#include <linux/pid_namespace.h>
#include <linux/idr.h>
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
-#include <linux/flex_array.h> /* used in cgroup_attach_task */
#include <linux/kthread.h>
#include <linux/delay.h>
/*
* cgroup_mutex is the master lock. Any modification to cgroup or its
* hierarchy must be performed while holding it.
+ *
+ * css_set_rwsem protects task->cgroups pointer, the list of css_set
+ * objects, and the chain of tasks off each css_set.
+ *
+ * These locks are exported if CONFIG_PROVE_RCU so that accessors in
+ * cgroup.h can use them for lockdep annotations.
*/
#ifdef CONFIG_PROVE_RCU
DEFINE_MUTEX(cgroup_mutex);
-EXPORT_SYMBOL_GPL(cgroup_mutex); /* only for lockdep */
+DECLARE_RWSEM(css_set_rwsem);
+EXPORT_SYMBOL_GPL(cgroup_mutex);
+EXPORT_SYMBOL_GPL(css_set_rwsem);
#else
static DEFINE_MUTEX(cgroup_mutex);
+static DECLARE_RWSEM(css_set_rwsem);
#endif
/*
#undef SUBSYS
/*
- * The dummy hierarchy, reserved for the subsystems that are otherwise
+ * The default hierarchy, reserved for the subsystems that are otherwise
* unattached - it never has more than a single cgroup, and all tasks are
* part of that cgroup.
*/
-static struct cgroupfs_root cgroup_dummy_root;
+struct cgroup_root cgrp_dfl_root;
-/* dummy_top is a shorthand for the dummy hierarchy's top cgroup */
-static struct cgroup * const cgroup_dummy_top = &cgroup_dummy_root.top_cgroup;
+/*
+ * The default hierarchy always exists but is hidden until mounted for the
+ * first time. This is for backward compatibility.
+ */
+static bool cgrp_dfl_root_visible;
/* The list of hierarchy roots */
static struct cftype cgroup_base_files[];
static void cgroup_put(struct cgroup *cgrp);
-static int rebind_subsystems(struct cgroupfs_root *root,
- unsigned long added_mask, unsigned removed_mask);
+static int rebind_subsystems(struct cgroup_root *dst_root,
+ unsigned long ss_mask);
static void cgroup_destroy_css_killed(struct cgroup *cgrp);
static int cgroup_destroy_locked(struct cgroup *cgrp);
static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \
(((ss) = cgroup_subsys[ssid]) || true); (ssid)++)
-/* iterate across the active hierarchies */
-#define for_each_active_root(root) \
+/* iterate across the hierarchies */
+#define for_each_root(root) \
list_for_each_entry((root), &cgroup_roots, root_list)
/**
struct list_head cgrp_link;
};
-/* The default css_set - used by init and its children prior to any
+/*
+ * The default css_set - used by init and its children prior to any
* hierarchies being mounted. It contains a pointer to the root state
* for each subsystem. Also used to anchor the list of css_sets. Not
* reference-counted, to improve performance when child cgroups
* haven't been created.
*/
+static struct css_set init_css_set = {
+ .refcount = ATOMIC_INIT(1),
+ .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links),
+ .tasks = LIST_HEAD_INIT(init_css_set.tasks),
+ .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks),
+ .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node),
+ .mg_node = LIST_HEAD_INIT(init_css_set.mg_node),
+};
-static struct css_set init_css_set;
-static struct cgrp_cset_link init_cgrp_cset_link;
-
-/*
- * css_set_rwsem protects the list of css_set objects, and the chain of
- * tasks off each css_set.
- */
-static DECLARE_RWSEM(css_set_rwsem);
-static int css_set_count;
+static int css_set_count = 1; /* 1 for init_css_set */
/*
* hash table for cgroup groups. This improves the performance to find
struct cgroup *cgrp,
struct cgroup_subsys_state *template[])
{
- struct cgroupfs_root *root = cgrp->root;
+ struct cgroup_root *root = cgrp->root;
struct cgroup_subsys *ss;
struct css_set *cset;
unsigned long key;
* won't change, so no need for locking.
*/
for_each_subsys(ss, i) {
- if (root->subsys_mask & (1UL << i)) {
+ if (root->cgrp.subsys_mask & (1UL << i)) {
/* Subsystem is in this hierarchy. So we want
* the subsystem state from the new
* cgroup */
atomic_set(&cset->refcount, 1);
INIT_LIST_HEAD(&cset->cgrp_links);
INIT_LIST_HEAD(&cset->tasks);
+ INIT_LIST_HEAD(&cset->mg_tasks);
+ INIT_LIST_HEAD(&cset->mg_preload_node);
+ INIT_LIST_HEAD(&cset->mg_node);
INIT_HLIST_NODE(&cset->hlist);
/* Copy the set of subsystem state objects generated in
return cset;
}
-static struct cgroupfs_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
+static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
{
- struct cgroup *top_cgrp = kf_root->kn->priv;
+ struct cgroup *root_cgrp = kf_root->kn->priv;
- return top_cgrp->root;
+ return root_cgrp->root;
}
-static int cgroup_init_root_id(struct cgroupfs_root *root, int start, int end)
+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, start, end,
- GFP_KERNEL);
+ id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL);
if (id < 0)
return id;
return 0;
}
-static void cgroup_exit_root_id(struct cgroupfs_root *root)
+static void cgroup_exit_root_id(struct cgroup_root *root)
{
lockdep_assert_held(&cgroup_mutex);
}
}
-static void cgroup_free_root(struct cgroupfs_root *root)
+static void cgroup_free_root(struct cgroup_root *root)
{
if (root) {
/* hierarhcy ID shoulid already have been released */
}
}
-static void cgroup_destroy_root(struct cgroupfs_root *root)
+static void cgroup_destroy_root(struct cgroup_root *root)
{
- struct cgroup *cgrp = &root->top_cgroup;
+ struct cgroup *cgrp = &root->cgrp;
struct cgrp_cset_link *link, *tmp_link;
mutex_lock(&cgroup_tree_mutex);
BUG_ON(!list_empty(&cgrp->children));
/* Rebind all subsystems back to the default hierarchy */
- WARN_ON(rebind_subsystems(root, 0, root->subsys_mask));
+ rebind_subsystems(&cgrp_dfl_root, cgrp->subsys_mask);
/*
* Release all the links from cset_links to this hierarchy's
cgroup_free_root(root);
}
-/*
- * Return the cgroup for "task" from the given hierarchy. Must be
- * called with cgroup_mutex and css_set_rwsem held.
- */
-static struct cgroup *task_cgroup_from_root(struct task_struct *task,
- struct cgroupfs_root *root)
+/* look up cgroup associated with given css_set on the specified hierarchy */
+static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
+ struct cgroup_root *root)
{
- struct css_set *cset;
struct cgroup *res = NULL;
lockdep_assert_held(&cgroup_mutex);
lockdep_assert_held(&css_set_rwsem);
- /*
- * No need to lock the task - since we hold cgroup_mutex the
- * task can't change groups, so the only thing that can happen
- * is that it exits and its css is set back to init_css_set.
- */
- cset = task_css_set(task);
if (cset == &init_css_set) {
- res = &root->top_cgroup;
+ res = &root->cgrp;
} else {
struct cgrp_cset_link *link;
}
/*
- * There is one global cgroup mutex. We also require taking
- * task_lock() when dereferencing a task's cgroup subsys pointers.
- * See "The task_lock() exception", at the end of this comment.
- *
+ * Return the cgroup for "task" from the given hierarchy. Must be
+ * called with cgroup_mutex and css_set_rwsem held.
+ */
+static struct cgroup *task_cgroup_from_root(struct task_struct *task,
+ struct cgroup_root *root)
+{
+ /*
+ * No need to lock the task - since we hold cgroup_mutex the
+ * task can't change groups, so the only thing that can happen
+ * is that it exits and its css is set back to init_css_set.
