* Based originally on the cpuset system, extracted by Paul Menage
* Copyright (C) 2006 Google, Inc
*
+ * Notifications support
+ * Copyright (C) 2009 Nokia Corporation
+ * Author: Kirill A. Shutemov
+ *
* Copyright notices from the original cpuset code:
* --------------------------------------------------
* Copyright (C) 2003 BULL SA.
*/
#include <linux/cgroup.h>
-#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/cgroupstats.h>
#include <linux/hash.h>
#include <linux/namei.h>
-#include <linux/smp_lock.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 <asm/atomic.h>
* is called after synchronize_rcu(). But for safe use, css_is_removed()
* css_tryget() should be used for avoiding race.
*/
- struct cgroup_subsys_state *css;
+ struct cgroup_subsys_state __rcu *css;
/*
* ID of this css.
*/
unsigned short stack[0]; /* Array of Length (depth+1) */
};
+/*
+ * cgroup_event represents events which userspace want to recieve.
+ */
+struct cgroup_event {
+ /*
+ * Cgroup which the event belongs to.
+ */
+ struct cgroup *cgrp;
+ /*
+ * 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 */
return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
}
+static int clone_children(const struct cgroup *cgrp)
+{
+ return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+}
+
/*
* for_each_subsys() allows you to iterate on each subsystem attached to
* an active hierarchy
{
mutex_lock(&cgroup_mutex);
}
+EXPORT_SYMBOL_GPL(cgroup_lock);
/**
* cgroup_unlock - release lock on cgroup changes
{
mutex_unlock(&cgroup_mutex);
}
+EXPORT_SYMBOL_GPL(cgroup_unlock);
/*
* A couple of forward declarations required, due to cyclic reference loop:
*/
static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode);
+static struct dentry *cgroup_lookup(struct inode *, struct dentry *, struct nameidata *);
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp);
static const struct inode_operations cgroup_dir_inode_operations;
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();
if (ret)
break;
}
+
return ret;
}
iput(inode);
}
+static int cgroup_delete(const struct dentry *d)
+{
+ return 1;
+}
+
static void remove_dir(struct dentry *d)
{
struct dentry *parent = dget(d->d_parent);
struct list_head *node;
BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
- spin_lock(&dcache_lock);
+ spin_lock(&dentry->d_lock);
node = dentry->d_subdirs.next;
while (node != &dentry->d_subdirs) {
struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
+
+ spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
list_del_init(node);
if (d->d_inode) {
/* This should never be called on a cgroup
* directory with child cgroups */
BUG_ON(d->d_inode->i_mode & S_IFDIR);
- d = dget_locked(d);
- spin_unlock(&dcache_lock);
+ dget_dlock(d);
+ spin_unlock(&d->d_lock);
+ spin_unlock(&dentry->d_lock);
d_delete(d);
simple_unlink(dentry->d_inode, d);
dput(d);
- spin_lock(&dcache_lock);
- }
+ spin_lock(&dentry->d_lock);
+ } else
+ spin_unlock(&d->d_lock);
node = dentry->d_subdirs.next;
}
- spin_unlock(&dcache_lock);
+ spin_unlock(&dentry->d_lock);
}
/*
*/
static void cgroup_d_remove_dir(struct dentry *dentry)
{
+ struct dentry *parent;
+
cgroup_clear_directory(dentry);
- spin_lock(&dcache_lock);
+ 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(&dcache_lock);
+ spin_unlock(&dentry->d_lock);
+ spin_unlock(&parent->d_lock);
remove_dir(dentry);
}
}
/*
- * Call with cgroup_mutex held.
+ * 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 final_bits)
if (ss->bind)
ss->bind(ss, cgrp);
mutex_unlock(&ss->hierarchy_mutex);
+ /* refcount was already taken, and we're keeping it */
} else if (bit & removed_bits) {
/* We're removing this subsystem */
BUG_ON(ss == NULL);
subsys[i]->root = &rootnode;
list_move(&ss->sibling, &rootnode.subsys_list);
mutex_unlock(&ss->hierarchy_mutex);
+ /* subsystem is now free - drop reference on module */
+ module_put(ss->module);
} else if (bit & final_bits) {
/* Subsystem state should already exist */
BUG_ON(ss == NULL);
BUG_ON(!cgrp->subsys[i]);
+ /*
+ * a refcount was taken, but we already had one, so
+ * drop the extra reference.
