#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
-#include <linux/backing-dev.h>
-#include <linux/seq_file.h>
#include <linux/slab.h>
-#include <linux/magic.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/sort.h>
#include <linux/kmod.h>
-#include <linux/module.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 */
-#include <linux/eventfd.h>
-#include <linux/poll.h>
#include <linux/flex_array.h> /* used in cgroup_attach_task */
#include <linux/kthread.h>
-#include <linux/file.h>
+#include <linux/delay.h>
#include <linux/atomic.h>
+/*
+ * pidlists linger the following amount before being destroyed. The goal
+ * is avoiding frequent destruction in the middle of consecutive read calls
+ * Expiring in the middle is a performance problem not a correctness one.
+ * 1 sec should be enough.
+ */
+#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
+ * creation, removal, css association and controller rebinding. This outer
+ * lock is needed mainly to resolve the circular dependency between kernfs
+ * active ref and cgroup_mutex. cgroup_tree_mutex nests above both.
+ */
+static DEFINE_MUTEX(cgroup_tree_mutex);
+
/*
* cgroup_mutex is the master lock. Any modification to cgroup or its
* hierarchy must be performed while holding it.
- *
- * cgroup_root_mutex nests inside cgroup_mutex and should be held to modify
- * cgroupfs_root of any cgroup hierarchy - subsys list, flags,
- * release_agent_path and so on. Modifying requires both cgroup_mutex and
- * cgroup_root_mutex. Readers can acquire either of the two. This is to
- * break the following locking order cycle.
- *
- * A. cgroup_mutex -> cred_guard_mutex -> s_type->i_mutex_key -> namespace_sem
- * B. namespace_sem -> cgroup_mutex
- *
- * B happens only through cgroup_show_options() and using cgroup_root_mutex
- * breaks it.
*/
#ifdef CONFIG_PROVE_RCU
DEFINE_MUTEX(cgroup_mutex);
static DEFINE_MUTEX(cgroup_mutex);
#endif
-static DEFINE_MUTEX(cgroup_root_mutex);
+/*
+ * Protects cgroup_subsys->release_agent_path. Modifying it also requires
+ * cgroup_mutex. Reading requires either cgroup_mutex or this spinlock.
+ */
+static DEFINE_SPINLOCK(release_agent_path_lock);
+
+#define cgroup_assert_mutexes_or_rcu_locked() \
+ rcu_lockdep_assert(rcu_read_lock_held() || \
+ lockdep_is_held(&cgroup_tree_mutex) || \
+ lockdep_is_held(&cgroup_mutex), \
+ "cgroup_[tree_]mutex or RCU read lock required");
/*
* cgroup destruction makes heavy use of work items and there can be a lot
static struct workqueue_struct *cgroup_destroy_wq;
/*
- * Generate an array of cgroup subsystem pointers. At boot time, this is
- * populated with the built in subsystems, and modular subsystems are
- * registered after that. The mutable section of this array is protected by
- * cgroup_mutex.
+ * pidlist destructions need to be flushed on cgroup destruction. Use a
+ * separate workqueue as flush domain.
*/
-#define SUBSYS(_x) [_x ## _subsys_id] = &_x ## _subsys,
-#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option)
-static struct cgroup_subsys *cgroup_subsys[CGROUP_SUBSYS_COUNT] = {
+static struct workqueue_struct *cgroup_pidlist_destroy_wq;
+
+/* generate an array of cgroup subsystem pointers */
+#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,
+static struct cgroup_subsys *cgroup_subsys[] = {
+#include <linux/cgroup_subsys.h>
+};
+#undef SUBSYS
+
+/* array of cgroup subsystem names */
+#define SUBSYS(_x) [_x ## _cgrp_id] = #_x,
+static const char *cgroup_subsys_name[] = {
#include <linux/cgroup_subsys.h>
};
+#undef SUBSYS
/*
* The dummy hierarchy, reserved for the subsystems that are otherwise
/* dummy_top is a shorthand for the dummy hierarchy's top cgroup */
static struct cgroup * const cgroup_dummy_top = &cgroup_dummy_root.top_cgroup;
-/*
- * cgroupfs file entry, pointed to from leaf dentry->d_fsdata.
- */
-struct cfent {
- struct list_head node;
- struct dentry *dentry;
- struct cftype *type;
- struct cgroup_subsys_state *css;
-
- /* file xattrs */
- struct simple_xattrs xattrs;
-};
-
-/*
- * cgroup_event represents events which userspace want to receive.
- */
-struct cgroup_event {
- /*
- * css which the event belongs to.
- */
- struct cgroup_subsys_state *css;
- /*
- * Control file which the event associated.
- */
- struct cftype *cft;
- /*
- * eventfd to signal userspace about the event.
- */
- struct eventfd_ctx *eventfd;
- /*
- * Each of these stored in a list by the cgroup.
- */
- struct list_head list;
- /*
- * All fields below needed to unregister event when
- * userspace closes eventfd.
- */
- poll_table pt;
- wait_queue_head_t *wqh;
- wait_queue_t wait;
- struct work_struct remove;
-};
-
/* The list of hierarchy roots */
static LIST_HEAD(cgroup_roots);
static int cgroup_root_count;
-/*
- * Hierarchy ID allocation and mapping. It follows the same exclusion
- * rules as other root ops - both cgroup_mutex and cgroup_root_mutex for
- * writes, either for reads.
- */
+/* 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);
+static void cgroup_enable_task_cg_lists(void);
/**
* cgroup_css - obtain a cgroup's css for the specified subsystem
struct cgroup_subsys *ss)
{
if (ss)
- return rcu_dereference_check(cgrp->subsys[ss->subsys_id],
- lockdep_is_held(&cgroup_mutex));
+ return rcu_dereference_check(cgrp->subsys[ss->id],
+ lockdep_is_held(&cgroup_tree_mutex) ||
+ lockdep_is_held(&cgroup_mutex));
else
return &cgrp->dummy_css;
}
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
}
/**
- * for_each_subsys - iterate all loaded cgroup subsystems
- * @ss: the iteration cursor
- * @i: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
+ * for_each_css - iterate all css's of a cgroup
+ * @css: the iteration cursor
+ * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end
+ * @cgrp: the target cgroup to iterate css's of
*
* Should be called under cgroup_mutex.
*/
-#define for_each_subsys(ss, i) \
- for ((i) = 0; (i) < CGROUP_SUBSYS_COUNT; (i)++) \
- if (({ lockdep_assert_held(&cgroup_mutex); \
- !((ss) = cgroup_subsys[i]); })) { } \
+#define for_each_css(css, ssid, cgrp) \
+ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \
+ if (!((css) = rcu_dereference_check( \
+ (cgrp)->subsys[(ssid)], \
+ lockdep_is_held(&cgroup_tree_mutex) || \
+ lockdep_is_held(&cgroup_mutex)))) { } \
else
/**
- * for_each_builtin_subsys - iterate all built-in cgroup subsystems
+ * for_each_subsys - iterate all enabled cgroup subsystems
* @ss: the iteration cursor
- * @i: the index of @ss, CGROUP_BUILTIN_SUBSYS_COUNT after reaching the end
- *
- * Bulit-in subsystems are always present and iteration itself doesn't
- * require any synchronization.
+ * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
*/
-#define for_each_builtin_subsys(ss, i) \
- for ((i) = 0; (i) < CGROUP_BUILTIN_SUBSYS_COUNT && \
- (((ss) = cgroup_subsys[i]) || true); (i)++)
-
-/* iterate each subsystem attached to a hierarchy */
-#define for_each_root_subsys(root, ss) \
- list_for_each_entry((ss), &(root)->subsys_list, sibling)
+#define for_each_subsys(ss, ssid) \
+ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \
+ (((ss) = cgroup_subsys[ssid]) || true); (ssid)++)
/* iterate across the active hierarchies */
#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
* fork()/exit() overhead for people who have cgroups compiled into their
* kernel but not actually in use.
*/
-static int use_task_css_set_links __read_mostly;
+static bool use_task_css_set_links __read_mostly;
static void __put_css_set(struct css_set *cset, int taskexit)
{
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_destroy_root(struct cgroupfs_root *root)
+{
+ struct cgroup *cgrp = &root->top_cgroup;
+ struct cgrp_cset_link *link, *tmp_link;
+
+ mutex_lock(&cgroup_tree_mutex);
+ mutex_lock(&cgroup_mutex);
+
+ BUG_ON(atomic_read(&root->nr_cgrps));
+ BUG_ON(!list_empty(&cgrp->children));
+
+ /* Rebind all subsystems back to the default hierarchy */
+ WARN_ON(rebind_subsystems(root, 0, root->subsys_mask));
+
+ /*
+ * 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);
-
- /*
- * 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.
- */
- dput(cgrp->parent->dentry);
-
- /*
- * 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);
-
- /*
- * if we're getting rid of the cgroup, refcount should ensure
- * that there are no pidlists left.
- */
- BUG_ON(!list_empty(&cgrp->pidlists));
-
- simple_xattrs_free(&cgrp->xattrs);
+ atomic_dec(&cgrp->root->nr_cgrps);
+ cgroup_pidlist_destroy_all(cgrp);
- kfree(rcu_dereference_raw(cgrp->name));
- kfree(cgrp);
+ if (cgrp->parent) {
+ /*
+ * 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.
+ */
+ cgroup_put(cgrp->parent);
+ kernfs_put(cgrp->kn);
+ kfree(cgrp);
+ } else {
+ /*
+ * This is top cgroup's refcnt reaching zero, which
+ * indicates that the root should be released.
+ */
+ cgroup_destroy_root(cgrp->root);
+ }
}
static void cgroup_free_rcu(struct rcu_head *head)
queue_work(cgroup_destroy_wq, &cgrp->destroy_work);
}
-static void cgroup_diput(struct dentry *dentry, struct inode *inode)
-{
- /* 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.
- */
- idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
- 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);
-}
-
-static void remove_dir(struct dentry *d)
+static void cgroup_get(struct cgroup *cgrp)
{
- struct dentry *parent = dget(d->d_parent);
-
- d_delete(d);
- simple_rmdir(parent->d_inode, d);
- dput(parent);
+ WARN_ON_ONCE(cgroup_is_dead(cgrp));
+ WARN_ON_ONCE(atomic_read(&cgrp->refcnt) <= 0);
+ atomic_inc(&cgrp->refcnt);
}
-static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
+static void cgroup_put(struct cgroup *cgrp)
{
- struct cfent *cfe;
-
- lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
- lockdep_assert_held(&cgroup_mutex);
+ if (!atomic_dec_and_test(&cgrp->refcnt))
+ return;
+ if (WARN_ON_ONCE(cgrp->parent && !cgroup_is_dead(cgrp)))
+ return;
/*
- * If we're doing cleanup due to failure of cgroup_create(),
- * the corresponding @cfe may not exist.
+ * 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.
*/
- list_for_each_entry(cfe, &cgrp->files, node) {
- struct dentry *d = cfe->dentry;
+ mutex_lock(&cgroup_mutex);
+ idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+ mutex_unlock(&cgroup_mutex);
+ cgrp->id = -1;
- if (cft && cfe->type != cft)
- continue;
+ call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
+}
- dget(d);
- d_delete(d);
- simple_unlink(cgrp->dentry->d_inode, d);
- list_del_init(&cfe->node);
- dput(d);
+static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
+{
+ char name[CGROUP_FILE_NAME_MAX];
- break;
- }
+ lockdep_assert_held(&cgroup_tree_mutex);
+ 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);
-}
-
-/*
- * Call with cgroup_mutex held. Drops reference counts on modules, including
- * any duplicate ones that parse_cgroupfs_options took. If this function
- * returns an error, no reference counts are touched.
