Merge branch 'restriper' of git://github.com/idryomov/btrfs-unstable into integration

1 files changed, 751 insertions, 39 deletions

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ac00e3aa80a1..9489a2aca47b 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -23,6 +23,7 @@
 #include <linux/random.h>
 #include <linux/iocontext.h>
 #include <linux/capability.h>
+#include <linux/kthread.h>
 #include <asm/div64.h>
 #include "compat.h"
 #include "ctree.h"
@@ -1282,7 +1283,6 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	bool clear_super = false;
 
 	mutex_lock(&uuid_mutex);
-	mutex_lock(&root->fs_info->volume_mutex);
 
 	all_avail = root->fs_info->avail_data_alloc_bits |
 		root->fs_info->avail_system_alloc_bits |
@@ -1452,7 +1452,6 @@ error_close:
 	if (bdev)
 		blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
 out:
-	mutex_unlock(&root->fs_info->volume_mutex);
 	mutex_unlock(&uuid_mutex);
 	return ret;
 error_undo:
@@ -1629,7 +1628,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	}
 
 	filemap_write_and_wait(bdev->bd_inode->i_mapping);
-	mutex_lock(&root->fs_info->volume_mutex);
 
 	devices = &root->fs_info->fs_devices->devices;
 	/*
@@ -1757,8 +1755,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 		ret = btrfs_relocate_sys_chunks(root);
 		BUG_ON(ret);
 	}
-out:
-	mutex_unlock(&root->fs_info->volume_mutex);
+
 	return ret;
 error:
 	blkdev_put(bdev, FMODE_EXCL);
@@ -1766,7 +1763,7 @@ error:
 		mutex_unlock(&uuid_mutex);
 		up_write(&sb->s_umount);
 	}
-	goto out;
+	return ret;
 }
 
 static noinline int btrfs_update_device(struct btrfs_trans_handle *trans,
@@ -2077,6 +2074,362 @@ error:
 	return ret;
 }
 