+ */
+ return cset_cgroup_from_root(task_css_set(task), root);
+}
+
+/*
* A task must hold cgroup_mutex to modify cgroups.
*
* Any task can increment and decrement the count field without lock.
* A cgroup can only be deleted if both its 'count' of using tasks
* is zero, and its list of 'children' cgroups is empty. Since all
* tasks in the system use _some_ cgroup, and since there is always at
- * least one task in the system (init, pid == 1), therefore, top_cgroup
+ * least one task in the system (init, pid == 1), therefore, root cgroup
* always has either children cgroups and/or using tasks. So we don't
- * need a special hack to ensure that top_cgroup cannot be deleted.
- *
- * The task_lock() exception
- *
- * The need for this exception arises from the action of
- * cgroup_attach_task(), which overwrites one task's cgroup pointer with
- * another. It does so using cgroup_mutex, however there are
- * several performance critical places that need to reference
- * task->cgroup without the expense of grabbing a system global
- * mutex. Therefore except as noted below, when dereferencing or, as
- * in cgroup_attach_task(), modifying a task's cgroup pointer we use
- * task_lock(), which acts on a spinlock (task->alloc_lock) already in
- * the task_struct routinely used for such matters.
+ * need a special hack to ensure that root cgroup cannot be deleted.
*
* P.S. One more locking exception. RCU is used to guard the
* update of a tasks cgroup pointer by cgroup_attach_task()
kfree(cgrp);
} else {
/*
- * This is top cgroup's refcnt reaching zero, which
+ * This is root cgroup's refcnt reaching zero, which
* indicates that the root should be released.
*/
cgroup_destroy_root(cgrp->root);
}
}
-static int rebind_subsystems(struct cgroupfs_root *root,
- unsigned long added_mask, unsigned removed_mask)
+static int rebind_subsystems(struct cgroup_root *dst_root,
+ unsigned long ss_mask)
{
- struct cgroup *cgrp = &root->top_cgroup;
struct cgroup_subsys *ss;
- int i, ret;
+ int ssid, ret;
lockdep_assert_held(&cgroup_tree_mutex);
lockdep_assert_held(&cgroup_mutex);
- /* Check that any added subsystems are currently free */
- for_each_subsys(ss, i)
- if ((added_mask & (1 << i)) && ss->root != &cgroup_dummy_root)
+ for_each_subsys(ss, ssid) {
+ if (!(ss_mask & (1 << ssid)))
+ continue;
+
+ /* if @ss is on the dummy_root, we can always move it */
+ if (ss->root == &cgrp_dfl_root)
+ continue;
+
+ /* if @ss has non-root cgroups attached to it, can't move */
+ if (!list_empty(&ss->root->cgrp.children))
return -EBUSY;
- ret = cgroup_populate_dir(cgrp, added_mask);
- if (ret)
- return ret;
+ /* can't move between two non-dummy roots either */
+ if (dst_root != &cgrp_dfl_root)
+ return -EBUSY;
+ }
+
+ ret = cgroup_populate_dir(&dst_root->cgrp, ss_mask);
+ if (ret) {
+ if (dst_root != &cgrp_dfl_root)
+ return ret;
+
+ /*
+ * Rebinding back to the default root is not allowed to
+ * fail. Using both default and non-default roots should
+ * be rare. Moving subsystems back and forth even more so.
+ * Just warn about it and continue.
+ */
+ if (cgrp_dfl_root_visible) {
+ pr_warning("cgroup: failed to create files (%d) while rebinding 0x%lx to default root\n",
+ ret, ss_mask);
+ pr_warning("cgroup: you may retry by moving them to a different hierarchy and unbinding\n");
+ }
+ }
/*
* Nothing can fail from this point on. Remove files for the
* removed subsystems and rebind each subsystem.
*/
mutex_unlock(&cgroup_mutex);
- cgroup_clear_dir(cgrp, removed_mask);
+ for_each_subsys(ss, ssid)
+ if (ss_mask & (1 << ssid))
+ cgroup_clear_dir(&ss->root->cgrp, 1 << ssid);
mutex_lock(&cgroup_mutex);
- for_each_subsys(ss, i) {
- unsigned long bit = 1UL << i;
-
- if (bit & added_mask) {
- /* We're binding this subsystem to this hierarchy */
- BUG_ON(cgroup_css(cgrp, ss));
- BUG_ON(!cgroup_css(cgroup_dummy_top, ss));
- BUG_ON(cgroup_css(cgroup_dummy_top, ss)->cgroup != cgroup_dummy_top);
+ for_each_subsys(ss, ssid) {
+ struct cgroup_root *src_root;
+ struct cgroup_subsys_state *css;
- rcu_assign_pointer(cgrp->subsys[i],
- cgroup_css(cgroup_dummy_top, ss));
- cgroup_css(cgrp, ss)->cgroup = cgrp;
+ if (!(ss_mask & (1 << ssid)))
+ continue;
- ss->root = root;
- if (ss->bind)
- ss->bind(cgroup_css(cgrp, ss));
+ src_root = ss->root;
+ css = cgroup_css(&src_root->cgrp, ss);
- /* refcount was already taken, and we're keeping it */
- root->subsys_mask |= bit;
- } else if (bit & removed_mask) {
- /* We're removing this subsystem */
- BUG_ON(cgroup_css(cgrp, ss) != cgroup_css(cgroup_dummy_top, ss));
- BUG_ON(cgroup_css(cgrp, ss)->cgroup != cgrp);
+ WARN_ON(!css || cgroup_css(&dst_root->cgrp, ss));
- if (ss->bind)
- ss->bind(cgroup_css(cgroup_dummy_top, ss));
+ RCU_INIT_POINTER(src_root->cgrp.subsys[ssid], NULL);
+ rcu_assign_pointer(dst_root->cgrp.subsys[ssid], css);
+ ss->root = dst_root;
+ css->cgroup = &dst_root->cgrp;
- cgroup_css(cgroup_dummy_top, ss)->cgroup = cgroup_dummy_top;
- RCU_INIT_POINTER(cgrp->subsys[i], NULL);
+ src_root->cgrp.subsys_mask &= ~(1 << ssid);
+ dst_root->cgrp.subsys_mask |= 1 << ssid;
- cgroup_subsys[i]->root = &cgroup_dummy_root;
- root->subsys_mask &= ~bit;
- }
+ if (ss->bind)
+ ss->bind(css);
}
- kernfs_activate(cgrp->kn);
+ kernfs_activate(dst_root->cgrp.kn);
return 0;
}
static int cgroup_show_options(struct seq_file *seq,
struct kernfs_root *kf_root)
{
- struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
+ struct cgroup_root *root = cgroup_root_from_kf(kf_root);
struct cgroup_subsys *ss;
int ssid;
for_each_subsys(ss, ssid)
- if (root->subsys_mask & (1 << ssid))
+ if (root->cgrp.subsys_mask & (1 << ssid))
seq_printf(seq, ",%s", ss->name);
if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
seq_puts(seq, ",sane_behavior");
seq_printf(seq, ",release_agent=%s", root->release_agent_path);
spin_unlock(&release_agent_path_lock);
- if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags))
+ if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags))
seq_puts(seq, ",clone_children");
if (strlen(root->name))
seq_printf(seq, ",name=%s", root->name);
return -ENOENT;
}
- /*
- * If the 'all' option was specified select all the subsystems,
- * otherwise if 'none', 'name=' and a subsystem name options
- * were not specified, let's default to 'all'
- */
- if (all_ss || (!one_ss && !opts->none && !opts->name))
- for_each_subsys(ss, i)
- if (!ss->disabled)
- set_bit(i, &opts->subsys_mask);
-
/* Consistency checks */
if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
pr_err("cgroup: sane_behavior: noprefix, xattr, clone_children, release_agent and name are not allowed\n");
return -EINVAL;
}
+ } else {
+ /*
+ * If the 'all' option was specified select all the
+ * subsystems, otherwise if 'none', 'name=' and a subsystem
+ * name options were not specified, let's default to 'all'
+ */
+ if (all_ss || (!one_ss && !opts->none && !opts->name))
+ for_each_subsys(ss, i)
+ if (!ss->disabled)
+ set_bit(i, &opts->subsys_mask);
+
+ /*
+ * We either have to specify by name or by subsystems. (So
+ * all empty hierarchies must have a name).
