linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
* Re: cgroup: deadlock between cpu_hotplug_lock and freezer_mutex
       [not found] <768be93b-a401-deab-600c-f946e0bd27fa@redhat.com>
@ 2023-02-15  7:25 ` Hillf Danton
  2023-02-15 10:36   ` Xiubo Li
  0 siblings, 1 reply; 2+ messages in thread
From: Hillf Danton @ 2023-02-15  7:25 UTC (permalink / raw)
  To: Xiubo Li; +Cc: tj, hannes, cgroups, linux-mm, linux-kernel

On Wed, 15 Feb 2023 10:07:23 +0800 Xiubo Li <xiubli@redhat.com>
> Hi
> 
> Recently when running some test cases for ceph we hit the following 
> deadlock issue in cgroup code. Has this been fixed ? I have checked the 
> latest code and it seems no any commit is fixing this.
> 
> This call trace could also be found in 
> https://tracker.ceph.com/issues/58564#note-4, which is more friendly to 
> read.
> 
>   ======================================================
>   WARNING: possible circular locking dependency detected
>   6.1.0-rc5-ceph-gc90f64b588ff #1 Tainted: G S
>   ------------------------------------------------------
>   runc/90769 is trying to acquire lock:
>   ffffffff82664cb0 (cpu_hotplug_lock){++++}-{0:0}, at: 
> static_key_slow_inc+0xe/0x20
>   #012but task is already holding lock:
>   ffffffff8276e468 (freezer_mutex){+.+.}-{3:3}, at: freezer_write+0x89/0x530
>   #012which lock already depends on the new lock.
>   #012the existing dependency chain (in reverse order) is:
>   #012-> #2 (freezer_mutex){+.+.}-{3:3}:
>         __mutex_lock+0x9c/0xf20
>         freezer_attach+0x2c/0xf0
>         cgroup_migrate_execute+0x3f3/0x4c0
>         cgroup_attach_task+0x22e/0x3e0
>         __cgroup1_procs_write.constprop.12+0xfb/0x140
>         cgroup_file_write+0x91/0x230
>         kernfs_fop_write_iter+0x137/0x1d0
>         vfs_write+0x344/0x4d0
>         ksys_write+0x5c/0xd0
>         do_syscall_64+0x34/0x80
>         entry_SYSCALL_64_after_hwframe+0x63/0xcd
>   #012-> #1 (cgroup_threadgroup_rwsem){++++}-{0:0}:
>         percpu_down_write+0x45/0x2c0
>         cgroup_procs_write_start+0x84/0x270
>         __cgroup1_procs_write.constprop.12+0x57/0x140
>         cgroup_file_write+0x91/0x230
>         kernfs_fop_write_iter+0x137/0x1d0
>         vfs_write+0x344/0x4d0
>         ksys_write+0x5c/0xd0
>         do_syscall_64+0x34/0x80
>         entry_SYSCALL_64_after_hwframe+0x63/0xcd
>   #012-> #0 (cpu_hotplug_lock){++++}-{0:0}:
>         __lock_acquire+0x103f/0x1de0
>         lock_acquire+0xd4/0x2f0
>         cpus_read_lock+0x3c/0xd0
>         static_key_slow_inc+0xe/0x20
>         freezer_apply_state+0x98/0xb0
>         freezer_write+0x307/0x530
>         cgroup_file_write+0x91/0x230
>         kernfs_fop_write_iter+0x137/0x1d0
>         vfs_write+0x344/0x4d0
>         ksys_write+0x5c/0xd0
>         do_syscall_64+0x34/0x80
>         entry_SYSCALL_64_after_hwframe+0x63/0xcd
>   #012other info that might help us debug this:
>   Chain exists of:#012  cpu_hotplug_lock --> cgroup_threadgroup_rwsem 
> --> freezer_mutex
>   Possible unsafe locking scenario:
>         CPU0                    CPU1
>         ----                    ----
>    lock(freezer_mutex);
>                                 lock(cgroup_threadgroup_rwsem);
>                                 lock(freezer_mutex);
>    lock(cpu_hotplug_lock);
>   #012 *** DEADLOCK ***

Thanks for your report.

