summaryrefslogtreecommitdiff
path: root/kernel/cgroup.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/cgroup.c')
-rw-r--r--kernel/cgroup.c306
1 files changed, 208 insertions, 98 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index f1603c153890..c03a640ef6da 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -57,8 +57,8 @@
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
#include <linux/kthread.h>
#include <linux/delay.h>
-
#include <linux/atomic.h>
+#include <net/sock.h>
/*
* pidlists linger the following amount before being destroyed. The goal
@@ -98,6 +98,12 @@ static DEFINE_SPINLOCK(css_set_lock);
static DEFINE_SPINLOCK(cgroup_idr_lock);
/*
+ * Protects cgroup_file->kn for !self csses. It synchronizes notifications
+ * against file removal/re-creation across css hiding.
+ */
+static DEFINE_SPINLOCK(cgroup_file_kn_lock);
+
+/*
* Protects cgroup_subsys->release_agent_path. Modifying it also requires
* cgroup_mutex. Reading requires either cgroup_mutex or this spinlock.
*/
@@ -205,6 +211,7 @@ static unsigned long have_free_callback __read_mostly;
/* Ditto for the can_fork callback. */
static unsigned long have_canfork_callback __read_mostly;
+static struct file_system_type cgroup2_fs_type;
static struct cftype cgroup_dfl_base_files[];
static struct cftype cgroup_legacy_base_files[];
@@ -434,11 +441,6 @@ static bool cgroup_tryget(struct cgroup *cgrp)
return css_tryget(&cgrp->self);
}
-static void cgroup_put(struct cgroup *cgrp)
-{
- css_put(&cgrp->self);
-}
-
struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
{
struct cgroup *cgrp = of->kn->parent->priv;
@@ -459,25 +461,6 @@ struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
}
EXPORT_SYMBOL_GPL(of_css);
-/**
- * cgroup_is_descendant - test ancestry
- * @cgrp: the cgroup to be tested
- * @ancestor: possible ancestor of @cgrp
- *
- * Test whether @cgrp is a descendant of @ancestor. It also returns %true
- * if @cgrp == @ancestor. This function is safe to call as long as @cgrp
- * and @ancestor are accessible.
- */
-bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor)
-{
- while (cgrp) {
- if (cgrp == ancestor)
- return true;
- cgrp = cgroup_parent(cgrp);
- }
- return false;
-}
-
static int notify_on_release(const struct cgroup *cgrp)
{
return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -754,9 +737,11 @@ static void put_css_set_locked(struct css_set *cset)
if (!atomic_dec_and_test(&cset->refcount))
return;
- /* This css_set is dead. unlink it and release cgroup refcounts */
- for_each_subsys(ss, ssid)
+ /* This css_set is dead. unlink it and release cgroup and css refs */
+ for_each_subsys(ss, ssid) {
list_del(&cset->e_cset_node[ssid]);
+ css_put(cset->subsys[ssid]);
+ }
hash_del(&cset->hlist);
css_set_count--;
@@ -1056,9 +1041,13 @@ static struct css_set *find_css_set(struct css_set *old_cset,
key = css_set_hash(cset->subsys);
hash_add(css_set_table, &cset->hlist, key);
- for_each_subsys(ss, ssid)
+ for_each_subsys(ss, ssid) {
+ struct cgroup_subsys_state *css = cset->subsys[ssid];
+
list_add_tail(&cset->e_cset_node[ssid],
- &cset->subsys[ssid]->cgroup->e_csets[ssid]);
+ &css->cgroup->e_csets[ssid]);
+ css_get(css);
+ }
spin_unlock_bh(&css_set_lock);
@@ -1393,6 +1382,16 @@ 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);
+ }
+
kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
}
@@ -1625,10 +1624,6 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
all_ss = true;
continue;
}
- if (!strcmp(token, "__DEVEL__sane_behavior")) {
- opts->flags |= CGRP_ROOT_SANE_BEHAVIOR;
- continue;
- }
if (!strcmp(token, "noprefix")) {
opts->flags |= CGRP_ROOT_NOPREFIX;
continue;
@@ -1695,15 +1690,6 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
return -ENOENT;
}
- if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
- pr_warn("sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
- if (nr_opts != 1) {
- pr_err("sane_behavior: no other mount options allowed\n");
- return -EINVAL;
- }
- return 0;
- }
-
/*
* If the 'all' option was specified select all the subsystems,
* otherwise if 'none', 'name=' and a subsystem name options were
@@ -1856,7 +1842,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
INIT_LIST_HEAD(&cgrp->self.sibling);
INIT_LIST_HEAD(&cgrp->self.children);
- INIT_LIST_HEAD(&cgrp->self.files);
INIT_LIST_HEAD(&cgrp->cset_links);
INIT_LIST_HEAD(&cgrp->pidlists);
mutex_init(&cgrp->pidlist_mutex);
@@ -1903,6 +1888,7 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
if (ret < 0)
goto out;
root_cgrp->id = ret;
+ root_cgrp->ancestor_ids[0] = ret;
ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0,
GFP_KERNEL);
@@ -1983,6 +1969,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
int flags, const char *unused_dev_name,
void *data)
{
+ bool is_v2 = fs_type == &cgroup2_fs_type;
struct super_block *pinned_sb = NULL;
struct cgroup_subsys *ss;
struct cgroup_root *root;
@@ -1999,6 +1986,17 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
if (!use_task_css_set_links)
cgroup_enable_task_cg_lists();
+ if (is_v2) {
+ if (data) {
+ pr_err("cgroup2: unknown option \"%s\"\n", (char *)data);
+ return ERR_PTR(-EINVAL);
+ }
+ cgrp_dfl_root_visible = true;
+ root = &cgrp_dfl_root;
+ cgroup_get(&root->cgrp);
+ goto out_mount;
+ }
+
mutex_lock(&cgroup_mutex);
/* First find the desired set of subsystems */
@@ -2006,15 +2004,6 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
if (ret)
goto out_unlock;
- /* look for a matching existing root */
- if (opts.flags & CGRP_ROOT_SANE_BEHAVIOR) {
- cgrp_dfl_root_visible = true;
- root = &cgrp_dfl_root;
- cgroup_get(&root->cgrp);
- ret = 0;
- goto out_unlock;
- }
-
/*
* Destruction of cgroup root is asynchronous, so subsystems may
* still be dying after the previous unmount. Let's drain the
@@ -2125,9 +2114,10 @@ out_free:
if (ret)
return ERR_PTR(ret);
-
+out_mount:
dentry = kernfs_mount(fs_type, flags, root->kf_root,
- CGROUP_SUPER_MAGIC, &new_sb);
+ is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC,
+ &new_sb);
if (IS_ERR(dentry) || !new_sb)
cgroup_put(&root->cgrp);
@@ -2170,6 +2160,12 @@ static struct file_system_type cgroup_fs_type = {
.kill_sb = cgroup_kill_sb,
};
+static struct file_system_type cgroup2_fs_type = {
+ .name = "cgroup2",
+ .mount = cgroup_mount,
+ .kill_sb = cgroup_kill_sb,
+};
+
/**
* task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
* @task: target task
@@ -2216,6 +2212,9 @@ struct cgroup_taskset {
struct list_head src_csets;
struct list_head dst_csets;
+ /* the subsys currently being processed */
+ int ssid;
+
/*
* Fields for cgroup_taskset_*() iteration.
*
@@ -2278,25 +2277,29 @@ static void cgroup_taskset_add(struct task_struct *task,
/**
* cgroup_taskset_first - reset taskset and return the first task
* @tset: taskset of interest
+ * @dst_cssp: output variable for the destination css
*
* @tset iteration is initialized and the first task is returned.
