#include <linux/jbd2.h>
#include <linux/errno.h>
#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <trace/events/jbd2.h>
/*
* Unlink a buffer from a transaction checkpoint list.
int ret = 0;
struct buffer_head *bh = jh2bh(jh);
- if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh)) {
+ if (jh->b_jlist == BJ_None && !buffer_locked(bh) &&
+ !buffer_dirty(bh) && !buffer_write_io_error(bh)) {
JBUFFER_TRACE(jh, "remove from checkpoint list");
ret = __jbd2_journal_remove_checkpoint(jh) + 1;
jbd_unlock_bh_state(bh);
*/
void __jbd2_log_wait_for_space(journal_t *journal)
{
- int nblocks;
+ int nblocks, space_left;
assert_spin_locked(&journal->j_state_lock);
nblocks = jbd_space_needed(journal);
/*
* Test again, another process may have checkpointed while we
- * were waiting for the checkpoint lock
+ * 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.
*/
spin_lock(&journal->j_state_lock);
+ spin_lock(&journal->j_list_lock);
nblocks = jbd_space_needed(journal);
- if (__jbd2_log_space_left(journal) < nblocks) {
+ 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);
spin_unlock(&journal->j_state_lock);
- jbd2_log_do_checkpoint(journal);
+ 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);
+ }
spin_lock(&journal->j_state_lock);
+ } else {
+ spin_unlock(&journal->j_list_lock);
}
mutex_unlock(&journal->j_checkpoint_mutex);
}
* buffers. Note that we take the buffers in the opposite ordering
* from the one in which they were submitted for IO.
*
+ * Return 0 on success, and return <0 if some buffers have failed
+ * to be written out.
+ *
* Called with j_list_lock held.
*/
-static void __wait_cp_io(journal_t *journal, transaction_t *transaction)
+static int __wait_cp_io(journal_t *journal, transaction_t *transaction)
{
struct journal_head *jh;
struct buffer_head *bh;
tid_t this_tid;
int released = 0;
+ int ret = 0;
this_tid = transaction->t_tid;
restart:
/* Did somebody clean up the transaction in the meanwhile? */
if (journal->j_checkpoint_transactions != transaction ||
transaction->t_tid != this_tid)
- return;
+ return ret;
while (!released && transaction->t_checkpoint_io_list) {
jh = transaction->t_checkpoint_io_list;
bh = jh2bh(jh);
spin_lock(&journal->j_list_lock);
goto restart;
}
+ if (unlikely(buffer_write_io_error(bh)))
+ ret = -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
jbd2_journal_remove_journal_head(bh);
__brelse(bh);
}
-}
-#define NR_BATCH 64
+ return ret;
+}
static void
-__flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
+__flush_batch(journal_t *journal, int *batch_count)
{
int i;
- ll_rw_block(SWRITE, *batch_count, bhs);
+ ll_rw_block(SWRITE, *batch_count, journal->j_chkpt_bhs);
for (i = 0; i < *batch_count; i++) {
- struct buffer_head *bh = bhs[i];
+ struct buffer_head *bh = journal->j_chkpt_bhs[i];
clear_buffer_jwrite(bh);
BUFFER_TRACE(bh, "brelse");
__brelse(bh);
* 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.
+ * 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
* Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
*/
static int __process_buffer(journal_t *journal, struct journal_head *jh,
- struct buffer_head **bhs, int *batch_count)
+ int *batch_count, transaction_t *transaction)
{
struct buffer_head *bh = jh2bh(jh);
int ret = 0;
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);
jbd_unlock_bh_state(bh);
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;
J_ASSERT_JH(jh, !buffer_jbddirty(bh));
BUFFER_TRACE(bh, "remove from checkpoint");
__jbd2_journal_remove_checkpoint(jh);
jbd_unlock_bh_state(bh);
jbd2_journal_remove_journal_head(bh);
__brelse(bh);
- ret = 1;
} else {
/*
* Important: we are about to write the buffer, and
get_bh(bh);
J_ASSERT_BH(bh, !buffer_jwrite(bh));
set_buffer_jwrite(bh);
- bhs[*batch_count] = bh;
+ journal->j_chkpt_bhs[*batch_count] = bh;
__buffer_relink_io(jh);
jbd_unlock_bh_state(bh);
+ transaction->t_chp_stats.cs_written++;
(*batch_count)++;
- if (*batch_count == NR_BATCH) {
+ if (*batch_count == JBD2_NR_BATCH) {
spin_unlock(&journal->j_list_lock);
- __flush_batch(journal, bhs, batch_count);
+ __flush_batch(journal, batch_count);
ret = 1;
}
}
* 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)
{
* 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 (journal->j_checkpoint_transactions == transaction &&
transaction->t_tid == this_tid) {
int batch_count = 0;
- struct buffer_head *bhs[NR_BATCH];
struct journal_head *jh;
- int retry = 0;
+ int retry = 0, err;
while (!retry && transaction->t_checkpoint_list) {
struct buffer_head *bh;
retry = 1;
break;
}
- retry = __process_buffer(journal, jh, bhs,&batch_count);
- if (!retry && lock_need_resched(&journal->j_list_lock)){
+ retry = __process_buffer(journal, jh, &batch_count,
+ transaction);
+ if (retry < 0 && !result)
+ result = retry;
+ if (!retry && (need_resched() ||
+ spin_needbreak(&journal->j_list_lock))) {
spin_unlock(&journal->j_list_lock);
retry = 1;
break;
spin_unlock(&journal->j_list_lock);
retry = 1;
}
- __flush_batch(journal, bhs, &batch_count);
+ __flush_batch(journal, &batch_count);
}
if (retry) {
* Now we have cleaned up the first transaction's checkpoint
* list. Let's clean up the second one
*/
- __wait_cp_io(journal, transaction);
+ err = __wait_cp_io(journal, transaction);
+ if (!result)
+ result = err;
}
out:
spin_unlock(&journal->j_list_lock);
- result = jbd2_cleanup_journal_tail(journal);
if (result < 0)
- return result;
- return 0;
+ jbd2_journal_abort(journal, result);
+ else
+ result = jbd2_cleanup_journal_tail(journal);
+
+ return (result < 0) ? result : 0;
}
/*
* This is the only part of the journaling code which really needs to be
* aware of transaction aborts. Checkpointing involves writing to the
* main filesystem area rather than to the journal, so it can proceed
- * even in abort state, but we must not update the journal superblock if
- * we have an abort error outstanding.
