/rm files for all cgroups created before */
css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
if (cgroup_is_dead(cgrp))
continue;
- inode = cgrp->dentry->d_inode;
- dget(cgrp->dentry);
- dput(prev);
- prev = cgrp->dentry;
-
- mutex_unlock(&cgroup_tree_mutex);
- mutex_lock(&inode->i_mutex);
- mutex_lock(&cgroup_tree_mutex);
- if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp))
- ret = cgroup_addrm_files(cgrp, cfts, is_add);
- mutex_unlock(&inode->i_mutex);
+ ret = cgroup_addrm_files(cgrp, cfts, is_add);
if (ret)
break;
}
- mutex_unlock(&cgroup_tree_mutex);
- dput(prev);
- deactivate_super(sb);
+
+ if (is_add && !ret)
+ kernfs_activate(root->kn);
return ret;
}
-/**
- * cgroup_add_cftypes - add an array of cftypes to a subsystem
- * @ss: target cgroup subsystem
- * @cfts: zero-length name terminated array of cftypes
- *
- * Register @cfts to @ss. Files described by @cfts are created for all
- * existing cgroups to which @ss is attached and all future cgroups will
- * have them too. This function can be called anytime whether @ss is
- * attached or not.
- *
- * Returns 0 on successful registration, -errno on failure. Note that this
- * function currently returns 0 as long as @cfts registration is successful
- * even if some file creation attempts on existing cgroups fail.
- */
-int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+static void cgroup_exit_cftypes(struct cftype *cfts)
{
- struct cftype_set *set;
struct cftype *cft;
- int ret;
- set = kzalloc(sizeof(*set), GFP_KERNEL);
- if (!set)
- return -ENOMEM;
+ for (cft = cfts; cft->name[0] != '\0'; cft++) {
+ /* free copy for custom atomic_write_len, see init_cftypes() */
+ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE)
+ kfree(cft->kf_ops);
+ cft->kf_ops = NULL;
+ cft->ss = NULL;
+ }
+}
+
+static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+{
+ struct cftype *cft;
+
+ for (cft = cfts; cft->name[0] != '\0'; cft++) {
+ struct kernfs_ops *kf_ops;
+
+ WARN_ON(cft->ss || cft->kf_ops);
+
+ if (cft->seq_start)
+ kf_ops = &cgroup_kf_ops;
+ else
+ kf_ops = &cgroup_kf_single_ops;
- for (cft = cfts; cft->name[0] != '\0'; cft++)
+ /*
+ * Ugh... if @cft wants a custom max_write_len, we need to
+ * make a copy of kf_ops to set its atomic_write_len.
+ */
+ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) {
+ kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL);
+ if (!kf_ops) {
+ cgroup_exit_cftypes(cfts);
+ return -ENOMEM;
+ }
+ kf_ops->atomic_write_len = cft->max_write_len;
+ }
+
+ cft->kf_ops = kf_ops;
cft->ss = ss;
+ }
- cgroup_cfts_prepare();
- set->cfts = cfts;
- list_add_tail(&set->node, &ss->cftsets);
- ret = cgroup_cfts_commit(cfts, true);
- if (ret)
- cgroup_rm_cftypes(cfts);
- return ret;
+ return 0;
+}
+
+static int cgroup_rm_cftypes_locked(struct cftype *cfts)
+{
+ lockdep_assert_held(&cgroup_tree_mutex);
+
+ if (!cfts || !cfts[0].ss)
+ return -ENOENT;
+
+ list_del(&cfts->node);
+ cgroup_apply_cftypes(cfts, false);
+ cgroup_exit_cftypes(cfts);
+ return 0;
}
-EXPORT_SYMBOL_GPL(cgroup_add_cftypes);
/**
* cgroup_rm_cftypes - remove an array of cftypes from a subsystem
*/
int cgroup_rm_cftypes(struct cftype *cfts)
{
- struct cftype_set *set;
+ int ret;
- if (!cfts || !cfts[0].ss)
- return -ENOENT;
+ mutex_lock(&cgroup_tree_mutex);
+ ret = cgroup_rm_cftypes_locked(cfts);
+ mutex_unlock(&cgroup_tree_mutex);
+ return ret;
+}
- cgroup_cfts_prepare();
+/**
+ * cgroup_add_cftypes - add an array of cftypes to a subsystem
+ * @ss: target cgroup subsystem
+ * @cfts: zero-length name terminated array of cftypes
+ *
+ * Register @cfts to @ss. Files described by @cfts are created for all
+ * existing cgroups to which @ss is attached and all future cgroups will
+ * have them too. This function can be called anytime whether @ss is
+ * attached or not.
