From: "Matthew Wilcox (Oracle)" <[email protected]>
Some filesystems want to be able to ensure that folios that are added to
the page cache are at least a certain size.
Add mapping_set_folio_min_order() to allow this level of control.
Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
Co-developed-by: Pankaj Raghav <[email protected]>
Signed-off-by: Pankaj Raghav <[email protected]>
Signed-off-by: Luis Chamberlain <[email protected]>
---
include/linux/pagemap.h | 116 +++++++++++++++++++++++++++++++++-------
1 file changed, 96 insertions(+), 20 deletions(-)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 2df35e65557d..2e5612de1749 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
@@ -344,9 +349,63 @@ 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_order_range() - Set the folio order range
+ * @mapping: The address_space.
+ * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive).
+ * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive).
+ *
+ * The filesystem should call this function in its inode constructor to
+ * indicate which base size (min) and maximum size (max) 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_order_range(struct address_space *mapping,
+ unsigned int min_order,
+ unsigned int max_order)
+{
+ if (min_order > MAX_PAGECACHE_ORDER)
+ min_order = MAX_PAGECACHE_ORDER;
+
+ if (max_order > MAX_PAGECACHE_ORDER)
+ max_order = MAX_PAGECACHE_ORDER;
+
+ max_order = max(max_order, min_order);
+ /*
+ * TODO: max_order is not yet supported in filemap.
+ */
+ mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) |
+ (min_order << AS_FOLIO_ORDER_MIN) |
+ (max_order << AS_FOLIO_ORDER_MAX);
+}
+
+static inline void mapping_set_folio_min_order(struct address_space *mapping,
+ unsigned int min)
+{
+ mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER);
+}
+
/**
* mapping_set_large_folios() - Indicate the file supports large folios.
- * @mapping: The file.
+ * @mapping: The address_space.
*
* The filesystem should call this function in its inode constructor to
* indicate that the VFS can use large folios to cache the contents of
@@ -357,7 +416,37 @@ 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_order_range(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 long mapping_min_folio_nrpages(struct address_space *mapping)
+{
+ return 1UL << mapping_min_folio_order(mapping);
+}
+
+/**
+ * mapping_align_start_index() - Align starting index based on the min
+ * folio order of the page cache.
+ * @mapping: The address_space.
+ *
+ * Ensure the index used is aligned to the minimum folio order when adding
+ * new folios to the page cache by rounding down to the nearest minimum
+ * folio number of pages.
+ */
+static inline pgoff_t mapping_align_start_index(struct address_space *mapping,
+ pgoff_t index)
+{
+ return round_down(index, mapping_min_folio_nrpages(mapping));
}
/*
@@ -367,7 +456,7 @@ 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 +617,6 @@ 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
--
2.34.1
On 4/25/24 13:37, Pankaj Raghav (Samsung) wrote:
> From: "Matthew Wilcox (Oracle)" <[email protected]>
>
> Some filesystems want to be able to ensure that folios that are added to
> the page cache are at least a certain size.
> Add mapping_set_folio_min_order() to allow this level of control.
>
> Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
> Co-developed-by: Pankaj Raghav <[email protected]>
> Signed-off-by: Pankaj Raghav <[email protected]>
> Signed-off-by: Luis Chamberlain <[email protected]>
> ---
> include/linux/pagemap.h | 116 +++++++++++++++++++++++++++++++++-------
> 1 file changed, 96 insertions(+), 20 deletions(-)
>
Reviewed-by: Hannes Reinecke <[email protected]>
Cheers,
Hannes
--
Dr. Hannes Reinecke Kernel Storage Architect
[email protected] +49 911 74053 688
SUSE Software Solutions GmbH, Frankenstr. 146, 90461 Nürnberg
HRB 36809 (AG Nürnberg), GF: I. Totev, A. McDonald, W. Knoblich
On Thu, Apr 25, 2024 at 01:37:37PM +0200, Pankaj Raghav (Samsung) wrote:
> From: "Matthew Wilcox (Oracle)" <[email protected]>
>
> Some filesystems want to be able to ensure that folios that are added to
> the page cache are at least a certain size.
> Add mapping_set_folio_min_order() to allow this level of control.
>
> Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
> Co-developed-by: Pankaj Raghav <[email protected]>
> Signed-off-by: Pankaj Raghav <[email protected]>
> Signed-off-by: Luis Chamberlain <[email protected]>
Looks good to me,
Reviewed-by: Darrick J. Wong <[email protected]>
--D
> ---
> include/linux/pagemap.h | 116 +++++++++++++++++++++++++++++++++-------
> 1 file changed, 96 insertions(+), 20 deletions(-)
>
> diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
> index 2df35e65557d..2e5612de1749 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
> @@ -344,9 +349,63 @@ 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_order_range() - Set the folio order range
> + * @mapping: The address_space.
> + * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive).
> + * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive).
> + *
> + * The filesystem should call this function in its inode constructor to
> + * indicate which base size (min) and maximum size (max) 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_order_range(struct address_space *mapping,
> + unsigned int min_order,
> + unsigned int max_order)
> +{
> + if (min_order > MAX_PAGECACHE_ORDER)
> + min_order = MAX_PAGECACHE_ORDER;
> +
> + if (max_order > MAX_PAGECACHE_ORDER)
> + max_order = MAX_PAGECACHE_ORDER;
> +
> + max_order = max(max_order, min_order);
> + /*
> + * TODO: max_order is not yet supported in filemap.
> + */
> + mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) |
> + (min_order << AS_FOLIO_ORDER_MIN) |
> + (max_order << AS_FOLIO_ORDER_MAX);
> +}
> +
> +static inline void mapping_set_folio_min_order(struct address_space *mapping,
> + unsigned int min)
> +{
> + mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER);
> +}
> +
> /**
> * mapping_set_large_folios() - Indicate the file supports large folios.
> - * @mapping: The file.
> + * @mapping: The address_space.
> *
> * The filesystem should call this function in its inode constructor to
> * indicate that the VFS can use large folios to cache the contents of
> @@ -357,7 +416,37 @@ 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_order_range(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 long mapping_min_folio_nrpages(struct address_space *mapping)
> +{
> + return 1UL << mapping_min_folio_order(mapping);
> +}
> +
> +/**
> + * mapping_align_start_index() - Align starting index based on the min
> + * folio order of the page cache.
> + * @mapping: The address_space.
> + *
> + * Ensure the index used is aligned to the minimum folio order when adding
> + * new folios to the page cache by rounding down to the nearest minimum
> + * folio number of pages.
> + */
> +static inline pgoff_t mapping_align_start_index(struct address_space *mapping,
> + pgoff_t index)
> +{
> + return round_down(index, mapping_min_folio_nrpages(mapping));
> }
>
> /*
> @@ -367,7 +456,7 @@ 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 +617,6 @@ 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
> --
> 2.34.1
>
>