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
  ...

2 files changed, 159 insertions, 82 deletions

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 9b4ca3811a24..11ea747228ae 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -23,7 +23,6 @@
 
 #define IOEND_BATCH_SIZE	4096
 
-typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length);
 /*
  * Structure allocated for each folio to track per-block uptodate, dirty state
  * and I/O completions.
@@ -1022,13 +1021,14 @@ retry:
 
 ssize_t
 iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
-		const struct iomap_ops *ops)
+		const struct iomap_ops *ops, void *private)
 {
 	struct iomap_iter iter = {
 		.inode		= iocb->ki_filp->f_mapping->host,
 		.pos		= iocb->ki_pos,
 		.len		= iov_iter_count(i),
 		.flags		= IOMAP_WRITE,
+		.private	= private,
 	};
 	ssize_t ret;
 
@@ -1046,15 +1046,14 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
 }
 EXPORT_SYMBOL_GPL(iomap_file_buffered_write);
 
-static int iomap_write_delalloc_ifs_punch(struct inode *inode,
+static void iomap_write_delalloc_ifs_punch(struct inode *inode,
 		struct folio *folio, loff_t start_byte, loff_t end_byte,
-		iomap_punch_t punch)
+		struct iomap *iomap, iomap_punch_t punch)
 {
 	unsigned int first_blk, last_blk, i;
 	loff_t last_byte;
 	u8 blkbits = inode->i_blkbits;
 	struct iomap_folio_state *ifs;
-	int ret = 0;
 
 	/*
 	 * When we have per-block dirty tracking, there can be
@@ -1064,47 +1063,35 @@ static int iomap_write_delalloc_ifs_punch(struct inode *inode,
 	 */
 	ifs = folio->private;
 	if (!ifs)
-		return ret;
+		return;
 
 	last_byte = min_t(loff_t, end_byte - 1,
 			folio_pos(folio) + folio_size(folio) - 1);
 	first_blk = offset_in_folio(folio, start_byte) >> blkbits;
 	last_blk = offset_in_folio(folio, last_byte) >> blkbits;
 	for (i = first_blk; i <= last_blk; i++) {
-		if (!ifs_block_is_dirty(folio, ifs, i)) {
-			ret = punch(inode, folio_pos(folio) + (i << blkbits),
-				    1 << blkbits);
-			if (ret)
-				return ret;
-		}
+		if (!ifs_block_is_dirty(folio, ifs, i))
+			punch(inode, folio_pos(folio) + (i << blkbits),
+				    1 << blkbits, iomap);
 	}
-
-	return ret;
 }
 
-
-static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio,
+static void iomap_write_delalloc_punch(struct inode *inode, struct folio *folio,
 		loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte,
-		iomap_punch_t punch)
+		struct iomap *iomap, iomap_punch_t punch)
 {
-	int ret = 0;
-
 	if (!folio_test_dirty(folio))
-		return ret;
+		return;
 
 	/* if dirty, punch up to offset */
 	if (start_byte > *punch_start_byte) {
-		ret = punch(inode, *punch_start_byte,
-				start_byte - *punch_start_byte);
-		if (ret)
-			return ret;
+		punch(inode, *punch_start_byte, start_byte - *punch_start_byte,
+				iomap);
 	}
 
 	/* Punch non-dirty blocks within folio */
-	ret = iomap_write_delalloc_ifs_punch(inode, folio, start_byte,
-			end_byte, punch);
-	if (ret)
-		return ret;
+	iomap_write_delalloc_ifs_punch(inode, folio, start_byte, end_byte,
+			iomap, punch);
 
 	/*
 	 * Make sure the next punch start is correctly bound to
@@ -1112,8 +1099,6 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio,
 	 */
 	*punch_start_byte = min_t(loff_t, end_byte,
 				folio_pos(folio) + folio_size(folio));
-
-	return ret;
 }
 
 /*
@@ -1133,13 +1118,12 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio,
  * This function uses [start_byte, end_byte) intervals (i.e. open ended) to
  * simplify range iterations.
  */
-static int iomap_write_delalloc_scan(struct inode *inode,
+static void iomap_write_delalloc_scan(struct inode *inode,
 		loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte,
-		iomap_punch_t punch)
+		struct iomap *iomap, iomap_punch_t punch)
 {
 	while (start_byte < end_byte) {
 		struct folio	*folio;
-		int ret;
 
 		/* grab locked page */
 		folio = filemap_lock_folio(inode->i_mapping,
@@ -1150,20 +1134,14 @@ static int iomap_write_delalloc_scan(struct inode *inode,
 			continue;
 		}
 
-		ret = iomap_write_delalloc_punch(inode, folio, punch_start_byte,
-						 start_byte, end_byte, punch);
-		if (ret) {
-			folio_unlock(folio);
-			folio_put(folio);
-			return ret;
-		}
+		iomap_write_delalloc_punch(inode, folio, punch_start_byte,
+				start_byte, end_byte, iomap, punch);
 
