Merge branch 'locks-3.20' of git://git.samba.org/jlayton/linux into for-3.20

Christoph's block pnfs patches have some minor dependencies on these
lock patches.

30 files changed, 736 insertions, 570 deletions

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 2d3e32ebfd15..8729cf68d2fe 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1552,7 +1552,6 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 {
 	int ret;
 	int type;
-	struct btrfs_tree_block_info *info;
 	struct btrfs_extent_inline_ref *eiref;
 
 	if (*ptr == (unsigned long)-1)
@@ -1573,9 +1572,17 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 	}
 
 	/* we can treat both ref types equally here */
-	info = (struct btrfs_tree_block_info *)(ei + 1);
 	*out_root = btrfs_extent_inline_ref_offset(eb, eiref);
-	*out_level = btrfs_tree_block_level(eb, info);
+
+	if (key->type == BTRFS_EXTENT_ITEM_KEY) {
+		struct btrfs_tree_block_info *info;
+
+		info = (struct btrfs_tree_block_info *)(ei + 1);
+		*out_level = btrfs_tree_block_level(eb, info);
+	} else {
+		ASSERT(key->type == BTRFS_METADATA_ITEM_KEY);
+		*out_level = (u8)key->offset;
+	}
 
 	if (ret == 1)
 		*ptr = (unsigned long)-1;
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 054577bddaf2..de4e70fb3cbb 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1857,6 +1857,14 @@ int btrfs_delayed_delete_inode_ref(struct inode *inode)
 {
 	struct btrfs_delayed_node *delayed_node;
 
+	/*
+	 * we don't do delayed inode updates during log recovery because it
+	 * leads to enospc problems.  This means we also can't do
+	 * delayed inode refs
+	 */
+	if (BTRFS_I(inode)->root->fs_info->log_root_recovering)
+		return -EAGAIN;
+
 	delayed_node = btrfs_get_or_create_delayed_node(inode);
 	if (IS_ERR(delayed_node))
 		return PTR_ERR(delayed_node);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index a80b97100d90..15116585e714 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3139,9 +3139,11 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 
 	ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1);
-	if (ret < 0)
+	if (ret) {
+		if (ret > 0)
+			ret = -ENOENT;
 		goto fail;
-	BUG_ON(ret); /* Corruption */
+	}
 
 	leaf = path->nodes[0];
 	bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
@@ -3149,11 +3151,9 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
 fail:
-	if (ret) {
+	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
-		return ret;
-	}
-	return 0;
+	return ret;
 
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e687bb0dc73a..8bf326affb94 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6255,8 +6255,10 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 out_fail:
 	btrfs_end_transaction(trans, root);
-	if (drop_on_err)
+	if (drop_on_err) {
+		inode_dec_link_count(inode);
 		iput(inode);
+	}
 	btrfs_balance_delayed_items(root);
 	btrfs_btree_balance_dirty(root);
 	return err;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index f2bb13a23f86..9e1569ffbf6e 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2607,9 +2607,9 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity,
 		ret = scrub_pages_for_parity(sparity, logical, l, physical, dev,
 					     flags, gen, mirror_num,
 					     have_csum ? csum : NULL);
-skip:
 		if (ret)
 			return ret;
+skip:
 		len -= l;
 		logical += l;
 		physical += l;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index f5013d92a7e6..c81c0e004588 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1416,7 +1416,7 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 		}
 	}
 
-	dout("fill_inline_data %p %llx.%llx len %lu locked_page %p\n",
+	dout("fill_inline_data %p %llx.%llx len %zu locked_page %p\n",
 	     inode, ceph_vinop(inode), len, locked_page);
 
 	if (len > 0) {
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index c35c5c614e38..06ea5cd05cd9 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -239,23 +239,21 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	return err;
 }
 
-/**
- * Must be called with lock_flocks() already held. Fills in the passed
- * counter variables, so you can prepare pagelist metadata before calling
- * ceph_encode_locks.
+/*
+ * Fills in the passed counter variables, so you can prepare pagelist metadata
+ * before calling ceph_encode_locks.
  */
 void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 {
-	struct file_lock *lock;
+	struct file_lock_context *ctx;
 
 	*fcntl_count = 0;
 	*flock_count = 0;
 
-	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-		if (lock->fl_flags & FL_POSIX)
-			++(*fcntl_count);
-		else if (lock->fl_flags & FL_FLOCK)
-			++(*flock_count);
+	ctx = inode->i_flctx;
+	if (ctx) {
+		*fcntl_count = ctx->flc_posix_cnt;
+		*flock_count = ctx->flc_flock_cnt;
 	}
 	dout("counted %d flock locks and %d fcntl locks",
 	     *flock_count, *fcntl_count);
@@ -271,6 +269,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 				int num_fcntl_locks, int num_flock_locks)
 {
 	struct file_lock *lock;
+	struct file_lock_context *ctx = inode->i_flctx;
 	int err = 0;
 	int seen_fcntl = 0;
 	int seen_flock = 0;
@@ -279,33 +278,34 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 	dout("encoding %d flock and %d fcntl locks", num_flock_locks,
 	     num_fcntl_locks);
 
-	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-		if (lock->fl_flags & FL_POSIX) {
-			++seen_fcntl;
-			if (seen_fcntl > num_fcntl_locks) {
-				err = -ENOSPC;
-				goto fail;
-			}
-			err = lock_to_ceph_filelock(lock, &flocks[l]);
-			if (err)
-				goto fail;
-			++l;
+	if (!ctx)
+		return 0;
+
+	spin_lock(&ctx->flc_lock);
+	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+		++seen_fcntl;
+		if (seen_fcntl > num_fcntl_locks) {
+			err = -ENOSPC;
+			goto fail;
 		}
+		err = lock_to_ceph_filelock(lock, &flocks[l]);
+		if (err)
+			goto fail;
+		++l;
 	}
-	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-		if (lock->fl_flags & FL_FLOCK) {
-			++seen_flock;
-			if (seen_flock > num_flock_locks) {
-				err = -ENOSPC;
-				goto fail;
-			}
-			err = lock_to_ceph_filelock(lock, &flocks[l]);
-			if (err)
-				goto fail;
-			++l;
+	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+		++seen_flock;
+		if (seen_flock > num_flock_locks) {
+			err = -ENOSPC;
+			goto fail;
 		}
+		err = lock_to_ceph_filelock(lock, &flocks[l]);
+		if (err)
+			goto fail;
+		++l;
 	}
 fail:
+	spin_unlock(&ctx->flc_lock);
 	return err;
 }
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d2171f4a6980..5f62fb7a5d0a 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2700,20 +2700,16 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		struct ceph_filelock *flocks;
 
 encode_again:
-		spin_lock(&inode->i_lock);
 		ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks);
-		spin_unlock(&inode->i_lock);
 		flocks = kmalloc((num_fcntl_locks+num_flock_locks) *
 				 sizeof(struct ceph_filelock), GFP_NOFS);
 		if (!flocks) {
 			err = -ENOMEM;
 			goto out_free;
 		}
-		spin_lock(&inode->i_lock);
 		err = ceph_encode_locks_to_buffer(inode, flocks,
 						  num_fcntl_locks,
 						  num_flock_locks);
-		spin_unlock(&inode->i_lock);
 		if (err) {
 			kfree(flocks);
 			if (err == -ENOSPC)
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 96b7e9b7706d..8c2ca6f62bad 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1109,11 +1109,6 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
 	return rc;
 }
 
-/* copied from fs/locks.c with a name change */
-#define cifs_for_each_lock(inode, lockp) \
-	for (lockp = &inode->i_flock; *lockp != NULL; \
-	     lockp = &(*lockp)->fl_next)
-
 struct lock_to_push {
 	struct list_head llist;
 	__u64 offset;
@@ -1128,8 +1123,9 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 {
 	struct inode *inode = cfile->dentry->d_inode;
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
-	struct file_lock *flock, **before;
-	unsigned int count = 0, i = 0;
+	struct file_lock *flock;
+	struct file_lock_context *flctx = inode->i_flctx;
+	unsigned int i;
 	int rc = 0, xid, type;
 	struct list_head locks_to_send, *el;
 	struct lock_to_push *lck, *tmp;
@@ -1137,21 +1133,17 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 
 	xid = get_xid();
 
-	spin_lock(&inode->i_lock);
-	cifs_for_each_lock(inode, before) {
-		if ((*before)->fl_flags & FL_POSIX)
-			count++;
-	}
-	spin_unlock(&inode->i_lock);
+	if (!flctx)
+		goto out;
 
 	INIT_LIST_HEAD(&locks_to_send);
 
 	/*
-	 * Allocating count locks is enough because no FL_POSIX locks can be
-	 * added to the list while we are holding cinode->lock_sem that
+	 * Allocating flc_posix_cnt locks is enough because no FL_POSIX locks
+	 * can be added to the list while we are holding cinode->lock_sem that
 	 * protects locking operations of this inode.
 	 */
-	for (; i < count; i++) {
+	for (i = 0; i < flctx->flc_posix_cnt; i++) {
 		lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL);
 		if (!lck) {
 			rc = -ENOMEM;
@@ -1161,11 +1153,8 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 	}
 
 	el = locks_to_send.next;
-	spin_lock(&inode->i_lock);
-	cifs_for_each_lock(inode, before) {
-		flock = *before;
-		if ((flock->fl_flags & FL_POSIX) == 0)
-			continue;
+	spin_lock(&flctx->flc_lock);
+	list_for_each_entry(flock, &flctx->flc_posix, fl_list) {
 		if (el == &locks_to_send) {
 			/*
 			 * The list ended. We don't have enough allocated
@@ -1185,9 +1174,8 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 		lck->length = length;
 		lck->type = type;
 		lck->offset = flock->fl_start;
-		el = el->next;
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&flctx->flc_lock);
 
 	list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) {
 		int stored_rc;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index e5d3eadf47b1..bed43081720f 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5166,8 +5166,8 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 
 	/* fallback to generic here if not in extents fmt */
 	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
-		return __generic_block_fiemap(inode, fieinfo, start, len,
-					      ext4_get_block);
+		return generic_block_fiemap(inode, fieinfo, start, len,
+			ext4_get_block);
 
 	if (fiemap_check_flags(fieinfo, EXT4_FIEMAP_FLAGS))
 		return -EBADR;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 513c12cf444c..8131be8c0af3 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -273,19 +273,24 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
  * we determine this extent as a data or a hole according to whether the
  * page cache has data or not.
  */
-static int ext4_find_unwritten_pgoff(struct inode *inode, int whence,
-				     loff_t endoff, loff_t *offset)
+static int ext4_find_unwritten_pgoff(struct inode *inode,
+				     int whence,
+				     struct ext4_map_blocks *map,
+				     loff_t *offset)
 {
 	struct pagevec pvec;
+	unsigned int blkbits;
 	pgoff_t index;
 	pgoff_t end;
+	loff_t endoff;
 	loff_t startoff;
 	loff_t lastoff;
 	int found = 0;
 
+	blkbits = inode->i_sb->s_blocksize_bits;
 	startoff = *offset;
 	lastoff = startoff;
-
+	endoff = (loff_t)(map->m_lblk + map->m_len) << blkbits;
 
 	index = startoff >> PAGE_CACHE_SHIFT;
 	end = endoff >> PAGE_CACHE_SHIFT;
@@ -403,144 +408,147 @@ out:
 static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
 {
 	struct inode *inode = file->f_mapping->host;
-	struct fiemap_extent_info fie;
-	struct fiemap_extent ext[2];
-	loff_t next;
-	int i, ret = 0;
+	struct ext4_map_blocks map;
+	struct extent_status es;
+	ext4_lblk_t start, last, end;
+	loff_t dataoff, isize;
+	int blkbits;
+	int ret = 0;
 
 	mutex_lock(&inode->i_mutex);
-	if (offset >= inode->i_size) {
+
+	isize = i_size_read(inode);
+	if (offset >= isize) {
 		mutex_unlock(&inode->i_mutex);
 		return -ENXIO;
 	}
-	fie.fi_flags = 0;
-	fie.fi_extents_max = 2;
-	fie.fi_extents_start = (struct fiemap_extent __user *) &ext;
-	while (1) {
-		mm_segment_t old_fs = get_fs();
-
-		fie.fi_extents_mapped = 0;
-		memset(ext, 0, sizeof(*ext) * fie.fi_extents_max);
-
-		set_fs(get_ds());
-		ret = ext4_fiemap(inode, &fie, offset, maxsize - offset);
-		set_fs(old_fs);
-		if (ret)
+
+	blkbits = inode->i_sb->s_blocksize_bits;
+	start = offset >> blkbits;
+	last = start;
+	end = isize >> blkbits;
+	dataoff = offset;
+
+	do {
+		map.m_lblk = last;
+		map.m_len = end - last + 1;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
+			if (last != start)
+				dataoff = (loff_t)last << blkbits;
 			break;
+		}
 
-		/* No extents found, EOF */
-		if (!fie.fi_extents_mapped) {
-			ret = -ENXIO;
+		/*
+		 * If there is a delay extent at this offset,
+		 * it will be as a data.
+		 */
+		ext4_es_find_delayed_extent_range(inode, last, last, &es);
+		if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
+			if (last != start)
+				dataoff = (loff_t)last << blkbits;
 			break;
 		}
-		for (i = 0; i < fie.fi_extents_mapped; i++) {
-			next = (loff_t)(ext[i].fe_length + ext[i].fe_logical);
 
-			if (offset < (loff_t)ext[i].fe_logical)
-				offset = (loff_t)ext[i].fe_logical;
-			/*
-			 * If extent is not unwritten, then it contains valid
-			 * data, mapped or delayed.
-			 */
-			if (!(ext[i].fe_flags & FIEMAP_EXTENT_UNWRITTEN))
-				goto out;
+		/*
+		 * If there is a unwritten extent at this offset,
+		 * it will be as a data or a hole according to page
+		 * cache that has data or not.
+		 */
+		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+			int unwritten;
+			unwritten = ext4_find_unwritten_pgoff(inode, SEEK_DATA,
+							      &map, &dataoff);
+			if (unwritten)
+				break;
+		}
 
-			/*
-			 * If there is a unwritten extent at this offset,
-			 * it will be as a data or a hole according to page
-			 * cache that has data or not.
-			 */
-			if (ext4_find_unwritten_pgoff(inode, SEEK_DATA,
-						      next, &offset))
-				goto out;
+		last++;
+		dataoff = (loff_t)last << blkbits;
+	} while (last <= end);
 
-			if (ext[i].fe_flags & FIEMAP_EXTENT_LAST) {
-				ret = -ENXIO;
-				goto out;
-			}
-			offset = next;
-		}
-	}
-	if (offset > inode->i_size)
-		offset = inode->i_size;
-out:
 	mutex_unlock(&inode->i_mutex);
-	if (ret)
-		return ret;
 
-	return vfs_setpos(file, offset, maxsize);
+	if (dataoff > isize)
+		return -ENXIO;
+
+	return vfs_setpos(file, dataoff, maxsize);
 }
 
 /*
- * ext4_seek_hole() retrieves the offset for SEEK_HOLE
+ * ext4_seek_hole() retrieves the offset for SEEK_HOLE.
  */
 static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
 {
 	struct inode *inode = file->f_mapping->host;
-	struct fiemap_extent_info fie;
-	struct fiemap_extent ext[2];
-	loff_t next;
-	int i, ret = 0;
+	struct ext4_map_blocks map;
+	struct extent_status es;
+	ext4_lblk_t start, last, end;
+	loff_t holeoff, isize;
+	int blkbits;
+	int ret = 0;
 
 	mutex_lock(&inode->i_mutex);
-	if (offset >= inode->i_size) {
+
+	isize = i_size_read(inode);
+	if (offset >= isize) {
 		mutex_unlock(&inode->i_mutex);
 		return -ENXIO;
 	}
 
-	fie.fi_flags = 0;
-	fie.fi_extents_max = 2;
-	fie.fi_extents_start = (struct fiemap_extent __user *)&ext;
-	while (1) {
-		mm_segment_t old_fs = get_fs();
-
-		fie.fi_extents_mapped = 0;
-		memset(ext, 0, sizeof(*ext));
+	blkbits = inode->i_sb->s_blocksize_bits;
+	start = offset >> blkbits;
+	last = start;
+	end = isize >> blkbits;
+	holeoff = offset;
 
-		set_fs(get_ds());
-		ret = ext4_fiemap(inode, &fie, offset, maxsize - offset);
-		set_fs(old_fs);
-		if (ret)
-			break;
+	do {
+		map.m_lblk = last;
+		map.m_len = end - last + 1;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
+			last += ret;
+			holeoff = (loff_t)last << blkbits;
+			continue;
+		}
 
-		/* No extents found */
-		if (!fie.fi_extents_mapped)
-			break;
+		/*
+		 * If there is a delay extent at this offset,
+		 * we will skip this extent.
+		 */
+		ext4_es_find_delayed_extent_range(inode, last, last, &es);
+		if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
+			last = es.es_lblk + es.es_len;
+			holeoff = (loff_t)last << blkbits;
+			continue;
+		}
 
-		for (i = 0; i < fie.fi_extents_mapped; i++) {
-			next = (loff_t)(ext[i].fe_logical + ext[i].fe_length);
-			/*
-			 * If extent is not unwritten, then it contains valid
-			 * data, mapped or delayed.
-			 */
-			if (!(ext[i].fe_flags & FIEMAP_EXTENT_UNWRITTEN)) {
-				if (offset < (loff_t)ext[i].fe_logical)
-					goto out;
-				offset = next;
+		/*
+		 * If there is a unwritten extent at this offset,
+		 * it will be as a data or a hole according to page
+		 * cache that has data or not.
+		 */
+		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+			int unwritten;
+			unwritten = ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
+							      &map, &holeoff);
+			if (!unwritten) {
+				last += ret;
+				holeoff = (loff_t)last << blkbits;
 				continue;
 			}
-			/*
-			 * If there is a unwritten extent at this offset,
-			 * it will be as a data or a hole according to page
-			 * cache that has data or not.
-			 */
-			if (ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
-						      next, &offset))
-				goto out;
-
-			offset = next;
-			if (ext[i].fe_flags & FIEMAP_EXTENT_LAST)
-				goto out;
 		}
-	}
-	if (offset > inode->i_size)
-		offset = inode->i_size;
-out:
+
+		/* find a hole */
+		break;
+	} while (last <= end);
+
 	mutex_unlock(&inode->i_mutex);
-	if (ret)
-		return ret;
 
-	return vfs_setpos(file, offset, maxsize);
+	if (holeoff > isize)
+		holeoff = isize;
+
+	return vfs_setpos(file, holeoff, maxsize);
 }
 
 /*
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index bf76f405a5f9..8a8ec6293b19 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -24,6 +24,18 @@ int ext4_resize_begin(struct super_block *sb)
 		return -EPERM;
 
 	/*
+	 * If we are not using the primary superblock/GDT copy don't resize,
+         * because the user tools have no way of handling this.  Probably a
+         * bad time to do it anyways.
+         */
+	if (EXT4_SB(sb)->s_sbh->b_blocknr !=
+	    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
+		ext4_warning(sb, "won't resize using backup superblock at %llu",
+			(unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr);
+		return -EPERM;
+	}
+
+	/*
 	 * We are not allowed to do online-resizing on a filesystem mounted
 	 * with error, because it can destroy the filesystem easily.
 	 */
@@ -758,18 +770,6 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 		       "EXT4-fs: ext4_add_new_gdb: adding group block %lu\n",
 		       gdb_num);
 
-	/*
-	 * If we are not using the primary superblock/GDT copy don't resize,
-         * because the user tools have no way of handling this.  Probably a
-         * bad time to do it anyways.
-         */
-	if (EXT4_SB(sb)->s_sbh->b_blocknr !=
-	    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
-		ext4_warning(sb, "won't resize using backup superblock at %llu",
-			(unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr);
-		return -EPERM;
-	}
-
 	gdb_bh = sb_bread(sb, gdblock);
 	if (!gdb_bh)
 		return -EIO;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 43c92b1685cb..74c5f53595fb 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3482,7 +3482,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) &&
 	    EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
-		ext4_warning(sb, KERN_INFO "metadata_csum and uninit_bg are "
+		ext4_warning(sb, "metadata_csum and uninit_bg are "
 			     "redundant flags; please run fsck.");
 
 	/* Check for a known checksum algorithm */
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 99d440a4a6ba..ee85cd4e136a 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -740,14 +740,15 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
 		O_RDONLY	| O_WRONLY	| O_RDWR	|
 		O_CREAT		| O_EXCL	| O_NOCTTY	|
 		O_TRUNC		| O_APPEND	| /* O_NONBLOCK	| */
 		__O_SYNC	| O_DSYNC	| FASYNC	|
 		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
 		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
-		__FMODE_EXEC	| O_PATH	| __O_TMPFILE
+		__FMODE_EXEC	| O_PATH	| __O_TMPFILE	|
+		__FMODE_NONOTIFY
 		));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ba1107977f2e..ed19a7d622fa 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -131,6 +131,13 @@ static void fuse_req_init_context(struct fuse_req *req)
 	req->in.h.pid = current->pid;
 }
 
+void fuse_set_initialized(struct fuse_conn *fc)
+{
+	/* Make sure stores before this are seen on another CPU */
+	smp_wmb();
+	fc->initialized = 1;
+}
+
 static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background)
 {
 	return !fc->initialized || (for_background && fc->blocked);
@@ -155,6 +162,8 @@ static struct fuse_req *__fuse_get_req(struct fuse_conn *fc, unsigned npages,
 		if (intr)
 			goto out;
 	}
+	/* Matches smp_wmb() in fuse_set_initialized() */
+	smp_rmb();
 
 	err = -ENOTCONN;
 	if (!fc->connected)
@@ -253,6 +262,8 @@ struct fuse_req *fuse_get_req_nofail_nopages(struct fuse_conn *fc,
 
 	atomic_inc(&fc->num_waiting);
 	wait_event(fc->blocked_waitq, fc->initialized);
+	/* Matches smp_wmb() in fuse_set_initialized() */
+	smp_rmb();
 	req = fuse_request_alloc(0);
 	if (!req)
 		req = get_reserved_req(fc, file);
@@ -511,6 +522,39 @@ void fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
 }
 EXPORT_SYMBOL_GPL(fuse_request_send);
 
+static void fuse_adjust_compat(struct fuse_conn *fc, struct fuse_args *args)
+{
+	if (fc->minor < 4 && args->in.h.opcode == FUSE_STATFS)
+		args->out.args[0].size = FUSE_COMPAT_STATFS_SIZE;
+
+	if (fc->minor < 9) {
+		switch (args->in.h.opcode) {
+		case FUSE_LOOKUP:
+		case FUSE_CREATE:
+		case FUSE_MKNOD:
+		case FUSE_MKDIR:
+		case FUSE_SYMLINK:
+		case FUSE_LINK:
+			args->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE;
+			break;
+		case FUSE_GETATTR:
+		case FUSE_SETATTR:
+			args->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE;
+			break;
+		}
+	}
+	if (fc->minor < 12) {
+		switch (args->in.h.opcode) {
+		case FUSE_CREATE:
+			args->in.args[0].size = sizeof(struct fuse_open_in);
+			break;
+		case FUSE_MKNOD:
+			args->in.args[0].size = FUSE_COMPAT_MKNOD_IN_SIZE;
+			break;
+		}
+	}
+}
+
 ssize_t fuse_simple_request(struct fuse_conn *fc, struct fuse_args *args)
 {
 	struct fuse_req *req;
@@ -520,6 +564,9 @@ ssize_t fuse_simple_request(struct fuse_conn *fc, struct fuse_args *args)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
+	/* Needs to be done after fuse_get_req() so that fc->minor is valid */
+	fuse_adjust_compat(fc, args);
+
 	req->in.h.opcode = args->in.h.opcode;
 	req->in.h.nodeid = args->in.h.nodeid;
 	req->in.numargs = args->in.numargs;
@@ -2127,7 +2174,7 @@ void fuse_abort_conn(struct fuse_conn *fc)
 	if (fc->connected) {
 		fc->connected = 0;
 		fc->blocked = 0;
-		fc->initialized = 1;
+		fuse_set_initialized(fc);
 		end_io_requests(fc);
 		end_queued_requests(fc);
 		end_polls(fc);
@@ -2146,7 +2193,7 @@ int fuse_dev_release(struct inode *inode, struct file *file)
 		spin_lock(&fc->lock);
 		fc->connected = 0;
 		fc->blocked = 0;
-		fc->initialized = 1;
+		fuse_set_initialized(fc);
 		end_queued_requests(fc);
 		end_polls(fc);
 		wake_up_all(&fc->blocked_waitq);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 252b8a5de8b5..08e7b1a9d5d0 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -156,10 +156,7 @@ static void fuse_lookup_init(struct fuse_conn *fc, struct fuse_args *args,
 	args->in.args[0].size = name->len + 1;
 	args->in.args[0].value = name->name;
 	args->out.numargs = 1;
-	if (fc->minor < 9)
-		args->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE;
-	else
-		args->out.args[0].size = sizeof(struct fuse_entry_out);
+	args->out.args[0].size = sizeof(struct fuse_entry_out);
 	args->out.args[0].value = outarg;
 }
 
@@ -422,16 +419,12 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	args.in.h.opcode = FUSE_CREATE;
 	args.in.h.nodeid = get_node_id(dir);
 	args.in.numargs = 2;
-	args.in.args[0].size = fc->minor < 12 ? sizeof(struct fuse_open_in) :
-						sizeof(inarg);
+	args.in.args[0].size = sizeof(inarg);
 	args.in.args[0].value = &inarg;
 	args.in.args[1].size = entry->d_name.len + 1;
 	args.in.args[1].value = entry->d_name.name;
 	args.out.numargs = 2;
-	if (fc->minor < 9)
-		args.out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE;
-	else
-		args.out.args[0].size = sizeof(outentry);
+	args.out.args[0].size = sizeof(outentry);
 	args.out.args[0].value = &outentry;
 	args.out.args[1].size = sizeof(outopen);
 	args.out.args[1].value = &outopen;
@@ -539,10 +532,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args,
 	memset(&outarg, 0, sizeof(outarg));
 	args->in.h.nodeid = get_node_id(dir);
 	args->out.numargs = 1;
-	if (fc->minor < 9)
-		args->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE;
-	else
-		args->out.args[0].size = sizeof(outarg);
+	args->out.args[0].size = sizeof(outarg);
 	args->out.args[0].value = &outarg;
 	err = fuse_simple_request(fc, args);
 	if (err)
@@ -592,8 +582,7 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, umode_t mode,
 	inarg.umask = current_umask();
 	args.in.h.opcode = FUSE_MKNOD;
 	args.in.numargs = 2;
-	args.in.args[0].size = fc->minor < 12 ? FUSE_COMPAT_MKNOD_IN_SIZE :
-