Merge tag 'iomap-6.6-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull iomap updates from Darrick Wong:
 "We've got some big changes for this release -- I'm very happy to be
  landing willy's work to enable large folios for the page cache for
  general read and write IOs when the fs can make contiguous space
  allocations, and Ritesh's work to track sub-folio dirty state to
  eliminate the write amplification problems inherent in using large
  folios.

  As a bonus, io_uring can now process write completions in the caller's
  context instead of bouncing through a workqueue, which should reduce
  io latency dramatically. IOWs, XFS should see a nice performance bump
  for both IO paths.

  Summary:

   - Make large writes to the page cache fill sparse parts of the cache
     with large folios, then use large memcpy calls for the large folio.

   - Track the per-block dirty state of each large folio so that a
     buffered write to a single byte on a large folio does not result in
     a (potentially) multi-megabyte writeback IO.

   - Allow some directio completions to be performed in the initiating
     task's context instead of punting through a workqueue. This will
     reduce latency for some io_uring requests"

* tag 'iomap-6.6-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (26 commits)
  iomap: support IOCB_DIO_CALLER_COMP
  io_uring/rw: add write support for IOCB_DIO_CALLER_COMP
  fs: add IOCB flags related to passing back dio completions
  iomap: add IOMAP_DIO_INLINE_COMP
  iomap: only set iocb->private for polled bio
  iomap: treat a write through cache the same as FUA
  iomap: use an unsigned type for IOMAP_DIO_* defines
  iomap: cleanup up iomap_dio_bio_end_io()
  iomap: Add per-block dirty state tracking to improve performance
  iomap: Allocate ifs in ->write_begin() early
  iomap: Refactor iomap_write_delalloc_punch() function out
  iomap: Use iomap_punch_t typedef
  iomap: Fix possible overflow condition in iomap_write_delalloc_scan
  iomap: Add some uptodate state handling helpers for ifs state bitmap
  iomap: Drop ifs argument from iomap_set_range_uptodate()
  iomap: Rename iomap_page to iomap_folio_state and others
  iomap: Copy larger chunks from userspace
  iomap: Create large folios in the buffered write path
  filemap: Allow __filemap_get_folio to allocate large folios
  filemap: Add fgf_t typedef
  ...

19 files changed, 659 insertions, 281 deletions

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 6e833ed0b22e..b7e5a3841aa4 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -376,10 +376,17 @@ invalidate_lock before invalidating page cache in truncate / hole punch
 path (and thus calling into ->invalidate_folio) to block races between page
 cache invalidation and page cache filling functions (fault, read, ...).
 
-->release_folio() is called when the kernel is about to try to drop the
-buffers from the folio in preparation for freeing it.  It returns false to
-indicate that the buffers are (or may be) freeable.  If ->release_folio is
-NULL, the kernel assumes that the fs has no private interest in the buffers.
+->release_folio() is called when the MM wants to make a change to the
+folio that would invalidate the filesystem's private data.  For example,
+it may be about to be removed from the address_space or split.  The folio
+is locked and not under writeback.  It may be dirty.  The gfp parameter
+is not usually used for allocation, but rather to indicate what the
+filesystem may do to attempt to free the private data.  The filesystem may
+return false to indicate that the folio's private data cannot be freed.
+If it returns true, it should have already removed the private data from
+the folio.  If a filesystem does not provide a ->release_folio method,
+the pagecache will assume that private data is buffer_heads and call
+try_to_free_buffers().
 
 ->free_folio() is called when the kernel has dropped the folio
 from the page cache.
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index b9e75c9f95ac..3887a8e1c964 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -876,9 +876,9 @@ static int prepare_uptodate_page(struct inode *inode,
 	return 0;
 }
 
