linux/fs/jbd/journal.c

2146 lines
58 KiB
C
Raw Normal View History

/*
* linux/fs/jbd/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/jbd.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/ratelimit.h>
#define CREATE_TRACE_POINTS
#include <trace/events/jbd.h>
#include <asm/uaccess.h>
#include <asm/page.h>
EXPORT_SYMBOL(journal_start);
EXPORT_SYMBOL(journal_restart);
EXPORT_SYMBOL(journal_extend);
EXPORT_SYMBOL(journal_stop);
EXPORT_SYMBOL(journal_lock_updates);
EXPORT_SYMBOL(journal_unlock_updates);
EXPORT_SYMBOL(journal_get_write_access);
EXPORT_SYMBOL(journal_get_create_access);
EXPORT_SYMBOL(journal_get_undo_access);
EXPORT_SYMBOL(journal_dirty_data);
EXPORT_SYMBOL(journal_dirty_metadata);
EXPORT_SYMBOL(journal_release_buffer);
EXPORT_SYMBOL(journal_forget);
#if 0
EXPORT_SYMBOL(journal_sync_buffer);
#endif
EXPORT_SYMBOL(journal_flush);
EXPORT_SYMBOL(journal_revoke);
EXPORT_SYMBOL(journal_init_dev);
EXPORT_SYMBOL(journal_init_inode);
EXPORT_SYMBOL(journal_update_format);
EXPORT_SYMBOL(journal_check_used_features);
EXPORT_SYMBOL(journal_check_available_features);
EXPORT_SYMBOL(journal_set_features);
EXPORT_SYMBOL(journal_create);
EXPORT_SYMBOL(journal_load);
EXPORT_SYMBOL(journal_destroy);
EXPORT_SYMBOL(journal_abort);
EXPORT_SYMBOL(journal_errno);
EXPORT_SYMBOL(journal_ack_err);
EXPORT_SYMBOL(journal_clear_err);
EXPORT_SYMBOL(log_wait_commit);
EXPORT_SYMBOL(log_start_commit);
EXPORT_SYMBOL(journal_start_commit);
EXPORT_SYMBOL(journal_force_commit_nested);
EXPORT_SYMBOL(journal_wipe);
EXPORT_SYMBOL(journal_blocks_per_page);
EXPORT_SYMBOL(journal_invalidatepage);
EXPORT_SYMBOL(journal_try_to_free_buffers);
EXPORT_SYMBOL(journal_force_commit);
static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
static void __journal_abort_soft (journal_t *journal, int errno);
static const char *journal_dev_name(journal_t *journal, char *buffer);
jbd: use a single printk for jbd_debug() Backport of jbd2 commit 169f1a2a87aae44034da4b9f81be1683d33de6d0 ("jbd2: use a single printk for jbd_debug()") Since the jbd_debug() is implemented with two separate printk() calls, it can lead to corrupted and misleading debug output like the following (see lines marked with "*"): [ 290.339362] (fs/jbd2/journal.c, 203): kjournald2: kjournald2 wakes [ 290.339365] (fs/jbd2/journal.c, 155): kjournald2: commit_sequence=42103, commit_request=42104 [ 290.339369] (fs/jbd2/journal.c, 158): kjournald2: OK, requests differ [* 290.339376] (fs/jbd2/journal.c, 648): jbd2_log_wait_commit: [* 290.339379] (fs/jbd2/commit.c, 370): jbd2_journal_commit_transaction: JBD2: want 42104, j_commit_sequence=42103 [* 290.339382] JBD2: starting commit of transaction 42104 [ 290.339410] (fs/jbd2/revoke.c, 566): jbd2_journal_write_revoke_records: Wrote 0 revoke records [ 290.376555] (fs/jbd2/commit.c, 1088): jbd2_journal_commit_transaction: JBD2: commit 42104 complete, head 42079 i.e. the debug output from log_wait_commit and journal_commit_transaction have become interleaved. The output should have been: (fs/jbd2/journal.c, 648): jbd2_log_wait_commit: JBD2: want 42104, j_commit_sequence=42103 (fs/jbd2/commit.c, 370): jbd2_journal_commit_transaction: JBD2: starting commit of transaction 42104 It is expected that this is not easy to replicate -- I was only able to cause it on preempt-rt kernels, and even then only under heavy I/O load. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by: Jan Kara <jack@suse.cz>
2013-08-01 21:01:08 +02:00
#ifdef CONFIG_JBD_DEBUG
void __jbd_debug(int level, const char *file, const char *func,
unsigned int line, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
if (level > journal_enable_debug)
return;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
printk(KERN_DEBUG "%s: (%s, %u): %pV\n", file, func, line, &vaf);
va_end(args);
}
EXPORT_SYMBOL(__jbd_debug);
#endif
/*
* 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);
}
/*
* kjournald: 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 kjournald(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);
set_freezable();
/* Record that the journal thread is running */
journal->j_task = current;
wake_up(&journal->j_wait_done_commit);
printk(KERN_INFO "kjournald starting. Commit interval %ld seconds\n",
journal->j_commit_interval / HZ);
/*
* And now, wait forever for commit wakeup events.
*/
spin_lock(&journal->j_state_lock);
loop:
if (journal->j_flags & JFS_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);
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 kjournald\n");
spin_unlock(&journal->j_state_lock);
try_to_freeze();
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 & JFS_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, "kjournald 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 journal_start_thread(journal_t *journal)
{
struct task_struct *t;
t = kthread_run(kjournald, journal, "kjournald");
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 |= JFS_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);
}
/*
* 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
* JFS_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 journal_write_metadata_buffer(transaction_t *transaction,
struct journal_head *jh_in,
struct journal_head **jh_out,
unsigned int 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);
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 */
atomic_set(&new_bh->b_count, 1);
new_jh = 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);
} else {
new_page = jh2bh(jh_in)->b_page;
new_offset = offset_in_page(jh2bh(jh_in)->b_data);
}
mapped_data = kmap_atomic(new_page);
/*
* Check for escaping
*/
if (*((__be32 *)(mapped_data + new_offset)) ==
cpu_to_be32(JFS_MAGIC_NUMBER)) {
need_copy_out = 1;
do_escape = 1;
}
kunmap_atomic(mapped_data);
/*
* Do we need to do a data copy?
*/
if (need_copy_out && !done_copy_out) {
char *tmp;
jbd_unlock_bh_state(bh_in);
tmp = jbd_alloc(bh_in->b_size, GFP_NOFS);
jbd_lock_bh_state(bh_in);
if (jh_in->b_frozen_data) {
jbd_free(tmp, bh_in->b_size);
goto repeat;
}
jh_in->b_frozen_data = tmp;
mapped_data = kmap_atomic(new_page);
memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size);
kunmap_atomic(mapped_data);
new_page = virt_to_page(tmp);
new_offset = offset_in_page(tmp);
done_copy_out = 1;
}
/*
* 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);
*((unsigned int *)(mapped_data + new_offset)) = 0;
kunmap_atomic(mapped_data);
}
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);
__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");
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.
*/
/*
* __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 __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;
}
/*
jbd: fix return value of journal_start_commit() journal_start_commit() returns 1 if either a transaction is committing or the function has queued a transaction commit. But it returns 0 if we raced with somebody queueing the transaction commit as well. This resulted in ext3_sync_fs() not functioning correctly (description from Arthur Jones): In the case of a data=ordered umount with pending long symlinks which are delayed due to a long list of other I/O on the backing block device, this causes the buffer associated with the long symlinks to not be moved to the inode dirty list in the second phase of fsync_super. Then, before they can be dirtied again, kjournald exits, seeing the UMOUNT flag and the dirty pages are never written to the backing block device, causing long symlink corruption and exposing new or previously freed block data to userspace. This can be reproduced with a script created by Eric Sandeen <sandeen@redhat.com>: #!/bin/bash umount /mnt/test2 mount /dev/sdb4 /mnt/test2 rm -f /mnt/test2/* dd if=/dev/zero of=/mnt/test2/bigfile bs=1M count=512 touch /mnt/test2/thisisveryveryveryveryveryveryveryveryveryveryveryveryveryveryveryverylongfilename ln -s /mnt/test2/thisisveryveryveryveryveryveryveryveryveryveryveryveryveryveryveryverylongfilename /mnt/test2/link umount /mnt/test2 mount /dev/sdb4 /mnt/test2 ls /mnt/test2/ This patch fixes journal_start_commit() to always return 1 when there's a transaction committing or queued for commit. Cc: Eric Sandeen <sandeen@redhat.com> Cc: Mike Snitzer <snitzer@gmail.com> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-11 22:04:25 +01:00
* Called under j_state_lock. Returns true if a transaction commit was started.
