#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include "cgroup-internal.h"
#include <linux/bpf-cgroup.h>
#include <linux/cred.h>
#include <linux/errno.h>
#include <linux/init_task.h>
#include <linux/kernel.h>
#include <linux/magic.h>
#include <linux/mutex.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/sched/task.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/percpu-rwsem.h>
#include <linux/string.h>
#include <linux/hashtable.h>
#include <linux/idr.h>
#include <linux/kthread.h>
#include <linux/atomic.h>
#include <linux/cpuset.h>
#include <linux/proc_ns.h>
#include <linux/nsproxy.h>
#include <linux/file.h>
#include <linux/fs_parser.h>
#include <linux/sched/cputime.h>
#include <linux/sched/deadline.h>
#include <linux/psi.h>
#include <net/sock.h>
#define CREATE_TRACE_POINTS
#include <trace/events/cgroup.h>
#define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \
MAX_CFTYPE_NAME + 2)
#define CGROUP_FILE_NOTIFY_MIN_INTV DIV_ROUND_UP(HZ, 100)
#define CGROUP_HAS_SUBSYS_CONFIG (CGROUP_SUBSYS_COUNT > 0)
DEFINE_MUTEX(cgroup_mutex);
DEFINE_SPINLOCK(css_set_lock);
#ifdef CONFIG_PROVE_RCU
EXPORT_SYMBOL_GPL(cgroup_mutex);
EXPORT_SYMBOL_GPL(css_set_lock);
#endif
DEFINE_SPINLOCK(trace_cgroup_path_lock);
char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
static bool cgroup_debug __read_mostly;
static DEFINE_SPINLOCK(cgroup_idr_lock);
static DEFINE_SPINLOCK(cgroup_file_kn_lock);
DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem);
#define cgroup_assert_mutex_or_rcu_locked() \
RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \
!lockdep_is_held(&cgroup_mutex), \
"cgroup_mutex or RCU read lock required");
static struct workqueue_struct *cgroup_destroy_wq;
#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,
struct cgroup_subsys *cgroup_subsys[] = {
#include <linux/cgroup_subsys.h>
};
#undef SUBSYS
#define SUBSYS(_x) [_x ## _cgrp_id] = #_x,
static const char *cgroup_subsys_name[] = {
#include <linux/cgroup_subsys.h>
};
#undef SUBSYS
#define SUBSYS(_x) \
DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_enabled_key); \
DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_on_dfl_key); \
EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_enabled_key); \
EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_on_dfl_key);
#include <linux/cgroup_subsys.h>
#undef SUBSYS
#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_enabled_key,
static struct static_key_true *cgroup_subsys_enabled_key[] = {
#include <linux/cgroup_subsys.h>
};
#undef SUBSYS
#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_on_dfl_key,
static struct static_key_true *cgroup_subsys_on_dfl_key[] = {
#include <linux/cgroup_subsys.h>
};
#undef SUBSYS
static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu);
struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu };
EXPORT_SYMBOL_GPL(cgrp_dfl_root);
static bool cgrp_dfl_visible;
static u16 cgrp_dfl_inhibit_ss_mask;
static u16 cgrp_dfl_implicit_ss_mask;
static u16 cgrp_dfl_threaded_ss_mask;
LIST_HEAD(cgroup_roots);
static int cgroup_root_count;
static DEFINE_IDR(cgroup_hierarchy_idr);
static u64 css_serial_nr_next = 1;
static u16 have_fork_callback __read_mostly;
static u16 have_exit_callback __read_mostly;
static u16 have_release_callback __read_mostly;
static u16 have_canfork_callback __read_mostly;
struct cgroup_namespace init_cgroup_ns = {
.ns.count = REFCOUNT_INIT(2),
.user_ns = &init_user_ns,
.ns.ops = &cgroupns_operations,
.ns.inum = PROC_CGROUP_INIT_INO,
.root_cset = &init_css_set,
};
static struct file_system_type cgroup2_fs_type;
static struct cftype cgroup_base_files[];
static struct cftype cgroup_psi_files[];
enum cgroup_opt_features {
#ifdef CONFIG_PSI
OPT_FEATURE_PRESSURE,
#endif
OPT_FEATURE_COUNT
};
static const char *cgroup_opt_feature_names[OPT_FEATURE_COUNT] = {
#ifdef CONFIG_PSI
"pressure",
#endif
};
static u16 cgroup_feature_disable_mask __read_mostly;
static int cgroup_apply_control(struct cgroup *cgrp);
static void cgroup_finalize_control(struct cgroup *cgrp, int ret);
static void css_task_iter_skip(struct css_task_iter *it,
struct task_struct *task);
static int cgroup_destroy_locked(struct cgroup *cgrp);
static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
struct cgroup_subsys *ss);
static void css_release(struct percpu_ref *ref);
static void kill_css(struct cgroup_subsys_state *css);
static int cgroup_addrm_files(struct cgroup_subsys_state *css,
struct cgroup *cgrp, struct cftype cfts[],
bool is_add);
#ifdef CONFIG_DEBUG_CGROUP_REF
#define CGROUP_REF_FN_ATTRS noinline
#define CGROUP_REF_EXPORT(fn) EXPORT_SYMBOL_GPL(fn);
#include <linux/cgroup_refcnt.h>
#endif
bool cgroup_ssid_enabled(int ssid)
{
if (!CGROUP_HAS_SUBSYS_CONFIG)
return false;
return static_key_enabled(cgroup_subsys_enabled_key[ssid]);
}
bool cgroup_on_dfl(const struct cgroup *cgrp)
{
return cgrp->root == &cgrp_dfl_root;
}
static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end,
gfp_t gfp_mask)
{
int ret;
idr_preload(gfp_mask);
spin_lock_bh(&cgroup_idr_lock);
ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_DIRECT_RECLAIM);
spin_unlock_bh(&cgroup_idr_lock);
idr_preload_end();
return ret;
}
static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id)
{
void *ret;
spin_lock_bh(&cgroup_idr_lock);
ret = idr_replace(idr, ptr, id);
spin_unlock_bh(&cgroup_idr_lock);
return ret;
}
static void cgroup_idr_remove(struct idr *idr, int id)
{
spin_lock_bh(&cgroup_idr_lock);
idr_remove(idr, id);
spin_unlock_bh(&cgroup_idr_lock);
}
static bool cgroup_has_tasks(struct cgroup *cgrp)
{
return cgrp->nr_populated_csets;
}
static bool cgroup_is_threaded(struct cgroup *cgrp)
{
return cgrp->dom_cgrp != cgrp;
}
static bool cgroup_is_mixable(struct cgroup *cgrp)
{
return !cgroup_parent(cgrp);
}
static bool cgroup_can_be_thread_root(struct cgroup *cgrp)
{
if (cgroup_is_mixable(cgrp))
return true;
if (cgroup_is_threaded(cgrp))
return false;
if (cgrp->nr_populated_domain_children)
return false;
if (cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask)
return false;
return true;
}
static bool cgroup_is_thread_root(struct cgroup *cgrp)
{
if (cgroup_is_threaded(cgrp))
return false;
if (cgrp->nr_threaded_children)
return true;
if (cgroup_has_tasks(cgrp) &&
(cgrp->subtree_control & cgrp_dfl_threaded_ss_mask))
return true;
return false;
}
static bool cgroup_is_valid_domain(struct cgroup *cgrp)
{
if (cgroup_is_threaded(cgrp))
return false;
while ((cgrp = cgroup_parent(cgrp))) {
if (!cgroup_is_mixable(cgrp) && cgroup_is_thread_root(cgrp))
return false;
if (cgroup_is_threaded(cgrp))
return false;
}
return true;
}
static u16 cgroup_control(struct cgroup *cgrp)
{
struct cgroup *parent = cgroup_parent(cgrp);
u16 root_ss_mask = cgrp->root->subsys_mask;
if (parent) {
u16 ss_mask = parent->subtree_control;
if (cgroup_is_threaded(cgrp))
ss_mask &= cgrp_dfl_threaded_ss_mask;
return ss_mask;
}
if (cgroup_on_dfl(cgrp))
root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask |
cgrp_dfl_implicit_ss_mask);
return root_ss_mask;
}
static u16 cgroup_ss_mask(struct cgroup *cgrp)
{
struct cgroup *parent = cgroup_parent(cgrp);
if (parent) {
u16 ss_mask = parent->subtree_ss_mask;
if (cgroup_is_threaded(cgrp))
ss_mask &= cgrp_dfl_threaded_ss_mask;
return ss_mask;
}
return cgrp->root->subsys_mask;
}
static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
struct cgroup_subsys *ss)
{
if (CGROUP_HAS_SUBSYS_CONFIG && ss)
return rcu_dereference_check(cgrp->subsys[ss->id],
lockdep_is_held(&cgroup_mutex));
else
return &cgrp->self;
}
static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp,
struct cgroup_subsys *ss)
{
lockdep_assert_held(&cgroup_mutex);
if (!ss)
return &cgrp->self;
while (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) {
cgrp = cgroup_parent(cgrp);
if (!cgrp)
return NULL;
}
return cgroup_css(cgrp, ss);
}
struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
struct cgroup_subsys *ss)
{
struct cgroup_subsys_state *css;
if (!CGROUP_HAS_SUBSYS_CONFIG)
return NULL;
do {
css = cgroup_css(cgrp, ss);
if (css)
return css;
cgrp = cgroup_parent(cgrp);
} while (cgrp);
return init_css_set.subsys[ss->id];
}
struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp,
struct cgroup_subsys *ss)
{
struct cgroup_subsys_state *css;
if (!CGROUP_HAS_SUBSYS_CONFIG)
return NULL;
rcu_read_lock();
do {
css = cgroup_css(cgrp, ss);
if (css && css_tryget_online(css))
goto out_unlock;
cgrp = cgroup_parent(cgrp);
} while (cgrp);
css = init_css_set.subsys[ss->id];
css_get(css);
out_unlock:
rcu_read_unlock();
return css;
}
EXPORT_SYMBOL_GPL(cgroup_get_e_css);
static void cgroup_get_live(struct cgroup *cgrp)
{
WARN_ON_ONCE(cgroup_is_dead(cgrp));
cgroup_get(cgrp);
}
int __cgroup_task_count(const struct cgroup *cgrp)
{
int count = 0;
struct cgrp_cset_link *link;
lockdep_assert_held(&css_set_lock);
list_for_each_entry(link, &cgrp->cset_links, cset_link)
count += link->cset->nr_tasks;
return count;
}
int cgroup_task_count(const struct cgroup *cgrp)
{
int count;
spin_lock_irq(&css_set_lock);
count = __cgroup_task_count(cgrp);
spin_unlock_irq(&css_set_lock);
return count;
}
struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
{
struct cgroup *cgrp = of->kn->parent->priv;
struct cftype *cft = of_cft(of);
if (CGROUP_HAS_SUBSYS_CONFIG && cft->ss)
return rcu_dereference_raw(cgrp->subsys[cft->ss->id]);
else
return &cgrp->self;
}
EXPORT_SYMBOL_GPL(of_css);
#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_mutex)))) { } \
else
#define do_each_subsys_mask(ss, ssid, ss_mask) do { \
unsigned long __ss_mask = (ss_mask); \
if (!CGROUP_HAS_SUBSYS_CONFIG) { \
(ssid) = 0; \
break; \
} \
for_each_set_bit(ssid, &__ss_mask, CGROUP_SUBSYS_COUNT) { \
(ss) = cgroup_subsys[ssid]; \
{
#define while_each_subsys_mask() \
} \
} \
} while (false)
#define cgroup_for_each_live_child(child, cgrp) \
list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \
if (({ lockdep_assert_held(&cgroup_mutex); \
cgroup_is_dead(child); })) \
; \
else
#define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \
css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \
if (({ lockdep_assert_held(&cgroup_mutex); \
(dsct) = (d_css)->cgroup; \
cgroup_is_dead(dsct); })) \
; \
else
#define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) \
css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL)) \
if (({ lockdep_assert_held(&cgroup_mutex); \
(dsct) = (d_css)->cgroup; \
cgroup_is_dead(dsct); })) \
; \
else
struct css_set init_css_set = {
.refcount = REFCOUNT_INIT(1),
.dom_cset = &init_css_set,
.tasks = LIST_HEAD_INIT(init_css_set.tasks),
.mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks),
.dying_tasks = LIST_HEAD_INIT(init_css_set.dying_tasks),
.task_iters = LIST_HEAD_INIT(init_css_set.task_iters),
.threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets),
.cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links),
.mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node),
.mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node),
.mg_node = LIST_HEAD_INIT(init_css_set.mg_node),
.dfl_cgrp = &cgrp_dfl_root.cgrp,
};
static int css_set_count = 1;
static bool css_set_threaded(struct css_set *cset)
{
return cset->dom_cset != cset;
}
static bool css_set_populated(struct css_set *cset)
{
lockdep_assert_held(&css_set_lock);
return !list_empty(&cset->tasks) || !list_empty(&cset->mg_tasks);
}
static void cgroup_update_populated(struct cgroup *cgrp, bool populated)
{
struct cgroup *child = NULL;
int adj = populated ? 1 : -1;
lockdep_assert_held(&css_set_lock);
do {
bool was_populated = cgroup_is_populated(cgrp);
if (!child) {
cgrp->nr_populated_csets += adj;
} else {
if (cgroup_is_threaded(child))
cgrp->nr_populated_threaded_children += adj;
else
cgrp->nr_populated_domain_children += adj;
}
if (was_populated == cgroup_is_populated(cgrp))
break;
cgroup1_check_for_release(cgrp);
TRACE_CGROUP_PATH(notify_populated, cgrp,
cgroup_is_populated(cgrp));
cgroup_file_notify(&cgrp->events_file);
child = cgrp;
cgrp = cgroup_parent(cgrp);
} while (cgrp);
}
static void css_set_update_populated(struct css_set *cset, bool populated)
{
struct cgrp_cset_link *link;
lockdep_assert_held(&css_set_lock);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link)
cgroup_update_populated(link->cgrp, populated);
}
static void css_set_skip_task_iters(struct css_set *cset,
struct task_struct *task)
{
struct css_task_iter *it, *pos;
list_for_each_entry_safe(it, pos, &cset->task_iters, iters_node)
css_task_iter_skip(it, task);
}
static void css_set_move_task(struct task_struct *task,
struct css_set *from_cset, struct css_set *to_cset,
bool use_mg_tasks)
{
lockdep_assert_held(&css_set_lock);
if (to_cset && !css_set_populated(to_cset))
css_set_update_populated(to_cset, true);
if (from_cset) {
WARN_ON_ONCE(list_empty(&task->cg_list));
css_set_skip_task_iters(from_cset, task);
list_del_init(&task->cg_list);
if (!css_set_populated(from_cset))
css_set_update_populated(from_cset, false);
} else {
WARN_ON_ONCE(!list_empty(&task->cg_list));
}
if (to_cset) {
WARN_ON_ONCE(task->flags & PF_EXITING);
cgroup_move_task(task, to_cset);
list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks :
&to_cset->tasks);
}
}
#define CSS_SET_HASH_BITS 7
static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS);
static unsigned long css_set_hash(struct cgroup_subsys_state **css)
{
unsigned long key = 0UL;
struct cgroup_subsys *ss;
int i;
for_each_subsys(ss, i)
key += (unsigned long)css[i];
key = (key >> 16) ^ key;
return key;
}
void put_css_set_locked(struct css_set *cset)
{
struct cgrp_cset_link *link, *tmp_link;
struct cgroup_subsys *ss;
int ssid;
lockdep_assert_held(&css_set_lock);
if (!refcount_dec_and_test(&cset->refcount))
return;
WARN_ON_ONCE(!list_empty(&cset->threaded_csets));
for_each_subsys(ss, ssid) {
list_del(&cset->e_cset_node[ssid]);
css_put(cset->subsys[ssid]);