-static unsigned int get_prepare_fgp_flags(bool nowait)
+static fgf_t get_prepare_fgp_flags(bool nowait)
 {
-	unsigned int fgp_flags = FGP_LOCK | FGP_ACCESSED | FGP_CREAT;
+	fgf_t fgp_flags = FGP_LOCK | FGP_ACCESSED | FGP_CREAT;
 
 	if (nowait)
 		fgp_flags |= FGP_NOWAIT;
@@ -910,7 +910,7 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
 	int i;
 	unsigned long index = pos >> PAGE_SHIFT;
 	gfp_t mask = get_prepare_gfp_flags(inode, nowait);
-	unsigned int fgp_flags = get_prepare_fgp_flags(nowait);
+	fgf_t fgp_flags = get_prepare_fgp_flags(nowait);
 	int err = 0;
 	int faili;
 
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 236d890f560b..0f7df9c11af3 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -1045,7 +1045,7 @@ static int prepare_compress_overwrite(struct compress_ctx *cc,
 	struct address_space *mapping = cc->inode->i_mapping;
 	struct page *page;
 	sector_t last_block_in_bio;
-	unsigned fgp_flag = FGP_LOCK | FGP_WRITE | FGP_CREAT;
+	fgf_t fgp_flag = FGP_LOCK | FGP_WRITE | FGP_CREAT;
 	pgoff_t start_idx = start_idx_of_cluster(cc);
 	int i, ret;
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e18272ae3119..613132339d72 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -2736,7 +2736,7 @@ static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
 
 static inline struct page *f2fs_pagecache_get_page(
 				struct address_space *mapping, pgoff_t index,
-				int fgp_flags, gfp_t gfp_mask)
+				fgf_t fgp_flags, gfp_t gfp_mask)
 {
 	if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET))
 		return NULL;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index ae49256b7c8c..9c4b26aec580 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -747,7 +747,7 @@ static const struct address_space_operations gfs2_aops = {
 	.writepages = gfs2_writepages,
 	.read_folio = gfs2_read_folio,
 	.readahead = gfs2_readahead,
-	.dirty_folio = filemap_dirty_folio,
+	.dirty_folio = iomap_dirty_folio,
 	.release_folio = iomap_release_folio,
 	.invalidate_folio = iomap_invalidate_folio,
 	.bmap = gfs2_bmap,
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 45ea63f7167d..f62366be7587 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -971,7 +971,7 @@ gfs2_iomap_get_folio(struct iomap_iter *iter, loff_t pos, unsigned len)
 	if (status)
 		return ERR_PTR(status);
 
-	folio = iomap_get_folio(iter, pos);
+	folio = iomap_get_folio(iter, pos, len);
 	if (IS_ERR(folio))
 		gfs2_trans_end(sdp);
 	return folio;
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index aa8967cca1a3..283fb96f6609 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -23,65 +23,169 @@
 
 #define IOEND_BATCH_SIZE	4096
 
+typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length);
 /*
- * Structure allocated for each folio when block size < folio size
- * to track sub-folio uptodate status and I/O completions.
+ * Structure allocated for each folio to track per-block uptodate, dirty state
+ * and I/O completions.
  */
-struct iomap_page {
+struct iomap_folio_state {
 	atomic_t		read_bytes_pending;
 	atomic_t		write_bytes_pending;
-	spinlock_t		uptodate_lock;
-	unsigned long		uptodate[];
+	spinlock_t		state_lock;
+
+	/*
+	 * Each block has two bits in this bitmap:
+	 * Bits [0..blocks_per_folio) has the uptodate status.
+	 * Bits [b_p_f...(2*b_p_f))   has the dirty status.
+	 */
+	unsigned long		state[];
 };
 
-static inline struct iomap_page *to_iomap_page(struct folio *folio)
+static struct bio_set iomap_ioend_bioset;
+
+static inline bool ifs_is_fully_uptodate(struct folio *folio,
+		struct iomap_folio_state *ifs)
 {
-	if (folio_test_private(folio))
-		return folio_get_private(folio);
-	return NULL;
+	struct inode *inode = folio->mapping->host;
+
+	return bitmap_full(ifs->state, i_blocks_per_folio(inode, folio));
 }
 
