buffered-io.c

// 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"

/*
 * Structure allocated for each page or THP when block size < page size
 * to track sub-page uptodate status and I/O completions.
 */
struct iomap_page {
	atomic_t		read_bytes_pending;
	atomic_t		write_bytes_pending;
	spinlock_t		uptodate_lock;
	unsigned long		uptodate[];
};

static inline struct iomap_page *to_iomap_page(struct page *page)
{
	/*
	 * per-block data is stored in the head page.  Callers should
	 * not be dealing with tail pages, and if they are, they can
	 * call thp_head() first.
	 */
	VM_BUG_ON_PGFLAGS(PageTail(page), page);

	if (page_has_private(page))
		return (struct iomap_page *)page_private(page);
	return NULL;
}

static struct bio_set iomap_ioend_bioset;

static struct iomap_page *
iomap_page_create(struct inode *inode, struct page *page)
{
	struct iomap_page *iop = to_iomap_page(page);
	unsigned int nr_blocks = i_blocks_per_page(inode, page);

	if (iop || nr_blocks <= 1)
		return iop;

	iop = kzalloc(struct_size(iop, uptodate, BITS_TO_LONGS(nr_blocks)),
			GFP_NOFS | __GFP_NOFAIL);
	spin_lock_init(&iop->uptodate_lock);
	if (PageUptodate(page))
		bitmap_fill(iop->uptodate, nr_blocks);
	attach_page_private(page, iop);
	return iop;
}

static void
iomap_page_release(struct page *page)
{
	struct iomap_page *iop = detach_page_private(page);
	unsigned int nr_blocks = i_blocks_per_page(page->mapping->host, page);

	if (!iop)
		return;
	WARN_ON_ONCE(atomic_read(&iop->read_bytes_pending));
	WARN_ON_ONCE(atomic_read(&iop->write_bytes_pending));
	WARN_ON_ONCE(bitmap_full(iop->uptodate, nr_blocks) !=
			PageUptodate(page));
	kfree(iop);
}

/*
 * Calculate the range inside the page that we actually need to read.
 */
static void
iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop,
		loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp)
{
	loff_t orig_pos = *pos;
	loff_t isize = i_size_read(inode);
	unsigned block_bits = inode->i_blkbits;
	unsigned block_size = (1 << block_bits);
	unsigned poff = offset_in_page(*pos);
	unsigned plen = min_t(loff_t, PAGE_SIZE - 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 (iop) {
		unsigned int i;

		/* move forward for each leading block marked uptodate */
		for (i = first; i <= last; i++) {
			if (!test_bit(i, iop->uptodate))
				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 (test_bit(i, iop->uptodate)) {
				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_page(isize - 1) >> block_bits;

		if (first <= end && last > end)
			plen -= (last - end) * block_size;
	}

	*offp = poff;
	*lenp = plen;
}

static void
iomap_iop_set_range_uptodate(struct page *page, unsigned off, unsigned len)
{
	struct iomap_page *iop = to_iomap_page(page);
	struct inode *inode = page->mapping->host;
	unsigned first = off >> inode->i_blkbits;
	unsigned last = (off + len - 1) >> inode->i_blkbits;
	unsigned long flags;

	spin_lock_irqsave(&iop->uptodate_lock, flags);
	bitmap_set(iop->uptodate, first, last - first + 1);
	if (bitmap_full(iop->uptodate, i_blocks_per_page(inode, page)))
		SetPageUptodate(page);
	spin_unlock_irqrestore(&iop->uptodate_lock, flags);
}

static void
iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len)
{
	if (PageError(page))
		return;

	if (page_has_private(page))
		iomap_iop_set_range_uptodate(page, off, len);
	else
		SetPageUptodate(page);
}

static void
iomap_read_page_end_io(struct bio_vec *bvec, int error)
{
	struct page *page = bvec->bv_page;
	struct iomap_page *iop = to_iomap_page(page);