- */
static int rebind_subsystems(struct cgroupfs_root *root,
unsigned long added_mask, unsigned removed_mask)
{
struct cgroup *cgrp = &root->top_cgroup;
struct cgroup_subsys *ss;
- unsigned long pinned = 0;
int i, ret;
- BUG_ON(!mutex_is_locked(&cgroup_mutex));
- BUG_ON(!mutex_is_locked(&cgroup_root_mutex));
+ lockdep_assert_held(&cgroup_tree_mutex);
+ lockdep_assert_held(&cgroup_mutex);
/* Check that any added subsystems are currently free */
- for_each_subsys(ss, i) {
- if (!(added_mask & (1 << i)))
- continue;
-
- /* is the subsystem mounted elsewhere? */
- if (ss->root != &cgroup_dummy_root) {
- ret = -EBUSY;
- goto out_put;
- }
-
- /* pin the module */
- if (!try_module_get(ss->module)) {
- ret = -ENOENT;
- goto out_put;
- }
- pinned |= 1 << i;
- }
-
- /* subsys could be missing if unloaded between parsing and here */
- if (added_mask != pinned) {
- ret = -ENOENT;
- goto out_put;
- }
+ for_each_subsys(ss, i)
+ if ((added_mask & (1 << i)) && ss->root != &cgroup_dummy_root)
+ return -EBUSY;
ret = cgroup_populate_dir(cgrp, added_mask);
if (ret)
- goto out_put;
+ return ret;
/*
* Nothing can fail from this point on. Remove files for the
* removed subsystems and rebind each subsystem.
*/
+ mutex_unlock(&cgroup_mutex);
cgroup_clear_dir(cgrp, removed_mask);
+ mutex_lock(&cgroup_mutex);
for_each_subsys(ss, i) {
unsigned long bit = 1UL << i;
cgroup_css(cgroup_dummy_top, ss));
cgroup_css(cgrp, ss)->cgroup = cgrp;
- list_move(&ss->sibling, &root->subsys_list);
ss->root = root;
if (ss->bind)
ss->bind(cgroup_css(cgrp, ss));
RCU_INIT_POINTER(cgrp->subsys[i], NULL);
cgroup_subsys[i]->root = &cgroup_dummy_root;
- list_move(&ss->sibling, &cgroup_dummy_root.subsys_list);
-
- /* subsystem is now free - drop reference on module */
- module_put(ss->module);
root->subsys_mask &= ~bit;
}
}
- /*
- * Mark @root has finished binding subsystems. @root->subsys_mask
- * now matches the bound subsystems.
- */
- root->flags |= CGRP_ROOT_SUBSYS_BOUND;
-
+ kernfs_activate(cgrp->kn);
return 0;
-
-out_put:
- for_each_subsys(ss, i)
- if (pinned & (1 << i))
- module_put(ss->module);
- return ret;
}
-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;
- mutex_lock(&cgroup_root_mutex);
- for_each_root_subsys(root, ss)
- seq_printf(seq, ",%s", ss->name);
+ for_each_subsys(ss, ssid)
+ if (root->subsys_mask & (1 << ssid))
+ seq_printf(seq, ",%s", ss->name);
if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
seq_puts(seq, ",sane_behavior");
if (root->flags & CGRP_ROOT_NOPREFIX)
seq_puts(seq, ",noprefix");
if (root->flags & CGRP_ROOT_XATTR)
seq_puts(seq, ",xattr");
+
+ spin_lock(&release_agent_path_lock);
if (strlen(root->release_agent_path))
seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+ spin_unlock(&release_agent_path_lock);
+
if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags))
seq_puts(seq, ",clone_children");
if (strlen(root->name))
seq_printf(seq, ",name=%s", root->name);
- mutex_unlock(&cgroup_root_mutex);
return 0;
}
char *name;
/* User explicitly requested empty subsystem */
bool none;
-
- struct cgroupfs_root *new_root;
-
};
/*
BUG_ON(!mutex_is_locked(&cgroup_mutex));
#ifdef CONFIG_CPUSETS
- mask = ~(1UL << cpuset_subsys_id);
+ mask = ~(1UL << cpuset_cgrp_id);
#endif
memset(opts, 0, sizeof(*opts));
if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
pr_warning("cgroup: sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
- if (opts->flags & CGRP_ROOT_NOPREFIX) {
- pr_err("cgroup: sane_behavior: noprefix is not allowed\n");
- return -EINVAL;
- }
-
- if (opts->cpuset_clone_children) {
- pr_err("cgroup: sane_behavior: clone_children is not allowed\n");
+ if ((opts->flags & (CGRP_ROOT_NOPREFIX | CGRP_ROOT_XATTR)) ||
+ opts->cpuset_clone_children || opts->release_agent ||
+ opts->name) {
+ pr_err("cgroup: sane_behavior: noprefix, xattr, clone_children, release_agent and name are not allowed\n");
return -EINVAL;
}
}
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);
- mutex_lock(&cgroup_root_mutex);
/* See what subsystems are wanted */
ret = parse_cgroupfs_options(data, &opts);
}
/* 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;
}
if (ret)
goto out_unlock;
- if (opts.release_agent)
+ if (opts.release_agent) {
+ spin_lock(&release_agent_path_lock);
strcpy(root->release_agent_path, opts.release_agent);
+ spin_unlock(&release_agent_path_lock);
+ }
out_unlock:
kfree(opts.release_agent);
kfree(opts.name);
- mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
- mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+ mutex_unlock(&cgroup_tree_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;
- INIT_LIST_HEAD(&cgrp->event_list);
- spin_lock_init(&cgrp->event_list_lock);
- simple_xattrs_init(&cgrp->xattrs);
}
static void init_cgroup_root(struct cgroupfs_root *root)
{
struct cgroup *cgrp = &root->top_cgroup;
- INIT_LIST_HEAD(&root->subsys_list);
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)
+static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
{
- int id;
-
- lockdep_assert_held(&cgroup_mutex);
- lockdep_assert_held(&cgroup_root_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);
- lockdep_assert_held(&cgroup_root_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;
+ struct cgroupfs_root *root;
if (!opts->subsys_mask && !opts->none)
- return NULL;
+ return ERR_PTR(-EINVAL);
root = kzalloc(sizeof(*root), GFP_KERNEL);
if (!root)
init_cgroup_root(root);
- /*
- * We need to set @root->subsys_mask now so that @root can be
- * matched by cgroup_test_super() before it finishes
- * initialization; otherwise, competing mounts with the same
- * options may try to bind the same subsystems instead of waiting
- * for the first one leading to unexpected mount errors.
- * SUBSYS_BOUND will be set once actual binding is complete.
- */
- root->subsys_mask = opts->subsys_mask;
root->flags = opts->flags;
if (opts->release_agent)
strcpy(root->release_agent_path, opts->release_agent);
return root;
}
-static void cgroup_free_root(struct cgroupfs_root *root)
+static int cgroup_setup_root(struct cgroupfs_root *root, unsigned long ss_mask)
{
- if (root) {
- /* hierarhcy ID shoulid already have been released */
- WARN_ON_ONCE(root->hierarchy_id);
-
- idr_destroy(&root->cgroup_idr);
- kfree(root);
- }
-}
+ LIST_HEAD(tmp_links);
+ struct cgroup *root_cgrp = &root->top_cgroup;
+ struct css_set *cset;
+ int i, ret;
-static int cgroup_set_super(struct super_block *sb, void *data)
-{
- int ret;
- struct cgroup_sb_opts *opts = data;
+ lockdep_assert_held(&cgroup_tree_mutex);
+ lockdep_assert_held(&cgroup_mutex);
- /* If we don't have a new root, we can't set up a new sb */
- if (!opts->new_root)
- return -EINVAL;
+ ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
+ if (ret < 0)
+ goto out;
+ root_cgrp->id = ret;
- BUG_ON(!opts->subsys_mask && !opts->none);
+ /*
+ * 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;
- ret = set_anon_super(sb, NULL);
+ /* ID 0 is reserved for dummy root, 1 for unified hierarchy */
+ ret = cgroup_init_root_id(root, 2, 0);
if (ret)
- return ret;
+ goto out;
+
+ 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;
- sb->s_fs_info = opts->new_root;
- opts->new_root->sb = sb;
+ ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true);
+ if (ret)
+ goto destroy_root;
- sb->s_blocksize = PAGE_CACHE_SIZE;
- sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
- sb->s_magic = CGROUP_SUPER_MAGIC;
- sb->s_op = &cgroup_ops;
+ ret = rebind_subsystems(root, ss_mask, 0);
+ if (ret)
+ goto destroy_root;
- return 0;
-}
+ /*
+ * There must be no failure case after here, since rebinding takes
+ * care of subsystems' refcounts, which are explicitly dropped in
+ * the failure exit path.
+ */
+ list_add(&root->root_list, &cgroup_roots);
+ cgroup_root_count++;
-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,
- };
+ /*
+ * Link the top cgroup in this hierarchy into all the css_set
+ * objects.
+ */
+ write_lock(&css_set_lock);
+ hash_for_each(css_set_table, i, cset, hlist)
+ link_css_set(&tmp_links, cset, root_cgrp);
+ write_unlock(&css_set_lock);
- struct inode *inode =
- cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);
+ BUG_ON(!list_empty(&root_cgrp->children));
+ BUG_ON(atomic_read(&root->nr_cgrps) != 1);
- if (!inode)
- return -ENOMEM;
+ kernfs_activate(root_cgrp->kn);
+ ret = 0;
+ goto out;
- 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;
+destroy_root:
+ kernfs_destroy_root(root->kf_root);
+ root->kf_root = NULL;
+exit_root_id:
+ cgroup_exit_root_id(root);
+out:
+ free_cgrp_cset_links(&tmp_links);
+ return ret;
}
static struct dentry *cgroup_mount(struct file_system_type *fs_type,
int flags, const char *unused_dev_name,
void *data)
{
- struct cgroup_sb_opts opts;
struct cgroupfs_root *root;
- int ret = 0;
- struct super_block *sb;
- struct cgroupfs_root *new_root;
- struct list_head tmp_links;
- struct inode *inode;
- const struct cred *cred;
-
- /* First find the desired set of subsystems */
- mutex_lock(&cgroup_mutex);
- ret = parse_cgroupfs_options(data, &opts);
- mutex_unlock(&cgroup_mutex);
- if (ret)
- goto out_err;
+ struct cgroup_sb_opts opts;
+ struct dentry *dentry;
+ int ret;
/*
- * Allocate a new cgroup root. We may not need it if we're
- * reusing an existing hierarchy.
+ * The first time anyone tries to mount a cgroup, enable the list
+ * linking each css_set to its tasks and fix up all existing tasks.
