cgroup.c

	struct cgroup_taskset tset = { };

	/*
	 * 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.
	 */
	group_size = get_nr_threads(leader);
	/* 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. */
	retval = flex_array_prealloc(group, 0, group_size - 1, GFP_KERNEL);
	if (retval)
		goto out_free_group_list;

	tsk = leader;
	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.
	 */
	rcu_read_lock();
	do {
		struct task_and_cgroup ent;

		/* @tsk either already exited or can't exit until the end */
		if (tsk->flags & PF_EXITING)
			continue;

		/* as per above, nr_threads may decrease, but not increase. */
		BUG_ON(i >= group_size);
		ent.task = tsk;
		ent.cgrp = task_cgroup_from_root(tsk, root);
		/* nothing to do if this task is already in the cgroup */
		if (ent.cgrp == cgrp)
			continue;
		/*
		 * saying GFP_ATOMIC has no effect here because we did prealloc
		 * earlier, but it's good form to communicate our expectations.
		 */
		retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
		BUG_ON(retval != 0);
		i++;
	} while_each_thread(leader, tsk);
	rcu_read_unlock();
	/* remember the number of threads in the array for later. */
	group_size = i;
	tset.tc_array = group;
	tset.tc_array_len = group_size;

	/* methods shouldn't be called if no task is actually migrating */
	retval = 0;
	if (!group_size)
		goto out_free_group_list;

	/*
	 * step 1: check that we can legitimately attach to the cgroup.
	 */
	for_each_subsys(root, ss) {
		if (ss->can_attach) {
			retval = ss->can_attach(cgrp, &tset);
			if (retval) {
				failed_ss = ss;
				goto out_cancel_attach;
			}
		}
	}

	/*
	 * 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++) {
		tc = flex_array_get(group, i);
		tc->cg = find_css_set(tc->task->cgroups, cgrp);
		if (!tc->cg) {
			retval = -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.
	 */
	for (i = 0; i < group_size; i++) {
		tc = flex_array_get(group, i);
		cgroup_task_migrate(cgrp, tc->cgrp, tc->task, tc->cg);
	}
	/* nothing is sensitive to fork() after this point. */

	/*
	 * step 4: do subsystem attach callbacks.
	 */
	for_each_subsys(root, ss) {
		if (ss->attach)
			ss->attach(cgrp, &tset);
	}

	/*
	 * step 5: success! and cleanup
	 */
	synchronize_rcu();
	cgroup_wakeup_rmdir_waiter(cgrp);
	retval = 0;
out_put_css_set_refs:
	if (retval) {
		for (i = 0; i < group_size; i++) {
			tc = flex_array_get(group, i);
			if (!tc->cg)
				break;
			put_css_set(tc->cg);
		}
	}
out_cancel_attach:
	if (retval) {
		for_each_subsys(root, ss) {
			if (ss == failed_ss)
				break;
			if (ss->cancel_attach)
				ss->cancel_attach(cgrp, &tset);
		}
	}
out_free_group_list:
	flex_array_free(group);
	return retval;
}

/*
 * 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.
 */
static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
{
	struct task_struct *tsk;
	const struct cred *cred = current_cred(), *tcred;
	int ret;

	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;

retry_find_task:
	rcu_read_lock();
	if (pid) {
		tsk = find_task_by_vpid(pid);
		if (!tsk) {
			rcu_read_unlock();
			ret= -ESRCH;
			goto out_unlock_cgroup;
		}
		/*
		 * even if we're attaching all tasks in the thread group, we
		 * only need to check permissions on one of them.
		 */
		tcred = __task_cred(tsk);
		if (cred->euid &&
		    cred->euid != tcred->uid &&
		    cred->euid != tcred->suid) {
			rcu_read_unlock();
			ret = -EACCES;
			goto out_unlock_cgroup;
		}
	} else
		tsk = current;

	if (threadgroup)
		tsk = tsk->group_leader;
	get_task_struct(tsk);
	rcu_read_unlock();