}
hash_del(&cset->hlist);
css_set_count--;
list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) {
list_del(&link->cset_link);
list_del(&link->cgrp_link);
if (cgroup_parent(link->cgrp))
cgroup_put(link->cgrp);
kfree(link);
}
if (css_set_threaded(cset)) {
list_del(&cset->threaded_csets_node);
put_css_set_locked(cset->dom_cset);
}
kfree_rcu(cset, rcu_head);
}
static bool compare_css_sets(struct css_set *cset,
struct css_set *old_cset,
struct cgroup *new_cgrp,
struct cgroup_subsys_state *template[])
{
struct cgroup *new_dfl_cgrp;
struct list_head *l1, *l2;
if (memcmp(template, cset->subsys, sizeof(cset->subsys)))
return false;
if (cgroup_on_dfl(new_cgrp))
new_dfl_cgrp = new_cgrp;
else
new_dfl_cgrp = old_cset->dfl_cgrp;
if (new_dfl_cgrp->dom_cgrp != cset->dom_cset->dfl_cgrp)
return false;
l1 = &cset->cgrp_links;
l2 = &old_cset->cgrp_links;
while (1) {
struct cgrp_cset_link *link1, *link2;
struct cgroup *cgrp1, *cgrp2;
l1 = l1->next;
l2 = l2->next;
if (l1 == &cset->cgrp_links) {
BUG_ON(l2 != &old_cset->cgrp_links);
break;
} else {
BUG_ON(l2 == &old_cset->cgrp_links);
}
link1 = list_entry(l1, struct cgrp_cset_link, cgrp_link);
link2 = list_entry(l2, struct cgrp_cset_link, cgrp_link);
cgrp1 = link1->cgrp;
cgrp2 = link2->cgrp;
BUG_ON(cgrp1->root != cgrp2->root);
if (cgrp1->root == new_cgrp->root) {
if (cgrp1 != new_cgrp)
return false;
} else {
if (cgrp1 != cgrp2)
return false;
}
}
return true;
}
static struct css_set *find_existing_css_set(struct css_set *old_cset,
struct cgroup *cgrp,
struct cgroup_subsys_state **template)
{
struct cgroup_root *root = cgrp->root;
struct cgroup_subsys *ss;
struct css_set *cset;
unsigned long key;
int i;
for_each_subsys(ss, i) {
if (root->subsys_mask & (1UL << i)) {
template[i] = cgroup_e_css_by_mask(cgrp, ss);
} else {
template[i] = old_cset->subsys[i];
}
}
key = css_set_hash(template);
hash_for_each_possible(css_set_table, cset, hlist, key) {
if (!compare_css_sets(cset, old_cset, cgrp, template))
continue;
return cset;
}
return NULL;
}
static void free_cgrp_cset_links(struct list_head *links_to_free)
{
struct cgrp_cset_link *link, *tmp_link;
list_for_each_entry_safe(link, tmp_link, links_to_free, cset_link) {
list_del(&link->cset_link);
kfree(link);
}
}
static int allocate_cgrp_cset_links(int count, struct list_head *tmp_links)
{
struct cgrp_cset_link *link;
int i;
INIT_LIST_HEAD(tmp_links);
for (i = 0; i < count; i++) {
link = kzalloc(sizeof(*link), GFP_KERNEL);
if (!link) {
free_cgrp_cset_links(tmp_links);
return -ENOMEM;
}
list_add(&link->cset_link, tmp_links);
}
return 0;
}
static void link_css_set(struct list_head *tmp_links, struct css_set *cset,
struct cgroup *cgrp)
{
struct cgrp_cset_link *link;
BUG_ON(list_empty(tmp_links));
if (cgroup_on_dfl(cgrp))
cset->dfl_cgrp = cgrp;
link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link);
link->cset = cset;
link->cgrp = cgrp;
list_move_tail(&link->cset_link, &cgrp->cset_links);
list_add_tail(&link->cgrp_link, &cset->cgrp_links);
if (cgroup_parent(cgrp))
cgroup_get_live(cgrp);
}
static struct css_set *find_css_set(struct css_set *old_cset,
struct cgroup *cgrp)
{
struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT] = { };
struct css_set *cset;
struct list_head tmp_links;
struct cgrp_cset_link *link;
struct cgroup_subsys *ss;
unsigned long key;
int ssid;
lockdep_assert_held(&cgroup_mutex);
spin_lock_irq(&css_set_lock);
cset = find_existing_css_set(old_cset, cgrp, template);
if (cset)
get_css_set(cset);
spin_unlock_irq(&css_set_lock);
if (cset)
return cset;
cset = kzalloc(sizeof(*cset), GFP_KERNEL);
if (!cset)
return NULL;
if (allocate_cgrp_cset_links(cgroup_root_count, &tmp_links) < 0) {
kfree(cset);
return NULL;
}
refcount_set(&cset->refcount, 1);
cset->dom_cset = cset;
INIT_LIST_HEAD(&cset->tasks);
INIT_LIST_HEAD(&cset->mg_tasks);
INIT_LIST_HEAD(&cset->dying_tasks);
INIT_LIST_HEAD(&cset->task_iters);
INIT_LIST_HEAD(&cset->threaded_csets);
INIT_HLIST_NODE(&cset->hlist);
INIT_LIST_HEAD(&cset->cgrp_links);
INIT_LIST_HEAD(&cset->mg_src_preload_node);
INIT_LIST_HEAD(&cset->mg_dst_preload_node);
INIT_LIST_HEAD(&cset->mg_node);
memcpy(cset->subsys, template, sizeof(cset->subsys));
spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
if (c->root == cgrp->root)
c = cgrp;
link_css_set(&tmp_links, cset, c);
}
BUG_ON(!list_empty(&tmp_links));
css_set_count++;
key = css_set_hash(cset->subsys);
hash_add(css_set_table, &cset->hlist, key);
for_each_subsys(ss, ssid) {
struct cgroup_subsys_state *css = cset->subsys[ssid];
list_add_tail(&cset->e_cset_node[ssid],
&css->cgroup->e_csets[ssid]);
css_get(css);
}
spin_unlock_irq(&css_set_lock);
if (cgroup_is_threaded(cset->dfl_cgrp)) {
struct css_set *dcset;
dcset = find_css_set(cset, cset->dfl_cgrp->dom_cgrp);
if (!dcset) {
put_css_set(cset);
return NULL;
}
spin_lock_irq(&css_set_lock);
cset->dom_cset = dcset;
list_add_tail(&cset->threaded_csets_node,
&dcset->threaded_csets);
spin_unlock_irq(&css_set_lock);
}
return cset;
}
struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
{
struct cgroup *root_cgrp = kernfs_root_to_node(kf_root)->priv;
return root_cgrp->root;
}
void cgroup_favor_dynmods(struct cgroup_root *root, bool favor)
{
bool favoring = root->flags & CGRP_ROOT_FAVOR_DYNMODS;
if (favor && !favoring) {
rcu_sync_enter(&cgroup_threadgroup_rwsem.rss);
root->flags |= CGRP_ROOT_FAVOR_DYNMODS;
} else if (!favor && favoring) {
rcu_sync_exit(&cgroup_threadgroup_rwsem.rss);
root->flags &= ~CGRP_ROOT_FAVOR_DYNMODS;
}
}
static int cgroup_init_root_id(struct cgroup_root *root)
{
int id;
lockdep_assert_held(&cgroup_mutex);
id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL);
if (id < 0)
return id;
root->hierarchy_id = id;
return 0;
}
static void cgroup_exit_root_id(struct cgroup_root *root)
{
lockdep_assert_held(&cgroup_mutex);
idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id);
}
void cgroup_free_root(struct cgroup_root *root)
{
kfree(root);
}
static void cgroup_destroy_root(struct cgroup_root *root)
{
struct cgroup *cgrp = &root->cgrp;
struct cgrp_cset_link *link, *tmp_link;
trace_cgroup_destroy_root(root);
cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
BUG_ON(atomic_read(&root->nr_cgrps));
BUG_ON(!list_empty(&cgrp->self.children));
WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask));
spin_lock_irq(&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);
}
spin_unlock_irq(&css_set_lock);
if (!list_empty(&root->root_list)) {
list_del(&root->root_list);
cgroup_root_count--;
}
cgroup_favor_dynmods(root, false);
cgroup_exit_root_id(root);
cgroup_unlock();
cgroup_rstat_exit(cgrp);
kernfs_destroy_root(root->kf_root);
cgroup_free_root(root);
}
static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset,
struct cgroup_root *root)
{
struct cgroup *res_cgroup = NULL;
if (cset == &init_css_set) {
res_cgroup = &root->cgrp;
} else if (root == &cgrp_dfl_root) {
res_cgroup = cset->dfl_cgrp;
} else {
struct cgrp_cset_link *link;
lockdep_assert_held(&css_set_lock);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
if (c->root == root) {
res_cgroup = c;
break;
}
}
}
BUG_ON(!res_cgroup);
return res_cgroup;
}
static struct cgroup *
current_cgns_cgroup_from_root(struct cgroup_root *root)
{
struct cgroup *res = NULL;
struct css_set *cset;
lockdep_assert_held(&css_set_lock);
rcu_read_lock();
cset = current->nsproxy->cgroup_ns->root_cset;
res = __cset_cgroup_from_root(cset, root);
rcu_read_unlock();
return res;
}
static struct cgroup *current_cgns_cgroup_dfl(void)
{
struct css_set *cset;
if (current->nsproxy) {
cset = current->nsproxy->cgroup_ns->root_cset;
return __cset_cgroup_from_root(cset, &cgrp_dfl_root);
} else {
return &cgrp_dfl_root.cgrp;
}
}
static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
struct cgroup_root *root)
{
lockdep_assert_held(&cgroup_mutex);
lockdep_assert_held(&css_set_lock);
return __cset_cgroup_from_root(cset, root);
}
struct cgroup *task_cgroup_from_root(struct task_struct *task,
struct cgroup_root *root)
{
return cset_cgroup_from_root(task_css_set(task), root);
}
static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
char *buf)
{
struct cgroup_subsys *ss = cft->ss;
if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) &&
!(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) {
const char *dbg = (cft->flags & CFTYPE_DEBUG) ? ".__DEBUG__." : "";
snprintf(buf, CGROUP_FILE_NAME_MAX, "%s%s.%s",
dbg, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
cft->name);
} else {
strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
}
return buf;
}
static umode_t cgroup_file_mode(const struct cftype *cft)
{
umode_t mode = 0;
if (cft->read_u64 || cft->read_s64 || cft->seq_show)
mode |= S_IRUGO;
if (cft->write_u64 || cft->write_s64 || cft->write) {
if (cft->flags & CFTYPE_WORLD_WRITABLE)
mode |= S_IWUGO;
else
mode |= S_IWUSR;
}
return mode;
}
static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask)
{
u16 cur_ss_mask = subtree_control;
struct cgroup_subsys *ss;
int ssid;
lockdep_assert_held(&cgroup_mutex);
cur_ss_mask |= cgrp_dfl_implicit_ss_mask;
while (true) {
u16 new_ss_mask = cur_ss_mask;
do_each_subsys_mask(ss, ssid, cur_ss_mask) {
new_ss_mask |= ss->depends_on;
} while_each_subsys_mask();
new_ss_mask &= this_ss_mask;
if (new_ss_mask == cur_ss_mask)
break;
cur_ss_mask = new_ss_mask;
}
return cur_ss_mask;
}
void cgroup_kn_unlock(struct kernfs_node *kn)
{
struct cgroup *cgrp;
if (kernfs_type(kn) == KERNFS_DIR)
cgrp = kn->priv;
else
cgrp = kn->parent->priv;
cgroup_unlock();
kernfs_unbreak_active_protection(kn);
cgroup_put(cgrp);
}
struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline)
{
struct cgroup *cgrp;
if (kernfs_type(kn) == KERNFS_DIR)
cgrp = kn->priv;
else
cgrp = kn->parent->priv;
if (!cgroup_tryget(cgrp))
return NULL;
kernfs_break_active_protection(kn);
if (drain_offline)
cgroup_lock_and_drain_offline(cgrp);
else
cgroup_lock();
if (!cgroup_is_dead(cgrp))
return cgrp;
cgroup_kn_unlock(kn);
return NULL;
}
static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
{
char name[CGROUP_FILE_NAME_MAX];
lockdep_assert_held(&cgroup_mutex);
if (cft->file_offset) {
struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss);
struct cgroup_file *cfile = (void *)css + cft->file_offset;
spin_lock_irq(&cgroup_file_kn_lock);
cfile->kn = NULL;
spin_unlock_irq(&cgroup_file_kn_lock);
del_timer_sync(&cfile->notify_timer);
}
kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
}
static void css_clear_dir(struct cgroup_subsys_state *css)
{
struct cgroup *cgrp = css->cgroup;
struct cftype *cfts;
if (!(css->flags & CSS_VISIBLE))
return;
css->flags &= ~CSS_VISIBLE;
if (!css->ss) {
if (cgroup_on_dfl(cgrp)) {
cgroup_addrm_files(css, cgrp,
cgroup_base_files, false);
if (cgroup_psi_enabled())
cgroup_addrm_files(css, cgrp,
cgroup_psi_files, false);
} else {
cgroup_addrm_files(css, cgrp,
cgroup1_base_files, false);
}
} else {
list_for_each_entry(cfts, &css->ss->cfts, node)
cgroup_addrm_files(css, cgrp, cfts, false);
}
}
static int css_populate_dir(struct cgroup_subsys_state *css)
{
struct cgroup *cgrp = css->cgroup;
struct cftype *cfts, *failed_cfts;
int ret;
if (css->flags & CSS_VISIBLE)
return 0;
if (!css->ss) {
if (cgroup_on_dfl(cgrp)) {
ret = cgroup_addrm_files(&cgrp->self, cgrp,
cgroup_base_files, true);
if (ret < 0)
return ret;
if (cgroup_psi_enabled()) {
ret = cgroup_addrm_files(&cgrp->self, cgrp,
cgroup_psi_files, true);
if (ret < 0)
return ret;
}
} else {
cgroup_addrm_files(css, cgrp,
cgroup1_base_files, true);
}
} else {
list_for_each_entry(cfts, &css->ss->cfts, node) {
ret = cgroup_addrm_files(css, cgrp, cfts, true);
if (ret < 0) {
failed_cfts = cfts;
goto err;
}
}
}
css->flags |= CSS_VISIBLE;
return 0;
err:
list_for_each_entry(cfts, &css->ss->cfts, node) {
if (cfts == failed_cfts)
break;
cgroup_addrm_files(css, cgrp, cfts, false);
}
return ret;
}
int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
{
struct cgroup *dcgrp = &dst_root->cgrp;
struct cgroup_subsys *ss;
int ssid, ret;
u16 dfl_disable_ss_mask = 0;
lockdep_assert_held(&cgroup_mutex);
do_each_subsys_mask(ss, ssid, ss_mask) {
if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)) &&
!ss->implicit_on_dfl)
return -EBUSY;
if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root)
return -EBUSY;
if (ss->root == &cgrp_dfl_root)
dfl_disable_ss_mask |= 1 << ssid;
} while_each_subsys_mask();
if (dfl_disable_ss_mask) {
struct cgroup *scgrp = &cgrp_dfl_root.cgrp;
cgrp_dfl_root.subsys_mask &= ~dfl_disable_ss_mask;
WARN_ON(cgroup_apply_control(scgrp));
cgroup_finalize_control(scgrp, 0);
}
do_each_subsys_mask(ss, ssid, ss_mask) {
struct cgroup_root *src_root = ss->root;
struct cgroup *scgrp = &src_root->cgrp;
struct cgroup_subsys_state *css = cgroup_css(scgrp, ss);
struct css_set *cset, *cset_pos;
struct css_task_iter *it;
WARN_ON(!css || cgroup_css(dcgrp, ss));
if (src_root != &cgrp_dfl_root) {
src_root->subsys_mask &= ~(1 << ssid);
WARN_ON(cgroup_apply_control(scgrp));
cgroup_finalize_control(scgrp, 0);
}
RCU_INIT_POINTER(scgrp->subsys[ssid], NULL);
rcu_assign_pointer(dcgrp->subsys[ssid], css);
ss->root = dst_root;
css->cgroup = dcgrp;
spin_lock_irq(&css_set_lock);
WARN_ON(!list_empty(&dcgrp->e_csets[ss->id]));
list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id],
e_cset_node[ss->id]) {
list_move_tail(&cset->e_cset_node[ss->id],
&dcgrp->e_csets[ss->id]);
list_for_each_entry(it, &cset->task_iters, iters_node)
if (it->cset_head == &scgrp->e_csets[ss->id])
it->cset_head = &dcgrp->e_csets[ss->id];
}
spin_unlock_irq(&css_set_lock);
if (ss->css_rstat_flush) {
list_del_rcu(&css->rstat_css_node);
synchronize_rcu();
list_add_rcu(&css->rstat_css_node,
&dcgrp->rstat_css_list);
}
dst_root->subsys_mask |= 1 << ssid;
if (dst_root == &cgrp_dfl_root) {
static_branch_enable(cgroup_subsys_on_dfl_key[ssid]);
} else {
dcgrp->subtree_control |= 1 << ssid;
static_branch_disable(cgroup_subsys_on_dfl_key[ssid]);