+ *
+ * Returns 0 on successful registration, -errno on failure. Note that this
+ * function currently returns 0 as long as @cfts registration is successful
+ * even if some file creation attempts on existing cgroups fail.
+ */
+int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+{
+ int ret;
- list_for_each_entry(set, &cfts[0].ss->cftsets, node) {
- if (set->cfts == cfts) {
- list_del(&set->node);
- kfree(set);
- cgroup_cfts_commit(cfts, false);
- return 0;
- }
- }
+ ret = cgroup_init_cftypes(ss, cfts);
+ if (ret)
+ return ret;
- cgroup_cfts_commit(NULL, false);
- return -ENOENT;
+ mutex_lock(&cgroup_tree_mutex);
+
+ list_add_tail(&cfts->node, &ss->cfts);
+ ret = cgroup_apply_cftypes(cfts, true);
+ if (ret)
+ cgroup_rm_cftypes_locked(cfts);
+
+ mutex_unlock(&cgroup_tree_mutex);
+ return ret;
}
+EXPORT_SYMBOL_GPL(cgroup_add_cftypes);
/**
* cgroup_task_count - count the number of tasks in a cgroup.
*/
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
{
- int ret = -EINVAL;
+ struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
struct cgroup *cgrp;
struct css_task_iter it;
struct task_struct *tsk;
+ /* it should be kernfs_node belonging to cgroupfs and is a directory */
+ if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
+ kernfs_type(kn) != KERNFS_DIR)
+ return -EINVAL;
+
/*
- * Validate dentry by checking the superblock operations,
- * and make sure it's a directory.
+ * We aren't being called from kernfs and there's no guarantee on
+ * @kn->priv's validity. For this and css_tryget_from_dir(),
+ * @kn->priv is RCU safe. Let's do the RCU dancing.
*/
- if (dentry->d_sb->s_op != &cgroup_ops ||
- !S_ISDIR(dentry->d_inode->i_mode))
- goto err;
-
- ret = 0;
- cgrp = dentry->d_fsdata;
+ rcu_read_lock();
+ cgrp = rcu_dereference(kn->priv);
+ if (!cgrp) {
+ rcu_read_unlock();
+ return -ENOENT;
+ }
css_task_iter_start(&cgrp->dummy_css, &it);
while ((tsk = css_task_iter_next(&it))) {
}
css_task_iter_end(&it);
-err:
- return ret;
+ rcu_read_unlock();
+ return 0;
}
* after a seek to the start). Use a binary-search to find the
* next pid to display, if any
*/
- struct cgroup_open_file *of = s->private;
+ struct kernfs_open_file *of = s->private;
struct cgroup *cgrp = seq_css(s)->cgroup;
struct cgroup_pidlist *l;
enum cgroup_filetype type = seq_cft(s)->private;
static void cgroup_pidlist_stop(struct seq_file *s, void *v)
{
- struct cgroup_open_file *of = s->private;
+ struct kernfs_open_file *of = s->private;
struct cgroup_pidlist *l = of->priv;
if (l)
static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct cgroup_open_file *of = s->private;
+ struct kernfs_open_file *of = s->private;
struct cgroup_pidlist *l = of->priv;
pid_t *p = v;
pid_t *end = l->list + l->length;
return 0;
}
-/*
- * When dput() is called asynchronously, if umount has been done and
- * then deactivate_super() in cgroup_free_fn() kills the superblock,
- * there's a small window that vfs will see the root dentry with non-zero
- * refcnt and trigger BUG().
