Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - the v9fs maintainers have been missing for a long time. I've taken
   over v9fs patch slinging.

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (116 commits)
  mm,oom_reaper: check for MMF_OOM_SKIP before complaining
  mm/ksm: fix interaction with THP
  mm/memblock.c: cast constant ULLONG_MAX to phys_addr_t
  headers: untangle kmemleak.h from mm.h
  include/linux/mmdebug.h: make VM_WARN* non-rvals
  mm/page_isolation.c: make start_isolate_page_range() fail if already isolated
  mm: change return type to vm_fault_t
  mm, oom: remove 3% bonus for CAP_SYS_ADMIN processes
  mm, page_alloc: wakeup kcompactd even if kswapd cannot free more memory
  kernel/fork.c: detect early free of a live mm
  mm: make counting of list_lru_one::nr_items lockless
  mm/swap_state.c: make bool enable_vma_readahead and swap_vma_readahead() static
  block_invalidatepage(): only release page if the full page was invalidated
  mm: kernel-doc: add missing parameter descriptions
  mm/swap.c: remove @cold parameter description for release_pages()
  mm/nommu: remove description of alloc_vm_area
  zram: drop max_zpage_size and use zs_huge_class_size()
  zsmalloc: introduce zs_huge_class_size()
  mm: fix races between swapoff and flush dcache
  fs/direct-io.c: minor cleanups in do_blockdev_direct_IO
  ...

25 files changed, 329 insertions, 390 deletions

diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 9a876bb07cac..0f157bbd3e0f 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -7119,7 +7119,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 			goto out_commit;
 		did_quota = 1;
 
-		data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;
+		data_ac->ac_resv = &oi->ip_la_data_resv;
 
 		ret = ocfs2_claim_clusters(handle, data_ac, 1, &bit_off,
 					   &num);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index e8e205bf2e41..302cd7caa4a7 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -346,7 +346,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 	unlock = 0;
 
 out_alloc:
-	up_read(&OCFS2_I(inode)->ip_alloc_sem);
+	up_read(&oi->ip_alloc_sem);
 out_inode_unlock:
 	ocfs2_inode_unlock(inode, 0);
 out:
@@ -2213,7 +2213,7 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
 	down_write(&oi->ip_alloc_sem);
 
 	if (first_get_block) {
-		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+		if (ocfs2_sparse_alloc(osb))
 			ret = ocfs2_zero_tail(inode, di_bh, pos);
 		else
 			ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 8614ff069d99..3494a62ed749 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -78,7 +78,7 @@ static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level)
 /*
  * Using a named enum representing lock types in terms of #N bit stored in
  * iocb->private, which is going to be used for communication between
- * ocfs2_dio_end_io() and ocfs2_file_aio_write/read().
+ * ocfs2_dio_end_io() and ocfs2_file_write/read_iter().
  */
 enum ocfs2_iocb_lock_bits {
 	OCFS2_IOCB_RW_LOCK = 0,
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index ea8c551bcd7e..91a8889abf9b 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -570,7 +570,16 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 		     current_page, vec_len, vec_start);
 
 		len = bio_add_page(bio, page, vec_len, vec_start);
-		if (len != vec_len) break;
+		if (len != vec_len) {
+			mlog(ML_ERROR, "Adding page[%d] to bio failed, "
+			     "page %p, len %d, vec_len %u, vec_start %u, "
+			     "bi_sector %llu\n", current_page, page, len,
+			     vec_len, vec_start,
+			     (unsigned long long)bio->bi_iter.bi_sector);
+			bio_put(bio);
+			bio = ERR_PTR(-EIO);
+			return bio;
+		}
 
 		cs += vec_len / (PAGE_SIZE/spp);
 		vec_start = 0;
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 977763d4c27d..b048d4fa3959 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -3072,7 +3072,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 			 * We need to return the correct block within the
 			 * cluster which should hold our entry.
 			 */
-			off = ocfs2_dx_dir_hash_idx(OCFS2_SB(dir->i_sb),
+			off = ocfs2_dx_dir_hash_idx(osb,
 						    &lookup->dl_hinfo);
 			get_bh(dx_leaves[off]);
 			lookup->dl_dx_leaf_bh = dx_leaves[off];
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index fd6bbbbd7d78..39831fc2fd52 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -224,14 +224,12 @@ void dlm_do_local_ast(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
 		      struct dlm_lock *lock)
 {
 	dlm_astlockfunc_t *fn;
-	struct dlm_lockstatus *lksb;
 
 	mlog(0, "%s: res %.*s, lock %u:%llu, Local AST\n", dlm->name,
 	     res->lockname.len, res->lockname.name,
 	     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
 	     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)));
 
-	lksb = lock->lksb;
 	fn = lock->ast;
 	BUG_ON(lock->ml.node != dlm->node_num);
 
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index e9f3705c4c9f..d06e27ec4be4 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -140,6 +140,7 @@ struct dlm_ctxt
 	u8 node_num;
 	u32 key;
 	u8  joining_node;
+	u8 migrate_done; /* set to 1 means node has migrated all lock resources */
 	wait_queue_head_t dlm_join_events;
 	unsigned long live_nodes_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
 	unsigned long domain_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
@@ -960,13 +961,10 @@ static inline int dlm_send_proxy_ast(struct dlm_ctxt *dlm,
 void dlm_print_one_lock_resource(struct dlm_lock_resource *res);
 void __dlm_print_one_lock_resource(struct dlm_lock_resource *res);
 
-u8 dlm_nm_this_node(struct dlm_ctxt *dlm);
 void dlm_kick_thread(struct dlm_ctxt *dlm, struct dlm_lock_resource *res);
 void __dlm_dirty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res);
 
 
-int dlm_nm_init(struct dlm_ctxt *dlm);
-int dlm_heartbeat_init(struct dlm_ctxt *dlm);
 void dlm_hb_node_down_cb(struct o2nm_node *node, int idx, void *data);
 void dlm_hb_node_up_cb(struct o2nm_node *node, int idx, void *data);
 
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index e1fea149f50b..425081be6161 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -461,6 +461,19 @@ redo_bucket:
 		cond_resched_lock(&dlm->spinlock);
 		num += n;
 	}
+
+	if (!num) {
+		if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) {
+			mlog(0, "%s: perhaps there are more lock resources "
+			     "need to be migrated after dlm recovery\n", dlm->name);
+			ret = -EAGAIN;
+		} else {
+			mlog(0, "%s: we won't do dlm recovery after migrating "
+			     "all lock resources\n", dlm->name);
+			dlm->migrate_done = 1;
+		}
+	}
+
 	spin_unlock(&dlm->spinlock);
 	wake_up(&dlm->dlm_thread_wq);
 
@@ -675,20 +688,6 @@ static void dlm_leave_domain(struct dlm_ctxt *dlm)
 	spin_unlock(&dlm->spinlock);
 }
 
-int dlm_shutting_down(struct dlm_ctxt *dlm)
-{
-	int ret = 0;
-
-	spin_lock(&dlm_domain_lock);
-
-	if (dlm->dlm_state == DLM_CTXT_IN_SHUTDOWN)
-		ret = 1;
-
-	spin_unlock(&dlm_domain_lock);
-
-	return ret;
-}
-
 void dlm_unregister_domain(struct dlm_ctxt *dlm)
 {
 	int leave = 0;
@@ -2052,6 +2051,8 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 	dlm->joining_node = DLM_LOCK_RES_OWNER_UNKNOWN;
 	init_waitqueue_head(&dlm->dlm_join_events);
 
