+
+/*
+ * 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 */
+static int proc_cgroup_show(struct seq_file *m, void *v)
+{
+ struct pid *pid;
+ struct task_struct *tsk;
+ char *buf;
+ int retval;
+ struct cgroupfs_root *root;
+
+ retval = -ENOMEM;
+ buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!buf)
+ goto out;
+
+ retval = -ESRCH;
+ pid = m->private;
+ tsk = get_pid_task(pid, PIDTYPE_PID);
+ if (!tsk)
+ goto out_free;
+
+ retval = 0;
+
+ mutex_lock(&cgroup_mutex);
+
+ for_each_root(root) {
+ struct cgroup_subsys *ss;
+ struct cgroup *cgrp;
+ int subsys_id;
+ int count = 0;
+
+ /* Skip this hierarchy if it has no active subsystems */
+ if (!root->actual_subsys_bits)
+ continue;
+ seq_printf(m, "%lu:", root->subsys_bits);
+ for_each_subsys(root, ss)
+ seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
+ seq_putc(m, ':');
+ get_first_subsys(&root->top_cgroup, NULL, &subsys_id);
+ cgrp = task_cgroup(tsk, subsys_id);
+ retval = cgroup_path(cgrp, buf, PAGE_SIZE);
+ if (retval < 0)
+ goto out_unlock;
+ seq_puts(m, buf);
+ seq_putc(m, '\n');
+ }
+
+out_unlock:
+ mutex_unlock(&cgroup_mutex);
+ put_task_struct(tsk);
+out_free:
+ kfree(buf);
+out:
+ return retval;
+}
+
+static int cgroup_open(struct inode *inode, struct file *file)
+{
+ struct pid *pid = PROC_I(inode)->pid;
+ return single_open(file, proc_cgroup_show, pid);
+}
+
+struct file_operations proc_cgroup_operations = {
+ .open = cgroup_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+/* Display information about each subsystem and each hierarchy */
+static int proc_cgroupstats_show(struct seq_file *m, void *v)
+{
+ int i;
+
+ seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
+ mutex_lock(&cgroup_mutex);
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ seq_printf(m, "%s\t%lu\t%d\t%d\n",
+ ss->name, ss->root->subsys_bits,
+ ss->root->number_of_cgroups, !ss->disabled);
+ }
+ mutex_unlock(&cgroup_mutex);
+ return 0;
+}
+
+static int cgroupstats_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, proc_cgroupstats_show, NULL);
+}
+
+static struct file_operations proc_cgroupstats_operations = {
+ .open = cgroupstats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+/**
+ * cgroup_fork - attach newly forked task to its parents cgroup.
+ * @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.
+ */
+void cgroup_fork(struct task_struct *child)
+{
+ task_lock(current);
+ child->cgroups = current->cgroups;
+ get_css_set(child->cgroups);
+ task_unlock(current);
+ INIT_LIST_HEAD(&child->cg_list);
+}
+
+/**
+ * cgroup_fork_callbacks - run fork callbacks
+ * @child: the new task
+ *
+ * Called on a new task very soon before adding it to the
+ * tasklist. No need to take any locks since no-one can
+ * be operating on this task.
+ */
+void cgroup_fork_callbacks(struct task_struct *child)
+{
+ if (need_forkexit_callback) {
+ int i;
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss->fork)
+ ss->fork(ss, child);
+ }
+ }
+}
+
+#ifdef CONFIG_MM_OWNER
+/**
+ * cgroup_mm_owner_callbacks - run callbacks when the mm->owner changes
+ * @p: the new owner
+ *
+ * Called on every change to mm->owner. mm_init_owner() does not
+ * invoke this routine, since it assigns the mm->owner the first time
+ * and does not change it.
