handle_t *journal_start(journal_t *journal, int nblocks)
{
handle_t *handle = journal_current_handle();
int err;
if (!journal)
return ERR_PTR(-EROFS);
if (handle) {
J_ASSERT(handle->h_transaction->t_journal == journal);
handle->h_ref++;
return handle;
}
handle = new_handle(nblocks);
if (!handle)
return ERR_PTR(-ENOMEM);
current->journal_info = handle;
err = start_this_handle(journal, handle);
if (err < 0) {
jbd_free_handle(handle);
current->journal_info = NULL;
handle = ERR_PTR(err);
goto out;
}
out:
return handle;
}
/*
* Wrappers for jbd2_journal_start/end.
*/
handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
int type, int nblocks)
{
journal_t *journal;
might_sleep();
trace_ext4_journal_start(sb, nblocks, _RET_IP_);
if (sb->s_flags & MS_RDONLY && !journal_current_handle())
return ERR_PTR(-EROFS);
WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
journal = EXT4_SB(sb)->s_journal;
if (!journal)
return ext4_get_nojournal();
/*
* Special case here: if the journal has aborted behind our
* backs (eg. EIO in the commit thread), then we still need to
* take the FS itself readonly cleanly.
*/
if (is_journal_aborted(journal)) {
ext4_abort(sb, "Detected aborted journal");
return ERR_PTR(-EROFS);
}
return jbd2__journal_start(journal, nblocks, GFP_NOFS, type, line);
}
int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
tid_t tid;
int need_to_start, ret;
if (is_handle_aborted(handle))
return 0;
J_ASSERT(atomic_read(&transaction->t_updates) > 0);
J_ASSERT(journal_current_handle() == handle);
read_lock(&journal->j_state_lock);
spin_lock(&transaction->t_handle_lock);
atomic_sub(handle->h_buffer_credits,
&transaction->t_outstanding_credits);
if (atomic_dec_and_test(&transaction->t_updates))
wake_up(&journal->j_wait_updates);
spin_unlock(&transaction->t_handle_lock);
jbd_debug(2, "restarting handle %p\n", handle);
tid = transaction->t_tid;
need_to_start = !tid_geq(journal->j_commit_request, tid);
read_unlock(&journal->j_state_lock);
if (need_to_start)
jbd2_log_start_commit(journal, tid);
lock_map_release(&handle->h_lockdep_map);
handle->h_buffer_credits = nblocks;
ret = start_this_handle(journal, handle, gfp_mask);
return ret;
}
/**
* ext4_has_free_blocks()
* @sbi: in-core super block structure.
* @nblocks: number of needed blocks
*
* Check if filesystem has nblocks free & available for allocation.
* On success return 1, return 0 on failure.
*/
static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
{
s64 free_blocks, dirty_blocks, root_blocks;
#ifdef CONFIG_EXT4_FS_SNAPSHOT_CTL_RESERVE
ext4_fsblk_t snapshot_r_blocks;
handle_t *handle = journal_current_handle();
#endif
struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
free_blocks = percpu_counter_read_positive(fbc);
dirty_blocks = percpu_counter_read_positive(dbc);
root_blocks = ext4_r_blocks_count(sbi->s_es);
#ifdef CONFIG_EXT4_FS_SNAPSHOT_CTL_RESERVE
if (handle && sbi->s_active_snapshot) {
snapshot_r_blocks =
le64_to_cpu(sbi->s_es->s_snapshot_r_blocks_count);
/*
* snapshot reserved blocks for COWing to active snapshot
*/
if (free_blocks < snapshot_r_blocks + 1 &&
!IS_COWING(handle)) {
return 0;
}
/*
* mortal users must reserve blocks for both snapshot and
* root user
*/
root_blocks += snapshot_r_blocks;
}
#endif
if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
EXT4_FREEBLOCKS_WATERMARK) {
free_blocks = percpu_counter_sum_positive(fbc);
dirty_blocks = percpu_counter_sum_positive(dbc);
if (dirty_blocks < 0) {
printk(KERN_CRIT "Dirty block accounting "
"went wrong %lld\n",
(long long)dirty_blocks);
}
}
/* Check whether we have space after
* accounting for current dirty blocks & root reserved blocks.
*/
if (free_blocks >= ((root_blocks + nblocks) + dirty_blocks))
return 1;
/* Hm, nope. Are (enough) root reserved blocks available? */
if (sbi->s_resuid == current_fsuid() ||
((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) ||
capable(CAP_SYS_RESOURCE)) {
if (free_blocks >= (nblocks + dirty_blocks))
return 1;
}
return 0;
}
/* pass it NULL and it will allocate a new handle object for you. If
* you pass it a handle however, it may still return error, in which
* case it has free'd the passed handle for you. */
handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int max_buffs)
{
journal_t *journal = osb->journal->j_journal;
handle_t *handle;
BUG_ON(!osb || !osb->journal->j_journal);
if (ocfs2_is_hard_readonly(osb))
return ERR_PTR(-EROFS);
BUG_ON(osb->journal->j_state == OCFS2_JOURNAL_FREE);
BUG_ON(max_buffs <= 0);
/* JBD might support this, but our journalling code doesn't yet. */
if (journal_current_handle()) {
mlog(ML_ERROR, "Recursive transaction attempted!\n");
BUG();
}
down_read(&osb->journal->j_trans_barrier);
handle = journal_start(journal, max_buffs);
if (IS_ERR(handle)) {
up_read(&osb->journal->j_trans_barrier);
mlog_errno(PTR_ERR(handle));
if (is_journal_aborted(journal)) {
ocfs2_abort(osb->sb, "Detected aborted journal");
handle = ERR_PTR(-EROFS);
}
} else {
if (!ocfs2_mount_local(osb))
atomic_inc(&(osb->journal->j_num_trans));
}
return handle;
}
int journal_restart(handle_t *handle, int nblocks)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
int ret;
/* If we've had an abort of any type, don't even think about
* actually doing the restart! */
if (is_handle_aborted(handle))
return 0;
/*
* First unlink the handle from its current transaction, and start the
* commit on that.
