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
  ...

Documentation/filesystems/iomap/design.rst

@@ -165,7 +165,7 @@ structure below:
      u16                 flags;
      struct block_device *bdev;
      struct dax_device   *dax_dev;
-     voidw               *inline_data;
+     void                *inline_data;
      void                *private;
      const struct iomap_folio_ops *folio_ops;
      u64                 validity_cookie;
@@ -426,7 +426,7 @@ iomap is concerned:
 
 The exact locking requirements are specific to the filesystem; for
 certain operations, some of these locks can be elided.
-All further mention of locking are *recommendations*, not mandates.
+All further mentions of locking are *recommendations*, not mandates.
 Each filesystem author must figure out the locking for themself.
 
 Bugs and Limitations

block/fops.c

@@ -666,7 +666,7 @@ blkdev_direct_write(struct kiocb *iocb, struct iov_iter *from)
 
 static ssize_t blkdev_buffered_write(struct kiocb *iocb, struct iov_iter *from)
 {
-	return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops);
+	return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops, NULL);
 }
 
 /*

fs/gfs2/file.c

@@ -1057,7 +1057,7 @@ static ssize_t gfs2_file_buffered_write(struct kiocb *iocb,
 	}
 
 	pagefault_disable();
-	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
+	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops, NULL);
 	pagefault_enable();
 	if (ret > 0)
 		written += ret;

fs/iomap/direct-io.c

@@ -27,6 +27,13 @@
 #define IOMAP_DIO_WRITE		(1U << 30)
 #define IOMAP_DIO_DIRTY		(1U << 31)
 
+/*
+ * Used for sub block zeroing in iomap_dio_zero()
+ */
+#define IOMAP_ZERO_PAGE_SIZE (SZ_64K)
+#define IOMAP_ZERO_PAGE_ORDER (get_order(IOMAP_ZERO_PAGE_SIZE))
+static struct page *zero_page;
+
 struct iomap_dio {
 	struct kiocb		*iocb;
 	const struct iomap_dio_ops *dops;
@@ -232,13 +239,20 @@ void iomap_dio_bio_end_io(struct bio *bio)
 }
 EXPORT_SYMBOL_GPL(iomap_dio_bio_end_io);
 
-static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
+static int iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
 		loff_t pos, unsigned len)
 {
 	struct inode *inode = file_inode(dio->iocb->ki_filp);
-	struct page *page = ZERO_PAGE(0);
 	struct bio *bio;
 
+	if (!len)
+		return 0;
+	/*
+	 * Max block size supported is 64k
+	 */
+	if (WARN_ON_ONCE(len > IOMAP_ZERO_PAGE_SIZE))
+		return -EINVAL;
+
 	bio = iomap_dio_alloc_bio(iter, dio, 1, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE);
 	fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits,
 				  GFP_KERNEL);
@@ -246,8 +260,9 @@ static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
 	bio->bi_private = dio;
 	bio->bi_end_io = iomap_dio_bio_end_io;
 
-	__bio_add_page(bio, page, len, 0);
+	__bio_add_page(bio, zero_page, len, 0);
 	iomap_dio_submit_bio(iter, dio, bio, pos);
+	return 0;
 }
 
 /*
@@ -356,8 +371,10 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 	if (need_zeroout) {
 		/* zero out from the start of the block to the write offset */
 		pad = pos & (fs_block_size - 1);
-		if (pad)
-			iomap_dio_zero(iter, dio, pos - pad, pad);
+
+		ret = iomap_dio_zero(iter, dio, pos - pad, pad);
+		if (ret)
+			goto out;
 	}
 
 	/*
@@ -431,7 +448,8 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 		/* zero out from the end of the write to the end of the block */
 		pad = pos & (fs_block_size - 1);
 		if (pad)
-			iomap_dio_zero(iter, dio, pos, fs_block_size - pad);
+			ret = iomap_dio_zero(iter, dio, pos,
+					     fs_block_size - pad);
 	}
 out:
 	/* Undo iter limitation to current extent */
@@ -753,3 +771,15 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	return iomap_dio_complete(dio);
 }
 EXPORT_SYMBOL_GPL(iomap_dio_rw);
+
+static int __init iomap_dio_init(void)
+{
+	zero_page = alloc_pages(GFP_KERNEL | __GFP_ZERO,
+				IOMAP_ZERO_PAGE_ORDER);
+
+	if (!zero_page)
+		return -ENOMEM;
+
+	return 0;
+}
+fs_initcall(iomap_dio_init);

fs/xfs/libxfs/xfs_attr_leaf.c

@@ -1138,10 +1138,7 @@ xfs_attr3_leaf_to_shortform(
 
 	trace_xfs_attr_leaf_to_sf(args);
 
