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

8 files changed, 1385 insertions, 98 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 67385033323..dfc136cc07d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -86,6 +86,9 @@ struct btrfs_ordered_sum;
 /* holds checksums of all the data extents */
 #define BTRFS_CSUM_TREE_OBJECTID 7ULL
 
+/* for storing balance parameters in the root tree */
+#define BTRFS_BALANCE_OBJECTID -4ULL
+
 /* orhpan objectid for tracking unlinked/truncated files */
 #define BTRFS_ORPHAN_OBJECTID -5ULL
 
@@ -692,6 +695,54 @@ struct btrfs_root_ref {
 	__le16 name_len;
 } __attribute__ ((__packed__));
 
+struct btrfs_disk_balance_args {
+	/*
+	 * profiles to operate on, single is denoted by
+	 * BTRFS_AVAIL_ALLOC_BIT_SINGLE
+	 */
+	__le64 profiles;
+
+	/* usage filter */
+	__le64 usage;
+
+	/* devid filter */
+	__le64 devid;
+
+	/* devid subset filter [pstart..pend) */
+	__le64 pstart;
+	__le64 pend;
+
+	/* btrfs virtual address space subset filter [vstart..vend) */
+	__le64 vstart;
+	__le64 vend;
+
+	/*
+	 * profile to convert to, single is denoted by
+	 * BTRFS_AVAIL_ALLOC_BIT_SINGLE
+	 */
+	__le64 target;
+
+	/* BTRFS_BALANCE_ARGS_* */
+	__le64 flags;
+
+	__le64 unused[8];
+} __attribute__ ((__packed__));
+
+/*
+ * store balance parameters to disk so that balance can be properly
+ * resumed after crash or unmount
+ */
+struct btrfs_balance_item {
+	/* BTRFS_BALANCE_* */
+	__le64 flags;
+
+	struct btrfs_disk_balance_args data;
+	struct btrfs_disk_balance_args meta;
+	struct btrfs_disk_balance_args sys;
+
+	__le64 unused[4];
+} __attribute__ ((__packed__));
+
 #define BTRFS_FILE_EXTENT_INLINE 0
 #define BTRFS_FILE_EXTENT_REG 1
 #define BTRFS_FILE_EXTENT_PREALLOC 2
@@ -751,14 +802,32 @@ struct btrfs_csum_item {
 } __attribute__ ((__packed__));
 
 /* different types of block groups (and chunks) */
-#define BTRFS_BLOCK_GROUP_DATA     (1 << 0)
-#define BTRFS_BLOCK_GROUP_SYSTEM   (1 << 1)
-#define BTRFS_BLOCK_GROUP_METADATA (1 << 2)
-#define BTRFS_BLOCK_GROUP_RAID0    (1 << 3)
-#define BTRFS_BLOCK_GROUP_RAID1    (1 << 4)
-#define BTRFS_BLOCK_GROUP_DUP	   (1 << 5)
-#define BTRFS_BLOCK_GROUP_RAID10   (1 << 6)
-#define BTRFS_NR_RAID_TYPES	   5
+#define BTRFS_BLOCK_GROUP_DATA		(1ULL << 0)
+#define BTRFS_BLOCK_GROUP_SYSTEM	(1ULL << 1)
+#define BTRFS_BLOCK_GROUP_METADATA	(1ULL << 2)
+#define BTRFS_BLOCK_GROUP_RAID0		(1ULL << 3)
+#define BTRFS_BLOCK_GROUP_RAID1		(1ULL << 4)
+#define BTRFS_BLOCK_GROUP_DUP		(1ULL << 5)
+#define BTRFS_BLOCK_GROUP_RAID10	(1ULL << 6)
+#define BTRFS_BLOCK_GROUP_RESERVED	BTRFS_AVAIL_ALLOC_BIT_SINGLE
+#define BTRFS_NR_RAID_TYPES		5
+
+#define BTRFS_BLOCK_GROUP_TYPE_MASK	(BTRFS_BLOCK_GROUP_DATA |    \
+					 BTRFS_BLOCK_GROUP_SYSTEM |  \
+					 BTRFS_BLOCK_GROUP_METADATA)
+
+#define BTRFS_BLOCK_GROUP_PROFILE_MASK	(BTRFS_BLOCK_GROUP_RAID0 |   \
+					 BTRFS_BLOCK_GROUP_RAID1 |   \
+					 BTRFS_BLOCK_GROUP_DUP |     \
+					 BTRFS_BLOCK_GROUP_RAID10)
+/*
+ * We need a bit for restriper to be able to tell when chunks of type
+ * SINGLE are available.  This "extended" profile format is used in
+ * fs_info->avail_*_alloc_bits (in-memory) and balance item fields
+ * (on-disk).  The corresponding on-disk bit in chunk.type is reserved
+ * to avoid remappings between two formats in future.
+ */
+#define BTRFS_AVAIL_ALLOC_BIT_SINGLE	(1ULL << 48)
 