	if (unlikely(error)) {
		ClearPageUptodate(page);
		SetPageError(page);
	} else {
		iomap_set_range_uptodate(page, bvec->bv_offset, bvec->bv_len);
	}

	if (!iop || atomic_sub_and_test(bvec->bv_len, &iop->read_bytes_pending))
		unlock_page(page);
}

static void
iomap_read_end_io(struct bio *bio)
{
	int error = blk_status_to_errno(bio->bi_status);
	struct bio_vec *bvec;
	struct bvec_iter_all iter_all;

	bio_for_each_segment_all(bvec, bio, iter_all)
		iomap_read_page_end_io(bvec, error);
	bio_put(bio);
}

struct iomap_readpage_ctx {
	struct page		*cur_page;
	bool			cur_page_in_bio;
	struct bio		*bio;
	struct readahead_control *rac;
};

/**
 * iomap_read_inline_data - copy inline data into the page cache
 * @iter: iteration structure
 * @page: page to copy to
 *
 * Copy the inline data in @iter into @page and zero out the rest of the page.
 * 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 page *page)
{
	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);
	void *addr;

	if (PageUptodate(page))
		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 (poff > 0)
		iomap_page_create(iter->inode, page);

	addr = kmap_local_page(page) + poff;
	memcpy(addr, iomap->inline_data, size);
	memset(addr + size, 0, PAGE_SIZE - poff - size);
	kunmap_local(addr);
	iomap_set_range_uptodate(page, poff, 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 page *page = ctx->cur_page;
	struct iomap_page *iop;
	loff_t orig_pos = pos;
	unsigned poff, plen;
	sector_t sector;

	if (iomap->type == IOMAP_INLINE)
		return iomap_read_inline_data(iter, page);

	/* zero post-eof blocks as the page may be mapped */
	iop = iomap_page_create(iter->inode, page);
	iomap_adjust_read_range(iter->inode, iop, &pos, length, &poff, &plen);
	if (plen == 0)
		goto done;

	if (iomap_block_needs_zeroing(iter, pos)) {
		zero_user(page, poff, plen);
		iomap_set_range_uptodate(page, poff, plen);
		goto done;
	}

	ctx->cur_page_in_bio = true;
	if (iop)
		atomic_add(plen, &iop->read_bytes_pending);

	sector = iomap_sector(iomap, pos);
	if (!ctx->bio ||
	    bio_end_sector(ctx->bio) != sector ||
	    bio_add_page(ctx->bio, page, plen, poff) != plen) {
		gfp_t gfp = mapping_gfp_constraint(page->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(gfp, bio_max_segs(nr_vecs));
		/*
		 * 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_readpage does.
		 */
		if (!ctx->bio)
			ctx->bio = bio_alloc(orig_gfp, 1);
		ctx->bio->bi_opf = REQ_OP_READ;
		if (ctx->rac)
			ctx->bio->bi_opf |= REQ_RAHEAD;
		ctx->bio->bi_iter.bi_sector = sector;
		bio_set_dev(ctx->bio, iomap->bdev);
		ctx->bio->bi_end_io = iomap_read_end_io;
		__bio_add_page(ctx->bio, page, 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_readpage(struct page *page, const struct iomap_ops *ops)
{
	struct iomap_iter iter = {
		.inode		= page->mapping->host,
		.pos		= page_offset(page),
		.len		= PAGE_SIZE,
	};
	struct iomap_readpage_ctx ctx = {
		.cur_page	= page,
	};
	int ret;

	trace_iomap_readpage(page->mapping->host, 1);

	while ((ret = iomap_iter(&iter, ops)) > 0)
		iter.processed = iomap_readpage_iter(&iter, &ctx, 0);

	if (ret < 0)
		SetPageError(page);

	if (ctx.bio) {
		submit_bio(ctx.bio);
		WARN_ON_ONCE(!ctx.cur_page_in_bio);
	} else {
		WARN_ON_ONCE(ctx.cur_page_in_bio);
		unlock_page(page);
	}

