Adding upstream version 6.6.15.upstream/6.6.15

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

9 files changed, 3575 insertions, 0 deletions

diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile
new file mode 100644
index 0000000000..fc070184b7
--- /dev/null
+++ b/fs/iomap/Makefile
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
+#
+# Copyright (c) 2019 Oracle.
+# All Rights Reserved.
+#
+
+ccflags-y += -I $(srctree)/$(src)		# needed for trace events
+
+obj-$(CONFIG_FS_IOMAP)		+= iomap.o
+
+iomap-y				+= trace.o \
+				   iter.o
+iomap-$(CONFIG_BLOCK)		+= buffered-io.o \
+				   direct-io.o \
+				   fiemap.o \
+				   seek.o
+iomap-$(CONFIG_SWAP)		+= swapfile.o
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
new file mode 100644
index 0000000000..2bc0aa23fd
--- /dev/null
+++ b/fs/iomap/buffered-io.c
@@ -0,0 +1,2002 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2010 Red Hat, Inc.
+ * Copyright (C) 2016-2019 Christoph Hellwig.
+ */
+#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/iomap.h>
+#include <linux/pagemap.h>
+#include <linux/uio.h>
+#include <linux/buffer_head.h>
+#include <linux/dax.h>
+#include <linux/writeback.h>
+#include <linux/list_sort.h>
+#include <linux/swap.h>
+#include <linux/bio.h>
+#include <linux/sched/signal.h>
+#include <linux/migrate.h>
+#include "trace.h"
+
+#include "../internal.h"
+
+#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.
+ */
+struct iomap_folio_state {
+	atomic_t		read_bytes_pending;
+	atomic_t		write_bytes_pending;
+	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 struct bio_set iomap_ioend_bioset;
+
+static inline bool ifs_is_fully_uptodate(struct folio *folio,
+		struct iomap_folio_state *ifs)
+{
+	struct inode *inode = folio->mapping->host;
+
+	return bitmap_full(ifs->state, i_blocks_per_folio(inode, folio));
+}
+
+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;
+
+	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_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 (ifs || nr_blocks <= 1)
+		return ifs;
+
+	if (flags & IOMAP_NOWAIT)
+		gfp = GFP_NOWAIT;
+	else
+		gfp = GFP_NOFS | __GFP_NOFAIL;
+
+	/*
+	 * 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 ifs_free(struct folio *folio)
+{
+	struct iomap_folio_state *ifs = folio_detach_private(folio);
+
+	if (!ifs)
+		return;
+	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(ifs);
+}
+
+/*
+ * Calculate the range inside the folio that we actually need to read.
+ */
+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_folio_state *ifs = folio->private;
+	loff_t orig_pos = *pos;
+	loff_t isize = i_size_read(inode);
+	unsigned block_bits = inode->i_blkbits;
+	unsigned block_size = (1 << block_bits);
+	size_t poff = offset_in_folio(folio, *pos);
+	size_t plen = min_t(loff_t, folio_size(folio) - poff, length);
+	unsigned first = poff >> block_bits;
+	unsigned last = (poff + plen - 1) >> block_bits;
+
+	/*
+	 * If the block size is smaller than the page size, we need to check the
+	 * per-block uptodate status and adjust the offset and length if needed
+	 * to avoid reading in already uptodate ranges.
+	 */
+	if (ifs) {
+		unsigned int i;
+
+		/* move forward for each leading block marked uptodate */
+		for (i = first; i <= last; i++) {
+			if (!ifs_block_is_uptodate(ifs, i))
+				break;
+			*pos += block_size;
+			poff += block_size;
+			plen -= block_size;
+			first++;
+		}
+
+		/* truncate len if we find any trailing uptodate block(s) */
+		for ( ; i <= last; i++) {
+			if (ifs_block_is_uptodate(ifs, i)) {
+				plen -= (last - i + 1) * block_size;
+				last = i - 1;
+				break;
+			}
+		}
+	}
+
+	/*
+	 * If the extent spans the block that contains the i_size, we need to
+	 * handle both halves separately so that we properly zero data in the
+	 * page cache for blocks that are entirely outside of i_size.
+	 */
+	if (orig_pos <= isize && orig_pos + length > isize) {
+		unsigned end = offset_in_folio(folio, isize - 1) >> block_bits;
+
+		if (first <= end && last > end)
+			plen -= (last - end) * block_size;
+	}
+
+	*offp = poff;
+	*lenp = plen;
+}
+
+static void iomap_finish_folio_read(struct folio *folio, size_t offset,
+		size_t len, int error)
+{
+	struct iomap_folio_state *ifs = folio->private;
+
+	if (unlikely(error)) {
+		folio_clear_uptodate(folio);
+		folio_set_error(folio);
+	} else {
+		iomap_set_range_uptodate(folio, offset, len);
+	}
+
+	if (!ifs || atomic_sub_and_test(len, &ifs->read_bytes_pending))
+		folio_unlock(folio);
+}
+
+static void iomap_read_end_io(struct bio *bio)
+{
+	int error = blk_status_to_errno(bio->bi_status);
+	struct folio_iter fi;
+
+	bio_for_each_folio_all(fi, bio)
+		iomap_finish_folio_read(fi.folio, fi.offset, fi.length, error);
+	bio_put(bio);
+}
+
+struct iomap_readpage_ctx {
+	struct folio		*cur_folio;
+	bool			cur_folio_in_bio;
+	struct bio		*bio;
+	struct readahead_control *rac;
+};
+
+/**
+ * iomap_read_inline_data - copy inline data into the page cache
+ * @iter: iteration structure
+ * @folio: folio to copy to
+ *
+ * Copy the inline data in @iter into @folio and zero out the rest of the folio.
+ * Only a single IOMAP_INLINE extent is allowed at the end of each file.
+ * Returns zero for success to complete the read, or the usual negative errno.
+ */
+static int iomap_read_inline_data(const struct iomap_iter *iter,
+		struct folio *folio)
+{
+	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);
+	size_t offset = offset_in_folio(folio, iomap->offset);
+	void *addr;
+
+	if (folio_test_uptodate(folio))
+		return 0;
+
+	if (WARN_ON_ONCE(size > PAGE_SIZE - poff))
+		return -EIO;
+	if (WARN_ON_ONCE(size > PAGE_SIZE -
+			 offset_in_page(iomap->inline_data)))
+		return -EIO;
+	if (WARN_ON_ONCE(size > iomap->length))
+		return -EIO;
+	if (offset > 0)
+		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, offset, PAGE_SIZE - poff);
+	return 0;
+}
+
+static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter,
+		loff_t pos)
+{
+	const struct iomap *srcmap = iomap_iter_srcmap(iter);
+
+	return srcmap->type != IOMAP_MAPPED ||
+		(srcmap->flags & IOMAP_F_NEW) ||
+		pos >= i_size_read(iter->inode);
+}
+
+static loff_t iomap_readpage_iter(const struct iomap_iter *iter,
+		struct iomap_readpage_ctx *ctx, loff_t offset)
+{
+	const struct iomap *iomap = &iter->iomap;
+	loff_t pos = iter->pos + offset;
+	loff_t length = iomap_length(iter) - offset;
+	struct folio *folio = ctx->cur_folio;
+	struct iomap_folio_state *ifs;
+	loff_t orig_pos = pos;
+	size_t poff, plen;
+	sector_t sector;
+
+	if (iomap->type == IOMAP_INLINE)
+		return iomap_read_inline_data(iter, folio);
+
+	/* zero post-eof blocks as the page may be mapped */
+	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, poff, plen);
+		goto done;
+	}
+
+	ctx->cur_folio_in_bio = true;
+	if (ifs)
+		atomic_add(plen, &ifs->read_bytes_pending);
+
+	sector = iomap_sector(iomap, pos);
+	if (!ctx->bio ||
+	    bio_end_sector(ctx->bio) != sector ||
+	    !bio_add_folio(ctx->bio, folio, plen, poff)) {
+		gfp_t gfp = mapping_gfp_constraint(folio->mapping, GFP_KERNEL);
+		gfp_t orig_gfp = gfp;
+		unsigned int nr_vecs = DIV_ROUND_UP(length, PAGE_SIZE);
+
+		if (ctx->bio)
+			submit_bio(ctx->bio);
+
+		if (ctx->rac) /* same as readahead_gfp_mask */
+			gfp |= __GFP_NORETRY | __GFP_NOWARN;
+		ctx->bio = bio_alloc(iomap->bdev, bio_max_segs(nr_vecs),
+				     REQ_OP_READ, gfp);
+		/*
+		 * If the bio_alloc fails, try it again for a single page to
+		 * avoid having to deal with partial page reads.  This emulates
+		 * what do_mpage_read_folio does.
+		 */
+		if (!ctx->bio) {
+			ctx->bio = bio_alloc(iomap->bdev, 1, REQ_OP_READ,
+					     orig_gfp);
+		}
+		if (ctx->rac)
+			ctx->bio->bi_opf |= REQ_RAHEAD;
+		ctx->bio->bi_iter.bi_sector = sector;
+		ctx->bio->bi_end_io = iomap_read_end_io;
+		bio_add_folio_nofail(ctx->bio, folio, plen, poff);
+	}
+
+done:
+	/*
+	 * Move the caller beyond our range so that it keeps making progress.
+	 * For that, we have to include any leading non-uptodate ranges, but
+	 * we can skip trailing ones as they will be handled in the next
+	 * iteration.
+	 */
+	return pos - orig_pos + plen;
+}
+
+int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops)
+{
+	struct iomap_iter iter = {
+		.inode		= folio->mapping->host,
+		.pos		= folio_pos(folio),
+		.len		= folio_size(folio),
+	};
+	struct iomap_readpage_ctx ctx = {
+		.cur_folio	= folio,
+	};
+	int ret;
+
+	trace_iomap_readpage(iter.inode, 1);
+
+	while ((ret = iomap_iter(&iter, ops)) > 0)
+		iter.processed = iomap_readpage_iter(&iter, &ctx, 0);
+
+	if (ret < 0)
+		folio_set_error(folio);
+
+	if (ctx.bio) {
+		submit_bio(ctx.bio);
+		WARN_ON_ONCE(!ctx.cur_folio_in_bio);
+	} else {
+		WARN_ON_ONCE(ctx.cur_folio_in_bio);
+		folio_unlock(folio);
+	}
+
+	/*
+	 * Just like mpage_readahead and block_read_full_folio, we always
+	 * return 0 and just set the folio error flag on errors.  This
+	 * should be cleaned up throughout the stack eventually.
+	 */
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_read_folio);
+
+static loff_t iomap_readahead_iter(const struct iomap_iter *iter,
+		struct iomap_readpage_ctx *ctx)
+{
+	loff_t length = iomap_length(iter);
+	loff_t done, ret;
+
+	for (done = 0; done < length; done += ret) {
+		if (ctx->cur_folio &&
+		    offset_in_folio(ctx->cur_folio, iter->pos + done) == 0) {
+			if (!ctx->cur_folio_in_bio)
+				folio_unlock(ctx->cur_folio);
+			ctx->cur_folio = NULL;
+		}
+		if (!ctx->cur_folio) {
+			ctx->cur_folio = readahead_folio(ctx->rac);
+			ctx->cur_folio_in_bio = false;
+		}
+		ret = iomap_readpage_iter(iter, ctx, done);
+		if (ret <= 0)
+			return ret;
+	}
+
+	return done;
+}
+
+/**
+ * iomap_readahead - Attempt to read pages from a file.
+ * @rac: Describes the pages to be read.
+ * @ops: The operations vector for the filesystem.
+ *
+ * This function is for filesystems to call to implement their readahead
+ * address_space operation.
+ *
+ * Context: The @ops callbacks may submit I/O (eg to read the addresses of
+ * blocks from disc), and may wait for it.  The caller may be trying to
+ * access a different page, and so sleeping excessively should be avoided.
+ * It may allocate memory, but should avoid costly allocations.  This
+ * function is called with memalloc_nofs set, so allocations will not cause
+ * the filesystem to be reentered.
+ */
+void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops)
+{
+	struct iomap_iter iter = {
+		.inode	= rac->mapping->host,
+		.pos	= readahead_pos(rac),
+		.len	= readahead_length(rac),
+	};
+	struct iomap_readpage_ctx ctx = {
+		.rac	= rac,
+	};
+
+	trace_iomap_readahead(rac->mapping->host, readahead_count(rac));
+
+	while (iomap_iter(&iter, ops) > 0)
+		iter.processed = iomap_readahead_iter(&iter, &ctx);
+
+	if (ctx.bio)
+		submit_bio(ctx.bio);
+	if (ctx.cur_folio) {
+		if (!ctx.cur_folio_in_bio)
+			folio_unlock(ctx.cur_folio);
+	}
+}
+EXPORT_SYMBOL_GPL(iomap_readahead);
+
+/*
+ * iomap_is_partially_uptodate checks whether blocks within a folio are
+ * uptodate or not.
+ *
+ * Returns true if all blocks which correspond to the specified part
+ * of the folio are uptodate.
+ */
+bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count)
+{
+	struct iomap_folio_state *ifs = folio->private;
+	struct inode *inode = folio->mapping->host;
+	unsigned first, last, i;
+
+	if (!ifs)
+		return false;
+
+	/* Caller's range may extend past the end of this folio */
+	count = min(folio_size(folio) - from, count);
+
+	/* First and last blocks in range within folio */
+	first = from >> inode->i_blkbits;
+	last = (from + count - 1) >> inode->i_blkbits;
+
+	for (i = first; i <= last; i++)
+		if (!ifs_block_is_uptodate(ifs, i))
+			return false;
+	return true;
+}
+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, size_t len)
+{
+	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));
+}
+EXPORT_SYMBOL_GPL(iomap_get_folio);
+
+bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags)
+{
+	trace_iomap_release_folio(folio->mapping->host, folio_pos(folio),
+			folio_size(folio));
+
+	/*
+	 * 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))
+		return false;
+	ifs_free(folio);
+	return true;
+}
+EXPORT_SYMBOL_GPL(iomap_release_folio);
+
+void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len)
+{
+	trace_iomap_invalidate_folio(folio->mapping->host,
+					folio_pos(folio) + offset, len);
+
+	/*
+	 * If we're invalidating the entire folio, clear the dirty state
+	 * from it and release it to avoid unnecessary buildup of the LRU.
