cgroup: use a dedicated workqueue for cgroup destruction

Since be44562613851 ("cgroup: remove synchronize_rcu() from
cgroup_diput()"), cgroup destruction path makes use of workqueue.  css
freeing is performed from a work item from that point on and a later
commit, ea15f8ccdb430 ("cgroup: split cgroup destruction into two
steps"), moves css offlining to workqueue too.

As cgroup destruction isn't depended upon for memory reclaim, the
destruction work items were put on the system_wq; unfortunately, some
controller may block in the destruction path for considerable duration
while holding cgroup_mutex.  As large part of destruction path is
synchronized through cgroup_mutex, when combined with high rate of
cgroup removals, this has potential to fill up system_wq's max_active
of 256.

Also, it turns out that memcg's css destruction path ends up queueing
and waiting for work items on system_wq through work_on_cpu().  If
such operation happens while system_wq is fully occupied by cgroup
destruction work items, work_on_cpu() can't make forward progress
because system_wq is full and other destruction work items on
system_wq can't make forward progress because the work item waiting
for work_on_cpu() is holding cgroup_mutex, leading to deadlock.

This can be fixed by queueing destruction work items on a separate
workqueue.  This patch creates a dedicated workqueue -
cgroup_destroy_wq - for this purpose.  As these work items shouldn't
have inter-dependencies and mostly serialized by cgroup_mutex anyway,
giving high concurrency level doesn't buy anything and the workqueue's
@max_active is set to 1 so that destruction work items are executed
one by one on each CPU.

Hugh Dickins: Because cgroup_init() is run before init_workqueues(),
cgroup_destroy_wq can't be allocated from cgroup_init().  Do it from a
separate core_initcall().  In the future, we probably want to reorder
so that workqueue init happens before cgroup_init().

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Hugh Dickins <hughd@google.com>
Reported-by: Shawn Bohrer <shawn.bohrer@gmail.com>
Link: http://lkml.kernel.org/r/20131111220626.GA7509@sbohrermbp13-local.rgmadvisors.com
Link: http://lkml.kernel.org/g/alpine.LNX.2.00.1310301606080.2333@eggly.anvils
Cc: stable@vger.kernel.org # v3.9+

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 4c62513..a7b98ee 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -89,6 +89,14 @@ static DEFINE_MUTEX(cgroup_mutex);
 
 static DEFINE_MUTEX(cgroup_root_mutex);
 
+/*
+ * cgroup destruction makes heavy use of work items and there can be a lot
+ * of concurrent destructions.  Use a separate workqueue so that cgroup
+ * destruction work items don't end up filling up max_active of system_wq
+ * which may lead to deadlock.
+ */
+static struct workqueue_struct *cgroup_destroy_wq;
+
 /*
  * Generate an array of cgroup subsystem pointers. At boot time, this is
  * populated with the built in subsystems, and modular subsystems are
@@ -871,7 +879,7 @@ static void cgroup_free_rcu(struct rcu_head *head)
        struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head);
 
        INIT_WORK(&cgrp->destroy_work, cgroup_free_fn);
-       schedule_work(&cgrp->destroy_work);
+       queue_work(cgroup_destroy_wq, &cgrp->destroy_work);
 }
 
 static void cgroup_diput(struct dentry *dentry, struct inode *inode)
@@ -4249,7 +4257,7 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head)
         * css_put().  dput() requires process context which we don't have.
         */
        INIT_WORK(&css->destroy_work, css_free_work_fn);
-       schedule_work(&css->destroy_work);
+       queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
 
 static void css_release(struct percpu_ref *ref)
@@ -4539,7 +4547,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
                container_of(ref, struct cgroup_subsys_state, refcnt);
 
        INIT_WORK(&css->destroy_work, css_killed_work_fn);
-       schedule_work(&css->destroy_work);
+       queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
 
 /**
@@ -5063,6 +5071,22 @@ out:
        return err;
 }
 
+static int __init cgroup_wq_init(void)
+{
+       /*
+        * There isn't much point in executing destruction path in
+        * parallel.  Good chunk is serialized with cgroup_mutex anyway.
+        * Use 1 for @max_active.
+        *
+        * We would prefer to do this in cgroup_init() above, but that
+        * is called before init_workqueues(): so leave this until after.
+        */
+       cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
+       BUG_ON(!cgroup_destroy_wq);
+       return 0;
+}
+core_initcall(cgroup_wq_init);
+
 /*
  * proc_cgroup_show()
  *  - Print task's cgroup paths into seq_file, one line for each hierarchy