-static struct bio_set iomap_ioend_bioset;
+static inline bool ifs_block_is_uptodate(struct iomap_folio_state *ifs,
+		unsigned int block)
+{
+	return test_bit(block, ifs->state);
+}
+
+static void ifs_set_range_uptodate(struct folio *folio,
+		struct iomap_folio_state *ifs, size_t off, size_t len)
+{
+	struct inode *inode = folio->mapping->host;
+	unsigned int first_blk = off >> inode->i_blkbits;
+	unsigned int last_blk = (off + len - 1) >> inode->i_blkbits;
+	unsigned int nr_blks = last_blk - first_blk + 1;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ifs->state_lock, flags);
+	bitmap_set(ifs->state, first_blk, nr_blks);
+	if (ifs_is_fully_uptodate(folio, ifs))
+		folio_mark_uptodate(folio);
+	spin_unlock_irqrestore(&ifs->state_lock, flags);
+}
+
+static void iomap_set_range_uptodate(struct folio *folio, size_t off,
+		size_t len)
+{
+	struct iomap_folio_state *ifs = folio->private;
+
+	if (ifs)
+		ifs_set_range_uptodate(folio, ifs, off, len);
+	else
+		folio_mark_uptodate(folio);
+}
+
+static inline bool ifs_block_is_dirty(struct folio *folio,
+		struct iomap_folio_state *ifs, int block)
+{
+	struct inode *inode = folio->mapping->host;
+	unsigned int blks_per_folio = i_blocks_per_folio(inode, folio);
+
+	return test_bit(block + blks_per_folio, ifs->state);
+}
+
+static void ifs_clear_range_dirty(struct folio *folio,
+		struct iomap_folio_state *ifs, size_t off, size_t len)
+{
+	struct inode *inode = folio->mapping->host;
+	unsigned int blks_per_folio = i_blocks_per_folio(inode, folio);
+	unsigned int first_blk = (off >> inode->i_blkbits);
+	unsigned int last_blk = (off + len - 1) >> inode->i_blkbits;
+	unsigned int nr_blks = last_blk - first_blk + 1;
+	unsigned long flags;
 
-static struct iomap_page *
-iomap_page_create(struct inode *inode, struct folio *folio, unsigned int flags)
+	spin_lock_irqsave(&ifs->state_lock, flags);
+	bitmap_clear(ifs->state, first_blk + blks_per_folio, nr_blks);
+	spin_unlock_irqrestore(&ifs->state_lock, flags);
+}
+
+static void iomap_clear_range_dirty(struct folio *folio, size_t off, size_t len)
 {
-	struct iomap_page *iop = to_iomap_page(folio);
+	struct iomap_folio_state *ifs = folio->private;
+
+	if (ifs)
+		ifs_clear_range_dirty(folio, ifs, off, len);
+}
+
+static void ifs_set_range_dirty(struct folio *folio,
+		struct iomap_folio_state *ifs, size_t off, size_t len)
+{
+	struct inode *inode = folio->mapping->host;
+	unsigned int blks_per_folio = i_blocks_per_folio(inode, folio);
+	unsigned int first_blk = (off >> inode->i_blkbits);
+	unsigned int last_blk = (off + len - 1) >> inode->i_blkbits;
+	unsigned int nr_blks = last_blk - first_blk + 1;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ifs->state_lock, flags);
+	bitmap_set(ifs->state, first_blk + blks_per_folio, nr_blks);
+	spin_unlock_irqrestore(&ifs->state_lock, flags);
+}
+
+static void iomap_set_range_dirty(struct folio *folio, size_t off, size_t len)
+{
+	struct iomap_folio_state *ifs = folio->private;
+
+	if (ifs)
+		ifs_set_range_dirty(folio, ifs, off, len);
+}
+
+static struct iomap_folio_state *ifs_alloc(struct inode *inode,
+		struct folio *folio, unsigned int flags)
+{
+	struct iomap_folio_state *ifs = folio->private;
 	unsigned int nr_blocks = i_blocks_per_folio(inode, folio);
 	gfp_t gfp;
 
-	if (iop || nr_blocks <= 1)
-		return iop;
+	if (ifs || nr_blocks <= 1)
+		return ifs;
 
 	if (flags & IOMAP_NOWAIT)
 		gfp = GFP_NOWAIT;
 	else
 		gfp = GFP_NOFS | __GFP_NOFAIL;
 
