*/
#include <linux/cgroup.h>
-#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/fs.h>
static int cgroup_call_pre_destroy(struct cgroup *cgrp)
{
struct cgroup_subsys *ss;
- struct cgroup_event *event, *tmp;
int ret = 0;
for_each_subsys(cgrp->root, ss)
if (ss->pre_destroy) {
ret = ss->pre_destroy(ss, cgrp);
if (ret)
- goto out;
+ break;
}
- /*
- * Unregister events and notify userspace.
- */
- spin_lock(&cgrp->event_list_lock);
- list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
- list_del(&event->list);
- eventfd_signal(event->eventfd, 1);
- schedule_work(&event->remove);
- }
- spin_unlock(&cgrp->event_list_lock);
-
-out:
return ret;
}
int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
{
char *start;
- struct dentry *dentry = rcu_dereference(cgrp->dentry);
+ struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
+ rcu_read_lock_held() ||
+ cgroup_lock_is_held());
if (!dentry || cgrp == dummytop) {
/*
*--start = '\0';
for (;;) {
int len = dentry->d_name.len;
+
if ((start -= len) < buf)
return -ENAMETOOLONG;
- memcpy(start, cgrp->dentry->d_name.name, len);
+ memcpy(start, dentry->d_name.name, len);
cgrp = cgrp->parent;
if (!cgrp)
break;
- dentry = rcu_dereference(cgrp->dentry);
+
+ dentry = rcu_dereference_check(cgrp->dentry,
+ rcu_read_lock_held() ||
+ cgroup_lock_is_held());
if (!cgrp->parent)
continue;
if (--start < buf)
event->cft->unregister_event(cgrp, event->cft, event->eventfd);
eventfd_ctx_put(event->eventfd);
- remove_wait_queue(event->wqh, &event->wait);
kfree(event);
+ dput(cgrp->dentry);
}
/*
unsigned long flags = (unsigned long)key;
if (flags & POLLHUP) {
+ __remove_wait_queue(event->wqh, &event->wait);
spin_lock(&cgrp->event_list_lock);
list_del(&event->list);
spin_unlock(&cgrp->event_list_lock);
goto fail;
}
+ /*
+ * Events should be removed after rmdir of cgroup directory, but before
+ * destroying subsystem state objects. Let's take reference to cgroup
+ * directory dentry to do that.
+ */
+ dget(cgrp->dentry);
+
spin_lock(&cgrp->event_list_lock);
list_add(&event->list, &cgrp->event_list);
spin_unlock(&cgrp->event_list_lock);
struct dentry *d;
struct cgroup *parent;
DEFINE_WAIT(wait);
+ struct cgroup_event *event, *tmp;
int ret;
/* the vfs holds both inode->i_mutex already */
set_bit(CGRP_RELEASABLE, &parent->flags);
check_for_release(parent);
+ /*
+ * Unregister events and notify userspace.
+ * Notify userspace about cgroup removing only after rmdir of cgroup
+ * directory to avoid race between userspace and kernelspace
+ */
+ spin_lock(&cgrp->event_list_lock);
+ list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
+ list_del(&event->list);
+ remove_wait_queue(event->wqh, &event->wait);
+ eventfd_signal(event->eventfd, 1);
+ schedule_work(&event->remove);
+ }
+ spin_unlock(&cgrp->event_list_lock);
+
mutex_unlock(&cgroup_mutex);
return 0;
}
* @ss: the subsystem to load
*
* This function should be called in a modular subsystem's initcall. If the
- * subsytem is built as a module, it will be assigned a new subsys_id and set
+ * subsystem is built as a module, it will be assigned a new subsys_id and set
* up for use. If the subsystem is built-in anyway, work is delegated to the
* simpler cgroup_init_subsys.
*/
*/
unsigned short css_id(struct cgroup_subsys_state *css)
{
- struct css_id *cssid = rcu_dereference(css->id);
+ struct css_id *cssid;
+
+ /*
+ * This css_id() can return correct value when somone has refcnt
+ * on this or this is under rcu_read_lock(). Once css->id is allocated,
+ * it's unchanged until freed.
+ */
+ cssid = rcu_dereference_check(css->id,
+ rcu_read_lock_held() || atomic_read(&css->refcnt));
if (cssid)
return cssid->id;
unsigned short css_depth(struct cgroup_subsys_state *css)
{
- struct css_id *cssid = rcu_dereference(css->id);
+ struct css_id *cssid;
+
+ cssid = rcu_dereference_check(css->id,
+ rcu_read_lock_held() || atomic_read(&css->refcnt));
if (cssid)
return cssid->depth;
}
EXPORT_SYMBOL_GPL(css_depth);
+/**
+ * css_is_ancestor - test "root" css is an ancestor of "child"
+ * @child: the css to be tested.
+ * @root: the css supporsed to be an ancestor of the child.
+ *
+ * Returns true if "root" is an ancestor of "child" in its hierarchy. Because
+ * this function reads css->id, this use rcu_dereference() and rcu_read_lock().
+ * But, considering usual usage, the csses should be valid objects after test.
+ * Assuming that the caller will do some action to the child if this returns
+ * returns true, the caller must take "child";s reference count.
+ * If "child" is valid object and this returns true, "root" is valid, too.
+ */
+
bool css_is_ancestor(struct cgroup_subsys_state *child,
const struct cgroup_subsys_state *root)
{
- struct css_id *child_id = rcu_dereference(child->id);
- struct css_id *root_id = rcu_dereference(root->id);
+ struct css_id *child_id;
+ struct css_id *root_id;
+ bool ret = true;
- if (!child_id || !root_id || (child_id->depth < root_id->depth))
- return false;
- return child_id->stack[root_id->depth] == root_id->id;
+ rcu_read_lock();
+ child_id = rcu_dereference(child->id);
+ root_id = rcu_dereference(root->id);
+ if (!child_id
+ || !root_id
+ || (child_id->depth < root_id->depth)
+ || (child_id->stack[root_id->depth] != root_id->id))
+ ret = false;
+ rcu_read_unlock();
+ return ret;
}
static void __free_css_id_cb(struct rcu_head *head)
{
int subsys_id, i, depth = 0;
struct cgroup_subsys_state *parent_css, *child_css;
- struct css_id *child_id, *parent_id = NULL;
+ struct css_id *child_id, *parent_id;
subsys_id = ss->subsys_id;
parent_css = parent->subsys[subsys_id];
child_css = child->subsys[subsys_id];
- depth = css_depth(parent_css) + 1;
parent_id = parent_css->id;
+ depth = parent_id->depth;
child_id = get_new_cssid(ss, depth);
if (IS_ERR(child_id))