path: root/fs/iomap/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 (io