*/
- 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;
-
- /* Locate an existing or new sb for this hierarchy */
- sb = sget(fs_type, cgroup_test_super, cgroup_set_super, 0, &opts);
- if (IS_ERR(sb)) {
- ret = PTR_ERR(sb);
- cgroup_free_root(opts.new_root);
- goto out_err;
- }
-
- 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 cgroup *root_cgrp = &root->top_cgroup;
- struct cgroupfs_root *existing_root;
- int i;
- struct css_set *cset;
-
- BUG_ON(sb->s_root != NULL);
-
- ret = cgroup_get_rootdir(sb);
- if (ret)
- goto drop_new_super;
- inode = sb->s_root->d_inode;
-
- mutex_lock(&inode->i_mutex);
- mutex_lock(&cgroup_mutex);
- mutex_lock(&cgroup_root_mutex);
-
- root_cgrp->id = idr_alloc(&root->cgroup_idr, root_cgrp,
- 0, 1, GFP_KERNEL);
- if (root_cgrp->id < 0)
- goto unlock_drop;
-
- /* 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 unlock_drop;
-
- /*
- * 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 unlock_drop;
-
- /* ID 0 is reserved for dummy root, 1 for unified hierarchy */
- ret = cgroup_init_root_id(root, 2, 0);
- if (ret)
- goto unlock_drop;
-
- sb->s_root->d_fsdata = root_cgrp;
- root_cgrp->dentry = sb->s_root;
-
- /*
- * 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);
-
- ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true);
- if (ret)
- goto rm_base_files;
+ if (!use_task_css_set_links)
+ cgroup_enable_task_cg_lists();
+retry:
+ mutex_lock(&cgroup_tree_mutex);
+ mutex_lock(&cgroup_mutex);
- ret = rebind_subsystems(root, root->subsys_mask, 0);
- if (ret)
- goto rm_base_files;
+ /* First find the desired set of subsystems */
+ ret = parse_cgroupfs_options(data, &opts);
+ if (ret)
+ goto out_unlock;
- revert_creds(cred);
+ /* look for a matching existing root */
+ for_each_active_root(root) {
+ bool name_match = false;
/*
- * There must be no failure case after here, since rebinding
- * takes care of subsystems' refcounts, which are explicitly
- * dropped in the failure exit path.
+ * 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;
+ }
- list_add(&root->root_list, &cgroup_roots);
- cgroup_root_count++;
-
- /* Link the top cgroup in this hierarchy into all
- * the css_set objects */
- write_lock(&css_set_lock);
- hash_for_each(css_set_table, i, cset, hlist)
- link_css_set(&tmp_links, cset, root_cgrp);
- write_unlock(&css_set_lock);
-
- free_cgrp_cset_links(&tmp_links);
-
- BUG_ON(!list_empty(&root_cgrp->children));
- BUG_ON(root->number_of_cgroups != 1);
-
- mutex_unlock(&cgroup_root_mutex);
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
- } 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_err("cgroup: sane_behavior: new mount options should match the existing superblock\n");
ret = -EINVAL;
- goto drop_new_super;
+ goto out_unlock;
} else {
pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n");
}
}
- }
- kfree(opts.release_agent);
- kfree(opts.name);
- return dget(sb->s_root);
-
- rm_base_files:
- free_cgrp_cset_links(&tmp_links);
- cgroup_addrm_files(&root->top_cgroup, cgroup_base_files, false);
- revert_creds(cred);
- unlock_drop:
- cgroup_exit_root_id(root);
- mutex_unlock(&cgroup_root_mutex);
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
- drop_new_super:
- deactivate_locked_super(sb);
- out_err:
- kfree(opts.release_agent);
- kfree(opts.name);
- return ERR_PTR(ret);
-}
-
-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));
+ /*
+ * A root's lifetime is governed by its top cgroup. Zero
+ * ref indicate that the root is being destroyed. Wait for
+ * destruction to complete so that the subsystems are free.
+ * We can use wait_queue for the wait but this path is
+ * super cold. Let's just sleep for a bit and retry.
+ */
+ if (!atomic_inc_not_zero(&root->top_cgroup.refcnt)) {
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
+ msleep(10);
+ goto retry;
+ }
- mutex_lock(&cgrp->dentry->d_inode->i_mutex);
- mutex_lock(&cgroup_mutex);
- mutex_lock(&cgroup_root_mutex);
+ ret = 0;
+ goto out_unlock;
+ }
- /* 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);
+ /* no such thing, create a new one */
+ root = cgroup_root_from_opts(&opts);
+ if (IS_ERR(root)) {
+ ret = PTR_ERR(root);
+ goto out_unlock;
}
- /*
- * Release all the links from cset_links to this hierarchy's
- * root cgroup
- */
- write_lock(&css_set_lock);
+ ret = cgroup_setup_root(root, opts.subsys_mask);
+ if (ret)
+ cgroup_free_root(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);
+out_unlock:
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
- if (!list_empty(&root->root_list)) {
- list_del(&root->root_list);
- cgroup_root_count--;
- }
+ kfree(opts.release_agent);
+ kfree(opts.name);
- cgroup_exit_root_id(root);
+ if (ret)
+ return ERR_PTR(ret);
- mutex_unlock(&cgroup_root_mutex);
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+ dentry = kernfs_mount(fs_type, flags, root->kf_root);
+ if (IS_ERR(dentry))
+ cgroup_put(&root->top_cgroup);
+ return dentry;
+}
- simple_xattrs_free(&cgrp->xattrs);
+static void cgroup_kill_sb(struct super_block *sb)
+{
+ struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
+ struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
- kill_litter_super(sb);
- cgroup_free_root(root);
+ cgroup_put(&root->top_cgroup);
+ 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);
rcu_assign_pointer(tsk->cgroups, new_cset);
task_unlock(tsk);
- /* Update the css_set linked lists if we're using them */
write_lock(&css_set_lock);
- if (!list_empty(&tsk->cg_list))
- list_move(&tsk->cg_list, &new_cset->tasks);
+ list_move(&tsk->cg_list, &new_cset->tasks);
write_unlock(&css_set_lock);
/*
bool threadgroup)
{
int retval, i, group_size;
- struct cgroup_subsys *ss, *failed_ss = NULL;
struct cgroupfs_root *root = cgrp->root;
+ struct cgroup_subsys_state *css, *failed_css = NULL;
/* threadgroup list cursor and array */
struct task_struct *leader = tsk;
struct task_and_cgroup *tc;
/*
* step 1: check that we can legitimately attach to the cgroup.
*/
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-
- if (ss->can_attach) {
- retval = ss->can_attach(css, &tset);
+ for_each_css(css, i, cgrp) {
+ if (css->ss->can_attach) {
+ retval = css->ss->can_attach(css, &tset);
if (retval) {
- failed_ss = ss;
+ failed_css = css;
goto out_cancel_attach;
}
}
/*
* step 4: do subsystem attach callbacks.
*/
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-
- if (ss->attach)
- ss->attach(css, &tset);
- }
+ for_each_css(css, i, cgrp)
+ if (css->ss->attach)
+ css->ss->attach(css, &tset);
/*
* step 5: success! and cleanup
}
out_cancel_attach:
if (retval) {
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-
- if (ss == failed_ss)
+ for_each_css(css, i, cgrp) {
+ if (css == failed_css)
break;
- if (ss->cancel_attach)
- ss->cancel_attach(css, &tset);
+ if (css->ss->cancel_attach)
+ css->ss->cancel_attach(css, &tset);
}
}
out_free_group_list:
tsk = find_task_by_vpid(pid);
if (!tsk) {
rcu_read_unlock();
- ret= -ESRCH;
+ ret = -ESRCH;
goto out_unlock_cgroup;
}
/*
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;
- mutex_lock(&cgroup_root_mutex);
- strcpy(css->cgroup->root->release_agent_path, buffer);
- mutex_unlock(&cgroup_root_mutex);
+ spin_lock(&release_agent_path_lock);
+ strlcpy(root->release_agent_path, buffer,
+ sizeof(root->release_agent_path));
+ spin_unlock(&release_agent_path_lock);
mutex_unlock(&cgroup_mutex);
return 0;
}
-static int cgroup_release_agent_show(struct cgroup_subsys_state *css,
- struct cftype *cft, struct seq_file *seq)
+static int cgroup_release_agent_show(struct seq_file *seq, void *v)
{
- struct cgroup *cgrp = css->cgroup;
+ struct cgroup *cgrp = seq_css(seq)->cgroup;
if (!cgroup_lock_live_group(cgrp))
return -ENODEV;
return 0;
}
-static int cgroup_sane_behavior_show(struct cgroup_subsys_state *css,
- struct cftype *cft, struct seq_file *seq)
+static int cgroup_sane_behavior_show(struct seq_file *seq, void *v)
{
- seq_printf(seq, "%d\n", cgroup_sane_behavior(css->cgroup));
+ struct cgroup *cgrp = seq_css(seq)->cgroup;
+
+ seq_printf(seq, "%d\n", cgroup_sane_behavior(cgrp));
return 0;
}
-/* A buffer size big enough for numbers or short strings */
-#define CGROUP_LOCAL_BUFFER_SIZE 64
-
-static ssize_t cgroup_write_X64(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- const char __user *userbuf, size_t nbytes,
- loff_t *unused_ppos)
+static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
+ size_t nbytes, loff_t off)
{
- char buffer[CGROUP_LOCAL_BUFFER_SIZE];
- int retval = 0;
- char *end;
+ struct cgroup *cgrp = of->kn->parent->priv;
+ struct cftype *cft = of->kn->priv;
+ struct cgroup_subsys_state *css;
+ int ret;
- if (!nbytes)
- return -EINVAL;
- if (nbytes >= sizeof(buffer))
- return -E2BIG;
- if (copy_from_user(buffer, userbuf, nbytes))
- return -EFAULT;
-
- buffer[nbytes] = 0; /* nul-terminate */
- if (cft->write_u64) {
- u64 val = simple_strtoull(strstrip(buffer), &end, 0);
- if (*end)
- return -EINVAL;
- retval = cft->write_u64(css, cft, val);
+ /*
+ * 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 if (cft->write_u64) {
+ unsigned long long v;
+ ret = kstrtoull(buf, 0, &v);
+ if (!ret)
+ ret = cft->write_u64(css, cft, v);
+ } else if (cft->write_s64) {
+ long long v;
+ ret = kstrtoll(buf, 0, &v);
+ if (!ret)
+ ret = cft->write_s64(css, cft, v);
+ } else if (cft->trigger) {
+ ret = cft->trigger(css, (unsigned int)cft->private);
} else {
- s64 val = simple_strtoll(strstrip(buffer), &end, 0);
- if (*end)
- return -EINVAL;
- retval = cft->write_s64(css, cft, val);
+ ret = -EINVAL;
}
- if (!retval)
- retval = nbytes;
- return retval;
+
+ return ret ?: nbytes;
}
-static ssize_t cgroup_write_string(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- const char __user *userbuf, size_t nbytes,
- loff_t *unused_ppos)
+static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
{
- char local_buffer[CGROUP_LOCAL_BUFFER_SIZE];
- int retval = 0;
- size_t max_bytes = cft->max_write_len;
- char *buffer = local_buffer;
-
- if (!max_bytes)
- max_bytes = sizeof(local_buffer) - 1;
- if (nbytes >= max_bytes)
- return -E2BIG;
- /* Allocate a dynamic buffer if we need one */
- if (nbytes >= sizeof(local_buffer)) {
- buffer = kmalloc(nbytes + 1, GFP_KERNEL);
- if (buffer == NULL)
- return -ENOMEM;
- }
- if (nbytes && copy_from_user(buffer, userbuf, nbytes)) {
- retval = -EFAULT;
- goto out;
- }
-
- buffer[nbytes] = 0; /* nul-terminate */
- retval = cft->write_string(css, cft, strstrip(buffer));
- if (!retval)
- retval = nbytes;
-out:
- if (buffer != local_buffer)
- kfree(buffer);
- return retval;
+ return seq_cft(seq)->seq_start(seq, ppos);
}
-static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
- size_t nbytes, loff_t *ppos)
+static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos)
{
- struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cgroup_subsys_state *css = cfe->css;
-
- if (cft->write)
- return cft->write(css, cft, file, buf, nbytes, ppos);
- if (cft->write_u64 || cft->write_s64)
- return cgroup_write_X64(css, cft, file, buf, nbytes, ppos);
- if (cft->write_string)
- return cgroup_write_string(css, cft, file, buf, nbytes, ppos);
- if (cft->trigger) {
- int ret = cft->trigger(css, (unsigned int)cft->private);
- return ret ? ret : nbytes;
- }
- return -EINVAL;
+ return seq_cft(seq)->seq_next(seq, v, ppos);
}
-static ssize_t cgroup_read_u64(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- char __user *buf, size_t nbytes, loff_t *ppos)
+static void cgroup_seqfile_stop(struct seq_file *seq, void *v)
{
- char tmp[CGROUP_LOCAL_BUFFER_SIZE];
- u64 val = cft->read_u64(css, cft);
- int len = sprintf(tmp, "%llu\n", (unsigned long long) val);
-
- return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
+ seq_cft(seq)->seq_stop(seq, v);
}
-static ssize_t cgroup_read_s64(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- char __user *buf, size_t nbytes, loff_t *ppos)
+static int cgroup_seqfile_show(struct seq_file *m, void *arg)
{
- char tmp[CGROUP_LOCAL_BUFFER_SIZE];
- s64 val = cft->read_s64(css, cft);
- int len = sprintf(tmp, "%lld\n", (long long) val);
+ struct cftype *cft = seq_cft(m);
+ struct cgroup_subsys_state *css = seq_css(m);
- return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
-}
-
-static ssize_t cgroup_file_read(struct file *file, char __user *buf,
- size_t nbytes, loff_t *ppos)
-{
- struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cgroup_subsys_state *css = cfe->css;
+ if (cft->seq_show)
+ return cft->seq_show(m, arg);
- if (cft->read)
- return cft->read(css, cft, file, buf, nbytes, ppos);
if (cft->read_u64)
- return cgroup_read_u64(css, cft, file, buf, nbytes, ppos);
- if (cft->read_s64)
- return cgroup_read_s64(css, cft, file, buf, nbytes, ppos);
- return -EINVAL;
-}
-
-/*
- * seqfile ops/methods for returning structured data. Currently just
- * supports string->u64 maps, but can be extended in future.