+ */
+void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
+{
+ struct cgroup *oldcgrp, *newcgrp;
+
+ if (need_mm_owner_callback) {
+ int i;
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ oldcgrp = task_cgroup(old, ss->subsys_id);
+ newcgrp = task_cgroup(new, ss->subsys_id);
+ if (oldcgrp == newcgrp)
+ continue;
+ if (ss->mm_owner_changed)
+ ss->mm_owner_changed(ss, oldcgrp, newcgrp);
+ }
+ }
+}
+#endif /* CONFIG_MM_OWNER */
+
+/**
+ * cgroup_post_fork - called on a new task after adding it to the task list
+ * @child: the task in question
+ *
+ * Adds the task to the list running through its css_set if necessary.
+ * Has to be after the task is visible on the task list in case we race
+ * with the first call to cgroup_iter_start() - to guarantee that the
+ * new task ends up on its list.
+ */
+void cgroup_post_fork(struct task_struct *child)
+{
+ if (use_task_css_set_links) {
+ write_lock(&css_set_lock);
+ if (list_empty(&child->cg_list))
+ list_add(&child->cg_list, &child->cgroups->tasks);
+ write_unlock(&css_set_lock);
+ }
+}
+/**
+ * cgroup_exit - detach cgroup from exiting task
+ * @tsk: pointer to task_struct of exiting process
+ * @run_callback: run exit callbacks?
+ *
+ * Description: Detach cgroup from @tsk and release it.
+ *
+ * Note that cgroups marked notify_on_release force every task in
+ * them to take the global cgroup_mutex mutex when exiting.
+ * This could impact scaling on very large systems. Be reluctant to
+ * 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.
+ */
+void cgroup_exit(struct task_struct *tsk, int run_callbacks)
+{
+ int i;
+ struct css_set *cg;
+
+ if (run_callbacks && need_forkexit_callback) {
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss->exit)
+ ss->exit(ss, tsk);
+ }
+ }
+
+ /*
+ * Unlink from the css_set task list if necessary.
+ * Optimistically check cg_list before taking
+ * css_set_lock
+ */
+ if (!list_empty(&tsk->cg_list)) {
+ write_lock(&css_set_lock);
+ if (!list_empty(&tsk->cg_list))
+ list_del(&tsk->cg_list);
+ write_unlock(&css_set_lock);
+ }
+
+ /* Reassign the task to the init_css_set. */
+ task_lock(tsk);
+ cg = tsk->cgroups;
+ tsk->cgroups = &init_css_set;
+ task_unlock(tsk);
+ if (cg)
+ put_css_set_taskexit(cg);
+}
+
+/**
+ * cgroup_clone - clone the cgroup the given subsystem is attached to
+ * @tsk: the task to be moved
+ * @subsys: the given subsystem
+ *
+ * Duplicate the current cgroup in the hierarchy that the given
+ * subsystem is attached to, and move this task into the new
+ * child.
+ */
+int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys)
+{
+ struct dentry *dentry;
+ int ret = 0;
+ char nodename[MAX_CGROUP_TYPE_NAMELEN];
+ struct cgroup *parent, *child;
+ struct inode *inode;
+ struct css_set *cg;
+ struct cgroupfs_root *root;
+ struct cgroup_subsys *ss;
+
+ /* We shouldn't be called by an unregistered subsystem */
+ BUG_ON(!subsys->active);
+