- *
- * That's why we hold a reference before dput() and drop it right after.
- */
-static void cgroup_dput(struct cgroup *cgrp)
-{
- struct super_block *sb = cgrp->root->sb;
-
- atomic_inc(&sb->s_active);
- dput(cgrp->dentry);
- deactivate_super(sb);
-}
-
static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
.flags = CFTYPE_INSANE | CFTYPE_ONLY_ON_ROOT,
.seq_show = cgroup_release_agent_show,
.write_string = cgroup_release_agent_write,
- .max_write_len = PATH_MAX,
+ .max_write_len = PATH_MAX - 1,
},
{ } /* terminate */
};
/* process cftsets of each subsystem */
for_each_subsys(ss, i) {
- struct cftype_set *set;
+ struct cftype *cfts;
if (!test_bit(i, &subsys_mask))
continue;
- list_for_each_entry(set, &ss->cftsets, node) {
- ret = cgroup_addrm_files(cgrp, set->cfts, true);
+ list_for_each_entry(cfts, &ss->cfts, node) {
+ ret = cgroup_addrm_files(cgrp, cfts, true);
if (ret < 0)
goto err;
}
css_put(css->parent);
css->ss->css_free(css);
- cgroup_dput(cgrp);
+ cgroup_put(cgrp);
}
static void css_free_rcu_fn(struct rcu_head *rcu_head)
struct cgroup_subsys_state *css =
container_of(rcu_head, struct cgroup_subsys_state, rcu_head);
- /*
- * css holds an extra ref to @cgrp->dentry which is put on the last
- * css_put(). dput() requires process context which we don't have.
- */
INIT_WORK(&css->destroy_work, css_free_work_fn);
queue_work(cgroup_destroy_wq, &css->destroy_work);
}
struct cgroup_subsys_state *css;
int err;
- lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
lockdep_assert_held(&cgroup_mutex);
css = ss->css_alloc(cgroup_css(parent, ss));
if (err)
goto err_free;
- dget(cgrp->dentry);
+ cgroup_get(cgrp);
css_get(css->parent);
if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
return err;
}
-/*
+/**
* cgroup_create - create a cgroup
* @parent: cgroup that will be parent of the new cgroup
- * @dentry: dentry of the new cgroup
- * @mode: mode to set on new inode
- *
- * Must be called with the mutex on the parent inode held
+ * @name: name of the new cgroup
+ * @mode: mode to set on new cgroup
*/
-static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
- umode_t mode)
+static long cgroup_create(struct cgroup *parent, const char *name,
+ umode_t mode)
{
struct cgroup *cgrp;
- struct cgroup_name *name;
struct cgroupfs_root *root = parent->root;
int ssid, err;
struct cgroup_subsys *ss;
- struct super_block *sb = root->sb;
+ struct kernfs_node *kn;
/* allocate the cgroup and its ID, 0 is reserved for the root */
cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
if (!cgrp)
return -ENOMEM;
- name = cgroup_alloc_name(dentry);
- if (!name) {
- err = -ENOMEM;
- goto err_free_cgrp;
- }
- rcu_assign_pointer(cgrp->name, name);
-
mutex_lock(&cgroup_tree_mutex);
/*
goto err_unlock;
}
- /* Grab a reference on the superblock so the hierarchy doesn't
- * get deleted on unmount if there are child cgroups. This
- * can be done outside cgroup_mutex, since the sb can't
- * disappear while someone has an open control file on the
- * fs */
- atomic_inc(&sb->s_active);
-
init_cgroup_housekeeping(cgrp);
- dentry->d_fsdata = cgrp;
- cgrp->dentry = dentry;
-
cgrp->parent = parent;
cgrp->dummy_css.parent = &parent->dummy_css;
cgrp->root = parent->root;
if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
+ /* create the directory */
+ kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
+ if (IS_ERR(kn)) {
+ err = PTR_ERR(kn);
+ goto err_free_id;
+ }
+ cgrp->kn = kn;
+
/*
- * Create directory. cgroup_create_file() returns with the new
- * directory locked on success so that it can be populated without
- * dropping cgroup_mutex.
