/*
 * linux/fs/jbd2/journal.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.
 *
 * Generic filesystem journal-writing code; part of the ext2fs
 * journaling system.
 *
 * This file manages journals: areas of disk reserved for logging
 * transactional updates.  This includes the kernel journaling thread
 * which is responsible for scheduling updates to the log.
 *
 * We do not actually manage the physical storage of the journal in this
 * file: that is left to a per-journal policy function, which allows us
 * to store the journal within a filesystem-specified area for ext2
 * journaling (ext2 can use a reserved inode for storing the log).
 */

#include <linux/module.h>
#include <linux/time.h>
#include <linux/fs.h>
#include <linux/jbd2.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/freezer.h>
#include <linux/pagemap.h>
#include <linux/kthread.h>
#include <linux/poison.h>
#include <linux/proc_fs.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/math64.h>
#include <linux/hash.h>

#define CREATE_TRACE_POINTS
#include <trace/events/jbd2.h>

#include <asm/uaccess.h>
#include <asm/page.h>

EXPORT_SYMBOL(jbd2_journal_start);
EXPORT_SYMBOL(jbd2_journal_restart);
EXPORT_SYMBOL(jbd2_journal_extend);
EXPORT_SYMBOL(jbd2_journal_stop);
EXPORT_SYMBOL(jbd2_journal_lock_updates);
EXPORT_SYMBOL(jbd2_journal_unlock_updates);
EXPORT_SYMBOL(jbd2_journal_get_write_access);
EXPORT_SYMBOL(jbd2_journal_get_create_access);
EXPORT_SYMBOL(jbd2_journal_get_undo_access);
EXPORT_SYMBOL(jbd2_journal_set_triggers);
EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
EXPORT_SYMBOL(jbd2_journal_release_buffer);
EXPORT_SYMBOL(jbd2_journal_forget);
#if 0
EXPORT_SYMBOL(journal_sync_buffer);
#endif
EXPORT_SYMBOL(jbd2_journal_flush);
EXPORT_SYMBOL(jbd2_journal_revoke);

EXPORT_SYMBOL(jbd2_journal_init_dev);
EXPORT_SYMBOL(jbd2_journal_init_inode);
EXPORT_SYMBOL(jbd2_journal_update_format);
EXPORT_SYMBOL(jbd2_journal_check_used_features);
EXPORT_SYMBOL(jbd2_journal_check_available_features);
EXPORT_SYMBOL(jbd2_journal_set_features);
EXPORT_SYMBOL(jbd2_journal_load);
EXPORT_SYMBOL(jbd2_journal_destroy);
EXPORT_SYMBOL(jbd2_journal_abort);
EXPORT_SYMBOL(jbd2_journal_errno);
EXPORT_SYMBOL(jbd2_journal_ack_err);
EXPORT_SYMBOL(jbd2_journal_clear_err);
EXPORT_SYMBOL(jbd2_log_wait_commit);
EXPORT_SYMBOL(jbd2_journal_start_commit);
EXPORT_SYMBOL(jbd2_journal_force_commit_nested);
EXPORT_SYMBOL(jbd2_journal_wipe);
EXPORT_SYMBOL(jbd2_journal_blocks_per_page);
EXPORT_SYMBOL(jbd2_journal_invalidatepage);
EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
EXPORT_SYMBOL(jbd2_journal_force_commit);
EXPORT_SYMBOL(jbd2_journal_file_inode);
EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);

static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
static void __journal_abort_soft (journal_t *journal, int errno);

/*
 * Helper function used to manage commit timeouts
 */

static void commit_timeout(unsigned long __data)
{
	struct task_struct * p = (struct task_struct *) __data;

	wake_up_process(p);
}

/*
 * kjournald2: The main thread function used to manage a logging device
 * journal.
 *
 * This kernel thread is responsible for two things:
 *
 * 1) COMMIT:  Every so often we need to commit the current state of the
 *    filesystem to disk.  The journal thread is responsible for writing
 *    all of the metadata buffers to disk.
 *
 * 2) CHECKPOINT: We cannot reuse a used section of the log file until all
 *    of the data in that part of the log has been rewritten elsewhere on
 *    the disk.  Flushing these old buffers to reclaim space in the log is
 *    known as checkpointing, and this thread is responsible for that job.
 */

static int kjournald2(void *arg)
{
	journal_t *journal = arg;
	transaction_t *transaction;

	/*
	 * Set up an interval timer which can be used to trigger a commit wakeup
	 * after the commit interval expires
	 */
	setup_timer(&journal->j_commit_timer, commit_timeout,
			(unsigned long)current);

	/* Record that the journal thread is running */
	journal->j_task = current;
	wake_up(&journal->j_wait_done_commit);

	printk(KERN_INFO "kjournald2 starting: pid %d, dev %s, "
	       "commit interval %ld seconds\n", current->pid,
	       journal->j_devname, journal->j_commit_interval / HZ);

	/*
	 * And now, wait forever for commit wakeup events.
	 */
	spin_lock(&journal->j_state_lock);

loop:
	if (journal->j_flags & JBD2_UNMOUNT)
		goto end_loop;

	jbd_debug(1, "commit_sequence=%d, commit_request=%d\n",
		journal->j_commit_sequence, journal->j_commit_request);

	if (journal->j_commit_sequence != journal->j_commit_request) {
		jbd_debug(1, "OK, requests differ\n");
		spin_unlock(&journal->j_state_lock);
		del_timer_sync(&journal->j_commit_timer);
		jbd2_journal_commit_transaction(journal);
		spin_lock(&journal->j_state_lock);
		goto loop;
	}

	wake_up(&journal->j_wait_done_commit);
	if (freezing(current)) {
		/*
		 * The simpler the better. Flushing journal isn't a
		 * good idea, because that depends on threads that may
		 * be already stopped.
		 */
		jbd_debug(1, "Now suspending kjournald2\n");
		spin_unlock(&journal->j_state_lock);
		refrigerator();
		spin_lock(&journal->j_state_lock);
	} else {
		/*
		 * We assume on resume that commits are already there,
		 * so we don't sleep
		 */
		DEFINE_WAIT(wait);
		int should_sleep = 1;

		prepare_to_wait(&journal->j_wait_commit, &wait,
				TASK_INTERRUPTIBLE);
		if (journal->j_commit_sequence != journal->j_commit_request)
			should_sleep = 0;
		transaction = journal->j_running_transaction;
		if (transaction && time_after_eq(jiffies,
						transaction->t_expires))
			should_sleep = 0;
		if (journal->j_flags & JBD2_UNMOUNT)
			should_sleep = 0;
		if (should_sleep) {
			spin_unlock(&journal->j_state_lock);
			schedule();
			spin_lock(&journal->j_state_lock);
		}
		finish_wait(&journal->j_wait_commit, &wait);
	}

	jbd_debug(1, "kjournald2 wakes\n");

