Commit bd8815a6 authored by Tejun Heo's avatar Tejun Heo
Browse files

cgroup: make css_for_each_descendant() and friends include the origin css in the iteration 



Previously, all css descendant iterators didn't include the origin
(root of subtree) css in the iteration.  The reasons were maintaining
consistency with css_for_each_child() and that at the time of
introduction more use cases needed skipping the origin anyway;
however, given that css_is_descendant() considers self to be a
descendant, omitting the origin css has become more confusing and
looking at the accumulated use cases rather clearly indicates that
including origin would result in simpler code overall.

While this is a change which can easily lead to subtle bugs, cgroup
API including the iterators has recently gone through major
restructuring and no out-of-tree changes will be applicable without
adjustments making this a relatively acceptable opportunity for this
type of change.

The conversions are mostly straight-forward.  If the iteration block
had explicit origin handling before or after, it's moved inside the
iteration.  If not, if (pos == origin) continue; is added.  Some
conversions add extra reference get/put around origin handling by
consolidating origin handling and the rest.  While the extra ref
operations aren't strictly necessary, this shouldn't cause any
noticeable difference.

Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Acked-by: default avatarLi Zefan <lizefan@huawei.com>
Acked-by: default avatarVivek Goyal <vgoyal@redhat.com>
Acked-by: default avatarAristeu Rozanski <aris@redhat.com>
Acked-by: default avatarMichal Hocko <mhocko@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Matt Helsley <matthltc@us.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
parent 95109b62

block/blk-cgroup.c

+2 −6
Original line number Diff line number Diff line
@@ -615,12 +615,10 @@ u64 blkg_stat_recursive_sum(struct blkg_policy_data *pd, int off) 
	struct blkcg_policy *pol = blkcg_policy[pd->plid];

	struct blkcg_gq *pos_blkg;

	struct cgroup_subsys_state *pos_css;

	u64 sum;

	u64 sum = 0;



	lockdep_assert_held(pd->blkg->q->queue_lock);



	sum = blkg_stat_read((void *)pd + off);



	rcu_read_lock();

	blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) {

		struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol);
@@ -650,13 +648,11 @@ struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkg_policy_data *pd, 
	struct blkcg_policy *pol = blkcg_policy[pd->plid];

	struct blkcg_gq *pos_blkg;

	struct cgroup_subsys_state *pos_css;

	struct blkg_rwstat sum;

	struct blkg_rwstat sum = { };

	int i;



	lockdep_assert_held(pd->blkg->q->queue_lock);



	sum = blkg_rwstat_read((void *)pd + off);



	rcu_read_lock();

	blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) {

		struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol);

block/blk-cgroup.h

+3 −1
Original line number Diff line number Diff line
@@ -291,6 +291,7 @@ struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q, 
 * read locked.  If called under either blkcg or queue lock, the iteration

 * is guaranteed to include all and only online blkgs.  The caller may

 * update @pos_css by calling css_rightmost_descendant() to skip subtree.

 * @p_blkg is included in the iteration and the first node to be visited.

 */

#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg)		\

	css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css)	\
@@ -304,7 +305,8 @@ struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q, 
 * @p_blkg: target blkg to walk descendants of

 *

 * Similar to blkg_for_each_descendant_pre() but performs post-order

 * traversal instead.  Synchronization rules are the same.

 * traversal instead.  Synchronization rules are the same.  @p_blkg is

 * included in the iteration and the last node to be visited.

 */

#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg)		\

	css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css)	\

block/blk-throttle.c

+0 −3
Original line number Diff line number Diff line
@@ -1379,7 +1379,6 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft, 
	 * restrictions in the whole hierarchy and allows them to bypass

	 * blk-throttle.

	 */

	tg_update_has_rules(tg);

	blkg_for_each_descendant_pre(blkg, pos_css, ctx.blkg)

		tg_update_has_rules(blkg_to_tg(blkg));
@@ -1639,8 +1638,6 @@ void blk_throtl_drain(struct request_queue *q) 
	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg)

		tg_drain_bios(&blkg_to_tg(blkg)->service_queue);



	tg_drain_bios(&td_root_tg(td)->service_queue);



	/* finally, transfer bios from top-level tg's into the td */

	tg_drain_bios(&td->service_queue);

include/linux/cgroup.h

+9 −8
Original line number Diff line number Diff line
@@ -798,7 +798,8 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos); 
 * @pos: the css * to use as the loop cursor