*/
int __log_start_commit(journal_t *journal, tid_t target)
{
/*
* The only transaction we can possibly wait upon is the
* currently running transaction (if it exists). Otherwise,
* the target tid must be an old one.
*/
if (journal->j_commit_request != target &&
journal->j_running_transaction &&
journal->j_running_transaction->t_tid == target) {
/*
* We want a new commit: OK, mark the request and wakeup 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;
} else if (!tid_geq(journal->j_commit_request, target))
/* This should never happen, but if it does, preserve
the evidence before kjournald goes into a loop and
increments j_commit_sequence beyond all recognition. */
WARN_ONCE(1, "jbd: bad log_start_commit: %u %u %u %u\n",
journal->j_commit_request, journal->j_commit_sequence,
target, journal->j_running_transaction ?
journal->j_running_transaction->t_tid : 0);
return 0;
}
int log_start_commit(journal_t *journal, tid_t tid)
{
int ret;
spin_lock(&journal->j_state_lock);
ret = __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 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;
__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);
log_wait_commit(journal, tid);
return 1;
}
/*
* Start a commit of the current running transaction (if any). Returns true
jbd: fix return value of journal_start_commit() journal_start_commit() returns 1 if either a transaction is committing or the function has queued a transaction commit. But it returns 0 if we raced with somebody queueing the transaction commit as well. This resulted in ext3_sync_fs() not functioning correctly (description from Arthur Jones): In the case of a data=ordered umount with pending long symlinks which are delayed due to a long list of other I/O on the backing block device, this causes the buffer associated with the long symlinks to not be moved to the inode dirty list in the second phase of fsync_super. Then, before they can be dirtied again, kjournald exits, seeing the UMOUNT flag and the dirty pages are never written to the backing block device, causing long symlink corruption and exposing new or previously freed block data to userspace. This can be reproduced with a script created by Eric Sandeen <sandeen@redhat.com>: #!/bin/bash umount /mnt/test2 mount /dev/sdb4 /mnt/test2 rm -f /mnt/test2/* dd if=/dev/zero of=/mnt/test2/bigfile bs=1M count=512 touch /mnt/test2/thisisveryveryveryveryveryveryveryveryveryveryveryveryveryveryveryverylongfilename ln -s /mnt/test2/thisisveryveryveryveryveryveryveryveryveryveryveryveryveryveryveryverylongfilename /mnt/test2/link umount /mnt/test2 mount /dev/sdb4 /mnt/test2 ls /mnt/test2/ This patch fixes journal_start_commit() to always return 1 when there's a transaction committing or queued for commit. Cc: Eric Sandeen <sandeen@redhat.com> Cc: Mike Snitzer <snitzer@gmail.com> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-11 22:04:25 +01:00
* if a transaction is going to be committed (or is currently already
* committing), and fills its tid in at *ptid
*/
int 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;
jbd: fix return value of journal_start_commit() journal_start_commit() returns 1 if either a transaction is committing or the function has queued a transaction commit. But it returns 0 if we raced with somebody queueing the transaction commit as well. This resulted in ext3_sync_fs() not functioning correctly (description from Arthur Jones): In the case of a data=ordered umount with pending long symlinks which are delayed due to a long list of other I/O on the backing block device, this causes the buffer associated with the long symlinks to not be moved to the inode dirty list in the second phase of fsync_super. Then, before they can be dirtied again, kjournald exits, seeing the UMOUNT flag and the dirty pages are never written to the backing block device, causing long symlink corruption and exposing new or previously freed block data to userspace. This can be reproduced with a script created by Eric Sandeen <sandeen@redhat.com>: #!/bin/bash umount /mnt/test2 mount /dev/sdb4 /mnt/test2 rm -f /mnt/test2/* dd if=/dev/zero of=/mnt/test2/bigfile bs=1M count=512 touch /mnt/test2/thisisveryveryveryveryveryveryveryveryveryveryveryveryveryveryveryverylongfilename ln -s /mnt/test2/thisisveryveryveryveryveryveryveryveryveryveryveryveryveryveryveryverylongfilename /mnt/test2/link umount /mnt/test2 mount /dev/sdb4 /mnt/test2 ls /mnt/test2/ This patch fixes journal_start_commit() to always return 1 when there's a transaction committing or queued for commit. Cc: Eric Sandeen <sandeen@redhat.com> Cc: Mike Snitzer <snitzer@gmail.com> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-11 22:04:25 +01:00
__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;
jbd: fix return value of journal_start_commit() journal_start_commit() returns 1 if either a transaction is committing or the function has queued a transaction commit. But it returns 0 if we raced with somebody queueing the transaction commit as well. This resulted in ext3_sync_fs() not functioning correctly (description from Arthur Jones): In the case of a data=ordered umount with pending long symlinks which are delayed due to a long list of other I/O on the backing block device, this causes the buffer associated with the long symlinks to not be moved to the inode dirty list in the second phase of fsync_super. Then, before they can be dirtied again, kjournald exits, seeing the UMOUNT flag and the dirty pages are never written to the backing block device, causing long symlink corruption and exposing new or previously freed block data to userspace. This can be reproduced with a script created by Eric Sandeen <sandeen@redhat.com>: #!/bin/bash umount /mnt/test2 mount /dev/sdb4 /mnt/test2 rm -f /mnt/test2/* dd if=/dev/zero of=/mnt/test2/bigfile bs=1M count=512 touch /mnt/test2/thisisveryveryveryveryveryveryveryveryveryveryveryveryveryveryveryverylongfilename ln -s /mnt/test2/thisisveryveryveryveryveryveryveryveryveryveryveryveryveryveryveryverylongfilename /mnt/test2/link umount /mnt/test2 mount /dev/sdb4 /mnt/test2 ls /mnt/test2/ This patch fixes journal_start_commit() to always return 1 when there's a transaction committing or queued for commit. Cc: Eric Sandeen <sandeen@redhat.com> Cc: Mike Snitzer <snitzer@gmail.com> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-11 22:04:25 +01:00
ret = 1;
} else if (journal->j_committing_transaction) {
/*
* If commit has been started, then we have to wait for
* completion of that transaction.
*/
jbd: fix return value of journal_start_commit() journal_start_commit() returns 1 if either a transaction is committing or the function has queued a transaction commit. But it returns 0 if we raced with somebody queueing the transaction commit as well. This resulted in ext3_sync_fs() not functioning correctly (description from Arthur Jones): In the case of a data=ordered umount with pending long symlinks which are delayed due to a long list of other I/O on the backing block device, this causes the buffer associated with the long symlinks to not be moved to the inode dirty list in the second phase of fsync_super. Then, before they can be dirtied again, kjournald exits, seeing the UMOUNT flag and the dirty pages are never written to the backing block device, causing long symlink corruption and exposing new or previously freed block data to userspace. This can be reproduced with a script created by Eric Sandeen <sandeen@redhat.com>: #!/bin/bash umount /mnt/test2 mount /dev/sdb4 /mnt/test2 rm -f /mnt/test2/* dd if=/dev/zero of=/mnt/test2/bigfile bs=1M count=512 touch /mnt/test2/thisisveryveryveryveryveryveryveryveryveryveryveryveryveryveryveryverylongfilename ln -s /mnt/test2/thisisveryveryveryveryveryveryveryveryveryveryveryveryveryveryveryverylongfilename /mnt/test2/link umount /mnt/test2 mount /dev/sdb4 /mnt/test2 ls /mnt/test2/ This patch fixes journal_start_commit() to always return 1 when there's a transaction committing or queued for commit. Cc: Eric Sandeen <sandeen@redhat.com> Cc: Mike Snitzer <snitzer@gmail.com> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-11 22:04:25 +01:00
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 log_wait_commit(journal_t *journal, tid_t tid)
{
int err = 0;
#ifdef CONFIG_JBD_DEBUG
spin_lock(&journal->j_state_lock);
if (!tid_geq(journal->j_commit_request, tid)) {
printk(KERN_ERR
"%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);
/*
* Not running or committing trans? Must be already committed. This
* saves us from waiting for a *long* time when tid overflows.
*/
if (!((journal->j_running_transaction &&
journal->j_running_transaction->t_tid == tid) ||
(journal->j_committing_transaction &&
journal->j_committing_transaction->t_tid == tid)))
goto out_unlock;
if (!tid_geq(journal->j_commit_waited, tid))
journal->j_commit_waited = tid;
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);
}
out_unlock:
spin_unlock(&journal->j_state_lock);
if (unlikely(is_journal_aborted(journal)))
err = -EIO;
return err;
}
/*
* Return 1 if a given transaction has not yet sent barrier request
* connected with a transaction commit. If 0 is returned, transaction
* may or may not have sent the barrier. Used to avoid sending barrier
* twice in common cases.
