1 files changed, 67 insertions, 9 deletions

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 9e4686900f18..9a7826990304 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -473,14 +473,18 @@ int __jbd2_log_space_left(journal_t *journal)
 }
 
 /*
- * 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 wakeup the
 		 * commit thread.  We do _not_ do the commit ourselves.
@@ -492,7 +496,15 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target)
 			  journal->j_commit_sequence);
 		wake_up(&journal->j_wait_commit);
 		return 1;
-	}
+	} else if (!tid_geq(journal->j_commit_request, target))
+		/* This should never happen, but if it does, preserve
+		   the evidence before kjournald goes into a loop and
+		   increments j_commit_sequence beyond all recognition. */
+		WARN_ONCE(1, "jbd: bad log_start_commit: %u %u %u %u\n",
+			  journal->j_commit_request,
+			  journal->j_commit_sequence,
+			  target, journal->j_running_transaction ? 
+			  journal->j_running_transaction->t_tid : 0);
 	return 0;
 }
 
@@ -520,11 +532,13 @@ int jbd2_journal_force_commit_nested(journal_t *journal)
 {
 	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;
 
@@ -535,6 +549,8 @@ int jbd2_journal_force_commit_nested(journal_t *journal)
 
 	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;
 }
@@ -572,6 +588,47 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
 }
 
 /*
+ * 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.
  */
@@ -912,7 +969,7 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
 	journal->j_wbufsize = n;
 	journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
 	if (!journal->j_wbuf) {
-		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
+		printk(KERN_ERR "%s: Can't allocate bhs for commit thread\n",
 			__func__);
 		goto out_err;
 	}
@@ -978,7 +1035,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 	journal->j_wbufsize = n;
 	journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
 	if (!journal->j_wbuf) {
-		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
+		printk(KERN_ERR "%s: Can't allocate bhs for commit thread\n",
 			__func__);
 		goto out_err;
 	}
@@ -986,7 +1043,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 	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;
 	}
@@ -2408,10 +2465,12 @@ const char *jbd2_dev_to_name(dev_t device)
 	new_dev = kmalloc(sizeof(struct devname_cache), GFP_KERNEL);
 	if (!new_dev)
 		return "NODEV-ALLOCFAILURE"; /* Something non-NULL */
+	bd = bdget(device);
 	spin_lock(&devname_cache_lock);
 	if (devcache[i]) {
 		if (devcache[i]->device == device) {
 			kfree(new_dev);
+			bdput(bd);
 			ret = devcache[i]->devname;
 			spin_unlock(&devname_cache_lock);
 			return ret;
@@ -2420,7 +2479,6 @@ const char *jbd2_dev_to_name(dev_t device)
 	}
 	devcache[i] = new_dev;
 	devcache[i]->device = device;
-	bd = bdget(device);
 	if (bd) {
 		bdevname(bd, devcache[i]->devname);
 		bdput(bd);