linux cgroup (4)----attach task

当向一个cgroup目录的tasks节点写入一个pid时，调用该cftype对应的write方法cgroup1_tasks_write，该方法找到pid对应的struct task，将其作为参数调用cgroup_attach_task.

	{
		.name = "tasks",
		.seq_start = cgroup_pidlist_start,
		.seq_next = cgroup_pidlist_next,
		.seq_stop = cgroup_pidlist_stop,
		.seq_show = cgroup_pidlist_show,
		.private = CGROUP_FILE_TASKS,
		.write = cgroup1_tasks_write,
	},

cgroup_attach_task

在attach task的过程中会使用一个结构体cgroup_mgctx维持这个活动。

int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
		       bool threadgroup)
{
	DEFINE_CGROUP_MGCTX(mgctx);
	struct task_struct *task;
	int ret;

	ret = cgroup_migrate_vet_dst(dst_cgrp);
	if (ret)
		return ret;

	/* look up all src csets */
	spin_lock_irq(&css_set_lock);
	rcu_read_lock();
	task = leader;
	do {
		cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &mgctx);
		//获取task所在css_set作为迁移过程中的源css_set(src_cst)，设置src_cst的mg_src_cgrp、mg_dst_cgrp,将src_cst连接到mgctx的preloaded_src_csets
		if (!threadgroup)
			break;
	} while_each_thread(leader, task);
	rcu_read_unlock();
	spin_unlock_irq(&css_set_lock);

	/* prepare dst csets and commit */
	ret = cgroup_migrate_prepare_dst(&mgctx); //查找或创建dst_cst，设置mgctx的ss_mask、preloaded_dst_csets。
	if (!ret)
		ret = cgroup_migrate(leader, threadgroup, &mgctx);//将task的cg_list接入dst_cst的tasks链表，

	cgroup_migrate_finish(&mgctx);

	if (!ret)
		TRACE_CGROUP_PATH(attach_task, dst_cgrp, leader, threadgroup);

	return ret;
}

cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &mgctx)

void cgroup_migrate_add_src(struct css_set *src_cset,
			    struct cgroup *dst_cgrp,
			    struct cgroup_mgctx *mgctx)
{
	struct cgroup *src_cgrp;

	lockdep_assert_held(&cgroup_mutex);
	lockdep_assert_held(&css_set_lock);

	/*
	 * If ->dead, @src_set is associated with one or more dead cgroups
	 * and doesn't contain any migratable tasks.  Ignore it early so
	 * that the rest of migration path doesn't get confused by it.
	 */
	if (src_cset->dead)
		return;

	src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);

	if (!list_empty(&src_cset->mg_preload_node))
		return;

	WARN_ON(src_cset->mg_src_cgrp);
	WARN_ON(src_cset->mg_dst_cgrp);
	WARN_ON(!list_empty(&src_cset->mg_tasks));
	WARN_ON(!list_empty(&src_cset->mg_node));

	src_cset->mg_src_cgrp = src_cgrp;
	src_cset->mg_dst_cgrp = dst_cgrp;
	get_css_set(src_cset);
	list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets);
}

cgroup_migrate_prepare_dst(&mgctx)

int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
{
	struct css_set *src_cset, *tmp_cset;

	lockdep_assert_held(&cgroup_mutex);

	/* look up the dst cset for each src cset and link it to src */
	list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets,
				 mg_preload_node) {
		struct css_set *dst_cset;
		struct cgroup_subsys *ss;
		int ssid;

		dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp);
		if (!dst_cset)
			goto err;

		WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset);