	/*
	 * Just like mpage_readahead and block_read_full_page, we always
	 * return 0 and just mark the page as PageError on errors.  This
	 * should be cleaned up throughout the stack eventually.
	 */
	return 0;
}
EXPORT_SYMBOL_GPL(iomap_readpage);

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_page && offset_in_page(iter->pos + done) == 0) {
			if (!ctx->cur_page_in_bio)
				unlock_page(ctx->cur_page);
			put_page(ctx->cur_page);
			ctx->cur_page = NULL;
		}
		if (!ctx->cur_page) {
			ctx->cur_page = readahead_page(ctx->rac);
			ctx->cur_page_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_page) {
		if (!ctx.cur_page_in_bio)
			unlock_page(ctx.cur_page);
		put_page(ctx.cur_page);
	}
}
EXPORT_SYMBOL_GPL(iomap_readahead);

/*
 * iomap_is_partially_uptodate checks whether blocks within a page are
 * uptodate or not.
 *
 * Returns true if all blocks which correspond to a file portion
 * we want to read within the page are uptodate.
 */
int
iomap_is_partially_uptodate(struct page *page, unsigned long from,
		unsigned long count)
{
	struct iomap_page *iop = to_iomap_page(page);
	struct inode *inode = page->mapping->host;
	unsigned len, first, last;
	unsigned i;

	/* Limit range to one page */
	len = min_t(unsigned, PAGE_SIZE - from, count);

	/* First and last blocks in range within page */
	first = from >> inode->i_blkbits;
	last = (from + len - 1) >> inode->i_blkbits;

	if (iop) {
		for (i = first; i <= last; i++)
			if (!test_bit(i, iop->uptodate))
				return 0;
		return 1;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);

int
iomap_releasepage(struct page *page, gfp_t gfp_mask)
{
	trace_iomap_releasepage(page->mapping->host, page_offset(page),
			PAGE_SIZE);

	/*
	 * mm accommodates an old ext3 case where clean pages might not have had
	 * the dirty bit cleared. Thus, it can send actual dirty pages to
	 * ->releasepage() via shrink_active_list(); skip those here.
	 */
	if (PageDirty(page) || PageWriteback(page))
		return 0;
	iomap_page_release(page);
	return 1;
}
EXPORT_SYMBOL_GPL(iomap_releasepage);

void
iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len)
{
	trace_iomap_invalidatepage(page->mapping->host, offset, len);

	/*
	 * If we're invalidating the entire page, clear the dirty state from it
	 * and release it to avoid unnecessary buildup of the LRU.
	 */
	if (offset == 0 && len == PAGE_SIZE) {
		WARN_ON_ONCE(PageWriteback(page));
		cancel_dirty_page(page);
		iomap_page_release(page);
	}
}
EXPORT_SYMBOL_GPL(iomap_invalidatepage);

#ifdef CONFIG_MIGRATION
int
iomap_migrate_page(struct address_space *mapping, struct page *newpage,
		struct page *page, enum migrate_mode mode)
{
	int ret;

	ret = migrate_page_move_mapping(mapping, newpage, page, 0);
	if (ret != MIGRATEPAGE_SUCCESS)
		return ret;

	if (page_has_private(page))
		attach_page_private(newpage, detach_page_private(page));

	if (mode != MIGRATE_SYNC_NO_COPY)
		migrate_page_copy(newpage, page);
	else
		migrate_page_states(newpage, page);
	return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL_GPL(iomap_migrate_page);
#endif /* CONFIG_MIGRATION */

