#include <linux/vmalloc.h>
#include <linux/backing-dev.h>
#include <linux/bitops.h>
+#include <linux/ratelimit.h>
#define CREATE_TRACE_POINTS
#include <trace/events/jbd2.h>
#include <asm/uaccess.h>
#include <asm/page.h>
-#include <asm/system.h>
EXPORT_SYMBOL(jbd2_journal_extend);
EXPORT_SYMBOL(jbd2_journal_stop);
EXPORT_SYMBOL(jbd2_journal_init_dev);
EXPORT_SYMBOL(jbd2_journal_init_inode);
-EXPORT_SYMBOL(jbd2_journal_update_format);
EXPORT_SYMBOL(jbd2_journal_check_used_features);
EXPORT_SYMBOL(jbd2_journal_check_available_features);
EXPORT_SYMBOL(jbd2_journal_set_features);
EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
+EXPORT_SYMBOL(jbd2_inode_cache);
-static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
static void __journal_abort_soft (journal_t *journal, int errno);
static int jbd2_journal_create_slab(size_t slab_size);
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);
*/
jbd_debug(1, "Now suspending kjournald2\n");
write_unlock(&journal->j_state_lock);
- refrigerator();
+ try_to_freeze();
write_lock(&journal->j_state_lock);
} else {
/*
new_offset = offset_in_page(jh2bh(jh_in)->b_data);
}
- mapped_data = kmap_atomic(new_page, KM_USER0);
+ mapped_data = kmap_atomic(new_page);
/*
* Fire data frozen trigger if data already wasn't frozen. Do this
* before checking for escaping, as the trigger may modify the magic
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?
}
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);
* 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);
}
/*
- * Called under j_state_lock. Returns true if a transaction commit was started.
+ * Called with j_state_lock locked for writing.
+ * Returns true if a transaction commit was started.
*/
int __jbd2_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_running_transaction &&
+ journal->j_running_transaction->t_tid == target) {
/*
- * We want a new commit: OK, mark the request and wakup the
+ * We want a new commit: OK, mark the request and wakeup the
* commit thread. We do _not_ do the commit ourselves.
*/
journal->j_commit_request = target;
- jbd_debug(1, "JBD: requesting commit %d/%d\n",
+ jbd_debug(1, "JBD2: requesting commit %d/%d\n",
journal->j_commit_request,
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, "JBD2: 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;
}
{
transaction_t *transaction = NULL;
tid_t tid;
+ int need_to_start = 0;
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);
+ if (!tid_geq(journal->j_commit_request, transaction->t_tid))
+ need_to_start = 1;
} else if (journal->j_committing_transaction)
transaction = journal->j_committing_transaction;
tid = transaction->t_tid;
read_unlock(&journal->j_state_lock);
+ if (need_to_start)
+ jbd2_log_start_commit(journal, tid);
jbd2_log_wait_commit(journal, tid);
return 1;
}
}
/*
+ * Return 1 if a given transaction has not yet sent barrier request
+ * connected with a transaction commit. If 0 is returned, transaction
+ * may or may not have sent the barrier. Used to avoid sending barrier
+ * twice in common cases.
+ */
+int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid)
+{
+ int ret = 0;
+ transaction_t *commit_trans;
+
+ if (!(journal->j_flags & JBD2_BARRIER))
+ return 0;
+ read_lock(&journal->j_state_lock);
+ /* Transaction already committed? */
+ if (tid_geq(journal->j_commit_sequence, tid))
+ goto out;
+ commit_trans = journal->j_committing_transaction;
+ if (!commit_trans || commit_trans->t_tid != tid) {
+ ret = 1;
+ goto out;
+ }
+ /*
+ * Transaction is being committed and we already proceeded to
+ * submitting a flush to fs partition?