-	tmpbuffer = kmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL);
-	if (!tmpbuffer)
-		return -ENOMEM;
-
+	tmpbuffer = kvmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL);
 	memcpy(tmpbuffer, bp->b_addr, args->geo->blksize);
 
 	leaf = (xfs_attr_leafblock_t *)tmpbuffer;
@@ -1205,7 +1202,7 @@ xfs_attr3_leaf_to_shortform(
 	error = 0;
 
 out:
-	kfree(tmpbuffer);
+	kvfree(tmpbuffer);
 	return error;
 }
 
@@ -1613,7 +1610,7 @@ xfs_attr3_leaf_compact(
 
 	trace_xfs_attr_leaf_compact(args);
 
-	tmpbuffer = kmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL);
+	tmpbuffer = kvmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL);
 	memcpy(tmpbuffer, bp->b_addr, args->geo->blksize);
 	memset(bp->b_addr, 0, args->geo->blksize);
 	leaf_src = (xfs_attr_leafblock_t *)tmpbuffer;
@@ -1651,7 +1648,7 @@ xfs_attr3_leaf_compact(
 	 */
 	xfs_trans_log_buf(trans, bp, 0, args->geo->blksize - 1);
 
-	kfree(tmpbuffer);
+	kvfree(tmpbuffer);
 }
 
 /*
@@ -2330,7 +2327,7 @@ xfs_attr3_leaf_unbalance(
 		struct xfs_attr_leafblock *tmp_leaf;
 		struct xfs_attr3_icleaf_hdr tmphdr;
 
-		tmp_leaf = kzalloc(state->args->geo->blksize,
+		tmp_leaf = kvzalloc(state->args->geo->blksize,
 				GFP_KERNEL | __GFP_NOFAIL);
 
 		/*
@@ -2371,7 +2368,7 @@ xfs_attr3_leaf_unbalance(
 		}
 		memcpy(save_leaf, tmp_leaf, state->args->geo->blksize);
 		savehdr = tmphdr; /* struct copy */
-		kfree(tmp_leaf);
+		kvfree(tmp_leaf);
 	}
 
 	xfs_attr3_leaf_hdr_to_disk(state->args->geo, save_leaf, &savehdr);

fs/xfs/libxfs/xfs_ialloc.c

@@ -3034,6 +3034,11 @@ xfs_ialloc_setup_geometry(
 		igeo->ialloc_align = mp->m_dalign;
 	else
 		igeo->ialloc_align = 0;
+
+	if (mp->m_sb.sb_blocksize > PAGE_SIZE)
+		igeo->min_folio_order = mp->m_sb.sb_blocklog - PAGE_SHIFT;
+	else
+		igeo->min_folio_order = 0;
 }
 
 /* Compute the location of the root directory inode that is laid out by mkfs. */

fs/xfs/libxfs/xfs_shared.h

@@ -224,6 +224,9 @@ struct xfs_ino_geometry {
 	/* precomputed value for di_flags2 */
 	uint64_t	new_diflags2;
 
+	/* minimum folio order of a page cache allocation */
+	unsigned int	min_folio_order;
+
 };
 
 #endif /* __XFS_SHARED_H__ */

fs/xfs/xfs_file.c

@@ -760,7 +760,7 @@ xfs_file_buffered_write(
 
 	trace_xfs_file_buffered_write(iocb, from);
 	ret = iomap_file_buffered_write(iocb, from,
-			&xfs_buffered_write_iomap_ops);
+			&xfs_buffered_write_iomap_ops, NULL);
 