+ */
+ if (!opts->subsys_mask && !opts->name)
+ return -EINVAL;
}
/*
if (opts->subsys_mask && opts->none)
return -EINVAL;
- /*
- * We either have to specify by name or by subsystems. (So all
- * empty hierarchies must have a name).
- */
- if (!opts->subsys_mask && !opts->name)
- return -EINVAL;
-
return 0;
}
static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
{
int ret = 0;
- struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
+ struct cgroup_root *root = cgroup_root_from_kf(kf_root);
struct cgroup_sb_opts opts;
unsigned long added_mask, removed_mask;
if (ret)
goto out_unlock;
- if (opts.subsys_mask != root->subsys_mask || opts.release_agent)
+ if (opts.subsys_mask != root->cgrp.subsys_mask || opts.release_agent)
pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n",
task_tgid_nr(current), current->comm);
- added_mask = opts.subsys_mask & ~root->subsys_mask;
- removed_mask = root->subsys_mask & ~opts.subsys_mask;
+ added_mask = opts.subsys_mask & ~root->cgrp.subsys_mask;
+ removed_mask = root->cgrp.subsys_mask & ~opts.subsys_mask;
/* Don't allow flags or name to change at remount */
if (((opts.flags ^ root->flags) & CGRP_ROOT_OPTION_MASK) ||
}
/* remounting is not allowed for populated hierarchies */
- if (!list_empty(&root->top_cgroup.children)) {
+ if (!list_empty(&root->cgrp.children)) {
ret = -EBUSY;
goto out_unlock;
}
- ret = rebind_subsystems(root, added_mask, removed_mask);
+ ret = rebind_subsystems(root, added_mask);
if (ret)
goto out_unlock;
+ rebind_subsystems(&cgrp_dfl_root, removed_mask);
+
if (opts.release_agent) {
spin_lock(&release_agent_path_lock);
strcpy(root->release_agent_path, opts.release_agent);
*/
read_lock(&tasklist_lock);
do_each_thread(g, p) {
- task_lock(p);
-
WARN_ON_ONCE(!list_empty(&p->cg_list) ||
task_css_set(p) != &init_css_set);
* We should check if the process is exiting, otherwise
* it will race with cgroup_exit() in that the list
* entry won't be deleted though the process has exited.
+ * Do it while holding siglock so that we don't end up
+ * racing against cgroup_exit().
*/
- if (!(p->flags & PF_EXITING))
- list_add(&p->cg_list, &task_css_set(p)->tasks);
+ spin_lock_irq(&p->sighand->siglock);
+ if (!(p->flags & PF_EXITING)) {
+ struct css_set *cset = task_css_set(p);
- task_unlock(p);
+ list_add(&p->cg_list, &cset->tasks);
+ get_css_set(cset);
+ }
+ spin_unlock_irq(&p->sighand->siglock);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
out_unlock:
cgrp->dummy_css.cgroup = cgrp;
}
-static void init_cgroup_root(struct cgroupfs_root *root)
+static void init_cgroup_root(struct cgroup_root *root,
+ struct cgroup_sb_opts *opts)
{
- struct cgroup *cgrp = &root->top_cgroup;
+ struct cgroup *cgrp = &root->cgrp;
INIT_LIST_HEAD(&root->root_list);
atomic_set(&root->nr_cgrps, 1);
cgrp->root = root;
init_cgroup_housekeeping(cgrp);
idr_init(&root->cgroup_idr);
-}
-
-static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
-{
- struct cgroupfs_root *root;
-
- if (!opts->subsys_mask && !opts->none)
- return ERR_PTR(-EINVAL);
-
- root = kzalloc(sizeof(*root), GFP_KERNEL);
- if (!root)
- return ERR_PTR(-ENOMEM);
-
- init_cgroup_root(root);
root->flags = opts->flags;
if (opts->release_agent)
if (opts->name)
strcpy(root->name, opts->name);
if (opts->cpuset_clone_children)
- set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags);
- return root;
+ set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
}
-static int cgroup_setup_root(struct cgroupfs_root *root, unsigned long ss_mask)
+static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
{
LIST_HEAD(tmp_links);
- struct cgroup *root_cgrp = &root->top_cgroup;
+ struct cgroup *root_cgrp = &root->cgrp;
struct css_set *cset;
int i, ret;
if (ret)
goto out;
- /* ID 0 is reserved for dummy root, 1 for unified hierarchy */
- ret = cgroup_init_root_id(root, 2, 0);
+ ret = cgroup_init_root_id(root);
if (ret)
goto out;
if (ret)
goto destroy_root;
- ret = rebind_subsystems(root, ss_mask, 0);
+ ret = rebind_subsystems(root, ss_mask);
if (ret)
goto destroy_root;
cgroup_root_count++;
/*
- * Link the top cgroup in this hierarchy into all the css_set
+ * Link the root cgroup in this hierarchy into all the css_set
* objects.
*/
down_write(&css_set_rwsem);
int flags, const char *unused_dev_name,
void *data)
{
- struct cgroupfs_root *root;
+ struct cgroup_root *root;
struct cgroup_sb_opts opts;
struct dentry *dentry;
int ret;
goto out_unlock;
/* look for a matching existing root */
- for_each_active_root(root) {
+ if (!opts.subsys_mask && !opts.none && !opts.name) {
+ cgrp_dfl_root_visible = true;
+ root = &cgrp_dfl_root;
+ cgroup_get(&root->cgrp);
+ ret = 0;
+ goto out_unlock;
+ }
+
+ for_each_root(root) {
bool name_match = false;
+ if (root == &cgrp_dfl_root)
+ continue;
+
/*
* If we asked for a name then it must match. Also, if
* name matches but sybsys_mask doesn't, we should fail.
* subsystems) then they must match.
*/
if ((opts.subsys_mask || opts.none) &&
- (opts.subsys_mask != root->subsys_mask)) {
+ (opts.subsys_mask != root->cgrp.subsys_mask)) {
if (!name_match)
continue;
ret = -EBUSY;
}
/*
- * A root's lifetime is governed by its top cgroup. Zero
+ * A root's lifetime is governed by its root cgroup. Zero
* ref indicate that the root is being destroyed. Wait for
* destruction to complete so that the subsystems are free.
* We can use wait_queue for the wait but this path is
* super cold. Let's just sleep for a bit and retry.
*/
- if (!atomic_inc_not_zero(&root->top_cgroup.refcnt)) {
+ if (!atomic_inc_not_zero(&root->cgrp.refcnt)) {
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgroup_tree_mutex);
kfree(opts.release_agent);
goto out_unlock;
}
- /* no such thing, create a new one */
- root = cgroup_root_from_opts(&opts);
- if (IS_ERR(root)) {
- ret = PTR_ERR(root);
+ /*
+ * No such thing, create a new one. name= matching without subsys
+ * specification is allowed for already existing hierarchies but we
+ * can't create new one without subsys specification.
