/*
- * linux/fs/jbd/journal.c
+ * linux/fs/jbd2/journal.c
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 1998
*
#include <linux/module.h>
#include <linux/time.h>
#include <linux/fs.h>
-#include <linux/jbd.h>
+#include <linux/jbd2.h>
#include <linux/errno.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/mm.h>
-#include <linux/suspend.h>
+#include <linux/freezer.h>
#include <linux/pagemap.h>
#include <linux/kthread.h>
#include <linux/poison.h>
#include <linux/proc_fs.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/math64.h>
+#include <linux/hash.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/jbd2.h>
#include <asm/uaccess.h>
#include <asm/page.h>
-EXPORT_SYMBOL(journal_start);
-EXPORT_SYMBOL(journal_restart);
-EXPORT_SYMBOL(journal_extend);
-EXPORT_SYMBOL(journal_stop);
-EXPORT_SYMBOL(journal_lock_updates);
-EXPORT_SYMBOL(journal_unlock_updates);
-EXPORT_SYMBOL(journal_get_write_access);
-EXPORT_SYMBOL(journal_get_create_access);
-EXPORT_SYMBOL(journal_get_undo_access);
-EXPORT_SYMBOL(journal_dirty_data);
-EXPORT_SYMBOL(journal_dirty_metadata);
-EXPORT_SYMBOL(journal_release_buffer);
-EXPORT_SYMBOL(journal_forget);
+EXPORT_SYMBOL(jbd2_journal_start);
+EXPORT_SYMBOL(jbd2_journal_restart);
+EXPORT_SYMBOL(jbd2_journal_extend);
+EXPORT_SYMBOL(jbd2_journal_stop);
+EXPORT_SYMBOL(jbd2_journal_lock_updates);
+EXPORT_SYMBOL(jbd2_journal_unlock_updates);
+EXPORT_SYMBOL(jbd2_journal_get_write_access);
+EXPORT_SYMBOL(jbd2_journal_get_create_access);
+EXPORT_SYMBOL(jbd2_journal_get_undo_access);
+EXPORT_SYMBOL(jbd2_journal_set_triggers);
+EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
+EXPORT_SYMBOL(jbd2_journal_release_buffer);
+EXPORT_SYMBOL(jbd2_journal_forget);
#if 0
EXPORT_SYMBOL(journal_sync_buffer);
#endif
-EXPORT_SYMBOL(journal_flush);
-EXPORT_SYMBOL(journal_revoke);
-
-EXPORT_SYMBOL(journal_init_dev);
-EXPORT_SYMBOL(journal_init_inode);
-EXPORT_SYMBOL(journal_update_format);
-EXPORT_SYMBOL(journal_check_used_features);
-EXPORT_SYMBOL(journal_check_available_features);
-EXPORT_SYMBOL(journal_set_features);
-EXPORT_SYMBOL(journal_create);
-EXPORT_SYMBOL(journal_load);
-EXPORT_SYMBOL(journal_destroy);
-EXPORT_SYMBOL(journal_update_superblock);
-EXPORT_SYMBOL(journal_abort);
-EXPORT_SYMBOL(journal_errno);
-EXPORT_SYMBOL(journal_ack_err);
-EXPORT_SYMBOL(journal_clear_err);
-EXPORT_SYMBOL(log_wait_commit);
-EXPORT_SYMBOL(journal_start_commit);
-EXPORT_SYMBOL(journal_force_commit_nested);
-EXPORT_SYMBOL(journal_wipe);
-EXPORT_SYMBOL(journal_blocks_per_page);
-EXPORT_SYMBOL(journal_invalidatepage);
-EXPORT_SYMBOL(journal_try_to_free_buffers);
-EXPORT_SYMBOL(journal_force_commit);
+EXPORT_SYMBOL(jbd2_journal_flush);
+EXPORT_SYMBOL(jbd2_journal_revoke);
+
+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_load);
+EXPORT_SYMBOL(jbd2_journal_destroy);
+EXPORT_SYMBOL(jbd2_journal_abort);
+EXPORT_SYMBOL(jbd2_journal_errno);
+EXPORT_SYMBOL(jbd2_journal_ack_err);
+EXPORT_SYMBOL(jbd2_journal_clear_err);
+EXPORT_SYMBOL(jbd2_log_wait_commit);
+EXPORT_SYMBOL(jbd2_journal_start_commit);
+EXPORT_SYMBOL(jbd2_journal_force_commit_nested);
+EXPORT_SYMBOL(jbd2_journal_wipe);
+EXPORT_SYMBOL(jbd2_journal_blocks_per_page);
+EXPORT_SYMBOL(jbd2_journal_invalidatepage);
+EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
+EXPORT_SYMBOL(jbd2_journal_force_commit);
+EXPORT_SYMBOL(jbd2_journal_file_inode);
+EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
+EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
+EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
static void __journal_abort_soft (journal_t *journal, int errno);
-static int journal_create_jbd_slab(size_t slab_size);
/*
* Helper function used to manage commit timeouts
}
/*
- * kjournald: The main thread function used to manage a logging device
+ * kjournald2: The main thread function used to manage a logging device
* journal.
*
* This kernel thread is responsible for two things:
* known as checkpointing, and this thread is responsible for that job.
*/
-static int kjournald(void *arg)
+static int kjournald2(void *arg)
{
journal_t *journal = arg;
transaction_t *transaction;
journal->j_task = current;
wake_up(&journal->j_wait_done_commit);
- printk(KERN_INFO "kjournald starting. Commit interval %ld seconds\n",
- journal->j_commit_interval / HZ);
-
/*
* And now, wait forever for commit wakeup events.
*/
spin_lock(&journal->j_state_lock);
loop:
- if (journal->j_flags & JFS_UNMOUNT)
+ if (journal->j_flags & JBD2_UNMOUNT)
goto end_loop;
jbd_debug(1, "commit_sequence=%d, commit_request=%d\n",
jbd_debug(1, "OK, requests differ\n");
spin_unlock(&journal->j_state_lock);
del_timer_sync(&journal->j_commit_timer);
- journal_commit_transaction(journal);
+ jbd2_journal_commit_transaction(journal);
spin_lock(&journal->j_state_lock);
goto loop;
}
* good idea, because that depends on threads that may
* be already stopped.
*/
- jbd_debug(1, "Now suspending kjournald\n");
+ jbd_debug(1, "Now suspending kjournald2\n");
spin_unlock(&journal->j_state_lock);
refrigerator();
spin_lock(&journal->j_state_lock);
if (transaction && time_after_eq(jiffies,
transaction->t_expires))
should_sleep = 0;
- if (journal->j_flags & JFS_UNMOUNT)
+ if (journal->j_flags & JBD2_UNMOUNT)
should_sleep = 0;
if (should_sleep) {
spin_unlock(&journal->j_state_lock);
finish_wait(&journal->j_wait_commit, &wait);
}
- jbd_debug(1, "kjournald wakes\n");
+ jbd_debug(1, "kjournald2 wakes\n");
/*
* Were we woken up by a commit wakeup event?
return 0;
}
-static void journal_start_thread(journal_t *journal)
+static int jbd2_journal_start_thread(journal_t *journal)
{
- kthread_run(kjournald, journal, "kjournald");
- wait_event(journal->j_wait_done_commit, journal->j_task != 0);
+ struct task_struct *t;
+
+ t = kthread_run(kjournald2, journal, "jbd2/%s",
+ journal->j_devname);
+ if (IS_ERR(t))
+ return PTR_ERR(t);
+
+ wait_event(journal->j_wait_done_commit, journal->j_task != NULL);
+ return 0;
}
static void journal_kill_thread(journal_t *journal)
{
spin_lock(&journal->j_state_lock);
- journal->j_flags |= JFS_UNMOUNT;
+ journal->j_flags |= JBD2_UNMOUNT;
while (journal->j_task) {
wake_up(&journal->j_wait_commit);
spin_unlock(&journal->j_state_lock);
- wait_event(journal->j_wait_done_commit, journal->j_task == 0);
+ wait_event(journal->j_wait_done_commit, journal->j_task == NULL);
spin_lock(&journal->j_state_lock);
}
spin_unlock(&journal->j_state_lock);
}
/*
- * journal_write_metadata_buffer: write a metadata buffer to the journal.
+ * jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal.
*
* Writes a metadata buffer to a given disk block. The actual IO is not
* performed but a new buffer_head is constructed which labels the data
*
* Any magic-number escaping which needs to be done will cause a
* copy-out here. If the buffer happens to start with the
- * JFS_MAGIC_NUMBER, then we can't write it to the log directly: the
+ * JBD2_MAGIC_NUMBER, then we can't write it to the log directly: the
* magic number is only written to the log for descripter blocks. In
* this case, we copy the data and replace the first word with 0, and we
* return a result code which indicates that this buffer needs to be
* Bit 1 set == buffer copy-out performed (kfree the data after IO)
*/
-int journal_write_metadata_buffer(transaction_t *transaction,
+int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
struct journal_head *jh_in,
struct journal_head **jh_out,
- unsigned long blocknr)
+ unsigned long long blocknr)
{
int need_copy_out = 0;
int done_copy_out = 0;
struct page *new_page;
unsigned int new_offset;
struct buffer_head *bh_in = jh2bh(jh_in);
+ struct jbd2_buffer_trigger_type *triggers;
+ journal_t *journal = transaction->t_journal;
/*
* The buffer really shouldn't be locked: only the current committing
J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
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 = jbd2_journal_add_journal_head(new_bh); /* This sleeps */
/*
* If a new transaction has already done a buffer copy-out, then
done_copy_out = 1;
new_page = virt_to_page(jh_in->b_frozen_data);
new_offset = offset_in_page(jh_in->b_frozen_data);
+ triggers = jh_in->b_frozen_triggers;
} else {
new_page = jh2bh(jh_in)->b_page;
new_offset = offset_in_page(jh2bh(jh_in)->b_data);
+ triggers = jh_in->b_triggers;
}
mapped_data = kmap_atomic(new_page, KM_USER0);
/*
+ * Fire any commit trigger. Do this before checking for escaping,
+ * as the trigger may modify the magic offset. If a copy-out
+ * happens afterwards, it will have the correct data in the buffer.
+ */
+ jbd2_buffer_commit_trigger(jh_in, mapped_data + new_offset,
+ triggers);
+
+ /*
* Check for escaping
*/
if (*((__be32 *)(mapped_data + new_offset)) ==
- cpu_to_be32(JFS_MAGIC_NUMBER)) {
+ cpu_to_be32(JBD2_MAGIC_NUMBER)) {
need_copy_out = 1;
do_escape = 1;
}
char *tmp;
jbd_unlock_bh_state(bh_in);
- tmp = jbd_slab_alloc(bh_in->b_size, GFP_NOFS);
+ tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
jbd_lock_bh_state(bh_in);
if (jh_in->b_frozen_data) {
- jbd_slab_free(tmp, bh_in->b_size);
+ jbd2_free(tmp, bh_in->b_size);
goto repeat;
}
new_page = virt_to_page(tmp);
new_offset = offset_in_page(tmp);
done_copy_out = 1;
+
+ /*
+ * This isn't strictly necessary, as we're using frozen
+ * data for the escaping, but it keeps consistency with
+ * b_frozen_data usage.
+ */
+ jh_in->b_frozen_triggers = jh_in->b_triggers;
}
/*
kunmap_atomic(mapped_data, KM_USER0);
}
- /* keep subsequent assertions sane */
- new_bh->b_state = 0;
- init_buffer(new_bh, NULL, NULL);
- atomic_set(&new_bh->b_count, 1);
- jbd_unlock_bh_state(bh_in);
-
- new_jh = journal_add_journal_head(new_bh); /* This sleeps */
-
set_bh_page(new_bh, new_page, new_offset);
new_jh->b_transaction = NULL;
new_bh->b_size = jh2bh(jh_in)->b_size;
* copying is moved to the transaction's shadow queue.
*/
JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
- journal_file_buffer(jh_in, transaction, BJ_Shadow);
+ spin_lock(&journal->j_list_lock);
+ __jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh_in);
+
JBUFFER_TRACE(new_jh, "file as BJ_IO");
- journal_file_buffer(new_jh, transaction, BJ_IO);
+ jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);
return do_escape | (done_copy_out << 1);
}
*/
/*
- * __log_space_left: Return the number of free blocks left in the journal.
+ * __jbd2_log_space_left: Return the number of free blocks left in the journal.
*
* Called with the journal already locked.
*
* Called under j_state_lock
*/
-int __log_space_left(journal_t *journal)
+int __jbd2_log_space_left(journal_t *journal)
{
int left = journal->j_free;
}
/*
- * Called under j_state_lock. Returns true if a transaction was started.
+ * Called under j_state_lock. Returns true if a transaction commit was started.
*/
-int __log_start_commit(journal_t *journal, tid_t target)
+int __jbd2_log_start_commit(journal_t *journal, tid_t target)
{
/*
* Are we already doing a recent enough commit?
return 0;
}
-int log_start_commit(journal_t *journal, tid_t tid)
+int jbd2_log_start_commit(journal_t *journal, tid_t tid)
{
int ret;
spin_lock(&journal->j_state_lock);
- ret = __log_start_commit(journal, tid);
+ ret = __jbd2_log_start_commit(journal, tid);
spin_unlock(&journal->j_state_lock);
return ret;
}
*
* Returns true if a transaction was started.
*/
-int journal_force_commit_nested(journal_t *journal)
+int jbd2_journal_force_commit_nested(journal_t *journal)
{
transaction_t *transaction = NULL;
tid_t tid;
spin_lock(&journal->j_state_lock);
if (journal->j_running_transaction && !current->journal_info) {
transaction = journal->j_running_transaction;
- __log_start_commit(journal, transaction->t_tid);
+ __jbd2_log_start_commit(journal, transaction->t_tid);
} else if (journal->j_committing_transaction)
transaction = journal->j_committing_transaction;
tid = transaction->t_tid;
spin_unlock(&journal->j_state_lock);
- log_wait_commit(journal, tid);
+ jbd2_log_wait_commit(journal, tid);
return 1;
}
/*
* Start a commit of the current running transaction (if any). Returns true
- * if a transaction was started, and fills its tid in at *ptid
+ * if a transaction is going to be committed (or is currently already
+ * committing), and fills its tid in at *ptid
*/
-int journal_start_commit(journal_t *journal, tid_t *ptid)
+int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
{
int ret = 0;
if (journal->j_running_transaction) {
tid_t tid = journal->j_running_transaction->t_tid;
- ret = __log_start_commit(journal, tid);
- if (ret && ptid)
+ __jbd2_log_start_commit(journal, tid);
+ /* There's a running transaction and we've just made sure
+ * it's commit has been scheduled. */
+ if (ptid)
*ptid = tid;
- } else if (journal->j_committing_transaction && 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
*/
- *ptid = journal->j_committing_transaction->t_tid;
+ if (ptid)
+ *ptid = journal->j_committing_transaction->t_tid;
ret = 1;
}
spin_unlock(&journal->j_state_lock);
* Wait for a specified commit to complete.
* The caller may not hold the journal lock.
*/
-int log_wait_commit(journal_t *journal, tid_t tid)
+int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
{
int err = 0;
-#ifdef CONFIG_JBD_DEBUG
+#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",
- __FUNCTION__, journal->j_commit_request, tid);
+ __func__, journal->j_commit_request, tid);
}
spin_unlock(&journal->j_state_lock);
#endif
* Log buffer allocation routines:
*/
-int journal_next_log_block(journal_t *journal, unsigned long *retp)
+int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
{
unsigned long blocknr;
if (journal->j_head == journal->j_last)
journal->j_head = journal->j_first;
spin_unlock(&journal->j_state_lock);
- return journal_bmap(journal, blocknr, retp);
+ return jbd2_journal_bmap(journal, blocknr, retp);
}
/*
* this is a no-op. If needed, we can use j_blk_offset - everything is
* ready.
