Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc bits

 - ocfs2 updates

 - almost all of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (131 commits)
  memory hotplug: fix comments when adding section
  mm: make alloc_node_mem_map a void call if we don't have CONFIG_FLAT_NODE_MEM_MAP
  mm: simplify nodemask printing
  mm,oom_reaper: remove pointless kthread_run() error check
  mm/page_ext.c: check if page_ext is not prepared
  writeback: remove unused function parameter
  mm: do not rely on preempt_count in print_vma_addr
  mm, sparse: do not swamp log with huge vmemmap allocation failures
  mm/hmm: remove redundant variable align_end
  mm/list_lru.c: mark expected switch fall-through
  mm/shmem.c: mark expected switch fall-through
  mm/page_alloc.c: broken deferred calculation
  mm: don't warn about allocations which stall for too long
  fs: fuse: account fuse_inode slab memory as reclaimable
  mm, page_alloc: fix potential false positive in __zone_watermark_ok
  mm: mlock: remove lru_add_drain_all()
  mm, sysctl: make NUMA stats configurable
  shmem: convert shmem_init_inodecache() to void
  Unify migrate_pages and move_pages access checks
  mm, pagevec: rename pagevec drained field
  ...

13 files changed, 86 insertions, 38 deletions

diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index addd7c5f2d3e..ab5105f9767e 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -3585,8 +3585,6 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path,
 		 * The easy case - we can just plop the record right in.
 		 */
 		*left_rec = *split_rec;
-
-		has_empty_extent = 0;
 	} else
 		le16_add_cpu(&left_rec->e_leaf_clusters, split_clusters);
 
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 88a31e9340a0..d1516327b787 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -134,6 +134,19 @@ bail:
 	return err;
 }
 
+static int ocfs2_lock_get_block(struct inode *inode, sector_t iblock,
+		    struct buffer_head *bh_result, int create)
+{
+	int ret = 0;
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+
+	down_read(&oi->ip_alloc_sem);
+	ret = ocfs2_get_block(inode, iblock, bh_result, create);
+	up_read(&oi->ip_alloc_sem);
+
+	return ret;
+}
+
 int ocfs2_get_block(struct inode *inode, sector_t iblock,
 		    struct buffer_head *bh_result, int create)
 {
@@ -2128,7 +2141,7 @@ static void ocfs2_dio_free_write_ctx(struct inode *inode,
  * called like this: dio->get_blocks(dio->inode, fs_startblk,
  * 					fs_count, map_bh, dio->rw == WRITE);
  */
-static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock,
+static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
 			       struct buffer_head *bh_result, int create)
 {
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -2154,12 +2167,9 @@ static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock,
 	 * while file size will be changed.
 	 */
 	if (pos + total_len <= i_size_read(inode)) {
-		down_read(&oi->ip_alloc_sem);
-		/* This is the fast path for re-write. */
-		ret = ocfs2_get_block(inode, iblock, bh_result, create);
-
-		up_read(&oi->ip_alloc_sem);
 
+		/* This is the fast path for re-write. */
+		ret = ocfs2_lock_get_block(inode, iblock, bh_result, create);
 		if (buffer_mapped(bh_result) &&
 		    !buffer_new(bh_result) &&
 		    ret == 0)
@@ -2424,9 +2434,9 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		return 0;
 
 	if (iov_iter_rw(iter) == READ)
-		get_block = ocfs2_get_block;
+		get_block = ocfs2_lock_get_block;
 	else
-		get_block = ocfs2_dio_get_block;
+		get_block = ocfs2_dio_wr_get_block;
 
 	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
 				    iter, get_block,
diff --git a/fs/ocfs2/buffer_head_io.h b/fs/ocfs2/buffer_head_io.h
index b97bcc6dde7c..b1bb70c8ca4d 100644
--- a/fs/ocfs2/buffer_head_io.h
+++ b/fs/ocfs2/buffer_head_io.h
@@ -28,9 +28,6 @@
 
 #include <linux/buffer_head.h>
 
-void ocfs2_end_buffer_io_sync(struct buffer_head *bh,
-			     int uptodate);
-
 int ocfs2_write_block(struct ocfs2_super          *osb,
 		      struct buffer_head  *bh,
 		      struct ocfs2_caching_info   *ci);
diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h
index 3ef5137dc362..a9e67efc0004 100644
--- a/fs/ocfs2/cluster/heartbeat.h
+++ b/fs/ocfs2/cluster/heartbeat.h
@@ -79,10 +79,8 @@ void o2hb_fill_node_map(unsigned long *map,
 			unsigned bytes);
 void o2hb_exit(void);
 int o2hb_init(void);
-int o2hb_check_node_heartbeating(u8 node_num);
 int o2hb_check_node_heartbeating_no_sem(u8 node_num);
 int o2hb_check_node_heartbeating_from_callback(u8 node_num);
-int o2hb_check_local_node_heartbeating(void);
 void o2hb_stop_all_regions(void);
 int o2hb_get_all_regions(char *region_uuids, u8 numregions);
 int o2hb_global_heartbeat_active(void);
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index a51200ece93d..da64c3a20eeb 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -40,6 +40,9 @@ char *o2nm_fence_method_desc[O2NM_FENCE_METHODS] = {
 		"panic",	/* O2NM_FENCE_PANIC */
 };
 