	threadgroup_lock(tsk);
	if (threadgroup) {
		if (!thread_group_leader(tsk)) {
			/*
			 * a race with de_thread from another thread's exec()
			 * may strip us of our leadership, if this happens,
			 * there is no choice but to throw this task away and
			 * try again; this is
			 * "double-double-toil-and-trouble-check locking".
			 */
			threadgroup_unlock(tsk);
			put_task_struct(tsk);
			goto retry_find_task;
		}
		ret = cgroup_attach_proc(cgrp, tsk);
	} else
		ret = cgroup_attach_task(cgrp, tsk);
	threadgroup_unlock(tsk);

	put_task_struct(tsk);
out_unlock_cgroup:
	cgroup_unlock();
	return ret;
}

static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
{
	return attach_task_by_pid(cgrp, pid, false);
}

static int cgroup_procs_write(struct cgroup *cgrp, struct cftype *cft, u64 tgid)
{
	return attach_task_by_pid(cgrp, tgid, true);
}

/**
 * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
 * @cgrp: the cgroup to be checked for liveness
 *
 * On success, returns true; the lock should be later released with
 * cgroup_unlock(). On failure returns false with no lock held.
 */
bool cgroup_lock_live_group(struct cgroup *cgrp)
{
	mutex_lock(&cgroup_mutex);
	if (cgroup_is_removed(cgrp)) {
		mutex_unlock(&cgroup_mutex);
		return false;
	}
	return true;
}
EXPORT_SYMBOL_GPL(cgroup_lock_live_group);

static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
				      const char *buffer)
{
	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
	if (strlen(buffer) >= PATH_MAX)
		return -EINVAL;
	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;
	mutex_lock(&cgroup_root_mutex);
	strcpy(cgrp->root->release_agent_path, buffer);
	mutex_unlock(&cgroup_root_mutex);
	cgroup_unlock();
	return 0;
}

static int cgroup_release_agent_show(struct cgroup *cgrp, struct cftype *cft,
				     struct seq_file *seq)
{
	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;
	seq_puts(seq, cgrp->root->release_agent_path);
	seq_putc(seq, '\n');
	cgroup_unlock();
	return 0;
}

/* A buffer size big enough for numbers or short strings */
#define CGROUP_LOCAL_BUFFER_SIZE 64

static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
				struct file *file,
				const char __user *userbuf,
				size_t nbytes, loff_t *unused_ppos)
{
	char buffer[CGROUP_LOCAL_BUFFER_SIZE];
	int retval = 0;
	char *end;

	if (!nbytes)
		return -EINVAL;
	if (nbytes >= sizeof(buffer))
		return -E2BIG;
	if (copy_from_user(buffer, userbuf, nbytes))
		return -EFAULT;

	buffer[nbytes] = 0;     /* nul-terminate */
	if (cft->write_u64) {
		u64 val = simple_strtoull(strstrip(buffer), &end, 0);
		if (*end)
			return -EINVAL;
		retval = cft->write_u64(cgrp, cft, val);
	} else {
		s64 val = simple_strtoll(strstrip(buffer), &end, 0);
		if (*end)
			return -EINVAL;
		retval = cft->write_s64(cgrp, cft, val);
	}
	if (!retval)
		retval = nbytes;
	return retval;
}

static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft,
				   struct file *file,
				   const char __user *userbuf,
				   size_t nbytes, loff_t *unused_ppos)
{
	char local_buffer[CGROUP_LOCAL_BUFFER_SIZE];
	int retval = 0;
	size_t max_bytes = cft->max_write_len;
	char *buffer = local_buffer;

	if (!max_bytes)
		max_bytes = sizeof(local_buffer) - 1;
	if (nbytes >= max_bytes)
		return -E2BIG;
	/* Allocate a dynamic buffer if we need one */
	if (nbytes >= sizeof(local_buffer)) {
		buffer = kmalloc(nbytes + 1, GFP_KERNEL);
		if (buffer == NULL)
			return -ENOMEM;
	}
	if (nbytes && copy_from_user(buffer, userbuf, nbytes)) {
		retval = -EFAULT;
		goto out;
	}

