Newer
Older
/*
* 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);
/*
* @cgrp might already have been destroyed while we're trying to
* grab the mutexes.
*/
if (!cgroup_is_dead(cgrp))
ret = cgroup_destroy_locked(cgrp);
kernfs_unbreak_active_protection(kn);
cgroup_put(cgrp);
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_mutex);
/* Create the top cgroup state for this subsystem */
ss->root = &cgroup_dummy_root;
css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss));
/* We don't handle early failures gracefully */
BUG_ON(IS_ERR(css));
init_css(css, ss, cgroup_dummy_top);
/* Update the init_css_set to contain a subsys
* 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->id] = css;
need_forkexit_callback |= ss->fork || ss->exit;
/* At system boot, before all subsystems have been
* registered, no tasks have been forked, so we don't
* need to invoke fork callbacks here. */
BUG_ON(!list_empty(&init_task.tasks));
BUG_ON(online_css(css));
mutex_unlock(&cgroup_mutex);
* cgroup_init_early - cgroup initialization at system boot
*
* Initialize cgroups at system boot, and initialize any
* subsystems that request early init.
*/
int __init cgroup_init_early(void)
{
atomic_set(&init_css_set.refcount, 1);
INIT_LIST_HEAD(&init_css_set.cgrp_links);
INIT_LIST_HEAD(&init_css_set.tasks);
INIT_HLIST_NODE(&init_css_set.hlist);
css_set_count = 1;
init_cgroup_root(&cgroup_dummy_root);
cgroup_root_count = 1;
RCU_INIT_POINTER(init_task.cgroups, &init_css_set);
init_cgrp_cset_link.cset = &init_css_set;
init_cgrp_cset_link.cgrp = cgroup_dummy_top;
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);
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,
WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN,
"cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]);
ss->name = cgroup_subsys_name[i];
if (ss->early_init)
cgroup_init_subsys(ss);
}
return 0;
}
/**
* cgroup_init - cgroup initialization
*
* Register cgroup filesystem and /proc file, and initialize
* any subsystems that didn't request early init.
*/
int __init cgroup_init(void)
{
BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
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 */
/* Add init_css_set to the hash table */
key = css_set_hash(init_css_set.subsys);
hash_add(css_set_table, &init_css_set.hlist, key);
BUG_ON(cgroup_init_root_id(&cgroup_dummy_root, 0, 1));
err = idr_alloc(&cgroup_dummy_root.cgroup_idr, cgroup_dummy_top,
0, 1, GFP_KERNEL);
BUG_ON(err < 0);
cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
err = register_filesystem(&cgroup_fs_type);
if (err < 0) {
kobject_put(cgroup_kobj);
proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations);
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.
*
* 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_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);
/*
* proc_cgroup_show()
* - Print task's cgroup paths into seq_file, one line for each hierarchy
* - Used for /proc/<pid>/cgroup.
* - No need to task_lock(tsk) on this tsk->cgroup reference, as it
* doesn't really matter if tsk->cgroup changes after we read it,
* and we take cgroup_mutex, keeping cgroup_attach_task() from changing it
* anyway. No need to check that tsk->cgroup != NULL, thanks to
* the_top_cgroup_hack in cgroup_exit(), which sets an exiting tasks
* cgroup to top_cgroup.
*/
/* TODO: Use a proper seq_file iterator */
int proc_cgroup_show(struct seq_file *m, void *v)
{
struct pid *pid;
struct task_struct *tsk;
int retval;
struct cgroupfs_root *root;
retval = -ENOMEM;
if (!buf)
goto out;
retval = -ESRCH;
pid = m->private;
tsk = get_pid_task(pid, PIDTYPE_PID);
if (!tsk)
goto out_free;
retval = 0;
mutex_lock(&cgroup_mutex);
for_each_active_root(root) {
struct cgroup *cgrp;
seq_printf(m, "%d:", root->hierarchy_id);
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);
cgrp = task_cgroup_from_root(tsk, root);
path = cgroup_path(cgrp, buf, PATH_MAX);
if (!path) {
retval = -ENAMETOOLONG;
seq_putc(m, '\n');
}
out_unlock:
mutex_unlock(&cgroup_mutex);
put_task_struct(tsk);
out_free:
kfree(buf);
out:
return retval;
}
/* Display information about each subsystem and each hierarchy */
static int proc_cgroupstats_show(struct seq_file *m, void *v)
{
seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
/*
* ideally we don't want subsystems moving around while we do this.