*/
-struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
+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);
+ return cgroup_taskset_next(tset, dst_cssp);
}
/**
* cgroup_taskset_next - iterate to the next task in taskset
* @tset: taskset of interest
+ * @dst_cssp: output variable for the destination css
*
* Return the next task in @tset. Iteration must have been initialized
* with cgroup_taskset_first().
*/
-struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
+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;
@@ -2311,6 +2314,18 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
if (&task->cg_list != &cset->mg_tasks) {
tset->cur_cset = cset;
tset->cur_task = task;
+
+ /*
+ * This function may be called both before and
+ * after cgroup_taskset_migrate(). The two cases
+ * can be distinguished by looking at whether @cset
+ * has its ->mg_dst_cset set.
+ */
+ if (cset->mg_dst_cset)
+ *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid];
+ else
+ *dst_cssp = cset->subsys[tset->ssid];
+
return task;
}
@@ -2346,7 +2361,8 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
/* check that we can legitimately attach to the cgroup */
for_each_e_css(css, i, dst_cgrp) {
if (css->ss->can_attach) {
- ret = css->ss->can_attach(css, tset);
+ tset->ssid = i;
+ ret = css->ss->can_attach(tset);
if (ret) {
failed_css = css;
goto out_cancel_attach;
@@ -2379,9 +2395,12 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
*/
tset->csets = &tset->dst_csets;
- for_each_e_css(css, i, dst_cgrp)
- if (css->ss->attach)
- css->ss->attach(css, tset);
+ for_each_e_css(css, i, dst_cgrp) {
+ if (css->ss->attach) {
+ tset->ssid = i;
+ css->ss->attach(tset);
+ }
+ }
ret = 0;
goto out_release_tset;
@@ -2390,8 +2409,10 @@ out_cancel_attach:
for_each_e_css(css, i, dst_cgrp) {
if (css == failed_css)
break;
- if (css->ss->cancel_attach)
- css->ss->cancel_attach(css, tset);
+ if (css->ss->cancel_attach) {
+ tset->ssid = i;
+ css->ss->cancel_attach(tset);
+ }
}
out_release_tset:
spin_lock_bh(&css_set_lock);
@@ -3313,9 +3334,9 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
if (cft->file_offset) {
struct cgroup_file *cfile = (void *)css + cft->file_offset;
- kernfs_get(kn);
+ spin_lock_irq(&cgroup_file_kn_lock);
cfile->kn = kn;
- list_add(&cfile->node, &css->files);
+ spin_unlock_irq(&cgroup_file_kn_lock);
}
return 0;
@@ -3553,6 +3574,22 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
}
/**
+ * cgroup_file_notify - generate a file modified event for a cgroup_file
+ * @cfile: target cgroup_file
+ *
+ * @cfile must have been obtained by setting cftype->file_offset.
+ */
+void cgroup_file_notify(struct cgroup_file *cfile)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&cgroup_file_kn_lock, flags);
+ if (cfile->kn)
+ kernfs_notify(cfile->kn);
+ spin_unlock_irqrestore(&cgroup_file_kn_lock, flags);
+}
+
+/**
* cgroup_task_count - count the number of tasks in a cgroup.
* @cgrp: the cgroup in question
*
@@ -4000,7 +4037,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
goto out_err;
/*
- * Migrate tasks one-by-one until @form is empty. This fails iff
+ * Migrate tasks one-by-one until @from is empty. This fails iff
* ->can_attach() fails.