+static inline void o2nm_lock_subsystem(void);
+static inline void o2nm_unlock_subsystem(void);
+
 struct o2nm_node *o2nm_get_node_by_num(u8 node_num)
 {
 	struct o2nm_node *node = NULL;
@@ -181,7 +184,10 @@ static struct o2nm_cluster *to_o2nm_cluster_from_node(struct o2nm_node *node)
 {
 	/* through the first node_set .parent
 	 * mycluster/nodes/mynode == o2nm_cluster->o2nm_node_group->o2nm_node */
-	return to_o2nm_cluster(node->nd_item.ci_parent->ci_parent);
+	if (node->nd_item.ci_parent)
+		return to_o2nm_cluster(node->nd_item.ci_parent->ci_parent);
+	else
+		return NULL;
 }
 
 enum {
@@ -194,7 +200,7 @@ static ssize_t o2nm_node_num_store(struct config_item *item, const char *page,
 				   size_t count)
 {
 	struct o2nm_node *node = to_o2nm_node(item);
-	struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node);
+	struct o2nm_cluster *cluster;
 	unsigned long tmp;
 	char *p = (char *)page;
 	int ret = 0;
@@ -214,6 +220,13 @@ static ssize_t o2nm_node_num_store(struct config_item *item, const char *page,
 	    !test_bit(O2NM_NODE_ATTR_PORT, &node->nd_set_attributes))
 		return -EINVAL; /* XXX */
 
+	o2nm_lock_subsystem();
+	cluster = to_o2nm_cluster_from_node(node);
+	if (!cluster) {
+		o2nm_unlock_subsystem();
+		return -EINVAL;
+	}
+
 	write_lock(&cluster->cl_nodes_lock);
 	if (cluster->cl_nodes[tmp])
 		ret = -EEXIST;
@@ -226,6 +239,8 @@ static ssize_t o2nm_node_num_store(struct config_item *item, const char *page,
 		set_bit(tmp, cluster->cl_nodes_bitmap);
 	}
 	write_unlock(&cluster->cl_nodes_lock);
+	o2nm_unlock_subsystem();
+
 	if (ret)
 		return ret;
 
@@ -269,7 +284,7 @@ static ssize_t o2nm_node_ipv4_address_store(struct config_item *item,
 					    size_t count)
 {
 	struct o2nm_node *node = to_o2nm_node(item);
-	struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node);
+	struct o2nm_cluster *cluster;
 	int ret, i;
 	struct rb_node **p, *parent;
 	unsigned int octets[4];
@@ -286,6 +301,13 @@ static ssize_t o2nm_node_ipv4_address_store(struct config_item *item,
 		be32_add_cpu(&ipv4_addr, octets[i] << (i * 8));
 	}
 
+	o2nm_lock_subsystem();
+	cluster = to_o2nm_cluster_from_node(node);
+	if (!cluster) {
+		o2nm_unlock_subsystem();
+		return -EINVAL;
+	}
+
 	ret = 0;
 	write_lock(&cluster->cl_nodes_lock);
 	if (o2nm_node_ip_tree_lookup(cluster, ipv4_addr, &p, &parent))
@@ -298,6 +320,8 @@ static ssize_t o2nm_node_ipv4_address_store(struct config_item *item,
 		rb_insert_color(&node->nd_ip_node, &cluster->cl_node_ip_tree);
 	}
 	write_unlock(&cluster->cl_nodes_lock);
+	o2nm_unlock_subsystem();
+
 	if (ret)
 		return ret;
 
@@ -315,7 +339,7 @@ static ssize_t o2nm_node_local_store(struct config_item *item, const char *page,
 				     size_t count)
 {
 	struct o2nm_node *node = to_o2nm_node(item);
-	struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node);
+	struct o2nm_cluster *cluster;
 	unsigned long tmp;
 	char *p = (char *)page;
 	ssize_t ret;
@@ -333,17 +357,26 @@ static ssize_t o2nm_node_local_store(struct config_item *item, const char *page,
 	    !test_bit(O2NM_NODE_ATTR_PORT, &node->nd_set_attributes))
 		return -EINVAL; /* XXX */
 
+	o2nm_lock_subsystem();
+	cluster = to_o2nm_cluster_from_node(node);
+	if (!cluster) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	/* the only failure case is trying to set a new local node
 	 * when a different one is already set */
 	if (tmp && tmp == cluster->cl_has_local &&
-	    cluster->cl_local_node != node->nd_num)
-		return -EBUSY;
+	    cluster->cl_local_node != node->nd_num) {
+		ret = -EBUSY;
+		goto out;
+	}
 
 	/* bring up the rx thread if we're setting the new local node. */
 	if (tmp && !cluster->cl_has_local) {
 		ret = o2net_start_listening(node);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	if (!tmp && cluster->cl_has_local &&
@@ -358,7 +391,11 @@ static ssize_t o2nm_node_local_store(struct config_item *item, const char *page,
 		cluster->cl_local_node = node->nd_num;
 	}
 
-	return count;
+	ret = count;
+
+out:
+	o2nm_unlock_subsystem();
+	return ret;
 }
 
 CONFIGFS_ATTR(o2nm_node_, num);
@@ -738,6 +775,16 @@ static struct o2nm_cluster_group o2nm_cluster_group = {
 	},
 };
 
+static inline void o2nm_lock_subsystem(void)
+{
+	mutex_lock(&o2nm_cluster_group.cs_subsys.su_mutex);
+}
+
+static inline void o2nm_unlock_subsystem(void)
+{
+	mutex_unlock(&o2nm_cluster_group.cs_subsys.su_mutex);
+}
+
 int o2nm_depend_item(struct config_item *item)
 {
 	return configfs_depend_item(&o2nm_cluster_group.cs_subsys, item);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index a2b19fbdcf46..e1fea149f50b 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -394,7 +394,6 @@ int dlm_domain_fully_joined(struct dlm_ctxt *dlm)
 static void dlm_destroy_dlm_worker(struct dlm_ctxt *dlm)
 {
 	if (dlm->dlm_worker) {
-		flush_workqueue(dlm->dlm_worker);
 		destroy_workqueue(dlm->dlm_worker);
 		dlm->dlm_worker = NULL;
 	}
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 3e04279446e8..9c3e0f13ca87 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2616,7 +2616,9 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
 	 * otherwise the assert_master from the new
 	 * master will destroy this.
 	 */
-	dlm_get_mle_inuse(mle);
+	if (ret != -EEXIST)
+		dlm_get_mle_inuse(mle);
+
 	spin_unlock(&dlm->master_lock);
 	spin_unlock(&dlm->spinlock);
 
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 74407c6dd592..ec8f75813beb 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -2419,6 +2419,7 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 					dlm_lockres_put(res);
 					continue;
 				}
+				dlm_move_lockres_to_recovery_list(dlm, res);
 			} else if (res->owner == dlm->node_num) {
 				dlm_free_dead_locks(dlm, res, dead_node);
 				__dlm_lockres_calc_usage(dlm, res);
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 988137de08f5..9c7c18c0e129 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -670,7 +670,6 @@ static void __exit exit_dlmfs_fs(void)
 {
 	unregister_filesystem(&dlmfs_fs_type);
 
-	flush_workqueue(user_dlm_worker);
 	destroy_workqueue(user_dlm_worker);
 
 	/*
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 6e41fc8fabbe..dc455d45a66a 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1161,6 +1161,13 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 	}
 	size_change = S_ISREG(inode->i_mode) && attr->ia_valid & ATTR_SIZE;
 	if (size_change) {
+		/*
+		 * Here we should wait dio to finish before inode lock
+		 * to avoid a deadlock between ocfs2_setattr() and
+		 * ocfs2_dio_end_io_write()
+		 */
+		inode_dio_wait(inode);
+
 		status = ocfs2_rw_lock(inode, 1);
 		if (status < 0) {
 			mlog_errno(status);
@@ -1200,8 +1207,6 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		if (status)
 			goto bail_unlock;
 
-		inode_dio_wait(inode);
-
 		if (i_size_read(inode) >= attr->ia_size) {
 			if (ocfs2_should_order_data(inode)) {
 				status = ocfs2_begin_ordered_truncate(inode,
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 71f22c8fbffd..9f0b95abc09f 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1147,12 +1147,9 @@ int ocfs2_reserve_cluster_bitmap_bits(struct ocfs2_super *osb,
 					     GLOBAL_BITMAP_SYSTEM_INODE,
 					     OCFS2_INVALID_SLOT, NULL,
 					     ALLOC_NEW_GROUP);
-	if (status < 0 && status != -ENOSPC) {
+	if (status < 0 && status != -ENOSPC)
 		mlog_errno(status);
-		goto bail;
-	}
 
-bail:
 	return status;
 }
 
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 80733496b22a..040bbb6a6e4b 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -2521,10 +2521,8 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
 	/* This function assumes that the caller has the main osb resource */
 
 	/* ocfs2_initializer_super have already created this workqueue */
-	if (osb->ocfs2_wq) {
-		flush_workqueue(osb->ocfs2_wq);
+	if (osb->ocfs2_wq)
 		destroy_workqueue(osb->ocfs2_wq);
-	}
 
 	ocfs2_free_slot_info(osb);
 
diff --git a/fs/ocfs2/super.h b/fs/ocfs2/super.h
index b023e4f3d740..d4550c8bbc41 100644
--- a/fs/ocfs2/super.h
+++ b/fs/ocfs2/super.h
@@ -26,9 +26,6 @@
 #ifndef OCFS2_SUPER_H
 #define OCFS2_SUPER_H
 
-int ocfs2_publish_get_mount_state(struct ocfs2_super *osb,
-				  int node_num);
-
 __printf(3, 4)
 int __ocfs2_error(struct super_block *sb, const char *function,
 		   const char *fmt, ...);