* Based originally on the cpuset system, extracted by Paul Menage
* Copyright (C) 2006 Google, Inc
*
+ * Notifications support
+ * Copyright (C) 2009 Nokia Corporation
+ * Author: Kirill A. Shutemov
+ *
* Copyright notices from the original cpuset code:
* --------------------------------------------------
* Copyright (C) 2003 BULL SA.
*/
#include <linux/cgroup.h>
-#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/pid_namespace.h>
#include <linux/idr.h>
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
+#include <linux/eventfd.h>
+#include <linux/poll.h>
#include <asm/atomic.h>
unsigned short stack[0]; /* Array of Length (depth+1) */
};
+/*
+ * cgroup_event represents events which userspace want to recieve.
+ */
+struct cgroup_event {
+ /*
+ * Cgroup which the event belongs to.
+ */
+ struct cgroup *cgrp;
+ /*
+ * Control file which the event associated.
+ */
+ struct cftype *cft;
+ /*
+ * eventfd to signal userspace about the event.
+ */
+ struct eventfd_ctx *eventfd;
+ /*
+ * Each of these stored in a list by the cgroup.
+ */
+ struct list_head list;
+ /*
+ * All fields below needed to unregister event when
+ * userspace closes eventfd.
+ */
+ poll_table pt;
+ wait_queue_head_t *wqh;
+ wait_queue_t wait;
+ struct work_struct remove;
+};
/* The list of hierarchy roots */
{
mutex_lock(&cgroup_mutex);
}
+EXPORT_SYMBOL_GPL(cgroup_lock);
/**
* cgroup_unlock - release lock on cgroup changes
{
mutex_unlock(&cgroup_mutex);
}
+EXPORT_SYMBOL_GPL(cgroup_unlock);
/*
* A couple of forward declarations required, due to cyclic reference loop:
if (ret)
break;
}
+
return ret;
}
INIT_LIST_HEAD(&cgrp->release_list);
INIT_LIST_HEAD(&cgrp->pidlists);
mutex_init(&cgrp->pidlist_mutex);
+ INIT_LIST_HEAD(&cgrp->event_list);
+ spin_lock_init(&cgrp->event_list_lock);
}
static void init_cgroup_root(struct cgroupfs_root *root)
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)
memmove(buf, start, buf + buflen - start);
return 0;
}
+EXPORT_SYMBOL_GPL(cgroup_path);
/**
* cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
}
return true;
}
+EXPORT_SYMBOL_GPL(cgroup_lock_live_group);
static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
const char *buffer)
.rename = cgroup_rename,
};
+/*
+ * Check if a file is a control file
+ */
+static inline struct cftype *__file_cft(struct file *file)
+{
+ if (file->f_dentry->d_inode->i_fop != &cgroup_file_operations)
+ return ERR_PTR(-EINVAL);
+ return __d_cft(file->f_dentry);
+}
+
static int cgroup_create_file(struct dentry *dentry, mode_t mode,
struct super_block *sb)
{
{
struct cgroup_pidlist *l;
/* don't need task_nsproxy() if we're looking at ourself */
- struct pid_namespace *ns = get_pid_ns(current->nsproxy->pid_ns);
+ struct pid_namespace *ns = current->nsproxy->pid_ns;
+
/*
* We can't drop the pidlist_mutex before taking the l->mutex in case
* the last ref-holder is trying to remove l from the list at the same
mutex_lock(&cgrp->pidlist_mutex);
list_for_each_entry(l, &cgrp->pidlists, links) {
if (l->key.type == type && l->key.ns == ns) {
- /* found a matching list - drop the extra refcount */
- put_pid_ns(ns);
/* make sure l doesn't vanish out from under us */
down_write(&l->mutex);
mutex_unlock(&cgrp->pidlist_mutex);
l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
if (!l) {
mutex_unlock(&cgrp->pidlist_mutex);
- put_pid_ns(ns);
return l;
}
init_rwsem(&l->mutex);
down_write(&l->mutex);
l->key.type = type;
- l->key.ns = ns;
+ l->key.ns = get_pid_ns(ns);
l->use_count = 0; /* don't increment here */
l->list = NULL;
l->owner = cgrp;
}
/*
+ * Unregister event and free resources.
+ *
+ * Gets called from workqueue.
+ */
+static void cgroup_event_remove(struct work_struct *work)
+{
+ struct cgroup_event *event = container_of(work, struct cgroup_event,
+ remove);
+ struct cgroup *cgrp = event->cgrp;
+
+ /* TODO: check return code */
+ event->cft->unregister_event(cgrp, event->cft, event->eventfd);
+
+ eventfd_ctx_put(event->eventfd);
+ kfree(event);
+ dput(cgrp->dentry);
+}
+
+/*
+ * Gets called on POLLHUP on eventfd when user closes it.
+ *
+ * Called with wqh->lock held and interrupts disabled.