+ */
+ if (!opts.subsys_mask && !opts.none) {
+ ret = -EINVAL;
goto out_unlock;
}
+ root = kzalloc(sizeof(*root), GFP_KERNEL);
+ if (!root) {
+ ret = -ENOMEM;
+ goto out_unlock;
+ }
+
+ init_cgroup_root(root, &opts);
+
ret = cgroup_setup_root(root, opts.subsys_mask);
if (ret)
cgroup_free_root(root);
dentry = kernfs_mount(fs_type, flags, root->kf_root);
if (IS_ERR(dentry))
- cgroup_put(&root->top_cgroup);
+ cgroup_put(&root->cgrp);
return dentry;
}
static void cgroup_kill_sb(struct super_block *sb)
{
struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
- struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
+ struct cgroup_root *root = cgroup_root_from_kf(kf_root);
- cgroup_put(&root->top_cgroup);
+ cgroup_put(&root->cgrp);
kernfs_kill_sb(sb);
}
*/
char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
{
- struct cgroupfs_root *root;
+ struct cgroup_root *root;
struct cgroup *cgrp;
int hierarchy_id = 1;
char *path = NULL;
}
EXPORT_SYMBOL_GPL(task_cgroup_path);
-/*
- * Control Group taskset
- */
-struct task_and_cgroup {
- struct task_struct *task;
- struct cgroup *cgrp;
- struct css_set *cset;
-};
-
+/* used to track tasks and other necessary states during migration */
struct cgroup_taskset {
- struct task_and_cgroup single;
- struct flex_array *tc_array;
- int tc_array_len;
- int idx;
+ /* the src and dst cset list running through cset->mg_node */
+ struct list_head src_csets;
+ struct list_head dst_csets;
+
+ /*
+ * Fields for cgroup_taskset_*() iteration.
+ *
+ * Before migration is committed, the target migration tasks are on
+ * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of
+ * the csets on ->dst_csets. ->csets point to either ->src_csets
+ * or ->dst_csets depending on whether migration is committed.
+ *
+ * ->cur_csets and ->cur_task point to the current task position
+ * during iteration.
+ */
+ struct list_head *csets;
+ struct css_set *cur_cset;
+ struct task_struct *cur_task;
};
/**
*/
struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
{
- if (tset->tc_array) {
- tset->idx = 0;
- return cgroup_taskset_next(tset);
- } else {
- return tset->single.task;
- }
+ tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node);
+ tset->cur_task = NULL;
+
+ return cgroup_taskset_next(tset);
}
/**
*/
struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
{
- struct task_and_cgroup *tc;
+ struct css_set *cset = tset->cur_cset;
+ struct task_struct *task = tset->cur_task;
- if (!tset->tc_array || tset->idx >= tset->tc_array_len)
- return NULL;
+ while (&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;
+ return task;
+ }
- tc = flex_array_get(tset->tc_array, tset->idx++);
- return tc->task;
+ cset = list_next_entry(cset, mg_node);
+ task = NULL;
+ }
+
+ return NULL;
}
/**
WARN_ON_ONCE(tsk->flags & PF_EXITING);
old_cset = task_css_set(tsk);
- task_lock(tsk);
+ get_css_set(new_cset);
rcu_assign_pointer(tsk->cgroups, new_cset);
- task_unlock(tsk);
- list_move(&tsk->cg_list, &new_cset->tasks);
+ /*
+ * Use move_tail so that cgroup_taskset_first() still returns the
+ * leader after migration. This works because cgroup_migrate()
+ * ensures that the dst_cset of the leader is the first on the
+ * tset's dst_csets list.
+ */
+ list_move_tail(&tsk->cg_list, &new_cset->mg_tasks);
/*
* We just gained a reference on old_cset by taking it from the
}
/**
- * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
- * @cgrp: the cgroup to attach to
- * @leader: the task or the leader of the threadgroup to be attached
- * @threadgroup: attach the whole threadgroup?
+ * cgroup_migrate_finish - cleanup after attach
+ * @preloaded_csets: list of preloaded css_sets
*
- * Call holding cgroup_mutex and the group_rwsem of the leader. Will take
- * task_lock of @tsk or each thread in the threadgroup individually in turn.
+ * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See
+ * those functions for details.
*/
-static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *leader,
- bool threadgroup)
+static void cgroup_migrate_finish(struct list_head *preloaded_csets)
{
- int ret, i, group_size;
- struct cgroupfs_root *root = cgrp->root;
- struct cgroup_subsys_state *css, *failed_css = NULL;
- /* threadgroup list cursor and array */
- struct task_struct *task;
- struct task_and_cgroup *tc;
- struct flex_array *group;
- struct cgroup_taskset tset = { };
+ struct css_set *cset, *tmp_cset;
- /*
- * step 0: in order to do expensive, possibly blocking operations for
- * every thread, we cannot iterate the thread group list, since it needs
- * rcu or tasklist locked. instead, build an array of all threads in the
- * group - group_rwsem prevents new threads from appearing, and if
- * threads exit, this will just be an over-estimate.
- */
- if (threadgroup)
- group_size = get_nr_threads(leader);
- else
- group_size = 1;
- /* flex_array supports very large thread-groups better than kmalloc. */
- group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL);
- if (!group)
- return -ENOMEM;
- /* pre-allocate to guarantee space while iterating in rcu read-side. */
- ret = flex_array_prealloc(group, 0, group_size, GFP_KERNEL);
- if (ret)
- goto out_free_group_list;
+ lockdep_assert_held(&cgroup_mutex);
+
+ down_write(&css_set_rwsem);
+ list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) {
+ cset->mg_src_cgrp = NULL;
+ cset->mg_dst_cset = NULL;
+ list_del_init(&cset->mg_preload_node);
+ put_css_set_locked(cset, false);
+ }
+ up_write(&css_set_rwsem);
+}
+
+/**
+ * cgroup_migrate_add_src - add a migration source css_set
+ * @src_cset: the source css_set to add
+ * @dst_cgrp: the destination cgroup
+ * @preloaded_csets: list of preloaded css_sets
+ *
+ * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin
+ * @src_cset and add it to @preloaded_csets, which should later be cleaned
+ * up by cgroup_migrate_finish().
+ *
+ * This function may be called without holding threadgroup_lock even if the
+ * target is a process. Threads may be created and destroyed but as long
+ * as cgroup_mutex is not dropped, no new css_set can be put into play and
+ * the preloaded css_sets are guaranteed to cover all migrations.
+ */
+static void cgroup_migrate_add_src(struct css_set *src_cset,
+ struct cgroup *dst_cgrp,
+ struct list_head *preloaded_csets)
+{
+ struct cgroup *src_cgrp;
+
+ lockdep_assert_held(&cgroup_mutex);
+ lockdep_assert_held(&css_set_rwsem);
+
+ src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
+
+ /* nothing to do if this cset already belongs to the cgroup */
+ if (src_cgrp == dst_cgrp)
+ return;
+
+ if (!list_empty(&src_cset->mg_preload_node))
+ return;
+
+ WARN_ON(src_cset->mg_src_cgrp);
+ WARN_ON(!list_empty(&src_cset->mg_tasks));
+ WARN_ON(!list_empty(&src_cset->mg_node));
+
+ src_cset->mg_src_cgrp = src_cgrp;
+ get_css_set(src_cset);
+ list_add(&src_cset->mg_preload_node, preloaded_csets);
+}
+
+/**
+ * cgroup_migrate_prepare_dst - prepare destination css_sets for migration
+ * @dst_cgrp: the destination cgroup
+ * @preloaded_csets: list of preloaded source css_sets
+ *
+ * Tasks are about to be moved to @dst_cgrp and all the source css_sets
+ * have been preloaded to @preloaded_csets. This function looks up and
+ * pins all destination css_sets, links each to its source, and put them on
+ * @preloaded_csets.
+ *
+ * This function must be called after cgroup_migrate_add_src() has been
+ * called on each migration source css_set. After migration is performed
+ * using cgroup_migrate(), cgroup_migrate_finish() must be called on
+ * @preloaded_csets.