+	dlm->migrate_done = 0;
+
 	dlm->reco.new_master = O2NM_INVALID_NODE_NUM;
 	dlm->reco.dead_node = O2NM_INVALID_NODE_NUM;
 
diff --git a/fs/ocfs2/dlm/dlmdomain.h b/fs/ocfs2/dlm/dlmdomain.h
index fd6122a38dbd..8a9281411c18 100644
--- a/fs/ocfs2/dlm/dlmdomain.h
+++ b/fs/ocfs2/dlm/dlmdomain.h
@@ -28,7 +28,30 @@
 extern spinlock_t dlm_domain_lock;
 extern struct list_head dlm_domains;
 
-int dlm_shutting_down(struct dlm_ctxt *dlm);
+static inline int dlm_joined(struct dlm_ctxt *dlm)
+{
+	int ret = 0;
+
+	spin_lock(&dlm_domain_lock);
+	if (dlm->dlm_state == DLM_CTXT_JOINED)
+		ret = 1;
+	spin_unlock(&dlm_domain_lock);
+
+	return ret;
+}
+
+static inline int dlm_shutting_down(struct dlm_ctxt *dlm)
+{
+	int ret = 0;
+
+	spin_lock(&dlm_domain_lock);
+	if (dlm->dlm_state == DLM_CTXT_IN_SHUTDOWN)
+		ret = 1;
+	spin_unlock(&dlm_domain_lock);
+
+	return ret;
+}
+
 void dlm_fire_domain_eviction_callbacks(struct dlm_ctxt *dlm,
 					int node_num);
 
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index 66c2a491f68d..74962315794e 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -77,8 +77,7 @@ int dlm_init_lock_cache(void)
 
 void dlm_destroy_lock_cache(void)
 {
-	if (dlm_lock_cache)
-		kmem_cache_destroy(dlm_lock_cache);
+	kmem_cache_destroy(dlm_lock_cache);
 }
 
 /* Tell us whether we can grant a new lock request.
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index a7df226f9449..aaca0949fe53 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -414,8 +414,7 @@ int dlm_init_mle_cache(void)
 
 void dlm_destroy_mle_cache(void)
 {
-	if (dlm_mle_cache)
-		kmem_cache_destroy(dlm_mle_cache);
+	kmem_cache_destroy(dlm_mle_cache);
 }
 
 static void dlm_mle_release(struct kref *kref)
@@ -472,15 +471,11 @@ bail:
 
 void dlm_destroy_master_caches(void)
 {
-	if (dlm_lockname_cache) {
-		kmem_cache_destroy(dlm_lockname_cache);
-		dlm_lockname_cache = NULL;
-	}
+	kmem_cache_destroy(dlm_lockname_cache);
+	dlm_lockname_cache = NULL;
 
-	if (dlm_lockres_cache) {
-		kmem_cache_destroy(dlm_lockres_cache);
-		dlm_lockres_cache = NULL;
-	}
+	kmem_cache_destroy(dlm_lockres_cache);
+	dlm_lockres_cache = NULL;
 }
 
 static void dlm_lockres_release(struct kref *kref)
@@ -2495,13 +2490,13 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
 }
 
 /*
- * A migrateable resource is one that is :
+ * A migratable resource is one that is :
  * 1. locally mastered, and,
  * 2. zero local locks, and,
  * 3. one or more non-local locks, or, one or more references
  * Returns 1 if yes, 0 if not.
  */
-static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
+static int dlm_is_lockres_migratable(struct dlm_ctxt *dlm,
 				      struct dlm_lock_resource *res)
 {
 	enum dlm_lockres_list idx;
@@ -2532,7 +2527,7 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
 				continue;
 			}
 			cookie = be64_to_cpu(lock->ml.cookie);
-			mlog(0, "%s: Not migrateable res %.*s, lock %u:%llu on "
+			mlog(0, "%s: Not migratable res %.*s, lock %u:%llu on "
 			     "%s list\n", dlm->name, res->lockname.len,
 			     res->lockname.name,
 			     dlm_get_lock_cookie_node(cookie),
@@ -2548,7 +2543,7 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
 			return 0;
 	}
 
-	mlog(0, "%s: res %.*s, Migrateable\n", dlm->name, res->lockname.len,
+	mlog(0, "%s: res %.*s, Migratable\n", dlm->name, res->lockname.len,
 	     res->lockname.name);
 
 	return 1;
@@ -2792,7 +2787,7 @@ int dlm_empty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 	assert_spin_locked(&dlm->spinlock);
 
 	spin_lock(&res->spinlock);
-	if (dlm_is_lockres_migrateable(dlm, res))
+	if (dlm_is_lockres_migratable(dlm, res))
 		target = dlm_pick_migration_target(dlm, res);
 	spin_unlock(&res->spinlock);
 
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index ec8f75813beb..802636d50365 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -62,7 +62,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node);
 static int dlm_init_recovery_area(struct dlm_ctxt *dlm, u8 dead_node);
 static int dlm_request_all_locks(struct dlm_ctxt *dlm,
 				 u8 request_from, u8 dead_node);
-static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm, u8 dead_node);
+static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm);
 
 static inline int dlm_num_locks_in_lockres(struct dlm_lock_resource *res);
 static void dlm_init_migratable_lockres(struct dlm_migratable_lockres *mres,
@@ -423,12 +423,11 @@ void dlm_wait_for_recovery(struct dlm_ctxt *dlm)
 
 static void dlm_begin_recovery(struct dlm_ctxt *dlm)
 {
-	spin_lock(&dlm->spinlock);
+	assert_spin_locked(&dlm->spinlock);
 	BUG_ON(dlm->reco.state & DLM_RECO_STATE_ACTIVE);
 	printk(KERN_NOTICE "o2dlm: Begin recovery on domain %s for node %u\n",
 	       dlm->name, dlm->reco.dead_node);
 	dlm->reco.state |= DLM_RECO_STATE_ACTIVE;
-	spin_unlock(&dlm->spinlock);
 }
 
 static void dlm_end_recovery(struct dlm_ctxt *dlm)
@@ -456,6 +455,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm)
 
 	spin_lock(&dlm->spinlock);
 
+	if (dlm->migrate_done) {
+		mlog(0, "%s: no need do recovery after migrating all "
+		     "lock resources\n", dlm->name);
+		spin_unlock(&dlm->spinlock);
+		return 0;
+	}
+
 	/* check to see if the new master has died */
 	if (dlm->reco.new_master != O2NM_INVALID_NODE_NUM &&
 	    test_bit(dlm->reco.new_master, dlm->recovery_map)) {
@@ -490,12 +496,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm)
 	mlog(0, "%s(%d):recovery thread found node %u in the recovery map!\n",
 	     dlm->name, task_pid_nr(dlm->dlm_reco_thread_task),
 	     dlm->reco.dead_node);
-	spin_unlock(&dlm->spinlock);
 
 	/* take write barrier */
 	/* (stops the list reshuffling thread, proxy ast handling) */
 	dlm_begin_recovery(dlm);
 
+	spin_unlock(&dlm->spinlock);
+
 	if (dlm->reco.new_master == dlm->node_num)
 		goto master_here;
 
@@ -739,7 +746,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 	}
 
 	if (destroy)
-		dlm_destroy_recovery_area(dlm, dead_node);
+		dlm_destroy_recovery_area(dlm);
 
 	return status;
 }
@@ -764,7 +771,7 @@ static int dlm_init_recovery_area(struct dlm_ctxt *dlm, u8 dead_node)
 
 		ndata = kzalloc(sizeof(*ndata), GFP_NOFS);
 		if (!ndata) {
-			dlm_destroy_recovery_area(dlm, dead_node);
+			dlm_destroy_recovery_area(dlm);
 			return -ENOMEM;
 		}
 		ndata->node_num = num;
@@ -778,7 +785,7 @@ static int dlm_init_recovery_area(struct dlm_ctxt *dlm, u8 dead_node)
 	return 0;
 }
 