}
ret = cgroup_apply_control(dcgrp);
if (ret)
pr_warn("partial failure to rebind %s controller (err=%d)\n",
ss->name, ret);
if (ss->bind)
ss->bind(css);
} while_each_subsys_mask();
kernfs_activate(dcgrp->kn);
return 0;
}
int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
struct kernfs_root *kf_root)
{
int len = 0;
char *buf = NULL;
struct cgroup_root *kf_cgroot = cgroup_root_from_kf(kf_root);
struct cgroup *ns_cgroup;
buf = kmalloc(PATH_MAX, GFP_KERNEL);
if (!buf)
return -ENOMEM;
spin_lock_irq(&css_set_lock);
ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot);
len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX);
spin_unlock_irq(&css_set_lock);
if (len >= PATH_MAX)
len = -ERANGE;
else if (len > 0) {
seq_escape(sf, buf, " \t\n\\");
len = 0;
}
kfree(buf);
return len;
}
enum cgroup2_param {
Opt_nsdelegate,
Opt_favordynmods,
Opt_memory_localevents,
Opt_memory_recursiveprot,
nr__cgroup2_params
};
static const struct fs_parameter_spec cgroup2_fs_parameters[] = {
fsparam_flag("nsdelegate", Opt_nsdelegate),
fsparam_flag("favordynmods", Opt_favordynmods),
fsparam_flag("memory_localevents", Opt_memory_localevents),
fsparam_flag("memory_recursiveprot", Opt_memory_recursiveprot),
{}
};
static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
struct fs_parse_result result;
int opt;
opt = fs_parse(fc, cgroup2_fs_parameters, param, &result);
if (opt < 0)
return opt;
switch (opt) {
case Opt_nsdelegate:
ctx->flags |= CGRP_ROOT_NS_DELEGATE;
return 0;
case Opt_favordynmods:
ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS;
return 0;
case Opt_memory_localevents:
ctx->flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS;
return 0;
case Opt_memory_recursiveprot:
ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT;
return 0;
}
return -EINVAL;
}
static void apply_cgroup_root_flags(unsigned int root_flags)
{
if (current->nsproxy->cgroup_ns == &init_cgroup_ns) {
if (root_flags & CGRP_ROOT_NS_DELEGATE)
cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE;
else
cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE;
cgroup_favor_dynmods(&cgrp_dfl_root,
root_flags & CGRP_ROOT_FAVOR_DYNMODS);
if (root_flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS;
else
cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_LOCAL_EVENTS;
if (root_flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)
cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT;
else
cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT;
}
}
static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root)
{
if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE)
seq_puts(seq, ",nsdelegate");
if (cgrp_dfl_root.flags & CGRP_ROOT_FAVOR_DYNMODS)
seq_puts(seq, ",favordynmods");
if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
seq_puts(seq, ",memory_localevents");
if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)
seq_puts(seq, ",memory_recursiveprot");
return 0;
}
static int cgroup_reconfigure(struct fs_context *fc)
{
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
apply_cgroup_root_flags(ctx->flags);
return 0;
}
static void init_cgroup_housekeeping(struct cgroup *cgrp)
{
struct cgroup_subsys *ss;
int ssid;
INIT_LIST_HEAD(&cgrp->self.sibling);
INIT_LIST_HEAD(&cgrp->self.children);
INIT_LIST_HEAD(&cgrp->cset_links);
INIT_LIST_HEAD(&cgrp->pidlists);
mutex_init(&cgrp->pidlist_mutex);
cgrp->self.cgroup = cgrp;
cgrp->self.flags |= CSS_ONLINE;
cgrp->dom_cgrp = cgrp;
cgrp->max_descendants = INT_MAX;
cgrp->max_depth = INT_MAX;
INIT_LIST_HEAD(&cgrp->rstat_css_list);
prev_cputime_init(&cgrp->prev_cputime);
for_each_subsys(ss, ssid)
INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
init_waitqueue_head(&cgrp->offline_waitq);
INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent);
}
void init_cgroup_root(struct cgroup_fs_context *ctx)
{
struct cgroup_root *root = ctx->root;
struct cgroup *cgrp = &root->cgrp;
INIT_LIST_HEAD(&root->root_list);
atomic_set(&root->nr_cgrps, 1);
cgrp->root = root;
init_cgroup_housekeeping(cgrp);
root->flags = ctx->flags & ~CGRP_ROOT_FAVOR_DYNMODS;
if (ctx->release_agent)
strscpy(root->release_agent_path, ctx->release_agent, PATH_MAX);
if (ctx->name)
strscpy(root->name, ctx->name, MAX_CGROUP_ROOT_NAMELEN);
if (ctx->cpuset_clone_children)
set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
}
int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
{
LIST_HEAD(tmp_links);
struct cgroup *root_cgrp = &root->cgrp;
struct kernfs_syscall_ops *kf_sops;
struct css_set *cset;
int i, ret;
lockdep_assert_held(&cgroup_mutex);
ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release,
0, GFP_KERNEL);
if (ret)
goto out;
ret = allocate_cgrp_cset_links(2 * css_set_count, &tmp_links);
if (ret)
goto cancel_ref;
ret = cgroup_init_root_id(root);
if (ret)
goto cancel_ref;
kf_sops = root == &cgrp_dfl_root ?
&cgroup_kf_syscall_ops : &cgroup1_kf_syscall_ops;
root->kf_root = kernfs_create_root(kf_sops,
KERNFS_ROOT_CREATE_DEACTIVATED |
KERNFS_ROOT_SUPPORT_EXPORTOP |
KERNFS_ROOT_SUPPORT_USER_XATTR,
root_cgrp);
if (IS_ERR(root->kf_root)) {
ret = PTR_ERR(root->kf_root);
goto exit_root_id;
}
root_cgrp->kn = kernfs_root_to_node(root->kf_root);
WARN_ON_ONCE(cgroup_ino(root_cgrp) != 1);
root_cgrp->ancestors[0] = root_cgrp;
ret = css_populate_dir(&root_cgrp->self);
if (ret)
goto destroy_root;
ret = cgroup_rstat_init(root_cgrp);
if (ret)
goto destroy_root;
ret = rebind_subsystems(root, ss_mask);
if (ret)
goto exit_stats;
ret = cgroup_bpf_inherit(root_cgrp);
WARN_ON_ONCE(ret);
trace_cgroup_setup_root(root);
list_add(&root->root_list, &cgroup_roots);
cgroup_root_count++;
spin_lock_irq(&css_set_lock);
hash_for_each(css_set_table, i, cset, hlist) {
link_css_set(&tmp_links, cset, root_cgrp);
if (css_set_populated(cset))
cgroup_update_populated(root_cgrp, true);
}
spin_unlock_irq(&css_set_lock);
BUG_ON(!list_empty(&root_cgrp->self.children));
BUG_ON(atomic_read(&root->nr_cgrps) != 1);
ret = 0;
goto out;
exit_stats:
cgroup_rstat_exit(root_cgrp);
destroy_root:
kernfs_destroy_root(root->kf_root);
root->kf_root = NULL;
exit_root_id:
cgroup_exit_root_id(root);
cancel_ref:
percpu_ref_exit(&root_cgrp->self.refcnt);
out:
free_cgrp_cset_links(&tmp_links);
return ret;
}
int cgroup_do_get_tree(struct fs_context *fc)
{
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
int ret;
ctx->kfc.root = ctx->root->kf_root;
if (fc->fs_type == &cgroup2_fs_type)
ctx->kfc.magic = CGROUP2_SUPER_MAGIC;
else
ctx->kfc.magic = CGROUP_SUPER_MAGIC;
ret = kernfs_get_tree(fc);
if (!ret && ctx->ns != &init_cgroup_ns) {
struct dentry *nsdentry;
struct super_block *sb = fc->root->d_sb;
struct cgroup *cgrp;
cgroup_lock();
spin_lock_irq(&css_set_lock);
cgrp = cset_cgroup_from_root(ctx->ns->root_cset, ctx->root);
spin_unlock_irq(&css_set_lock);
cgroup_unlock();
nsdentry = kernfs_node_dentry(cgrp->kn, sb);
dput(fc->root);
if (IS_ERR(nsdentry)) {
deactivate_locked_super(sb);
ret = PTR_ERR(nsdentry);
nsdentry = NULL;
}
fc->root = nsdentry;
}
if (!ctx->kfc.new_sb_created)
cgroup_put(&ctx->root->cgrp);
return ret;
}
static void cgroup_fs_context_free(struct fs_context *fc)
{
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
kfree(ctx->name);
kfree(ctx->release_agent);
put_cgroup_ns(ctx->ns);
kernfs_free_fs_context(fc);
kfree(ctx);
}
static int cgroup_get_tree(struct fs_context *fc)
{
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
int ret;
WRITE_ONCE(cgrp_dfl_visible, true);
cgroup_get_live(&cgrp_dfl_root.cgrp);
ctx->root = &cgrp_dfl_root;
ret = cgroup_do_get_tree(fc);
if (!ret)
apply_cgroup_root_flags(ctx->flags);
return ret;
}
static const struct fs_context_operations cgroup_fs_context_ops = {
.free = cgroup_fs_context_free,
.parse_param = cgroup2_parse_param,
.get_tree = cgroup_get_tree,
.reconfigure = cgroup_reconfigure,
};
static const struct fs_context_operations cgroup1_fs_context_ops = {
.free = cgroup_fs_context_free,
.parse_param = cgroup1_parse_param,
.get_tree = cgroup1_get_tree,
.reconfigure = cgroup1_reconfigure,
};
static int cgroup_init_fs_context(struct fs_context *fc)
{
struct cgroup_fs_context *ctx;
ctx = kzalloc(sizeof(struct cgroup_fs_context), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
ctx->ns = current->nsproxy->cgroup_ns;
get_cgroup_ns(ctx->ns);
fc->fs_private = &ctx->kfc;
if (fc->fs_type == &cgroup2_fs_type)
fc->ops = &cgroup_fs_context_ops;
else
fc->ops = &cgroup1_fs_context_ops;
put_user_ns(fc->user_ns);
fc->user_ns = get_user_ns(ctx->ns->user_ns);
fc->global = true;
#ifdef CONFIG_CGROUP_FAVOR_DYNMODS
ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS;
#endif
return 0;
}
static void cgroup_kill_sb(struct super_block *sb)
{
struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
struct cgroup_root *root = cgroup_root_from_kf(kf_root);
if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root &&
!percpu_ref_is_dying(&root->cgrp.self.refcnt)) {
cgroup_bpf_offline(&root->cgrp);
percpu_ref_kill(&root->cgrp.self.refcnt);
}
cgroup_put(&root->cgrp);
kernfs_kill_sb(sb);
}
struct file_system_type cgroup_fs_type = {
.name = "cgroup",
.init_fs_context = cgroup_init_fs_context,
.parameters = cgroup1_fs_parameters,
.kill_sb = cgroup_kill_sb,
.fs_flags = FS_USERNS_MOUNT,
};
static struct file_system_type cgroup2_fs_type = {
.name = "cgroup2",
.init_fs_context = cgroup_init_fs_context,
.parameters = cgroup2_fs_parameters,
.kill_sb = cgroup_kill_sb,
.fs_flags = FS_USERNS_MOUNT,
};
#ifdef CONFIG_CPUSETS
static const struct fs_context_operations cpuset_fs_context_ops = {
.get_tree = cgroup1_get_tree,
.free = cgroup_fs_context_free,
};
static int cpuset_init_fs_context(struct fs_context *fc)
{
char *agent = kstrdup("/sbin/cpuset_release_agent", GFP_USER);
struct cgroup_fs_context *ctx;
int err;
err = cgroup_init_fs_context(fc);
if (err) {
kfree(agent);
return err;
}
fc->ops = &cpuset_fs_context_ops;
ctx = cgroup_fc2context(fc);
ctx->subsys_mask = 1 << cpuset_cgrp_id;
ctx->flags |= CGRP_ROOT_NOPREFIX;
ctx->release_agent = agent;
get_filesystem(&cgroup_fs_type);
put_filesystem(fc->fs_type);
fc->fs_type = &cgroup_fs_type;
return 0;
}
static struct file_system_type cpuset_fs_type = {
.name = "cpuset",
.init_fs_context = cpuset_init_fs_context,
.fs_flags = FS_USERNS_MOUNT,
};
#endif
int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
struct cgroup_namespace *ns)
{
struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root);
return kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen);
}
int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
struct cgroup_namespace *ns)
{
int ret;
cgroup_lock();
spin_lock_irq(&css_set_lock);
ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns);
spin_unlock_irq(&css_set_lock);
cgroup_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(cgroup_path_ns);
void cgroup_attach_lock(bool lock_threadgroup)
{
cpus_read_lock();
if (lock_threadgroup)
percpu_down_write(&cgroup_threadgroup_rwsem);
}
void cgroup_attach_unlock(bool lock_threadgroup)
{
if (lock_threadgroup)
percpu_up_write(&cgroup_threadgroup_rwsem);
cpus_read_unlock();
}
static void cgroup_migrate_add_task(struct task_struct *task,
struct cgroup_mgctx *mgctx)
{
struct css_set *cset;
lockdep_assert_held(&css_set_lock);
if (task->flags & PF_EXITING)
return;
WARN_ON_ONCE(list_empty(&task->cg_list));
cset = task_css_set(task);
if (!cset->mg_src_cgrp)
return;
mgctx->tset.nr_tasks++;
list_move_tail(&task->cg_list, &cset->mg_tasks);
if (list_empty(&cset->mg_node))
list_add_tail(&cset->mg_node,
&mgctx->tset.src_csets);
if (list_empty(&cset->mg_dst_cset->mg_node))
list_add_tail(&cset->mg_dst_cset->mg_node,
&mgctx->tset.dst_csets);
}
struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
struct cgroup_subsys_state **dst_cssp)
{
tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node);
tset->cur_task = NULL;
return cgroup_taskset_next(tset, dst_cssp);
}
struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
struct cgroup_subsys_state **dst_cssp)
{
struct css_set *cset = tset->cur_cset;
struct task_struct *task = tset->cur_task;
while (CGROUP_HAS_SUBSYS_CONFIG && &cset->mg_node != tset->csets) {
if (!task)
task = list_first_entry(&cset->mg_tasks,
struct task_struct, cg_list);
else
task = list_next_entry(task, cg_list);
if (&task->cg_list != &cset->mg_tasks) {
tset->cur_cset = cset;
tset->cur_task = task;
if (cset->mg_dst_cset)
*dst_cssp = cset->mg_dst_cset->subsys[tset->ssid];
else
*dst_cssp = cset->subsys[tset->ssid];
return task;
}
cset = list_next_entry(cset, mg_node);
task = NULL;
}
return NULL;
}
static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
{
struct cgroup_taskset *tset = &mgctx->tset;
struct cgroup_subsys *ss;
struct task_struct *task, *tmp_task;
struct css_set *cset, *tmp_cset;
int ssid, failed_ssid, ret;
if (tset->nr_tasks) {
do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
if (ss->can_attach) {
tset->ssid = ssid;
ret = ss->can_attach(tset);
if (ret) {
failed_ssid = ssid;
goto out_cancel_attach;
}
}
} while_each_subsys_mask();
}
spin_lock_irq(&css_set_lock);
list_for_each_entry(cset, &tset->src_csets, mg_node) {
list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) {
struct css_set *from_cset = task_css_set(task);
struct css_set *to_cset = cset->mg_dst_cset;
get_css_set(to_cset);
to_cset->nr_tasks++;
css_set_move_task(task, from_cset, to_cset, true);
from_cset->nr_tasks--;
cgroup_freezer_migrate_task(task, from_cset->dfl_cgrp,
to_cset->dfl_cgrp);
put_css_set_locked(from_cset);
}
}
spin_unlock_irq(&css_set_lock);
tset->csets = &tset->dst_csets;
if (tset->nr_tasks) {
do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
if (ss->attach) {
tset->ssid = ssid;
ss->attach(tset);
}
} while_each_subsys_mask();
}
ret = 0;
goto out_release_tset;
out_cancel_attach:
if (tset->nr_tasks) {
do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
if (ssid == failed_ssid)
break;
