Re: [PATCH v3 4/6] percpu: generalize pcpu_balance_populated()

[Dennis Zhou <dennis@kernel.org>]

Hello,

On Wed, Apr 07, 2021 at 08:57:34PM -0700, Roman Gushchin wrote:
> To prepare for the depopulation of percpu chunks, split out the
> populating part of the pcpu_balance_populated() into the new
> pcpu_grow_populated() (with an intention to add
> pcpu_shrink_populated() in the next commit).
> 
> The goal of pcpu_balance_populated() is to determine whether
> there is a shortage or an excessive amount of empty percpu pages
> and call into the corresponding function.
> 
> pcpu_grow_populated() takes a desired number of pages as an argument
> (nr_to_pop). If it creates a new chunk, nr_to_pop should be updated
> to reflect that the new chunk could be created already populated.
> Otherwise an infinite loop might appear.
> 
> Signed-off-by: Roman Gushchin <guro@fb.com>
> ---
>  mm/percpu.c | 63 +++++++++++++++++++++++++++++++++--------------------
>  1 file changed, 39 insertions(+), 24 deletions(-)
> 
> diff --git a/mm/percpu.c b/mm/percpu.c
> index 61339b3d9337..e20119668c42 100644
> --- a/mm/percpu.c
> +++ b/mm/percpu.c
> @@ -1979,7 +1979,7 @@ static void pcpu_balance_free(enum pcpu_chunk_type type)
>  }
>  
>  /**
> - * pcpu_balance_populated - manage the amount of populated pages
> + * pcpu_grow_populated - populate chunk(s) to satisfy atomic allocations
>   * @type: chunk type
>   *
>   * Maintain a certain amount of populated pages to satisfy atomic allocations.
> @@ -1988,35 +1988,15 @@ static void pcpu_balance_free(enum pcpu_chunk_type type)
>   * allocation causes the failure as it is possible that requests can be
>   * serviced from already backed regions.
>   */
> -static void pcpu_balance_populated(enum pcpu_chunk_type type)
> +static void pcpu_grow_populated(enum pcpu_chunk_type type, int nr_to_pop)
>  {
>  	/* gfp flags passed to underlying allocators */
>  	const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
>  	struct list_head *pcpu_slot = pcpu_chunk_list(type);
>  	struct pcpu_chunk *chunk;
> -	int slot, nr_to_pop, ret;
> +	int slot, ret;
>  
> -	/*
> -	 * Ensure there are certain number of free populated pages for
> -	 * atomic allocs.  Fill up from the most packed so that atomic
> -	 * allocs don't increase fragmentation.  If atomic allocation
> -	 * failed previously, always populate the maximum amount.  This
> -	 * should prevent atomic allocs larger than PAGE_SIZE from keeping
> -	 * failing indefinitely; however, large atomic allocs are not
> -	 * something we support properly and can be highly unreliable and
> -	 * inefficient.
> -	 */
>  retry_pop:
> -	if (pcpu_atomic_alloc_failed) {
> -		nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH;
> -		/* best effort anyway, don't worry about synchronization */
> -		pcpu_atomic_alloc_failed = false;
> -	} else {
> -		nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH -
> -				  pcpu_nr_empty_pop_pages[type],
> -				  0, PCPU_EMPTY_POP_PAGES_HIGH);
> -	}
> -
>  	for (slot = pcpu_size_to_slot(PAGE_SIZE); slot < pcpu_nr_slots; slot++) {
>  		unsigned int nr_unpop = 0, rs, re;
>  
> @@ -2060,12 +2040,47 @@ static void pcpu_balance_populated(enum pcpu_chunk_type type)
>  		if (chunk) {
>  			spin_lock_irq(&pcpu_lock);
>  			pcpu_chunk_relocate(chunk, -1);
> +			nr_to_pop = max_t(int, 0, nr_to_pop - chunk->nr_populated);
>  			spin_unlock_irq(&pcpu_lock);
> -			goto retry_pop;
> +			if (nr_to_pop)
> +				goto retry_pop;
>  		}
>  	}
>  }
>  
> +/**
> + * pcpu_balance_populated - manage the amount of populated pages
> + * @type: chunk type
> + *
> + * Populate or depopulate chunks to maintain a certain amount
> + * of free pages to satisfy atomic allocations, but not waste
> + * large amounts of memory.
> + */
> +static void pcpu_balance_populated(enum pcpu_chunk_type type)
> +{
> +	int nr_to_pop;
> +
> +	/*
> +	 * Ensure there are certain number of free populated pages for
> +	 * atomic allocs.  Fill up from the most packed so that atomic
> +	 * allocs don't increase fragmentation.  If atomic allocation
> +	 * failed previously, always populate the maximum amount.  This
> +	 * should prevent atomic allocs larger than PAGE_SIZE from keeping
> +	 * failing indefinitely; however, large atomic allocs are not
> +	 * something we support properly and can be highly unreliable and
> +	 * inefficient.
> +	 */
> +	if (pcpu_atomic_alloc_failed) {
> +		nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH;
> +		/* best effort anyway, don't worry about synchronization */
> +		pcpu_atomic_alloc_failed = false;
> +		pcpu_grow_populated(type, nr_to_pop);
> +	} else if (pcpu_nr_empty_pop_pages[type] < PCPU_EMPTY_POP_PAGES_HIGH) {
> +		nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH - pcpu_nr_empty_pop_pages[type];
> +		pcpu_grow_populated(type, nr_to_pop);
> +	}
> +}
> +
>  /**
>   * pcpu_balance_workfn - manage the amount of free chunks and populated pages
>   * @work: unused
> -- 
> 2.30.2
> 

I've applied this for-5.14.

Thanks,
Dennis