	buffer[nbytes] = 0;     /* nul-terminate */
	retval = cft->write_string(cgrp, cft, strstrip(buffer));
	if (!retval)
		retval = nbytes;
out:
	if (buffer != local_buffer)
		kfree(buffer);
	return retval;
}

static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
						size_t nbytes, loff_t *ppos)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);

	if (cgroup_is_removed(cgrp))
		return -ENODEV;
	if (cft->write)
		return cft->write(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->write_u64 || cft->write_s64)
		return cgroup_write_X64(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->write_string)
		return cgroup_write_string(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->trigger) {
		int ret = cft->trigger(cgrp, (unsigned int)cft->private);
		return ret ? ret : nbytes;
	}
	return -EINVAL;
}

static ssize_t cgroup_read_u64(struct cgroup *cgrp, struct cftype *cft,
			       struct file *file,
			       char __user *buf, size_t nbytes,
			       loff_t *ppos)
{
	char tmp[CGROUP_LOCAL_BUFFER_SIZE];
	u64 val = cft->read_u64(cgrp, cft);
	int len = sprintf(tmp, "%llu\n", (unsigned long long) val);

	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
}

static ssize_t cgroup_read_s64(struct cgroup *cgrp, struct cftype *cft,
			       struct file *file,
			       char __user *buf, size_t nbytes,
			       loff_t *ppos)
{
	char tmp[CGROUP_LOCAL_BUFFER_SIZE];
	s64 val = cft->read_s64(cgrp, cft);
	int len = sprintf(tmp, "%lld\n", (long long) val);

	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
}

static ssize_t cgroup_file_read(struct file *file, char __user *buf,
				   size_t nbytes, loff_t *ppos)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);

	if (cgroup_is_removed(cgrp))
		return -ENODEV;

	if (cft->read)
		return cft->read(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->read_u64)
		return cgroup_read_u64(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->read_s64)
		return cgroup_read_s64(cgrp, cft, file, buf, nbytes, ppos);
	return -EINVAL;
}

/*
 * seqfile ops/methods for returning structured data. Currently just
 * supports string->u64 maps, but can be extended in future.
 */

struct cgroup_seqfile_state {
	struct cftype *cft;
	struct cgroup *cgroup;
};

static int cgroup_map_add(struct cgroup_map_cb *cb, const char *key, u64 value)
{
	struct seq_file *sf = cb->state;
	return seq_printf(sf, "%s %llu\n", key, (unsigned long long)value);
}

static int cgroup_seqfile_show(struct seq_file *m, void *arg)
{
	struct cgroup_seqfile_state *state = m->private;
	struct cftype *cft = state->cft;
	if (cft->read_map) {
		struct cgroup_map_cb cb = {
			.fill = cgroup_map_add,
			.state = m,
		};
		return cft->read_map(state->cgroup, cft, &cb);
	}
	return cft->read_seq_string(state->cgroup, cft, m);
}

static int cgroup_seqfile_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq = file->private_data;
	kfree(seq->private);
	return single_release(inode, file);
}

static const struct file_operations cgroup_seqfile_operations = {
	.read = seq_read,
	.write = cgroup_file_write,
	.llseek = seq_lseek,
	.release = cgroup_seqfile_release,
};

static int cgroup_file_open(struct inode *inode, struct file *file)
{
	int err;
	struct cftype *cft;

	err = generic_file_open(inode, file);
	if (err)
		return err;
	cft = __d_cft(file->f_dentry);

	if (cft->read_map || cft->read_seq_string) {
		struct cgroup_seqfile_state *state =
			kzalloc(sizeof(*state), GFP_USER);
		if (!state)
			return -ENOMEM;
		state->cft = cft;
		state->cgroup = __d_cgrp(file->f_dentry->d_parent);
		file->f_op = &cgroup_seqfile_operations;
		err = single_open(file, cgroup_seqfile_show, state);
		if (err < 0)
			kfree(state);
	} else if (cft->open)
		err = cft->open(inode, file);
	else
		err = 0;

	return err;
}

static int cgroup_file_release(struct inode *inode, struct file *file)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	if (cft->release)
		return cft->release(inode, file);
	return 0;
}

