jbd2: Change j_state_lock to be a rwlock_t
Lockstat reports have shown that j_state_lock is a major source of lock contention, especially on systems with more than 4 CPU cores. So change it to be a read/write spinlock. Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
This commit is contained in:
Theodore Ts'o
parent
a51dca9cd3
commit
a931da6ac9
|
|
@ -5066,7 +5066,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
|
|||
transaction_t *transaction;
|
||||
tid_t tid;
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
read_lock(&journal->j_state_lock);
|
||||
if (journal->j_running_transaction)
|
||||
transaction = journal->j_running_transaction;
|
||||
else
|
||||
|
|
@ -5075,7 +5075,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
|
|||
tid = transaction->t_tid;
|
||||
else
|
||||
tid = journal->j_commit_sequence;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
ei->i_sync_tid = tid;
|
||||
ei->i_datasync_tid = tid;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -3232,7 +3232,7 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
|
|||
journal->j_min_batch_time = sbi->s_min_batch_time;
|
||||
journal->j_max_batch_time = sbi->s_max_batch_time;
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
if (test_opt(sb, BARRIER))
|
||||
journal->j_flags |= JBD2_BARRIER;
|
||||
else
|
||||
|
|
@ -3241,7 +3241,7 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
|
|||
journal->j_flags |= JBD2_ABORT_ON_SYNCDATA_ERR;
|
||||
else
|
||||
journal->j_flags &= ~JBD2_ABORT_ON_SYNCDATA_ERR;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
}
|
||||
|
||||
static journal_t *ext4_get_journal(struct super_block *sb,
|
||||
|
|
|
|||
|
|
@ -118,13 +118,13 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
|
|||
void __jbd2_log_wait_for_space(journal_t *journal)
|
||||
{
|
||||
int nblocks, space_left;
|
||||
assert_spin_locked(&journal->j_state_lock);
|
||||
/* 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;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
mutex_lock(&journal->j_checkpoint_mutex);
|
||||
|
||||
/*
|
||||
|
|
@ -138,7 +138,7 @@ void __jbd2_log_wait_for_space(journal_t *journal)
|
|||
* filesystem, so abort the journal and leave a stack
|
||||
* trace for forensic evidence.
|
||||
*/
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
spin_lock(&journal->j_list_lock);
|
||||
nblocks = jbd_space_needed(journal);
|
||||
space_left = __jbd2_log_space_left(journal);
|
||||
|
|
@ -149,7 +149,7 @@ void __jbd2_log_wait_for_space(journal_t *journal)
|
|||
if (journal->j_committing_transaction)
|
||||
tid = journal->j_committing_transaction->t_tid;
|
||||
spin_unlock(&journal->j_list_lock);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
if (chkpt) {
|
||||
jbd2_log_do_checkpoint(journal);
|
||||
} else if (jbd2_cleanup_journal_tail(journal) == 0) {
|
||||
|
|
@ -167,7 +167,7 @@ void __jbd2_log_wait_for_space(journal_t *journal)
|
|||
WARN_ON(1);
|
||||
jbd2_journal_abort(journal, 0);
|
||||
}
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
} else {
|
||||
spin_unlock(&journal->j_list_lock);
|
||||
}
|
||||
|
|
@ -474,7 +474,7 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
|
|||
* next transaction ID we will write, and where it will
|
||||
* start. */
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
spin_lock(&journal->j_list_lock);
|
||||
transaction = journal->j_checkpoint_transactions;
|
||||
if (transaction) {
|
||||
|
|
@ -496,7 +496,7 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
|
|||
/* If the oldest pinned transaction is at the tail of the log
|
||||
already then there's not much we can do right now. */
|
||||
if (journal->j_tail_sequence == first_tid) {
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
return 1;
|
||||
}
|
||||
|
||||
|
|
@ -516,7 +516,7 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
|
|||
journal->j_free += freed;
|
||||
journal->j_tail_sequence = first_tid;
|
||||
journal->j_tail = blocknr;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
|
||||
/*
|
||||