-static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm, u8 dead_node)
+static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm)
 {
 	struct dlm_reco_node_data *ndata, *next;
 	LIST_HEAD(tmplist);
@@ -1378,6 +1385,15 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	if (!dlm_grab(dlm))
 		return -EINVAL;
 
+	if (!dlm_joined(dlm)) {
+		mlog(ML_ERROR, "Domain %s not joined! "
+			  "lockres %.*s, master %u\n",
+			  dlm->name, mres->lockname_len,
+			  mres->lockname, mres->master);
+		dlm_put(dlm);
+		return -EINVAL;
+	}
+
 	BUG_ON(!(mres->flags & (DLM_MRES_RECOVERY|DLM_MRES_MIGRATION)));
 
 	real_master = mres->master;
@@ -1807,7 +1823,6 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 	int i, j, bad;
 	struct dlm_lock *lock;
 	u8 from = O2NM_MAX_NODES;
-	unsigned int added = 0;
 	__be64 c;
 
 	mlog(0, "running %d locks for this lockres\n", mres->num_locks);
@@ -1823,7 +1838,6 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 			spin_lock(&res->spinlock);
 			dlm_lockres_set_refmap_bit(dlm, res, from);
 			spin_unlock(&res->spinlock);
-			added++;
 			break;
 		}
 		BUG_ON(ml->highest_blocked != LKM_IVMODE);
@@ -1911,7 +1925,6 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 			/* do not alter lock refcount.  switching lists. */
 			list_move_tail(&lock->list, queue);
 			spin_unlock(&res->spinlock);
-			added++;
 
 			mlog(0, "just reordered a local lock!\n");
 			continue;
@@ -2037,7 +2050,6 @@ skip_lvb:
 			     "setting refmap bit\n", dlm->name,
 			     res->lockname.len, res->lockname.name, ml->node);
 			dlm_lockres_set_refmap_bit(dlm, res, ml->node);
-			added++;
 		}
 		spin_unlock(&res->spinlock);
 	}
@@ -2331,13 +2343,6 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm,
 	__dlm_dirty_lockres(dlm, res);
 }
 
-/* if this node is the recovery master, and there are no
- * locks for a given lockres owned by this node that are in
- * either PR or EX mode, zero out the lvb before requesting.
- *
- */
-
-
 static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 {
 	struct dlm_lock_resource *res;
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index b552d1f8508c..97a972efab83 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -1756,8 +1756,7 @@ int ocfs2_rw_lock(struct inode *inode, int write)
 
 	level = write ? DLM_LOCK_EX : DLM_LOCK_PR;
 
-	status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres, level, 0,
-				    0);
+	status = ocfs2_cluster_lock(osb, lockres, level, 0, 0);
 	if (status < 0)
 		mlog_errno(status);
 
@@ -1796,7 +1795,7 @@ void ocfs2_rw_unlock(struct inode *inode, int write)
 	     write ? "EXMODE" : "PRMODE");
 
 	if (!ocfs2_mount_local(osb))
-		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level);
+		ocfs2_cluster_unlock(osb, lockres, level);
 }
 
 /*
@@ -1816,8 +1815,7 @@ int ocfs2_open_lock(struct inode *inode)
 
 	lockres = &OCFS2_I(inode)->ip_open_lockres;
 
-	status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres,
-				    DLM_LOCK_PR, 0, 0);
+	status = ocfs2_cluster_lock(osb, lockres, DLM_LOCK_PR, 0, 0);
 	if (status < 0)
 		mlog_errno(status);
 
@@ -1854,8 +1852,7 @@ int ocfs2_try_open_lock(struct inode *inode, int write)
 	 * other nodes and the -EAGAIN will indicate to the caller that
 	 * this inode is still in use.
 	 */
-	status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres,
-				    level, DLM_LKF_NOQUEUE, 0);
+	status = ocfs2_cluster_lock(osb, lockres, level, DLM_LKF_NOQUEUE, 0);
 
 out:
 	return status;
@@ -1876,11 +1873,9 @@ void ocfs2_open_unlock(struct inode *inode)
 		goto out;
 
 	if(lockres->l_ro_holders)
-		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres,
-				     DLM_LOCK_PR);
+		ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_PR);
 	if(lockres->l_ex_holders)
-		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres,
-				     DLM_LOCK_EX);
+		ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_EX);
 
 out:
 	return;
@@ -2601,9 +2596,9 @@ void ocfs2_inode_unlock(struct inode *inode,
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
 	     ex ? "EXMODE" : "PRMODE");
 
-	if (!ocfs2_is_hard_readonly(OCFS2_SB(inode->i_sb)) &&
+	if (!ocfs2_is_hard_readonly(osb) &&
 	    !ocfs2_mount_local(osb))
-		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level);
+		ocfs2_cluster_unlock(osb, lockres, level);
 }
 
 /*
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 5d1784a365a3..6ee94bc23f5b 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -101,7 +101,7 @@ static int ocfs2_file_open(struct inode *inode, struct file *file)
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
 	trace_ocfs2_file_open(inode, file, file->f_path.dentry,
-			      (unsigned long long)OCFS2_I(inode)->ip_blkno,
+			      (unsigned long long)oi->ip_blkno,
 			      file->f_path.dentry->d_name.len,
 			      file->f_path.dentry->d_name.name, mode);
 
@@ -116,7 +116,7 @@ static int ocfs2_file_open(struct inode *inode, struct file *file)
 	/* Check that the inode hasn't been wiped from disk by another
 	 * node. If it hasn't then we're safe as long as we hold the
 	 * spin lock until our increment of open count. */
-	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_DELETED) {
+	if (oi->ip_flags & OCFS2_INODE_DELETED) {
 		spin_unlock(&oi->ip_lock);
 
 		status = -ENOENT;
@@ -190,7 +190,7 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
 	bool needs_barrier = false;
 
 	trace_ocfs2_sync_file(inode, file, file->f_path.dentry,
-			      OCFS2_I(inode)->ip_blkno,
+			      oi->ip_blkno,
 			      file->f_path.dentry->d_name.len,
 			      file->f_path.dentry->d_name.name,
 			      (unsigned long long)datasync);
@@ -296,7 +296,7 @@ int ocfs2_update_inode_atime(struct inode *inode,
 	ocfs2_journal_dirty(handle, bh);
 
 out_commit:
-	ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+	ocfs2_commit_trans(osb, handle);
 out:
 	return ret;
 }
@@ -2257,7 +2257,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
 	int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0;
 
-	trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry,
+	trace_ocfs2_file_write_iter(inode, file, file->f_path.dentry,
 		(unsigned long long)OCFS2_I(inode)->ip_blkno,
 		file->f_path.dentry->d_name.len,
 		file->f_path.dentry->d_name.name,
@@ -2405,7 +2405,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
 	int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0;
 
-	trace_ocfs2_file_aio_read(inode, filp, filp->f_path.dentry,
+	trace_ocfs2_file_read_iter(inode, filp, filp->f_path.dentry,
 			(unsigned long long)OCFS2_I(inode)->ip_blkno,
 			filp->f_path.dentry->d_name.len,
 			filp->f_path.dentry->d_name.name,
@@ -2448,7 +2448,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	 *
 	 * Take and drop the meta data lock to update inode fields
 	 * like i_size. This allows the checks down below
-	 * generic_file_aio_read() a chance of actually working.
+	 * generic_file_read_iter() a chance of actually working.
 	 */
 	ret = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level,
 				     !nowait);
@@ -2460,7 +2460,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	ocfs2_inode_unlock(inode, lock_level);
 
 	ret = generic_file_read_iter(iocb, to);
-	trace_generic_file_aio_read_ret(ret);
+	trace_generic_file_read_iter_ret(ret);
 