Change locking order if it is impossible to update freezer_active in atomic manner.

Only for thoughts.

Hillf
+++ linux-6.1.3/kernel/cgroup/legacy_freezer.c
@@ -350,7 +350,7 @@ static void freezer_apply_state(struct f
 
 	if (freeze) {
 		if (!(freezer->state & CGROUP_FREEZING))
-			static_branch_inc(&freezer_active);
+			static_branch_inc_cpuslocked(&freezer_active);
 		freezer->state |= state;
 		freeze_cgroup(freezer);
 	} else {
@@ -361,7 +361,7 @@ static void freezer_apply_state(struct f
 		if (!(freezer->state & CGROUP_FREEZING)) {
 			freezer->state &= ~CGROUP_FROZEN;
 			if (was_freezing)
-				static_branch_dec(&freezer_active);
+				static_branch_dec_cpuslocked(&freezer_active);
 			unfreeze_cgroup(freezer);
 		}
 	}
@@ -379,6 +379,7 @@ static void freezer_change_state(struct
 {
 	struct cgroup_subsys_state *pos;
 
+	cpus_read_lock();
 	/*
 	 * Update all its descendants in pre-order traversal.  Each
 	 * descendant will try to inherit its parent's FREEZING state as
@@ -407,6 +408,7 @@ static void freezer_change_state(struct
 	}
 	rcu_read_unlock();
 	mutex_unlock(&freezer_mutex);
+	cpus_read_unlock();
 }
 
 static ssize_t freezer_write(struct kernfs_open_file *of,


^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: cgroup: deadlock between cpu_hotplug_lock and freezer_mutex
  2023-02-15  7:25 ` cgroup: deadlock between cpu_hotplug_lock and freezer_mutex Hillf Danton
@ 2023-02-15 10:36   ` Xiubo Li
  0 siblings, 0 replies; 2+ messages in thread
From: Xiubo Li @ 2023-02-15 10:36 UTC (permalink / raw)
  To: Hillf Danton; +Cc: tj, hannes, cgroups, linux-mm, linux-kernel