*/
J_ASSERT(transaction->t_updates > 0);
J_ASSERT(journal_current_handle() == handle);
spin_lock(&journal->j_state_lock);
spin_lock(&transaction->t_handle_lock);
transaction->t_outstanding_credits -= handle->h_buffer_credits;
transaction->t_updates--;
if (!transaction->t_updates)
wake_up(&journal->j_wait_updates);
spin_unlock(&transaction->t_handle_lock);
jbd_debug(2, "restarting handle %p\n", handle);
__log_start_commit(journal, transaction->t_tid);
spin_unlock(&journal->j_state_lock);
lock_map_release(&handle->h_lockdep_map);
handle->h_buffer_credits = nblocks;
ret = start_this_handle(journal, handle);
return ret;
}
handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int max_buffs)
{
journal_t *journal = osb->journal->j_journal;
handle_t *handle;
BUG_ON(!osb || !osb->journal->j_journal);
if (ocfs2_is_hard_readonly(osb))
return ERR_PTR(-EROFS);
BUG_ON(osb->journal->j_state == OCFS2_JOURNAL_FREE);
BUG_ON(max_buffs <= 0);
if (journal_current_handle())
return jbd2_journal_start(journal, max_buffs);
down_read(&osb->journal->j_trans_barrier);
handle = jbd2_journal_start(journal, max_buffs);
if (IS_ERR(handle)) {
up_read(&osb->journal->j_trans_barrier);
mlog_errno(PTR_ERR(handle));
if (is_journal_aborted(journal)) {
ocfs2_abort(osb->sb, "Detected aborted journal");
handle = ERR_PTR(-EROFS);
}
} else {
if (!ocfs2_mount_local(osb))
atomic_inc(&(osb->journal->j_num_trans));
}
return handle;
}
int journal_stop(handle_t *handle)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
int err;
pid_t pid;
J_ASSERT(journal_current_handle() == handle);
if (is_handle_aborted(handle))
err = -EIO;
else {
J_ASSERT(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);
/*
* Implement synchronous transaction batching. If the handle
* was synchronous, don't force a commit immediately. Let's
* yield and let another thread piggyback onto this transaction.
* Keep doing that while new threads continue to arrive.
* It doesn't cost much - we're about to run a commit and sleep
* on IO anyway. Speeds up many-threaded, many-dir operations
* by 30x or more...
*
* We try and optimize the sleep time against what the underlying disk
* can do, instead of having a static sleep time. This is usefull for
* the case where our storage is so fast that it is more optimal to go
* ahead and force a flush and wait for the transaction to be committed
* than it is to wait for an arbitrary amount of time for new writers to
* join the transaction. We achieve this by measuring how long it takes
* to commit a transaction, and compare it with how long this
* transaction has been running, and if run time < commit time then we
* sleep for the delta and commit. This greatly helps super fast disks
* that would see slowdowns as more threads started doing fsyncs.
*
* But don't do this if this process was the most recent one to
* perform a synchronous write. We do this to detect the case where a
* single process is doing a stream of sync writes. No point in waiting
* for joiners in that case.
*/
pid = current->pid;
if (handle->h_sync && journal->j_last_sync_writer != pid) {
u64 commit_time, trans_time;
journal->j_last_sync_writer = pid;
spin_lock(&journal->j_state_lock);
commit_time = journal->j_average_commit_time;
spin_unlock(&journal->j_state_lock);
trans_time = ktime_to_ns(ktime_sub(ktime_get(),
transaction->t_start_time));
commit_time = min_t(u64, commit_time,
1000*jiffies_to_usecs(1));
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;
spin_lock(&journal->j_state_lock);
spin_lock(&transaction->t_handle_lock);
transaction->t_outstanding_credits -= handle->h_buffer_credits;
transaction->t_updates--;
if (!transaction->t_updates) {
wake_up(&journal->j_wait_updates);
if (journal->j_barrier_count)
wake_up(&journal->j_wait_transaction_locked);
}
/*
* If the handle is marked SYNC, we need to set another commit
* going! We also want to force a commit if the current
* transaction is occupying too much of the log, or if the
* transaction is too old now.
*/
if (handle->h_sync ||
transaction->t_outstanding_credits >
journal->j_max_transaction_buffers ||
time_after_eq(jiffies, transaction->t_expires)) {
/* Do this even for aborted journals: an abort still
* completes the commit thread, it just doesn't write
* anything to disk. */
tid_t tid = transaction->t_tid;
spin_unlock(&transaction->t_handle_lock);
jbd_debug(2, "transaction too old, requesting commit for "
"handle %p\n", handle);
/* This is non-blocking */
__log_start_commit(journal, transaction->t_tid);
spin_unlock(&journal->j_state_lock);
/*
* Special case: JFS_SYNC synchronous updates require us
* to wait for the commit to complete.
*/
if (handle->h_sync && !(current->flags & PF_MEMALLOC))
err = log_wait_commit(journal, tid);
} else {
spin_unlock(&transaction->t_handle_lock);
spin_unlock(&journal->j_state_lock);
}
lock_map_release(&handle->h_lockdep_map);
jbd_free_handle(handle);
return err;
}
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;
}
