[PATCH] cgroup/cpuset: remove circular dependency deadlock

From: Prateek Sood
Date: Thu Sep 07 2017 - 09:56:44 EST


Remove circular dependency deadlock in a scenario where hotplug of CPU is
being done while there is updation in cgroup and cpuset triggered from
userspace.

Process A => kthreadd => Process B => Process C => Process A

Process A
cpu_subsys_offline();
cpu_down();
_cpu_down();
percpu_down_write(&cpu_hotplug_lock); //held
cpuhp_invoke_callback();
workqueue_offline_cpu();
wq_update_unbound_numa();
kthread_create_on_node();
wake_up_process(); //wakeup kthreadd
flush_work();
wait_for_completion();

kthreadd
kthreadd();
kernel_thread();
do_fork();
copy_process();
percpu_down_read(&cgroup_threadgroup_rwsem);
__rwsem_down_read_failed_common(); //waiting

Process B
kernfs_fop_write();
cgroup_file_write();
cgroup_procs_write();
percpu_down_write(&cgroup_threadgroup_rwsem); //held
cgroup_attach_task();
cgroup_migrate();
cgroup_migrate_execute();
cpuset_can_attach();
mutex_lock(&cpuset_mutex); //waiting

Process C
kernfs_fop_write();
cgroup_file_write();
cpuset_write_resmask();
mutex_lock(&cpuset_mutex); //held
update_cpumask();
update_cpumasks_hier();
rebuild_sched_domains_locked();
get_online_cpus();
percpu_down_read(&cpu_hotplug_lock); //waiting

Signed-off-by: Prateek Sood <prsood@xxxxxxxxxxxxxx>
---
kernel/cgroup/cpuset.c | 32 +++++++++++++++++++-------------
1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 2f4039b..60dc0ac 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -816,16 +816,15 @@ static int generate_sched_domains(cpumask_var_t **domains,
* 'cpus' is removed, then call this routine to rebuild the
* scheduler's dynamic sched domains.
*
- * Call with cpuset_mutex held. Takes get_online_cpus().
*/
-static void rebuild_sched_domains_locked(void)
+static void rebuild_sched_domains_cpuslocked(void)
{
struct sched_domain_attr *attr;
cpumask_var_t *doms;
int ndoms;

+ lockdep_assert_cpus_held();
lockdep_assert_held(&cpuset_mutex);
- get_online_cpus();

/*
* We have raced with CPU hotplug. Don't do anything to avoid
@@ -833,27 +832,27 @@ static void rebuild_sched_domains_locked(void)
* Anyways, hotplug work item will rebuild sched domains.
*/
if (!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
- goto out;
+ return;

/* Generate domain masks and attrs */
ndoms = generate_sched_domains(&doms, &attr);

/* Have scheduler rebuild the domains */
partition_sched_domains(ndoms, doms, attr);
-out:
- put_online_cpus();
}
#else /* !CONFIG_SMP */
-static void rebuild_sched_domains_locked(void)
+static void rebuild_sched_domains_cpuslocked(void)
{
}
#endif /* CONFIG_SMP */

void rebuild_sched_domains(void)
{
+ get_online_cpus();
mutex_lock(&cpuset_mutex);
- rebuild_sched_domains_locked();
+ rebuild_sched_domains_cpuslocked();
mutex_unlock(&cpuset_mutex);
+ put_online_cpus();
}

/**
@@ -940,7 +939,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
rcu_read_unlock();

if (need_rebuild_sched_domains)
- rebuild_sched_domains_locked();
+ rebuild_sched_domains_cpuslocked();
}

/**
@@ -1273,7 +1272,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
cs->relax_domain_level = val;
if (!cpumask_empty(cs->cpus_allowed) &&
is_sched_load_balance(cs))
- rebuild_sched_domains_locked();
+ rebuild_sched_domains_cpuslocked();
}

return 0;
@@ -1306,7 +1305,6 @@ static void update_tasks_flags(struct cpuset *cs)
*
* Call with cpuset_mutex held.
*/
-
static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
int turning_on)
{
@@ -1339,7 +1337,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
spin_unlock_irq(&callback_lock);

if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
- rebuild_sched_domains_locked();
+ rebuild_sched_domains_cpuslocked();

if (spread_flag_changed)
update_tasks_flags(cs);
@@ -1607,6 +1605,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
cpuset_filetype_t type = cft->private;
int retval = 0;

+ get_online_cpus();
mutex_lock(&cpuset_mutex);
if (!is_cpuset_online(cs)) {
retval = -ENODEV;
@@ -1644,6 +1643,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
}
out_unlock:
mutex_unlock(&cpuset_mutex);
+ put_online_cpus();
return retval;
}

@@ -1654,6 +1654,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
cpuset_filetype_t type = cft->private;
int retval = -ENODEV;

+ get_online_cpus();
mutex_lock(&cpuset_mutex);
if (!is_cpuset_online(cs))
goto out_unlock;
@@ -1668,6 +1669,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
}
out_unlock:
mutex_unlock(&cpuset_mutex);
+ put_online_cpus();
return retval;
}

@@ -1706,6 +1708,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
kernfs_break_active_protection(of->kn);
flush_work(&cpuset_hotplug_work);

+ get_online_cpus();
mutex_lock(&cpuset_mutex);
if (!is_cpuset_online(cs))
goto out_unlock;
@@ -1731,6 +1734,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
free_trial_cpuset(trialcs);
out_unlock:
mutex_unlock(&cpuset_mutex);
+ put_online_cpus();
kernfs_unbreak_active_protection(of->kn);
css_put(&cs->css);
flush_workqueue(cpuset_migrate_mm_wq);
@@ -2031,13 +2035,14 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
/*
* If the cpuset being removed has its flag 'sched_load_balance'
* enabled, then simulate turning sched_load_balance off, which
- * will call rebuild_sched_domains_locked().
+ * will call rebuild_sched_domains_cpuslocked().
*/

static void cpuset_css_offline(struct cgroup_subsys_state *css)
{
struct cpuset *cs = css_cs(css);

+ get_online_cpus();
mutex_lock(&cpuset_mutex);

if (is_sched_load_balance(cs))
@@ -2047,6 +2052,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
clear_bit(CS_ONLINE, &cs->flags);

mutex_unlock(&cpuset_mutex);
+ put_online_cpus();
}

static void cpuset_css_free(struct cgroup_subsys_state *css)
--
Qualcomm India Private Limited, on behalf of Qualcomm Innovation Center, Inc.,
is a member of Code Aurora Forum, a Linux Foundation Collaborative Project.