/*
* __jbd2_log_wait_for_space: wait until there is space in the journal.
*
* Called under j-state_lock *only*. It will be unlocked if we have to wait
* for a checkpoint to free up some space in the log.
*/
void __jbd2_log_wait_for_space(journal_t *journal)
{
int nblocks, space_left;
/* assert_spin_locked(&journal->j_state_lock); */
nblocks = jbd_space_needed(journal);
while (__jbd2_log_space_left(journal) < nblocks) {
if (journal->j_flags & JBD2_ABORT)
return;
write_unlock(&journal->j_state_lock);
mutex_lock(&journal->j_checkpoint_mutex);
/*
* Test again, another process may have checkpointed while we
* were waiting for the checkpoint lock. If there are no
* transactions ready to be checkpointed, try to recover
* journal space by calling cleanup_journal_tail(), and if
* that doesn't work, by waiting for the currently committing
* transaction to complete. If there is absolutely no way
* to make progress, this is either a BUG or corrupted
* filesystem, so abort the journal and leave a stack
* trace for forensic evidence.
*/
write_lock(&journal->j_state_lock);
spin_lock(&journal->j_list_lock);
nblocks = jbd_space_needed(journal);
space_left = __jbd2_log_space_left(journal);
if (space_left < nblocks) {
int chkpt = journal->j_checkpoint_transactions != NULL;
tid_t tid = 0;
if (journal->j_committing_transaction)
tid = journal->j_committing_transaction->t_tid;
spin_unlock(&journal->j_list_lock);
write_unlock(&journal->j_state_lock);
if (chkpt) {
jbd2_log_do_checkpoint(journal);
} else if (jbd2_cleanup_journal_tail(journal) == 0) {
/* We were able to recover space; yay! */
;
} else if (tid) {
jbd2_log_wait_commit(journal, tid);
} else {
printk(KERN_ERR "%s: needed %d blocks and "
"only had %d space available\n",
__func__, nblocks, space_left);
printk(KERN_ERR "%s: no way to get more "
"journal space in %s\n", __func__,
journal->j_devname);
WARN_ON(1);
jbd2_journal_abort(journal, 0);
}
write_lock(&journal->j_state_lock);
} else {
spin_unlock(&journal->j_list_lock);
}
mutex_unlock(&journal->j_checkpoint_mutex);
}
}
void __jbd2_log_wait_for_space(journal_t *journal)
{
int nblocks, space_left;
/* */
nblocks = jbd_space_needed(journal);
while (__jbd2_log_space_left(journal) < nblocks) {
if (journal->j_flags & JBD2_ABORT)
return;
write_unlock(&journal->j_state_lock);
mutex_lock(&journal->j_checkpoint_mutex);
/*
*/
write_lock(&journal->j_state_lock);
spin_lock(&journal->j_list_lock);
nblocks = jbd_space_needed(journal);
space_left = __jbd2_log_space_left(journal);
if (space_left < nblocks) {
int chkpt = journal->j_checkpoint_transactions != NULL;
tid_t tid = 0;
if (journal->j_committing_transaction)
tid = journal->j_committing_transaction->t_tid;
spin_unlock(&journal->j_list_lock);
write_unlock(&journal->j_state_lock);
if (chkpt) {
jbd2_log_do_checkpoint(journal);
} else if (jbd2_cleanup_journal_tail(journal) == 0) {
/* */
;
} else if (tid) {
jbd2_log_wait_commit(journal, tid);
} else {
printk(KERN_ERR "%s: needed %d blocks and "
"only had %d space available\n",
__func__, nblocks, space_left);
printk(KERN_ERR "%s: no way to get more "
"journal space in %s\n", __func__,
journal->j_devname);
WARN_ON(1);
jbd2_journal_abort(journal, 0);
}
write_lock(&journal->j_state_lock);
} else {
spin_unlock(&journal->j_list_lock);
}
mutex_unlock(&journal->j_checkpoint_mutex);
}
}
int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
int ret;
tid_t commit_tid;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file(file, dentry, datasync);
if (inode->i_sb->s_flags & MS_RDONLY)
return 0;
ret = flush_aio_dio_completed_IO(inode);
if (ret < 0)
return ret;
if (!journal)
return simple_fsync(file, dentry, datasync);
/*
* data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
* Metadata is in the journal, we wait for proper transaction to
* commit here.
*
* data=journal:
* filemap_fdatawrite won't do anything (the buffers are clean).
* ext4_force_commit will write the file data into the journal and
* will wait on that.
* filemap_fdatawait() will encounter a ton of newly-dirtied pages
* (they were dirtied by commit). But that's OK - the blocks are
* safe in-journal, which is all fsync() needs to ensure.
