Commit 4a3e62df authored by Tejun Heo's avatar Tejun Heo
Browse files

cgroup: Merge branch 'for-6.17-fixes' into for-6.18 



Pull for-6.17-fixes to receive 79f919a8 ("cgroup: split
cgroup_destroy_wq into 3 workqueues") to resolve its conflict with
7fa33aa3 ("cgroup: WQ_PERCPU added to alloc_workqueue users"). The
latter adds WQ_PERCPU when creating cgroup_destroy_wq and the former splits
the workqueue into three. Resolve by applying WQ_PERCPU to the three split
workqueues.

Signed-off-by: default avatarTejun Heo <tj@kernel.org>
parents 7fa33aa3 94a4acfe

Documentation/admin-guide/cgroup-v2.rst

+2 −2
Original line number Diff line number Diff line
@@ -435,8 +435,8 @@ both cgroups. 
Controlling Controllers

-----------------------



Availablity

~~~~~~~~~~~

Availability

~~~~~~~~~~~~



A controller is available in a cgroup when it is supported by the kernel (i.e.,

compiled in, not disabled and not attached to a v1 hierarchy) and listed in the

kernel/cgroup/cgroup.c

+37 −7
Original line number Diff line number Diff line
@@ -126,8 +126,31 @@ DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem); 
 * of concurrent destructions.  Use a separate workqueue so that cgroup

 * destruction work items don't end up filling up max_active of system_percpu_wq

 * which may lead to deadlock.

 */

static struct workqueue_struct *cgroup_destroy_wq;

 *

 * A cgroup destruction should enqueue work sequentially to:

 * cgroup_offline_wq: use for css offline work

 * cgroup_release_wq: use for css release work

 * cgroup_free_wq: use for free work

 *

 * Rationale for using separate workqueues:

 * The cgroup root free work may depend on completion of other css offline

 * operations. If all tasks were enqueued to a single workqueue, this could

 * create a deadlock scenario where:

 * - Free work waits for other css offline work to complete.

 * - But other css offline work is queued after free work in the same queue.

 *

 * Example deadlock scenario with single workqueue (cgroup_destroy_wq):

 * 1. umount net_prio

 * 2. net_prio root destruction enqueues work to cgroup_destroy_wq (CPUx)

 * 3. perf_event CSS A offline enqueues work to same cgroup_destroy_wq (CPUx)

 * 4. net_prio cgroup_destroy_root->cgroup_lock_and_drain_offline.

 * 5. net_prio root destruction blocks waiting for perf_event CSS A offline,

 *    which can never complete as it's behind in the same queue and

 *    workqueue's max_active is 1.

 */

static struct workqueue_struct *cgroup_offline_wq;

static struct workqueue_struct *cgroup_release_wq;

static struct workqueue_struct *cgroup_free_wq;



/* generate an array of cgroup subsystem pointers */

#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,
@@ -4173,6 +4196,7 @@ static void cgroup_file_release(struct kernfs_open_file *of) 
		cft->release(of);

	put_cgroup_ns(ctx->ns);

	kfree(ctx);

	of->priv = NULL;

}



static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
@@ -5577,7 +5601,7 @@ static void css_release_work_fn(struct work_struct *work) 
	cgroup_unlock();



	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);

	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);

	queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);

}



static void css_release(struct percpu_ref *ref)
@@ -5586,7 +5610,7 @@ static void css_release(struct percpu_ref *ref) 
		container_of(ref, struct cgroup_subsys_state, refcnt);



	INIT_WORK(&css->destroy_work, css_release_work_fn);

	queue_work(cgroup_destroy_wq, &css->destroy_work);

	queue_work(cgroup_release_wq, &css->destroy_work);

}



static void init_and_link_css(struct cgroup_subsys_state *css,
@@ -5720,7 +5744,7 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, 
	list_del_rcu(&css->sibling);

err_free_css:

	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);

	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);

	queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);

	return ERR_PTR(err);

}
@@ -5960,7 +5984,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref) 


	if (atomic_dec_and_test(&css->online_cnt)) {

		INIT_WORK(&css->destroy_work, css_killed_work_fn);

		queue_work(cgroup_destroy_wq, &css->destroy_work);

		queue_work(cgroup_offline_wq, &css->destroy_work);

	}

}
@@ -6346,8 +6370,14 @@ static int __init cgroup_wq_init(void) 
	 * 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", WQ_PERCPU, 1);

	BUG_ON(!cgroup_destroy_wq);

	cgroup_offline_wq = alloc_workqueue("cgroup_offline", WQ_PERCPU, 1);

	BUG_ON(!cgroup_offline_wq);



	cgroup_release_wq = alloc_workqueue("cgroup_release", WQ_PERCPU, 1);

	BUG_ON(!cgroup_release_wq);



	cgroup_free_wq = alloc_workqueue("cgroup_free", WQ_PERCPU, 1);

	BUG_ON(!cgroup_free_wq);

	return 0;

}

core_initcall(cgroup_wq_init);