+	 */
+	if (offset == 0 && len == folio_size(folio)) {
+		WARN_ON_ONCE(folio_test_writeback(folio));
+		folio_cancel_dirty(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)
+{
+	loff_t i_size = i_size_read(inode);
+
+	/*
+	 * Only truncate newly allocated pages beyoned EOF, even if the
+	 * write started inside the existing inode size.
+	 */
+	if (pos + len > i_size)
+		truncate_pagecache_range(inode, max(pos, i_size),
+					 pos + len - 1);
+}
+
+static int iomap_read_folio_sync(loff_t block_start, struct folio *folio,
+		size_t poff, size_t plen, const struct iomap *iomap)
+{
+	struct bio_vec bvec;
+	struct bio bio;
+
+	bio_init(&bio, iomap->bdev, &bvec, 1, REQ_OP_READ);
+	bio.bi_iter.bi_sector = iomap_sector(iomap, block_start);
+	bio_add_folio_nofail(&bio, folio, plen, poff);
+	return submit_bio_wait(&bio);
+}
+
+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_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);
+	unsigned int nr_blocks = i_blocks_per_folio(iter->inode, folio);
+	size_t from = offset_in_folio(folio, pos), to = from + len;
+	size_t poff, plen;
+
+	/*
+	 * If the write or zeroing 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.
+	 * For the unshare case, we must read in the ondisk contents because we
+	 * are not changing pagecache contents.
+	 */
+	if (!(iter->flags & IOMAP_UNSHARE) && pos <= folio_pos(folio) &&
+	    pos + len >= folio_pos(folio) + folio_size(folio))
+		return 0;
+
+	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);
+		if (plen == 0)
+			break;
+
+		if (!(iter->flags & IOMAP_UNSHARE) &&
+		    (from <= poff || from >= poff + plen) &&
+		    (to <= poff || to >= poff + plen))
+			continue;
+
+		if (iomap_block_needs_zeroing(iter, block_start)) {
+			if (WARN_ON_ONCE(iter->flags & IOMAP_UNSHARE))
+				return -EIO;
+			folio_zero_segments(folio, poff, from, to, poff + plen);
+		} else {
+			int status;
+
+			if (iter->flags & IOMAP_NOWAIT)
+				return -EAGAIN;
+
+			status = iomap_read_folio_sync(block_start, folio,
+					poff, plen, srcmap);
+			if (status)
+				return status;
+		}
+		iomap_set_range_uptodate(folio, poff, plen);
+	} while ((block_start += plen) < block_end);
+
+	return 0;
+}
+
+static struct folio *__iomap_get_folio(struct iomap_iter *iter, loff_t pos,
+		size_t len)
+{
+	const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops;
+
+	if (folio_ops && folio_ops->get_folio)
+		return folio_ops->get_folio(iter, pos, len);
+	else
+		return iomap_get_folio(iter, pos, len);
+}
+
+static void __iomap_put_folio(struct iomap_iter *iter, loff_t pos, size_t ret,
+		struct folio *folio)
+{
+	const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops;
+
+	if (folio_ops && folio_ops->put_folio) {
+		folio_ops->put_folio(iter->inode, pos, ret, folio);
+	} else {
+		folio_unlock(folio);
+		folio_put(folio);
+	}
+}
+
+static int iomap_write_begin_inline(const struct iomap_iter *iter,
+		struct folio *folio)
+{
+	/* needs more work for the tailpacking case; disable for now */
+	if (WARN_ON_ONCE(iomap_iter_srcmap(iter)->offset != 0))
+		return -EIO;
+	return iomap_read_inline_data(iter, folio);
+}
+
+static int iomap_write_begin(struct iomap_iter *iter, loff_t pos,
+		size_t len, struct folio **foliop)
+{
+	const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops;
+	const struct iomap *srcmap = iomap_iter_srcmap(iter);
+	struct folio *folio;
+	int status = 0;
+
+	BUG_ON(pos + len > iter->iomap.offset + iter->iomap.length);
+	if (srcmap != &iter->iomap)
+		BUG_ON(pos + len > srcmap->offset + srcmap->length);
+
+	if (fatal_signal_pending(current))
+		return -EINTR;
+
+	if (!mapping_large_folio_support(iter->inode->i_mapping))
+		len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos));
+
+	folio = __iomap_get_folio(iter, pos, len);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
+
+	/*
+	 * Now we have a locked folio, before we do anything with it we need to
+	 * check that the iomap we have cached is not stale. The inode extent
+	 * mapping can change due to concurrent IO in flight (e.g.
+	 * IOMAP_UNWRITTEN state can change and memory reclaim could have
+	 * reclaimed a previously partially written page at this index after IO
+	 * completion before this write reaches this file offset) and hence we
+	 * could do the wrong thing here (zero a page range incorrectly or fail
+	 * to zero) and corrupt data.
+	 */
+	if (folio_ops && folio_ops->iomap_valid) {
+		bool iomap_valid = folio_ops->iomap_valid(iter->inode,
+							 &iter->iomap);
+		if (!iomap_valid) {
+			iter->iomap.flags |= IOMAP_F_STALE;
+			status = 0;
+			goto out_unlock;
+		}
+	}
+
+	if (pos + len > folio_pos(folio) + folio_size(folio))
+		len = folio_pos(folio) + folio_size(folio) - pos;
+
+	if (srcmap->type == IOMAP_INLINE)
+		status = iomap_write_begin_inline(iter, folio);
+	else if (srcmap->flags & IOMAP_F_BUFFER_HEAD)
+		status = __block_write_begin_int(folio, pos, len, NULL, srcmap);
+	else
+		status = __iomap_write_begin(iter, pos, len, folio);
+
+	if (unlikely(status))
+		goto out_unlock;
+
+	*foliop = folio;
+	return 0;
+
+out_unlock:
+	__iomap_put_folio(iter, pos, 0, folio);
+	iomap_write_failed(iter->inode, pos, len);
+
+	return status;
+}
+
+static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
+		size_t copied, struct folio *folio)
+{
+	flush_dcache_folio(folio);
+
+	/*
+	 * The blocks that were entirely written will now be uptodate, so we
+	 * don't have to worry about a read_folio reading them and overwriting a
+	 * partial write.  However, if we've encountered a short write and only
+	 * partially written into a block, it will not be marked uptodate, so a
+	 * read_folio might come in and destroy our partial write.
+	 *
+	 * Do the simplest thing and just treat any short write to a
+	 * non-uptodate page as a zero-length write, and force the caller to
+	 * redo the whole thing.
+	 */
+	if (unlikely(copied < len && !folio_test_uptodate(folio)))
+		return 0;
+	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;
+}
+
+static size_t iomap_write_end_inline(const struct iomap_iter *iter,
+		struct folio *folio, loff_t pos, size_t copied)
+{
+	const struct iomap *iomap = &iter->iomap;
+	void *addr;
+
+	WARN_ON_ONCE(!folio_test_uptodate(folio));
+	BUG_ON(!iomap_inline_data_valid(iomap));
+
+	flush_dcache_folio(folio);
+	addr = kmap_local_folio(folio, pos);
+	memcpy(iomap_inline_data(iomap, pos), addr, copied);
+	kunmap_local(addr);
+
+	mark_inode_dirty(iter->inode);
+	return copied;
+}
+
+/* Returns the number of bytes copied.  May be 0.  Cannot be an errno. */
+static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
+		size_t copied, struct folio *folio)
+{
+	const struct iomap *srcmap = iomap_iter_srcmap(iter);
+	loff_t old_size = iter->inode->i_size;
+	size_t ret;
+
+	if (srcmap->type == IOMAP_INLINE) {
+		ret = iomap_write_end_inline(iter, folio, pos, copied);
+	} else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
+		ret = block_write_end(NULL, iter->inode->i_mapping, pos, len,
+				copied, &folio->page, NULL);
+	} else {
+		ret = __iomap_write_end(iter->inode, pos, len, copied, folio);
+	}
+
+	/*
+	 * Update the in-memory inode size after copying the data into the page
+	 * cache.  It's up to the file system to write the updated size to disk,
+	 * preferably after I/O completion so that no stale data is exposed.
+	 */
+	if (pos + ret > old_size) {
+		i_size_write(iter->inode, pos + ret);
+		iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
+	}
+	__iomap_put_folio(iter, pos, ret, folio);
+
+	if (old_size < pos)
+		pagecache_isize_extended(iter->inode, old_size, pos);
+	if (ret < len)
+		iomap_write_failed(iter->inode, pos + ret, len - ret);
+	return ret;
+}
+
+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;
+	struct address_space *mapping = iter->inode->i_mapping;
+	unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0;
+
+	do {
+		struct folio *folio;
+		size_t offset;		/* Offset into folio */
+		size_t bytes;		/* Bytes to write to folio */
+		size_t copied;		/* Bytes copied from user */
+
+		bytes = iov_iter_count(i);
+retry:
+		offset = pos & (chunk - 1);
+		bytes = min(chunk - offset, bytes);
+		status = balance_dirty_pages_ratelimited_flags(mapping,
+							       bdp_flags);
+		if (unlikely(status))
+			break;
+
+		if (bytes > length)
+			bytes = length;
+
+		/*
+		 * Bring in the user page that we'll copy from _first_.
+		 * Otherwise there's a nasty deadlock on copying from the
+		 * same page as we're writing to, without it being marked
+		 * up-to-date.
+		 *
+		 * For async buffered writes the assumption is that the user
+		 * page has already been faulted in. This can be optimized by
+		 * faulting the user page.
+		 */
+		if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) {
+			status = -EFAULT;
+			break;
+		}
+
+		status = iomap_write_begin(iter, pos, bytes, &folio);
+		if (unlikely(status))
+			break;
+		if (iter->iomap.flags & IOMAP_F_STALE)
+			break;
+
+		offset = offset_in_folio(folio, pos);
+		if (bytes > folio_size(folio) - offset)
+			bytes = folio_size(folio) - offset;
+
+		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))
+			iov_iter_revert(i, copied - status);
+
+		cond_resched();
+		if (unlikely(status == 0)) {
+			/*
+			 * A short copy made iomap_write_end() reject the
+			 * thing entirely.  Might be memory poisoning
+			 * halfway through, might be a race with munmap,
+			 * might be severe memory pressure.
+			 */
+			if (chunk > PAGE_SIZE)
+				chunk /= 2;
+			if (copied) {
+				bytes = copied;
+				goto retry;
+			}
+		} else {
+			pos += status;
+			written += status;
+			length -= status;
+		}
+	} while (iov_iter_count(i) && length);
+
+	if (status == -EAGAIN) {
+		iov_iter_revert(i, written);
+		return -EAGAIN;
+	}
+	return written ? written : status;
+}
+
+ssize_t
+iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
+		const struct iomap_ops *ops)
+{
+	struct iomap_iter iter = {
+		.inode		= iocb->ki_filp->f_mapping->host,
+		.pos		= iocb->ki_pos,
+		.len		= iov_iter_count(i),
+		.flags		= IOMAP_WRITE,
+	};
+	ssize_t ret;
+
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		iter.flags |= IOMAP_NOWAIT;
+
+	while ((ret = iomap_iter(&iter, ops)) > 0)
+		iter.processed = iomap_write_iter(&iter, i);
+
+	if (unlikely(iter.pos == iocb->ki_pos))
+		return ret;
+	ret = iter.pos - iocb->ki_pos;
+	iocb->ki_pos = iter.pos;
+	return ret;
+}
+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 preceding range and update the offset from which
+ * the next punch will start from.
+ *
+ * We can punch out storage reservations under clean pages because they either
+ * contain data that has been written back - in which case the delalloc punch
+ * over that range is a no-op - or they have been read faults in which case they
+ * contain zeroes and we can remove the delalloc backing range and any new
+ * writes to those pages will do the normal hole filling operation...
+ *
+ * This makes the logic simple: we only need to keep the delalloc extents only
+ * over the dirty ranges of the page cache.
+ *
+ * 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,
+		loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte,
+		iomap_punch_t punch)
+{
+	while (start_byte < end_byte) {
+		struct folio	*folio;
+		int ret;
+
+		/* grab locked page */
+		folio = filemap_lock_folio(inode->i_mapping,
+				start_byte >> PAGE_SHIFT);
+		if (IS_ERR(folio)) {
+			start_byte = ALIGN_DOWN(start_byte, PAGE_SIZE) +
+					PAGE_SIZE;
+			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;
+		}
+
+		/* 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;
+}
+
+/*
+ * Punch out all the delalloc blocks in the range given except for those that
+ * have dirty data still pending in the page cache - those are going to be
+ * written and so must still retain the delalloc backing for writeback.
+ *
+ * As we are scanning the page cache for data, we don't need to reimplement the
+ * wheel - mapping_seek_hole_data() does exactly what we need to identify the
+ * start and end of data ranges correctly even for sub-folio block sizes. This
+ * byte range based iteration is especially convenient because it means we
+ * don't have to care about variable size folios, nor where the start or end of
+ * the data range lies within a folio, if they lie within the same folio or even
+ * if there are multiple discontiguous data ranges within the folio.