+ */
+ if (journal->j_fs_dev != journal->j_dev) {
+ if (!commit_trans->t_need_data_flush ||
+ commit_trans->t_state >= T_COMMIT_DFLUSH)
+ goto out;
+ } else {
+ if (commit_trans->t_state >= T_COMMIT_JFLUSH)
+ goto out;
+ }
+ ret = 1;
+out:
+ read_unlock(&journal->j_state_lock);
+ return ret;
+}
+EXPORT_SYMBOL(jbd2_trans_will_send_data_barrier);
+
+/*
* Wait for a specified commit to complete.
* The caller may not hold the journal lock.
*/
}
#endif
while (tid_gt(tid, journal->j_commit_sequence)) {
- jbd_debug(1, "JBD: want %d, j_commit_sequence=%d\n",
+ jbd_debug(1, "JBD2: want %d, j_commit_sequence=%d\n",
tid, journal->j_commit_sequence);
wake_up(&journal->j_wait_commit);
read_unlock(&journal->j_state_lock);
return jbd2_journal_add_journal_head(bh);
}
+/*
+ * Return tid of the oldest transaction in the journal and block in the journal
+ * where the transaction starts.
+ *
+ * If the journal is now empty, return which will be the next transaction ID
+ * we will write and where will that transaction start.
+ *
+ * The return value is 0 if journal tail cannot be pushed any further, 1 if
+ * it can.
+ */
+int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid,
+ unsigned long *block)
+{
+ transaction_t *transaction;
+ int ret;
+
+ read_lock(&journal->j_state_lock);
+ spin_lock(&journal->j_list_lock);
+ transaction = journal->j_checkpoint_transactions;
+ if (transaction) {
+ *tid = transaction->t_tid;
+ *block = transaction->t_log_start;
+ } else if ((transaction = journal->j_committing_transaction) != NULL) {
+ *tid = transaction->t_tid;
+ *block = transaction->t_log_start;
+ } else if ((transaction = journal->j_running_transaction) != NULL) {
+ *tid = transaction->t_tid;
+ *block = journal->j_head;
+ } else {
+ *tid = journal->j_transaction_sequence;
+ *block = journal->j_head;
+ }
+ ret = tid_gt(*tid, journal->j_tail_sequence);
+ spin_unlock(&journal->j_list_lock);
+ read_unlock(&journal->j_state_lock);
+
+ return ret;
+}
+
+/*
+ * Update information in journal structure and in on disk journal superblock
+ * about log tail. This function does not check whether information passed in
+ * really pushes log tail further. It's responsibility of the caller to make
+ * sure provided log tail information is valid (e.g. by holding
+ * j_checkpoint_mutex all the time between computing log tail and calling this
+ * function as is the case with jbd2_cleanup_journal_tail()).
+ *
+ * Requires j_checkpoint_mutex
+ */
+void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
+{
+ unsigned long freed;
+
+ BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
+
+ /*
+ * We cannot afford for write to remain in drive's caches since as
+ * soon as we update j_tail, next transaction can start reusing journal
+ * space and if we lose sb update during power failure we'd replay
+ * old transaction with possibly newly overwritten data.
+ */
+ jbd2_journal_update_sb_log_tail(journal, tid, block, WRITE_FUA);
+ write_lock(&journal->j_state_lock);
+ freed = block - journal->j_tail;
+ if (block < journal->j_tail)
+ freed += journal->j_last - journal->j_first;
+
+ trace_jbd2_update_log_tail(journal, tid, block, freed);
+ jbd_debug(1,
+ "Cleaning journal tail from %d to %d (offset %lu), "
+ "freeing %lu\n",
+ journal->j_tail_sequence, tid, block, freed);
+
+ journal->j_free += freed;
+ journal->j_tail_sequence = tid;
+ journal->j_tail = block;
+ write_unlock(&journal->j_state_lock);
+}
+
+/*
+ * This is a variaon of __jbd2_update_log_tail which checks for validity of
+ * provided log tail and locks j_checkpoint_mutex. So it is safe against races
+ * with other threads updating log tail.
