btrfs: fix wrong free space information of btrfs

When we store data by raid profile in btrfs with two or more different size
disks, df command shows there is some free space in the filesystem, but the
user can not write any data in fact, df command shows the wrong free space
information of btrfs.

 # mkfs.btrfs -d raid1 /dev/sda9 /dev/sda10
 # btrfs-show
 Label: none  uuid: a95cd49e-6e33-45b8-8741-a36153ce4b64
 	Total devices 2 FS bytes used 28.00KB
 	devid    1 size 5.01GB used 2.03GB path /dev/sda9
 	devid    2 size 10.00GB used 2.01GB path /dev/sda10
 # btrfs device scan /dev/sda9 /dev/sda10
 # mount /dev/sda9 /mnt
 # dd if=/dev/zero of=tmpfile0 bs=4K count=9999999999
   (fill the filesystem)
 # sync
 # df -TH
 Filesystem	Type	Size	Used	Avail	Use%	Mounted on
 /dev/sda9	btrfs	17G	8.6G	5.4G	62%	/mnt
 # btrfs-show
 Label: none  uuid: a95cd49e-6e33-45b8-8741-a36153ce4b64
 	Total devices 2 FS bytes used 3.99GB
 	devid    1 size 5.01GB used 5.01GB path /dev/sda9
 	devid    2 size 10.00GB used 4.99GB path /dev/sda10

It is because btrfs cannot allocate chunks when one of the pairing disks has
no space, the free space on the other disks can not be used for ever, and should
be subtracted from the total space, but btrfs doesn't subtract this space from
the total. It is strange to the user.

This patch fixes it by calcing the free space that can be used to allocate
chunks.

Implementation:
1. get all the devices free space, and align them by stripe length.
2. sort the devices by the free space.
3. check the free space of the devices,
   3.1. if it is not zero, and then check the number of the devices that has
        more free space than this device,
        if the number of the devices is beyond the min stripe number, the free
        space can be used, and add into total free space.
        if the number of the devices is below the min stripe number, we can not
        use the free space, the check ends.
   3.2. if the free space is zero, check the next devices, goto 3.1

This implementation is just likely fake chunk allocation.

After appling this patch, df can show correct space information:
 # df -TH
 Filesystem	Type	Size	Used	Avail	Use%	Mounted on
 /dev/sda9	btrfs	17G	8.6G	0	100%	/mnt

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>

1 files changed, 57 insertions, 1 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1e1c9a177626..04bfc3a2bd9f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3090,7 +3090,7 @@ static u64 get_alloc_profile(struct btrfs_root *root, u64 flags)
 	return btrfs_reduce_alloc_profile(root, flags);
 }
 
-static u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
+u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
 {
 	u64 flags;
 
@@ -8019,6 +8019,62 @@ out:
 	return ret;
 }
 
+/*
+ * helper to account the unused space of all the readonly block group in the
+ * list. takes mirrors into account.
+ */
+static u64 __btrfs_get_ro_block_group_free_space(struct list_head *groups_list)
+{
+	struct btrfs_block_group_cache *block_group;
+	u64 free_bytes = 0;
+	int factor;
+
+	list_for_each_entry(block_group, groups_list, list) {
+		spin_lock(&block_group->lock);
+
+		if (!block_group->ro) {
+			spin_unlock(&block_group->lock);
+			continue;
+		}
+
+		if (block_group->flags & (BTRFS_BLOCK_GROUP_RAID1 |
+					  BTRFS_BLOCK_GROUP_RAID10 |
+					  BTRFS_BLOCK_GROUP_DUP))
+			factor = 2;
+		else
+			factor = 1;
+
+		free_bytes += (block_group->key.offset -
+			       btrfs_block_group_used(&block_group->item)) *
+			       factor;
+
+		spin_unlock(&block_group->lock);
+	}
+
+	return free_bytes;
+}
+
+/*
+ * helper to account the unused space of all the readonly block group in the
+ * space_info. takes mirrors into account.
+ */
+u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
+{
+	int i;
+	u64 free_bytes = 0;
+
+	spin_lock(&sinfo->lock);
+
+	for(i = 0; i < BTRFS_NR_RAID_TYPES; i++)
+		if (!list_empty(&sinfo->block_groups[i]))
+			free_bytes += __btrfs_get_ro_block_group_free_space(
+						&sinfo->block_groups[i]);
+
+	spin_unlock(&sinfo->lock);
+
+	return free_bytes;
+}
+
 int btrfs_set_block_group_rw(struct btrfs_root *root,
 			      struct btrfs_block_group_cache *cache)
 {