dlm: fixes for nodir mode

The "nodir" mode (statically assign master nodes instead
of using the resource directory) has always been highly
experimental, and never seriously used.  This commit
fixes a number of problems, making nodir much more usable.

- Major change to recovery: recover all locks and restart
  all in-progress operations after recovery.  In some
  cases it's not possible to know which in-progess locks
  to recover, so recover all.  (Most require recovery
  in nodir mode anyway since rehashing changes most
  master nodes.)

- Change the way nodir mode is enabled, from a command
  line mount arg passed through gfs2, into a sysfs
  file managed by dlm_controld, consistent with the
  other config settings.

- Allow recovering MSTCPY locks on an rsb that has not
  yet been turned into a master copy.

- Ignore RCOM_LOCK and RCOM_LOCK_REPLY recovery messages
  from a previous, aborted recovery cycle.  Base this
  on the local recovery status not being in the state
  where any nodes should be sending LOCK messages for the
  current recovery cycle.

- Hold rsb lock around dlm_purge_mstcpy_locks() because it
  may run concurrently with dlm_recover_master_copy().

- Maintain highbast on process-copy lkb's (in addition to
  the master as is usual), because the lkb can switch
  back and forth between being a master and being a
  process copy as the master node changes in recovery.

- When recovering MSTCPY locks, flag rsb's that have
  non-empty convert or waiting queues for granting
  at the end of recovery.  (Rename flag from LOCKS_PURGED
  to RECOVER_GRANT and similar for the recovery function,
  because it's not only resources with purged locks
  that need grant a grant attempt.)

- Replace a couple of unnecessary assertion panics with
  error messages.

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

1 files changed, 6 insertions, 2 deletions

diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index 0e74832..bc342f7 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -271,6 +271,8 @@ struct dlm_lkb {
 	ktime_t			lkb_last_cast_time;	/* for debugging */
 	ktime_t			lkb_last_bast_time;	/* for debugging */
 
+	uint64_t		lkb_recover_seq; /* from ls_recover_seq */
+
 	char			*lkb_lvbptr;
 	struct dlm_lksb		*lkb_lksb;      /* caller's status block */
 	void			(*lkb_astfn) (void *astparam);
@@ -325,7 +327,7 @@ enum rsb_flags {
 	RSB_NEW_MASTER,
 	RSB_NEW_MASTER2,
 	RSB_RECOVER_CONVERT,
-	RSB_LOCKS_PURGED,
+	RSB_RECOVER_GRANT,
 };
 
 static inline void rsb_set_flag(struct dlm_rsb *r, enum rsb_flags flag)
@@ -571,6 +573,7 @@ struct dlm_ls {
 	struct mutex		ls_requestqueue_mutex;
 	struct dlm_rcom		*ls_recover_buf;
 	int			ls_recover_nodeid; /* for debugging */
+	unsigned int		ls_recover_locks_in; /* for log info */
 	uint64_t		ls_rcom_seq;
 	spinlock_t		ls_rcom_spin;
 	struct list_head	ls_recover_list;
@@ -597,6 +600,7 @@ struct dlm_ls {
 #define LSFL_UEVENT_WAIT	5
 #define LSFL_TIMEWARN		6
 #define LSFL_CB_DELAY		7
+#define LSFL_NODIR		8
 
 /* much of this is just saving user space pointers associated with the
    lock that we pass back to the user lib with an ast */
@@ -644,7 +648,7 @@ static inline int dlm_recovery_stopped(struct dlm_ls *ls)
 
 static inline int dlm_no_directory(struct dlm_ls *ls)
 {
-	return (ls->ls_exflags & DLM_LSFL_NODIR) ? 1 : 0;
+	return test_bit(LSFL_NODIR, &ls->ls_flags);
 }
 
 int dlm_netlink_init(void);