+ */
+static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp,
+ struct list_head *preloaded_csets)
+{
+ LIST_HEAD(csets);
+ struct css_set *src_cset;
+
+ lockdep_assert_held(&cgroup_mutex);
+
+ /* look up the dst cset for each src cset and link it to src */
+ list_for_each_entry(src_cset, preloaded_csets, mg_preload_node) {
+ struct css_set *dst_cset;
+
+ dst_cset = find_css_set(src_cset, dst_cgrp);
+ if (!dst_cset)
+ goto err;
+
+ WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset);
+ src_cset->mg_dst_cset = dst_cset;
+
+ if (list_empty(&dst_cset->mg_preload_node))
+ list_add(&dst_cset->mg_preload_node, &csets);
+ else
+ put_css_set(dst_cset, false);
+ }
+
+ list_splice(&csets, preloaded_csets);
+ return 0;
+err:
+ cgroup_migrate_finish(&csets);
+ return -ENOMEM;
+}
+
+/**
+ * cgroup_migrate - migrate a process or task to a cgroup
+ * @cgrp: the destination cgroup
+ * @leader: the leader of the process or the task to migrate
+ * @threadgroup: whether @leader points to the whole process or a single task
+ *
+ * Migrate a process or task denoted by @leader to @cgrp. If migrating a
+ * process, the caller must be holding threadgroup_lock of @leader. The
+ * caller is also responsible for invoking cgroup_migrate_add_src() and
+ * cgroup_migrate_prepare_dst() on the targets before invoking this
+ * function and following up with cgroup_migrate_finish().
+ *
+ * As long as a controller's ->can_attach() doesn't fail, this function is
+ * guaranteed to succeed. This means that, excluding ->can_attach()
+ * failure, when migrating multiple targets, the success or failure can be
+ * decided for all targets by invoking group_migrate_prepare_dst() before
+ * actually starting migrating.
+ */
+static int cgroup_migrate(struct cgroup *cgrp, struct task_struct *leader,
+ bool threadgroup)
+{
+ struct cgroup_taskset tset = {
+ .src_csets = LIST_HEAD_INIT(tset.src_csets),
+ .dst_csets = LIST_HEAD_INIT(tset.dst_csets),
+ .csets = &tset.src_csets,
+ };
+ struct cgroup_subsys_state *css, *failed_css = NULL;
+ struct css_set *cset, *tmp_cset;
+ struct task_struct *task, *tmp_task;
+ int i, ret;
- i = 0;
/*
* Prevent freeing of tasks while we take a snapshot. Tasks that are
* already PF_EXITING could be freed from underneath us unless we
* take an rcu_read_lock.
*/
- down_read(&css_set_rwsem);
+ down_write(&css_set_rwsem);
rcu_read_lock();
task = leader;
do {
- struct task_and_cgroup ent;
-
/* @task either already exited or can't exit until the end */
if (task->flags & PF_EXITING)
goto next;
- /* as per above, nr_threads may decrease, but not increase. */
- BUG_ON(i >= group_size);
- ent.task = task;
- ent.cgrp = task_cgroup_from_root(task, root);
- /* nothing to do if this task is already in the cgroup */
- if (ent.cgrp == cgrp)
+ /* leave @task alone if post_fork() hasn't linked it yet */
+ if (list_empty(&task->cg_list))
+ goto next;
+
+ cset = task_css_set(task);
+ if (!cset->mg_src_cgrp)
goto next;
+
/*
- * saying GFP_ATOMIC has no effect here because we did prealloc
- * earlier, but it's good form to communicate our expectations.
+ * cgroup_taskset_first() must always return the leader.
+ * Take care to avoid disturbing the ordering.
*/
- ret = flex_array_put(group, i, &ent, GFP_ATOMIC);
- BUG_ON(ret != 0);
- i++;
+ list_move_tail(&task->cg_list, &cset->mg_tasks);
+ if (list_empty(&cset->mg_node))
+ list_add_tail(&cset->mg_node, &tset.src_csets);
+ if (list_empty(&cset->mg_dst_cset->mg_node))
+ list_move_tail(&cset->mg_dst_cset->mg_node,
+ &tset.dst_csets);
next:
if (!threadgroup)
break;
} while_each_thread(leader, task);
rcu_read_unlock();
- up_read(&css_set_rwsem);
- /* remember the number of threads in the array for later. */
- group_size = i;
- tset.tc_array = group;
- tset.tc_array_len = group_size;
+ up_write(&css_set_rwsem);
/* methods shouldn't be called if no task is actually migrating */
- ret = 0;
- if (!group_size)
- goto out_free_group_list;
+ if (list_empty(&tset.src_csets))
+ return 0;
- /*
- * step 1: check that we can legitimately attach to the cgroup.
- */
+ /* check that we can legitimately attach to the cgroup */
for_each_css(css, i, cgrp) {
if (css->ss->can_attach) {
ret = css->ss->can_attach(css, &tset);
}
/*
- * step 2: make sure css_sets exist for all threads to be migrated.
- * we use find_css_set, which allocates a new one if necessary.
- */
- for (i = 0; i < group_size; i++) {
- struct css_set *old_cset;
-
- tc = flex_array_get(group, i);
- old_cset = task_css_set(tc->task);
- tc->cset = find_css_set(old_cset, cgrp);
- if (!tc->cset) {
- ret = -ENOMEM;
- goto out_put_css_set_refs;
- }
- }
-
- /*
- * step 3: now that we're guaranteed success wrt the css_sets,
- * proceed to move all tasks to the new cgroup. There are no
- * failure cases after here, so this is the commit point.
+ * Now that we're guaranteed success, proceed to move all tasks to
+ * the new cgroup. There are no failure cases after here, so this
+ * is the commit point.
*/
down_write(&css_set_rwsem);
- for (i = 0; i < group_size; i++) {
- tc = flex_array_get(group, i);
- cgroup_task_migrate(tc->cgrp, tc->task, tc->cset);
+ list_for_each_entry(cset, &tset.src_csets, mg_node) {
+ list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list)
+ cgroup_task_migrate(cset->mg_src_cgrp, task,
+ cset->mg_dst_cset);
}
up_write(&css_set_rwsem);
- /* nothing is sensitive to fork() after this point. */
/*
- * step 4: do subsystem attach callbacks.
+ * Migration is committed, all target tasks are now on dst_csets.
+ * Nothing is sensitive to fork() after this point. Notify
+ * controllers that migration is complete.
*/
+ tset.csets = &tset.dst_csets;
+
for_each_css(css, i, cgrp)
if (css->ss->attach)
css->ss->attach(css, &tset);
- /*
- * step 5: success! and cleanup
- */
ret = 0;
-out_put_css_set_refs:
- if (ret) {
- for (i = 0; i < group_size; i++) {
- tc = flex_array_get(group, i);
- if (!tc->cset)
- break;
- put_css_set(tc->cset, false);
- }
- }
+ goto out_release_tset;
+
out_cancel_attach:
- if (ret) {
- for_each_css(css, i, cgrp) {
- if (css == failed_css)
- break;
- if (css->ss->cancel_attach)
- css->ss->cancel_attach(css, &tset);
- }
+ for_each_css(css, i, cgrp) {
+ if (css == failed_css)
+ break;
+ if (css->ss->cancel_attach)
+ css->ss->cancel_attach(css, &tset);
+ }
+out_release_tset:
+ down_write(&css_set_rwsem);
+ 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);
}
-out_free_group_list:
- flex_array_free(group);
+ up_write(&css_set_rwsem);
+ return ret;
+}
+
+/**
+ * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
+ * @dst_cgrp: the cgroup to attach to
+ * @leader: the task or the leader of the threadgroup to be attached
+ * @threadgroup: attach the whole threadgroup?
+ *
+ * Call holding cgroup_mutex and threadgroup_lock of @leader.
+ */
+static int cgroup_attach_task(struct cgroup *dst_cgrp,
+ struct task_struct *leader, bool threadgroup)
+{
+ LIST_HEAD(preloaded_csets);
+ struct task_struct *task;
+ int ret;
+
+ /* look up all src csets */
+ down_read(&css_set_rwsem);
+ rcu_read_lock();
+ task = leader;
+ do {
+ cgroup_migrate_add_src(task_css_set(task), dst_cgrp,
+ &preloaded_csets);
+ if (!threadgroup)
+ break;
+ } while_each_thread(leader, task);
+ rcu_read_unlock();
+ up_read(&css_set_rwsem);
+
+ /* prepare dst csets and commit */
+ ret = cgroup_migrate_prepare_dst(dst_cgrp, &preloaded_csets);
+ if (!ret)
+ ret = cgroup_migrate(dst_cgrp, leader, threadgroup);
+
+ cgroup_migrate_finish(&preloaded_csets);
return ret;
}
/*
* Find the task_struct of the task to attach by vpid and pass it along to the
* function to attach either it or all tasks in its threadgroup. Will lock
- * cgroup_mutex and threadgroup; may take task_lock of task.