-	iop = kzalloc(struct_size(iop, uptodate, BITS_TO_LONGS(nr_blocks)),
-		      gfp);
-	if (iop) {
-		spin_lock_init(&iop->uptodate_lock);
-		if (folio_test_uptodate(folio))
-			bitmap_fill(iop->uptodate, nr_blocks);
-		folio_attach_private(folio, iop);
-	}
-	return iop;
+	/*
+	 * ifs->state tracks two sets of state flags when the
+	 * filesystem block size is smaller than the folio size.
+	 * The first state tracks per-block uptodate and the
+	 * second tracks per-block dirty state.
+	 */
+	ifs = kzalloc(struct_size(ifs, state,
+		      BITS_TO_LONGS(2 * nr_blocks)), gfp);
+	if (!ifs)
+		return ifs;
+
+	spin_lock_init(&ifs->state_lock);
+	if (folio_test_uptodate(folio))
+		bitmap_set(ifs->state, 0, nr_blocks);
+	if (folio_test_dirty(folio))
+		bitmap_set(ifs->state, nr_blocks, nr_blocks);
+	folio_attach_private(folio, ifs);
+
+	return ifs;
 }
 
-static void iomap_page_release(struct folio *folio)
+static void ifs_free(struct folio *folio)
 {
-	struct iomap_page *iop = folio_detach_private(folio);
-	struct inode *inode = folio->mapping->host;
-	unsigned int nr_blocks = i_blocks_per_folio(inode, folio);
+	struct iomap_folio_state *ifs = folio_detach_private(folio);
 
-	if (!iop)
+	if (!ifs)
 		return;
-	WARN_ON_ONCE(atomic_read(&iop->read_bytes_pending));
-	WARN_ON_ONCE(atomic_read(&iop->write_bytes_pending));
-	WARN_ON_ONCE(bitmap_full(iop->uptodate, nr_blocks) !=
+	WARN_ON_ONCE(atomic_read(&ifs->read_bytes_pending));
+	WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending));
+	WARN_ON_ONCE(ifs_is_fully_uptodate(folio, ifs) !=
 			folio_test_uptodate(folio));
-	kfree(iop);
+	kfree(ifs);
 }
 
 /*
@@ -90,7 +194,7 @@ static void iomap_page_release(struct folio *folio)
 static void iomap_adjust_read_range(struct inode *inode, struct folio *folio,
 		loff_t *pos, loff_t length, size_t *offp, size_t *lenp)
 {
-	struct iomap_page *iop = to_iomap_page(folio);
+	struct iomap_folio_state *ifs = folio->private;
 	loff_t orig_pos = *pos;
 	loff_t isize = i_size_read(inode);
 	unsigned block_bits = inode->i_blkbits;
@@ -105,12 +209,12 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio,
 	 * per-block uptodate status and adjust the offset and length if needed
 	 * to avoid reading in already uptodate ranges.
 	 */
-	if (iop) {
+	if (ifs) {
 		unsigned int i;
 
 		/* move forward for each leading block marked uptodate */
 		for (i = first; i <= last; i++) {
-			if (!test_bit(i, iop->uptodate))
+			if (!ifs_block_is_uptodate(ifs, i))
 				break;
 			*pos += block_size;
 			poff += block_size;
@@ -120,7 +224,7 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio,
 
 		/* truncate len if we find any trailing uptodate block(s) */
 		for ( ; i <= last; i++) {
-			if (test_bit(i, iop->uptodate)) {
+			if (ifs_block_is_uptodate(ifs, i)) {
 				plen -= (last - i + 1) * block_size;
 				last = i - 1;
 				break;
@@ -144,43 +248,19 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio,
 	*lenp = plen;
 }
 
