The cgroup root_list is already RCU-safe. Therefore, we can replace the
cgroup_mutex with the RCU read lock in some particular paths. This change
will be particularly beneficial for frequent operations, such as
`cat /proc/self/cgroup`, in a cgroup1-based container environment.
I did stress tests with this change, as outlined below
(with CONFIG_PROVE_RCU_LIST enabled):
- Continuously mounting and unmounting named cgroups in some tasks,
for example:
cgrp_name=$1
while true
do
mount -t cgroup -o none,name=$cgrp_name none /$cgrp_name
umount /$cgrp_name
done
- Continuously triggering proc_cgroup_show() in some tasks concurrently,
for example:
while true; do cat /proc/self/cgroup > /dev/null; done
They can ran successfully after implementing this change, with no RCU
warnings in dmesg.
Signed-off-by: Yafang Shao <laoar.shao@xxxxxxxxx>
---
kernel/cgroup/cgroup.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 28b8ccc..cc6a6d9 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6261,7 +6261,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
if (!buf)
goto out;
- cgroup_lock();
+ rcu_read_lock();
spin_lock_irq(&css_set_lock);
for_each_root(root) {
@@ -6272,6 +6272,11 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible))
continue;
+ cgrp = task_cgroup_from_root(tsk, root);
+ /* The root has already been unmounted. */
+ if (!cgrp)
+ continue;
+
seq_printf(m, "%d:", root->hierarchy_id);
if (root != &cgrp_dfl_root)
for_each_subsys(ss, ssid)
@@ -6282,9 +6287,6 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
seq_printf(m, "%sname=%s", count ? "," : "",
root->name);
seq_putc(m, ':');
-
- cgrp = task_cgroup_from_root(tsk, root);
-
/*
* On traditional hierarchies, all zombie tasks show up as
* belonging to the root cgroup. On the default hierarchy,
@@ -6316,7 +6318,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
retval = 0;
out_unlock:
spin_unlock_irq(&css_set_lock);
- cgroup_unlock();
+ rcu_read_unlock();
kfree(buf);
out:
return retval;
--
1.8.3.1
