Re: [PATCH v3 2/5] mm: mlock: use folios and a folio batch internally

[Vlastimil Babka]

On 12/26/22 09:44, Lorenzo Stoakes wrote:
> This brings mlock in line with the folio batches declared in mm/swap.c and
> makes the code more consistent across the two.
> 
> The existing mechanism for identifying which operation each folio in the
> batch is undergoing is maintained, i.e. using the lower 2 bits of the
> struct folio address (previously struct page address). This should continue
> to function correctly as folios remain at least system word-aligned.
> 
> All invoctions of mlock() pass either a non-compound page or the head of a
> THP-compound page and no tail pages need updating so this functionality
> works with struct folios being used internally rather than struct pages.
> 
> In this patch the external interface is kept identical to before in order
> to maintain separation between patches in the series, using a rather
> awkward conversion from struct page to struct folio in relevant functions.
> 
> However, this maintenance of the existing interface is intended to be
> temporary - the next patch in the series will update the interfaces to
> accept folios directly.
> 
> Signed-off-by: Lorenzo Stoakes <lstoakes@xxxxxxxxx>

Acked-by: Vlastimil Babka <vbabka@xxxxxxx>

with some nits:

> -static struct lruvec *__munlock_page(struct page *page, struct lruvec *lruvec)
> +static struct lruvec *__munlock_folio(struct folio *folio, struct lruvec *lruvec)
>  {
> -	int nr_pages = thp_nr_pages(page);
> +	int nr_pages = folio_nr_pages(folio);
>  	bool isolated = false;
>  
> -	if (!TestClearPageLRU(page))
> +	if (!folio_test_clear_lru(folio))
>  		goto munlock;
>  
>  	isolated = true;
> -	lruvec = folio_lruvec_relock_irq(page_folio(page), lruvec);
> +	lruvec = folio_lruvec_relock_irq(folio, lruvec);
>  
> -	if (PageUnevictable(page)) {
> +	if (folio_test_unevictable(folio)) {
>  		/* Then mlock_count is maintained, but might undercount */
> -		if (page->mlock_count)
> -			page->mlock_count--;
> -		if (page->mlock_count)
> +		if (folio->mlock_count)
> +			folio->mlock_count--;
> +		if (folio->mlock_count)
>  			goto out;
>  	}
>  	/* else assume that was the last mlock: reclaim will fix it if not */
>  
>  munlock:
> -	if (TestClearPageMlocked(page)) {
> -		__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
> -		if (isolated || !PageUnevictable(page))
> +	if (folio_test_clear_mlocked(folio)) {
> +		zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages);

AFAIK the 1:1 replacement would be __zone_stat_mod_folio(), this is stronger
thus not causing a bug, but unneccessary?

> +		if (isolated || !folio_test_unevictable(folio))
>  			__count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages);
>  		else
>  			__count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages);
>  	}
>  
> -	/* page_evictable() has to be checked *after* clearing Mlocked */
> -	if (isolated && PageUnevictable(page) && page_evictable(page)) {
> -		del_page_from_lru_list(page, lruvec);
> -		ClearPageUnevictable(page);
> -		add_page_to_lru_list(page, lruvec);
> +	/* folio_evictable() has to be checked *after* clearing Mlocked */
> +	if (isolated && folio_test_unevictable(folio) && folio_evictable(folio)) {
> +		lruvec_del_folio(lruvec, folio);
> +		folio_clear_unevictable(folio);
> +		lruvec_add_folio(lruvec, folio);
>  		__count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages);
>  	}
>  out:
>  	if (isolated)
> -		SetPageLRU(page);
> +		folio_set_lru(folio);
>  	return lruvec;
>  }
>  
>  /*
> - * Flags held in the low bits of a struct page pointer on the mlock_pvec.
> + * Flags held in the low bits of a struct folio pointer on the mlock_fbatch.
>   */
>  #define LRU_PAGE 0x1
>  #define NEW_PAGE 0x2

Should it be X_FOLIO now?

> -static inline struct page *mlock_lru(struct page *page)
> +static inline struct folio *mlock_lru(struct folio *folio)
>  {
> -	return (struct page *)((unsigned long)page + LRU_PAGE);
> +	return (struct folio *)((unsigned long)folio + LRU_PAGE);
>  }
>  
> -static inline struct page *mlock_new(struct page *page)
> +static inline struct folio *mlock_new(struct folio *folio)
>  {
> -	return (struct page *)((unsigned long)page + NEW_PAGE);
> +	return (struct folio *)((unsigned long)folio + NEW_PAGE);
>  }
>  
>  /*
> - * mlock_pagevec() is derived from pagevec_lru_move_fn():
> - * perhaps that can make use of such page pointer flags in future,
> - * but for now just keep it for mlock.  We could use three separate
> - * pagevecs instead, but one feels better (munlocking a full pagevec
> - * does not need to drain mlocking pagevecs first).
> + * mlock_folio_batch() is derived from folio_batch_move_lru(): perhaps that can
> + * make use of such page pointer flags in future, but for now just keep it for

		       ^ folio?	

> + * mlock.  We could use three separate folio batches instead, but one feels
> + * better (munlocking a full folio batch does not need to drain mlocking folio
> + * batches first).
>   */
> -static void mlock_pagevec(struct pagevec *pvec)
> +static void mlock_folio_batch(struct folio_batch *fbatch)