*/
-int journal_bmap(journal_t *journal, unsigned long blocknr,
- unsigned long *retp)
+int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
+ unsigned long long *retp)
{
int err = 0;
- unsigned long ret;
+ unsigned long long ret;
if (journal->j_inode) {
ret = bmap(journal->j_inode, blocknr);
if (ret)
*retp = ret;
else {
- char b[BDEVNAME_SIZE];
-
printk(KERN_ALERT "%s: journal block not found "
"at offset %lu on %s\n",
- __FUNCTION__,
- blocknr,
- bdevname(journal->j_dev, b));
+ __func__, blocknr, journal->j_devname);
err = -EIO;
__journal_abort_soft(journal, err);
}
* the journal without copying their contents, but for journal
* descriptor blocks we do need to generate bona fide buffers.
*
- * After the caller of journal_get_descriptor_buffer() has finished modifying
+ * After the caller of jbd2_journal_get_descriptor_buffer() has finished modifying
* the buffer's contents they really should run flush_dcache_page(bh->b_page).
* But we don't bother doing that, so there will be coherency problems with
* mmaps of blockdevs which hold live JBD-controlled filesystems.
*/
-struct journal_head *journal_get_descriptor_buffer(journal_t *journal)
+struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
{
struct buffer_head *bh;
- unsigned long blocknr;
+ unsigned long long blocknr;
int err;
- err = journal_next_log_block(journal, &blocknr);
+ err = jbd2_journal_next_log_block(journal, &blocknr);
if (err)
return NULL;
bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+ if (!bh)
+ return NULL;
lock_buffer(bh);
memset(bh->b_data, 0, journal->j_blocksize);
set_buffer_uptodate(bh);
unlock_buffer(bh);
BUFFER_TRACE(bh, "return this buffer");
- return journal_add_journal_head(bh);
+ return jbd2_journal_add_journal_head(bh);
+}
+
+struct jbd2_stats_proc_session {
+ journal_t *journal;
+ struct transaction_stats_s *stats;
+ int start;
+ int max;
+};
+
+static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos)
+{
+ return *pos ? NULL : SEQ_START_TOKEN;
+}
+
+static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ return NULL;
+}
+
+static int jbd2_seq_info_show(struct seq_file *seq, void *v)
+{
+ struct jbd2_stats_proc_session *s = seq->private;
+
+ if (v != SEQ_START_TOKEN)
+ return 0;
+ seq_printf(seq, "%lu transaction, each up to %u blocks\n",
+ s->stats->ts_tid,
+ s->journal->j_max_transaction_buffers);
+ if (s->stats->ts_tid == 0)
+ return 0;
+ seq_printf(seq, "average: \n %ums waiting for transaction\n",
+ jiffies_to_msecs(s->stats->run.rs_wait / s->stats->ts_tid));
+ seq_printf(seq, " %ums running transaction\n",
+ jiffies_to_msecs(s->stats->run.rs_running / s->stats->ts_tid));
+ seq_printf(seq, " %ums transaction was being locked\n",
+ jiffies_to_msecs(s->stats->run.rs_locked / s->stats->ts_tid));
+ seq_printf(seq, " %ums flushing data (in ordered mode)\n",
+ jiffies_to_msecs(s->stats->run.rs_flushing / s->stats->ts_tid));
+ seq_printf(seq, " %ums logging transaction\n",
+ jiffies_to_msecs(s->stats->run.rs_logging / s->stats->ts_tid));
+ seq_printf(seq, " %lluus average transaction commit time\n",
+ div_u64(s->journal->j_average_commit_time, 1000));
+ seq_printf(seq, " %lu handles per transaction\n",
+ s->stats->run.rs_handle_count / s->stats->ts_tid);
+ seq_printf(seq, " %lu blocks per transaction\n",
+ s->stats->run.rs_blocks / s->stats->ts_tid);
+ seq_printf(seq, " %lu logged blocks per transaction\n",
+ s->stats->run.rs_blocks_logged / s->stats->ts_tid);
+ return 0;
+}
+
+static void jbd2_seq_info_stop(struct seq_file *seq, void *v)
+{
+}
+
+static const struct seq_operations jbd2_seq_info_ops = {
+ .start = jbd2_seq_info_start,
+ .next = jbd2_seq_info_next,
+ .stop = jbd2_seq_info_stop,
+ .show = jbd2_seq_info_show,
+};
+
+static int jbd2_seq_info_open(struct inode *inode, struct file *file)
+{
+ journal_t *journal = PDE(inode)->data;
+ struct jbd2_stats_proc_session *s;
+ int rc, size;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (s == NULL)
+ return -ENOMEM;
+ size = sizeof(struct transaction_stats_s);
+ s->stats = kmalloc(size, GFP_KERNEL);
+ if (s->stats == NULL) {
+ kfree(s);
+ return -ENOMEM;
+ }
+ spin_lock(&journal->j_history_lock);
+ memcpy(s->stats, &journal->j_stats, size);
+ s->journal = journal;
+ spin_unlock(&journal->j_history_lock);
+
+ rc = seq_open(file, &jbd2_seq_info_ops);
+ if (rc == 0) {
+ struct seq_file *m = file->private_data;
+ m->private = s;
+ } else {
+ kfree(s->stats);
+ kfree(s);
+ }
+ return rc;
+
+}
+
+static int jbd2_seq_info_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+ struct jbd2_stats_proc_session *s = seq->private;
+ kfree(s->stats);
+ kfree(s);
+ return seq_release(inode, file);
+}
+
+static struct file_operations jbd2_seq_info_fops = {
+ .owner = THIS_MODULE,
+ .open = jbd2_seq_info_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = jbd2_seq_info_release,
+};
+
+static struct proc_dir_entry *proc_jbd2_stats;
+
+static void jbd2_stats_proc_init(journal_t *journal)
+{
+ journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats);
+ if (journal->j_proc_entry) {
+ proc_create_data("info", S_IRUGO, journal->j_proc_entry,
+ &jbd2_seq_info_fops, journal);
+ }
+}
+
+static void jbd2_stats_proc_exit(journal_t *journal)
+{
+ remove_proc_entry("info", journal->j_proc_entry);
+ remove_proc_entry(journal->j_devname, proc_jbd2_stats);
}
/*
journal_t *journal;
int err;
- journal = jbd_kmalloc(sizeof(*journal), GFP_KERNEL);
+ journal = kzalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL);
if (!journal)
goto fail;
- memset(journal, 0, sizeof(*journal));
init_waitqueue_head(&journal->j_wait_transaction_locked);
init_waitqueue_head(&journal->j_wait_logspace);
spin_lock_init(&journal->j_list_lock);
spin_lock_init(&journal->j_state_lock);
- journal->j_commit_interval = (HZ * JBD_DEFAULT_MAX_COMMIT_AGE);
+ journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE);
+ journal->j_min_batch_time = 0;
+ journal->j_max_batch_time = 15000; /* 15ms */
/* The journal is marked for error until we succeed with recovery! */
- journal->j_flags = JFS_ABORT;
+ journal->j_flags = JBD2_ABORT;
/* Set up a default-sized revoke table for the new mount. */
- err = journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
+ err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
if (err) {
kfree(journal);
goto fail;
}
+
+ spin_lock_init(&journal->j_history_lock);
+
return journal;
fail:
return NULL;
}
-/* journal_init_dev and journal_init_inode:
+/* jbd2_journal_init_dev and jbd2_journal_init_inode:
*
* Create a journal structure assigned some fixed set of disk blocks to
* the journal. We don't actually touch those disk blocks yet, but we
*/
/**
- * journal_t * journal_init_dev() - creates an initialises a journal structure
+ * journal_t * jbd2_journal_init_dev() - creates and initialises a journal structure
* @bdev: Block device on which to create the journal
* @fs_dev: Device which hold journalled filesystem for this journal.
* @start: Block nr Start of journal.
* @len: Length of the journal in blocks.
* @blocksize: blocksize of journalling device
- * @returns: a newly created journal_t *
*
- * journal_init_dev creates a journal which maps a fixed contiguous
+ * Returns: a newly created journal_t *
+ *
+ * jbd2_journal_init_dev creates a journal which maps a fixed contiguous
* range of blocks on an arbitrary block device.