+ */
+ module_put(ss->module);
+#ifdef CONFIG_MODULE_UNLOAD
+ BUG_ON(ss->module && !module_refcount(ss->module));
+#endif
} else {
/* Subsystem state shouldn't exist */
BUG_ON(cgrp->subsys[i]);
seq_puts(seq, ",noprefix");
if (strlen(root->release_agent_path))
seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+ if (clone_children(&root->top_cgroup))
+ seq_puts(seq, ",clone_children");
if (strlen(root->name))
seq_printf(seq, ",name=%s", root->name);
mutex_unlock(&cgroup_mutex);
unsigned long subsys_bits;
unsigned long flags;
char *release_agent;
+ bool clone_children;
char *name;
/* User explicitly requested empty subsystem */
bool none;
/*
* Convert a hierarchy specifier into a bitmask of subsystems and flags. Call
- * with cgroup_mutex held to protect the subsys[] array.
+ * with cgroup_mutex held to protect the subsys[] array. This function takes
+ * refcounts on subsystems to be used, unless it returns error, in which case
+ * no refcounts are taken.
*/
-static int parse_cgroupfs_options(char *data,
- struct cgroup_sb_opts *opts)
+static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
{
- char *token, *o = data ?: "all";
+ char *token, *o = data;
+ bool all_ss = false, one_ss = false;
unsigned long mask = (unsigned long)-1;
+ int i;
+ bool module_pin_failed = false;
BUG_ON(!mutex_is_locked(&cgroup_mutex));
while ((token = strsep(&o, ",")) != NULL) {
if (!*token)
return -EINVAL;
- if (!strcmp(token, "all")) {
- /* Add all non-disabled subsystems */
- int i;
- opts->subsys_bits = 0;
- for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
- struct cgroup_subsys *ss = subsys[i];
- if (ss == NULL)
- continue;
- if (!ss->disabled)
- opts->subsys_bits |= 1ul << i;
- }
- } else if (!strcmp(token, "none")) {
+ if (!strcmp(token, "none")) {
/* Explicitly have no subsystems */
opts->none = true;
- } else if (!strcmp(token, "noprefix")) {
+ continue;
+ }
+ if (!strcmp(token, "all")) {
+ /* Mutually exclusive option 'all' + subsystem name */
+ if (one_ss)
+ return -EINVAL;
+ all_ss = true;
+ continue;
+ }
+ if (!strcmp(token, "noprefix")) {
set_bit(ROOT_NOPREFIX, &opts->flags);
- } else if (!strncmp(token, "release_agent=", 14)) {
+ continue;
+ }
+ if (!strcmp(token, "clone_children")) {
+ opts->clone_children = true;
+ continue;
+ }
+ if (!strncmp(token, "release_agent=", 14)) {
/* Specifying two release agents is forbidden */
if (opts->release_agent)
return -EINVAL;
opts->release_agent =
- kstrndup(token + 14, PATH_MAX, GFP_KERNEL);
+ kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL);
if (!opts->release_agent)
return -ENOMEM;
- } else if (!strncmp(token, "name=", 5)) {
- int i;
+ continue;
+ }
+ if (!strncmp(token, "name=", 5)) {
const char *name = token + 5;
/* Can't specify an empty name */
if (!strlen(name))
if (opts->name)
return -EINVAL;
opts->name = kstrndup(name,
- MAX_CGROUP_ROOT_NAMELEN,
+ MAX_CGROUP_ROOT_NAMELEN - 1,
GFP_KERNEL);
if (!opts->name)
return -ENOMEM;
- } else {
- struct cgroup_subsys *ss;
- int i;
- for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
- ss = subsys[i];
- if (ss == NULL)
- continue;
- if (!strcmp(token, ss->name)) {
- if (!ss->disabled)
- set_bit(i, &opts->subsys_bits);
- break;
- }
- }
- if (i == CGROUP_SUBSYS_COUNT)
- return -ENOENT;
+
+ continue;
+ }
+
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss == NULL)
+ continue;
+ if (strcmp(token, ss->name))
+ continue;
+ if (ss->disabled)
+ continue;