 	/* buffered aio wouldn't have proper lock coverage today */
 	BUG_ON(ret == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT));
diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c
index 6b92cb241138..f65f2b2f594d 100644
--- a/fs/ocfs2/filecheck.c
+++ b/fs/ocfs2/filecheck.c
@@ -53,36 +53,6 @@ static const char * const ocfs2_filecheck_errs[] = {
 	"UNSUPPORTED"
 };
 
-static DEFINE_SPINLOCK(ocfs2_filecheck_sysfs_lock);
-static LIST_HEAD(ocfs2_filecheck_sysfs_list);
-
-struct ocfs2_filecheck {
-	struct list_head fc_head;	/* File check entry list head */
-	spinlock_t fc_lock;
-	unsigned int fc_max;	/* Maximum number of entry in list */
-	unsigned int fc_size;	/* Current entry count in list */
-	unsigned int fc_done;	/* Finished entry count in list */
-};
-
-struct ocfs2_filecheck_sysfs_entry {	/* sysfs entry per mounting */
-	struct list_head fs_list;
-	atomic_t fs_count;
-	struct super_block *fs_sb;
-	struct kset *fs_devicekset;
-	struct kset *fs_fcheckkset;
-	struct ocfs2_filecheck *fs_fcheck;
-};
-
-#define OCFS2_FILECHECK_MAXSIZE		100
-#define OCFS2_FILECHECK_MINSIZE		10
-
-/* File check operation type */
-enum {
-	OCFS2_FILECHECK_TYPE_CHK = 0,	/* Check a file(inode) */
-	OCFS2_FILECHECK_TYPE_FIX,	/* Fix a file(inode) */
-	OCFS2_FILECHECK_TYPE_SET = 100	/* Set entry list maximum size */
-};
-
 struct ocfs2_filecheck_entry {
 	struct list_head fe_list;
 	unsigned long fe_ino;
@@ -110,35 +80,84 @@ ocfs2_filecheck_error(int errno)
 	return ocfs2_filecheck_errs[errno - OCFS2_FILECHECK_ERR_START + 1];
 }
 
-static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
-				    struct kobj_attribute *attr,
-				    char *buf);
-static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
-				     struct kobj_attribute *attr,
-				     const char *buf, size_t count);
-static struct kobj_attribute ocfs2_attr_filecheck_chk =
+static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					char *buf);
+static ssize_t ocfs2_filecheck_attr_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t count);
+static struct kobj_attribute ocfs2_filecheck_attr_chk =
 					__ATTR(check, S_IRUSR | S_IWUSR,
-					ocfs2_filecheck_show,
-					ocfs2_filecheck_store);
-static struct kobj_attribute ocfs2_attr_filecheck_fix =
+					ocfs2_filecheck_attr_show,
+					ocfs2_filecheck_attr_store);
+static struct kobj_attribute ocfs2_filecheck_attr_fix =
 					__ATTR(fix, S_IRUSR | S_IWUSR,
-					ocfs2_filecheck_show,
-					ocfs2_filecheck_store);
-static struct kobj_attribute ocfs2_attr_filecheck_set =
+					ocfs2_filecheck_attr_show,
+					ocfs2_filecheck_attr_store);
+static struct kobj_attribute ocfs2_filecheck_attr_set =
 					__ATTR(set, S_IRUSR | S_IWUSR,
-					ocfs2_filecheck_show,
-					ocfs2_filecheck_store);
+					ocfs2_filecheck_attr_show,
+					ocfs2_filecheck_attr_store);
+static struct attribute *ocfs2_filecheck_attrs[] = {
+	&ocfs2_filecheck_attr_chk.attr,
+	&ocfs2_filecheck_attr_fix.attr,
+	&ocfs2_filecheck_attr_set.attr,
+	NULL
+};
+
+static void ocfs2_filecheck_release(struct kobject *kobj)
+{
+	struct ocfs2_filecheck_sysfs_entry *entry = container_of(kobj,
+				struct ocfs2_filecheck_sysfs_entry, fs_kobj);
+
+	complete(&entry->fs_kobj_unregister);
+}
+
+static ssize_t
+ocfs2_filecheck_show(struct kobject *kobj, struct attribute *attr, char *buf)
+{
+	ssize_t ret = -EIO;
+	struct kobj_attribute *kattr = container_of(attr,
+					struct kobj_attribute, attr);
+
+	kobject_get(kobj);
+	if (kattr->show)
+		ret = kattr->show(kobj, kattr, buf);
+	kobject_put(kobj);
+	return ret;
+}
+
+static ssize_t
+ocfs2_filecheck_store(struct kobject *kobj, struct attribute *attr,
+			const char *buf, size_t count)
+{
+	ssize_t ret = -EIO;
+	struct kobj_attribute *kattr = container_of(attr,
+					struct kobj_attribute, attr);
+
+	kobject_get(kobj);
+	if (kattr->store)
+		ret = kattr->store(kobj, kattr, buf, count);
+	kobject_put(kobj);
+	return ret;
+}
+
+static const struct sysfs_ops ocfs2_filecheck_ops = {
+	.show = ocfs2_filecheck_show,
+	.store = ocfs2_filecheck_store,
+};
+
+static struct kobj_type ocfs2_ktype_filecheck = {
+	.default_attrs = ocfs2_filecheck_attrs,
+	.sysfs_ops = &ocfs2_filecheck_ops,
+	.release = ocfs2_filecheck_release,
+};
 
 static void
 ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry)
 {
 	struct ocfs2_filecheck_entry *p;
 
-	if (!atomic_dec_and_test(&entry->fs_count)) {
-		wait_var_event(&entry->fs_count,
-			       !atomic_read(&entry->fs_count));
-	}
-
 	spin_lock(&entry->fs_fcheck->fc_lock);
 	while (!list_empty(&entry->fs_fcheck->fc_head)) {
 		p = list_first_entry(&entry->fs_fcheck->fc_head,
@@ -149,151 +168,48 @@ ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry)
 	}
 	spin_unlock(&entry->fs_fcheck->fc_lock);
 
-	kset_unregister(entry->fs_fcheckkset);
-	kset_unregister(entry->fs_devicekset);
 	kfree(entry->fs_fcheck);
-	kfree(entry);
-}
-
-static void
-ocfs2_filecheck_sysfs_add(struct ocfs2_filecheck_sysfs_entry *entry)
-{
-	spin_lock(&ocfs2_filecheck_sysfs_lock);
-	list_add_tail(&entry->fs_list, &ocfs2_filecheck_sysfs_list);
-	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+	entry->fs_fcheck = NULL;
 }
 