- */
-
-static int cgroup_map_add(struct cgroup_map_cb *cb, const char *key, u64 value)
-{
- struct seq_file *sf = cb->state;
- return seq_printf(sf, "%s %llu\n", key, (unsigned long long)value);
-}
-
-static int cgroup_seqfile_show(struct seq_file *m, void *arg)
-{
- struct cfent *cfe = m->private;
- struct cftype *cft = cfe->type;
- struct cgroup_subsys_state *css = cfe->css;
-
- if (cft->read_map) {
- struct cgroup_map_cb cb = {
- .fill = cgroup_map_add,
- .state = m,
- };
- return cft->read_map(css, cft, &cb);
- }
- return cft->read_seq_string(css, cft, m);
+ 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 const struct file_operations cgroup_seqfile_operations = {
- .read = seq_read,
- .write = cgroup_file_write,
- .llseek = seq_lseek,
- .release = cgroup_file_release,
+static struct kernfs_ops cgroup_kf_single_ops = {
+ .atomic_write_len = PAGE_SIZE,
+ .write = cgroup_file_write,
+ .seq_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;
- 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;
-
- if (cft->read_map || cft->read_seq_string) {
- file->f_op = &cgroup_seqfile_operations;
- err = single_open(file, cgroup_seqfile_show, cfe);
- } else if (cft->open) {
- err = cft->open(inode, file);
- }
-
- if (css->ss && err)
- css_put(css);
- return err;
-}
-
-static int cgroup_file_release(struct inode *inode, struct file *file)
-{
- struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cgroup_subsys_state *css = cfe->css;
- int ret = 0;
-
- if (cft->release)
- ret = cft->release(inode, file);
- if (css->ss)
- css_put(css);
- if (file->f_op == &cgroup_seqfile_operations)
- single_release(inode, file);
- return ret;
-}
+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 int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
+ const char *new_name_str)
{
+ struct cgroup *cgrp = kn->priv;
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))
+ if (kernfs_type(kn) != KERNFS_DIR)
return -ENOTDIR;
- if (new_dentry->d_inode)
- return -EEXIST;
- if (old_dir != new_dir)
+ if (kn->parent != new_parent)
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 = cgroup_file_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,
-};
-
-/*
- * Check if a file is a control file
- */
-static inline struct cftype *__file_cft(struct file *file)
-{
- if (file_inode(file)->i_fop != &cgroup_file_operations)
- return ERR_PTR(-EINVAL);
- return __d_cft(file->f_dentry);
-}
-
-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;
-
- /* start off with i_nlink == 2 (for "." entry) */
- inc_nlink(inode);
- inc_nlink(dentry->d_parent->d_inode);
-
- /*
- * 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 */
- 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 umode_t cgroup_file_mode(const struct cftype *cft)
-{
- umode_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;
+ mutex_lock(&cgroup_tree_mutex);
+ mutex_lock(&cgroup_mutex);
- if (cft->write || cft->write_u64 || cft->write_s64 ||
- cft->write_string || cft->trigger)
- mode |= S_IWUSR;
+ ret = kernfs_rename(kn, new_parent, new_name_str);
- return mode;
+ 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));
-
- cfe = kzalloc(sizeof(*cfe), GFP_KERNEL);
- if (!cfe)
- return -ENOMEM;
+ char name[CGROUP_FILE_NAME_MAX];
+ struct kernfs_node *kn;
+ struct lock_class_key *key = NULL;
- 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_mutex);
+ lockdep_assert_held(&cgroup_tree_mutex);
for (cft = cfts; cft->name[0] != '\0'; cft++) {
/* does cft->flags tell us to skip this file on @cgrp? */
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_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;
- /* %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_mutex);
- 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;
+ lockdep_assert_held(&cgroup_tree_mutex);
- mutex_unlock(&cgroup_mutex);
+ /* don't bother if @ss isn't attached */
+ if (ss->root == &cgroup_dummy_root)
+ return 0;
/* add/rm files for all cgroups created before */
- rcu_read_lock();
css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
struct cgroup *cgrp = css->cgroup;
if (cgroup_is_dead(cgrp))
continue;
- inode = cgrp->dentry->d_inode;
- dget(cgrp->dentry);
- rcu_read_unlock();
-
- dput(prev);
- prev = cgrp->dentry;
-
- mutex_lock(&inode->i_mutex);
- mutex_lock(&cgroup_mutex);
- if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp))
- ret = cgroup_addrm_files(cgrp, cfts, is_add);
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
-
- rcu_read_lock();
+ ret = cgroup_addrm_files(cgrp, cfts, is_add);
if (ret)
break;
}
- rcu_read_unlock();
- 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;
+
+ /*
+ * 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;
+ }
- for (cft = cfts; cft->name[0] != '\0'; cft++)
+ 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;
+
+ mutex_lock(&cgroup_tree_mutex);
+ ret = cgroup_rm_cftypes_locked(cfts);
+ mutex_unlock(&cgroup_tree_mutex);
+ 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)
+{
+ int ret;
- if (!cfts || !cfts[0].ss)
- return -ENOENT;
+ ret = cgroup_init_cftypes(ss, cfts);
+ if (ret)
+ return ret;
- cgroup_cfts_prepare();
+ mutex_lock(&cgroup_tree_mutex);
- 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;
- }
- }
+ list_add_tail(&cfts->node, &ss->cfts);
+ ret = cgroup_apply_cftypes(cfts, true);
+ if (ret)
+ cgroup_rm_cftypes_locked(cfts);
- cgroup_cfts_commit(NULL, false);
- return -ENOENT;
+ mutex_unlock(&cgroup_tree_mutex);
+ return ret;
}
+EXPORT_SYMBOL_GPL(cgroup_add_cftypes);
/**
* cgroup_task_count - count the number of tasks in a cgroup.
* To reduce the fork() overhead for systems that are not actually using
* their cgroups capability, we don't maintain the lists running through
* each css_set to its tasks until we see the list actually used - in other
- * words after the first call to css_task_iter_start().
+ * words after the first mount.
*/
static void cgroup_enable_task_cg_lists(void)
{
struct task_struct *p, *g;
+
write_lock(&css_set_lock);
- use_task_css_set_links = 1;
+
+ if (use_task_css_set_links)
+ goto out_unlock;
+
+ use_task_css_set_links = true;
+
/*
* We need tasklist_lock because RCU is not safe against
* while_each_thread(). Besides, a forking task that has passed
read_lock(&tasklist_lock);
do_each_thread(g, p) {
task_lock(p);
+
+ WARN_ON_ONCE(!list_empty(&p->cg_list) ||
+ task_css_set(p) != &init_css_set);
+
/*
* We should check if the process is exiting, otherwise
* it will race with cgroup_exit() in that the list
* entry won't be deleted though the process has exited.
*/
- if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
+ if (!(p->flags & PF_EXITING))
list_add(&p->cg_list, &task_css_set(p)->tasks);
+
task_unlock(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
+out_unlock:
write_unlock(&css_set_lock);
}
* @parent_css: css whose children to walk
*
* This function returns the next child of @parent_css and should be called
- * under RCU read lock. The only requirement is that @parent_css and
- * @pos_css are accessible. The next sibling is guaranteed to be returned
- * regardless of their states.
+ * under either cgroup_mutex or RCU read lock. The only requirement is
+ * that @parent_css and @pos_css are accessible. The next sibling is
+ * guaranteed to be returned regardless of their states.
*/
struct cgroup_subsys_state *
css_next_child(struct cgroup_subsys_state *pos_css,
struct cgroup *cgrp = parent_css->cgroup;
struct cgroup *next;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutexes_or_rcu_locked();
/*
* @pos could already have been removed. Once a cgroup is removed,
* to visit for pre-order traversal of @root's descendants. @root is
* included in the iteration and the first node to be visited.
*
- * While this function requires RCU read locking, it doesn't require the
- * whole traversal to be contained in a single RCU critical section. This
- * function will return the correct next descendant as long as both @pos
- * and @root are accessible and @pos is a descendant of @root.
+ * While this function requires cgroup_mutex or RCU read locking, it
+ * doesn't require the whole traversal to be contained in a single critical
+ * section. This function will return the correct next descendant as long
+ * as both @pos and @root are accessible and @pos is a descendant of @root.
*/
struct cgroup_subsys_state *
css_next_descendant_pre(struct cgroup_subsys_state *pos,
{
struct cgroup_subsys_state *next;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutexes_or_rcu_locked();
/* if first iteration, visit @root */
if (!pos)
* is returned. This can be used during pre-order traversal to skip
* subtree of @pos.