+ * even in abort state, but we must not update the super block if
+ * checkpointing may have failed. Otherwise, we would lose some metadata
+ * buffers which should be written-back to the filesystem.
*/
int jbd2_cleanup_journal_tail(journal_t *journal)
tid_t first_tid;
unsigned long blocknr, freed;
+ if (is_journal_aborted(journal))
+ return 1;
+
/* OK, work out the oldest transaction remaining in the log, and
* the log block it starts at.
*
if (blocknr < journal->j_tail)
freed = freed + journal->j_last - journal->j_first;
+ trace_jbd2_cleanup_journal_tail(journal, first_tid, blocknr, freed);
jbd_debug(1,
"Cleaning journal tail from %d to %d (offset %lu), "
"freeing %lu\n",
journal->j_tail_sequence = first_tid;
journal->j_tail = blocknr;
spin_unlock(&journal->j_state_lock);
+
+ /*
+ * If there is an external journal, we need to make sure that
+ * any data blocks that were recently written out --- perhaps
+ * by jbd2_log_do_checkpoint() --- are flushed out before we
+ * drop the transactions from the external journal. It's
+ * unlikely this will be necessary, especially with a
+ * appropriately sized journal, but we need this to guarantee
+ * correctness. Fortunately jbd2_cleanup_journal_tail()
+ * doesn't get called all that often.
+ */
+ if ((journal->j_fs_dev != journal->j_dev) &&
+ (journal->j_flags & JBD2_BARRIER))
+ blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL,
+ BLKDEV_IFL_WAIT);
if (!(journal->j_flags & JBD2_ABORT))
jbd2_journal_update_superblock(journal, 1);
return 0;
int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
{
+ struct transaction_chp_stats_s *stats;
transaction_t *transaction;
journal_t *journal;
int ret = 0;
/*
* There is one special case to worry about: if we have just pulled the
- * buffer off a committing transaction's forget list, then even if the
- * checkpoint list is empty, the transaction obviously cannot be
- * dropped!
+ * buffer off a running or committing transaction's checkpoing list,
+ * then even if the checkpoint list is empty, the transaction obviously
+ * cannot be dropped!
*
- * The locking here around j_committing_transaction is a bit sleazy.
+ * The locking here around t_state is a bit sleazy.
* See the comment at the end of jbd2_journal_commit_transaction().
*/
- if (transaction == journal->j_committing_transaction) {
- JBUFFER_TRACE(jh, "belongs to committing transaction");
+ if (transaction->t_state != T_FINISHED) {
+ JBUFFER_TRACE(jh, "belongs to running/committing transaction");
goto out;
}
/* OK, that was the last buffer for the transaction: we can now
safely remove this transaction from the log */
+ stats = &transaction->t_chp_stats;
+ if (stats->cs_chp_time)
+ stats->cs_chp_time = jbd2_time_diff(stats->cs_chp_time,
+ jiffies);
+ trace_jbd2_checkpoint_stats(journal->j_fs_dev->bd_dev,
+ transaction->t_tid, stats);
__jbd2_journal_drop_transaction(journal, transaction);
+ kfree(transaction);
/* Just in case anybody was waiting for more transactions to be
checkpointed... */
J_ASSERT(transaction->t_state == T_FINISHED);
J_ASSERT(transaction->t_buffers == NULL);
- J_ASSERT(transaction->t_sync_datalist == NULL);
J_ASSERT(transaction->t_forget == NULL);
J_ASSERT(transaction->t_iobuf_list == NULL);
J_ASSERT(transaction->t_shadow_list == NULL);
J_ASSERT(journal->j_running_transaction != transaction);
jbd_debug(1, "Dropping transaction %d, all done\n", transaction->t_tid);
- kfree(transaction);
}