if (ss->cancel_attach) {
tset->ssid = ssid;
ss->cancel_attach(tset);
}
} while_each_subsys_mask();
}
out_release_tset:
spin_lock_irq(&css_set_lock);
list_splice_init(&tset->dst_csets, &tset->src_csets);
list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) {
list_splice_tail_init(&cset->mg_tasks, &cset->tasks);
list_del_init(&cset->mg_node);
}
spin_unlock_irq(&css_set_lock);
tset->nr_tasks = 0;
tset->csets = &tset->src_csets;
return ret;
}
int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp)
{
if (!cgroup_on_dfl(dst_cgrp))
return 0;
if (!cgroup_is_valid_domain(dst_cgrp->dom_cgrp))
return -EOPNOTSUPP;
if (cgroup_can_be_thread_root(dst_cgrp) || cgroup_is_threaded(dst_cgrp))
return 0;
if (dst_cgrp->subtree_control)
return -EBUSY;
return 0;
}
void cgroup_migrate_finish(struct cgroup_mgctx *mgctx)
{
struct css_set *cset, *tmp_cset;
lockdep_assert_held(&cgroup_mutex);
spin_lock_irq(&css_set_lock);
list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets,
mg_src_preload_node) {
cset->mg_src_cgrp = NULL;
cset->mg_dst_cgrp = NULL;
cset->mg_dst_cset = NULL;
list_del_init(&cset->mg_src_preload_node);
put_css_set_locked(cset);
}
list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets,
mg_dst_preload_node) {
cset->mg_src_cgrp = NULL;
cset->mg_dst_cgrp = NULL;
cset->mg_dst_cset = NULL;
list_del_init(&cset->mg_dst_preload_node);
put_css_set_locked(cset);
}
spin_unlock_irq(&css_set_lock);
}
void cgroup_migrate_add_src(struct css_set *src_cset,
struct cgroup *dst_cgrp,
struct cgroup_mgctx *mgctx)
{
struct cgroup *src_cgrp;
lockdep_assert_held(&cgroup_mutex);
lockdep_assert_held(&css_set_lock);
if (src_cset->dead)
return;
if (!list_empty(&src_cset->mg_src_preload_node))
return;
src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
WARN_ON(src_cset->mg_src_cgrp);
WARN_ON(src_cset->mg_dst_cgrp);
WARN_ON(!list_empty(&src_cset->mg_tasks));
WARN_ON(!list_empty(&src_cset->mg_node));
src_cset->mg_src_cgrp = src_cgrp;
src_cset->mg_dst_cgrp = dst_cgrp;
get_css_set(src_cset);
list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets);
}
int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
{
struct css_set *src_cset, *tmp_cset;
lockdep_assert_held(&cgroup_mutex);
list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets,
mg_src_preload_node) {
struct css_set *dst_cset;
struct cgroup_subsys *ss;
int ssid;
dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp);
if (!dst_cset)
return -ENOMEM;
WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset);
if (src_cset == dst_cset) {
src_cset->mg_src_cgrp = NULL;
src_cset->mg_dst_cgrp = NULL;
list_del_init(&src_cset->mg_src_preload_node);
put_css_set(src_cset);
put_css_set(dst_cset);
continue;
}
src_cset->mg_dst_cset = dst_cset;
if (list_empty(&dst_cset->mg_dst_preload_node))
list_add_tail(&dst_cset->mg_dst_preload_node,
&mgctx->preloaded_dst_csets);
else
put_css_set(dst_cset);
for_each_subsys(ss, ssid)
if (src_cset->subsys[ssid] != dst_cset->subsys[ssid])
mgctx->ss_mask |= 1 << ssid;
}
return 0;
}
int cgroup_migrate(struct task_struct *leader, bool threadgroup,
struct cgroup_mgctx *mgctx)
{
struct task_struct *task;
spin_lock_irq(&css_set_lock);
task = leader;
do {
cgroup_migrate_add_task(task, mgctx);
if (!threadgroup)
break;
} while_each_thread(leader, task);
spin_unlock_irq(&css_set_lock);
return cgroup_migrate_execute(mgctx);
}
int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
bool threadgroup)
{
DEFINE_CGROUP_MGCTX(mgctx);
struct task_struct *task;
int ret = 0;
spin_lock_irq(&css_set_lock);
rcu_read_lock();
task = leader;
do {
cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &mgctx);
if (!threadgroup)
break;
} while_each_thread(leader, task);
rcu_read_unlock();
spin_unlock_irq(&css_set_lock);
ret = cgroup_migrate_prepare_dst(&mgctx);
if (!ret)
ret = cgroup_migrate(leader, threadgroup, &mgctx);
cgroup_migrate_finish(&mgctx);
if (!ret)
TRACE_CGROUP_PATH(attach_task, dst_cgrp, leader, threadgroup);
return ret;
}
struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
bool *threadgroup_locked)
{
struct task_struct *tsk;
pid_t pid;
if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
return ERR_PTR(-EINVAL);
lockdep_assert_held(&cgroup_mutex);
*threadgroup_locked = pid || threadgroup;
cgroup_attach_lock(*threadgroup_locked);
rcu_read_lock();
if (pid) {
tsk = find_task_by_vpid(pid);
if (!tsk) {
tsk = ERR_PTR(-ESRCH);
goto out_unlock_threadgroup;
}
} else {
tsk = current;
}
if (threadgroup)
tsk = tsk->group_leader;
if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) {
tsk = ERR_PTR(-EINVAL);
goto out_unlock_threadgroup;
}
get_task_struct(tsk);
goto out_unlock_rcu;
out_unlock_threadgroup:
cgroup_attach_unlock(*threadgroup_locked);
*threadgroup_locked = false;
out_unlock_rcu:
rcu_read_unlock();
return tsk;
}
void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked)
{
struct cgroup_subsys *ss;
int ssid;
put_task_struct(task);
cgroup_attach_unlock(threadgroup_locked);
for_each_subsys(ss, ssid)
if (ss->post_attach)
ss->post_attach();
}
static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask)
{
struct cgroup_subsys *ss;
bool printed = false;
int ssid;
do_each_subsys_mask(ss, ssid, ss_mask) {
if (printed)
seq_putc(seq, ' ');
seq_puts(seq, ss->name);
printed = true;
} while_each_subsys_mask();
if (printed)
seq_putc(seq, '\n');
}
static int cgroup_controllers_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
cgroup_print_ss_mask(seq, cgroup_control(cgrp));
return 0;
}
static int cgroup_subtree_control_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
cgroup_print_ss_mask(seq, cgrp->subtree_control);
return 0;
}
static int cgroup_update_dfl_csses(struct cgroup *cgrp)
{
DEFINE_CGROUP_MGCTX(mgctx);
struct cgroup_subsys_state *d_css;
struct cgroup *dsct;
struct css_set *src_cset;
bool has_tasks;
int ret;
lockdep_assert_held(&cgroup_mutex);
spin_lock_irq(&css_set_lock);
cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
struct cgrp_cset_link *link;
if (dsct == cgrp)
continue;
list_for_each_entry(link, &dsct->cset_links, cset_link)
cgroup_migrate_add_src(link->cset, dsct, &mgctx);
}
spin_unlock_irq(&css_set_lock);
has_tasks = !list_empty(&mgctx.preloaded_src_csets);
cgroup_attach_lock(has_tasks);
ret = cgroup_migrate_prepare_dst(&mgctx);
if (ret)
goto out_finish;
spin_lock_irq(&css_set_lock);
list_for_each_entry(src_cset, &mgctx.preloaded_src_csets,
mg_src_preload_node) {
struct task_struct *task, *ntask;
list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list)
cgroup_migrate_add_task(task, &mgctx);
}
spin_unlock_irq(&css_set_lock);
ret = cgroup_migrate_execute(&mgctx);
out_finish:
cgroup_migrate_finish(&mgctx);
cgroup_attach_unlock(has_tasks);
return ret;
}
void cgroup_lock_and_drain_offline(struct cgroup *cgrp)
__acquires(&cgroup_mutex)
{
struct cgroup *dsct;
struct cgroup_subsys_state *d_css;
struct cgroup_subsys *ss;
int ssid;
restart:
cgroup_lock();
cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) {
for_each_subsys(ss, ssid) {
struct cgroup_subsys_state *css = cgroup_css(dsct, ss);
DEFINE_WAIT(wait);
if (!css || !percpu_ref_is_dying(&css->refcnt))
continue;
cgroup_get_live(dsct);
prepare_to_wait(&dsct->offline_waitq, &wait,
TASK_UNINTERRUPTIBLE);
cgroup_unlock();
schedule();
finish_wait(&dsct->offline_waitq, &wait);
cgroup_put(dsct);
goto restart;
}
}
}
static void cgroup_save_control(struct cgroup *cgrp)
{
struct cgroup *dsct;
struct cgroup_subsys_state *d_css;
cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
dsct->old_subtree_control = dsct->subtree_control;
dsct->old_subtree_ss_mask = dsct->subtree_ss_mask;
dsct->old_dom_cgrp = dsct->dom_cgrp;
}
}
static void cgroup_propagate_control(struct cgroup *cgrp)
{
struct cgroup *dsct;
struct cgroup_subsys_state *d_css;
cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
dsct->subtree_control &= cgroup_control(dsct);
dsct->subtree_ss_mask =
cgroup_calc_subtree_ss_mask(dsct->subtree_control,
cgroup_ss_mask(dsct));
}
}
static void cgroup_restore_control(struct cgroup *cgrp)
{
struct cgroup *dsct;
struct cgroup_subsys_state *d_css;
cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) {
dsct->subtree_control = dsct->old_subtree_control;
dsct->subtree_ss_mask = dsct->old_subtree_ss_mask;
dsct->dom_cgrp = dsct->old_dom_cgrp;
}
}
static bool css_visible(struct cgroup_subsys_state *css)
{
struct cgroup_subsys *ss = css->ss;
struct cgroup *cgrp = css->cgroup;
if (cgroup_control(cgrp) & (1 << ss->id))
return true;
if (!(cgroup_ss_mask(cgrp) & (1 << ss->id)))
return false;
return cgroup_on_dfl(cgrp) && ss->implicit_on_dfl;
}
static int cgroup_apply_control_enable(struct cgroup *cgrp)
{
struct cgroup *dsct;
struct cgroup_subsys_state *d_css;
struct cgroup_subsys *ss;
int ssid, ret;
cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
for_each_subsys(ss, ssid) {
struct cgroup_subsys_state *css = cgroup_css(dsct, ss);
if (!(cgroup_ss_mask(dsct) & (1 << ss->id)))
continue;
if (!css) {
css = css_create(dsct, ss);
if (IS_ERR(css))
return PTR_ERR(css);
}
WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt));
if (css_visible(css)) {
ret = css_populate_dir(css);
if (ret)
return ret;
}
}
}
return 0;
}
static void cgroup_apply_control_disable(struct cgroup *cgrp)
{
struct cgroup *dsct;
struct cgroup_subsys_state *d_css;
struct cgroup_subsys *ss;
int ssid;
cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) {
for_each_subsys(ss, ssid) {
struct cgroup_subsys_state *css = cgroup_css(dsct, ss);
if (!css)
continue;
WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt));
if (css->parent &&
!(cgroup_ss_mask(dsct) & (1 << ss->id))) {
kill_css(css);
} else if (!css_visible(css)) {
css_clear_dir(css);
if (ss->css_reset)
ss->css_reset(css);
}
}
}
}
static int cgroup_apply_control(struct cgroup *cgrp)
{
int ret;
cgroup_propagate_control(cgrp);
ret = cgroup_apply_control_enable(cgrp);
if (ret)
return ret;
return cgroup_update_dfl_csses(cgrp);
}
static void cgroup_finalize_control(struct cgroup *cgrp, int ret)
{
if (ret) {
cgroup_restore_control(cgrp);
cgroup_propagate_control(cgrp);
}
cgroup_apply_control_disable(cgrp);
}
static int cgroup_vet_subtree_control_enable(struct cgroup *cgrp, u16 enable)
{
u16 domain_enable = enable & ~cgrp_dfl_threaded_ss_mask;
if (!enable)
return 0;
if (!cgroup_is_valid_domain(cgrp->dom_cgrp))
return -EOPNOTSUPP;
if (cgroup_is_mixable(cgrp))
return 0;
if (domain_enable) {
if (cgroup_is_thread_root(cgrp) || cgroup_is_threaded(cgrp))
return -EOPNOTSUPP;
} else {
if (cgroup_can_be_thread_root(cgrp) || cgroup_is_threaded(cgrp))
return 0;
}
if (cgroup_has_tasks(cgrp))
return -EBUSY;
return 0;
}
static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
u16 enable = 0, disable = 0;
struct cgroup *cgrp, *child;
struct cgroup_subsys *ss;
char *tok;
int ssid, ret;
buf = strstrip(buf);
while ((tok = strsep(&buf, " "))) {
if (tok[0] == '\0')
continue;
do_each_subsys_mask(ss, ssid, ~cgrp_dfl_inhibit_ss_mask) {
if (!cgroup_ssid_enabled(ssid) ||
strcmp(tok + 1, ss->name))
continue;
if (*tok == '+') {
enable |= 1 << ssid;
disable &= ~(1 << ssid);
} else if (*tok == '-') {
disable |= 1 << ssid;
enable &= ~(1 << ssid);
} else {
return -EINVAL;
}
break;
} while_each_subsys_mask();
if (ssid == CGROUP_SUBSYS_COUNT)
return -EINVAL;
}
cgrp = cgroup_kn_lock_live(of->kn, true);
if (!cgrp)
return -ENODEV;
for_each_subsys(ss, ssid) {
if (enable & (1 << ssid)) {
if (cgrp->subtree_control & (1 << ssid)) {
enable &= ~(1 << ssid);
continue;
}
if (!(cgroup_control(cgrp) & (1 << ssid))) {
ret = -ENOENT;
goto out_unlock;
}
} else if (disable & (1 << ssid)) {
if (!(cgrp->subtree_control & (1 << ssid))) {
disable &= ~(1 << ssid);
continue;
}
cgroup_for_each_live_child(child, cgrp) {
if (child->subtree_control & (1 << ssid)) {
ret = -EBUSY;
goto out_unlock;
}
}
}
}
if (!enable && !disable) {
ret = 0;
goto out_unlock;
}
ret = cgroup_vet_subtree_control_enable(cgrp, enable);
if (ret)
goto out_unlock;
cgroup_save_control(cgrp);
cgrp->subtree_control |= enable;
cgrp->subtree_control &= ~disable;
ret = cgroup_apply_control(cgrp);
cgroup_finalize_control(cgrp, ret);
if (ret)
goto out_unlock;
kernfs_activate(cgrp->kn);
out_unlock:
cgroup_kn_unlock(of->kn);
return ret ?: nbytes;
}
static int cgroup_enable_threaded(struct cgroup *cgrp)
{
struct cgroup *parent = cgroup_parent(cgrp);
struct cgroup *dom_cgrp = parent->dom_cgrp;
struct cgroup *dsct;
struct cgroup_subsys_state *d_css;
int ret;
lockdep_assert_held(&cgroup_mutex);
if (cgroup_is_threaded(cgrp))
return 0;
if (cgroup_is_populated(cgrp) ||
cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask)
return -EOPNOTSUPP;
if (!cgroup_is_valid_domain(dom_cgrp) ||
!cgroup_can_be_thread_root(dom_cgrp))
return -EOPNOTSUPP;
cgroup_save_control(cgrp);
cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp)
if (dsct == cgrp || cgroup_is_threaded(dsct))
dsct->dom_cgrp = dom_cgrp;
ret = cgroup_apply_control(cgrp);
if (!ret)
parent->nr_threaded_children++;
cgroup_finalize_control(cgrp, ret);
return ret;
}
static int cgroup_type_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
if (cgroup_is_threaded(cgrp))
seq_puts(seq, "threaded\n");
else if (!cgroup_is_valid_domain(cgrp))
seq_puts(seq, "domain invalid\n");
else if (cgroup_is_thread_root(cgrp))
seq_puts(seq, "domain threaded\n");
else
seq_puts(seq, "domain\n");
return 0;
}
static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct cgroup *cgrp;
int ret;
if (strcmp(strstrip(buf), "threaded"))
return -EINVAL;
cgrp = cgroup_kn_lock_live(of->kn, true);
if (!cgrp)
return -ENOENT;
ret = cgroup_enable_threaded(cgrp);
cgroup_kn_unlock(of->kn);
return ret ?: nbytes;
}
static int cgroup_max_descendants_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
int descendants = READ_ONCE(cgrp->max_descendants);
if (descendants == INT_MAX)
seq_puts(seq, "max\n");
else
seq_printf(seq, "%d\n", descendants);
return 0;