*/
int journal_trans_will_send_data_barrier(journal_t *journal, tid_t tid)
{
int ret = 0;
transaction_t *commit_trans;
if (!(journal->j_flags & JFS_BARRIER))
return 0;
spin_lock(&journal->j_state_lock);
/* Transaction already committed? */
if (tid_geq(journal->j_commit_sequence, tid))
goto out;
/*
* Transaction is being committed and we already proceeded to
* writing commit record?
*/
commit_trans = journal->j_committing_transaction;
if (commit_trans && commit_trans->t_tid == tid &&
commit_trans->t_state >= T_COMMIT_RECORD)
goto out;
ret = 1;
out:
spin_unlock(&journal->j_state_lock);
return ret;
}
EXPORT_SYMBOL(journal_trans_will_send_data_barrier);
/*
* Log buffer allocation routines:
*/
int journal_next_log_block(journal_t *journal, unsigned int *retp)
{
unsigned int 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 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 journal_bmap(journal_t *journal, unsigned int blocknr,
unsigned int *retp)
{
int err = 0;
unsigned int ret;
if (journal->j_inode) {
ret = bmap(journal->j_inode, blocknr);
if (ret)
*retp = ret;
else {
char b[BDEVNAME_SIZE];
printk(KERN_ALERT "%s: journal block not found "
"at offset %u on %s\n",
__func__,
blocknr,
bdevname(journal->j_dev, b));
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 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 *journal_get_descriptor_buffer(journal_t *journal)
{
struct buffer_head *bh;
unsigned int blocknr;
int err;
err = 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 journal_add_journal_head(bh);
}
/*
* 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);
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_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 * JBD_DEFAULT_MAX_COMMIT_AGE);
/* The journal is marked for error until we succeed with recovery! */
journal->j_flags = JFS_ABORT;
/* Set up a default-sized revoke table for the new mount. */
err = journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
if (err) {
kfree(journal);
goto fail;
}
return journal;
fail:
return NULL;
}
/* journal_init_dev and 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 * 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 *
*
* journal_init_dev creates a journal which maps a fixed contiguous
* range of blocks on an arbitrary block device.
*
*/
journal_t * journal_init_dev(struct block_device *bdev,
struct block_device *fs_dev,
int start, int len, int blocksize)
{
journal_t *journal = journal_init_common();
struct buffer_head *bh;
int n;
if (!journal)
return NULL;
/* journal descriptor can store up to n blocks -bzzz */
journal->j_blocksize = blocksize;
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: Can't 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;
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:
kfree(journal->j_wbuf);
kfree(journal);
return NULL;
}
/**
* journal_t * journal_init_inode () - creates a journal which maps to a inode.
* @inode: An inode to create the journal in
*
* 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 * journal_init_inode (struct inode *inode)
{
struct buffer_head *bh;
journal_t *journal = journal_init_common();
int err;
int n;
unsigned int blocknr;
if (!journal)
return NULL;
journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev;
journal->j_inode = inode;
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;
/* 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: Can't allocate bhs for commit thread\n",
__func__);
goto out_err;
}
err = journal_bmap(journal, 0, &blocknr);
/* If that failed, give up */
if (err) {
printk(KERN_ERR "%s: Cannot locate journal superblock\n",
__func__);
goto out_err;
}
bh = getblk_unmovable(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:
kfree(journal->j_wbuf);
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 int first, last;
first = be32_to_cpu(sb->s_first);
last = be32_to_cpu(sb->s_maxlen);
if (first + JFS_MIN_JOURNAL_BLOCKS > last + 1) {
printk(KERN_ERR "JBD: Journal too short (blocks %u-%u).\n",
first, last);
journal_fail_superblock(journal);
return -EINVAL;
}
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;
/*
* As a special case, if the on-disk copy is already marked as needing
* no recovery (s_start == 0), then we can safely defer the superblock
* update until the next commit by setting JFS_FLUSHED. This avoids
* attempting a write to a potential-readonly device.
*/
if (sb->s_start == 0) {
jbd_debug(1,"JBD: Skipping superblock update on recovered sb "
"(start %u, seq %d, errno %d)\n",
journal->j_tail, journal->j_tail_sequence,
journal->j_errno);
journal->j_flags |= JFS_FLUSHED;
} else {
/* Lock here to make assertions happy... */
mutex_lock(&journal->j_checkpoint_mutex);
/*
* Update log tail information. We use WRITE_FUA since new
* transaction will start reusing journal space and so we
* must make sure information about current log tail is on
* disk before that.
*/
journal_update_sb_log_tail(journal,
journal->j_tail_sequence,
journal->j_tail,
WRITE_FUA);
mutex_unlock(&journal->j_checkpoint_mutex);
}
return journal_start_thread(journal);
}
/**
* int journal_create() - Initialise the new journal file
* @journal: Journal to create. This structure must have been initialised
*
* Given a journal_t structure which tells us which disk blocks we can
* use, create a new journal superblock and initialise all of the
* journal fields from scratch.
**/
int journal_create(journal_t *journal)
{
unsigned int blocknr;
struct buffer_head *bh;
journal_superblock_t *sb;
int i, err;
if (journal->j_maxlen < JFS_MIN_JOURNAL_BLOCKS) {
printk (KERN_ERR "Journal length (%d blocks) too short.\n",
journal->j_maxlen);
journal_fail_superblock(journal);
return -EINVAL;
}
if (journal->j_inode == NULL) {
/*
* We don't know what block to start at!
*/
printk(KERN_EMERG
"%s: creation of journal on external device!\n",
__func__);
BUG();
}
/* Zero out the entire journal on disk. We cannot afford to
have any blocks on disk beginning with JFS_MAGIC_NUMBER. */
jbd_debug(1, "JBD: Zeroing out journal blocks...\n");
for (i = 0; i < journal->j_maxlen; i++) {
err = journal_bmap(journal, i, &blocknr);
if (err)
return err;
bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
if (unlikely(!bh))
return -ENOMEM;
lock_buffer(bh);
memset (bh->b_data, 0, journal->j_blocksize);
BUFFER_TRACE(bh, "marking dirty");
mark_buffer_dirty(bh);
BUFFER_TRACE(bh, "marking uptodate");
set_buffer_uptodate(bh);
unlock_buffer(bh);
__brelse(bh);
}
sync_blockdev(journal->j_dev);
jbd_debug(1, "JBD: journal cleared.\n");
/* OK, fill in the initial static fields in the new superblock */
sb = journal->j_superblock;
sb->s_header.h_magic = cpu_to_be32(JFS_MAGIC_NUMBER);
sb->s_header.h_blocktype = cpu_to_be32(JFS_SUPERBLOCK_V2);
sb->s_blocksize = cpu_to_be32(journal->j_blocksize);
sb->s_maxlen = cpu_to_be32(journal->j_maxlen);
sb->s_first = cpu_to_be32(1);
journal->j_transaction_sequence = 1;
journal->j_flags &= ~JFS_ABORT;
journal->j_format_version = 2;
return journal_reset(journal);
}
static void journal_write_superblock(journal_t *journal, int write_op)
{
struct buffer_head *bh = journal->j_sb_buffer;
int ret;
trace_journal_write_superblock(journal, write_op);
if (!(journal->j_flags & JFS_BARRIER))
write_op &= ~(REQ_FUA | REQ_FLUSH);
lock_buffer(bh);
if (buffer_write_io_error(bh)) {
char b[BDEVNAME_SIZE];
/*
* 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 "JBD: previous I/O error detected "
"for journal superblock update for %s.\n",
journal_dev_name(journal, b));
clear_buffer_write_io_error(bh);
set_buffer_uptodate(bh);
}
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
ret = submit_bh(write_op, bh);
wait_on_buffer(bh);
if (buffer_write_io_error(bh)) {
clear_buffer_write_io_error(bh);
set_buffer_uptodate(bh);
ret = -EIO;
}
if (ret) {
char b[BDEVNAME_SIZE];
printk(KERN_ERR "JBD: Error %d detected "
"when updating journal superblock for %s.\n",
ret, journal_dev_name(journal, b));
}
}
/**
* journal_update_sb_log_tail() - Update log tail in journal sb on disk.
* @journal: The journal to update.
* @tail_tid: TID of the new transaction at the tail of the log
* @tail_block: The first block of the transaction at the tail of the log
* @write_op: With which operation should we write the journal sb
*
* Update a journal's superblock information about log tail and write it to
* disk, waiting for the IO to complete.