+ * cgroup_mutex and threadgroup.
*/
static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
{
*/
int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
{
- struct cgroupfs_root *root;
+ struct cgroup_root *root;
int retval = 0;
mutex_lock(&cgroup_mutex);
- for_each_active_root(root) {
+ for_each_root(root) {
struct cgroup *from_cgrp;
+ if (root == &cgrp_dfl_root)
+ continue;
+
down_read(&css_set_rwsem);
from_cgrp = task_cgroup_from_root(from, root);
up_read(&css_set_rwsem);
}
static int cgroup_release_agent_write(struct cgroup_subsys_state *css,
- struct cftype *cft, const char *buffer)
+ struct cftype *cft, char *buffer)
{
- struct cgroupfs_root *root = css->cgroup->root;
+ struct cgroup_root *root = css->cgroup->root;
BUILD_BUG_ON(sizeof(root->release_agent_path) < PATH_MAX);
if (!cgroup_lock_live_group(css->cgroup))
if (cgroup_sane_behavior(cgrp))
return -EPERM;
+ /*
+ * We're gonna grab cgroup_tree_mutex which nests outside kernfs
+ * active_ref. kernfs_rename() doesn't require active_ref
+ * protection. Break them before grabbing cgroup_tree_mutex.
+ */
+ kernfs_break_active_protection(new_parent);
+ kernfs_break_active_protection(kn);
+
mutex_lock(&cgroup_tree_mutex);
mutex_lock(&cgroup_mutex);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgroup_tree_mutex);
+
+ kernfs_unbreak_active_protection(kn);
+ kernfs_unbreak_active_protection(new_parent);
return ret;
}
for (cft = cfts; cft->name[0] != '\0'; cft++) {
/* does cft->flags tell us to skip this file on @cgrp? */
+ if ((cft->flags & CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp))
+ continue;
if ((cft->flags & CFTYPE_INSANE) && cgroup_sane_behavior(cgrp))
continue;
if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
{
LIST_HEAD(pending);
struct cgroup_subsys *ss = cfts[0].ss;
- struct cgroup *root = &ss->root->top_cgroup;
+ struct cgroup *root = &ss->root->cgrp;
struct cgroup_subsys_state *css;
int ret = 0;
lockdep_assert_held(&cgroup_tree_mutex);
/* don't bother if @ss isn't attached */
- if (ss->root == &cgroup_dummy_root)
+ if (ss->root == &cgrp_dfl_root)
return 0;
/* add/rm files for all cgroups created before */
}
link = list_entry(l, struct cgrp_cset_link, cset_link);
cset = link->cset;
- } while (list_empty(&cset->tasks));
+ } while (list_empty(&cset->tasks) && list_empty(&cset->mg_tasks));
+
it->cset_link = l;
- it->task = cset->tasks.next;
+
+ if (!list_empty(&cset->tasks))
+ it->task = cset->tasks.next;
+ else
+ it->task = cset->mg_tasks.next;
}
/**
{
struct task_struct *res;
struct list_head *l = it->task;
- struct cgrp_cset_link *link;
+ struct cgrp_cset_link *link = list_entry(it->cset_link,
+ struct cgrp_cset_link, cset_link);
/* If the iterator cg is NULL, we have no tasks */
if (!it->cset_link)
return NULL;
res = list_entry(l, struct task_struct, cg_list);
- /* Advance iterator to find next entry */
+
+ /*
+ * Advance iterator to find next entry. cset->tasks is consumed
+ * first and then ->mg_tasks. After ->mg_tasks, we move onto the
+ * next cset.
+ */
l = l->next;
- link = list_entry(it->cset_link, struct cgrp_cset_link, cset_link);
- if (l == &link->cset->tasks) {
- /*
- * We reached the end of this task list - move on to the
- * next cgrp_cset_link.
- */
+
+ if (l == &link->cset->tasks)
+ l = link->cset->mg_tasks.next;
+
+ if (l == &link->cset->mg_tasks)
css_advance_task_iter(it);
- } else {
+ else
it->task = l;
- }
+
return res;
}
* cgroup_trasnsfer_tasks - move tasks from one cgroup to another
* @to: cgroup to which the tasks will be moved
* @from: cgroup in which the tasks currently reside
+ *
+ * Locking rules between cgroup_post_fork() and the migration path
+ * guarantee that, if a task is forking while being migrated, the new child
+ * is guaranteed to be either visible in the source cgroup after the
+ * parent's migration is complete or put into the target cgroup. No task
+ * can slip out of migration through forking.
*/
int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
{
+ LIST_HEAD(preloaded_csets);
+ struct cgrp_cset_link *link;
struct css_task_iter it;
struct task_struct *task;
- int ret = 0;
+ int ret;
+
+ mutex_lock(&cgroup_mutex);
+
+ /* all tasks in @from are being moved, all csets are source */
+ down_read(&css_set_rwsem);
+ list_for_each_entry(link, &from->cset_links, cset_link)
+ cgroup_migrate_add_src(link->cset, to, &preloaded_csets);
+ up_read(&css_set_rwsem);
+ ret = cgroup_migrate_prepare_dst(to, &preloaded_csets);
+ if (ret)
+ goto out_err;
+
+ /*
+ * Migrate tasks one-by-one until @form is empty. This fails iff
+ * ->can_attach() fails.
+ */
do {
css_task_iter_start(&from->dummy_css, &it);
task = css_task_iter_next(&it);
css_task_iter_end(&it);
if (task) {
- mutex_lock(&cgroup_mutex);
- ret = cgroup_attach_task(to, task, false);
- mutex_unlock(&cgroup_mutex);
+ ret = cgroup_migrate(to, task, false);
put_task_struct(task);
}
} while (task && !ret);
-
+out_err:
+ cgroup_migrate_finish(&preloaded_csets);
+ mutex_unlock(&cgroup_mutex);
return ret;
}
struct cgroup_subsys_state *css =
container_of(ref, struct cgroup_subsys_state, refcnt);
- rcu_assign_pointer(css->cgroup->subsys[css->ss->id], NULL);
+ RCU_INIT_POINTER(css->cgroup->subsys[css->ss->id], NULL);
call_rcu(&css->rcu_head, css_free_rcu_fn);
}
cgroup_get(cgrp);
css_get(css->parent);
+ cgrp->subsys_mask |= 1 << ss->id;
+
if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
parent->parent) {
pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
umode_t mode)
{
struct cgroup *cgrp;
- struct cgroupfs_root *root = parent->root;
+ struct cgroup_root *root = parent->root;
int ssid, err;
struct cgroup_subsys *ss;
struct kernfs_node *kn;
+ /*
+ * XXX: The default hierarchy isn't fully implemented yet. Block
+ * !root cgroup creation on it for now.
+ */
+ if (root == &cgrp_dfl_root)
+ return -EINVAL;
+
/* allocate the cgroup and its ID, 0 is reserved for the root */
cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
if (!cgrp)
/* let's create and online css's */
for_each_subsys(ss, ssid) {
- if (root->subsys_mask & (1 << ssid)) {
+ if (root->cgrp.subsys_mask & (1 << ssid)) {
err = create_css(cgrp, ss);
if (err)
goto err_destroy;
umode_t mode)
{
struct cgroup *parent = parent_kn->priv;
+ int ret;
+
+ /*
+ * cgroup_create() grabs cgroup_tree_mutex which nests outside
+ * kernfs active_ref and cgroup_create() already synchronizes
+ * properly against removal through cgroup_lock_live_group().
+ * Break it before calling cgroup_create().