*
- * While this function requires RCU read locking, it doesn't require the
- * whole traversal to be contained in a single RCU critical section. This
- * function will return the correct rightmost descendant as long as @pos is
- * accessible.
+ * While this function requires cgroup_mutex or RCU read locking, it
+ * doesn't require the whole traversal to be contained in a single critical
+ * section. This function will return the correct rightmost descendant as
+ * long as @pos is accessible.
*/
struct cgroup_subsys_state *
css_rightmost_descendant(struct cgroup_subsys_state *pos)
{
struct cgroup_subsys_state *last, *tmp;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutexes_or_rcu_locked();
do {
last = pos;
* to visit for post-order traversal of @root's descendants. @root is
* included in the iteration and the last node to be visited.
*
- * While this function requires RCU read locking, it doesn't require the
- * whole traversal to be contained in a single RCU critical section. This
- * function will return the correct next descendant as long as both @pos
- * and @cgroup are accessible and @pos is a descendant of @cgroup.
+ * While this function requires cgroup_mutex or RCU read locking, it
+ * doesn't require the whole traversal to be contained in a single critical
+ * section. This function will return the correct next descendant as long
+ * as both @pos and @cgroup are accessible and @pos is a descendant of
+ * @cgroup.
*/
struct cgroup_subsys_state *
css_next_descendant_post(struct cgroup_subsys_state *pos,
{
struct cgroup_subsys_state *next;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutexes_or_rcu_locked();
/* if first iteration, visit leftmost descendant which may be @root */
if (!pos)
struct css_task_iter *it)
__acquires(css_set_lock)
{
- /*
- * The first time anyone tries to iterate across a css, we need to
- * enable the list linking each css_set to its tasks, and fix up
- * all existing tasks.
- */
- if (!use_task_css_set_links)
- cgroup_enable_task_cg_lists();
+ /* no one should try to iterate before mounting cgroups */
+ WARN_ON_ONCE(!use_task_css_set_links);
read_lock(&css_set_lock);
pid_t *list;
/* how many elements the above list has */
int length;
- /* how many files are using the current array */
- int use_count;
/* each of these stored in a list by its cgroup */
struct list_head links;
/* pointer to the cgroup we belong to, for list removal purposes */
struct cgroup *owner;
- /* protects the other fields */
- struct rw_semaphore rwsem;
+ /* for delayed destruction */
+ struct delayed_work destroy_dwork;
};
/*
else
return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
}
+
static void pidlist_free(void *p)
{
if (is_vmalloc_addr(p))
kfree(p);
}
+/*
+ * Used to destroy all pidlists lingering waiting for destroy timer. None
+ * should be left afterwards.
+ */
+static void cgroup_pidlist_destroy_all(struct cgroup *cgrp)
+{
+ struct cgroup_pidlist *l, *tmp_l;
+
+ mutex_lock(&cgrp->pidlist_mutex);
+ list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links)
+ mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0);
+ mutex_unlock(&cgrp->pidlist_mutex);
+
+ flush_workqueue(cgroup_pidlist_destroy_wq);
+ BUG_ON(!list_empty(&cgrp->pidlists));
+}
+
+static void cgroup_pidlist_destroy_work_fn(struct work_struct *work)
+{
+ struct delayed_work *dwork = to_delayed_work(work);
+ struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist,
+ destroy_dwork);
+ struct cgroup_pidlist *tofree = NULL;
+
+ mutex_lock(&l->owner->pidlist_mutex);
+
+ /*
+ * Destroy iff we didn't get queued again. The state won't change
+ * as destroy_dwork can only be queued while locked.
+ */
+ if (!delayed_work_pending(dwork)) {
+ list_del(&l->links);
+ pidlist_free(l->list);
+ put_pid_ns(l->key.ns);
+ tofree = l;
+ }
+
+ mutex_unlock(&l->owner->pidlist_mutex);
+ kfree(tofree);
+}
+
/*
* pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
* Returns the number of unique elements.
return dest;
}
+/*
+ * The two pid files - task and cgroup.procs - guaranteed that the result
+ * is sorted, which forced this whole pidlist fiasco. As pid order is
+ * different per namespace, each namespace needs differently sorted list,
+ * making it impossible to use, for example, single rbtree of member tasks
+ * sorted by task pointer. As pidlists can be fairly large, allocating one
+ * per open file is dangerous, so cgroup had to implement shared pool of
+ * pidlists keyed by cgroup and namespace.
+ *
+ * All this extra complexity was caused by the original implementation
+ * committing to an entirely unnecessary property. In the long term, we
+ * want to do away with it. Explicitly scramble sort order if
+ * sane_behavior so that no such expectation exists in the new interface.
+ *
+ * Scrambling is done by swapping every two consecutive bits, which is
+ * non-identity one-to-one mapping which disturbs sort order sufficiently.
+ */
+static pid_t pid_fry(pid_t pid)
+{
+ unsigned a = pid & 0x55555555;
+ unsigned b = pid & 0xAAAAAAAA;
+
+ return (a << 1) | (b >> 1);
+}
+
+static pid_t cgroup_pid_fry(struct cgroup *cgrp, pid_t pid)
+{
+ if (cgroup_sane_behavior(cgrp))
+ return pid_fry(pid);
+ else
+ return pid;
+}
+
static int cmppid(const void *a, const void *b)
{
return *(pid_t *)a - *(pid_t *)b;
}
+static int fried_cmppid(const void *a, const void *b)
+{
+ return pid_fry(*(pid_t *)a) - pid_fry(*(pid_t *)b);
+}
+
+static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
+ enum cgroup_filetype type)
+{
+ struct cgroup_pidlist *l;
+ /* don't need task_nsproxy() if we're looking at ourself */
+ struct pid_namespace *ns = task_active_pid_ns(current);
+
+ lockdep_assert_held(&cgrp->pidlist_mutex);
+
+ list_for_each_entry(l, &cgrp->pidlists, links)
+ if (l->key.type == type && l->key.ns == ns)
+ return l;
+ return NULL;
+}
+
/*
* find the appropriate pidlist for our purpose (given procs vs tasks)
* returns with the lock on that pidlist already held, and takes care
* of the use count, or returns NULL with no locks held if we're out of
* memory.
*/
-static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
- enum cgroup_filetype type)
+static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp,
+ enum cgroup_filetype type)
{
struct cgroup_pidlist *l;
- /* don't need task_nsproxy() if we're looking at ourself */
- struct pid_namespace *ns = task_active_pid_ns(current);
- /*
- * We can't drop the pidlist_mutex before taking the l->rwsem in case
- * the last ref-holder is trying to remove l from the list at the same
- * time. Holding the pidlist_mutex precludes somebody taking whichever
- * list we find out from under us - compare release_pid_array().
- */
- mutex_lock(&cgrp->pidlist_mutex);
- list_for_each_entry(l, &cgrp->pidlists, links) {
- if (l->key.type == type && l->key.ns == ns) {
- /* make sure l doesn't vanish out from under us */
- down_write(&l->rwsem);
- mutex_unlock(&cgrp->pidlist_mutex);
- return l;
- }
- }
+ lockdep_assert_held(&cgrp->pidlist_mutex);
+
+ l = cgroup_pidlist_find(cgrp, type);
+ if (l)
+ return l;
+
/* entry not found; create a new one */
l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
- if (!l) {
- mutex_unlock(&cgrp->pidlist_mutex);
+ if (!l)
return l;
- }
- init_rwsem(&l->rwsem);
- down_write(&l->rwsem);
+
+ INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn);
l->key.type = type;
- l->key.ns = get_pid_ns(ns);
+ /* don't need task_nsproxy() if we're looking at ourself */
+ l->key.ns = get_pid_ns(task_active_pid_ns(current));
l->owner = cgrp;
list_add(&l->links, &cgrp->pidlists);
- mutex_unlock(&cgrp->pidlist_mutex);
return l;
}
struct task_struct *tsk;
struct cgroup_pidlist *l;
+ lockdep_assert_held(&cgrp->pidlist_mutex);
+
/*
* If cgroup gets more users after we read count, we won't have
* enough space - tough. This race is indistinguishable to the
css_task_iter_end(&it);
length = n;
/* now sort & (if procs) strip out duplicates */
- sort(array, length, sizeof(pid_t), cmppid, NULL);
+ if (cgroup_sane_behavior(cgrp))
+ sort(array, length, sizeof(pid_t), fried_cmppid, NULL);
+ else
+ sort(array, length, sizeof(pid_t), cmppid, NULL);
if (type == CGROUP_FILE_PROCS)
length = pidlist_uniq(array, length);
- l = cgroup_pidlist_find(cgrp, type);
+
+ l = cgroup_pidlist_find_create(cgrp, type);
if (!l) {
+ mutex_unlock(&cgrp->pidlist_mutex);
pidlist_free(array);
return -ENOMEM;
}
- /* store array, freeing old if necessary - lock already held */
+
+ /* store array, freeing old if necessary */
pidlist_free(l->list);
l->list = array;
l->length = length;
- l->use_count++;
- up_write(&l->rwsem);
*lp = l;
return 0;
}
*/
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_pidlist *l = 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;
int index = 0, pid = *pos;
- int *iter;
+ int *iter, ret;
+
+ mutex_lock(&cgrp->pidlist_mutex);
+
+ /*
+ * !NULL @of->priv indicates that this isn't the first start()
+ * after open. If the matching pidlist is around, we can use that.
+ * Look for it. Note that @of->priv can't be used directly. It
+ * could already have been destroyed.
+ */
+ if (of->priv)
+ of->priv = cgroup_pidlist_find(cgrp, type);
+
+ /*
+ * Either this is the first start() after open or the matching
+ * pidlist has been destroyed inbetween. Create a new one.
+ */
+ if (!of->priv) {
+ ret = pidlist_array_load(cgrp, type,
+ (struct cgroup_pidlist **)&of->priv);
+ if (ret)
+ return ERR_PTR(ret);
+ }
+ l = of->priv;
- down_read(&l->rwsem);
if (pid) {
int end = l->length;
while (index < end) {
int mid = (index + end) / 2;
- if (l->list[mid] == pid) {
+ if (cgroup_pid_fry(cgrp, l->list[mid]) == pid) {
index = mid;
break;
- } else if (l->list[mid] <= pid)
+ } else if (cgroup_pid_fry(cgrp, l->list[mid]) <= pid)
index = mid + 1;
else
end = mid;
return NULL;
/* Update the abstract position to be the actual pid that we found */
iter = l->list + index;
- *pos = *iter;
+ *pos = cgroup_pid_fry(cgrp, *iter);
return iter;
}
static void cgroup_pidlist_stop(struct seq_file *s, void *v)
{
- struct cgroup_pidlist *l = s->private;
- up_read(&l->rwsem);
+ struct kernfs_open_file *of = s->private;
+ struct cgroup_pidlist *l = of->priv;
+
+ if (l)
+ mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork,
+ CGROUP_PIDLIST_DESTROY_DELAY);
+ mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex);
}
static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct cgroup_pidlist *l = 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;
/*
if (p >= end) {
return NULL;
} else {
- *pos = *p;
+ *pos = cgroup_pid_fry(seq_css(s)->cgroup, *p);
return p;
}
}
static const struct seq_operations cgroup_pidlist_seq_operations = {
.start = cgroup_pidlist_start,
.stop = cgroup_pidlist_stop,
- .next = cgroup_pidlist_next,
- .show = cgroup_pidlist_show,
-};
-
-static void cgroup_release_pid_array(struct cgroup_pidlist *l)
-{
- /*
- * the case where we're the last user of this particular pidlist will
- * have us remove it from the cgroup's list, which entails taking the
- * mutex. since in pidlist_find the pidlist->lock depends on cgroup->
- * pidlist_mutex, we have to take pidlist_mutex first.
