15 files changed, 74 insertions, 28 deletions

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 1ef547e49373..d9f222987f24 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1251,7 +1251,7 @@ static int ocfs2_write_cluster(struct address_space *mapping,
         ret = ocfs2_extent_map_get_blocks(inode, v_blkno, &p_blkno, NULL,
                                           NULL);
         if (ret < 0) {
-                ocfs2_error(inode->i_sb, "Corrupting extend for inode %llu, "
+                mlog(ML_ERROR, "Get physical blkno failed for inode %llu, "
                             "at logical block %llu",
                             (unsigned long long)OCFS2_I(inode)->ip_blkno,
                             (unsigned long long)v_blkno);
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index eb9d48746ab4..16eff45727ee 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1127,10 +1127,10 @@ static int o2hb_thread(void *data)
                 elapsed_msec = o2hb_elapsed_msecs(&before_hb, &after_hb);
 
                 mlog(ML_HEARTBEAT,
-                     "start = %lu.%lu, end = %lu.%lu, msec = %u\n",
+                     "start = %lu.%lu, end = %lu.%lu, msec = %u, ret = %d\n",
                      before_hb.tv_sec, (unsigned long) before_hb.tv_usec,
                      after_hb.tv_sec, (unsigned long) after_hb.tv_usec,
-                     elapsed_msec);
+                     elapsed_msec, ret);
 
                 if (!kthread_should_stop() &&
                     elapsed_msec < reg->hr_timeout_ms) {
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index a96044004064..2e355e0f8335 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1736,7 +1736,7 @@ static void o2net_connect_expired(struct work_struct *work)
                      o2net_idle_timeout() / 1000,
                      o2net_idle_timeout() % 1000);
 
-                o2net_set_nn_state(nn, NULL, 0, -ENOTCONN);
+                o2net_set_nn_state(nn, NULL, 0, 0);
         }
         spin_unlock(&nn->nn_lock);
 }
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index c43d9b4a1ec0..79d56dc981bc 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -744,7 +744,7 @@ restart:
                 if (ocfs2_read_dir_block(dir, block, &bh, 0)) {
                         /* read error, skip block & hope for the best.
                          * ocfs2_read_dir_block() has released the bh. */
-                        ocfs2_error(dir->i_sb, "reading directory %llu, "
+                        mlog(ML_ERROR, "reading directory %llu, "
                                     "offset %lu\n",
                                     (unsigned long long)OCFS2_I(dir)->ip_blkno,
                                     block);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 02d315fef432..50a59d2337b2 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -877,7 +877,7 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data,
          * to be put in someone's domain map.
          * Also, explicitly disallow joining at certain troublesome
          * times (ie. during recovery). */
-        if (dlm && dlm->dlm_state != DLM_CTXT_LEAVING) {
+        if (dlm->dlm_state != DLM_CTXT_LEAVING) {
                 int bit = query->node_idx;
                 spin_lock(&dlm->spinlock);
 
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 215e41abf101..3689b3592042 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -1460,6 +1460,18 @@ way_up_top:
 
                 /* take care of the easy cases up front */
                 spin_lock(&res->spinlock);
+
+                /*
+                 * Right after dlm spinlock was released, dlm_thread could have
+                 * purged the lockres. Check if lockres got unhashed. If so
+                 * start over.
+                 */
+                if (hlist_unhashed(&res->hash_node)) {
+                        spin_unlock(&res->spinlock);
+                        dlm_lockres_put(res);
+                        goto way_up_top;
+                }
+
                 if (res->state & (DLM_LOCK_RES_RECOVERING|
                                   DLM_LOCK_RES_MIGRATING)) {
                         spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 3365839d2971..79b5af5e6a7b 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1656,14 +1656,18 @@ int dlm_do_master_requery(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
         req.namelen = res->lockname.len;
         memcpy(req.name, res->lockname.name, res->lockname.len);
 