+ */
+ cgroup_get(parent);
+ kernfs_break_active_protection(parent_kn);
+
+ ret = cgroup_create(parent, name, mode);
- return cgroup_create(parent, name, mode);
+ kernfs_unbreak_active_protection(parent_kn);
+ cgroup_put(parent);
+ return ret;
}
/*
queue_work(cgroup_destroy_wq, &css->destroy_work);
}
-/**
- * kill_css - destroy a css
- * @css: css to destroy
- *
- * This function initiates destruction of @css by removing cgroup interface
- * files and putting its base reference. ->css_offline() will be invoked
- * asynchronously once css_tryget() is guaranteed to fail and when the
- * reference count reaches zero, @css will be released.
- */
-static void kill_css(struct cgroup_subsys_state *css)
+static void __kill_css(struct cgroup_subsys_state *css)
{
+ lockdep_assert_held(&cgroup_tree_mutex);
+
/*
* This must happen before css is disassociated with its cgroup.
* See seq_css() for details.
percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn);
}
+/**
+ * kill_css - destroy a css
+ * @css: css to destroy
+ *
+ * This function initiates destruction of @css by removing cgroup interface
+ * files and putting its base reference. ->css_offline() will be invoked
+ * asynchronously once css_tryget() is guaranteed to fail and when the
+ * reference count reaches zero, @css will be released.
+ */
+static void kill_css(struct cgroup_subsys_state *css)
+{
+ struct cgroup *cgrp = css->cgroup;
+
+ lockdep_assert_held(&cgroup_tree_mutex);
+
+ /* if already killed, noop */
+ if (cgrp->subsys_mask & (1 << css->ss->id)) {
+ cgrp->subsys_mask &= ~(1 << css->ss->id);
+ __kill_css(css);
+ }
+}
+
/**
* cgroup_destroy_locked - the first stage of cgroup destruction
* @cgrp: cgroup to be destroyed
if (!empty)
return -EBUSY;
+ /*
+ * Mark @cgrp dead. This prevents further task migration and child
+ * creation by disabling cgroup_lock_live_group(). Note that
+ * CGRP_DEAD assertion is depended upon by css_next_child() to
+ * resume iteration after dropping RCU read lock. See
+ * css_next_child() for details.
+ */
+ set_bit(CGRP_DEAD, &cgrp->flags);
+
/*
* Initiate massacre of all css's. cgroup_destroy_css_killed()
* will be invoked to perform the rest of destruction once the
kill_css(css);
mutex_lock(&cgroup_mutex);
- /*
- * Mark @cgrp dead. This prevents further task migration and child
- * creation by disabling cgroup_lock_live_group(). Note that
- * CGRP_DEAD assertion is depended upon by css_next_child() to
- * resume iteration after dropping RCU read lock. See
- * css_next_child() for details.
- */
- set_bit(CGRP_DEAD, &cgrp->flags);
-
/* CGRP_DEAD is set, remove from ->release_list for the last time */
raw_spin_lock(&release_list_lock);
if (!list_empty(&cgrp->release_list))
INIT_LIST_HEAD(&ss->cfts);
- /* Create the top cgroup state for this subsystem */
- ss->root = &cgroup_dummy_root;
- css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss));
+ /* Create the root cgroup state for this subsystem */
+ ss->root = &cgrp_dfl_root;
+ css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss));
/* We don't handle early failures gracefully */
BUG_ON(IS_ERR(css));
- init_css(css, ss, cgroup_dummy_top);
+ init_css(css, ss, &cgrp_dfl_root.cgrp);
/* Update the init_css_set to contain a subsys
* pointer to this state - since the subsystem is
* newly registered, all tasks and hence the
- * init_css_set is in the subsystem's top cgroup. */
+ * init_css_set is in the subsystem's root cgroup. */
init_css_set.subsys[ss->id] = css;
need_forkexit_callback |= ss->fork || ss->exit;
BUG_ON(online_css(css));
+ cgrp_dfl_root.cgrp.subsys_mask |= 1 << ss->id;
+
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgroup_tree_mutex);
}
*/
int __init cgroup_init_early(void)
{
+ static struct cgroup_sb_opts __initdata opts =
+ { .flags = CGRP_ROOT_SANE_BEHAVIOR };
struct cgroup_subsys *ss;
int i;
- atomic_set(&init_css_set.refcount, 1);
- INIT_LIST_HEAD(&init_css_set.cgrp_links);
- INIT_LIST_HEAD(&init_css_set.tasks);
- INIT_HLIST_NODE(&init_css_set.hlist);
- css_set_count = 1;
- init_cgroup_root(&cgroup_dummy_root);
- cgroup_root_count = 1;
+ init_cgroup_root(&cgrp_dfl_root, &opts);
RCU_INIT_POINTER(init_task.cgroups, &init_css_set);
- init_cgrp_cset_link.cset = &init_css_set;
- init_cgrp_cset_link.cgrp = cgroup_dummy_top;
- list_add(&init_cgrp_cset_link.cset_link, &cgroup_dummy_top->cset_links);
- list_add(&init_cgrp_cset_link.cgrp_link, &init_css_set.cgrp_links);
-
for_each_subsys(ss, i) {
WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id,
"invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p name:id=%d:%s\n",
{
struct cgroup_subsys *ss;
unsigned long key;
- int i, err;
+ int ssid, err;
BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
- for_each_subsys(ss, i) {
+ mutex_lock(&cgroup_tree_mutex);
+ mutex_lock(&cgroup_mutex);
+
+ /* Add init_css_set to the hash table */
+ key = css_set_hash(init_css_set.subsys);
+ hash_add(css_set_table, &init_css_set.hlist, key);
+
+ BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
+
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
+
+ for_each_subsys(ss, ssid) {
if (!ss->early_init)
cgroup_init_subsys(ss);
WARN_ON(cgroup_add_cftypes(ss, ss->base_cftypes));
}
- /* allocate id for the dummy hierarchy */
- mutex_lock(&cgroup_mutex);
-
- /* Add init_css_set to the hash table */
- key = css_set_hash(init_css_set.subsys);
- hash_add(css_set_table, &init_css_set.hlist, key);
-
- BUG_ON(cgroup_init_root_id(&cgroup_dummy_root, 0, 1));
-
- err = idr_alloc(&cgroup_dummy_root.cgroup_idr, cgroup_dummy_top,
- 0, 1, GFP_KERNEL);
- BUG_ON(err < 0);
-
- mutex_unlock(&cgroup_mutex);
-
cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
if (!cgroup_kobj)
return -ENOMEM;
/*
* There isn't much point in executing destruction path in
* parallel. Good chunk is serialized with cgroup_mutex anyway.
- *
- * XXX: Must be ordered to make sure parent is offlined after
- * children. The ordering requirement is for memcg where a
- * parent's offline may wait for a child's leading to deadlock. In
- * the long term, this should be fixed from memcg side.
+ * Use 1 for @max_active.
*
* We would prefer to do this in cgroup_init() above, but that
* is called before init_workqueues(): so leave this until after.
*/
- cgroup_destroy_wq = alloc_ordered_workqueue("cgroup_destroy", 0);
+ cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
BUG_ON(!cgroup_destroy_wq);
/*
* proc_cgroup_show()
* - Print task's cgroup paths into seq_file, one line for each hierarchy
* - Used for /proc/<pid>/cgroup.
- * - No need to task_lock(tsk) on this tsk->cgroup reference, as it
- * doesn't really matter if tsk->cgroup changes after we read it,
- * and we take cgroup_mutex, keeping cgroup_attach_task() from changing it
- * anyway. No need to check that tsk->cgroup != NULL, thanks to
- * the_top_cgroup_hack in cgroup_exit(), which sets an exiting tasks
- * cgroup to top_cgroup.