*
*/
-journal_t * journal_init_dev(struct block_device *bdev,
+journal_t * jbd2_journal_init_dev(struct block_device *bdev,
struct block_device *fs_dev,
- int start, int len, int blocksize)
+ unsigned long long start, int len, int blocksize)
{
journal_t *journal = journal_init_common();
struct buffer_head *bh;
+ char *p;
int n;
if (!journal)
/* 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",
- __FUNCTION__);
- kfree(journal);
- journal = NULL;
+ __func__);
+ goto out_err;
}
journal->j_dev = bdev;
journal->j_fs_dev = fs_dev;
journal->j_blk_offset = start;
journal->j_maxlen = len;
+ bdevname(journal->j_dev, journal->j_devname);
+ p = journal->j_devname;
+ while ((p = strchr(p, '/')))
+ *p = '!';
bh = __getblk(journal->j_dev, start, journal->j_blocksize);
- J_ASSERT(bh != NULL);
+ if (!bh) {
+ printk(KERN_ERR
+ "%s: Cannot get buffer for journal superblock\n",
+ __func__);
+ goto out_err;
+ }
journal->j_sb_buffer = bh;
journal->j_superblock = (journal_superblock_t *)bh->b_data;
return journal;
+out_err:
+ jbd2_stats_proc_exit(journal);
+ kfree(journal);
+ return NULL;
}
/**
- * journal_t * journal_init_inode () - creates a journal which maps to a inode.
+ * journal_t * jbd2_journal_init_inode () - creates a journal which maps to a inode.
* @inode: An inode to create the journal in
*
- * journal_init_inode creates a journal which maps an on-disk inode as
+ * jbd2_journal_init_inode creates a journal which maps an on-disk inode as
* the journal. The inode must exist already, must support bmap() and
* must have all data blocks preallocated.
*/
-journal_t * journal_init_inode (struct inode *inode)
+journal_t * jbd2_journal_init_inode (struct inode *inode)
{
struct buffer_head *bh;
journal_t *journal = journal_init_common();
+ char *p;
int err;
int n;
- unsigned long blocknr;
+ unsigned long long blocknr;
if (!journal)
return NULL;
journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev;
journal->j_inode = inode;
+ bdevname(journal->j_dev, journal->j_devname);
+ p = journal->j_devname;
+ while ((p = strchr(p, '/')))
+ *p = '!';
+ p = journal->j_devname + strlen(journal->j_devname);
+ sprintf(p, "-%lu", journal->j_inode->i_ino);
jbd_debug(1,
"journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n",
journal, inode->i_sb->s_id, inode->i_ino,
journal->j_maxlen = inode->i_size >> inode->i_sb->s_blocksize_bits;
journal->j_blocksize = inode->i_sb->s_blocksize;
+ jbd2_stats_proc_init(journal);
/* journal descriptor can store up to n blocks -bzzz */
n = journal->j_blocksize / sizeof(journal_block_tag_t);
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",
- __FUNCTION__);
- kfree(journal);
- return NULL;
+ __func__);
+ goto out_err;
}
- err = journal_bmap(journal, 0, &blocknr);
+ err = jbd2_journal_bmap(journal, 0, &blocknr);
/* If that failed, give up */
if (err) {
printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
- __FUNCTION__);
- kfree(journal);
- return NULL;
+ __func__);
+ goto out_err;
}
bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
- J_ASSERT(bh != NULL);
+ if (!bh) {
+ printk(KERN_ERR
+ "%s: Cannot get buffer for journal superblock\n",
+ __func__);
+ goto out_err;
+ }
journal->j_sb_buffer = bh;
journal->j_superblock = (journal_superblock_t *)bh->b_data;
return journal;
+out_err:
+ jbd2_stats_proc_exit(journal);
+ kfree(journal);
+ return NULL;
}
/*
static int journal_reset(journal_t *journal)
{
journal_superblock_t *sb = journal->j_superblock;
- unsigned long first, last;
+ unsigned long long first, last;
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",
+ first, last);
+ journal_fail_superblock(journal);
+ return -EINVAL;
+ }
journal->j_first = first;
journal->j_last = last;
journal->j_max_transaction_buffers = journal->j_maxlen / 4;
/* Add the dynamic fields and write it to disk. */
- journal_update_superblock(journal, 1);
- journal_start_thread(journal);
- return 0;
-}
-
-/**
- * int journal_create() - Initialise the new journal file
- * @journal: Journal to create. This structure must have been initialised
- *
- * Given a journal_t structure which tells us which disk blocks we can
- * use, create a new journal superblock and initialise all of the
- * journal fields from scratch.
- **/
-int journal_create(journal_t *journal)
-{
- unsigned long blocknr;
- struct buffer_head *bh;
- journal_superblock_t *sb;
- int i, err;
-
- if (journal->j_maxlen < JFS_MIN_JOURNAL_BLOCKS) {
- printk (KERN_ERR "Journal length (%d blocks) too short.\n",
- journal->j_maxlen);
- journal_fail_superblock(journal);
- return -EINVAL;
- }
-
- if (journal->j_inode == NULL) {
- /*
- * We don't know what block to start at!
- */
- printk(KERN_EMERG
- "%s: creation of journal on external device!\n",
- __FUNCTION__);
- BUG();
- }
-
- /* Zero out the entire journal on disk. We cannot afford to
- have any blocks on disk beginning with JFS_MAGIC_NUMBER. */
- jbd_debug(1, "JBD: Zeroing out journal blocks...\n");
- for (i = 0; i < journal->j_maxlen; i++) {
- err = journal_bmap(journal, i, &blocknr);
- if (err)
- return err;
- bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
- lock_buffer(bh);
- memset (bh->b_data, 0, journal->j_blocksize);
- BUFFER_TRACE(bh, "marking dirty");
- mark_buffer_dirty(bh);
- BUFFER_TRACE(bh, "marking uptodate");
- set_buffer_uptodate(bh);
- unlock_buffer(bh);
- __brelse(bh);
- }
-
- sync_blockdev(journal->j_dev);
- jbd_debug(1, "JBD: journal cleared.\n");
-
- /* OK, fill in the initial static fields in the new superblock */
- sb = journal->j_superblock;
-
- sb->s_header.h_magic = cpu_to_be32(JFS_MAGIC_NUMBER);
- sb->s_header.h_blocktype = cpu_to_be32(JFS_SUPERBLOCK_V2);
-
- sb->s_blocksize = cpu_to_be32(journal->j_blocksize);
- sb->s_maxlen = cpu_to_be32(journal->j_maxlen);
- sb->s_first = cpu_to_be32(1);
-
- journal->j_transaction_sequence = 1;
-
- journal->j_flags &= ~JFS_ABORT;
- journal->j_format_version = 2;
-
- return journal_reset(journal);
+ jbd2_journal_update_superblock(journal, 1);
+ return jbd2_journal_start_thread(journal);
}
/**
- * void journal_update_superblock() - Update journal sb on disk.
+ * 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 journal_update_superblock(journal_t *journal, int wait)
+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 JFS_FLUSHED. This avoids
+ * 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 ==
goto out;
}
+ if (buffer_write_io_error(bh)) {
+ /*
+ * Oh, dear. A previous attempt to write the journal
+ * superblock failed. This could happen because the
+ * USB device was yanked out. Or it could happen to
+ * be a transient write error and maybe the block will
+ * be remapped. Nothing we can do but to retry the
+ * write and hope for the best.
+ */
+ printk(KERN_ERR "JBD2: previous I/O error detected "
+ "for journal superblock update for %s.\n",
+ journal->j_devname);
+ clear_buffer_write_io_error(bh);
+ set_buffer_uptodate(bh);
+ }
+
spin_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);
BUFFER_TRACE(bh, "marking dirty");
mark_buffer_dirty(bh);
- if (wait)
+ if (wait) {
sync_dirty_buffer(bh);
- else
+ 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
ll_rw_block(SWRITE, 1, &bh);
out:
spin_lock(&journal->j_state_lock);
if (sb->s_start)
- journal->j_flags &= ~JFS_FLUSHED;
+ journal->j_flags &= ~JBD2_FLUSHED;
else
- journal->j_flags |= JFS_FLUSHED;
+ journal->j_flags |= JBD2_FLUSHED;
spin_unlock(&journal->j_state_lock);
}
err = -EINVAL;
- if (sb->s_header.h_magic != cpu_to_be32(JFS_MAGIC_NUMBER) ||
+ 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");
goto out;
}
switch(be32_to_cpu(sb->s_header.h_blocktype)) {
- case JFS_SUPERBLOCK_V1:
+ case JBD2_SUPERBLOCK_V1:
journal->j_format_version = 1;
break;
- case JFS_SUPERBLOCK_V2:
+ case JBD2_SUPERBLOCK_V2:
journal->j_format_version = 2;
break;
default:
/**
- * int journal_load() - Read journal from disk.