+static int insert_balance_item(struct btrfs_root *root,
+			       struct btrfs_balance_control *bctl)
+{
+	struct btrfs_trans_handle *trans;
+	struct btrfs_balance_item *item;
+	struct btrfs_disk_balance_args disk_bargs;
+	struct btrfs_path *path;
+	struct extent_buffer *leaf;
+	struct btrfs_key key;
+	int ret, err;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	trans = btrfs_start_transaction(root, 0);
+	if (IS_ERR(trans)) {
+		btrfs_free_path(path);
+		return PTR_ERR(trans);
+	}
+
+	key.objectid = BTRFS_BALANCE_OBJECTID;
+	key.type = BTRFS_BALANCE_ITEM_KEY;
+	key.offset = 0;
+
+	ret = btrfs_insert_empty_item(trans, root, path, &key,
+				      sizeof(*item));
+	if (ret)
+		goto out;
+
+	leaf = path->nodes[0];
+	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item);
+
+	memset_extent_buffer(leaf, 0, (unsigned long)item, sizeof(*item));
+
+	btrfs_cpu_balance_args_to_disk(&disk_bargs, &bctl->data);
+	btrfs_set_balance_data(leaf, item, &disk_bargs);
+	btrfs_cpu_balance_args_to_disk(&disk_bargs, &bctl->meta);
+	btrfs_set_balance_meta(leaf, item, &disk_bargs);
+	btrfs_cpu_balance_args_to_disk(&disk_bargs, &bctl->sys);
+	btrfs_set_balance_sys(leaf, item, &disk_bargs);
+
+	btrfs_set_balance_flags(leaf, item, bctl->flags);
+
+	btrfs_mark_buffer_dirty(leaf);
+out:
+	btrfs_free_path(path);
+	err = btrfs_commit_transaction(trans, root);
+	if (err && !ret)
+		ret = err;
+	return ret;
+}
+
+static int del_balance_item(struct btrfs_root *root)
+{
+	struct btrfs_trans_handle *trans;
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	int ret, err;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	trans = btrfs_start_transaction(root, 0);
+	if (IS_ERR(trans)) {
+		btrfs_free_path(path);
+		return PTR_ERR(trans);
+	}
+
+	key.objectid = BTRFS_BALANCE_OBJECTID;
+	key.type = BTRFS_BALANCE_ITEM_KEY;
+	key.offset = 0;
+
+	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+	if (ret < 0)
+		goto out;
+	if (ret > 0) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	ret = btrfs_del_item(trans, root, path);
+out:
+	btrfs_free_path(path);
+	err = btrfs_commit_transaction(trans, root);
+	if (err && !ret)
+		ret = err;
+	return ret;
+}
+
+/*
+ * This is a heuristic used to reduce the number of chunks balanced on
+ * resume after balance was interrupted.
+ */
+static void update_balance_args(struct btrfs_balance_control *bctl)
+{
+	/*
+	 * Turn on soft mode for chunk types that were being converted.
+	 */
+	if (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT)
+		bctl->data.flags |= BTRFS_BALANCE_ARGS_SOFT;
+	if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT)
+		bctl->sys.flags |= BTRFS_BALANCE_ARGS_SOFT;
+	if (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT)
+		bctl->meta.flags |= BTRFS_BALANCE_ARGS_SOFT;
+
+	/*
+	 * Turn on usage filter if is not already used.  The idea is
+	 * that chunks that we have already balanced should be
+	 * reasonably full.  Don't do it for chunks that are being
+	 * converted - that will keep us from relocating unconverted
+	 * (albeit full) chunks.
+	 */
+	if (!(bctl->data.flags & BTRFS_BALANCE_ARGS_USAGE) &&
+	    !(bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT)) {
+		bctl->data.flags |= BTRFS_BALANCE_ARGS_USAGE;
+		bctl->data.usage = 90;
+	}
+	if (!(bctl->sys.flags & BTRFS_BALANCE_ARGS_USAGE) &&
+	    !(bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT)) {
+		bctl->sys.flags |= BTRFS_BALANCE_ARGS_USAGE;
+		bctl->sys.usage = 90;
+	}
+	if (!(bctl->meta.flags & BTRFS_BALANCE_ARGS_USAGE) &&
+	    !(bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT)) {
+		bctl->meta.flags |= BTRFS_BALANCE_ARGS_USAGE;
+		bctl->meta.usage = 90;
+	}
+}
+
+/*
+ * Should be called with both balance and volume mutexes held to
+ * serialize other volume operations (add_dev/rm_dev/resize) with
+ * restriper.  Same goes for unset_balance_control.
+ */
+static void set_balance_control(struct btrfs_balance_control *bctl)
+{
+	struct btrfs_fs_info *fs_info = bctl->fs_info;
+
+	BUG_ON(fs_info->balance_ctl);
+
+	spin_lock(&fs_info->balance_lock);
+	fs_info->balance_ctl = bctl;
+	spin_unlock(&fs_info->balance_lock);
+}
+
+static void unset_balance_control(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+
+	BUG_ON(!fs_info->balance_ctl);
+
+	spin_lock(&fs_info->balance_lock);
+	fs_info->balance_ctl = NULL;
+	spin_unlock(&fs_info->balance_lock);
+
+	kfree(bctl);
+}
+
+/*
+ * Balance filters.  Return 1 if chunk should be filtered out
+ * (should not be balanced).
+ */
+static int chunk_profiles_filter(u64 chunk_profile,
+				 struct btrfs_balance_args *bargs)
+{
+	chunk_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK;
+
+	if (chunk_profile == 0)
+		chunk_profile = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+
