path: root/fs/jbd2/commit.c

/*
 * linux/fs/jbd2/commit.c
 *
 * Written by Stephen C. Tweedie <sct@redhat.com>, 1998
 *
 * Copyright 1998 Red Hat corp --- All Rights Reserved
 *
 * This file is part of the Linux kernel and is made available under
 * the terms of the GNU General Public License, version 2, or at your
 * option, any later version, incorporated herein by reference.
 *
 * Journal commit routines for the generic filesystem journaling code;
 * part of the ext2fs journaling system.
 */

#include <linux/time.h>
#include <linux/fs.h>
#include <linux/jbd2.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/jiffies.h>
#include <linux/crc32.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <trace/events/jbd2.h>

/*
 * Default IO end handler for temporary BJ_IO buffer_heads.
 */
static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
{
	BUFFER_TRACE(bh, "");
	if (uptodate)
		set_buffer_uptodate(bh);
	else
		clear_buffer_uptodate(bh);
	unlock_buffer(bh);
}

/*
 * When an ext4 file is truncated, it is possible that some pages are not
 * successfully freed, because they are attached to a committing transaction.
 * After the transaction commits, these pages are left on the LRU, with no
 * ->mapping, and with attached buffers.  These pages are trivially reclaimable
 * by the VM, but their apparent absence upsets the VM accounting, and it makes
 * the numbers in /proc/meminfo look odd.
 *
 * So here, we have a buffer which has just come off the forget list.  Look to
 * see if we can strip all buffers from the backing page.
 *
 * Called under lock_journal(), and possibly under journal_datalist_lock.  The
 * caller provided us with a ref against the buffer, and we drop that here.
 */
static void release_buffer_page(struct buffer_head *bh)
{
	struct page *page;

	if (buffer_dirty(bh))
		goto nope;
	if (atomic_read(&bh->b_count) != 1)
		goto nope;
	page = bh->b_page;
	if (!page)
		goto nope;
	if (page->mapping)
		goto nope;

	/* OK, it's a truncated page */
	if (!trylock_page(page))
		goto nope;

	page_cache_get(page);
	__brelse(bh);
	try_to_free_buffers(page);
	unlock_page(page);
	page_cache_release(page);
	return;

nope:
	__brelse(bh);
}

/*
 * Done it all: now submit the commit record.  We should have
 * cleaned up our previous buffers by now, so if we are in abort
 * mode we can now just skip the rest of the journal write
 * entirely.
 *
 * Returns 1 if the journal needs to be aborted or 0 on success
 */
static int journal_submit_commit_record(journal_t *journal,
					transaction_t *commit_transaction,
					struct buffer_head **cbh,
					__u32 crc32_sum)
{
	struct journal_head *descriptor;
	struct commit_header *tmp;
	struct buffer_head *bh;
	int ret;
	int barrier_done = 0;
	struct timespec now = current_kernel_time();

	if (is_journal_aborted(journal))
		return 0;

	descriptor = jbd2_journal_get_descriptor_buffer(journal);
	if (!descriptor)
		return 1;

	bh = jh2bh(descriptor);

	tmp = (struct commit_header *)bh->b_data;
	tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
	tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK);
	tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid);
	tmp->h_commit_sec = cpu_to_be64(now.tv_sec);
	tmp->h_commit_nsec = cpu_to_be32(now.tv_nsec);

	if (JBD2_HAS_COMPAT_FEATURE(journal,
				    JBD2_FEATURE_COMPAT_CHECKSUM)) {
		tmp->h_chksum_type 	= JBD2_CRC32_CHKSUM;
		tmp->h_chksum_size 	= JBD2_CRC32_CHKSUM_SIZE;
		tmp->h_chksum[0] 	= cpu_to_be32(crc32_sum);
	}

	JBUFFER_TRACE(descriptor, "submit commit block");
	lock_buffer(bh);
	clear_buffer_dirty(bh);
	set_buffer_uptodate(bh);
	bh->b_end_io = journal_end_buffer_io_sync;

	if (journal->j_flags & JBD2_BARRIER &&
		!JBD2_HAS_INCOMPAT_FEATURE(journal,
					 JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
		set_buffer_ordered(bh);
		barrier_done = 1;
	}
	ret = submit_bh(WRITE_SYNC_PLUG, bh);
	if (barrier_done)
		clear_buffer_ordered(bh);

	/* is it possible for another commit to fail at roughly
	 * the same time as this one?  If so, we don't want to
	 * trust the barrier flag in the super, but instead want
	 * to remember if we sent a barrier request
	 */
	if (ret == -EOPNOTSUPP && barrier_done) {
		printk(KERN_WARNING
		       "JBD: barrier-based sync failed on %s - "
		       "disabling barriers\n", journal->j_devname);
		spin_lock(&journal->j_state_lock);
		journal->j_flags &= ~JBD2_BARRIER;
		spin_unlock(&journal->j_state_lock);

		/* And try again, without the barrier */
		lock_buffer(bh);
		set_buffer_uptodate(bh);
		clear_buffer_dirty(bh);