ocfs2_dlm: fix race in dlm_remaster_locks

There is a possibility that dlm_remaster_locks could overwride node->state
with DLM_RECO_NODE_DATA_REQUESTED after dlm_reco_data_done_handler sets the
node->state to DLM_RECO_NODE_DATA_DONE. This could lead to recovery getting
stuck and requires a cluster reboot. Synchronize with dlm_reco_state_lock
spinlock.

Signed-off-by: Srinivas Eeda <srinivas.eeda@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>

diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 6d4a83d..c1807a4 100644 (file)
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -611,6 +611,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
                        }
                } while (status != 0);
 
+               spin_lock(&dlm_reco_state_lock);
                switch (ndata->state) {
                        case DLM_RECO_NODE_DATA_INIT:
                        case DLM_RECO_NODE_DATA_FINALIZE_SENT:
@@ -641,6 +642,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
                                     ndata->node_num, dead_node);
                                break;
                }
+               spin_unlock(&dlm_reco_state_lock);
        }
 
        mlog(0, "done requesting all lock info\n");