+	if (bargs->profiles & chunk_profile)
+		return 0;
+
+	return 1;
+}
+
+static u64 div_factor_fine(u64 num, int factor)
+{
+	if (factor <= 0)
+		return 0;
+	if (factor >= 100)
+		return num;
+
+	num *= factor;
+	do_div(num, 100);
+	return num;
+}
+
+static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
+			      struct btrfs_balance_args *bargs)
+{
+	struct btrfs_block_group_cache *cache;
+	u64 chunk_used, user_thresh;
+	int ret = 1;
+
+	cache = btrfs_lookup_block_group(fs_info, chunk_offset);
+	chunk_used = btrfs_block_group_used(&cache->item);
+
+	user_thresh = div_factor_fine(cache->key.offset, bargs->usage);
+	if (chunk_used < user_thresh)
+		ret = 0;
+
+	btrfs_put_block_group(cache);
+	return ret;
+}
+
+static int chunk_devid_filter(struct extent_buffer *leaf,
+			      struct btrfs_chunk *chunk,
+			      struct btrfs_balance_args *bargs)
+{
+	struct btrfs_stripe *stripe;
+	int num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+	int i;
+
+	for (i = 0; i < num_stripes; i++) {
+		stripe = btrfs_stripe_nr(chunk, i);
+		if (btrfs_stripe_devid(leaf, stripe) == bargs->devid)
+			return 0;
+	}
+
+	return 1;
+}
+
+/* [pstart, pend) */
+static int chunk_drange_filter(struct extent_buffer *leaf,
+			       struct btrfs_chunk *chunk,
+			       u64 chunk_offset,
+			       struct btrfs_balance_args *bargs)
+{
+	struct btrfs_stripe *stripe;
+	int num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+	u64 stripe_offset;
+	u64 stripe_length;
+	int factor;
+	int i;
+
+	if (!(bargs->flags & BTRFS_BALANCE_ARGS_DEVID))
+		return 0;
+
+	if (btrfs_chunk_type(leaf, chunk) & (BTRFS_BLOCK_GROUP_DUP |
+	     BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10))
+		factor = 2;
+	else
+		factor = 1;
+	factor = num_stripes / factor;
+
+	for (i = 0; i < num_stripes; i++) {
+		stripe = btrfs_stripe_nr(chunk, i);
+		if (btrfs_stripe_devid(leaf, stripe) != bargs->devid)
+			continue;
+
+		stripe_offset = btrfs_stripe_offset(leaf, stripe);
+		stripe_length = btrfs_chunk_length(leaf, chunk);
+		do_div(stripe_length, factor);
+
+		if (stripe_offset < bargs->pend &&
+		    stripe_offset + stripe_length > bargs->pstart)
+			return 0;
+	}
+
+	return 1;
+}
+
+/* [vstart, vend) */
+static int chunk_vrange_filter(struct extent_buffer *leaf,
+			       struct btrfs_chunk *chunk,
+			       u64 chunk_offset,
+			       struct btrfs_balance_args *bargs)
+{
+	if (chunk_offset < bargs->vend &&
+	    chunk_offset + btrfs_chunk_length(leaf, chunk) > bargs->vstart)
+		/* at least part of the chunk is inside this vrange */
+		return 0;
+
+	return 1;
+}
+
+static int chunk_soft_convert_filter(u64 chunk_profile,
+				     struct btrfs_balance_args *bargs)
+{
+	if (!(bargs->flags & BTRFS_BALANCE_ARGS_CONVERT))
+		return 0;
+
+	chunk_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK;
+
+	if (chunk_profile == 0)
+		chunk_profile = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+
+	if (bargs->target & chunk_profile)
+		return 1;
+
+	return 0;
+}
+
+static int should_balance_chunk(struct btrfs_root *root,
+				struct extent_buffer *leaf,
+				struct btrfs_chunk *chunk, u64 chunk_offset)
+{
+	struct btrfs_balance_control *bctl = root->fs_info->balance_ctl;
+	struct btrfs_balance_args *bargs = NULL;
+	u64 chunk_type = btrfs_chunk_type(leaf, chunk);
+
+	/* type filter */
+	if (!((chunk_type & BTRFS_BLOCK_GROUP_TYPE_MASK) &
+	      (bctl->flags & BTRFS_BALANCE_TYPE_MASK))) {
+		return 0;
+	}
+
+	if (chunk_type & BTRFS_BLOCK_GROUP_DATA)
+		bargs = &bctl->data;
+	else if (chunk_type & BTRFS_BLOCK_GROUP_SYSTEM)
+		bargs = &bctl->sys;
+	else if (chunk_type & BTRFS_BLOCK_GROUP_METADATA)
+		bargs = &bctl->meta;
+
+	/* profiles filter */
+	if ((bargs->flags & BTRFS_BALANCE_ARGS_PROFILES) &&
+	    chunk_profiles_filter(chunk_type, bargs)) {
+		return 0;
+	}
+
+	/* usage filter */
+	if ((bargs->flags & BTRFS_BALANCE_ARGS_USAGE) &&
+	    chunk_usage_filter(bctl->fs_info, chunk_offset, bargs)) {
+		return 0;
+	}
+
+	/* devid filter */
+	if ((bargs->flags & BTRFS_BALANCE_ARGS_DEVID) &&
+	    chunk_devid_filter(leaf, chunk, bargs)) {
+		return 0;
+	}
+
+	/* drange filter, makes sense only with devid filter */
+	if ((bargs->flags & BTRFS_BALANCE_ARGS_DRANGE) &&
+	    chunk_drange_filter(leaf, chunk, chunk_offset, bargs)) {
+		return 0;
+	}
+
+	/* vrange filter */
+	if ((bargs->flags & BTRFS_BALANCE_ARGS_VRANGE) &&
+	    chunk_vrange_filter(leaf, chunk, chunk_offset, bargs)) {
+		return 0;
+	}
+
+	/* soft profile changing mode */
+	if ((bargs->flags & BTRFS_BALANCE_ARGS_SOFT) &&
+	    chunk_soft_convert_filter(chunk_type, bargs)) {
+		return 0;
+	}
+
+	return 1;
+}
+
 static u64 div_factor(u64 num, int factor)
 {
 	if (factor == 10)
@@ -2086,29 +2439,28 @@ static u64 div_factor(u64 num, int factor)
 	return num;
 }
 
-int btrfs_balance(struct btrfs_root *dev_root)
+static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 {
-	int ret;
-	struct list_head *devices = &dev_root->fs_info->fs_devices->devices;
+	struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+	struct btrfs_root *chunk_root = fs_info->chunk_root;
+	struct btrfs_root *dev_root = fs_info->dev_root;
+	struct list_head *devices;
 	struct btrfs_device *device;
 	u64 old_size;
 	u64 size_to_free;
+	struct btrfs_chunk *chunk;
 	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;
-
-	if (dev_root->fs_info->sb->s_flags & MS_RDONLY)
-		return -EROFS;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	mutex_lock(&dev_root->fs_info->volume_mutex);
-	dev_root = dev_root->fs_info->dev_root;
+	struct btrfs_trans_handle *trans;
+	struct extent_buffer *leaf;
+	int slot;
+	int ret;
+	int enospc_errors = 0;
+	bool counting = true;
 
 	/* step one make some room on all the devices */
+	devices = &fs_info->fs_devices->devices;
 	list_for_each_entry(device, devices, dev_list) {
 		old_size = device->total_bytes;
 		size_to_free = div_factor(old_size, 1);
@@ -2137,11 +2489,23 @@ int btrfs_balance(struct btrfs_root *dev_root)
 		ret = -ENOMEM;
 		goto error;
 	}
+
+	/* zero out stat counters */
+	spin_lock(&fs_info->balance_lock);
+	memset(&bctl->stat, 0, sizeof(bctl->stat));
+	spin_unlock(&fs_info->balance_lock);
+again:
 	key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
 	key.offset = (u64)-1;
 	key.type = BTRFS_CHUNK_ITEM_KEY;
 