* If there is an external journal, we need to make sure that
|
||||
|
|
|
|||
|
|
@ -152,9 +152,9 @@ static int journal_submit_commit_record(journal_t *journal,
|
|||
printk(KERN_WARNING
|
||||
"JBD2: Disabling barriers on %s, "
|
||||
"not supported by device\n", journal->j_devname);
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
journal->j_flags &= ~JBD2_BARRIER;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
|
||||
/* And try again, without the barrier */
|
||||
lock_buffer(bh);
|
||||
|
|
@ -182,9 +182,9 @@ retry:
|
|||
printk(KERN_WARNING
|
||||
"JBD2: %s: disabling barries on %s - not supported "
|
||||
"by device\n", __func__, journal->j_devname);
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
journal->j_flags &= ~JBD2_BARRIER;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
|
||||
lock_buffer(bh);
|
||||
clear_buffer_dirty(bh);
|
||||
|
|
@ -400,7 +400,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
|
|||
jbd_debug(1, "JBD: starting commit of transaction %d\n",
|
||||
commit_transaction->t_tid);
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
commit_transaction->t_state = T_LOCKED;
|
||||
|
||||
/*
|
||||
|
|
@ -424,9 +424,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
|
|||
TASK_UNINTERRUPTIBLE);
|
||||
if (atomic_read(&commit_transaction->t_updates)) {
|
||||
spin_unlock(&commit_transaction->t_handle_lock);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
schedule();
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
spin_lock(&commit_transaction->t_handle_lock);
|
||||
}
|
||||
finish_wait(&journal->j_wait_updates, &wait);
|
||||
|
|
@ -497,7 +497,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
|
|||
start_time = ktime_get();
|
||||
commit_transaction->t_log_start = journal->j_head;
|
||||
wake_up(&journal->j_wait_transaction_locked);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
|
||||
jbd_debug (3, "JBD: commit phase 2\n");
|
||||
|
||||
|
|
@ -519,9 +519,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
|
|||
* transaction! Now comes the tricky part: we need to write out
|
||||
* metadata. Loop over the transaction's entire buffer list:
|
||||
*/
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
commit_transaction->t_state = T_COMMIT;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
|
||||
trace_jbd2_commit_logging(journal, commit_transaction);
|
||||
stats.run.rs_logging = jiffies;
|
||||
|
|
@ -978,7 +978,7 @@ restart_loop:
|
|||
* __jbd2_journal_drop_transaction(). Otherwise we could race with
|
||||
* other checkpointing code processing the transaction...
|
||||
*/
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
spin_lock(&journal->j_list_lock);
|
||||
/*
|
||||
* Now recheck if some buffers did not get attached to the transaction
|
||||
|
|
@ -986,7 +986,7 @@ restart_loop:
|
|||
*/
|
||||
if (commit_transaction->t_forget) {
|
||||
spin_unlock(&journal->j_list_lock);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
goto restart_loop;
|
||||
}
|
||||
|
||||
|
|
@ -1038,7 +1038,7 @@ restart_loop:
|
|||
journal->j_average_commit_time*3) / 4;
|
||||
else
|
||||
journal->j_average_commit_time = commit_time;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
|
||||
if (commit_transaction->t_checkpoint_list == NULL &&
|
||||
commit_transaction->t_checkpoint_io_list == NULL) {
|
||||
|
|
|
|||
|
|
@ -142,7 +142,7 @@ static int kjournald2(void *arg)
|
|||
/*
|
||||
* And now, wait forever for commit wakeup events.
|
||||
*/
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
|
||||
loop:
|
||||
if (journal->j_flags & JBD2_UNMOUNT)
|
||||
|
|
@ -153,10 +153,10 @@ loop:
|
|||
|
||||
if (journal->j_commit_sequence != journal->j_commit_request) {
|
||||
jbd_debug(1, "OK, requests differ\n");
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
del_timer_sync(&journal->j_commit_timer);
|
||||
jbd2_journal_commit_transaction(journal);
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
goto loop;
|
||||
}
|
||||
|
||||
|
|
@ -168,9 +168,9 @@ loop:
|
|||
* be already stopped.
