Re: [RFC v2 01/14] fs: Allow fine-grained control of folio sizes

["Darrick J. Wong" <djwong@kernel.org>]

On Tue, Feb 13, 2024 at 10:37:00AM +0100, Pankaj Raghav (Samsung) wrote:
> From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
> 
> Some filesystems want to be able to limit the maximum size of folios,
> and some want to be able to ensure that folios are at least a certain
> size.  Add mapping_set_folio_orders() to allow this level of control.
> The max folio order parameter is ignored and it is always set to
> MAX_PAGECACHE_ORDER.

Why?  If MAX_PAGECACHE_ORDER is 8 and I instead pass in max==3, I'm
going to be surprised by my constraint being ignored.  Maybe I said that
because I'm not prepared to handle an order-7 folio; or some customer
will have some weird desire to twist this knob to make their workflow
faster.

--D

> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
> Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
> ---
>  include/linux/pagemap.h | 92 ++++++++++++++++++++++++++++++++---------
>  1 file changed, 73 insertions(+), 19 deletions(-)
> 
> diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
> index 2df35e65557d..5618f762187b 100644
> --- a/include/linux/pagemap.h
> +++ b/include/linux/pagemap.h
> @@ -202,13 +202,18 @@ enum mapping_flags {
>  	AS_EXITING	= 4, 	/* final truncate in progress */
>  	/* writeback related tags are not used */
>  	AS_NO_WRITEBACK_TAGS = 5,
> -	AS_LARGE_FOLIO_SUPPORT = 6,
> -	AS_RELEASE_ALWAYS,	/* Call ->release_folio(), even if no private data */
> -	AS_STABLE_WRITES,	/* must wait for writeback before modifying
> +	AS_RELEASE_ALWAYS = 6,	/* Call ->release_folio(), even if no private data */
> +	AS_STABLE_WRITES = 7,	/* must wait for writeback before modifying
>  				   folio contents */
> -	AS_UNMOVABLE,		/* The mapping cannot be moved, ever */
> +	AS_FOLIO_ORDER_MIN = 8,
> +	AS_FOLIO_ORDER_MAX = 13, /* Bit 8-17 are used for FOLIO_ORDER */
> +	AS_UNMOVABLE = 18,		/* The mapping cannot be moved, ever */
>  };
>  
> +#define AS_FOLIO_ORDER_MIN_MASK 0x00001f00
> +#define AS_FOLIO_ORDER_MAX_MASK 0x0003e000
> +#define AS_FOLIO_ORDER_MASK (AS_FOLIO_ORDER_MIN_MASK | AS_FOLIO_ORDER_MAX_MASK)
> +
>  /**
>   * mapping_set_error - record a writeback error in the address_space
>   * @mapping: the mapping in which an error should be set
> @@ -344,6 +349,53 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
>  	m->gfp_mask = mask;
>  }
>  
> +/*
> + * There are some parts of the kernel which assume that PMD entries
> + * are exactly HPAGE_PMD_ORDER.  Those should be fixed, but until then,
> + * limit the maximum allocation order to PMD size.  I'm not aware of any
> + * assumptions about maximum order if THP are disabled, but 8 seems like
> + * a good order (that's 1MB if you're using 4kB pages)
> + */
> +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> +#define MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
> +#else
> +#define MAX_PAGECACHE_ORDER	8
> +#endif
> +
> +/*
> + * mapping_set_folio_orders() - Set the range of folio sizes supported.
> + * @mapping: The file.
> + * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive).
> + * @max: Maximum folio order (between 0-MAX_PAGECACHE_ORDER inclusive).
> + *
> + * The filesystem should call this function in its inode constructor to
> + * indicate which sizes of folio the VFS can use to cache the contents
> + * of the file.  This should only be used if the filesystem needs special
> + * handling of folio sizes (ie there is something the core cannot know).
> + * Do not tune it based on, eg, i_size.
> + *
> + * Context: This should not be called while the inode is active as it
> + * is non-atomic.
> + */
> +static inline void mapping_set_folio_orders(struct address_space *mapping,
> +					    unsigned int min, unsigned int max)
> +{
> +	if (min == 1)
> +		min = 2;
> +	if (max < min)
> +		max = min;
> +	if (max > MAX_PAGECACHE_ORDER)
> +		max = MAX_PAGECACHE_ORDER;
> +
> +	/*
> +	 * XXX: max is ignored as only minimum folio order is supported
> +	 * currently.
> +	 */
> +	mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) |
> +			 (min << AS_FOLIO_ORDER_MIN) |
> +			 (MAX_PAGECACHE_ORDER << AS_FOLIO_ORDER_MAX);
> +}
> +
>  /**
>   * mapping_set_large_folios() - Indicate the file supports large folios.
>   * @mapping: The file.
> @@ -357,7 +409,22 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
>   */
>  static inline void mapping_set_large_folios(struct address_space *mapping)
>  {
> -	__set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
> +	mapping_set_folio_orders(mapping, 0, MAX_PAGECACHE_ORDER);
> +}
> +
> +static inline unsigned int mapping_max_folio_order(struct address_space *mapping)
> +{
> +	return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX;
> +}
> +
> +static inline unsigned int mapping_min_folio_order(struct address_space *mapping)
> +{
> +	return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN;
> +}
> +
> +static inline unsigned int mapping_min_folio_nrpages(struct address_space *mapping)
> +{
> +	return 1U << mapping_min_folio_order(mapping);
>  }
>  
>  /*
> @@ -367,7 +434,7 @@ static inline void mapping_set_large_folios(struct address_space *mapping)
>  static inline bool mapping_large_folio_support(struct address_space *mapping)
>  {
>  	return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
> -		test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
> +	       (mapping_max_folio_order(mapping) > 0);
>  }
>  
>  static inline int filemap_nr_thps(struct address_space *mapping)
> @@ -528,19 +595,6 @@ static inline void *detach_page_private(struct page *page)
>  	return folio_detach_private(page_folio(page));
>  }
>  
> -/*
> - * There are some parts of the kernel which assume that PMD entries
> - * are exactly HPAGE_PMD_ORDER.  Those should be fixed, but until then,
> - * limit the maximum allocation order to PMD size.  I'm not aware of any
> - * assumptions about maximum order if THP are disabled, but 8 seems like
> - * a good order (that's 1MB if you're using 4kB pages)
> - */
> -#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> -#define MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
> -#else
> -#define MAX_PAGECACHE_ORDER	8
> -#endif
> -
>  #ifdef CONFIG_NUMA
>  struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order);
>  #else
> -- 
> 2.43.0
> 
>