-static void iomap_iop_set_range_uptodate(struct folio *folio,
-		struct iomap_page *iop, size_t off, size_t len)
-{
-	struct inode *inode = folio->mapping->host;
-	unsigned first = off >> inode->i_blkbits;
-	unsigned last = (off + len - 1) >> inode->i_blkbits;
-	unsigned long flags;
-
-	spin_lock_irqsave(&iop->uptodate_lock, flags);
-	bitmap_set(iop->uptodate, first, last - first + 1);
-	if (bitmap_full(iop->uptodate, i_blocks_per_folio(inode, folio)))
-		folio_mark_uptodate(folio);
-	spin_unlock_irqrestore(&iop->uptodate_lock, flags);
-}
-
-static void iomap_set_range_uptodate(struct folio *folio,
-		struct iomap_page *iop, size_t off, size_t len)
-{
-	if (iop)
-		iomap_iop_set_range_uptodate(folio, iop, off, len);
-	else
-		folio_mark_uptodate(folio);
-}
-
 static void iomap_finish_folio_read(struct folio *folio, size_t offset,
 		size_t len, int error)
 {
-	struct iomap_page *iop = to_iomap_page(folio);
+	struct iomap_folio_state *ifs = folio->private;
 
 	if (unlikely(error)) {
 		folio_clear_uptodate(folio);
 		folio_set_error(folio);
 	} else {
-		iomap_set_range_uptodate(folio, iop, offset, len);
+		iomap_set_range_uptodate(folio, offset, len);
 	}
 
-	if (!iop || atomic_sub_and_test(len, &iop->read_bytes_pending))
+	if (!ifs || atomic_sub_and_test(len, &ifs->read_bytes_pending))
 		folio_unlock(folio);
 }
 
@@ -213,7 +293,6 @@ struct iomap_readpage_ctx {
 static int iomap_read_inline_data(const struct iomap_iter *iter,
 		struct folio *folio)
 {
-	struct iomap_page *iop;
 	const struct iomap *iomap = iomap_iter_srcmap(iter);
 	size_t size = i_size_read(iter->inode) - iomap->offset;
 	size_t poff = offset_in_page(iomap->offset);
@@ -231,15 +310,13 @@ static int iomap_read_inline_data(const struct iomap_iter *iter,
 	if (WARN_ON_ONCE(size > iomap->length))
 		return -EIO;
 	if (offset > 0)
-		iop = iomap_page_create(iter->inode, folio, iter->flags);
-	else
-		iop = to_iomap_page(folio);
+		ifs_alloc(iter->inode, folio, iter->flags);
 
 	addr = kmap_local_folio(folio, offset);
 	memcpy(addr, iomap->inline_data, size);
 	memset(addr + size, 0, PAGE_SIZE - poff - size);
 	kunmap_local(addr);
-	iomap_set_range_uptodate(folio, iop, offset, PAGE_SIZE - poff);
+	iomap_set_range_uptodate(folio, offset, PAGE_SIZE - poff);
 	return 0;
 }
 
@@ -260,7 +337,7 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter,
 	loff_t pos = iter->pos + offset;
 	loff_t length = iomap_length(iter) - offset;
 	struct folio *folio = ctx->cur_folio;
-	struct iomap_page *iop;
+	struct iomap_folio_state *ifs;
 	loff_t orig_pos = pos;
 	size_t poff, plen;
 	sector_t sector;
@@ -269,20 +346,20 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter,
 		return iomap_read_inline_data(iter, folio);
 
 	/* zero post-eof blocks as the page may be mapped */
-	iop = iomap_page_create(iter->inode, folio, iter->flags);
+	ifs = ifs_alloc(iter->inode, folio, iter->flags);
 	iomap_adjust_read_range(iter->inode, folio, &pos, length, &poff, &plen);
 	if (plen == 0)
 		goto done;
 
 	if (iomap_block_needs_zeroing(iter, pos)) {
 		folio_zero_range(folio, poff, plen);
-		iomap_set_range_uptodate(folio, iop, poff, plen);
+		iomap_set_range_uptodate(folio, poff, plen);
 		goto done;
 	}
 
 	ctx->cur_folio_in_bio = true;
-	if (iop)
-		atomic_add(plen, &iop->read_bytes_pending);
+	if (ifs)
+		atomic_add(plen, &ifs->read_bytes_pending);
 
 	sector = iomap_sector(iomap, pos);
 	if (!ctx->bio ||
@@ -436,11 +513,11 @@ EXPORT_SYMBOL_GPL(iomap_readahead);
  */
 bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count)
 {
-	struct iomap_page *iop = to_iomap_page(folio);
+	struct iomap_folio_state *ifs = folio->private;
 	struct inode *inode = folio->mapping->host;
 	unsigned first, last, i;
 