+
+ /* Mutually exclusive option 'all' + subsystem name */
+ if (all_ss)
+ return -EINVAL;
+ set_bit(i, &opts->subsys_bits);
+ one_ss = true;
+
+ break;
+ }
+ if (i == CGROUP_SUBSYS_COUNT)
+ return -ENOENT;
+ }
+
+ /*
+ * If the 'all' option was specified select all the subsystems,
+ * otherwise 'all, 'none' and a subsystem name options were not
+ * specified, let's default to 'all'
+ */
+ if (all_ss || (!all_ss && !one_ss && !opts->none)) {
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss == NULL)
+ continue;
+ if (ss->disabled)
+ continue;
+ set_bit(i, &opts->subsys_bits);
}
}
if (!opts->subsys_bits && !opts->name)
return -EINVAL;
+ /*
+ * Grab references on all the modules we'll need, so the subsystems
+ * don't dance around before rebind_subsystems attaches them. This may
+ * take duplicate reference counts on a subsystem that's already used,
+ * but rebind_subsystems handles this case.
+ */
+ for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) {
+ unsigned long bit = 1UL << i;
+
+ if (!(bit & opts->subsys_bits))
+ continue;
+ if (!try_module_get(subsys[i]->module)) {
+ module_pin_failed = true;
+ break;
+ }
+ }
+ if (module_pin_failed) {
+ /*
+ * oops, one of the modules was going away. this means that we
+ * raced with a module_delete call, and to the user this is
+ * essentially a "subsystem doesn't exist" case.
+ */
+ for (i--; i >= CGROUP_BUILTIN_SUBSYS_COUNT; i--) {
+ /* drop refcounts only on the ones we took */
+ unsigned long bit = 1UL << i;
+
+ if (!(bit & opts->subsys_bits))
+ continue;
+ module_put(subsys[i]->module);
+ }
+ return -ENOENT;
+ }
+
return 0;
}
+static void drop_parsed_module_refcounts(unsigned long subsys_bits)
+{
+ int i;
+ for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) {
+ unsigned long bit = 1UL << i;
+
+ if (!(bit & subsys_bits))
+ continue;
+ module_put(subsys[i]->module);
+ }
+}
+
static int cgroup_remount(struct super_block *sb, int *flags, char *data)
{
int ret = 0;
struct cgroup *cgrp = &root->top_cgroup;
struct cgroup_sb_opts opts;
- lock_kernel();
mutex_lock(&cgrp->dentry->d_inode->i_mutex);
mutex_lock(&cgroup_mutex);
if (ret)
goto out_unlock;
- /* Don't allow flags to change at remount */
- if (opts.flags != root->flags) {
- ret = -EINVAL;
- goto out_unlock;
- }
-
- /* Don't allow name to change at remount */
- if (opts.name && strcmp(opts.name, root->name)) {
+ /* Don't allow flags or name to change at remount */
+ if (opts.flags != root->flags ||
+ (opts.name && strcmp(opts.name, root->name))) {
ret = -EINVAL;
+ drop_parsed_module_refcounts(opts.subsys_bits);
goto out_unlock;
}
ret = rebind_subsystems(root, opts.subsys_bits);
- if (ret)
+ if (ret) {
+ drop_parsed_module_refcounts(opts.subsys_bits);
goto out_unlock;
+ }
/* (re)populate subsystem files */
cgroup_populate_dir(cgrp);
kfree(opts.name);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
- unlock_kernel();
return ret;
}
INIT_LIST_HEAD(&cgrp->release_list);
INIT_LIST_HEAD(&cgrp->pidlists);
mutex_init(&cgrp->pidlist_mutex);
+ INIT_LIST_HEAD(&cgrp->event_list);
+ spin_lock_init(&cgrp->event_list_lock);
}
static void init_cgroup_root(struct cgroupfs_root *root)
strcpy(root->release_agent_path, opts->release_agent);
if (opts->name)
strcpy(root->name, opts->name);
+ if (opts->clone_children)
+ set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags);
return root;
}
static int cgroup_get_rootdir(struct super_block *sb)
{