-static int ocfs2_filecheck_sysfs_del(const char *devname)
+int ocfs2_filecheck_create_sysfs(struct ocfs2_super *osb)
 {
-	struct ocfs2_filecheck_sysfs_entry *p;
-
-	spin_lock(&ocfs2_filecheck_sysfs_lock);
-	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
-		if (!strcmp(p->fs_sb->s_id, devname)) {
-			list_del(&p->fs_list);
-			spin_unlock(&ocfs2_filecheck_sysfs_lock);
-			ocfs2_filecheck_sysfs_free(p);
-			return 0;
-		}
-	}
-	spin_unlock(&ocfs2_filecheck_sysfs_lock);
-	return 1;
-}
-
-static void
-ocfs2_filecheck_sysfs_put(struct ocfs2_filecheck_sysfs_entry *entry)
-{
-	if (atomic_dec_and_test(&entry->fs_count))
-		wake_up_var(&entry->fs_count);
-}
-
-static struct ocfs2_filecheck_sysfs_entry *
-ocfs2_filecheck_sysfs_get(const char *devname)
-{
-	struct ocfs2_filecheck_sysfs_entry *p = NULL;
-
-	spin_lock(&ocfs2_filecheck_sysfs_lock);
-	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
-		if (!strcmp(p->fs_sb->s_id, devname)) {
-			atomic_inc(&p->fs_count);
-			spin_unlock(&ocfs2_filecheck_sysfs_lock);
-			return p;
-		}
-	}
-	spin_unlock(&ocfs2_filecheck_sysfs_lock);
-	return NULL;
-}
-
-int ocfs2_filecheck_create_sysfs(struct super_block *sb)
-{
-	int ret = 0;
-	struct kset *device_kset = NULL;
-	struct kset *fcheck_kset = NULL;
-	struct ocfs2_filecheck *fcheck = NULL;
-	struct ocfs2_filecheck_sysfs_entry *entry = NULL;
-	struct attribute **attrs = NULL;
-	struct attribute_group attrgp;
-
-	if (!ocfs2_kset)
-		return -ENOMEM;
-
-	attrs = kmalloc(sizeof(struct attribute *) * 4, GFP_NOFS);
-	if (!attrs) {
-		ret = -ENOMEM;
-		goto error;
-	} else {
-		attrs[0] = &ocfs2_attr_filecheck_chk.attr;
-		attrs[1] = &ocfs2_attr_filecheck_fix.attr;
-		attrs[2] = &ocfs2_attr_filecheck_set.attr;
-		attrs[3] = NULL;
-		memset(&attrgp, 0, sizeof(attrgp));
-		attrgp.attrs = attrs;
-	}
+	int ret;
+	struct ocfs2_filecheck *fcheck;
+	struct ocfs2_filecheck_sysfs_entry *entry = &osb->osb_fc_ent;
 
 	fcheck = kmalloc(sizeof(struct ocfs2_filecheck), GFP_NOFS);
-	if (!fcheck) {
-		ret = -ENOMEM;
-		goto error;
-	} else {
-		INIT_LIST_HEAD(&fcheck->fc_head);
-		spin_lock_init(&fcheck->fc_lock);
-		fcheck->fc_max = OCFS2_FILECHECK_MINSIZE;
-		fcheck->fc_size = 0;
-		fcheck->fc_done = 0;
-	}
-
-	if (strlen(sb->s_id) <= 0) {
-		mlog(ML_ERROR,
-		"Cannot get device basename when create filecheck sysfs\n");
-		ret = -ENODEV;
-		goto error;
-	}
-
-	device_kset = kset_create_and_add(sb->s_id, NULL, &ocfs2_kset->kobj);
-	if (!device_kset) {
-		ret = -ENOMEM;
-		goto error;
-	}
-
-	fcheck_kset = kset_create_and_add("filecheck", NULL,
-					  &device_kset->kobj);
-	if (!fcheck_kset) {
-		ret = -ENOMEM;
-		goto error;
-	}
-
-	ret = sysfs_create_group(&fcheck_kset->kobj, &attrgp);
-	if (ret)
-		goto error;
+	if (!fcheck)
+		return -ENOMEM;
 
-	entry = kmalloc(sizeof(struct ocfs2_filecheck_sysfs_entry), GFP_NOFS);
-	if (!entry) {
-		ret = -ENOMEM;
-		goto error;
-	} else {
-		atomic_set(&entry->fs_count, 1);
-		entry->fs_sb = sb;
-		entry->fs_devicekset = device_kset;
-		entry->fs_fcheckkset = fcheck_kset;
-		entry->fs_fcheck = fcheck;
-		ocfs2_filecheck_sysfs_add(entry);
+	INIT_LIST_HEAD(&fcheck->fc_head);
+	spin_lock_init(&fcheck->fc_lock);
+	fcheck->fc_max = OCFS2_FILECHECK_MINSIZE;
+	fcheck->fc_size = 0;
+	fcheck->fc_done = 0;
+
+	entry->fs_kobj.kset = osb->osb_dev_kset;
+	init_completion(&entry->fs_kobj_unregister);
+	ret = kobject_init_and_add(&entry->fs_kobj, &ocfs2_ktype_filecheck,
+					NULL, "filecheck");
+	if (ret) {
+		kfree(fcheck);
+		return ret;
 	}
 
-	kfree(attrs);
+	entry->fs_fcheck = fcheck;
 	return 0;
-
-error:
-	kfree(attrs);
-	kfree(entry);
-	kfree(fcheck);
-	kset_unregister(fcheck_kset);
-	kset_unregister(device_kset);
-	return ret;
 }
 
-int ocfs2_filecheck_remove_sysfs(struct super_block *sb)
+void ocfs2_filecheck_remove_sysfs(struct ocfs2_super *osb)
 {
-	return ocfs2_filecheck_sysfs_del(sb->s_id);
+	if (!osb->osb_fc_ent.fs_fcheck)
+		return;
+
+	kobject_del(&osb->osb_fc_ent.fs_kobj);
+	kobject_put(&osb->osb_fc_ent.fs_kobj);
+	wait_for_completion(&osb->osb_fc_ent.fs_kobj_unregister);
+	ocfs2_filecheck_sysfs_free(&osb->osb_fc_ent);
 }
 
 static int
@@ -310,7 +226,7 @@ ocfs2_filecheck_adjust_max(struct ocfs2_filecheck_sysfs_entry *ent,
 
 	spin_lock(&ent->fs_fcheck->fc_lock);
 	if (len < (ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done)) {
-		mlog(ML_ERROR,
+		mlog(ML_NOTICE,
 		"Cannot set online file check maximum entry number "
 		"to %u due to too many pending entries(%u)\n",
 		len, ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done);
@@ -387,7 +303,7 @@ ocfs2_filecheck_args_parse(const char *name, const char *buf, size_t count,
 	return 0;
 }
 
-static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
+static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj,
 				    struct kobj_attribute *attr,
 				    char *buf)
 {
@@ -395,19 +311,12 @@ static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
 	ssize_t ret = 0, total = 0, remain = PAGE_SIZE;
 	unsigned int type;
 	struct ocfs2_filecheck_entry *p;
-	struct ocfs2_filecheck_sysfs_entry *ent;
+	struct ocfs2_filecheck_sysfs_entry *ent = container_of(kobj,
+				struct ocfs2_filecheck_sysfs_entry, fs_kobj);
 
 	if (ocfs2_filecheck_type_parse(attr->attr.name, &type))
 		return -EINVAL;
 