+ /* First figure out what hierarchy and cgroup we're dealing
+ * with, and pin them so we can drop cgroup_mutex */
+ mutex_lock(&cgroup_mutex);
+ again:
+ root = subsys->root;
+ if (root == &rootnode) {
+ printk(KERN_INFO
+ "Not cloning cgroup for unused subsystem %s\n",
+ subsys->name);
+ mutex_unlock(&cgroup_mutex);
+ return 0;
+ }
+ cg = tsk->cgroups;
+ parent = task_cgroup(tsk, subsys->subsys_id);
+
+ snprintf(nodename, MAX_CGROUP_TYPE_NAMELEN, "%d", tsk->pid);
+
+ /* Pin the hierarchy */
+ atomic_inc(&parent->root->sb->s_active);
+
+ /* Keep the cgroup alive */
+ get_css_set(cg);
+ mutex_unlock(&cgroup_mutex);
+
+ /* Now do the VFS work to create a cgroup */
+ inode = parent->dentry->d_inode;
+
+ /* Hold the parent directory mutex across this operation to
+ * stop anyone else deleting the new cgroup */
+ mutex_lock(&inode->i_mutex);
+ dentry = lookup_one_len(nodename, parent->dentry, strlen(nodename));
+ if (IS_ERR(dentry)) {
+ printk(KERN_INFO
+ "cgroup: Couldn't allocate dentry for %s: %ld\n", nodename,
+ PTR_ERR(dentry));
+ ret = PTR_ERR(dentry);
+ goto out_release;
+ }
+
+ /* Create the cgroup directory, which also creates the cgroup */
+ ret = vfs_mkdir(inode, dentry, S_IFDIR | 0755);
+ child = __d_cgrp(dentry);
+ dput(dentry);
+ if (ret) {
+ printk(KERN_INFO
+ "Failed to create cgroup %s: %d\n", nodename,
+ ret);
+ goto out_release;
+ }
+
+ if (!child) {
+ printk(KERN_INFO
+ "Couldn't find new cgroup %s\n", nodename);
+ ret = -ENOMEM;
+ goto out_release;
+ }
+
+ /* The cgroup now exists. Retake cgroup_mutex and check
+ * that we're still in the same state that we thought we
+ * were. */
+ mutex_lock(&cgroup_mutex);
+ if ((root != subsys->root) ||
+ (parent != task_cgroup(tsk, subsys->subsys_id))) {
+ /* Aargh, we raced ... */
+ mutex_unlock(&inode->i_mutex);
+ put_css_set(cg);
+
+ deactivate_super(parent->root->sb);
+ /* The cgroup is still accessible in the VFS, but
+ * we're not going to try to rmdir() it at this
+ * point. */
+ printk(KERN_INFO
+ "Race in cgroup_clone() - leaking cgroup %s\n",
+ nodename);
+ goto again;
+ }
+
+ /* do any required auto-setup */
+ for_each_subsys(root, ss) {
+ if (ss->post_clone)
+ ss->post_clone(ss, child);
+ }
+
+ /* All seems fine. Finish by moving the task into the new cgroup */
+ ret = cgroup_attach_task(child, tsk);
+ mutex_unlock(&cgroup_mutex);
+
+ out_release:
+ mutex_unlock(&inode->i_mutex);
+
+ mutex_lock(&cgroup_mutex);
+ put_css_set(cg);
+ mutex_unlock(&cgroup_mutex);
+ deactivate_super(parent->root->sb);
+ return ret;
+}
+
+/**
+ * cgroup_is_descendant - see if @cgrp is a descendant of current task's cgrp
+ * @cgrp: the cgroup in question
+ *
+ * See if @cgrp is a descendant of the current task's cgroup in
+ * the appropriate hierarchy.
+ *
+ * If we are sending in dummytop, then presumably we are creating
+ * the top cgroup in the subsystem.
+ *
+ * Called only by the ns (nsproxy) cgroup.