+ *
+ * It should be noted that mapping_seek_hole_data() is not aware of EOF, and so
+ * can return data ranges that exist in the cache beyond EOF. e.g. a page fault
+ * spanning EOF will initialise the post-EOF data to zeroes and mark it up to
+ * date. A write page fault can then mark it dirty. If we then fail a write()
+ * beyond EOF into that up to date cached range, we allocate a delalloc block
+ * beyond EOF and then have to punch it out. Because the range is up to date,
+ * mapping_seek_hole_data() will return it, and we will skip the punch because
+ * the folio is dirty. THis is incorrect - we always need to punch out delalloc
+ * beyond EOF in this case as writeback will never write back and covert that
+ * delalloc block beyond EOF. Hence we limit the cached data scan range to EOF,
+ * resulting in always punching out the range from the EOF to the end of the
+ * range the iomap spans.
+ *
+ * Intervals are of the form [start_byte, end_byte) (i.e. open ended) because it
+ * matches the intervals returned by mapping_seek_hole_data(). i.e. SEEK_DATA
+ * returns the start of a data range (start_byte), and SEEK_HOLE(start_byte)
+ * returns the end of the data range (data_end). Using closed intervals would
+ * 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)
+{
+	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
+	 * folios and dirtying them via ->page_mkwrite whilst we walk the
+	 * cache and perform delalloc extent removal. Failing to do this can
+	 * leave dirty pages with no space reservation in the cache.
+	 */
+	filemap_invalidate_lock(inode->i_mapping);
+	while (start_byte < scan_end_byte) {
+		loff_t		data_end;
+
+		start_byte = mapping_seek_hole_data(inode->i_mapping,
+				start_byte, scan_end_byte, SEEK_DATA);
+		/*
+		 * If there is no more data to scan, all that is left is to
+		 * punch out the remaining range.
+		 */
+		if (start_byte == -ENXIO || start_byte == scan_end_byte)
+			break;
+		if (start_byte < 0) {
+			error = start_byte;
+			goto out_unlock;
+		}
+		WARN_ON_ONCE(start_byte < punch_start_byte);
+		WARN_ON_ONCE(start_byte > scan_end_byte);
+
+		/*
+		 * We find the end of this contiguous cached data range by
+		 * seeking from start_byte to the beginning of the next hole.
+		 */
+		data_end = mapping_seek_hole_data(inode->i_mapping, start_byte,
+				scan_end_byte, SEEK_HOLE);
+		if (data_end < 0) {
+			error = data_end;
+			goto out_unlock;
+		}
+		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;
+
+		/* 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);
+out_unlock:
+	filemap_invalidate_unlock(inode->i_mapping);
+	return error;
+}
+
+/*
+ * When a short write occurs, the filesystem may need to remove reserved space
+ * that was allocated in ->iomap_begin from it's ->iomap_end method. For
+ * filesystems that use delayed allocation, we need to punch out delalloc
+ * extents from the range that are not dirty in the page cache. As the write can
+ * race with page faults, there can be dirty pages over the delalloc extent
+ * outside the range of a short write but still within the delalloc extent
+ * allocated for this iomap.
+ *
+ * This function uses [start_byte, end_byte) intervals (i.e. open ended) to
+ * simplify range iterations.
+ *
+ * The punch() callback *must* only punch delalloc extents in the range passed
+ * to it. It must skip over all other types of extents in the range and leave
+ * them completely unchanged. It must do this punch atomically with respect to
+ * other extent modifications.
+ *
+ * The punch() callback may be called with a folio locked to prevent writeback
+ * extent allocation racing at the edge of the range we are currently punching.
+ * The locked folio may or may not cover the range being punched, so it is not
+ * safe for the punch() callback to lock folios itself.
+ *
+ * Lock order is:
+ *
+ * inode->i_rwsem (shared or exclusive)
+ *   inode->i_mapping->invalidate_lock (exclusive)
+ *     folio_lock()
+ *       ->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)
+{
+	loff_t			start_byte;
+	loff_t			end_byte;
+	unsigned int		blocksize = i_blocksize(inode);
+
+	if (iomap->type != IOMAP_DELALLOC)
+		return 0;
+
+	/* If we didn't reserve the blocks, we're not allowed to punch them. */
+	if (!(iomap->flags & IOMAP_F_NEW))
+		return 0;
+
+	/*
+	 * start_byte refers to the first unused block after a short write. If
+	 * nothing was written, round offset down to point at the first block in
+	 * the range.
+	 */
+	if (unlikely(!written))
+		start_byte = round_down(pos, blocksize);
+	else
+		start_byte = round_up(pos + written, blocksize);
+	end_byte = round_up(pos + length, blocksize);
+
+	/* Nothing to do if we've written the entire delalloc extent */
+	if (start_byte >= end_byte)
+		return 0;
+
+	return iomap_write_delalloc_release(inode, start_byte, end_byte,
+					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 */
+	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)
+		return length;
+
+	do {
+		struct folio *folio;
+		int status;
+		size_t offset;
+		size_t bytes = min_t(u64, SIZE_MAX, length);
+
+		status = iomap_write_begin(iter, pos, bytes, &folio);
+		if (unlikely(status))
+			return status;
+		if (iomap->flags & IOMAP_F_STALE)
+			break;
+
+		offset = offset_in_folio(folio, pos);
+		if (bytes > folio_size(folio) - offset)
+			bytes = folio_size(folio) - offset;
+
+		bytes = iomap_write_end(iter, pos, bytes, bytes, folio);
+		if (WARN_ON_ONCE(bytes == 0))
+			return -EIO;
+
+		cond_resched();
+
+		pos += bytes;
+		written += bytes;
+		length -= bytes;
+
+		balance_dirty_pages_ratelimited(iter->inode->i_mapping);
+	} while (length > 0);
+
+	return written;
+}
+
+int
+iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
+		const struct iomap_ops *ops)
+{
+	struct iomap_iter iter = {
+		.inode		= inode,
+		.pos		= pos,
+		.len		= len,
+		.flags		= IOMAP_WRITE | IOMAP_UNSHARE,
+	};
+	int ret;
+
+	while ((ret = iomap_iter(&iter, ops)) > 0)
+		iter.processed = iomap_unshare_iter(&iter);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iomap_file_unshare);
+
+static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
+{
+	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)
+		return length;
+
+	do {
+		struct folio *folio;
+		int status;
+		size_t offset;
+		size_t bytes = min_t(u64, SIZE_MAX, length);
+
+		status = iomap_write_begin(iter, pos, bytes, &folio);
+		if (status)
+			return status;
+		if (iter->iomap.flags & IOMAP_F_STALE)
+			break;
+
+		offset = offset_in_folio(folio, pos);
+		if (bytes > folio_size(folio) - offset)
+			bytes = folio_size(folio) - offset;
+
+		folio_zero_range(folio, offset, bytes);
+		folio_mark_accessed(folio);
+
+		bytes = iomap_write_end(iter, pos, bytes, bytes, folio);
+		if (WARN_ON_ONCE(bytes == 0))
+			return -EIO;
+
+		pos += bytes;
+		length -= bytes;
+		written += bytes;
+	} while (length > 0);
+
+	if (did_zero)
+		*did_zero = true;
+	return written;
+}
+
+int
+iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
+		const struct iomap_ops *ops)
+{
+	struct iomap_iter iter = {
+		.inode		= inode,
+		.pos		= pos,
+		.len		= len,
+		.flags		= IOMAP_ZERO,
+	};
+	int ret;
+
+	while ((ret = iomap_iter(&iter, ops)) > 0)
+		iter.processed = iomap_zero_iter(&iter, did_zero);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iomap_zero_range);
+
+int
+iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
+		const struct iomap_ops *ops)
+{
+	unsigned int blocksize = i_blocksize(inode);
+	unsigned int off = pos & (blocksize - 1);
+
+	/* Block boundary? Nothing to do */
+	if (!off)
+		return 0;
+	return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops);
+}
+EXPORT_SYMBOL_GPL(iomap_truncate_page);
+
+static loff_t iomap_folio_mkwrite_iter(struct iomap_iter *iter,
+		struct folio *folio)
+{
+	loff_t length = iomap_length(iter);
+	int ret;
+
+	if (iter->iomap.flags & IOMAP_F_BUFFER_HEAD) {
+		ret = __block_write_begin_int(folio, iter->pos, length, NULL,
+					      &iter->iomap);
+		if (ret)
+			return ret;
+		block_commit_write(&folio->page, 0, length);
+	} else {
+		WARN_ON_ONCE(!folio_test_uptodate(folio));
+		folio_mark_dirty(folio);
+	}
+
+	return length;
+}
+
+vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
+{
+	struct iomap_iter iter = {
+		.inode		= file_inode(vmf->vma->vm_file),
+		.flags		= IOMAP_WRITE | IOMAP_FAULT,
+	};
+	struct folio *folio = page_folio(vmf->page);
+	ssize_t ret;
+
+	folio_lock(folio);
+	ret = folio_mkwrite_check_truncate(folio, iter.inode);
+	if (ret < 0)
+		goto out_unlock;
+	iter.pos = folio_pos(folio);
+	iter.len = ret;
+	while ((ret = iomap_iter(&iter, ops)) > 0)
+		iter.processed = iomap_folio_mkwrite_iter(&iter, folio);
+
+	if (ret < 0)
+		goto out_unlock;
+	folio_wait_stable(folio);
+	return VM_FAULT_LOCKED;
+out_unlock:
+	folio_unlock(folio);
+	return vmf_fs_error(ret);
+}
+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_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 && !ifs);
+	WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) <= 0);
+
+	if (!ifs || atomic_sub_and_test(len, &ifs->write_bytes_pending))
+		folio_end_writeback(folio);
+}
+
+/*
+ * We're now finished for good with this ioend structure.  Update the page
+ * state, release holds on bios, and finally free up memory.  Do not use the
+ * ioend after this.
+ */
+static u32
+iomap_finish_ioend(struct iomap_ioend *ioend, int error)
+{
+	struct inode *inode = ioend->io_inode;
+	struct bio *bio = &ioend->io_inline_bio;
+	struct bio *last = ioend->io_bio, *next;
+	u64 start = bio->bi_iter.bi_sector;
+	loff_t offset = ioend->io_offset;
+	bool quiet = bio_flagged(bio, BIO_QUIET);
+	u32 folio_count = 0;
+
+	for (bio = &ioend->io_inline_bio; bio; bio = next) {
+		struct folio_iter fi;
+
+		/*
+		 * For the last bio, bi_private points to the ioend, so we
+		 * need to explicitly end the iteration here.
+		 */
+		if (bio == last)
+			next = NULL;
+		else
+			next = bio->bi_private;
+
+		/* walk all folios in bio, ending page IO on them */
+		bio_for_each_folio_all(fi, bio) {
+			iomap_finish_folio_write(inode, fi.folio, fi.length,
+					error);
+			folio_count++;
+		}
+		bio_put(bio);
+	}
+	/* The ioend has been freed by bio_put() */
+
+	if (unlikely(error && !quiet)) {
+		printk_ratelimited(KERN_ERR
+"%s: writeback error on inode %lu, offset %lld, sector %llu",
+			inode->i_sb->s_id, inode->i_ino, offset, start);
+	}
+	return folio_count;
+}
+
+/*
+ * Ioend completion routine for merged bios. This can only be called from task
+ * contexts as merged ioends can be of unbound length. Hence we have to break up
+ * the writeback completions into manageable chunks to avoid long scheduler
+ * holdoffs. We aim to keep scheduler holdoffs down below 10ms so that we get
+ * good batch processing throughput without creating adverse scheduler latency
+ * conditions.
+ */
+void
+iomap_finish_ioends(struct iomap_ioend *ioend, int error)
+{
+	struct list_head tmp;
+	u32 completions;
+
+	might_sleep();
+
+	list_replace_init(&ioend->io_list, &tmp);
+	completions = iomap_finish_ioend(ioend, error);
+
+	while (!list_empty(&tmp)) {
+		if (completions > IOEND_BATCH_SIZE * 8) {
+			cond_resched();
+			completions = 0;
+		}
+		ioend = list_first_entry(&tmp, struct iomap_ioend, io_list);
+		list_del_init(&ioend->io_list);
+		completions += iomap_finish_ioend(ioend, error);
+	}
+}
+EXPORT_SYMBOL_GPL(iomap_finish_ioends);
+
+/*
+ * We can merge two adjacent ioends if they have the same set of work to do.
+ */
+static bool
+iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next)
+{
+	if (ioend->io_bio->bi_status != next->io_bio->bi_status)
+		return false;
+	if ((ioend->io_flags & IOMAP_F_SHARED) ^
+	    (next->io_flags & IOMAP_F_SHARED))
+		return false;
+	if ((ioend->io_type == IOMAP_UNWRITTEN) ^
+	    (next->io_type == IOMAP_UNWRITTEN))
+		return false;
+	if (ioend->io_offset + ioend->io_size != next->io_offset)
+		return false;
+	/*
+	 * Do not merge physically discontiguous ioends. The filesystem
+	 * completion functions will have to iterate the physical
+	 * discontiguities even if we merge the ioends at a logical level, so
+	 * we don't gain anything by merging physical discontiguities here.
+	 *
+	 * We cannot use bio->bi_iter.bi_sector here as it is modified during
+	 * submission so does not point to the start sector of the bio at
+	 * completion.