	/*
	 * Were we woken up by a commit wakeup event?
	 */
	transaction = journal->j_running_transaction;
	if (transaction && time_after_eq(jiffies, transaction->t_expires)) {
		journal->j_commit_request = transaction->t_tid;
		jbd_debug(1, "woke because of timeout\n");
	}
	goto loop;

end_loop:
	spin_unlock(&journal->j_state_lock);
	del_timer_sync(&journal->j_commit_timer);
	journal->j_task = NULL;
	wake_up(&journal->j_wait_done_commit);
	jbd_debug(1, "Journal thread exiting.\n");
	return 0;
}

static int jbd2_journal_start_thread(journal_t *journal)
{
	struct task_struct *t;

	t = kthread_run(kjournald2, journal, "kjournald2");
	if (IS_ERR(t))
		return PTR_ERR(t);

	wait_event(journal->j_wait_done_commit, journal->j_task != NULL);
	return 0;
}

static void journal_kill_thread(journal_t *journal)
{
	spin_lock(&journal->j_state_lock);
	journal->j_flags |= JBD2_UNMOUNT;

	while (journal->j_task) {
		wake_up(&journal->j_wait_commit);
		spin_unlock(&journal->j_state_lock);
		wait_event(journal->j_wait_done_commit, journal->j_task == NULL);
		spin_lock(&journal->j_state_lock);
	}
	spin_unlock(&journal->j_state_lock);
}

/*
 * jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal.
 *
 * Writes a metadata buffer to a given disk block.  The actual IO is not
 * performed but a new buffer_head is constructed which labels the data
 * to be written with the correct destination disk block.
 *
 * Any magic-number escaping which needs to be done will cause a
 * copy-out here.  If the buffer happens to start with the
 * JBD2_MAGIC_NUMBER, then we can't write it to the log directly: the
 * magic number is only written to the log for descripter blocks.  In
 * this case, we copy the data and replace the first word with 0, and we
 * return a result code which indicates that this buffer needs to be
 * marked as an escaped buffer in the corresponding log descriptor
 * block.  The missing word can then be restored when the block is read
 * during recovery.
 *
 * If the source buffer has already been modified by a new transaction
 * since we took the last commit snapshot, we use the frozen copy of
 * that data for IO.  If we end up using the existing buffer_head's data
 * for the write, then we *have* to lock the buffer to prevent anyone
 * else from using and possibly modifying it while the IO is in
 * progress.
 *
 * The function returns a pointer to the buffer_heads to be used for IO.
 *
 * We assume that the journal has already been locked in this function.
 *
 * Return value:
 *  <0: Error
 * >=0: Finished OK
 *
 * On success:
 * Bit 0 set == escape performed on the data
 * Bit 1 set == buffer copy-out performed (kfree the data after IO)
 */

int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
				  struct journal_head  *jh_in,
				  struct journal_head **jh_out,
				  unsigned long long blocknr)
{
	int need_copy_out = 0;
	int done_copy_out = 0;
	int do_escape = 0;
	char *mapped_data;
	struct buffer_head *new_bh;
	struct journal_head *new_jh;
	struct page *new_page;
	unsigned int new_offset;
	struct buffer_head *bh_in = jh2bh(jh_in);
	struct jbd2_buffer_trigger_type *triggers;
	journal_t *journal = transaction->t_journal;

	/*
	 * The buffer really shouldn't be locked: only the current committing
	 * transaction is allowed to write it, so nobody else is allowed
	 * to do any IO.
	 *
	 * akpm: except if we're journalling data, and write() output is
	 * also part of a shared mapping, and another thread has
	 * decided to launch a writepage() against this buffer.
	 */
	J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));

	new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
	/* keep subsequent assertions sane */
	new_bh->b_state = 0;
	init_buffer(new_bh, NULL, NULL);
	atomic_set(&new_bh->b_count, 1);
	new_jh = jbd2_journal_add_journal_head(new_bh);	/* This sleeps */

	/*
	 * If a new transaction has already done a buffer copy-out, then
	 * we use that version of the data for the commit.
	 */
	jbd_lock_bh_state(bh_in);
repeat:
	if (jh_in->b_frozen_data) {
		done_copy_out = 1;
		new_page = virt_to_page(jh_in->b_frozen_data);
		new_offset = offset_in_page(jh_in->b_frozen_data);
		triggers = jh_in->b_frozen_triggers;
	} else {
		new_page = jh2bh(jh_in)->b_page;
		new_offset = offset_in_page(jh2bh(jh_in)->b_data);
		triggers = jh_in->b_triggers;
	}

	mapped_data = kmap_atomic(new_page, KM_USER0);
	/*
	 * Fire any commit trigger.  Do this before checking for escaping,
	 * as the trigger may modify the magic offset.  If a copy-out
	 * happens afterwards, it will have the correct data in the buffer.
	 */
	jbd2_buffer_commit_trigger(jh_in, mapped_data + new_offset,
				   triggers);

	/*
	 * Check for escaping
	 */
	if (*((__be32 *)(mapped_data + new_offset)) ==
				cpu_to_be32(JBD2_MAGIC_NUMBER)) {
		need_copy_out = 1;
		do_escape = 1;
	}
	kunmap_atomic(mapped_data, KM_USER0);

	/*
	 * Do we need to do a data copy?
	 */
	if (need_copy_out && !done_copy_out) {
		char *tmp;

		jbd_unlock_bh_state(bh_in);
		tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
		jbd_lock_bh_state(bh_in);
		if (jh_in->b_frozen_data) {
			jbd2_free(tmp, bh_in->b_size);
			goto repeat;
		}

		jh_in->b_frozen_data = tmp;
		mapped_data = kmap_atomic(new_page, KM_USER0);
		memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size);
		kunmap_atomic(mapped_data, KM_USER0);

		new_page = virt_to_page(tmp);
		new_offset = offset_in_page(tmp);
		done_copy_out = 1;

		/*
		 * This isn't strictly necessary, as we're using frozen
		 * data for the escaping, but it keeps consistency with
		 * b_frozen_data usage.
		 */
		jh_in->b_frozen_triggers = jh_in->b_triggers;
	}

	/*
	 * Did we need to do an escaping?  Now we've done all the
	 * copying, we can finally do so.
	 */
	if (do_escape) {
		mapped_data = kmap_atomic(new_page, KM_USER0);
		*((unsigned int *)(mapped_data + new_offset)) = 0;
		kunmap_atomic(mapped_data, KM_USER0);
	}

	set_bh_page(new_bh, new_page, new_offset);
	new_jh->b_transaction = NULL;
	new_bh->b_size = jh2bh(jh_in)->b_size;
	new_bh->b_bdev = transaction->t_journal->j_dev;
	new_bh->b_blocknr = blocknr;
	set_buffer_mapped(new_bh);
	set_buffer_dirty(new_bh);

	*jh_out = new_jh;