|
||||
*/
|
||||
jbd_debug(1, "Now suspending kjournald2\n");
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
refrigerator();
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
} else {
|
||||
/*
|
||||
* We assume on resume that commits are already there,
|
||||
|
|
@ -190,9 +190,9 @@ loop:
|
|||
if (journal->j_flags & JBD2_UNMOUNT)
|
||||
should_sleep = 0;
|
||||
if (should_sleep) {
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
schedule();
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
}
|
||||
finish_wait(&journal->j_wait_commit, &wait);
|
||||
}
|
||||
|
|
@ -210,7 +210,7 @@ loop:
|
|||
goto loop;
|
||||
|
||||
end_loop:
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
del_timer_sync(&journal->j_commit_timer);
|
||||
journal->j_task = NULL;
|
||||
wake_up(&journal->j_wait_done_commit);
|
||||
|
|
@ -233,16 +233,16 @@ static int jbd2_journal_start_thread(journal_t *journal)
|
|||
|
||||
static void journal_kill_thread(journal_t *journal)
|
||||
{
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
journal->j_flags |= JBD2_UNMOUNT;
|
||||
|
||||
while (journal->j_task) {
|
||||
wake_up(&journal->j_wait_commit);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
wait_event(journal->j_wait_done_commit, journal->j_task == NULL);
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
}
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -452,7 +452,7 @@ int __jbd2_log_space_left(journal_t *journal)
|
|||
{
|
||||
int left = journal->j_free;
|
||||
|
||||
assert_spin_locked(&journal->j_state_lock);
|
||||
/* assert_spin_locked(&journal->j_state_lock); */
|
||||
|
||||
/*
|
||||
* Be pessimistic here about the number of those free blocks which
|
||||
|
|
@ -497,9 +497,9 @@ int jbd2_log_start_commit(journal_t *journal, tid_t tid)
|
|||
{
|
||||
int ret;
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
ret = __jbd2_log_start_commit(journal, tid);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
|
@ -518,7 +518,7 @@ int jbd2_journal_force_commit_nested(journal_t *journal)
|
|||
transaction_t *transaction = NULL;
|
||||
tid_t tid;
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
read_lock(&journal->j_state_lock);
|
||||
if (journal->j_running_transaction && !current->journal_info) {
|
||||
transaction = journal->j_running_transaction;
|
||||
__jbd2_log_start_commit(journal, transaction->t_tid);
|
||||
|
|
@ -526,12 +526,12 @@ int jbd2_journal_force_commit_nested(journal_t *journal)
|
|||
transaction = journal->j_committing_transaction;
|
||||
|
||||
if (!transaction) {
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
return 0; /* Nothing to retry */
|
||||
}
|
||||
|
||||
tid = transaction->t_tid;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
jbd2_log_wait_commit(journal, tid);
|
||||
return 1;
|
||||
}
|
||||
|
|
@ -545,7 +545,7 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
|
|||
{
|
||||
int ret = 0;
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
if (journal->j_running_transaction) {
|
||||
tid_t tid = journal->j_running_transaction->t_tid;
|
||||
|
||||
|
|
@ -564,7 +564,7 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
|
|||
*ptid = journal->j_committing_transaction->t_tid;
|
||||
ret = 1;
|
||||
}
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
|
@ -576,26 +576,24 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
|
|||
{
|
||||
int err = 0;
|
||||
|
||||
read_lock(&journal->j_state_lock);
|
||||
#ifdef CONFIG_JBD2_DEBUG
|
||||
spin_lock(&journal->j_state_lock);
|
||||
if (!tid_geq(journal->j_commit_request, tid)) {
|
||||
printk(KERN_EMERG
|
||||
"%s: error: j_commit_request=%d, tid=%d\n",
|
||||
__func__, journal->j_commit_request, tid);
|
||||
}
