1 files changed, 217 insertions, 22 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 67385033323d..27ebe61d3ccc 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];
@@ -971,7 +1041,7 @@ struct btrfs_fs_info {
          * is required instead of the faster short fsync log commits
          */
         u64 last_trans_log_full_commit;
-        unsigned long mount_opt:20;
+        unsigned long mount_opt:21;
         unsigned long compress_type:4;
         u64 max_inline;
         u64 alloc_start;
@@ -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;
@@ -1155,6 +1236,10 @@ struct btrfs_fs_info {
         int scrub_workers_refcnt;
         struct btrfs_workers scrub_workers;
 
+#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+        u32 check_integrity_print_mask;
+#endif
+
         /* filesystem state */
         u64 fs_state;
 
@@ -1383,6 +1468,8 @@ 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 +1500,9 @@ 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_MOUNT_CHECK_INTEGRITY     (1 << 20)
+#define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
 
 #define btrfs_clear_opt(o, opt)         ((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)           ((o) |= BTRFS_MOUNT_##opt)
@@ -2077,8 +2167,86 @@ 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,
@@ -2196,7 +2364,7 @@ static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb,
         return btrfs_item_size(eb, e) - offset;
 }
 
-static inline struct btrfs_root *btrfs_sb(struct super_block *sb)
+static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
 {
         return sb->s_fs_info;
 }
@@ -2277,11 +2445,11 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
                                         struct btrfs_root *root, u32 blocksize,
                                         u64 parent, u64 root_objectid,
                                         struct btrfs_disk_key *key, int level,
-                                        u64 hint, u64 empty_size);
+                                        u64 hint, u64 empty_size, int for_cow);
 void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
                            struct btrfs_root *root,
                            struct extent_buffer *buf,
-                           u64 parent, int last_ref);
+                           u64 parent, int last_ref, int for_cow);
 struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans,
                                             struct btrfs_root *root,
                                             u64 bytenr, u32 blocksize,
@@ -2301,17 +2469,17 @@ int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
                                   u64 search_end, struct btrfs_key *ins,
                                   u64 data);
 int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-                  struct extent_buffer *buf, int full_backref);
+                  struct extent_buffer *buf, int full_backref, int for_cow);
 int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-                  struct extent_buffer *buf, int full_backref);
+                  struct extent_buffer *buf, int full_backref, int for_cow);
 int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
                                 struct btrfs_root *root,
                                 u64 bytenr, u64 num_bytes, u64 flags,
                                 int is_data);
 int btrfs_free_extent(struct btrfs_trans_handle *trans,
                       struct btrfs_root *root,
-                      u64 bytenr, u64 num_bytes, u64 parent,
-                      u64 root_objectid, u64 owner, u64 offset);
+                      u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
+                      u64 owner, u64 offset, int for_cow);
 
 int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len);
 int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root,
@@ -2323,7 +2491,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
                          struct btrfs_root *root,
                          u64 bytenr, u64 num_bytes, u64 parent,
-                         u64 root_objectid, u64 owner, u64 offset);
+                         u64 root_objectid, u64 owner, u64 offset, int for_cow);
 
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
                                     struct btrfs_root *root);
@@ -2482,10 +2650,18 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans,
 }
 
 int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path);
+static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p)
+{
+        ++p->slots[0];
+        if (p->slots[0] >= btrfs_header_nritems(p->nodes[0]))
+                return btrfs_next_leaf(root, p);
+        return 0;
+}
 int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
 int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf);
 void btrfs_drop_snapshot(struct btrfs_root *root,
-                         struct btrfs_block_rsv *block_rsv, int update_ref);
+                         struct btrfs_block_rsv *block_rsv, int update_ref,
+                         int for_reloc);
 int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
                         struct btrfs_root *root,
                         struct extent_buffer *node,
@@ -2500,6 +2676,7 @@ 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 +2687,24 @@ 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,