 	while (1) {
+		if ((!counting && atomic_read(&fs_info->balance_pause_req)) ||
+		    atomic_read(&fs_info->balance_cancel_req)) {
+			ret = -ECANCELED;
+			goto error;
+		}
+
 		ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
 		if (ret < 0)
 			goto error;
@@ -2151,15 +2515,19 @@ int btrfs_balance(struct btrfs_root *dev_root)
 		 * failed
 		 */
 		if (ret == 0)
-			break;
+			BUG(); /* FIXME break ? */
 
 		ret = btrfs_previous_item(chunk_root, path, 0,
 					  BTRFS_CHUNK_ITEM_KEY);
-		if (ret)
+		if (ret) {
+			ret = 0;
 			break;
+		}
+
+		leaf = path->nodes[0];
+		slot = path->slots[0];
+		btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
-		btrfs_item_key_to_cpu(path->nodes[0], &found_key,
-				      path->slots[0]);
 		if (found_key.objectid != key.objectid)
 			break;
 
@@ -2167,22 +2535,375 @@ int btrfs_balance(struct btrfs_root *dev_root)
 		if (found_key.offset == 0)
 			break;
 
+		chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
+
+		if (!counting) {
+			spin_lock(&fs_info->balance_lock);
+			bctl->stat.considered++;
+			spin_unlock(&fs_info->balance_lock);
+		}
+
+		ret = should_balance_chunk(chunk_root, leaf, chunk,
+					   found_key.offset);
 		btrfs_release_path(path);
+		if (!ret)
+			goto loop;
+
+		if (counting) {
+			spin_lock(&fs_info->balance_lock);
+			bctl->stat.expected++;
+			spin_unlock(&fs_info->balance_lock);
+			goto loop;
+		}
+
 		ret = btrfs_relocate_chunk(chunk_root,
 					   chunk_root->root_key.objectid,
 					   found_key.objectid,
 					   found_key.offset);
 		if (ret && ret != -ENOSPC)
 			goto error;
+		if (ret == -ENOSPC) {
+			enospc_errors++;
+		} else {
+			spin_lock(&fs_info->balance_lock);
+			bctl->stat.completed++;
+			spin_unlock(&fs_info->balance_lock);
+		}
+loop:
 		key.offset = found_key.offset - 1;
 	}
-	ret = 0;
+
+	if (counting) {
+		btrfs_release_path(path);
+		counting = false;
+		goto again;
+	}
 error:
 	btrfs_free_path(path);
-	mutex_unlock(&dev_root->fs_info->volume_mutex);
+	if (enospc_errors) {
+		printk(KERN_INFO "btrfs: %d enospc errors during balance\n",
+		       enospc_errors);
+		if (!ret)
+			ret = -ENOSPC;
+	}
+
 	return ret;
 }
 
+static inline int balance_need_close(struct btrfs_fs_info *fs_info)
+{
+	/* cancel requested || normal exit path */
+	return atomic_read(&fs_info->balance_cancel_req) ||
+		(atomic_read(&fs_info->balance_pause_req) == 0 &&
+		 atomic_read(&fs_info->balance_cancel_req) == 0);
+}
+
+static void __cancel_balance(struct btrfs_fs_info *fs_info)
+{
+	int ret;
+
+	unset_balance_control(fs_info);
+	ret = del_balance_item(fs_info->tree_root);
+	BUG_ON(ret);
+}
+
+void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+			       struct btrfs_ioctl_balance_args *bargs);
+
+/*
+ * Should be called with both balance and volume mutexes held
+ */
+int btrfs_balance(struct btrfs_balance_control *bctl,
+		  struct btrfs_ioctl_balance_args *bargs)
+{
+	struct btrfs_fs_info *fs_info = bctl->fs_info;
+	u64 allowed;
+	int ret;
+
+	if (btrfs_fs_closing(fs_info) ||
+	    atomic_read(&fs_info->balance_pause_req) ||
+	    atomic_read(&fs_info->balance_cancel_req)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * In case of mixed groups both data and meta should be picked,
+	 * and identical options should be given for both of them.
+	 */
+	allowed = btrfs_super_incompat_flags(fs_info->super_copy);
+	if ((allowed & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
+	    (bctl->flags & (BTRFS_BALANCE_DATA | BTRFS_BALANCE_METADATA))) {
+		if (!(bctl->flags & BTRFS_BALANCE_DATA) ||
+		    !(bctl->flags & BTRFS_BALANCE_METADATA) ||
+		    memcmp(&bctl->data, &bctl->meta, sizeof(bctl->data))) {
+			printk(KERN_ERR "btrfs: with mixed groups data and "
+			       "metadata balance options must be the same\n");
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	/*
+	 * Profile changing sanity checks.  Skip them if a simple
+	 * balance is requested.
+	 */
+	if (!((bctl->data.flags | bctl->sys.flags | bctl->meta.flags) &
+	      BTRFS_BALANCE_ARGS_CONVERT))
+		goto do_balance;
+
+	allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+	if (fs_info->fs_devices->num_devices == 1)
+		allowed |= BTRFS_BLOCK_GROUP_DUP;
+	else if (fs_info->fs_devices->num_devices < 4)
+		allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1);
+	else
+		allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 |
+				BTRFS_BLOCK_GROUP_RAID10);
+
+	if (!profile_is_valid(bctl->data.target, 1) ||
+	    bctl->data.target & ~allowed) {
+		printk(KERN_ERR "btrfs: unable to start balance with target "
+		       "data profile %llu\n",
+		       (unsigned long long)bctl->data.target);
+		ret = -EINVAL;
+		goto out;
+	}
+	if (!profile_is_valid(bctl->meta.target, 1) ||
+	    bctl->meta.target & ~allowed) {
+		printk(KERN_ERR "btrfs: unable to start balance with target "
+		       "metadata profile %llu\n",
+		       (unsigned long long)bctl->meta.target);
+		ret = -EINVAL;
+		goto out;
+	}
+	if (!profile_is_valid(bctl->sys.target, 1) ||
+	    bctl->sys.target & ~allowed) {
+		printk(KERN_ERR "btrfs: unable to start balance with target "
+		       "system profile %llu\n",
+		       (unsigned long long)bctl->sys.target);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (bctl->data.target & BTRFS_BLOCK_GROUP_DUP) {
+		printk(KERN_ERR "btrfs: dup for data is not allowed\n");
+		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;
+	if (((bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+	     (fs_info->avail_system_alloc_bits & allowed) &&
+	     !(bctl->sys.target & allowed)) ||
+	    ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+	     (fs_info->avail_metadata_alloc_bits & allowed) &&
+	     !(bctl->meta.target & allowed))) {
+		if (bctl->flags & BTRFS_BALANCE_FORCE) {
+			printk(KERN_INFO "btrfs: force reducing metadata "
+			       "integrity\n");
+		} else {
+			printk(KERN_ERR "btrfs: balance will reduce metadata "
+			       "integrity, use force if you want this\n");
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+do_balance:
+	ret = insert_balance_item(fs_info->tree_root, bctl);
+	if (ret && ret != -EEXIST)
+		goto out;
+
+	if (!(bctl->flags & BTRFS_BALANCE_RESUME)) {
+		BUG_ON(ret == -EEXIST);
+		set_balance_control(bctl);
+	} else {
+		BUG_ON(ret != -EEXIST);
+		spin_lock(&fs_info->balance_lock);
+		update_balance_args(bctl);
+		spin_unlock(&fs_info->balance_lock);
+	}
+
+	atomic_inc(&fs_info->balance_running);
+	mutex_unlock(&fs_info->balance_mutex);
+
+	ret = __btrfs_balance(fs_info);
+
+	mutex_lock(&fs_info->balance_mutex);
+	atomic_dec(&fs_info->balance_running);
+
+	if (bargs) {
+		memset(bargs, 0, sizeof(*bargs));
+		update_ioctl_balance_args(fs_info, 0, bargs);
+	}
+
+	if ((ret && ret != -ECANCELED && ret != -ENOSPC) ||
+	    balance_need_close(fs_info)) {
+		__cancel_balance(fs_info);
+	}
+
+	wake_up(&fs_info->balance_wait_q);
+
+	return ret;
+out:
+	if (bctl->flags & BTRFS_BALANCE_RESUME)
+		__cancel_balance(fs_info);
+	else
+		kfree(bctl);
+	return ret;
+}
+
+static int balance_kthread(void *data)
+{
+	struct btrfs_balance_control *bctl =
+			(struct btrfs_balance_control *)data;
+	struct btrfs_fs_info *fs_info = bctl->fs_info;
+	int ret = 0;
+
+	mutex_lock(&fs_info->volume_mutex);
+	mutex_lock(&fs_info->balance_mutex);
+
+	set_balance_control(bctl);
+
+	if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) {
+		printk(KERN_INFO "btrfs: force skipping balance\n");
+	} else {
+		printk(KERN_INFO "btrfs: continuing balance\n");
+		ret = btrfs_balance(bctl, NULL);
+	}
+
+	mutex_unlock(&fs_info->balance_mutex);
+	mutex_unlock(&fs_info->volume_mutex);
+	return ret;
+}
+
+int btrfs_recover_balance(struct btrfs_root *tree_root)
+{
+	struct task_struct *tsk;
+	struct btrfs_balance_control *bctl;
+	struct btrfs_balance_item *item;
+	struct btrfs_disk_balance_args disk_bargs;
+	struct btrfs_path *path;
+	struct extent_buffer *leaf;
+	struct btrfs_key key;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	bctl = kzalloc(sizeof(*bctl), GFP_NOFS);
+	if (!bctl) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	key.objectid = BTRFS_BALANCE_OBJECTID;
+	key.type = BTRFS_BALANCE_ITEM_KEY;
+	key.offset = 0;
+
+	ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out_bctl;
+	if (ret > 0) { /* ret = -ENOENT; */
+		ret = 0;
+		goto out_bctl;
+	}
+
+	leaf = path->nodes[0];
+	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item);
+
+	bctl->fs_info = tree_root->fs_info;
+	bctl->flags = btrfs_balance_flags(leaf, item) | BTRFS_BALANCE_RESUME;
+
+	btrfs_balance_data(leaf, item, &disk_bargs);
+	btrfs_disk_balance_args_to_cpu(&bctl->data, &disk_bargs);
+	btrfs_balance_meta(leaf, item, &disk_bargs);
+	btrfs_disk_balance_args_to_cpu(&bctl->meta, &disk_bargs);
+	btrfs_balance_sys(leaf, item, &disk_bargs);
+	btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs);
+
+	tsk = kthread_run(balance_kthread, bctl, "btrfs-balance");
+	if (IS_ERR(tsk))
+		ret = PTR_ERR(tsk);
+	else
+		goto out;
+
+out_bctl:
+	kfree(bctl);
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
+int btrfs_pause_balance(struct btrfs_fs_info *fs_info)
+{
+	int ret = 0;
+
+	mutex_lock(&fs_info->balance_mutex);
+	if (!fs_info->balance_ctl) {
+		mutex_unlock(&fs_info->balance_mutex);
+		return -ENOTCONN;
+	}
+
+	if (atomic_read(&fs_info->balance_running)) {
+		atomic_inc(&fs_info->balance_pause_req);
+		mutex_unlock(&fs_info->balance_mutex);
+
+		wait_event(fs_info->balance_wait_q,
+			   atomic_read(&fs_info->balance_running) == 0);
+
+		mutex_lock(&fs_info->balance_mutex);
+		/* we are good with balance_ctl ripped off from under us */
+		BUG_ON(atomic_read(&fs_info->balance_running));
+		atomic_dec(&fs_info->balance_pause_req);
+	} else {
+		ret = -ENOTCONN;
+	}
+
+	mutex_unlock(&fs_info->balance_mutex);
+	return ret;
+}
+
+int btrfs_cancel_balance(struct btrfs_fs_info *fs_info)
+{
+	mutex_lock(&fs_info->balance_mutex);
+	if (!fs_info->balance_ctl) {
+		mutex_unlock(&fs_info->balance_mutex);
+		return -ENOTCONN;
+	}
+
+	atomic_inc(&fs_info->balance_cancel_req);
+	/*
+	 * if we are running just wait and return, balance item is
+	 * deleted in btrfs_balance in this case
+	 */
+	if (atomic_read(&fs_info->balance_running)) {
+		mutex_unlock(&fs_info->balance_mutex);
+		wait_event(fs_info->balance_wait_q,
+			   atomic_read(&fs_info->balance_running) == 0);
+		mutex_lock(&fs_info->balance_mutex);
+	} else {
+		/* __cancel_balance needs volume_mutex */
+		mutex_unlock(&fs_info->balance_mutex);
+		mutex_lock(&fs_info->volume_mutex);
+		mutex_lock(&fs_info->balance_mutex);
+
+		if (fs_info->balance_ctl)
+			__cancel_balance(fs_info);
+
+		mutex_unlock(&fs_info->volume_mutex);
+	}
+
+	BUG_ON(fs_info->balance_ctl || atomic_read(&fs_info->balance_running));
+	atomic_dec(&fs_info->balance_cancel_req);
+	mutex_unlock(&fs_info->balance_mutex);
+	return 0;
+}
+
 /*
  * shrinking a device means finding all of the device extents past
  * the new size, and then following the back refs to the chunks.
@@ -2756,8 +3477,7 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans,
 		return ret;
 
 	alloc_profile = BTRFS_BLOCK_GROUP_METADATA |
-			(fs_info->metadata_alloc_profile &
-			 fs_info->avail_metadata_alloc_bits);
+				fs_info->avail_metadata_alloc_bits;
 	alloc_profile = btrfs_reduce_alloc_profile(root, alloc_profile);
 
 	ret = __btrfs_alloc_chunk(trans, extent_root, &map, &chunk_size,
@@ -2767,8 +3487,7 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans,
 	sys_chunk_offset = chunk_offset + chunk_size;
 
 	alloc_profile = BTRFS_BLOCK_GROUP_SYSTEM |
-			(fs_info->system_alloc_profile &
-			 fs_info->avail_system_alloc_bits);
+				fs_info->avail_system_alloc_bits;
 	alloc_profile = btrfs_reduce_alloc_profile(root, alloc_profile);
 
 	ret = __btrfs_alloc_chunk(trans, extent_root, &sys_map,
@@ -2955,12 +3674,8 @@ again:
 		}
 	}
 	if (rw & REQ_DISCARD) {
-		if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
-				 BTRFS_BLOCK_GROUP_RAID1 |
-				 BTRFS_BLOCK_GROUP_DUP |
-				 BTRFS_BLOCK_GROUP_RAID10)) {
+		if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK)
 			stripes_required = map->num_stripes;
-		}
 	}
 	if (bbio_ret && (rw & (REQ_WRITE | REQ_DISCARD)) &&
 	    stripes_allocated < stripes_required) {
@@ -2984,10 +3699,7 @@ again:
 
 	if (rw & REQ_DISCARD)
 		*length = min_t(u64, em->len - offset, *length);
-	else if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
-			      BTRFS_BLOCK_GROUP_RAID1 |
-			      BTRFS_BLOCK_GROUP_RAID10 |
-			      BTRFS_BLOCK_GROUP_DUP)) {
+	else if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
 		/* we limit the length of each bio to what fits in a stripe */
 		*length = min_t(u64, em->len - offset,
 				map->stripe_len - stripe_offset);