}
static ssize_t cgroup_max_descendants_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct cgroup *cgrp;
int descendants;
ssize_t ret;
buf = strstrip(buf);
if (!strcmp(buf, "max")) {
descendants = INT_MAX;
} else {
ret = kstrtoint(buf, 0, &descendants);
if (ret)
return ret;
}
if (descendants < 0)
return -ERANGE;
cgrp = cgroup_kn_lock_live(of->kn, false);
if (!cgrp)
return -ENOENT;
cgrp->max_descendants = descendants;
cgroup_kn_unlock(of->kn);
return nbytes;
}
static int cgroup_max_depth_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
int depth = READ_ONCE(cgrp->max_depth);
if (depth == INT_MAX)
seq_puts(seq, "max\n");
else
seq_printf(seq, "%d\n", depth);
return 0;
}
static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct cgroup *cgrp;
ssize_t ret;
int depth;
buf = strstrip(buf);
if (!strcmp(buf, "max")) {
depth = INT_MAX;
} else {
ret = kstrtoint(buf, 0, &depth);
if (ret)
return ret;
}
if (depth < 0)
return -ERANGE;
cgrp = cgroup_kn_lock_live(of->kn, false);
if (!cgrp)
return -ENOENT;
cgrp->max_depth = depth;
cgroup_kn_unlock(of->kn);
return nbytes;
}
static int cgroup_events_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
seq_printf(seq, "populated %d\n", cgroup_is_populated(cgrp));
seq_printf(seq, "frozen %d\n", test_bit(CGRP_FROZEN, &cgrp->flags));
return 0;
}
static int cgroup_stat_show(struct seq_file *seq, void *v)
{
struct cgroup *cgroup = seq_css(seq)->cgroup;
seq_printf(seq, "nr_descendants %d\n",
cgroup->nr_descendants);
seq_printf(seq, "nr_dying_descendants %d\n",
cgroup->nr_dying_descendants);
return 0;
}
#ifdef CONFIG_CGROUP_SCHED
static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
struct cgroup_subsys *ss)
{
struct cgroup_subsys_state *css;
rcu_read_lock();
css = cgroup_css(cgrp, ss);
if (css && !css_tryget_online(css))
css = NULL;
rcu_read_unlock();
return css;
}
static int cgroup_extra_stat_show(struct seq_file *seq, int ssid)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
struct cgroup_subsys *ss = cgroup_subsys[ssid];
struct cgroup_subsys_state *css;
int ret;
if (!ss->css_extra_stat_show)
return 0;
css = cgroup_tryget_css(cgrp, ss);
if (!css)
return 0;
ret = ss->css_extra_stat_show(seq, css);
css_put(css);
return ret;
}
static int cgroup_local_stat_show(struct seq_file *seq,
struct cgroup *cgrp, int ssid)
{
struct cgroup_subsys *ss = cgroup_subsys[ssid];
struct cgroup_subsys_state *css;
int ret;
if (!ss->css_local_stat_show)
return 0;
css = cgroup_tryget_css(cgrp, ss);
if (!css)
return 0;
ret = ss->css_local_stat_show(seq, css);
css_put(css);
return ret;
}
#endif
static int cpu_stat_show(struct seq_file *seq, void *v)
{
int ret = 0;
cgroup_base_stat_cputime_show(seq);
#ifdef CONFIG_CGROUP_SCHED
ret = cgroup_extra_stat_show(seq, cpu_cgrp_id);
#endif
return ret;
}
static int cpu_local_stat_show(struct seq_file *seq, void *v)
{
struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup;
int ret = 0;
#ifdef CONFIG_CGROUP_SCHED
ret = cgroup_local_stat_show(seq, cgrp, cpu_cgrp_id);
#endif
return ret;
}
#ifdef CONFIG_PSI
static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
struct psi_group *psi = cgroup_psi(cgrp);
return psi_show(seq, psi, PSI_IO);
}
static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
struct psi_group *psi = cgroup_psi(cgrp);
return psi_show(seq, psi, PSI_MEM);
}
static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
struct psi_group *psi = cgroup_psi(cgrp);
return psi_show(seq, psi, PSI_CPU);
}
static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, enum psi_res res)
{
struct cgroup_file_ctx *ctx = of->priv;
struct psi_trigger *new;
struct cgroup *cgrp;
struct psi_group *psi;
cgrp = cgroup_kn_lock_live(of->kn, false);
if (!cgrp)
return -ENODEV;
cgroup_get(cgrp);
cgroup_kn_unlock(of->kn);
if (ctx->psi.trigger) {
cgroup_put(cgrp);
return -EBUSY;
}
psi = cgroup_psi(cgrp);
new = psi_trigger_create(psi, buf, res, of->file, of);
if (IS_ERR(new)) {
cgroup_put(cgrp);
return PTR_ERR(new);
}
smp_store_release(&ctx->psi.trigger, new);
cgroup_put(cgrp);
return nbytes;
}
static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
return pressure_write(of, buf, nbytes, PSI_IO);
}
static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
return pressure_write(of, buf, nbytes, PSI_MEM);
}
static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
return pressure_write(of, buf, nbytes, PSI_CPU);
}
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
static int cgroup_irq_pressure_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
struct psi_group *psi = cgroup_psi(cgrp);
return psi_show(seq, psi, PSI_IRQ);
}
static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
return pressure_write(of, buf, nbytes, PSI_IRQ);
}
#endif
static int cgroup_pressure_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
struct psi_group *psi = cgroup_psi(cgrp);
seq_printf(seq, "%d\n", psi->enabled);
return 0;
}
static ssize_t cgroup_pressure_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
ssize_t ret;
int enable;
struct cgroup *cgrp;
struct psi_group *psi;
ret = kstrtoint(strstrip(buf), 0, &enable);
if (ret)
return ret;
if (enable < 0 || enable > 1)
return -ERANGE;
cgrp = cgroup_kn_lock_live(of->kn, false);
if (!cgrp)
return -ENOENT;
psi = cgroup_psi(cgrp);
if (psi->enabled != enable) {
int i;
for (i = 0; i < NR_PSI_RESOURCES; i++)
cgroup_file_show(&cgrp->psi_files[i], enable);
psi->enabled = enable;
if (enable)
psi_cgroup_restart(psi);
}
cgroup_kn_unlock(of->kn);
return nbytes;
}
static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
poll_table *pt)
{
struct cgroup_file_ctx *ctx = of->priv;
return psi_trigger_poll(&ctx->psi.trigger, of->file, pt);
}
static int cgroup_pressure_open(struct kernfs_open_file *of)
{
if (of->file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE))
return -EPERM;
return 0;
}
static void cgroup_pressure_release(struct kernfs_open_file *of)
{
struct cgroup_file_ctx *ctx = of->priv;
psi_trigger_destroy(ctx->psi.trigger);
}
bool cgroup_psi_enabled(void)
{
if (static_branch_likely(&psi_disabled))
return false;
return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0;
}
#else /* CONFIG_PSI */
bool cgroup_psi_enabled(void)
{
return false;
}
#endif /* CONFIG_PSI */
static int cgroup_freeze_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
seq_printf(seq, "%d\n", cgrp->freezer.freeze);
return 0;
}
static ssize_t cgroup_freeze_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct cgroup *cgrp;
ssize_t ret;
int freeze;
ret = kstrtoint(strstrip(buf), 0, &freeze);
if (ret)
return ret;
if (freeze < 0 || freeze > 1)
return -ERANGE;
cgrp = cgroup_kn_lock_live(of->kn, false);
if (!cgrp)
return -ENOENT;
cgroup_freeze(cgrp, freeze);
cgroup_kn_unlock(of->kn);
return nbytes;
}
static void __cgroup_kill(struct cgroup *cgrp)
{
struct css_task_iter it;
struct task_struct *task;
lockdep_assert_held(&cgroup_mutex);
spin_lock_irq(&css_set_lock);
set_bit(CGRP_KILL, &cgrp->flags);
spin_unlock_irq(&css_set_lock);
css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it);
while ((task = css_task_iter_next(&it))) {
if (task->flags & PF_KTHREAD)
continue;
if (__fatal_signal_pending(task))
continue;
send_sig(SIGKILL, task, 0);
}
css_task_iter_end(&it);
spin_lock_irq(&css_set_lock);
clear_bit(CGRP_KILL, &cgrp->flags);
spin_unlock_irq(&css_set_lock);
}
static void cgroup_kill(struct cgroup *cgrp)
{
struct cgroup_subsys_state *css;
struct cgroup *dsct;
lockdep_assert_held(&cgroup_mutex);
cgroup_for_each_live_descendant_pre(dsct, css, cgrp)
__cgroup_kill(dsct);
}
static ssize_t cgroup_kill_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
ssize_t ret = 0;
int kill;
struct cgroup *cgrp;
ret = kstrtoint(strstrip(buf), 0, &kill);
if (ret)
return ret;
if (kill != 1)
return -ERANGE;
cgrp = cgroup_kn_lock_live(of->kn, false);
if (!cgrp)
return -ENOENT;
if (cgroup_is_threaded(cgrp))
ret = -EOPNOTSUPP;
else
cgroup_kill(cgrp);
cgroup_kn_unlock(of->kn);
return ret ?: nbytes;
}
static int cgroup_file_open(struct kernfs_open_file *of)
{
struct cftype *cft = of_cft(of);
struct cgroup_file_ctx *ctx;
int ret;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
ctx->ns = current->nsproxy->cgroup_ns;
get_cgroup_ns(ctx->ns);
of->priv = ctx;
if (!cft->open)
return 0;
ret = cft->open(of);
if (ret) {
put_cgroup_ns(ctx->ns);
kfree(ctx);
}
return ret;
}
static void cgroup_file_release(struct kernfs_open_file *of)
{
struct cftype *cft = of_cft(of);
struct cgroup_file_ctx *ctx = of->priv;
if (cft->release)
cft->release(of);
put_cgroup_ns(ctx->ns);
kfree(ctx);
}
static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct cgroup_file_ctx *ctx = of->priv;
struct cgroup *cgrp = of->kn->parent->priv;
struct cftype *cft = of_cft(of);
struct cgroup_subsys_state *css;
int ret;
if (!nbytes)
return 0;
if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) &&
!(cft->flags & CFTYPE_NS_DELEGATABLE) &&
ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp)
return -EPERM;
if (cft->write)
return cft->write(of, buf, nbytes, off);
rcu_read_lock();
css = cgroup_css(cgrp, cft->ss);
rcu_read_unlock();
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 {
ret = -EINVAL;
}
return ret ?: nbytes;
}
static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt)
{
struct cftype *cft = of_cft(of);
if (cft->poll)
return cft->poll(of, pt);
return kernfs_generic_poll(of, pt);
}
static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
{
return seq_cft(seq)->seq_start(seq, ppos);
}
static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos)
{
return seq_cft(seq)->seq_next(seq, v, ppos);
}
static void cgroup_seqfile_stop(struct seq_file *seq, void *v)
{
if (seq_cft(seq)->seq_stop)
seq_cft(seq)->seq_stop(seq, v);
}
static int cgroup_seqfile_show(struct seq_file *m, void *arg)
{
struct cftype *cft = seq_cft(m);
struct cgroup_subsys_state *css = seq_css(m);
if (cft->seq_show)
return cft->seq_show(m, arg);
if (cft->read_u64)
seq_printf(m, "%llu\n", cft->read_u64(css, cft));
else if (cft->read_s64)
seq_printf(m, "%lld\n", cft->read_s64(css, cft));
else
return -EINVAL;
return 0;
}
static struct kernfs_ops cgroup_kf_single_ops = {
.atomic_write_len = PAGE_SIZE,
.open = cgroup_file_open,
.release = cgroup_file_release,
.write = cgroup_file_write,
.poll = cgroup_file_poll,
.seq_show = cgroup_seqfile_show,
};
static struct kernfs_ops cgroup_kf_ops = {
.atomic_write_len = PAGE_SIZE,
.open = cgroup_file_open,
.release = cgroup_file_release,
.write = cgroup_file_write,
.poll = cgroup_file_poll,
.seq_start = cgroup_seqfile_start,
.seq_next = cgroup_seqfile_next,
.seq_stop = cgroup_seqfile_stop,
.seq_show = cgroup_seqfile_show,
};
static int cgroup_kn_set_ugid(struct kernfs_node *kn)
{
struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
.ia_uid = current_fsuid(),
.ia_gid = current_fsgid(), };
if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
return 0;
return kernfs_setattr(kn, &iattr);
}
static void cgroup_file_notify_timer(struct timer_list *timer)
{
cgroup_file_notify(container_of(timer, struct cgroup_file,
notify_timer));
}
static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
struct cftype *cft)
{
char name[CGROUP_FILE_NAME_MAX];
struct kernfs_node *kn;
struct lock_class_key *key = NULL;
int ret;
#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),
GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
0, cft->kf_ops, cft,
NULL, key);
if (IS_ERR(kn))
return PTR_ERR(kn);
ret = cgroup_kn_set_ugid(kn);
if (ret) {
kernfs_remove(kn);
return ret;
}
if (cft->file_offset) {
struct cgroup_file *cfile = (void *)css + cft->file_offset;
timer_setup(&cfile->notify_timer, cgroup_file_notify_timer, 0);
spin_lock_irq(&cgroup_file_kn_lock);
cfile->kn = kn;
spin_unlock_irq(&cgroup_file_kn_lock);
}
return 0;
}
static int cgroup_addrm_files(struct cgroup_subsys_state *css,
struct cgroup *cgrp, struct cftype cfts[],
bool is_add)
{
struct cftype *cft, *cft_end = NULL;
int ret = 0;
lockdep_assert_held(&cgroup_mutex);
restart:
for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) {
if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp))
continue;
if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp))
continue;
if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp))
continue;
if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp))
continue;
if ((cft->flags & CFTYPE_DEBUG) && !cgroup_debug)
continue;
if (is_add) {
ret = cgroup_add_file(css, cgrp, cft);
if (ret) {
pr_warn("%s: failed to add %s, err=%d\n",
__func__, cft->name, ret);
cft_end = cft;
is_add = false;
goto restart;
}
} else {
cgroup_rm_file(cgrp, cft);
}
}
return ret;
}
static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add)
{
struct cgroup_subsys *ss = cfts[0].ss;
struct cgroup *root = &ss->root->cgrp;
struct cgroup_subsys_state *css;
int ret = 0;
lockdep_assert_held(&cgroup_mutex);
css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
struct cgroup *cgrp = css->cgroup;
if (!(css->flags & CSS_VISIBLE))
continue;
ret = cgroup_addrm_files(css, cgrp, cfts, is_add);
if (ret)
break;
}
if (is_add && !ret)
kernfs_activate(root->kn);
return ret;
}
static void cgroup_exit_cftypes(struct cftype *cfts)
{
struct cftype *cft;
for (cft = cfts; cft->name[0] != '\0'; cft++) {
if (cft->max_write_len && cft->max_write_len != PAGE_SIZE)
kfree(cft->kf_ops);
cft->kf_ops = NULL;
cft->ss = NULL;
cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL |
__CFTYPE_ADDED);
}
}
static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
struct cftype *cft;
int ret = 0;
for (cft = cfts; cft->name[0] != '\0'; cft++) {
struct kernfs_ops *kf_ops;
WARN_ON(cft->ss || cft->kf_ops);
if (cft->flags & __CFTYPE_ADDED) {
ret = -EBUSY;
break;
}
if (cft->seq_start)
kf_ops = &cgroup_kf_ops;
else
kf_ops = &cgroup_kf_single_ops;
if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) {
kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL);