+ static const struct dentry_operations cgroup_dops = {
+ .d_iput = cgroup_diput,
+ .d_delete = cgroup_delete,
+ };
+
struct inode *inode =
cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);
struct dentry *dentry;
return -ENOMEM;
}
sb->s_root = dentry;
+ /* for everything else we want ->d_op set */
+ sb->s_d_op = &cgroup_dops;
return 0;
}
-static int cgroup_get_sb(struct file_system_type *fs_type,
+static struct dentry *cgroup_mount(struct file_system_type *fs_type,
int flags, const char *unused_dev_name,
- void *data, struct vfsmount *mnt)
+ void *data)
{
struct cgroup_sb_opts opts;
struct cgroupfs_root *root;
new_root = cgroup_root_from_opts(&opts);
if (IS_ERR(new_root)) {
ret = PTR_ERR(new_root);
- goto out_err;
+ goto drop_modules;
}
opts.new_root = new_root;
if (IS_ERR(sb)) {
ret = PTR_ERR(sb);
cgroup_drop_root(opts.new_root);
- goto out_err;
+ goto drop_modules;
}
root = sb->s_fs_info;
free_cg_links(&tmp_cg_links);
goto drop_new_super;
}
+ /*
+ * There must be no failure case after here, since rebinding
+ * takes care of subsystems' refcounts, which are explicitly
+ * dropped in the failure exit path.
+ */
/* EBUSY should be the only error here */
BUG_ON(ret);
* any) is not needed
*/
cgroup_drop_root(opts.new_root);
+ /* no subsys rebinding, so refcounts don't change */
+ drop_parsed_module_refcounts(opts.subsys_bits);
}
- simple_set_mnt(mnt, sb);
kfree(opts.release_agent);
kfree(opts.name);
- return 0;
+ return dget(sb->s_root);
drop_new_super:
deactivate_locked_super(sb);
+ drop_modules:
+ drop_parsed_module_refcounts(opts.subsys_bits);
out_err:
kfree(opts.release_agent);
kfree(opts.name);
-
- return ret;
+ return ERR_PTR(ret);
}
static void cgroup_kill_sb(struct super_block *sb) {
static struct file_system_type cgroup_fs_type = {
.name = "cgroup",
- .get_sb = cgroup_get_sb,
+ .mount = cgroup_mount,
.kill_sb = cgroup_kill_sb,
};
+static struct kobject *cgroup_kobj;
+
static inline struct cgroup *__d_cgrp(struct dentry *dentry)
{
return dentry->d_fsdata;
int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
{
char *start;
- struct dentry *dentry = rcu_dereference(cgrp->dentry);
+ struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
+ rcu_read_lock_held() ||
+ cgroup_lock_is_held());
if (!dentry || cgrp == dummytop) {
/*
*--start = '\0';
for (;;) {
int len = dentry->d_name.len;
+
if ((start -= len) < buf)
return -ENAMETOOLONG;
- memcpy(start, cgrp->dentry->d_name.name, len);
+ memcpy(start, dentry->d_name.name, len);
cgrp = cgrp->parent;
if (!cgrp)
break;
- dentry = rcu_dereference(cgrp->dentry);
+
+ dentry = rcu_dereference_check(cgrp->dentry,
+ rcu_read_lock_held() ||
+ cgroup_lock_is_held());
if (!cgrp->parent)
continue;
if (--start < buf)
memmove(buf, start, buf + buflen - start);
return 0;
}
+EXPORT_SYMBOL_GPL(cgroup_path);
/**
* cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
/* Update the css_set linked lists if we're using them */
write_lock(&css_set_lock);
- if (!list_empty(&tsk->cg_list)) {
- list_del(&tsk->cg_list);
- list_add(&tsk->cg_list, &newcg->tasks);
- }
+ if (!list_empty(&tsk->cg_list))
+ list_move(&tsk->cg_list, &newcg->tasks);
write_unlock(&css_set_lock);
for_each_subsys(root, ss) {
return retval;
}
+/**
+ * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
+ * @from: attach to all cgroups of a given task
+ * @tsk: the task to be attached
+ */
+int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
+{