- */
- mutex_lock(&l->owner->pidlist_mutex);
- down_write(&l->rwsem);
- BUG_ON(!l->use_count);
- if (!--l->use_count) {
- /* we're the last user if refcount is 0; remove and free */
- list_del(&l->links);
- mutex_unlock(&l->owner->pidlist_mutex);
- pidlist_free(l->list);
- put_pid_ns(l->key.ns);
- up_write(&l->rwsem);
- kfree(l);
- return;
- }
- mutex_unlock(&l->owner->pidlist_mutex);
- up_write(&l->rwsem);
-}
-
-static int cgroup_pidlist_release(struct inode *inode, struct file *file)
-{
- struct cgroup_pidlist *l;
- if (!(file->f_mode & FMODE_READ))
- return 0;
- /*
- * the seq_file will only be initialized if the file was opened for
- * reading; hence we check if it's not null only in that case.
- */
- l = ((struct seq_file *)file->private_data)->private;
- cgroup_release_pid_array(l);
- return seq_release(inode, file);
-}
-
-static const struct file_operations cgroup_pidlist_operations = {
- .read = seq_read,
- .llseek = seq_lseek,
- .write = cgroup_file_write,
- .release = cgroup_pidlist_release,
-};
-
-/*
- * The following functions handle opens on a file that displays a pidlist
- * (tasks or procs). Prepare an array of the process/thread IDs of whoever's
- * in the cgroup.
- */
-/* helper function for the two below it */
-static int cgroup_pidlist_open(struct file *file, enum cgroup_filetype type)
-{
- struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
- struct cgroup_pidlist *l;
- int retval;
-
- /* Nothing to do for write-only files */
- if (!(file->f_mode & FMODE_READ))
- return 0;
-
- /* have the array populated */
- retval = pidlist_array_load(cgrp, type, &l);
- if (retval)
- return retval;
- /* configure file information */
- file->f_op = &cgroup_pidlist_operations;
-
- retval = seq_open(file, &cgroup_pidlist_seq_operations);
- if (retval) {
- cgroup_release_pid_array(l);
- return retval;
- }
- ((struct seq_file *)file->private_data)->private = l;
- return 0;
-}
-static int cgroup_tasks_open(struct inode *unused, struct file *file)
-{
- return cgroup_pidlist_open(file, CGROUP_FILE_TASKS);
-}
-static int cgroup_procs_open(struct inode *unused, struct file *file)
-{
- return cgroup_pidlist_open(file, CGROUP_FILE_PROCS);
-}
-
-static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
- struct cftype *cft)
-{
- return notify_on_release(css->cgroup);
-}
-
-static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
- struct cftype *cft, u64 val)
-{
- clear_bit(CGRP_RELEASABLE, &css->cgroup->flags);
- if (val)
- set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
- else
- clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
- 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);
-}
-
-/*
- * Unregister event and free resources.
- *
- * Gets called from workqueue.
- */
-static void cgroup_event_remove(struct work_struct *work)
-{
- struct cgroup_event *event = container_of(work, struct cgroup_event,
- remove);
- struct cgroup_subsys_state *css = event->css;
-
- remove_wait_queue(event->wqh, &event->wait);
-
- event->cft->unregister_event(css, event->cft, event->eventfd);
-
- /* Notify userspace the event is going away. */
- eventfd_signal(event->eventfd, 1);
-
- eventfd_ctx_put(event->eventfd);
- kfree(event);
- css_put(css);
-}
-
-/*
- * Gets called on POLLHUP on eventfd when user closes it.
- *
- * Called with wqh->lock held and interrupts disabled.
- */
-static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
- int sync, void *key)
-{
- struct cgroup_event *event = container_of(wait,
- struct cgroup_event, wait);
- struct cgroup *cgrp = event->css->cgroup;
- unsigned long flags = (unsigned long)key;
-
- if (flags & POLLHUP) {
- /*
- * If the event has been detached at cgroup removal, we
- * can simply return knowing the other side will cleanup
- * for us.
- *
- * We can't race against event freeing since the other
- * side will require wqh->lock via remove_wait_queue(),
- * which we hold.
- */
- spin_lock(&cgrp->event_list_lock);
- if (!list_empty(&event->list)) {
- list_del_init(&event->list);
- /*
- * We are in atomic context, but cgroup_event_remove()
- * may sleep, so we have to call it in workqueue.
- */
- schedule_work(&event->remove);
- }
- spin_unlock(&cgrp->event_list_lock);
- }
-
- return 0;
-}
-
-static void cgroup_event_ptable_queue_proc(struct file *file,
- wait_queue_head_t *wqh, poll_table *pt)
-{
- struct cgroup_event *event = container_of(pt,
- struct cgroup_event, pt);
-
- event->wqh = wqh;
- add_wait_queue(wqh, &event->wait);
-}
-
-/*
- * Parse input and register new cgroup event handler.
- *
- * Input must be in format '<event_fd> <control_fd> <args>'.
- * Interpretation of args is defined by control file implementation.
- */
-static int cgroup_write_event_control(struct cgroup_subsys_state *dummy_css,
- struct cftype *cft, const char *buffer)
-{
- struct cgroup *cgrp = dummy_css->cgroup;
- struct cgroup_event *event;
- struct cgroup_subsys_state *cfile_css;
- unsigned int efd, cfd;
- struct fd efile;
- struct fd cfile;
- char *endp;
- int ret;
-
- efd = simple_strtoul(buffer, &endp, 10);
- if (*endp != ' ')
- return -EINVAL;
- buffer = endp + 1;
-
- cfd = simple_strtoul(buffer, &endp, 10);
- if ((*endp != ' ') && (*endp != '\0'))
- return -EINVAL;
- buffer = endp + 1;
-
- event = kzalloc(sizeof(*event), GFP_KERNEL);
- if (!event)
- return -ENOMEM;
-
- INIT_LIST_HEAD(&event->list);
- init_poll_funcptr(&event->pt, cgroup_event_ptable_queue_proc);
- init_waitqueue_func_entry(&event->wait, cgroup_event_wake);
- INIT_WORK(&event->remove, cgroup_event_remove);
-
- efile = fdget(efd);
- if (!efile.file) {
- ret = -EBADF;
- goto out_kfree;
- }
-
- event->eventfd = eventfd_ctx_fileget(efile.file);
- if (IS_ERR(event->eventfd)) {
- ret = PTR_ERR(event->eventfd);
- goto out_put_efile;
- }
-
- cfile = fdget(cfd);
- if (!cfile.file) {
- ret = -EBADF;
- goto out_put_eventfd;
- }
-
- /* the process need read permission on control file */
- /* AV: shouldn't we check that it's been opened for read instead? */
- ret = inode_permission(file_inode(cfile.file), MAY_READ);
- if (ret < 0)
- goto out_put_cfile;
-
- event->cft = __file_cft(cfile.file);
- if (IS_ERR(event->cft)) {
- ret = PTR_ERR(event->cft);
- goto out_put_cfile;
- }
-
- if (!event->cft->ss) {
- ret = -EBADF;
- goto out_put_cfile;
- }
-
- /*
- * Determine the css of @cfile, verify it belongs to the same
- * cgroup as cgroup.event_control, and associate @event with it.
- * Remaining events are automatically removed on cgroup destruction
- * but the removal is asynchronous, so take an extra ref.
- */
- rcu_read_lock();
-
- ret = -EINVAL;
- event->css = cgroup_css(cgrp, event->cft->ss);
- cfile_css = css_from_dir(cfile.file->f_dentry->d_parent, event->cft->ss);
- if (event->css && event->css == cfile_css && css_tryget(event->css))
- ret = 0;
-
- rcu_read_unlock();
- if (ret)
- goto out_put_cfile;
-
- if (!event->cft->register_event || !event->cft->unregister_event) {
- ret = -EINVAL;
- goto out_put_css;
- }
-
- ret = event->cft->register_event(event->css, event->cft,
- event->eventfd, buffer);
- if (ret)
- goto out_put_css;
-
- efile.file->f_op->poll(efile.file, &event->pt);
-
- spin_lock(&cgrp->event_list_lock);
- list_add(&event->list, &cgrp->event_list);
- spin_unlock(&cgrp->event_list_lock);
+ .next = cgroup_pidlist_next,
+ .show = cgroup_pidlist_show,
+};
- fdput(cfile);
- fdput(efile);
+static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
+ struct cftype *cft)
+{
+ return notify_on_release(css->cgroup);
+}
+static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
+ struct cftype *cft, u64 val)
+{
+ clear_bit(CGRP_RELEASABLE, &css->cgroup->flags);
+ if (val)
+ set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
+ else
+ clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
return 0;
-
-out_put_css:
- css_put(event->css);
-out_put_cfile:
- fdput(cfile);
-out_put_eventfd:
- eventfd_ctx_put(event->eventfd);
-out_put_efile:
- fdput(efile);
-out_kfree:
- kfree(event);
-
- return ret;
}
static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
static struct cftype cgroup_base_files[] = {
{
.name = "cgroup.procs",
- .open = cgroup_procs_open,
+ .seq_start = cgroup_pidlist_start,
+ .seq_next = cgroup_pidlist_next,
+ .seq_stop = cgroup_pidlist_stop,
+ .seq_show = cgroup_pidlist_show,
+ .private = CGROUP_FILE_PROCS,
.write_u64 = cgroup_procs_write,
- .release = cgroup_pidlist_release,
.mode = S_IRUGO | S_IWUSR,
},
- {
- .name = "cgroup.event_control",
- .write_string = cgroup_write_event_control,
- .mode = S_IWUGO,
- },
{
.name = "cgroup.clone_children",
.flags = CFTYPE_INSANE,
{
.name = "cgroup.sane_behavior",
.flags = CFTYPE_ONLY_ON_ROOT,
- .read_seq_string = cgroup_sane_behavior_show,
+ .seq_show = cgroup_sane_behavior_show,
},
/*
{
.name = "tasks",
.flags = CFTYPE_INSANE, /* use "procs" instead */
- .open = cgroup_tasks_open,
+ .seq_start = cgroup_pidlist_start,
+ .seq_next = cgroup_pidlist_next,
+ .seq_stop = cgroup_pidlist_stop,
+ .seq_show = cgroup_pidlist_show,
+ .private = CGROUP_FILE_TASKS,
.write_u64 = cgroup_tasks_write,
- .release = cgroup_pidlist_release,
.mode = S_IRUGO | S_IWUSR,
},
{
{
.name = "release_agent",
.flags = CFTYPE_INSANE | CFTYPE_ONLY_ON_ROOT,
- .read_seq_string = cgroup_release_agent_show,
+ .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 =
container_of(ref, struct cgroup_subsys_state, refcnt);
- rcu_assign_pointer(css->cgroup->subsys[css->ss->subsys_id], NULL);
+ rcu_assign_pointer(css->cgroup->subsys[css->ss->id], NULL);
call_rcu(&css->rcu_head, css_free_rcu_fn);
}
struct cgroup_subsys *ss = css->ss;
int ret = 0;
+ lockdep_assert_held(&cgroup_tree_mutex);
lockdep_assert_held(&cgroup_mutex);
if (ss->css_online)
if (!ret) {
css->flags |= CSS_ONLINE;
css->cgroup->nr_css++;
- rcu_assign_pointer(css->cgroup->subsys[ss->subsys_id], css);
+ rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
}
return ret;
}
{
struct cgroup_subsys *ss = css->ss;
+ lockdep_assert_held(&cgroup_tree_mutex);
lockdep_assert_held(&cgroup_mutex);
if (!(css->flags & CSS_ONLINE))
css->flags &= ~CSS_ONLINE;
css->cgroup->nr_css--;
- RCU_INIT_POINTER(css->cgroup->subsys[ss->subsys_id], css);
+ RCU_INIT_POINTER(css->cgroup->subsys[ss->id], css);
}
-/*
+/**
+ * create_css - create a cgroup_subsys_state
+ * @cgrp: the cgroup new css will be associated with
+ * @ss: the subsys of new css
+ *
+ * Create a new css associated with @cgrp - @ss pair. On success, the new
+ * css is online and installed in @cgrp with all interface files created.
