[PATCH v8 0/8] Balance management patches, v8

@@ -873,6 +873,11 @@ struct btrfs_block_group_cache {
 	struct list_head cluster_list;
 };
 
+struct btrfs_balance_info {
+	u32 expected;
+	u32 completed;
+};
+
 struct reloc_control;
 struct btrfs_device;
 struct btrfs_fs_devices;

@@ -1115,6 +1120,10 @@ struct btrfs_fs_info {
 	u64 fs_state;
 
 	struct btrfs_delayed_root *delayed_root;
+
+	/* Keep track of any rebalance operations on this FS */
+	spinlock_t balance_info_lock;
+	struct btrfs_balance_info *balance_info;
 };
 
 /*

@@ -1619,6 +1619,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
 	spin_lock_init(&fs_info->delayed_iput_lock);
 	spin_lock_init(&fs_info->defrag_inodes_lock);
+	spin_lock_init(&fs_info->balance_info_lock);
 	mutex_init(&fs_info->reloc_mutex);
 
 	init_completion(&fs_info->kobj_unregister);

@@ -1648,6 +1649,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	fs_info->metadata_ratio = 0;
 	fs_info->defrag_inodes = RB_ROOT;
 	fs_info->trans_no_join = 0;
+	fs_info->balance_info = NULL;
 
 	fs_info->thread_pool_size = min_t(unsigned long,
 					  num_online_cpus() + 2, 8);

@@ -2836,6 +2836,38 @@ static long btrfs_ioctl_scrub_progress(struct btrfs_root *root,
 	return ret;
 }
 
+/*
+ * Return the current status of any balance operation
+ */
+long btrfs_ioctl_balance_progress(
+	struct btrfs_fs_info *fs_info,
+	struct btrfs_ioctl_balance_progress __user *user_dest)
+{
+	int ret = 0;
+	struct btrfs_ioctl_balance_progress dest;
+
+	spin_lock(&fs_info->balance_info_lock);
+	if (!fs_info->balance_info) {
+		ret = -EINVAL;
+		goto error;
+	}
+
+	dest.expected = fs_info->balance_info->expected;
+	dest.completed = fs_info->balance_info->completed;
+
+	spin_unlock(&fs_info->balance_info_lock);
+
+	if (copy_to_user(user_dest, &dest,
+			 sizeof(struct btrfs_ioctl_balance_progress)))
+		return -EFAULT;
+
+	return 0;
+
+error:
+	spin_unlock(&fs_info->balance_info_lock);
+	return ret;
+}
+
 long btrfs_ioctl(struct file *file, unsigned int
 		cmd, unsigned long arg)
 {

@@ -2881,6 +2913,8 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_dev_info(root, argp);
 	case BTRFS_IOC_BALANCE:
 		return btrfs_balance(root->fs_info->dev_root);
+	case BTRFS_IOC_BALANCE_PROGRESS:
+		return btrfs_ioctl_balance_progress(root->fs_info, argp);
 	case BTRFS_IOC_CLONE:
 		return btrfs_ioctl_clone(file, arg, 0, 0, 0);
 	case BTRFS_IOC_CLONE_RANGE:

@@ -193,6 +193,11 @@ struct btrfs_ioctl_space_args {
 	struct btrfs_ioctl_space_info spaces[0];
 };
 
+struct btrfs_ioctl_balance_progress {
+	__u32 expected;
+	__u32 completed;
+};
+
 #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
 				   struct btrfs_ioctl_vol_args)
 #define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \

@@ -248,4 +253,6 @@ struct btrfs_ioctl_space_args {
 				 struct btrfs_ioctl_dev_info_args)
 #define BTRFS_IOC_FS_INFO _IOR(BTRFS_IOCTL_MAGIC, 31, \
 			       struct btrfs_ioctl_fs_info_args)
+#define BTRFS_IOC_BALANCE_PROGRESS _IOR(BTRFS_IOCTL_MAGIC, 32, \
+				  struct btrfs_ioctl_balance_progress)
 #endif

@@ -2026,6 +2026,7 @@ int btrfs_balance(struct btrfs_root *dev_root)
 	struct btrfs_root *chunk_root = dev_root->fs_info->chunk_root;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_key found_key;
+	struct btrfs_balance_info *bal_info;
 
 	if (dev_root->fs_info->sb->s_flags & MS_RDONLY)
 		return -EROFS;

@@ -2036,6 +2037,20 @@ int btrfs_balance(struct btrfs_root *dev_root)
 	mutex_lock(&dev_root->fs_info->volume_mutex);
 	dev_root = dev_root->fs_info->dev_root;
 
+	bal_info = kmalloc(
+		sizeof(struct btrfs_balance_info),
+		GFP_NOFS);
+	if (!bal_info) {
+		ret = -ENOMEM;
+		goto error_no_status;
+	}
+	spin_lock(&dev_root->fs_info->balance_info_lock);
+	dev_root->fs_info->balance_info = bal_info;
+	bal_info->expected = -1; /* One less than actually counted,
+				    because chunk 0 is special */
+	bal_info->completed = 0;
+	spin_unlock(&dev_root->fs_info->balance_info_lock);
+
 	/* step one make some room on all the devices */
 	list_for_each_entry(device, devices, dev_list) {
 		old_size = device->total_bytes;

@@ -2059,10 +2074,37 @@ int btrfs_balance(struct btrfs_root *dev_root)
 		btrfs_end_transaction(trans, dev_root);
 	}
 
-	/* step two, relocate all the chunks */
+	/* step two, count the chunks */
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
+	key.offset = (u64)-1;
+	key.type = BTRFS_CHUNK_ITEM_KEY;
+
+	ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
+	if (ret <= 0) {
+		printk(KERN_ERR "btrfs: Failed to find the last chunk.\n");
+		BUG();
+	}
+
+	while (1) {
+		ret = btrfs_previous_item(chunk_root, path, 0,
+					  BTRFS_CHUNK_ITEM_KEY);
+		if (ret)
+			break;
+
+		spin_lock(&dev_root->fs_info->balance_info_lock);
+		bal_info->expected++;
+		spin_unlock(&dev_root->fs_info->balance_info_lock);
+	}
+
+	btrfs_release_path(path);
 
+	/* step three, relocate all the chunks */
 	key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
 	key.offset = (u64)-1;
 	key.type = BTRFS_CHUNK_ITEM_KEY;

@@ -2100,10 +2142,20 @@ int btrfs_balance(struct btrfs_root *dev_root)
 					   found_key.offset);
 		BUG_ON(ret && ret != -ENOSPC);
 		key.offset = found_key.offset - 1;
+		spin_lock(&dev_root->fs_info->balance_info_lock);
+		bal_info->completed++;
+		spin_unlock(&dev_root->fs_info->balance_info_lock);
+		printk(KERN_INFO "btrfs: balance: %u/%u block groups completed\n",
+		       bal_info->completed, bal_info->expected);
 	}
 	ret = 0;
 error:
 	btrfs_free_path(path);
+	spin_lock(&dev_root->fs_info->balance_info_lock);
+	kfree(dev_root->fs_info->balance_info);
+	dev_root->fs_info->balance_info = NULL;
+	spin_unlock(&dev_root->fs_info->balance_info_lock);
+error_no_status:
 	mutex_unlock(&dev_root->fs_info->volume_mutex);
 	return ret;
 }

@@ -876,6 +876,7 @@ struct btrfs_block_group_cache {
 struct btrfs_balance_info {
 	u32 expected;
 	u32 completed;
+	int cancel_pending;
 };
 
 struct reloc_control;

@@ -2868,6 +2868,32 @@ error:
 	return ret;
 }
 
+/*
+ * Cancel a running balance operation
+ */
+long btrfs_ioctl_balance_cancel(struct btrfs_fs_info *fs_info)
+{
+	int err = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	spin_lock(&fs_info->balance_info_lock);
+	if (!fs_info->balance_info) {
+		err = -EINVAL;
+		goto error;
+	}
+	if (fs_info->balance_info->cancel_pending) {
+		err = -ECANCELED;
+		goto error;
+	}
+	fs_info->balance_info->cancel_pending = 1;
+
+error:
+	spin_unlock(&fs_info->balance_info_lock);
+	return err;
+}
+
 long btrfs_ioctl(struct file *file, unsigned int
 		cmd, unsigned long arg)
 {

@@ -2915,6 +2941,8 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_balance(root->fs_info->dev_root);
 	case BTRFS_IOC_BALANCE_PROGRESS:
 		return btrfs_ioctl_balance_progress(root->fs_info, argp);
+	case BTRFS_IOC_BALANCE_CANCEL:
+		return btrfs_ioctl_balance_cancel(root->fs_info);
 	case BTRFS_IOC_CLONE:
 		return btrfs_ioctl_clone(file, arg, 0, 0, 0);
 	case BTRFS_IOC_CLONE_RANGE:

@@ -255,4 +255,5 @@ struct btrfs_ioctl_balance_progress {
 			       struct btrfs_ioctl_fs_info_args)
 #define BTRFS_IOC_BALANCE_PROGRESS _IOR(BTRFS_IOCTL_MAGIC, 32, \
 				  struct btrfs_ioctl_balance_progress)
+#define BTRFS_IOC_BALANCE_CANCEL _IO(BTRFS_IOCTL_MAGIC, 33)
 #endif

@@ -2049,6 +2049,7 @@ int btrfs_balance(struct btrfs_root *dev_root)
 	bal_info->expected = -1; /* One less than actually counted,
 				    because chunk 0 is special */
 	bal_info->completed = 0;
+	bal_info->cancel_pending = 0;
 	spin_unlock(&dev_root->fs_info->balance_info_lock);
 
 	/* step one make some room on all the devices */

@@ -2109,7 +2110,7 @@ int btrfs_balance(struct btrfs_root *dev_root)
 	key.offset = (u64)-1;
 	key.type = BTRFS_CHUNK_ITEM_KEY;
 
-	while (1) {
+	while (!bal_info->cancel_pending) {
 		ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
 		if (ret < 0)
 			goto error;

@@ -2149,6 +2150,10 @@ int btrfs_balance(struct btrfs_root *dev_root)
 		       bal_info->completed, bal_info->expected);
 	}
 	ret = 0;
+	if (bal_info->cancel_pending) {
+		printk(KERN_INFO "btrfs: balance cancelled\n");
+		ret = -EINTR;
+	}
 error:
 	btrfs_free_path(path);
 	spin_lock(&dev_root->fs_info->balance_info_lock);

@@ -2014,6 +2014,97 @@ static u64 div_factor(u64 num, int factor)
 	return num;
 }
 
+/* Define a type, and two functions which can be used for the two
+ * phases of the balance operation: one for counting chunks, and one
+ * for actually moving them. */
+typedef void (*balance_iterator_function)(struct btrfs_root *,
+					  struct btrfs_balance_info *,
+					  struct btrfs_path *,
+					  struct btrfs_key *);
+
+static void balance_count_chunks(struct btrfs_root *chunk_root,
+			  struct btrfs_balance_info *bal_info,
+			  struct btrfs_path *path,
+			  struct btrfs_key *key)
+{
+	spin_lock(&chunk_root->fs_info->balance_info_lock);
+	bal_info->expected++;
+	spin_unlock(&chunk_root->fs_info->balance_info_lock);
+}
+
+static void balance_move_chunks(struct btrfs_root *chunk_root,
+			 struct btrfs_balance_info *bal_info,
+			 struct btrfs_path *path,
+			 struct btrfs_key *key)
+{
+	int ret;
+
+	ret = btrfs_relocate_chunk(chunk_root,
+				   chunk_root->root_key.objectid,
+				   key->objectid,
+				   key->offset);
+	BUG_ON(ret && ret != -ENOSPC);
+	spin_lock(&chunk_root->fs_info->balance_info_lock);
+	bal_info->completed++;
+	spin_unlock(&chunk_root->fs_info->balance_info_lock);
+	printk(KERN_INFO "btrfs: balance: %u/%u block groups completed\n",
+	       bal_info->completed, bal_info->expected);
+}
+
+/* Iterate through all chunks, performing some function on each one. */
+static int balance_iterate_chunks(struct btrfs_root *chunk_root,
+			   struct btrfs_balance_info *bal_info,
+			   balance_iterator_function iterator_fn)
+{
+	int ret = 0;
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct btrfs_key found_key;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
+	key.offset = (u64)-1;
+	key.type = BTRFS_CHUNK_ITEM_KEY;
+
+	while (!bal_info->cancel_pending) {
+		ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
+		if (ret < 0)
+			break;
+		/*
+		 * this shouldn't happen, it means the last relocate
+		 * failed
+		 */
+		if (ret == 0)
+			break;
+
+		ret = btrfs_previous_item(chunk_root, path, 0,
+					  BTRFS_CHUNK_ITEM_KEY);
+		if (ret)
+			break;
+
+		btrfs_item_key_to_cpu(path->nodes[0], &found_key,
+				      path->slots[0]);
+		if (found_key.objectid != key.objectid)
+			break;
+
+		/* chunk zero is special */
+		if (found_key.offset == 0)
+			break;
+
+		/* Call the function to do the work for this chunk */
+		btrfs_release_path(path);
+		iterator_fn(chunk_root, bal_info, path, &found_key);
+
+		key.offset = found_key.offset - 1;
+	}
+
+	btrfs_free_path(path);
+	return ret;
+}
+
 int btrfs_balance(struct btrfs_root *dev_root)
 {
 	int ret;

@@ -2021,11 +2112,8 @@ int btrfs_balance(struct btrfs_root *dev_root)
 	struct btrfs_device *device;
 	u64 old_size;
 	u64 size_to_free;
-	struct btrfs_path *path;
-	struct btrfs_key key;
 	struct btrfs_root *chunk_root = dev_root->fs_info->chunk_root;
 	struct btrfs_trans_handle *trans;
-	struct btrfs_key found_key;
 	struct btrfs_balance_info *bal_info;
 
 	if (dev_root->fs_info->sb->s_flags & MS_RDONLY)

@@ -2046,8 +2134,7 @@ int btrfs_balance(struct btrfs_root *dev_root)
 	}
 	spin_lock(&dev_root->fs_info->balance_info_lock);
 	dev_root->fs_info->balance_info = bal_info;
-	bal_info->expected = -1; /* One less than actually counted,
-				    because chunk 0 is special */
+	bal_info->expected = 0;
 	bal_info->completed = 0;
 	bal_info->cancel_pending = 0;
 	spin_unlock(&dev_root->fs_info->balance_info_lock);

@@ -2076,86 +2163,23 @@ int btrfs_balance(struct btrfs_root *dev_root)
 	}
 
 	/* step two, count the chunks */
-	path = btrfs_alloc_path();
-	if (!path) {
-		ret = -ENOMEM;
+	ret = balance_iterate_chunks(chunk_root, bal_info,
+				     balance_count_chunks);
+	if (ret)
 		goto error;
-	}
-
-	key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
-	key.offset = (u64)-1;
-	key.type = BTRFS_CHUNK_ITEM_KEY;
-
-	ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
-	if (ret <= 0) {
-		printk(KERN_ERR "btrfs: Failed to find the last chunk.\n");
-		BUG();
-	}
-
-	while (1) {
-		ret = btrfs_previous_item(chunk_root, path, 0,
-					  BTRFS_CHUNK_ITEM_KEY);
-		if (ret)
-			break;
-
-		spin_lock(&dev_root->fs_info->balance_info_lock);
-		bal_info->expected++;
-		spin_unlock(&dev_root->fs_info->balance_info_lock);
-	}
-
-	btrfs_release_path(path);
 
 	/* step three, relocate all the chunks */
-	key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
-	key.offset = (u64)-1;
-	key.type = BTRFS_CHUNK_ITEM_KEY;
-
-	while (!bal_info->cancel_pending) {
-		ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
-		if (ret < 0)
-			goto error;
-
-		/*
-		 * this shouldn't happen, it means the last relocate
-		 * failed
-		 */
-		if (ret == 0)
-			break;
-
-		ret = btrfs_previous_item(chunk_root, path, 0,
-					  BTRFS_CHUNK_ITEM_KEY);
-		if (ret)
-			break;
-
-		btrfs_item_key_to_cpu(path->nodes[0], &found_key,
-				      path->slots[0]);
-		if (found_key.objectid != key.objectid)
-			break;
-
-		/* chunk zero is special */
-		if (found_key.offset == 0)
-			break;
+	ret = balance_iterate_chunks(chunk_root, bal_info,
+				     balance_move_chunks);
+	if (ret)
+		goto error;
 
-		btrfs_release_path(path);
-		ret = btrfs_relocate_chunk(chunk_root,
-					   chunk_root->root_key.objectid,
-					   found_key.objectid,
-					   found_key.offset);
-		BUG_ON(ret && ret != -ENOSPC);
-		key.offset = found_key.offset - 1;
-		spin_lock(&dev_root->fs_info->balance_info_lock);
-		bal_info->completed++;
-		spin_unlock(&dev_root->fs_info->balance_info_lock);
-		printk(KERN_INFO "btrfs: balance: %u/%u block groups completed\n",
-		       bal_info->completed, bal_info->expected);
-	}
 	ret = 0;
 	if (bal_info->cancel_pending) {
 		printk(KERN_INFO "btrfs: balance cancelled\n");
 		ret = -EINTR;
 	}
 error:
-	btrfs_free_path(path);
 	spin_lock(&dev_root->fs_info->balance_info_lock);
 	kfree(dev_root->fs_info->balance_info);
 	dev_root->fs_info->balance_info = NULL;

@@ -2894,6 +2894,44 @@ error:
 	return err;
 }
 
+long btrfs_ioctl_balance(struct btrfs_root *dev_root,
+			 struct btrfs_ioctl_balance_start __user *user_filters)
+{
+	int ret = 0;
+	struct btrfs_ioctl_balance_start *dest;
+
+	dest = kmalloc(sizeof(struct btrfs_ioctl_balance_start), GFP_KERNEL);
+	if (!dest)
+		return -ENOMEM;
+
+	if (copy_from_user(dest, user_filters,
+			   sizeof(struct btrfs_ioctl_balance_start))) {
+		ret = -EFAULT;
+		goto error;
+	}
+
+	/* Basic sanity checking: has the user requested anything outside
+	 * the range we know about? */
+	if (dest->flags & ~BTRFS_BALANCE_FILTER_MASK) {
+		ret = -ENOTSUPP;
+		goto error;
+	}
+
+	/* Do the balance */
+	ret = btrfs_balance(dev_root, dest);
+	if (ret)
+		goto error;
+
+	if (copy_to_user(user_filters, dest,
+			 sizeof(struct btrfs_ioctl_balance_start))) {
+		ret = -EFAULT;
+	}
+
+error:
+	kfree(dest);
+	return ret;
+}
+
 long btrfs_ioctl(struct file *file, unsigned int
 		cmd, unsigned long arg)
 {

@@ -2938,11 +2976,13 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case BTRFS_IOC_DEV_INFO:
 		return btrfs_ioctl_dev_info(root, argp);
 	case BTRFS_IOC_BALANCE:
-		return btrfs_balance(root->fs_info->dev_root);
+		return btrfs_ioctl_balance(root->fs_info->dev_root, NULL);
 	case BTRFS_IOC_BALANCE_PROGRESS:
 		return btrfs_ioctl_balance_progress(root->fs_info, argp);
 	case BTRFS_IOC_BALANCE_CANCEL:
 		return btrfs_ioctl_balance_cancel(root->fs_info);
+	case BTRFS_IOC_BALANCE_FILTERED:
+		return btrfs_ioctl_balance(root->fs_info->dev_root, argp);
 	case BTRFS_IOC_CLONE:
 		return btrfs_ioctl_clone(file, arg, 0, 0, 0);
 	case BTRFS_IOC_CLONE_RANGE:

@@ -198,6 +198,31 @@ struct btrfs_ioctl_balance_progress {
 	__u32 completed;
 };
 
+/* Types of balance filter */
+#define BTRFS_BALANCE_FILTER_COUNT_ONLY (1 << 0)
+
+#define BTRFS_BALANCE_FILTER_CHUNK_TYPE (1 << 1)
+#define BTRFS_BALANCE_FILTER_MASK ((1 << 2) - 1) /* Logical or of all filter
+				       * flags -- effectively versions
+				       * the filtered balance ioctl */
+
+/* All the possible options for a filter */
+struct btrfs_ioctl_balance_start {
+	__u64 flags; /* Bit field indicating which fields of this struct
+			are filled */
+
+	/* Output values: chunk counts */
+	__u32 examined;
+	__u32 balanced;
+
+	/* For FILTER_CHUNK_TYPE */
+	__u64 chunk_type;      /* Flag bits required */
+	__u64 chunk_type_mask; /* Mask of bits to examine */
+
+	__u64 spare[507]; /* Make up the size of the structure to 4088
+			   * bytes for future expansion */
+};
+
 #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
 				   struct btrfs_ioctl_vol_args)
 #define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \

@@ -256,4 +281,6 @@ struct btrfs_ioctl_balance_progress {
 #define BTRFS_IOC_BALANCE_PROGRESS _IOR(BTRFS_IOCTL_MAGIC, 32, \
 				  struct btrfs_ioctl_balance_progress)
 #define BTRFS_IOC_BALANCE_CANCEL _IO(BTRFS_IOCTL_MAGIC, 33)
+#define BTRFS_IOC_BALANCE_FILTERED _IOWR(BTRFS_IOCTL_MAGIC, 34, \
+				struct btrfs_ioctl_balance_start)
 #endif

@@ -2014,6 +2014,36 @@ static u64 div_factor(u64 num, int factor)
 	return num;
 }
 
+int balance_chunk_filter(struct btrfs_ioctl_balance_start *filter,
+						 struct btrfs_root *chunk_root,
+						 struct btrfs_path *path,
+						 struct btrfs_key *key)
+{
+	struct extent_buffer *eb;
+	struct btrfs_chunk *chunk;
+
+	/* No filter defined, everything matches */
+	if (!filter)
+		return 1;
+
+	/* No flags set, everything matches */
+	if (filter->flags == 0)
+		return 1;
+
+	eb = path->nodes[0];
+	chunk = btrfs_item_ptr(eb, path->slots[0],
+						   struct btrfs_chunk);
+
+	if (filter->flags & BTRFS_BALANCE_FILTER_CHUNK_TYPE) {
+		if ((btrfs_chunk_type(eb, chunk) & filter->chunk_type_mask)
+			!= filter->chunk_type) {
+			return 0;
+		}
+	}
+
+	return 1;
+}
+
 /* Define a type, and two functions which can be used for the two
  * phases of the balance operation: one for counting chunks, and one
  * for actually moving them. */

@@ -2054,6 +2084,7 @@ static void balance_move_chunks(struct btrfs_root *chunk_root,
 /* Iterate through all chunks, performing some function on each one. */
 static int balance_iterate_chunks(struct btrfs_root *chunk_root,
 			   struct btrfs_balance_info *bal_info,
+			   struct btrfs_ioctl_balance_start *filter,
 			   balance_iterator_function iterator_fn)
 {
 	int ret = 0;

@@ -2069,6 +2100,9 @@ static int balance_iterate_chunks(struct btrfs_root *chunk_root,
 	key.offset = (u64)-1;
 	key.type = BTRFS_CHUNK_ITEM_KEY;
 
+	filter->examined = 0;
+	filter->balanced = 0;
+
 	while (!bal_info->cancel_pending) {
 		ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
 		if (ret < 0)

@@ -2095,17 +2129,29 @@ static int balance_iterate_chunks(struct btrfs_root *chunk_root,
 			break;
 
 		/* Call the function to do the work for this chunk */
-		btrfs_release_path(path);
-		iterator_fn(chunk_root, bal_info, path, &found_key);
+		filter->examined += 1;
+
+		if (balance_chunk_filter(filter, chunk_root,
+					 path, &found_key)) {
+			btrfs_release_path(path);
+			iterator_fn(chunk_root, bal_info, path, &found_key);
+			filter->balanced += 1;
+		} else {
+			btrfs_release_path(path);
+		}
 
 		key.offset = found_key.offset - 1;
 	}
 
+	printk(KERN_INFO "btrfs: balance: %u chunks considered, %u chunks balanced\n",
+		   filter->examined, filter->balanced);
+
 	btrfs_free_path(path);
 	return ret;
 }
 
-int btrfs_balance(struct btrfs_root *dev_root)
+int btrfs_balance(struct btrfs_root *dev_root,
+				  struct btrfs_ioctl_balance_start *filters)
 {
 	int ret;
 	struct list_head *devices = &dev_root->fs_info->fs_devices->devices;

@@ -2164,15 +2210,17 @@ int btrfs_balance(struct btrfs_root *dev_root)
 
 	/* step two, count the chunks */
 	ret = balance_iterate_chunks(chunk_root, bal_info,
-				     balance_count_chunks);
+				 filters, balance_count_chunks);
 	if (ret)
 		goto error;
 
 	/* step three, relocate all the chunks */
-	ret = balance_iterate_chunks(chunk_root, bal_info,
-				     balance_move_chunks);
-	if (ret)
-		goto error;
+	if (!(filters->flags & BTRFS_BALANCE_FILTER_COUNT_ONLY)) {
+		ret = balance_iterate_chunks(chunk_root, bal_info,
+					     filters, balance_move_chunks);
+		if (ret)
+			goto error;
+	}
 
 	ret = 0;
 	if (bal_info->cancel_pending) {

@@ -22,6 +22,7 @@
 #include <linux/bio.h>
 #include <linux/sort.h>
 #include "async-thread.h"
+#include "ioctl.h"
 
 #define BTRFS_STRIPE_LEN	(64 * 1024)
 

@@ -208,7 +209,10 @@ struct btrfs_device *btrfs_find_device(struct btrfs_root *root, u64 devid,
 				       u8 *uuid, u8 *fsid);
 int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
 int btrfs_init_new_device(struct btrfs_root *root, char *path);
-int btrfs_balance(struct btrfs_root *dev_root);
+int btrfs_balance(struct btrfs_root *dev_root,
+		  struct btrfs_ioctl_balance_start *filters);
+void btrfs_unlock_volumes(void);
+void btrfs_lock_volumes(void);
 int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset);
 int find_free_dev_extent(struct btrfs_trans_handle *trans,
 			 struct btrfs_device *device, u64 num_bytes,

@@ -202,7 +202,8 @@ struct btrfs_ioctl_balance_progress {
 #define BTRFS_BALANCE_FILTER_COUNT_ONLY (1 << 0)
 
 #define BTRFS_BALANCE_FILTER_CHUNK_TYPE (1 << 1)
-#define BTRFS_BALANCE_FILTER_MASK ((1 << 2) - 1) /* Logical or of all filter
+#define BTRFS_BALANCE_FILTER_DEVID (1 << 2)
+#define BTRFS_BALANCE_FILTER_MASK ((1 << 3) - 1) /* Logical or of all filter
 				       * flags -- effectively versions
 				       * the filtered balance ioctl */
 

@@ -219,7 +220,10 @@ struct btrfs_ioctl_balance_start {
 	__u64 chunk_type;      /* Flag bits required */
 	__u64 chunk_type_mask; /* Mask of bits to examine */
 
-	__u64 spare[507]; /* Make up the size of the structure to 4088
+	/* For FILTER_DEVID */
+	__u64 devid;
+
+	__u64 spare[506]; /* Make up the size of the structure to 4088
 			   * bytes for future expansion */
 };
 

@@ -2021,6 +2021,7 @@ int balance_chunk_filter(struct btrfs_ioctl_balance_start *filter,
 {
 	struct extent_buffer *eb;
 	struct btrfs_chunk *chunk;
+	int i;
 
 	/* No filter defined, everything matches */
 	if (!filter)

@@ -2040,6 +2041,19 @@ int balance_chunk_filter(struct btrfs_ioctl_balance_start *filter,
 			return 0;
 		}
 	}
+	if (filter->flags & BTRFS_BALANCE_FILTER_DEVID) {
+		int num_stripes = btrfs_chunk_num_stripes(eb, chunk);
+		int res = 0;
+		for (i = 0; i < num_stripes; i++) {
+			struct btrfs_stripe *stripe = btrfs_stripe_nr(chunk, i);
+			if (btrfs_stripe_devid(eb, stripe) == filter->devid) {
+				res = 1;
+				break;
+			}
+		}
+		if (!res)
+			return 0;
+	}
 
 	return 1;
 }

@@ -203,7 +203,8 @@ struct btrfs_ioctl_balance_progress {
 
 #define BTRFS_BALANCE_FILTER_CHUNK_TYPE (1 << 1)
 #define BTRFS_BALANCE_FILTER_DEVID (1 << 2)
-#define BTRFS_BALANCE_FILTER_MASK ((1 << 3) - 1) /* Logical or of all filter
+#define BTRFS_BALANCE_FILTER_VIRTUAL_ADDRESS_RANGE (1 << 3)
+#define BTRFS_BALANCE_FILTER_MASK ((1 << 4) - 1) /* Logical or of all filter
 				       * flags -- effectively versions
 				       * the filtered balance ioctl */
 

@@ -223,7 +224,11 @@ struct btrfs_ioctl_balance_start {
 	/* For FILTER_DEVID */
 	__u64 devid;
 
-	__u64 spare[506]; /* Make up the size of the structure to 4088
+	/* For FILTER_VIRTUAL_ADDRESS_RANGE */
+	__u64 vrange_start;
+	__u64 vrange_end;
+
+	__u64 spare[504]; /* Make up the size of the structure to 4088
 			   * bytes for future expansion */
 };
 

@@ -2054,6 +2054,12 @@ int balance_chunk_filter(struct btrfs_ioctl_balance_start *filter,
 		if (!res)
 			return 0;
 	}
+	if (filter->flags & BTRFS_BALANCE_FILTER_VIRTUAL_ADDRESS_RANGE) {
+		u64 start = key->offset;
+		u64 end = start + btrfs_chunk_length(eb, chunk);
+		if (filter->vrange_start >= end || start >= filter->vrange_end)
+			return 0;
+	}
 
 	return 1;
 }

@@ -965,12 +965,12 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 	struct btrfs_device_info *devices_info;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *device;
+	struct btrfs_replication_info repl_info;
 	u64 skip_space;
 	u64 type;
 	u64 avail_space;
 	u64 used_space;
 	u64 min_stripe_size;
-	int min_stripes = 1;
 	int i = 0, nr_devices;
 	int ret;
 

@@ -984,12 +984,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 
 	/* calc min stripe number for data space alloction */
 	type = btrfs_get_alloc_profile(root, 1);
-	if (type & BTRFS_BLOCK_GROUP_RAID0)
-		min_stripes = 2;
-	else if (type & BTRFS_BLOCK_GROUP_RAID1)
-		min_stripes = 2;
-	else if (type & BTRFS_BLOCK_GROUP_RAID10)
-		min_stripes = 4;
+	btrfs_get_replication_info(&repl_info, type);
 
 	if (type & BTRFS_BLOCK_GROUP_DUP)
 		min_stripe_size = 2 * BTRFS_STRIPE_LEN;

@@ -1057,14 +1052,15 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 
 	i = nr_devices - 1;
 	avail_space = 0;
-	while (nr_devices >= min_stripes) {
+	while (nr_devices >= repl_info.devs_min) {
 		if (devices_info[i].max_avail >= min_stripe_size) {
 			int j;
 			u64 alloc_size;
 
-			avail_space += devices_info[i].max_avail * min_stripes;
+			avail_space += devices_info[i].max_avail
+				* repl_info.devs_min;
 			alloc_size = devices_info[i].max_avail;
-			for (j = i + 1 - min_stripes; j <= i; j++)
+			for (j = i + 1 - repl_info.devs_min; j <= i; j++)
 				devices_info[j].max_avail -= alloc_size;
 		}
 		i--;

@@ -117,6 +117,52 @@ static void requeue_list(struct btrfs_pending_bios *pending_bios,
 		pending_bios->tail = tail;
 }
 
+void btrfs_get_replication_info(struct btrfs_replication_info *info,
+								u64 type)
+{
+	info->sub_stripes = 1;
+	info->dev_stripes = 1;
+	info->devs_increment = 1;
+	info->num_copies = 1;
+	info->devs_max = 0;	/* 0 == as many as possible */
+	info->devs_min = 1;
+
+	if (type & BTRFS_BLOCK_GROUP_DUP) {
+		info->dev_stripes = 2;
+		info->num_copies = 2;
+		info->devs_max = 1;
+	} else if (type & BTRFS_BLOCK_GROUP_RAID0) {
+		info->devs_min = 2;
+	} else if (type & BTRFS_BLOCK_GROUP_RAID1) {
+		info->devs_increment = 2;
+		info->num_copies = 2;
+		info->devs_max = 2;
+		info->devs_min = 2;
+	} else if (type & BTRFS_BLOCK_GROUP_RAID10) {
+		info->sub_stripes = 2;
+		info->devs_increment = 2;
+		info->num_copies = 2;
+		info->devs_min = 4;
+	}
+
+	if (type & BTRFS_BLOCK_GROUP_DATA) {
+		info->max_stripe_size = 1024 * 1024 * 1024;
+		info->min_stripe_size = 64 * 1024 * 1024;
+		info->max_chunk_size = 10 * info->max_stripe_size;
+	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
+		info->max_stripe_size = 256 * 1024 * 1024;
+		info->min_stripe_size = 32 * 1024 * 1024;
+		info->max_chunk_size = info->max_stripe_size;
+	} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
+		info->max_stripe_size = 8 * 1024 * 1024;
+		info->min_stripe_size = 1 * 1024 * 1024;
+		info->max_chunk_size = 2 * info->max_stripe_size;
+	} else {
+		printk(KERN_ERR "Block group is of an unknown usage type: not data, metadata or system.\n");
+		BUG_ON(1);
+	}
+}
+
 /*
  * we try to collect pending bios for a device so we don't get a large
  * number of procs sending bios down to the same device.  This greatly

@@ -1216,6 +1262,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	struct block_device *bdev;
 	struct buffer_head *bh = NULL;
 	struct btrfs_super_block *disk_super;
+	struct btrfs_replication_info repl_info;
 	struct btrfs_fs_devices *cur_devices;
 	u64 all_avail;
 	u64 devid;

@@ -1231,18 +1278,16 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		root->fs_info->avail_system_alloc_bits |
 		root->fs_info->avail_metadata_alloc_bits;
 
-	if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) &&
-	    root->fs_info->fs_devices->num_devices <= 4) {
-		printk(KERN_ERR "btrfs: unable to go below four devices "
-		       "on raid10\n");
-		ret = -EINVAL;
-		goto out;
-	}
+	btrfs_get_replication_info(&repl_info, all_avail);
 
-	if ((all_avail & BTRFS_BLOCK_GROUP_RAID1) &&
-	    root->fs_info->fs_devices->num_devices <= 2) {
-		printk(KERN_ERR "btrfs: unable to go below two "
-		       "devices on raid1\n");
+	if (root->fs_info->fs_devices->num_devices <= repl_info.devs_min) {
+		if (all_avail & BTRFS_BLOCK_GROUP_RAID10) {
+			printk(KERN_ERR "btrfs: unable to go below four "
+				   "devices on raid10\n");
+		} else if (all_avail & BTRFS_BLOCK_GROUP_RAID1) {
+			printk(KERN_ERR "btrfs: unable to go below two "
+				   "devices on raid1\n");
+		}
 		ret = -EINVAL;
 		goto out;
 	}

@@ -2446,16 +2491,10 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	struct extent_map_tree *em_tree;
 	struct extent_map *em;
 	struct btrfs_device_info *devices_info = NULL;
+	struct btrfs_replication_info repl_info;
 	u64 total_avail;
 	int num_stripes;	/* total number of stripes to allocate */
-	int sub_stripes;	/* sub_stripes info for map */
-	int dev_stripes;	/* stripes per dev */
-	int devs_max;		/* max devs to use */
-	int devs_min;		/* min devs needed */
-	int devs_increment;	/* ndevs has to be a multiple of this */
-	int ncopies;		/* how many copies to data has */
 	int ret;
-	u64 max_stripe_size;
 	u64 max_chunk_size;
 	u64 stripe_size;
 	u64 num_bytes;

@@ -2472,56 +2511,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	if (list_empty(&fs_devices->alloc_list))
 		return -ENOSPC;
 
-	sub_stripes = 1;
-	dev_stripes = 1;
-	devs_increment = 1;
-	ncopies = 1;
-	devs_max = 0;	/* 0 == as many as possible */
-	devs_min = 1;
-
-	/*
-	 * define the properties of each RAID type.
-	 * FIXME: move this to a global table and use it in all RAID
-	 * calculation code
-	 */
-	if (type & (BTRFS_BLOCK_GROUP_DUP)) {
-		dev_stripes = 2;
-		ncopies = 2;
-		devs_max = 1;
-	} else if (type & (BTRFS_BLOCK_GROUP_RAID0)) {
-		devs_min = 2;
-	} else if (type & (BTRFS_BLOCK_GROUP_RAID1)) {
-		devs_increment = 2;
-		ncopies = 2;
-		devs_max = 2;
-		devs_min = 2;
-	} else if (type & (BTRFS_BLOCK_GROUP_RAID10)) {
-		sub_stripes = 2;
-		devs_increment = 2;
-		ncopies = 2;
-		devs_min = 4;
-	} else {
-		devs_max = 1;
-	}
-
-	if (type & BTRFS_BLOCK_GROUP_DATA) {
-		max_stripe_size = 1024 * 1024 * 1024;
-		max_chunk_size = 10 * max_stripe_size;
-	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
-		max_stripe_size = 256 * 1024 * 1024;
-		max_chunk_size = max_stripe_size;
-	} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
-		max_stripe_size = 8 * 1024 * 1024;
-		max_chunk_size = 2 * max_stripe_size;
-	} else {
-		printk(KERN_ERR "btrfs: invalid chunk type 0x%llx requested\n",
-		       type);
-		BUG_ON(1);
-	}
+	btrfs_get_replication_info(&repl_info, type);
 
 	/* we don't want a chunk larger than 10% of writeable space */
 	max_chunk_size = min(div_factor(fs_devices->total_rw_bytes, 1),
-			     max_chunk_size);
+			     repl_info.max_chunk_size);
 
 	devices_info = kzalloc(sizeof(*devices_info) * fs_devices->rw_devices,
 			       GFP_NOFS);