/*
 * cgroup_rename - Only allow simple rename of directories in place.
 */
static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
			    struct inode *new_dir, struct dentry *new_dentry)
{
	if (!S_ISDIR(old_dentry->d_inode->i_mode))
		return -ENOTDIR;
	if (new_dentry->d_inode)
		return -EEXIST;
	if (old_dir != new_dir)
		return -EIO;
	return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
}

static const struct file_operations cgroup_file_operations = {
	.read = cgroup_file_read,
	.write = cgroup_file_write,
	.llseek = generic_file_llseek,
	.open = cgroup_file_open,
	.release = cgroup_file_release,
};

static const struct inode_operations cgroup_dir_inode_operations = {
	.lookup = cgroup_lookup,
	.mkdir = cgroup_mkdir,
	.rmdir = cgroup_rmdir,
	.rename = cgroup_rename,
};

static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
{
	if (dentry->d_name.len > NAME_MAX)
		return ERR_PTR(-ENAMETOOLONG);
	d_add(dentry, NULL);
	return NULL;
}

/*
 * 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, umode_t mode,
				struct super_block *sb)
{
	struct inode *inode;

	if (!dentry)
		return -ENOENT;
	if (dentry->d_inode)
		return -EEXIST;

	inode = cgroup_new_inode(mode, sb);
	if (!inode)
		return -ENOMEM;

	if (S_ISDIR(mode)) {
		inode->i_op = &cgroup_dir_inode_operations;
		inode->i_fop = &simple_dir_operations;

		/* start off with i_nlink == 2 (for "." entry) */
		inc_nlink(inode);

		/* start with the directory inode held, so that we can
		 * populate it without racing with another mkdir */
		mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
	} else if (S_ISREG(mode)) {
		inode->i_size = 0;
		inode->i_fop = &cgroup_file_operations;
	}
	d_instantiate(dentry, inode);
	dget(dentry);	/* Extra count - pin the dentry in core */
	return 0;
}

/*
 * cgroup_create_dir - create a directory for an object.
 * @cgrp: the cgroup we create the directory for. It must have a valid
 *        ->parent field. And we are going to fill its ->dentry field.
 * @dentry: dentry of the new cgroup
 * @mode: mode to set on new directory.
 */
static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
				umode_t mode)
{
	struct dentry *parent;
	int error = 0;

	parent = cgrp->parent->dentry;
	error = cgroup_create_file(dentry, S_IFDIR | mode, cgrp->root->sb);
	if (!error) {
		dentry->d_fsdata = cgrp;
		inc_nlink(parent->d_inode);
		rcu_assign_pointer(cgrp->dentry, dentry);
		dget(dentry);
	}
	dput(dentry);

	return error;
}

/**
 * cgroup_file_mode - deduce file mode of a control file
 * @cft: the control file in question
 *
 * returns cft->mode if ->mode is not 0
 * returns S_IRUGO|S_IWUSR if it has both a read and a write handler
 * returns S_IRUGO if it has only a read handler
 * returns S_IWUSR if it has only a write hander
 */
static umode_t cgroup_file_mode(const struct cftype *cft)
{
	umode_t mode = 0;

	if (cft->mode)
		return cft->mode;

	if (cft->read || cft->read_u64 || cft->read_s64 ||
	    cft->read_map || cft->read_seq_string)
		mode |= S_IRUGO;

	if (cft->write || cft->write_u64 || cft->write_s64 ||
	    cft->write_string || cft->trigger)
		mode |= S_IWUSR;