*/
if (ext4_should_journal_data(inode))
return ext4_force_commit(inode->i_sb);
commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
if (jbd2_log_start_commit(journal, commit_tid)) {
/*
* When the journal is on a different device than the
* fs data disk, we need to issue the barrier in
* writeback mode. (In ordered mode, the jbd2 layer
* will take care of issuing the barrier. In
* data=journal, all of the data blocks are written to
* the journal device.)
*/
if (ext4_should_writeback_data(inode) &&
(journal->j_fs_dev != journal->j_dev) &&
(journal->j_flags & JBD2_BARRIER))
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
ret = jbd2_log_wait_commit(journal, commit_tid);
} else if (journal->j_flags & JBD2_BARRIER)
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
return ret;
}
int ext4_sync_file(struct file *file, int datasync)
{
struct inode *inode = file->f_mapping->host;
struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
int ret;
tid_t commit_tid;
bool needs_barrier = false;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file(file, datasync);
if (inode->i_sb->s_flags & MS_RDONLY)
return 0;
ret = flush_completed_IO(inode);
if (ret < 0)
return ret;
if (!journal) {
ret = generic_file_fsync(file, datasync);
if (!ret && !list_empty(&inode->i_dentry))
ext4_sync_parent(inode);
return ret;
}
/*
* data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
* Metadata is in the journal, we wait for proper transaction to
* commit here.
*
* data=journal:
* filemap_fdatawrite won't do anything (the buffers are clean).
* ext4_force_commit will write the file data into the journal and
* will wait on that.
* filemap_fdatawait() will encounter a ton of newly-dirtied pages
* (they were dirtied by commit). But that's OK - the blocks are
* safe in-journal, which is all fsync() needs to ensure.
*/
if (ext4_should_journal_data(inode))
return ext4_force_commit(inode->i_sb);
commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
if (journal->j_flags & JBD2_BARRIER &&
!jbd2_trans_will_send_data_barrier(journal, commit_tid))
needs_barrier = true;
jbd2_log_start_commit(journal, commit_tid);
ret = jbd2_log_wait_commit(journal, commit_tid);
if (needs_barrier)
blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL,
BLKDEV_IFL_WAIT);
return ret;
}
static int __process_buffer(journal_t *journal, struct journal_head *jh,
int *batch_count, transaction_t *transaction)
{
struct buffer_head *bh = jh2bh(jh);
int ret = 0;
if (buffer_locked(bh)) {
get_bh(bh);
spin_unlock(&journal->j_list_lock);
wait_on_buffer(bh);
BUFFER_TRACE(bh, "brelse");
__brelse(bh);
ret = 1;
} else if (jh->b_transaction != NULL) {
transaction_t *t = jh->b_transaction;
tid_t tid = t->t_tid;
transaction->t_chp_stats.cs_forced_to_close++;
spin_unlock(&journal->j_list_lock);
if (unlikely(journal->j_flags & JBD2_UNMOUNT))
printk(KERN_ERR "JBD2: %s: "
"Waiting for Godot: block %llu\n",
journal->j_devname,
(unsigned long long) bh->b_blocknr);
jbd2_log_start_commit(journal, tid);
jbd2_log_wait_commit(journal, tid);
ret = 1;
} else if (!buffer_dirty(bh)) {
ret = 1;
if (unlikely(buffer_write_io_error(bh)))
ret = -EIO;
get_bh(bh);
BUFFER_TRACE(bh, "remove from checkpoint");
__jbd2_journal_remove_checkpoint(jh);
spin_unlock(&journal->j_list_lock);
__brelse(bh);
} else {
BUFFER_TRACE(bh, "queue");
get_bh(bh);
J_ASSERT_BH(bh, !buffer_jwrite(bh));
journal->j_chkpt_bhs[*batch_count] = bh;
__buffer_relink_io(jh);
transaction->t_chp_stats.cs_written++;
(*batch_count)++;
if (*batch_count == JBD2_NR_BATCH) {
spin_unlock(&journal->j_list_lock);
__flush_batch(journal, batch_count);
ret = 1;
}
}
return ret;
}
/*
* Perform an actual checkpoint. We take the first transaction on the
* list of transactions to be checkpointed and send all its buffers
* to disk. We submit larger chunks of data at once.
*
* The journal should be locked before calling this function.
* Called with j_checkpoint_mutex held.
*/
int jbd2_log_do_checkpoint(journal_t *journal)
{
struct journal_head *jh;
struct buffer_head *bh;
transaction_t *transaction;
tid_t this_tid;
int result, batch_count = 0;
jbd_debug(1, "Start checkpoint\n");
/*
* First thing: if there are any transactions in the log which
* don't need checkpointing, just eliminate them from the
* journal straight away.