* cgroup_mutex is also necessary to guarantee an atomic snapshot of
* subsys/hierarchy state.
*/
seq_printf(m, "%s\t%d\t%d\t%d\n",
ss->name, ss->root->hierarchy_id,
ss->root->number_of_cgroups, !ss->disabled);
mutex_unlock(&cgroup_mutex);
return 0;
}
static int cgroupstats_open(struct inode *inode, struct file *file)
{
return single_open(file, proc_cgroupstats_show, NULL);
static const struct file_operations proc_cgroupstats_operations = {
.open = cgroupstats_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
/**
* cgroup_fork - attach newly forked task to its parents cgroup.
* @child: pointer to task_struct of forking parent process.
*
* Description: A task inherits its parent's cgroup at fork().
*
* A pointer to the shared css_set was automatically copied in
* fork.c by dup_task_struct(). However, we ignore that copy, since
* it was not made under the protection of RCU or cgroup_mutex, so
* might no longer be a valid cgroup pointer. cgroup_attach_task() might
* have already changed current->cgroups, allowing the previously
* referenced cgroup group to be removed and freed.
*
* At the point that cgroup_fork() is called, 'current' is the parent
* task, and the passed argument 'child' points to the child task.
*/
void cgroup_fork(struct task_struct *child)
{
task_lock(current);
get_css_set(task_css_set(current));
child->cgroups = current->cgroups;
task_unlock(current);
INIT_LIST_HEAD(&child->cg_list);
* cgroup_post_fork - called on a new task after adding it to the task list
* @child: the task in question
*
Tejun Heo
committed
* Adds the task to the list running through its css_set if necessary and
* call the subsystem fork() callbacks. Has to be after the task is
* visible on the task list in case we race with the first call to
* cgroup_task_iter_start() - to guarantee that the new task ends up on its
Tejun Heo
committed
* list.
void cgroup_post_fork(struct task_struct *child)
{
Tejun Heo
committed
int i;
Frederic Weisbecker
committed
/*
* use_task_css_set_links is set to 1 before we walk the tasklist
* under the tasklist_lock and we read it here after we added the child
* to the tasklist under the tasklist_lock as well. If the child wasn't
* yet in the tasklist when we walked through it from
* cgroup_enable_task_cg_lists(), then use_task_css_set_links value
* should be visible now due to the paired locking and barriers implied
* by LOCK/UNLOCK: it is written before the tasklist_lock unlock
* in cgroup_enable_task_cg_lists() and read here after the tasklist_lock
* lock on fork.
*/
if (use_task_css_set_links) {
write_lock(&css_set_lock);
task_lock(child);
if (list_empty(&child->cg_list))
list_add(&child->cg_list, &task_css_set(child)->tasks);
task_unlock(child);
write_unlock(&css_set_lock);
}
Tejun Heo
committed
/*
* Call ss->fork(). This must happen after @child is linked on
* css_set; otherwise, @child might change state between ->fork()
* and addition to css_set.
*/
if (need_forkexit_callback) {
Tejun Heo
committed
if (ss->fork)
ss->fork(child);
}
Tejun Heo
committed
/**
* cgroup_exit - detach cgroup from exiting task
* @tsk: pointer to task_struct of exiting process
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
*
* Description: Detach cgroup from @tsk and release it.
*
* Note that cgroups marked notify_on_release force every task in
* them to take the global cgroup_mutex mutex when exiting.
* This could impact scaling on very large systems. Be reluctant to
* use notify_on_release cgroups where very high task exit scaling
* is required on large systems.
*
* the_top_cgroup_hack:
*
* Set the exiting tasks cgroup to the root cgroup (top_cgroup).