	return mode;
}

int cgroup_add_file(struct cgroup *cgrp,
		       struct cgroup_subsys *subsys,
		       const struct cftype *cft)
{
	struct dentry *dir = cgrp->dentry;
	struct dentry *dentry;
	int error;
	umode_t mode;

	char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
	if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
		strcpy(name, subsys->name);
		strcat(name, ".");
	}
	strcat(name, cft->name);
	BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));
	dentry = lookup_one_len(name, dir, strlen(name));
	if (!IS_ERR(dentry)) {
		mode = cgroup_file_mode(cft);
		error = cgroup_create_file(dentry, mode | S_IFREG,
						cgrp->root->sb);
		if (!error)
			dentry->d_fsdata = (void *)cft;
		dput(dentry);
	} else
		error = PTR_ERR(dentry);
	return error;
}
EXPORT_SYMBOL_GPL(cgroup_add_file);

int cgroup_add_files(struct cgroup *cgrp,
			struct cgroup_subsys *subsys,
			const struct cftype cft[],
			int count)
{
	int i, err;
	for (i = 0; i < count; i++) {
		err = cgroup_add_file(cgrp, subsys, &cft[i]);
		if (err)
			return err;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(cgroup_add_files);

/**
 * cgroup_task_count - count the number of tasks in a cgroup.
 * @cgrp: the cgroup in question
 *
 * Return the number of tasks in the cgroup.
 */
int cgroup_task_count(const struct cgroup *cgrp)
{
	int count = 0;
	struct cg_cgroup_link *link;

	read_lock(&css_set_lock);
	list_for_each_entry(link, &cgrp->css_sets, cgrp_link_list) {
		count += atomic_read(&link->cg->refcount);
	}
	read_unlock(&css_set_lock);
	return count;
}

/*
 * Advance a list_head iterator.  The iterator should be positioned at
 * the start of a css_set
 */
static void cgroup_advance_iter(struct cgroup *cgrp,
				struct cgroup_iter *it)
{
	struct list_head *l = it->cg_link;
	struct cg_cgroup_link *link;
	struct css_set *cg;

	/* Advance to the next non-empty css_set */
	do {
		l = l->next;
		if (l == &cgrp->css_sets) {
			it->cg_link = NULL;
			return;
		}
		link = list_entry(l, struct cg_cgroup_link, cgrp_link_list);
		cg = link->cg;
	} while (list_empty(&cg->tasks));
	it->cg_link = l;
	it->task = cg->tasks.next;
}

/*
 * To reduce the fork() overhead for systems that are not actually
 * using their cgroups capability, we don't maintain the lists running
 * through each css_set to its tasks until we see the list actually
 * used - in other words after the first call to cgroup_iter_start().
 */
static void cgroup_enable_task_cg_lists(void)
{
	struct task_struct *p, *g;
	write_lock(&css_set_lock);
	use_task_css_set_links = 1;
	/*
	 * We need tasklist_lock because RCU is not safe against
	 * while_each_thread(). Besides, a forking task that has passed
	 * cgroup_post_fork() without seeing use_task_css_set_links = 1
	 * is not guaranteed to have its child immediately visible in the
	 * tasklist if we walk through it with RCU.
	 */
	read_lock(&tasklist_lock);
	do_each_thread(g, p) {
		task_lock(p);
		/*
		 * 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.
		 */
		if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
			list_add(&p->cg_list, &p->cgroups->tasks);
		task_unlock(p);
	} while_each_thread(g, p);
	read_unlock(&tasklist_lock);
	write_unlock(&css_set_lock);
}

void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
	__acquires(css_set_lock)
{
	/*
	 * The first time anyone tries to iterate across a cgroup,
	 * we need to enable the list linking each css_set to its
	 * tasks, and fix up all existing tasks.
	 */
	if (!use_task_css_set_links)
		cgroup_enable_task_cg_lists();

	read_lock(&css_set_lock);
	it->cg_link = &cgrp->css_sets;
	cgroup_advance_iter(cgrp, it);
}

struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
					struct cgroup_iter *it)
{
	struct task_struct *res;
	struct list_head *l = it->task;
	struct cg_cgroup_link *link;