-	if (!iop)
+	if (!ifs)
 		return false;
 
 	/* Caller's range may extend past the end of this folio */
@@ -451,7 +528,7 @@ bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count)
 	last = (from + count - 1) >> inode->i_blkbits;
 
 	for (i = first; i <= last; i++)
-		if (!test_bit(i, iop->uptodate))
+		if (!ifs_block_is_uptodate(ifs, i))
 			return false;
 	return true;
 }
@@ -461,16 +538,18 @@ EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);
  * iomap_get_folio - get a folio reference for writing
  * @iter: iteration structure
  * @pos: start offset of write
+ * @len: Suggested size of folio to create.
  *
  * Returns a locked reference to the folio at @pos, or an error pointer if the
  * folio could not be obtained.
  */
-struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos)
+struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len)
 {
-	unsigned fgp = FGP_WRITEBEGIN | FGP_NOFS;
+	fgf_t fgp = FGP_WRITEBEGIN | FGP_NOFS;
 
 	if (iter->flags & IOMAP_NOWAIT)
 		fgp |= FGP_NOWAIT;
+	fgp |= fgf_set_order(len);
 
 	return __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT,
 			fgp, mapping_gfp_mask(iter->inode->i_mapping));
@@ -483,14 +562,13 @@ bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags)
 			folio_size(folio));
 
 	/*
-	 * mm accommodates an old ext3 case where clean folios might
-	 * not have had the dirty bit cleared.  Thus, it can send actual
-	 * dirty folios to ->release_folio() via shrink_active_list();
-	 * skip those here.
+	 * If the folio is dirty, we refuse to release our metadata because
+	 * it may be partially dirty.  Once we track per-block dirty state,
+	 * we can release the metadata if every block is dirty.
 	 */
-	if (folio_test_dirty(folio) || folio_test_writeback(folio))
+	if (folio_test_dirty(folio))
 		return false;
-	iomap_page_release(folio);
+	ifs_free(folio);
 	return true;
 }
 EXPORT_SYMBOL_GPL(iomap_release_folio);
@@ -507,16 +585,22 @@ void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len)
 	if (offset == 0 && len == folio_size(folio)) {
 		WARN_ON_ONCE(folio_test_writeback(folio));
 		folio_cancel_dirty(folio);
-		iomap_page_release(folio);
-	} else if (folio_test_large(folio)) {
-		/* Must release the iop so the page can be split */
-		WARN_ON_ONCE(!folio_test_uptodate(folio) &&
-			     folio_test_dirty(folio));
-		iomap_page_release(folio);
+		ifs_free(folio);
 	}
 }
 EXPORT_SYMBOL_GPL(iomap_invalidate_folio);
 
+bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio)
+{
+	struct inode *inode = mapping->host;
+	size_t len = folio_size(folio);
+
+	ifs_alloc(inode, folio, 0);
+	iomap_set_range_dirty(folio, 0, len);
+	return filemap_dirty_folio(mapping, folio);
+}
+EXPORT_SYMBOL_GPL(iomap_dirty_folio);
+
 static void
 iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 {
@@ -547,7 +631,7 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 		size_t len, struct folio *folio)
 {
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
-	struct iomap_page *iop;
+	struct iomap_folio_state *ifs;
 	loff_t block_size = i_blocksize(iter->inode);
 	loff_t block_start = round_down(pos, block_size);
 	loff_t block_end = round_up(pos + len, block_size);
@@ -555,14 +639,23 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 	size_t from = offset_in_folio(folio, pos), to = from + len;
 	size_t poff, plen;
 
-	if (folio_test_uptodate(folio))
+	/*
+	 * If the write completely overlaps the current folio, then
+	 * entire folio will be dirtied so there is no need for
+	 * per-block state tracking structures to be attached to this folio.
+	 */
+	if (pos <= folio_pos(folio) &&
+	    pos + len >= folio_pos(folio) + folio_size(folio))
 		return 0;
-	folio_clear_error(folio);
 
