1 files changed, 86 insertions, 19 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index d6dd49b51ba8..e795bf135e80 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -961,8 +961,8 @@ struct btrfs_dev_replace_item {
 #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_RAID5    (1 << 7)
-#define BTRFS_BLOCK_GROUP_RAID6    (1 << 8)
+#define BTRFS_BLOCK_GROUP_RAID5         (1ULL << 7)
+#define BTRFS_BLOCK_GROUP_RAID6         (1ULL << 8)
 #define BTRFS_BLOCK_GROUP_RESERVED      BTRFS_AVAIL_ALLOC_BIT_SINGLE
 
 enum btrfs_raid_types {
@@ -1102,6 +1102,18 @@ struct btrfs_space_info {
                                    account */
 
         /*
+         * bytes_pinned is kept in line with what is actually pinned, as in
+         * we've called update_block_group and dropped the bytes_used counter
+         * and increased the bytes_pinned counter.  However this means that
+         * bytes_pinned does not reflect the bytes that will be pinned once the
+         * delayed refs are flushed, so this counter is inc'ed everytime we call
+         * btrfs_free_extent so it is a realtime count of what will be freed
+         * once the transaction is committed.  It will be zero'ed everytime the
+         * transaction commits.
+         */
+        struct percpu_counter total_bytes_pinned;
+
+        /*
          * we bump reservation progress every time we decrement
          * bytes_reserved.  This way people waiting for reservations
          * know something good has happened and they can check
@@ -1437,25 +1449,22 @@ struct btrfs_fs_info {
         atomic_t open_ioctl_trans;
 
         /*
-         * this is used by the balancing code to wait for all the pending
-         * ordered extents
+         * this is used to protect the following list -- ordered_roots.
          */
-        spinlock_t ordered_extent_lock;
+        spinlock_t ordered_root_lock;
 
         /*
-         * all of the data=ordered extents pending writeback
+         * all fs/file tree roots in which there are data=ordered extents
+         * pending writeback are added into this list.
+         *
          * these can span multiple transactions and basically include
          * every dirty data page that isn't from nodatacow
          */
-        struct list_head ordered_extents;
+        struct list_head ordered_roots;
 
-        spinlock_t delalloc_lock;
-        /*
-         * all of the inodes that have delalloc bytes.  It is possible for
-         * this list to be empty even when there is still dirty data=ordered
-         * extents waiting to finish IO.
-         */
-        struct list_head delalloc_inodes;
+        spinlock_t delalloc_root_lock;
+        /* all fs/file tree roots that have delalloc inodes. */
+        struct list_head delalloc_roots;
 
         /*
          * there is a pool of worker threads for checksumming during writes
@@ -1498,8 +1507,6 @@ struct btrfs_fs_info {
         int do_barriers;
         int closing;
         int log_root_recovering;
-        int enospc_unlink;
-        int trans_no_join;
 
         u64 total_pinned;
 
@@ -1594,6 +1601,12 @@ struct btrfs_fs_info {
         struct rb_root qgroup_tree;
         spinlock_t qgroup_lock;
 
+        /*
+         * used to avoid frequently calling ulist_alloc()/ulist_free()
+         * when doing qgroup accounting, it must be protected by qgroup_lock.
+         */
+        struct ulist *qgroup_ulist;
+
         /* protect user change for quota operations */
         struct mutex qgroup_ioctl_lock;
 
@@ -1607,6 +1620,8 @@ struct btrfs_fs_info {
         struct mutex qgroup_rescan_lock; /* protects the progress item */
         struct btrfs_key qgroup_rescan_progress;
         struct btrfs_workers qgroup_rescan_workers;
+        struct completion qgroup_rescan_completion;
+        struct btrfs_work qgroup_rescan_work;
 
