3 files changed, 46 insertions, 11 deletions

diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index ca0f5eb62b20..886849370950 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -22,6 +22,7 @@
 #include <linux/jbd2.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/blkdev.h>
 #include <trace/events/jbd2.h>
 
 /*
@@ -515,6 +516,20 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
         journal->j_tail_sequence = first_tid;
         journal->j_tail = blocknr;
         spin_unlock(&journal->j_state_lock);
+
+        /*
+         * If there is an external journal, we need to make sure that
+         * any data blocks that were recently written out --- perhaps
+         * by jbd2_log_do_checkpoint() --- are flushed out before we
+         * drop the transactions from the external journal.  It's
+         * unlikely this will be necessary, especially with a
+         * appropriately sized journal, but we need this to guarantee
+         * correctness.  Fortunately jbd2_cleanup_journal_tail()
+         * doesn't get called all that often.
+         */
+        if ((journal->j_fs_dev != journal->j_dev) &&
+            (journal->j_flags & JBD2_BARRIER))
+                blkdev_issue_flush(journal->j_fs_dev, NULL);
         if (!(journal->j_flags & JBD2_ABORT))
                 jbd2_journal_update_superblock(journal, 1);
         return 0;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index d4cfd6d2779e..1bc74b6f26d2 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -259,6 +259,7 @@ static int journal_submit_data_buffers(journal_t *journal,
                         ret = err;
                 spin_lock(&journal->j_list_lock);
                 J_ASSERT(jinode->i_transaction == commit_transaction);
+                commit_transaction->t_flushed_data_blocks = 1;
                 jinode->i_flags &= ~JI_COMMIT_RUNNING;
                 wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
         }
@@ -286,7 +287,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
                 if (err) {
                         /*
                          * Because AS_EIO is cleared by
-                         * wait_on_page_writeback_range(), set it again so
+                         * filemap_fdatawait_range(), set it again so
                          * that user process can get -EIO from fsync().
                          */
                         set_bit(AS_EIO,
@@ -636,6 +637,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
                 JBUFFER_TRACE(jh, "ph3: write metadata");
                 flags = jbd2_journal_write_metadata_buffer(commit_transaction,
                                                       jh, &new_jh, blocknr);
+                if (flags < 0) {
+                        jbd2_journal_abort(journal, flags);
+                        continue;
+                }
                 set_bit(BH_JWrite, &jh2bh(new_jh)->b_state);
                 wbuf[bufs++] = jh2bh(new_jh);
 
@@ -704,8 +709,17 @@ start_journal_io:
                 }
         }
 
-        /* Done it all: now write the commit record asynchronously. */
+        /* 
+         * If the journal is not located on the file system device,
+         * then we must flush the file system device before we issue
+         * the commit record
+         */
+        if (commit_transaction->t_flushed_data_blocks &&
+            (journal->j_fs_dev != journal->j_dev) &&
+            (journal->j_flags & JBD2_BARRIER))
+                blkdev_issue_flush(journal->j_fs_dev, NULL);
 
+        /* Done it all: now write the commit record asynchronously. */
         if (JBD2_HAS_INCOMPAT_FEATURE(journal,
                                       JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
                 err = journal_submit_commit_record(journal, commit_transaction,
@@ -716,13 +730,6 @@ start_journal_io:
                         blkdev_issue_flush(journal->j_dev, NULL);
         }
 
-        /*
-         * This is the right place to wait for data buffers both for ASYNC
-         * and !ASYNC commit. If commit is ASYNC, we need to wait only after
-         * the commit block went to disk (which happens above). If commit is
-         * SYNC, we need to wait for data buffers before we start writing
-         * commit block, which happens below in such setting.
-         */
         err = journal_finish_inode_data_buffers(journal, commit_transaction);
         if (err) {
                 printk(KERN_WARNING
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index fed85388ee86..ac0d027595d0 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -78,6 +78,7 @@ EXPORT_SYMBOL(jbd2_journal_errno);
 EXPORT_SYMBOL(jbd2_journal_ack_err);
 EXPORT_SYMBOL(jbd2_journal_clear_err);
 EXPORT_SYMBOL(jbd2_log_wait_commit);
+EXPORT_SYMBOL(jbd2_log_start_commit);
 EXPORT_SYMBOL(jbd2_journal_start_commit);
 EXPORT_SYMBOL(jbd2_journal_force_commit_nested);
 EXPORT_SYMBOL(jbd2_journal_wipe);
@@ -358,6 +359,10 @@ repeat:
 
                 jbd_unlock_bh_state(bh_in);
                 tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
+                if (!tmp) {
+                        jbd2_journal_put_journal_head(new_jh);
+                        return -ENOMEM;
+                }
                 jbd_lock_bh_state(bh_in);
                 if (jh_in->b_frozen_data) {
                         jbd2_free(tmp, bh_in->b_size);
@@ -809,7 +814,7 @@ static journal_t * journal_init_common (void)
         journal_t *journal;
         int err;
 
-        journal = kzalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL);
+        journal = kzalloc(sizeof(*journal), GFP_KERNEL);
         if (!journal)
                 goto fail;
 
@@ -1248,6 +1253,13 @@ int jbd2_journal_load(journal_t *journal)
         if (jbd2_journal_recover(journal))
                 goto recovery_error;
 
+        if (journal->j_failed_commit) {
+                printk(KERN_ERR "JBD2: journal transaction %u on %s "
+                       "is corrupt.\n", journal->j_failed_commit,
+                       journal->j_devname);
+                return -EIO;
+        }
+
         /* OK, we've finished with the dynamic journal bits:
          * reinitialise the dynamic contents of the superblock in memory
          * and reset them on disk. */
@@ -2103,7 +2115,8 @@ static void __init jbd2_create_debugfs_entry(void)
 {
         jbd2_debugfs_dir = debugfs_create_dir("jbd2", NULL);
         if (jbd2_debugfs_dir)
-                jbd2_debug = debugfs_create_u8(JBD2_DEBUG_NAME, S_IRUGO,
+                jbd2_debug = debugfs_create_u8(JBD2_DEBUG_NAME,
+                                               S_IRUGO | S_IWUSR,
                                                jbd2_debugfs_dir,
                                                &jbd2_journal_enable_debug);
 }