+ * int jbd2_journal_load() - Read journal from disk.
* @journal: Journal to act on.
*
* Given a journal_t structure which tells us which disk blocks contain
* a journal, read the journal from disk to initialise the in-memory
* structures.
*/
-int journal_load(journal_t *journal)
+int jbd2_journal_load(journal_t *journal)
{
int err;
journal_superblock_t *sb;
if (journal->j_format_version >= 2) {
if ((sb->s_feature_ro_compat &
- ~cpu_to_be32(JFS_KNOWN_ROCOMPAT_FEATURES)) ||
+ ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) ||
(sb->s_feature_incompat &
- ~cpu_to_be32(JFS_KNOWN_INCOMPAT_FEATURES))) {
+ ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) {
printk (KERN_WARNING
"JBD: Unrecognised features on journal\n");
return -EINVAL;
}
}
- /*
- * Create a slab for this blocksize
- */
- err = journal_create_jbd_slab(be32_to_cpu(sb->s_blocksize));
- if (err)
- return err;
-
/* Let the recovery code check whether it needs to recover any
* data from the journal. */
- if (journal_recover(journal))
+ if (jbd2_journal_recover(journal))
goto recovery_error;
/* OK, we've finished with the dynamic journal bits:
if (journal_reset(journal))
goto recovery_error;
- journal->j_flags &= ~JFS_ABORT;
- journal->j_flags |= JFS_LOADED;
+ journal->j_flags &= ~JBD2_ABORT;
+ journal->j_flags |= JBD2_LOADED;
return 0;
recovery_error:
}
/**
- * void journal_destroy() - Release a journal_t structure.
+ * void jbd2_journal_destroy() - Release a journal_t structure.
* @journal: Journal to act on.
*
* Release a journal_t structure once it is no longer in use by the
* journaled object.
+ * Return <0 if we couldn't clean up the journal.
*/
-void journal_destroy(journal_t *journal)
+int jbd2_journal_destroy(journal_t *journal)
{
+ int err = 0;
+
/* Wait for the commit thread to wake up and die. */
journal_kill_thread(journal);
/* Force a final log commit */
if (journal->j_running_transaction)
- journal_commit_transaction(journal);
+ jbd2_journal_commit_transaction(journal);
/* Force any old transactions to disk */
spin_lock(&journal->j_list_lock);
while (journal->j_checkpoint_transactions != NULL) {
spin_unlock(&journal->j_list_lock);
- log_do_checkpoint(journal);
+ mutex_lock(&journal->j_checkpoint_mutex);
+ jbd2_log_do_checkpoint(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
spin_lock(&journal->j_list_lock);
}
J_ASSERT(journal->j_checkpoint_transactions == NULL);
spin_unlock(&journal->j_list_lock);
- /* We can now mark the journal as empty. */
- journal->j_tail = 0;
- journal->j_tail_sequence = ++journal->j_transaction_sequence;
if (journal->j_sb_buffer) {
- journal_update_superblock(journal, 1);
+ 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 {
+ err = -EIO;
+ }
brelse(journal->j_sb_buffer);
}
+ if (journal->j_proc_entry)
+ jbd2_stats_proc_exit(journal);
if (journal->j_inode)
iput(journal->j_inode);
if (journal->j_revoke)
- journal_destroy_revoke(journal);
+ jbd2_journal_destroy_revoke(journal);
kfree(journal->j_wbuf);
kfree(journal);
+
+ return err;
}
/**
- *int journal_check_used_features () - Check if features specified are used.
+ *int jbd2_journal_check_used_features () - Check if features specified are used.
* @journal: Journal to check.
* @compat: bitmask of compatible features
* @ro: bitmask of features that force read-only mount
* features. Return true (non-zero) if it does.
**/
-int journal_check_used_features (journal_t *journal, unsigned long compat,
+int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat,
unsigned long ro, unsigned long incompat)
{
journal_superblock_t *sb;
}
/**
- * int journal_check_available_features() - Check feature set in journalling layer
+ * int jbd2_journal_check_available_features() - Check feature set in journalling layer
* @journal: Journal to check.
* @compat: bitmask of compatible features
* @ro: bitmask of features that force read-only mount
* all of a given set of features on this journal. Return true
* (non-zero) if it can. */
-int journal_check_available_features (journal_t *journal, unsigned long compat,
+int jbd2_journal_check_available_features (journal_t *journal, unsigned long compat,
unsigned long ro, unsigned long incompat)
{
journal_superblock_t *sb;
if (journal->j_format_version != 2)
return 0;
- if ((compat & JFS_KNOWN_COMPAT_FEATURES) == compat &&
- (ro & JFS_KNOWN_ROCOMPAT_FEATURES) == ro &&
- (incompat & JFS_KNOWN_INCOMPAT_FEATURES) == incompat)
+ if ((compat & JBD2_KNOWN_COMPAT_FEATURES) == compat &&
+ (ro & JBD2_KNOWN_ROCOMPAT_FEATURES) == ro &&
+ (incompat & JBD2_KNOWN_INCOMPAT_FEATURES) == incompat)
return 1;
return 0;
}
/**
- * int journal_set_features () - Mark a given journal feature in the superblock
+ * int jbd2_journal_set_features () - Mark a given journal feature in the superblock
* @journal: Journal to act on.
* @compat: bitmask of compatible features
* @ro: bitmask of features that force read-only mount
*
*/
-int journal_set_features (journal_t *journal, unsigned long compat,
+int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
unsigned long ro, unsigned long incompat)
{
journal_superblock_t *sb;
- if (journal_check_used_features(journal, compat, ro, incompat))
+ if (jbd2_journal_check_used_features(journal, compat, ro, incompat))
return 1;
- if (!journal_check_available_features(journal, compat, ro, incompat))
+ if (!jbd2_journal_check_available_features(journal, compat, ro, incompat))
return 0;
jbd_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n",
return 1;
}
+/*
+ * jbd2_journal_clear_features () - Clear a given journal feature in the
+ * superblock
+ * @journal: Journal to act on.
+ * @compat: bitmask of compatible features
+ * @ro: bitmask of features that force read-only mount
+ * @incompat: bitmask of incompatible features
+ *
+ * Clear a given journal feature as present on the
+ * superblock.
+ */
+void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
+ unsigned long ro, unsigned long incompat)
+{
+ journal_superblock_t *sb;
+
+ jbd_debug(1, "Clear features 0x%lx/0x%lx/0x%lx\n",
+ compat, ro, incompat);
+
+ sb = journal->j_superblock;
+
+ sb->s_feature_compat &= ~cpu_to_be32(compat);
+ sb->s_feature_ro_compat &= ~cpu_to_be32(ro);
+ sb->s_feature_incompat &= ~cpu_to_be32(incompat);
+}
+EXPORT_SYMBOL(jbd2_journal_clear_features);
/**
- * int journal_update_format () - Update on-disk journal structure.
+ * 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 journal_update_format (journal_t *journal)
+int jbd2_journal_update_format (journal_t *journal)
{
journal_superblock_t *sb;
int err;
sb = journal->j_superblock;
switch (be32_to_cpu(sb->s_header.h_blocktype)) {
- case JFS_SUPERBLOCK_V2:
+ case JBD2_SUPERBLOCK_V2:
return 0;
- case JFS_SUPERBLOCK_V1:
+ case JBD2_SUPERBLOCK_V1:
return journal_convert_superblock_v1(journal, sb);
default:
break;
memset(&sb->s_feature_compat, 0, blocksize-offset);
sb->s_nr_users = cpu_to_be32(1);
- sb->s_header.h_blocktype = cpu_to_be32(JFS_SUPERBLOCK_V2);
+ sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2);
journal->j_format_version = 2;
bh = journal->j_sb_buffer;
/**
- * int journal_flush () - Flush journal
+ * int jbd2_journal_flush () - Flush journal
* @journal: Journal to act on.
*
* Flush all data for a given journal to disk and empty the journal.