	/*
	 * The to-be-written buffer needs to get moved to the io queue,
	 * and the original buffer whose contents we are shadowing or
	 * copying is moved to the transaction's shadow queue.
	 */
	JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
	spin_lock(&journal->j_list_lock);
	__jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
	spin_unlock(&journal->j_list_lock);
	jbd_unlock_bh_state(bh_in);

	JBUFFER_TRACE(new_jh, "file as BJ_IO");
	jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);

	return do_escape | (done_copy_out << 1);
}

/*
 * Allocation code for the journal file.  Manage the space left in the
 * journal, so that we can begin checkpointing when appropriate.
 */

/*
 * __jbd2_log_space_left: Return the number of free blocks left in the journal.
 *
 * Called with the journal already locked.
 *
 * Called under j_state_lock
 */

int __jbd2_log_space_left(journal_t *journal)
{
	int left = journal->j_free;

	assert_spin_locked(&journal->j_state_lock);

	/*
	 * Be pessimistic here about the number of those free blocks which
	 * might be required for log descriptor control blocks.
	 */

#define MIN_LOG_RESERVED_BLOCKS 32 /* Allow for rounding errors */

	left -= MIN_LOG_RESERVED_BLOCKS;

	if (left <= 0)
		return 0;
	left -= (left >> 3);
	return left;
}

/*
 * Called under j_state_lock.  Returns true if a transaction commit was started.
 */
int __jbd2_log_start_commit(journal_t *journal, tid_t target)
{
	/*
	 * Are we already doing a recent enough commit?
	 */
	if (!tid_geq(journal->j_commit_request, target)) {
		/*
		 * We want a new commit: OK, mark the request and wakup the
		 * commit thread.  We do _not_ do the commit ourselves.
		 */

		journal->j_commit_request = target;
		jbd_debug(1, "JBD: requesting commit %d/%d\n",
			  journal->j_commit_request,
			  journal->j_commit_sequence);
		wake_up(&journal->j_wait_commit);
		return 1;
	}
	return 0;
}

int jbd2_log_start_commit(journal_t *journal, tid_t tid)
{
	int ret;

	spin_lock(&journal->j_state_lock);
	ret = __jbd2_log_start_commit(journal, tid);
	spin_unlock(&journal->j_state_lock);
	return ret;
}

/*
 * Force and wait upon a commit if the calling process is not within
 * transaction.  This is used for forcing out undo-protected data which contains
 * bitmaps, when the fs is running out of space.
 *
 * We can only force the running transaction if we don't have an active handle;
 * otherwise, we will deadlock.
 *
 * Returns true if a transaction was started.
 */
int jbd2_journal_force_commit_nested(journal_t *journal)
{
	transaction_t *transaction = NULL;
	tid_t tid;

	spin_lock(&journal->j_state_lock);
	if (journal->j_running_transaction && !current->journal_info) {
		transaction = journal->j_running_transaction;
		__jbd2_log_start_commit(journal, transaction->t_tid);
	} else if (journal->j_committing_transaction)
		transaction = journal->j_committing_transaction;

	if (!transaction) {
		spin_unlock(&journal->j_state_lock);
		return 0;	/* Nothing to retry */
	}

	tid = transaction->t_tid;
	spin_unlock(&journal->j_state_lock);
	jbd2_log_wait_commit(journal, tid);
	return 1;
}

/*
 * Start a commit of the current running transaction (if any).  Returns true
 * if a transaction is going to be committed (or is currently already
 * committing), and fills its tid in at *ptid
 */
int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
{
	int ret = 0;

	spin_lock(&journal->j_state_lock);
	if (journal->j_running_transaction) {
		tid_t tid = journal->j_running_transaction->t_tid;

		__jbd2_log_start_commit(journal, tid);
		/* There's a running transaction and we've just made sure
		 * it's commit has been scheduled. */
		if (ptid)
			*ptid = tid;
		ret = 1;
	} else if (journal->j_committing_transaction) {
		/*
		 * If ext3_write_super() recently started a commit, then we
		 * have to wait for completion of that transaction
		 */
		if (ptid)
			*ptid = journal->j_committing_transaction->t_tid;
		ret = 1;
	}
	spin_unlock(&journal->j_state_lock);
	return ret;
}

/*
 * Wait for a specified commit to complete.
 * The caller may not hold the journal lock.
 */
int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
{
	int err = 0;

#ifdef CONFIG_JBD2_DEBUG
	spin_lock(&journal->j_state_lock);
	if (!tid_geq(journal->j_commit_request, tid)) {
		printk(KERN_EMERG
		       "%s: error: j_commit_request=%d, tid=%d\n",
		       __func__, journal->j_commit_request, tid);
	}
	spin_unlock(&journal->j_state_lock);
#endif
	spin_lock(&journal->j_state_lock);
	while (tid_gt(tid, journal->j_commit_sequence)) {
		jbd_debug(1, "JBD: want %d, j_commit_sequence=%d\n",
				  tid, journal->j_commit_sequence);
		wake_up(&journal->j_wait_commit);
		spin_unlock(&journal->j_state_lock);
		wait_event(journal->j_wait_done_commit,
				!tid_gt(tid, journal->j_commit_sequence));
		spin_lock(&journal->j_state_lock);
	}
	spin_unlock(&journal->j_state_lock);

	if (unlikely(is_journal_aborted(journal))) {
		printk(KERN_EMERG "journal commit I/O error\n");
		err = -EIO;
	}
	return err;
}

/*
 * Log buffer allocation routines:
 */

int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
{
	unsigned long blocknr;

	spin_lock(&journal->j_state_lock);
	J_ASSERT(journal->j_free > 1);

	blocknr = journal->j_head;
	journal->j_head++;
	journal->j_free--;
	if (journal->j_head == journal->j_last)
		journal->j_head = journal->j_first;
	spin_unlock(&journal->j_state_lock);
	return jbd2_journal_bmap(journal, blocknr, retp);
}

/*
 * Conversion of logical to physical block numbers for the journal
 *
 * On external journals the journal blocks are identity-mapped, so
 * this is a no-op.  If needed, we can use j_blk_offset - everything is
 * ready.
 */
int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
		 unsigned long long *retp)
{
	int err = 0;
	unsigned long long ret;

	if (journal->j_inode) {
		ret = bmap(journal->j_inode, blocknr);
		if (ret)
			*retp = ret;
		else {
			printk(KERN_ALERT "%s: journal block not found "
					"at offset %lu on %s\n",
			       __func__, blocknr, journal->j_devname);
			err = -EIO;
			__journal_abort_soft(journal, err);
		}
	} else {
		*retp = blocknr; /* +journal->j_blk_offset */
	}
	return err;
}