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
#endif
|
||||
spin_lock(&journal->j_state_lock);
|
||||
while (tid_gt(tid, journal->j_commit_sequence)) {
|
||||
jbd_debug(1, "JBD: want %d, j_commit_sequence=%d\n",
|
||||
tid, journal->j_commit_sequence);
|
||||
wake_up(&journal->j_wait_commit);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_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);
|
||||
read_lock(&journal->j_state_lock);
|
||||
}
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
|
||||
if (unlikely(is_journal_aborted(journal))) {
|
||||
printk(KERN_EMERG "journal commit I/O error\n");
|
||||
|
|
@ -612,7 +610,7 @@ int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
|
|||
{
|
||||
unsigned long blocknr;
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
J_ASSERT(journal->j_free > 1);
|
||||
|
||||
blocknr = journal->j_head;
|
||||
|
|
@ -620,7 +618,7 @@ int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
|
|||
journal->j_free--;
|
||||
if (journal->j_head == journal->j_last)
|
||||
journal->j_head = journal->j_first;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
return jbd2_journal_bmap(journal, blocknr, retp);
|
||||
}
|
||||
|
||||
|
|
@ -840,7 +838,7 @@ static journal_t * journal_init_common (void)
|
|||
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);
|
||||
rwlock_init(&journal->j_state_lock);
|
||||
|
||||
journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE);
|
||||
journal->j_min_batch_time = 0;
|
||||
|
|
@ -1106,14 +1104,14 @@ void jbd2_journal_update_superblock(journal_t *journal, int wait)
|
|||
set_buffer_uptodate(bh);
|
||||
}
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
read_lock(&journal->j_state_lock);
|
||||
jbd_debug(1,"JBD: updating superblock (start %ld, seq %d, errno %d)\n",
|
||||
journal->j_tail, journal->j_tail_sequence, journal->j_errno);
|
||||
|
||||
sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
|
||||
sb->s_start = cpu_to_be32(journal->j_tail);
|
||||
sb->s_errno = cpu_to_be32(journal->j_errno);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
|
||||
BUFFER_TRACE(bh, "marking dirty");
|
||||
mark_buffer_dirty(bh);
|
||||
|
|
@ -1134,12 +1132,12 @@ out:
|
|||
* any future commit will have to be careful to update the
|
||||
* superblock again to re-record the true start of the log. */
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
if (sb->s_start)
|
||||
journal->j_flags &= ~JBD2_FLUSHED;
|
||||
else
|
||||
journal->j_flags |= JBD2_FLUSHED;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -1551,7 +1549,7 @@ int jbd2_journal_flush(journal_t *journal)
|
|||
transaction_t *transaction = NULL;
|
||||
unsigned long old_tail;
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
|
||||
/* Force everything buffered to the log... */
|
||||
if (journal->j_running_transaction) {
|
||||
|
|
@ -1564,10 +1562,10 @@ int jbd2_journal_flush(journal_t *journal)
|
|||
if (transaction) {
|
||||
tid_t tid = transaction->t_tid;
|
||||
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
jbd2_log_wait_commit(journal, tid);
|
||||
} else {
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
}
|
||||
|
||||
/* ...and flush everything in the log out to disk. */
|
||||
|
|
@ -1591,12 +1589,12 @@ int jbd2_journal_flush(journal_t *journal)
|
|||
* the magic code for a fully-recovered superblock. Any future
|
||||
* commits of data to the journal will restore the current
|
||||
* s_start value. */
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
old_tail = journal->j_tail;
|
||||
journal->j_tail = 0;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
jbd2_journal_update_superblock(journal, 1);
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
journal->j_tail = old_tail;