 struct btrfs_block_group_item {
 	__le64 used;
@@ -916,6 +985,7 @@ struct btrfs_block_group_cache {
 struct reloc_control;
 struct btrfs_device;
 struct btrfs_fs_devices;
+struct btrfs_balance_control;
 struct btrfs_delayed_root;
 struct btrfs_fs_info {
 	u8 fsid[BTRFS_FSID_SIZE];
@@ -1132,12 +1202,23 @@ struct btrfs_fs_info {
 	spinlock_t ref_cache_lock;
 	u64 total_ref_cache_size;
 
+	/*
+	 * these three are in extended format (availability of single
+	 * chunks is denoted by BTRFS_AVAIL_ALLOC_BIT_SINGLE bit, other
+	 * types are denoted by corresponding BTRFS_BLOCK_GROUP_* bits)
+	 */
 	u64 avail_data_alloc_bits;
 	u64 avail_metadata_alloc_bits;
 	u64 avail_system_alloc_bits;
-	u64 data_alloc_profile;
-	u64 metadata_alloc_profile;
-	u64 system_alloc_profile;
+
+	/* restriper state */
+	spinlock_t balance_lock;
+	struct mutex balance_mutex;
+	atomic_t balance_running;
+	atomic_t balance_pause_req;
+	atomic_t balance_cancel_req;
+	struct btrfs_balance_control *balance_ctl;
+	wait_queue_head_t balance_wait_q;
 
 	unsigned data_chunk_allocations;
 	unsigned metadata_ratio;
@@ -1383,6 +1464,8 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_DEV_ITEM_KEY	216
 #define BTRFS_CHUNK_ITEM_KEY	228
 
+#define BTRFS_BALANCE_ITEM_KEY	248
+
 /*
  * string items are for debugging.  They just store a short string of
  * data in the FS
@@ -1413,6 +1496,7 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_MOUNT_AUTO_DEFRAG		(1 << 16)
 #define BTRFS_MOUNT_INODE_MAP_CACHE	(1 << 17)
 #define BTRFS_MOUNT_RECOVERY		(1 << 18)
+#define BTRFS_MOUNT_SKIP_BALANCE	(1 << 19)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
@@ -2077,8 +2161,86 @@ BTRFS_SETGET_STACK_FUNCS(backup_bytes_used, struct btrfs_root_backup,
 BTRFS_SETGET_STACK_FUNCS(backup_num_devices, struct btrfs_root_backup,
 		   num_devices, 64);
 
-/* struct btrfs_super_block */
+/* struct btrfs_balance_item */
+BTRFS_SETGET_FUNCS(balance_flags, struct btrfs_balance_item, flags, 64);
+
+static inline void btrfs_balance_data(struct extent_buffer *eb,
+				      struct btrfs_balance_item *bi,
+				      struct btrfs_disk_balance_args *ba)
+{
+	read_eb_member(eb, bi, struct btrfs_balance_item, data, ba);
+}
+
+static inline void btrfs_set_balance_data(struct extent_buffer *eb,
+					  struct btrfs_balance_item *bi,
+					  struct btrfs_disk_balance_args *ba)
+{
+	write_eb_member(eb, bi, struct btrfs_balance_item, data, ba);
+}
+
+static inline void btrfs_balance_meta(struct extent_buffer *eb,
+				      struct btrfs_balance_item *bi,
+				      struct btrfs_disk_balance_args *ba)
+{
+	read_eb_member(eb, bi, struct btrfs_balance_item, meta, ba);
+}
 