/*
 * We play buffer_head aliasing tricks to write data/metadata blocks to
 * the journal without copying their contents, but for journal
 * descriptor blocks we do need to generate bona fide buffers.
 *
 * After the caller of jbd2_journal_get_descriptor_buffer() has finished modifying
 * the buffer's contents they really should run flush_dcache_page(bh->b_page).
 * But we don't bother doing that, so there will be coherency problems with
 * mmaps of blockdevs which hold live JBD-controlled filesystems.
 */
struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
{
	struct buffer_head *bh;
	unsigned long long blocknr;
	int err;

	err = jbd2_journal_next_log_block(journal, &blocknr);

	if (err)
		return NULL;

	bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
	if (!bh)
		return NULL;
	lock_buffer(bh);
	memset(bh->b_data, 0, journal->j_blocksize);
	set_buffer_uptodate(bh);
	unlock_buffer(bh);
	BUFFER_TRACE(bh, "return this buffer");
	return jbd2_journal_add_journal_head(bh);
}

struct jbd2_stats_proc_session {
	journal_t *journal;
	struct transaction_stats_s *stats;
	int start;
	int max;
};

static void *jbd2_history_skip_empty(struct jbd2_stats_proc_session *s,
					struct transaction_stats_s *ts,
					int first)
{
	if (ts == s->stats + s->max)
		ts = s->stats;
	if (!first && ts == s->stats + s->start)
		return NULL;
	while (ts->ts_type == 0) {
		ts++;
		if (ts == s->stats + s->max)
			ts = s->stats;
		if (ts == s->stats + s->start)
			return NULL;
	}
	return ts;

}

static void *jbd2_seq_history_start(struct seq_file *seq, loff_t *pos)
{
	struct jbd2_stats_proc_session *s = seq->private;
	struct transaction_stats_s *ts;
	int l = *pos;

	if (l == 0)
		return SEQ_START_TOKEN;
	ts = jbd2_history_skip_empty(s, s->stats + s->start, 1);
	if (!ts)
		return NULL;
	l--;
	while (l) {
		ts = jbd2_history_skip_empty(s, ++ts, 0);
		if (!ts)
			break;
		l--;
	}
	return ts;
}

static void *jbd2_seq_history_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct jbd2_stats_proc_session *s = seq->private;
	struct transaction_stats_s *ts = v;

	++*pos;
	if (v == SEQ_START_TOKEN)
		return jbd2_history_skip_empty(s, s->stats + s->start, 1);
	else
		return jbd2_history_skip_empty(s, ++ts, 0);
}

static int jbd2_seq_history_show(struct seq_file *seq, void *v)
{
	struct transaction_stats_s *ts = v;
	if (v == SEQ_START_TOKEN) {
		seq_printf(seq, "%-4s %-5s %-5s %-5s %-5s %-5s %-5s %-6s %-5s "
				"%-5s %-5s %-5s %-5s %-5s\n", "R/C", "tid",
				"wait", "run", "lock", "flush", "log", "hndls",
				"block", "inlog", "ctime", "write", "drop",
				"close");
		return 0;
	}
	if (ts->ts_type == JBD2_STATS_RUN)
		seq_printf(seq, "%-4s %-5lu %-5u %-5u %-5u %-5u %-5u "
				"%-6lu %-5lu %-5lu\n", "R", ts->ts_tid,
				jiffies_to_msecs(ts->u.run.rs_wait),
				jiffies_to_msecs(ts->u.run.rs_running),
				jiffies_to_msecs(ts->u.run.rs_locked),
				jiffies_to_msecs(ts->u.run.rs_flushing),
				jiffies_to_msecs(ts->u.run.rs_logging),
				ts->u.run.rs_handle_count,
				ts->u.run.rs_blocks,
				ts->u.run.rs_blocks_logged);
	else if (ts->ts_type == JBD2_STATS_CHECKPOINT)
		seq_printf(seq, "%-4s %-5lu %48s %-5u %-5lu %-5lu %-5lu\n",
				"C", ts->ts_tid, " ",
				jiffies_to_msecs(ts->u.chp.cs_chp_time),
				ts->u.chp.cs_written, ts->u.chp.cs_dropped,
				ts->u.chp.cs_forced_to_close);
	else
		J_ASSERT(0);
	return 0;
}

static void jbd2_seq_history_stop(struct seq_file *seq, void *v)
{
}

static struct seq_operations jbd2_seq_history_ops = {
	.start  = jbd2_seq_history_start,
	.next   = jbd2_seq_history_next,
	.stop   = jbd2_seq_history_stop,
	.show   = jbd2_seq_history_show,
};

static int jbd2_seq_history_open(struct inode *inode, struct file *file)
{
	journal_t *journal = PDE(inode)->data;
	struct jbd2_stats_proc_session *s;
	int rc, size;

	s = kmalloc(sizeof(*s), GFP_KERNEL);
	if (s == NULL)
		return -ENOMEM;
	size = sizeof(struct transaction_stats_s) * journal->j_history_max;
	s->stats = kmalloc(size, GFP_KERNEL);
	if (s->stats == NULL) {
		kfree(s);
		return -ENOMEM;
	}
	spin_lock(&journal->j_history_lock);
	memcpy(s->stats, journal->j_history, size);
	s->max = journal->j_history_max;
	s->start = journal->j_history_cur % s->max;
	spin_unlock(&journal->j_history_lock);

	rc = seq_open(file, &jbd2_seq_history_ops);
	if (rc == 0) {
		struct seq_file *m = file->private_data;
		m->private = s;
	} else {
		kfree(s->stats);
		kfree(s);
	}
	return rc;

}

static int jbd2_seq_history_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq = file->private_data;
	struct jbd2_stats_proc_session *s = seq->private;

	kfree(s->stats);
	kfree(s);
	return seq_release(inode, file);
}

static struct file_operations jbd2_seq_history_fops = {
	.owner		= THIS_MODULE,
	.open           = jbd2_seq_history_open,
	.read           = seq_read,
	.llseek         = seq_lseek,
	.release        = jbd2_seq_history_release,
};

static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos)
{
	return *pos ? NULL : SEQ_START_TOKEN;
}

static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos)
{
	return NULL;
}

static int jbd2_seq_info_show(struct seq_file *seq, void *v)
{
	struct jbd2_stats_proc_session *s = seq->private;

	if (v != SEQ_START_TOKEN)
		return 0;
	seq_printf(seq, "%lu transaction, each upto %u blocks\n",
			s->stats->ts_tid,
			s->journal->j_max_transaction_buffers);
	if (s->stats->ts_tid == 0)
		return 0;
	seq_printf(seq, "average: \n  %ums waiting for transaction\n",
	    jiffies_to_msecs(s->stats->u.run.rs_wait / s->stats->ts_tid));
	seq_printf(seq, "  %ums running transaction\n",
	    jiffies_to_msecs(s->stats->u.run.rs_running / s->stats->ts_tid));
	seq_printf(seq, "  %ums transaction was being locked\n",
	    jiffies_to_msecs(s->stats->u.run.rs_locked / s->stats->ts_tid));
	seq_printf(seq, "  %ums flushing data (in ordered mode)\n",
	    jiffies_to_msecs(s->stats->u.run.rs_flushing / s->stats->ts_tid));
	seq_printf(seq, "  %ums logging transaction\n",
	    jiffies_to_msecs(s->stats->u.run.rs_logging / s->stats->ts_tid));
	seq_printf(seq, "  %lluus average transaction commit time\n",
		   div_u64(s->journal->j_average_commit_time, 1000));
	seq_printf(seq, "  %lu handles per transaction\n",
	    s->stats->u.run.rs_handle_count / s->stats->ts_tid);
	seq_printf(seq, "  %lu blocks per transaction\n",
	    s->stats->u.run.rs_blocks / s->stats->ts_tid);
	seq_printf(seq, "  %lu logged blocks per transaction\n",
	    s->stats->u.run.rs_blocks_logged / s->stats->ts_tid);
	return 0;
}