|
||||
|
||||
J_ASSERT(!journal->j_running_transaction);
|
||||
|
|
@ -1604,7 +1602,7 @@ int jbd2_journal_flush(journal_t *journal)
|
|||
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);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
@ -1668,12 +1666,12 @@ void __jbd2_journal_abort_hard(journal_t *journal)
|
|||
printk(KERN_ERR "Aborting journal on device %s.\n",
|
||||
journal->j_devname);
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
journal->j_flags |= JBD2_ABORT;
|
||||
transaction = journal->j_running_transaction;
|
||||
if (transaction)
|
||||
__jbd2_log_start_commit(journal, transaction->t_tid);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
}
|
||||
|
||||
/* Soft abort: record the abort error status in the journal superblock,
|
||||
|
|
@ -1758,12 +1756,12 @@ int jbd2_journal_errno(journal_t *journal)
|
|||
{
|
||||
int err;
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
read_lock(&journal->j_state_lock);
|
||||
if (journal->j_flags & JBD2_ABORT)
|
||||
err = -EROFS;
|
||||
else
|
||||
err = journal->j_errno;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
return err;
|
||||
}
|
||||
|
||||
|
|
@ -1778,12 +1776,12 @@ int jbd2_journal_clear_err(journal_t *journal)
|
|||
{
|
||||
int err = 0;
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
if (journal->j_flags & JBD2_ABORT)
|
||||
err = -EROFS;
|
||||
else
|
||||
journal->j_errno = 0;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
return err;
|
||||
}
|
||||
|
||||
|
|
@ -1796,10 +1794,10 @@ int jbd2_journal_clear_err(journal_t *journal)
|
|||
*/
|
||||
void jbd2_journal_ack_err(journal_t *journal)
|
||||
{
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
if (journal->j_errno)
|
||||
journal->j_flags |= JBD2_ACK_ERR;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
}
|
||||
|
||||
int jbd2_journal_blocks_per_page(struct inode *inode)
|
||||
|
|
|
|||
|
|
@ -124,36 +124,38 @@ alloc_transaction:
|
|||
|
||||
jbd_debug(3, "New handle %p going live.\n", handle);
|
||||
|
||||
repeat:
|
||||
|
||||
/*
|
||||
* We need to hold j_state_lock until t_updates has been incremented,
|
||||
* for proper journal barrier handling
|
||||
*/
|
||||
spin_lock(&journal->j_state_lock);
|
||||
repeat_locked:
|
||||
repeat:
|
||||
read_lock(&journal->j_state_lock);
|
||||
if (is_journal_aborted(journal) ||
|
||||
(journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) {
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
kfree(new_transaction);
|
||||
return -EROFS;
|
||||
}
|
||||
|
||||
/* Wait on the journal's transaction barrier if necessary */
|
||||
if (journal->j_barrier_count) {
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
wait_event(journal->j_wait_transaction_locked,
|
||||
journal->j_barrier_count == 0);
|
||||
goto repeat;
|
||||
}
|
||||
|
||||
if (!journal->j_running_transaction) {
|
||||
if (!new_transaction) {
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
if (!new_transaction)
|
||||
goto alloc_transaction;
|
||||
write_lock(&journal->j_state_lock);
|
||||
if (!journal->j_running_transaction) {
|
||||
jbd2_get_transaction(journal, new_transaction);
|
||||
new_transaction = NULL;
|
||||
}
|
||||
jbd2_get_transaction(journal, new_transaction);
|
||||
new_transaction = NULL;
|
||||
write_unlock(&journal->j_state_lock);
|
||||
goto repeat;
|
||||
}
|
||||
|
||||
transaction = journal->j_running_transaction;
|
||||
|
|
@ -167,7 +169,7 @@ repeat_locked:
|
|||
|
||||
prepare_to_wait(&journal->j_wait_transaction_locked,
|
||||
&wait, TASK_UNINTERRUPTIBLE);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
schedule();
|
||||
finish_wait(&journal->j_wait_transaction_locked, &wait);
|
||||
goto repeat;
|
||||
|
|