+ struct cgroupfs_root *root;
+ int retval = 0;
+
+ cgroup_lock();
+ for_each_active_root(root) {
+ struct cgroup *from_cg = task_cgroup_from_root(from, root);
+
+ retval = cgroup_attach_task(from_cg, tsk);
+ if (retval)
+ break;
+ }
+ cgroup_unlock();
+
+ return retval;
+}
+EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
+
/*
* Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex
* held. May take task_lock of task
}
return true;
}
+EXPORT_SYMBOL_GPL(cgroup_lock_live_group);
static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
const char *buffer)
{
BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
+ if (strlen(buffer) >= PATH_MAX)
+ return -EINVAL;
if (!cgroup_lock_live_group(cgrp))
return -ENODEV;
strcpy(cgrp->root->release_agent_path, buffer);
};
static const struct inode_operations cgroup_dir_inode_operations = {
- .lookup = simple_lookup,
+ .lookup = cgroup_lookup,
.mkdir = cgroup_mkdir,
.rmdir = cgroup_rmdir,
.rename = cgroup_rename,
};
+static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+{
+ if (dentry->d_name.len > NAME_MAX)
+ return ERR_PTR(-ENAMETOOLONG);
+ d_add(dentry, NULL);
+ return NULL;
+}
+
+/*
+ * Check if a file is a control file
+ */
+static inline struct cftype *__file_cft(struct file *file)
+{
+ if (file->f_dentry->d_inode->i_fop != &cgroup_file_operations)
+ return ERR_PTR(-EINVAL);
+ return __d_cft(file->f_dentry);
+}
+
static int cgroup_create_file(struct dentry *dentry, mode_t mode,
struct super_block *sb)
{
- static const struct dentry_operations cgroup_dops = {
- .d_iput = cgroup_diput,
- };
-
struct inode *inode;
if (!dentry)
inode->i_size = 0;
inode->i_fop = &cgroup_file_operations;
}
- dentry->d_op = &cgroup_dops;
d_instantiate(dentry, inode);
dget(dentry); /* Extra count - pin the dentry in core */
return 0;
{
struct cgroup_pidlist *l;
/* don't need task_nsproxy() if we're looking at ourself */
- struct pid_namespace *ns = get_pid_ns(current->nsproxy->pid_ns);
+ struct pid_namespace *ns = current->nsproxy->pid_ns;
+
/*
* We can't drop the pidlist_mutex before taking the l->mutex in case
* the last ref-holder is trying to remove l from the list at the same
mutex_lock(&cgrp->pidlist_mutex);
list_for_each_entry(l, &cgrp->pidlists, links) {
if (l->key.type == type && l->key.ns == ns) {
- /* found a matching list - drop the extra refcount */
- put_pid_ns(ns);
/* make sure l doesn't vanish out from under us */
down_write(&l->mutex);
mutex_unlock(&cgrp->pidlist_mutex);
l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
if (!l) {
mutex_unlock(&cgrp->pidlist_mutex);
- put_pid_ns(ns);
return l;
}
init_rwsem(&l->mutex);
down_write(&l->mutex);
l->key.type = type;
- l->key.ns = ns;
+ l->key.ns = get_pid_ns(ns);
l->use_count = 0; /* don't increment here */
l->list = NULL;
l->owner = cgrp;
}
/*
+ * 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 *cgrp = event->cgrp;
+
+ event->cft->unregister_event(cgrp, event->cft, event->eventfd);
+
+ eventfd_ctx_put(event->eventfd);
+ kfree(event);
+ dput(cgrp->dentry);
+}
+
+/*
+ * 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->cgrp;
+ unsigned long flags = (unsigned long)key;
+
+ if (flags & POLLHUP) {
+ __remove_wait_queue(event->wqh, &event->wait);
+ spin_lock(&cgrp->event_list_lock);
+ list_del(&event->list);
+ spin_unlock(&cgrp->event_list_lock);
+ /*
+ * We are in atomic context, but cgroup_event_remove() may
+ * sleep, so we have to call it in workqueue.