+	 */
+	if (ioend->io_sector + (ioend->io_size >> 9) != next->io_sector)
+		return false;
+	return true;
+}
+
+void
+iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends)
+{
+	struct iomap_ioend *next;
+
+	INIT_LIST_HEAD(&ioend->io_list);
+
+	while ((next = list_first_entry_or_null(more_ioends, struct iomap_ioend,
+			io_list))) {
+		if (!iomap_ioend_can_merge(ioend, next))
+			break;
+		list_move_tail(&next->io_list, &ioend->io_list);
+		ioend->io_size += next->io_size;
+	}
+}
+EXPORT_SYMBOL_GPL(iomap_ioend_try_merge);
+
+static int
+iomap_ioend_compare(void *priv, const struct list_head *a,
+		const struct list_head *b)
+{
+	struct iomap_ioend *ia = container_of(a, struct iomap_ioend, io_list);
+	struct iomap_ioend *ib = container_of(b, struct iomap_ioend, io_list);
+
+	if (ia->io_offset < ib->io_offset)
+		return -1;
+	if (ia->io_offset > ib->io_offset)
+		return 1;
+	return 0;
+}
+
+void
+iomap_sort_ioends(struct list_head *ioend_list)
+{
+	list_sort(NULL, ioend_list, iomap_ioend_compare);
+}
+EXPORT_SYMBOL_GPL(iomap_sort_ioends);
+
+static void iomap_writepage_end_bio(struct bio *bio)
+{
+	struct iomap_ioend *ioend = bio->bi_private;
+
+	iomap_finish_ioend(ioend, blk_status_to_errno(bio->bi_status));
+}
+
+/*
+ * Submit the final bio for an ioend.
+ *
+ * If @error is non-zero, it means that we have a situation where some part of
+ * the submission process has failed after we've marked pages for writeback
+ * and unlocked them.  In this situation, we need to fail the bio instead of
+ * submitting it.  This typically only happens on a filesystem shutdown.
+ */
+static int
+iomap_submit_ioend(struct iomap_writepage_ctx *wpc, struct iomap_ioend *ioend,
+		int error)
+{
+	ioend->io_bio->bi_private = ioend;
+	ioend->io_bio->bi_end_io = iomap_writepage_end_bio;
+
+	if (wpc->ops->prepare_ioend)
+		error = wpc->ops->prepare_ioend(ioend, error);
+	if (error) {
+		/*
+		 * If we're failing the IO now, just mark the ioend with an
+		 * error and finish it.  This will run IO completion immediately
+		 * as there is only one reference to the ioend at this point in
+		 * time.
+		 */
+		ioend->io_bio->bi_status = errno_to_blk_status(error);
+		bio_endio(ioend->io_bio);
+		return error;
+	}
+
+	submit_bio(ioend->io_bio);
+	return 0;
+}
+
+static struct iomap_ioend *
+iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc,
+		loff_t offset, sector_t sector, struct writeback_control *wbc)
+{
+	struct iomap_ioend *ioend;
+	struct bio *bio;
+
+	bio = bio_alloc_bioset(wpc->iomap.bdev, BIO_MAX_VECS,
+			       REQ_OP_WRITE | wbc_to_write_flags(wbc),
+			       GFP_NOFS, &iomap_ioend_bioset);
+	bio->bi_iter.bi_sector = sector;
+	wbc_init_bio(wbc, bio);
+
+	ioend = container_of(bio, struct iomap_ioend, io_inline_bio);
+	INIT_LIST_HEAD(&ioend->io_list);
+	ioend->io_type = wpc->iomap.type;
+	ioend->io_flags = wpc->iomap.flags;
+	ioend->io_inode = inode;
+	ioend->io_size = 0;
+	ioend->io_folios = 0;
+	ioend->io_offset = offset;
+	ioend->io_bio = bio;
+	ioend->io_sector = sector;
+	return ioend;
+}
+
+/*
+ * Allocate a new bio, and chain the old bio to the new one.
+ *
+ * Note that we have to perform the chaining in this unintuitive order
+ * so that the bi_private linkage is set up in the right direction for the
+ * traversal in iomap_finish_ioend().
+ */
+static struct bio *
+iomap_chain_bio(struct bio *prev)
+{
+	struct bio *new;
+
+	new = bio_alloc(prev->bi_bdev, BIO_MAX_VECS, prev->bi_opf, GFP_NOFS);
+	bio_clone_blkg_association(new, prev);
+	new->bi_iter.bi_sector = bio_end_sector(prev);
+
+	bio_chain(prev, new);
+	bio_get(prev);		/* for iomap_finish_ioend */
+	submit_bio(prev);
+	return new;
+}
+
+static bool
+iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset,
+		sector_t sector)
+{
+	if ((wpc->iomap.flags & IOMAP_F_SHARED) !=
+	    (wpc->ioend->io_flags & IOMAP_F_SHARED))
+		return false;
+	if (wpc->iomap.type != wpc->ioend->io_type)
+		return false;
+	if (offset != wpc->ioend->io_offset + wpc->ioend->io_size)
+		return false;
+	if (sector != bio_end_sector(wpc->ioend->io_bio))
+		return false;
+	/*
+	 * Limit ioend bio chain lengths to minimise IO completion latency. This
+	 * also prevents long tight loops ending page writeback on all the
+	 * folios in the ioend.
+	 */
+	if (wpc->ioend->io_folios >= IOEND_BATCH_SIZE)
+		return false;
+	return true;
+}
+
+/*
+ * Test to see if we have an existing ioend structure that we could append to
+ * first; otherwise finish off the current ioend and start another.
+ */
+static void
+iomap_add_to_ioend(struct inode *inode, loff_t pos, struct folio *folio,
+		struct iomap_folio_state *ifs, struct iomap_writepage_ctx *wpc,
+		struct writeback_control *wbc, struct list_head *iolist)
+{
+	sector_t sector = iomap_sector(&wpc->iomap, pos);
+	unsigned len = i_blocksize(inode);
+	size_t poff = offset_in_folio(folio, pos);
+
+	if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos, sector)) {
+		if (wpc->ioend)
+			list_add(&wpc->ioend->io_list, iolist);
+		wpc->ioend = iomap_alloc_ioend(inode, wpc, pos, sector, wbc);
+	}
+
+	if (!bio_add_folio(wpc->ioend->io_bio, folio, len, poff)) {
+		wpc->ioend->io_bio = iomap_chain_bio(wpc->ioend->io_bio);
+		bio_add_folio_nofail(wpc->ioend->io_bio, folio, len, poff);
+	}
+
+	if (ifs)
+		atomic_add(len, &ifs->write_bytes_pending);
+	wpc->ioend->io_size += len;
+	wbc_account_cgroup_owner(wbc, &folio->page, len);
+}
+
+/*
+ * We implement an immediate ioend submission policy here to avoid needing to
+ * chain multiple ioends and hence nest mempool allocations which can violate
+ * the forward progress guarantees we need to provide. The current ioend we're
+ * adding blocks to is cached in the writepage context, and if the new block
+ * doesn't append to the cached ioend, it will create a new ioend and cache that
+ * instead.
+ *
+ * If a new ioend is created and cached, the old ioend is returned and queued
+ * locally for submission once the entire page is processed or an error has been
+ * detected.  While ioends are submitted immediately after they are completed,
+ * batching optimisations are provided by higher level block plugging.
+ *
+ * At the end of a writeback pass, there will be a cached ioend remaining on the
+ * writepage context that the caller will need to submit.
+ */
+static int
+iomap_writepage_map(struct iomap_writepage_ctx *wpc,
+		struct writeback_control *wbc, struct inode *inode,
+		struct folio *folio, u64 end_pos)
+{
+	struct iomap_folio_state *ifs = folio->private;
+	struct iomap_ioend *ioend, *next;
+	unsigned len = i_blocksize(inode);
+	unsigned nblocks = i_blocks_per_folio(inode, folio);
+	u64 pos = folio_pos(folio);
+	int error = 0, count = 0, i;
+	LIST_HEAD(submit_list);
+
+	WARN_ON_ONCE(end_pos <= pos);
+
+	if (!ifs && nblocks > 1) {
+		ifs = ifs_alloc(inode, folio, 0);
+		iomap_set_range_dirty(folio, 0, end_pos - pos);
+	}
+
+	WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) != 0);
+
+	/*
+	 * Walk through the folio to find areas to write back. If we
+	 * run off the end of the current map or find the current map
+	 * invalid, grab a new one.
+	 */
+	for (i = 0; i < nblocks && pos < end_pos; i++, pos += len) {
+		if (ifs && !ifs_block_is_dirty(folio, ifs, i))
+			continue;
+
+		error = wpc->ops->map_blocks(wpc, inode, pos);
+		if (error)
+			break;
+		trace_iomap_writepage_map(inode, &wpc->iomap);
+		if (WARN_ON_ONCE(wpc->iomap.type == IOMAP_INLINE))
+			continue;
+		if (wpc->iomap.type == IOMAP_HOLE)
+			continue;
+		iomap_add_to_ioend(inode, pos, folio, ifs, wpc, wbc,
+				 &submit_list);
+		count++;
+	}
+	if (count)
+		wpc->ioend->io_folios++;
+
+	WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list));
+	WARN_ON_ONCE(!folio_test_locked(folio));
+	WARN_ON_ONCE(folio_test_writeback(folio));
+	WARN_ON_ONCE(folio_test_dirty(folio));
+
+	/*
+	 * We cannot cancel the ioend directly here on error.  We may have
+	 * already set other pages under writeback and hence we have to run I/O
+	 * completion to mark the error state of the pages under writeback
+	 * appropriately.
+	 */
+	if (unlikely(error)) {
+		/*
+		 * Let the filesystem know what portion of the current page
+		 * failed to map. If the page hasn't been added to ioend, it
+		 * won't be affected by I/O completion and we must unlock it
+		 * now.
+		 */
+		if (wpc->ops->discard_folio)
+			wpc->ops->discard_folio(folio, pos);
+		if (!count) {
+			folio_unlock(folio);
+			goto done;
+		}
+	}
+
+	/*
+	 * We can have dirty bits set past end of file in page_mkwrite path
+	 * while mapping the last partial folio. Hence it's better to clear
+	 * all the dirty bits in the folio here.
+	 */
+	iomap_clear_range_dirty(folio, 0, folio_size(folio));
+	folio_start_writeback(folio);
+	folio_unlock(folio);
+
+	/*
+	 * Preserve the original error if there was one; catch
+	 * submission errors here and propagate into subsequent ioend
+	 * submissions.
+	 */
+	list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
+		int error2;
+
+		list_del_init(&ioend->io_list);
+		error2 = iomap_submit_ioend(wpc, ioend, error);
+		if (error2 && !error)
+			error = error2;
+	}
+
+	/*
+	 * We can end up here with no error and nothing to write only if we race
+	 * with a partial page truncate on a sub-page block sized filesystem.
+	 */
+	if (!count)
+		folio_end_writeback(folio);
+done:
+	mapping_set_error(inode->i_mapping, error);
+	return error;
+}
+
+/*
+ * Write out a dirty page.
+ *
+ * For delalloc space on the page, we need to allocate space and flush it.
+ * For unwritten space on the page, we need to start the conversion to
+ * regular allocated space.
+ */
+static int iomap_do_writepage(struct folio *folio,
+		struct writeback_control *wbc, void *data)
+{
+	struct iomap_writepage_ctx *wpc = data;
+	struct inode *inode = folio->mapping->host;
+	u64 end_pos, isize;
+
+	trace_iomap_writepage(inode, folio_pos(folio), folio_size(folio));
+
+	/*
+	 * Refuse to write the folio out if we're called from reclaim context.
+	 *
+	 * This avoids stack overflows when called from deeply used stacks in
+	 * random callers for direct reclaim or memcg reclaim.  We explicitly
+	 * allow reclaim from kswapd as the stack usage there is relatively low.
+	 *
+	 * This should never happen except in the case of a VM regression so
+	 * warn about it.
+	 */
+	if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
+			PF_MEMALLOC))
+		goto redirty;
+
+	/*
+	 * Is this folio beyond the end of the file?
+	 *
+	 * The folio index is less than the end_index, adjust the end_pos
+	 * to the highest offset that this folio should represent.
+	 * -----------------------------------------------------
+	 * |			file mapping	       | <EOF> |
+	 * -----------------------------------------------------
+	 * | Page ... | Page N-2 | Page N-1 |  Page N  |       |
+	 * ^--------------------------------^----------|--------
+	 * |     desired writeback range    |      see else    |
+	 * ---------------------------------^------------------|
+	 */
+	isize = i_size_read(inode);
+	end_pos = folio_pos(folio) + folio_size(folio);
+	if (end_pos > isize) {
+		/*
+		 * Check whether the page to write out is beyond or straddles
+		 * i_size or not.
+		 * -------------------------------------------------------
+		 * |		file mapping		        | <EOF>  |
+		 * -------------------------------------------------------
+		 * | Page ... | Page N-2 | Page N-1 |  Page N   | Beyond |
+		 * ^--------------------------------^-----------|---------
+		 * |				    |      Straddles     |
+		 * ---------------------------------^-----------|--------|
+		 */
+		size_t poff = offset_in_folio(folio, isize);
+		pgoff_t end_index = isize >> PAGE_SHIFT;
+
+		/*
+		 * Skip the page if it's fully outside i_size, e.g.
+		 * due to a truncate operation that's in progress.  We've
+		 * cleaned this page and truncate will finish things off for
+		 * us.
+		 *
+		 * Note that the end_index is unsigned long.  If the given
+		 * offset is greater than 16TB on a 32-bit system then if we
+		 * checked if the page is fully outside i_size with
+		 * "if (page->index >= end_index + 1)", "end_index + 1" would
+		 * overflow and evaluate to 0.  Hence this page would be
+		 * redirtied and written out repeatedly, which would result in
+		 * an infinite loop; the user program performing this operation
+		 * would hang.  Instead, we can detect this situation by
+		 * checking if the page is totally beyond i_size or if its
+		 * offset is just equal to the EOF.
+		 */
+		if (folio->index > end_index ||
+		    (folio->index == end_index && poff == 0))
+			goto unlock;
+
+		/*
+		 * The page straddles i_size.  It must be zeroed out on each
+		 * and every writepage invocation because it may be mmapped.
+		 * "A file is mapped in multiples of the page size.  For a file
+		 * that is not a multiple of the page size, the remaining
+		 * memory is zeroed when mapped, and writes to that region are
+		 * not written out to the file."