 * @root: css whose descendants to walk

 *

 * Walk @root's descendants.  Must be called under rcu_read_lock().  A

 * Walk @root's descendants.  @root is included in the iteration and the

 * first node to be visited.  Must be called under rcu_read_lock().  A

 * descendant css which hasn't finished ->css_online() or already has

 * finished ->css_offline() may show up during traversal and it's each

 * subsystem's responsibility to verify that each @pos is alive.
@@ -820,13 +821,12 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos); 
 *

 * my_update_state(@css)

 * {

 *	Lock @css;

 *	Update @css's state;

 *	Unlock @css;

 *

 *	css_for_each_descendant_pre(@pos, @css) {

 *		Lock @pos;

 *		Verify @pos is alive and inherit state from @pos's parent;

 *		if (@pos == @css)

 *			Update @css's state;

 *		else

 *			Verify @pos is alive and inherit state from its parent;

 *		Unlock @pos;

 *	}

 * }
@@ -864,8 +864,9 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, 
 * @css: css whose descendants to walk

 *

 * Similar to css_for_each_descendant_pre() but performs post-order

 * traversal instead.  Note that the walk visibility guarantee described in

 * pre-order walk doesn't apply the same to post-order walks.

 * traversal instead.  @root is included in the iteration and the last

 * node to be visited.  Note that the walk visibility guarantee described

 * in pre-order walk doesn't apply the same to post-order walks.

 */

#define css_for_each_descendant_post(pos, css)				\

	for ((pos) = css_next_descendant_post(NULL, (css)); (pos);	\

kernel/cgroup.c

+11 −18
Original line number Diff line number Diff line
@@ -2868,17 +2868,6 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) 


	mutex_unlock(&cgroup_mutex);



	/* @root always needs to be updated */

	inode = root->dentry->d_inode;

	mutex_lock(&inode->i_mutex);

	mutex_lock(&cgroup_mutex);

	ret = cgroup_addrm_files(root, cfts, is_add);

	mutex_unlock(&cgroup_mutex);

	mutex_unlock(&inode->i_mutex);



	if (ret)

		goto out_deact;



	/* add/rm files for all cgroups created before */

	rcu_read_lock();

	css_for_each_descendant_pre(css, cgroup_css(root, ss->subsys_id)) {
@@ -2907,7 +2896,6 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) 
	}

	rcu_read_unlock();

	dput(prev);

out_deact:

	deactivate_super(sb);

	return ret;

}
@@ -3099,7 +3087,8 @@ EXPORT_SYMBOL_GPL(css_next_child); 
 * @root: css whose descendants to walk

 *

 * To be used by css_for_each_descendant_pre().  Find the next descendant

 * to visit for pre-order traversal of @root's descendants.

 * to visit for pre-order traversal of @root's descendants.  @root is

 * included in the iteration and the first node to be visited.

 *

 * While this function requires RCU read locking, it doesn't require the

 * whole traversal to be contained in a single RCU critical section.  This
@@ -3114,9 +3103,9 @@ css_next_descendant_pre(struct cgroup_subsys_state *pos, 


	WARN_ON_ONCE(!rcu_read_lock_held());



	/* if first iteration, pretend we just visited @root */

	/* if first iteration, visit @root */

	if (!pos)

		pos = root;

		return root;



	/* visit the first child if exists */

	next = css_next_child(NULL, pos);
@@ -3186,7 +3175,8 @@ css_leftmost_descendant(struct cgroup_subsys_state *pos) 
 * @root: css whose descendants to walk

 *

 * To be used by css_for_each_descendant_post().  Find the next descendant

 * to visit for post-order traversal of @root's descendants.

 * to visit for post-order traversal of @root's descendants.  @root is

 * included in the iteration and the last node to be visited.

 *

 * While this function requires RCU read locking, it doesn't require the

 * whole traversal to be contained in a single RCU critical section.  This
@@ -3207,14 +3197,17 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, 
		return next != root ? next : NULL;

	}



	/* if we visited @root, we're done */

	if (pos == root)

		return NULL;



	/* if there's an unvisited sibling, visit its leftmost descendant */

	next = css_next_child(pos, css_parent(pos));

	if (next)

		return css_leftmost_descendant(next);



	/* no sibling left, visit parent */

	next = css_parent(pos);

	return next != root ? next : NULL;

	return css_parent(pos);

}

EXPORT_SYMBOL_GPL(css_next_descendant_post);

CRA Git | Maintained and supported by SUSTech CRA and CCSE