 		/* move offset to start of next folio in range */
 		start_byte = folio_next_index(folio) << PAGE_SHIFT;
 		folio_unlock(folio);
 		folio_put(folio);
 	}
-	return 0;
 }
 
 /*
@@ -1199,12 +1177,12 @@ static int iomap_write_delalloc_scan(struct inode *inode,
  * require sprinkling this code with magic "+ 1" and "- 1" arithmetic and expose
  * the code to subtle off-by-one bugs....
  */
-static int iomap_write_delalloc_release(struct inode *inode,
-		loff_t start_byte, loff_t end_byte, iomap_punch_t punch)
+static void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
+		loff_t end_byte, unsigned flags, struct iomap *iomap,
+		iomap_punch_t punch)
 {
 	loff_t punch_start_byte = start_byte;
 	loff_t scan_end_byte = min(i_size_read(inode), end_byte);
-	int error = 0;
 
 	/*
 	 * Lock the mapping to avoid races with page faults re-instantiating
@@ -1221,13 +1199,15 @@ static int iomap_write_delalloc_release(struct inode *inode,
 		/*
 		 * If there is no more data to scan, all that is left is to
 		 * punch out the remaining range.
+		 *
+		 * Note that mapping_seek_hole_data is only supposed to return
+		 * either an offset or -ENXIO, so WARN on any other error as
+		 * that would be an API change without updating the callers.
 		 */
 		if (start_byte == -ENXIO || start_byte == scan_end_byte)
 			break;
-		if (start_byte < 0) {
-			error = start_byte;
+		if (WARN_ON_ONCE(start_byte < 0))
 			goto out_unlock;
-		}
 		WARN_ON_ONCE(start_byte < punch_start_byte);
 		WARN_ON_ONCE(start_byte > scan_end_byte);
 
@@ -1237,28 +1217,31 @@ static int iomap_write_delalloc_release(struct inode *inode,
 		 */
 		data_end = mapping_seek_hole_data(inode->i_mapping, start_byte,
 				scan_end_byte, SEEK_HOLE);
-		if (data_end < 0) {
-			error = data_end;
+		if (WARN_ON_ONCE(data_end < 0))
 			goto out_unlock;
-		}
-		WARN_ON_ONCE(data_end <= start_byte);
+
+		/*
+		 * If we race with post-direct I/O invalidation of the page cache,
+		 * there might be no data left at start_byte.
+		 */
+		if (data_end == start_byte)
+			continue;
+
+		WARN_ON_ONCE(data_end < start_byte);
 		WARN_ON_ONCE(data_end > scan_end_byte);
 
-		error = iomap_write_delalloc_scan(inode, &punch_start_byte,
-				start_byte, data_end, punch);
-		if (error)
-			goto out_unlock;
+		iomap_write_delalloc_scan(inode, &punch_start_byte, start_byte,
+				data_end, iomap, punch);
 
 		/* The next data search starts at the end of this one. */
 		start_byte = data_end;
 	}
 
 	if (punch_start_byte < end_byte)
-		error = punch(inode, punch_start_byte,
-				end_byte - punch_start_byte);
+		punch(inode, punch_start_byte, end_byte - punch_start_byte,
+				iomap);
 out_unlock:
 	filemap_invalidate_unlock(inode->i_mapping);
-	return error;
 }
 
 /*
@@ -1291,20 +1274,20 @@ out_unlock:
  *       ->punch
  *         internal filesystem allocation lock
  */
-int iomap_file_buffered_write_punch_delalloc(struct inode *inode,
-		struct iomap *iomap, loff_t pos, loff_t length,
-		ssize_t written, iomap_punch_t punch)
+void iomap_file_buffered_write_punch_delalloc(struct inode *inode,
+		loff_t pos, loff_t length, ssize_t written, unsigned flags,
+		struct iomap *iomap, iomap_punch_t punch)
 {
 	loff_t			start_byte;
 	loff_t			end_byte;
 	unsigned int		blocksize = i_blocksize(inode);
 
 	if (iomap->type != IOMAP_DELALLOC)
-		return 0;
+		return;
 
 	/* If we didn't reserve the blocks, we're not allowed to punch them. */
 	if (!(iomap->flags & IOMAP_F_NEW))
-		return 0;
+		return;
 
 	/*
 	 * start_byte refers to the first unused block after a short write. If
@@ -1319,26 +1302,35 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode,
 
 	/* Nothing to do if we've written the entire delalloc extent */
 	if (start_byte >= end_byte)
-		return 0;
+		return;
 