*/
void journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
unsigned int tail_block, int write_op)
{
journal_superblock_t *sb = journal->j_superblock;
BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
jbd_debug(1,"JBD: updating superblock (start %u, seq %u)\n",
tail_block, tail_tid);
sb->s_sequence = cpu_to_be32(tail_tid);
sb->s_start = cpu_to_be32(tail_block);
journal_write_superblock(journal, write_op);
/* Log is no longer empty */
spin_lock(&journal->j_state_lock);
WARN_ON(!sb->s_sequence);
journal->j_flags &= ~JFS_FLUSHED;
spin_unlock(&journal->j_state_lock);
}
/**
* mark_journal_empty() - Mark on disk journal as empty.
* @journal: The journal to update.
*
* Update a journal's dynamic superblock fields to show that journal is empty.
* Write updated superblock to disk waiting for IO to complete.
*/
static void mark_journal_empty(journal_t *journal)
{
journal_superblock_t *sb = journal->j_superblock;
BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
spin_lock(&journal->j_state_lock);
/* Is it already empty? */
if (sb->s_start == 0) {
spin_unlock(&journal->j_state_lock);
return;
}
jbd_debug(1, "JBD: Marking journal as empty (seq %d)\n",
journal->j_tail_sequence);
sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
sb->s_start = cpu_to_be32(0);
spin_unlock(&journal->j_state_lock);
journal_write_superblock(journal, WRITE_FUA);
spin_lock(&journal->j_state_lock);
/* Log is empty */
journal->j_flags |= JFS_FLUSHED;
spin_unlock(&journal->j_state_lock);
}
/**
* journal_update_sb_errno() - Update error in the journal.
* @journal: The journal to update.
*
* Update a journal's errno. Write updated superblock to disk waiting for IO
* to complete.
*/
static void journal_update_sb_errno(journal_t *journal)
{
journal_superblock_t *sb = journal->j_superblock;
spin_lock(&journal->j_state_lock);
jbd_debug(1, "JBD: updating superblock error (errno %d)\n",
journal->j_errno);
sb->s_errno = cpu_to_be32(journal->j_errno);
spin_unlock(&journal->j_state_lock);
journal_write_superblock(journal, WRITE_SYNC);
}
/*
* 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(JFS_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 JFS_SUPERBLOCK_V1:
journal->j_format_version = 1;
break;
case JFS_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;
}
if (be32_to_cpu(sb->s_first) == 0 ||
be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
printk(KERN_WARNING
"JBD: Invalid start block of journal: %u\n",
be32_to_cpu(sb->s_first));
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 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 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(JFS_KNOWN_ROCOMPAT_FEATURES)) ||
(sb->s_feature_incompat &
~cpu_to_be32(JFS_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 (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 &= ~JFS_ABORT;
journal->j_flags |= JFS_LOADED;
return 0;
recovery_error:
printk (KERN_WARNING "JBD: recovery failed\n");
return -EIO;
}
/**
* void 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.
jbd: fix error handling for checkpoint io When a checkpointing IO fails, current JBD code doesn't check the error and continue journaling. This means latest metadata can be lost from both the journal and filesystem. This patch leaves the failed metadata blocks in the journal space and aborts journaling in the case of log_do_checkpoint(). To achieve this, we need to do: 1. don't remove the failed buffer from the checkpoint list where in the case of __try_to_free_cp_buf() because it may be released or overwritten by a later transaction 2. log_do_checkpoint() is the last chance, remove the failed buffer from the checkpoint list and abort the journal 3. when checkpointing fails, don't update the journal super block to prevent the journaled contents from being cleaned. For safety, don't update j_tail and j_tail_sequence either 4. when checkpointing fails, notify this error to the ext3 layer so that ext3 don't clear the needs_recovery flag, otherwise the journaled contents are ignored and cleaned in the recovery phase 5. if the recovery fails, keep the needs_recovery flag 6. prevent cleanup_journal_tail() from being called between __journal_drop_transaction() and journal_abort() (a race issue between journal_flush() and __log_wait_for_space() Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Jan Kara <jack@suse.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-22 23:15:00 +02:00
* Return <0 if we couldn't clean up the journal.
*/
jbd: fix error handling for checkpoint io When a checkpointing IO fails, current JBD code doesn't check the error and continue journaling. This means latest metadata can be lost from both the journal and filesystem. This patch leaves the failed metadata blocks in the journal space and aborts journaling in the case of log_do_checkpoint(). To achieve this, we need to do: 1. don't remove the failed buffer from the checkpoint list where in the case of __try_to_free_cp_buf() because it may be released or overwritten by a later transaction 2. log_do_checkpoint() is the last chance, remove the failed buffer from the checkpoint list and abort the journal 3. when checkpointing fails, don't update the journal super block to prevent the journaled contents from being cleaned. For safety, don't update j_tail and j_tail_sequence either 4. when checkpointing fails, notify this error to the ext3 layer so that ext3 don't clear the needs_recovery flag, otherwise the journaled contents are ignored and cleaned in the recovery phase 5. if the recovery fails, keep the needs_recovery flag 6. prevent cleanup_journal_tail() from being called between __journal_drop_transaction() and journal_abort() (a race issue between journal_flush() and __log_wait_for_space() Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Jan Kara <jack@suse.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-22 23:15:00 +02:00
int journal_destroy(journal_t *journal)
{
jbd: fix error handling for checkpoint io When a checkpointing IO fails, current JBD code doesn't check the error and continue journaling. This means latest metadata can be lost from both the journal and filesystem. This patch leaves the failed metadata blocks in the journal space and aborts journaling in the case of log_do_checkpoint(). To achieve this, we need to do: 1. don't remove the failed buffer from the checkpoint list where in the case of __try_to_free_cp_buf() because it may be released or overwritten by a later transaction 2. log_do_checkpoint() is the last chance, remove the failed buffer from the checkpoint list and abort the journal 3. when checkpointing fails, don't update the journal super block to prevent the journaled contents from being cleaned. For safety, don't update j_tail and j_tail_sequence either 4. when checkpointing fails, notify this error to the ext3 layer so that ext3 don't clear the needs_recovery flag, otherwise the journaled contents are ignored and cleaned in the recovery phase 5. if the recovery fails, keep the needs_recovery flag 6. prevent cleanup_journal_tail() from being called between __journal_drop_transaction() and journal_abort() (a race issue between journal_flush() and __log_wait_for_space() Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Jan Kara <jack@suse.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-22 23:15:00 +02:00
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)
journal_commit_transaction(journal);
/* Force any old transactions to disk */
/* We cannot race with anybody but must keep assertions happy */
mutex_lock(&journal->j_checkpoint_mutex);
/* Totally anal locking here... */
spin_lock(&journal->j_list_lock);
while (journal->j_checkpoint_transactions != NULL) {
spin_unlock(&journal->j_list_lock);
log_do_checkpoint(journal);
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) {
jbd: fix error handling for checkpoint io When a checkpointing IO fails, current JBD code doesn't check the error and continue journaling. This means latest metadata can be lost from both the journal and filesystem. This patch leaves the failed metadata blocks in the journal space and aborts journaling in the case of log_do_checkpoint(). To achieve this, we need to do: 1. don't remove the failed buffer from the checkpoint list where in the case of __try_to_free_cp_buf() because it may be released or overwritten by a later transaction 2. log_do_checkpoint() is the last chance, remove the failed buffer from the checkpoint list and abort the journal 3. when checkpointing fails, don't update the journal super block to prevent the journaled contents from being cleaned. For safety, don't update j_tail and j_tail_sequence either 4. when checkpointing fails, notify this error to the ext3 layer so that ext3 don't clear the needs_recovery flag, otherwise the journaled contents are ignored and cleaned in the recovery phase 5. if the recovery fails, keep the needs_recovery flag 6. prevent cleanup_journal_tail() from being called between __journal_drop_transaction() and journal_abort() (a race issue between journal_flush() and __log_wait_for_space() Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Jan Kara <jack@suse.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-22 23:15:00 +02:00
if (!is_journal_aborted(journal)) {
journal->j_tail_sequence =
++journal->j_transaction_sequence;
mark_journal_empty(journal);
} else
jbd: fix error handling for checkpoint io When a checkpointing IO fails, current JBD code doesn't check the error and continue journaling. This means latest metadata can be lost from both the journal and filesystem. This patch leaves the failed metadata blocks in the journal space and aborts journaling in the case of log_do_checkpoint(). To achieve this, we need to do: 1. don't remove the failed buffer from the checkpoint list where in the case of __try_to_free_cp_buf() because it may be released or overwritten by a later transaction 2. log_do_checkpoint() is the last chance, remove the failed buffer from the checkpoint list and abort the journal 3. when checkpointing fails, don't update the journal super block to prevent the journaled contents from being cleaned. For safety, don't update j_tail and j_tail_sequence either 4. when checkpointing fails, notify this error to the ext3 layer so that ext3 don't clear the needs_recovery flag, otherwise the journaled contents are ignored and cleaned in the recovery phase 5. if the recovery fails, keep the needs_recovery flag 6. prevent cleanup_journal_tail() from being called between __journal_drop_transaction() and journal_abort() (a race issue between journal_flush() and __log_wait_for_space() Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Jan Kara <jack@suse.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-22 23:15:00 +02:00