*
* We call cgroup_exit() while the task is still competent to
* handle notify_on_release(), then leave the task attached to the
* root cgroup in each hierarchy for the remainder of its exit.
*
* To do this properly, we would increment the reference count on
* top_cgroup, and near the very end of the kernel/exit.c do_exit()
* code we would add a second cgroup function call, to drop that
* reference. This would just create an unnecessary hot spot on
* the top_cgroup reference count, to no avail.
*
* Normally, holding a reference to a cgroup without bumping its
* count is unsafe. The cgroup could go away, or someone could
* attach us to a different cgroup, decrementing the count on
* the first cgroup that we never incremented. But in this case,
* top_cgroup isn't going away, and either task has PF_EXITING set,
* which wards off any cgroup_attach_task() attempts, or task is a failed
* fork, never visible to cgroup_attach_task.
*/
void cgroup_exit(struct task_struct *tsk, int run_callbacks)
{
struct css_set *cset;
/*
* Unlink from the css_set task list if necessary.
* Optimistically check cg_list before taking
* css_set_lock
*/
if (!list_empty(&tsk->cg_list)) {
write_lock(&css_set_lock);
if (!list_empty(&tsk->cg_list))
list_del_init(&tsk->cg_list);
write_unlock(&css_set_lock);
}
/* Reassign the task to the init_css_set. */
task_lock(tsk);
cset = task_css_set(tsk);
RCU_INIT_POINTER(tsk->cgroups, &init_css_set);
if (run_callbacks && need_forkexit_callback) {
/* see cgroup_post_fork() for details */
for_each_subsys(ss, i) {
struct cgroup_subsys_state *old_css = cset->subsys[i];
struct cgroup_subsys_state *css = task_css(tsk, i);
ss->exit(css, old_css, tsk);
put_css_set_taskexit(cset);
static void check_for_release(struct cgroup *cgrp)
if (cgroup_is_releasable(cgrp) &&
list_empty(&cgrp->cset_links) && list_empty(&cgrp->children)) {
/*
* Control Group is currently removeable. If it's not
* already queued for a userspace notification, queue
int need_schedule_work = 0;
raw_spin_lock(&release_list_lock);
list_empty(&cgrp->release_list)) {
list_add(&cgrp->release_list, &release_list);
need_schedule_work = 1;
}
raw_spin_unlock(&release_list_lock);
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
if (need_schedule_work)
schedule_work(&release_agent_work);
}
}
/*
* Notify userspace when a cgroup is released, by running the
* configured release agent with the name of the cgroup (path
* relative to the root of cgroup file system) as the argument.
*
* Most likely, this user command will try to rmdir this cgroup.
*
* This races with the possibility that some other task will be
* attached to this cgroup before it is removed, or that some other
* user task will 'mkdir' a child cgroup of this cgroup. That's ok.
* The presumed 'rmdir' will fail quietly if this cgroup is no longer
* unused, and this cgroup will be reprieved from its death sentence,
* to continue to serve a useful existence. Next time it's released,
* we will get notified again, if it still has 'notify_on_release' set.
*
* The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which
* means only wait until the task is successfully execve()'d. The
* separate release agent task is forked by call_usermodehelper(),
* then control in this thread returns here, without waiting for the
* release agent task. We don't bother to wait because the caller of
* this routine has no use for the exit status of the release agent
* task, so no sense holding our caller up for that.