-	return iomap_write_delalloc_release(inode, start_byte, end_byte,
-					punch);
+	iomap_write_delalloc_release(inode, start_byte, end_byte, flags, iomap,
+			punch);
 }
 EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc);
 
 static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 {
 	struct iomap *iomap = &iter->iomap;
-	const struct iomap *srcmap = iomap_iter_srcmap(iter);
 	loff_t pos = iter->pos;
 	loff_t length = iomap_length(iter);
 	loff_t written = 0;
 
-	/* don't bother with blocks that are not shared to start with */
+	/* Don't bother with blocks that are not shared to start with. */
 	if (!(iomap->flags & IOMAP_F_SHARED))
 		return length;
-	/* don't bother with holes or unwritten extents */
-	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
+
+	/*
+	 * Don't bother with holes or unwritten extents.
+	 *
+	 * Note that we use srcmap directly instead of iomap_iter_srcmap as
+	 * unsharing requires providing a separate source map, and the presence
+	 * of one is a good indicator that unsharing is needed, unlike
+	 * IOMAP_F_SHARED which can be set for any data that goes into the COW
+	 * fork for XFS.
+	 */
+	if (iter->srcmap.type == IOMAP_HOLE ||
+	    iter->srcmap.type == IOMAP_UNWRITTEN)
 		return length;
 
 	do {
@@ -1393,16 +1385,53 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 }
 EXPORT_SYMBOL_GPL(iomap_file_unshare);
 
-static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
+/*
+ * Flush the remaining range of the iter and mark the current mapping stale.
+ * This is used when zero range sees an unwritten mapping that may have had
+ * dirty pagecache over it.
+ */
+static inline int iomap_zero_iter_flush_and_stale(struct iomap_iter *i)
+{
+	struct address_space *mapping = i->inode->i_mapping;
+	loff_t end = i->pos + i->len - 1;
+
+	i->iomap.flags |= IOMAP_F_STALE;
+	return filemap_write_and_wait_range(mapping, i->pos, end);
+}
+
+static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero,
+		bool *range_dirty)
 {
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
 	loff_t pos = iter->pos;
 	loff_t length = iomap_length(iter);
 	loff_t written = 0;
 
-	/* already zeroed?  we're done. */
-	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
+	/*
+	 * We must zero subranges of unwritten mappings that might be dirty in
+	 * pagecache from previous writes. We only know whether the entire range
+	 * was clean or not, however, and dirty folios may have been written
+	 * back or reclaimed at any point after mapping lookup.
+	 *
+	 * The easiest way to deal with this is to flush pagecache to trigger
+	 * any pending unwritten conversions and then grab the updated extents
+	 * from the fs. The flush may change the current mapping, so mark it
+	 * stale for the iterator to remap it for the next pass to handle
+	 * properly.
+	 *
+	 * Note that holes are treated the same as unwritten because zero range
+	 * is (ab)used for partial folio zeroing in some cases. Hole backed
+	 * post-eof ranges can be dirtied via mapped write and the flush
+	 * triggers writeback time post-eof zeroing.
+	 */
+	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) {
+		if (*range_dirty) {
+			*range_dirty = false;
+			return iomap_zero_iter_flush_and_stale(iter);
+		}
+		/* range is clean and already zeroed, nothing to do */
 		return length;
+	}
 
 	do {
 		struct folio *folio;
@@ -1450,9 +1479,27 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 		.flags		= IOMAP_ZERO,
 	};
 	int ret;
+	bool range_dirty;
+
+	/*
+	 * Zero range wants to skip pre-zeroed (i.e. unwritten) mappings, but
+	 * pagecache must be flushed to ensure stale data from previous
+	 * buffered writes is not exposed. A flush is only required for certain
+	 * types of mappings, but checking pagecache after mapping lookup is
+	 * racy with writeback and reclaim.
+	 *
+	 * Therefore, check the entire range first and pass along whether any
+	 * part of it is dirty. If so and an underlying mapping warrants it,
+	 * flush the cache at that point. This trades off the occasional false
+	 * positive (and spurious flush, if the dirty data and mapping don't
+	 * happen to overlap) for simplicity in handling a relatively uncommon
+	 * situation.
+	 */
+	range_dirty = filemap_range_needs_writeback(inode->i_mapping,
+					pos, pos + len - 1);
 
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.processed = iomap_zero_iter(&iter, did_zero);
+		iter.processed = iomap_zero_iter(&iter, did_zero, &range_dirty);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iomap_zero_range);
@@ -2007,10 +2054,10 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
 }
 EXPORT_SYMBOL_GPL(iomap_writepages);
 
-static int __init iomap_init(void)
+static int __init iomap_buffered_init(void)
 {
 	return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
 			   offsetof(struct iomap_ioend, io_bio),
 			   BIOSET_NEED_BVECS);
 }
-fs_initcall(iomap_init);
+fs_initcall(iomap_buffered_init);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index f3b43d223a46..f637aa0706a3 100644
--- a/fs/iomap/direct-io.c
+++ b/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 @@ release_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 @@ zero_tail:
 		/* 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);