*/
do {
@@ -4613,13 +4650,9 @@ static void css_free_work_fn(struct work_struct *work)
container_of(work, struct cgroup_subsys_state, destroy_work);
struct cgroup_subsys *ss = css->ss;
struct cgroup *cgrp = css->cgroup;
- struct cgroup_file *cfile;
percpu_ref_exit(&css->refcnt);
- list_for_each_entry(cfile, &css->files, node)
- kernfs_put(cfile->kn);
-
if (ss) {
/* css free path */
int id = css->id;
@@ -4724,7 +4757,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
css->ss = ss;
INIT_LIST_HEAD(&css->sibling);
INIT_LIST_HEAD(&css->children);
- INIT_LIST_HEAD(&css->files);
css->serial_nr = css_serial_nr_next++;
if (cgroup_parent(cgrp)) {
@@ -4846,11 +4878,11 @@ err_free_css:
static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
umode_t mode)
{
- struct cgroup *parent, *cgrp;
+ struct cgroup *parent, *cgrp, *tcgrp;
struct cgroup_root *root;
struct cgroup_subsys *ss;
struct kernfs_node *kn;
- int ssid, ret;
+ int level, ssid, ret;
/* Do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable.
*/
@@ -4861,9 +4893,11 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
if (!parent)
return -ENODEV;
root = parent->root;
+ level = parent->level + 1;
/* allocate the cgroup and its ID, 0 is reserved for the root */
- cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
+ cgrp = kzalloc(sizeof(*cgrp) +
+ sizeof(cgrp->ancestor_ids[0]) * (level + 1), GFP_KERNEL);
if (!cgrp) {
ret = -ENOMEM;
goto out_unlock;
@@ -4887,6 +4921,10 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
cgrp->self.parent = &parent->self;
cgrp->root = root;
+ cgrp->level = level;
+
+ for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp))
+ cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;
if (notify_on_release(parent))
set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -5131,7 +5169,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
{
struct cgroup_subsys_state *css;
- printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);
+ pr_debug("Initializing cgroup subsys %s\n", ss->name);
mutex_lock(&cgroup_mutex);
@@ -5289,6 +5327,7 @@ int __init cgroup_init(void)
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("cgroups", 0, NULL, &proc_cgroupstats_operations));
return 0;
@@ -5432,19 +5471,6 @@ static const struct file_operations proc_cgroupstats_operations = {
.release = single_release,
};
-static void **subsys_canfork_priv_p(void *ss_priv[CGROUP_CANFORK_COUNT], int i)
-{
- if (CGROUP_CANFORK_START <= i && i < CGROUP_CANFORK_END)
- return &ss_priv[i - CGROUP_CANFORK_START];
- return NULL;
-}
-
-static void *subsys_canfork_priv(void *ss_priv[CGROUP_CANFORK_COUNT], int i)
-{
- void **private = subsys_canfork_priv_p(ss_priv, i);
- return private ? *private : NULL;
-}
-
/**
* cgroup_fork - initialize cgroup related fields during copy_process()
* @child: pointer to task_struct of forking parent process.
@@ -5467,14 +5493,13 @@ void cgroup_fork(struct task_struct *child)
* returns an error, the fork aborts with that error code. This allows for
* a cgroup subsystem to conditionally allow or deny new forks.
*/
-int cgroup_can_fork(struct task_struct *child,
- void *ss_priv[CGROUP_CANFORK_COUNT])
+int cgroup_can_fork(struct task_struct *child)
{
struct cgroup_subsys *ss;
int i, j, ret;
for_each_subsys_which(ss, i, &have_canfork_callback) {
- ret = ss->can_fork(child, subsys_canfork_priv_p(ss_priv, i));
+ ret = ss->can_fork(child);
if (ret)
goto out_revert;
}
@@ -5486,7 +5511,7 @@ out_revert:
if (j >= i)
break;
if (ss->cancel_fork)
- ss->cancel_fork(child, subsys_canfork_priv(ss_priv, j));
+ ss->cancel_fork(child);
}
return ret;
@@ -5499,15 +5524,14 @@ out_revert:
* This calls the cancel_fork() callbacks if a fork failed *after*
* cgroup_can_fork() succeded.
