[v12,01/10] fs: Allow fine-grained control of folio sizes

Commit Message

Pankaj Raghav (Samsung) Aug. 15, 2024, 9:08 a.m. UTC

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

We need filesystems to be able to communicate acceptable folio sizes
to the pagecache for a variety of uses (e.g. large block sizes).
Support a range of folio sizes between order-0 and order-31.

Signed-off-by: Matthew Wilcox (Oracle) <[e-mail]>
Co-developed-by: Pankaj Raghav <[e-mail]>
Signed-off-by: Pankaj Raghav <[e-mail]>
Reviewed-by: Hannes Reinecke <[e-mail]>
Reviewed-by: Darrick J. Wong <[e-mail]>
---
 include/linux/pagemap.h | 89 ++++++++++++++++++++++++++++++++++-------
 mm/filemap.c            |  6 +--
 mm/readahead.c          |  4 +-
 3 files changed, 79 insertions(+), 20 deletions(-)

Patch

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index d9c7edb6422bd..75bbe88b89904 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -204,14 +204,20 @@  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_INACCESSIBLE,	/* Do not attempt direct R/W access to the mapping,
-				   including to move the mapping */
+	AS_INACCESSIBLE = 8,	/* Do not attempt direct R/W access to the mapping */
+	/* Bits 16-25 are used for FOLIO_ORDER */
+	AS_FOLIO_ORDER_BITS = 5,
+	AS_FOLIO_ORDER_MIN = 16,
+	AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS,
 };
 
+#define AS_FOLIO_ORDER_MASK     ((1u << AS_FOLIO_ORDER_BITS) - 1)
+#define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_MASK << AS_FOLIO_ORDER_MIN)
+#define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_MASK << AS_FOLIO_ORDER_MAX)
+
 /**
  * mapping_set_error - record a writeback error in the address_space
  * @mapping: the mapping in which an error should be set
@@ -367,9 +373,51 @@  static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 #define MAX_XAS_ORDER		(XA_CHUNK_SHIFT * 2 - 1)
 #define MAX_PAGECACHE_ORDER	min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER)
 
+/*
+ * mapping_set_folio_order_range() - Set the orders supported by a file.
+ * @mapping: The address space of the file.
+ * @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,
+						 unsigned int max)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return;
+
+	if (min > MAX_PAGECACHE_ORDER)
+		min = MAX_PAGECACHE_ORDER;
+
+	if (max > MAX_PAGECACHE_ORDER)
+		max = MAX_PAGECACHE_ORDER;
+
+	if (max < min)
+		max = min;
+
+	mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) |
+		(min << AS_FOLIO_ORDER_MIN) | (max << 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 of the file.
  *
  * The filesystem should call this function in its inode constructor to
  * indicate that the VFS can use large folios to cache the contents of
@@ -380,7 +428,23 @@  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(const struct address_space *mapping)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 0;
+	return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX;
+}
+
+static inline unsigned int
+mapping_min_folio_order(const struct address_space *mapping)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 0;
+	return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN;
 }
 
 /*
@@ -389,20 +453,17 @@  static inline void mapping_set_large_folios(struct address_space *mapping)
  */
 static inline bool mapping_large_folio_support(struct address_space *mapping)
 {
-	/* AS_LARGE_FOLIO_SUPPORT is only reasonable for pagecache folios */
+	/* AS_FOLIO_ORDER is only reasonable for pagecache folios */
 	VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON,
 			"Anonymous mapping always supports large folio");
 
-	return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
-		test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
+	return mapping_max_folio_order(mapping) > 0;
 }
 
 /* Return the maximum folio size for this pagecache mapping, in bytes. */
-static inline size_t mapping_max_folio_size(struct address_space *mapping)
+static inline size_t mapping_max_folio_size(const struct address_space *mapping)
 {
-	if (mapping_large_folio_support(mapping))
-		return PAGE_SIZE << MAX_PAGECACHE_ORDER;
-	return PAGE_SIZE;
+	return PAGE_SIZE << mapping_max_folio_order(mapping);
 }
 
 static inline int filemap_nr_thps(struct address_space *mapping)
diff --git a/mm/filemap.c b/mm/filemap.c
index 29fec1fccd0a6..6c4489ada3ecc 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1933,10 +1933,8 @@  struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
 			fgp_flags |= FGP_LOCK;
 
-		if (!mapping_large_folio_support(mapping))
-			order = 0;
-		if (order > MAX_PAGECACHE_ORDER)
-			order = MAX_PAGECACHE_ORDER;
+		if (order > mapping_max_folio_order(mapping))
+			order = mapping_max_folio_order(mapping);
 		/* If we're not aligned, allocate a smaller folio */
 		if (index & ((1UL << order) - 1))
 			order = __ffs(index);
diff --git a/mm/readahead.c b/mm/readahead.c
index 517c0be7ce665..3e5239e9e1777 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -449,10 +449,10 @@  void page_cache_ra_order(struct readahead_control *ractl,
 
 	limit = min(limit, index + ra->size - 1);
 
-	if (new_order < MAX_PAGECACHE_ORDER)
+	if (new_order < mapping_max_folio_order(mapping))
 		new_order += 2;
 
-	new_order = min_t(unsigned int, MAX_PAGECACHE_ORDER, new_order);
+	new_order = min(mapping_max_folio_order(mapping), new_order);
 	new_order = min_t(unsigned int, new_order, ilog2(ra->size));
 
 	/* See comment in page_cache_ra_unbounded() */