cgroup: Fix dom_cgrp propagation when enabling threaded mode
A cgroup which is already a threaded domain may be converted into a
threaded cgroup if the prerequisite conditions are met. When this
happens, all threaded descendant should also have their ->dom_cgrp
updated to the new threaded domain cgroup. Unfortunately, this
propagation was missing leading to the following failure.
# cd /sys/fs/cgroup/unified
# cat cgroup.subtree_control # show that no controllers are enabled
# mkdir -p mycgrp/a/b/c
# echo threaded > mycgrp/a/b/cgroup.type
At this point, the hierarchy looks as follows:
mycgrp [d]
a [dt]
b [t]
c [inv]
Now let's make node "a" threaded (and thus "mycgrp" s made "domain threaded"):
# echo threaded > mycgrp/a/cgroup.type
By this point, we now have a hierarchy that looks as follows:
mycgrp [dt]
a [t]
b [t]
c [inv]
But, when we try to convert the node "c" from "domain invalid" to
"threaded", we get ENOTSUP on the write():
# echo threaded > mycgrp/a/b/c/cgroup.type
sh: echo: write error: Operation not supported
This patch fixes the problem by
* Moving the opencoded ->dom_cgrp save and restoration in
cgroup_enable_threaded() into cgroup_{save|restore}_control() so
that mulitple cgroups can be handled.
* Updating all threaded descendants' ->dom_cgrp to point to the new
dom_cgrp when enabling threaded mode.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-and-tested-by: "Michael Kerrisk (man-pages)" <mtk.manpages@gmail.com>
Reported-by: Amin Jamali <ajamali@pivotal.io>
Reported-by: Joao De Almeida Pereira <jpereira@pivotal.io>
Link: https://lore.kernel.org/r/CAKgNAkhHYCMn74TCNiMJ=ccLd7DcmXSbvw3CbZ1YREeG7iJM5g@mail.gmail.com
Fixes: 454000adaa2a ("cgroup: introduce cgroup->dom_cgrp and threaded css_set handling")
Cc: stable@vger.kernel.org # v4.14+
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index ff20b67..22254c1 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -412,6 +412,7 @@
* specific task are charged to the dom_cgrp.
*/
struct cgroup *dom_cgrp;
+ struct cgroup *old_dom_cgrp; /* used while enabling threaded */
/* per-cpu recursive resource statistics */
struct cgroup_rstat_cpu __percpu *rstat_cpu;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index aae10baf..4a3dae2 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2836,11 +2836,12 @@
}
/**
- * cgroup_save_control - save control masks of a subtree
+ * cgroup_save_control - save control masks and dom_cgrp of a subtree
* @cgrp: root of the target subtree
*
- * Save ->subtree_control and ->subtree_ss_mask to the respective old_
- * prefixed fields for @cgrp's subtree including @cgrp itself.
+ * Save ->subtree_control, ->subtree_ss_mask and ->dom_cgrp to the
+ * respective old_ prefixed fields for @cgrp's subtree including @cgrp
+ * itself.
*/
static void cgroup_save_control(struct cgroup *cgrp)
{
@@ -2850,6 +2851,7 @@
cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
dsct->old_subtree_control = dsct->subtree_control;
dsct->old_subtree_ss_mask = dsct->subtree_ss_mask;
+ dsct->old_dom_cgrp = dsct->dom_cgrp;
}
}
@@ -2875,11 +2877,12 @@
}
/**
- * cgroup_restore_control - restore control masks of a subtree
+ * cgroup_restore_control - restore control masks and dom_cgrp of a subtree
* @cgrp: root of the target subtree
*
- * Restore ->subtree_control and ->subtree_ss_mask from the respective old_
- * prefixed fields for @cgrp's subtree including @cgrp itself.
+ * Restore ->subtree_control, ->subtree_ss_mask and ->dom_cgrp from the
+ * respective old_ prefixed fields for @cgrp's subtree including @cgrp
+ * itself.
*/
static void cgroup_restore_control(struct cgroup *cgrp)
{
@@ -2889,6 +2892,7 @@
cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) {
dsct->subtree_control = dsct->old_subtree_control;
dsct->subtree_ss_mask = dsct->old_subtree_ss_mask;
+ dsct->dom_cgrp = dsct->old_dom_cgrp;
}
}
@@ -3196,6 +3200,8 @@
{
struct cgroup *parent = cgroup_parent(cgrp);
struct cgroup *dom_cgrp = parent->dom_cgrp;
+ struct cgroup *dsct;
+ struct cgroup_subsys_state *d_css;
int ret;
lockdep_assert_held(&cgroup_mutex);
@@ -3225,12 +3231,13 @@
*/
cgroup_save_control(cgrp);
- cgrp->dom_cgrp = dom_cgrp;
+ cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp)
+ if (dsct == cgrp || cgroup_is_threaded(dsct))
+ dsct->dom_cgrp = dom_cgrp;
+
ret = cgroup_apply_control(cgrp);
if (!ret)
parent->nr_threaded_children++;
- else
- cgrp->dom_cgrp = cgrp;
cgroup_finalize_control(cgrp, ret);
return ret;