* recovery does not need to happen on remount.
*/
-int journal_flush(journal_t *journal)
+int jbd2_journal_flush(journal_t *journal)
{
int err = 0;
transaction_t *transaction = NULL;
/* Force everything buffered to the log... */
if (journal->j_running_transaction) {
transaction = journal->j_running_transaction;
- __log_start_commit(journal, transaction->t_tid);
+ __jbd2_log_start_commit(journal, transaction->t_tid);
} else if (journal->j_committing_transaction)
transaction = journal->j_committing_transaction;
tid_t tid = transaction->t_tid;
spin_unlock(&journal->j_state_lock);
- log_wait_commit(journal, tid);
+ jbd2_log_wait_commit(journal, tid);
} else {
spin_unlock(&journal->j_state_lock);
}
spin_lock(&journal->j_list_lock);
while (!err && journal->j_checkpoint_transactions != NULL) {
spin_unlock(&journal->j_list_lock);
- err = log_do_checkpoint(journal);
+ mutex_lock(&journal->j_checkpoint_mutex);
+ err = jbd2_log_do_checkpoint(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
spin_lock(&journal->j_list_lock);
}
spin_unlock(&journal->j_list_lock);
- cleanup_journal_tail(journal);
+
+ if (is_journal_aborted(journal))
+ return -EIO;
+
+ jbd2_cleanup_journal_tail(journal);
/* Finally, mark the journal as really needing no recovery.
* This sets s_start==0 in the underlying superblock, which is
old_tail = journal->j_tail;
journal->j_tail = 0;
spin_unlock(&journal->j_state_lock);
- journal_update_superblock(journal, 1);
+ jbd2_journal_update_superblock(journal, 1);
spin_lock(&journal->j_state_lock);
journal->j_tail = old_tail;
J_ASSERT(journal->j_head == journal->j_tail);
J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence);
spin_unlock(&journal->j_state_lock);
- return err;
+ return 0;
}
/**
- * int journal_wipe() - Wipe journal contents
+ * int jbd2_journal_wipe() - Wipe journal contents
* @journal: Journal to act on.
* @write: flag (see below)
*
* Wipe out all of the contents of a journal, safely. This will produce
* a warning if the journal contains any valid recovery information.
- * Must be called between journal_init_*() and journal_load().
+ * Must be called between journal_init_*() and jbd2_journal_load().
*
* If 'write' is non-zero, then we wipe out the journal on disk; otherwise
* we merely suppress recovery.
*/
-int journal_wipe(journal_t *journal, int write)
+int jbd2_journal_wipe(journal_t *journal, int write)
{
journal_superblock_t *sb;
int err = 0;
- J_ASSERT (!(journal->j_flags & JFS_LOADED));
+ J_ASSERT (!(journal->j_flags & JBD2_LOADED));
err = load_superblock(journal);
if (err)
printk (KERN_WARNING "JBD: %s recovery information on journal\n",
write ? "Clearing" : "Ignoring");
- err = journal_skip_recovery(journal);
+ err = jbd2_journal_skip_recovery(journal);
if (write)
- journal_update_superblock(journal, 1);
+ jbd2_journal_update_superblock(journal, 1);
no_recovery:
return err;
}
/*
- * journal_dev_name: format a character string to describe on what
- * device this journal is present.
- */
-
-static const char *journal_dev_name(journal_t *journal, char *buffer)
-{
- struct block_device *bdev;
-
- if (journal->j_inode)
- bdev = journal->j_inode->i_sb->s_bdev;
- else
- bdev = journal->j_dev;
-
- return bdevname(bdev, buffer);
-}
-
-/*
* Journal abort has very specific semantics, which we describe
* for journal abort.
*
- * Two internal function, which provide abort to te jbd layer
+ * Two internal functions, which provide abort to the jbd layer
* itself are here.
*/
* Aborts hard --- we mark the abort as occurred, but do _nothing_ else,
* and don't attempt to make any other journal updates.
*/
-void __journal_abort_hard(journal_t *journal)
+void __jbd2_journal_abort_hard(journal_t *journal)
{
transaction_t *transaction;
- char b[BDEVNAME_SIZE];
- if (journal->j_flags & JFS_ABORT)
+ if (journal->j_flags & JBD2_ABORT)
return;
printk(KERN_ERR "Aborting journal on device %s.\n",
- journal_dev_name(journal, b));
+ journal->j_devname);
spin_lock(&journal->j_state_lock);
- journal->j_flags |= JFS_ABORT;
+ journal->j_flags |= JBD2_ABORT;
transaction = journal->j_running_transaction;
if (transaction)
- __log_start_commit(journal, transaction->t_tid);
+ __jbd2_log_start_commit(journal, transaction->t_tid);
spin_unlock(&journal->j_state_lock);
}
* but don't do any other IO. */
static void __journal_abort_soft (journal_t *journal, int errno)
{
- if (journal->j_flags & JFS_ABORT)
+ if (journal->j_flags & JBD2_ABORT)
return;
if (!journal->j_errno)
journal->j_errno = errno;
- __journal_abort_hard(journal);
+ __jbd2_journal_abort_hard(journal);
if (errno)
- journal_update_superblock(journal, 1);
+ jbd2_journal_update_superblock(journal, 1);
}
/**
- * void journal_abort () - Shutdown the journal immediately.
+ * void jbd2_journal_abort () - Shutdown the journal immediately.
* @journal: the journal to shutdown.
* @errno: an error number to record in the journal indicating
* the reason for the shutdown.
* journal (not of a single transaction). This operation cannot be
* undone without closing and reopening the journal.
*
- * The journal_abort function is intended to support higher level error
+ * The jbd2_journal_abort function is intended to support higher level error
* recovery mechanisms such as the ext2/ext3 remount-readonly error
* mode.
*
*
* Any attempt to get a new transaction handle on a journal which is in
* ABORT state will just result in an -EROFS error return. A
- * journal_stop on an existing handle will return -EIO if we have
+ * jbd2_journal_stop on an existing handle will return -EIO if we have
* entered abort state during the update.
*
* Recursive transactions are not disturbed by journal abort until the
- * final journal_stop, which will receive the -EIO error.
+ * final jbd2_journal_stop, which will receive the -EIO error.
*
- * Finally, the journal_abort call allows the caller to supply an errno
+ * Finally, the jbd2_journal_abort call allows the caller to supply an errno
* which will be recorded (if possible) in the journal superblock. This
* allows a client to record failure conditions in the middle of a
* transaction without having to complete the transaction to record the
*
*/
-void journal_abort(journal_t *journal, int errno)
+void jbd2_journal_abort(journal_t *journal, int errno)
{
__journal_abort_soft(journal, errno);
}
/**
- * int journal_errno () - returns the journal's error state.
+ * int jbd2_journal_errno () - returns the journal's error state.
* @journal: journal to examine.
*
- * This is the errno numbet set with journal_abort(), the last
+ * This is the errno number set with jbd2_journal_abort(), the last
* time the journal was mounted - if the journal was stopped
* without calling abort this will be 0.
*
* If the journal has been aborted on this mount time -EROFS will
* be returned.
*/
-int journal_errno(journal_t *journal)
+int jbd2_journal_errno(journal_t *journal)
{
int err;
spin_lock(&journal->j_state_lock);
- if (journal->j_flags & JFS_ABORT)
+ if (journal->j_flags & JBD2_ABORT)
err = -EROFS;
else
err = journal->j_errno;
}
/**
- * int journal_clear_err () - clears the journal's error state
+ * int jbd2_journal_clear_err () - clears the journal's error state
* @journal: journal to act on.
*
- * An error must be cleared or Acked to take a FS out of readonly
+ * An error must be cleared or acked to take a FS out of readonly
* mode.
*/
-int journal_clear_err(journal_t *journal)
+int jbd2_journal_clear_err(journal_t *journal)
{
int err = 0;
spin_lock(&journal->j_state_lock);
- if (journal->j_flags & JFS_ABORT)
+ if (journal->j_flags & JBD2_ABORT)
err = -EROFS;
else
journal->j_errno = 0;
}
/**
- * void journal_ack_err() - Ack journal err.
+ * void jbd2_journal_ack_err() - Ack journal err.
* @journal: journal to act on.