+ */
+void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
+{
+ mutex_lock(&journal->j_checkpoint_mutex);
+ if (tid_gt(tid, journal->j_tail_sequence))
+ __jbd2_update_log_tail(journal, tid, block);
+ mutex_unlock(&journal->j_checkpoint_mutex);
+}
+
struct jbd2_stats_proc_session {
journal_t *journal;
struct transaction_stats_s *stats;
journal = kzalloc(sizeof(*journal), GFP_KERNEL);
if (!journal)
- goto fail;
+ return NULL;
init_waitqueue_head(&journal->j_wait_transaction_locked);
init_waitqueue_head(&journal->j_wait_logspace);
err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
if (err) {
kfree(journal);
- goto fail;
+ return NULL;
}
spin_lock_init(&journal->j_history_lock);
return journal;
-fail:
- return NULL;
}
/* jbd2_journal_init_dev and jbd2_journal_init_inode:
/* journal descriptor can store up to n blocks -bzzz */
journal->j_blocksize = blocksize;
- jbd2_stats_proc_init(journal);
- n = journal->j_blocksize / sizeof(journal_block_tag_t);
- 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",
- __func__);
- goto out_err;
- }
journal->j_dev = bdev;
journal->j_fs_dev = fs_dev;
journal->j_blk_offset = start;
p = journal->j_devname;
while ((p = strchr(p, '/')))
*p = '!';
+ jbd2_stats_proc_init(journal);
+ n = journal->j_blocksize / sizeof(journal_block_tag_t);
+ journal->j_wbufsize = n;
+ journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
+ if (!journal->j_wbuf) {
+ printk(KERN_ERR "%s: Can't allocate bhs for commit thread\n",
+ __func__);
+ goto out_err;
+ }
bh = __getblk(journal->j_dev, start, journal->j_blocksize);
if (!bh) {
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;
}
err = jbd2_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;
}
first = be32_to_cpu(sb->s_first);
last = be32_to_cpu(sb->s_maxlen);
if (first + JBD2_MIN_JOURNAL_BLOCKS > last + 1) {
- printk(KERN_ERR "JBD: Journal too short (blocks %llu-%llu).\n",
+ printk(KERN_ERR "JBD2: Journal too short (blocks %llu-%llu).\n",
first, last);
journal_fail_superblock(journal);
return -EINVAL;
journal->j_max_transaction_buffers = journal->j_maxlen / 4;
- /* Add the dynamic fields and write it to disk. */
- jbd2_journal_update_superblock(journal, 1);
- return jbd2_journal_start_thread(journal);
-}
-
-/**
- * void jbd2_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 jbd2_journal_update_superblock(journal_t *journal, int wait)
-{
- journal_superblock_t *sb = journal->j_superblock;
- struct buffer_head *bh = journal->j_sb_buffer;
-
/*
* 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 JBD2_FLUSHED. This avoids
+ * no recovery (s_start == 0), then we can safely defer the superblock
+ * update until the next commit by setting JBD2_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 "
+ if (sb->s_start == 0) {
+ jbd_debug(1, "JBD2: Skipping superblock update on recovered sb "
"(start %ld, seq %d, errno %d)\n",
journal->j_tail, journal->j_tail_sequence,
journal->j_errno);
- goto out;
+ journal->j_flags |= JBD2_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.