+resend:
         ret = o2net_send_message(DLM_MASTER_REQUERY_MSG, dlm->key,
                                  &req, sizeof(req), nodenum, &status);
-        /* XXX: negative status not handled properly here. */
         if (ret < 0)
                 mlog(ML_ERROR, "Error %d when sending message %u (key "
                      "0x%x) to node %u\n", ret, DLM_MASTER_REQUERY_MSG,
                      dlm->key, nodenum);
-        else {
+        else if (status == -ENOMEM) {
+                mlog_errno(status);
+                msleep(50);
+                goto resend;
+        } else {
                 BUG_ON(status < 0);
                 BUG_ON(status > DLM_LOCK_RES_OWNER_UNKNOWN);
                 *real_master = (u8) (status & 0xff);
@@ -1705,9 +1709,13 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
                         int ret = dlm_dispatch_assert_master(dlm, res,
                                                              0, 0, flags);
                         if (ret < 0) {
-                                mlog_errno(-ENOMEM);
-                                /* retry!? */
-                                BUG();
+                                mlog_errno(ret);
+                                spin_unlock(&res->spinlock);
+                                dlm_lockres_put(res);
+                                spin_unlock(&dlm->spinlock);
+                                dlm_put(dlm);
+                                /* sender will take care of this and retry */
+                                return ret;
                         } else
                                 __dlm_lockres_grab_inflight_worker(dlm, res);
                         spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 37297c14f9a3..1c423af04c69 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -861,8 +861,13 @@ static inline void ocfs2_generic_handle_convert_action(struct ocfs2_lock_res *lo
          * We set the OCFS2_LOCK_UPCONVERT_FINISHING flag before clearing
          * the OCFS2_LOCK_BUSY flag to prevent the dc thread from
          * downconverting the lock before the upconvert has fully completed.
+         * Do not prevent the dc thread from downconverting if NONBLOCK lock
+         * had already returned.
          */
-        lockres_or_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING);
+        if (!(lockres->l_flags & OCFS2_LOCK_NONBLOCK_FINISHED))
+                lockres_or_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING);
+        else
+                lockres_clear_flags(lockres, OCFS2_LOCK_NONBLOCK_FINISHED);
 
         lockres_clear_flags(lockres, OCFS2_LOCK_BUSY);
 }
@@ -1324,13 +1329,12 @@ static void lockres_add_mask_waiter(struct ocfs2_lock_res *lockres,
 
 /* returns 0 if the mw that was removed was already satisfied, -EBUSY
  * if the mask still hadn't reached its goal */
-static int lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres,
+static int __lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres,
                                       struct ocfs2_mask_waiter *mw)
 {
-        unsigned long flags;
         int ret = 0;
 
-        spin_lock_irqsave(&lockres->l_lock, flags);
+        assert_spin_locked(&lockres->l_lock);
         if (!list_empty(&mw->mw_item)) {
                 if ((lockres->l_flags & mw->mw_mask) != mw->mw_goal)
                         ret = -EBUSY;
@@ -1338,6 +1342,18 @@ static int lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres,
                 list_del_init(&mw->mw_item);
                 init_completion(&mw->mw_complete);
         }
+
+        return ret;
+}
+
+static int lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres,
+                                      struct ocfs2_mask_waiter *mw)
+{
+        unsigned long flags;
+        int ret = 0;
+
+        spin_lock_irqsave(&lockres->l_lock, flags);
+        ret = __lockres_remove_mask_waiter(lockres, mw);
         spin_unlock_irqrestore(&lockres->l_lock, flags);
 
         return ret;
@@ -1373,6 +1389,7 @@ static int __ocfs2_cluster_lock(struct ocfs2_super *osb,
         unsigned long flags;
         unsigned int gen;
         int noqueue_attempted = 0;
+        int dlm_locked = 0;
 
         ocfs2_init_mask_waiter(&mw);
 