@ -194,7 +196,7 @@ repeat_locked:
|
|||
prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
|
||||
TASK_UNINTERRUPTIBLE);
|
||||
__jbd2_log_start_commit(journal, transaction->t_tid);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
schedule();
|
||||
finish_wait(&journal->j_wait_transaction_locked, &wait);
|
||||
goto repeat;
|
||||
|
|
@ -228,8 +230,12 @@ repeat_locked:
|
|||
if (__jbd2_log_space_left(journal) < jbd_space_needed(journal)) {
|
||||
jbd_debug(2, "Handle %p waiting for checkpoint...\n", handle);
|
||||
spin_unlock(&transaction->t_handle_lock);
|
||||
__jbd2_log_wait_for_space(journal);
|
||||
goto repeat_locked;
|
||||
read_unlock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
if (__jbd2_log_space_left(journal) < jbd_space_needed(journal))
|
||||
__jbd2_log_wait_for_space(journal);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
goto repeat;
|
||||
}
|
||||
|
||||
/* OK, account for the buffers that this operation expects to
|
||||
|
|
@ -250,7 +256,7 @@ repeat_locked:
|
|||
atomic_read(&transaction->t_outstanding_credits),
|
||||
__jbd2_log_space_left(journal));
|
||||
spin_unlock(&transaction->t_handle_lock);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
|
||||
lock_map_acquire(&handle->h_lockdep_map);
|
||||
kfree(new_transaction);
|
||||
|
|
@ -362,7 +368,7 @@ int jbd2_journal_extend(handle_t *handle, int nblocks)
|
|||
|
||||
result = 1;
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
read_lock(&journal->j_state_lock);
|
||||
|
||||
/* Don't extend a locked-down transaction! */
|
||||
if (handle->h_transaction->t_state != T_RUNNING) {
|
||||
|
|
@ -394,7 +400,7 @@ int jbd2_journal_extend(handle_t *handle, int nblocks)
|
|||
unlock:
|
||||
spin_unlock(&transaction->t_handle_lock);
|
||||
error_out:
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
out:
|
||||
return result;
|
||||
}
|
||||
|
|
@ -432,7 +438,7 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, int gfp_mask)
|
|||
J_ASSERT(atomic_read(&transaction->t_updates) > 0);
|
||||
J_ASSERT(journal_current_handle() == handle);
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
read_lock(&journal->j_state_lock);
|
||||
spin_lock(&transaction->t_handle_lock);
|
||||
atomic_sub(handle->h_buffer_credits,
|
||||
&transaction->t_outstanding_credits);
|
||||
|
|
@ -442,7 +448,7 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, int gfp_mask)
|
|||
|
||||
jbd_debug(2, "restarting handle %p\n", handle);
|
||||
__jbd2_log_start_commit(journal, transaction->t_tid);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
|
||||
lock_map_release(&handle->h_lockdep_map);
|
||||
handle->h_buffer_credits = nblocks;
|
||||
|
|
@ -472,7 +478,7 @@ void jbd2_journal_lock_updates(journal_t *journal)
|
|||
{
|
||||
DEFINE_WAIT(wait);
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
++journal->j_barrier_count;
|
||||
|
||||
/* Wait until there are no running updates */
|
||||
|
|
@ -490,12 +496,12 @@ void jbd2_journal_lock_updates(journal_t *journal)
|
|||
prepare_to_wait(&journal->j_wait_updates, &wait,
|
||||
TASK_UNINTERRUPTIBLE);
|
||||
spin_unlock(&transaction->t_handle_lock);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
schedule();
|
||||
finish_wait(&journal->j_wait_updates, &wait);
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
}
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
|
||||
/*
|
||||
* We have now established a barrier against other normal updates, but
|
||||
|
|
@ -519,9 +525,9 @@ void jbd2_journal_unlock_updates (journal_t *journal)
|
|||
J_ASSERT(journal->j_barrier_count != 0);
|
||||
|
||||
mutex_unlock(&journal->j_barrier);
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
--journal->j_barrier_count;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