+ */
+ jbd2_journal_update_sb_log_tail(journal,
+ journal->j_tail_sequence,
+ journal->j_tail,
+ WRITE_FUA);
+ mutex_unlock(&journal->j_checkpoint_mutex);
}
+ return jbd2_journal_start_thread(journal);
+}
+
+static void jbd2_write_superblock(journal_t *journal, int write_op)
+{
+ struct buffer_head *bh = journal->j_sb_buffer;
+ int ret;
+ trace_jbd2_write_superblock(journal, write_op);
+ if (!(journal->j_flags & JBD2_BARRIER))
+ write_op &= ~(REQ_FUA | REQ_FLUSH);
+ lock_buffer(bh);
if (buffer_write_io_error(bh)) {
/*
* Oh, dear. A previous attempt to write the journal
clear_buffer_write_io_error(bh);
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) {
+ printk(KERN_ERR "JBD2: Error %d detected when updating "
+ "journal superblock for %s.\n", ret,
+ journal->j_devname);
+ }
+}
+
+/**
+ * jbd2_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 jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
+ unsigned long tail_block, int write_op)
+{
+ journal_superblock_t *sb = journal->j_superblock;
+
+ BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
+ jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n",
+ tail_block, tail_tid);
+
+ sb->s_sequence = cpu_to_be32(tail_tid);
+ sb->s_start = cpu_to_be32(tail_block);
+
+ jbd2_write_superblock(journal, write_op);
+
+ /* Log is no longer empty */
+ write_lock(&journal->j_state_lock);
+ WARN_ON(!sb->s_sequence);
+ journal->j_flags &= ~JBD2_FLUSHED;
+ write_unlock(&journal->j_state_lock);
+}
+
+/**
+ * jbd2_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 jbd2_mark_journal_empty(journal_t *journal)
+{
+ journal_superblock_t *sb = journal->j_superblock;
+ BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
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);
+ jbd_debug(1, "JBD2: 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);
read_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)) {
- printk(KERN_ERR "JBD2: I/O error detected "
- "when updating journal superblock for %s.\n",
- journal->j_devname);
- clear_buffer_write_io_error(bh);
- set_buffer_uptodate(bh);
- }
- } else
- write_dirty_buffer(bh, WRITE);
-
-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. */
+ jbd2_write_superblock(journal, WRITE_FUA);
+ /* Log is no longer empty */
write_lock(&journal->j_state_lock);
- if (sb->s_start)
- journal->j_flags &= ~JBD2_FLUSHED;
- else
- journal->j_flags |= JBD2_FLUSHED;
+ journal->j_flags |= JBD2_FLUSHED;
write_unlock(&journal->j_state_lock);
}
+
+/**
+ * jbd2_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 jbd2_journal_update_sb_errno(journal_t *journal)
+{
+ journal_superblock_t *sb = journal->j_superblock;
+
+ read_lock(&journal->j_state_lock);
+ jbd_debug(1, "JBD2: updating superblock error (errno %d)\n",
+ journal->j_errno);
+ sb->s_errno = cpu_to_be32(journal->j_errno);
+ read_unlock(&journal->j_state_lock);
+
+ jbd2_write_superblock(journal, WRITE_SYNC);
+}
+
/*
* Read the superblock for a given journal, performing initial
* validation of the format.
*/
-
static int journal_get_superblock(journal_t *journal)
{
struct buffer_head *bh;
ll_rw_block(READ, 1, &bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
- printk (KERN_ERR
- "JBD: IO error reading journal superblock\n");
+ printk(KERN_ERR
+ "JBD2: IO error reading journal superblock\n");
goto out;
}
}
if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) ||
sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) {
- printk(KERN_WARNING "JBD: no valid journal superblock found\n");
+ printk(KERN_WARNING "JBD2: no valid journal superblock found\n");
goto out;
}
journal->j_format_version = 2;
break;
default:
- printk(KERN_WARNING "JBD: unrecognised superblock format ID\n");
+ printk(KERN_WARNING "JBD2: unrecognised superblock format ID\n");
goto out;
}
if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
- printk (KERN_WARNING "JBD: journal file too short\n");
+ printk(KERN_WARNING "JBD2: journal file too short\n");
+ goto out;
+ }
+
+ if (be32_to_cpu(sb->s_first) == 0 ||
+ be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+ printk(KERN_WARNING
+ "JBD2: Invalid start block of journal: %u\n",
+ be32_to_cpu(sb->s_first));
goto out;
}
~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) ||
(sb->s_feature_incompat &
~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) {
- printk (KERN_WARNING
- "JBD: Unrecognised features on journal\n");
+ printk(KERN_WARNING
+ "JBD2: Unrecognised features on journal\n");
return -EINVAL;
}
}
return 0;
recovery_error:
- printk (KERN_WARNING "JBD: recovery failed\n");
+ printk(KERN_WARNING "JBD2: recovery failed\n");
return -EIO;
}
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;
- jbd2_journal_update_superblock(journal, 1);
- } else {
+ mutex_lock(&journal->j_checkpoint_mutex);
+ jbd2_mark_journal_empty(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
+ } else
err = -EIO;
- }
brelse(journal->j_sb_buffer);
}
EXPORT_SYMBOL(jbd2_journal_clear_features);
/**
- * int jbd2_journal_update_format () - Update on-disk journal structure.