-	ent = ocfs2_filecheck_sysfs_get(kobj->parent->name);
-	if (!ent) {
-		mlog(ML_ERROR,
-		"Cannot get the corresponding entry via device basename %s\n",
-		kobj->name);
-		return -ENODEV;
-	}
-
 	if (type == OCFS2_FILECHECK_TYPE_SET) {
 		spin_lock(&ent->fs_fcheck->fc_lock);
 		total = snprintf(buf, remain, "%u\n", ent->fs_fcheck->fc_max);
@@ -441,11 +350,26 @@ static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
 	spin_unlock(&ent->fs_fcheck->fc_lock);
 
 exit:
-	ocfs2_filecheck_sysfs_put(ent);
 	return total;
 }
 
-static int
+static inline int
+ocfs2_filecheck_is_dup_entry(struct ocfs2_filecheck_sysfs_entry *ent,
+				unsigned long ino)
+{
+	struct ocfs2_filecheck_entry *p;
+
+	list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) {
+		if (!p->fe_done) {
+			if (p->fe_ino == ino)
+				return 1;
+		}
+	}
+
+	return 0;
+}
+
+static inline int
 ocfs2_filecheck_erase_entry(struct ocfs2_filecheck_sysfs_entry *ent)
 {
 	struct ocfs2_filecheck_entry *p;
@@ -484,21 +408,21 @@ static void
 ocfs2_filecheck_done_entry(struct ocfs2_filecheck_sysfs_entry *ent,
 			   struct ocfs2_filecheck_entry *entry)
 {
-	entry->fe_done = 1;
 	spin_lock(&ent->fs_fcheck->fc_lock);
+	entry->fe_done = 1;
 	ent->fs_fcheck->fc_done++;
 	spin_unlock(&ent->fs_fcheck->fc_lock);
 }
 
 static unsigned int
-ocfs2_filecheck_handle(struct super_block *sb,
+ocfs2_filecheck_handle(struct ocfs2_super *osb,
 		       unsigned long ino, unsigned int flags)
 {
 	unsigned int ret = OCFS2_FILECHECK_ERR_SUCCESS;
 	struct inode *inode = NULL;
 	int rc;
 
-	inode = ocfs2_iget(OCFS2_SB(sb), ino, flags, 0);
+	inode = ocfs2_iget(osb, ino, flags, 0);
 	if (IS_ERR(inode)) {
 		rc = (int)(-(long)inode);
 		if (rc >= OCFS2_FILECHECK_ERR_START &&
@@ -516,11 +440,14 @@ static void
 ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent,
 			     struct ocfs2_filecheck_entry *entry)
 {
+	struct ocfs2_super *osb = container_of(ent, struct ocfs2_super,
+						osb_fc_ent);
+
 	if (entry->fe_type == OCFS2_FILECHECK_TYPE_CHK)
-		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+		entry->fe_status = ocfs2_filecheck_handle(osb,
 				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_CHK);
 	else if (entry->fe_type == OCFS2_FILECHECK_TYPE_FIX)
-		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+		entry->fe_status = ocfs2_filecheck_handle(osb,
 				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_FIX);
 	else
 		entry->fe_status = OCFS2_FILECHECK_ERR_UNSUPPORTED;
@@ -528,30 +455,21 @@ ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent,
 	ocfs2_filecheck_done_entry(ent, entry);
 }
 
-static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
+static ssize_t ocfs2_filecheck_attr_store(struct kobject *kobj,
 				     struct kobj_attribute *attr,
 				     const char *buf, size_t count)
 {
+	ssize_t ret = 0;
 	struct ocfs2_filecheck_args args;
 	struct ocfs2_filecheck_entry *entry;
-	struct ocfs2_filecheck_sysfs_entry *ent;
-	ssize_t ret = 0;
+	struct ocfs2_filecheck_sysfs_entry *ent = container_of(kobj,
+				struct ocfs2_filecheck_sysfs_entry, fs_kobj);
 
 	if (count == 0)
 		return count;
 
-	if (ocfs2_filecheck_args_parse(attr->attr.name, buf, count, &args)) {
-		mlog(ML_ERROR, "Invalid arguments for online file check\n");
+	if (ocfs2_filecheck_args_parse(attr->attr.name, buf, count, &args))
 		return -EINVAL;
-	}
-
-	ent = ocfs2_filecheck_sysfs_get(kobj->parent->name);
-	if (!ent) {
-		mlog(ML_ERROR,
-		"Cannot get the corresponding entry via device basename %s\n",
-		kobj->parent->name);
-		return -ENODEV;
-	}
 
 	if (args.fa_type == OCFS2_FILECHECK_TYPE_SET) {
 		ret = ocfs2_filecheck_adjust_max(ent, args.fa_len);
@@ -565,13 +483,16 @@ static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
 	}
 
 	spin_lock(&ent->fs_fcheck->fc_lock);
-	if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
-	    (ent->fs_fcheck->fc_done == 0)) {
-		mlog(ML_ERROR,
+	if (ocfs2_filecheck_is_dup_entry(ent, args.fa_ino)) {
+		ret = -EEXIST;
+		kfree(entry);
+	} else if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
+		(ent->fs_fcheck->fc_done == 0)) {
+		mlog(ML_NOTICE,
 		"Cannot do more file check "
 		"since file check queue(%u) is full now\n",
 		ent->fs_fcheck->fc_max);
-		ret = -EBUSY;
+		ret = -EAGAIN;
 		kfree(entry);
 	} else {
 		if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
@@ -596,6 +517,5 @@ static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
 		ocfs2_filecheck_handle_entry(ent, entry);
 
 exit:
-	ocfs2_filecheck_sysfs_put(ent);
 	return (!ret ? count : ret);
 }
diff --git a/fs/ocfs2/filecheck.h b/fs/ocfs2/filecheck.h
index e5cd002a2c09..6a22ee79e8d0 100644
--- a/fs/ocfs2/filecheck.h
+++ b/fs/ocfs2/filecheck.h
@@ -43,7 +43,32 @@ enum {
 #define OCFS2_FILECHECK_ERR_START	OCFS2_FILECHECK_ERR_FAILED
 #define OCFS2_FILECHECK_ERR_END		OCFS2_FILECHECK_ERR_UNSUPPORTED
 
-int ocfs2_filecheck_create_sysfs(struct super_block *sb);
-int ocfs2_filecheck_remove_sysfs(struct super_block *sb);
+struct ocfs2_filecheck {
+	struct list_head fc_head;	/* File check entry list head */
+	spinlock_t fc_lock;
+	unsigned int fc_max;	/* Maximum number of entry in list */
+	unsigned int fc_size;	/* Current entry count in list */
+	unsigned int fc_done;	/* Finished entry count in list */
+};
+
+#define OCFS2_FILECHECK_MAXSIZE		100
+#define OCFS2_FILECHECK_MINSIZE		10
+
+/* File check operation type */
+enum {
+	OCFS2_FILECHECK_TYPE_CHK = 0,	/* Check a file(inode) */
+	OCFS2_FILECHECK_TYPE_FIX,	/* Fix a file(inode) */
+	OCFS2_FILECHECK_TYPE_SET = 100	/* Set entry list maximum size */
+};
+
+struct ocfs2_filecheck_sysfs_entry {	/* sysfs entry per partition */
+	struct kobject fs_kobj;
+	struct completion fs_kobj_unregister;
+	struct ocfs2_filecheck *fs_fcheck;
+};
+
+
+int ocfs2_filecheck_create_sysfs(struct ocfs2_super *osb);
+void ocfs2_filecheck_remove_sysfs(struct ocfs2_super *osb);
 
 #endif  /* FILECHECK_H */
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index d51b80edd972..ddc3e9470c87 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1135,7 +1135,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 	trace_ocfs2_clear_inode((unsigned long long)oi->ip_blkno,
 				inode->i_nlink);
 
-	mlog_bug_on_msg(OCFS2_SB(inode->i_sb) == NULL,
+	mlog_bug_on_msg(osb == NULL,
 			"Inode=%lu\n", inode->i_ino);
 
 	dquot_drop(inode);
@@ -1150,7 +1150,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 	ocfs2_mark_lockres_freeing(osb, &oi->ip_inode_lockres);
 	ocfs2_mark_lockres_freeing(osb, &oi->ip_open_lockres);
 
-	ocfs2_resv_discard(&OCFS2_SB(inode->i_sb)->osb_la_resmap,
+	ocfs2_resv_discard(&osb->osb_la_resmap,
 			   &oi->ip_la_data_resv);
 	ocfs2_resv_init_once(&oi->ip_la_data_resv);
 