	/* If the iterator cg is NULL, we have no tasks */
	if (!it->cg_link)
		return NULL;
	res = list_entry(l, struct task_struct, cg_list);
	/* Advance iterator to find next entry */
	l = l->next;
	link = list_entry(it->cg_link, struct cg_cgroup_link, cgrp_link_list);
	if (l == &link->cg->tasks) {
		/* We reached the end of this task list - move on to
		 * the next cg_cgroup_link */
		cgroup_advance_iter(cgrp, it);
	} else {
		it->task = l;
	}
	return res;
}

void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it)
	__releases(css_set_lock)
{
	read_unlock(&css_set_lock);
}

static inline int started_after_time(struct task_struct *t1,
				     struct timespec *time,
				     struct task_struct *t2)
{
	int start_diff = timespec_compare(&t1->start_time, time);
	if (start_diff > 0) {
		return 1;
	} else if (start_diff < 0) {
		return 0;
	} else {
		/*
		 * Arbitrarily, if two processes started at the same
		 * time, we'll say that the lower pointer value
		 * started first. Note that t2 may have exited by now
		 * so this may not be a valid pointer any longer, but
		 * that's fine - it still serves to distinguish
		 * between two tasks started (effectively) simultaneously.
		 */
		return t1 > t2;
	}
}

/*
 * This function is a callback from heap_insert() and is used to order
 * the heap.
 * In this case we order the heap in descending task start time.
 */
static inline int started_after(void *p1, void *p2)
{
	struct task_struct *t1 = p1;
	struct task_struct *t2 = p2;
	return started_after_time(t1, &t2->start_time, t2);
}

/**
 * cgroup_scan_tasks - iterate though all the tasks in a cgroup
 * @scan: struct cgroup_scanner containing arguments for the scan
 *
 * Arguments include pointers to callback functions test_task() and
 * process_task().
 * Iterate through all the tasks in a cgroup, calling test_task() for each,
 * and if it returns true, call process_task() for it also.
 * The test_task pointer may be NULL, meaning always true (select all tasks).
 * Effectively duplicates cgroup_iter_{start,next,end}()
 * but does not lock css_set_lock for the call to process_task().
 * The struct cgroup_scanner may be embedded in any structure of the caller's
 * creation.
 * It is guaranteed that process_task() will act on every task that
 * is a member of the cgroup for the duration of this call. This
 * function may or may not call process_task() for tasks that exit
 * or move to a different cgroup during the call, or are forked or
 * move into the cgroup during the call.
 *
 * Note that test_task() may be called with locks held, and may in some
 * situations be called multiple times for the same task, so it should
 * be cheap.
 * If the heap pointer in the struct cgroup_scanner is non-NULL, a heap has been
 * pre-allocated and will be used for heap operations (and its "gt" member will
 * be overwritten), else a temporary heap will be used (allocation of which
 * may cause this function to fail).
 */
int cgroup_scan_tasks(struct cgroup_scanner *scan)
{
	int retval, i;
	struct cgroup_iter it;
	struct task_struct *p, *dropped;
	/* Never dereference latest_task, since it's not refcounted */
	struct task_struct *latest_task = NULL;
	struct ptr_heap tmp_heap;
	struct ptr_heap *heap;
	struct timespec latest_time = { 0, 0 };

	if (scan->heap) {
		/* The caller supplied our heap and pre-allocated its memory */
		heap = scan->heap;
		heap->gt = &started_after;
	} else {
		/* We need to allocate our own heap memory */
		heap = &tmp_heap;
		retval = heap_init(heap, PAGE_SIZE, GFP_KERNEL, &started_after);
		if (retval)
			/* cannot allocate the heap */
			return retval;
	}