static void jbd2_seq_info_stop(struct seq_file *seq, void *v)
{
}

static struct seq_operations jbd2_seq_info_ops = {
	.start  = jbd2_seq_info_start,
	.next   = jbd2_seq_info_next,
	.stop   = jbd2_seq_info_stop,
	.show   = jbd2_seq_info_show,
};

static int jbd2_seq_info_open(struct inode *inode, struct file *file)
{
	journal_t *journal = PDE(inode)->data;
	struct jbd2_stats_proc_session *s;
	int rc, size;

	s = kmalloc(sizeof(*s), GFP_KERNEL);
	if (s == NULL)
		return -ENOMEM;
	size = sizeof(struct transaction_stats_s);
	s->stats = kmalloc(size, GFP_KERNEL);
	if (s->stats == NULL) {
		kfree(s);
		return -ENOMEM;
	}
	spin_lock(&journal->j_history_lock);
	memcpy(s->stats, &journal->j_stats, size);
	s->journal = journal;
	spin_unlock(&journal->j_history_lock);

	rc = seq_open(file, &jbd2_seq_info_ops);
	if (rc == 0) {
		struct seq_file *m = file->private_data;
		m->private = s;
	} else {
		kfree(s->stats);
		kfree(s);
	}
	return rc;

}

static int jbd2_seq_info_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq = file->private_data;
	struct jbd2_stats_proc_session *s = seq->private;
	kfree(s->stats);
	kfree(s);
	return seq_release(inode, file);
}

static struct file_operations jbd2_seq_info_fops = {
	.owner		= THIS_MODULE,
	.open           = jbd2_seq_info_open,
	.read           = seq_read,
	.llseek         = seq_lseek,
	.release        = jbd2_seq_info_release,
};

static struct proc_dir_entry *proc_jbd2_stats;

static void jbd2_stats_proc_init(journal_t *journal)
{
	journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats);
	if (journal->j_proc_entry) {
		proc_create_data("history", S_IRUGO, journal->j_proc_entry,
				 &jbd2_seq_history_fops, journal);
		proc_create_data("info", S_IRUGO, journal->j_proc_entry,
				 &jbd2_seq_info_fops, journal);
	}
}

static void jbd2_stats_proc_exit(journal_t *journal)
{
	remove_proc_entry("info", journal->j_proc_entry);
	remove_proc_entry("history", journal->j_proc_entry);
	remove_proc_entry(journal->j_devname, proc_jbd2_stats);
}

static void journal_init_stats(journal_t *journal)
{
	int size;

	if (!proc_jbd2_stats)
		return;

	journal->j_history_max = 100;
	size = sizeof(struct transaction_stats_s) * journal->j_history_max;
	journal->j_history = kzalloc(size, GFP_KERNEL);
	if (!journal->j_history) {
		journal->j_history_max = 0;
		return;
	}
	spin_lock_init(&journal->j_history_lock);
}

/*
 * Management for journal control blocks: functions to create and
 * destroy journal_t structures, and to initialise and read existing
 * journal blocks from disk.  */

/* First: create and setup a journal_t object in memory.  We initialise
 * very few fields yet: that has to wait until we have created the
 * journal structures from from scratch, or loaded them from disk. */

static journal_t * journal_init_common (void)
{
	journal_t *journal;
	int err;

	journal = kzalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL);
	if (!journal)
		goto fail;

	init_waitqueue_head(&journal->j_wait_transaction_locked);
	init_waitqueue_head(&journal->j_wait_logspace);
	init_waitqueue_head(&journal->j_wait_done_commit);
	init_waitqueue_head(&journal->j_wait_checkpoint);
	init_waitqueue_head(&journal->j_wait_commit);
	init_waitqueue_head(&journal->j_wait_updates);
	mutex_init(&journal->j_barrier);
	mutex_init(&journal->j_checkpoint_mutex);
	spin_lock_init(&journal->j_revoke_lock);
	spin_lock_init(&journal->j_list_lock);
	spin_lock_init(&journal->j_state_lock);

	journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE);
	journal->j_min_batch_time = 0;
	journal->j_max_batch_time = 15000; /* 15ms */

	/* The journal is marked for error until we succeed with recovery! */
	journal->j_flags = JBD2_ABORT;

	/* Set up a default-sized revoke table for the new mount. */
	err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
	if (err) {
		kfree(journal);
		goto fail;
	}

	journal_init_stats(journal);

	return journal;
fail:
	return NULL;
}

/* jbd2_journal_init_dev and jbd2_journal_init_inode:
 *
 * Create a journal structure assigned some fixed set of disk blocks to
 * the journal.  We don't actually touch those disk blocks yet, but we
 * need to set up all of the mapping information to tell the journaling
 * system where the journal blocks are.
 *
 */

/**
 *  journal_t * jbd2_journal_init_dev() - creates and initialises a journal structure
 *  @bdev: Block device on which to create the journal
 *  @fs_dev: Device which hold journalled filesystem for this journal.
 *  @start: Block nr Start of journal.
 *  @len:  Length of the journal in blocks.
 *  @blocksize: blocksize of journalling device
 *
 *  Returns: a newly created journal_t *
 *
 *  jbd2_journal_init_dev creates a journal which maps a fixed contiguous
 *  range of blocks on an arbitrary block device.
 *
 */
journal_t * jbd2_journal_init_dev(struct block_device *bdev,
			struct block_device *fs_dev,
			unsigned long long start, int len, int blocksize)
{
	journal_t *journal = journal_init_common();
	struct buffer_head *bh;
	char *p;
	int n;

	if (!journal)
		return NULL;

	/* journal descriptor can store up to n blocks -bzzz */
	journal->j_blocksize = blocksize;
	jbd2_stats_proc_init(journal);
	n = journal->j_blocksize / sizeof(journal_block_tag_t);
	journal->j_wbufsize = n;
	journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
	if (!journal->j_wbuf) {
		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
			__func__);
		goto out_err;
	}
	journal->j_dev = bdev;
	journal->j_fs_dev = fs_dev;
	journal->j_blk_offset = start;
	journal->j_maxlen = len;
	bdevname(journal->j_dev, journal->j_devname);
	p = journal->j_devname;
	while ((p = strchr(p, '/')))
		*p = '!';

	bh = __getblk(journal->j_dev, start, journal->j_blocksize);
	if (!bh) {
		printk(KERN_ERR
		       "%s: Cannot get buffer for journal superblock\n",
		       __func__);
		goto out_err;
	}
	journal->j_sb_buffer = bh;
	journal->j_superblock = (journal_superblock_t *)bh->b_data;

	return journal;
out_err:
	jbd2_stats_proc_exit(journal);
	kfree(journal);
	return NULL;
}