 	/*
 	 * If we hit a space limit, try to free up some lingering preallocated

fs/xfs/xfs_icache.c

@@ -100,7 +100,8 @@ xfs_inode_alloc(
 
 	/* VFS doesn't initialise i_mode! */
 	VFS_I(ip)->i_mode = 0;
-	mapping_set_large_folios(VFS_I(ip)->i_mapping);
+	mapping_set_folio_min_order(VFS_I(ip)->i_mapping,
+				    M_IGEO(mp)->min_folio_order);
 
 	XFS_STATS_INC(mp, vn_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
@@ -360,7 +361,8 @@ xfs_reinit_inode(
 	inode->i_uid = uid;
 	inode->i_gid = gid;
 	inode->i_state = state;
-	mapping_set_large_folios(inode->i_mapping);
+	mapping_set_folio_min_order(inode->i_mapping,
+				    M_IGEO(mp)->min_folio_order);
 	return error;
 }
 

fs/xfs/xfs_iomap.c

@@ -1208,14 +1208,14 @@ xfs_buffered_write_iomap_begin(
 	return error;
 }
 
-static int
+static void
 xfs_buffered_write_delalloc_punch(
 	struct inode		*inode,
 	loff_t			offset,
-	loff_t			length)
+	loff_t			length,
+	struct iomap		*iomap)
 {
 	xfs_bmap_punch_delalloc_range(XFS_I(inode), offset, offset + length);
-	return 0;
 }
 
 static int
@@ -1227,17 +1227,8 @@ xfs_buffered_write_iomap_end(
 	unsigned		flags,
 	struct iomap		*iomap)
 {
-
-	struct xfs_mount	*mp = XFS_M(inode->i_sb);
-	int			error;
-
-	error = iomap_file_buffered_write_punch_delalloc(inode, iomap, offset,
-			length, written, &xfs_buffered_write_delalloc_punch);
-	if (error && !xfs_is_shutdown(mp)) {
-		xfs_alert(mp, "%s: unable to clean up ino 0x%llx",
-			__func__, XFS_I(inode)->i_ino);
-		return error;
-	}
+	iomap_file_buffered_write_punch_delalloc(inode, offset, length, written,
+			flags, iomap, &xfs_buffered_write_delalloc_punch);
 	return 0;
 }
 

fs/xfs/xfs_iops.c

@@ -567,7 +567,7 @@ xfs_stat_blksize(
 			return 1U << mp->m_allocsize_log;
 	}
 
-	return PAGE_SIZE;
+	return max_t(uint32_t, PAGE_SIZE, mp->m_sb.sb_blocksize);
 }
 
 STATIC int
@@ -870,16 +870,6 @@ xfs_setattr_size(
 		error = xfs_zero_range(ip, oldsize, newsize - oldsize,
 				&did_zeroing);
 	} else {
-		/*
-		 * iomap won't detect a dirty page over an unwritten block (or a
-		 * cow block over a hole) and subsequently skips zeroing the
-		 * newly post-EOF portion of the page. Flush the new EOF to
-		 * convert the block before the pagecache truncate.
-		 */
-		error = filemap_write_and_wait_range(inode->i_mapping, newsize,
-						     newsize);
-		if (error)
-			return error;
 		error = xfs_truncate_page(ip, newsize, &did_zeroing);
 	}
 

fs/xfs/xfs_mount.c

@@ -132,11 +132,15 @@ xfs_sb_validate_fsb_count(
 	xfs_sb_t	*sbp,
 	uint64_t	nblocks)
 {
-	ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
+	uint64_t		max_bytes;
+
 	ASSERT(sbp->sb_blocklog >= BBSHIFT);
 
+	if (check_shl_overflow(nblocks, sbp->sb_blocklog, &max_bytes))
+		return -EFBIG;
+
 	/* Limited by ULONG_MAX of page cache index */
-	if (nblocks >> (PAGE_SHIFT - sbp->sb_blocklog) > ULONG_MAX)
+	if (max_bytes >> PAGE_SHIFT > ULONG_MAX)
 		return -EFBIG;
 	return 0;
 }

fs/xfs/xfs_super.c

@@ -1638,18 +1638,30 @@ xfs_fs_fill_super(
 		goto out_free_sb;
 	}
 
-	/*
-	 * Until this is fixed only page-sized or smaller data blocks work.
-	 */
 	if (mp->m_sb.sb_blocksize > PAGE_SIZE) {
+		size_t max_folio_size = mapping_max_folio_size_supported();
+
+		if (!xfs_has_crc(mp)) {
 			xfs_warn(mp,
-		"File system with blocksize %d bytes. "
-		"Only pagesize (%ld) or less will currently work.",
+"V4 Filesystem with blocksize %d bytes. Only pagesize (%ld) or less is supported.",
 				mp->m_sb.sb_blocksize, PAGE_SIZE);
 			error = -ENOSYS;
 			goto out_free_sb;
 		}
 