+		 */
+		folio_zero_segment(folio, poff, folio_size(folio));
+		end_pos = isize;
+	}
+
+	return iomap_writepage_map(wpc, wbc, inode, folio, end_pos);
+
+redirty:
+	folio_redirty_for_writepage(wbc, folio);
+unlock:
+	folio_unlock(folio);
+	return 0;
+}
+
+int
+iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
+		struct iomap_writepage_ctx *wpc,
+		const struct iomap_writeback_ops *ops)
+{
+	int			ret;
+
+	wpc->ops = ops;
+	ret = write_cache_pages(mapping, wbc, iomap_do_writepage, wpc);
+	if (!wpc->ioend)
+		return ret;
+	return iomap_submit_ioend(wpc, wpc->ioend, ret);
+}
+EXPORT_SYMBOL_GPL(iomap_writepages);
+
+static int __init iomap_init(void)
+{
+	return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
+			   offsetof(struct iomap_ioend, io_inline_bio),
+			   BIOSET_NEED_BVECS);
+}
+fs_initcall(iomap_init);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
new file mode 100644
index 0000000000..bcd3f8cf5e
--- /dev/null
+++ b/fs/iomap/direct-io.c
@@ -0,0 +1,754 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2010 Red Hat, Inc.
+ * Copyright (c) 2016-2021 Christoph Hellwig.
+ */
+#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/fscrypt.h>
+#include <linux/pagemap.h>
+#include <linux/iomap.h>
+#include <linux/backing-dev.h>
+#include <linux/uio.h>
+#include <linux/task_io_accounting_ops.h>
+#include "trace.h"
+
+#include "../internal.h"
+
+/*
+ * Private flags for iomap_dio, must not overlap with the public ones in
+ * iomap.h:
+ */
+#define IOMAP_DIO_CALLER_COMP	(1U << 26)
+#define IOMAP_DIO_INLINE_COMP	(1U << 27)
+#define IOMAP_DIO_WRITE_THROUGH	(1U << 28)
+#define IOMAP_DIO_NEED_SYNC	(1U << 29)
+#define IOMAP_DIO_WRITE		(1U << 30)
+#define IOMAP_DIO_DIRTY		(1U << 31)
+
+struct iomap_dio {
+	struct kiocb		*iocb;
+	const struct iomap_dio_ops *dops;
+	loff_t			i_size;
+	loff_t			size;
+	atomic_t		ref;
+	unsigned		flags;
+	int			error;
+	size_t			done_before;
+	bool			wait_for_completion;
+
+	union {
+		/* used during submission and for synchronous completion: */
+		struct {
+			struct iov_iter		*iter;
+			struct task_struct	*waiter;
+		} submit;
+
+		/* used for aio completion: */
+		struct {
+			struct work_struct	work;
+		} aio;
+	};
+};
+
+static struct bio *iomap_dio_alloc_bio(const struct iomap_iter *iter,
+		struct iomap_dio *dio, unsigned short nr_vecs, blk_opf_t opf)
+{
+	if (dio->dops && dio->dops->bio_set)
+		return bio_alloc_bioset(iter->iomap.bdev, nr_vecs, opf,
+					GFP_KERNEL, dio->dops->bio_set);
+	return bio_alloc(iter->iomap.bdev, nr_vecs, opf, GFP_KERNEL);
+}
+
+static void iomap_dio_submit_bio(const struct iomap_iter *iter,
+		struct iomap_dio *dio, struct bio *bio, loff_t pos)
+{
+	struct kiocb *iocb = dio->iocb;
+
+	atomic_inc(&dio->ref);
+
+	/* Sync dio can't be polled reliably */
+	if ((iocb->ki_flags & IOCB_HIPRI) && !is_sync_kiocb(iocb)) {
+		bio_set_polled(bio, iocb);
+		WRITE_ONCE(iocb->private, bio);
+	}
+
+	if (dio->dops && dio->dops->submit_io)
+		dio->dops->submit_io(iter, bio, pos);
+	else
+		submit_bio(bio);
+}
+
+ssize_t iomap_dio_complete(struct iomap_dio *dio)
+{
+	const struct iomap_dio_ops *dops = dio->dops;
+	struct kiocb *iocb = dio->iocb;
+	loff_t offset = iocb->ki_pos;
+	ssize_t ret = dio->error;
+
+	if (dops && dops->end_io)
+		ret = dops->end_io(iocb, dio->size, ret, dio->flags);
+
+	if (likely(!ret)) {
+		ret = dio->size;
+		/* check for short read */
+		if (offset + ret > dio->i_size &&
+		    !(dio->flags & IOMAP_DIO_WRITE))
+			ret = dio->i_size - offset;
+	}
+
+	/*
+	 * Try again to invalidate clean pages which might have been cached by
+	 * non-direct readahead, or faulted in by get_user_pages() if the source
+	 * of the write was an mmap'ed region of the file we're writing.  Either
+	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
+	 * this invalidation fails, tough, the write still worked...
+	 *
+	 * And this page cache invalidation has to be after ->end_io(), as some
+	 * filesystems convert unwritten extents to real allocations in
+	 * ->end_io() when necessary, otherwise a racing buffer read would cache
+	 * zeros from unwritten extents.
+	 */
+	if (!dio->error && dio->size && (dio->flags & IOMAP_DIO_WRITE))
+		kiocb_invalidate_post_direct_write(iocb, dio->size);
+
+	inode_dio_end(file_inode(iocb->ki_filp));
+
+	if (ret > 0) {
+		iocb->ki_pos += ret;
+
+		/*
+		 * If this is a DSYNC write, make sure we push it to stable
+		 * storage now that we've written data.
+		 */
+		if (dio->flags & IOMAP_DIO_NEED_SYNC)
+			ret = generic_write_sync(iocb, ret);
+		if (ret > 0)
+			ret += dio->done_before;
+	}
+	trace_iomap_dio_complete(iocb, dio->error, ret);
+	kfree(dio);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iomap_dio_complete);
+
+static ssize_t iomap_dio_deferred_complete(void *data)
+{
+	return iomap_dio_complete(data);
+}
+
+static void iomap_dio_complete_work(struct work_struct *work)
+{
+	struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work);
+	struct kiocb *iocb = dio->iocb;
+
+	iocb->ki_complete(iocb, iomap_dio_complete(dio));
+}
+
+/*
+ * Set an error in the dio if none is set yet.  We have to use cmpxchg
+ * as the submission context and the completion context(s) can race to
+ * update the error.
+ */
+static inline void iomap_dio_set_error(struct iomap_dio *dio, int ret)
+{
+	cmpxchg(&dio->error, 0, ret);
+}
+
+void iomap_dio_bio_end_io(struct bio *bio)
+{
+	struct iomap_dio *dio = bio->bi_private;
+	bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY);
+	struct kiocb *iocb = dio->iocb;
+
+	if (bio->bi_status)
+		iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status));
+	if (!atomic_dec_and_test(&dio->ref))
+		goto release_bio;
+
+	/*
+	 * Synchronous dio, task itself will handle any completion work
+	 * that needs after IO. All we need to do is wake the task.
+	 */
+	if (dio->wait_for_completion) {
+		struct task_struct *waiter = dio->submit.waiter;
+
+		WRITE_ONCE(dio->submit.waiter, NULL);
+		blk_wake_io_task(waiter);
+		goto release_bio;
+	}
+
+	/*
+	 * Flagged with IOMAP_DIO_INLINE_COMP, we can complete it inline
+	 */
+	if (dio->flags & IOMAP_DIO_INLINE_COMP) {
+		WRITE_ONCE(iocb->private, NULL);
+		iomap_dio_complete_work(&dio->aio.work);
+		goto release_bio;
+	}
+
+	/*
+	 * If this dio is flagged with IOMAP_DIO_CALLER_COMP, then schedule
+	 * our completion that way to avoid an async punt to a workqueue.
+	 */
+	if (dio->flags & IOMAP_DIO_CALLER_COMP) {
+		/* only polled IO cares about private cleared */
+		iocb->private = dio;
+		iocb->dio_complete = iomap_dio_deferred_complete;
+
+		/*
+		 * Invoke ->ki_complete() directly. We've assigned our
+		 * dio_complete callback handler, and since the issuer set
+		 * IOCB_DIO_CALLER_COMP, we know their ki_complete handler will
+		 * notice ->dio_complete being set and will defer calling that
+		 * handler until it can be done from a safe task context.
+		 *
+		 * Note that the 'res' being passed in here is not important
+		 * for this case. The actual completion value of the request
+		 * will be gotten from dio_complete when that is run by the
+		 * issuer.
+		 */
+		iocb->ki_complete(iocb, 0);
+		goto release_bio;
+	}
+
+	/*
+	 * Async DIO completion that requires filesystem level completion work
+	 * gets punted to a work queue to complete as the operation may require
+	 * more IO to be issued to finalise filesystem metadata changes or
+	 * guarantee data integrity.
+	 */
+	INIT_WORK(&dio->aio.work, iomap_dio_complete_work);
+	queue_work(file_inode(iocb->ki_filp)->i_sb->s_dio_done_wq,
+			&dio->aio.work);
+release_bio:
+	if (should_dirty) {
+		bio_check_pages_dirty(bio);
+	} else {
+		bio_release_pages(bio, false);
+		bio_put(bio);
+	}
+}
+EXPORT_SYMBOL_GPL(iomap_dio_bio_end_io);
+
+static void 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;
+
+	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);
+	bio->bi_iter.bi_sector = iomap_sector(&iter->iomap, pos);
+	bio->bi_private = dio;
+	bio->bi_end_io = iomap_dio_bio_end_io;
+
+	__bio_add_page(bio, page, len, 0);
+	iomap_dio_submit_bio(iter, dio, bio, pos);
+}
+
+/*
+ * Figure out the bio's operation flags from the dio request, the
+ * mapping, and whether or not we want FUA.  Note that we can end up
+ * clearing the WRITE_THROUGH flag in the dio request.
+ */
+static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio,
+		const struct iomap *iomap, bool use_fua)
+{
+	blk_opf_t opflags = REQ_SYNC | REQ_IDLE;
+
+	if (!(dio->flags & IOMAP_DIO_WRITE))
+		return REQ_OP_READ;
+
+	opflags |= REQ_OP_WRITE;
+	if (use_fua)
+		opflags |= REQ_FUA;
+	else
+		dio->flags &= ~IOMAP_DIO_WRITE_THROUGH;
+
+	return opflags;
+}
+
+static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
+		struct iomap_dio *dio)
+{
+	const struct iomap *iomap = &iter->iomap;
+	struct inode *inode = iter->inode;
+	unsigned int fs_block_size = i_blocksize(inode), pad;
+	loff_t length = iomap_length(iter);
+	loff_t pos = iter->pos;
+	blk_opf_t bio_opf;
+	struct bio *bio;
+	bool need_zeroout = false;
+	bool use_fua = false;
+	int nr_pages, ret = 0;
+	size_t copied = 0;
+	size_t orig_count;
+
+	if ((pos | length) & (bdev_logical_block_size(iomap->bdev) - 1) ||
+	    !bdev_iter_is_aligned(iomap->bdev, dio->submit.iter))
+		return -EINVAL;
+
+	if (iomap->type == IOMAP_UNWRITTEN) {
+		dio->flags |= IOMAP_DIO_UNWRITTEN;
+		need_zeroout = true;
+	}
+
+	if (iomap->flags & IOMAP_F_SHARED)
+		dio->flags |= IOMAP_DIO_COW;
+
+	if (iomap->flags & IOMAP_F_NEW) {
+		need_zeroout = true;
+	} else if (iomap->type == IOMAP_MAPPED) {
+		/*
+		 * Use a FUA write if we need datasync semantics, this is a pure
+		 * data IO that doesn't require any metadata updates (including
+		 * after IO completion such as unwritten extent conversion) and
+		 * the underlying device either supports FUA or doesn't have
+		 * a volatile write cache. This allows us to avoid cache flushes
+		 * on IO completion. If we can't use writethrough and need to
+		 * sync, disable in-task completions as dio completion will
+		 * need to call generic_write_sync() which will do a blocking
+		 * fsync / cache flush call.
+		 */
+		if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
+		    (dio->flags & IOMAP_DIO_WRITE_THROUGH) &&
+		    (bdev_fua(iomap->bdev) || !bdev_write_cache(iomap->bdev)))
+			use_fua = true;
+		else if (dio->flags & IOMAP_DIO_NEED_SYNC)
+			dio->flags &= ~IOMAP_DIO_CALLER_COMP;
+	}
+
+	/*
+	 * Save the original count and trim the iter to just the extent we
+	 * are operating on right now.  The iter will be re-expanded once
+	 * we are done.
+	 */
+	orig_count = iov_iter_count(dio->submit.iter);
+	iov_iter_truncate(dio->submit.iter, length);
+
+	if (!iov_iter_count(dio->submit.iter))
+		goto out;
+
+	/*
+	 * We can only do deferred completion for pure overwrites that
+	 * don't require additional IO at completion. This rules out
+	 * writes that need zeroing or extent conversion, extend
+	 * the file size, or issue journal IO or cache flushes
+	 * during completion processing.
+	 */
+	if (need_zeroout ||
+	    ((dio->flags & IOMAP_DIO_NEED_SYNC) && !use_fua) ||
+	    ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode)))
+		dio->flags &= ~IOMAP_DIO_CALLER_COMP;
+
+	/*
+	 * The rules for polled IO completions follow the guidelines as the
+	 * ones we set for inline and deferred completions. If none of those
+	 * are available for this IO, clear the polled flag.
+	 */
+	if (!(dio->flags & (IOMAP_DIO_INLINE_COMP|IOMAP_DIO_CALLER_COMP)))
+		dio->iocb->ki_flags &= ~IOCB_HIPRI;
+
+	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);
+	}
+
+	/*
+	 * Set the operation flags early so that bio_iov_iter_get_pages
+	 * can set up the page vector appropriately for a ZONE_APPEND
+	 * operation.
