Re: regression 4.4: deadlock in with cgroup percpu_rwsem

[Christian Borntraeger]

On 01/14/2016 08:56 PM, Tejun Heo wrote:
> Hello,
> 
> Thanks a lot for the report and detailed analysis.  Can you please
> test whether the following patch fixes the issue?
> 
> Thanks.
> 


Yes, the deadlock is gone and the system is still running.
After some time I had the following WARN in the logs, though.
Not sure yet if that is related.

[25331.763607] DEBUG_LOCKS_WARN_ON(lock->owner != current)
[25331.763630] ------------[ cut here ]------------
[25331.763634] WARNING: at kernel/locking/mutex-debug.c:80
[25331.763637] Modules linked in: nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 xt_tcpudp iptable_filter ip_tables x_tables bridge stp llc btrfs xor raid6_pq ghash_s390 prng ecb aes_s390 des_s390 des_generic sha512_s390 sha256_s390 sha1_s390 sha_common eadm_sch nfsd auth_rpcgss oid_registry nfs_acl lockd vhost_net tun vhost macvtap macvlan grace sunrpc dm_service_time dm_multipath dm_mod autofs4
[25331.763708] CPU: 56 PID: 114657 Comm: systemd-udevd Not tainted 4.4.0+ #91
[25331.763711] task: 000000fadc79de40 ti: 000000f95e7f8000 task.ti: 000000f95e7f8000
[25331.763715] Krnl PSW : 0404c00180000000 00000000001b7f32 (debug_mutex_unlock+0x16a/0x188)
[25331.763726]            R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:3 CC:0 PM:0 EA:3
Krnl GPRS: 0000004c00000037 000000fadc79de40 000000000000002b 0000000000000000
[25331.763732]            000000000028da3c 0000000000000000 000000f95e7fbf08 000000fab8e10df0
[25331.763735]            000000000000005c 000000facc0dc000 000000000000005c 000000000033e14a
[25331.763738]            0700000000000000 000000fab8e10df0 00000000001b7f2e 000000f95e7fbc80
[25331.763746] Krnl Code: 00000000001b7f22: c0200042784c	larl	%r2,a06fba
           00000000001b7f28: c0e50006ad50	brasl	%r14,28d9c8
          #00000000001b7f2e: a7f40001		brc	15,1b7f30
          >00000000001b7f32: a7f4ffe1		brc	15,1b7ef4
           00000000001b7f36: c03000429c9f	larl	%r3,a0b874
           00000000001b7f3c: c0200042783f	larl	%r2,a06fba
           00000000001b7f42: c0e50006ad43	brasl	%r14,28d9c8
           00000000001b7f48: a7f40001		brc	15,1b7f4a
[25331.763795] Call Trace:
[25331.763798] ([<00000000001b7f2e>] debug_mutex_unlock+0x166/0x188)
[25331.763804]  [<0000000000836a08>] __mutex_unlock_slowpath+0xa8/0x190
[25331.763808]  [<000000000033e14a>] seq_read+0x1c2/0x450
[25331.763813]  [<0000000000311e72>] __vfs_read+0x42/0x100
[25331.763818]  [<000000000031284e>] vfs_read+0x76/0x130
[25331.763821]  [<000000000031361e>] SyS_read+0x66/0xd8
[25331.763826]  [<000000000083af06>] system_call+0xd6/0x270
[25331.763829]  [<000003ffae1f19c8>] 0x3ffae1f19c8
[25331.763831] INFO: lockdep is turned off.
[25331.763833] Last Breaking-Event-Address:
[25331.763836]  [<00000000001b7f2e>] debug_mutex_unlock+0x166/0x188
[25331.763839] ---[ end trace 45177640eb39ef44 ]---





