Merge tag 'vfs-6.12.blocksize' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs

Pull vfs blocksize updates from Christian Brauner:
 "This contains the vfs infrastructure as well as the xfs bits to enable
  support for block sizes (bs) larger than page sizes (ps) plus a few
  fixes to related infrastructure.

  There has been efforts over the last 16 years to enable enable Large
  Block Sizes (LBS), that is block sizes in filesystems where bs > page
  size. Through these efforts we have learned that one of the main
  blockers to supporting bs > ps in filesystems has been a way to
  allocate pages that are at least the filesystem block size on the page
  cache where bs > ps.

  Thanks to various previous efforts it is possible to support bs > ps
  in XFS with only a few changes in XFS itself. Most changes are to the
  page cache to support minimum order folio support for the target block
  size on the filesystem.

  A motivation for Large Block Sizes today is to support high-capacity
  (large amount of Terabytes) QLC SSDs where the internal Indirection
  Unit (IU) are typically greater than 4k to help reduce DRAM and so in
  turn cost and space. In practice this then allows different
  architectures to use a base page size of 4k while still enabling
  support for block sizes aligned to the larger IUs by relying on high
  order folios on the page cache when needed.

  It also allows to take advantage of the drive's support for atomics
  larger than 4k with buffered IO support in Linux. As described this
  year at LSFMM, supporting large atomics greater than 4k enables
  databases to remove the need to rely on their own journaling, so they
  can disable double buffered writes, which is a feature different cloud
  providers are already enabling through custom storage solutions"

* tag 'vfs-6.12.blocksize' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs: (22 commits)
  Documentation: iomap: fix a typo
  iomap: remove the iomap_file_buffered_write_punch_delalloc return value
  iomap: pass the iomap to the punch callback
  iomap: pass flags to iomap_file_buffered_write_punch_delalloc
  iomap: improve shared block detection in iomap_unshare_iter
  iomap: handle a post-direct I/O invalidate race in iomap_write_delalloc_release
  docs:filesystems: fix spelling and grammar mistakes in iomap design page
  filemap: fix htmldoc warning for mapping_align_index()
  iomap: make zero range flush conditional on unwritten mappings
  iomap: fix handling of dirty folios over unwritten extents
  iomap: add a private argument for iomap_file_buffered_write
  iomap: remove set_memor_ro() on zero page
  xfs: enable block size larger than page size support
  xfs: make the calculation generic in xfs_sb_validate_fsb_count()
  xfs: expose block size in stat
  xfs: use kvmalloc for xattr buffers
  iomap: fix iomap_dio_zero() for fs bs > system page size
  filemap: cap PTE range to be created to allowed zero fill in folio_map_range()
  mm: split a folio in minimum folio order chunks
  readahead: allocate folios with mapping_min_order in readahead
  ...

3 files changed, 142 insertions, 23 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index e25d9ebfdf89..7a570e0437c9 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -96,6 +96,8 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr;
 #define thp_vma_allowable_order(vma, vm_flags, tva_flags, order) \
 	(!!thp_vma_allowable_orders(vma, vm_flags, tva_flags, BIT(order)))
 
+#define split_folio(f) split_folio_to_list(f, NULL)
+
 #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES
 #define HPAGE_PMD_SHIFT PMD_SHIFT
 #define HPAGE_PUD_SHIFT PUD_SHIFT
@@ -317,9 +319,24 @@ unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long add
 bool can_split_folio(struct folio *folio, int *pextra_pins);
 int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 		unsigned int new_order);
+int min_order_for_split(struct folio *folio);
+int split_folio_to_list(struct folio *folio, struct list_head *list);
 static inline int split_huge_page(struct page *page)
 {
-	return split_huge_page_to_list_to_order(page, NULL, 0);
+	struct folio *folio = page_folio(page);
+	int ret = min_order_for_split(folio);
+
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * split_huge_page() locks the page before splitting and
+	 * expects the same page that has been split to be locked when
+	 * returned. split_folio(page_folio(page)) cannot be used here
+	 * because it converts the page to folio and passes the head
+	 * page to be split.
+	 */
+	return split_huge_page_to_list_to_order(page, NULL, ret);
 }
 void deferred_split_folio(struct folio *folio);
 
@@ -484,6 +501,12 @@ static inline int split_huge_page(struct page *page)
 {
 	return 0;
 }
+
+static inline int split_folio_to_list(struct folio *folio, struct list_head *list)
+{
+	return 0;
+}
+
 static inline void deferred_split_folio(struct folio *folio) {}
 #define split_huge_pmd(__vma, __pmd, __address)	\
 	do { } while (0)
@@ -598,7 +621,4 @@ static inline int split_folio_to_order(struct folio *folio, int new_order)
 	return split_folio_to_list_to_order(folio, NULL, new_order);
 }
 
-#define split_folio_to_list(f, l) split_folio_to_list_to_order(f, l, 0)
-#define split_folio(f) split_folio_to_order(f, 0)
-
 #endif /* _LINUX_HUGE_MM_H */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 6fc1c858013d..4ad12a3c8bae 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -257,11 +257,7 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i)
 }
 
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
-		const struct iomap_ops *ops);
-int iomap_file_buffered_write_punch_delalloc(struct inode *inode,
-		struct iomap *iomap, loff_t pos, loff_t length, ssize_t written,
-		int (*punch)(struct inode *inode, loff_t pos, loff_t length));
-
+		const struct iomap_ops *ops, void *private);
 int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
 void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
 bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count);
@@ -277,6 +273,13 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 		const struct iomap_ops *ops);
 vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf,
 			const struct iomap_ops *ops);
+
+typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length,
+		struct iomap *iomap);
+void iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos,
+		loff_t length, ssize_t written, unsigned flag,
+		struct iomap *iomap, iomap_punch_t punch);
+
 int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		u64 start, u64 len, const struct iomap_ops *ops);
 loff_t iomap_seek_hole(struct inode *inode, loff_t offset,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e39c3a7ce33c..68a5f1ff3301 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -206,14 +206,21 @@ 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_BITS_MASK ((1u << AS_FOLIO_ORDER_BITS) - 1)
+#define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MIN)
+#define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MAX)
+#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
@@ -369,9 +376,64 @@ 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_max_folio_size_supported() - Check the max folio size supported
+ *
+ * The filesystem should call this function at mount time if there is a
+ * requirement on the folio mapping size in the page cache.
+ */
+static inline size_t mapping_max_folio_size_supported(void)
+{
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER);
+	return PAGE_SIZE;
+}
+
+/*
+ * 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
@@ -382,7 +444,44 @@ 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;
+}
+
+static inline unsigned long
+mapping_min_folio_nrpages(struct address_space *mapping)
+{
+	return 1UL << mapping_min_folio_order(mapping);
+}
+
+/**
+ * mapping_align_index() - Align index for this mapping.
+ * @mapping: The address_space.
+ * @index: The page index.
+ *
+ * The index of a folio must be naturally aligned.  If you are adding a
+ * new folio to the page cache and need to know what index to give it,
+ * call this function.
+ */
+static inline pgoff_t mapping_align_index(struct address_space *mapping,
+					  pgoff_t index)
+{
+	return round_down(index, mapping_min_folio_nrpages(mapping));
 }
 
 /*
@@ -391,20 +490,17 @@ 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)