/**
 *  journal_t * jbd2_journal_init_inode () - creates a journal which maps to a inode.
 *  @inode: An inode to create the journal in
 *
 * jbd2_journal_init_inode creates a journal which maps an on-disk inode as
 * the journal.  The inode must exist already, must support bmap() and
 * must have all data blocks preallocated.
 */
journal_t * jbd2_journal_init_inode (struct inode *inode)
{
	struct buffer_head *bh;
	journal_t *journal = journal_init_common();
	char *p;
	int err;
	int n;
	unsigned long long blocknr;

	if (!journal)
		return NULL;

	journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev;
	journal->j_inode = inode;
	bdevname(journal->j_dev, journal->j_devname);
	p = journal->j_devname;
	while ((p = strchr(p, '/')))
		*p = '!';
	p = journal->j_devname + strlen(journal->j_devname);
	sprintf(p, ":%lu", journal->j_inode->i_ino);
	jbd_debug(1,
		  "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n",
		  journal, inode->i_sb->s_id, inode->i_ino,
		  (long long) inode->i_size,
		  inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize);

	journal->j_maxlen = inode->i_size >> inode->i_sb->s_blocksize_bits;
	journal->j_blocksize = inode->i_sb->s_blocksize;
	jbd2_stats_proc_init(journal);

	/* journal descriptor can store up to n blocks -bzzz */
	n = journal->j_blocksize / sizeof(journal_block_tag_t);
	journal->j_wbufsize = n;
	journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
	if (!journal->j_wbuf) {
		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
			__func__);
		goto out_err;
	}

	err = jbd2_journal_bmap(journal, 0, &blocknr);
	/* If that failed, give up */
	if (err) {
		printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
		       __func__);
		goto out_err;
	}

	bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
	if (!bh) {
		printk(KERN_ERR
		       "%s: Cannot get buffer for journal superblock\n",
		       __func__);
		goto out_err;
	}
	journal->j_sb_buffer = bh;
	journal->j_superblock = (journal_superblock_t *)bh->b_data;

	return journal;
out_err:
	jbd2_stats_proc_exit(journal);
	kfree(journal);
	return NULL;
}

/*
 * If the journal init or create aborts, we need to mark the journal
 * superblock as being NULL to prevent the journal destroy from writing
 * back a bogus superblock.
 */
static void journal_fail_superblock (journal_t *journal)
{
	struct buffer_head *bh = journal->j_sb_buffer;
	brelse(bh);
	journal->j_sb_buffer = NULL;
}

/*
 * Given a journal_t structure, initialise the various fields for
 * startup of a new journaling session.  We use this both when creating
 * a journal, and after recovering an old journal to reset it for
 * subsequent use.
 */

static int journal_reset(journal_t *journal)
{
	journal_superblock_t *sb = journal->j_superblock;
	unsigned long long first, last;

	first = be32_to_cpu(sb->s_first);
	last = be32_to_cpu(sb->s_maxlen);

	journal->j_first = first;
	journal->j_last = last;

	journal->j_head = first;
	journal->j_tail = first;
	journal->j_free = last - first;

	journal->j_tail_sequence = journal->j_transaction_sequence;
	journal->j_commit_sequence = journal->j_transaction_sequence - 1;
	journal->j_commit_request = journal->j_commit_sequence;

	journal->j_max_transaction_buffers = journal->j_maxlen / 4;

	/* Add the dynamic fields and write it to disk. */
	jbd2_journal_update_superblock(journal, 1);
	return jbd2_journal_start_thread(journal);
}

/**
 * void jbd2_journal_update_superblock() - Update journal sb on disk.
 * @journal: The journal to update.
 * @wait: Set to '0' if you don't want to wait for IO completion.
 *
 * Update a journal's dynamic superblock fields and write it to disk,
 * optionally waiting for the IO to complete.
 */
void jbd2_journal_update_superblock(journal_t *journal, int wait)
{
	journal_superblock_t *sb = journal->j_superblock;
	struct buffer_head *bh = journal->j_sb_buffer;

	/*
	 * As a special case, if the on-disk copy is already marked as needing
	 * no recovery (s_start == 0) and there are no outstanding transactions
	 * in the filesystem, then we can safely defer the superblock update
	 * until the next commit by setting JBD2_FLUSHED.  This avoids
	 * attempting a write to a potential-readonly device.
	 */
	if (sb->s_start == 0 && journal->j_tail_sequence ==
				journal->j_transaction_sequence) {
		jbd_debug(1,"JBD: Skipping superblock update on recovered sb "
			"(start %ld, seq %d, errno %d)\n",
			journal->j_tail, journal->j_tail_sequence,
			journal->j_errno);
		goto out;
	}

	if (buffer_write_io_error(bh)) {
		/*
		 * Oh, dear.  A previous attempt to write the journal
		 * superblock failed.  This could happen because the
		 * USB device was yanked out.  Or it could happen to
		 * be a transient write error and maybe the block will
		 * be remapped.  Nothing we can do but to retry the
		 * write and hope for the best.
		 */
		printk(KERN_ERR "JBD2: previous I/O error detected "
		       "for journal superblock update for %s.\n",
		       journal->j_devname);
		clear_buffer_write_io_error(bh);
		set_buffer_uptodate(bh);
	}

	spin_lock(&journal->j_state_lock);
	jbd_debug(1,"JBD: updating superblock (start %ld, seq %d, errno %d)\n",
		  journal->j_tail, journal->j_tail_sequence, journal->j_errno);

	sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
	sb->s_start    = cpu_to_be32(journal->j_tail);
	sb->s_errno    = cpu_to_be32(journal->j_errno);
	spin_unlock(&journal->j_state_lock);

	BUFFER_TRACE(bh, "marking dirty");
	mark_buffer_dirty(bh);
	if (wait) {
		sync_dirty_buffer(bh);
		if (buffer_write_io_error(bh)) {
			printk(KERN_ERR "JBD2: I/O error detected "
			       "when updating journal superblock for %s.\n",
			       journal->j_devname);
			clear_buffer_write_io_error(bh);
			set_buffer_uptodate(bh);
		}
	} else
		ll_rw_block(SWRITE, 1, &bh);

out:
	/* If we have just flushed the log (by marking s_start==0), then
	 * any future commit will have to be careful to update the
	 * superblock again to re-record the true start of the log. */

	spin_lock(&journal->j_state_lock);
	if (sb->s_start)
		journal->j_flags &= ~JBD2_FLUSHED;
	else
		journal->j_flags |= JBD2_FLUSHED;
	spin_unlock(&journal->j_state_lock);
}