if (!kf_ops) {
ret = -ENOMEM;
break;
}
kf_ops->atomic_write_len = cft->max_write_len;
}
cft->kf_ops = kf_ops;
cft->ss = ss;
cft->flags |= __CFTYPE_ADDED;
}
if (ret)
cgroup_exit_cftypes(cfts);
return ret;
}
static void cgroup_rm_cftypes_locked(struct cftype *cfts)
{
lockdep_assert_held(&cgroup_mutex);
list_del(&cfts->node);
cgroup_apply_cftypes(cfts, false);
cgroup_exit_cftypes(cfts);
}
int cgroup_rm_cftypes(struct cftype *cfts)
{
if (!cfts || cfts[0].name[0] == '\0')
return 0;
if (!(cfts[0].flags & __CFTYPE_ADDED))
return -ENOENT;
cgroup_lock();
cgroup_rm_cftypes_locked(cfts);
cgroup_unlock();
return 0;
}
static int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
int ret;
if (!cgroup_ssid_enabled(ss->id))
return 0;
if (!cfts || cfts[0].name[0] == '\0')
return 0;
ret = cgroup_init_cftypes(ss, cfts);
if (ret)
return ret;
cgroup_lock();
list_add_tail(&cfts->node, &ss->cfts);
ret = cgroup_apply_cftypes(cfts, true);
if (ret)
cgroup_rm_cftypes_locked(cfts);
cgroup_unlock();
return ret;
}
int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
struct cftype *cft;
for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
cft->flags |= __CFTYPE_ONLY_ON_DFL;
return cgroup_add_cftypes(ss, cfts);
}
int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
struct cftype *cft;
for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
cft->flags |= __CFTYPE_NOT_ON_DFL;
return cgroup_add_cftypes(ss, cfts);
}
void cgroup_file_notify(struct cgroup_file *cfile)
{
unsigned long flags;
spin_lock_irqsave(&cgroup_file_kn_lock, flags);
if (cfile->kn) {
unsigned long last = cfile->notified_at;
unsigned long next = last + CGROUP_FILE_NOTIFY_MIN_INTV;
if (time_in_range(jiffies, last, next)) {
timer_reduce(&cfile->notify_timer, next);
} else {
kernfs_notify(cfile->kn);
cfile->notified_at = jiffies;
}
}
spin_unlock_irqrestore(&cgroup_file_kn_lock, flags);
}
void cgroup_file_show(struct cgroup_file *cfile, bool show)
{
struct kernfs_node *kn;
spin_lock_irq(&cgroup_file_kn_lock);
kn = cfile->kn;
kernfs_get(kn);
spin_unlock_irq(&cgroup_file_kn_lock);
if (kn)
kernfs_show(kn, show);
kernfs_put(kn);
}
struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
struct cgroup_subsys_state *parent)
{
struct cgroup_subsys_state *next;
cgroup_assert_mutex_or_rcu_locked();
if (!pos) {
next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling);
} else if (likely(!(pos->flags & CSS_RELEASED))) {
next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling);
} else {
list_for_each_entry_rcu(next, &parent->children, sibling,
lockdep_is_held(&cgroup_mutex))
if (next->serial_nr > pos->serial_nr)
break;
}
if (&next->sibling != &parent->children)
return next;
return NULL;
}
struct cgroup_subsys_state *
css_next_descendant_pre(struct cgroup_subsys_state *pos,
struct cgroup_subsys_state *root)
{
struct cgroup_subsys_state *next;
cgroup_assert_mutex_or_rcu_locked();
if (!pos)
return root;
next = css_next_child(NULL, pos);
if (next)
return next;
while (pos != root) {
next = css_next_child(pos, pos->parent);
if (next)
return next;
pos = pos->parent;
}
return NULL;
}
EXPORT_SYMBOL_GPL(css_next_descendant_pre);
struct cgroup_subsys_state *
css_rightmost_descendant(struct cgroup_subsys_state *pos)
{
struct cgroup_subsys_state *last, *tmp;
cgroup_assert_mutex_or_rcu_locked();
do {
last = pos;
pos = NULL;
css_for_each_child(tmp, last)
pos = tmp;
} while (pos);
return last;
}
static struct cgroup_subsys_state *
css_leftmost_descendant(struct cgroup_subsys_state *pos)
{
struct cgroup_subsys_state *last;
do {
last = pos;
pos = css_next_child(NULL, pos);
} while (pos);
return last;
}
struct cgroup_subsys_state *
css_next_descendant_post(struct cgroup_subsys_state *pos,
struct cgroup_subsys_state *root)
{
struct cgroup_subsys_state *next;
cgroup_assert_mutex_or_rcu_locked();
if (!pos)
return css_leftmost_descendant(root);
if (pos == root)
return NULL;
next = css_next_child(pos, pos->parent);
if (next)
return css_leftmost_descendant(next);
return pos->parent;
}
bool css_has_online_children(struct cgroup_subsys_state *css)
{
struct cgroup_subsys_state *child;
bool ret = false;
rcu_read_lock();
css_for_each_child(child, css) {
if (child->flags & CSS_ONLINE) {
ret = true;
break;
}
}
rcu_read_unlock();
return ret;
}
static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it)
{
struct list_head *l;
struct cgrp_cset_link *link;
struct css_set *cset;
lockdep_assert_held(&css_set_lock);
if (it->tcset_pos) {
l = it->tcset_pos->next;
if (l != it->tcset_head) {
it->tcset_pos = l;
return container_of(l, struct css_set,
threaded_csets_node);
}
it->tcset_pos = NULL;
}
l = it->cset_pos;
l = l->next;
if (l == it->cset_head) {
it->cset_pos = NULL;
return NULL;
}
if (it->ss) {
cset = container_of(l, struct css_set, e_cset_node[it->ss->id]);
} else {
link = list_entry(l, struct cgrp_cset_link, cset_link);
cset = link->cset;
}
it->cset_pos = l;
if (it->flags & CSS_TASK_ITER_THREADED) {
if (it->cur_dcset)
put_css_set_locked(it->cur_dcset);
it->cur_dcset = cset;
get_css_set(cset);
it->tcset_head = &cset->threaded_csets;
it->tcset_pos = &cset->threaded_csets;
}
return cset;
}
static void css_task_iter_advance_css_set(struct css_task_iter *it)
{
struct css_set *cset;
lockdep_assert_held(&css_set_lock);
while ((cset = css_task_iter_next_css_set(it))) {
if (!list_empty(&cset->tasks)) {
it->cur_tasks_head = &cset->tasks;
break;
} else if (!list_empty(&cset->mg_tasks)) {
it->cur_tasks_head = &cset->mg_tasks;
break;
} else if (!list_empty(&cset->dying_tasks)) {
it->cur_tasks_head = &cset->dying_tasks;
break;
}
}
if (!cset) {
it->task_pos = NULL;
return;
}
it->task_pos = it->cur_tasks_head->next;
if (it->cur_cset) {
list_del(&it->iters_node);
put_css_set_locked(it->cur_cset);
}
get_css_set(cset);
it->cur_cset = cset;
list_add(&it->iters_node, &cset->task_iters);
}
static void css_task_iter_skip(struct css_task_iter *it,
struct task_struct *task)
{
lockdep_assert_held(&css_set_lock);
if (it->task_pos == &task->cg_list) {
it->task_pos = it->task_pos->next;
it->flags |= CSS_TASK_ITER_SKIPPED;
}
}
static void css_task_iter_advance(struct css_task_iter *it)
{
struct task_struct *task;
lockdep_assert_held(&css_set_lock);
repeat:
if (it->task_pos) {
if (it->flags & CSS_TASK_ITER_SKIPPED)
it->flags &= ~CSS_TASK_ITER_SKIPPED;
else
it->task_pos = it->task_pos->next;
if (it->task_pos == &it->cur_cset->tasks) {
it->cur_tasks_head = &it->cur_cset->mg_tasks;
it->task_pos = it->cur_tasks_head->next;
}
if (it->task_pos == &it->cur_cset->mg_tasks) {
it->cur_tasks_head = &it->cur_cset->dying_tasks;
it->task_pos = it->cur_tasks_head->next;
}
if (it->task_pos == &it->cur_cset->dying_tasks)
css_task_iter_advance_css_set(it);
} else {
css_task_iter_advance_css_set(it);
}
if (!it->task_pos)
return;
task = list_entry(it->task_pos, struct task_struct, cg_list);
if (it->flags & CSS_TASK_ITER_PROCS) {
if (!thread_group_leader(task))
goto repeat;
if (it->cur_tasks_head == &it->cur_cset->dying_tasks &&
!atomic_read(&task->signal->live))
goto repeat;
} else {
if (it->cur_tasks_head == &it->cur_cset->dying_tasks)
goto repeat;
}
}
void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
struct css_task_iter *it)
{
memset(it, 0, sizeof(*it));
spin_lock_irq(&css_set_lock);
it->ss = css->ss;
it->flags = flags;
if (CGROUP_HAS_SUBSYS_CONFIG && it->ss)
it->cset_pos = &css->cgroup->e_csets[css->ss->id];
else
it->cset_pos = &css->cgroup->cset_links;
it->cset_head = it->cset_pos;
css_task_iter_advance(it);
spin_unlock_irq(&css_set_lock);
}
struct task_struct *css_task_iter_next(struct css_task_iter *it)
{
if (it->cur_task) {
put_task_struct(it->cur_task);
it->cur_task = NULL;
}
spin_lock_irq(&css_set_lock);
if (it->flags & CSS_TASK_ITER_SKIPPED)
css_task_iter_advance(it);
if (it->task_pos) {
it->cur_task = list_entry(it->task_pos, struct task_struct,
cg_list);
get_task_struct(it->cur_task);
css_task_iter_advance(it);
}
spin_unlock_irq(&css_set_lock);
return it->cur_task;
}
void css_task_iter_end(struct css_task_iter *it)
{
if (it->cur_cset) {
spin_lock_irq(&css_set_lock);
list_del(&it->iters_node);
put_css_set_locked(it->cur_cset);
spin_unlock_irq(&css_set_lock);
}
if (it->cur_dcset)
put_css_set(it->cur_dcset);
if (it->cur_task)
put_task_struct(it->cur_task);
}
static void cgroup_procs_release(struct kernfs_open_file *of)
{
struct cgroup_file_ctx *ctx = of->priv;
if (ctx->procs.started)
css_task_iter_end(&ctx->procs.iter);
}
static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos)
{
struct kernfs_open_file *of = s->private;
struct cgroup_file_ctx *ctx = of->priv;
if (pos)
(*pos)++;
return css_task_iter_next(&ctx->procs.iter);
}
static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
unsigned int iter_flags)
{
struct kernfs_open_file *of = s->private;
struct cgroup *cgrp = seq_css(s)->cgroup;
struct cgroup_file_ctx *ctx = of->priv;
struct css_task_iter *it = &ctx->procs.iter;
if (!ctx->procs.started) {
if (WARN_ON_ONCE((*pos)))
return ERR_PTR(-EINVAL);
css_task_iter_start(&cgrp->self, iter_flags, it);
ctx->procs.started = true;
} else if (!(*pos)) {
css_task_iter_end(it);
css_task_iter_start(&cgrp->self, iter_flags, it);
} else
return it->cur_task;
return cgroup_procs_next(s, NULL, NULL);
}
static void *cgroup_procs_start(struct seq_file *s, loff_t *pos)
{
struct cgroup *cgrp = seq_css(s)->cgroup;
if (cgroup_is_threaded(cgrp))
return ERR_PTR(-EOPNOTSUPP);
return __cgroup_procs_start(s, pos, CSS_TASK_ITER_PROCS |
CSS_TASK_ITER_THREADED);
}
static int cgroup_procs_show(struct seq_file *s, void *v)
{
seq_printf(s, "%d\n", task_pid_vnr(v));
return 0;
}
static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb)
{
int ret;
struct inode *inode;
lockdep_assert_held(&cgroup_mutex);
inode = kernfs_get_inode(sb, cgrp->procs_file.kn);
if (!inode)
return -ENOMEM;
ret = inode_permission(&nop_mnt_idmap, inode, MAY_WRITE);
iput(inode);
return ret;
}
static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
struct cgroup *dst_cgrp,
struct super_block *sb,
struct cgroup_namespace *ns)
{
struct cgroup *com_cgrp = src_cgrp;
int ret;
lockdep_assert_held(&cgroup_mutex);
while (!cgroup_is_descendant(dst_cgrp, com_cgrp))
com_cgrp = cgroup_parent(com_cgrp);
ret = cgroup_may_write(com_cgrp, sb);
if (ret)
return ret;
if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) &&
(!cgroup_is_descendant(src_cgrp, ns->root_cset->dfl_cgrp) ||
!cgroup_is_descendant(dst_cgrp, ns->root_cset->dfl_cgrp)))
return -ENOENT;
return 0;
}
static int cgroup_attach_permissions(struct cgroup *src_cgrp,
struct cgroup *dst_cgrp,
struct super_block *sb, bool threadgroup,
struct cgroup_namespace *ns)
{
int ret = 0;
ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns);
if (ret)
return ret;
ret = cgroup_migrate_vet_dst(dst_cgrp);
if (ret)
return ret;
if (!threadgroup && (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp))
ret = -EOPNOTSUPP;
return ret;
}
static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
bool threadgroup)
{
struct cgroup_file_ctx *ctx = of->priv;
struct cgroup *src_cgrp, *dst_cgrp;
struct task_struct *task;
const struct cred *saved_cred;
ssize_t ret;
bool threadgroup_locked;
dst_cgrp = cgroup_kn_lock_live(of->kn, false);
if (!dst_cgrp)
return -ENODEV;
task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked);
ret = PTR_ERR_OR_ZERO(task);
if (ret)
goto out_unlock;
spin_lock_irq(&css_set_lock);
src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
spin_unlock_irq(&css_set_lock);
saved_cred = override_creds(of->file->f_cred);
ret = cgroup_attach_permissions(src_cgrp, dst_cgrp,
of->file->f_path.dentry->d_sb,
threadgroup, ctx->ns);
revert_creds(saved_cred);
if (ret)
goto out_finish;
ret = cgroup_attach_task(dst_cgrp, task, threadgroup);
out_finish:
cgroup_procs_write_finish(task, threadgroup_locked);
out_unlock:
cgroup_kn_unlock(of->kn);
return ret;
}
static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
return __cgroup_procs_write(of, buf, true) ?: nbytes;
}
static void *cgroup_threads_start(struct seq_file *s, loff_t *pos)
{
return __cgroup_procs_start(s, pos, 0);
}
static ssize_t cgroup_threads_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
return __cgroup_procs_write(of, buf, false) ?: nbytes;
}
static struct cftype cgroup_base_files[] = {
{
.name = "cgroup.type",
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = cgroup_type_show,
.write = cgroup_type_write,
},
{
.name = "cgroup.procs",
.flags = CFTYPE_NS_DELEGATABLE,
.file_offset = offsetof(struct cgroup, procs_file),
.release = cgroup_procs_release,
.seq_start = cgroup_procs_start,
.seq_next = cgroup_procs_next,
.seq_show = cgroup_procs_show,
.write = cgroup_procs_write,
},
{
.name = "cgroup.threads",
.flags = CFTYPE_NS_DELEGATABLE,
.release = cgroup_procs_release,
.seq_start = cgroup_threads_start,
.seq_next = cgroup_procs_next,
.seq_show = cgroup_procs_show,
.write = cgroup_threads_write,
},
{
.name = "cgroup.controllers",
.seq_show = cgroup_controllers_show,
},
{
.name = "cgroup.subtree_control",
.flags = CFTYPE_NS_DELEGATABLE,
.seq_show = cgroup_subtree_control_show,
.write = cgroup_subtree_control_write,
},
{
.name = "cgroup.events",
.flags = CFTYPE_NOT_ON_ROOT,
.file_offset = offsetof(struct cgroup, events_file),
.seq_show = cgroup_events_show,
},
{
.name = "cgroup.max.descendants",
.seq_show = cgroup_max_descendants_show,
.write = cgroup_max_descendants_write,
},
{
.name = "cgroup.max.depth",
.seq_show = cgroup_max_depth_show,
.write = cgroup_max_depth_write,
},
{
.name = "cgroup.stat",
.seq_show = cgroup_stat_show,
},
{
.name = "cgroup.freeze",
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = cgroup_freeze_show,
.write = cgroup_freeze_write,
},
{
.name = "cgroup.kill",
.flags = CFTYPE_NOT_ON_ROOT,
.write = cgroup_kill_write,
},
{
.name = "cpu.stat",
.seq_show = cpu_stat_show,
},
{
.name = "cpu.stat.local",
.seq_show = cpu_local_stat_show,