- * @journal: Journal to act on.
- *
- * Given an initialised but unloaded journal struct, poke about in the
- * on-disk structure to update it to the most recent supported version.
- */
-int jbd2_journal_update_format (journal_t *journal)
-{
- journal_superblock_t *sb;
- int err;
-
- err = journal_get_superblock(journal);
- if (err)
- return err;
-
- sb = journal->j_superblock;
-
- switch (be32_to_cpu(sb->s_header.h_blocktype)) {
- case JBD2_SUPERBLOCK_V2:
- return 0;
- case JBD2_SUPERBLOCK_V1:
- return journal_convert_superblock_v1(journal, sb);
- default:
- break;
- }
- return -EINVAL;
-}
-
-static int journal_convert_superblock_v1(journal_t *journal,
- journal_superblock_t *sb)
-{
- int offset, blocksize;
- struct buffer_head *bh;
-
- printk(KERN_WARNING
- "JBD: Converting superblock from version 1 to 2.\n");
-
- /* Pre-initialise new fields to zero */
- offset = ((char *) &(sb->s_feature_compat)) - ((char *) sb);
- blocksize = be32_to_cpu(sb->s_blocksize);
- memset(&sb->s_feature_compat, 0, blocksize-offset);
-
- sb->s_nr_users = cpu_to_be32(1);
- sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2);
- journal->j_format_version = 2;
-
- bh = journal->j_sb_buffer;
- BUFFER_TRACE(bh, "marking dirty");
- mark_buffer_dirty(bh);
- sync_dirty_buffer(bh);
- return 0;
-}
-
-
-/**
* int jbd2_journal_flush () - Flush journal
* @journal: Journal to act on.
*
{
int err = 0;
transaction_t *transaction = NULL;
- unsigned long old_tail;
write_lock(&journal->j_state_lock);
if (is_journal_aborted(journal))
return -EIO;
+ mutex_lock(&journal->j_checkpoint_mutex);
jbd2_cleanup_journal_tail(journal);
/* Finally, mark the journal as really needing no recovery.
* the magic code for a fully-recovered superblock. Any future
* commits of data to the journal will restore the current
* s_start value. */
+ jbd2_mark_journal_empty(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
write_lock(&journal->j_state_lock);
- old_tail = journal->j_tail;
- journal->j_tail = 0;
- write_unlock(&journal->j_state_lock);
- jbd2_journal_update_superblock(journal, 1);
- write_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);
if (!journal->j_tail)
goto no_recovery;
- printk (KERN_WARNING "JBD: %s recovery information on journal\n",
+ printk(KERN_WARNING "JBD2: %s recovery information on journal\n",
write ? "Clearing" : "Ignoring");
err = jbd2_journal_skip_recovery(journal);
- if (write)
- jbd2_journal_update_superblock(journal, 1);
+ if (write) {
+ /* Lock to make assertions happy... */
+ mutex_lock(&journal->j_checkpoint_mutex);
+ jbd2_mark_journal_empty(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
+ }
no_recovery:
return err;
__jbd2_journal_abort_hard(journal);
if (errno)
- jbd2_journal_update_superblock(journal, 1);
+ jbd2_journal_update_sb_errno(journal);
}
/**
*/
#define JBD2_MAX_SLABS 8
static struct kmem_cache *jbd2_slab[JBD2_MAX_SLABS];
-static DECLARE_MUTEX(jbd2_slab_create_sem);
static const char *jbd2_slab_names[JBD2_MAX_SLABS] = {
"jbd2_1k", "jbd2_2k", "jbd2_4k", "jbd2_8k",
static int jbd2_journal_create_slab(size_t size)
{
+ static DEFINE_MUTEX(jbd2_slab_create_mutex);
int i = order_base_2(size) - 10;
size_t slab_size;
if (unlikely(i < 0))
i = 0;
- down(&jbd2_slab_create_sem);
+ mutex_lock(&jbd2_slab_create_mutex);
if (jbd2_slab[i]) {
