aboutsummaryrefslogtreecommitdiff
path: root/fs/jbd/journal.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/jbd/journal.c')
-rw-r--r--fs/jbd/journal.c407
1 files changed, 245 insertions, 162 deletions
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index da1b5e4ffce..06fe11e0abf 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -38,6 +38,9 @@
#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>
@@ -87,6 +90,24 @@ 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);
+#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
*/
@@ -126,6 +147,8 @@ static int kjournald(void *arg)
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);
@@ -163,7 +186,7 @@ loop:
*/
jbd_debug(1, "Now suspending kjournald\n");
spin_unlock(&journal->j_state_lock);
- refrigerator();
+ try_to_freeze();
spin_lock(&journal->j_state_lock);
} else {
/*
@@ -305,8 +328,6 @@ int journal_write_metadata_buffer(transaction_t *transaction,
new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
/* keep subsequent assertions sane */
- new_bh->b_state = 0;
- init_buffer(new_bh, NULL, NULL);
atomic_set(&new_bh->b_count, 1);
new_jh = journal_add_journal_head(new_bh); /* This sleeps */
@@ -325,7 +346,7 @@ repeat:
new_offset = offset_in_page(jh2bh(jh_in)->b_data);
}
- mapped_data = kmap_atomic(new_page, KM_USER0);
+ mapped_data = kmap_atomic(new_page);
/*
* Check for escaping
*/
@@ -334,7 +355,7 @@ repeat:
need_copy_out = 1;
do_escape = 1;
}
- kunmap_atomic(mapped_data, KM_USER0);
+ kunmap_atomic(mapped_data);
/*
* Do we need to do a data copy?
@@ -351,9 +372,9 @@ repeat:
}
jh_in->b_frozen_data = tmp;
- mapped_data = kmap_atomic(new_page, KM_USER0);
+ mapped_data = kmap_atomic(new_page);
memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size);
- kunmap_atomic(mapped_data, KM_USER0);
+ kunmap_atomic(mapped_data);
new_page = virt_to_page(tmp);
new_offset = offset_in_page(tmp);
@@ -365,9 +386,9 @@ repeat:
* copying, we can finally do so.
*/
if (do_escape) {
- mapped_data = kmap_atomic(new_page, KM_USER0);
+ mapped_data = kmap_atomic(new_page);
*((unsigned int *)(mapped_data + new_offset)) = 0;
- kunmap_atomic(mapped_data, KM_USER0);
+ kunmap_atomic(mapped_data);
}
set_bh_page(new_bh, new_page, new_offset);
@@ -437,9 +458,13 @@ int __log_space_left(journal_t *journal)
int __log_start_commit(journal_t *journal, tid_t target)
{
/*
- * Are we already doing a recent enough commit?
+ * 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 (!tid_geq(journal->j_commit_request, target)) {
+ 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.
@@ -451,7 +476,14 @@ int __log_start_commit(journal_t *journal, tid_t target)
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;
}
@@ -519,8 +551,8 @@ int journal_start_commit(journal_t *journal, tid_t *ptid)
ret = 1;
} else if (journal->j_committing_transaction) {
/*
- * If ext3_write_super() recently started a commit, then we
- * have to wait for completion of that transaction
+ * If commit has been started, then we have to wait for
+ * completion of that transaction.
*/
if (ptid)
*ptid = journal->j_committing_transaction->t_tid;
@@ -541,13 +573,25 @@ int log_wait_commit(journal_t *journal, tid_t tid)
#ifdef CONFIG_JBD_DEBUG
spin_lock(&journal->j_state_lock);
if (!tid_geq(journal->j_commit_request, tid)) {
- printk(KERN_EMERG
+ 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);
@@ -557,12 +601,11 @@ int log_wait_commit(journal_t *journal, tid_t tid)
!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))) {
- printk(KERN_EMERG "journal commit I/O error\n");
+ if (unlikely(is_journal_aborted(journal)))
err = -EIO;
- }
return err;
}
@@ -708,7 +751,6 @@ static journal_t * journal_init_common (void)
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_barrier);
mutex_init(&journal->j_checkpoint_mutex);
spin_lock_init(&journal->j_revoke_lock);
spin_lock_init(&journal->j_list_lock);
@@ -770,7 +812,7 @@ journal_t * journal_init_dev(struct block_device *bdev,
journal->j_wbufsize = n;
journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
if (!journal->j_wbuf) {
- printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
+ printk(KERN_ERR "%s: Can't allocate bhs for commit thread\n",
__func__);
goto out_err;
}
@@ -831,7 +873,7 @@ journal_t * journal_init_inode (struct inode *inode)
journal->j_wbufsize = n;
journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
if (!journal->j_wbuf) {
- printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
+ printk(KERN_ERR "%s: Can't allocate bhs for commit thread\n",
__func__);
goto out_err;
}
@@ -839,7 +881,7 @@ journal_t * journal_init_inode (struct inode *inode)
err = journal_bmap(journal, 0, &blocknr);
/* If that failed, give up */
if (err) {
- printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
+ printk(KERN_ERR "%s: Cannot locate journal superblock\n",
__func__);
goto out_err;
}
@@ -907,8 +949,33 @@ static int journal_reset(journal_t *journal)
journal->j_max_transaction_buffers = journal->j_maxlen / 4;
- /* Add the dynamic fields and write it to disk. */
- journal_update_superblock(journal, 1);
+ /*
+ * 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);
}
@@ -985,35 +1052,15 @@ int journal_create(journal_t *journal)
return journal_reset(journal);
}
-/**
- * void journal_update_superblock() - Update journal sb on disk.