-	iop = iomap_page_create(iter->inode, folio, iter->flags);
-	if ((iter->flags & IOMAP_NOWAIT) && !iop && nr_blocks > 1)
+	ifs = ifs_alloc(iter->inode, folio, iter->flags);
+	if ((iter->flags & IOMAP_NOWAIT) && !ifs && nr_blocks > 1)
 		return -EAGAIN;
 
+	if (folio_test_uptodate(folio))
+		return 0;
+	folio_clear_error(folio);
+
 	do {
 		iomap_adjust_read_range(iter->inode, folio, &block_start,
 				block_end - block_start, &poff, &plen);
@@ -589,7 +682,7 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 			if (status)
 				return status;
 		}
-		iomap_set_range_uptodate(folio, iop, poff, plen);
+		iomap_set_range_uptodate(folio, poff, plen);
 	} while ((block_start += plen) < block_end);
 
 	return 0;
@@ -603,7 +696,7 @@ static struct folio *__iomap_get_folio(struct iomap_iter *iter, loff_t pos,
 	if (folio_ops && folio_ops->get_folio)
 		return folio_ops->get_folio(iter, pos, len);
 	else
-		return iomap_get_folio(iter, pos);
+		return iomap_get_folio(iter, pos, len);
 }
 
 static void __iomap_put_folio(struct iomap_iter *iter, loff_t pos, size_t ret,
@@ -696,7 +789,6 @@ out_unlock:
 static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
 		size_t copied, struct folio *folio)
 {
-	struct iomap_page *iop = to_iomap_page(folio);
 	flush_dcache_folio(folio);
 
 	/*
@@ -712,7 +804,8 @@ static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
 	 */
 	if (unlikely(copied < len && !folio_test_uptodate(folio)))
 		return 0;
-	iomap_set_range_uptodate(folio, iop, offset_in_folio(folio, pos), len);
+	iomap_set_range_uptodate(folio, offset_in_folio(folio, pos), len);
+	iomap_set_range_dirty(folio, offset_in_folio(folio, pos), copied);
 	filemap_dirty_folio(inode->i_mapping, folio);
 	return copied;
 }
@@ -773,6 +866,7 @@ static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
 static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 {
 	loff_t length = iomap_length(iter);
+	size_t chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
 	loff_t pos = iter->pos;
 	ssize_t written = 0;
 	long status = 0;
@@ -781,15 +875,12 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 
 	do {
 		struct folio *folio;
-		struct page *page;
-		unsigned long offset;	/* Offset into pagecache page */
-		unsigned long bytes;	/* Bytes to write to page */
+		size_t offset;		/* Offset into folio */
+		size_t bytes;		/* Bytes to write to folio */
 		size_t copied;		/* Bytes copied from user */
 
-		offset = offset_in_page(pos);
-		bytes = min_t(unsigned long, PAGE_SIZE - offset,
-						iov_iter_count(i));
-again:
+		offset = pos & (chunk - 1);
+		bytes = min(chunk - offset, iov_iter_count(i));
 		status = balance_dirty_pages_ratelimited_flags(mapping,
 							       bdp_flags);
 		if (unlikely(status))
@@ -819,12 +910,14 @@ again:
 		if (iter->iomap.flags & IOMAP_F_STALE)
 			break;
 
-		page = folio_file_page(folio, pos >> PAGE_SHIFT);
-		if (mapping_writably_mapped(mapping))
-			flush_dcache_page(page);
+		offset = offset_in_folio(folio, pos);
+		if (bytes > folio_size(folio) - offset)
+			bytes = folio_size(folio) - offset;
 
-		copied = copy_page_from_iter_atomic(page, offset, bytes, i);
+		if (mapping_writably_mapped(mapping))
+			flush_dcache_folio(folio);
 