+ * This extra ref will be put in cgroup_free_fn() and guarantees
+ * that @cgrp->kn is always accessible.
*/
- err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
- if (err < 0)
- goto err_free_id;
- lockdep_assert_held(&dentry->d_inode->i_mutex);
+ kernfs_get(kn);
cgrp->serial_nr = cgroup_serial_nr_next++;
/* allocation complete, commit to creation */
list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
- root->number_of_cgroups++;
+ atomic_inc(&root->nr_cgrps);
- /* hold a ref to the parent's dentry */
- dget(parent->dentry);
+ /*
+ * Grab a reference on the root and parent so that they don't get
+ * deleted while there are child cgroups.
+ */
+ cgroup_get_root(root);
+ cgroup_get(parent);
/*
* @cgrp is now fully operational. If something fails after this
}
}
+ kernfs_activate(kn);
+
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgroup_tree_mutex);
- mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
return 0;
err_free_id:
idr_remove(&root->cgroup_idr, cgrp->id);
- /* Release the reference count that we took on the superblock */
- deactivate_super(sb);
err_unlock:
mutex_unlock(&cgroup_mutex);
err_unlock_tree:
mutex_unlock(&cgroup_tree_mutex);
- kfree(rcu_dereference_raw(cgrp->name));
-err_free_cgrp:
kfree(cgrp);
return err;
cgroup_destroy_locked(cgrp);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgroup_tree_mutex);
- mutex_unlock(&dentry->d_inode->i_mutex);
return err;
}
-static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
+ umode_t mode)
{
- struct cgroup *c_parent = dentry->d_parent->d_fsdata;
+ struct cgroup *parent = parent_kn->priv;
- /* the vfs holds inode->i_mutex already */
- return cgroup_create(c_parent, dentry, mode | S_IFDIR);
+ return cgroup_create(parent, name, mode);
}
/*
*/
static void kill_css(struct cgroup_subsys_state *css)
{
+ /*
+ * This must happen before css is disassociated with its cgroup.
+ * See seq_css() for details.
+ */
cgroup_clear_dir(css->cgroup, 1 << css->ss->id);
/*
static int cgroup_destroy_locked(struct cgroup *cgrp)
__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
{
- struct dentry *d = cgrp->dentry;
- struct cgroup_subsys_state *css;
struct cgroup *child;
+ struct cgroup_subsys_state *css;
bool empty;
int ssid;
- lockdep_assert_held(&d->d_inode->i_mutex);
lockdep_assert_held(&cgroup_tree_mutex);
lockdep_assert_held(&cgroup_mutex);
if (!cgrp->nr_css)
cgroup_destroy_css_killed(cgrp);
+ /* remove @cgrp directory along with the base files */
+ mutex_unlock(&cgroup_mutex);
+
/*
- * Clear the base files and remove @cgrp directory. The removal
- * puts the base ref but we aren't quite done with @cgrp yet, so
- * hold onto it.
+ * There are two control paths which try to determine cgroup from
+ * dentry without going through kernfs - cgroupstats_build() and
+ * css_tryget_from_dir(). Those are supported by RCU protecting
+ * clearing of cgrp->kn->priv backpointer, which should happen
+ * after all files under it have been removed.