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);
}

static int
iomap_read_page_sync(loff_t block_start, struct page *page, unsigned poff,
		unsigned plen, const struct iomap *iomap)
{
	struct bio_vec bvec;
	struct bio bio;

	bio_init(&bio, &bvec, 1);
	bio.bi_opf = REQ_OP_READ;
	bio.bi_iter.bi_sector = iomap_sector(iomap, block_start);
	bio_set_dev(&bio, iomap->bdev);
	__bio_add_page(&bio, page, plen, poff);
	return submit_bio_wait(&bio);
}

static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
		unsigned len, struct page *page)
{
	const struct iomap *srcmap = iomap_iter_srcmap(iter);
	struct iomap_page *iop = iomap_page_create(iter->inode, page);
	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 from = offset_in_page(pos), to = from + len, poff, plen;

	if (PageUptodate(page))
		return 0;
	ClearPageError(page);

	do {
		iomap_adjust_read_range(iter->inode, iop, &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;
			zero_user_segments(page, poff, from, to, poff + plen);
		} else {
			int status = iomap_read_page_sync(block_start, page,
					poff, plen, srcmap);
			if (status)
				return status;
		}
		iomap_set_range_uptodate(page, poff, plen);
	} while ((block_start += plen) < block_end);

	return 0;
}

static int iomap_write_begin_inline(const struct iomap_iter *iter,
		struct page *page)
{
	/* 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, page);
}

static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
		unsigned len, struct page **pagep)
{
	const struct iomap_page_ops *page_ops = iter->iomap.page_ops;
	const struct iomap *srcmap = iomap_iter_srcmap(iter);
	struct page *page;
	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 (page_ops && page_ops->page_prepare) {
		status = page_ops->page_prepare(iter->inode, pos, len);
		if (status)
			return status;
	}

	page = grab_cache_page_write_begin(iter->inode->i_mapping,
				pos >> PAGE_SHIFT, AOP_FLAG_NOFS);
	if (!page) {
		status = -ENOMEM;
		goto out_no_page;
	}

	if (srcmap->type == IOMAP_INLINE)
		status = iomap_write_begin_inline(iter, page);
	else if (srcmap->flags & IOMAP_F_BUFFER_HEAD)
		status = __block_write_begin_int(page, pos, len, NULL, srcmap);
	else
		status = __iomap_write_begin(iter, pos, len, page);

	if (unlikely(status))
		goto out_unlock;

	*pagep = page;
	return 0;

out_unlock:
	unlock_page(page);
	put_page(page);
	iomap_write_failed(iter->inode, pos, len);

out_no_page:
	if (page_ops && page_ops->page_done)
		page_ops->page_done(iter->inode, pos, 0, NULL);
	return status;
}

static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
		size_t copied, struct page *page)
{
	flush_dcache_page(page);

	/*
	 * The blocks that were entirely written will now be uptodate, so we
	 * don't have to worry about a readpage 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
	 * readpage 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 && !PageUptodate(page)))
		return 0;
	iomap_set_range_uptodate(page, offset_in_page(pos), len);
	__set_page_dirty_nobuffers(page);
	return copied;
}

static size_t iomap_write_end_inline(const struct iomap_iter *iter,
		struct page *page, loff_t pos, size_t copied)
{
	const struct iomap *iomap = &iter->iomap;
	void *addr;

	WARN_ON_ONCE(!PageUptodate(page));
	BUG_ON(!iomap_inline_data_valid(iomap));

	flush_dcache_page(page);
	addr = kmap_local_page(page) + 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 page *page)
{
	const struct iomap_page_ops *page_ops = iter->iomap.page_ops;
	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, page, pos, copied);
	} else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
		ret = block_write_end(NULL, iter->inode->i_mapping, pos, len,
				copied, page, NULL);
	} else {
		ret = __iomap_write_end(iter->inode, pos, len, copied, page);
	}

