blk-throttle: implement proper hierarchy support

With the recent updates, blk-throttle is finally ready for proper
hierarchy support.  Dispatching now honors service_queue->parent_sq
and propagates correctly.  The only thing missing is setting
->parent_sq correctly so that throtl_grp hierarchy matches the cgroup
hierarchy.

This patch updates throtl_pd_init() such that service_queues form the
same hierarchy as the cgroup hierarchy if sane_behavior is enabled.
As this concludes proper hierarchy support for blkcg, the shameful
.broken_hierarchy tag is removed from blkio_subsys.

v2: Updated blkio-controller.txt as suggested by Vivek.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Cc: Li Zefan <lizefan@huawei.com>

2 files changed, 21 insertions, 9 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index d0747605f56c..290792a13e3c 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -911,14 +911,6 @@ struct cgroup_subsys blkio_subsys = {
         .subsys_id = blkio_subsys_id,
         .base_cftypes = blkcg_files,
         .module = THIS_MODULE,
-
-        /*
-         * blkio subsystem is utterly broken in terms of hierarchy support.
-         * It treats all cgroups equally regardless of where they're
-         * located in the hierarchy - all cgroups are treated as if they're
-         * right below the root.  Fix it and remove the following.
-         */
-        .broken_hierarchy = true,
 };
 EXPORT_SYMBOL_GPL(blkio_subsys);
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 27f006bb363b..08a32dfd3844 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -397,10 +397,30 @@ static void throtl_pd_init(struct blkcg_gq *blkg)
 {
         struct throtl_grp *tg = blkg_to_tg(blkg);
         struct throtl_data *td = blkg->q->td;
+        struct throtl_service_queue *parent_sq;
         unsigned long flags;
         int rw;
 
-        throtl_service_queue_init(&tg->service_queue, &td->service_queue);
+        /*
+         * If sane_hierarchy is enabled, we switch to properly hierarchical
+         * behavior where limits on a given throtl_grp are applied to the
+         * whole subtree rather than just the group itself.  e.g. If 16M
+         * read_bps limit is set on the root group, the whole system can't
+         * exceed 16M for the device.
+         *
+         * If sane_hierarchy is not enabled, the broken flat hierarchy
+         * behavior is retained where all throtl_grps are treated as if
+         * they're all separate root groups right below throtl_data.
+         * Limits of a group don't interact with limits of other groups
+         * regardless of the position of the group in the hierarchy.
+         */
+        parent_sq = &td->service_queue;
+
+        if (cgroup_sane_behavior(blkg->blkcg->css.cgroup) && blkg->parent)
+                parent_sq = &blkg_to_tg(blkg->parent)->service_queue;
+
+        throtl_service_queue_init(&tg->service_queue, parent_sq);
+
         for (rw = READ; rw <= WRITE; rw++) {
                 throtl_qnode_init(&tg->qnode_on_self[rw], tg);
                 throtl_qnode_init(&tg->qnode_on_parent[rw], tg);