Re: [PATCH] mm, swap: Remove unnecessary smp_rmb() in swap_type_to_swap_info()

[Huang, Ying]

Peter Zijlstra <peterz@xxxxxxxxxxxxx> writes:

> On Thu, May 13, 2021 at 02:48:37PM +0800, Huang Ying wrote:
>>  mm/swapfile.c | 18 +++++++++---------
>>  1 file changed, 9 insertions(+), 9 deletions(-)
>> 
>> diff --git a/mm/swapfile.c b/mm/swapfile.c
>> index 2aad85751991..4c1fb28bbe0e 100644
>> --- a/mm/swapfile.c
>> +++ b/mm/swapfile.c
>> @@ -100,10 +100,14 @@ atomic_t nr_rotate_swap = ATOMIC_INIT(0);
>>  
>>  static struct swap_info_struct *swap_type_to_swap_info(int type)
>>  {
>> -	if (type >= READ_ONCE(nr_swapfiles))
>> +	if (type >= MAX_SWAPFILES)
>>  		return NULL;
>>  
>> -	smp_rmb();	/* Pairs with smp_wmb in alloc_swap_info. */
>> +	/*
>> +	 * The data dependency ordering from the READ_ONCE() pairs
>> +	 * with smp_wmb() in alloc_swap_info() to guarantee the
>> +	 * swap_info_struct fields are read after swap_info[type].
>> +	 */
>>  	return READ_ONCE(swap_info[type]);
>>  }
>>  
>> @@ -2884,14 +2888,10 @@ static struct swap_info_struct *alloc_swap_info(void)
>>  	}
>>  	if (type >= nr_swapfiles) {
>>  		p->type = type;
>> -		WRITE_ONCE(swap_info[type], p);
>> -		/*
>> -		 * Write swap_info[type] before nr_swapfiles, in case a
>> -		 * racing procfs swap_start() or swap_next() is reading them.
>> -		 * (We never shrink nr_swapfiles, we never free this entry.)
>> -		 */
>> +		/* Paired with READ_ONCE() in swap_type_to_swap_info() */
>>  		smp_wmb();
>> -		WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1);
>> +		WRITE_ONCE(swap_info[type], p);
>> +		nr_swapfiles++;
>
> Ah, I think I see what you meant to say, it would perhaps help if you
> write it like so:
>
>
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 149e77454e3c..94735248dcd2 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -99,11 +99,10 @@ atomic_t nr_rotate_swap = ATOMIC_INIT(0);
>  
>  static struct swap_info_struct *swap_type_to_swap_info(int type)
>  {
> -	if (type >= READ_ONCE(nr_swapfiles))
> +	if (type >= MAX_SWAPFILES)
>  		return NULL;
>  
> -	smp_rmb();	/* Pairs with smp_wmb in alloc_swap_info. */
> -	return READ_ONCE(swap_info[type]);
> +	return READ_ONCE(swap_info[type]); /* rcu_dereference() */
>  }
>  
>  static inline unsigned char swap_count(unsigned char ent)
> @@ -2869,14 +2868,11 @@ static struct swap_info_struct *alloc_swap_info(void)
>  	}
>  	if (type >= nr_swapfiles) {
>  		p->type = type;
> -		WRITE_ONCE(swap_info[type], p);
>  		/*
> -		 * Write swap_info[type] before nr_swapfiles, in case a
> -		 * racing procfs swap_start() or swap_next() is reading them.
> -		 * (We never shrink nr_swapfiles, we never free this entry.)
> +		 * Publish the swap_info_struct.
>  		 */
> -		smp_wmb();
> -		WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1);
> +		smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */
> +		nr_swapfiles++;
>  	} else {
>  		defer = p;
>  		p = swap_info[type];

OK.  It seems that this helps people to understand.  I will use this in
the next version.

Best Regards,
Huang, Ying