		/*
		 * If src cset equals dst, it's noop.  Drop the src.
		 * cgroup_migrate() will skip the cset too.  Note that we
		 * can't handle src == dst as some nodes are used by both.
		 */
		if (src_cset == dst_cset) {
			src_cset->mg_src_cgrp = NULL;
			src_cset->mg_dst_cgrp = NULL;
			list_del_init(&src_cset->mg_preload_node);
			put_css_set(src_cset);
			put_css_set(dst_cset);
			continue;
		}

		src_cset->mg_dst_cset = dst_cset;

		if (list_empty(&dst_cset->mg_preload_node))
			list_add_tail(&dst_cset->mg_preload_node,
				      &mgctx->preloaded_dst_csets);
		else
			put_css_set(dst_cset);

		for_each_subsys(ss, ssid)
			if (src_cset->subsys[ssid] != dst_cset->subsys[ssid])
				mgctx->ss_mask |= 1 << ssid;
	}

	return 0;
err:
	cgroup_migrate_finish(mgctx);
	return -ENOMEM;
}

cgroup_migrate(leader, threadgroup, &mgctx)

int cgroup_migrate(struct task_struct *leader, bool threadgroup,
		   struct cgroup_mgctx *mgctx)
{
	struct task_struct *task;

	/*
	 * 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.
	 */
	spin_lock_irq(&css_set_lock);
	rcu_read_lock();
	task = leader;
	do {
		cgroup_migrate_add_task(task, mgctx);
		if (!threadgroup)
			break;
	} while_each_thread(leader, task);
	rcu_read_unlock();
	spin_unlock_irq(&css_set_lock);

	return cgroup_migrate_execute(mgctx);
}

cgroup_migrate_add_task(task, mgctx);

static void cgroup_migrate_add_task(struct task_struct *task,
				    struct cgroup_mgctx *mgctx)
{
	struct css_set *cset;

	lockdep_assert_held(&css_set_lock);

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

	/* leave @task alone if post_fork() hasn't linked it yet */
	if (list_empty(&task->cg_list))
		return;

	cset = task_css_set(task);
	if (!cset->mg_src_cgrp)
		return;

	mgctx->tset.nr_tasks++;

	list_move_tail(&task->cg_list, &cset->mg_tasks);
	if (list_empty(&cset->mg_node))
		list_add_tail(&cset->mg_node,
			      &mgctx->tset.src_csets);
	if (list_empty(&cset->mg_dst_cset->mg_node))
		list_add_tail(&cset->mg_dst_cset->mg_node,
			      &mgctx->tset.dst_csets);
}

cgroup_migrate_execute(mgctx)

static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
{
	struct cgroup_taskset *tset = &mgctx->tset;
	struct cgroup_subsys *ss;
	struct task_struct *task, *tmp_task;
	struct css_set *cset, *tmp_cset;
	int ssid, failed_ssid, ret;

	/* check that we can legitimately attach to the cgroup */
	if (tset->nr_tasks) {
		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
			if (ss->can_attach) {
				tset->ssid = ssid;
				ret = ss->can_attach(tset);
				if (ret) {
					failed_ssid = ssid;
					goto out_cancel_attach;
				}
			}
		} while_each_subsys_mask();
	}

	/*
	 * 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.
	 */
	spin_lock_irq(&css_set_lock);
	list_for_each_entry(cset, &tset->src_csets, mg_node) {
		list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) {
			struct css_set *from_cset = task_css_set(task);
			struct css_set *to_cset = cset->mg_dst_cset;

			get_css_set(to_cset);
			to_cset->nr_tasks++;
			css_set_move_task(task, from_cset, to_cset, true);
			put_css_set_locked(from_cset);
			from_cset->nr_tasks--;
		}
	}
	spin_unlock_irq(&css_set_lock);

	/*
	 * 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;

	if (tset->nr_tasks) {
		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
			if (ss->attach) {
				tset->ssid = ssid;
				ss->attach(tset);
			}
		} while_each_subsys_mask();
	}

	ret = 0;
	goto out_release_tset;

out_cancel_attach:
	if (tset->nr_tasks) {
		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
			if (ssid == failed_ssid)
				break;
			if (ss->cancel_attach) {
				tset->ssid = ssid;
				ss->cancel_attach(tset);
			}
		} while_each_subsys_mask();
	}
out_release_tset:
	spin_lock_irq(&css_set_lock);
	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);
	}
	spin_unlock_irq(&css_set_lock);

	/*
	 * Re-initialize the cgroup_taskset structure in case it is reused
	 * again in another cgroup_migrate_add_task()/cgroup_migrate_execute()
	 * iteration.
	 */
	tset->nr_tasks = 0;
	tset->csets    = &tset->src_csets;
	return ret;
}