- up(&jbd2_slab_create_sem);
+ mutex_unlock(&jbd2_slab_create_mutex);
return 0; /* Already created */
}
slab_size = 1 << (i+10);
jbd2_slab[i] = kmem_cache_create(jbd2_slab_names[i], slab_size,
slab_size, 0, NULL);
- up(&jbd2_slab_create_sem);
+ mutex_unlock(&jbd2_slab_create_mutex);
if (!jbd2_slab[i]) {
printk(KERN_EMERG "JBD2: no memory for jbd2_slab cache\n");
return -ENOMEM;
static atomic_t nr_journal_heads = ATOMIC_INIT(0);
#endif
-static int journal_init_jbd2_journal_head_cache(void)
+static int jbd2_journal_init_journal_head_cache(void)
{
int retval;
retval = 0;
if (!jbd2_journal_head_cache) {
retval = -ENOMEM;
- printk(KERN_EMERG "JBD: no memory for journal_head cache\n");
+ printk(KERN_EMERG "JBD2: no memory for journal_head cache\n");
}
return retval;
}
-static void jbd2_journal_destroy_jbd2_journal_head_cache(void)
+static void jbd2_journal_destroy_journal_head_cache(void)
{
if (jbd2_journal_head_cache) {
kmem_cache_destroy(jbd2_journal_head_cache);
static struct journal_head *journal_alloc_journal_head(void)
{
struct journal_head *ret;
- static unsigned long last_warning;
#ifdef CONFIG_JBD2_DEBUG
atomic_inc(&nr_journal_heads);
ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS);
if (!ret) {
jbd_debug(1, "out of memory for journal_head\n");
- if (time_after(jiffies, last_warning + 5*HZ)) {
- printk(KERN_NOTICE "ENOMEM in %s, retrying.\n",
- __func__);
- last_warning = jiffies;
- }
+ pr_notice_ratelimited("ENOMEM in %s, retrying.\n", __func__);
while (!ret) {
yield();
ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS);
* 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 jbd2_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
* (Attach a journal_head if needed. Increments b_jcount)
* struct journal_head *jh = jbd2_journal_add_journal_head(bh);
* ...
+ * (Get another reference for transaction)
+ * jbd2_journal_grab_journal_head(bh);
* jh->b_transaction = xxx;
+ * (Put original reference)
* jbd2_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.
*/
/*
* Give a buffer_head a journal_head.
*
- * Doesn't need the journal lock.
* May sleep.
*/
struct journal_head *jbd2_journal_add_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__);
- jbd2_free(jh->b_frozen_data, bh->b_size);
- }
- if (jh->b_committed_data) {
- printk(KERN_WARNING "%s: freeing "
- "b_committed_data\n",
- __func__);
- jbd2_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__);
+ jbd2_free(jh->b_frozen_data, bh->b_size);
}
+ if (jh->b_committed_data) {
+ printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__);
+ jbd2_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);
}
/*
- * jbd2_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 jbd2_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 jbd2_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 jbd2_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);
}
/*
#endif
-struct kmem_cache *jbd2_handle_cache;
+struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache;
-static int __init journal_init_handle_cache(void)
+static int __init jbd2_journal_init_handle_cache(void)
{
- jbd2_handle_cache = kmem_cache_create("jbd2_journal_handle",
- sizeof(handle_t),
- 0, /* offset */
- SLAB_TEMPORARY, /* flags */
- NULL); /* ctor */
+ jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY);