*/
result = jbd2_cleanup_journal_tail(journal);
trace_jbd2_checkpoint(journal, result);
jbd_debug(1, "cleanup_journal_tail returned %d\n", result);
if (result <= 0)
return result;
/*
* OK, we need to start writing disk blocks. Take one transaction
* and write it.
*/
result = 0;
spin_lock(&journal->j_list_lock);
if (!journal->j_checkpoint_transactions)
goto out;
transaction = journal->j_checkpoint_transactions;
if (transaction->t_chp_stats.cs_chp_time == 0)
transaction->t_chp_stats.cs_chp_time = jiffies;
this_tid = transaction->t_tid;
restart:
/*
* If someone cleaned up this transaction while we slept, we're
* done (maybe it's a new transaction, but it fell at the same
* address).
*/
if (journal->j_checkpoint_transactions != transaction ||
transaction->t_tid != this_tid)
goto out;
/* checkpoint all of the transaction's buffers */
while (transaction->t_checkpoint_list) {
jh = transaction->t_checkpoint_list;
bh = jh2bh(jh);
if (buffer_locked(bh)) {
spin_unlock(&journal->j_list_lock);
get_bh(bh);
wait_on_buffer(bh);
/* the journal_head may have gone by now */
BUFFER_TRACE(bh, "brelse");
__brelse(bh);
goto retry;
}
if (jh->b_transaction != NULL) {
transaction_t *t = jh->b_transaction;
tid_t tid = t->t_tid;
transaction->t_chp_stats.cs_forced_to_close++;
spin_unlock(&journal->j_list_lock);
if (unlikely(journal->j_flags & JBD2_UNMOUNT))
/*
* The journal thread is dead; so
* starting and waiting for a commit
* to finish will cause us to wait for
* a _very_ long time.
*/
printk(KERN_ERR
"JBD2: %s: Waiting for Godot: block %llu\n",
journal->j_devname, (unsigned long long) bh->b_blocknr);
jbd2_log_start_commit(journal, tid);
jbd2_log_wait_commit(journal, tid);
goto retry;
}
if (!buffer_dirty(bh)) {
if (unlikely(buffer_write_io_error(bh)) && !result)
result = -EIO;
BUFFER_TRACE(bh, "remove from checkpoint");
if (__jbd2_journal_remove_checkpoint(jh))
/* The transaction was released; we're done */
goto out;
continue;
}
/*
* Important: we are about to write the buffer, and
* possibly block, while still holding the journal
* lock. We cannot afford to let the transaction
* logic start messing around with this buffer before
* we write it to disk, as that would break
* recoverability.
*/
BUFFER_TRACE(bh, "queue");
get_bh(bh);
J_ASSERT_BH(bh, !buffer_jwrite(bh));
journal->j_chkpt_bhs[batch_count++] = bh;
__buffer_relink_io(jh);
transaction->t_chp_stats.cs_written++;
if ((batch_count == JBD2_NR_BATCH) ||
need_resched() ||
spin_needbreak(&journal->j_list_lock))
goto unlock_and_flush;
}
if (batch_count) {
unlock_and_flush:
spin_unlock(&journal->j_list_lock);
retry:
if (batch_count)
__flush_batch(journal, &batch_count);
spin_lock(&journal->j_list_lock);
goto restart;
}
/*
* Now we issued all of the transaction's buffers, let's deal
* with the buffers that are out for I/O.