err = -EIO;
brelse(journal->j_sb_buffer);
}
mutex_unlock(&journal->j_checkpoint_mutex);
iput(journal->j_inode);
if (journal->j_revoke)
journal_destroy_revoke(journal);
kfree(journal->j_wbuf);
kfree(journal);
jbd: fix error handling for checkpoint io When a checkpointing IO fails, current JBD code doesn't check the error and continue journaling. This means latest metadata can be lost from both the journal and filesystem. This patch leaves the failed metadata blocks in the journal space and aborts journaling in the case of log_do_checkpoint(). To achieve this, we need to do: 1. don't remove the failed buffer from the checkpoint list where in the case of __try_to_free_cp_buf() because it may be released or overwritten by a later transaction 2. log_do_checkpoint() is the last chance, remove the failed buffer from the checkpoint list and abort the journal 3. when checkpointing fails, don't update the journal super block to prevent the journaled contents from being cleaned. For safety, don't update j_tail and j_tail_sequence either 4. when checkpointing fails, notify this error to the ext3 layer so that ext3 don't clear the needs_recovery flag, otherwise the journaled contents are ignored and cleaned in the recovery phase 5. if the recovery fails, keep the needs_recovery flag 6. prevent cleanup_journal_tail() from being called between __journal_drop_transaction() and journal_abort() (a race issue between journal_flush() and __log_wait_for_space() Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Jan Kara <jack@suse.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-22 23:15:00 +02:00
return err;
}
/**
*int 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 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 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 journal_check_available_features (journal_t *journal, unsigned long compat,
unsigned long ro, unsigned long incompat)
{
if (!compat && !ro && !incompat)
return 1;
/* 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 & JFS_KNOWN_COMPAT_FEATURES) == compat &&
(ro & JFS_KNOWN_ROCOMPAT_FEATURES) == ro &&
(incompat & JFS_KNOWN_INCOMPAT_FEATURES) == incompat)
return 1;
return 0;
}
/**
* int 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 journal_set_features (journal_t *journal, unsigned long compat,
unsigned long ro, unsigned long incompat)
{
journal_superblock_t *sb;
if (journal_check_used_features(journal, compat, ro, incompat))
return 1;
if (!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;
}
/**
* int 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 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 JFS_SUPERBLOCK_V2:
return 0;
case JFS_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(JFS_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 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 journal_flush(journal_t *journal)
{
int err = 0;
transaction_t *transaction = NULL;
spin_lock(&journal->j_state_lock);
/* Force everything buffered to the log... */
if (journal->j_running_transaction) {
transaction = journal->j_running_transaction;
__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);
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);
jbd: fix error handling for checkpoint io When a checkpointing IO fails, current JBD code doesn't check the error and continue journaling. This means latest metadata can be lost from both the journal and filesystem. This patch leaves the failed metadata blocks in the journal space and aborts journaling in the case of log_do_checkpoint(). To achieve this, we need to do: 1. don't remove the failed buffer from the checkpoint list where in the case of __try_to_free_cp_buf() because it may be released or overwritten by a later transaction 2. log_do_checkpoint() is the last chance, remove the failed buffer from the checkpoint list and abort the journal 3. when checkpointing fails, don't update the journal super block to prevent the journaled contents from being cleaned. For safety, don't update j_tail and j_tail_sequence either 4. when checkpointing fails, notify this error to the ext3 layer so that ext3 don't clear the needs_recovery flag, otherwise the journaled contents are ignored and cleaned in the recovery phase 5. if the recovery fails, keep the needs_recovery flag 6. prevent cleanup_journal_tail() from being called between __journal_drop_transaction() and journal_abort() (a race issue between journal_flush() and __log_wait_for_space() Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Jan Kara <jack@suse.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-22 23:15:00 +02:00
mutex_lock(&journal->j_checkpoint_mutex);
err = log_do_checkpoint(journal);
jbd: fix error handling for checkpoint io When a checkpointing IO fails, current JBD code doesn't check the error and continue journaling. This means latest metadata can be lost from both the journal and filesystem. This patch leaves the failed metadata blocks in the journal space and aborts journaling in the case of log_do_checkpoint(). To achieve this, we need to do: 1. don't remove the failed buffer from the checkpoint list where in the case of __try_to_free_cp_buf() because it may be released or overwritten by a later transaction 2. log_do_checkpoint() is the last chance, remove the failed buffer from the checkpoint list and abort the journal 3. when checkpointing fails, don't update the journal super block to prevent the journaled contents from being cleaned. For safety, don't update j_tail and j_tail_sequence either 4. when checkpointing fails, notify this error to the ext3 layer so that ext3 don't clear the needs_recovery flag, otherwise the journaled contents are ignored and cleaned in the recovery phase 5. if the recovery fails, keep the needs_recovery flag 6. prevent cleanup_journal_tail() from being called between __journal_drop_transaction() and journal_abort() (a race issue between journal_flush() and __log_wait_for_space() Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Jan Kara <jack@suse.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-22 23:15:00 +02:00
mutex_unlock(&journal->j_checkpoint_mutex);
spin_lock(&journal->j_list_lock);
}
spin_unlock(&journal->j_list_lock);
jbd: fix error handling for checkpoint io When a checkpointing IO fails, current JBD code doesn't check the error and continue journaling. This means latest metadata can be lost from both the journal and filesystem. This patch leaves the failed metadata blocks in the journal space and aborts journaling in the case of log_do_checkpoint(). To achieve this, we need to do: 1. don't remove the failed buffer from the checkpoint list where in the case of __try_to_free_cp_buf() because it may be released or overwritten by a later transaction 2. log_do_checkpoint() is the last chance, remove the failed buffer from the checkpoint list and abort the journal 3. when checkpointing fails, don't update the journal super block to prevent the journaled contents from being cleaned. For safety, don't update j_tail and j_tail_sequence either 4. when checkpointing fails, notify this error to the ext3 layer so that ext3 don't clear the needs_recovery flag, otherwise the journaled contents are ignored and cleaned in the recovery phase 5. if the recovery fails, keep the needs_recovery flag 6. prevent cleanup_journal_tail() from being called between __journal_drop_transaction() and journal_abort() (a race issue between journal_flush() and __log_wait_for_space() Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Jan Kara <jack@suse.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-22 23:15:00 +02:00
if (is_journal_aborted(journal))
return -EIO;
mutex_lock(&journal->j_checkpoint_mutex);
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. */
mark_journal_empty(journal);
mutex_unlock(&journal->j_checkpoint_mutex);
spin_lock(&journal->j_state_lock);
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);
jbd: fix error handling for checkpoint io When a checkpointing IO fails, current JBD code doesn't check the error and continue journaling. This means latest metadata can be lost from both the journal and filesystem. This patch leaves the failed metadata blocks in the journal space and aborts journaling in the case of log_do_checkpoint(). To achieve this, we need to do: 1. don't remove the failed buffer from the checkpoint list where in the case of __try_to_free_cp_buf() because it may be released or overwritten by a later transaction 2. log_do_checkpoint() is the last chance, remove the failed buffer from the checkpoint list and abort the journal 3. when checkpointing fails, don't update the journal super block to prevent the journaled contents from being cleaned. For safety, don't update j_tail and j_tail_sequence either 4. when checkpointing fails, notify this error to the ext3 layer so that ext3 don't clear the needs_recovery flag, otherwise the journaled contents are ignored and cleaned in the recovery phase 5. if the recovery fails, keep the needs_recovery flag 6. prevent cleanup_journal_tail() from being called between __journal_drop_transaction() and journal_abort() (a race issue between journal_flush() and __log_wait_for_space() Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Jan Kara <jack@suse.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-22 23:15:00 +02:00
return 0;
}
/**
* int 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 journal_load().
*
* If 'write' is non-zero, then we wipe out the journal on disk; otherwise
* we merely suppress recovery.
