Merge tag 'v4.4.55' into linux-linaro-lsk-v4.4lsk-v4.4-17.03

 This is the 4.4.55 stable release

17 files changed, 244 insertions, 123 deletions

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 239bc9cba28c..f54f77037d22 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -644,6 +644,9 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
 {
 	dout("__unregister_request %p tid %lld\n", req, req->r_tid);
 
+	/* Never leave an unregistered request on an unsafe list! */
+	list_del_init(&req->r_unsafe_item);
+
 	if (req->r_tid == mdsc->oldest_tid) {
 		struct rb_node *p = rb_next(&req->r_node);
 		mdsc->oldest_tid = 0;
@@ -1051,7 +1054,6 @@ static void cleanup_session_requests(struct ceph_mds_client *mdsc,
 	while (!list_empty(&session->s_unsafe)) {
 		req = list_first_entry(&session->s_unsafe,
 				       struct ceph_mds_request, r_unsafe_item);
-		list_del_init(&req->r_unsafe_item);
 		pr_warn_ratelimited(" dropping unsafe request %llu\n",
 				    req->r_tid);
 		__unregister_request(mdsc, req);
@@ -2477,7 +2479,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 			 * useful we could do with a revised return value.
 			 */
 			dout("got safe reply %llu, mds%d\n", tid, mds);
-			list_del_init(&req->r_unsafe_item);
 
 			/* last unsafe request during umount? */
 			if (mdsc->stopping && !__get_oldest_req(mdsc))
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 9da42ace762a..8a456f9b8a44 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5362,7 +5362,8 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	ext4_lblk_t stop, *iterator, ex_start, ex_end;
 
 	/* Let path point to the last extent */
-	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
+				EXT4_EX_NOCACHE);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 
@@ -5371,15 +5372,15 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	if (!extent)
 		goto out;
 
-	stop = le32_to_cpu(extent->ee_block) +
-			ext4_ext_get_actual_len(extent);
+	stop = le32_to_cpu(extent->ee_block);
 
        /*
 	 * In case of left shift, Don't start shifting extents until we make
 	 * sure the hole is big enough to accommodate the shift.
 	*/
 	if (SHIFT == SHIFT_LEFT) {
-		path = ext4_find_extent(inode, start - 1, &path, 0);
+		path = ext4_find_extent(inode, start - 1, &path,
+					EXT4_EX_NOCACHE);
 		if (IS_ERR(path))
 			return PTR_ERR(path);
 		depth = path->p_depth;
@@ -5411,9 +5412,14 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	else
 		iterator = &stop;
 
-	/* Its safe to start updating extents */
-	while (start < stop) {
-		path = ext4_find_extent(inode, *iterator, &path, 0);
+	/*
+	 * Its safe to start updating extents.  Start and stop are unsigned, so
+	 * in case of right shift if extent with 0 block is reached, iterator
+	 * becomes NULL to indicate the end of the loop.
+	 */
+	while (iterator && start <= stop) {
+		path = ext4_find_extent(inode, *iterator, &path,
+					EXT4_EX_NOCACHE);
 		if (IS_ERR(path))
 			return PTR_ERR(path);
 		depth = path->p_depth;
@@ -5440,8 +5446,11 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 					ext4_ext_get_actual_len(extent);
 		} else {
 			extent = EXT_FIRST_EXTENT(path[depth].p_hdr);
-			*iterator =  le32_to_cpu(extent->ee_block) > 0 ?
-				le32_to_cpu(extent->ee_block) - 1 : 0;
+			if (le32_to_cpu(extent->ee_block) > 0)
+				*iterator = le32_to_cpu(extent->ee_block) - 1;
+			else
+				/* Beginning is reached, end of the loop */
+				iterator = NULL;
 			/* Update path extent in case we need to stop */
 			while (le32_to_cpu(extent->ee_block) < start)
 				extent++;
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 8968a93e2150..d4be4e23bc21 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -933,8 +933,15 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 				  struct page *page)
 {
 	int i_size_changed = 0;
+	int ret;
 