/*
 * Read the superblock for a given journal, performing initial
 * validation of the format.
 */

static int journal_get_superblock(journal_t *journal)
{
	struct buffer_head *bh;
	journal_superblock_t *sb;
	int err = -EIO;

	bh = journal->j_sb_buffer;

	J_ASSERT(bh != NULL);
	if (!buffer_uptodate(bh)) {
		ll_rw_block(READ, 1, &bh);
		wait_on_buffer(bh);
		if (!buffer_uptodate(bh)) {
			printk (KERN_ERR
				"JBD: IO error reading journal superblock\n");
			goto out;
		}
	}

	sb = journal->j_superblock;

	err = -EINVAL;

	if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) ||
	    sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) {
		printk(KERN_WARNING "JBD: no valid journal superblock found\n");
		goto out;
	}

	switch(be32_to_cpu(sb->s_header.h_blocktype)) {
	case JBD2_SUPERBLOCK_V1:
		journal->j_format_version = 1;
		break;
	case JBD2_SUPERBLOCK_V2:
		journal->j_format_version = 2;
		break;
	default:
		printk(KERN_WARNING "JBD: unrecognised superblock format ID\n");
		goto out;
	}

	if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
		journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
	else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
		printk (KERN_WARNING "JBD: journal file too short\n");
		goto out;
	}

	return 0;

out:
	journal_fail_superblock(journal);
	return err;
}

/*
 * Load the on-disk journal superblock and read the key fields into the
 * journal_t.
 */

static int load_superblock(journal_t *journal)
{
	int err;
	journal_superblock_t *sb;

	err = journal_get_superblock(journal);
	if (err)
		return err;

	sb = journal->j_superblock;

	journal->j_tail_sequence = be32_to_cpu(sb->s_sequence);
	journal->j_tail = be32_to_cpu(sb->s_start);
	journal->j_first = be32_to_cpu(sb->s_first);
	journal->j_last = be32_to_cpu(sb->s_maxlen);
	journal->j_errno = be32_to_cpu(sb->s_errno);

	return 0;
}


/**
 * int jbd2_journal_load() - Read journal from disk.
 * @journal: Journal to act on.
 *
 * Given a journal_t structure which tells us which disk blocks contain
 * a journal, read the journal from disk to initialise the in-memory
 * structures.
 */
int jbd2_journal_load(journal_t *journal)
{
	int err;
	journal_superblock_t *sb;

	err = load_superblock(journal);
	if (err)
		return err;

	sb = journal->j_superblock;
	/* If this is a V2 superblock, then we have to check the
	 * features flags on it. */

	if (journal->j_format_version >= 2) {
		if ((sb->s_feature_ro_compat &
		     ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) ||
		    (sb->s_feature_incompat &
		     ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) {
			printk (KERN_WARNING
				"JBD: Unrecognised features on journal\n");
			return -EINVAL;
		}
	}

	/* Let the recovery code check whether it needs to recover any
	 * data from the journal. */
	if (jbd2_journal_recover(journal))
		goto recovery_error;

	/* OK, we've finished with the dynamic journal bits:
	 * reinitialise the dynamic contents of the superblock in memory
	 * and reset them on disk. */
	if (journal_reset(journal))
		goto recovery_error;

	journal->j_flags &= ~JBD2_ABORT;
	journal->j_flags |= JBD2_LOADED;
	return 0;

recovery_error:
	printk (KERN_WARNING "JBD: recovery failed\n");
	return -EIO;
}

/**
 * void jbd2_journal_destroy() - Release a journal_t structure.
 * @journal: Journal to act on.
 *
 * Release a journal_t structure once it is no longer in use by the
 * journaled object.
 * Return <0 if we couldn't clean up the journal.
 */
int jbd2_journal_destroy(journal_t *journal)
{
	int err = 0;

	/* Wait for the commit thread to wake up and die. */
	journal_kill_thread(journal);

	/* Force a final log commit */
	if (journal->j_running_transaction)
		jbd2_journal_commit_transaction(journal);

	/* Force any old transactions to disk */

	/* Totally anal locking here... */
	spin_lock(&journal->j_list_lock);
	while (journal->j_checkpoint_transactions != NULL) {
		spin_unlock(&journal->j_list_lock);
		mutex_lock(&journal->j_checkpoint_mutex);
		jbd2_log_do_checkpoint(journal);
		mutex_unlock(&journal->j_checkpoint_mutex);
		spin_lock(&journal->j_list_lock);
	}

	J_ASSERT(journal->j_running_transaction == NULL);
	J_ASSERT(journal->j_committing_transaction == NULL);
	J_ASSERT(journal->j_checkpoint_transactions == NULL);
	spin_unlock(&journal->j_list_lock);

	if (journal->j_sb_buffer) {
		if (!is_journal_aborted(journal)) {
			/* We can now mark the journal as empty. */
			journal->j_tail = 0;
			journal->j_tail_sequence =
				++journal->j_transaction_sequence;
			jbd2_journal_update_superblock(journal, 1);
		} else {
			err = -EIO;
		}
		brelse(journal->j_sb_buffer);
	}

	if (journal->j_proc_entry)
		jbd2_stats_proc_exit(journal);
	if (journal->j_inode)
		iput(journal->j_inode);
	if (journal->j_revoke)
		jbd2_journal_destroy_revoke(journal);
	kfree(journal->j_wbuf);
	kfree(journal);

	return err;
}


/**
 *int jbd2_journal_check_used_features () - Check if features specified are used.
 * @journal: Journal to check.
 * @compat: bitmask of compatible features
 * @ro: bitmask of features that force read-only mount
 * @incompat: bitmask of incompatible features
 *
 * Check whether the journal uses all of a given set of
 * features.  Return true (non-zero) if it does.
 **/

int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat,
				 unsigned long ro, unsigned long incompat)
{
	journal_superblock_t *sb;

	if (!compat && !ro && !incompat)
		return 1;
	if (journal->j_format_version == 1)
		return 0;

	sb = journal->j_superblock;

	if (((be32_to_cpu(sb->s_feature_compat) & compat) == compat) &&
	    ((be32_to_cpu(sb->s_feature_ro_compat) & ro) == ro) &&
	    ((be32_to_cpu(sb->s_feature_incompat) & incompat) == incompat))
		return 1;

	return 0;
}

/**
 * int jbd2_journal_check_available_features() - Check feature set in journalling layer
 * @journal: Journal to check.
 * @compat: bitmask of compatible features
 * @ro: bitmask of features that force read-only mount
 * @incompat: bitmask of incompatible features
 *
 * Check whether the journaling code supports the use of
 * all of a given set of features on this journal.  Return true
 * (non-zero) if it can. */

int jbd2_journal_check_available_features (journal_t *journal, unsigned long compat,
				      unsigned long ro, unsigned long incompat)
{
	journal_superblock_t *sb;

	if (!compat && !ro && !incompat)
		return 1;

	sb = journal->j_superblock;