wake_up(&journal->j_wait_transaction_locked);
|
||||
}
|
||||
|
||||
|
|
@ -1314,9 +1320,9 @@ int jbd2_journal_stop(handle_t *handle)
|
|||
|
||||
journal->j_last_sync_writer = pid;
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
read_lock(&journal->j_state_lock);
|
||||
commit_time = journal->j_average_commit_time;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
|
||||
trans_time = ktime_to_ns(ktime_sub(ktime_get(),
|
||||
transaction->t_start_time));
|
||||
|
|
@ -1748,7 +1754,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
|
|||
goto zap_buffer_unlocked;
|
||||
|
||||
/* OK, we have data buffer in journaled mode */
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
jbd_lock_bh_state(bh);
|
||||
spin_lock(&journal->j_list_lock);
|
||||
|
||||
|
|
@ -1801,7 +1807,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
|
|||
jbd2_journal_put_journal_head(jh);
|
||||
spin_unlock(&journal->j_list_lock);
|
||||
jbd_unlock_bh_state(bh);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
return ret;
|
||||
} else {
|
||||
/* There is no currently-running transaction. So the
|
||||
|
|
@ -1815,7 +1821,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
|
|||
jbd2_journal_put_journal_head(jh);
|
||||
spin_unlock(&journal->j_list_lock);
|
||||
jbd_unlock_bh_state(bh);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
return ret;
|
||||
} else {
|
||||
/* The orphan record's transaction has
|
||||
|
|
@ -1839,7 +1845,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
|
|||
jbd2_journal_put_journal_head(jh);
|
||||
spin_unlock(&journal->j_list_lock);
|
||||
jbd_unlock_bh_state(bh);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
return 0;
|
||||
} else {
|
||||
/* Good, the buffer belongs to the running transaction.
|
||||
|
|
@ -1858,7 +1864,7 @@ zap_buffer:
|
|||
zap_buffer_no_jh:
|
||||
spin_unlock(&journal->j_list_lock);
|
||||
jbd_unlock_bh_state(bh);
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
zap_buffer_unlocked:
|
||||
clear_buffer_dirty(bh);
|
||||
J_ASSERT_BH(bh, !buffer_jbddirty(bh));
|
||||
|
|
@ -2165,9 +2171,9 @@ int jbd2_journal_begin_ordered_truncate(journal_t *journal,
|
|||
/* Locks are here just to force reading of recent values, it is
|
||||
* enough that the transaction was not committing before we started
|
||||
* a transaction adding the inode to orphan list */
|
||||
spin_lock(&journal->j_state_lock);
|
||||
read_lock(&journal->j_state_lock);
|
||||
commit_trans = journal->j_committing_transaction;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
read_unlock(&journal->j_state_lock);
|
||||
spin_lock(&journal->j_list_lock);
|
||||
inode_trans = jinode->i_transaction;
|
||||
spin_unlock(&journal->j_list_lock);
|
||||
|
|
|
|||
|
|
@ -760,13 +760,13 @@ void ocfs2_set_journal_params(struct ocfs2_super *osb)
|
|||
if (osb->osb_commit_interval)
|
||||
commit_interval = osb->osb_commit_interval;
|
||||
|
||||
spin_lock(&journal->j_state_lock);
|
||||
write_lock(&journal->j_state_lock);
|
||||
journal->j_commit_interval = commit_interval;
|
||||
if (osb->s_mount_opt & OCFS2_MOUNT_BARRIER)
|
||||
journal->j_flags |= JBD2_BARRIER;
|
||||
else
|
||||
journal->j_flags &= ~JBD2_BARRIER;
|
||||
spin_unlock(&journal->j_state_lock);
|
||||
write_unlock(&journal->j_state_lock);
|
||||
}
|
||||
|
||||
int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
|
||||
|
|
|
|||
|
|
@ -764,7 +764,7 @@ struct journal_s
|
|||
/*
|
||||
* Protect the various scalars in the journal
|
||||
*/
|
||||
spinlock_t j_state_lock;
|
||||
rwlock_t j_state_lock;
|
||||
|
||||
/*
|
||||
* Number of processes waiting to create a barrier lock [j_state_lock]
|
||||
|
|
|
|||
Loading…
Reference in New Issue