+	 */
+	bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua);
+
+	nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS);
+	do {
+		size_t n;
+		if (dio->error) {
+			iov_iter_revert(dio->submit.iter, copied);
+			copied = ret = 0;
+			goto out;
+		}
+
+		bio = iomap_dio_alloc_bio(iter, dio, nr_pages, bio_opf);
+		fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits,
+					  GFP_KERNEL);
+		bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
+		bio->bi_ioprio = dio->iocb->ki_ioprio;
+		bio->bi_private = dio;
+		bio->bi_end_io = iomap_dio_bio_end_io;
+
+		ret = bio_iov_iter_get_pages(bio, dio->submit.iter);
+		if (unlikely(ret)) {
+			/*
+			 * We have to stop part way through an IO. We must fall
+			 * through to the sub-block tail zeroing here, otherwise
+			 * this short IO may expose stale data in the tail of
+			 * the block we haven't written data to.
+			 */
+			bio_put(bio);
+			goto zero_tail;
+		}
+
+		n = bio->bi_iter.bi_size;
+		if (dio->flags & IOMAP_DIO_WRITE) {
+			task_io_account_write(n);
+		} else {
+			if (dio->flags & IOMAP_DIO_DIRTY)
+				bio_set_pages_dirty(bio);
+		}
+
+		dio->size += n;
+		copied += n;
+
+		nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter,
+						 BIO_MAX_VECS);
+		/*
+		 * We can only poll for single bio I/Os.
+		 */
+		if (nr_pages)
+			dio->iocb->ki_flags &= ~IOCB_HIPRI;
+		iomap_dio_submit_bio(iter, dio, bio, pos);
+		pos += n;
+	} while (nr_pages);
+
+	/*
+	 * We need to zeroout the tail of a sub-block write if the extent type
+	 * requires zeroing or the write extends beyond EOF. If we don't zero
+	 * the block tail in the latter case, we can expose stale data via mmap
+	 * reads of the EOF block.
+	 */
+zero_tail:
+	if (need_zeroout ||
+	    ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) {
+		/* 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);
+	}
+out:
+	/* Undo iter limitation to current extent */
+	iov_iter_reexpand(dio->submit.iter, orig_count - copied);
+	if (copied)
+		return copied;
+	return ret;
+}
+
+static loff_t iomap_dio_hole_iter(const struct iomap_iter *iter,
+		struct iomap_dio *dio)
+{
+	loff_t length = iov_iter_zero(iomap_length(iter), dio->submit.iter);
+
+	dio->size += length;
+	if (!length)
+		return -EFAULT;
+	return length;
+}
+
+static loff_t iomap_dio_inline_iter(const struct iomap_iter *iomi,
+		struct iomap_dio *dio)
+{
+	const struct iomap *iomap = &iomi->iomap;
+	struct iov_iter *iter = dio->submit.iter;
+	void *inline_data = iomap_inline_data(iomap, iomi->pos);
+	loff_t length = iomap_length(iomi);
+	loff_t pos = iomi->pos;
+	size_t copied;
+
+	if (WARN_ON_ONCE(!iomap_inline_data_valid(iomap)))
+		return -EIO;
+
+	if (dio->flags & IOMAP_DIO_WRITE) {
+		loff_t size = iomi->inode->i_size;
+
+		if (pos > size)
+			memset(iomap_inline_data(iomap, size), 0, pos - size);
+		copied = copy_from_iter(inline_data, length, iter);
+		if (copied) {
+			if (pos + copied > size)
+				i_size_write(iomi->inode, pos + copied);
+			mark_inode_dirty(iomi->inode);
+		}
+	} else {
+		copied = copy_to_iter(inline_data, length, iter);
+	}
+	dio->size += copied;
+	if (!copied)
+		return -EFAULT;
+	return copied;
+}
+
+static loff_t iomap_dio_iter(const struct iomap_iter *iter,
+		struct iomap_dio *dio)
+{
+	switch (iter->iomap.type) {
+	case IOMAP_HOLE:
+		if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE))
+			return -EIO;
+		return iomap_dio_hole_iter(iter, dio);
+	case IOMAP_UNWRITTEN:
+		if (!(dio->flags & IOMAP_DIO_WRITE))
+			return iomap_dio_hole_iter(iter, dio);
+		return iomap_dio_bio_iter(iter, dio);
+	case IOMAP_MAPPED:
+		return iomap_dio_bio_iter(iter, dio);
+	case IOMAP_INLINE:
+		return iomap_dio_inline_iter(iter, dio);
+	case IOMAP_DELALLOC:
+		/*
+		 * DIO is not serialised against mmap() access at all, and so
+		 * if the page_mkwrite occurs between the writeback and the
+		 * iomap_iter() call in the DIO path, then it will see the
+		 * DELALLOC block that the page-mkwrite allocated.
+		 */
+		pr_warn_ratelimited("Direct I/O collision with buffered writes! File: %pD4 Comm: %.20s\n",
+				    dio->iocb->ki_filp, current->comm);
+		return -EIO;
+	default:
+		WARN_ON_ONCE(1);
+		return -EIO;
+	}
+}
+
+/*
+ * iomap_dio_rw() always completes O_[D]SYNC writes regardless of whether the IO
+ * is being issued as AIO or not.  This allows us to optimise pure data writes
+ * to use REQ_FUA rather than requiring generic_write_sync() to issue a
+ * REQ_FLUSH post write. This is slightly tricky because a single request here
+ * can be mapped into multiple disjoint IOs and only a subset of the IOs issued
+ * may be pure data writes. In that case, we still need to do a full data sync
+ * completion.
+ *
+ * When page faults are disabled and @dio_flags includes IOMAP_DIO_PARTIAL,
+ * __iomap_dio_rw can return a partial result if it encounters a non-resident
+ * page in @iter after preparing a transfer.  In that case, the non-resident
+ * pages can be faulted in and the request resumed with @done_before set to the
+ * number of bytes previously transferred.  The request will then complete with
+ * the correct total number of bytes transferred; this is essential for
+ * completing partial requests asynchronously.
+ *
+ * Returns -ENOTBLK In case of a page invalidation invalidation failure for
+ * writes.  The callers needs to fall back to buffered I/O in this case.
+ */
+struct iomap_dio *
+__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		unsigned int dio_flags, void *private, size_t done_before)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct iomap_iter iomi = {
+		.inode		= inode,
+		.pos		= iocb->ki_pos,
+		.len		= iov_iter_count(iter),
+		.flags		= IOMAP_DIRECT,
+		.private	= private,
+	};
+	bool wait_for_completion =
+		is_sync_kiocb(iocb) || (dio_flags & IOMAP_DIO_FORCE_WAIT);
+	struct blk_plug plug;
+	struct iomap_dio *dio;
+	loff_t ret = 0;
+
+	trace_iomap_dio_rw_begin(iocb, iter, dio_flags, done_before);
+
+	if (!iomi.len)
+		return NULL;
+
+	dio = kmalloc(sizeof(*dio), GFP_KERNEL);
+	if (!dio)
+		return ERR_PTR(-ENOMEM);
+
+	dio->iocb = iocb;
+	atomic_set(&dio->ref, 1);
+	dio->size = 0;
+	dio->i_size = i_size_read(inode);
+	dio->dops = dops;
+	dio->error = 0;
+	dio->flags = 0;
+	dio->done_before = done_before;
+
+	dio->submit.iter = iter;
+	dio->submit.waiter = current;
+
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		iomi.flags |= IOMAP_NOWAIT;
+
+	if (iov_iter_rw(iter) == READ) {
+		/* reads can always complete inline */
+		dio->flags |= IOMAP_DIO_INLINE_COMP;
+
+		if (iomi.pos >= dio->i_size)
+			goto out_free_dio;
+
+		if (user_backed_iter(iter))
+			dio->flags |= IOMAP_DIO_DIRTY;
+
+		ret = kiocb_write_and_wait(iocb, iomi.len);
+		if (ret)
+			goto out_free_dio;
+	} else {
+		iomi.flags |= IOMAP_WRITE;
+		dio->flags |= IOMAP_DIO_WRITE;
+
+		/*
+		 * Flag as supporting deferred completions, if the issuer
+		 * groks it. This can avoid a workqueue punt for writes.
+		 * We may later clear this flag if we need to do other IO
+		 * as part of this IO completion.
+		 */
+		if (iocb->ki_flags & IOCB_DIO_CALLER_COMP)
+			dio->flags |= IOMAP_DIO_CALLER_COMP;
+
+		if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) {
+			ret = -EAGAIN;
+			if (iomi.pos >= dio->i_size ||
+			    iomi.pos + iomi.len > dio->i_size)
+				goto out_free_dio;
+			iomi.flags |= IOMAP_OVERWRITE_ONLY;
+		}
+
+		/* for data sync or sync, we need sync completion processing */
+		if (iocb_is_dsync(iocb)) {
+			dio->flags |= IOMAP_DIO_NEED_SYNC;
+
+		       /*
+			* For datasync only writes, we optimistically try using
+			* WRITE_THROUGH for this IO. This flag requires either
+			* FUA writes through the device's write cache, or a
+			* normal write to a device without a volatile write
+			* cache. For the former, Any non-FUA write that occurs
+			* will clear this flag, hence we know before completion
+			* whether a cache flush is necessary.
+			*/
+			if (!(iocb->ki_flags & IOCB_SYNC))
+				dio->flags |= IOMAP_DIO_WRITE_THROUGH;
+		}
+
+		/*
+		 * Try to invalidate cache pages for the range we are writing.
+		 * If this invalidation fails, let the caller fall back to
+		 * buffered I/O.
+		 */
+		ret = kiocb_invalidate_pages(iocb, iomi.len);
+		if (ret) {
+			if (ret != -EAGAIN) {
+				trace_iomap_dio_invalidate_fail(inode, iomi.pos,
+								iomi.len);
+				ret = -ENOTBLK;
+			}
+			goto out_free_dio;
+		}
+
+		if (!wait_for_completion && !inode->i_sb->s_dio_done_wq) {
+			ret = sb_init_dio_done_wq(inode->i_sb);
+			if (ret < 0)
+				goto out_free_dio;
+		}
+	}
+
+	inode_dio_begin(inode);
+
+	blk_start_plug(&plug);
+	while ((ret = iomap_iter(&iomi, ops)) > 0) {
+		iomi.processed = iomap_dio_iter(&iomi, dio);
+
+		/*
+		 * We can only poll for single bio I/Os.
+		 */
+		iocb->ki_flags &= ~IOCB_HIPRI;
+	}
+
+	blk_finish_plug(&plug);
+
+	/*
+	 * We only report that we've read data up to i_size.
+	 * Revert iter to a state corresponding to that as some callers (such
+	 * as the splice code) rely on it.
+	 */
+	if (iov_iter_rw(iter) == READ && iomi.pos >= dio->i_size)
+		iov_iter_revert(iter, iomi.pos - dio->i_size);
+
+	if (ret == -EFAULT && dio->size && (dio_flags & IOMAP_DIO_PARTIAL)) {
+		if (!(iocb->ki_flags & IOCB_NOWAIT))
+			wait_for_completion = true;
+		ret = 0;
+	}
+
+	/* magic error code to fall back to buffered I/O */
+	if (ret == -ENOTBLK) {
+		wait_for_completion = true;
+		ret = 0;
+	}
+	if (ret < 0)
+		iomap_dio_set_error(dio, ret);
+
+	/*
+	 * If all the writes we issued were already written through to the
+	 * media, we don't need to flush the cache on IO completion. Clear the
+	 * sync flag for this case.
+	 */
+	if (dio->flags & IOMAP_DIO_WRITE_THROUGH)
+		dio->flags &= ~IOMAP_DIO_NEED_SYNC;
+
+	/*
+	 * We are about to drop our additional submission reference, which
+	 * might be the last reference to the dio.  There are three different
+	 * ways we can progress here:
+	 *
+	 *  (a) If this is the last reference we will always complete and free
+	 *	the dio ourselves.
+	 *  (b) If this is not the last reference, and we serve an asynchronous
+	 *	iocb, we must never touch the dio after the decrement, the
+	 *	I/O completion handler will complete and free it.
+	 *  (c) If this is not the last reference, but we serve a synchronous
+	 *	iocb, the I/O completion handler will wake us up on the drop
+	 *	of the final reference, and we will complete and free it here
+	 *	after we got woken by the I/O completion handler.
+	 */
+	dio->wait_for_completion = wait_for_completion;
+	if (!atomic_dec_and_test(&dio->ref)) {
+		if (!wait_for_completion) {
+			trace_iomap_dio_rw_queued(inode, iomi.pos, iomi.len);
+			return ERR_PTR(-EIOCBQUEUED);
+		}
+
+		for (;;) {
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			if (!READ_ONCE(dio->submit.waiter))
+				break;
+
+			blk_io_schedule();
+		}
+		__set_current_state(TASK_RUNNING);
+	}
+
+	return dio;
+
+out_free_dio:
+	kfree(dio);
+	if (ret)
+		return ERR_PTR(ret);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(__iomap_dio_rw);
+
+ssize_t
+iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		unsigned int dio_flags, void *private, size_t done_before)
+{
+	struct iomap_dio *dio;
+
+	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, private,
+			     done_before);
+	if (IS_ERR_OR_NULL(dio))
+		return PTR_ERR_OR_ZERO(dio);
+	return iomap_dio_complete(dio);
+}
+EXPORT_SYMBOL_GPL(iomap_dio_rw);
diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c
new file mode 100644
index 0000000000..610ca6f1ec
--- /dev/null
+++ b/fs/iomap/fiemap.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016-2021 Christoph Hellwig.