-	copied = ext4_write_inline_data_end(inode, pos, len, copied, page);
+	ret = ext4_write_inline_data_end(inode, pos, len, copied, page);
+	if (ret < 0) {
+		unlock_page(page);
+		put_page(page);
+		return ret;
+	}
+	copied = ret;
 
 	/*
 	 * No need to use i_size_read() here, the i_size
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 10690e5ba2eb..7dcc97eadb12 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1165,8 +1165,11 @@ static int ext4_write_end(struct file *file,
 	if (ext4_has_inline_data(inode)) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
 						 copied, page);
-		if (ret < 0)
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
 			goto errout;
+		}
 		copied = ret;
 	} else
 		copied = block_write_end(file, mapping, pos,
@@ -1220,7 +1223,9 @@ errout:
  * set the buffer to be dirty, since in data=journalled mode we need
  * to call ext4_handle_dirty_metadata() instead.
  */
-static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
+static void ext4_journalled_zero_new_buffers(handle_t *handle,
+					    struct page *page,
+					    unsigned from, unsigned to)
 {
 	unsigned int block_start = 0, block_end;
 	struct buffer_head *head, *bh;
@@ -1237,7 +1242,7 @@ static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
 					size = min(to, block_end) - start;
 
 					zero_user(page, start, size);
-					set_buffer_uptodate(bh);
+					write_end_fn(handle, bh);
 				}
 				clear_buffer_new(bh);
 			}
@@ -1266,18 +1271,25 @@ static int ext4_journalled_write_end(struct file *file,
 
 	BUG_ON(!ext4_handle_valid(handle));
 
-	if (ext4_has_inline_data(inode))
-		copied = ext4_write_inline_data_end(inode, pos, len,
-						    copied, page);
-	else {
-		if (copied < len) {
-			if (!PageUptodate(page))
-				copied = 0;
-			zero_new_buffers(page, from+copied, to);
+	if (ext4_has_inline_data(inode)) {
+		ret = ext4_write_inline_data_end(inode, pos, len,
+						 copied, page);
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
+			goto errout;
 		}
-
+		copied = ret;
+	} else if (unlikely(copied < len) && !PageUptodate(page)) {
+		copied = 0;
+		ext4_journalled_zero_new_buffers(handle, page, from, to);
+	} else {
+		if (unlikely(copied < len))
+			ext4_journalled_zero_new_buffers(handle, page,
+							 from + copied, to);
 		ret = ext4_walk_page_buffers(handle, page_buffers(page), from,
-					     to, &partial, write_end_fn);
+					     from + copied, &partial,
+					     write_end_fn);
 		if (!partial)
 			SetPageUptodate(page);
 	}
@@ -1303,6 +1315,7 @@ static int ext4_journalled_write_end(struct file *file,
 		 */
 		ext4_orphan_add(handle, inode);
 
+errout:
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
@@ -3560,6 +3573,10 @@ static int ext4_block_truncate_page(handle_t *handle,
 	unsigned blocksize;
 	struct inode *inode = mapping->host;
 
+	/* If we are processing an encrypted inode during orphan list handling */
+	if (ext4_encrypted_inode(inode) && !ext4_has_encryption_key(inode))
+		return 0;
+
 	blocksize = inode->i_sb->s_blocksize;
 	length = blocksize - (offset & (blocksize - 1));
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index b7a3957a9dca..84cd77663e1f 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3120,6 +3120,13 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	if (ar->pright && start + size - 1 >= ar->lright)
 		size -= start + size - ar->lright;
 
+	/*
+	 * Trim allocation request for filesystems with artificially small
+	 * groups.
+	 */
+	if (size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb))
+		size = EXT4_BLOCKS_PER_GROUP(ac->ac_sb);
+
 	end = start + size;
 
 	/* check we don't cross already preallocated blocks */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b405a7b74ce0..6fe8e30eeb99 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -793,6 +793,7 @@ static void ext4_put_super(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
+	int aborted = 0;
 	int i, err;
 
 	ext4_unregister_li_request(sb);
@@ -802,9 +803,10 @@ static void ext4_put_super(struct super_block *sb)
 	destroy_workqueue(sbi->rsv_conversion_wq);
 
 	if (sbi->s_journal) {
+		aborted = is_journal_aborted(sbi->s_journal);
 		err = jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
-		if (err < 0)
+		if ((err < 0) && !aborted)
 			ext4_abort(sb, "Couldn't clean up the journal");
 	}
 
@@ -816,7 +818,7 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_ext_release(sb);
 	ext4_xattr_put_super(sb);
 
-	if (!(sb->s_flags & MS_RDONLY)) {
+	if (!(sb->s_flags & MS_RDONLY) && !aborted) {
 		ext4_clear_feature_journal_needs_recovery(sb);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
 	}
@@ -3746,7 +3748,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 * root first: it may be modified in the journal!
 	 */
 	if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) {
-		if (ext4_load_journal(sb, es, journal_devnum))
+		err = ext4_load_journal(sb, es, journal_devnum);
+		if (err)
 			goto failed_mount3a;
 	} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
 		   ext4_has_feature_journal_needs_recovery(sb)) {
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 509411dd3698..cf644d52c0cf 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1269,6 +1269,16 @@ out:
 	return 0;
 }
 
+static void fat_dummy_inode_init(struct inode *inode)
+{
+	/* Initialize this dummy inode to work as no-op. */
+	MSDOS_I(inode)->mmu_private = 0;
+	MSDOS_I(inode)->i_start = 0;
+	MSDOS_I(inode)->i_logstart = 0;
+	MSDOS_I(inode)->i_attrs = 0;
+	MSDOS_I(inode)->i_pos = 0;
+}
+
 static int fat_read_root(struct inode *inode)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
@@ -1713,12 +1723,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	fat_inode = new_inode(sb);
 	if (!fat_inode)
 		goto out_fail;
-	MSDOS_I(fat_inode)->i_pos = 0;
+	fat_dummy_inode_init(fat_inode);
 	sbi->fat_inode = fat_inode;
 
 	fsinfo_inode = new_inode(sb);
 	if (!fsinfo_inode)
 		goto out_fail;
+	fat_dummy_inode_init(fsinfo_inode);
 	fsinfo_inode->i_ino = MSDOS_FSINFO_INO;
 	sbi->fsinfo_inode = fsinfo_inode;
 	insert_inode_hash(fsinfo_inode);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 8821c380a71a..11538a8be9f0 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -100,6 +100,7 @@ static void fuse_file_put(struct fuse_file *ff, bool sync)
 			iput(req->misc.release.inode);
 			fuse_put_request(ff->fc, req);
 		} else if (sync) {
+			__set_bit(FR_FORCE, &req->flags);
 			__clear_bit(FR_BACKGROUND, &req->flags);
 			fuse_request_send(ff->fc, req);
 			iput(req->misc.release.inode);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 32e74710b1aa..9cd8c92b953d 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -651,9 +651,11 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	struct kmem_cache *cachep;
 	int ret, tries = 0;
 
+	rcu_read_lock();
 	gl = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms);
 	if (gl && !lockref_get_not_dead(&gl->gl_lockref))
 		gl = NULL;
+	rcu_read_unlock();
 
 	*glp = gl;
 	if (gl)
@@ -721,15 +723,18 @@ again:
 
 	if (ret == -EEXIST) {
 		ret = 0;
+		rcu_read_lock();
 		tmp = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms);
 		if (tmp == NULL || !lockref_get_not_dead(&tmp->gl_lockref)) {
 			if (++tries < 100) {
+				rcu_read_unlock();
 				cond_resched();
 				goto again;
 			}
 			tmp = NULL;
 			ret = -ENOMEM;
 		}
+		rcu_read_unlock();
 	} else {
 		WARN_ON_ONCE(ret);
 	}
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index fa1b8e0dcacf..a2e724053919 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1876,7 +1876,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
 
 	__blist_del_buffer(list, jh);
 	jh->b_jlist = BJ_None;
-	if (test_clear_buffer_jbddirty(bh))
+	if (transaction && is_journal_aborted(transaction->t_journal))
+		clear_buffer_jbddirty(bh);
+	else if (test_clear_buffer_jbddirty(bh))
 		mark_buffer_dirty(bh);	/* Expose it to the VM */
 }
 
diff --git a/fs/mount.h b/fs/mount.h
index 14db05d424f7..3dc7dea5a357 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -86,7 +86,6 @@ static inline int is_mounted(struct vfsmount *mnt)
 }
 
 extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *);
-extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *);
 
 extern int __legitimize_mnt(struct vfsmount *, unsigned);
 extern bool legitimize_mnt(struct vfsmount *, unsigned);
diff --git a/fs/namespace.c b/fs/namespace.c
index da98a1bbd8b5..7df3d406d3e0 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -638,28 +638,6 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 }
 
 /*
- * find the last mount at @dentry on vfsmount @mnt.
- * mount_lock must be held.
- */
-struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
-{
-	struct mount *p, *res = NULL;
-	p = __lookup_mnt(mnt, dentry);
-	if (!p)
-		goto out;
-	if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-		res = p;
-	hlist_for_each_entry_continue(p, mnt_hash) {
-		if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
-			break;
-		if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-			res = p;
-	}
-out:
-	return res;
-}
-
-/*
  * lookup_mnt - Return the first child mount mounted at path
  *
  * "First" means first mounted chronologically.  If you create the
@@ -879,6 +857,13 @@ void mnt_set_mountpoint(struct mount *mnt,
 	hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
 }
 
+static void __attach_mnt(struct mount *mnt, struct mount *parent)
+{
+	hlist_add_head_rcu(&mnt->mnt_hash,
+			   m_hash(&parent->mnt, mnt->mnt_mountpoint));
+	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+}
+
 /*
  * vfsmount lock must be held for write
  */
@@ -887,28 +872,45 @@ static void attach_mnt(struct mount *mnt,
 			struct mountpoint *mp)
 {
 	mnt_set_mountpoint(parent, mp, mnt);
-	hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
-	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+	__attach_mnt(mnt, parent);
 }
 
-static void attach_shadowed(struct mount *mnt,
-			struct mount *parent,
-			struct mount *shadows)
+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt)
 {
-	if (shadows) {
-		hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash);
-		list_add(&mnt->mnt_child, &shadows->mnt_child);
-	} else {
-		hlist_add_head_rcu(&mnt->mnt_hash,
-				m_hash(&parent->mnt, mnt->mnt_mountpoint));
-		list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
-	}
+	struct mountpoint *old_mp = mnt->mnt_mp;
+	struct dentry *old_mountpoint = mnt->mnt_mountpoint;
+	struct mount *old_parent = mnt->mnt_parent;
+
+	list_del_init(&mnt->mnt_child);
+	hlist_del_init(&mnt->mnt_mp_list);
+	hlist_del_init_rcu(&mnt->mnt_hash);
+
+	attach_mnt(mnt, parent, mp);
+
+	put_mountpoint(old_mp);
+
+	/*
+	 * Safely avoid even the suggestion this code might sleep or
+	 * lock the mount hash by taking advantage of the knowledge that
+	 * mnt_change_mountpoint will not release the final reference
+	 * to a mountpoint.
+	 *
+	 * During mounting, the mount passed in as the parent mount will
+	 * continue to use the old mountpoint and during unmounting, the
+	 * old mountpoint will continue to exist until namespace_unlock,
+	 * which happens well after mnt_change_mountpoint.
+	 */
+	spin_lock(&old_mountpoint->d_lock);
+	old_mountpoint->d_lockref.count--;
+	spin_unlock(&old_mountpoint->d_lock);
+
+	mnt_add_count(old_parent, -1);
 }
 
 /*
  * vfsmount lock must be held for write
  */
-static void commit_tree(struct mount *mnt, struct mount *shadows)
+static void commit_tree(struct mount *mnt)
 {
 	struct mount *parent = mnt->mnt_parent;
 	struct mount *m;
@@ -923,7 +925,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows)
 
 	list_splice(&head, n->list.prev);
 
-	attach_shadowed(mnt, parent, shadows);
+	__attach_mnt(mnt, parent);
 	touch_mnt_namespace(n);
 }
 
@@ -1718,7 +1720,6 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 			continue;
 
 		for (s = r; s; s = next_mnt(s, r)) {
-			struct mount *t = NULL;
 			if (!(flag & CL_COPY_UNBINDABLE) &&
 			    IS_MNT_UNBINDABLE(s)) {
 				s = skip_mnt_tree(s);
@@ -1740,14 +1741,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 				goto out;
 			lock_mount_hash();
 			list_add_tail(&q->mnt_list, &res->mnt_list);
-			mnt_set_mountpoint(parent, p->mnt_mp, q);
-			if (!list_empty(&parent->mnt_mounts)) {
-				t = list_last_entry(&parent->mnt_mounts,
-					struct mount, mnt_child);
-				if (t->mnt_mp != p->mnt_mp)
-					t = NULL;
-			}
-			attach_shadowed(q, parent, t);
+			attach_mnt(q, parent, p->mnt_mp);
 			unlock_mount_hash();
 		}
 	}
@@ -1925,10 +1919,18 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 			struct path *parent_path)
 {
 	HLIST_HEAD(tree_list);
+	struct mountpoint *smp;
 	struct mount *child, *p;
 	struct hlist_node *n;
 	int err;
 
+	/* Preallocate a mountpoint in case the new mounts need
+	 * to be tucked under other mounts.
+	 */
+	smp = get_mountpoint(source_mnt->mnt.mnt_root);
+	if (IS_ERR(smp))
+		return PTR_ERR(smp);
+
 	if (IS_MNT_SHARED(dest_mnt)) {
 		err = invent_group_ids(source_mnt, true);
 		if (err)
@@ -1948,16 +1950,19 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
 		mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
-		commit_tree(source_mnt, NULL);
+		commit_tree(source_mnt);
 	}
 
 	hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
 		struct mount *q;
 		hlist_del_init(&child->mnt_hash);
-		q = __lookup_mnt_last(&child->mnt_parent->mnt,
-				      child->mnt_mountpoint);
-		commit_tree(child, q);
+		q = __lookup_mnt(&child->mnt_parent->mnt,
+				 child->mnt_mountpoint);
+		if (q)
+			mnt_change_mountpoint(child, smp, q);
+		commit_tree(child);
 	}
+	put_mountpoint(smp);
 	unlock_mount_hash();
 
 	return 0;
@@ -1970,6 +1975,10 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	unlock_mount_hash();
 	cleanup_group_ids(source_mnt, NULL);
  out:
+	read_seqlock_excl(&mount_lock);
+	put_mountpoint(smp);
+	read_sequnlock_excl(&mount_lock);
+
 	return err;
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 9a524e763c3e..4e3679b25b9b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2452,6 +2452,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	ret = PTR_ERR(state);
 	if (IS_ERR(state))
 		goto out;
+	ctx->state = state;
 	if (server->caps & NFS_CAP_POSIX_LOCK)
 		set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
 
@@ -2474,7 +2475,6 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	if (ret != 0)
 		goto out;
 
-	ctx->state = state;
 	if (d_inode(dentry) == state->inode) {
 		nfs_inode_attach_open_context(ctx);
 		if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
@@ -4711,7 +4711,7 @@ out:
  */
 static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
 {
-	struct page *pages[NFS4ACL_MAXPAGES] = {NULL, };
+	struct page *pages[NFS4ACL_MAXPAGES + 1] = {NULL, };
 	struct nfs_getaclargs args = {
 		.fh = NFS_FH(inode),
 		.acl_pages = pages,
@@ -4725,13 +4725,9 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
+	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE) + 1;
 	int ret = -ENOMEM, i;
 
-	/* As long as we're doing a round trip to the server anyway,
-	 * let's be prepared for a page of acl data. */
-	if (npages == 0)
-		npages = 1;
 	if (npages > ARRAY_SIZE(pages))
 		return -ERANGE;
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 4e4441216804..1cb50bb898b0 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -2487,7 +2487,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
-	replen = hdr.replen + op_decode_hdr_maxsz + 1;
+	replen = hdr.replen + op_decode_hdr_maxsz;
 	encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr);
 
 	xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 994d66fbb446..91e0c5429b4d 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -369,7 +369,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	__be32		err;
 	int		host_err;
 	bool		get_write_count;
-	int		size_change = 0;
+	bool		size_change = (iap->ia_valid & ATTR_SIZE);
 
 	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
 		accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
@@ -382,11 +382,11 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	/* Get inode */
 	err = fh_verify(rqstp, fhp, ftype, accmode);
 	if (err)
-		goto out;
+		return err;
 	if (get_write_count) {
 		host_err = fh_want_write(fhp);
 		if (host_err)
-			return nfserrno(host_err);
+			goto out;
 	}
 
 	dentry = fhp->fh_dentry;
@@ -397,20 +397,28 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 		iap->ia_valid &= ~ATTR_MODE;
 
 	if (!iap->ia_valid)
-		goto out;
+		return 0;
 
 	nfsd_sanitize_attrs(inode, iap);
 
+	if (check_guard && guardtime != inode->i_ctime.tv_sec)
+		return nfserr_notsync;
+
 	/*
 	 * The size case is special, it changes the file in addition to the
-	 * attributes.
+	 * attributes, and file systems don't expect it to be mixed with
+	 * "random" attribute changes.  We thus split out the size change
+	 * into a separate call to ->setattr, and do the rest as a separate
+	 * setattr call.
 	 */
-	if (iap->ia_valid & ATTR_SIZE) {
+	if (size_change) {
 		err = nfsd_get_write_access(rqstp, fhp, iap);
 		if (err)
-			goto out;
-		size_change = 1;
+			return err;
+	}
 
+	fh_lock(fhp);
+	if (size_change) {
 		/*
 		 * RFC5661, Section 18.30.4:
 		 *   Changing the size of a file with SETATTR indirectly
@@ -418,29 +426,36 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 		 *
 		 * (and similar for the older RFCs)
 		 */
-		if (iap->ia_size != i_size_read(inode))
-			iap->ia_valid |= ATTR_MTIME;
-	}
+		struct iattr size_attr = {
+			.ia_valid	= ATTR_SIZE | ATTR_CTIME | ATTR_MTIME,
+			.ia_size	= iap->ia_size,
+		};
 
-	iap->ia_valid |= ATTR_CTIME;
+		host_err = notify_change(dentry, &size_attr, NULL);
+		if (host_err)
+			goto out_unlock;
+		iap->ia_valid &= ~ATTR_SIZE;
 
-	if (check_guard && guardtime != inode->i_ctime.tv_sec) {
-		err = nfserr_notsync;
-		goto out_put_write_access;
+		/*
+		 * Avoid the additional setattr call below if the only other
+		 * attribute that the client sends is the mtime, as we update
+		 * it as part of the size change above.
+		 */
+		if ((iap->ia_valid & ~ATTR_MTIME) == 0)
+			goto out_unlock;
 	}
 
-	fh_lock(fhp);
+	iap->ia_valid |= ATTR_CTIME;
 	host_err = notify_change(dentry, iap, NULL);
-	fh_unlock(fhp);
-	err = nfserrno(host_err);
 
-out_put_write_access:
+out_unlock:
+	fh_unlock(fhp);
 	if (size_change)
 		put_write_access(inode);
-	if (!err)
-		err = nfserrno(commit_metadata(fhp));
 out:
-	return err;
+	if (!host_err)
+		host_err = commit_metadata(fhp);
+	return nfserrno(host_err);
 }
 
 #if defined(CONFIG_NFSD_V4)
diff --git a/fs/pnode.c b/fs/pnode.c
index 99899705b105..b9f2af59b9a6 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -324,6 +324,21 @@ out:
 	return ret;
 }
 
+static struct mount *find_topper(struct mount *mnt)
+{
+	/* If there is exactly one mount covering mnt completely return it. */
+	struct mount *child;
+
+	if (!list_is_singular(&mnt->mnt_mounts))
+		return NULL;
+
+	child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child);
+	if (child->mnt_mountpoint != mnt->mnt.mnt_root)
+		return NULL;
+
+	return child;
+}
+
 /*
  * return true if the refcount is greater than count
  */
@@ -344,9 +359,8 @@ static inline int do_refcount_check(struct mount *mnt, int count)
  */
 int propagate_mount_busy(struct mount *mnt, int refcnt)
 {
-	struct mount *m, *child;
+	struct mount *m, *child, *topper;
 	struct mount *parent = mnt->mnt_parent;
-	int ret = 0;
 
 	if (mnt == parent)
 		return do_refcount_check(mnt, refcnt);
@@ -361,12 +375,24 @@ int propagate_mount_busy(struct mount *mnt, int refcnt)
 
 	for (m = propagation_next(parent, parent); m;
 	     		m = propagation_next(m, parent)) {
-		child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint);
-		if (child && list_empty(&child->mnt_mounts) &&
-		    (ret = do_refcount_check(child, 1)))
-			break;
+		int count = 1;
+		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
+		if (!child)
+			continue;
+
+		/* Is there exactly one mount on the child that covers
+		 * it completely whose reference should be ignored?
+		 */
+		topper = find_topper(child);
+		if (topper)
+			count += 1;
+		else if (!list_empty(&child->mnt_mounts))
+			continue;
+
+		if (do_refcount_check(child, count))
+			return 1;
 	}
-	return ret;
+	return 0;
 }
 
 /*
@@ -383,7 +409,7 @@ void propagate_mount_unlock(struct mount *mnt)
 
 	for (m = propagation_next(parent, parent); m;
 			m = propagation_next(m, parent)) {
-		child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint);
+		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
 		if (child)
 			child->mnt.mnt_flags &= ~MNT_LOCKED;
 	}
@@ -401,9 +427,11 @@ static void mark_umount_candidates(struct mount *mnt)
 
 	for (m = propagation_next(parent, parent); m;
 			m = propagation_next(m, parent)) {
-		struct mount *child = __lookup_mnt_last(&m->mnt,
+		struct mount *child = __lookup_mnt(&m->mnt,
 						mnt->mnt_mountpoint);
-		if (child && (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m))) {
+		if (!child || (child->mnt.mnt_flags & MNT_UMOUNT))
+			continue;
+		if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) {
 			SET_MNT_MARK(child);
 		}
 	}
@@ -422,8 +450,8 @@ static void __propagate_umount(struct mount *mnt)
 
 	for (m = propagation_next(parent, parent); m;
 			m = propagation_next(m, parent)) {
-
-		struct mount *child = __lookup_mnt_last(&m->mnt,
+		struct mount *topper;
+		struct mount *child = __lookup_mnt(&m->mnt,
 						mnt->mnt_mountpoint);
 		/*
 		 * umount the child only if the child has no children
@@ -432,6 +460,15 @@ static void __propagate_umount(struct mount *mnt)
 		if (!child || !IS_MNT_MARKED(child))
 			continue;
 		CLEAR_MNT_MARK(child);
+
+		/* If there is exactly one mount covering all of child
+		 * replace child with that mount.
+		 */
+		topper = find_topper(child);
+		if (topper)
+			mnt_change_mountpoint(child->mnt_parent, child->mnt_mp,
+					      topper);
+
 		if (list_empty(&child->mnt_mounts)) {
 			list_del_init(&child->mnt_child);
 			child->mnt.mnt_flags |= MNT_UMOUNT;
diff --git a/fs/pnode.h b/fs/pnode.h
index 0fcdbe7ca648..623f01772bec 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -49,6 +49,8 @@ int get_dominating_id(struct mount *mnt, const struct path *root);
 unsigned int mnt_get_count(struct mount *mnt);
 void mnt_set_mountpoint(struct mount *, struct mountpoint *,
 			struct mount *);
+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,
+			   struct mount *mnt);
 struct mount *copy_tree(struct mount *, struct dentry *, int);
 bool is_path_reachable(struct mount *, struct dentry *,
 			 const struct path *root);