linux/fs/mpage.c

// SPDX-License-Identifier: GPL-2.0
/*
 * fs/mpage.c
 *
 * Copyright (C) 2002, Linus Torvalds.
 *
 * Contains functions related to preparing and submitting BIOs which contain
 * multiple pagecache pages.
 *
 * 15May2002	Andrew Morton
 *		Initial version
 * 27Jun2002	[email protected]
 *		use bio_add_page() to build bio's just the right size
 */

#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/kdev_t.h>
#include <linux/gfp.h>
#include <linux/bio.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/highmem.h>
#include <linux/prefetch.h>
#include <linux/mpage.h>
#include <linux/mm_inline.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include "internal.h"

/*
 * I/O completion handler for multipage BIOs.
 *
 * The mpage code never puts partial pages into a BIO (except for end-of-file).
 * If a page does not map to a contiguous run of blocks then it simply falls
 * back to block_read_full_folio().
 *
 * Why is this?  If a page's completion depends on a number of different BIOs
 * which can complete in any order (or at the same time) then determining the
 * status of that page is hard.  See end_buffer_async_read() for the details.
 * There is no point in duplicating all that complexity.
 */
static void mpage_read_end_io(struct bio *bio)
{ … }

static void mpage_write_end_io(struct bio *bio)
{ … }

static struct bio *mpage_bio_submit_read(struct bio *bio)
{ … }

static struct bio *mpage_bio_submit_write(struct bio *bio)
{ … }

/*
 * support function for mpage_readahead.  The fs supplied get_block might
 * return an up to date buffer.  This is used to map that buffer into
 * the page, which allows read_folio to avoid triggering a duplicate call
 * to get_block.
 *
 * The idea is to avoid adding buffers to pages that don't already have
 * them.  So when the buffer is up to date and the page size == block size,
 * this marks the page up to date instead of adding new buffers.
 */
static void map_buffer_to_folio(struct folio *folio, struct buffer_head *bh,
		int page_block)
{ … }

struct mpage_readpage_args { … };

/*
 * This is the worker routine which does all the work of mapping the disk
 * blocks and constructs largest possible bios, submits them for IO if the
 * blocks are not contiguous on the disk.
 *
 * We pass a buffer_head back and forth and use its buffer_mapped() flag to
 * represent the validity of its disk mapping and to decide when to do the next
 * get_block() call.
 */
static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
{ … }

/**
 * mpage_readahead - start reads against pages
 * @rac: Describes which pages to read.
 * @get_block: The filesystem's block mapper function.
 *
 * This function walks the pages and the blocks within each page, building and
 * emitting large BIOs.
 *
 * If anything unusual happens, such as:
 *
 * - encountering a page which has buffers
 * - encountering a page which has a non-hole after a hole
 * - encountering a page with non-contiguous blocks
 *
 * then this code just gives up and calls the buffer_head-based read function.
 * It does handle a page which has holes at the end - that is a common case:
 * the end-of-file on blocksize < PAGE_SIZE setups.
 *
 * BH_Boundary explanation:
 *
 * There is a problem.  The mpage read code assembles several pages, gets all
 * their disk mappings, and then submits them all.  That's fine, but obtaining
 * the disk mappings may require I/O.  Reads of indirect blocks, for example.
 *
 * So an mpage read of the first 16 blocks of an ext2 file will cause I/O to be
 * submitted in the following order:
 *
 * 	12 0 1 2 3 4 5 6 7 8 9 10 11 13 14 15 16
 *
 * because the indirect block has to be read to get the mappings of blocks
 * 13,14,15,16.  Obviously, this impacts performance.
 *
 * So what we do it to allow the filesystem's get_block() function to set
 * BH_Boundary when it maps block 11.  BH_Boundary says: mapping of the block
 * after this one will require I/O against a block which is probably close to
 * this one.  So you should push what I/O you have currently accumulated.
 *
 * This all causes the disk requests to be issued in the correct order.
 */
void mpage_readahead(struct readahead_control *rac, get_block_t get_block)
{ … }
EXPORT_SYMBOL(…);

/*
 * This isn't called much at all
 */
int mpage_read_folio(struct folio *folio, get_block_t get_block)
{ … }
EXPORT_SYMBOL(…);

/*
 * Writing is not so simple.
 *
 * If the page has buffers then they will be used for obtaining the disk
 * mapping.  We only support pages which are fully mapped-and-dirty, with a
 * special case for pages which are unmapped at the end: end-of-file.
 *
 * If the page has no buffers (preferred) then the page is mapped here.
 *
 * If all blocks are found to be contiguous then the page can go into the
 * BIO.  Otherwise fall back to the mapping's writepage().
 * 
 * FIXME: This code wants an estimate of how many pages are still to be
 * written, so it can intelligently allocate a suitably-sized BIO.  For now,
 * just allocate full-size (16-page) BIOs.
 */

struct mpage_data { … };

/*
 * We have our BIO, so we can now mark the buffers clean.  Make
 * sure to only clean buffers which we know we'll be writing.
 */
static void clean_buffers(struct folio *folio, unsigned first_unmapped)
{ … }

static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc,
		      void *data)
{ … }

/**
 * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them
 * @mapping: address space structure to write
 * @wbc: subtract the number of written pages from *@wbc->nr_to_write
 * @get_block: the filesystem's block mapper function.
 *
 * This is a library function, which implements the writepages()
 * address_space_operation.
 */
int
mpage_writepages(struct address_space *mapping,
		struct writeback_control *wbc, get_block_t get_block)
{ … }
EXPORT_SYMBOL(…);