+		if (mp->m_sb.sb_blocksize > max_folio_size) {
+			xfs_warn(mp,
+"block size (%u bytes) not supported; Only block size (%zu) or less is supported",
+				mp->m_sb.sb_blocksize, max_folio_size);
+			error = -ENOSYS;
+			goto out_free_sb;
+		}
+
+		xfs_warn(mp,
+"EXPERIMENTAL: V5 Filesystem with Large Block Size (%d bytes) enabled.",
+			mp->m_sb.sb_blocksize);
+	}
+
 	/* Ensure this filesystem fits in the page cache limits */
 	if (xfs_sb_validate_fsb_count(&mp->m_sb, mp->m_sb.sb_dblocks) ||
 	    xfs_sb_validate_fsb_count(&mp->m_sb, mp->m_sb.sb_rblocks)) {

fs/zonefs/file.c

@@ -563,7 +563,7 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
 	if (ret <= 0)
 		goto inode_unlock;
 
-	ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops);
+	ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops, NULL);
 	if (ret == -EIO)
 		zonefs_io_error(inode, true);
 

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 */

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,

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)

mm/filemap.c

@@ -859,6 +859,8 @@ noinline int __filemap_add_folio(struct address_space *mapping,
 
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio);
+	VM_BUG_ON_FOLIO(folio_order(folio) < mapping_min_folio_order(mapping),
+			folio);
 	mapping_set_update(&xas, mapping);
 
 	VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio);
@@ -1919,8 +1921,10 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		folio_wait_stable(folio);
 no_page:
 	if (!folio && (fgp_flags & FGP_CREAT)) {
-		unsigned order = FGF_GET_ORDER(fgp_flags);
+		unsigned int min_order = mapping_min_folio_order(mapping);
+		unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags));
 		int err;
+		index = mapping_align_index(mapping, index);
 
 		if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
 			gfp |= __GFP_WRITE;
@@ -1933,10 +1937,8 @@ 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);
@@ -1945,7 +1947,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 			gfp_t alloc_gfp = gfp;
 
 			err = -ENOMEM;
-			if (order > 0)
+			if (order > min_order)
 				alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
 			folio = filemap_alloc_folio(alloc_gfp, order);
 			if (!folio)
@@ -1960,7 +1962,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 				break;
 			folio_put(folio);
 			folio = NULL;
-		} while (order-- > 0);
+		} while (order-- > min_order);
 
 		if (err == -EEXIST)
 			goto repeat;
@@ -2449,13 +2451,15 @@ static int filemap_update_page(struct kiocb *iocb,
 }
 
 static int filemap_create_folio(struct file *file,
-		struct address_space *mapping, pgoff_t index,
+		struct address_space *mapping, loff_t pos,
 		struct folio_batch *fbatch)
 {
 	struct folio *folio;
 	int error;
+	unsigned int min_order = mapping_min_folio_order(mapping);
+	pgoff_t index;
 
-	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), 0);
+	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order);
 	if (!folio)
 		return -ENOMEM;
 
@@ -2473,6 +2477,7 @@ static int filemap_create_folio(struct file *file,
 	 * well to keep locking rules simple.
 	 */
 	filemap_invalidate_lock_shared(mapping);
+	index = (pos >> (PAGE_SHIFT + min_order)) << min_order;
 	error = filemap_add_folio(mapping, folio, index,
 			mapping_gfp_constraint(mapping, GFP_KERNEL));
 	if (error == -EEXIST)
@@ -2533,8 +2538,7 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count,
 	if (!folio_batch_count(fbatch)) {
 		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
 			return -EAGAIN;
-		err = filemap_create_folio(filp, mapping,
-				iocb->ki_pos >> PAGE_SHIFT, fbatch);
+		err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch);
 		if (err == AOP_TRUNCATED_PAGE)
 			goto retry;
 		return err;
@@ -3611,7 +3615,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	struct vm_area_struct *vma = vmf->vma;
 	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
-	pgoff_t last_pgoff = start_pgoff;
+	pgoff_t file_end, last_pgoff = start_pgoff;
 	unsigned long addr;
 	XA_STATE(xas, &mapping->i_pages, start_pgoff);
 	struct folio *folio;
@@ -3637,6 +3641,10 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		goto out;
 	}
 