- * @journal: The journal to update.
- * @wait: Set to '0' if you don't want to wait for IO completion.
- *
- * Update a journal's dynamic superblock fields and write it to disk,
- * optionally waiting for the IO to complete.
- */
-void journal_update_superblock(journal_t *journal, int wait)
+static void journal_write_superblock(journal_t *journal, int write_op)
{
- journal_superblock_t *sb = journal->j_superblock;
struct buffer_head *bh = journal->j_sb_buffer;
+ int ret;
- /*
- * As a special case, if the on-disk copy is already marked as needing
- * no recovery (s_start == 0) and there are no outstanding transactions
- * in the filesystem, 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 && journal->j_tail_sequence ==
- journal->j_transaction_sequence) {
- 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);
- goto out;
- }
-
+ 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];
/*
@@ -1031,41 +1078,105 @@ void journal_update_superblock(journal_t *journal, int wait)
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);
- jbd_debug(1,"JBD: updating superblock (start %u, seq %d, errno %d)\n",
- journal->j_tail, journal->j_tail_sequence, journal->j_errno);
+ /* 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(journal->j_tail);
- sb->s_errno = cpu_to_be32(journal->j_errno);
+ sb->s_start = cpu_to_be32(0);
spin_unlock(&journal->j_state_lock);
- BUFFER_TRACE(bh, "marking dirty");
- mark_buffer_dirty(bh);
- if (wait) {
- sync_dirty_buffer(bh);
- if (buffer_write_io_error(bh)) {
- char b[BDEVNAME_SIZE];
- printk(KERN_ERR "JBD: I/O error detected "
- "when updating journal superblock for %s.\n",
- journal_dev_name(journal, b));
- clear_buffer_write_io_error(bh);
- set_buffer_uptodate(bh);
- }
- } else
- write_dirty_buffer(bh, WRITE);
+ journal_write_superblock(journal, WRITE_FUA);
-out:
- /* If we have just flushed the log (by marking s_start==0), then
- * 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);
+ /* 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);
- if (sb->s_start)
- journal->j_flags &= ~JFS_FLUSHED;
- else
- journal->j_flags |= JFS_FLUSHED;
+ 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);
}
/*
@@ -1121,6 +1232,14 @@ static int journal_get_superblock(journal_t *journal)
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:
@@ -1228,6 +1347,8 @@ int journal_destroy(journal_t *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) {
@@ -1243,16 +1364,14 @@ int journal_destroy(journal_t *journal)
if (journal->j_sb_buffer) {
if (!is_journal_aborted(journal)) {
- /* We can now mark the journal as empty. */
- journal->j_tail = 0;
journal->j_tail_sequence =
++journal->j_transaction_sequence;
- journal_update_superblock(journal, 1);
- } else {
+ mark_journal_empty(journal);
+ } else
err = -EIO;
- }
brelse(journal->j_sb_buffer);
}
+ mutex_unlock(&journal->j_checkpoint_mutex);
if (journal->j_inode)
iput(journal->j_inode);
@@ -1432,7 +1551,6 @@ int journal_flush(journal_t *journal)
{
int err = 0;
transaction_t *transaction = NULL;
- unsigned int old_tail;
spin_lock(&journal->j_state_lock);
@@ -1467,6 +1585,7 @@ int journal_flush(journal_t *journal)
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.