+ * Returns 0 on success, -errno on failure.
+ */
+static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+ struct cgroup *parent = cgrp->parent;
+ struct cgroup_subsys_state *css;
+ int err;
+
+ lockdep_assert_held(&cgroup_mutex);
+
+ css = ss->css_alloc(cgroup_css(parent, ss));
+ if (IS_ERR(css))
+ return PTR_ERR(css);
+
+ err = percpu_ref_init(&css->refcnt, css_release);
+ if (err)
+ goto err_free;
+
+ init_css(css, ss, cgrp);
+
+ err = cgroup_populate_dir(cgrp, 1 << ss->id);
+ if (err)
+ goto err_free;
+
+ err = online_css(css);
+ if (err)
+ goto err_free;
+
+ cgroup_get(cgrp);
+ css_get(css->parent);
+
+ if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
+ parent->parent) {
+ pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
+ current->comm, current->pid, ss->name);
+ if (!strcmp(ss->name, "memory"))
+ pr_warning("cgroup: \"memory\" requires setting use_hierarchy to 1 on the root.\n");
+ ss->warned_broken_hierarchy = true;
+ }
+
+ return 0;
+
+err_free:
+ percpu_ref_cancel_init(&css->refcnt);
+ ss->css_free(css);
+ 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_subsys_state *css_ar[CGROUP_SUBSYS_COUNT] = { };
struct cgroup *cgrp;
- struct cgroup_name *name;
struct cgroupfs_root *root = parent->root;
- int err = 0;
+ 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)
- goto err_free_cgrp;
- rcu_assign_pointer(cgrp->name, name);
-
- /*
- * Temporarily set the pointer to NULL, so idr_find() won't return
- * a half-baked cgroup.
- */
- cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
- if (cgrp->id < 0)
- goto err_free_name;
+ mutex_lock(&cgroup_tree_mutex);
/*
* Only live parents can have children. Note that the liveliness
*/
if (!cgroup_lock_live_group(parent)) {
err = -ENODEV;
- goto err_free_id;
+ goto err_unlock_tree;
}
- /* 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);
+ /*
+ * Temporarily set the pointer to NULL, so idr_find() won't return
+ * a half-baked cgroup.
+ */
+ cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
+ if (cgrp->id < 0) {
+ err = -ENOMEM;
+ goto err_unlock;
+ }
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);
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css;
-
- css = ss->css_alloc(cgroup_css(parent, ss));
- if (IS_ERR(css)) {
- err = PTR_ERR(css);
- goto err_free_all;
- }
- css_ar[ss->subsys_id] = css;
-
- err = percpu_ref_init(&css->refcnt, css_release);
- if (err)
- goto err_free_all;
-
- init_css(css, ss, cgrp);
+ /* 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_all;
- 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++;
-
- /* hold a ref to the parent's dentry */
- dget(parent->dentry);
-
- /* creation succeeded, notify subsystems */
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
- err = online_css(css);
- if (err)
- goto err_destroy;
-
- /* each css holds a ref to the cgroup's dentry and parent css */
- dget(dentry);
- css_get(css->parent);
-
- /* mark it consumed for error path */
- css_ar[ss->subsys_id] = NULL;
-
- if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
- parent->parent) {
- pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
- current->comm, current->pid, ss->name);
- if (!strcmp(ss->name, "memory"))
- pr_warning("cgroup: \"memory\" requires setting use_hierarchy to 1 on the root.\n");
- ss->warned_broken_hierarchy = true;
- }
- }
+ atomic_inc(&root->nr_cgrps);
+ cgroup_get(parent);
+ /*
+ * @cgrp is now fully operational. If something fails after this
+ * point, it'll be released via the normal destruction path.
+ */
idr_replace(&root->cgroup_idr, cgrp, cgrp->id);
err = cgroup_addrm_files(cgrp, cgroup_base_files, true);
if (err)
goto err_destroy;
- err = cgroup_populate_dir(cgrp, root->subsys_mask);
- if (err)
- goto err_destroy;
+ /* let's create and online css's */
+ for_each_subsys(ss, ssid) {
+ if (root->subsys_mask & (1 << ssid)) {
+ err = create_css(cgrp, ss);
+ if (err)
+ goto err_destroy;
+ }
+ }
+
+ kernfs_activate(kn);
mutex_unlock(&cgroup_mutex);
- mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
return 0;
-err_free_all:
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
- if (css) {
- percpu_ref_cancel_init(&css->refcnt);
- ss->css_free(css);
- }
- }
- mutex_unlock(&cgroup_mutex);
- /* Release the reference count that we took on the superblock */
- deactivate_super(sb);
err_free_id:
idr_remove(&root->cgroup_idr, cgrp->id);
-err_free_name:
- kfree(rcu_dereference_raw(cgrp->name));
-err_free_cgrp:
+err_unlock:
+ mutex_unlock(&cgroup_mutex);
+err_unlock_tree:
+ mutex_unlock(&cgroup_tree_mutex);
kfree(cgrp);
return err;
err_destroy:
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
- if (css) {
- percpu_ref_cancel_init(&css->refcnt);
- ss->css_free(css);
- }
- }
cgroup_destroy_locked(cgrp);
mutex_unlock(&cgroup_mutex);
- mutex_unlock(&dentry->d_inode->i_mutex);
+ mutex_unlock(&cgroup_tree_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);
}
/*
container_of(work, struct cgroup_subsys_state, destroy_work);
struct cgroup *cgrp = css->cgroup;
+ mutex_lock(&cgroup_tree_mutex);
mutex_lock(&cgroup_mutex);
/*
cgroup_destroy_css_killed(cgrp);
mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
/*
* Put the css refs from kill_css(). Each css holds an extra
*/
static void kill_css(struct cgroup_subsys_state *css)
{
- cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id);
+ /*
+ * This must happen before css is disassociated with its cgroup.
+ * See seq_css() for details.
+ */
+ cgroup_clear_dir(css->cgroup, 1 << css->ss->id);
/*
* Killing would put the base ref, but we need to keep it alive
static int cgroup_destroy_locked(struct cgroup *cgrp)
__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
{
- struct dentry *d = cgrp->dentry;
- struct cgroup_event *event, *tmp;
- struct cgroup_subsys *ss;
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);
/*
/*
* Initiate massacre of all css's. cgroup_destroy_css_killed()
* will be invoked to perform the rest of destruction once the
- * percpu refs of all css's are confirmed to be killed.
+ * percpu refs of all css's are confirmed to be killed. This
+ * involves removing the subsystem's files, drop cgroup_mutex.
*/
- for_each_root_subsys(cgrp->root, ss) {
- struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-
- if (css)
- kill_css(css);
- }
+ mutex_unlock(&cgroup_mutex);
+ for_each_css(css, ssid, cgrp)
+ kill_css(css);
+ mutex_lock(&cgroup_mutex);
/*
* Mark @cgrp dead. This prevents further task migration and child
if (!cgrp->nr_css)
cgroup_destroy_css_killed(cgrp);
- /*
- * 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.
- */
- cgroup_addrm_files(cgrp, cgroup_base_files, false);
- dget(d);
- cgroup_d_remove_dir(d);
+ /* remove @cgrp directory along with the base files */
+ mutex_unlock(&cgroup_mutex);
/*
- * Unregister events and notify userspace.
- * Notify userspace about cgroup removing only after rmdir of cgroup
- * directory to avoid race between userspace and kernelspace.
+ * 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.
*/
- spin_lock(&cgrp->event_list_lock);
- list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
- list_del_init(&event->list);
- schedule_work(&event->remove);
- }
- spin_unlock(&cgrp->event_list_lock);
+ 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;
-
- mutex_lock(&cgroup_mutex);
- ret = cgroup_destroy_locked(dentry->d_fsdata);
- mutex_unlock(&cgroup_mutex);
+ struct cgroup *cgrp = kn->priv;
+ int ret = 0;
- return ret;
-}
+ /*
+ * 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);
-static void __init_or_module cgroup_init_cftsets(struct cgroup_subsys *ss)
-{
- INIT_LIST_HEAD(&ss->cftsets);
+ mutex_lock(&cgroup_tree_mutex);
+ mutex_lock(&cgroup_mutex);
/*
- * 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;
printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);
+ 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 */
- list_add(&ss->sibling, &cgroup_dummy_root.subsys_list);
ss->root = &cgroup_dummy_root;
css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss));
/* We don't handle early failures gracefully */
* pointer to this state - since the subsystem is
* newly registered, all tasks and hence the
* init_css_set is in the subsystem's top cgroup. */
- init_css_set.subsys[ss->subsys_id] = css;
+ init_css_set.subsys[ss->id] = css;
need_forkexit_callback |= ss->fork || ss->exit;
BUG_ON(online_css(css));
mutex_unlock(&cgroup_mutex);
-
- /* this function shouldn't be used with modular subsystems, since they
- * need to register a subsys_id, among other things */
- BUG_ON(ss->module);
-}
-
-/**
- * cgroup_load_subsys: load and register a modular subsystem at runtime
- * @ss: the subsystem to load
- *
- * This function should be called in a modular subsystem's initcall. If the
- * subsystem is built as a module, it will be assigned a new subsys_id and set
- * up for use. If the subsystem is built-in anyway, work is delegated to the
- * simpler cgroup_init_subsys.
- */
-int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
-{
- struct cgroup_subsys_state *css;
- int i, ret;
- struct hlist_node *tmp;
- struct css_set *cset;
- unsigned long key;
-
- /* check name and function validity */
- if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN ||
- ss->css_alloc == NULL || ss->css_free == NULL)
- return -EINVAL;
-
- /*
- * we don't support callbacks in modular subsystems. this check is
- * before the ss->module check for consistency; a subsystem that could
- * be a module should still have no callbacks even if the user isn't
- * compiling it as one.
- */
- if (ss->fork || ss->exit)
- return -EINVAL;
-
- /*
- * an optionally modular subsystem is built-in: we want to do nothing,
- * since cgroup_init_subsys will have already taken care of it.