+ */
+static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
+ int sync, void *key)
+{
+ struct cgroup_event *event = container_of(wait,
+ struct cgroup_event, wait);
+ struct cgroup *cgrp = event->cgrp;
+ 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);
+ /*
+ * We are in atomic context, but cgroup_event_remove() may
+ * sleep, so we have to call it in workqueue.
+ */
+ schedule_work(&event->remove);
+ }
+
+ return 0;
+}
+
+static void cgroup_event_ptable_queue_proc(struct file *file,
+ wait_queue_head_t *wqh, poll_table *pt)
+{
+ struct cgroup_event *event = container_of(pt,
+ struct cgroup_event, pt);
+
+ event->wqh = wqh;
+ add_wait_queue(wqh, &event->wait);
+}
+
+/*
+ * Parse input and register new cgroup event handler.
+ *
+ * Input must be in format '<event_fd> <control_fd> <args>'.
+ * Interpretation of args is defined by control file implementation.
+ */
+static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft,
+ const char *buffer)
+{
+ struct cgroup_event *event = NULL;
+ unsigned int efd, cfd;
+ struct file *efile = NULL;
+ struct file *cfile = NULL;
+ char *endp;
+ int ret;
+
+ efd = simple_strtoul(buffer, &endp, 10);
+ if (*endp != ' ')
+ return -EINVAL;
+ buffer = endp + 1;
+
+ cfd = simple_strtoul(buffer, &endp, 10);
+ if ((*endp != ' ') && (*endp != '\0'))
+ return -EINVAL;
+ buffer = endp + 1;
+
+ event = kzalloc(sizeof(*event), GFP_KERNEL);
+ if (!event)
+ return -ENOMEM;
+ event->cgrp = cgrp;
+ INIT_LIST_HEAD(&event->list);
+ init_poll_funcptr(&event->pt, cgroup_event_ptable_queue_proc);
+ init_waitqueue_func_entry(&event->wait, cgroup_event_wake);
+ INIT_WORK(&event->remove, cgroup_event_remove);
+
+ efile = eventfd_fget(efd);
+ if (IS_ERR(efile)) {
+ ret = PTR_ERR(efile);
+ goto fail;
+ }
+
+ event->eventfd = eventfd_ctx_fileget(efile);
+ if (IS_ERR(event->eventfd)) {
+ ret = PTR_ERR(event->eventfd);
+ goto fail;
+ }
+
+ cfile = fget(cfd);
+ if (!cfile) {
+ ret = -EBADF;
+ goto fail;
+ }
+
+ /* the process need read permission on control file */
+ ret = file_permission(cfile, MAY_READ);
+ if (ret < 0)
+ goto fail;
+
+ event->cft = __file_cft(cfile);
+ if (IS_ERR(event->cft)) {
+ ret = PTR_ERR(event->cft);
+ goto fail;
+ }
+
+ if (!event->cft->register_event || !event->cft->unregister_event) {
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ ret = event->cft->register_event(cgrp, event->cft,
+ event->eventfd, buffer);
+ if (ret)
+ goto fail;
+
+ if (efile->f_op->poll(efile, &event->pt) & POLLHUP) {
+ event->cft->unregister_event(cgrp, event->cft, event->eventfd);
+ ret = 0;
+ 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);
+
+ fput(cfile);
+ fput(efile);
+
+ return 0;
+
+fail:
+ if (cfile)
+ fput(cfile);
+
+ if (event && event->eventfd && !IS_ERR(event->eventfd))
+ eventfd_ctx_put(event->eventfd);
+
+ if (!IS_ERR_OR_NULL(efile))
+ fput(efile);
+
+ kfree(event);
+
+ return ret;
+}
+
+/*
* for the common functions, 'private' gives the type of file
*/
/* for hysterical raisins, we can't put this on the older files */
.read_u64 = cgroup_read_notify_on_release,
.write_u64 = cgroup_write_notify_on_release,
},
+ {
+ .name = CGROUP_FILE_GENERIC_PREFIX "event_control",
+ .write_string = cgroup_write_event_control,
+ .mode = S_IWUGO,
+ },
};
static struct cftype cft_release_agent = {
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.
*/
rcu_read_unlock();
WARN_ON_ONCE(val < 1);
}
+EXPORT_SYMBOL_GPL(__css_put);
/*
* Notify userspace when a cgroup is released, by running the
*/
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;
return 0;
}
+EXPORT_SYMBOL_GPL(css_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;
return 0;
}
+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)
spin_unlock(&ss->id_lock);
call_rcu(&id->rcu_head, __free_css_id_cb);
}
+EXPORT_SYMBOL_GPL(free_css_id);
/*
* This is called by init or create(). Then, calls to this function are
{
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))
return rcu_dereference(cssid->css);
}
+EXPORT_SYMBOL_GPL(css_lookup);
/**
* css_get_next - lookup next cgroup under specified hierarchy.