	/* We can support any known requested features iff the
	 * superblock is in version 2.  Otherwise we fail to support any
	 * extended sb features. */

	if (journal->j_format_version != 2)
		return 0;

	if ((compat   & JBD2_KNOWN_COMPAT_FEATURES) == compat &&
	    (ro       & JBD2_KNOWN_ROCOMPAT_FEATURES) == ro &&
	    (incompat & JBD2_KNOWN_INCOMPAT_FEATURES) == incompat)
		return 1;

	return 0;
}

/**
 * int jbd2_journal_set_features () - Mark a given journal feature in the superblock
 * @journal: Journal to act on.
 * @compat: bitmask of compatible features
 * @ro: bitmask of features that force read-only mount
 * @incompat: bitmask of incompatible features
 *
 * Mark a given journal feature as present on the
 * superblock.  Returns true if the requested features could be set.
 *
 */

int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
			  unsigned long ro, unsigned long incompat)
{
	journal_superblock_t *sb;

	if (jbd2_journal_check_used_features(journal, compat, ro, incompat))
		return 1;

	if (!jbd2_journal_check_available_features(journal, compat, ro, incompat))
		return 0;

	jbd_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n",
		  compat, ro, incompat);

	sb = journal->j_superblock;

	sb->s_feature_compat    |= cpu_to_be32(compat);
	sb->s_feature_ro_compat |= cpu_to_be32(ro);
	sb->s_feature_incompat  |= cpu_to_be32(incompat);

	return 1;
}

/*
 * jbd2_journal_clear_features () - Clear a given journal feature in the
 * 				    superblock
 * @journal: Journal to act on.
 * @compat: bitmask of compatible features
 * @ro: bitmask of features that force read-only mount
 * @incompat: bitmask of incompatible features
 *
 * Clear a given journal feature as present on the
 * superblock.
 */
void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
				unsigned long ro, unsigned long incompat)
{
	journal_superblock_t *sb;

	jbd_debug(1, "Clear features 0x%lx/0x%lx/0x%lx\n",
		  compat, ro, incompat);

	sb = journal->j_superblock;

	sb->s_feature_compat    &= ~cpu_to_be32(compat);
	sb->s_feature_ro_compat &= ~cpu_to_be32(ro);
	sb->s_feature_incompat  &= ~cpu_to_be32(incompat);
}
EXPORT_SYMBOL(jbd2_journal_clear_features);

/**
 * int jbd2_journal_update_format () - Update on-disk journal structure.
 * @journal: Journal to act on.
 *
 * Given an initialised but unloaded journal struct, poke about in the
 * on-disk structure to update it to the most recent supported version.
 */
int jbd2_journal_update_format (journal_t *journal)
{
	journal_superblock_t *sb;
	int err;

	err = journal_get_superblock(journal);
	if (err)
		return err;

	sb = journal->j_superblock;

	switch (be32_to_cpu(sb->s_header.h_blocktype)) {
	case JBD2_SUPERBLOCK_V2:
		return 0;
	case JBD2_SUPERBLOCK_V1:
		return journal_convert_superblock_v1(journal, sb);
	default:
		break;
	}
	return -EINVAL;
}

static int journal_convert_superblock_v1(journal_t *journal,
					 journal_superblock_t *sb)
{
	int offset, blocksize;
	struct buffer_head *bh;

	printk(KERN_WARNING
		"JBD: Converting superblock from version 1 to 2.\n");

	/* Pre-initialise new fields to zero */
	offset = ((char *) &(sb->s_feature_compat)) - ((char *) sb);
	blocksize = be32_to_cpu(sb->s_blocksize);
	memset(&sb->s_feature_compat, 0, blocksize-offset);

	sb->s_nr_users = cpu_to_be32(1);
	sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2);
	journal->j_format_version = 2;

	bh = journal->j_sb_buffer;
	BUFFER_TRACE(bh, "marking dirty");
	mark_buffer_dirty(bh);
	sync_dirty_buffer(bh);
	return 0;
}


/**
 * int jbd2_journal_flush () - Flush journal
 * @journal: Journal to act on.
 *
 * Flush all data for a given journal to disk and empty the journal.
 * Filesystems can use this when remounting readonly to ensure that
 * recovery does not need to happen on remount.
 */

int jbd2_journal_flush(journal_t *journal)
{
	int err = 0;
	transaction_t *transaction = NULL;
	unsigned long old_tail;

	spin_lock(&journal->j_state_lock);

	/* Force everything buffered to the log... */
	if (journal->j_running_transaction) {
		transaction = journal->j_running_transaction;
		__jbd2_log_start_commit(journal, transaction->t_tid);
	} else if (journal->j_committing_transaction)
		transaction = journal->j_committing_transaction;

	/* Wait for the log commit to complete... */
	if (transaction) {
		tid_t tid = transaction->t_tid;

		spin_unlock(&journal->j_state_lock);
		jbd2_log_wait_commit(journal, tid);
	} else {
		spin_unlock(&journal->j_state_lock);
	}

	/* ...and flush everything in the log out to disk. */
	spin_lock(&journal->j_list_lock);
	while (!err && journal->j_checkpoint_transactions != NULL) {
		spin_unlock(&journal->j_list_lock);
		mutex_lock(&journal->j_checkpoint_mutex);
		err = jbd2_log_do_checkpoint(journal);
		mutex_unlock(&journal->j_checkpoint_mutex);
		spin_lock(&journal->j_list_lock);
	}
	spin_unlock(&journal->j_list_lock);

	if (is_journal_aborted(journal))
		return -EIO;

	jbd2_cleanup_journal_tail(journal);

	/* Finally, mark the journal as really needing no recovery.
	 * This sets s_start==0 in the underlying superblock, which is
	 * the magic code for a fully-recovered superblock.  Any future
	 * commits of data to the journal will restore the current
	 * s_start value. */
	spin_lock(&journal->j_state_lock);
	old_tail = journal->j_tail;
	journal->j_tail = 0;
	spin_unlock(&journal->j_state_lock);
	jbd2_journal_update_superblock(journal, 1);
	spin_lock(&journal->j_state_lock);
	journal->j_tail = old_tail;

	J_ASSERT(!journal->j_running_transaction);
	J_ASSERT(!journal->j_committing_transaction);
	J_ASSERT(!journal->j_checkpoint_transactions);
	J_ASSERT(journal->j_head == journal->j_tail);
	J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence);
	spin_unlock(&journal->j_state_lock);
	return 0;
}

/**
 * int jbd2_journal_wipe() - Wipe journal contents
 * @journal: Journal to act on.
 * @write: flag (see below)
 *
 * Wipe out all of the contents of a journal, safely.  This will produce
 * a warning if the journal contains any valid recovery information.
 * Must be called between journal_init_*() and jbd2_journal_load().
 *
 * If 'write' is non-zero, then we wipe out the journal on disk; otherwise…