jbd2: don't leak modified metadata buffers on an aborted journal

[pandora-kernel.git] / fs / jbd2 / transaction.c

diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index a0e41a4..61537fe 100644 (file)
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -179,7 +179,8 @@ repeat:
                if (!new_transaction)
                        goto alloc_transaction;
                write_lock(&journal->j_state_lock);
-               if (!journal->j_running_transaction) {
+               if (!journal->j_running_transaction &&
+                   !journal->j_barrier_count) {
                        jbd2_get_transaction(journal, new_transaction);
                        new_transaction = NULL;
                }
@@ -469,10 +470,10 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
                   &transaction->t_outstanding_credits);
        if (atomic_dec_and_test(&transaction->t_updates))
                wake_up(&journal->j_wait_updates);
+       tid = transaction->t_tid;
        spin_unlock(&transaction->t_handle_lock);
 
        jbd_debug(2, "restarting handle %p\n", handle);
-       tid = transaction->t_tid;
        need_to_start = !tid_geq(journal->j_commit_request, tid);
        read_unlock(&journal->j_state_lock);
        if (need_to_start)
@@ -1015,9 +1016,12 @@ out:
 void jbd2_journal_set_triggers(struct buffer_head *bh,
                               struct jbd2_buffer_trigger_type *type)
 {
-       struct journal_head *jh = bh2jh(bh);
+       struct journal_head *jh = jbd2_journal_grab_journal_head(bh);
 
+       if (WARN_ON(!jh))
+               return;
        jh->b_triggers = type;
+       jbd2_journal_put_journal_head(jh);
 }
 
 void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data,
@@ -1069,17 +1073,18 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 {
        transaction_t *transaction = handle->h_transaction;
        journal_t *journal = transaction->t_journal;
-       struct journal_head *jh = bh2jh(bh);
+       struct journal_head *jh;
        int ret = 0;
 
-       jbd_debug(5, "journal_head %p\n", jh);
-       JBUFFER_TRACE(jh, "entry");
        if (is_handle_aborted(handle))
                goto out;
-       if (!buffer_jbd(bh)) {
+       jh = jbd2_journal_grab_journal_head(bh);
+       if (!jh) {
                ret = -EUCLEAN;
                goto out;
        }
+       jbd_debug(5, "journal_head %p\n", jh);
+       JBUFFER_TRACE(jh, "entry");
 
        jbd_lock_bh_state(bh);
 
@@ -1170,6 +1175,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
        spin_unlock(&journal->j_list_lock);
 out_unlock_bh:
        jbd_unlock_bh_state(bh);
+       jbd2_journal_put_journal_head(jh);
 out:
        JBUFFER_TRACE(jh, "exit");
        WARN_ON(ret);   /* All errors are bugs, so dump the stack */
@@ -1382,9 +1388,12 @@ int jbd2_journal_stop(handle_t *handle)
         * to perform a synchronous write.  We do this to detect the
         * case where a single process is doing a stream of sync
         * writes.  No point in waiting for joiners in that case.
+        *
+        * Setting max_batch_time to 0 disables this completely.
         */
        pid = current->pid;
-       if (handle->h_sync && journal->j_last_sync_writer != pid) {
+       if (handle->h_sync && journal->j_last_sync_writer != pid &&
+           journal->j_max_batch_time) {
                u64 commit_time, trans_time;
 
                journal->j_last_sync_writer = pid;
@@ -1592,7 +1601,9 @@ void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
 
        __blist_del_buffer(list, jh);
        jh->b_jlist = BJ_None;
-       if (test_clear_buffer_jbddirty(bh))
+       if (transaction && is_journal_aborted(transaction->t_journal))
+               clear_buffer_jbddirty(bh);
+       else if (test_clear_buffer_jbddirty(bh))
                mark_buffer_dirty(bh);  /* Expose it to the VM */
 }
 
@@ -1867,6 +1878,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 
                if (!buffer_dirty(bh)) {
                        /* bdflush has written it.  We can drop it now */
+                       __jbd2_journal_remove_checkpoint(jh);
                        goto zap_buffer;
                }
 
@@ -1904,6 +1916,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
                                /* The orphan record's transaction has
                                 * committed.  We can cleanse this buffer */
                                clear_buffer_jbddirty(bh);
+                               __jbd2_journal_remove_checkpoint(jh);
                                goto zap_buffer;
                        }
                }
@@ -1948,6 +1961,8 @@ zap_buffer_unlocked:
        clear_buffer_mapped(bh);
        clear_buffer_req(bh);
        clear_buffer_new(bh);
+       clear_buffer_delay(bh);
+       clear_buffer_unwritten(bh);
        bh->b_bdev = NULL;
        return may_free;
 }