+ */
+ schedule_work(&event->remove);
+ }
+
+ 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 *cgrp, struct cftype *cft,
+ const char *buffer)
+{
+ struct cgroup_event *event = NULL;
+ unsigned int efd, cfd;
+ struct file *efile = NULL;
+ struct file *cfile = NULL;
+ 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;
+ event->cgrp = cgrp;
+ 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 = eventfd_fget(efd);
+ if (IS_ERR(efile)) {
+ ret = PTR_ERR(efile);
+ goto fail;
+ }
+
+ event->eventfd = eventfd_ctx_fileget(efile);
+ if (IS_ERR(event->eventfd)) {
+ ret = PTR_ERR(event->eventfd);
+ goto fail;
+ }
+
+ cfile = fget(cfd);
+ if (!cfile) {
+ ret = -EBADF;
+ goto fail;
+ }
+
+ /* the process need read permission on control file */
+ ret = file_permission(cfile, MAY_READ);
+ if (ret < 0)
+ goto fail;
+
+ event->cft = __file_cft(cfile);
+ if (IS_ERR(event->cft)) {
+ ret = PTR_ERR(event->cft);
+ goto fail;
+ }
+
+ if (!event->cft->register_event || !event->cft->unregister_event) {
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ ret = event->cft->register_event(cgrp, event->cft,
+ event->eventfd, buffer);
+ if (ret)
+ goto fail;
+
+ if (efile->f_op->poll(efile, &event->pt) & POLLHUP) {
+ event->cft->unregister_event(cgrp, event->cft, event->eventfd);
+ ret = 0;
+ goto fail;
+ }
+
+ /*
+ * Events should be removed after rmdir of cgroup directory, but before
+ * destroying subsystem state objects. Let's take reference to cgroup
+ * directory dentry to do that.
+ */
+ dget(cgrp->dentry);
+
+ spin_lock(&cgrp->event_list_lock);
+ list_add(&event->list, &cgrp->event_list);
+ spin_unlock(&cgrp->event_list_lock);
+
+ fput(cfile);
+ fput(efile);
+
+ return 0;
+
+fail:
+ if (cfile)
+ fput(cfile);
+
+ if (event && event->eventfd && !IS_ERR(event->eventfd))
+ eventfd_ctx_put(event->eventfd);
+
+ if (!IS_ERR_OR_NULL(efile))
+ fput(efile);
+
+ kfree(event);
+
+ return ret;
+}
+
+static u64 cgroup_clone_children_read(struct cgroup *cgrp,
+ struct cftype *cft)
+{
+ return clone_children(cgrp);
+}
+
+static int cgroup_clone_children_write(struct cgroup *cgrp,
+ struct cftype *cft,
+ u64 val)
+{
+ if (val)
+ set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+ else
+ clear_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+ return 0;
+}
+
+/*
* for the common functions, 'private' gives the type of file
*/
/* for hysterical raisins, we can't put this on the older files */
.read_u64 = cgroup_read_notify_on_release,
.write_u64 = cgroup_write_notify_on_release,
},
+ {
+ .name = CGROUP_FILE_GENERIC_PREFIX "event_control",
+ .write_string = cgroup_write_event_control,
+ .mode = S_IWUGO,
+ },
+ {
+ .name = "cgroup.clone_children",
+ .read_u64 = cgroup_clone_children_read,
+ .write_u64 = cgroup_clone_children_write,
+ },
};
static struct cftype cft_release_agent = {
if (notify_on_release(parent))
set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
+ if (clone_children(parent))
+ set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+
for_each_subsys(root, ss) {
struct cgroup_subsys_state *css = ss->create(ss, cgrp);
goto err_destroy;
}
/* At error, ->destroy() callback has to free assigned ID. */
+ if (clone_children(parent) && ss->post_clone)
+ ss->post_clone(ss, cgrp);
}
cgroup_lock_hierarchy(root);
struct dentry *d;
struct cgroup *parent;
DEFINE_WAIT(wait);
+ struct cgroup_event *event, *tmp;
int ret;
/* the vfs holds both inode->i_mutex already */
spin_lock(&release_list_lock);
set_bit(CGRP_REMOVED, &cgrp->flags);
if (!list_empty(&cgrp->release_list))
- list_del(&cgrp->release_list);
+ list_del_init(&cgrp->release_list);
spin_unlock(&release_list_lock);
cgroup_lock_hierarchy(cgrp->root);
/* delete this cgroup from parent->children */
- list_del(&cgrp->sibling);
+ list_del_init(&cgrp->sibling);
cgroup_unlock_hierarchy(cgrp->root);
- spin_lock(&cgrp->dentry->d_lock);
d = dget(cgrp->dentry);
- spin_unlock(&d->d_lock);
cgroup_d_remove_dir(d);
dput(d);
set_bit(CGRP_RELEASABLE, &parent->flags);
check_for_release(parent);
+ /*
+ * Unregister events and notify userspace.
