1 files changed, 86 insertions, 5 deletions

diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 2c9e8f5d13aa..7665e01c2dcf 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -609,6 +609,12 @@ repeat:
 		goto done;
 
 	/*
+	 * this is the first time this transaction is touching this buffer,
+	 * reset the modified flag
+	 */
+	jh->b_modified = 0;
+
+	/*
 	 * If there is already a copy-out version of this buffer, then we don't
 	 * need to make another one
 	 */
@@ -820,9 +826,16 @@ int journal_get_create_access(handle_t *handle, struct buffer_head *bh)
 
 	if (jh->b_transaction == NULL) {
 		jh->b_transaction = transaction;
+
+		/* first access by this transaction */
+		jh->b_modified = 0;
+
 		JBUFFER_TRACE(jh, "file as BJ_Reserved");
 		__journal_file_buffer(jh, transaction, BJ_Reserved);
 	} else if (jh->b_transaction == journal->j_committing_transaction) {
+		/* first access by this transaction */
+		jh->b_modified = 0;
+
 		JBUFFER_TRACE(jh, "set next transaction");
 		jh->b_next_transaction = transaction;
 	}
@@ -1222,6 +1235,7 @@ int journal_forget (handle_t *handle, struct buffer_head *bh)
 	struct journal_head *jh;
 	int drop_reserve = 0;
 	int err = 0;
+	int was_modified = 0;
 
 	BUFFER_TRACE(bh, "entry");
 
@@ -1240,6 +1254,9 @@ int journal_forget (handle_t *handle, struct buffer_head *bh)
 		goto not_jbd;
 	}
 
+	/* keep track of wether or not this transaction modified us */
+	was_modified = jh->b_modified;
+
 	/*
 	 * The buffer's going from the transaction, we must drop
 	 * all references -bzzz
@@ -1257,7 +1274,12 @@ int journal_forget (handle_t *handle, struct buffer_head *bh)
 
 		JBUFFER_TRACE(jh, "belongs to current transaction: unfile");
 
-		drop_reserve = 1;
+		/*
+		 * we only want to drop a reference if this transaction
+		 * modified the buffer
+		 */
+		if (was_modified)
+			drop_reserve = 1;
 
 		/*
 		 * We are no longer going to journal this buffer.
@@ -1297,7 +1319,13 @@ int journal_forget (handle_t *handle, struct buffer_head *bh)
 		if (jh->b_next_transaction) {
 			J_ASSERT(jh->b_next_transaction == transaction);
 			jh->b_next_transaction = NULL;
-			drop_reserve = 1;
+
+			/*
+			 * only drop a reference if this transaction modified
+			 * the buffer
+			 */
+			if (was_modified)
+				drop_reserve = 1;
 		}
 	}
 
@@ -1620,12 +1648,42 @@ out:
 	return;
 }
 
+/*
+ * journal_try_to_free_buffers() could race with journal_commit_transaction()
+ * The latter might still hold the a count on buffers when inspecting
+ * them on t_syncdata_list or t_locked_list.
+ *
+ * journal_try_to_free_buffers() will call this function to
+ * wait for the current transaction to finish syncing data buffers, before
+ * tryinf to free that buffer.
+ *
+ * Called with journal->j_state_lock held.
+ */
+static void journal_wait_for_transaction_sync_data(journal_t *journal)
+{
+	transaction_t *transaction = NULL;
+	tid_t tid;
+
+	spin_lock(&journal->j_state_lock);
+	transaction = journal->j_committing_transaction;
+
+	if (!transaction) {
+		spin_unlock(&journal->j_state_lock);
+		return;
+	}
+
+	tid = transaction->t_tid;
+	spin_unlock(&journal->j_state_lock);
+	log_wait_commit(journal, tid);
+}
 
 /**
  * int journal_try_to_free_buffers() - try to free page buffers.
  * @journal: journal for operation
  * @page: to try and free
- * @unused_gfp_mask: unused
+ * @gfp_mask: we use the mask to detect how hard should we try to release
+ * buffers. If __GFP_WAIT and __GFP_FS is set, we wait for commit code to
+ * release the buffers.
  *
  *
  * For all the buffers on this page,
@@ -1654,9 +1712,11 @@ out:
  * journal_try_to_free_buffer() is changing its state.  But that
  * cannot happen because we never reallocate freed data as metadata
  * while the data is part of a transaction.  Yes?
+ *
+ * Return 0 on failure, 1 on success
  */
 int journal_try_to_free_buffers(journal_t *journal,
-				struct page *page, gfp_t unused_gfp_mask)
+				struct page *page, gfp_t gfp_mask)
 {
 	struct buffer_head *head;
 	struct buffer_head *bh;
@@ -1685,7 +1745,28 @@ int journal_try_to_free_buffers(journal_t *journal,
 		if (buffer_jbd(bh))
 			goto busy;
 	} while ((bh = bh->b_this_page) != head);
+
 	ret = try_to_free_buffers(page);
+
+	/*
+	 * There are a number of places where journal_try_to_free_buffers()
+	 * could race with journal_commit_transaction(), the later still
+	 * holds the reference to the buffers to free while processing them.
+	 * try_to_free_buffers() failed to free those buffers. Some of the
+	 * caller of releasepage() request page buffers to be dropped, otherwise
+	 * treat the fail-to-free as errors (such as generic_file_direct_IO())
+	 *
+	 * So, if the caller of try_to_release_page() wants the synchronous
+	 * behaviour(i.e make sure buffers are dropped upon return),
+	 * let's wait for the current transaction to finish flush of
+	 * dirty data buffers, then try to free those buffers again,
+	 * with the journal locked.
+	 */
+	if (ret == 0 && (gfp_mask & __GFP_WAIT) && (gfp_mask & __GFP_FS)) {
+		journal_wait_for_transaction_sync_data(journal);
+		ret = try_to_free_buffers(page);
+	}
+
 busy:
 	return ret;
 }
@@ -2069,7 +2150,7 @@ void __journal_refile_buffer(struct journal_head *jh)
 	jh->b_transaction = jh->b_next_transaction;
 	jh->b_next_transaction = NULL;
 	__journal_file_buffer(jh, jh->b_transaction,
-				was_dirty ? BJ_Metadata : BJ_Reserved);
+				jh->b_modified ? BJ_Metadata : BJ_Reserved);
 	J_ASSERT_JH(jh, jh->b_transaction->t_state == T_RUNNING);
 
 	if (was_dirty)