As noted by Michal, the blkg_iostat_set's in the lockless list
hold reference to blkg's to protect against their removal. Those
blkg's hold reference to blkcg. When a cgroup is being destroyed,
cgroup_rstat_flush() is only called at css_release_work_fn() which is
called when the blkcg reference count reaches 0. This circular dependency
will prevent blkcg from being freed until some other events cause
cgroup_rstat_flush() to be called to flush out the pending blkcg stats.
To prevent this delayed blkcg removal, add a new cgroup_rstat_css_flush()
function to flush stats for a given css and cpu and call it at the blkgs
destruction path, blkcg_destroy_blkgs(), whenever there are still some
pending stats to be flushed. This will ensure that blkcg reference
count can reach 0 ASAP.
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
block/blk-cgroup.c | 12 ++++++++++++
include/linux/cgroup.h | 1 +
kernel/cgroup/rstat.c | 20 ++++++++++++++++++++
3 files changed, 33 insertions(+)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index c466aef0d467..534f3baeb84a 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1090,6 +1090,8 @@ struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css)
*/
static void blkcg_destroy_blkgs(struct blkcg *blkcg)
{
+ int cpu;
+
/*
* blkcg_destroy_blkgs() shouldn't be called with all the blkcg
* references gone.
@@ -1099,6 +1101,16 @@ static void blkcg_destroy_blkgs(struct blkcg *blkcg)
might_sleep();
+ /*
+ * Flush all the non-empty percpu lockless lists.
+ */
+ for_each_possible_cpu(cpu) {
+ struct llist_head *lhead = per_cpu_ptr(blkcg->lhead, cpu);
+
+ if (!llist_empty(lhead))
+ cgroup_rstat_css_cpu_flush(&blkcg->css, cpu);
+ }
+
spin_lock_irq(&blkcg->lock);
while (!hlist_empty(&blkcg->blkg_list)) {
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 528bd44b59e2..6c4e66b3fa84 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -766,6 +766,7 @@ void cgroup_rstat_flush(struct cgroup *cgrp);
void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp);
void cgroup_rstat_flush_hold(struct cgroup *cgrp);
void cgroup_rstat_flush_release(void);
+void cgroup_rstat_css_cpu_flush(struct cgroup_subsys_state *css, int cpu);
/*
* Basic resource stats.
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 793ecff29038..910e633869b0 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -281,6 +281,26 @@ void cgroup_rstat_flush_release(void)
spin_unlock_irq(&cgroup_rstat_lock);
}
+/**
+ * cgroup_rstat_css_cpu_flush - flush stats for the given css and cpu
+ * @css: target css to be flush
+ * @cpu: the cpu that holds the stats to be flush
+ *
+ * A lightweight rstat flush operation for a given css and cpu.
+ * Only the cpu_lock is being held for mutual exclusion, the cgroup_rstat_lock
+ * isn't used.
+ */
+void cgroup_rstat_css_cpu_flush(struct cgroup_subsys_state *css, int cpu)
+{
+ raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
+
+ raw_spin_lock_irq(cpu_lock);
+ rcu_read_lock();
+ css->ss->css_rstat_flush(css, cpu);
+ rcu_read_unlock();
+ raw_spin_unlock_irq(cpu_lock);
+}
+
int cgroup_rstat_init(struct cgroup *cgrp)
{
int cpu;
--
2.31.1