         /* filesystem state */
         unsigned long fs_state;
@@ -1739,6 +1754,31 @@ struct btrfs_root {
         int force_cow;
 
         spinlock_t root_item_lock;
+        atomic_t refs;
+
+        spinlock_t delalloc_lock;
+        /*
+         * all of the inodes that have delalloc bytes.  It is possible for
+         * this list to be empty even when there is still dirty data=ordered
+         * extents waiting to finish IO.
+         */
+        struct list_head delalloc_inodes;
+        struct list_head delalloc_root;
+        u64 nr_delalloc_inodes;
+        /*
+         * this is used by the balancing code to wait for all the pending
+         * ordered extents
+         */
+        spinlock_t ordered_extent_lock;
+
+        /*
+         * all of the data=ordered extents pending writeback
+         * these can span multiple transactions and basically include
+         * every dirty data page that isn't from nodatacow
+         */
+        struct list_head ordered_extents;
+        struct list_head ordered_root;
+        u64 nr_ordered_extents;
 };
 
 struct btrfs_ioctl_defrag_range_args {
@@ -3028,6 +3068,8 @@ static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_root *root,
                 num_items;
 }
 
+int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
+                                       struct btrfs_root *root);
 void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
                            struct btrfs_root *root, unsigned long count);
@@ -3039,6 +3081,8 @@ int btrfs_pin_extent(struct btrfs_root *root,
                      u64 bytenr, u64 num, int reserved);
 int btrfs_pin_extent_for_log_replay(struct btrfs_root *root,
                                     u64 bytenr, u64 num_bytes);
+int btrfs_exclude_logged_extents(struct btrfs_root *root,
+                                 struct extent_buffer *eb);
 int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
                           struct btrfs_root *root,
                           u64 objectid, u64 offset, u64 bytenr);
@@ -3155,6 +3199,9 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
 int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
                             struct btrfs_block_rsv *dst_rsv,
                             u64 num_bytes);
+int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
+                             struct btrfs_block_rsv *dest, u64 num_bytes,
+                             int min_factor);
 void btrfs_block_rsv_release(struct btrfs_root *root,
                              struct btrfs_block_rsv *block_rsv,
                              u64 num_bytes);
@@ -3311,6 +3358,18 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
         smp_mb();
         return fs_info->closing;
 }
+
+/*
+ * If we remount the fs to be R/O or umount the fs, the cleaner needn't do
+ * anything except sleeping. This function is used to check the status of
+ * the fs.
+ */
+static inline int btrfs_need_cleaner_sleep(struct btrfs_root *root)
+{
+        return (root->fs_info->sb->s_flags & MS_RDONLY ||
+                btrfs_fs_closing(root->fs_info));
+}
+
 static inline void free_fs_info(struct btrfs_fs_info *fs_info)
 {
         kfree(fs_info->balance_ctl);
@@ -3357,9 +3416,9 @@ int __must_check btrfs_update_root(struct btrfs_trans_handle *trans,
                                    struct btrfs_root_item *item);
 void btrfs_read_root_item(struct extent_buffer *eb, int slot,
                           struct btrfs_root_item *item);
-int btrfs_find_last_root(struct btrfs_root *root, u64 objectid, struct
-                         btrfs_root_item *item, struct btrfs_key *key);
-int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid);
+int btrfs_find_root(struct btrfs_root *root, struct btrfs_key *search_key,
+                    struct btrfs_path *path, struct btrfs_root_item *root_item,
+                    struct btrfs_key *root_key);
 int btrfs_find_orphan_roots(struct btrfs_root *tree_root);
 void btrfs_set_root_node(struct btrfs_root_item *item,
                          struct extent_buffer *node);
@@ -3493,6 +3552,10 @@ void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work);
 struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page,
                                            size_t pg_offset, u64 start, u64 len,
                                            int create);
+noinline int can_nocow_extent(struct btrfs_trans_handle *trans,
+                              struct inode *inode, u64 offset, u64 *len,
+                              u64 *orig_start, u64 *orig_block_len,
+                              u64 *ram_bytes);
 
 /* RHEL and EL kernels have a patch that renames PG_checked to FsMisc */
 #if defined(ClearPageFsMisc) && !defined(ClearPageChecked)
@@ -3530,6 +3593,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
                                u32 min_type);
 
 int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput);
+int btrfs_start_all_delalloc_inodes(struct btrfs_fs_info *fs_info,
+                                    int delay_iput);
 int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
                               struct extent_state **cached_state);
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
@@ -3814,6 +3879,8 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 int btrfs_quota_disable(struct btrfs_trans_handle *trans,
                         struct btrfs_fs_info *fs_info);
 int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
+void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info);
 int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
                               struct btrfs_fs_info *fs_info, u64 src, u64 dst);
 int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,