path: root/fs/gfs2/aops.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/mpage.h>
#include <linux/fs.h>
#include <linux/writeback.h>
#include <linux/swap.h>
#include <linux/gfs2_ondisk.h>
#include <linux/backing-dev.h>
#include <linux/uio.h>
#include <trace/events/writeback.h>
#include <linux/sched/signal.h>

#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "inode.h"
#include "log.h"
#include "meta_io.h"
#include "quota.h"
#include "trans.h"
#include "rgrp.h"
#include "super.h"
#include "util.h"
#include "glops.h"
#include "aops.h"


void gfs2_trans_add_databufs(struct gfs2_inode *ip, struct folio *folio,
			     size_t from, size_t len)
{
	struct buffer_head *head = folio_buffers(folio);
	unsigned int bsize = head->b_size;
	struct buffer_head *bh;
	size_t to = from + len;
	size_t start, end;

	for (bh = head, start = 0; bh != head || !start;
	     bh = bh->b_this_page, start = end) {
		end = start + bsize;
		if (end <= from)
			continue;
		if (start >= to)
			break;
		set_buffer_uptodate(bh);
		gfs2_trans_add_data(ip->i_gl, bh);
	}
}

/**
 * gfs2_get_block_noalloc - Fills in a buffer head with details about a block
 * @inode: The inode
 * @lblock: The block number to look up
 * @bh_result: The buffer head to return the result in
 * @create: Non-zero if we may add block to the file
 *
 * Returns: errno
 */

static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
				  struct buffer_head *bh_result, int create)
{
	int error;

	error = gfs2_block_map(inode, lblock, bh_result, 0);
	if (error)
		return error;
	if (!buffer_mapped(bh_result))
		return -ENODATA;
	return 0;
}

/**
 * gfs2_write_jdata_folio - gfs2 jdata-specific version of block_write_full_folio
 * @folio: The folio to write
 * @wbc: The writeback control
 *
 * This is the same as calling block_write_full_folio, but it also
 * writes pages outside of i_size
 */
static int gfs2_write_jdata_folio(struct folio *folio,
				 struct writeback_control *wbc)
{
	struct inode * const inode = folio->mapping->host;
	loff_t i_size = i_size_read(inode);

	/*
	 * The folio 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."
	 */
	if (folio_pos(folio) < i_size &&
	    i_size < folio_pos(folio) + folio_size(folio))
		folio_zero_segment(folio, offset_in_folio(folio, i_size),
				folio_size(folio));

	return __block_write_full_folio(inode, folio, gfs2_get_block_noalloc,
			wbc);
}

/**
 * __gfs2_jdata_write_folio - The core of jdata writepage
 * @folio: The folio to write
 * @wbc: The writeback control
 *
 * Implements the core of write back. If a transaction is required then
 * the checked flag will have been set and the transaction will have
 * already been started before this is called.
 */
static int __gfs2_jdata_write_folio(struct folio *folio,
		struct writeback_control *wbc)
{
	struct inode *inode = folio->mapping->host;
	struct gfs2_inode *ip = GFS2_I(inode);

	if (folio_test_checked(folio)) {
		folio_clear_checked(folio);
		if (!folio_buffers(folio)) {
			create_empty_buffers(folio,
					inode->i_sb->s_blocksize,
					BIT(BH_Dirty)|BIT(BH_Uptodate));
		}
		gfs2_trans_add_databufs(ip, folio, 0, folio_size(folio));
	}
	return gfs2_write_jdata_folio(folio, wbc);
}

/**
 * gfs2_jdata_writepage - Write complete page
 * @page: Page to write
 * @wbc: The writeback control
 *
 * Returns: errno
 *
 */

static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
{
	struct folio *folio = page_folio(page);
	struct inode *inode = page->mapping->host;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);

	if (gfs2_assert_withdraw(sdp, ip->i_gl->gl_state == LM_ST_EXCLUSIVE))
		goto out;
	if (folio_test_checked(folio) || current->journal_info)
		goto out_ignore;
	return __gfs2_jdata_write_folio(folio, wbc);

out_ignore:
	folio_redirty_for_writepage(wbc, folio);
out:
	folio_unlock(folio);
	return 0;
}

/**
 * gfs2_writepages - Write a bunch of dirty pages back to disk
 * @mapping: The mapping to write
 * @wbc: Write-back control
 *
 * Used for both ordered and writeback modes.
 */
static int gfs2_writepages(struct address_space *mapping,
			   struct writeback_control *wbc)
{
	struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
	struct iomap_writepage_ctx wpc = { };
	int ret;

	/*
	 * Even if we didn't write enough pages here, we might still be holding
	 * dirty pages in the ail. We forcibly flush the ail because we don't
	 * want balance_dirty_pages() to loop indefinitely trying to write out
	 * pages held in the ail that it can't find.
	 */
	ret = iomap_writepages(mapping, wbc, &wpc, &gfs2_writeback_ops);
	if (ret == 0 && wbc->nr_to_write > 0)
		set_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags);
	return ret;
}

/**
 * gfs2_write_jdata_batch - Write back a folio batch's worth of folios
 * @mapping: The mapping
 * @wbc: The writeback control
 * @fbatch: The batch of folios
 * @done_index: Page index
 *
 * Returns: non-zero if loop should terminate, zero otherwise
 */

static int gfs2_write_jdata_batch(struct address_space *mapping,
				    struct writeback_control *wbc,
				    struct folio_batch *fbatch,
				    pgoff_t *done_index)
{
	struct inode *inode = mapping->host;
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	unsigned nrblocks;
	int i;
	int ret;
	size_t size = 0;
	int nr_folios = folio_batch_count(fbatch);

	for (i = 0; i < nr_folios; i++)
		size += folio_size(fbatch->folios[i]);
	nrblocks = size >> inode->i_blkbits;

	ret = gfs2_trans_begin(sdp, nrblocks, nrblocks);
	if (ret < 0)
		return ret;

	for (i = 0; i < nr_folios; i++) {
		struct folio *folio = fbatch->folios[i];

		*done_index = folio->index;

		folio_lock(folio);

		if (unlikely(folio->mapping != mapping)) {
continue_unlock:
			folio_unlock(folio);
			continue;
		}

		if (!folio_test_dirty(folio)) {
			/* someone wrote it for us */
			goto continue_unlock;
		}

		if (folio_test_writeback(folio)) {
			if (wbc->sync_mode != WB_SYNC_NONE)
				folio_wait_writeback(folio);
			else
				goto continue_unlock;
		}

		BUG_ON(folio_test_writeback(folio));
		if (!folio_clear_dirty_for_io(folio))
			goto continue_unlock;

		trace_wbc_writepage(wbc, inode_to_bdi(inode));

		ret = __gfs2_jdata_write_folio(folio, wbc);
		if (unlikely(ret)) {
			if (ret == AOP_WRITEPAGE_ACTIVATE) {
				folio_unlock(folio);
				ret = 0;
			} else {

				/*
				 * done_index is set past this page,
				 * so media errors will not choke
				 * background writeout for the entire
				 * file. This has consequences for
				 * range_cyclic semantics (ie. it may
				 * not be suitable for data integrity
				 * writeout).
				 */
				*done_index = folio_next_index(folio);
				ret = 1;
				break;
			}
		}

		/*
		 * We stop writing back only if we are not doing
		 * integrity sync. In case of integrity sync we have to
		 * keep going until we have written all the pages
		 * we tagged for writeback prior to entering thi