*/
- mutex_unlock(&cgroup_mutex);
- cgroup_addrm_files(cgrp, cgroup_base_files, false);
- dget(d);
- cgroup_d_remove_dir(d);
+ kernfs_remove(cgrp->kn); /* @cgrp has an extra ref on its kn */
+ RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);
+
mutex_lock(&cgroup_mutex);
return 0;
static void cgroup_destroy_css_killed(struct cgroup *cgrp)
{
struct cgroup *parent = cgrp->parent;
- struct dentry *d = cgrp->dentry;
lockdep_assert_held(&cgroup_tree_mutex);
lockdep_assert_held(&cgroup_mutex);
/* delete this cgroup from parent->children */
list_del_rcu(&cgrp->sibling);
- dput(d);
+ cgroup_put(cgrp);
set_bit(CGRP_RELEASABLE, &parent->flags);
check_for_release(parent);
}
-static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
+static int cgroup_rmdir(struct kernfs_node *kn)
{
- int ret;
+ struct cgroup *cgrp = kn->priv;
+ int ret = 0;
+
+ /*
+ * This is self-destruction but @kn can't be removed while this
+ * callback is in progress. Let's break active protection. Once
+ * the protection is broken, @cgrp can be destroyed at any point.
+ * Pin it so that it stays accessible.
+ */
+ cgroup_get(cgrp);
+ kernfs_break_active_protection(kn);
mutex_lock(&cgroup_tree_mutex);
mutex_lock(&cgroup_mutex);
- ret = cgroup_destroy_locked(dentry->d_fsdata);
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&cgroup_tree_mutex);
-
- return ret;
-}
-
-static void __init cgroup_init_cftsets(struct cgroup_subsys *ss)
-{
- INIT_LIST_HEAD(&ss->cftsets);
/*
- * base_cftset is embedded in subsys itself, no need to worry about
- * deregistration.
+ * @cgrp might already have been destroyed while we're trying to
+ * grab the mutexes.
*/
- if (ss->base_cftypes) {
- struct cftype *cft;
+ if (!cgroup_is_dead(cgrp))
+ ret = cgroup_destroy_locked(cgrp);
- for (cft = ss->base_cftypes; cft->name[0] != '\0'; cft++)
- cft->ss = ss;
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
- ss->base_cftset.cfts = ss->base_cftypes;
- list_add_tail(&ss->base_cftset.node, &ss->cftsets);
- }
+ kernfs_unbreak_active_protection(kn);
+ cgroup_put(cgrp);
+ return ret;
}
+static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
+ .remount_fs = cgroup_remount,
+ .show_options = cgroup_show_options,
+ .mkdir = cgroup_mkdir,
+ .rmdir = cgroup_rmdir,
+ .rename = cgroup_rename,
+};
+
static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
{
struct cgroup_subsys_state *css;
mutex_lock(&cgroup_tree_mutex);
mutex_lock(&cgroup_mutex);
- /* init base cftset */
- cgroup_init_cftsets(ss);
+ INIT_LIST_HEAD(&ss->cfts);
/* Create the top cgroup state for this subsystem */
ss->root = &cgroup_dummy_root;
unsigned long key;
int i, err;
- err = bdi_init(&cgroup_backing_dev_info);
- if (err)
- return err;
+ BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
for_each_subsys(ss, i) {
if (!ss->early_init)
cgroup_init_subsys(ss);
+
+ /*
+ * cftype registration needs kmalloc and can't be done
+ * during early_init. Register base cftypes separately.