+	file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1;
+	if (end_pgoff > file_end)
+		end_pgoff = file_end;
+
 	folio_type = mm_counter_file(folio);
 	do {
 		unsigned long end;
@@ -3757,9 +3765,11 @@ static struct folio *do_read_cache_folio(struct address_space *mapping,
 repeat:
 	folio = filemap_get_folio(mapping, index);
 	if (IS_ERR(folio)) {
-		folio = filemap_alloc_folio(gfp, 0);
+		folio = filemap_alloc_folio(gfp,
+					    mapping_min_folio_order(mapping));
 		if (!folio)
 			return ERR_PTR(-ENOMEM);
+		index = mapping_align_index(mapping, index);
 		err = filemap_add_folio(mapping, folio, index, gfp);
 		if (unlikely(err)) {
 			folio_put(folio);

mm/huge_memory.c

@@ -3081,6 +3081,9 @@ bool can_split_folio(struct folio *folio, int *pextra_pins)
  * released, or if some unexpected race happened (e.g., anon VMA disappeared,
  * truncation).
  *
+ * Callers should ensure that the order respects the address space mapping
+ * min-order if one is set for non-anonymous folios.
+ *
  * Returns -EINVAL when trying to split to an order that is incompatible
  * with the folio. Splitting to order 0 is compatible with all folios.
  */
@@ -3162,6 +3165,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 		mapping = NULL;
 		anon_vma_lock_write(anon_vma);
 	} else {
+		unsigned int min_order;
 		gfp_t gfp;
 
 		mapping = folio->mapping;
@@ -3172,6 +3176,14 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 			goto out;
 		}
 
+		min_order = mapping_min_folio_order(folio->mapping);
+		if (new_order < min_order) {
+			VM_WARN_ONCE(1, "Cannot split mapped folio below min-order: %u",
+				     min_order);
+			ret = -EINVAL;
+			goto out;
+		}
+
 		gfp = current_gfp_context(mapping_gfp_mask(mapping) &
 							GFP_RECLAIM_MASK);
 
@@ -3284,6 +3296,30 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 	return ret;
 }
 
+int min_order_for_split(struct folio *folio)
+{
+	if (folio_test_anon(folio))
+		return 0;
+
+	if (!folio->mapping) {
+		if (folio_test_pmd_mappable(folio))
+			count_vm_event(THP_SPLIT_PAGE_FAILED);
+		return -EBUSY;
+	}
+
+	return mapping_min_folio_order(folio->mapping);
+}
+
+int split_folio_to_list(struct folio *folio, struct list_head *list)
+{
+	int ret = min_order_for_split(folio);
+
+	if (ret < 0)
+		return ret;
+
+	return split_huge_page_to_list_to_order(&folio->page, list, ret);
+}
+
 void __folio_undo_large_rmappable(struct folio *folio)
 {
 	struct deferred_split *ds_queue;
@@ -3514,6 +3550,8 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 		struct vm_area_struct *vma = vma_lookup(mm, addr);
 		struct page *page;
 		struct folio *folio;
+		struct address_space *mapping;
+		unsigned int target_order = new_order;
 
 		if (!vma)
 			break;
@@ -3534,7 +3572,13 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 		if (!is_transparent_hugepage(folio))
 			goto next;
 
-		if (new_order >= folio_order(folio))
+		if (!folio_test_anon(folio)) {
+			mapping = folio->mapping;
+			target_order = max(new_order,
+					   mapping_min_folio_order(mapping));
+		}
+
+		if (target_order >= folio_order(folio))
 			goto next;
 
 		total++;
@@ -3550,9 +3594,14 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 		if (!folio_trylock(folio))
 			goto next;
 