- */
- if (ss->module == NULL) {
- /* a sanity check */
- BUG_ON(cgroup_subsys[ss->subsys_id] != ss);
- return 0;
- }
-
- /* init base cftset */
- cgroup_init_cftsets(ss);
-
- mutex_lock(&cgroup_mutex);
- cgroup_subsys[ss->subsys_id] = ss;
-
- /*
- * no ss->css_alloc seems to need anything important in the ss
- * struct, so this can happen first (i.e. before the dummy root
- * attachment).
- */
- css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss));
- if (IS_ERR(css)) {
- /* failure case - need to deassign the cgroup_subsys[] slot. */
- cgroup_subsys[ss->subsys_id] = NULL;
- mutex_unlock(&cgroup_mutex);
- return PTR_ERR(css);
- }
-
- list_add(&ss->sibling, &cgroup_dummy_root.subsys_list);
- ss->root = &cgroup_dummy_root;
-
- /* our new subsystem will be attached to the dummy hierarchy. */
- init_css(css, ss, cgroup_dummy_top);
-
- /*
- * Now we need to entangle the css into the existing css_sets. unlike
- * in cgroup_init_subsys, there are now multiple css_sets, so each one
- * will need a new pointer to it; done by iterating the css_set_table.
- * furthermore, modifying the existing css_sets will corrupt the hash
- * table state, so each changed css_set will need its hash recomputed.
- * this is all done under the css_set_lock.
- */
- write_lock(&css_set_lock);
- hash_for_each_safe(css_set_table, i, tmp, cset, hlist) {
- /* skip entries that we already rehashed */
- if (cset->subsys[ss->subsys_id])
- continue;
- /* remove existing entry */
- hash_del(&cset->hlist);
- /* set new value */
- cset->subsys[ss->subsys_id] = css;
- /* recompute hash and restore entry */
- key = css_set_hash(cset->subsys);
- hash_add(css_set_table, &cset->hlist, key);
- }
- write_unlock(&css_set_lock);
-
- ret = online_css(css);
- if (ret)
- goto err_unload;
-
- /* success! */
- mutex_unlock(&cgroup_mutex);
- return 0;
-
-err_unload:
- mutex_unlock(&cgroup_mutex);
- /* @ss can't be mounted here as try_module_get() would fail */
- cgroup_unload_subsys(ss);
- return ret;
-}
-EXPORT_SYMBOL_GPL(cgroup_load_subsys);
-
-/**
- * cgroup_unload_subsys: unload a modular subsystem
- * @ss: the subsystem to unload
- *
- * This function should be called in a modular subsystem's exitcall. When this
- * function is invoked, the refcount on the subsystem's module will be 0, so
- * the subsystem will not be attached to any hierarchy.
- */
-void cgroup_unload_subsys(struct cgroup_subsys *ss)
-{
- struct cgrp_cset_link *link;
-
- BUG_ON(ss->module == NULL);
-
- /*
- * we shouldn't be called if the subsystem is in use, and the use of
- * try_module_get() in rebind_subsystems() should ensure that it
- * doesn't start being used while we're killing it off.
- */
- BUG_ON(ss->root != &cgroup_dummy_root);
-
- mutex_lock(&cgroup_mutex);
-
- offline_css(cgroup_css(cgroup_dummy_top, ss));
-
- /* deassign the subsys_id */
- cgroup_subsys[ss->subsys_id] = NULL;
-
- /* remove subsystem from the dummy root's list of subsystems */
- list_del_init(&ss->sibling);
-
- /*
- * disentangle the css from all css_sets attached to the dummy
- * top. as in loading, we need to pay our respects to the hashtable
- * gods.
- */
- write_lock(&css_set_lock);
- list_for_each_entry(link, &cgroup_dummy_top->cset_links, cset_link) {
- struct css_set *cset = link->cset;
- unsigned long key;
-
- hash_del(&cset->hlist);
- cset->subsys[ss->subsys_id] = NULL;
- key = css_set_hash(cset->subsys);
- hash_add(css_set_table, &cset->hlist, key);
- }
- write_unlock(&css_set_lock);
-
- /*
- * remove subsystem's css from the cgroup_dummy_top and free it -
- * need to free before marking as null because ss->css_free needs
- * the cgrp->subsys pointer to find their state.
- */
- ss->css_free(cgroup_css(cgroup_dummy_top, ss));
- RCU_INIT_POINTER(cgroup_dummy_top->subsys[ss->subsys_id], NULL);
-
- mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
}
-EXPORT_SYMBOL_GPL(cgroup_unload_subsys);
/**
* cgroup_init_early - cgroup initialization at system boot
list_add(&init_cgrp_cset_link.cset_link, &cgroup_dummy_top->cset_links);
list_add(&init_cgrp_cset_link.cgrp_link, &init_css_set.cgrp_links);
- /* at bootup time, we don't worry about modular subsystems */
- for_each_builtin_subsys(ss, i) {
- BUG_ON(!ss->name);
- BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
- BUG_ON(!ss->css_alloc);
- BUG_ON(!ss->css_free);
- if (ss->subsys_id != i) {
- printk(KERN_ERR "cgroup: Subsys %s id == %d\n",
- ss->name, ss->subsys_id);
- BUG();
- }
+ for_each_subsys(ss, i) {
+ WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id,
+ "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p name:id=%d:%s\n",
+ i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free,
+ ss->id, ss->name);
+ WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN,
+ "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]);
+
+ ss->id = i;
+ ss->name = cgroup_subsys_name[i];
if (ss->early_init)
cgroup_init_subsys(ss);
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_builtin_subsys(ss, i) {
+ 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_lock(&cgroup_mutex);
- mutex_lock(&cgroup_root_mutex);
/* Add init_css_set to the hash table */
key = css_set_hash(init_css_set.subsys);
0, 1, GFP_KERNEL);
BUG_ON(err < 0);
- mutex_unlock(&cgroup_root_mutex);
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)
/*
* There isn't much point in executing destruction path in
* parallel. Good chunk is serialized with cgroup_mutex anyway.
- * Use 1 for @max_active.
+ *
+ * XXX: Must be ordered to make sure parent is offlined after
+ * children. The ordering requirement is for memcg where a
+ * parent's offline may wait for a child's leading to deadlock. In
+ * the long term, this should be fixed from memcg side.
*
* We would prefer to do this in cgroup_init() above, but that
* is called before init_workqueues(): so leave this until after.
*/
- cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
+ cgroup_destroy_wq = alloc_ordered_workqueue("cgroup_destroy", 0);
BUG_ON(!cgroup_destroy_wq);
+
+ /*
+ * Used to destroy pidlists and separate to serve as flush domain.
+ * Cap @max_active to 1 too.
+ */
+ cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy",
+ 0, 1);
+ BUG_ON(!cgroup_pidlist_destroy_wq);
+
return 0;
}
core_initcall(cgroup_wq_init);
{
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;
for_each_active_root(root) {
struct cgroup_subsys *ss;
struct cgroup *cgrp;
- int count = 0;
+ int ssid, count = 0;
seq_printf(m, "%d:", root->hierarchy_id);
- for_each_root_subsys(root, ss)
- seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
+ for_each_subsys(ss, ssid)
+ if (root->subsys_mask & (1 << ssid))
+ seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
if (strlen(root->name))
seq_printf(m, "%sname=%s", count ? "," : "",
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;
* and addition to css_set.
*/
if (need_forkexit_callback) {
- /*
- * fork/exit callbacks are supported only for builtin
- * subsystems, and the builtin section of the subsys
- * array is immutable, so we don't need to lock the
- * subsys array here. On the other hand, modular section
- * of the array can be freed at module unload, so we
- * can't touch that.
- */
- for_each_builtin_subsys(ss, i)
+ for_each_subsys(ss, i)
if (ss->fork)
ss->fork(child);
}
RCU_INIT_POINTER(tsk->cgroups, &init_css_set);
if (run_callbacks && need_forkexit_callback) {
- /*
- * fork/exit callbacks are supported only for builtin
- * subsystems, see cgroup_post_fork() for details.
- */
- for_each_builtin_subsys(ss, i) {
+ /* see cgroup_post_fork() for details */
+ for_each_subsys(ss, i) {
if (ss->exit) {
struct cgroup_subsys_state *old_css = cset->subsys[i];
struct cgroup_subsys_state *css = task_css(tsk, i);
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;
if (!*token)
continue;
- /*
- * cgroup_disable, being at boot time, can't know about
- * module subsystems, so we don't worry about them.
- */
- for_each_builtin_subsys(ss, i) {
+ for_each_subsys(ss, i) {
if (!strcmp(token, ss->name)) {
ss->disabled = 1;
printk(KERN_INFO "Disabling %s control group"
__setup("cgroup_disable=", cgroup_disable);
/**
- * css_from_dir - get corresponding css from the dentry of a cgroup dir
+ * css_tryget_from_dir - get corresponding css from the dentry of a cgroup dir
* @dentry: directory dentry of interest
* @ss: subsystem of interest
*
- * Must be called under RCU read lock. The caller is responsible for
- * pinning the returned css if it needs to be accessed outside the RCU
- * critical section.
+ * If @dentry is a directory for a cgroup which has @ss enabled on it, try
+ * to get the corresponding css and return it. If such css doesn't exist
+ * or can't be pinned, an ERR_PTR value is returned.
*/
-struct cgroup_subsys_state *css_from_dir(struct dentry *dentry,
- struct cgroup_subsys *ss)
+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;
- WARN_ON_ONCE(!rcu_read_lock_held());
-
/* 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);
- cgrp = __d_cgrp(dentry);
- return cgroup_css(cgrp, ss) ?: ERR_PTR(-ENOENT);
+ rcu_read_lock();
+
+ /*
+ * 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);
+
+ rcu_read_unlock();
+ return css;
}
/**
{
struct cgroup *cgrp;
- rcu_lockdep_assert(rcu_read_lock_held() ||
- lockdep_is_held(&cgroup_mutex),
- "css_from_id() needs proper protection");
+ cgroup_assert_mutexes_or_rcu_locked();
cgrp = idr_find(&ss->root->cgroup_idr, id);
if (cgrp)
return count;
}
-static int current_css_set_cg_links_read(struct cgroup_subsys_state *css,
- struct cftype *cft,
- struct seq_file *seq)
+static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
{
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;
}
#define MAX_TASKS_SHOWN_PER_CSS 25
-static int cgroup_css_links_read(struct cgroup_subsys_state *css,
- struct cftype *cft, struct seq_file *seq)
+static int cgroup_css_links_read(struct seq_file *seq, void *v)
{
+ struct cgroup_subsys_state *css = seq_css(seq);
struct cgrp_cset_link *link;
read_lock(&css_set_lock);
{
.name = "current_css_set_cg_links",
- .read_seq_string = current_css_set_cg_links_read,
+ .seq_show = current_css_set_cg_links_read,
},
{
.name = "cgroup_css_links",
- .read_seq_string = cgroup_css_links_read,
+ .seq_show = cgroup_css_links_read,
},
{
{ } /* terminate */
};
-struct cgroup_subsys debug_subsys = {
- .name = "debug",
+struct cgroup_subsys debug_cgrp_subsys = {
.css_alloc = debug_css_alloc,
.css_free = debug_css_free,
- .subsys_id = debug_subsys_id,
.base_cftypes = debug_files,
};
#endif /* CONFIG_CGROUP_DEBUG */
projects / firefly-linux-kernel-4.4.55.git / blobdiff