dlm: fix race between remove and lookup

It was possible for a remove message on an old
rsb to be sent after a lookup message on a new
rsb, where the rsbs were for the same resource
name.  This could lead to a missing directory
entry for the new rsb.

It is fixed by keeping a copy of the resource
name being removed until after the remove has
been sent.  A lookup checks if this in-progress
remove matches the name it is looking up.

Signed-off-by: David Teigland <teigland@redhat.com>

1 files changed, 19 insertions, 2 deletions

diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index d4d3b3165c6c..952557d00ccd 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -506,6 +506,15 @@ static int new_lockspace(const char *name, const char *cluster,
                 spin_lock_init(&ls->ls_rsbtbl[i].lock);
         }
 
+        spin_lock_init(&ls->ls_remove_spin);
+
+        for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++) {
+                ls->ls_remove_names[i] = kzalloc(DLM_RESNAME_MAXLEN+1,
+                                                 GFP_KERNEL);
+                if (!ls->ls_remove_names[i])
+                        goto out_rsbtbl;
+        }
+
         idr_init(&ls->ls_lkbidr);
         spin_lock_init(&ls->ls_lkbidr_spin);
 
@@ -556,7 +565,7 @@ static int new_lockspace(const char *name, const char *cluster,
 
         ls->ls_recover_buf = kmalloc(dlm_config.ci_buffer_size, GFP_NOFS);
         if (!ls->ls_recover_buf)
-                goto out_lkbfree;
+                goto out_lkbidr;
 
         ls->ls_slot = 0;
         ls->ls_num_slots = 0;
@@ -640,8 +649,13 @@ static int new_lockspace(const char *name, const char *cluster,
         spin_unlock(&lslist_lock);
         idr_destroy(&ls->ls_recover_idr);
         kfree(ls->ls_recover_buf);
- out_lkbfree:
+ out_lkbidr:
         idr_destroy(&ls->ls_lkbidr);
+        for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++) {
+                if (ls->ls_remove_names[i])
+                        kfree(ls->ls_remove_names[i]);
+        }
+ out_rsbtbl:
         vfree(ls->ls_rsbtbl);
  out_lsfree:
         if (do_unreg)
@@ -796,6 +810,9 @@ static int release_lockspace(struct dlm_ls *ls, int force)
 
         vfree(ls->ls_rsbtbl);
 
+        for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++)
+                kfree(ls->ls_remove_names[i]);
+
         while (!list_empty(&ls->ls_new_rsb)) {
                 rsb = list_first_entry(&ls->ls_new_rsb, struct dlm_rsb,
                                        res_hashchain);