+ */
+int cgroup_is_descendant(const struct cgroup *cgrp)
+{
+ int ret;
+ struct cgroup *target;
+ int subsys_id;
+
+ if (cgrp == dummytop)
+ return 1;
+
+ get_first_subsys(cgrp, NULL, &subsys_id);
+ target = task_cgroup(current, subsys_id);
+ while (cgrp != target && cgrp!= cgrp->top_cgroup)
+ cgrp = cgrp->parent;
+ ret = (cgrp == target);
+ return ret;
+}
+
+static void check_for_release(struct cgroup *cgrp)
+{
+ /* All of these checks rely on RCU to keep the cgroup
+ * structure alive */
+ if (cgroup_is_releasable(cgrp) && !atomic_read(&cgrp->count)
+ && list_empty(&cgrp->children) && !cgroup_has_css_refs(cgrp)) {
+ /* Control Group is currently removeable. If it's not
+ * already queued for a userspace notification, queue
+ * it now */
+ int need_schedule_work = 0;
+ spin_lock(&release_list_lock);
+ if (!cgroup_is_removed(cgrp) &&
+ list_empty(&cgrp->release_list)) {
+ list_add(&cgrp->release_list, &release_list);
+ need_schedule_work = 1;
+ }
+ spin_unlock(&release_list_lock);
+ if (need_schedule_work)
+ schedule_work(&release_agent_work);
+ }
+}
+
+void __css_put(struct cgroup_subsys_state *css)
+{
+ struct cgroup *cgrp = css->cgroup;
+ rcu_read_lock();
+ if (atomic_dec_and_test(&css->refcnt) && notify_on_release(cgrp)) {
+ set_bit(CGRP_RELEASABLE, &cgrp->flags);
+ check_for_release(cgrp);
+ }
+ rcu_read_unlock();
+}
+
+/*
+ * Notify userspace when a cgroup is released, by running the
+ * configured release agent with the name of the cgroup (path
+ * relative to the root of cgroup file system) as the argument.
+ *
+ * Most likely, this user command will try to rmdir this cgroup.
+ *
+ * This races with the possibility that some other task will be
+ * attached to this cgroup before it is removed, or that some other
+ * user task will 'mkdir' a child cgroup of this cgroup. That's ok.
+ * The presumed 'rmdir' will fail quietly if this cgroup is no longer
+ * unused, and this cgroup will be reprieved from its death sentence,
+ * to continue to serve a useful existence. Next time it's released,
+ * we will get notified again, if it still has 'notify_on_release' set.
+ *
+ * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which
+ * means only wait until the task is successfully execve()'d. The
+ * separate release agent task is forked by call_usermodehelper(),
+ * then control in this thread returns here, without waiting for the
+ * release agent task. We don't bother to wait because the caller of
+ * this routine has no use for the exit status of the release agent
+ * task, so no sense holding our caller up for that.
+ */
+static void cgroup_release_agent(struct work_struct *work)
+{
+ BUG_ON(work != &release_agent_work);
+ mutex_lock(&cgroup_mutex);
+ spin_lock(&release_list_lock);
+ while (!list_empty(&release_list)) {
+ char *argv[3], *envp[3];
+ int i;
+ char *pathbuf;
+ struct cgroup *cgrp = list_entry(release_list.next,
+ struct cgroup,
+ release_list);
+ list_del_init(&cgrp->release_list);
+ spin_unlock(&release_list_lock);
+ pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!pathbuf) {
+ spin_lock(&release_list_lock);
+ continue;
+ }
+
+ if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0) {
+ kfree(pathbuf);
+ spin_lock(&release_list_lock);
+ continue;
+ }
+
+ i = 0;
+ argv[i++] = cgrp->root->release_agent_path;
+ argv[i++] = (char *)pathbuf;
+ argv[i] = NULL;
+
+ i = 0;
+ /* minimal command environment */
+ envp[i++] = "HOME=/";
+ envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
+ envp[i] = NULL;
+
+ /* Drop the lock while we invoke the usermode helper,
+ * since the exec could involve hitting disk and hence
+ * be a slow process */
+ mutex_unlock(&cgroup_mutex);
+ call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+ kfree(pathbuf);
+ mutex_lock(&cgroup_mutex);
+ spin_lock(&release_list_lock);
+ }
+ spin_unlock(&release_list_lock);
+ mutex_unlock(&cgroup_mutex);
+}
+
+static int __init cgroup_disable(char *str)
+{
+ int i;
+ char *token;
+
+ while ((token = strsep(&str, ",")) != NULL) {
+ if (!*token)
+ continue;
+
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+
+ if (!strcmp(token, ss->name)) {
+ ss->disabled = 1;
+ printk(KERN_INFO "Disabling %s control group"
+ " subsystem\n", ss->name);
+ break;
+ }
+ }
+ }
+ return 1;
+}
+__setup("cgroup_disable=", cgroup_disable);