Merge commit 'v2.6.28-rc2' into x86/pci-ioapic-boot-irq-quirks

1 files changed, 70 insertions, 7 deletions

diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 67ff2024c23..d15cd6e7251 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -291,7 +291,7 @@ handle_t *journal_start(journal_t *journal, int nblocks)
 		goto out;
 	}
 
-	lock_acquire(&handle->h_lockdep_map, 0, 0, 0, 2, _THIS_IP_);
+	lock_map_acquire(&handle->h_lockdep_map);
 
 out:
 	return handle;
@@ -954,9 +954,10 @@ int journal_dirty_data(handle_t *handle, struct buffer_head *bh)
 	journal_t *journal = handle->h_transaction->t_journal;
 	int need_brelse = 0;
 	struct journal_head *jh;
+	int ret = 0;
 
 	if (is_handle_aborted(handle))
-		return 0;
+		return ret;
 
 	jh = journal_add_journal_head(bh);
 	JBUFFER_TRACE(jh, "entry");
@@ -1067,7 +1068,16 @@ int journal_dirty_data(handle_t *handle, struct buffer_head *bh)
 				   time if it is redirtied */
 			}
 
-			/* journal_clean_data_list() may have got there first */
+			/*
+			 * We cannot remove the buffer with io error from the
+			 * committing transaction, because otherwise it would
+			 * miss the error and the commit would not abort.
+			 */
+			if (unlikely(!buffer_uptodate(bh))) {
+				ret = -EIO;
+				goto no_journal;
+			}
+
 			if (jh->b_transaction != NULL) {
 				JBUFFER_TRACE(jh, "unfile from commit");
 				__journal_temp_unlink_buffer(jh);
@@ -1108,7 +1118,7 @@ no_journal:
 	}
 	JBUFFER_TRACE(jh, "exit");
 	journal_put_journal_head(jh);
-	return 0;
+	return ret;
 }
 
 /**
@@ -1448,7 +1458,7 @@ int journal_stop(handle_t *handle)
 		spin_unlock(&journal->j_state_lock);
 	}
 
-	lock_release(&handle->h_lockdep_map, 1, _THIS_IP_);
+	lock_map_release(&handle->h_lockdep_map);
 
 	jbd_free_handle(handle);
 	return err;
@@ -1648,12 +1658,42 @@ 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,
@@ -1682,9 +1722,11 @@ 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;
@@ -1713,7 +1755,28 @@ 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;
 }