if (jbd2_handle_cache == NULL) {
- printk(KERN_EMERG "JBD: failed to create handle cache\n");
+ printk(KERN_EMERG "JBD2: failed to create handle cache\n");
+ return -ENOMEM;
+ }
+ jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0);
+ if (jbd2_inode_cache == NULL) {
+ printk(KERN_EMERG "JBD2: failed to create inode cache\n");
+ kmem_cache_destroy(jbd2_handle_cache);
return -ENOMEM;
}
return 0;
{
if (jbd2_handle_cache)
kmem_cache_destroy(jbd2_handle_cache);
+ if (jbd2_inode_cache)
+ kmem_cache_destroy(jbd2_inode_cache);
+
}
/*
ret = jbd2_journal_init_revoke_caches();
if (ret == 0)
- ret = journal_init_jbd2_journal_head_cache();
+ ret = jbd2_journal_init_journal_head_cache();
+ if (ret == 0)
+ ret = jbd2_journal_init_handle_cache();
if (ret == 0)
- ret = journal_init_handle_cache();
+ ret = jbd2_journal_init_transaction_cache();
return ret;
}
static void jbd2_journal_destroy_caches(void)
{
jbd2_journal_destroy_revoke_caches();
- jbd2_journal_destroy_jbd2_journal_head_cache();
+ jbd2_journal_destroy_journal_head_cache();
jbd2_journal_destroy_handle_cache();
+ jbd2_journal_destroy_transaction_cache();
jbd2_journal_destroy_slabs();
}
#ifdef CONFIG_JBD2_DEBUG
int n = atomic_read(&nr_journal_heads);
if (n)
- printk(KERN_EMERG "JBD: leaked %d journal_heads!\n", n);
+ printk(KERN_EMERG "JBD2: leaked %d journal_heads!\n", n);
#endif
jbd2_remove_debugfs_entry();
jbd2_remove_jbd_stats_proc_entry();
jbd2_journal_destroy_caches();
}
-/*
- * jbd2_dev_to_name is a utility function used by the jbd2 and ext4
- * tracing infrastructure to map a dev_t to a device name.
- *
- * The caller should use rcu_read_lock() in order to make sure the
- * device name stays valid until its done with it. We use
- * rcu_read_lock() as well to make sure we're safe in case the caller
- * gets sloppy, and because rcu_read_lock() is cheap and can be safely
- * nested.
- */
-struct devname_cache {
- struct rcu_head rcu;
- dev_t device;
- char devname[BDEVNAME_SIZE];
-};
-#define CACHE_SIZE_BITS 6
-static struct devname_cache *devcache[1 << CACHE_SIZE_BITS];
-static DEFINE_SPINLOCK(devname_cache_lock);
-
-static void free_devcache(struct rcu_head *rcu)
-{
- kfree(rcu);
-}
-
-const char *jbd2_dev_to_name(dev_t device)
-{
- int i = hash_32(device, CACHE_SIZE_BITS);
- char *ret;
- struct block_device *bd;
- static struct devname_cache *new_dev;
-
- rcu_read_lock();
- if (devcache[i] && devcache[i]->device == device) {
- ret = devcache[i]->devname;
- rcu_read_unlock();
- return ret;
- }
- rcu_read_unlock();
-
- new_dev = kmalloc(sizeof(struct devname_cache), GFP_KERNEL);
- if (!new_dev)
- return "NODEV-ALLOCFAILURE"; /* Something non-NULL */
- spin_lock(&devname_cache_lock);
- if (devcache[i]) {
- if (devcache[i]->device == device) {
- kfree(new_dev);
- ret = devcache[i]->devname;
- spin_unlock(&devname_cache_lock);
- return ret;
- }
- call_rcu(&devcache[i]->rcu, free_devcache);
- }
- devcache[i] = new_dev;
- devcache[i]->device = device;
- bd = bdget(device);
- if (bd) {
- bdevname(bd, devcache[i]->devname);
- bdput(bd);
- } else
- __bdevname(device, devcache[i]->devname);
- ret = devcache[i]->devname;
- spin_unlock(&devname_cache_lock);
- return ret;
-}
-EXPORT_SYMBOL(jbd2_dev_to_name);
-
MODULE_LICENSE("GPL");
module_init(journal_init);
module_exit(journal_exit);