*/
int journal_wipe(journal_t *journal, int write)
{
int err = 0;
J_ASSERT (!(journal->j_flags & JFS_LOADED));
err = load_superblock(journal);
if (err)
return err;
if (!journal->j_tail)
goto no_recovery;
printk (KERN_WARNING "JBD: %s recovery information on journal\n",
write ? "Clearing" : "Ignoring");
err = journal_skip_recovery(journal);
if (write) {
/* Lock to make assertions happy... */
mutex_lock(&journal->j_checkpoint_mutex);
mark_journal_empty(journal);
mutex_unlock(&journal->j_checkpoint_mutex);
}
no_recovery:
return err;
}
/*
* journal_dev_name: format a character string to describe on what
* device this journal is present.
*/
static const char *journal_dev_name(journal_t *journal, char *buffer)
{
struct block_device *bdev;
if (journal->j_inode)
bdev = journal->j_inode->i_sb->s_bdev;
else
bdev = journal->j_dev;
return bdevname(bdev, buffer);
}
/*
* Journal abort has very specific semantics, which we describe
* for journal abort.
*
* Two internal function, which provide abort to te jbd layer
* itself are here.
*/
/*
* Quick version for internal journal use (doesn't lock the journal).
* Aborts hard --- we mark the abort as occurred, but do _nothing_ else,
* and don't attempt to make any other journal updates.
*/
static void __journal_abort_hard(journal_t *journal)
{
transaction_t *transaction;
char b[BDEVNAME_SIZE];
if (journal->j_flags & JFS_ABORT)
return;
printk(KERN_ERR "Aborting journal on device %s.\n",
journal_dev_name(journal, b));
spin_lock(&journal->j_state_lock);
journal->j_flags |= JFS_ABORT;
transaction = journal->j_running_transaction;
if (transaction)
__log_start_commit(journal, transaction->t_tid);
spin_unlock(&journal->j_state_lock);
}
/* Soft abort: record the abort error status in the journal superblock,
* but don't do any other IO. */
static void __journal_abort_soft (journal_t *journal, int errno)
{
if (journal->j_flags & JFS_ABORT)
return;
if (!journal->j_errno)
journal->j_errno = errno;
__journal_abort_hard(journal);
if (errno)
journal_update_sb_errno(journal);
}
/**
* void journal_abort () - Shutdown the journal immediately.
* @journal: the journal to shutdown.
* @errno: an error number to record in the journal indicating
* the reason for the shutdown.
*
* Perform a complete, immediate shutdown of the ENTIRE
* journal (not of a single transaction). This operation cannot be
* undone without closing and reopening the journal.
*
* The journal_abort function is intended to support higher level error
* recovery mechanisms such as the ext2/ext3 remount-readonly error
* mode.
*
* Journal abort has very specific semantics. Any existing dirty,
* unjournaled buffers in the main filesystem will still be written to
* disk by bdflush, but the journaling mechanism will be suspended
* immediately and no further transaction commits will be honoured.
*
* Any dirty, journaled buffers will be written back to disk without
* hitting the journal. Atomicity cannot be guaranteed on an aborted
* filesystem, but we _do_ attempt to leave as much data as possible
* behind for fsck to use for cleanup.
*
* Any attempt to get a new transaction handle on a journal which is in
* ABORT state will just result in an -EROFS error return. A
* journal_stop on an existing handle will return -EIO if we have
* entered abort state during the update.
*
* Recursive transactions are not disturbed by journal abort until the
* final journal_stop, which will receive the -EIO error.
*
* Finally, the journal_abort call allows the caller to supply an errno
* which will be recorded (if possible) in the journal superblock. This
* allows a client to record failure conditions in the middle of a
* transaction without having to complete the transaction to record the
* failure to disk. ext3_error, for example, now uses this
* functionality.
*
* Errors which originate from within the journaling layer will NOT
* supply an errno; a null errno implies that absolutely no further
* writes are done to the journal (unless there are any already in
* progress).
*
*/
void journal_abort(journal_t *journal, int errno)
{
__journal_abort_soft(journal, errno);
}
/**
* int journal_errno () - returns the journal's error state.
* @journal: journal to examine.
*
* This is the errno numbet set with journal_abort(), the last
* time the journal was mounted - if the journal was stopped
* without calling abort this will be 0.
*
* If the journal has been aborted on this mount time -EROFS will
* be returned.
*/
int journal_errno(journal_t *journal)
{
int err;
spin_lock(&journal->j_state_lock);
if (journal->j_flags & JFS_ABORT)
err = -EROFS;
else
err = journal->j_errno;
spin_unlock(&journal->j_state_lock);
return err;
}
/**
* int journal_clear_err () - clears the journal's error state
* @journal: journal to act on.
*
* An error must be cleared or Acked to take a FS out of readonly
* mode.
*/
int journal_clear_err(journal_t *journal)
{
int err = 0;
spin_lock(&journal->j_state_lock);
if (journal->j_flags & JFS_ABORT)
err = -EROFS;
else
journal->j_errno = 0;
spin_unlock(&journal->j_state_lock);
return err;
}
/**
* void journal_ack_err() - Ack journal err.
* @journal: journal to act on.
*
* An error must be cleared or Acked to take a FS out of readonly
* mode.
*/
void journal_ack_err(journal_t *journal)
{
spin_lock(&journal->j_state_lock);
if (journal->j_errno)
journal->j_flags |= JFS_ACK_ERR;
spin_unlock(&journal->j_state_lock);
}
int journal_blocks_per_page(struct inode *inode)
{
return 1 << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
}
/*
* Journal_head storage management
*/
static struct kmem_cache *journal_head_cache;
#ifdef CONFIG_JBD_DEBUG
static atomic_t nr_journal_heads = ATOMIC_INIT(0);
#endif
static int journal_init_journal_head_cache(void)
{
int retval;
J_ASSERT(journal_head_cache == NULL);
journal_head_cache = kmem_cache_create("journal_head",
sizeof(struct journal_head),
0, /* offset */
SLAB_TEMPORARY, /* flags */
NULL); /* ctor */
retval = 0;
if (!journal_head_cache) {
retval = -ENOMEM;
printk(KERN_EMERG "JBD: no memory for journal_head cache\n");
}
return retval;
}
static void journal_destroy_journal_head_cache(void)
{
if (journal_head_cache) {
kmem_cache_destroy(journal_head_cache);
journal_head_cache = NULL;
}
}
/*
* journal_head splicing and dicing
*/
static struct journal_head *journal_alloc_journal_head(void)
{
struct journal_head *ret;
#ifdef CONFIG_JBD_DEBUG
atomic_inc(&nr_journal_heads);
#endif
ret = kmem_cache_zalloc(journal_head_cache, GFP_NOFS);
if (ret == NULL) {
jbd_debug(1, "out of memory for journal_head\n");
printk_ratelimited(KERN_NOTICE "ENOMEM in %s, retrying.\n",
__func__);
while (ret == NULL) {
yield();
ret = kmem_cache_zalloc(journal_head_cache, GFP_NOFS);
}
}
return ret;
}
static void journal_free_journal_head(struct journal_head *jh)
{
#ifdef CONFIG_JBD_DEBUG
atomic_dec(&nr_journal_heads);
memset(jh, JBD_POISON_FREE, sizeof(*jh));
#endif
kmem_cache_free(journal_head_cache, jh);
}
/*
* A journal_head is attached to a buffer_head whenever JBD has an
* interest in the buffer.
*
* Whenever a buffer has an attached journal_head, its ->b_state:BH_JBD bit
* is set. This bit is tested in core kernel code where we need to take
* JBD-specific actions. Testing the zeroness of ->b_private is not reliable
* there.
*
* When a buffer has its BH_JBD bit set, its ->b_count is elevated by one.
*
* When a buffer has its BH_JBD bit set it is immune from being released by
* core kernel code, mainly via ->b_count.
*
jbd: Fix oops in journal_remove_journal_head() journal_remove_journal_head() can oops when trying to access journal_head returned by bh2jh(). This is caused for example by the following race: TASK1 TASK2 journal_commit_transaction() ... processing t_forget list __journal_refile_buffer(jh); if (!jh->b_transaction) { jbd_unlock_bh_state(bh); journal_try_to_free_buffers() journal_grab_journal_head(bh) jbd_lock_bh_state(bh) __journal_try_to_free_buffer() journal_put_journal_head(jh) journal_remove_journal_head(bh); journal_put_journal_head() in TASK2 sees that b_jcount == 0 and buffer is not part of any transaction and thus frees journal_head before TASK1 gets to doing so. Note that even buffer_head can be released by try_to_free_buffers() after journal_put_journal_head() which adds even larger opportunity for oops (but I didn't see this happen in reality). Fix the problem by making transactions hold their own journal_head reference (in b_jcount). That way we don't have to remove journal_head explicitely via journal_remove_journal_head() and instead just remove journal_head when b_jcount drops to zero. The result of this is that [__]journal_refile_buffer(), [__]journal_unfile_buffer(), and __journal_remove_checkpoint() can free journal_head which needs modification of a few callers. Also we have to be careful because once journal_head is removed, buffer_head might be freed as well. So we have to get our own buffer_head reference where it matters. Signed-off-by: Jan Kara <jack@suse.cz>
2011-06-24 23:11:59 +02:00
* A journal_head is detached from its buffer_head when the journal_head's
* b_jcount reaches zero. Running transaction (b_transaction) and checkpoint
* transaction (b_cp_transaction) hold their references to b_jcount.