+ */
+ if (ss->base_cftypes)
+ WARN_ON(cgroup_add_cftypes(ss, ss->base_cftypes));
}
/* allocate id for the dummy hierarchy */
mutex_unlock(&cgroup_mutex);
cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
- if (!cgroup_kobj) {
- err = -ENOMEM;
- goto out;
- }
+ if (!cgroup_kobj)
+ return -ENOMEM;
err = register_filesystem(&cgroup_fs_type);
if (err < 0) {
kobject_put(cgroup_kobj);
- goto out;
+ return err;
}
proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations);
-
-out:
- if (err)
- bdi_destroy(&cgroup_backing_dev_info);
-
- return err;
+ return 0;
}
static int __init cgroup_wq_init(void)
{
struct pid *pid;
struct task_struct *tsk;
- char *buf;
+ char *buf, *path;
int retval;
struct cgroupfs_root *root;
retval = -ENOMEM;
- buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ buf = kmalloc(PATH_MAX, GFP_KERNEL);
if (!buf)
goto out;
root->name);
seq_putc(m, ':');
cgrp = task_cgroup_from_root(tsk, root);
- retval = cgroup_path(cgrp, buf, PAGE_SIZE);
- if (retval < 0)
+ path = cgroup_path(cgrp, buf, PATH_MAX);
+ if (!path) {
+ retval = -ENAMETOOLONG;
goto out_unlock;
- seq_puts(m, buf);
+ }
+ seq_puts(m, path);
seq_putc(m, '\n');
}
for_each_subsys(ss, i)
seq_printf(m, "%s\t%d\t%d\t%d\n",
ss->name, ss->root->hierarchy_id,
- ss->root->number_of_cgroups, !ss->disabled);
+ atomic_read(&ss->root->nr_cgrps), !ss->disabled);
mutex_unlock(&cgroup_mutex);
return 0;
while (!list_empty(&release_list)) {
char *argv[3], *envp[3];
int i;
- char *pathbuf = NULL, *agentbuf = NULL;
+ char *pathbuf = NULL, *agentbuf = NULL, *path;
struct cgroup *cgrp = list_entry(release_list.next,
struct cgroup,
release_list);
list_del_init(&cgrp->release_list);
raw_spin_unlock(&release_list_lock);
- pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
if (!pathbuf)
goto continue_free;
- if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0)
+ path = cgroup_path(cgrp, pathbuf, PATH_MAX);
+ if (!path)
goto continue_free;
agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
if (!agentbuf)
i = 0;
argv[i++] = agentbuf;
- argv[i++] = pathbuf;
+ argv[i++] = path;
argv[i] = NULL;
i = 0;
struct cgroup_subsys_state *css_tryget_from_dir(struct dentry *dentry,
struct cgroup_subsys *ss)
{
+ struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
+ struct cgroup_subsys_state *css = NULL;
struct cgroup *cgrp;
- struct cgroup_subsys_state *css;
/* is @dentry a cgroup dir? */
- if (!dentry->d_inode ||
- dentry->d_inode->i_op != &cgroup_dir_inode_operations)
+ if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
+ kernfs_type(kn) != KERNFS_DIR)
return ERR_PTR(-EBADF);
rcu_read_lock();
- cgrp = __d_cgrp(dentry);
- css = cgroup_css(cgrp, ss);
+ /*
+ * This path doesn't originate from kernfs and @kn could already
+ * have been or be removed at any point. @kn->priv is RCU
+ * protected for this access. See destroy_locked() for details.
+ */
+ cgrp = rcu_dereference(kn->priv);
+ if (cgrp)
+ css = cgroup_css(cgrp, ss);
if (!css || !css_tryget(css))
css = ERR_PTR(-ENOENT);
{
struct cgrp_cset_link *link;
struct css_set *cset;
+ char *name_buf;
+
+ name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL);
+ if (!name_buf)
+ return -ENOMEM;
read_lock(&css_set_lock);
rcu_read_lock();
cset = rcu_dereference(current->cgroups);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
- const char *name;
+ const char *name = "?";
+
+ if (c != cgroup_dummy_top) {
+ cgroup_name(c, name_buf, NAME_MAX + 1);
+ name = name_buf;
+ }
- if (c->dentry)
- name = c->dentry->d_name.name;
- else
- name = "?";
seq_printf(seq, "Root %d group %s\n",
c->root->hierarchy_id, name);
}
rcu_read_unlock();
read_unlock(&css_set_lock);
+ kfree(name_buf);
return 0;
}
projects / karo-tx-linux.git / blobdiff