+ */
+#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/iomap.h>
+#include <linux/fiemap.h>
+#include <linux/pagemap.h>
+
+static int iomap_to_fiemap(struct fiemap_extent_info *fi,
+		const struct iomap *iomap, u32 flags)
+{
+	switch (iomap->type) {
+	case IOMAP_HOLE:
+		/* skip holes */
+		return 0;
+	case IOMAP_DELALLOC:
+		flags |= FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN;
+		break;
+	case IOMAP_MAPPED:
+		break;
+	case IOMAP_UNWRITTEN:
+		flags |= FIEMAP_EXTENT_UNWRITTEN;
+		break;
+	case IOMAP_INLINE:
+		flags |= FIEMAP_EXTENT_DATA_INLINE;
+		break;
+	}
+
+	if (iomap->flags & IOMAP_F_MERGED)
+		flags |= FIEMAP_EXTENT_MERGED;
+	if (iomap->flags & IOMAP_F_SHARED)
+		flags |= FIEMAP_EXTENT_SHARED;
+
+	return fiemap_fill_next_extent(fi, iomap->offset,
+			iomap->addr != IOMAP_NULL_ADDR ? iomap->addr : 0,
+			iomap->length, flags);
+}
+
+static loff_t iomap_fiemap_iter(const struct iomap_iter *iter,
+		struct fiemap_extent_info *fi, struct iomap *prev)
+{
+	int ret;
+
+	if (iter->iomap.type == IOMAP_HOLE)
+		return iomap_length(iter);
+
+	ret = iomap_to_fiemap(fi, prev, 0);
+	*prev = iter->iomap;
+	switch (ret) {
+	case 0:		/* success */
+		return iomap_length(iter);
+	case 1:		/* extent array full */
+		return 0;
+	default:	/* error */
+		return ret;
+	}
+}
+
+int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
+		u64 start, u64 len, const struct iomap_ops *ops)
+{
+	struct iomap_iter iter = {
+		.inode		= inode,
+		.pos		= start,
+		.len		= len,
+		.flags		= IOMAP_REPORT,
+	};
+	struct iomap prev = {
+		.type		= IOMAP_HOLE,
+	};
+	int ret;
+
+	ret = fiemap_prep(inode, fi, start, &iter.len, 0);
+	if (ret)
+		return ret;
+
+	while ((ret = iomap_iter(&iter, ops)) > 0)
+		iter.processed = iomap_fiemap_iter(&iter, fi, &prev);
+
+	if (prev.type != IOMAP_HOLE) {
+		ret = iomap_to_fiemap(fi, &prev, FIEMAP_EXTENT_LAST);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* inode with no (attribute) mapping will give ENOENT */
+	if (ret < 0 && ret != -ENOENT)
+		return ret;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_fiemap);
+
+/* legacy ->bmap interface.  0 is the error return (!) */
+sector_t
+iomap_bmap(struct address_space *mapping, sector_t bno,
+		const struct iomap_ops *ops)
+{
+	struct iomap_iter iter = {
+		.inode	= mapping->host,
+		.pos	= (loff_t)bno << mapping->host->i_blkbits,
+		.len	= i_blocksize(mapping->host),
+		.flags	= IOMAP_REPORT,
+	};
+	const unsigned int blkshift = mapping->host->i_blkbits - SECTOR_SHIFT;
+	int ret;
+
+	if (filemap_write_and_wait(mapping))
+		return 0;
+
+	bno = 0;
+	while ((ret = iomap_iter(&iter, ops)) > 0) {
+		if (iter.iomap.type == IOMAP_MAPPED)
+			bno = iomap_sector(&iter.iomap, iter.pos) >> blkshift;
+		/* leave iter.processed unset to abort loop */
+	}
+	if (ret)
+		return 0;
+
+	return bno;
+}
+EXPORT_SYMBOL_GPL(iomap_bmap);
diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c
new file mode 100644
index 0000000000..79a0614eaa
--- /dev/null
+++ b/fs/iomap/iter.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2010 Red Hat, Inc.
+ * Copyright (c) 2016-2021 Christoph Hellwig.
+ */
+#include <linux/fs.h>
+#include <linux/iomap.h>
+#include "trace.h"
+
+/*
+ * Advance to the next range we need to map.
+ *
+ * If the iomap is marked IOMAP_F_STALE, it means the existing map was not fully
+ * processed - it was aborted because the extent the iomap spanned may have been
+ * changed during the operation. In this case, the iteration behaviour is to
+ * remap the unprocessed range of the iter, and that means we may need to remap
+ * even when we've made no progress (i.e. iter->processed = 0). Hence the
+ * "finished iterating" case needs to distinguish between
+ * (processed = 0) meaning we are done and (processed = 0 && stale) meaning we
+ * need to remap the entire remaining range.
+ */
+static inline int iomap_iter_advance(struct iomap_iter *iter)
+{
+	bool stale = iter->iomap.flags & IOMAP_F_STALE;
+
+	/* handle the previous iteration (if any) */
+	if (iter->iomap.length) {
+		if (iter->processed < 0)
+			return iter->processed;
+		if (!iter->processed && !stale)
+			return 0;
+		if (WARN_ON_ONCE(iter->processed > iomap_length(iter)))
+			return -EIO;
+		iter->pos += iter->processed;
+		iter->len -= iter->processed;
+		if (!iter->len)
+			return 0;
+	}
+
+	/* clear the state for the next iteration */
+	iter->processed = 0;
+	memset(&iter->iomap, 0, sizeof(iter->iomap));
+	memset(&iter->srcmap, 0, sizeof(iter->srcmap));
+	return 1;
+}
+
+static inline void iomap_iter_done(struct iomap_iter *iter)
+{
+	WARN_ON_ONCE(iter->iomap.offset > iter->pos);
+	WARN_ON_ONCE(iter->iomap.length == 0);
+	WARN_ON_ONCE(iter->iomap.offset + iter->iomap.length <= iter->pos);
+	WARN_ON_ONCE(iter->iomap.flags & IOMAP_F_STALE);
+
+	trace_iomap_iter_dstmap(iter->inode, &iter->iomap);
+	if (iter->srcmap.type != IOMAP_HOLE)
+		trace_iomap_iter_srcmap(iter->inode, &iter->srcmap);
+}
+
+/**
+ * iomap_iter - iterate over a ranges in a file
+ * @iter: iteration structue
+ * @ops: iomap ops provided by the file system
+ *
+ * Iterate over filesystem-provided space mappings for the provided file range.
+ *
+ * This function handles cleanup of resources acquired for iteration when the
+ * filesystem indicates there are no more space mappings, which means that this
+ * function must be called in a loop that continues as long it returns a
+ * positive value.  If 0 or a negative value is returned, the caller must not
+ * return to the loop body.  Within a loop body, there are two ways to break out
+ * of the loop body:  leave @iter.processed unchanged, or set it to a negative
+ * errno.
+ */
+int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops)
+{
+	int ret;
+
+	if (iter->iomap.length && ops->iomap_end) {
+		ret = ops->iomap_end(iter->inode, iter->pos, iomap_length(iter),
+				iter->processed > 0 ? iter->processed : 0,
+				iter->flags, &iter->iomap);
+		if (ret < 0 && !iter->processed)
+			return ret;
+	}
+
+	trace_iomap_iter(iter, ops, _RET_IP_);
+	ret = iomap_iter_advance(iter);
+	if (ret <= 0)
+		return ret;
+
+	ret = ops->iomap_begin(iter->inode, iter->pos, iter->len, iter->flags,
+			       &iter->iomap, &iter->srcmap);
+	if (ret < 0)
+		return ret;
+	iomap_iter_done(iter);
+	return 1;
+}
diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c
new file mode 100644
index 0000000000..a845c012b5
--- /dev/null
+++ b/fs/iomap/seek.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Red Hat, Inc.
+ * Copyright (c) 2018-2021 Christoph Hellwig.
+ */
+#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/iomap.h>
+#include <linux/pagemap.h>
+#include <linux/pagevec.h>
+
+static loff_t iomap_seek_hole_iter(const struct iomap_iter *iter,
+		loff_t *hole_pos)
+{
+	loff_t length = iomap_length(iter);
+
+	switch (iter->iomap.type) {
+	case IOMAP_UNWRITTEN:
+		*hole_pos = mapping_seek_hole_data(iter->inode->i_mapping,
+				iter->pos, iter->pos + length, SEEK_HOLE);
+		if (*hole_pos == iter->pos + length)
+			return length;
+		return 0;
+	case IOMAP_HOLE:
+		*hole_pos = iter->pos;
+		return 0;
+	default:
+		return length;
+	}
+}
+
+loff_t
+iomap_seek_hole(struct inode *inode, loff_t pos, const struct iomap_ops *ops)
+{
+	loff_t size = i_size_read(inode);
+	struct iomap_iter iter = {
+		.inode	= inode,
+		.pos	= pos,
+		.flags	= IOMAP_REPORT,
+	};
+	int ret;
+
+	/* Nothing to be found before or beyond the end of the file. */
+	if (pos < 0 || pos >= size)
+		return -ENXIO;
+
+	iter.len = size - pos;
+	while ((ret = iomap_iter(&iter, ops)) > 0)
+		iter.processed = iomap_seek_hole_iter(&iter, &pos);
+	if (ret < 0)
+		return ret;
+	if (iter.len) /* found hole before EOF */
+		return pos;
+	return size;
+}
+EXPORT_SYMBOL_GPL(iomap_seek_hole);
+
+static loff_t iomap_seek_data_iter(const struct iomap_iter *iter,
+		loff_t *hole_pos)
+{
+	loff_t length = iomap_length(iter);
+
+	switch (iter->iomap.type) {
+	case IOMAP_HOLE:
+		return length;
+	case IOMAP_UNWRITTEN:
+		*hole_pos = mapping_seek_hole_data(iter->inode->i_mapping,
+				iter->pos, iter->pos + length, SEEK_DATA);
+		if (*hole_pos < 0)
+			return length;
+		return 0;
+	default:
+		*hole_pos = iter->pos;
+		return 0;
+	}
+}
+
+loff_t
+iomap_seek_data(struct inode *inode, loff_t pos, const struct iomap_ops *ops)
+{
+	loff_t size = i_size_read(inode);
+	struct iomap_iter iter = {
+		.inode	= inode,
+		.pos	= pos,
+		.flags	= IOMAP_REPORT,
+	};
+	int ret;
+
+	/* Nothing to be found before or beyond the end of the file. */
+	if (pos < 0 || pos >= size)
+		return -ENXIO;
+
+	iter.len = size - pos;
+	while ((ret = iomap_iter(&iter, ops)) > 0)
+		iter.processed = iomap_seek_data_iter(&iter, &pos);
+	if (ret < 0)
+		return ret;
+	if (iter.len) /* found data before EOF */
+		return pos;
+	/* We've reached the end of the file without finding data */
+	return -ENXIO;
+}
+EXPORT_SYMBOL_GPL(iomap_seek_data);
diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c
new file mode 100644
index 0000000000..5fc0ac36de
--- /dev/null
+++ b/fs/iomap/swapfile.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/iomap.h>
+#include <linux/swap.h>
+
+/* Swapfile activation */
+
+struct iomap_swapfile_info {
+	struct iomap iomap;		/* accumulated iomap */
+	struct swap_info_struct *sis;
+	uint64_t lowest_ppage;		/* lowest physical addr seen (pages) */
+	uint64_t highest_ppage;		/* highest physical addr seen (pages) */
+	unsigned long nr_pages;		/* number of pages collected */
+	int nr_extents;			/* extent count */
+	struct file *file;
+};
+
+/*
+ * Collect physical extents for this swap file.  Physical extents reported to
+ * the swap code must be trimmed to align to a page boundary.  The logical
+ * offset within the file is irrelevant since the swapfile code maps logical
+ * page numbers of the swap device to the physical page-aligned extents.
+ */
+static int iomap_swapfile_add_extent(struct iomap_swapfile_info *isi)
+{
+	struct iomap *iomap = &isi->iomap;
+	unsigned long nr_pages;
+	unsigned long max_pages;
+	uint64_t first_ppage;
+	uint64_t first_ppage_reported;
+	uint64_t next_ppage;
+	int error;
+
+	if (unlikely(isi->nr_pages >= isi->sis->max))
+		return 0;
+	max_pages = isi->sis->max - isi->nr_pages;
+
+	/*
+	 * Round the start up and the end down so that the physical
+	 * extent aligns to a page boundary.
+	 */
+	first_ppage = ALIGN(iomap->addr, PAGE_SIZE) >> PAGE_SHIFT;
+	next_ppage = ALIGN_DOWN(iomap->addr + iomap->length, PAGE_SIZE) >>
+			PAGE_SHIFT;
+
+	/* Skip too-short physical extents. */
+	if (first_ppage >= next_ppage)
+		return 0;
+	nr_pages = next_ppage - first_ppage;
+	nr_pages = min(nr_pages, max_pages);
+
+	/*
+	 * Calculate how much swap space we're adding; the first page contains
+	 * the swap header and doesn't count.  The mm still wants that first
+	 * page fed to add_swap_extent, however.
+	 */
+	first_ppage_reported = first_ppage;
+	if (iomap->offset == 0)
+		first_ppage_reported++;
+	if (isi->lowest_ppage > first_ppage_reported)
+		isi->lowest_ppage = first_ppage_reported;
+	if (isi->highest_ppage < (next_ppage - 1))
+		isi->highest_ppage = next_ppage - 1;
+
+	/* Add extent, set up for the next call. */
+	error = add_swap_extent(isi->sis, isi->nr_pages, nr_pages, first_ppage);
+	if (error < 0)
+		return error;
+	isi->nr_extents += error;
+	isi->nr_pages += nr_pages;
+	return 0;
+}
+
+static int iomap_swapfile_fail(struct iomap_swapfile_info *isi, const char *str)
+{
+	char *buf, *p = ERR_PTR(-ENOMEM);
+
+	buf = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (buf)
+		p = file_path(isi->file, buf, PATH_MAX);
+	pr_err("swapon: file %s %s\n", IS_ERR(p) ? "<unknown>" : p, str);
+	kfree(buf);
+	return -EINVAL;
+}
+
+/*
+ * Accumulate iomaps for this swap file.  We have to accumulate iomaps because
+ * swap only cares about contiguous page-aligned physical extents and makes no
+ * distinction between written and unwritten extents.