*/
static void cgroup_release_agent(struct work_struct *work)
{
BUG_ON(work != &release_agent_work);
mutex_lock(&cgroup_mutex);
raw_spin_lock(&release_list_lock);
while (!list_empty(&release_list)) {
char *argv[3], *envp[3];
int i;
struct cgroup *cgrp = list_entry(release_list.next,
struct cgroup,
release_list);
list_del_init(&cgrp->release_list);
raw_spin_unlock(&release_list_lock);
if (!pathbuf)
goto continue_free;
path = cgroup_path(cgrp, pathbuf, PATH_MAX);
if (!path)
goto continue_free;
agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
if (!agentbuf)
goto continue_free;
i = 0;
argv[i++] = agentbuf;
argv[i] = NULL;
i = 0;
/* minimal command environment */
envp[i++] = "HOME=/";
envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
envp[i] = NULL;
/* Drop the lock while we invoke the usermode helper,
* since the exec could involve hitting disk and hence
* be a slow process */
mutex_unlock(&cgroup_mutex);
call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
mutex_lock(&cgroup_mutex);
continue_free:
kfree(pathbuf);
kfree(agentbuf);
raw_spin_lock(&release_list_lock);
raw_spin_unlock(&release_list_lock);
mutex_unlock(&cgroup_mutex);
}
static int __init cgroup_disable(char *str)
{
char *token;
while ((token = strsep(&str, ",")) != NULL) {
if (!*token)
continue;
if (!strcmp(token, ss->name)) {
ss->disabled = 1;
printk(KERN_INFO "Disabling %s control group"
" subsystem\n", ss->name);
break;
}
}
}
return 1;
}
__setup("cgroup_disable=", cgroup_disable);
/**
* css_tryget_from_dir - get corresponding css from the dentry of a cgroup dir
* @dentry: directory dentry of interest
* @ss: subsystem of interest
* 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_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;
/* is @dentry a cgroup dir? */
if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
kernfs_type(kn) != KERNFS_DIR)
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;
/**
* css_from_id - lookup css by id
* @id: the cgroup id
* @ss: cgroup subsys to be looked into
*
* Returns the css if there's valid one with @id, otherwise returns NULL.
* Should be called under rcu_read_lock().
*/
struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
{
struct cgroup *cgrp;
cgrp = idr_find(&ss->root->cgroup_idr, id);
if (cgrp)
return cgroup_css(cgrp, ss);
#ifdef CONFIG_CGROUP_DEBUG
static struct cgroup_subsys_state *
debug_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
if (!css)
return ERR_PTR(-ENOMEM);
return css;
}
static void debug_css_free(struct cgroup_subsys_state *css)
{
kfree(css);
}
static u64 debug_taskcount_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return cgroup_task_count(css->cgroup);
}
static u64 current_css_set_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return (u64)(unsigned long)current->cgroups;
}
static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css,
{
u64 count;
rcu_read_lock();
count = atomic_read(&task_css_set(current)->refcount);
rcu_read_unlock();
return count;
}
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;
if (c != cgroup_dummy_top) {
cgroup_name(c, name_buf, NAME_MAX + 1);
name = name_buf;
}
seq_printf(seq, "Root %d group %s\n",
c->root->hierarchy_id, name);
}
rcu_read_unlock();
read_unlock(&css_set_lock);
return 0;
}
#define MAX_TASKS_SHOWN_PER_CSS 25
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);
list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
struct css_set *cset = link->cset;
struct task_struct *task;
int count = 0;
seq_printf(seq, "css_set %p\n", cset);
list_for_each_entry(task, &cset->tasks, cg_list) {
if (count++ > MAX_TASKS_SHOWN_PER_CSS) {
seq_puts(seq, " ...\n");
break;
} else {
seq_printf(seq, " task %d\n",
task_pid_vnr(task));
}
}
}
read_unlock(&css_set_lock);
return 0;
}
static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft)
{
return test_bit(CGRP_RELEASABLE, &css->cgroup->flags);
}
static struct cftype debug_files[] = {
{
.name = "taskcount",
.read_u64 = debug_taskcount_read,
},
{
.name = "current_css_set",
.read_u64 = current_css_set_read,
},
{
.name = "current_css_set_refcount",
.read_u64 = current_css_set_refcount_read,
},
{
.name = "current_css_set_cg_links",
.seq_show = current_css_set_cg_links_read,
},
{
.name = "cgroup_css_links",
.seq_show = cgroup_css_links_read,
},
{
.name = "releasable",
.read_u64 = releasable_read,
},
{ } /* terminate */
};
struct cgroup_subsys debug_cgrp_subsys = {
Tejun Heo
committed
.css_alloc = debug_css_alloc,
.css_free = debug_css_free,
.base_cftypes = debug_files,
};
#endif /* CONFIG_CGROUP_DEBUG */