@@ -1160,7 +1160,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 	 * exception here are successfully wiped inodes - their
 	 * metadata can now be considered to be part of the system
 	 * inodes from which it came. */
-	if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_DELETED))
+	if (!(oi->ip_flags & OCFS2_INODE_DELETED))
 		ocfs2_checkpoint_inode(inode);
 
 	mlog_bug_on_msg(!list_empty(&oi->ip_io_markers),
@@ -1223,7 +1223,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 	 * the journal is flushed before journal shutdown. Thus it is safe to
 	 * have inodes get cleaned up after journal shutdown.
 	 */
-	jbd2_journal_release_jbd_inode(OCFS2_SB(inode->i_sb)->journal->j_journal,
+	jbd2_journal_release_jbd_inode(osb->journal->j_journal,
 				       &oi->ip_jinode);
 }
 
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index c801eddc4bf3..8dd6f703c819 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -525,7 +525,7 @@ static int __ocfs2_mknod_locked(struct inode *dir,
 	 * these are used by the support functions here and in
 	 * callers. */
 	inode->i_ino = ino_from_blkno(osb->sb, fe_blkno);
-	OCFS2_I(inode)->ip_blkno = fe_blkno;
+	oi->ip_blkno = fe_blkno;
 	spin_lock(&osb->osb_lock);
 	inode->i_generation = osb->s_next_generation++;
 	spin_unlock(&osb->osb_lock);
@@ -1186,8 +1186,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 	}
 
 	trace_ocfs2_double_lock_end(
-			(unsigned long long)OCFS2_I(inode1)->ip_blkno,
-			(unsigned long long)OCFS2_I(inode2)->ip_blkno);
+			(unsigned long long)oi1->ip_blkno,
+			(unsigned long long)oi2->ip_blkno);
 
 bail:
 	if (status)
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 6867eef2e06b..4f86ac0027b5 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -50,6 +50,8 @@
 
 #include "reservations.h"
 
+#include "filecheck.h"
+
 /* Caching of metadata buffers */
 
 /* Most user visible OCFS2 inodes will have very few pieces of
@@ -472,6 +474,12 @@ struct ocfs2_super
 	 * workqueue and schedule on our own.
 	 */
 	struct workqueue_struct *ocfs2_wq;
+
+	/* sysfs directory per partition */
+	struct kset *osb_dev_kset;
+
+	/* file check related stuff */
+	struct ocfs2_filecheck_sysfs_entry osb_fc_ent;
 };
 
 #define OCFS2_SB(sb)	    ((struct ocfs2_super *)(sb)->s_fs_info)
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index e2a11aaece10..2ee76a90ba8f 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -1311,11 +1311,11 @@ DEFINE_OCFS2_FILE_OPS(ocfs2_file_release);
 
 DEFINE_OCFS2_FILE_OPS(ocfs2_sync_file);
 
-DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_write);
+DEFINE_OCFS2_FILE_OPS(ocfs2_file_write_iter);
 
 DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_write);
 
-DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_read);
+DEFINE_OCFS2_FILE_OPS(ocfs2_file_read_iter);
 
 DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_truncate_file);
 
@@ -1467,7 +1467,7 @@ TRACE_EVENT(ocfs2_prepare_inode_for_write,
 		  __entry->saved_pos, __entry->count, __entry->wait)
 );
 
-DEFINE_OCFS2_INT_EVENT(generic_file_aio_read_ret);
+DEFINE_OCFS2_INT_EVENT(generic_file_read_iter_ret);
 
 /* End of trace events for fs/ocfs2/file.c. */
 
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index ab156e35ec00..01c6b3894406 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -573,7 +573,7 @@ static int ocfs2_create_refcount_tree(struct inode *inode,
 	BUG_ON(ocfs2_is_refcount_inode(inode));
 
 	trace_ocfs2_create_refcount_tree(
-		(unsigned long long)OCFS2_I(inode)->ip_blkno);
+		(unsigned long long)oi->ip_blkno);
 
 	ret = ocfs2_reserve_new_metadata_blocks(osb, 1, &meta_ac);
 	if (ret) {
@@ -3359,7 +3359,7 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context)
 	unsigned int ext_flags;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) {
+	if (!ocfs2_refcount_tree(osb)) {
 		return ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n",
 				   inode->i_ino);
 	}
@@ -3707,7 +3707,7 @@ int ocfs2_add_refcount_flag(struct inode *inode,
 	trace_ocfs2_add_refcount_flag(ref_blocks, credits);
 
 	if (ref_blocks) {
-		ret = ocfs2_reserve_new_metadata_blocks(OCFS2_SB(inode->i_sb),
+		ret = ocfs2_reserve_new_metadata_blocks(osb,
 							ref_blocks, &meta_ac);
 		if (ret) {
 			mlog_errno(ret);
@@ -4766,8 +4766,8 @@ static int ocfs2_reflink_inodes_lock(struct inode *s_inode,
 		*bh2 = *bh1;
 
 	trace_ocfs2_double_lock_end(
-			(unsigned long long)OCFS2_I(inode1)->ip_blkno,
-			(unsigned long long)OCFS2_I(inode2)->ip_blkno);
+			(unsigned long long)oi1->ip_blkno,
+			(unsigned long long)oi2->ip_blkno);
 
 	return 0;
 
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index d8f5f6ce99dc..f7c972fbed6a 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -79,8 +79,6 @@ static u64 ocfs2_group_from_res(struct ocfs2_suballoc_result *res)
 	return ocfs2_which_suballoc_group(res->sr_blkno, res->sr_bit_offset);
 }
 
-static inline void ocfs2_debug_bg(struct ocfs2_group_desc *bg);
-static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe);
 static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl);
 static int ocfs2_block_group_fill(handle_t *handle,
 				  struct inode *alloc_inode,
@@ -387,7 +385,7 @@ static int ocfs2_block_group_fill(handle_t *handle,
 
 	memset(bg, 0, sb->s_blocksize);
 	strcpy(bg->bg_signature, OCFS2_GROUP_DESC_SIGNATURE);
-	bg->bg_generation = cpu_to_le32(OCFS2_SB(sb)->fs_generation);
+	bg->bg_generation = cpu_to_le32(osb->fs_generation);
 	bg->bg_size = cpu_to_le16(ocfs2_group_bitmap_size(sb, 1,
 						osb->s_feature_incompat));
 	bg->bg_chain = cpu_to_le16(my_chain);
@@ -1521,7 +1519,7 @@ static int ocfs2_cluster_group_search(struct inode *inode,
 				OCFS2_I(inode)->ip_clusters, max_bits);
 		}
 
-		ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb),
+		ret = ocfs2_block_group_find_clear_bits(osb,
 							group_bh, bits_wanted,
 							max_bits, res);
 		if (ret)
@@ -2626,53 +2624,6 @@ int ocfs2_release_clusters(handle_t *handle,
 				    _ocfs2_clear_bit);
 }
 