> ---
>  include/linux/cpuset.h |    6 ++++++
>  kernel/cgroup.c        |    2 ++
>  kernel/cpuset.c        |   48 +++++++++++++++++++++++++++++++++++++++++++-----
>  3 files changed, 51 insertions(+), 5 deletions(-)
> 
> --- a/include/linux/cpuset.h
> +++ b/include/linux/cpuset.h
> @@ -137,6 +137,8 @@ static inline void set_mems_allowed(node
>  	task_unlock(current);
>  }
> 
> +extern void cpuset_post_attach_flush(void);
> +
>  #else /* !CONFIG_CPUSETS */
> 
>  static inline bool cpusets_enabled(void) { return false; }
> @@ -243,6 +245,10 @@ static inline bool read_mems_allowed_ret
>  	return false;
>  }
> 
> +static inline void cpuset_post_attach_flush(void)
> +{
> +}
> +
>  #endif /* !CONFIG_CPUSETS */
> 
>  #endif /* _LINUX_CPUSET_H */
> --- a/kernel/cgroup.c
> +++ b/kernel/cgroup.c
> @@ -57,6 +57,7 @@
>  #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
>  #include <linux/kthread.h>
>  #include <linux/delay.h>
> +#include <linux/cpuset.h>
> 
>  #include <linux/atomic.h>
> 
> @@ -2739,6 +2740,7 @@ out_unlock_rcu:
>  out_unlock_threadgroup:
>  	percpu_up_write(&cgroup_threadgroup_rwsem);
>  	cgroup_kn_unlock(of->kn);
> +	cpuset_post_attach_flush();
>  	return ret ?: nbytes;
>  }
> 
> --- a/kernel/cpuset.c
> +++ b/kernel/cpuset.c
> @@ -287,6 +287,8 @@ static struct cpuset top_cpuset = {
>  static DEFINE_MUTEX(cpuset_mutex);
>  static DEFINE_SPINLOCK(callback_lock);
> 
> +static struct workqueue_struct *cpuset_migrate_mm_wq;
> +
>  /*
>   * CPU / memory hotplug is handled asynchronously.
>   */
> @@ -971,6 +973,23 @@ static int update_cpumask(struct cpuset
>  	return 0;
>  }
> 
> +struct cpuset_migrate_mm_work {
> +	struct work_struct	work;
> +	struct mm_struct	*mm;
> +	nodemask_t		from;
> +	nodemask_t		to;
> +};
> +
> +static void cpuset_migrate_mm_workfn(struct work_struct *work)
> +{
> +	struct cpuset_migrate_mm_work *mwork =
> +		container_of(work, struct cpuset_migrate_mm_work, work);
> +
> +	do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL);
> +	mmput(mwork->mm);
> +	kfree(mwork);
> +}
> +
>  /*
>   * cpuset_migrate_mm
>   *
> @@ -989,16 +1008,31 @@ static void cpuset_migrate_mm(struct mm_
>  							const nodemask_t *to)
>  {
>  	struct task_struct *tsk = current;
> +	struct cpuset_migrate_mm_work *mwork;
> 
>  	tsk->mems_allowed = *to;
> 
> -	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
> +	mwork = kzalloc(sizeof(*mwork), GFP_KERNEL);
> +	if (mwork) {
> +		mwork->mm = mm;
> +		mwork->from = *from;
> +		mwork->to = *to;
> +		INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn);
> +		queue_work(cpuset_migrate_mm_wq, &mwork->work);
> +	} else {
> +		mmput(mm);
> +	}
> 
>  	rcu_read_lock();
>  	guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed);
>  	rcu_read_unlock();
>  }
> 
> +void cpuset_post_attach_flush(void)
> +{
> +	flush_workqueue(cpuset_migrate_mm_wq);
> +}
> +
>  /*
>   * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy
>   * @tsk: the task to change
> @@ -1097,7 +1131,8 @@ static void update_tasks_nodemask(struct
>  		mpol_rebind_mm(mm, &cs->mems_allowed);
>  		if (migrate)
>  			cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
> -		mmput(mm);
> +		else
> +			mmput(mm);
>  	}
>  	css_task_iter_end(&it);
> 
> @@ -1545,11 +1580,11 @@ static void cpuset_attach(struct cgroup_
>  			 * @old_mems_allowed is the right nodesets that we
>  			 * migrate mm from.
>  			 */
> -			if (is_memory_migrate(cs)) {
> +			if (is_memory_migrate(cs))
>  				cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
>  						  &cpuset_attach_nodemask_to);
> -			}
> -			mmput(mm);
> +			else
> +				mmput(mm);
>  		}
>  	}
> 
> @@ -2359,6 +2394,9 @@ void __init cpuset_init_smp(void)
>  	top_cpuset.effective_mems = node_states[N_MEMORY];
> 
>  	register_hotmemory_notifier(&cpuset_track_online_nodes_nb);
> +
> +	cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0);
> +	BUG_ON(!cpuset_migrate_mm_wq);
>  }
> 
>  /**
>