*
* Various places in the kernel want to attach a journal_head to a buffer_head
* _before_ attaching the journal_head to a transaction. To protect the
* journal_head in this situation, journal_add_journal_head elevates the
* journal_head's b_jcount refcount by one. The caller must call
* journal_put_journal_head() to undo this.
*
* So the typical usage would be:
*
* (Attach a journal_head if needed. Increments b_jcount)
* struct journal_head *jh = journal_add_journal_head(bh);
* ...
jbd: Fix oops in journal_remove_journal_head() journal_remove_journal_head() can oops when trying to access journal_head returned by bh2jh(). This is caused for example by the following race: TASK1 TASK2 journal_commit_transaction() ... processing t_forget list __journal_refile_buffer(jh); if (!jh->b_transaction) { jbd_unlock_bh_state(bh); journal_try_to_free_buffers() journal_grab_journal_head(bh) jbd_lock_bh_state(bh) __journal_try_to_free_buffer() journal_put_journal_head(jh) journal_remove_journal_head(bh); journal_put_journal_head() in TASK2 sees that b_jcount == 0 and buffer is not part of any transaction and thus frees journal_head before TASK1 gets to doing so. Note that even buffer_head can be released by try_to_free_buffers() after journal_put_journal_head() which adds even larger opportunity for oops (but I didn't see this happen in reality). Fix the problem by making transactions hold their own journal_head reference (in b_jcount). That way we don't have to remove journal_head explicitely via journal_remove_journal_head() and instead just remove journal_head when b_jcount drops to zero. The result of this is that [__]journal_refile_buffer(), [__]journal_unfile_buffer(), and __journal_remove_checkpoint() can free journal_head which needs modification of a few callers. Also we have to be careful because once journal_head is removed, buffer_head might be freed as well. So we have to get our own buffer_head reference where it matters. Signed-off-by: Jan Kara <jack@suse.cz>
2011-06-24 23:11:59 +02:00
* (Get another reference for transaction)
* journal_grab_journal_head(bh);
* jh->b_transaction = xxx;
* (Put original reference)
* journal_put_journal_head(jh);
*/
/*
* Give a buffer_head a journal_head.
*
* May sleep.
*/
struct journal_head *journal_add_journal_head(struct buffer_head *bh)
{
struct journal_head *jh;
struct journal_head *new_jh = NULL;
repeat:
if (!buffer_jbd(bh))
new_jh = journal_alloc_journal_head();
jbd_lock_bh_journal_head(bh);
if (buffer_jbd(bh)) {
jh = bh2jh(bh);
} else {
J_ASSERT_BH(bh,
(atomic_read(&bh->b_count) > 0) ||
(bh->b_page && bh->b_page->mapping));
if (!new_jh) {
jbd_unlock_bh_journal_head(bh);
goto repeat;
}
jh = new_jh;
new_jh = NULL; /* We consumed it */
set_buffer_jbd(bh);
bh->b_private = jh;
jh->b_bh = bh;
get_bh(bh);
BUFFER_TRACE(bh, "added journal_head");
}
jh->b_jcount++;
jbd_unlock_bh_journal_head(bh);
if (new_jh)
journal_free_journal_head(new_jh);
return bh->b_private;
}
/*
* Grab a ref against this buffer_head's journal_head. If it ended up not
* having a journal_head, return NULL
*/
struct journal_head *journal_grab_journal_head(struct buffer_head *bh)
{
struct journal_head *jh = NULL;
jbd_lock_bh_journal_head(bh);
if (buffer_jbd(bh)) {
jh = bh2jh(bh);
jh->b_jcount++;
}
jbd_unlock_bh_journal_head(bh);
return jh;
}
static void __journal_remove_journal_head(struct buffer_head *bh)
{
struct journal_head *jh = bh2jh(bh);
J_ASSERT_JH(jh, jh->b_jcount >= 0);
jbd: Fix oops in journal_remove_journal_head() journal_remove_journal_head() can oops when trying to access journal_head returned by bh2jh(). This is caused for example by the following race: TASK1 TASK2 journal_commit_transaction() ... processing t_forget list __journal_refile_buffer(jh); if (!jh->b_transaction) { jbd_unlock_bh_state(bh); journal_try_to_free_buffers() journal_grab_journal_head(bh) jbd_lock_bh_state(bh) __journal_try_to_free_buffer() journal_put_journal_head(jh) journal_remove_journal_head(bh); journal_put_journal_head() in TASK2 sees that b_jcount == 0 and buffer is not part of any transaction and thus frees journal_head before TASK1 gets to doing so. Note that even buffer_head can be released by try_to_free_buffers() after journal_put_journal_head() which adds even larger opportunity for oops (but I didn't see this happen in reality). Fix the problem by making transactions hold their own journal_head reference (in b_jcount). That way we don't have to remove journal_head explicitely via journal_remove_journal_head() and instead just remove journal_head when b_jcount drops to zero. The result of this is that [__]journal_refile_buffer(), [__]journal_unfile_buffer(), and __journal_remove_checkpoint() can free journal_head which needs modification of a few callers. Also we have to be careful because once journal_head is removed, buffer_head might be freed as well. So we have to get our own buffer_head reference where it matters. Signed-off-by: Jan Kara <jack@suse.cz>
2011-06-24 23:11:59 +02:00
J_ASSERT_JH(jh, jh->b_transaction == NULL);
J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
J_ASSERT_JH(jh, jh->b_cp_transaction == NULL);
J_ASSERT_JH(jh, jh->b_jlist == BJ_None);
J_ASSERT_BH(bh, buffer_jbd(bh));
J_ASSERT_BH(bh, jh2bh(jh) == bh);
BUFFER_TRACE(bh, "remove journal_head");
if (jh->b_frozen_data) {
printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__);
jbd_free(jh->b_frozen_data, bh->b_size);
}
jbd: Fix oops in journal_remove_journal_head() journal_remove_journal_head() can oops when trying to access journal_head returned by bh2jh(). This is caused for example by the following race: TASK1 TASK2 journal_commit_transaction() ... processing t_forget list __journal_refile_buffer(jh); if (!jh->b_transaction) { jbd_unlock_bh_state(bh); journal_try_to_free_buffers() journal_grab_journal_head(bh) jbd_lock_bh_state(bh) __journal_try_to_free_buffer() journal_put_journal_head(jh) journal_remove_journal_head(bh); journal_put_journal_head() in TASK2 sees that b_jcount == 0 and buffer is not part of any transaction and thus frees journal_head before TASK1 gets to doing so. Note that even buffer_head can be released by try_to_free_buffers() after journal_put_journal_head() which adds even larger opportunity for oops (but I didn't see this happen in reality). Fix the problem by making transactions hold their own journal_head reference (in b_jcount). That way we don't have to remove journal_head explicitely via journal_remove_journal_head() and instead just remove journal_head when b_jcount drops to zero. The result of this is that [__]journal_refile_buffer(), [__]journal_unfile_buffer(), and __journal_remove_checkpoint() can free journal_head which needs modification of a few callers. Also we have to be careful because once journal_head is removed, buffer_head might be freed as well. So we have to get our own buffer_head reference where it matters. Signed-off-by: Jan Kara <jack@suse.cz>
2011-06-24 23:11:59 +02:00
if (jh->b_committed_data) {
printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__);
jbd_free(jh->b_committed_data, bh->b_size);
}
bh->b_private = NULL;
jh->b_bh = NULL; /* debug, really */
clear_buffer_jbd(bh);
journal_free_journal_head(jh);
}
/*
jbd: Fix oops in journal_remove_journal_head() journal_remove_journal_head() can oops when trying to access journal_head returned by bh2jh(). This is caused for example by the following race: TASK1 TASK2 journal_commit_transaction() ... processing t_forget list __journal_refile_buffer(jh); if (!jh->b_transaction) { jbd_unlock_bh_state(bh); journal_try_to_free_buffers() journal_grab_journal_head(bh) jbd_lock_bh_state(bh) __journal_try_to_free_buffer() journal_put_journal_head(jh) journal_remove_journal_head(bh); journal_put_journal_head() in TASK2 sees that b_jcount == 0 and buffer is not part of any transaction and thus frees journal_head before TASK1 gets to doing so. Note that even buffer_head can be released by try_to_free_buffers() after journal_put_journal_head() which adds even larger opportunity for oops (but I didn't see this happen in reality). Fix the problem by making transactions hold their own journal_head reference (in b_jcount). That way we don't have to remove journal_head explicitely via journal_remove_journal_head() and instead just remove journal_head when b_jcount drops to zero. The result of this is that [__]journal_refile_buffer(), [__]journal_unfile_buffer(), and __journal_remove_checkpoint() can free journal_head which needs modification of a few callers. Also we have to be careful because once journal_head is removed, buffer_head might be freed as well. So we have to get our own buffer_head reference where it matters. Signed-off-by: Jan Kara <jack@suse.cz>
2011-06-24 23:11:59 +02:00
* Drop a reference on the passed journal_head. If it fell to zero then
* release the journal_head from the buffer_head.