-		if (!split_folio_to_order(folio, new_order))
+		if (!folio_test_anon(folio) && folio->mapping != mapping)
+			goto unlock;
+
+		if (!split_folio_to_order(folio, target_order))
 			split++;
 
+unlock:
+
 		folio_unlock(folio);
 next:
 		folio_put(folio);
@@ -3577,6 +3626,8 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
 	pgoff_t index;
 	int nr_pages = 1;
 	unsigned long total = 0, split = 0;
+	unsigned int min_order;
+	unsigned int target_order;
 
 	file = getname_kernel(file_path);
 	if (IS_ERR(file))
@@ -3590,6 +3641,8 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
 		 file_path, off_start, off_end);
 
 	mapping = candidate->f_mapping;
+	min_order = mapping_min_folio_order(mapping);
+	target_order = max(new_order, min_order);
 
 	for (index = off_start; index < off_end; index += nr_pages) {
 		struct folio *folio = filemap_get_folio(mapping, index);
@@ -3604,15 +3657,19 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
 		total++;
 		nr_pages = folio_nr_pages(folio);
 
-		if (new_order >= folio_order(folio))
+		if (target_order >= folio_order(folio))
 			goto next;
 
 		if (!folio_trylock(folio))
 			goto next;
 
-		if (!split_folio_to_order(folio, new_order))
+		if (folio->mapping != mapping)
+			goto unlock;
+
+		if (!split_folio_to_order(folio, target_order))
 			split++;
 
+unlock:
 		folio_unlock(folio);
 next:
 		folio_put(folio);

mm/readahead.c

@@ -206,9 +206,10 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 		unsigned long nr_to_read, unsigned long lookahead_size)
 {
 	struct address_space *mapping = ractl->mapping;
-	unsigned long index = readahead_index(ractl);
+	unsigned long ra_folio_index, index = readahead_index(ractl);
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
-	unsigned long i;
+	unsigned long mark, i = 0;
+	unsigned int min_nrpages = mapping_min_folio_nrpages(mapping);
 
 	/*
 	 * Partway through the readahead operation, we will have added
@@ -223,10 +224,24 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 	unsigned int nofs = memalloc_nofs_save();
 
 	filemap_invalidate_lock_shared(mapping);
+	index = mapping_align_index(mapping, index);
+
+	/*
+	 * As iterator `i` is aligned to min_nrpages, round_up the
+	 * difference between nr_to_read and lookahead_size to mark the
+	 * index that only has lookahead or "async_region" to set the
+	 * readahead flag.
+	 */
+	ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size,
+				  min_nrpages);
+	mark = ra_folio_index - index;
+	nr_to_read += readahead_index(ractl) - index;
+	ractl->_index = index;
+
 	/*
 	 * Preallocate as many pages as we will need.
 	 */
-	for (i = 0; i < nr_to_read; i++) {
+	while (i < nr_to_read) {
 		struct folio *folio = xa_load(&mapping->i_pages, index + i);
 		int ret;
 
@@ -240,12 +255,13 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 			 * not worth getting one just for that.
 			 */
 			read_pages(ractl);
-			ractl->_index++;
-			i = ractl->_index + ractl->_nr_pages - index - 1;
+			ractl->_index += min_nrpages;
+			i = ractl->_index + ractl->_nr_pages - index;
 			continue;
 		}
 
-		folio = filemap_alloc_folio(gfp_mask, 0);
+		folio = filemap_alloc_folio(gfp_mask,
+					    mapping_min_folio_order(mapping));
 		if (!folio)
 			break;
 
@@ -255,14 +271,15 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 			if (ret == -ENOMEM)
 				break;
 			read_pages(ractl);
-			ractl->_index++;
-			i = ractl->_index + ractl->_nr_pages - index - 1;
+			ractl->_index += min_nrpages;
+			i = ractl->_index + ractl->_nr_pages - index;
 			continue;
 		}
-		if (i == nr_to_read - lookahead_size)
+		if (i == mark)
 			folio_set_readahead(folio);
 		ractl->_workingset |= folio_test_workingset(folio);
-		ractl->_nr_pages++;
+		ractl->_nr_pages += min_nrpages;
+		i += min_nrpages;
 	}
 