+		copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
 		status = iomap_write_end(iter, pos, bytes, copied, folio);
 
 		if (unlikely(copied != status))
@@ -840,11 +933,13 @@ again:
 			 */
 			if (copied)
 				bytes = copied;
-			goto again;
+			if (chunk > PAGE_SIZE)
+				chunk /= 2;
+		} else {
+			pos += status;
+			written += status;
+			length -= status;
 		}
-		pos += status;
-		written += status;
-		length -= status;
 	} while (iov_iter_count(i) && length);
 
 	if (status == -EAGAIN) {
@@ -880,6 +975,76 @@ 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,
+		struct folio *folio, loff_t start_byte, loff_t end_byte,
+		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
+	 * blocks within a folio which are marked uptodate
+	 * but not dirty. In that case it is necessary to punch
+	 * out such blocks to avoid leaking any delalloc blocks.
+	 */
+	ifs = folio->private;
+	if (!ifs)
+		return ret;
+
+	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;
+		}
+	}
+
+	return ret;
+}
+
+
+static int 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)
+{
+	int ret = 0;
+
+	if (!folio_test_dirty(folio))
+		return ret;
+
+	/* 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 non-dirty blocks within folio */
+	ret = iomap_write_delalloc_ifs_punch(inode, folio, start_byte,
+			end_byte, punch);
+	if (ret)
+		return ret;
+
+	/*
+	 * Make sure the next punch start is correctly bound to
+	 * the end of this data range, not the end of the folio.
+	 */
+	*punch_start_byte = min_t(loff_t, end_byte,
+				folio_pos(folio) + folio_size(folio));
+
+	return ret;
+}
+
 /*
  * Scan the data range passed to us for dirty page cache folios. If we find a
  * dirty folio, punch out the preceeding range and update the offset from which
@@ -899,10 +1064,11 @@ EXPORT_SYMBOL_GPL(iomap_file_buffered_write);
  */
 static int iomap_write_delalloc_scan(struct inode *inode,
 		loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte,
-		int (*punch)(struct inode *inode, loff_t offset, loff_t length))
+		iomap_punch_t punch)
 {
 	while (start_byte < end_byte) {
 		struct folio	*folio;
+		int ret;
 
 		/* grab locked page */
 		folio = filemap_lock_folio(inode->i_mapping,
@@ -913,26 +1079,12 @@ static int iomap_write_delalloc_scan(struct inode *inode,
 			continue;
 		}
 
-		/* if dirty, punch up to offset */
-		if (folio_test_dirty(folio)) {
-			if (start_byte > *punch_start_byte) {
-				int	error;
-
-				error = punch(inode, *punch_start_byte,
-						start_byte - *punch_start_byte);
-				if (error) {
-					folio_unlock(folio);
-					folio_put(folio);
-					return error;
-				}
-			}
-
-			/*
-			 * Make sure the next punch start is correctly bound to
-			 * the end of this data range, not the end of the folio.
-			 */
-			*punch_start_byte = min_t(loff_t, end_byte,
-					folio_next_index(folio) << PAGE_SHIFT);
+		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;
 		}
 
 		/* move offset to start of next folio in range */
@@ -977,8 +1129,7 @@ static int iomap_write_delalloc_scan(struct inode *inode,
  * 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,
-		int (*punch)(struct inode *inode, loff_t pos, loff_t length))
+		loff_t start_byte, loff_t end_byte, iomap_punch_t punch)
 {
 	loff_t punch_start_byte = start_byte;
 	loff_t scan_end_byte = min(i_size_read(inode), end_byte);
@@ -1071,8 +1222,7 @@ out_unlock:
  */
 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))
+		ssize_t written, iomap_punch_t punch)
 {
 	loff_t			start_byte;
 	loff_t			end_byte;
@@ -1293,17 +1443,17 @@ EXPORT_SYMBOL_GPL(iomap_page_mkwrite);
 static void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
 		size_t len, int error)
 {
-	struct iomap_page *iop = to_iomap_page(folio);
+	struct iomap_folio_state *ifs = folio->private;
 
 	if (error) {
 		folio_set_error(folio);
 		mapping_set_error(inode->i_mapping, error);
 	}
 
-	WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !iop);
-	WARN_ON_ONCE(iop &