[PATCH v3 02/11] fs: Allow fine-grained control of folio sizes

["Pankaj Raghav (Samsung)" <kernel@pankajraghav.com>]

From: "Matthew Wilcox (Oracle)" <willy@infradead.org>

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) <willy@infradead.org>
Co-developed-by: Pankaj Raghav <p.raghav@samsung.com>
Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 include/linux/pagemap.h | 100 ++++++++++++++++++++++++++++++++--------
 1 file changed, 80 insertions(+), 20 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 2df35e65557d..fc8eb9c94e9c 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 +349,47 @@ 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_min_order() - Set the minimum folio order
+ * @mapping: The address_space.
+ * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive).
+ *
+ * The filesystem should call this function in its inode constructor to
+ * indicate which base size 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_min_order(struct address_space *mapping,
+					       unsigned int min)
+{
+	if (min > MAX_PAGECACHE_ORDER)
+		min = MAX_PAGECACHE_ORDER;
+
+	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.
+ * @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 +400,37 @@ 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_min_order(mapping, 0);
+}
+
+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 +440,7 @@ 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 +601,6 @@ 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