Hi Hillf,

On 15/02/2023 15:25, Hillf Danton wrote:
> On Wed, 15 Feb 2023 10:07:23 +0800 Xiubo Li <xiubli@redhat.com>
>> Hi
>>
>> Recently when running some test cases for ceph we hit the following
>> deadlock issue in cgroup code. Has this been fixed ? I have checked the
>> latest code and it seems no any commit is fixing this.
>>
>> This call trace could also be found in
>> https://tracker.ceph.com/issues/58564#note-4, which is more friendly to
>> read.
>>
>>    ======================================================
>>    WARNING: possible circular locking dependency detected
>>    6.1.0-rc5-ceph-gc90f64b588ff #1 Tainted: G S
>>    ------------------------------------------------------
>>    runc/90769 is trying to acquire lock:
>>    ffffffff82664cb0 (cpu_hotplug_lock){++++}-{0:0}, at:
>> static_key_slow_inc+0xe/0x20
>>    #012but task is already holding lock:
>>    ffffffff8276e468 (freezer_mutex){+.+.}-{3:3}, at: freezer_write+0x89/0x530
>>    #012which lock already depends on the new lock.
>>    #012the existing dependency chain (in reverse order) is:
>>    #012-> #2 (freezer_mutex){+.+.}-{3:3}:
>>          __mutex_lock+0x9c/0xf20
>>          freezer_attach+0x2c/0xf0
>>          cgroup_migrate_execute+0x3f3/0x4c0
>>          cgroup_attach_task+0x22e/0x3e0
>>          __cgroup1_procs_write.constprop.12+0xfb/0x140
>>          cgroup_file_write+0x91/0x230
>>          kernfs_fop_write_iter+0x137/0x1d0
>>          vfs_write+0x344/0x4d0
>>          ksys_write+0x5c/0xd0
>>          do_syscall_64+0x34/0x80
>>          entry_SYSCALL_64_after_hwframe+0x63/0xcd
>>    #012-> #1 (cgroup_threadgroup_rwsem){++++}-{0:0}:
>>          percpu_down_write+0x45/0x2c0
>>          cgroup_procs_write_start+0x84/0x270
>>          __cgroup1_procs_write.constprop.12+0x57/0x140
>>          cgroup_file_write+0x91/0x230
>>          kernfs_fop_write_iter+0x137/0x1d0
>>          vfs_write+0x344/0x4d0
>>          ksys_write+0x5c/0xd0
>>          do_syscall_64+0x34/0x80
>>          entry_SYSCALL_64_after_hwframe+0x63/0xcd
>>    #012-> #0 (cpu_hotplug_lock){++++}-{0:0}:
>>          __lock_acquire+0x103f/0x1de0
>>          lock_acquire+0xd4/0x2f0
>>          cpus_read_lock+0x3c/0xd0
>>          static_key_slow_inc+0xe/0x20
>>          freezer_apply_state+0x98/0xb0
>>          freezer_write+0x307/0x530
>>          cgroup_file_write+0x91/0x230
>>          kernfs_fop_write_iter+0x137/0x1d0
>>          vfs_write+0x344/0x4d0
>>          ksys_write+0x5c/0xd0
>>          do_syscall_64+0x34/0x80
>>          entry_SYSCALL_64_after_hwframe+0x63/0xcd
>>    #012other info that might help us debug this:
>>    Chain exists of:#012  cpu_hotplug_lock --> cgroup_threadgroup_rwsem
>> --> freezer_mutex
>>    Possible unsafe locking scenario:
>>          CPU0                    CPU1
>>          ----                    ----
>>     lock(freezer_mutex);
>>                                  lock(cgroup_threadgroup_rwsem);
>>                                  lock(freezer_mutex);
>>     lock(cpu_hotplug_lock);
>>    #012 *** DEADLOCK ***
> Thanks for your report.
>
> Change locking order if it is impossible to update freezer_active in atomic manner.
>
> Only for thoughts.

Sure, I will test this.

Thanks


>
> Hillf
> +++ linux-6.1.3/kernel/cgroup/legacy_freezer.c
> @@ -350,7 +350,7 @@ static void freezer_apply_state(struct f
>   
>   	if (freeze) {
>   		if (!(freezer->state & CGROUP_FREEZING))
> -			static_branch_inc(&freezer_active);
> +			static_branch_inc_cpuslocked(&freezer_active);
>   		freezer->state |= state;
>   		freeze_cgroup(freezer);
>   	} else {
> @@ -361,7 +361,7 @@ static void freezer_apply_state(struct f
>   		if (!(freezer->state & CGROUP_FREEZING)) {
>   			freezer->state &= ~CGROUP_FROZEN;
>   			if (was_freezing)
> -				static_branch_dec(&freezer_active);
> +				static_branch_dec_cpuslocked(&freezer_active);
>   			unfreeze_cgroup(freezer);
>   		}
>   	}
> @@ -379,6 +379,7 @@ static void freezer_change_state(struct
>   {
>   	struct cgroup_subsys_state *pos;
>   
> +	cpus_read_lock();
>   	/*
>   	 * Update all its descendants in pre-order traversal.  Each
>   	 * descendant will try to inherit its parent's FREEZING state as
> @@ -407,6 +408,7 @@ static void freezer_change_state(struct
>   	}
>   	rcu_read_unlock();
>   	mutex_unlock(&freezer_mutex);
> +	cpus_read_unlock();
>   }
>   
>   static ssize_t freezer_write(struct kernfs_open_file *of,
>
-- 
Best Regards,

Xiubo Li (李秀波)

Email: xiubli@redhat.com/xiubli@ibm.com
Slack: @Xiubo Li



^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2023-02-15 10:36 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
     [not found] <768be93b-a401-deab-600c-f946e0bd27fa@redhat.com>
2023-02-15  7:25 ` cgroup: deadlock between cpu_hotplug_lock and freezer_mutex Hillf Danton
2023-02-15 10:36   ` Xiubo Li

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox