Merge branch 'ino-alloc' of git://repo.or.cz/linux-btrfs-devel into inode_numbers

Conflicts:
	fs/btrfs/free-space-cache.c
Signed-off-by: NChris Mason <chris.mason@oracle.com>

fs/btrfs/btrfs_inode.h

@@ -166,6 +166,15 @@ static inline struct btrfs_inode *BTRFS_I(struct inode *inode)
 	return container_of(inode, struct btrfs_inode, vfs_inode);
 }
 
+static inline u64 btrfs_ino(struct inode *inode)
+{
+	u64 ino = BTRFS_I(inode)->location.objectid;
+
+	if (ino <= BTRFS_FIRST_FREE_OBJECTID)
+		ino = inode->i_ino;
+	return ino;
+}
+
 static inline void btrfs_i_size_write(struct inode *inode, u64 size)
 {
 	i_size_write(inode, size);

fs/btrfs/compression.c

@@ -125,9 +125,10 @@ static int check_compressed_csum(struct inode *inode,
 		kunmap_atomic(kaddr, KM_USER0);
 
 		if (csum != *cb_sum) {
-			printk(KERN_INFO "btrfs csum failed ino %lu "
+			printk(KERN_INFO "btrfs csum failed ino %llu "
 			       "extent %llu csum %u "
-			       "wanted %u mirror %d\n", inode->i_ino,
+			       "wanted %u mirror %d\n",
+			       (unsigned long long)btrfs_ino(inode),
 			       (unsigned long long)disk_start,
 			       csum, *cb_sum, cb->mirror_num);
 			ret = -EIO;

fs/btrfs/ctree.h

@@ -105,6 +105,12 @@ struct btrfs_ordered_sum;
 /* For storing free space cache */
 #define BTRFS_FREE_SPACE_OBJECTID -11ULL
 
+/*
+ * The inode number assigned to the special inode for sotring
+ * free ino cache
+ */
+#define BTRFS_FREE_INO_OBJECTID -12ULL
+
 /* dummy objectid represents multiple objectids */
 #define BTRFS_MULTIPLE_OBJECTIDS -255ULL
 
@@ -830,9 +836,6 @@ struct btrfs_block_group_cache {
 	u64 bytes_super;
 	u64 flags;
 	u64 sectorsize;
-	int extents_thresh;
-	int free_extents;
-	int total_bitmaps;
 	unsigned int ro:1;
 	unsigned int dirty:1;
 	unsigned int iref:1;
@@ -847,9 +850,7 @@ struct btrfs_block_group_cache {
 	struct btrfs_space_info *space_info;
 
 	/* free space cache stuff */
-	spinlock_t tree_lock;
-	struct rb_root free_space_offset;
-	u64 free_space;
+	struct btrfs_free_space_ctl *free_space_ctl;
 
 	/* block group cache stuff */
 	struct rb_node cache_node;
@@ -1107,6 +1108,16 @@ struct btrfs_root {
 	spinlock_t accounting_lock;
 	struct btrfs_block_rsv *block_rsv;
 
+	/* free ino cache stuff */
+	struct mutex fs_commit_mutex;
+	struct btrfs_free_space_ctl *free_ino_ctl;
+	enum btrfs_caching_type cached;
+	spinlock_t cache_lock;
+	wait_queue_head_t cache_wait;
+	struct btrfs_free_space_ctl *free_ino_pinned;
+	u64 cache_progress;
+	struct inode *cache_inode;
+
 	struct mutex log_mutex;
 	wait_queue_head_t log_writer_wait;
 	wait_queue_head_t log_commit_wait[2];
@@ -2413,12 +2424,6 @@ int btrfs_del_orphan_item(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root, u64 offset);
 int btrfs_find_orphan_item(struct btrfs_root *root, u64 offset);
 
-/* inode-map.c */
-int btrfs_find_free_objectid(struct btrfs_trans_handle *trans,
-			     struct btrfs_root *fs_root,
-			     u64 dirid, u64 *objectid);
-int btrfs_find_highest_inode(struct btrfs_root *fs_root, u64 *objectid);
-
 /* inode-item.c */
 int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,

fs/btrfs/disk-io.c

@@ -41,6 +41,7 @@
 #include "locking.h"
 #include "tree-log.h"
 #include "free-space-cache.h"
+#include "inode-map.h"
 
 static struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
@@ -1326,6 +1327,19 @@ struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
 	if (IS_ERR(root))
 		return root;
 
+	root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS);
+	if (!root->free_ino_ctl)
+		goto fail;
+	root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned),
+					GFP_NOFS);
+	if (!root->free_ino_pinned)
+		goto fail;
+
+	btrfs_init_free_ino_ctl(root);
+	mutex_init(&root->fs_commit_mutex);
+	spin_lock_init(&root->cache_lock);
+	init_waitqueue_head(&root->cache_wait);
+
 	set_anon_super(&root->anon_super, NULL);
 
 	if (btrfs_root_refs(&root->root_item) == 0) {
@@ -2404,12 +2418,15 @@ int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
 	if (btrfs_root_refs(&root->root_item) == 0)
 		synchronize_srcu(&fs_info->subvol_srcu);
 
+	__btrfs_remove_free_space_cache(root->free_ino_pinned);
+	__btrfs_remove_free_space_cache(root->free_ino_ctl);
 	free_fs_root(root);
 	return 0;
 }
 
 static void free_fs_root(struct btrfs_root *root)
 {
+	iput(root->cache_inode);
 	WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
 	if (root->anon_super.s_dev) {
 		down_write(&root->anon_super.s_umount);
@@ -2417,6 +2434,8 @@ static void free_fs_root(struct btrfs_root *root)
 	}
 	free_extent_buffer(root->node);
 	free_extent_buffer(root->commit_root);
+	kfree(root->free_ino_ctl);
+	kfree(root->free_ino_pinned);
 	kfree(root->name);
 	kfree(root);
 }

fs/btrfs/export.c

@@ -32,7 +32,7 @@ static int btrfs_encode_fh(struct dentry *dentry, u32 *fh, int *max_len,
 	len  = BTRFS_FID_SIZE_NON_CONNECTABLE;
 	type = FILEID_BTRFS_WITHOUT_PARENT;
 
-	fid->objectid = inode->i_ino;
+	fid->objectid = btrfs_ino(inode);
 	fid->root_objectid = BTRFS_I(inode)->root->objectid;
 	fid->gen = inode->i_generation;
 
@@ -178,13 +178,13 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
 	if (!path)
 		return ERR_PTR(-ENOMEM);
 
-	if (dir->i_ino == BTRFS_FIRST_FREE_OBJECTID) {
+	if (btrfs_ino(dir) == BTRFS_FIRST_FREE_OBJECTID) {
 		key.objectid = root->root_key.objectid;
 		key.type = BTRFS_ROOT_BACKREF_KEY;
 		key.offset = (u64)-1;
 		root = root->fs_info->tree_root;
 	} else {
-		key.objectid = dir->i_ino;
+		key.objectid = btrfs_ino(dir);
 		key.type = BTRFS_INODE_REF_KEY;
 		key.offset = (u64)-1;
 	}
@@ -244,6 +244,7 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 	struct btrfs_key key;
 	int name_len;
 	int ret;
+	u64 ino;
 
 	if (!dir || !inode)
 		return -EINVAL;
@@ -251,19 +252,21 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 	if (!S_ISDIR(dir->i_mode))
 		return -EINVAL;
 
+	ino = btrfs_ino(inode);
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 	path->leave_spinning = 1;
 
-	if (inode->i_ino == BTRFS_FIRST_FREE_OBJECTID) {
+	if (ino == BTRFS_FIRST_FREE_OBJECTID) {
 		key.objectid = BTRFS_I(inode)->root->root_key.objectid;
 		key.type = BTRFS_ROOT_BACKREF_KEY;
 		key.offset = (u64)-1;
 		root = root->fs_info->tree_root;
 	} else {
-		key.objectid = inode->i_ino;
-		key.offset = dir->i_ino;
+		key.objectid = ino;
+		key.offset = btrfs_ino(dir);
 		key.type = BTRFS_INODE_REF_KEY;
 	}
 
@@ -272,7 +275,7 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 		btrfs_free_path(path);
 		return ret;
 	} else if (ret > 0) {
-		if (inode->i_ino == BTRFS_FIRST_FREE_OBJECTID) {
+		if (ino == BTRFS_FIRST_FREE_OBJECTID) {
 			path->slots[0]--;
 		} else {
 			btrfs_free_path(path);
@@ -281,11 +284,11 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 	}
 	leaf = path->nodes[0];
 
-	if (inode->i_ino == BTRFS_FIRST_FREE_OBJECTID) {
-	       rref = btrfs_item_ptr(leaf, path->slots[0],
+	if (ino == BTRFS_FIRST_FREE_OBJECTID) {
+		rref = btrfs_item_ptr(leaf, path->slots[0],
 				     struct btrfs_root_ref);
-	       name_ptr = (unsigned long)(rref + 1);
-	       name_len = btrfs_root_ref_name_len(leaf, rref);
+		name_ptr = (unsigned long)(rref + 1);
+		name_len = btrfs_root_ref_name_len(leaf, rref);
 	} else {
 		iref = btrfs_item_ptr(leaf, path->slots[0],
 				      struct btrfs_inode_ref);

fs/btrfs/extent-tree.c

@@ -105,6 +105,7 @@ void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
 		WARN_ON(cache->pinned > 0);
 		WARN_ON(cache->reserved > 0);
 		WARN_ON(cache->reserved_pinned > 0);
+		kfree(cache->free_space_ctl);
 		kfree(cache);
 	}
 }
@@ -3144,7 +3145,8 @@ int btrfs_check_data_free_space(struct inode *inode, u64 bytes)
 	/* make sure bytes are sectorsize aligned */
 	bytes = (bytes + root->sectorsize - 1) & ~((u64)root->sectorsize - 1);
 
-	if (root == root->fs_info->tree_root) {
+	if (root == root->fs_info->tree_root ||
+	    BTRFS_I(inode)->location.objectid == BTRFS_FREE_INO_OBJECTID) {
 		alloc_chunk = 0;
 		committed = 1;
 	}
@@ -4893,7 +4895,7 @@ wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
 		return 0;
 
 	wait_event(caching_ctl->wait, block_group_cache_done(cache) ||
-		   (cache->free_space >= num_bytes));
+		   (cache->free_space_ctl->free_space >= num_bytes));
 
 	put_caching_control(caching_ctl);
 	return 0;
@@ -7008,8 +7010,8 @@ static noinline int get_new_locations(struct inode *reloc_inode,
 
 	cur_pos = extent_key->objectid - offset;
 	last_byte = extent_key->objectid + extent_key->offset;
-	ret = btrfs_lookup_file_extent(NULL, root, path, reloc_inode->i_ino,
-				       cur_pos, 0);
+	ret = btrfs_lookup_file_extent(NULL, root, path,
+				       btrfs_ino(reloc_inode), cur_pos, 0);
 	if (ret < 0)
 		goto out;
 	if (ret > 0) {
@@ -7032,7 +7034,7 @@ static noinline int get_new_locations(struct inode *reloc_inode,
 		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
 		if (found_key.offset != cur_pos ||
 		    found_key.type != BTRFS_EXTENT_DATA_KEY ||
-		    found_key.objectid != reloc_inode->i_ino)
+		    found_key.objectid != btrfs_ino(reloc_inode))
 			break;
 
 		fi = btrfs_item_ptr(leaf, path->slots[0],
@@ -7178,7 +7180,7 @@ static noinline int replace_one_extent(struct btrfs_trans_handle *trans,
 				break;
 		}
 
-		if (inode && key.objectid != inode->i_ino) {
+		if (inode && key.objectid != btrfs_ino(inode)) {
 			BUG_ON(extent_locked);
 			btrfs_release_path(root, path);
 			mutex_unlock(&inode->i_mutex);
@@ -7487,7 +7489,7 @@ static noinline int invalidate_extent_cache(struct btrfs_root *root,
 			continue;
 		if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0)
 			continue;
-		if (!inode || inode->i_ino != key.objectid) {
+		if (!inode || btrfs_ino(inode) != key.objectid) {
 			iput(inode);
 			inode = btrfs_ilookup(target_root->fs_info->sb,
 					      key.objectid, target_root, 1);
@@ -8555,10 +8557,16 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 			ret = -ENOMEM;
 			goto error;
 		}
+		cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
+						GFP_NOFS);
+		if (!cache->free_space_ctl) {
+			kfree(cache);
+			ret = -ENOMEM;
+			goto error;
+		}
 
 		atomic_set(&cache->count, 1);
 		spin_lock_init(&cache->lock);
-		spin_lock_init(&cache->tree_lock);
 		cache->fs_info = info;
 		INIT_LIST_HEAD(&cache->list);
 		INIT_LIST_HEAD(&cache->cluster_list);
@@ -8566,14 +8574,6 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 		if (need_clear)
 			cache->disk_cache_state = BTRFS_DC_CLEAR;
 
-		/*
-		 * we only want to have 32k of ram per block group for keeping
-		 * track of free space, and if we pass 1/2 of that we want to
-		 * start converting things over to using bitmaps
-		 */
-		cache->extents_thresh = ((1024 * 32) / 2) /
-			sizeof(struct btrfs_free_space);
-
 		read_extent_buffer(leaf, &cache->item,
 				   btrfs_item_ptr_offset(leaf, path->slots[0]),
 				   sizeof(cache->item));
@@ -8584,6 +8584,8 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 		cache->flags = btrfs_block_group_flags(&cache->item);
 		cache->sectorsize = root->sectorsize;
 
+		btrfs_init_free_space_ctl(cache);
+
 		/*
 		 * We need to exclude the super stripes now so that the space
 		 * info has super bytes accounted for, otherwise we'll think
@@ -8670,6 +8672,12 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	cache = kzalloc(sizeof(*cache), GFP_NOFS);
 	if (!cache)
 		return -ENOMEM;
+	cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
+					GFP_NOFS);
+	if (!cache->free_space_ctl) {
+		kfree(cache);
+		return -ENOMEM;
+	}
 
 	cache->key.objectid = chunk_offset;
 	cache->key.offset = size;
@@ -8677,19 +8685,13 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	cache->sectorsize = root->sectorsize;
 	cache->fs_info = root->fs_info;
 
-	/*
-	 * we only want to have 32k of ram per block group for keeping track
-	 * of free space, and if we pass 1/2 of that we want to start
-	 * converting things over to using bitmaps
-	 */
-	cache->extents_thresh = ((1024 * 32) / 2) /
-		sizeof(struct btrfs_free_space);
 	atomic_set(&cache->count, 1);
 	spin_lock_init(&cache->lock);
-	spin_lock_init(&cache->tree_lock);
 	INIT_LIST_HEAD(&cache->list);
 	INIT_LIST_HEAD(&cache->cluster_list);
 
+	btrfs_init_free_space_ctl(cache);
+
 	btrfs_set_block_group_used(&cache->item, bytes_used);
 	btrfs_set_block_group_chunk_objectid(&cache->item, chunk_objectid);
 	cache->flags = type;

fs/btrfs/extent_io.c

@@ -3030,7 +3030,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	 * because there might be preallocation past i_size
 	 */
 	ret = btrfs_lookup_file_extent(NULL, BTRFS_I(inode)->root,
-				       path, inode->i_ino, -1, 0);
+				       path, btrfs_ino(inode), -1, 0);
 	if (ret < 0) {
 		btrfs_free_path(path);
 		return ret;
@@ -3043,7 +3043,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	found_type = btrfs_key_type(&found_key);
 
 	/* No extents, but there might be delalloc bits */
-	if (found_key.objectid != inode->i_ino ||
+	if (found_key.objectid != btrfs_ino(inode) ||
 	    found_type != BTRFS_EXTENT_DATA_KEY) {
 		/* have to trust i_size as the end */
 		last = (u64)-1;

fs/btrfs/file-item.c

@@ -208,8 +208,9 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 						EXTENT_NODATASUM, GFP_NOFS);
 				} else {
 					printk(KERN_INFO "btrfs no csum found "
-					       "for inode %lu start %llu\n",
-					       inode->i_ino,
+					       "for inode %llu start %llu\n",
+					       (unsigned long long)
+					       btrfs_ino(inode),
 					       (unsigned long long)offset);
 				}
 				item = NULL;

fs/btrfs/file.c

@@ -298,6 +298,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode,
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	struct btrfs_key new_key;
+	u64 ino = btrfs_ino(inode);
 	u64 search_start = start;
 	u64 disk_bytenr = 0;
 	u64 num_bytes = 0;
@@ -318,14 +319,14 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode,
 
 	while (1) {
 		recow = 0;
-		ret = btrfs_lookup_file_extent(trans, root, path, inode->i_ino,
+		ret = btrfs_lookup_file_extent(trans, root, path, ino,
 					       search_start, -1);
 		if (ret < 0)
 			break;
 		if (ret > 0 && path->slots[0] > 0 && search_start == start) {
 			leaf = path->nodes[0];
 			btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1);
-			if (key.objectid == inode->i_ino &&
+			if (key.objectid == ino &&
 			    key.type == BTRFS_EXTENT_DATA_KEY)
 				path->slots[0]--;
 		}
@@ -346,7 +347,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode,
 		}
 
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-		if (key.objectid > inode->i_ino ||
+		if (key.objectid > ino ||
 		    key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end)
 			break;
 
@@ -592,6 +593,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 	int del_slot = 0;
 	int recow;
 	int ret;
+	u64 ino = btrfs_ino(inode);
 
 	btrfs_drop_extent_cache(inode, start, end - 1, 0);
 
@@ -600,7 +602,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 again:
 	recow = 0;
 	split = start;
-	key.objectid = inode->i_ino;
+	key.objectid = ino;
 	key.type = BTRFS_EXTENT_DATA_KEY;
 	key.offset = split;
 
@@ -612,8 +614,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 
 	leaf = path->nodes[0];
 	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-	BUG_ON(key.objectid != inode->i_ino ||
-	       key.type != BTRFS_EXTENT_DATA_KEY);
+	BUG_ON(key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY);
 	fi = btrfs_item_ptr(leaf, path->slots[0],
 			    struct btrfs_file_extent_item);
 	BUG_ON(btrfs_file_extent_type(leaf, fi) !=
@@ -630,7 +631,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 		other_start = 0;
 		other_end = start;
 		if (extent_mergeable(leaf, path->slots[0] - 1,
-				     inode->i_ino, bytenr, orig_offset,
+				     ino, bytenr, orig_offset,
 				     &other_start, &other_end)) {
 			new_key.offset = end;
 			btrfs_set_item_key_safe(trans, root, path, &new_key);
@@ -653,7 +654,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 		other_start = end;
 		other_end = 0;
 		if (extent_mergeable(leaf, path->slots[0] + 1,
-				     inode->i_ino, bytenr, orig_offset,
+				     ino, bytenr, orig_offset,
 				     &other_start, &other_end)) {
 			fi = btrfs_item_ptr(leaf, path->slots[0],
 					    struct btrfs_file_extent_item);
@@ -702,7 +703,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 
 		ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0,
 					   root->root_key.objectid,
-					   inode->i_ino, orig_offset);
+					   ino, orig_offset);
 		BUG_ON(ret);
 
 		if (split == start) {
@@ -718,7 +719,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 	other_start = end;
 	other_end = 0;
 	if (extent_mergeable(leaf, path->slots[0] + 1,
-			     inode->i_ino, bytenr, orig_offset,
+			     ino, bytenr, orig_offset,
 			     &other_start, &other_end)) {
 		if (recow) {
 			btrfs_release_path(root, path);
@@ -729,13 +730,13 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 		del_nr++;
 		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
 					0, root->root_key.objectid,
-					inode->i_ino, orig_offset);
+					ino, orig_offset);
 		BUG_ON(ret);
 	}
 	other_start = 0;
 	other_end = start;
 	if (extent_mergeable(leaf, path->slots[0] - 1,
-			     inode->i_ino, bytenr, orig_offset,
+			     ino, bytenr, orig_offset,
 			     &other_start, &other_end)) {
 		if (recow) {
 			btrfs_release_path(root, path);
@@ -746,7 +747,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 		del_nr++;
 		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
 					0, root->root_key.objectid,
-					inode->i_ino, orig_offset);
+					ino, orig_offset);
 		BUG_ON(ret);
 	}
 	if (del_nr == 0) {

fs/btrfs/free-space-cache.h

@@ -27,6 +27,25 @@ struct btrfs_free_space {
 	struct list_head list;
 };
 
+struct btrfs_free_space_ctl {
+	spinlock_t tree_lock;
+	struct rb_root free_space_offset;
+	u64 free_space;
+	int extents_thresh;
+	int free_extents;
+	int total_bitmaps;
+	int unit;
+	u64 start;
+	struct btrfs_free_space_op *op;
+	void *private;
+};
+
+struct btrfs_free_space_op {
+	void (*recalc_thresholds)(struct btrfs_free_space_ctl *ctl);
+	bool (*use_bitmap)(struct btrfs_free_space_ctl *ctl,
+			   struct btrfs_free_space *info);
+};
+
 struct inode *lookup_free_space_inode(struct btrfs_root *root,
 				      struct btrfs_block_group_cache
 				      *block_group, struct btrfs_path *path);
@@ -45,17 +64,38 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 			  struct btrfs_trans_handle *trans,
 			  struct btrfs_block_group_cache *block_group,
 			  struct btrfs_path *path);
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
-			 u64 bytenr, u64 size);
+
+struct inode *lookup_free_ino_inode(struct btrfs_root *root,
+				    struct btrfs_path *path);
+int create_free_ino_inode(struct btrfs_root *root,
+			  struct btrfs_trans_handle *trans,
+			  struct btrfs_path *path);
+int load_free_ino_cache(struct btrfs_fs_info *fs_info,
+			struct btrfs_root *root);
+int btrfs_write_out_ino_cache(struct btrfs_root *root,
+			      struct btrfs_trans_handle *trans,
+			      struct btrfs_path *path);
+
+void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group);
+int __btrfs_add_free_space(struct btrfs_free_space_ctl *ctl,
+			   u64 bytenr, u64 size);
+static inline int
+btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+		     u64 bytenr, u64 size)
+{
+	return __btrfs_add_free_space(block_group->free_space_ctl,
+				      bytenr, size);
+}
 int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
 			    u64 bytenr, u64 size);
+void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl);
 void btrfs_remove_free_space_cache(struct btrfs_block_group_cache
-				   *block_group);
+				     *block_group);
 u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
 			       u64 offset, u64 bytes, u64 empty_size);
+u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root);
 void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
 			   u64 bytes);
-u64 btrfs_block_group_free_space(struct btrfs_block_group_cache *block_group);
 int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root,
 			     struct btrfs_block_group_cache *block_group,

fs/btrfs/inode-map.c

@@ -16,11 +16,430 @@
  * Boston, MA 021110-1307, USA.
  */
 
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/pagemap.h>
+
 #include "ctree.h"
 #include "disk-io.h"
+#include "free-space-cache.h"
+#include "inode-map.h"
 #include "transaction.h"
 
-int btrfs_find_highest_inode(struct btrfs_root *root, u64 *objectid)
+static int caching_kthread(void *data)
+{
+	struct btrfs_root *root = data;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct btrfs_key key;
+	struct btrfs_path *path;
+	struct extent_buffer *leaf;
+	u64 last = (u64)-1;
+	int slot;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	/* Since the commit root is read-only, we can safely skip locking. */
+	path->skip_locking = 1;
+	path->search_commit_root = 1;
+	path->reada = 2;
+
+	key.objectid = BTRFS_FIRST_FREE_OBJECTID;
+	key.offset = 0;
+	key.type = BTRFS_INODE_ITEM_KEY;
+again:
+	/* need to make sure the commit_root doesn't disappear */
+	mutex_lock(&root->fs_commit_mutex);
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+
+	while (1) {
+		smp_mb();
+		if (fs_info->closing > 1)
+			goto out;
+
+		leaf = path->nodes[0];
+		slot = path->slots[0];
+		if (path->slots[0] >= btrfs_header_nritems(leaf)) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto out;
+			else if (ret > 0)
+				break;
+
+			if (need_resched() ||
+			    btrfs_transaction_in_commit(fs_info)) {
+				leaf = path->nodes[0];
+
+				if (btrfs_header_nritems(leaf) == 0) {
+					WARN_ON(1);
+					break;
+				}
+
+				/*
+				 * Save the key so we can advances forward
+				 * in the next search.
+				 */
+				btrfs_item_key_to_cpu(leaf, &key, 0);
+				btrfs_release_path(root, path);
+				root->cache_progress = last;
+				mutex_unlock(&root->fs_commit_mutex);
+				schedule_timeout(1);
+				goto again;
+			} else
+				continue;
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+
+		if (key.type != BTRFS_INODE_ITEM_KEY)
+			goto next;
+
+		if (key.objectid >= BTRFS_LAST_FREE_OBJECTID)
+			break;
+
+		if (last != (u64)-1 && last + 1 != key.objectid) {
+			__btrfs_add_free_space(ctl, last + 1,
+					       key.objectid - last - 1);
+			wake_up(&root->cache_wait);
+		}
+
+		last = key.objectid;
+next:
+		path->slots[0]++;
+	}
+
+	if (last < BTRFS_LAST_FREE_OBJECTID - 1) {
+		__btrfs_add_free_space(ctl, last + 1,
+				       BTRFS_LAST_FREE_OBJECTID - last - 1);
+	}
+
+	spin_lock(&root->cache_lock);
+	root->cached = BTRFS_CACHE_FINISHED;
+	spin_unlock(&root->cache_lock);
+
+	root->cache_progress = (u64)-1;
+	btrfs_unpin_free_ino(root);
+out:
+	wake_up(&root->cache_wait);
+	mutex_unlock(&root->fs_commit_mutex);
+
+	btrfs_free_path(path);
+
+	return ret;
+}
+
+static void start_caching(struct btrfs_root *root)
+{
+	struct task_struct *tsk;
+	int ret;
+
+	spin_lock(&root->cache_lock);
+	if (root->cached != BTRFS_CACHE_NO) {
+		spin_unlock(&root->cache_lock);
+		return;
+	}
+
+	root->cached = BTRFS_CACHE_STARTED;
+	spin_unlock(&root->cache_lock);
+
+	ret = load_free_ino_cache(root->fs_info, root);
+	if (ret == 1) {
+		spin_lock(&root->cache_lock);
+		root->cached = BTRFS_CACHE_FINISHED;
+		spin_unlock(&root->cache_lock);
+		return;
+	}
+
+	tsk = kthread_run(caching_kthread, root, "btrfs-ino-cache-%llu\n",
+			  root->root_key.objectid);
+	BUG_ON(IS_ERR(tsk));
+}
+
+int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid)
+{
+again:
+	*objectid = btrfs_find_ino_for_alloc(root);
+
+	if (*objectid != 0)
+		return 0;
+
+	start_caching(root);
+
+	wait_event(root->cache_wait,
+		   root->cached == BTRFS_CACHE_FINISHED ||
+		   root->free_ino_ctl->free_space > 0);
+
+	if (root->cached == BTRFS_CACHE_FINISHED &&
+	    root->free_ino_ctl->free_space == 0)
+		return -ENOSPC;
+	else
+		goto again;
+}
+
+void btrfs_return_ino(struct btrfs_root *root, u64 objectid)
+{
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct btrfs_free_space_ctl *pinned = root->free_ino_pinned;
+again:
+	if (root->cached == BTRFS_CACHE_FINISHED) {
+		__btrfs_add_free_space(ctl, objectid, 1);
+	} else {
+		/*
+		 * If we are in the process of caching free ino chunks,
+		 * to avoid adding the same inode number to the free_ino
+		 * tree twice due to cross transaction, we'll leave it
+		 * in the pinned tree until a transaction is committed
+		 * or the caching work is done.
+		 */
+
+		mutex_lock(&root->fs_commit_mutex);
+		spin_lock(&root->cache_lock);
+		if (root->cached == BTRFS_CACHE_FINISHED) {
+			spin_unlock(&root->cache_lock);
+			mutex_unlock(&root->fs_commit_mutex);
+			goto again;
+		}
+		spin_unlock(&root->cache_lock);
+
+		start_caching(root);
+
+		if (objectid <= root->cache_progress)
+			__btrfs_add_free_space(ctl, objectid, 1);
+		else
+			__btrfs_add_free_space(pinned, objectid, 1);
+
+		mutex_unlock(&root->fs_commit_mutex);
+	}
+}
+
+/*
+ * When a transaction is committed, we'll move those inode numbers which
+ * are smaller than root->cache_progress from pinned tree to free_ino tree,
+ * and others will just be dropped, because the commit root we were
+ * searching has changed.
+ *
+ * Must be called with root->fs_commit_mutex held
+ */
+void btrfs_unpin_free_ino(struct btrfs_root *root)
+{
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct rb_root *rbroot = &root->free_ino_pinned->free_space_offset;
+	struct btrfs_free_space *info;
+	struct rb_node *n;
+	u64 count;
+
+	while (1) {
+		n = rb_first(rbroot);
+		if (!n)
+			break;
+
+		info = rb_entry(n, struct btrfs_free_space, offset_index);
+		BUG_ON(info->bitmap);
+
+		if (info->offset > root->cache_progress)
+			goto free;
+		else if (info->offset + info->bytes > root->cache_progress)
+			count = root->cache_progress - info->offset + 1;
+		else
+			count = info->bytes;
+
+		__btrfs_add_free_space(ctl, info->offset, count);
+free:
+		rb_erase(&info->offset_index, rbroot);
+		kfree(info);
+	}
+}
+
+#define INIT_THRESHOLD	(((1024 * 32) / 2) / sizeof(struct btrfs_free_space))
+#define INODES_PER_BITMAP (PAGE_CACHE_SIZE * 8)
+
+/*
+ * The goal is to keep the memory used by the free_ino tree won't
+ * exceed the memory if we use bitmaps only.
+ */
+static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
+{
+	struct btrfs_free_space *info;
+	struct rb_node *n;
+	int max_ino;
+	int max_bitmaps;
+
+	n = rb_last(&ctl->free_space_offset);
+	if (!n) {
+		ctl->extents_thresh = INIT_THRESHOLD;
+		return;
+	}
+	info = rb_entry(n, struct btrfs_free_space, offset_index);
+
+	/*
+	 * Find the maximum inode number in the filesystem. Note we
+	 * ignore the fact that this can be a bitmap, because we are
+	 * not doing precise calculation.
+	 */
+	max_ino = info->bytes - 1;
+
+	max_bitmaps = ALIGN(max_ino, INODES_PER_BITMAP) / INODES_PER_BITMAP;
+	if (max_bitmaps <= ctl->total_bitmaps) {
+		ctl->extents_thresh = 0;
+		return;
+	}
+
+	ctl->extents_thresh = (max_bitmaps - ctl->total_bitmaps) *
+				PAGE_CACHE_SIZE / sizeof(*info);
+}
+
+/*
+ * We don't fall back to bitmap, if we are below the extents threshold
+ * or this chunk of inode numbers is a big one.
+ */
+static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
+		       struct btrfs_free_space *info)
+{
+	if (ctl->free_extents < ctl->extents_thresh ||
+	    info->bytes > INODES_PER_BITMAP / 10)
+		return false;
+
+	return true;
+}
+
+static struct btrfs_free_space_op free_ino_op = {
+	.recalc_thresholds	= recalculate_thresholds,
+	.use_bitmap		= use_bitmap,
+};
+
+static void pinned_recalc_thresholds(struct btrfs_free_space_ctl *ctl)
+{
+}
+
+static bool pinned_use_bitmap(struct btrfs_free_space_ctl *ctl,
+			      struct btrfs_free_space *info)
+{
+	/*
+	 * We always use extents for two reasons:
+	 *
+	 * - The pinned tree is only used during the process of caching
+	 *   work.
+	 * - Make code simpler. See btrfs_unpin_free_ino().
+	 */
+	return false;
+}
+
+static struct btrfs_free_space_op pinned_free_ino_op = {
+	.recalc_thresholds	= pinned_recalc_thresholds,
+	.use_bitmap		= pinned_use_bitmap,
+};
+
+void btrfs_init_free_ino_ctl(struct btrfs_root *root)
+{
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct btrfs_free_space_ctl *pinned = root->free_ino_pinned;
+
+	spin_lock_init(&ctl->tree_lock);
+	ctl->unit = 1;
+	ctl->start = 0;
+	ctl->private = NULL;
+	ctl->op = &free_ino_op;
+
+	/*
+	 * Initially we allow to use 16K of ram to cache chunks of
+	 * inode numbers before we resort to bitmaps. This is somewhat
+	 * arbitrary, but it will be adjusted in runtime.
+	 */
+	ctl->extents_thresh = INIT_THRESHOLD;
+
+	spin_lock_init(&pinned->tree_lock);
+	pinned->unit = 1;
+	pinned->start = 0;
+	pinned->private = NULL;
+	pinned->extents_thresh = 0;
+	pinned->op = &pinned_free_ino_op;
+}
+
+int btrfs_save_ino_cache(struct btrfs_root *root,
+			 struct btrfs_trans_handle *trans)
+{
+	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+	struct btrfs_path *path;
+	struct inode *inode;
+	u64 alloc_hint = 0;
+	int ret;
+	int prealloc;
+	bool retry = false;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+again:
+	inode = lookup_free_ino_inode(root, path);
+	if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
+		ret = PTR_ERR(inode);
+		goto out;
+	}
+
+	if (IS_ERR(inode)) {
+		BUG_ON(retry);
+		retry = true;
+
+		ret = create_free_ino_inode(root, trans, path);
+		if (ret)
+			goto out;
+		goto again;
+	}
+
+	BTRFS_I(inode)->generation = 0;
+	ret = btrfs_update_inode(trans, root, inode);
+	WARN_ON(ret);
+
+	if (i_size_read(inode) > 0) {
+		ret = btrfs_truncate_free_space_cache(root, trans, path, inode);
+		if (ret)
+			goto out_put;
+	}
+
+	spin_lock(&root->cache_lock);
+	if (root->cached != BTRFS_CACHE_FINISHED) {
+		ret = -1;
+		spin_unlock(&root->cache_lock);
+		goto out_put;
+	}
+	spin_unlock(&root->cache_lock);
+
+	spin_lock(&ctl->tree_lock);
+	prealloc = sizeof(struct btrfs_free_space) * ctl->free_extents;
+	prealloc = ALIGN(prealloc, PAGE_CACHE_SIZE);
+	prealloc += ctl->total_bitmaps * PAGE_CACHE_SIZE;
+	spin_unlock(&ctl->tree_lock);
+
+	/* Just to make sure we have enough space */
+	prealloc += 8 * PAGE_CACHE_SIZE;
+
+	ret = btrfs_check_data_free_space(inode, prealloc);
+	if (ret)
+		goto out_put;
+
+	ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
+					      prealloc, prealloc, &alloc_hint);
+	if (ret)
+		goto out_put;
+	btrfs_free_reserved_data_space(inode, prealloc);
+
+out_put:
+	iput(inode);
+out:
+	if (ret == 0)
+		ret = btrfs_write_out_ino_cache(root, trans, path);
+
+	btrfs_free_path(path);
+	return ret;
+}
+
+static int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
 {
 	struct btrfs_path *path;
 	int ret;
@@ -55,15 +474,14 @@ int btrfs_find_highest_inode(struct btrfs_root *root, u64 *objectid)
 	return ret;
 }
 
-int btrfs_find_free_objectid(struct btrfs_trans_handle *trans,
-			     struct btrfs_root *root,
-			     u64 dirid, u64 *objectid)
+int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid)
 {
 	int ret;
 	mutex_lock(&root->objectid_mutex);
 
 	if (unlikely(root->highest_objectid < BTRFS_FIRST_FREE_OBJECTID)) {
-		ret = btrfs_find_highest_inode(root, &root->highest_objectid);
+		ret = btrfs_find_highest_objectid(root,
+						  &root->highest_objectid);
 		if (ret)
 			goto out;
 	}

fs/btrfs/inode-map.h

+#ifndef __BTRFS_INODE_MAP
+#define __BTRFS_INODE_MAP
+
+void btrfs_init_free_ino_ctl(struct btrfs_root *root);
+void btrfs_unpin_free_ino(struct btrfs_root *root);
+void btrfs_return_ino(struct btrfs_root *root, u64 objectid);
+int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid);
+int btrfs_save_ino_cache(struct btrfs_root *root,
+			 struct btrfs_trans_handle *trans);
+
+int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
+
+#endif

fs/btrfs/ioctl.c

@@ -50,6 +50,7 @@
 #include "print-tree.h"
 #include "volumes.h"
 #include "locking.h"
+#include "inode-map.h"
 
 /* Mask out flags that are inappropriate for the given type of inode. */
 static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags)
@@ -329,8 +330,7 @@ static noinline int create_subvol(struct btrfs_root *root,
 	u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
 	u64 index = 0;
 
-	ret = btrfs_find_free_objectid(NULL, root->fs_info->tree_root,
-				       0, &objectid);
+	ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid);
 	if (ret) {
 		dput(parent);
 		return ret;
@@ -422,7 +422,7 @@ static noinline int create_subvol(struct btrfs_root *root,
 	BUG_ON(ret);
 
 	ret = btrfs_insert_dir_item(trans, root,
-				    name, namelen, dir->i_ino, &key,
+				    name, namelen, btrfs_ino(dir), &key,
 				    BTRFS_FT_DIR, index);
 	if (ret)
 		goto fail;
@@ -433,7 +433,7 @@ static noinline int create_subvol(struct btrfs_root *root,
 
 	ret = btrfs_add_root_ref(trans, root->fs_info->tree_root,
 				 objectid, root->root_key.objectid,
-				 dir->i_ino, index, name, namelen);
+				 btrfs_ino(dir), index, name, namelen);
 
 	BUG_ON(ret);
 
@@ -1129,7 +1129,7 @@ static noinline int btrfs_ioctl_subvol_getflags(struct file *file,
 	int ret = 0;
 	u64 flags = 0;
 
-	if (inode->i_ino != BTRFS_FIRST_FREE_OBJECTID)
+	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID)
 		return -EINVAL;
 
 	down_read(&root->fs_info->subvol_sem);
@@ -1156,7 +1156,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
 	if (root->fs_info->sb->s_flags & MS_RDONLY)
 		return -EROFS;
 
-	if (inode->i_ino != BTRFS_FIRST_FREE_OBJECTID)
+	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID)
 		return -EINVAL;
 
 	if (copy_from_user(&flags, arg, sizeof(flags)))
@@ -1639,7 +1639,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 			goto out_dput;
 	}
 
-	if (inode->i_ino != BTRFS_FIRST_FREE_OBJECTID) {
+	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
 		err = -EINVAL;
 		goto out_dput;
 	}
@@ -1925,7 +1925,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	}
 
 	/* clone data */
-	key.objectid = src->i_ino;
+	key.objectid = btrfs_ino(src);
 	key.type = BTRFS_EXTENT_DATA_KEY;
 	key.offset = 0;
 
@@ -1952,7 +1952,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 
 		btrfs_item_key_to_cpu(leaf, &key, slot);
 		if (btrfs_key_type(&key) > BTRFS_EXTENT_DATA_KEY ||
-		    key.objectid != src->i_ino)
+		    key.objectid != btrfs_ino(src))
 			break;
 
 		if (btrfs_key_type(&key) == BTRFS_EXTENT_DATA_KEY) {
@@ -1995,7 +1995,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 				goto next;
 
 			memcpy(&new_key, &key, sizeof(new_key));
-			new_key.objectid = inode->i_ino;
+			new_key.objectid = btrfs_ino(inode);
 			if (off <= key.offset)
 				new_key.offset = key.offset + destoff - off;
 			else
@@ -2049,7 +2049,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 					ret = btrfs_inc_extent_ref(trans, root,
 							disko, diskl, 0,
 							root->root_key.objectid,
-							inode->i_ino,
+							btrfs_ino(inode),
 							new_key.offset - datao);
 					BUG_ON(ret);
 				}

fs/btrfs/relocation.c

@@ -30,6 +30,7 @@
 #include "btrfs_inode.h"
 #include "async-thread.h"
 #include "free-space-cache.h"
+#include "inode-map.h"
 
 /*
  * backref_node, mapping_node and tree_block start with this
@@ -1409,9 +1410,9 @@ static struct inode *find_next_inode(struct btrfs_root *root, u64 objectid)
 		prev = node;
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
 
-		if (objectid < entry->vfs_inode.i_ino)
+		if (objectid < btrfs_ino(&entry->vfs_inode))
 			node = node->rb_left;
-		else if (objectid > entry->vfs_inode.i_ino)
+		else if (objectid > btrfs_ino(&entry->vfs_inode))
 			node = node->rb_right;
 		else
 			break;
@@ -1419,7 +1420,7 @@ static struct inode *find_next_inode(struct btrfs_root *root, u64 objectid)
 	if (!node) {
 		while (prev) {
 			entry = rb_entry(prev, struct btrfs_inode, rb_node);
-			if (objectid <= entry->vfs_inode.i_ino) {
+			if (objectid <= btrfs_ino(&entry->vfs_inode)) {
 				node = prev;
 				break;
 			}
@@ -1434,7 +1435,7 @@ static struct inode *find_next_inode(struct btrfs_root *root, u64 objectid)
 			return inode;
 		}
 
-		objectid = entry->vfs_inode.i_ino + 1;
+		objectid = btrfs_ino(&entry->vfs_inode) + 1;
 		if (cond_resched_lock(&root->inode_lock))
 			goto again;
 
@@ -1470,7 +1471,7 @@ static int get_new_location(struct inode *reloc_inode, u64 *new_bytenr,
 		return -ENOMEM;
 
 	bytenr -= BTRFS_I(reloc_inode)->index_cnt;
-	ret = btrfs_lookup_file_extent(NULL, root, path, reloc_inode->i_ino,
+	ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(reloc_inode),
 				       bytenr, 0);
 	if (ret < 0)
 		goto out;
@@ -1558,11 +1559,11 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 			if (first) {
 				inode = find_next_inode(root, key.objectid);
 				first = 0;
-			} else if (inode && inode->i_ino < key.objectid) {
+			} else if (inode && btrfs_ino(inode) < key.objectid) {
 				btrfs_add_delayed_iput(inode);
 				inode = find_next_inode(root, key.objectid);
 			}
-			if (inode && inode->i_ino == key.objectid) {
+			if (inode && btrfs_ino(inode) == key.objectid) {
 				end = key.offset +
 				      btrfs_file_extent_num_bytes(leaf, fi);
 				WARN_ON(!IS_ALIGNED(key.offset,
@@ -1893,6 +1894,7 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 	struct inode *inode = NULL;
 	u64 objectid;
 	u64 start, end;
+	u64 ino;
 
 	objectid = min_key->objectid;
 	while (1) {
@@ -1905,17 +1907,18 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 		inode = find_next_inode(root, objectid);
 		if (!inode)
 			break;
+		ino = btrfs_ino(inode);
 
-		if (inode->i_ino > max_key->objectid) {
+		if (ino > max_key->objectid) {
 			iput(inode);
 			break;
 		}
 
-		objectid = inode->i_ino + 1;
+		objectid = ino + 1;
 		if (!S_ISREG(inode->i_mode))
 			continue;
 
-		if (unlikely(min_key->objectid == inode->i_ino)) {
+		if (unlikely(min_key->objectid == ino)) {
 			if (min_key->type > BTRFS_EXTENT_DATA_KEY)
 				continue;
 			if (min_key->type < BTRFS_EXTENT_DATA_KEY)
@@ -1928,7 +1931,7 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 			start = 0;
 		}
 
-		if (unlikely(max_key->objectid == inode->i_ino)) {
+		if (unlikely(max_key->objectid == ino)) {
 			if (max_key->type < BTRFS_EXTENT_DATA_KEY)
 				continue;
 			if (max_key->type > BTRFS_EXTENT_DATA_KEY) {
@@ -3897,7 +3900,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
 	if (IS_ERR(trans))
 		return ERR_CAST(trans);
 
-	err = btrfs_find_free_objectid(trans, root, objectid, &objectid);
+	err = btrfs_find_free_objectid(root, &objectid);
 	if (err)
 		goto out;
 

fs/btrfs/transaction.c

@@ -27,6 +27,7 @@
 #include "transaction.h"
 #include "locking.h"
 #include "tree-log.h"
+#include "inode-map.h"
 
 #define BTRFS_ROOT_TRANS_TAG 0
 
@@ -760,8 +761,14 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
 			btrfs_update_reloc_root(trans, root);
 			btrfs_orphan_commit_root(trans, root);
 
+			btrfs_save_ino_cache(root, trans);
+
 			if (root->commit_root != root->node) {
+				mutex_lock(&root->fs_commit_mutex);
 				switch_commit_root(root);
+				btrfs_unpin_free_ino(root);
+				mutex_unlock(&root->fs_commit_mutex);
+
 				btrfs_set_root_node(&root->root_item,
 						    root->node);
 			}
@@ -930,7 +937,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	ret = btrfs_find_free_objectid(trans, tree_root, 0, &objectid);
+	ret = btrfs_find_free_objectid(tree_root, &objectid);
 	if (ret) {
 		pending->error = ret;
 		goto fail;
@@ -967,7 +974,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	BUG_ON(ret);
 	ret = btrfs_insert_dir_item(trans, parent_root,
 				dentry->d_name.name, dentry->d_name.len,
-				parent_inode->i_ino, &key,
+				btrfs_ino(parent_inode), &key,
 				BTRFS_FT_DIR, index);
 	BUG_ON(ret);
 
@@ -1009,7 +1016,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	 */
 	ret = btrfs_add_root_ref(trans, tree_root, objectid,
 				 parent_root->root_key.objectid,
-				 parent_inode->i_ino, index,
+				 btrfs_ino(parent_inode), index,
 				 dentry->d_name.name, dentry->d_name.len);
 	BUG_ON(ret);
 	dput(parent);

fs/btrfs/tree-log.c

@@ -519,7 +519,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	 * file.  This must be done before the btrfs_drop_extents run
 	 * so we don't try to drop this extent.
 	 */
-	ret = btrfs_lookup_file_extent(trans, root, path, inode->i_ino,
+	ret = btrfs_lookup_file_extent(trans, root, path, btrfs_ino(inode),
 				       start, 0);
 
 	if (ret == 0 &&
@@ -832,7 +832,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 	read_extent_buffer(eb, name, (unsigned long)(ref + 1), namelen);
 
 	/* if we already have a perfect match, we're done */
-	if (inode_in_dir(root, path, dir->i_ino, inode->i_ino,
+	if (inode_in_dir(root, path, btrfs_ino(dir), btrfs_ino(inode),
 			 btrfs_inode_ref_index(eb, ref),
 			 name, namelen)) {
 		goto out;
@@ -960,8 +960,9 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 	unsigned long ptr;
 	unsigned long ptr_end;
 	int name_len;
+	u64 ino = btrfs_ino(inode);
 
-	key.objectid = inode->i_ino;
+	key.objectid = ino;
 	key.type = BTRFS_INODE_REF_KEY;
 	key.offset = (u64)-1;
 
@@ -980,7 +981,7 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &key,
 				      path->slots[0]);
-		if (key.objectid != inode->i_ino ||
+		if (key.objectid != ino ||
 		    key.type != BTRFS_INODE_REF_KEY)
 			break;
 		ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
@@ -1011,10 +1012,10 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 	if (inode->i_nlink == 0) {
 		if (S_ISDIR(inode->i_mode)) {
 			ret = replay_dir_deletes(trans, root, NULL, path,
-						 inode->i_ino, 1);
+						 ino, 1);
 			BUG_ON(ret);
 		}
-		ret = insert_orphan_item(trans, root, inode->i_ino);
+		ret = insert_orphan_item(trans, root, ino);
 		BUG_ON(ret);
 	}
 	btrfs_free_path(path);
@@ -2197,6 +2198,7 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 	int ret;
 	int err = 0;
 	int bytes_del = 0;
+	u64 dir_ino = btrfs_ino(dir);
 
 	if (BTRFS_I(dir)->logged_trans < trans->transid)
 		return 0;
@@ -2214,7 +2216,7 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 		goto out_unlock;
 	}
 
-	di = btrfs_lookup_dir_item(trans, log, path, dir->i_ino,
+	di = btrfs_lookup_dir_item(trans, log, path, dir_ino,
 				   name, name_len, -1);
 	if (IS_ERR(di)) {
 		err = PTR_ERR(di);
@@ -2226,7 +2228,7 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 		BUG_ON(ret);
 	}
 	btrfs_release_path(log, path);
-	di = btrfs_lookup_dir_index_item(trans, log, path, dir->i_ino,
+	di = btrfs_lookup_dir_index_item(trans, log, path, dir_ino,
 					 index, name, name_len, -1);
 	if (IS_ERR(di)) {
 		err = PTR_ERR(di);
@@ -2244,7 +2246,7 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 	if (bytes_del) {
 		struct btrfs_key key;
 
-		key.objectid = dir->i_ino;
+		key.objectid = dir_ino;
 		key.offset = 0;
 		key.type = BTRFS_INODE_ITEM_KEY;
 		btrfs_release_path(log, path);
@@ -2303,7 +2305,7 @@ int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
 	log = root->log_root;
 	mutex_lock(&BTRFS_I(inode)->log_mutex);
 
-	ret = btrfs_del_inode_ref(trans, log, name, name_len, inode->i_ino,
+	ret = btrfs_del_inode_ref(trans, log, name, name_len, btrfs_ino(inode),
 				  dirid, &index);
 	mutex_unlock(&BTRFS_I(inode)->log_mutex);
 	if (ret == -ENOSPC) {
@@ -2369,13 +2371,14 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 	int nritems;
 	u64 first_offset = min_offset;
 	u64 last_offset = (u64)-1;
+	u64 ino = btrfs_ino(inode);
 
 	log = root->log_root;
-	max_key.objectid = inode->i_ino;
+	max_key.objectid = ino;
 	max_key.offset = (u64)-1;
 	max_key.type = key_type;
 
-	min_key.objectid = inode->i_ino;
+	min_key.objectid = ino;
 	min_key.type = key_type;
 	min_key.offset = min_offset;
 
@@ -2388,9 +2391,8 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 	 * we didn't find anything from this transaction, see if there
 	 * is anything at all
 	 */
-	if (ret != 0 || min_key.objectid != inode->i_ino ||
-	    min_key.type != key_type) {
-		min_key.objectid = inode->i_ino;
+	if (ret != 0 || min_key.objectid != ino || min_key.type != key_type) {
+		min_key.objectid = ino;
 		min_key.type = key_type;
 		min_key.offset = (u64)-1;
 		btrfs_release_path(root, path);
@@ -2399,7 +2401,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 			btrfs_release_path(root, path);
 			return ret;
 		}
-		ret = btrfs_previous_item(root, path, inode->i_ino, key_type);
+		ret = btrfs_previous_item(root, path, ino, key_type);
 
 		/* if ret == 0 there are items for this type,
 		 * create a range to tell us the last key of this type.
@@ -2417,7 +2419,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 	}
 
 	/* go backward to find any previous key */
-	ret = btrfs_previous_item(root, path, inode->i_ino, key_type);
+	ret = btrfs_previous_item(root, path, ino, key_type);
 	if (ret == 0) {
 		struct btrfs_key tmp;
 		btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]);
@@ -2452,8 +2454,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 		for (i = path->slots[0]; i < nritems; i++) {
 			btrfs_item_key_to_cpu(src, &min_key, i);
 
-			if (min_key.objectid != inode->i_ino ||
-			    min_key.type != key_type)
+			if (min_key.objectid != ino || min_key.type != key_type)
 				goto done;
 			ret = overwrite_item(trans, log, dst_path, src, i,
 					     &min_key);
@@ -2474,7 +2475,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 			goto done;
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]);
-		if (tmp.objectid != inode->i_ino || tmp.type != key_type) {
+		if (tmp.objectid != ino || tmp.type != key_type) {
 			last_offset = (u64)-1;
 			goto done;
 		}
@@ -2500,8 +2501,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 		 * is valid
 		 */
 		ret = insert_dir_log_key(trans, log, path, key_type,
-					 inode->i_ino, first_offset,
-					 last_offset);
+					 ino, first_offset, last_offset);
 		if (ret)
 			err = ret;
 	}
@@ -2745,6 +2745,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	int nritems;
 	int ins_start_slot = 0;
 	int ins_nr;
+	u64 ino = btrfs_ino(inode);
 
 	log = root->log_root;
 
@@ -2757,11 +2758,11 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 	}
 
-	min_key.objectid = inode->i_ino;
+	min_key.objectid = ino;
 	min_key.type = BTRFS_INODE_ITEM_KEY;
 	min_key.offset = 0;
 
-	max_key.objectid = inode->i_ino;
+	max_key.objectid = ino;
 
 	/* today the code can only do partial logging of directories */
 	if (!S_ISDIR(inode->i_mode))
@@ -2784,8 +2785,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 
 		if (inode_only == LOG_INODE_EXISTS)
 			max_key_type = BTRFS_XATTR_ITEM_KEY;
-		ret = drop_objectid_items(trans, log, path,
-					  inode->i_ino, max_key_type);
+		ret = drop_objectid_items(trans, log, path, ino, max_key_type);
 	} else {
 		ret = btrfs_truncate_inode_items(trans, log, inode, 0, 0);
 	}
@@ -2803,7 +2803,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			break;
 again:
 		/* note, ins_nr might be > 0 here, cleanup outside the loop */
-		if (min_key.objectid != inode->i_ino)
+		if (min_key.objectid != ino)
 			break;
 		if (min_key.type > max_key.type)
 			break;

fs/btrfs/xattr.c

@@ -44,7 +44,7 @@ ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
 		return -ENOMEM;
 
 	/* lookup the xattr by name */
-	di = btrfs_lookup_xattr(NULL, root, path, inode->i_ino, name,
+	di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), name,
 				strlen(name), 0);
 	if (!di) {
 		ret = -ENODATA;
@@ -103,7 +103,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 
 	/* first lets see if we already have this xattr */
-	di = btrfs_lookup_xattr(trans, root, path, inode->i_ino, name,
+	di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), name,
 				strlen(name), -1);
 	if (IS_ERR(di)) {
 		ret = PTR_ERR(di);
@@ -136,7 +136,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 	}
 
 	/* ok we have to create a completely new xattr */
-	ret = btrfs_insert_xattr_item(trans, root, path, inode->i_ino,
+	ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode),
 				      name, name_len, value, size);
 	BUG_ON(ret);
 out:
@@ -190,7 +190,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 	 * NOTE: we set key.offset = 0; because we want to start with the
 	 * first xattr that we find and walk forward
 	 */
-	key.objectid = inode->i_ino;
+	key.objectid = btrfs_ino(inode);
 	btrfs_set_key_type(&key, BTRFS_XATTR_ITEM_KEY);
 	key.offset = 0;