*
- * An error must be cleared or Acked to take a FS out of readonly
+ * An error must be cleared or acked to take a FS out of readonly
* mode.
*/
-void journal_ack_err(journal_t *journal)
+void jbd2_journal_ack_err(journal_t *journal)
{
spin_lock(&journal->j_state_lock);
if (journal->j_errno)
- journal->j_flags |= JFS_ACK_ERR;
+ journal->j_flags |= JBD2_ACK_ERR;
spin_unlock(&journal->j_state_lock);
}
-int journal_blocks_per_page(struct inode *inode)
+int jbd2_journal_blocks_per_page(struct inode *inode)
{
return 1 << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
}
/*
- * Simple support for retrying memory allocations. Introduced to help to
- * debug different VM deadlock avoidance strategies.
+ * helper functions to deal with 32 or 64bit block numbers.
*/
-void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry)
+size_t journal_tag_bytes(journal_t *journal)
{
- return kmalloc(size, flags | (retry ? __GFP_NOFAIL : 0));
-}
-
-/*
- * jbd slab management: create 1k, 2k, 4k, 8k slabs as needed
- * and allocate frozen and commit buffers from these slabs.
- *
- * Reason for doing this is to avoid, SLAB_DEBUG - since it could
- * cause bh to cross page boundary.
- */
-
-#define JBD_MAX_SLABS 5
-#define JBD_SLAB_INDEX(size) (size >> 11)
-
-static kmem_cache_t *jbd_slab[JBD_MAX_SLABS];
-static const char *jbd_slab_names[JBD_MAX_SLABS] = {
- "jbd_1k", "jbd_2k", "jbd_4k", NULL, "jbd_8k"
-};
-
-static void journal_destroy_jbd_slabs(void)
-{
- int i;
-
- for (i = 0; i < JBD_MAX_SLABS; i++) {
- if (jbd_slab[i])
- kmem_cache_destroy(jbd_slab[i]);
- jbd_slab[i] = NULL;
- }
-}
-
-static int journal_create_jbd_slab(size_t slab_size)
-{
- int i = JBD_SLAB_INDEX(slab_size);
-
- BUG_ON(i >= JBD_MAX_SLABS);
-
- /*
- * Check if we already have a slab created for this size
- */
- if (jbd_slab[i])
- return 0;
-
- /*
- * Create a slab and force alignment to be same as slabsize -
- * this will make sure that allocations won't cross the page
- * boundary.
- */
- jbd_slab[i] = kmem_cache_create(jbd_slab_names[i],
- slab_size, slab_size, 0, NULL, NULL);
- if (!jbd_slab[i]) {
- printk(KERN_EMERG "JBD: no memory for jbd_slab cache\n");
- return -ENOMEM;
- }
- return 0;
-}
-
-void * jbd_slab_alloc(size_t size, gfp_t flags)
-{
- int idx;
-
- idx = JBD_SLAB_INDEX(size);
- BUG_ON(jbd_slab[idx] == NULL);
- return kmem_cache_alloc(jbd_slab[idx], flags | __GFP_NOFAIL);
-}
-
-void jbd_slab_free(void *ptr, size_t size)
-{
- int idx;
-
- idx = JBD_SLAB_INDEX(size);
- BUG_ON(jbd_slab[idx] == NULL);
- kmem_cache_free(jbd_slab[idx], ptr);
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
+ return JBD2_TAG_SIZE64;
+ else
+ return JBD2_TAG_SIZE32;
}
/*
* Journal_head storage management
*/
-static kmem_cache_t *journal_head_cache;
-#ifdef CONFIG_JBD_DEBUG
+static struct kmem_cache *jbd2_journal_head_cache;
+#ifdef CONFIG_JBD2_DEBUG
static atomic_t nr_journal_heads = ATOMIC_INIT(0);
#endif
-static int journal_init_journal_head_cache(void)
+static int journal_init_jbd2_journal_head_cache(void)
{
int retval;
- J_ASSERT(journal_head_cache == 0);
- journal_head_cache = kmem_cache_create("journal_head",
+ J_ASSERT(jbd2_journal_head_cache == NULL);
+ jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head",
sizeof(struct journal_head),
0, /* offset */
- 0, /* flags */
- NULL, /* ctor */
- NULL); /* dtor */
+ SLAB_TEMPORARY, /* flags */
+ NULL); /* ctor */
retval = 0;
- if (journal_head_cache == 0) {
+ if (!jbd2_journal_head_cache) {
retval = -ENOMEM;
printk(KERN_EMERG "JBD: no memory for journal_head cache\n");
}
return retval;
}
-static void journal_destroy_journal_head_cache(void)
+static void jbd2_journal_destroy_jbd2_journal_head_cache(void)
{
- J_ASSERT(journal_head_cache != NULL);
- kmem_cache_destroy(journal_head_cache);
- journal_head_cache = NULL;
+ if (jbd2_journal_head_cache) {
+ kmem_cache_destroy(jbd2_journal_head_cache);
+ jbd2_journal_head_cache = NULL;
+ }
}
/*
struct journal_head *ret;
static unsigned long last_warning;
-#ifdef CONFIG_JBD_DEBUG
+#ifdef CONFIG_JBD2_DEBUG
atomic_inc(&nr_journal_heads);
#endif
- ret = kmem_cache_alloc(journal_head_cache, GFP_NOFS);
- if (ret == 0) {
+ 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",
- __FUNCTION__);
+ __func__);
last_warning = jiffies;
}
- while (ret == 0) {
+ while (!ret) {
yield();
- ret = kmem_cache_alloc(journal_head_cache, GFP_NOFS);
+ ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS);
}
}
return ret;
static void journal_free_journal_head(struct journal_head *jh)
{
-#ifdef CONFIG_JBD_DEBUG
+#ifdef CONFIG_JBD2_DEBUG
atomic_dec(&nr_journal_heads);
- memset(jh, JBD_POISON_FREE, sizeof(*jh));
+ memset(jh, JBD2_POISON_FREE, sizeof(*jh));
#endif
- kmem_cache_free(journal_head_cache, jh);
+ kmem_cache_free(jbd2_journal_head_cache, jh);
}
/*
*
* 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
+ * Various places in JBD call jbd2_journal_remove_journal_head() to indicate that the
* journal_head can be dropped if needed.
*
* 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
- * journal_head in this situation, journal_add_journal_head elevates the
+ * journal_head in this situation, jbd2_journal_add_journal_head elevates the
* journal_head's b_jcount refcount by one. The caller must call
- * journal_put_journal_head() to undo this.
+ * jbd2_journal_put_journal_head() to undo this.
*
* So the typical usage would be:
*
* (Attach a journal_head if needed. Increments b_jcount)
- * struct journal_head *jh = journal_add_journal_head(bh);
+ * struct journal_head *jh = jbd2_journal_add_journal_head(bh);
* ...
* jh->b_transaction = xxx;
- * journal_put_journal_head(jh);
+ * 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.
* Doesn't need the journal lock.
* May sleep.
*/
-struct journal_head *journal_add_journal_head(struct buffer_head *bh)
+struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh)
{
struct journal_head *jh;
struct journal_head *new_jh = NULL;
* Grab a ref against this buffer_head's journal_head. If it ended up not
* having a journal_head, return NULL
*/
-struct journal_head *journal_grab_journal_head(struct buffer_head *bh)
+struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh)
{
struct journal_head *jh = NULL;
if (jh->b_frozen_data) {
printk(KERN_WARNING "%s: freeing "
"b_frozen_data\n",
- __FUNCTION__);
- jbd_slab_free(jh->b_frozen_data, bh->b_size);
+ __func__);
+ jbd2_free(jh->b_frozen_data, bh->b_size);
}
if (jh->b_committed_data) {
printk(KERN_WARNING "%s: freeing "
"b_committed_data\n",
- __FUNCTION__);
- jbd_slab_free(jh->b_committed_data, bh->b_size);
+ __func__);
+ jbd2_free(jh->b_committed_data, bh->b_size);
}
bh->b_private = NULL;
jh->b_bh = NULL; /* debug, really */
}
/*
- * journal_remove_journal_head(): if the buffer isn't attached to a transaction
+ * 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 journal_remove_journal_head() *must* run __brelse(bh) at some
+ * 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 journal_remove_journal_head(struct buffer_head *bh)
+void jbd2_journal_remove_journal_head(struct buffer_head *bh)
{
jbd_lock_bh_journal_head(bh);
__journal_remove_journal_head(bh);
* Drop a reference on the passed journal_head. If it fell to zero then try to
* release the journal_head from the buffer_head.