@@ -1474,14 +1593,9 @@ int 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. */
+ mark_journal_empty(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
spin_lock(&journal->j_state_lock);
- old_tail = journal->j_tail;
- journal->j_tail = 0;
- spin_unlock(&journal->j_state_lock);
- journal_update_superblock(journal, 1);
- spin_lock(&journal->j_state_lock);
- journal->j_tail = old_tail;
-
J_ASSERT(!journal->j_running_transaction);
J_ASSERT(!journal->j_committing_transaction);
J_ASSERT(!journal->j_checkpoint_transactions);
@@ -1521,8 +1635,12 @@ int journal_wipe(journal_t *journal, int write)
write ? "Clearing" : "Ignoring");
err = journal_skip_recovery(journal);
- if (write)
- journal_update_superblock(journal, 1);
+ 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;
@@ -1590,7 +1708,7 @@ static void __journal_abort_soft (journal_t *journal, int errno)
__journal_abort_hard(journal);
if (errno)
- journal_update_superblock(journal, 1);
+ journal_update_sb_errno(journal);
}
/**
@@ -1752,7 +1870,7 @@ static struct journal_head *journal_alloc_journal_head(void)
#ifdef CONFIG_JBD_DEBUG
atomic_inc(&nr_journal_heads);
#endif
- ret = kmem_cache_alloc(journal_head_cache, GFP_NOFS);
+ 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",
@@ -1760,7 +1878,7 @@ static struct journal_head *journal_alloc_journal_head(void)
while (ret == NULL) {
yield();
- ret = kmem_cache_alloc(journal_head_cache, GFP_NOFS);
+ ret = kmem_cache_zalloc(journal_head_cache, GFP_NOFS);
}
}
return ret;
@@ -1789,10 +1907,9 @@ static void journal_free_journal_head(struct journal_head *jh)
* When a buffer has its BH_JBD bit set it is immune from being released by
* core kernel code, mainly via ->b_count.
*
- * A journal_head may be detached from its buffer_head when the journal_head's
- * b_transaction, b_cp_transaction and b_next_transaction pointers are NULL.
- * Various places in JBD call journal_remove_journal_head() to indicate that the
- * journal_head can be dropped if needed.
+ * 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
@@ -1805,17 +1922,16 @@ static void journal_free_journal_head(struct journal_head *jh)
* (Attach a journal_head if needed. Increments b_jcount)
* struct journal_head *jh = journal_add_journal_head(bh);
* ...
- * jh->b_transaction = xxx;
- * journal_put_journal_head(jh);
- *
- * Now, the journal_head's b_jcount is zero, but it is safe from being released
- * because it has a non-zero b_transaction.
+ * (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.
*
- * Doesn't need the journal lock.
* May sleep.
*/
struct journal_head *journal_add_journal_head(struct buffer_head *bh)
@@ -1824,10 +1940,8 @@ struct journal_head *journal_add_journal_head(struct buffer_head *bh)
struct journal_head *new_jh = NULL;
repeat:
- if (!buffer_jbd(bh)) {
+ if (!buffer_jbd(bh))
new_jh = journal_alloc_journal_head();
- memset(new_jh, 0, sizeof(*new_jh));
- }
jbd_lock_bh_journal_head(bh);
if (buffer_jbd(bh)) {
@@ -1879,61 +1993,29 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
struct journal_head *jh = bh2jh(bh);
J_ASSERT_JH(jh, jh->b_jcount >= 0);
-
- get_bh(bh);
- if (jh->b_jcount == 0) {
- if (jh->b_transaction == NULL &&
- jh->b_next_transaction == NULL &&
- 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);
- }
- 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);
- __brelse(bh);
- journal_free_journal_head(jh);
- } else {
- BUFFER_TRACE(bh, "journal_head was locked");
- }
+ 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);
}
+ 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);
}
/*
- * journal_remove_journal_head(): if the buffer isn't attached to a transaction
- * and has a zero b_jcount then remove and release its journal_head. If we did
- * see that the buffer is not used by any transaction we also "logically"
- * decrement ->b_count.
- *
- * We in fact take an additional increment on ->b_count as a convenience,
- * because the caller usually wants to do additional things with the bh
- * after calling here.
- * The caller of journal_remove_journal_head() *must* run __brelse(bh) at some
- * time. Once the caller has run __brelse(), the buffer is eligible for
- * reaping by try_to_free_buffers().
- */
-void journal_remove_journal_head(struct buffer_head *bh)
-{
- jbd_lock_bh_journal_head(bh);
- __journal_remove_journal_head(bh);
- jbd_unlock_bh_journal_head(bh);
-}
-
-/*
- * Drop a reference on the passed journal_head. If it fell to zero then try to
+ * 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)
@@ -1943,11 +2025,12 @@ void journal_put_journal_head(struct journal_head *jh)
jbd_lock_bh_journal_head(bh);
J_ASSERT_JH(jh, jh->b_jcount > 0);
--jh->b_jcount;
- if (!jh->b_jcount && !jh->b_transaction) {
+ if (!jh->b_jcount) {
__journal_remove_journal_head(bh);
+ jbd_unlock_bh_journal_head(bh);
__brelse(bh);
- }
- jbd_unlock_bh_journal_head(bh);
+ } else
+ jbd_unlock_bh_journal_head(bh);
}
/*
@@ -2051,7 +2134,7 @@ static void __exit journal_exit(void)
#ifdef CONFIG_JBD_DEBUG
int n = atomic_read(&nr_journal_heads);
if (n)
- printk(KERN_EMERG "JBD: leaked %d journal_heads!\n", n);
+ printk(KERN_ERR "JBD: leaked %d journal_heads!\n", n);
#endif
jbd_remove_debugfs_entry();
journal_destroy_caches();