@@ -1481,6 +1498,7 @@ again:
                         ocfs2_recover_from_dlm_error(lockres, 1);
                         goto out;
                 }
+                dlm_locked = 1;
 
                 mlog(0, "lock %s, successful return from ocfs2_dlm_lock\n",
                      lockres->l_name);
@@ -1514,10 +1532,17 @@ out:
         if (wait && arg_flags & OCFS2_LOCK_NONBLOCK &&
             mw.mw_mask & (OCFS2_LOCK_BUSY|OCFS2_LOCK_BLOCKED)) {
                 wait = 0;
-                if (lockres_remove_mask_waiter(lockres, &mw))
+                spin_lock_irqsave(&lockres->l_lock, flags);
+                if (__lockres_remove_mask_waiter(lockres, &mw)) {
+                        if (dlm_locked)
+                                lockres_or_flags(lockres,
+                                        OCFS2_LOCK_NONBLOCK_FINISHED);
+                        spin_unlock_irqrestore(&lockres->l_lock, flags);
                         ret = -EAGAIN;
-                else
+                } else {
+                        spin_unlock_irqrestore(&lockres->l_lock, flags);
                         goto again;
+                }
         }
         if (wait) {
                 ret = ocfs2_wait_for_mask(&mw);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 324dc93ac896..69fb9f75b082 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2381,9 +2381,7 @@ out_dio:
                 if (ret < 0)
                         written = ret;
 
-                if (!ret && ((old_size != i_size_read(inode)) ||
-                             (old_clusters != OCFS2_I(inode)->ip_clusters) ||
-                             has_refcount)) {
+                if (!ret) {
                         ret = jbd2_journal_force_commit(osb->journal->j_journal);
                         if (ret < 0)
                                 written = ret;
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 437de7f768c6..c8b25de9efbb 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -540,8 +540,7 @@ bail:
         if (status < 0)
                 make_bad_inode(inode);
 
-        if (args && bh)
-                brelse(bh);
+        brelse(bh);
 
         return status;
 }
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 74caffeeee1d..56a768d06aa6 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -904,9 +904,6 @@ static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
         struct buffer_head *di_bh = NULL;
         struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-        if (!inode)
-                return -ENOENT;
-
         if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
                 return -EROFS;
 
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index bbec539230fd..7d6b7d090452 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -144,6 +144,12 @@ enum ocfs2_unlock_action {
                                                      * before the upconvert
                                                      * has completed */
 
+#define OCFS2_LOCK_NONBLOCK_FINISHED (0x00001000) /* NONBLOCK cluster
+                                                   * lock has already
+                                                   * returned, do not block
+                                                   * dc thread from
+                                                   * downconverting */
+
 struct ocfs2_lock_res_ops;
 
 typedef void (*ocfs2_lock_callback)(int status, unsigned long data);
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index a88b2a4fcc85..d5493e361a38 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -306,7 +306,7 @@ int ocfs2_slot_to_node_num_locked(struct ocfs2_super *osb, int slot_num,
         assert_spin_locked(&osb->osb_lock);
 
         BUG_ON(slot_num < 0);
-        BUG_ON(slot_num > osb->max_slots);
+        BUG_ON(slot_num >= osb->max_slots);
 
         if (!si->si_slots[slot_num].sl_valid)
                 return -ENOENT;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 0945814ddb7b..83723179e1ec 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1629,8 +1629,9 @@ static int __init ocfs2_init(void)
 
         ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL);
         if (!ocfs2_debugfs_root) {
-                status = -EFAULT;
+                status = -ENOMEM;
                 mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n");
+                goto out4;
         }
 
         ocfs2_set_locking_protocol();
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 016f01df3825..662f8dee149f 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -1284,7 +1284,7 @@ int ocfs2_xattr_get_nolock(struct inode *inode,
                 return -EOPNOTSUPP;
 
         if (!(oi->ip_dyn_features & OCFS2_HAS_XATTR_FL))
-                ret = -ENODATA;
+                return -ENODATA;
 
         xis.inode_bh = xbs.inode_bh = di_bh;
         di = (struct ocfs2_dinode *)di_bh->b_data;