*/
/* TODO: Use a proper seq_file iterator */
struct task_struct *tsk;
char *buf, *path;
int retval;
- struct cgroupfs_root *root;
+ struct cgroup_root *root;
retval = -ENOMEM;
buf = kmalloc(PATH_MAX, GFP_KERNEL);
mutex_lock(&cgroup_mutex);
down_read(&css_set_rwsem);
- for_each_active_root(root) {
+ for_each_root(root) {
struct cgroup_subsys *ss;
struct cgroup *cgrp;
int ssid, count = 0;
+ if (root == &cgrp_dfl_root && !cgrp_dfl_root_visible)
+ continue;
+
seq_printf(m, "%d:", root->hierarchy_id);
for_each_subsys(ss, ssid)
- if (root->subsys_mask & (1 << ssid))
+ if (root->cgrp.subsys_mask & (1 << ssid))
seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
if (strlen(root->name))
seq_printf(m, "%sname=%s", count ? "," : "",
};
/**
- * cgroup_fork - attach newly forked task to its parents cgroup.
+ * cgroup_fork - initialize cgroup related fields during copy_process()
* @child: pointer to task_struct of forking parent process.
*
- * Description: A task inherits its parent's cgroup at fork().
- *
- * A pointer to the shared css_set was automatically copied in
- * fork.c by dup_task_struct(). However, we ignore that copy, since
- * it was not made under the protection of RCU or cgroup_mutex, so
- * might no longer be a valid cgroup pointer. cgroup_attach_task() might
- * have already changed current->cgroups, allowing the previously
- * referenced cgroup group to be removed and freed.
- *
- * At the point that cgroup_fork() is called, 'current' is the parent
- * task, and the passed argument 'child' points to the child task.
+ * A task is associated with the init_css_set until cgroup_post_fork()
+ * attaches it to the parent's css_set. Empty cg_list indicates that
+ * @child isn't holding reference to its css_set.
*/
void cgroup_fork(struct task_struct *child)
{
- task_lock(current);
- get_css_set(task_css_set(current));
- child->cgroups = current->cgroups;
- task_unlock(current);
+ RCU_INIT_POINTER(child->cgroups, &init_css_set);
INIT_LIST_HEAD(&child->cg_list);
}
int i;
/*
- * use_task_css_set_links is set to 1 before we walk the tasklist
- * under the tasklist_lock and we read it here after we added the child
- * to the tasklist under the tasklist_lock as well. If the child wasn't
- * yet in the tasklist when we walked through it from
- * cgroup_enable_task_cg_lists(), then use_task_css_set_links value
- * should be visible now due to the paired locking and barriers implied
- * by LOCK/UNLOCK: it is written before the tasklist_lock unlock
- * in cgroup_enable_task_cg_lists() and read here after the tasklist_lock
- * lock on fork.
+ * This may race against cgroup_enable_task_cg_links(). As that
+ * function sets use_task_css_set_links before grabbing
+ * tasklist_lock and we just went through tasklist_lock to add
+ * @child, it's guaranteed that either we see the set
+ * use_task_css_set_links or cgroup_enable_task_cg_lists() sees
+ * @child during its iteration.
+ *
+ * If we won the race, @child is associated with %current's
+ * css_set. Grabbing css_set_rwsem guarantees both that the
+ * association is stable, and, on completion of the parent's
+ * migration, @child is visible in the source of migration or
+ * already in the destination cgroup. This guarantee is necessary
+ * when implementing operations which need to migrate all tasks of
+ * a cgroup to another.
+ *
+ * Note that if we lose to cgroup_enable_task_cg_links(), @child
+ * will remain in init_css_set. This is safe because all tasks are
+ * in the init_css_set before cg_links is enabled and there's no
+ * operation which transfers all tasks out of init_css_set.
*/
if (use_task_css_set_links) {
+ struct css_set *cset;
+
down_write(&css_set_rwsem);
- task_lock(child);
- if (list_empty(&child->cg_list))
- list_add(&child->cg_list, &task_css_set(child)->tasks);
- task_unlock(child);
+ cset = task_css_set(current);
+ if (list_empty(&child->cg_list)) {
+ rcu_assign_pointer(child->cgroups, cset);
+ list_add(&child->cg_list, &cset->tasks);
+ get_css_set(cset);
+ }
up_write(&css_set_rwsem);
}
* use notify_on_release cgroups where very high task exit scaling
* is required on large systems.
*
- * the_top_cgroup_hack:
- *
- * Set the exiting tasks cgroup to the root cgroup (top_cgroup).
- *
- * We call cgroup_exit() while the task is still competent to
- * handle notify_on_release(), then leave the task attached to the
- * root cgroup in each hierarchy for the remainder of its exit.
- *
- * To do this properly, we would increment the reference count on
- * top_cgroup, and near the very end of the kernel/exit.c do_exit()
- * code we would add a second cgroup function call, to drop that
- * reference. This would just create an unnecessary hot spot on
- * the top_cgroup reference count, to no avail.
- *
- * Normally, holding a reference to a cgroup without bumping its
- * count is unsafe. The cgroup could go away, or someone could
- * attach us to a different cgroup, decrementing the count on
- * the first cgroup that we never incremented. But in this case,
- * top_cgroup isn't going away, and either task has PF_EXITING set,
- * which wards off any cgroup_attach_task() attempts, or task is a failed
- * fork, never visible to cgroup_attach_task.
+ * We set the exiting tasks cgroup to the root cgroup (top_cgroup). We
+ * call cgroup_exit() while the task is still competent to handle
+ * notify_on_release(), then leave the task attached to the root cgroup in
+ * each hierarchy for the remainder of its exit. No need to bother with
+ * init_css_set refcnting. init_css_set never goes away and we can't race
+ * with migration path - PF_EXITING is visible to migration path.
*/
void cgroup_exit(struct task_struct *tsk, int run_callbacks)
{
struct cgroup_subsys *ss;
struct css_set *cset;
+ bool put_cset = false;
int i;
/*
- * Unlink from the css_set task list if necessary. Optimistically
- * check cg_list before taking css_set_rwsem.
+ * Unlink from @tsk from its css_set. As migration path can't race
+ * with us, we can check cg_list without grabbing css_set_rwsem.
*/
if (!list_empty(&tsk->cg_list)) {
down_write(&css_set_rwsem);
- if (!list_empty(&tsk->cg_list))
- list_del_init(&tsk->cg_list);
+ list_del_init(&tsk->cg_list);
up_write(&css_set_rwsem);
+ put_cset = true;
}
/* Reassign the task to the init_css_set. */
- task_lock(tsk);
cset = task_css_set(tsk);
RCU_INIT_POINTER(tsk->cgroups, &init_css_set);
}
}
}
- task_unlock(tsk);
- put_css_set(cset, true);
+ if (put_cset)
+ put_css_set(cset, true);
}
static void check_for_release(struct cgroup *cgrp)
cset = rcu_dereference(current->cgroups);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
- const char *name = "?";
-
- if (c != cgroup_dummy_top) {
- cgroup_name(c, name_buf, NAME_MAX + 1);
- name = name_buf;
- }
+ cgroup_name(c, name_buf, NAME_MAX + 1);
seq_printf(seq, "Root %d group %s\n",
- c->root->hierarchy_id, name);
+ c->root->hierarchy_id, name_buf);
}
rcu_read_unlock();
up_read(&css_set_rwsem);
struct css_set *cset = link->cset;
struct task_struct *task;
int count = 0;
+
seq_printf(seq, "css_set %p\n", cset);
+
list_for_each_entry(task, &cset->tasks, cg_list) {
- if (count++ > MAX_TASKS_SHOWN_PER_CSS) {
- seq_puts(seq, " ...\n");
- break;
- } else {
- seq_printf(seq, " task %d\n",
- task_pid_vnr(task));
- }
+ if (count++ > MAX_TASKS_SHOWN_PER_CSS)
+ goto overflow;
+ seq_printf(seq, " task %d\n", task_pid_vnr(task));
+ }
+
+ list_for_each_entry(task, &cset->mg_tasks, cg_list) {
+ if (count++ > MAX_TASKS_SHOWN_PER_CSS)
+ goto overflow;
+ seq_printf(seq, " task %d\n", task_pid_vnr(task));
}
+ continue;
+ overflow:
+ seq_puts(seq, " ...\n");
}
up_read(&css_set_rwsem);
return 0;