jbd2: Avoid possible NULL dereference in jbd2_journal_begin_ordered_truncate()

If we race with commit code setting i_transaction to NULL, we could
possibly dereference it.  Proper locking requires the journal pointer
(to access journal->j_list_lock), which we don't have.  So we have to
change the prototype of the function so that filesystem passes us the
journal pointer.  Also add a more detailed comment about why the
function jbd2_journal_begin_ordered_truncate() does what it does and
how it should be used.

Thanks to Dan Carpenter <error27@gmail.com> for pointing to the
suspitious code.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Acked-by: Joel Becker <joel.becker@oracle.com>
CC: linux-ext4@vger.kernel.org
CC: ocfs2-devel@oss.oracle.com
CC: mfasheh@suse.de
CC: Dan Carpenter <error27@gmail.com>

4 files changed, 41 insertions, 16 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 03ba20be1329..658c4a7f2578 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -47,8 +47,10 @@
 static inline int ext4_begin_ordered_truncate(struct inode *inode,
 					      loff_t new_size)
 {
-	return jbd2_journal_begin_ordered_truncate(&EXT4_I(inode)->jinode,
-						   new_size);
+	return jbd2_journal_begin_ordered_truncate(
+					EXT4_SB(inode->i_sb)->s_journal,
+					&EXT4_I(inode)->jinode,
+					new_size);
 }
 
 static void ext4_invalidatepage(struct page *page, unsigned long offset);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 46b4e347ed7d..28ce21d8598e 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2129,26 +2129,46 @@ done:
 }
 
 /*
- * This function must be called when inode is journaled in ordered mode
- * before truncation happens. It starts writeout of truncated part in
- * case it is in the committing transaction so that we stand to ordered
- * mode consistency guarantees.
+ * File truncate and transaction commit interact with each other in a
+ * non-trivial way.  If a transaction writing data block A is
+ * committing, we cannot discard the data by truncate until we have
+ * written them.  Otherwise if we crashed after the transaction with
+ * write has committed but before the transaction with truncate has
+ * committed, we could see stale data in block A.  This function is a
+ * helper to solve this problem.  It starts writeout of the truncated
+ * part in case it is in the committing transaction.
+ *
+ * Filesystem code must call this function when inode is journaled in
+ * ordered mode before truncation happens and after the inode has been
+ * placed on orphan list with the new inode size. The second condition
+ * avoids the race that someone writes new data and we start
+ * committing the transaction after this function has been called but
+ * before a transaction for truncate is started (and furthermore it
+ * allows us to optimize the case where the addition to orphan list
+ * happens in the same transaction as write --- we don't have to write
+ * any data in such case).
  */
-int jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode,
+int jbd2_journal_begin_ordered_truncate(journal_t *journal,
+					struct jbd2_inode *jinode,
 					loff_t new_size)
 {
-	journal_t *journal;
-	transaction_t *commit_trans;
+	transaction_t *inode_trans, *commit_trans;
 	int ret = 0;
 
-	if (!inode->i_transaction && !inode->i_next_transaction)
+	/* This is a quick check to avoid locking if not necessary */
+	if (!jinode->i_transaction)
 		goto out;
-	journal = inode->i_transaction->t_journal;
+	/* Locks are here just to force reading of recent values, it is
+	 * enough that the transaction was not committing before we started
+	 * a transaction adding the inode to orphan list */
 	spin_lock(&journal->j_state_lock);
 	commit_trans = journal->j_committing_transaction;
 	spin_unlock(&journal->j_state_lock);
-	if (inode->i_transaction == commit_trans) {
-		ret = filemap_fdatawrite_range(inode->i_vfs_inode->i_mapping,
+	spin_lock(&journal->j_list_lock);
+	inode_trans = jinode->i_transaction;
+	spin_unlock(&journal->j_list_lock);
+	if (inode_trans == commit_trans) {
+		ret = filemap_fdatawrite_range(jinode->i_vfs_inode->i_mapping,
 			new_size, LLONG_MAX);
 		if (ret)
 			jbd2_journal_abort(journal, ret);
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 3c3532e1307c..172850a9a12a 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -513,8 +513,10 @@ static inline int ocfs2_jbd2_file_inode(handle_t *handle, struct inode *inode)
 static inline int ocfs2_begin_ordered_truncate(struct inode *inode,
 					       loff_t new_size)
 {
-	return jbd2_journal_begin_ordered_truncate(&OCFS2_I(inode)->ip_jinode,
-						   new_size);
+	return jbd2_journal_begin_ordered_truncate(
+				OCFS2_SB(inode->i_sb)->journal->j_journal,
+				&OCFS2_I(inode)->ip_jinode,
+				new_size);
 }
 
 #endif /* OCFS2_JOURNAL_H */
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index b28b37eb11c6..4d248b3f1323 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1150,7 +1150,8 @@ extern int	   jbd2_journal_clear_err  (journal_t *);
 extern int	   jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
 extern int	   jbd2_journal_force_commit(journal_t *);
 extern int	   jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode);
-extern int	   jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode, loff_t new_size);
+extern int	   jbd2_journal_begin_ordered_truncate(journal_t *journal,
+				struct jbd2_inode *inode, loff_t new_size);
 extern void	   jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);
 extern void	   jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode);