Re: [PATCH 2/2] mm/page_alloc: Leave IRQs enabled for per-cpu page allocations

[Vlastimil Babka]

On 11/21/22 17:03, Mel Gorman wrote:
> On Mon, Nov 21, 2022 at 12:01:23PM +0000, Mel Gorman wrote:
>> On Fri, Nov 18, 2022 at 03:30:57PM +0100, Vlastimil Babka wrote:
>> > On 11/18/22 11:17, Mel Gorman wrote:
>> > AFAICS if this block was just "locked_zone = NULL;" then the existing code
>> > would do the right thing.
>> > Or maybe to have simpler code, just do batch_count++ here and
>> > make the relocking check do
>> > if (zone != locked_zone || batch_count == SWAP_CLUSTER_MAX)
>> > 
>> 
>> While I think you're right, I think it's a bit subtle, the batch reset would
>> need to move, rechecked within the "Different zone, different pcp lock."
>> block and it would be easy to forget exactly why it's structured like
>> that in the future.  Rather than being a fix, it could be a standalone
>> patch so it would be obvious in git blame but I don't feel particularly
>> strongly about it.
>> 
> 
> Ok, less subtle than I initially thought but still deserving of a separate
> patch instead of being a fix. This?

Yeah, thanks!

> --8<--
> mm/page_alloc: Simplify locking during free_unref_page_list
> 
> While freeing a large list, the zone lock will be released and reacquired
> to avoid long hold times since commit c24ad77d962c ("mm/page_alloc.c: avoid
> excessive IRQ disabled times in free_unref_page_list()"). As suggested
> by Vlastimil Babka, the lockrelease/reacquire logic can be simplified by
> reusing the logic that acquires a different lock when changing zones.
> 
> Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>

Reviewed-by: Vlastimil Babka <vbabka@xxxxxxx>

> ---
>  mm/page_alloc.c | 25 +++++++++----------------
>  1 file changed, 9 insertions(+), 16 deletions(-)
> 
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 445066617204..08e32daf0918 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3518,13 +3518,19 @@ void free_unref_page_list(struct list_head *list)
>  		list_del(&page->lru);
>  		migratetype = get_pcppage_migratetype(page);
>  
> -		/* Different zone, different pcp lock. */
> -		if (zone != locked_zone) {
> +		/*
> +		 * Either different zone requiring a different pcp lock or
> +		 * excessive lock hold times when freeing a large list of
> +		 * pages.
> +		 */
> +		if (zone != locked_zone || batch_count == SWAP_CLUSTER_MAX) {
>  			if (pcp) {
>  				pcp_spin_unlock(pcp);
>  				pcp_trylock_finish(UP_flags);
>  			}
>  
> +			batch_count = 0;
> +
>  			/*
>  			 * trylock is necessary as pages may be getting freed
>  			 * from IRQ or SoftIRQ context after an IO completion.
> @@ -3539,7 +3545,6 @@ void free_unref_page_list(struct list_head *list)
>  				continue;
>  			}
>  			locked_zone = zone;
> -			batch_count = 0;
>  		}
>  
>  		/*
> @@ -3551,19 +3556,7 @@ void free_unref_page_list(struct list_head *list)
>  
>  		trace_mm_page_free_batched(page);
>  		free_unref_page_commit(zone, pcp, page, migratetype, 0);
> -
> -		/*
> -		 * Guard against excessive lock hold times when freeing
> -		 * a large list of pages. Lock will be reacquired if
> -		 * necessary on the next iteration.
> -		 */
> -		if (++batch_count == SWAP_CLUSTER_MAX) {
> -			pcp_spin_unlock(pcp);
> -			pcp_trylock_finish(UP_flags);
> -			batch_count = 0;
> -			pcp = NULL;
> -			locked_zone = NULL;
> -		}
> +		batch_count++;
>  	}
>  
>  	if (pcp) {