Re: [regression] cpuset,mm: update tasks' mems_allowed in time (58568d2)

[Miao Xie <miaox@cn.fujitsu.com>]

on 2010-2-22 20:06, Nick Piggin wrote: 
>>>>> guarantee_online_cpus() truly does require callback_mutex, the 
>>>>> cgroup_scan_tasks() iterator locking can protect changes in the cgroup 
>>>>> hierarchy but it doesn't protect a store to cs->cpus_allowed or for 
>>>>> hotplug.
>>>>
>>>> Right, but the callback_mutex was being removed by this patch.
>>>>
>>>
>>> I was making the case for it to be readded :)
>>
>> But cgroup_mutex is held when someone changes cs->cpus_allowed or doing hotplug,
>> so I think callback_mutex is not necessary in this case.
> 
> So long as that's done consistently (and we should update the comments
> too).

I will update the comments.

>> ---
>> diff --git a/init/main.c b/init/main.c
>> index 4cb47a1..512ba15 100644
>> --- a/init/main.c
>> +++ b/init/main.c
>> @@ -846,7 +846,7 @@ static int __init kernel_init(void * unused)
>>  	/*
>>  	 * init can allocate pages on any node
>>  	 */
>> -	set_mems_allowed(node_possible_map);
>> +	set_mems_allowed(node_states[N_HIGH_MEMORY]);
>>  	/*
>>  	 * init can run on any cpu.
>>  	 */
>> diff --git a/kernel/cpuset.c b/kernel/cpuset.c
>> index ba401fa..e29b440 100644
>> --- a/kernel/cpuset.c
>> +++ b/kernel/cpuset.c
>> @@ -935,10 +935,12 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
>>  	struct task_struct *tsk = current;
>>  
>>  	tsk->mems_allowed = *to;
>> +	wmb();
>>  
>>  	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
>>  
>>  	guarantee_online_mems(task_cs(tsk),&tsk->mems_allowed);
>> +	wmb();
>>  }
>>  
>>  /*
> 
> You always need to comment barriers (and use smp_ variants unless you're
> doing mmio).

It's my mistake. 
I'll remake a new patch and change it.

Thanks.
Miao

> 
> 
>> @@ -1391,11 +1393,10 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
>>  
>>  	if (cs == &top_cpuset) {
>>  		cpumask_copy(cpus_attach, cpu_possible_mask);
>> -		to = node_possible_map;
>>  	} else {
>>  		guarantee_online_cpus(cs, cpus_attach);
>> -		guarantee_online_mems(cs, &to);
>>  	}
>> +	guarantee_online_mems(cs, &to);
>>  
>>  	/* do per-task migration stuff possibly for each in the threadgroup */
>>  	cpuset_attach_task(tsk, &to, cs);
>> @@ -2090,15 +2091,19 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
>>  static int cpuset_track_online_nodes(struct notifier_block *self,
>>  				unsigned long action, void *arg)
>>  {
>> +	nodemask_t oldmems;
>> +
>>  	cgroup_lock();
>>  	switch (action) {
>>  	case MEM_ONLINE:
>> -	case MEM_OFFLINE:
>> +		oldmems = top_cpuset.mems_allowed;
>>  		mutex_lock(&callback_mutex);
>>  		top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
>>  		mutex_unlock(&callback_mutex);
>> -		if (action == MEM_OFFLINE)
>> -			scan_for_empty_cpusets(&top_cpuset);
>> +		update_tasks_nodemask(&top_cpuset, &oldmems, NULL);
>> +		break;
>> +	case MEM_OFFLINE:
>> +		scan_for_empty_cpusets(&top_cpuset);
>>  		break;
>>  	default:
>>  		break;
>> diff --git a/kernel/kthread.c b/kernel/kthread.c
>> index fbb6222..84c7f99 100644
>> --- a/kernel/kthread.c
>> +++ b/kernel/kthread.c
>> @@ -219,7 +219,7 @@ int kthreadd(void *unused)
>>  	set_task_comm(tsk, "kthreadd");
>>  	ignore_signals(tsk);
>>  	set_cpus_allowed_ptr(tsk, cpu_all_mask);
>> -	set_mems_allowed(node_possible_map);
>> +	set_mems_allowed(node_states[N_HIGH_MEMORY]);
>>  
>>  	current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;
>>  
> 
> 
>