-static inline void ocfs2_debug_bg(struct ocfs2_group_desc *bg)
-{
-	printk("Block Group:\n");
-	printk("bg_signature:       %s\n", bg->bg_signature);
-	printk("bg_size:            %u\n", bg->bg_size);
-	printk("bg_bits:            %u\n", bg->bg_bits);
-	printk("bg_free_bits_count: %u\n", bg->bg_free_bits_count);
-	printk("bg_chain:           %u\n", bg->bg_chain);
-	printk("bg_generation:      %u\n", le32_to_cpu(bg->bg_generation));
-	printk("bg_next_group:      %llu\n",
-	       (unsigned long long)bg->bg_next_group);
-	printk("bg_parent_dinode:   %llu\n",
-	       (unsigned long long)bg->bg_parent_dinode);
-	printk("bg_blkno:           %llu\n",
-	       (unsigned long long)bg->bg_blkno);
-}
-
-static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe)
-{
-	int i;
-
-	printk("Suballoc Inode %llu:\n", (unsigned long long)fe->i_blkno);
-	printk("i_signature:                  %s\n", fe->i_signature);
-	printk("i_size:                       %llu\n",
-	       (unsigned long long)fe->i_size);
-	printk("i_clusters:                   %u\n", fe->i_clusters);
-	printk("i_generation:                 %u\n",
-	       le32_to_cpu(fe->i_generation));
-	printk("id1.bitmap1.i_used:           %u\n",
-	       le32_to_cpu(fe->id1.bitmap1.i_used));
-	printk("id1.bitmap1.i_total:          %u\n",
-	       le32_to_cpu(fe->id1.bitmap1.i_total));
-	printk("id2.i_chain.cl_cpg:           %u\n", fe->id2.i_chain.cl_cpg);
-	printk("id2.i_chain.cl_bpc:           %u\n", fe->id2.i_chain.cl_bpc);
-	printk("id2.i_chain.cl_count:         %u\n", fe->id2.i_chain.cl_count);
-	printk("id2.i_chain.cl_next_free_rec: %u\n",
-	       fe->id2.i_chain.cl_next_free_rec);
-	for(i = 0; i < fe->id2.i_chain.cl_next_free_rec; i++) {
-		printk("fe->id2.i_chain.cl_recs[%d].c_free:  %u\n", i,
-		       fe->id2.i_chain.cl_recs[i].c_free);
-		printk("fe->id2.i_chain.cl_recs[%d].c_total: %u\n", i,
-		       fe->id2.i_chain.cl_recs[i].c_total);
-		printk("fe->id2.i_chain.cl_recs[%d].c_blkno: %llu\n", i,
-		       (unsigned long long)fe->id2.i_chain.cl_recs[i].c_blkno);
-	}
-}
-
 /*
  * For a given allocation, determine which allocators will need to be
  * accessed, and lock them, reserving the appropriate number of bits.
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index ffa4952d432b..3415e0b09398 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -423,10 +423,10 @@ static int ocfs2_sync_fs(struct super_block *sb, int wait)
 		ocfs2_schedule_truncate_log_flush(osb, 0);
 	}
 
-	if (jbd2_journal_start_commit(OCFS2_SB(sb)->journal->j_journal,
+	if (jbd2_journal_start_commit(osb->journal->j_journal,
 				      &target)) {
 		if (wait)
-			jbd2_log_wait_commit(OCFS2_SB(sb)->journal->j_journal,
+			jbd2_log_wait_commit(osb->journal->j_journal,
 					     target);
 	}
 	return 0;
@@ -1161,6 +1161,23 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 
 	ocfs2_complete_mount_recovery(osb);
 
+	osb->osb_dev_kset = kset_create_and_add(sb->s_id, NULL,
+						&ocfs2_kset->kobj);
+	if (!osb->osb_dev_kset) {
+		status = -ENOMEM;
+		mlog(ML_ERROR, "Unable to create device kset %s.\n", sb->s_id);
+		goto read_super_error;
+	}
+
+	/* Create filecheck sysfs related directories/files at
+	 * /sys/fs/ocfs2/<devname>/filecheck */
+	if (ocfs2_filecheck_create_sysfs(osb)) {
+		status = -ENOMEM;
+		mlog(ML_ERROR, "Unable to create filecheck sysfs directory at "
+			"/sys/fs/ocfs2/%s/filecheck.\n", sb->s_id);
+		goto read_super_error;
+	}
+
 	if (ocfs2_mount_local(osb))
 		snprintf(nodestr, sizeof(nodestr), "local");
 	else
@@ -1199,9 +1216,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 	/* Start this when the mount is almost sure of being successful */
 	ocfs2_orphan_scan_start(osb);
 
-	/* Create filecheck sysfile /sys/fs/ocfs2/<devname>/filecheck */
-	ocfs2_filecheck_create_sysfs(sb);
-
 	return status;
 
 read_super_error:
@@ -1653,7 +1667,6 @@ static void ocfs2_put_super(struct super_block *sb)
 
 	ocfs2_sync_blockdev(sb);
 	ocfs2_dismount_volume(sb, 0);
-	ocfs2_filecheck_remove_sysfs(sb);
 }
 
 static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -1768,12 +1781,9 @@ static int ocfs2_initialize_mem_caches(void)
 					NULL);
 	if (!ocfs2_inode_cachep || !ocfs2_dquot_cachep ||
 	    !ocfs2_qf_chunk_cachep) {
-		if (ocfs2_inode_cachep)
-			kmem_cache_destroy(ocfs2_inode_cachep);
-		if (ocfs2_dquot_cachep)
-			kmem_cache_destroy(ocfs2_dquot_cachep);
-		if (ocfs2_qf_chunk_cachep)
-			kmem_cache_destroy(ocfs2_qf_chunk_cachep);
+		kmem_cache_destroy(ocfs2_inode_cachep);
+		kmem_cache_destroy(ocfs2_dquot_cachep);
+		kmem_cache_destroy(ocfs2_qf_chunk_cachep);
 		return -ENOMEM;
 	}
 
@@ -1787,16 +1797,13 @@ static void ocfs2_free_mem_caches(void)
 	 * destroy cache.
 	 */
 	rcu_barrier();
-	if (ocfs2_inode_cachep)
-		kmem_cache_destroy(ocfs2_inode_cachep);
+	kmem_cache_destroy(ocfs2_inode_cachep);
 	ocfs2_inode_cachep = NULL;
 
-	if (ocfs2_dquot_cachep)
-		kmem_cache_destroy(ocfs2_dquot_cachep);
+	kmem_cache_destroy(ocfs2_dquot_cachep);
 	ocfs2_dquot_cachep = NULL;
 
-	if (ocfs2_qf_chunk_cachep)
-		kmem_cache_destroy(ocfs2_qf_chunk_cachep);
+	kmem_cache_destroy(ocfs2_qf_chunk_cachep);
 	ocfs2_qf_chunk_cachep = NULL;
 }
 
@@ -1899,6 +1906,12 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	osb = OCFS2_SB(sb);
 	BUG_ON(!osb);
 
+	/* Remove file check sysfs related directores/files,
+	 * and wait for the pending file check operations */
+	ocfs2_filecheck_remove_sysfs(osb);
+
+	kset_unregister(osb->osb_dev_kset);
+
 	debugfs_remove(osb->osb_ctxt);
 
 	/* Orphan scan should be stopped as early as possible */
diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c
index 82e17b076ce7..78f09c76ab3c 100644
--- a/fs/ocfs2/uptodate.c
+++ b/fs/ocfs2/uptodate.c
@@ -633,6 +633,5 @@ int __init init_ocfs2_uptodate_cache(void)
 
 void exit_ocfs2_uptodate_cache(void)
 {
-	if (ocfs2_uptodate_cachep)
-		kmem_cache_destroy(ocfs2_uptodate_cachep);
+	kmem_cache_destroy(ocfs2_uptodate_cachep);
 }
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index c261c1dfd374..3a24ce3deb01 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -3564,7 +3564,7 @@ int ocfs2_xattr_set(struct inode *inode,
 		.not_found = -ENODATA,
 	};
 
-	if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb)))
+	if (!ocfs2_supports_xattr(osb))
 		return -EOPNOTSUPP;
 
 	/*