*/
-void cgroup_cancel_fork(struct task_struct *child,
- void *ss_priv[CGROUP_CANFORK_COUNT])
+void cgroup_cancel_fork(struct task_struct *child)
{
struct cgroup_subsys *ss;
int i;
for_each_subsys(ss, i)
if (ss->cancel_fork)
- ss->cancel_fork(child, subsys_canfork_priv(ss_priv, i));
+ ss->cancel_fork(child);
}
/**
@@ -5520,8 +5544,7 @@ void cgroup_cancel_fork(struct task_struct *child,
* cgroup_task_iter_start() - to guarantee that the new task ends up on its
* list.
*/
-void cgroup_post_fork(struct task_struct *child,
- void *old_ss_priv[CGROUP_CANFORK_COUNT])
+void cgroup_post_fork(struct task_struct *child)
{
struct cgroup_subsys *ss;
int i;
@@ -5565,7 +5588,7 @@ void cgroup_post_fork(struct task_struct *child,
* and addition to css_set.
*/
for_each_subsys_which(ss, i, &have_fork_callback)
- ss->fork(child, subsys_canfork_priv(old_ss_priv, i));
+ ss->fork(child);
}
/**
@@ -5765,6 +5788,93 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
return id > 0 ? idr_find(&ss->css_idr, id) : NULL;
}
+/**
+ * cgroup_get_from_path - lookup and get a cgroup from its default hierarchy path
+ * @path: path on the default hierarchy
+ *
+ * Find the cgroup at @path on the default hierarchy, increment its
+ * reference count and return it. Returns pointer to the found cgroup on
+ * success, ERR_PTR(-ENOENT) if @path doens't exist and ERR_PTR(-ENOTDIR)
+ * if @path points to a non-directory.
+ */
+struct cgroup *cgroup_get_from_path(const char *path)
+{
+ struct kernfs_node *kn;
+ struct cgroup *cgrp;
+
+ mutex_lock(&cgroup_mutex);
+
+ kn = kernfs_walk_and_get(cgrp_dfl_root.cgrp.kn, path);
+ if (kn) {
+ if (kernfs_type(kn) == KERNFS_DIR) {
+ cgrp = kn->priv;
+ cgroup_get(cgrp);
+ } else {
+ cgrp = ERR_PTR(-ENOTDIR);
+ }
+ kernfs_put(kn);
+ } else {
+ cgrp = ERR_PTR(-ENOENT);
+ }
+
+ mutex_unlock(&cgroup_mutex);
+ return cgrp;
+}
+EXPORT_SYMBOL_GPL(cgroup_get_from_path);
+
+/*
+ * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data
+ * definition in cgroup-defs.h.
+ */
+#ifdef CONFIG_SOCK_CGROUP_DATA
+
+#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
+
+DEFINE_SPINLOCK(cgroup_sk_update_lock);
+static bool cgroup_sk_alloc_disabled __read_mostly;
+
+void cgroup_sk_alloc_disable(void)
+{
+ if (cgroup_sk_alloc_disabled)
+ return;
+ pr_info("cgroup: disabling cgroup2 socket matching due to net_prio or net_cls activation\n");
+ cgroup_sk_alloc_disabled = true;
+}
+
+#else
+
+#define cgroup_sk_alloc_disabled false
+
+#endif
+
+void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
+{
+ if (cgroup_sk_alloc_disabled)
+ return;
+
+ rcu_read_lock();
+
+ while (true) {
+ struct css_set *cset;
+
+ cset = task_css_set(current);
+ if (likely(cgroup_tryget(cset->dfl_cgrp))) {
+ skcd->val = (unsigned long)cset->dfl_cgrp;
+ break;
+ }
+ cpu_relax();
+ }
+
+ rcu_read_unlock();
+}
+
+void cgroup_sk_free(struct sock_cgroup_data *skcd)
+{
+ cgroup_put(sock_cgroup_ptr(skcd));
+}
+
+#endif /* CONFIG_SOCK_CGROUP_DATA */
+
#ifdef CONFIG_CGROUP_DEBUG
static struct cgroup_subsys_state *
debug_css_alloc(struct cgroup_subsys_state *parent_css)