 again:
	/*
	 * Scan tasks in the cgroup, using the scanner's "test_task" callback
	 * to determine which are of interest, and using the scanner's
	 * "process_task" callback to process any of them that need an update.
	 * Since we don't want to hold any locks during the task updates,
	 * gather tasks to be processed in a heap structure.
	 * The heap is sorted by descending task start time.
	 * If the statically-sized heap fills up, we overflow tasks that
	 * started later, and in future iterations only consider tasks that
	 * started after the latest task in the previous pass. This
	 * guarantees forward progress and that we don't miss any tasks.
	 */
	heap->size = 0;
	cgroup_iter_start(scan->cg, &it);
	while ((p = cgroup_iter_next(scan->cg, &it))) {
		/*
		 * Only affect tasks that qualify per the caller's callback,
		 * if he provided one
		 */
		if (scan->test_task && !scan->test_task(p, scan))
			continue;
		/*
		 * Only process tasks that started after the last task
		 * we processed
		 */
		if (!started_after_time(p, &latest_time, latest_task))
			continue;
		dropped = heap_insert(heap, p);
		if (dropped == NULL) {
			/*
			 * The new task was inserted; the heap wasn't
			 * previously full
			 */
			get_task_struct(p);
		} else if (dropped != p) {
			/*
			 * The new task was inserted, and pushed out a
			 * different task
			 */
			get_task_struct(p);
			put_task_struct(dropped);
		}
		/*
		 * Else the new task was newer than anything already in
		 * the heap and wasn't inserted
		 */
	}
	cgroup_iter_end(scan->cg, &it);

	if (heap->size) {
		for (i = 0; i < heap->size; i++) {
			struct task_struct *q = heap->ptrs[i];
			if (i == 0) {
				latest_time = q->start_time;
				latest_task = q;
			}
			/* Process the task per the caller's callback */
			scan->process_task(q, scan);
			put_task_struct(q);
		}
		/*
		 * If we had to process any tasks at all, scan again
		 * in case some of them were in the middle of forking
		 * children that didn't get processed.
		 * Not the most efficient way to do it, but it avoids
		 * having to take callback_mutex in the fork path
		 */
		goto again;
	}
	if (heap == &tmp_heap)
		heap_free(&tmp_heap);
	return 0;
}

/*
 * Stuff for reading the 'tasks'/'procs' files.
 *
 * Reading this file can return large amounts of data if a cgroup has
 * *lots* of attached tasks. So it may need several calls to read(),
 * but we cannot guarantee that the information we produce is correct
 * unless we produce it entirely atomically.
 *
 */

/* which pidlist file are we talking about? */
enum cgroup_filetype {
	CGROUP_FILE_PROCS,
	CGROUP_FILE_TASKS,
};

/*
 * A pidlist is a list of pids that virtually represents the contents of one
 * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists,
 * a pair (one each for procs, tasks) for each pid namespace that's relevant
 * to the cgroup.
 */
struct cgroup_pidlist {
	/*
	 * used to find which pidlist is wanted. doesn't change as long as
	 * this particular list stays in the list.
	*/
	struct { enum cgroup_filetype type; struct pid_namespace *ns; } key;
	/* array of xids */
	pid_t *list;
	/* how many elements the above list has */
	int length;
	/* how many files are using the current array */
	int use_count;
	/* each of these stored in a list by its cgroup */
	struct list_head links;
	/* pointer to the cgroup we belong to, for list removal purposes */
	struct cgroup *owner;
	/* protects the other fields */
	struct rw_semaphore mutex;
};

/*
 * The following two functions "fix" the issue where there are more pids
 * than kmalloc will give memory for; in such cases, we use vmalloc/vfree.
 * TODO: replace with a kernel-wide solution to this problem
 */
#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
static void *pidlist_allocate(int count)
{
	if (PIDLIST_TOO_LARGE(count))
		return vmalloc(count * sizeof(pid_t));
	else
		return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
}
static void pidlist_free(void *p)
{
	if (is_vmalloc_addr(p))
		vfree(p);
	else
		kfree(p);
}
static void *pidlist_resize(void *p, int newcount)
{
	void *newlist;
	/* note: if new alloc fails, old p will still be valid either way */