Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel...

[linux-2.6-block.git] / fs / jbd2 / transaction.c

diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 46b4e347ed7d9f3949df7b2b475bda7d7f2b8fef..28ce21d8598e11f16182a973d31d7e8bef83c145 100644 (file)
--- 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);