},
{ }
};
static struct cftype cgroup_psi_files[] = {
#ifdef CONFIG_PSI
{
.name = "io.pressure",
.file_offset = offsetof(struct cgroup, psi_files[PSI_IO]),
.open = cgroup_pressure_open,
.seq_show = cgroup_io_pressure_show,
.write = cgroup_io_pressure_write,
.poll = cgroup_pressure_poll,
.release = cgroup_pressure_release,
},
{
.name = "memory.pressure",
.file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]),
.open = cgroup_pressure_open,
.seq_show = cgroup_memory_pressure_show,
.write = cgroup_memory_pressure_write,
.poll = cgroup_pressure_poll,
.release = cgroup_pressure_release,
},
{
.name = "cpu.pressure",
.file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]),
.open = cgroup_pressure_open,
.seq_show = cgroup_cpu_pressure_show,
.write = cgroup_cpu_pressure_write,
.poll = cgroup_pressure_poll,
.release = cgroup_pressure_release,
},
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
{
.name = "irq.pressure",
.file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]),
.open = cgroup_pressure_open,
.seq_show = cgroup_irq_pressure_show,
.write = cgroup_irq_pressure_write,
.poll = cgroup_pressure_poll,
.release = cgroup_pressure_release,
},
#endif
{
.name = "cgroup.pressure",
.seq_show = cgroup_pressure_show,
.write = cgroup_pressure_write,
},
#endif /* CONFIG_PSI */
{ }
};
static void css_free_rwork_fn(struct work_struct *work)
{
struct cgroup_subsys_state *css = container_of(to_rcu_work(work),
struct cgroup_subsys_state, destroy_rwork);
struct cgroup_subsys *ss = css->ss;
struct cgroup *cgrp = css->cgroup;
percpu_ref_exit(&css->refcnt);
if (ss) {
struct cgroup_subsys_state *parent = css->parent;
int id = css->id;
ss->css_free(css);
cgroup_idr_remove(&ss->css_idr, id);
cgroup_put(cgrp);
if (parent)
css_put(parent);
} else {
atomic_dec(&cgrp->root->nr_cgrps);
cgroup1_pidlist_destroy_all(cgrp);
cancel_work_sync(&cgrp->release_agent_work);
bpf_cgrp_storage_free(cgrp);
if (cgroup_parent(cgrp)) {
cgroup_put(cgroup_parent(cgrp));
kernfs_put(cgrp->kn);
psi_cgroup_free(cgrp);
cgroup_rstat_exit(cgrp);
kfree(cgrp);
} else {
cgroup_destroy_root(cgrp->root);
}
}
}
static void css_release_work_fn(struct work_struct *work)
{
struct cgroup_subsys_state *css =
container_of(work, struct cgroup_subsys_state, destroy_work);
struct cgroup_subsys *ss = css->ss;
struct cgroup *cgrp = css->cgroup;
cgroup_lock();
css->flags |= CSS_RELEASED;
list_del_rcu(&css->sibling);
if (ss) {
if (!list_empty(&css->rstat_css_node)) {
cgroup_rstat_flush(cgrp);
list_del_rcu(&css->rstat_css_node);
}
cgroup_idr_replace(&ss->css_idr, NULL, css->id);
if (ss->css_released)
ss->css_released(css);
} else {
struct cgroup *tcgrp;
TRACE_CGROUP_PATH(release, cgrp);
cgroup_rstat_flush(cgrp);
spin_lock_irq(&css_set_lock);
for (tcgrp = cgroup_parent(cgrp); tcgrp;
tcgrp = cgroup_parent(tcgrp))
tcgrp->nr_dying_descendants--;
spin_unlock_irq(&css_set_lock);
if (cgrp->kn)
RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv,
NULL);
}
cgroup_unlock();
INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
}
static void css_release(struct percpu_ref *ref)
{
struct cgroup_subsys_state *css =
container_of(ref, struct cgroup_subsys_state, refcnt);
INIT_WORK(&css->destroy_work, css_release_work_fn);
queue_work(cgroup_destroy_wq, &css->destroy_work);
}
static void init_and_link_css(struct cgroup_subsys_state *css,
struct cgroup_subsys *ss, struct cgroup *cgrp)
{
lockdep_assert_held(&cgroup_mutex);
cgroup_get_live(cgrp);
memset(css, 0, sizeof(*css));
css->cgroup = cgrp;
css->ss = ss;
css->id = -1;
INIT_LIST_HEAD(&css->sibling);
INIT_LIST_HEAD(&css->children);
INIT_LIST_HEAD(&css->rstat_css_node);
css->serial_nr = css_serial_nr_next++;
atomic_set(&css->online_cnt, 0);
if (cgroup_parent(cgrp)) {
css->parent = cgroup_css(cgroup_parent(cgrp), ss);
css_get(css->parent);
}
if (ss->css_rstat_flush)
list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list);
BUG_ON(cgroup_css(cgrp, ss));
}
static int online_css(struct cgroup_subsys_state *css)
{
struct cgroup_subsys *ss = css->ss;
int ret = 0;
lockdep_assert_held(&cgroup_mutex);
if (ss->css_online)
ret = ss->css_online(css);
if (!ret) {
css->flags |= CSS_ONLINE;
rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
atomic_inc(&css->online_cnt);
if (css->parent)
atomic_inc(&css->parent->online_cnt);
}
return ret;
}
static void offline_css(struct cgroup_subsys_state *css)
{
struct cgroup_subsys *ss = css->ss;
lockdep_assert_held(&cgroup_mutex);
if (!(css->flags & CSS_ONLINE))
return;
if (ss->css_offline)
ss->css_offline(css);
css->flags &= ~CSS_ONLINE;
RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL);
wake_up_all(&css->cgroup->offline_waitq);
}
static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
struct cgroup_subsys *ss)
{
struct cgroup *parent = cgroup_parent(cgrp);
struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss);
struct cgroup_subsys_state *css;
int err;
lockdep_assert_held(&cgroup_mutex);
css = ss->css_alloc(parent_css);
if (!css)
css = ERR_PTR(-ENOMEM);
if (IS_ERR(css))
return css;
init_and_link_css(css, ss, cgrp);
err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL);
if (err)
goto err_free_css;
err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL);
if (err < 0)
goto err_free_css;
css->id = err;
list_add_tail_rcu(&css->sibling, &parent_css->children);
cgroup_idr_replace(&ss->css_idr, css, css->id);
err = online_css(css);
if (err)
goto err_list_del;
return css;
err_list_del:
list_del_rcu(&css->sibling);
err_free_css:
list_del_rcu(&css->rstat_css_node);
INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
return ERR_PTR(err);
}
static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
umode_t mode)
{
struct cgroup_root *root = parent->root;
struct cgroup *cgrp, *tcgrp;
struct kernfs_node *kn;
int level = parent->level + 1;
int ret;
cgrp = kzalloc(struct_size(cgrp, ancestors, (level + 1)), GFP_KERNEL);
if (!cgrp)
return ERR_PTR(-ENOMEM);
ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL);
if (ret)
goto out_free_cgrp;
ret = cgroup_rstat_init(cgrp);
if (ret)
goto out_cancel_ref;
kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
if (IS_ERR(kn)) {
ret = PTR_ERR(kn);
goto out_stat_exit;
}
cgrp->kn = kn;
init_cgroup_housekeeping(cgrp);
cgrp->self.parent = &parent->self;
cgrp->root = root;
cgrp->level = level;
ret = psi_cgroup_alloc(cgrp);
if (ret)
goto out_kernfs_remove;
ret = cgroup_bpf_inherit(cgrp);
if (ret)
goto out_psi_free;
cgrp->freezer.e_freeze = parent->freezer.e_freeze;
if (cgrp->freezer.e_freeze) {
set_bit(CGRP_FREEZE, &cgrp->flags);
set_bit(CGRP_FROZEN, &cgrp->flags);
}
spin_lock_irq(&css_set_lock);
for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
cgrp->ancestors[tcgrp->level] = tcgrp;
if (tcgrp != cgrp) {
tcgrp->nr_descendants++;
if (cgrp->freezer.e_freeze)
tcgrp->freezer.nr_frozen_descendants++;
}
}
spin_unlock_irq(&css_set_lock);
if (notify_on_release(parent))
set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
cgrp->self.serial_nr = css_serial_nr_next++;
list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children);
atomic_inc(&root->nr_cgrps);
cgroup_get_live(parent);
if (!cgroup_on_dfl(cgrp))
cgrp->subtree_control = cgroup_control(cgrp);
cgroup_propagate_control(cgrp);
return cgrp;
out_psi_free:
psi_cgroup_free(cgrp);
out_kernfs_remove:
kernfs_remove(cgrp->kn);
out_stat_exit:
cgroup_rstat_exit(cgrp);
out_cancel_ref:
percpu_ref_exit(&cgrp->self.refcnt);
out_free_cgrp:
kfree(cgrp);
return ERR_PTR(ret);
}
static bool cgroup_check_hierarchy_limits(struct cgroup *parent)
{
struct cgroup *cgroup;
int ret = false;
int level = 1;
lockdep_assert_held(&cgroup_mutex);
for (cgroup = parent; cgroup; cgroup = cgroup_parent(cgroup)) {
if (cgroup->nr_descendants >= cgroup->max_descendants)
goto fail;
if (level > cgroup->max_depth)
goto fail;
level++;
}
ret = true;
fail:
return ret;
}
int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
{
struct cgroup *parent, *cgrp;
int ret;
if (strchr(name, '\n'))
return -EINVAL;
parent = cgroup_kn_lock_live(parent_kn, false);
if (!parent)
return -ENODEV;
if (!cgroup_check_hierarchy_limits(parent)) {
ret = -EAGAIN;
goto out_unlock;
}
cgrp = cgroup_create(parent, name, mode);
if (IS_ERR(cgrp)) {
ret = PTR_ERR(cgrp);
goto out_unlock;
}
kernfs_get(cgrp->kn);
ret = cgroup_kn_set_ugid(cgrp->kn);
if (ret)
goto out_destroy;
ret = css_populate_dir(&cgrp->self);
if (ret)
goto out_destroy;
ret = cgroup_apply_control_enable(cgrp);
if (ret)
goto out_destroy;
TRACE_CGROUP_PATH(mkdir, cgrp);
kernfs_activate(cgrp->kn);
ret = 0;
goto out_unlock;
out_destroy:
cgroup_destroy_locked(cgrp);
out_unlock:
cgroup_kn_unlock(parent_kn);
return ret;
}
static void css_killed_work_fn(struct work_struct *work)
{
struct cgroup_subsys_state *css =
container_of(work, struct cgroup_subsys_state, destroy_work);
cgroup_lock();
do {
offline_css(css);
css_put(css);
css = css->parent;
} while (css && atomic_dec_and_test(&css->online_cnt));
cgroup_unlock();
}
static void css_killed_ref_fn(struct percpu_ref *ref)
{
struct cgroup_subsys_state *css =
container_of(ref, struct cgroup_subsys_state, refcnt);
if (atomic_dec_and_test(&css->online_cnt)) {
INIT_WORK(&css->destroy_work, css_killed_work_fn);
queue_work(cgroup_destroy_wq, &css->destroy_work);
}
}
static void kill_css(struct cgroup_subsys_state *css)
{
lockdep_assert_held(&cgroup_mutex);
if (css->flags & CSS_DYING)
return;
css->flags |= CSS_DYING;
css_clear_dir(css);
css_get(css);
percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn);
}
static int cgroup_destroy_locked(struct cgroup *cgrp)
__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
{
struct cgroup *tcgrp, *parent = cgroup_parent(cgrp);
struct cgroup_subsys_state *css;
struct cgrp_cset_link *link;
int ssid;
lockdep_assert_held(&cgroup_mutex);
if (cgroup_is_populated(cgrp))
return -EBUSY;
if (css_has_online_children(&cgrp->self))
return -EBUSY;
cgrp->self.flags &= ~CSS_ONLINE;
spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &cgrp->cset_links, cset_link)
link->cset->dead = true;
spin_unlock_irq(&css_set_lock);
for_each_css(css, ssid, cgrp)
kill_css(css);
css_clear_dir(&cgrp->self);
kernfs_remove(cgrp->kn);
if (cgroup_is_threaded(cgrp))
parent->nr_threaded_children--;
spin_lock_irq(&css_set_lock);
for (tcgrp = parent; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
tcgrp->nr_descendants--;
tcgrp->nr_dying_descendants++;
if (test_bit(CGRP_FROZEN, &cgrp->flags))
tcgrp->freezer.nr_frozen_descendants--;
}
spin_unlock_irq(&css_set_lock);
cgroup1_check_for_release(parent);
cgroup_bpf_offline(cgrp);
percpu_ref_kill(&cgrp->self.refcnt);
return 0;
};
int cgroup_rmdir(struct kernfs_node *kn)
{
struct cgroup *cgrp;
int ret = 0;
cgrp = cgroup_kn_lock_live(kn, false);
if (!cgrp)
return 0;
ret = cgroup_destroy_locked(cgrp);
if (!ret)
TRACE_CGROUP_PATH(rmdir, cgrp);
cgroup_kn_unlock(kn);
return ret;
}
static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
.show_options = cgroup_show_options,
.mkdir = cgroup_mkdir,
.rmdir = cgroup_rmdir,
.show_path = cgroup_show_path,
};
static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
{
struct cgroup_subsys_state *css;
pr_debug("Initializing cgroup subsys %s\n", ss->name);
cgroup_lock();
idr_init(&ss->css_idr);
INIT_LIST_HEAD(&ss->cfts);
ss->root = &cgrp_dfl_root;
css = ss->css_alloc(NULL);
BUG_ON(IS_ERR(css));
init_and_link_css(css, ss, &cgrp_dfl_root.cgrp);
css->flags |= CSS_NO_REF;
if (early) {
css->id = 1;
} else {
css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL);
BUG_ON(css->id < 0);
}
init_css_set.subsys[ss->id] = css;
have_fork_callback |= (bool)ss->fork << ss->id;
have_exit_callback |= (bool)ss->exit << ss->id;
have_release_callback |= (bool)ss->release << ss->id;
have_canfork_callback |= (bool)ss->can_fork << ss->id;
BUG_ON(!list_empty(&init_task.tasks));
BUG_ON(online_css(css));
cgroup_unlock();
}
int __init cgroup_init_early(void)
{
static struct cgroup_fs_context __initdata ctx;
struct cgroup_subsys *ss;
int i;
ctx.root = &cgrp_dfl_root;
init_cgroup_root(&ctx);
cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF;
RCU_INIT_POINTER(init_task.cgroups, &init_css_set);
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 id:name=%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->legacy_name)
ss->legacy_name = cgroup_subsys_name[i];
if (ss->early_init)
cgroup_init_subsys(ss, true);
}
return 0;
}
int __init cgroup_init(void)
{
struct cgroup_subsys *ss;
int ssid;
BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16);
BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files));
BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files));
cgroup_rstat_boot();
get_user_ns(init_cgroup_ns.user_ns);
cgroup_lock();
hash_add(css_set_table, &init_css_set.hlist,
css_set_hash(init_css_set.subsys));
BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
cgroup_unlock();
for_each_subsys(ss, ssid) {
if (ss->early_init) {
struct cgroup_subsys_state *css =
init_css_set.subsys[ss->id];
css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2,
GFP_KERNEL);
BUG_ON(css->id < 0);
} else {
cgroup_init_subsys(ss, false);
}
list_add_tail(&init_css_set.e_cset_node[ssid],
&cgrp_dfl_root.cgrp.e_csets[ssid]);
if (!cgroup_ssid_enabled(ssid))
continue;
if (cgroup1_ssid_disabled(ssid))
pr_info("Disabling %s control group subsystem in v1 mounts\n",
ss->name);
cgrp_dfl_root.subsys_mask |= 1 << ss->id;
WARN_ON(ss->implicit_on_dfl && !ss->threaded);
if (ss->implicit_on_dfl)
cgrp_dfl_implicit_ss_mask |= 1 << ss->id;
else if (!ss->dfl_cftypes)
cgrp_dfl_inhibit_ss_mask |= 1 << ss->id;
if (ss->threaded)
cgrp_dfl_threaded_ss_mask |= 1 << ss->id;
if (ss->dfl_cftypes == ss->legacy_cftypes) {
WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes));
} else {
WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes));
WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes));
}
if (ss->bind)
ss->bind(init_css_set.subsys[ssid]);
cgroup_lock();
css_populate_dir(init_css_set.subsys[ssid]);
cgroup_unlock();
}
hash_del(&init_css_set.hlist);
hash_add(css_set_table, &init_css_set.hlist,
css_set_hash(init_css_set.subsys));
WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup"));
WARN_ON(register_filesystem(&cgroup_fs_type));
WARN_ON(register_filesystem(&cgroup2_fs_type));
WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show));
#ifdef CONFIG_CPUSETS
WARN_ON(register_filesystem(&cpuset_fs_type));
#endif
return 0;
}
static int __init cgroup_wq_init(void)
{
cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
BUG_ON(!cgroup_destroy_wq);
return 0;
}
core_initcall(cgroup_wq_init);
void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen)
{
struct kernfs_node *kn;
kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id);
if (!kn)
return;
kernfs_path(kn, buf, buflen);
kernfs_put(kn);
}
struct cgroup *cgroup_get_from_id(u64 id)
{
struct kernfs_node *kn;
struct cgroup *cgrp, *root_cgrp;
kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id);
if (!kn)
return ERR_PTR(-ENOENT);
if (kernfs_type(kn) != KERNFS_DIR) {
kernfs_put(kn);
return ERR_PTR(-ENOENT);
}
rcu_read_lock();
cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv);
if (cgrp && !cgroup_tryget(cgrp))
cgrp = NULL;
rcu_read_unlock();
kernfs_put(kn);
if (!cgrp)
return ERR_PTR(-ENOENT);
root_cgrp = current_cgns_cgroup_dfl();
if (!cgroup_is_descendant(cgrp, root_cgrp)) {
cgroup_put(cgrp);
return ERR_PTR(-ENOENT);
}
return cgrp;
}
EXPORT_SYMBOL_GPL(cgroup_get_from_id);
int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *tsk)
{
char *buf;
int retval;
struct cgroup_root *root;
retval = -ENOMEM;
buf = kmalloc(PATH_MAX, GFP_KERNEL);
if (!buf)
goto out;
cgroup_lock();
spin_lock_irq(&css_set_lock);
for_each_root(root) {
struct cgroup_subsys *ss;
struct cgroup *cgrp;
int ssid, count = 0;
if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible))
continue;
seq_printf(m, "%d:", root->hierarchy_id);
if (root != &cgrp_dfl_root)
for_each_subsys(ss, ssid)
if (root->subsys_mask & (1 << ssid))
seq_printf(m, "%s%s", count++ ? "," : "",
ss->legacy_name);
if (strlen(root->name))
seq_printf(m, "%sname=%s", count ? "," : "",
root->name);
seq_putc(m, ':');
cgrp = task_cgroup_from_root(tsk, root);
if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) {
retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX,
current->nsproxy->cgroup_ns);
if (retval >= PATH_MAX)
retval = -ENAMETOOLONG;
if (retval < 0)
goto out_unlock;
seq_puts(m, buf);
} else {
seq_puts(m, "/");
}
if (cgroup_on_dfl(cgrp) && cgroup_is_dead(cgrp))
seq_puts(m, " (deleted)\n");
else
seq_putc(m, '\n');
}
retval = 0;
out_unlock:
spin_unlock_irq(&css_set_lock);
cgroup_unlock();
kfree(buf);
out:
return retval;
}
void cgroup_fork(struct task_struct *child)
{
RCU_INIT_POINTER(child->cgroups, &init_css_set);
INIT_LIST_HEAD(&child->cg_list);
}
static struct cgroup *cgroup_v1v2_get_from_file(struct file *f)
{
struct cgroup_subsys_state *css;
css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
if (IS_ERR(css))
return ERR_CAST(css);
return css->cgroup;
}
static struct cgroup *cgroup_get_from_file(struct file *f)
{
struct cgroup *cgrp = cgroup_v1v2_get_from_file(f);
if (IS_ERR(cgrp))
return ERR_CAST(cgrp);
if (!cgroup_on_dfl(cgrp)) {
cgroup_put(cgrp);
return ERR_PTR(-EBADF);
}
return cgrp;
}
static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
__acquires(&cgroup_mutex) __acquires(&cgroup_threadgroup_rwsem)
{
int ret;
struct cgroup *dst_cgrp = NULL;
struct css_set *cset;
struct super_block *sb;
struct file *f;
if (kargs->flags & CLONE_INTO_CGROUP)
cgroup_lock();
cgroup_threadgroup_change_begin(current);
spin_lock_irq(&css_set_lock);
cset = task_css_set(current);
get_css_set(cset);
spin_unlock_irq(&css_set_lock);
if (!(kargs->flags & CLONE_INTO_CGROUP)) {
kargs->cset = cset;
return 0;
}
f = fget_raw(kargs->cgroup);
if (!f) {
ret = -EBADF;
goto err;
}
sb = f->f_path.dentry->d_sb;
dst_cgrp = cgroup_get_from_file(f);
if (IS_ERR(dst_cgrp)) {
ret = PTR_ERR(dst_cgrp);
dst_cgrp = NULL;
goto err;
}
if (cgroup_is_dead(dst_cgrp)) {
ret = -ENODEV;
goto err;
}
ret = cgroup_may_write(dst_cgrp, sb);
if (ret)
goto err;
ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb,
!(kargs->flags & CLONE_THREAD),
current->nsproxy->cgroup_ns);
if (ret)
goto err;
kargs->cset = find_css_set(cset, dst_cgrp);
if (!kargs->cset) {
ret = -ENOMEM;
goto err;
}
put_css_set(cset);
fput(f);
kargs->cgrp = dst_cgrp;
return ret;
err:
cgroup_threadgroup_change_end(current);
cgroup_unlock();
if (f)
fput(f);
if (dst_cgrp)
cgroup_put(dst_cgrp);
put_css_set(cset);
if (kargs->cset)
put_css_set(kargs->cset);
return ret;
}
static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs)
__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
{
struct cgroup *cgrp = kargs->cgrp;
struct css_set *cset = kargs->cset;
cgroup_threadgroup_change_end(current);
if (cset) {
put_css_set(cset);
kargs->cset = NULL;
}
if (kargs->flags & CLONE_INTO_CGROUP) {
cgroup_unlock();
if (cgrp) {
cgroup_put(cgrp);
kargs->cgrp = NULL;
}
}
}
int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs)
{
struct cgroup_subsys *ss;
int i, j, ret;
ret = cgroup_css_set_fork(kargs);
if (ret)
return ret;
do_each_subsys_mask(ss, i, have_canfork_callback) {
ret = ss->can_fork(child, kargs->cset);
if (ret)
goto out_revert;
} while_each_subsys_mask();
return 0;
out_revert:
for_each_subsys(ss, j) {
if (j >= i)
break;
if (ss->cancel_fork)
ss->cancel_fork(child, kargs->cset);
}
cgroup_css_set_put_fork(kargs);
return ret;
}
void cgroup_cancel_fork(struct task_struct *child,
struct kernel_clone_args *kargs)
{
struct cgroup_subsys *ss;
int i;
for_each_subsys(ss, i)
if (ss->cancel_fork)
ss->cancel_fork(child, kargs->cset);
cgroup_css_set_put_fork(kargs);
}
void cgroup_post_fork(struct task_struct *child,
struct kernel_clone_args *kargs)
__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
{
unsigned long cgrp_flags = 0;
bool kill = false;
struct cgroup_subsys *ss;
struct css_set *cset;
int i;
cset = kargs->cset;
kargs->cset = NULL;
spin_lock_irq(&css_set_lock);
if (likely(child->pid)) {
if (kargs->cgrp)
cgrp_flags = kargs->cgrp->flags;
else
cgrp_flags = cset->dfl_cgrp->flags;
WARN_ON_ONCE(!list_empty(&child->cg_list));
cset->nr_tasks++;
css_set_move_task(child, NULL, cset, false);
} else {
put_css_set(cset);
cset = NULL;
}
if (!(child->flags & PF_KTHREAD)) {
if (unlikely(test_bit(CGRP_FREEZE, &cgrp_flags))) {
spin_lock(&child->sighand->siglock);
WARN_ON_ONCE(child->frozen);
child->jobctl |= JOBCTL_TRAP_FREEZE;
spin_unlock(&child->sighand->siglock);
}
kill = test_bit(CGRP_KILL, &cgrp_flags);
}
spin_unlock_irq(&css_set_lock);
do_each_subsys_mask(ss, i, have_fork_callback) {
ss->fork(child);
} while_each_subsys_mask();
if (kargs->flags & CLONE_NEWCGROUP) {
struct css_set *rcset = child->nsproxy->cgroup_ns->root_cset;
get_css_set(cset);
child->nsproxy->cgroup_ns->root_cset = cset;
put_css_set(rcset);
}
if (unlikely(kill))
do_send_sig_info(SIGKILL, SEND_SIG_NOINFO, child, PIDTYPE_TGID);
cgroup_css_set_put_fork(kargs);
}
void cgroup_exit(struct task_struct *tsk)
{
struct cgroup_subsys *ss;
struct css_set *cset;
int i;
spin_lock_irq(&css_set_lock);
WARN_ON_ONCE(list_empty(&tsk->cg_list));
cset = task_css_set(tsk);
css_set_move_task(tsk, cset, NULL, false);
list_add_tail(&tsk->cg_list, &cset->dying_tasks);
cset->nr_tasks--;
if (dl_task(tsk))
dec_dl_tasks_cs(tsk);
WARN_ON_ONCE(cgroup_task_frozen(tsk));
if (unlikely(!(tsk->flags & PF_KTHREAD) &&
test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags)))
cgroup_update_frozen(task_dfl_cgroup(tsk));
spin_unlock_irq(&css_set_lock);
do_each_subsys_mask(ss, i, have_exit_callback) {
ss->exit(tsk);
} while_each_subsys_mask();
}
void cgroup_release(struct task_struct *task)
{
struct cgroup_subsys *ss;
int ssid;
do_each_subsys_mask(ss, ssid, have_release_callback) {
ss->release(task);
} while_each_subsys_mask();
spin_lock_irq(&css_set_lock);
css_set_skip_task_iters(task_css_set(task), task);
list_del_init(&task->cg_list);
spin_unlock_irq(&css_set_lock);
}
void cgroup_free(struct task_struct *task)
{
struct css_set *cset = task_css_set(task);
put_css_set(cset);
}
static int __init cgroup_disable(char *str)
{
struct cgroup_subsys *ss;
char *token;
int i;
while ((token = strsep(&str, ",")) != NULL) {
if (!*token)
continue;
for_each_subsys(ss, i) {
if (strcmp(token, ss->name) &&
strcmp(token, ss->legacy_name))
continue;
static_branch_disable(cgroup_subsys_enabled_key[i]);
pr_info("Disabling %s control group subsystem\n",
ss->name);
}
for (i = 0; i < OPT_FEATURE_COUNT; i++) {
if (strcmp(token, cgroup_opt_feature_names[i]))
continue;
cgroup_feature_disable_mask |= 1 << i;
pr_info("Disabling %s control group feature\n",
cgroup_opt_feature_names[i]);
break;
}
}
return 1;
}
__setup("cgroup_disable=", cgroup_disable);
void __init __weak enable_debug_cgroup(void) { }
static int __init enable_cgroup_debug(char *str)
{
cgroup_debug = true;
enable_debug_cgroup();
return 1;
}
__setup("cgroup_debug", enable_cgroup_debug);
struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
struct cgroup_subsys *ss)
{
struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
struct file_system_type *s_type = dentry->d_sb->s_type;
struct cgroup_subsys_state *css = NULL;
struct cgroup *cgrp;
if ((s_type != &cgroup_fs_type && s_type != &cgroup2_fs_type) ||
!kn || kernfs_type(kn) != KERNFS_DIR)
return ERR_PTR(-EBADF);
rcu_read_lock();
cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv);
if (cgrp)
css = cgroup_css(cgrp, ss);
if (!css || !css_tryget_online(css))
css = ERR_PTR(-ENOENT);
rcu_read_unlock();
return css;
}
struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
{
WARN_ON_ONCE(!rcu_read_lock_held());
return idr_find(&ss->css_idr, id);
}
struct cgroup *cgroup_get_from_path(const char *path)
{
struct kernfs_node *kn;
struct cgroup *cgrp = ERR_PTR(-ENOENT);
struct cgroup *root_cgrp;
root_cgrp = current_cgns_cgroup_dfl();
kn = kernfs_walk_and_get(root_cgrp->kn, path);
if (!kn)
goto out;
if (kernfs_type(kn) != KERNFS_DIR) {
cgrp = ERR_PTR(-ENOTDIR);
goto out_kernfs;
}
rcu_read_lock();
cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv);
if (!cgrp || !cgroup_tryget(cgrp))
cgrp = ERR_PTR(-ENOENT);
rcu_read_unlock();
out_kernfs:
kernfs_put(kn);
out:
return cgrp;
}
EXPORT_SYMBOL_GPL(cgroup_get_from_path);
struct cgroup *cgroup_v1v2_get_from_fd(int fd)
{
struct cgroup *cgrp;
struct fd f = fdget_raw(fd);
if (!f.file)
return ERR_PTR(-EBADF);
cgrp = cgroup_v1v2_get_from_file(f.file);
fdput(f);
return cgrp;
}
struct cgroup *cgroup_get_from_fd(int fd)
{
struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd);
if (IS_ERR(cgrp))
return ERR_CAST(cgrp);
if (!cgroup_on_dfl(cgrp)) {
cgroup_put(cgrp);
return ERR_PTR(-EBADF);
}
return cgrp;
}
EXPORT_SYMBOL_GPL(cgroup_get_from_fd);
static u64 power_of_ten(int power)
{
u64 v = 1;
while (power--)
v *= 10;
return v;
}
int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v)
{
s64 whole, frac = 0;
int fstart = 0, fend = 0, flen;
if (!sscanf(input, "%lld.%n%lld%n", &whole, &fstart, &frac, &fend))
return -EINVAL;
if (frac < 0)
return -EINVAL;
flen = fend > fstart ? fend - fstart : 0;
if (flen < dec_shift)
frac *= power_of_ten(dec_shift - flen);
else
frac = DIV_ROUND_CLOSEST_ULL(frac, power_of_ten(flen - dec_shift));
*v = whole * power_of_ten(dec_shift) + frac;
return 0;
}
#ifdef CONFIG_SOCK_CGROUP_DATA
void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
{
struct cgroup *cgroup;
rcu_read_lock();
if (in_interrupt()) {
cgroup = &cgrp_dfl_root.cgrp;
cgroup_get(cgroup);
goto out;
}
while (true) {
struct css_set *cset;
cset = task_css_set(current);
if (likely(cgroup_tryget(cset->dfl_cgrp))) {
cgroup = cset->dfl_cgrp;
break;
}
cpu_relax();
}
out:
skcd->cgroup = cgroup;
cgroup_bpf_get(cgroup);
rcu_read_unlock();
}
void cgroup_sk_clone(struct sock_cgroup_data *skcd)
{
struct cgroup *cgrp = sock_cgroup_ptr(skcd);
cgroup_get(cgrp);
cgroup_bpf_get(cgrp);
}
void cgroup_sk_free(struct sock_cgroup_data *skcd)
{
struct cgroup *cgrp = sock_cgroup_ptr(skcd);
cgroup_bpf_put(cgrp);
cgroup_put(cgrp);
}
#endif /* CONFIG_SOCK_CGROUP_DATA */
#ifdef CONFIG_SYSFS
static ssize_t show_delegatable_files(struct cftype *files, char *buf,
ssize_t size, const char *prefix)
{
struct cftype *cft;
ssize_t ret = 0;
for (cft = files; cft && cft->name[0] != '\0'; cft++) {
if (!(cft->flags & CFTYPE_NS_DELEGATABLE))
continue;
if (prefix)
ret += snprintf(buf + ret, size - ret, "%s.", prefix);
ret += snprintf(buf + ret, size - ret, "%s\n", cft->name);
if (WARN_ON(ret >= size))
break;
}
return ret;
}
static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr,
char *buf)
{
struct cgroup_subsys *ss;
int ssid;
ssize_t ret = 0;
ret = show_delegatable_files(cgroup_base_files, buf + ret,
PAGE_SIZE - ret, NULL);
if (cgroup_psi_enabled())
ret += show_delegatable_files(cgroup_psi_files, buf + ret,
PAGE_SIZE - ret, NULL);
for_each_subsys(ss, ssid)
ret += show_delegatable_files(ss->dfl_cftypes, buf + ret,
PAGE_SIZE - ret,
cgroup_subsys_name[ssid]);
return ret;
}
static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate);
static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
char *buf)
{
return snprintf(buf, PAGE_SIZE,
"nsdelegate\n"
"favordynmods\n"
"memory_localevents\n"
"memory_recursiveprot\n");
}
static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);
static struct attribute *cgroup_sysfs_attrs[] = {
&cgroup_delegate_attr.attr,
&cgroup_features_attr.attr,
NULL,
};
static const struct attribute_group cgroup_sysfs_attr_group = {
.attrs = cgroup_sysfs_attrs,
.name = "cgroup",
};
static int __init cgroup_sysfs_init(void)
{
return sysfs_create_group(kernel_kobj, &cgroup_sysfs_attr_group);
}
subsys_initcall(cgroup_sysfs_init);
#endif /* CONFIG_SYSFS */