*/
void journal_put_journal_head(struct journal_head *jh)
{
struct buffer_head *bh = jh2bh(jh);
jbd_lock_bh_journal_head(bh);
J_ASSERT_JH(jh, jh->b_jcount > 0);
--jh->b_jcount;
jbd: Fix oops in journal_remove_journal_head() journal_remove_journal_head() can oops when trying to access journal_head returned by bh2jh(). This is caused for example by the following race: TASK1 TASK2 journal_commit_transaction() ... processing t_forget list __journal_refile_buffer(jh); if (!jh->b_transaction) { jbd_unlock_bh_state(bh); journal_try_to_free_buffers() journal_grab_journal_head(bh) jbd_lock_bh_state(bh) __journal_try_to_free_buffer() journal_put_journal_head(jh) journal_remove_journal_head(bh); journal_put_journal_head() in TASK2 sees that b_jcount == 0 and buffer is not part of any transaction and thus frees journal_head before TASK1 gets to doing so. Note that even buffer_head can be released by try_to_free_buffers() after journal_put_journal_head() which adds even larger opportunity for oops (but I didn't see this happen in reality). Fix the problem by making transactions hold their own journal_head reference (in b_jcount). That way we don't have to remove journal_head explicitely via journal_remove_journal_head() and instead just remove journal_head when b_jcount drops to zero. The result of this is that [__]journal_refile_buffer(), [__]journal_unfile_buffer(), and __journal_remove_checkpoint() can free journal_head which needs modification of a few callers. Also we have to be careful because once journal_head is removed, buffer_head might be freed as well. So we have to get our own buffer_head reference where it matters. Signed-off-by: Jan Kara <jack@suse.cz>
2011-06-24 23:11:59 +02:00
if (!jh->b_jcount) {
__journal_remove_journal_head(bh);
jbd: Fix oops in journal_remove_journal_head() journal_remove_journal_head() can oops when trying to access journal_head returned by bh2jh(). This is caused for example by the following race: TASK1 TASK2 journal_commit_transaction() ... processing t_forget list __journal_refile_buffer(jh); if (!jh->b_transaction) { jbd_unlock_bh_state(bh); journal_try_to_free_buffers() journal_grab_journal_head(bh) jbd_lock_bh_state(bh) __journal_try_to_free_buffer() journal_put_journal_head(jh) journal_remove_journal_head(bh); journal_put_journal_head() in TASK2 sees that b_jcount == 0 and buffer is not part of any transaction and thus frees journal_head before TASK1 gets to doing so. Note that even buffer_head can be released by try_to_free_buffers() after journal_put_journal_head() which adds even larger opportunity for oops (but I didn't see this happen in reality). Fix the problem by making transactions hold their own journal_head reference (in b_jcount). That way we don't have to remove journal_head explicitely via journal_remove_journal_head() and instead just remove journal_head when b_jcount drops to zero. The result of this is that [__]journal_refile_buffer(), [__]journal_unfile_buffer(), and __journal_remove_checkpoint() can free journal_head which needs modification of a few callers. Also we have to be careful because once journal_head is removed, buffer_head might be freed as well. So we have to get our own buffer_head reference where it matters. Signed-off-by: Jan Kara <jack@suse.cz>
2011-06-24 23:11:59 +02:00
jbd_unlock_bh_journal_head(bh);
__brelse(bh);
jbd: Fix oops in journal_remove_journal_head() journal_remove_journal_head() can oops when trying to access journal_head returned by bh2jh(). This is caused for example by the following race: TASK1 TASK2 journal_commit_transaction() ... processing t_forget list __journal_refile_buffer(jh); if (!jh->b_transaction) { jbd_unlock_bh_state(bh); journal_try_to_free_buffers() journal_grab_journal_head(bh) jbd_lock_bh_state(bh) __journal_try_to_free_buffer() journal_put_journal_head(jh) journal_remove_journal_head(bh); journal_put_journal_head() in TASK2 sees that b_jcount == 0 and buffer is not part of any transaction and thus frees journal_head before TASK1 gets to doing so. Note that even buffer_head can be released by try_to_free_buffers() after journal_put_journal_head() which adds even larger opportunity for oops (but I didn't see this happen in reality). Fix the problem by making transactions hold their own journal_head reference (in b_jcount). That way we don't have to remove journal_head explicitely via journal_remove_journal_head() and instead just remove journal_head when b_jcount drops to zero. The result of this is that [__]journal_refile_buffer(), [__]journal_unfile_buffer(), and __journal_remove_checkpoint() can free journal_head which needs modification of a few callers. Also we have to be careful because once journal_head is removed, buffer_head might be freed as well. So we have to get our own buffer_head reference where it matters. Signed-off-by: Jan Kara <jack@suse.cz>
2011-06-24 23:11:59 +02:00
} else
jbd_unlock_bh_journal_head(bh);
}
/*
* debugfs tunables
*/
#ifdef CONFIG_JBD_DEBUG
u8 journal_enable_debug __read_mostly;
EXPORT_SYMBOL(journal_enable_debug);
static struct dentry *jbd_debugfs_dir;
static struct dentry *jbd_debug;
static void __init jbd_create_debugfs_entry(void)
{
jbd_debugfs_dir = debugfs_create_dir("jbd", NULL);
if (jbd_debugfs_dir)
jbd_debug = debugfs_create_u8("jbd-debug", S_IRUGO | S_IWUSR,
jbd_debugfs_dir,
&journal_enable_debug);
}
static void __exit jbd_remove_debugfs_entry(void)
{
debugfs_remove(jbd_debug);
debugfs_remove(jbd_debugfs_dir);
}
#else
static inline void jbd_create_debugfs_entry(void)
{
}
static inline void jbd_remove_debugfs_entry(void)
{
}
#endif
struct kmem_cache *jbd_handle_cache;
static int __init journal_init_handle_cache(void)
{
jbd_handle_cache = kmem_cache_create("journal_handle",
sizeof(handle_t),
0, /* offset */
SLAB_TEMPORARY, /* flags */
NULL); /* ctor */
if (jbd_handle_cache == NULL) {
printk(KERN_EMERG "JBD: failed to create handle cache\n");
return -ENOMEM;
}
return 0;
}
static void journal_destroy_handle_cache(void)
{
if (jbd_handle_cache)
kmem_cache_destroy(jbd_handle_cache);
}
/*
* Module startup and shutdown
*/
static int __init journal_init_caches(void)
{
int ret;
ret = journal_init_revoke_caches();
if (ret == 0)
ret = journal_init_journal_head_cache();
if (ret == 0)
ret = journal_init_handle_cache();
return ret;
}
static void journal_destroy_caches(void)
{
journal_destroy_revoke_caches();
journal_destroy_journal_head_cache();
journal_destroy_handle_cache();
}
static int __init journal_init(void)
{
int ret;
BUILD_BUG_ON(sizeof(struct journal_superblock_s) != 1024);
ret = journal_init_caches();
if (ret != 0)
journal_destroy_caches();
jbd_create_debugfs_entry();
return ret;
}
static void __exit journal_exit(void)
{
#ifdef CONFIG_JBD_DEBUG
int n = atomic_read(&nr_journal_heads);
if (n)
printk(KERN_ERR "JBD: leaked %d journal_heads!\n", n);
#endif
jbd_remove_debugfs_entry();
journal_destroy_caches();
}
MODULE_LICENSE("GPL");
module_init(journal_init);
module_exit(journal_exit);