[RFC,01/23] fs: Allow fine-grained control of folio sizes

Commit Message

Pankaj Raghav (Samsung) Sept. 15, 2023, 6:38 p.m. UTC

From: "Matthew Wilcox (Oracle)" <[e-mail]>

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.

[Pankaj]: added mapping_min_folio_order(), changed MAX_MASK to 0x0003e000
Signed-off-by: Pankaj Raghav <[e-mail]>
[mcgrof: rebase in light of "mm, netfs, fscache: stop read optimisation
when folio removed from pagecache" which adds AS_RELEASE_ALWAYS]
Signed-off-by: Matthew Wilcox (Oracle) <[e-mail]>
---
 include/linux/pagemap.h | 78 +++++++++++++++++++++++++++++++----------
 1 file changed, 60 insertions(+), 18 deletions(-)

Comments

Matthew Wilcox Sept. 15, 2023, 7:03 p.m. UTC | #1

On Fri, Sep 15, 2023 at 08:38:26PM +0200, Pankaj Raghav wrote:
> +static inline void mapping_set_folio_orders(struct address_space *mapping,
> +					    unsigned int min, unsigned int max)
> +{
> +	/*
> +	 * XXX: max is ignored as only minimum folio order is supported
> +	 * currently.
> +	 */

I think we need some sanity checking ...

	if (min == 1)
		min = 2;
	if (max < min)
		max = min;
	if (max > MAX_PAGECACHE_ORDER)
		max = MAX_PAGECACHE_ORDER;

> +	mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) |
> +			 (min << AS_FOLIO_ORDER_MIN) |
> +			 (MAX_PAGECACHE_ORDER << AS_FOLIO_ORDER_MAX);
> +}

Patch

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 759b29d9a69a..d2b5308cc59e 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -202,10 +202,16 @@  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_RELEASE_ALWAYS = 6,      /* Call ->release_folio(), even if no private data */
+	AS_FOLIO_ORDER_MIN = 8,
+	AS_FOLIO_ORDER_MAX = 13,
+	/* 8-17 are used for FOLIO_ORDER */
 };
 
+#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
@@ -310,6 +316,46 @@  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)
+{
+	/*
+	 * 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.
@@ -323,7 +369,17 @@  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;
 }
 
 /*
@@ -332,8 +388,7 @@  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);
+	return mapping_max_folio_order(mapping) > 0;
 }
 
 static inline int filemap_nr_thps(struct address_space *mapping)
@@ -494,19 +549,6 @@  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