Re: [PATCH v3] mm/slab_common: Deleting kobject in kmem_cache_destroy() without holding slab_mutex/cpu_hotplug_lock

[Waiman Long <longman@redhat.com>]

On 8/13/22 11:00, Hyeonggon Yoo wrote:
> On Fri, Aug 12, 2022 at 02:30:33PM -0400, Waiman Long wrote:
>> A circular locking problem is reported by lockdep due to the following
>> circular locking dependency.
>>
>>    +--> cpu_hotplug_lock --> slab_mutex --> kn->active --+
>>    |                                                     |
>>    +-----------------------------------------------------+
>>
>> The forward cpu_hotplug_lock ==> slab_mutex ==> kn->active dependency
>> happens in
>>
>>    kmem_cache_destroy():	cpus_read_lock(); mutex_lock(&slab_mutex);
>>    ==> sysfs_slab_unlink()
>>        ==> kobject_del()
>>            ==> kernfs_remove()
>> 	      ==> __kernfs_remove()
>> 	          ==> kernfs_drain(): rwsem_acquire(&kn->dep_map, ...);
> Maybe you mean this?
>
>          /* but everyone should wait for draining */
>          wait_event(root->deactivate_waitq,
>                     atomic_read(&kn->active) == KN_DEACTIVATED_BIAS);
>
This is part of the kernfs_drain() operation. However, I am focusing on 
the behavior of the pseudo lock that causes the lockdep splat in the 
first place. That is why I am showcasing the rwsem_acquire() call here.


>> The backward kn->active ==> cpu_hotplug_lock dependency happens in
>>
>>    kernfs_fop_write_iter(): kernfs_get_active();
>>    ==> slab_attr_store()
>>        ==> cpu_partial_store()
>>            ==> flush_all(): cpus_read_lock()
>>
>> One way to break this circular locking chain is to avoid holding
>> cpu_hotplug_lock and slab_mutex while deleting the kobject in
>> sysfs_slab_unlink() which should be equivalent to doing a write_lock
>> and write_unlock pair of the kn->active virtual lock.
>>
>> Since the kobject structures are not protected by slab_mutex or the
>> cpu_hotplug_lock, we can certainly release those locks before doing
>> the delete operation.
>>
>> Move sysfs_slab_unlink() and sysfs_slab_release() to the newly
>> created kmem_cache_release() and call it outside the slab_mutex &
>> cpu_hotplug_lock critical sections. There will be a slight delay
>> in the deletion of sysfs files if kmem_cache_release() is called
>> indirectly from a work function.
>>
>> Signed-off-by: Waiman Long <longman@redhat.com>
>> ---
>>
>>   [v3] Move sysfs_slab_unlink() out to kmem_cache_release() and move
>>        schedule_work() back right after list_add_tail().
>>
>>   mm/slab_common.c | 45 +++++++++++++++++++++++++++++----------------
>>   1 file changed, 29 insertions(+), 16 deletions(-)
>>
>> diff --git a/mm/slab_common.c b/mm/slab_common.c
>> index 17996649cfe3..07b948288f84 100644
>> --- a/mm/slab_common.c
>> +++ b/mm/slab_common.c
>> @@ -392,6 +392,28 @@ kmem_cache_create(const char *name, unsigned int size, unsigned int align,
>>   }
>>   EXPORT_SYMBOL(kmem_cache_create);
>>   
>> +#ifdef SLAB_SUPPORTS_SYSFS
>> +/*
>> + * For a given kmem_cache, kmem_cache_destroy() should only be called
>> + * once or there will be a use-after-free problem. The actual deletion
>> + * and release of the kobject does not need slab_mutex or cpu_hotplug_lock
>> + * protection. So they are now done without holding those locks.
>> + *
>> + * Note that there will be a slight delay in the deletion of sysfs files
>> + * if kmem_cache_release() is called indrectly from a work function.
>> + */
>> +static void kmem_cache_release(struct kmem_cache *s)
>> +{
>> +	sysfs_slab_unlink(s);
>> +	sysfs_slab_release(s);
>> +}
>> +#else
>> +static void kmem_cache_release(struct kmem_cache *s)
>> +{
>> +	slab_kmem_cache_release(s);
>> +}
>> +#endif
>> +
>>   static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
>>   {
>>   	LIST_HEAD(to_destroy);
>> @@ -418,11 +440,7 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
>>   	list_for_each_entry_safe(s, s2, &to_destroy, list) {
>>   		debugfs_slab_release(s);
>>   		kfence_shutdown_cache(s);
>> -#ifdef SLAB_SUPPORTS_SYSFS
>> -		sysfs_slab_release(s);
>> -#else
>> -		slab_kmem_cache_release(s);
>> -#endif
>> +		kmem_cache_release(s);
>>   	}
>>   }
>>   
>> @@ -437,20 +455,11 @@ static int shutdown_cache(struct kmem_cache *s)
>>   	list_del(&s->list);
>>   
>>   	if (s->flags & SLAB_TYPESAFE_BY_RCU) {
>> -#ifdef SLAB_SUPPORTS_SYSFS
>> -		sysfs_slab_unlink(s);
>> -#endif
>>   		list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
>>   		schedule_work(&slab_caches_to_rcu_destroy_work);
>>   	} else {
>>   		kfence_shutdown_cache(s);
>>   		debugfs_slab_release(s);
>> -#ifdef SLAB_SUPPORTS_SYSFS
>> -		sysfs_slab_unlink(s);
>> -		sysfs_slab_release(s);
>> -#else
>> -		slab_kmem_cache_release(s);
>> -#endif
>>   	}
>>   
>>   	return 0;
>> @@ -465,14 +474,16 @@ void slab_kmem_cache_release(struct kmem_cache *s)
>>   
>>   void kmem_cache_destroy(struct kmem_cache *s)
>>   {
>> +	int refcnt;
>> +
>>   	if (unlikely(!s) || !kasan_check_byte(s))
>>   		return;
>>   
>>   	cpus_read_lock();
>>   	mutex_lock(&slab_mutex);
>>   
>> -	s->refcount--;
>> -	if (s->refcount)
>> +	refcnt = --s->refcount;
>> +	if (refcnt)
>>   		goto out_unlock;
>>   
>>   	WARN(shutdown_cache(s),
>> @@ -481,6 +492,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
>>   out_unlock:
>>   	mutex_unlock(&slab_mutex);
>>   	cpus_read_unlock();
>> +	if (!refcnt && !(s->flags & SLAB_TYPESAFE_BY_RCU))
>> +		kmem_cache_release(s);
>>   }
>>   EXPORT_SYMBOL(kmem_cache_destroy);
>>   
>> -- 
>> 2.31.1
>>
> little bit complicated but looks good to me.
> Thank you for fixing this.
>
> Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
>
Thanks for the review.

Cheers,
Longman