*/
-void journal_put_journal_head(struct journal_head *jh)
+void jbd2_journal_put_journal_head(struct journal_head *jh)
{
struct buffer_head *bh = jh2bh(jh);
}
/*
- * /proc tunables
+ * Initialize jbd inode head
*/
-#if defined(CONFIG_JBD_DEBUG)
-int journal_enable_debug;
-EXPORT_SYMBOL(journal_enable_debug);
-#endif
+void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode)
+{
+ jinode->i_transaction = NULL;
+ jinode->i_next_transaction = NULL;
+ jinode->i_vfs_inode = inode;
+ jinode->i_flags = 0;
+ INIT_LIST_HEAD(&jinode->i_list);
+}
+
+/*
+ * Function to be called before we start removing inode from memory (i.e.,
+ * clear_inode() is a fine place to be called from). It removes inode from
+ * transaction's lists.
+ */
+void jbd2_journal_release_jbd_inode(journal_t *journal,
+ struct jbd2_inode *jinode)
+{
+ int writeout = 0;
+
+ if (!journal)
+ return;
+restart:
+ spin_lock(&journal->j_list_lock);
+ /* Is commit writing out inode - we have to wait */
+ if (jinode->i_flags & JI_COMMIT_RUNNING) {
+ wait_queue_head_t *wq;
+ DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING);
+ wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING);
+ prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+ spin_unlock(&journal->j_list_lock);
+ schedule();
+ finish_wait(wq, &wait.wait);
+ goto restart;
+ }
-#if defined(CONFIG_JBD_DEBUG) && defined(CONFIG_PROC_FS)
+ /* Do we need to wait for data writeback? */
+ if (journal->j_committing_transaction == jinode->i_transaction)
+ writeout = 1;
+ if (jinode->i_transaction) {
+ list_del(&jinode->i_list);
+ jinode->i_transaction = NULL;
+ }
+ spin_unlock(&journal->j_list_lock);
+}
-static struct proc_dir_entry *proc_jbd_debug;
+/*
+ * debugfs tunables
+ */
+#ifdef CONFIG_JBD2_DEBUG
+u8 jbd2_journal_enable_debug __read_mostly;
+EXPORT_SYMBOL(jbd2_journal_enable_debug);
-static int read_jbd_debug(char *page, char **start, off_t off,
- int count, int *eof, void *data)
+#define JBD2_DEBUG_NAME "jbd2-debug"
+
+static struct dentry *jbd2_debugfs_dir;
+static struct dentry *jbd2_debug;
+
+static void __init jbd2_create_debugfs_entry(void)
{
- int ret;
+ jbd2_debugfs_dir = debugfs_create_dir("jbd2", NULL);
+ if (jbd2_debugfs_dir)
+ jbd2_debug = debugfs_create_u8(JBD2_DEBUG_NAME, S_IRUGO,
+ jbd2_debugfs_dir,
+ &jbd2_journal_enable_debug);
+}
- ret = sprintf(page + off, "%d\n", journal_enable_debug);
- *eof = 1;
- return ret;
+static void __exit jbd2_remove_debugfs_entry(void)
+{
+ debugfs_remove(jbd2_debug);
+ debugfs_remove(jbd2_debugfs_dir);
}
-static int write_jbd_debug(struct file *file, const char __user *buffer,
- unsigned long count, void *data)
+#else
+
+static void __init jbd2_create_debugfs_entry(void)
{
- char buf[32];
+}
- if (count > ARRAY_SIZE(buf) - 1)
- count = ARRAY_SIZE(buf) - 1;
- if (copy_from_user(buf, buffer, count))
- return -EFAULT;
- buf[ARRAY_SIZE(buf) - 1] = '\0';
- journal_enable_debug = simple_strtoul(buf, NULL, 10);
- return count;
+static void __exit jbd2_remove_debugfs_entry(void)
+{
}
-#define JBD_PROC_NAME "sys/fs/jbd-debug"
+#endif
+
+#ifdef CONFIG_PROC_FS
-static void __init create_jbd_proc_entry(void)
+#define JBD2_STATS_PROC_NAME "fs/jbd2"
+
+static void __init jbd2_create_jbd_stats_proc_entry(void)
{
- proc_jbd_debug = create_proc_entry(JBD_PROC_NAME, 0644, NULL);
- if (proc_jbd_debug) {
- /* Why is this so hard? */
- proc_jbd_debug->read_proc = read_jbd_debug;
- proc_jbd_debug->write_proc = write_jbd_debug;
- }
+ proc_jbd2_stats = proc_mkdir(JBD2_STATS_PROC_NAME, NULL);
}
-static void __exit remove_jbd_proc_entry(void)
+static void __exit jbd2_remove_jbd_stats_proc_entry(void)
{
- if (proc_jbd_debug)
- remove_proc_entry(JBD_PROC_NAME, NULL);
+ if (proc_jbd2_stats)
+ remove_proc_entry(JBD2_STATS_PROC_NAME, NULL);
}
#else
-#define create_jbd_proc_entry() do {} while (0)
-#define remove_jbd_proc_entry() do {} while (0)
+#define jbd2_create_jbd_stats_proc_entry() do {} while (0)
+#define jbd2_remove_jbd_stats_proc_entry() do {} while (0)
#endif
-kmem_cache_t *jbd_handle_cache;
+struct kmem_cache *jbd2_handle_cache;
static int __init journal_init_handle_cache(void)
{
- jbd_handle_cache = kmem_cache_create("journal_handle",
+ jbd2_handle_cache = kmem_cache_create("jbd2_journal_handle",
sizeof(handle_t),
0, /* offset */
- 0, /* flags */
- NULL, /* ctor */
- NULL); /* dtor */
- if (jbd_handle_cache == NULL) {
+ SLAB_TEMPORARY, /* flags */
+ NULL); /* ctor */
+ if (jbd2_handle_cache == NULL) {
printk(KERN_EMERG "JBD: failed to create handle cache\n");
return -ENOMEM;
}
return 0;
}
-static void journal_destroy_handle_cache(void)
+static void jbd2_journal_destroy_handle_cache(void)
{
- if (jbd_handle_cache)
- kmem_cache_destroy(jbd_handle_cache);
+ if (jbd2_handle_cache)
+ kmem_cache_destroy(jbd2_handle_cache);
}
/*
{
int ret;
- ret = journal_init_revoke_caches();
+ ret = jbd2_journal_init_revoke_caches();
if (ret == 0)
- ret = journal_init_journal_head_cache();
+ ret = journal_init_jbd2_journal_head_cache();
if (ret == 0)
ret = journal_init_handle_cache();
return ret;
}
-static void journal_destroy_caches(void)
+static void jbd2_journal_destroy_caches(void)
{
- journal_destroy_revoke_caches();
- journal_destroy_journal_head_cache();
- journal_destroy_handle_cache();
- journal_destroy_jbd_slabs();
+ jbd2_journal_destroy_revoke_caches();
+ jbd2_journal_destroy_jbd2_journal_head_cache();
+ jbd2_journal_destroy_handle_cache();
}
static int __init journal_init(void)
BUILD_BUG_ON(sizeof(struct journal_superblock_s) != 1024);
ret = journal_init_caches();
- if (ret != 0)
- journal_destroy_caches();
- create_jbd_proc_entry();
+ if (ret == 0) {
+ jbd2_create_debugfs_entry();
+ jbd2_create_jbd_stats_proc_entry();
+ } else {
+ jbd2_journal_destroy_caches();
+ }
return ret;
}
static void __exit journal_exit(void)
{
-#ifdef CONFIG_JBD_DEBUG
+#ifdef CONFIG_JBD2_DEBUG
int n = atomic_read(&nr_journal_heads);
if (n)
printk(KERN_EMERG "JBD: leaked %d journal_heads!\n", n);
#endif
- remove_jbd_proc_entry();
- journal_destroy_caches();
+ 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);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff