Merge branch 'misc-for-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux into for-linus-4.5

fs/btrfs/btrfs_inode.h

@@ -192,6 +192,10 @@ struct btrfs_inode {
 	/* File creation time. */
 	struct timespec i_otime;
 
+	/* Hook into fs_info->delayed_iputs */
+	struct list_head delayed_iput;
+	long delayed_iput_count;
+
 	struct inode vfs_inode;
 };
 

fs/btrfs/ctree.c

@@ -2248,7 +2248,6 @@ static void reada_for_search(struct btrfs_root *root,
 	u64 target;
 	u64 nread = 0;
 	u64 gen;
-	int direction = path->reada;
 	struct extent_buffer *eb;
 	u32 nr;
 	u32 blocksize;
@@ -2276,16 +2275,16 @@ static void reada_for_search(struct btrfs_root *root,
 	nr = slot;
 
 	while (1) {
-		if (direction < 0) {
+		if (path->reada == READA_BACK) {
 			if (nr == 0)
 				break;
 			nr--;
-		} else if (direction > 0) {
+		} else if (path->reada == READA_FORWARD) {
 			nr++;
 			if (nr >= nritems)
 				break;
 		}
-		if (path->reada < 0 && objectid) {
+		if (path->reada == READA_BACK && objectid) {
 			btrfs_node_key(node, &disk_key, nr);
 			if (btrfs_disk_key_objectid(&disk_key) != objectid)
 				break;
@@ -2493,7 +2492,7 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 	btrfs_set_path_blocking(p);
 
 	free_extent_buffer(tmp);
-	if (p->reada)
+	if (p->reada != READA_NONE)
 		reada_for_search(root, p, level, slot, key->objectid);
 
 	btrfs_release_path(p);

fs/btrfs/ctree.h

@@ -177,7 +177,7 @@ struct btrfs_ordered_sum;
 /* csum types */
 #define BTRFS_CSUM_TYPE_CRC32	0
 
-static int btrfs_csum_sizes[] = { 4 };
+static const int btrfs_csum_sizes[] = { 4 };
 
 /* four bytes for CRC32 */
 #define BTRFS_EMPTY_DIR_SIZE 0
@@ -598,14 +598,15 @@ struct btrfs_node {
  * The slots array records the index of the item or block pointer
  * used while walking the tree.
  */
+enum { READA_NONE = 0, READA_BACK, READA_FORWARD };
 struct btrfs_path {
 	struct extent_buffer *nodes[BTRFS_MAX_LEVEL];
 	int slots[BTRFS_MAX_LEVEL];
 	/* if there is real range locking, this locks field will change */
-	int locks[BTRFS_MAX_LEVEL];
-	int reada;
+	u8 locks[BTRFS_MAX_LEVEL];
+	u8 reada;
 	/* keep some upper locks as we walk down */
-	int lowest_level;
+	u8 lowest_level;
 
 	/*
 	 * set by btrfs_split_item, tells search_slot to keep all locks

fs/btrfs/delayed-ref.c

@@ -493,12 +493,12 @@ update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
 				memcpy(&existing_ref->extent_op->key,
 				       &ref->extent_op->key,
 				       sizeof(ref->extent_op->key));
-				existing_ref->extent_op->update_key = 1;
+				existing_ref->extent_op->update_key = true;
 			}
 			if (ref->extent_op->update_flags) {
 				existing_ref->extent_op->flags_to_set |=
 					ref->extent_op->flags_to_set;
-				existing_ref->extent_op->update_flags = 1;
+				existing_ref->extent_op->update_flags = true;
 			}
 			btrfs_free_delayed_extent_op(ref->extent_op);
 		}

fs/btrfs/delayed-ref.h

@@ -75,11 +75,11 @@ struct btrfs_delayed_ref_node {
 
 struct btrfs_delayed_extent_op {
 	struct btrfs_disk_key key;
+	u8 level;
+	bool update_key;
+	bool update_flags;
+	bool is_data;
 	u64 flags_to_set;
-	int level;
-	unsigned int update_key:1;
-	unsigned int update_flags:1;
-	unsigned int is_data:1;
 };
 
 /*

fs/btrfs/disk-io.c

@@ -2682,6 +2682,7 @@ int open_ctree(struct super_block *sb,
 	if (btrfs_check_super_csum(bh->b_data)) {
 		printk(KERN_ERR "BTRFS: superblock checksum mismatch\n");
 		err = -EINVAL;
+		brelse(bh);
 		goto fail_alloc;
 	}
 

fs/btrfs/extent-tree.c

@@ -437,7 +437,7 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
 	 */
 	path->skip_locking = 1;
 	path->search_commit_root = 1;
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 
 	key.objectid = last;
 	key.offset = 0;
@@ -2131,7 +2131,7 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	/* this will setup the path even if it fails to insert the back ref */
 	ret = insert_inline_extent_backref(trans, fs_info->extent_root, path,
@@ -2157,7 +2157,7 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
 
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	/* now insert the actual backref */
 	ret = insert_extent_backref(trans, root->fs_info->extent_root,
@@ -2270,7 +2270,7 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans,
 	}
 
 again:
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	ret = btrfs_search_slot(trans, root->fs_info->extent_root, &key,
 				path, 0, 1);
@@ -3007,9 +3007,9 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 
 	extent_op->flags_to_set = flags;
-	extent_op->update_flags = 1;
-	extent_op->update_key = 0;
-	extent_op->is_data = is_data ? 1 : 0;
+	extent_op->update_flags = true;
+	extent_op->update_key = false;
+	extent_op->is_data = is_data ? true : false;
 	extent_op->level = level;
 
 	ret = btrfs_add_delayed_extent_op(root->fs_info, trans, bytenr,
@@ -6472,7 +6472,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 
 	is_data = owner_objectid >= BTRFS_FIRST_FREE_OBJECTID;
@@ -8031,12 +8031,9 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		else
 			memset(&extent_op->key, 0, sizeof(extent_op->key));
 		extent_op->flags_to_set = flags;
-		if (skinny_metadata)
-			extent_op->update_key = 0;
-		else
-			extent_op->update_key = 1;
-		extent_op->update_flags = 1;
-		extent_op->is_data = 0;
+		extent_op->update_key = skinny_metadata ? false : true;
+		extent_op->update_flags = true;
+		extent_op->is_data = false;
 		extent_op->level = level;
 
 		ret = btrfs_add_delayed_tree_ref(root->fs_info, trans,
@@ -9745,7 +9742,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 
 	cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy);
 	if (btrfs_test_opt(root, SPACE_CACHE) &&

fs/btrfs/file-item.c

@@ -202,7 +202,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	}
 
 	if (bio->bi_iter.bi_size > PAGE_CACHE_SIZE * 8)
-		path->reada = 2;
+		path->reada = READA_FORWARD;
 
 	WARN_ON(bio->bi_vcnt <= 0);
 
@@ -328,7 +328,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 
 	if (search_commit) {
 		path->skip_locking = 1;
-		path->reada = 2;
+		path->reada = READA_FORWARD;
 		path->search_commit_root = 1;
 	}
 

fs/btrfs/free-space-cache.c

@@ -2016,7 +2016,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
 	return true;
 }
 
-static struct btrfs_free_space_op free_space_op = {
+static const struct btrfs_free_space_op free_space_op = {
 	.recalc_thresholds	= recalculate_thresholds,
 	.use_bitmap		= use_bitmap,
 };

fs/btrfs/free-space-cache.h

@@ -37,7 +37,7 @@ struct btrfs_free_space_ctl {
 	int total_bitmaps;
 	int unit;
 	u64 start;
-	struct btrfs_free_space_op *op;
+	const struct btrfs_free_space_op *op;
 	void *private;
 	struct mutex cache_writeout_mutex;
 	struct list_head trimming_ranges;

fs/btrfs/inode-map.c

@@ -48,7 +48,7 @@ static int caching_kthread(void *data)
 	/* Since the commit root is read-only, we can safely skip locking. */
 	path->skip_locking = 1;
 	path->search_commit_root = 1;
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 
 	key.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	key.offset = 0;
@@ -334,7 +334,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
 	return true;
 }
 
-static struct btrfs_free_space_op free_ino_op = {
+static const struct btrfs_free_space_op free_ino_op = {
 	.recalc_thresholds	= recalculate_thresholds,
 	.use_bitmap		= use_bitmap,
 };
@@ -356,7 +356,7 @@ static bool pinned_use_bitmap(struct btrfs_free_space_ctl *ctl,
 	return false;
 }
 
-static struct btrfs_free_space_op pinned_free_ino_op = {
+static const struct btrfs_free_space_op pinned_free_ino_op = {
 	.recalc_thresholds	= pinned_recalc_thresholds,
 	.use_bitmap		= pinned_use_bitmap,
 };

fs/btrfs/inode.c

@@ -81,17 +81,16 @@ static const struct inode_operations btrfs_file_inode_operations;
 static const struct address_space_operations btrfs_aops;
 static const struct address_space_operations btrfs_symlink_aops;
 static const struct file_operations btrfs_dir_file_operations;
-static struct extent_io_ops btrfs_extent_io_ops;
+static const struct extent_io_ops btrfs_extent_io_ops;
 
 static struct kmem_cache *btrfs_inode_cachep;
-static struct kmem_cache *btrfs_delalloc_work_cachep;
 struct kmem_cache *btrfs_trans_handle_cachep;
 struct kmem_cache *btrfs_transaction_cachep;
 struct kmem_cache *btrfs_path_cachep;
 struct kmem_cache *btrfs_free_space_cachep;
 
 #define S_SHIFT 12
-static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
+static const unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
 	[S_IFREG >> S_SHIFT]	= BTRFS_FT_REG_FILE,
 	[S_IFDIR >> S_SHIFT]	= BTRFS_FT_DIR,
 	[S_IFCHR >> S_SHIFT]	= BTRFS_FT_CHRDEV,
@@ -3113,55 +3112,47 @@ static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 				      start, (size_t)(end - start + 1));
 }
 
-struct delayed_iput {
-	struct list_head list;
-	struct inode *inode;
-};
-
-/* JDM: If this is fs-wide, why can't we add a pointer to
- * btrfs_inode instead and avoid the allocation? */
 void btrfs_add_delayed_iput(struct inode *inode)
 {
 	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
-	struct delayed_iput *delayed;
+	struct btrfs_inode *binode = BTRFS_I(inode);
 
 	if (atomic_add_unless(&inode->i_count, -1, 1))
 		return;
 
-	delayed = kmalloc(sizeof(*delayed), GFP_NOFS | __GFP_NOFAIL);
-	delayed->inode = inode;
-
 	spin_lock(&fs_info->delayed_iput_lock);
-	list_add_tail(&delayed->list, &fs_info->delayed_iputs);
+	if (binode->delayed_iput_count == 0) {
+		ASSERT(list_empty(&binode->delayed_iput));
+		list_add_tail(&binode->delayed_iput, &fs_info->delayed_iputs);
+	} else {
+		binode->delayed_iput_count++;
+	}
 	spin_unlock(&fs_info->delayed_iput_lock);
 }
 
 void btrfs_run_delayed_iputs(struct btrfs_root *root)
 {
-	LIST_HEAD(list);
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct delayed_iput *delayed;
-	int empty;
-
-	spin_lock(&fs_info->delayed_iput_lock);
-	empty = list_empty(&fs_info->delayed_iputs);
-	spin_unlock(&fs_info->delayed_iput_lock);
-	if (empty)
-		return;
 
 	down_read(&fs_info->delayed_iput_sem);
-
 	spin_lock(&fs_info->delayed_iput_lock);
-	list_splice_init(&fs_info->delayed_iputs, &list);
-	spin_unlock(&fs_info->delayed_iput_lock);
-
-	while (!list_empty(&list)) {
-		delayed = list_entry(list.next, struct delayed_iput, list);
-		list_del(&delayed->list);
-		iput(delayed->inode);
-		kfree(delayed);
+	while (!list_empty(&fs_info->delayed_iputs)) {
+		struct btrfs_inode *inode;
+
+		inode = list_first_entry(&fs_info->delayed_iputs,
+				struct btrfs_inode, delayed_iput);
+		if (inode->delayed_iput_count) {
+			inode->delayed_iput_count--;
+			list_move_tail(&inode->delayed_iput,
+					&fs_info->delayed_iputs);
+		} else {
+			list_del_init(&inode->delayed_iput);
+		}
+		spin_unlock(&fs_info->delayed_iput_lock);
+		iput(&inode->vfs_inode);
+		spin_lock(&fs_info->delayed_iput_lock);
 	}
-
+	spin_unlock(&fs_info->delayed_iput_lock);
 	up_read(&root->fs_info->delayed_iput_sem);
 }
 
@@ -3358,7 +3349,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 		ret = -ENOMEM;
 		goto out;
 	}
-	path->reada = -1;
+	path->reada = READA_BACK;
 
 	key.objectid = BTRFS_ORPHAN_OBJECTID;
 	key.type = BTRFS_ORPHAN_ITEM_KEY;
@@ -4324,7 +4315,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = -1;
+	path->reada = READA_BACK;
 
 	/*
 	 * We want to drop from the next block forward in case this new size is
@@ -5760,7 +5751,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 
 	if (key_type == BTRFS_DIR_INDEX_KEY) {
 		INIT_LIST_HEAD(&ins_list);
@@ -6791,7 +6782,7 @@ again:
 		 * Chances are we'll be called again, so go ahead and do
 		 * readahead
 		 */
-		path->reada = 1;
+		path->reada = READA_FORWARD;
 	}
 
 	ret = btrfs_lookup_file_extent(trans, root, path,
@@ -8563,15 +8554,28 @@ int btrfs_readpage(struct file *file, struct page *page)
 static int btrfs_writepage(struct page *page, struct writeback_control *wbc)
 {
 	struct extent_io_tree *tree;
-
+	struct inode *inode = page->mapping->host;
+	int ret;
 
 	if (current->flags & PF_MEMALLOC) {
 		redirty_page_for_writepage(wbc, page);
 		unlock_page(page);
 		return 0;
 	}
+
+	/*
+	 * If we are under memory pressure we will call this directly from the
+	 * VM, we need to make sure we have the inode referenced for the ordered
+	 * extent.  If not just return like we didn't do anything.
+	 */
+	if (!igrab(inode)) {
+		redirty_page_for_writepage(wbc, page);
+		return AOP_WRITEPAGE_ACTIVATE;
+	}
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
-	return extent_write_full_page(tree, page, btrfs_get_extent, wbc);
+	ret = extent_write_full_page(tree, page, btrfs_get_extent, wbc);
+	btrfs_add_delayed_iput(inode);
+	return ret;
 }
 
 static int btrfs_writepages(struct address_space *mapping,
@@ -9053,6 +9057,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->dir_index = 0;
 	ei->last_unlink_trans = 0;
 	ei->last_log_commit = 0;
+	ei->delayed_iput_count = 0;
 
 	spin_lock_init(&ei->lock);
 	ei->outstanding_extents = 0;
@@ -9077,6 +9082,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	mutex_init(&ei->delalloc_mutex);
 	btrfs_ordered_inode_tree_init(&ei->ordered_tree);
 	INIT_LIST_HEAD(&ei->delalloc_inodes);
+	INIT_LIST_HEAD(&ei->delayed_iput);
 	RB_CLEAR_NODE(&ei->rb_node);
 
 	return inode;
@@ -9181,8 +9187,6 @@ void btrfs_destroy_cachep(void)
 		kmem_cache_destroy(btrfs_path_cachep);
 	if (btrfs_free_space_cachep)
 		kmem_cache_destroy(btrfs_free_space_cachep);
-	if (btrfs_delalloc_work_cachep)
-		kmem_cache_destroy(btrfs_delalloc_work_cachep);
 }
 
 int btrfs_init_cachep(void)
@@ -9217,13 +9221,6 @@ int btrfs_init_cachep(void)
 	if (!btrfs_free_space_cachep)
 		goto fail;
 
-	btrfs_delalloc_work_cachep = kmem_cache_create("btrfs_delalloc_work",
-			sizeof(struct btrfs_delalloc_work), 0,
-			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
-			NULL);
-	if (!btrfs_delalloc_work_cachep)
-		goto fail;
-
 	return 0;
 fail:
 	btrfs_destroy_cachep();
@@ -9464,7 +9461,7 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
 {
 	struct btrfs_delalloc_work *work;
 
-	work = kmem_cache_zalloc(btrfs_delalloc_work_cachep, GFP_NOFS);
+	work = kmalloc(sizeof(*work), GFP_NOFS);
 	if (!work)
 		return NULL;
 
@@ -9482,7 +9479,7 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
 void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work)
 {
 	wait_for_completion(&work->completion);
-	kmem_cache_free(btrfs_delalloc_work_cachep, work);
+	kfree(work);
 }
 
 /*
@@ -10047,7 +10044,7 @@ static const struct file_operations btrfs_dir_file_operations = {
 	.fsync		= btrfs_sync_file,
 };
 
-static struct extent_io_ops btrfs_extent_io_ops = {
+static const struct extent_io_ops btrfs_extent_io_ops = {
 	.fill_delalloc = run_delalloc_range,
 	.submit_bio_hook = btrfs_submit_bio_hook,
 	.merge_bio_hook = btrfs_merge_bio_hook,

fs/btrfs/ioctl.c

@@ -655,22 +655,28 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 		return -EINVAL;
 
+	pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS);
+	if (!pending_snapshot)
+		return -ENOMEM;
+
+	pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item),
+			GFP_NOFS);
+	pending_snapshot->path = btrfs_alloc_path();
+	if (!pending_snapshot->root_item || !pending_snapshot->path) {
+		ret = -ENOMEM;
+		goto free_pending;
+	}
+
 	atomic_inc(&root->will_be_snapshoted);
 	smp_mb__after_atomic();
 	btrfs_wait_for_no_snapshoting_writes(root);
 
 	ret = btrfs_start_delalloc_inodes(root, 0);
 	if (ret)
-		goto out;
+		goto dec_and_free;
 
 	btrfs_wait_ordered_extents(root, -1);
 
-	pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS);
-	if (!pending_snapshot) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
 	btrfs_init_block_rsv(&pending_snapshot->block_rsv,
 			     BTRFS_BLOCK_RSV_TEMP);
 	/*
@@ -686,7 +692,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 					&pending_snapshot->qgroup_reserved,
 					false);
 	if (ret)
-		goto free;
+		goto dec_and_free;
 
 	pending_snapshot->dentry = dentry;
 	pending_snapshot->root = root;
@@ -737,11 +743,14 @@ fail:
 	btrfs_subvolume_release_metadata(BTRFS_I(dir)->root,
 					 &pending_snapshot->block_rsv,
 					 pending_snapshot->qgroup_reserved);
-free:
-	kfree(pending_snapshot);
-out:
+dec_and_free:
 	if (atomic_dec_and_test(&root->will_be_snapshoted))
 		wake_up_atomic_t(&root->will_be_snapshoted);
+free_pending:
+	kfree(pending_snapshot->root_item);
+	btrfs_free_path(pending_snapshot->path);
+	kfree(pending_snapshot);
+
 	return ret;
 }
 
@@ -3478,7 +3487,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 		return ret;
 	}
 
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 	/* clone data */
 	key.objectid = btrfs_ino(src);
 	key.type = BTRFS_EXTENT_DATA_KEY;
@@ -5286,7 +5295,7 @@ out_unlock:
 static int btrfs_ioctl_get_supported_features(struct file *file,
 					      void __user *arg)
 {
-	static struct btrfs_ioctl_feature_flags features[3] = {
+	static const struct btrfs_ioctl_feature_flags features[3] = {
 		INIT_FEATURE_FLAGS(SUPP),
 		INIT_FEATURE_FLAGS(SAFE_SET),
 		INIT_FEATURE_FLAGS(SAFE_CLEAR)

fs/btrfs/relocation.c

@@ -708,8 +708,8 @@ struct backref_node *build_backref_tree(struct reloc_control *rc,
 		err = -ENOMEM;
 		goto out;
 	}
-	path1->reada = 1;
-	path2->reada = 2;
+	path1->reada = READA_FORWARD;
+	path2->reada = READA_FORWARD;
 
 	node = alloc_backref_node(cache);
 	if (!node) {
@@ -2130,7 +2130,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 
 	reloc_root = root->reloc_root;
 	root_item = &reloc_root->root_item;
@@ -3527,7 +3527,7 @@ static int find_data_references(struct reloc_control *rc,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 
 	root = read_fs_root(rc->extent_root->fs_info, ref_root);
 	if (IS_ERR(root)) {
@@ -3917,7 +3917,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 
 	ret = prepare_to_relocate(rc);
 	if (ret) {
@@ -4343,7 +4343,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = -1;
+	path->reada = READA_BACK;
 
 	key.objectid = BTRFS_TREE_RELOC_OBJECTID;
 	key.type = BTRFS_ROOT_ITEM_KEY;

fs/btrfs/scrub.c

@@ -3507,7 +3507,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
@@ -3735,27 +3735,27 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
 	if (fs_info->scrub_workers_refcnt == 0) {
 		if (is_dev_replace)
 			fs_info->scrub_workers =
-				btrfs_alloc_workqueue("btrfs-scrub", flags,
+				btrfs_alloc_workqueue("scrub", flags,
 						      1, 4);
 		else
 			fs_info->scrub_workers =
-				btrfs_alloc_workqueue("btrfs-scrub", flags,
+				btrfs_alloc_workqueue("scrub", flags,
 						      max_active, 4);
 		if (!fs_info->scrub_workers)
 			goto fail_scrub_workers;
 
 		fs_info->scrub_wr_completion_workers =
-			btrfs_alloc_workqueue("btrfs-scrubwrc", flags,
+			btrfs_alloc_workqueue("scrubwrc", flags,
 					      max_active, 2);
 		if (!fs_info->scrub_wr_completion_workers)
 			goto fail_scrub_wr_completion_workers;
 
 		fs_info->scrub_nocow_workers =
-			btrfs_alloc_workqueue("btrfs-scrubnc", flags, 1, 0);
+			btrfs_alloc_workqueue("scrubnc", flags, 1, 0);
 		if (!fs_info->scrub_nocow_workers)
 			goto fail_scrub_nocow_workers;
 		fs_info->scrub_parity_workers =
-			btrfs_alloc_workqueue("btrfs-scrubparity", flags,
+			btrfs_alloc_workqueue("scrubparity", flags,
 					      max_active, 2);
 		if (!fs_info->scrub_parity_workers)
 			goto fail_scrub_parity_workers;

fs/btrfs/super.c

@@ -310,7 +310,7 @@ enum {
 	Opt_err,
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
 	{Opt_degraded, "degraded"},
 	{Opt_subvol, "subvol=%s"},
 	{Opt_subvolid, "subvolid=%s"},
@@ -1991,6 +1991,8 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
  * there are other factors that may change the result (like a new metadata
  * chunk).
  *
+ * If metadata is exhausted, f_bavail will be 0.
+ *
  * FIXME: not accurate for mixed block groups, total and free/used are ok,
  * available appears slightly larger.
  */
@@ -2002,11 +2004,13 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct btrfs_space_info *found;
 	u64 total_used = 0;
 	u64 total_free_data = 0;
+	u64 total_free_meta = 0;
 	int bits = dentry->d_sb->s_blocksize_bits;
 	__be32 *fsid = (__be32 *)fs_info->fsid;
 	unsigned factor = 1;
 	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
 	int ret;
+	u64 thresh = 0;
 
 	/*
 	 * holding chunk_muext to avoid allocating new chunks, holding
@@ -2032,6 +2036,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 				}
 			}
 		}
+		if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
+			total_free_meta += found->disk_total - found->disk_used;
 
 		total_used += found->disk_used;
 	}
@@ -2054,6 +2060,24 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail += div_u64(total_free_data, factor);
 	buf->f_bavail = buf->f_bavail >> bits;
 
+	/*
+	 * We calculate the remaining metadata space minus global reserve. If
+	 * this is (supposedly) smaller than zero, there's no space. But this
+	 * does not hold in practice, the exhausted state happens where's still
+	 * some positive delta. So we apply some guesswork and compare the
+	 * delta to a 4M threshold.  (Practically observed delta was ~2M.)
+	 *
+	 * We probably cannot calculate the exact threshold value because this
+	 * depends on the internal reservations requested by various
+	 * operations, so some operations that consume a few metadata will
+	 * succeed even if the Avail is zero. But this is better than the other
+	 * way around.
+	 */
+	thresh = 4 * 1024 * 1024;
+
+	if (total_free_meta - thresh < block_rsv->size)
+		buf->f_bavail = 0;
+
 	buf->f_type = BTRFS_SUPER_MAGIC;
 	buf->f_bsize = dentry->d_sb->s_blocksize;
 	buf->f_namelen = BTRFS_NAME_LEN;

fs/btrfs/tests/free-space-tests.c

@@ -410,9 +410,11 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	int ret;
 	u64 offset;
 	u64 max_extent_size;
-
-	bool (*use_bitmap_op)(struct btrfs_free_space_ctl *,
-			      struct btrfs_free_space *);
+	const struct btrfs_free_space_op test_free_space_ops = {
+		.recalc_thresholds = cache->free_space_ctl->op->recalc_thresholds,
+		.use_bitmap = test_use_bitmap,
+	};
+	const struct btrfs_free_space_op *orig_free_space_ops;
 
 	test_msg("Running space stealing from bitmap to extent\n");
 
@@ -434,8 +436,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * that forces use of bitmaps as soon as we have at least 1
 	 * extent entry.
 	 */
-	use_bitmap_op = cache->free_space_ctl->op->use_bitmap;
-	cache->free_space_ctl->op->use_bitmap = test_use_bitmap;
+	orig_free_space_ops = cache->free_space_ctl->op;
+	cache->free_space_ctl->op = &test_free_space_ops;
 
 	/*
 	 * Extent entry covering free space range [128Mb - 256Kb, 128Mb - 128Kb[
@@ -842,7 +844,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	if (ret)
 		return ret;
 
-	cache->free_space_ctl->op->use_bitmap = use_bitmap_op;
+	cache->free_space_ctl->op = orig_free_space_ops;
 	__btrfs_remove_free_space_cache(cache->free_space_ctl);
 
 	return 0;

fs/btrfs/transaction.c

@@ -1336,17 +1336,11 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	u64 root_flags;
 	uuid_le new_uuid;
 
-	path = btrfs_alloc_path();
-	if (!path) {
-		pending->error = -ENOMEM;
-		return 0;
-	}
+	ASSERT(pending->path);
+	path = pending->path;
 
-	new_root_item = kmalloc(sizeof(*new_root_item), GFP_NOFS);
-	if (!new_root_item) {
-		pending->error = -ENOMEM;
-		goto root_item_alloc_fail;
-	}
+	ASSERT(pending->root_item);
+	new_root_item = pending->root_item;
 
 	pending->error = btrfs_find_free_objectid(tree_root, &objectid);
 	if (pending->error)
@@ -1579,8 +1573,10 @@ clear_skip_qgroup:
 	btrfs_clear_skip_qgroup(trans);
 no_free_objectid:
 	kfree(new_root_item);
-root_item_alloc_fail:
+	pending->root_item = NULL;
 	btrfs_free_path(path);
+	pending->path = NULL;
+
 	return ret;
 }
 

fs/btrfs/transaction.h

@@ -137,8 +137,10 @@ struct btrfs_pending_snapshot {
 	struct dentry *dentry;
 	struct inode *dir;
 	struct btrfs_root *root;
+	struct btrfs_root_item *root_item;
 	struct btrfs_root *snap;
 	struct btrfs_qgroup_inherit *inherit;
+	struct btrfs_path *path;
 	/* block reservation for the operation */
 	struct btrfs_block_rsv block_rsv;
 	u64 qgroup_reserved;

fs/btrfs/volumes.c

@@ -1103,7 +1103,7 @@ int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 
 	key.objectid = device->devid;
 	key.offset = start;
@@ -1272,7 +1272,7 @@ again:
 		goto out;
 	}
 
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
@@ -3724,14 +3724,6 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		goto out;
 	}
 
-	/* allow dup'ed data chunks only in mixed mode */
-	if (!mixed && (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
-	    (bctl->data.target & BTRFS_BLOCK_GROUP_DUP)) {
-		btrfs_err(fs_info, "dup for data is not allowed");
-		ret = -EINVAL;
-		goto out;
-	}
-
 	/* allow to reduce meta or sys integrity only if force set */
 	allowed = BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
 			BTRFS_BLOCK_GROUP_RAID10 |
@@ -3757,6 +3749,13 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		}
 	} while (read_seqretry(&fs_info->profiles_lock, seq));
 
+	if (btrfs_get_num_tolerated_disk_barrier_failures(bctl->meta.target) <
+		btrfs_get_num_tolerated_disk_barrier_failures(bctl->data.target)) {
+		btrfs_warn(fs_info,
+	"metatdata profile 0x%llx has lower redundancy than data profile 0x%llx",
+			bctl->meta.target, bctl->data.target);
+	}
+
 	if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
 		fs_info->num_tolerated_disk_barrier_failures = min(
 			btrfs_calc_num_tolerated_disk_barrier_failures(fs_info),
@@ -4269,7 +4268,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size)
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 
 	lock_chunks(root);
 
@@ -6526,6 +6525,14 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 				goto out_short_read;
 
 			num_stripes = btrfs_chunk_num_stripes(sb, chunk);
+			if (!num_stripes) {
+				printk(KERN_ERR
+	    "BTRFS: invalid number of stripes %u in sys_array at offset %u\n",
+					num_stripes, cur_offset);
+				ret = -EIO;
+				break;
+			}
+
 			len = btrfs_chunk_item_size(num_stripes);
 			if (cur_offset + len > array_size)
 				goto out_short_read;
@@ -6534,6 +6541,9 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 			if (ret)
 				break;
 		} else {
+			printk(KERN_ERR
+		"BTRFS: unexpected item type %u in sys_array at offset %u\n",
+				(u32)key.type, cur_offset);
 			ret = -EIO;
 			break;
 		}

fs/btrfs/xattr.c

@@ -283,7 +283,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 
 	/* search for our xattrs */
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);