*/
restart2:
/* Did somebody clean up the transaction in the meanwhile? */
if (journal->j_checkpoint_transactions != transaction ||
transaction->t_tid != this_tid)
goto out;
while (transaction->t_checkpoint_io_list) {
jh = transaction->t_checkpoint_io_list;
bh = jh2bh(jh);
if (buffer_locked(bh)) {
spin_unlock(&journal->j_list_lock);
get_bh(bh);
wait_on_buffer(bh);
/* the journal_head may have gone by now */
BUFFER_TRACE(bh, "brelse");
__brelse(bh);
spin_lock(&journal->j_list_lock);
goto restart2;
}
if (unlikely(buffer_write_io_error(bh)) && !result)
result = -EIO;
/*
* Now in whatever state the buffer currently is, we
* know that it has been written out and so we can
* drop it from the list
*/
if (__jbd2_journal_remove_checkpoint(jh))
break;
}
out:
spin_unlock(&journal->j_list_lock);
if (result < 0)
jbd2_journal_abort(journal, result);
else
result = jbd2_cleanup_journal_tail(journal);
return (result < 0) ? result : 0;
}
int jbd2_journal_stop(handle_t *handle)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
int err, wait_for_commit = 0;
tid_t tid;
pid_t pid;
J_ASSERT(journal_current_handle() == handle);
if (is_handle_aborted(handle))
err = -EIO;
else {
J_ASSERT(atomic_read(&transaction->t_updates) > 0);
err = 0;
}
if (--handle->h_ref > 0) {
jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1,
handle->h_ref);
return err;
}
jbd_debug(4, "Handle %p going down\n", handle);
pid = current->pid;
if (handle->h_sync && journal->j_last_sync_writer != pid) {
u64 commit_time, trans_time;
journal->j_last_sync_writer = pid;
read_lock(&journal->j_state_lock);
commit_time = journal->j_average_commit_time;
read_unlock(&journal->j_state_lock);
trans_time = ktime_to_ns(ktime_sub(ktime_get(),
transaction->t_start_time));
commit_time = max_t(u64, commit_time,
1000*journal->j_min_batch_time);
commit_time = min_t(u64, commit_time,
1000*journal->j_max_batch_time);
if (trans_time < commit_time) {
ktime_t expires = ktime_add_ns(ktime_get(),
commit_time);
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
}
}
if (handle->h_sync)
transaction->t_synchronous_commit = 1;
current->journal_info = NULL;
atomic_sub(handle->h_buffer_credits,
&transaction->t_outstanding_credits);
if (handle->h_sync ||
(atomic_read(&transaction->t_outstanding_credits) >
journal->j_max_transaction_buffers) ||
time_after_eq(jiffies, transaction->t_expires)) {
jbd_debug(2, "transaction too old, requesting commit for "
"handle %p\n", handle);
jbd2_log_start_commit(journal, transaction->t_tid);
if (handle->h_sync && !(current->flags & PF_MEMALLOC))
wait_for_commit = 1;
}
tid = transaction->t_tid;
if (atomic_dec_and_test(&transaction->t_updates)) {
wake_up(&journal->j_wait_updates);
if (journal->j_barrier_count)
wake_up(&journal->j_wait_transaction_locked);
}
if (wait_for_commit)
err = jbd2_log_wait_commit(journal, tid);
lock_map_release(&handle->h_lockdep_map);
jbd2_free_handle(handle);
return err;
}
/*
* Try to flush one buffer from the checkpoint list to disk.
*
* Return 1 if something happened which requires us to abort the current
* scan of the checkpoint list. Return <0 if the buffer has failed to
* be written out.
*
* Called with j_list_lock held and drops it if 1 is returned
*/
static int __process_buffer(journal_t *journal, struct journal_head *jh,
int *batch_count, transaction_t *transaction)
{
struct buffer_head *bh = jh2bh(jh);
int ret = 0;
if (buffer_locked(bh)) {
get_bh(bh);
spin_unlock(&journal->j_list_lock);
wait_on_buffer(bh);
/* the journal_head may have gone by now */
BUFFER_TRACE(bh, "brelse");
__brelse(bh);
ret = 1;
} else if (jh->b_transaction != NULL) {
transaction_t *t = jh->b_transaction;
tid_t tid = t->t_tid;
transaction->t_chp_stats.cs_forced_to_close++;
spin_unlock(&journal->j_list_lock);
if (unlikely(journal->j_flags & JBD2_UNMOUNT))
/*
* The journal thread is dead; so starting and
* waiting for a commit to finish will cause
* us to wait for a _very_ long time.
*/
printk(KERN_ERR "JBD2: %s: "
"Waiting for Godot: block %llu\n",
journal->j_devname,
(unsigned long long) bh->b_blocknr);
jbd2_log_start_commit(journal, tid);
jbd2_log_wait_commit(journal, tid);
ret = 1;
} else if (!buffer_dirty(bh)) {
ret = 1;
if (unlikely(buffer_write_io_error(bh)))
ret = -EIO;
get_bh(bh);
BUFFER_TRACE(bh, "remove from checkpoint");
__jbd2_journal_remove_checkpoint(jh);
spin_unlock(&journal->j_list_lock);
__brelse(bh);
} else {
/*
* Important: we are about to write the buffer, and
* possibly block, while still holding the journal lock.
* We cannot afford to let the transaction logic start
* messing around with this buffer before we write it to
* disk, as that would break recoverability.
*/
BUFFER_TRACE(bh, "queue");
get_bh(bh);
J_ASSERT_BH(bh, !buffer_jwrite(bh));
journal->j_chkpt_bhs[*batch_count] = bh;
__buffer_relink_io(jh);
transaction->t_chp_stats.cs_written++;
(*batch_count)++;
if (*batch_count == JBD2_NR_BATCH) {
spin_unlock(&journal->j_list_lock);
__flush_batch(journal, batch_count);
ret = 1;
}
}
return ret;
}