	/*
	 * 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;
	}
	unlock_page(page);

	if (old_size < pos)
		pagecache_isize_extended(iter->inode, old_size, pos);
	if (page_ops && page_ops->page_done)
		page_ops->page_done(iter->inode, pos, ret, page);
	put_page(page);

	if (ret < len)
		iomap_write_failed(iter->inode, pos, len);
	return ret;
}

static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
{
	loff_t length = iomap_length(iter);
	loff_t pos = iter->pos;
	ssize_t written = 0;
	long status = 0;

	do {
		struct page *page;
		unsigned long offset;	/* Offset into pagecache page */
		unsigned long bytes;	/* Bytes to write to page */
		size_t copied;		/* Bytes copied from user */

		offset = offset_in_page(pos);
		bytes = min_t(unsigned long, PAGE_SIZE - offset,
						iov_iter_count(i));
again:
		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.
		 */
		if (unlikely(fault_in_iov_iter_readable(i, bytes))) {
			status = -EFAULT;
			break;
		}

		status = iomap_write_begin(iter, pos, bytes, &page);
		if (unlikely(status))
			break;

		if (mapping_writably_mapped(iter->inode->i_mapping))
			flush_dcache_page(page);

		copied = copy_page_from_iter_atomic(page, offset, bytes, i);

		status = iomap_write_end(iter, pos, bytes, copied, page);

		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 (copied)
				bytes = copied;
			goto again;
		}
		pos += status;
		written += status;
		length -= status;

		balance_dirty_pages_ratelimited(iter->inode->i_mapping);
	} while (iov_iter_count(i) && length);

	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,
	};
	int ret;

	while ((ret = iomap_iter(&iter, ops)) > 0)
		iter.processed = iomap_write_iter(&iter, i);
	if (iter.pos == iocb->ki_pos)
		return ret;
	return iter.pos - iocb->ki_pos;
}
EXPORT_SYMBOL_GPL(iomap_file_buffered_write);

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);
	long status = 0;
	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 {
		unsigned long offset = offset_in_page(pos);
		unsigned long bytes = min_t(loff_t, PAGE_SIZE - offset, length);
		struct page *page;

		status = iomap_write_begin(iter, pos, bytes, &page);
		if (unlikely(status))
			return status;

		status = iomap_write_end(iter, pos, bytes, bytes, page);
		if (WARN_ON_ONCE(status == 0))
			return -EIO;

		cond_resched();

		pos += status;
		written += status;
		length -= status;

		balance_dirty_pages_ratelimited(iter->inode->i_mapping);
	} while (length);

	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 s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length)
{
	struct page *page;
	int status;
	unsigned offset = offset_in_page(pos);
	unsigned bytes = min_t(u64, PAGE_SIZE - offset, length);

	status = iomap_write_begin(iter, pos, bytes, &page);
	if (status)
		return status;

	zero_user(page, offset, bytes);
	mark_page_accessed(page);

	return iomap_write_end(iter, pos, bytes, bytes, page);
}

static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
{
	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;

	/* already zeroed?  we're done. */
	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
		return length;

	do {
		s64 bytes;

		if (IS_DAX(iter->inode))
			bytes = dax_iomap_zero(pos, length, iomap);
		else
			bytes = __iomap_zero_iter(iter, pos, length);
		if (bytes < 0)
			return bytes;

		pos += bytes;
		length -= bytes;
		written += bytes;
		if (did_zero)
			*did_zero = true;
	} while (length > 0);

	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_page_mkwrite_iter(struct iomap_iter *iter,
		struct page *page)
{
	loff_t length = iomap_length(iter);
	int ret;

	if (iter->iomap.flags & IOMAP_F_BUFFER_HEAD) {
		ret = __block_write_begin_int(page, iter->pos, length, NULL,
					      &iter->iomap);
		if (ret)
			return ret;
		block_commit_write(page, 0, length);
	} else {
		WARN_ON_ONCE(!PageUptodate(page));
		set_page_dirty(page);
	}

	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 page *page = vmf->page;
	ssize_t ret;

	lock_page(page);
	ret = page_mkwrite_check_truncate(page, iter.inode);
	if (ret < 0)
		goto out_unlock;
	iter.pos = page_offset(page);
	iter.len = ret;
	while ((ret = iomap_iter(&iter, ops)) > 0)
		iter.processed = iomap_page_mkwrite_iter(&iter, page);

	if (ret < 0)
		goto out_unlock;
	wait_for_stable_page(page);