+static inline void btrfs_set_balance_meta(struct extent_buffer *eb,
+					  struct btrfs_balance_item *bi,
+					  struct btrfs_disk_balance_args *ba)
+{
+	write_eb_member(eb, bi, struct btrfs_balance_item, meta, ba);
+}
+
+static inline void btrfs_balance_sys(struct extent_buffer *eb,
+				     struct btrfs_balance_item *bi,
+				     struct btrfs_disk_balance_args *ba)
+{
+	read_eb_member(eb, bi, struct btrfs_balance_item, sys, ba);
+}
+
+static inline void btrfs_set_balance_sys(struct extent_buffer *eb,
+					 struct btrfs_balance_item *bi,
+					 struct btrfs_disk_balance_args *ba)
+{
+	write_eb_member(eb, bi, struct btrfs_balance_item, sys, ba);
+}
+
+static inline void
+btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
+			       struct btrfs_disk_balance_args *disk)
+{
+	memset(cpu, 0, sizeof(*cpu));
+
+	cpu->profiles = le64_to_cpu(disk->profiles);
+	cpu->usage = le64_to_cpu(disk->usage);
+	cpu->devid = le64_to_cpu(disk->devid);
+	cpu->pstart = le64_to_cpu(disk->pstart);
+	cpu->pend = le64_to_cpu(disk->pend);
+	cpu->vstart = le64_to_cpu(disk->vstart);
+	cpu->vend = le64_to_cpu(disk->vend);
+	cpu->target = le64_to_cpu(disk->target);
+	cpu->flags = le64_to_cpu(disk->flags);
+}
+
+static inline void
+btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk,
+			       struct btrfs_balance_args *cpu)
+{
+	memset(disk, 0, sizeof(*disk));
+
+	disk->profiles = cpu_to_le64(cpu->profiles);
+	disk->usage = cpu_to_le64(cpu->usage);
+	disk->devid = cpu_to_le64(cpu->devid);
+	disk->pstart = cpu_to_le64(cpu->pstart);
+	disk->pend = cpu_to_le64(cpu->pend);
+	disk->vstart = cpu_to_le64(cpu->vstart);
+	disk->vend = cpu_to_le64(cpu->vend);
+	disk->target = cpu_to_le64(cpu->target);
+	disk->flags = cpu_to_le64(cpu->flags);
+}
+
+/* struct btrfs_super_block */
 BTRFS_SETGET_STACK_FUNCS(super_bytenr, struct btrfs_super_block, bytenr, 64);
 BTRFS_SETGET_STACK_FUNCS(super_flags, struct btrfs_super_block, flags, 64);
 BTRFS_SETGET_STACK_FUNCS(super_generation, struct btrfs_super_block,
@@ -2500,6 +2662,7 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
 }
 static inline void free_fs_info(struct btrfs_fs_info *fs_info)
 {
+	kfree(fs_info->balance_ctl);
 	kfree(fs_info->delayed_root);
 	kfree(fs_info->extent_root);
 	kfree(fs_info->tree_root);
@@ -2510,6 +2673,24 @@ static inline void free_fs_info(struct btrfs_fs_info *fs_info)
 	kfree(fs_info->super_for_commit);
 	kfree(fs_info);
 }
+/**
+ * profile_is_valid - tests whether a given profile is valid and reduced
+ * @flags: profile to validate
+ * @extended: if true @flags is treated as an extended profile
+ */
+static inline int profile_is_valid(u64 flags, int extended)
+{
+	u64 mask = ~BTRFS_BLOCK_GROUP_PROFILE_MASK;
+
+	flags &= ~BTRFS_BLOCK_GROUP_TYPE_MASK;
+	if (extended)
+		mask &= ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+
+	if (flags & mask)
+		return 0;
+	/* true if zero or exactly one bit set */
+	return (flags & (~flags + 1)) == flags;
+}
 
 /* root-item.c */
 int btrfs_find_root_ref(struct btrfs_root *tree_root,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f44b3928dc2..9c1a744e595 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2002,6 +2002,14 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	init_rwsem(&fs_info->scrub_super_lock);
 	fs_info->scrub_workers_refcnt = 0;
 
+	spin_lock_init(&fs_info->balance_lock);
+	mutex_init(&fs_info->balance_mutex);
+	atomic_set(&fs_info->balance_running, 0);
+	atomic_set(&fs_info->balance_pause_req, 0);
+	atomic_set(&fs_info->balance_cancel_req, 0);
+	fs_info->balance_ctl = NULL;
+	init_waitqueue_head(&fs_info->balance_wait_q);
+
 	sb->s_blocksize = 4096;
 	sb->s_blocksize_bits = blksize_bits(4096);
 	sb->s_bdi = &fs_info->bdi;
@@ -2321,9 +2329,6 @@ retry_root_backup:
 
 	fs_info->generation = generation;
 	fs_info->last_trans_committed = generation;
-	fs_info->data_alloc_profile = (u64)-1;
-	fs_info->metadata_alloc_profile = (u64)-1;
-	fs_info->system_alloc_profile = fs_info->metadata_alloc_profile;
 
 	ret = btrfs_init_space_info(fs_info);
 	if (ret) {
@@ -2426,6 +2431,10 @@ retry_root_backup:
 		if (!err)
 			err = btrfs_orphan_cleanup(fs_info->tree_root);
 		up_read(&fs_info->cleanup_work_sem);
+
+		if (!err)
+			err = btrfs_recover_balance(fs_info->tree_root);
+
 		if (err) {
 			close_ctree(tree_root);
 			return ERR_PTR(err);
@@ -2975,6 +2984,9 @@ int close_ctree(struct btrfs_root *root)
 	fs_info->closing = 1;
 	smp_mb();
 
+	/* pause restriper - we want to resume on mount */
+	btrfs_pause_balance(root->fs_info);
+
 	btrfs_scrub_cancel(root);
 
 	/* wait for any defraggers to finish */
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 37594e4bf66..352083ad233 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -618,8 +618,7 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info,
 	struct list_head *head = &info->space_info;
 	struct btrfs_space_info *found;
 
-	flags &= BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_SYSTEM |
-		 BTRFS_BLOCK_GROUP_METADATA;
+	flags &= BTRFS_BLOCK_GROUP_TYPE_MASK;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(found, head, list) {
@@ -2999,9 +2998,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 		INIT_LIST_HEAD(&found->block_groups[i]);
 	init_rwsem(&found->groups_sem);
 	spin_lock_init(&found->lock);
-	found->flags = flags & (BTRFS_BLOCK_GROUP_DATA |
-				BTRFS_BLOCK_GROUP_SYSTEM |
-				BTRFS_BLOCK_GROUP_METADATA);
+	found->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
 	found->total_bytes = total_bytes;
 	found->disk_total = total_bytes * factor;
 	found->bytes_used = bytes_used;
@@ -3022,20 +3019,27 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 
 static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 {
-	u64 extra_flags = flags & (BTRFS_BLOCK_GROUP_RAID0 |
-				   BTRFS_BLOCK_GROUP_RAID1 |
-				   BTRFS_BLOCK_GROUP_RAID10 |
-				   BTRFS_BLOCK_GROUP_DUP);
-	if (extra_flags) {
-		if (flags & BTRFS_BLOCK_GROUP_DATA)
-			fs_info->avail_data_alloc_bits |= extra_flags;
-		if (flags & BTRFS_BLOCK_GROUP_METADATA)
-			fs_info->avail_metadata_alloc_bits |= extra_flags;
-		if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
-			fs_info->avail_system_alloc_bits |= extra_flags;
-	}
+	u64 extra_flags = flags & BTRFS_BLOCK_GROUP_PROFILE_MASK;
+
+	/* chunk -> extended profile */
+	if (extra_flags == 0)
+		extra_flags = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+
+	if (flags & BTRFS_BLOCK_GROUP_DATA)
+		fs_info->avail_data_alloc_bits |= extra_flags;
+	if (flags & BTRFS_BLOCK_GROUP_METADATA)
+		fs_info->avail_metadata_alloc_bits |= extra_flags;
+	if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
+		fs_info->avail_system_alloc_bits |= extra_flags;
 }
 
+/*
+ * @flags: available profiles in extended format (see ctree.h)
+ *
+ * Returns reduced profile in chunk format.  If profile changing is in
+ * progress (either running or paused) picks the target profile (if it's
+ * already available), otherwise falls back to plain reducing.
+ */
 u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
 {
 	/*
@@ -3046,6 +3050,34 @@ u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
 	u64 num_devices = root->fs_info->fs_devices->rw_devices +
 		root->fs_info->fs_devices->missing_devices;
 
+	/* pick restriper's target profile if it's available */
+	spin_lock(&root->fs_info->balance_lock);
+	if (root->fs_info->balance_ctl) {
+		struct btrfs_balance_control *bctl = root->fs_info->balance_ctl;
+		u64 tgt = 0;
+
+		if ((flags & BTRFS_BLOCK_GROUP_DATA) &&
+		    (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+		    (flags & bctl->data.target)) {
+			tgt = BTRFS_BLOCK_GROUP_DATA | bctl->data.target;
+		} else if ((flags & BTRFS_BLOCK_GROUP_SYSTEM) &&
+			   (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+			   (flags & bctl->sys.target)) {
+			tgt = BTRFS_BLOCK_GROUP_SYSTEM | bctl->sys.target;
+		} else if ((flags & BTRFS_BLOCK_GROUP_METADATA) &&
+			   (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+			   (flags & bctl->meta.target)) {
+			tgt = BTRFS_BLOCK_GROUP_METADATA | bctl->meta.target;
+		}
+
+		if (tgt) {
+			spin_unlock(&root->fs_info->balance_lock);
+			flags = tgt;
+			goto out;
+		}
+	}
+	spin_unlock(&root->fs_info->balance_lock);
+
 	if (num_devices == 1)
 		flags &= ~(BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID0);
 	if (num_devices < 4)
@@ -3065,22 +3097,25 @@ u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
 	if ((flags & BTRFS_BLOCK_GROUP_RAID0) &&
 	    ((flags & BTRFS_BLOCK_GROUP_RAID1) |
 	     (flags & BTRFS_BLOCK_GROUP_RAID10) |
-	     (flags & BTRFS_BLOCK_GROUP_DUP)))
+	     (flags & BTRFS_BLOCK_GROUP_DUP))) {
 		flags &= ~BTRFS_BLOCK_GROUP_RAID0;
+	}
+
+out:
+	/* extended -> chunk profile */
+	flags &= ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
 	return flags;
 }
 
 static u64 get_alloc_profile(struct btrfs_root *root, u64 flags)
 {
 	if (flags & BTRFS_BLOCK_GROUP_DATA)
-		flags |= root->fs_info->avail_data_alloc_bits &
-			 root->fs_info->data_alloc_profile;
+		flags |= root->fs_info->avail_data_alloc_bits;
 	else if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
-		flags |= root->fs_info->avail_system_alloc_bits &
-			 root->fs_info->system_alloc_profile;
+		flags |= root->fs_info->avail_system_alloc_bits;
 	else if (flags & BTRFS_BLOCK_GROUP_METADATA)
-		flags |= root->fs_info->avail_metadata_alloc_bits &
-			 root->fs_info->metadata_alloc_profile;
+		flags |= root->fs_info->avail_metadata_alloc_bits;
+
 	return btrfs_reduce_alloc_profile(root, flags);
 }
 
@@ -3282,7 +3317,7 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 	int wait_for_alloc = 0;
 	int ret = 0;
 
-	flags = btrfs_reduce_alloc_profile(extent_root, flags);
+	BUG_ON(!profile_is_valid(flags, 0));
 
 	space_info = __find_space_info(extent_root->fs_info, flags);
 	if (!space_info) {
@@ -6792,6 +6827,29 @@ static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
 	u64 stripped = BTRFS_BLOCK_GROUP_RAID0 |
 		BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10;
 
+	if (root->fs_info->balance_ctl) {
+		struct btrfs_balance_control *bctl = root->fs_info->balance_ctl;
+		u64 tgt = 0;
+
+		/* pick restriper's target profile and return */
+		if (flags & BTRFS_BLOCK_GROUP_DATA &&
+		    bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+			tgt = BTRFS_BLOCK_GROUP_DATA | bctl->data.target;
+		} else if (flags & BTRFS_BLOCK_GROUP_SYSTEM &&
+			   bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+			tgt = BTRFS_BLOCK_GROUP_SYSTEM | bctl->sys.target;
+		} else if (flags & BTRFS_BLOCK_GROUP_METADATA &&
+			   bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+			tgt = BTRFS_BLOCK_GROUP_METADATA | bctl->meta.target;
+		}
+
+		if (tgt) {
+			/* extended -> chunk profile */
+			tgt &= ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+			return tgt;
+		}
+	}
+
 	/*
 	 * we add in the count of missing devices because we want
 	 * to make sure that any RAID levels on a degraded FS
@@ -7466,6 +7524,22 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
+{
+	u64 extra_flags = flags & BTRFS_BLOCK_GROUP_PROFILE_MASK;
+
+	/* chunk -> extended profile */
+	if (extra_flags == 0)
+		extra_flags = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+
+	if (flags & BTRFS_BLOCK_GROUP_DATA)
+		fs_info->avail_data_alloc_bits &= ~extra_flags;
+	if (flags & BTRFS_BLOCK_GROUP_METADATA)
+		fs_info->avail_metadata_alloc_bits &= ~extra_flags;
+	if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
+		fs_info->avail_system_alloc_bits &= ~extra_flags;
+}
+
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 group_start)
 {
@@ -7476,6 +7550,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	struct inode *inode;
 	int ret;
+	int index;
 	int factor;
 
 	root = root->fs_info->extent_root;
@@ -7491,6 +7566,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	free_excluded_extents(root, block_group);
 
 	memcpy(&key, &block_group->key, sizeof(key));
+	index = get_block_group_index(block_group);
 	if (block_group->flags & (BTRFS_BLOCK_GROUP_DUP |
 				  BTRFS_BLOCK_GROUP_RAID1 |
 				  BTRFS_BLOCK_GROUP_RAID10))
@@ -7565,6 +7641,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * are still on the list after taking the semaphore
 	 */
 	list_del_init(&block_group->list);
+	if (list_empty(&block_group->space_info->block_groups[index]))
+		clear_avail_alloc_bits(root->fs_info, block_group->flags);
 	up_write(&block_group->space_info->groups_sem);
 
 	if (block_group->cached == BTRFS_CACHE_STARTED)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index c04f02c7d5b..1e7a9bac31a 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1203,13 +1203,21 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	mutex_lock(&root->fs_info->volume_mutex);
+	if (root->fs_info->balance_ctl) {
+		printk(KERN_INFO "btrfs: balance in progress\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
 	vol_args = memdup_user(arg, sizeof(*vol_args));
-	if (IS_ERR(vol_args))
-		return PTR_ERR(vol_args);
+	if (IS_ERR(vol_args)) {
+		ret = PTR_ERR(vol_args);
+		goto out;
+	}
 
 	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
 
-	mutex_lock(&root->fs_info->volume_mutex);
 	sizestr = vol_args->name;
 	devstr = strchr(sizestr, ':');
 	if (devstr) {
@@ -1226,7 +1234,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 		printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
 		       (unsigned long long)devid);
 		ret = -EINVAL;
-		goto out_unlock;
+		goto out_free;
 	}
 	if (!strcmp(sizestr, "max"))
 		new_size = device->bdev->bd_inode->i_size;
@@ -1241,7 +1249,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 		new_size = memparse(sizestr, NULL);
 		if (new_size == 0) {
 			ret = -EINVAL;
-			goto out_unlock;
+			goto out_free;
 		}
 	}
 
@@ -1250,7 +1258,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 	if (mod < 0) {
 		if (new_size > old_size) {
 			ret = -EINVAL;
-			goto out_unlock;
+			goto out_free;
 		}
 		new_size = old_size - new_size;
 	} else if (mod > 0) {
@@ -1259,11 +1267,11 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 
 	if (new_size < 256 * 1024 * 1024) {
 		ret = -EINVAL;
-		goto out_unlock;
+		goto out_free;
 	}
 	if (new_size > device->bdev->bd_inode->i_size) {
 		ret = -EFBIG;
-		goto out_unlock;
+		goto out_free;
 	}
 
 	do_div(new_size, root->sectorsize);
@@ -1276,7 +1284,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 		trans = btrfs_start_transaction(root, 0);
 		if (IS_ERR(trans)) {
 			ret = PTR_ERR(trans);
-			goto out_unlock;
+			goto out_free;
 		}
 		ret = btrfs_grow_device(trans, device, new_size);
 		btrfs_commit_transaction(trans, root);
@@ -1284,9 +1292,10 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 		ret = btrfs_shrink_device(device, new_size);
 	}
 
-out_unlock:
-	mutex_unlock(&root->fs_info->volume_mutex);
+out_free:
 	kfree(vol_args);
+out:
+	mutex_unlock(&root->fs_info->volume_mutex);
 	return ret;
 }
 
@@ -2052,14 +2061,25 @@ static long btrfs_ioctl_add_dev(struct btrfs_root *root, void __user *arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	mutex_lock(&root->fs_info->volume_mutex);
+	if (root->fs_info->balance_ctl) {
+		printk(KERN_INFO "btrfs: balance in progress\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
 	vol_args = memdup_user(arg, sizeof(*vol_args));
-	if (IS_ERR(vol_args))
-		return PTR_ERR(vol_args);
+	if (IS_ERR(vol_args)) {
+		ret = PTR_ERR(vol_args);
+		goto out;
+	}
 
 	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
 	ret = btrfs_init_new_device(root, vol_args->name);
 
 	kfree(vol_args);
+out:
+	mutex_unlock(&root->fs_info->volume_mutex);
 	return ret;
 }
 
@@ -2074,14 +2094,25 @@ static long btrfs_ioctl_rm_dev(struct btrfs_root *root, void __user *arg)
 	if (root->fs_info->sb->s_flags & MS_RDONLY)
 		return -EROFS;
 
+	mutex_lock(&root->fs_info->volume_mutex);
+	if (root->fs_info->balance_ctl) {
+		printk(KERN_INFO "btrfs: balance in progress\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
 	vol_args = memdup_user(arg, sizeof(*vol_args));
-	if (IS_ERR(vol_args))
-		return PTR_ERR(vol_args);
+	if (IS_ERR(vol_args)) {
+		ret = PTR_ERR(vol_args);
+		goto out;
+	}
 
 	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
 	ret = btrfs_rm_device(root, vol_args->name);
 
 	kfree(vol_args);
+out:
+	mutex_unlock(&root->fs_info->volume_mutex);
 	return ret;
 }
 
@@ -3034,6 +3065,163 @@ out:
 	return ret;
 }
 
+void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+			       struct btrfs_ioctl_balance_args *bargs)
+{
+	struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+
+	bargs->flags = bctl->flags;
+
+	if (atomic_read(&fs_info->balance_running))
+		bargs->state |= BTRFS_BALANCE_STATE_RUNNING;
+	if (atomic_read(&fs_info->balance_pause_req))
+		bargs->state |= BTRFS_BALANCE_STATE_PAUSE_REQ;
+	if (atomic_read(&fs_info->balance_cancel_req))
+		bargs->state |= BTRFS_BALANCE_STATE_CANCEL_REQ;
+
+	memcpy(&bargs->data, &bctl->data, sizeof(bargs->data));
+	memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta));
+	memcpy(&bargs->sys, &bctl->sys, sizeof(bargs->sys));
+
+	if (lock) {
+		spin_lock(&fs_info->balance_lock);
+		memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
+		spin_unlock(&fs_info->balance_lock);
+	} else {
+		memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
+	}
+}
+
+static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_ioctl_balance_args *bargs;
+	struct btrfs_balance_control *bctl;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (fs_info->sb->s_flags & MS_RDONLY)
+		return -EROFS;
+
+	mutex_lock(&fs_info->volume_mutex);
+	mutex_lock(&fs_info->balance_mutex);
+
+	if (arg) {
+		bargs = memdup_user(arg, sizeof(*bargs));
+		if (IS_ERR(bargs)) {
+			ret = PTR_ERR(bargs);
+			goto out;
+		}
+
+		if (bargs->flags & BTRFS_BALANCE_RESUME) {
+			if (!fs_info->balance_ctl) {
+				ret = -ENOTCONN;
+				goto out_bargs;
+			}
+
+			bctl = fs_info->balance_ctl;
+			spin_lock(&fs_info->balance_lock);
+			bctl->flags |= BTRFS_BALANCE_RESUME;
+			spin_unlock(&fs_info->balance_lock);
+
+			goto do_balance;
+		}
+	} else {
+		bargs = NULL;
+	}
+
+	if (fs_info->balance_ctl) {
+		ret = -EINPROGRESS;
+		goto out_bargs;
+	}
+
+	bctl = kzalloc(sizeof(*bctl), GFP_NOFS);
+	if (!bctl) {
+		ret = -ENOMEM;
+		goto out_bargs;
+	}
+
+	bctl->fs_info = fs_info;
+	if (arg) {
+		memcpy(&bctl->data, &bargs->data, sizeof(bctl->data));
+		memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta));
+		memcpy(&bctl->sys, &bargs->sys, sizeof(bctl->sys));
+
+		bctl->flags = bargs->flags;
+	} else {
+		/* balance everything - no filters */
+		bctl->flags |= BTRFS_BALANCE_TYPE_MASK;
+	}
+
+do_balance:
+	ret = btrfs_balance(bctl, bargs);
+	/*
+	 * bctl is freed in __cancel_balance or in free_fs_info if
+	 * restriper was paused all the way until unmount
+	 */
+	if (arg) {
+		if (copy_to_user(arg, bargs, sizeof(*bargs)))
+			ret = -EFAULT;
+	}
+
+out_bargs:
+	kfree(bargs);
+out:
+	mutex_unlock(&fs_info->balance_mutex);
+	mutex_unlock(&fs_info->volume_mutex);
+	return ret;
+}
+
+static long btrfs_ioctl_balance_ctl(struct btrfs_root *root, int cmd)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	switch (cmd) {
+	case BTRFS_BALANCE_CTL_PAUSE:
+		return btrfs_pause_balance(root->fs_info);
+	case BTRFS_BALANCE_CTL_CANCEL:
+		return btrfs_cancel_balance(root->fs_info);
+	}
+
+	return -EINVAL;
+}
+
+static long btrfs_ioctl_balance_progress(struct btrfs_root *root,
+					 void __user *arg)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_ioctl_balance_args *bargs;
+	int ret = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	mutex_lock(&fs_info->balance_mutex);
+	if (!fs_info->balance_ctl) {
+		ret = -ENOTCONN;
+		goto out;
+	}
+
+	bargs = kzalloc(sizeof(*bargs), GFP_NOFS);
+	if (!bargs) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	update_ioctl_balance_args(fs_info, 1, bargs);
+
+	if (copy_to_user(arg, bargs, sizeof(*bargs)))
+		ret = -EFAULT;
+
+	kfree(bargs);
+out:
+	mutex_unlock(&fs_info->balance_mutex);
+	return ret;
+}
+
 long btrfs_ioctl(struct file *file, unsigned int
 		cmd, unsigned long arg)
 {
@@ -3078,7 +3266,7 @@ 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, NULL);
 	case BTRFS_IOC_CLONE:
 		return btrfs_ioctl_clone(file, arg, 0, 0, 0);
 	case BTRFS_IOC_CLONE_RANGE:
@@ -3110,6 +3298,12 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_scrub_cancel(root, argp);
 	case BTRFS_IOC_SCRUB_PROGRESS:
 		return btrfs_ioctl_scrub_progress(root, argp);
+	case BTRFS_IOC_BALANCE_V2:
+		return btrfs_ioctl_balance(root, argp);
+	case BTRFS_IOC_BALANCE_CTL:
+		return btrfs_ioctl_balance_ctl(root, arg);
+	case BTRFS_IOC_BALANCE_PROGRESS:
+		return btrfs_ioctl_balance_progress(root, argp);
 	}
 
 	return -ENOTTY;
diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h
index 252ae9915de..4f69028a68c 100644
--- a/fs/btrfs/ioctl.h
+++ b/fs/btrfs/ioctl.h
@@ -109,6 +109,55 @@ struct btrfs_ioctl_fs_info_args {
 	__u64 reserved[124];			/* pad to 1k */
 };
 
+/* balance control ioctl modes */
+#define BTRFS_BALANCE_CTL_PAUSE		1
+#define BTRFS_BALANCE_CTL_CANCEL	2
+
+/*
+ * this is packed, because it should be exactly the same as its disk
+ * byte order counterpart (struct btrfs_disk_balance_args)
+ */
+struct btrfs_balance_args {
+	__u64 profiles;
+	__u64 usage;
+	__u64 devid;
+	__u64 pstart;
+	__u64 pend;
+	__u64 vstart;
+	__u64 vend;
+
+	__u64 target;
+
+	__u64 flags;
+
+	__u64 unused[8];
+} __attribute__ ((__packed__));
+
+/* report balance progress to userspace */
+struct btrfs_balance_progress {
+	__u64 expected;		/* estimated # of chunks that will be
+				 * relocated to fulfill the request */
+	__u64 considered;	/* # of chunks we have considered so far */
+	__u64 completed;	/* # of chunks relocated so far */
+};
+
+#define BTRFS_BALANCE_STATE_RUNNING	(1ULL << 0)
+#define BTRFS_BALANCE_STATE_PAUSE_REQ	(1ULL << 1)
+#define BTRFS_BALANCE_STATE_CANCEL_REQ	(1ULL << 2)
+
+struct btrfs_ioctl_balance_args {
+	__u64 flags;				/* in/out */
+	__u64 state;				/* out */
+
+	struct btrfs_balance_args data;		/* in/out */
+	struct btrfs_balance_args meta;		/* in/out */
+	struct btrfs_balance_args sys;		/* in/out */
+
+	struct btrfs_balance_progress stat;	/* out */
+
+	__u64 unused[72];			/* pad to 1k */
+};
+
 #define BTRFS_INO_LOOKUP_PATH_MAX 4080
 struct btrfs_ioctl_ino_lookup_args {
 	__u64 treeid;
@@ -272,6 +321,11 @@ struct btrfs_ioctl_logical_ino_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_V2 _IOWR(BTRFS_IOCTL_MAGIC, 32, \
+				   struct btrfs_ioctl_balance_args)
+#define BTRFS_IOC_BALANCE_CTL _IOW(BTRFS_IOCTL_MAGIC, 33, int)
+#define BTRFS_IOC_BALANCE_PROGRESS _IOR(BTRFS_IOCTL_MAGIC, 34, \
+					struct btrfs_ioctl_balance_args)
 #define BTRFS_IOC_INO_PATHS _IOWR(BTRFS_IOCTL_MAGIC, 35, \
 					struct btrfs_ioctl_ino_path_args)
 #define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 200f63bc667..5a7227fa938 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -164,8 +164,9 @@ enum {
 	Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
 	Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
 	Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
-	Opt_enospc_debug, Opt_subvolrootid, Opt_defrag,
-	Opt_inode_cache, Opt_no_space_cache, Opt_recovery, Opt_err,
+	Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_inode_cache,
+	Opt_no_space_cache, Opt_recovery, Opt_skip_balance,
+	Opt_err,
 };
 
 static match_table_t tokens = {
@@ -200,6 +201,7 @@ static match_table_t tokens = {
 	{Opt_inode_cache, "inode_cache"},
 	{Opt_no_space_cache, "nospace_cache"},
 	{Opt_recovery, "recovery"},
+	{Opt_skip_balance, "skip_balance"},
 	{Opt_err, NULL},
 };
 
@@ -398,6 +400,9 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			printk(KERN_INFO "btrfs: enabling auto recovery");
 			btrfs_set_opt(info->mount_opt, RECOVERY);
 			break;
+		case Opt_skip_balance:
+			btrfs_set_opt(info->mount_opt, SKIP_BALANCE);
+			break;
 		case Opt_err:
 			printk(KERN_INFO "btrfs: unrecognized mount option "
 			       "'%s'\n", p);
@@ -723,6 +728,8 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",autodefrag");
 	if (btrfs_test_opt(root, INODE_MAP_CACHE))
 		seq_puts(seq, ",inode_cache");
+	if (btrfs_test_opt(root, SKIP_BALANCE))
+		seq_puts(seq, ",skip_balance");
 	return 0;
 }
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ac00e3aa80a..9489a2aca47 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)