cgroup: Elide write-locking threadgroup_rwsem when updating csses on an empty subtree

[ Upstream commit 671c11f0619e5ccb380bcf0f062f69ba95fc974a ]

cgroup_update_dfl_csses() write-lock the threadgroup_rwsem as updating the
csses can trigger process migrations. However, if the subtree doesn't
contain any tasks, there aren't gonna be any cgroup migrations. This
condition can be trivially detected by testing whether
mgctx.preloaded_src_csets is empty. Elide write-locking threadgroup_rwsem if
the subtree is empty.

After this optimization, the usage pattern of creating a cgroup, enabling
the necessary controllers, and then seeding it with CLONE_INTO_CGROUP and
then removing the cgroup after it becomes empty doesn't need to write-lock
threadgroup_rwsem at all.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 5046c99deba8638410f8f6df8ae14b3773ac1f7a..1072843b25709979b0ba265f81290250947eec88 100644 (file)
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2908,12 +2908,11 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
        struct cgroup_subsys_state *d_css;
        struct cgroup *dsct;
        struct css_set *src_cset;
+       bool has_tasks;
        int ret;
 
        lockdep_assert_held(&cgroup_mutex);
 
-       percpu_down_write(&cgroup_threadgroup_rwsem);
-
        /* look up all csses currently attached to @cgrp's subtree */
        spin_lock_irq(&css_set_lock);
        cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
@@ -2924,6 +2923,16 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
        }
        spin_unlock_irq(&css_set_lock);
 
+       /*
+        * We need to write-lock threadgroup_rwsem while migrating tasks.
+        * However, if there are no source csets for @cgrp, changing its
+        * controllers isn't gonna produce any task migrations and the
+        * write-locking can be skipped safely.
+        */
+       has_tasks = !list_empty(&mgctx.preloaded_src_csets);
+       if (has_tasks)
+               percpu_down_write(&cgroup_threadgroup_rwsem);
+
        /* NULL dst indicates self on default hierarchy */
        ret = cgroup_migrate_prepare_dst(&mgctx);
        if (ret)
@@ -2943,7 +2952,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
        ret = cgroup_migrate_execute(&mgctx);
 out_finish:
        cgroup_migrate_finish(&mgctx);
-       percpu_up_write(&cgroup_threadgroup_rwsem);
+       if (has_tasks)
+               percpu_up_write(&cgroup_threadgroup_rwsem);
        return ret;
 }