+ * Notify userspace about cgroup removing only after rmdir of cgroup
+ * directory to avoid race between userspace and kernelspace
+ */
+ spin_lock(&cgrp->event_list_lock);
+ list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
+ list_del(&event->list);
+ remove_wait_queue(event->wqh, &event->wait);
+ eventfd_signal(event->eventfd, 1);
+ schedule_work(&event->remove);
+ }
+ spin_unlock(&cgrp->event_list_lock);
+
mutex_unlock(&cgroup_mutex);
return 0;
}
* @ss: the subsystem to load
*
* This function should be called in a modular subsystem's initcall. If the
- * subsytem is built as a module, it will be assigned a new subsys_id and set
+ * 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.
*/
lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
ss->active = 1;
- /*
- * pin the subsystem's module so it doesn't go away. this shouldn't
- * fail, since the module's initcall calls us.
- * TODO: with module unloading, move this elsewhere
- */
- BUG_ON(!try_module_get(ss->module));
-
/* success! */
mutex_unlock(&cgroup_mutex);
return 0;
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 cg_cgroup_link *link;
+ struct hlist_head *hhead;
+
+ BUG_ON(ss->module == NULL);
+
+ /*
+ * we shouldn't be called if the subsystem is in use, and the use of
+ * try_module_get in parse_cgroupfs_options should ensure that it
+ * doesn't start being used while we're killing it off.
+ */
+ BUG_ON(ss->root != &rootnode);
+
+ mutex_lock(&cgroup_mutex);
+ /* deassign the subsys_id */
+ BUG_ON(ss->subsys_id < CGROUP_BUILTIN_SUBSYS_COUNT);
+ subsys[ss->subsys_id] = NULL;
+
+ /* remove subsystem from rootnode's list of subsystems */
+ list_del_init(&ss->sibling);
+
+ /*
+ * disentangle the css from all css_sets attached to the dummytop. as
+ * in loading, we need to pay our respects to the hashtable gods.
+ */
+ write_lock(&css_set_lock);
+ list_for_each_entry(link, &dummytop->css_sets, cgrp_link_list) {
+ struct css_set *cg = link->cg;
+
+ hlist_del(&cg->hlist);
+ BUG_ON(!cg->subsys[ss->subsys_id]);
+ cg->subsys[ss->subsys_id] = NULL;
+ hhead = css_set_hash(cg->subsys);
+ hlist_add_head(&cg->hlist, hhead);
+ }
+ write_unlock(&css_set_lock);
+
+ /*
+ * remove subsystem's css from the dummytop and free it - need to free
+ * before marking as null because ss->destroy needs the cgrp->subsys
+ * pointer to find their state. note that this also takes care of
+ * freeing the css_id.
