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: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Acked-by: Aristeu Rozanski <aris@redhat.com>
Acked-by: Michal 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>

3 files changed, 5 insertions, 10 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 54ad00292ed..e90c7c164c8 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -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);
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 85553863030..ae6969a7ffd 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -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)	\
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 8cefa7f8590..8331aba9426 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -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);