 	/*
@@ -438,26 +455,41 @@ void page_cache_ra_order(struct readahead_control *ractl,
 	struct address_space *mapping = ractl->mapping;
 	pgoff_t start = readahead_index(ractl);
 	pgoff_t index = start;
+	unsigned int min_order = mapping_min_folio_order(mapping);
 	pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT;
 	pgoff_t mark = index + ra->size - ra->async_size;
 	unsigned int nofs;
 	int err = 0;
 	gfp_t gfp = readahead_gfp_mask(mapping);
+	unsigned int min_ra_size = max(4, mapping_min_folio_nrpages(mapping));
 
-	if (!mapping_large_folio_support(mapping) || ra->size < 4)
+	/*
+	 * Fallback when size < min_nrpages as each folio should be
+	 * at least min_nrpages anyway.
+	 */
+	if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size)
 		goto fallback;
 
 	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));
+	new_order = max(new_order, min_order);
 
 	/* See comment in page_cache_ra_unbounded() */
 	nofs = memalloc_nofs_save();
 	filemap_invalidate_lock_shared(mapping);
+	/*
+	 * If the new_order is greater than min_order and index is
+	 * already aligned to new_order, then this will be noop as index
+	 * aligned to new_order should also be aligned to min_order.
+	 */
+	ractl->_index = mapping_align_index(mapping, index);
+	index = readahead_index(ractl);
+
 	while (index <= limit) {
 		unsigned int order = new_order;
 
@@ -465,7 +497,7 @@ void page_cache_ra_order(struct readahead_control *ractl,
 		if (index & ((1UL << order) - 1))
 			order = __ffs(index);
 		/* Don't allocate pages past EOF */
-		while (index + (1UL << order) - 1 > limit)
+		while (order > min_order && index + (1UL << order) - 1 > limit)
 			order--;
 		err = ra_alloc_folio(ractl, index, mark, order, gfp);
 		if (err)
@@ -703,8 +735,15 @@ void readahead_expand(struct readahead_control *ractl,
 	struct file_ra_state *ra = ractl->ra;
 	pgoff_t new_index, new_nr_pages;
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
+	unsigned long min_nrpages = mapping_min_folio_nrpages(mapping);
+	unsigned int min_order = mapping_min_folio_order(mapping);
 
 	new_index = new_start / PAGE_SIZE;
+	/*
+	 * Readahead code should have aligned the ractl->_index to
+	 * min_nrpages before calling readahead aops.
+	 */
+	VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages));
 
 	/* Expand the leading edge downwards */
 	while (ractl->_index > new_index) {
@@ -714,9 +753,11 @@ void readahead_expand(struct readahead_control *ractl,
 		if (folio && !xa_is_value(folio))
 			return; /* Folio apparently present */
 
-		folio = filemap_alloc_folio(gfp_mask, 0);
+		folio = filemap_alloc_folio(gfp_mask, min_order);
 		if (!folio)
 			return;
+
+		index = mapping_align_index(mapping, index);
 		if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) {
 			folio_put(folio);
 			return;
@@ -726,7 +767,7 @@ void readahead_expand(struct readahead_control *ractl,
 			ractl->_workingset = true;
 			psi_memstall_enter(&ractl->_pflags);
 		}
-		ractl->_nr_pages++;
+		ractl->_nr_pages += min_nrpages;
 		ractl->_index = folio->index;
 	}
 
@@ -741,9 +782,11 @@ void readahead_expand(struct readahead_control *ractl,
 		if (folio && !xa_is_value(folio))
 			return; /* Folio apparently present */
 
-		folio = filemap_alloc_folio(gfp_mask, 0);
+		folio = filemap_alloc_folio(gfp_mask, min_order);
 		if (!folio)
 			return;
+
+		index = mapping_align_index(mapping, index);
 		if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) {
 			folio_put(folio);
 			return;
@@ -753,10 +796,10 @@ void readahead_expand(struct readahead_control *ractl,
 			ractl->_workingset = true;
 			psi_memstall_enter(&ractl->_pflags);
 		}
-		ractl->_nr_pages++;
+		ractl->_nr_pages += min_nrpages;
 		if (ra) {
-			ra->size++;
-			ra->async_size++;
+			ra->size += min_nrpages;
+			ra->async_size += min_nrpages;
 		}
 	}
 }