+ */
+ ss->destroy(ss, dummytop);
+ dummytop->subsys[ss->subsys_id] = NULL;
+
+ mutex_unlock(&cgroup_mutex);
+}
+EXPORT_SYMBOL_GPL(cgroup_unload_subsys);
+
+/**
* cgroup_init_early - cgroup initialization at system boot
*
* Initialize cgroups at system boot, and initialize any
hhead = css_set_hash(init_css_set.subsys);
hlist_add_head(&init_css_set.hlist, hhead);
BUG_ON(!init_root_id(&rootnode));
+
+ cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
+ if (!cgroup_kobj) {
+ err = -ENOMEM;
+ goto out;
+ }
+
err = register_filesystem(&cgroup_fs_type);
- if (err < 0)
+ if (err < 0) {
+ kobject_put(cgroup_kobj);
goto out;
+ }
proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations);
if (!list_empty(&tsk->cg_list)) {
write_lock(&css_set_lock);
if (!list_empty(&tsk->cg_list))
- list_del(&tsk->cg_list);
+ list_del_init(&tsk->cg_list);
write_unlock(&css_set_lock);
}
rcu_read_unlock();
WARN_ON_ONCE(val < 1);
}
+EXPORT_SYMBOL_GPL(__css_put);
/*
* Notify userspace when a cgroup is released, by running the
*/
unsigned short css_id(struct cgroup_subsys_state *css)
{
- struct css_id *cssid = rcu_dereference(css->id);
+ struct css_id *cssid;
+
+ /*
+ * This css_id() can return correct value when somone has refcnt
+ * on this or this is under rcu_read_lock(). Once css->id is allocated,
+ * it's unchanged until freed.
+ */
+ cssid = rcu_dereference_check(css->id,
+ rcu_read_lock_held() || atomic_read(&css->refcnt));
if (cssid)
return cssid->id;
return 0;
}
+EXPORT_SYMBOL_GPL(css_id);
unsigned short css_depth(struct cgroup_subsys_state *css)
{
- struct css_id *cssid = rcu_dereference(css->id);
+ struct css_id *cssid;
+
+ cssid = rcu_dereference_check(css->id,
+ rcu_read_lock_held() || atomic_read(&css->refcnt));
if (cssid)
return cssid->depth;
return 0;
}
+EXPORT_SYMBOL_GPL(css_depth);
+
+/**
+ * css_is_ancestor - test "root" css is an ancestor of "child"
+ * @child: the css to be tested.
+ * @root: the css supporsed to be an ancestor of the child.
+ *
+ * Returns true if "root" is an ancestor of "child" in its hierarchy. Because
+ * this function reads css->id, this use rcu_dereference() and rcu_read_lock().
+ * But, considering usual usage, the csses should be valid objects after test.
+ * Assuming that the caller will do some action to the child if this returns
+ * returns true, the caller must take "child";s reference count.
+ * If "child" is valid object and this returns true, "root" is valid, too.
+ */
bool css_is_ancestor(struct cgroup_subsys_state *child,
const struct cgroup_subsys_state *root)
{
- struct css_id *child_id = rcu_dereference(child->id);
- struct css_id *root_id = rcu_dereference(root->id);
+ struct css_id *child_id;
+ struct css_id *root_id;
+ bool ret = true;
- if (!child_id || !root_id || (child_id->depth < root_id->depth))
- return false;
- return child_id->stack[root_id->depth] == root_id->id;
+ rcu_read_lock();
+ child_id = rcu_dereference(child->id);
+ root_id = rcu_dereference(root->id);
+ if (!child_id
+ || !root_id
+ || (child_id->depth < root_id->depth)
+ || (child_id->stack[root_id->depth] != root_id->id))
+ ret = false;
+ rcu_read_unlock();
+ return ret;
}
static void __free_css_id_cb(struct rcu_head *head)
spin_unlock(&ss->id_lock);
call_rcu(&id->rcu_head, __free_css_id_cb);
}
+EXPORT_SYMBOL_GPL(free_css_id);
/*
* This is called by init or create(). Then, calls to this function are
{
int subsys_id, i, depth = 0;
struct cgroup_subsys_state *parent_css, *child_css;
- struct css_id *child_id, *parent_id = NULL;
+ struct css_id *child_id, *parent_id;
subsys_id = ss->subsys_id;
parent_css = parent->subsys[subsys_id];
child_css = child->subsys[subsys_id];
- depth = css_depth(parent_css) + 1;
parent_id = parent_css->id;
+ depth = parent_id->depth + 1;
child_id = get_new_cssid(ss, depth);
if (IS_ERR(child_id))
return rcu_dereference(cssid->css);
}
+EXPORT_SYMBOL_GPL(css_lookup);
/**
* css_get_next - lookup next cgroup under specified hierarchy.