+ */
+static loff_t iomap_swapfile_iter(const struct iomap_iter *iter,
+		struct iomap *iomap, struct iomap_swapfile_info *isi)
+{
+	switch (iomap->type) {
+	case IOMAP_MAPPED:
+	case IOMAP_UNWRITTEN:
+		/* Only real or unwritten extents. */
+		break;
+	case IOMAP_INLINE:
+		/* No inline data. */
+		return iomap_swapfile_fail(isi, "is inline");
+	default:
+		return iomap_swapfile_fail(isi, "has unallocated extents");
+	}
+
+	/* No uncommitted metadata or shared blocks. */
+	if (iomap->flags & IOMAP_F_DIRTY)
+		return iomap_swapfile_fail(isi, "is not committed");
+	if (iomap->flags & IOMAP_F_SHARED)
+		return iomap_swapfile_fail(isi, "has shared extents");
+
+	/* Only one bdev per swap file. */
+	if (iomap->bdev != isi->sis->bdev)
+		return iomap_swapfile_fail(isi, "outside the main device");
+
+	if (isi->iomap.length == 0) {
+		/* No accumulated extent, so just store it. */
+		memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
+	} else if (isi->iomap.addr + isi->iomap.length == iomap->addr) {
+		/* Append this to the accumulated extent. */
+		isi->iomap.length += iomap->length;
+	} else {
+		/* Otherwise, add the retained iomap and store this one. */
+		int error = iomap_swapfile_add_extent(isi);
+		if (error)
+			return error;
+		memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
+	}
+	return iomap_length(iter);
+}
+
+/*
+ * Iterate a swap file's iomaps to construct physical extents that can be
+ * passed to the swapfile subsystem.
+ */
+int iomap_swapfile_activate(struct swap_info_struct *sis,
+		struct file *swap_file, sector_t *pagespan,
+		const struct iomap_ops *ops)
+{
+	struct inode *inode = swap_file->f_mapping->host;
+	struct iomap_iter iter = {
+		.inode	= inode,
+		.pos	= 0,
+		.len	= ALIGN_DOWN(i_size_read(inode), PAGE_SIZE),
+		.flags	= IOMAP_REPORT,
+	};
+	struct iomap_swapfile_info isi = {
+		.sis = sis,
+		.lowest_ppage = (sector_t)-1ULL,
+		.file = swap_file,
+	};
+	int ret;
+
+	/*
+	 * Persist all file mapping metadata so that we won't have any
+	 * IOMAP_F_DIRTY iomaps.
+	 */
+	ret = vfs_fsync(swap_file, 1);
+	if (ret)
+		return ret;
+
+	while ((ret = iomap_iter(&iter, ops)) > 0)
+		iter.processed = iomap_swapfile_iter(&iter, &iter.iomap, &isi);
+	if (ret < 0)
+		return ret;
+
+	if (isi.iomap.length) {
+		ret = iomap_swapfile_add_extent(&isi);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * If this swapfile doesn't contain even a single page-aligned
+	 * contiguous range of blocks, reject this useless swapfile to
+	 * prevent confusion later on.
+	 */
+	if (isi.nr_pages == 0) {
+		pr_warn("swapon: Cannot find a single usable page in file.\n");
+		return -EINVAL;
+	}
+
+	*pagespan = 1 + isi.highest_ppage - isi.lowest_ppage;
+	sis->max = isi.nr_pages;
+	sis->pages = isi.nr_pages - 1;
+	sis->highest_bit = isi.nr_pages - 1;
+	return isi.nr_extents;
+}
+EXPORT_SYMBOL_GPL(iomap_swapfile_activate);
diff --git a/fs/iomap/trace.c b/fs/iomap/trace.c
new file mode 100644
index 0000000000..728d5443da
--- /dev/null
+++ b/fs/iomap/trace.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Christoph Hellwig
+ */
+#include <linux/iomap.h>
+#include <linux/uio.h>
+
+/*
+ * We include this last to have the helpers above available for the trace
+ * event implementations.
+ */
+#define CREATE_TRACE_POINTS
+#include "trace.h"
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
new file mode 100644
index 0000000000..c16fd55f55
--- /dev/null
+++ b/fs/iomap/trace.h
@@ -0,0 +1,269 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2009-2021 Christoph Hellwig
+ *
+ * NOTE: none of these tracepoints shall be considered a stable kernel ABI
+ * as they can change at any time.
+ *
+ * Current conventions for printing numbers measuring specific units:
+ *
+ * offset: byte offset into a subcomponent of a file operation
+ * pos: file offset, in bytes
+ * length: length of a file operation, in bytes
+ * ino: inode number
+ *
+ * Numbers describing space allocations should be formatted in hexadecimal.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM iomap
+
+#if !defined(_IOMAP_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _IOMAP_TRACE_H
+
+#include <linux/tracepoint.h>
+
+struct inode;
+
+DECLARE_EVENT_CLASS(iomap_readpage_class,
+	TP_PROTO(struct inode *inode, int nr_pages),
+	TP_ARGS(inode, nr_pages),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(u64, ino)
+		__field(int, nr_pages)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->nr_pages = nr_pages;
+	),
+	TP_printk("dev %d:%d ino 0x%llx nr_pages %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->nr_pages)
+)
+
+#define DEFINE_READPAGE_EVENT(name)		\
+DEFINE_EVENT(iomap_readpage_class, name,	\
+	TP_PROTO(struct inode *inode, int nr_pages), \
+	TP_ARGS(inode, nr_pages))
+DEFINE_READPAGE_EVENT(iomap_readpage);
+DEFINE_READPAGE_EVENT(iomap_readahead);
+
+DECLARE_EVENT_CLASS(iomap_range_class,
+	TP_PROTO(struct inode *inode, loff_t off, u64 len),
+	TP_ARGS(inode, off, len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(u64, ino)
+		__field(loff_t, size)
+		__field(loff_t, offset)
+		__field(u64, length)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->size = i_size_read(inode);
+		__entry->offset = off;
+		__entry->length = len;
+	),
+	TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx length 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->size,
+		  __entry->offset,
+		  __entry->length)
+)
+
+#define DEFINE_RANGE_EVENT(name)		\
+DEFINE_EVENT(iomap_range_class, name,	\
+	TP_PROTO(struct inode *inode, loff_t off, u64 len),\
+	TP_ARGS(inode, off, len))
+DEFINE_RANGE_EVENT(iomap_writepage);
+DEFINE_RANGE_EVENT(iomap_release_folio);
+DEFINE_RANGE_EVENT(iomap_invalidate_folio);
+DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail);
+DEFINE_RANGE_EVENT(iomap_dio_rw_queued);
+
+#define IOMAP_TYPE_STRINGS \
+	{ IOMAP_HOLE,		"HOLE" }, \
+	{ IOMAP_DELALLOC,	"DELALLOC" }, \
+	{ IOMAP_MAPPED,		"MAPPED" }, \
+	{ IOMAP_UNWRITTEN,	"UNWRITTEN" }, \
+	{ IOMAP_INLINE,		"INLINE" }
+
+#define IOMAP_FLAGS_STRINGS \
+	{ IOMAP_WRITE,		"WRITE" }, \
+	{ IOMAP_ZERO,		"ZERO" }, \
+	{ IOMAP_REPORT,		"REPORT" }, \
+	{ IOMAP_FAULT,		"FAULT" }, \
+	{ IOMAP_DIRECT,		"DIRECT" }, \
+	{ IOMAP_NOWAIT,		"NOWAIT" }
+
+#define IOMAP_F_FLAGS_STRINGS \
+	{ IOMAP_F_NEW,		"NEW" }, \
+	{ IOMAP_F_DIRTY,	"DIRTY" }, \
+	{ IOMAP_F_SHARED,	"SHARED" }, \
+	{ IOMAP_F_MERGED,	"MERGED" }, \
+	{ IOMAP_F_BUFFER_HEAD,	"BH" }, \
+	{ IOMAP_F_SIZE_CHANGED,	"SIZE_CHANGED" }
+
+#define IOMAP_DIO_STRINGS \
+	{IOMAP_DIO_FORCE_WAIT,	"DIO_FORCE_WAIT" }, \
+	{IOMAP_DIO_OVERWRITE_ONLY, "DIO_OVERWRITE_ONLY" }, \
+	{IOMAP_DIO_PARTIAL,	"DIO_PARTIAL" }
+
+DECLARE_EVENT_CLASS(iomap_class,
+	TP_PROTO(struct inode *inode, struct iomap *iomap),
+	TP_ARGS(inode, iomap),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(u64, ino)
+		__field(u64, addr)
+		__field(loff_t, offset)
+		__field(u64, length)
+		__field(u16, type)
+		__field(u16, flags)
+		__field(dev_t, bdev)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->addr = iomap->addr;
+		__entry->offset = iomap->offset;
+		__entry->length = iomap->length;
+		__entry->type = iomap->type;
+		__entry->flags = iomap->flags;
+		__entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0;
+	),
+	TP_printk("dev %d:%d ino 0x%llx bdev %d:%d addr 0x%llx offset 0x%llx "
+		  "length 0x%llx type %s flags %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  MAJOR(__entry->bdev), MINOR(__entry->bdev),
+		  __entry->addr,
+		  __entry->offset,
+		  __entry->length,
+		  __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS),
+		  __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS))
+)
+
+#define DEFINE_IOMAP_EVENT(name)		\
+DEFINE_EVENT(iomap_class, name,	\
+	TP_PROTO(struct inode *inode, struct iomap *iomap), \
+	TP_ARGS(inode, iomap))
+DEFINE_IOMAP_EVENT(iomap_iter_dstmap);
+DEFINE_IOMAP_EVENT(iomap_iter_srcmap);
+DEFINE_IOMAP_EVENT(iomap_writepage_map);
+
+TRACE_EVENT(iomap_iter,
+	TP_PROTO(struct iomap_iter *iter, const void *ops,
+		 unsigned long caller),
+	TP_ARGS(iter, ops, caller),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(u64, ino)
+		__field(loff_t, pos)
+		__field(u64, length)
+		__field(unsigned int, flags)
+		__field(const void *, ops)
+		__field(unsigned long, caller)
+	),
+	TP_fast_assign(
+		__entry->dev = iter->inode->i_sb->s_dev;
+		__entry->ino = iter->inode->i_ino;
+		__entry->pos = iter->pos;
+		__entry->length = iomap_length(iter);
+		__entry->flags = iter->flags;
+		__entry->ops = ops;
+		__entry->caller = caller;
+	),
+	TP_printk("dev %d:%d ino 0x%llx pos 0x%llx length 0x%llx flags %s (0x%x) ops %ps caller %pS",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		   __entry->ino,
+		   __entry->pos,
+		   __entry->length,
+		   __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS),
+		   __entry->flags,
+		   __entry->ops,
+		   (void *)__entry->caller)
+);
+
+TRACE_EVENT(iomap_dio_rw_begin,
+	TP_PROTO(struct kiocb *iocb, struct iov_iter *iter,
+		 unsigned int dio_flags, size_t done_before),
+	TP_ARGS(iocb, iter, dio_flags, done_before),
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t, isize)
+		__field(loff_t, pos)
+		__field(size_t,	count)
+		__field(size_t,	done_before)
+		__field(int,	ki_flags)
+		__field(unsigned int,	dio_flags)
+		__field(bool,	aio)
+	),
+	TP_fast_assign(
+		__entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev;
+		__entry->ino = file_inode(iocb->ki_filp)->i_ino;
+		__entry->isize = file_inode(iocb->ki_filp)->i_size;
+		__entry->pos = iocb->ki_pos;
+		__entry->count = iov_iter_count(iter);
+		__entry->done_before = done_before;
+		__entry->ki_flags = iocb->ki_flags;
+		__entry->dio_flags = dio_flags;
+		__entry->aio = !is_sync_kiocb(iocb);
+	),
+	TP_printk("dev %d:%d ino 0x%lx size 0x%llx offset 0x%llx length 0x%zx done_before 0x%zx flags %s dio_flags %s aio %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->isize,
+		  __entry->pos,
+		  __entry->count,
+		  __entry->done_before,
+		  __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS),
+		  __print_flags(__entry->dio_flags, "|", IOMAP_DIO_STRINGS),
+		  __entry->aio)
+);
+
+TRACE_EVENT(iomap_dio_complete,
+	TP_PROTO(struct kiocb *iocb, int error, ssize_t ret),
+	TP_ARGS(iocb, error, ret),
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t, isize)
+		__field(loff_t, pos)
+		__field(int,	ki_flags)
+		__field(bool,	aio)
+		__field(int,	error)
+		__field(ssize_t, ret)
+	),
+	TP_fast_assign(
+		__entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev;
+		__entry->ino = file_inode(iocb->ki_filp)->i_ino;
+		__entry->isize = file_inode(iocb->ki_filp)->i_size;
+		__entry->pos = iocb->ki_pos;
+		__entry->ki_flags = iocb->ki_flags;
+		__entry->aio = !is_sync_kiocb(iocb);
+		__entry->error = error;
+		__entry->ret = ret;
+	),
+	TP_printk("dev %d:%d ino 0x%lx size 0x%llx offset 0x%llx flags %s aio %d error %d ret %zd",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->isize,
+		  __entry->pos,
+		  __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS),
+		  __entry->aio,
+		  __entry->error,
+		  __entry->ret)
+);
+
+#endif /* _IOMAP_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>