static void add_root_to_dirty_list(struct btrfs_root *root)
{
spin_lock(&root->fs_info->trans_lock);
- if (root->track_dirty && list_empty(&root->dirty_list)) {
+ if (test_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state) &&
+ list_empty(&root->dirty_list)) {
list_add(&root->dirty_list,
&root->fs_info->dirty_cowonly_roots);
}
int level;
struct btrfs_disk_key disk_key;
- WARN_ON(root->ref_cows && trans->transid !=
- root->fs_info->running_transaction->transid);
- WARN_ON(root->ref_cows && trans->transid != root->last_trans);
+ WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+ trans->transid != root->fs_info->running_transaction->transid);
+ WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+ trans->transid != root->last_trans);
level = btrfs_header_level(buf);
if (level == 0)
}
/*
- * Increment the upper half of tree_mod_seq, set lower half zero.
- *
- * Must be called with fs_info->tree_mod_seq_lock held.
- */
-static inline u64 btrfs_inc_tree_mod_seq_major(struct btrfs_fs_info *fs_info)
-{
- u64 seq = atomic64_read(&fs_info->tree_mod_seq);
- seq &= 0xffffffff00000000ull;
- seq += 1ull << 32;
- atomic64_set(&fs_info->tree_mod_seq, seq);
- return seq;
-}
-
-/*
- * Increment the lower half of tree_mod_seq.
- *
- * Must be called with fs_info->tree_mod_seq_lock held. The way major numbers
- * are generated should not technically require a spin lock here. (Rationale:
- * incrementing the minor while incrementing the major seq number is between its
- * atomic64_read and atomic64_set calls doesn't duplicate sequence numbers, it
- * just returns a unique sequence number as usual.) We have decided to leave
- * that requirement in here and rethink it once we notice it really imposes a
- * problem on some workload.
+ * Pull a new tree mod seq number for our operation.
*/
-static inline u64 btrfs_inc_tree_mod_seq_minor(struct btrfs_fs_info *fs_info)
+static inline u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info)
{
return atomic64_inc_return(&fs_info->tree_mod_seq);
}
-/*
- * return the last minor in the previous major tree_mod_seq number
- */
-u64 btrfs_tree_mod_seq_prev(u64 seq)
-{
- return (seq & 0xffffffff00000000ull) - 1ull;
-}
-
/*
* This adds a new blocker to the tree mod log's blocker list if the @elem
* passed does not already have a sequence number set. So when a caller expects
u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
struct seq_list *elem)
{
- u64 seq;
-
tree_mod_log_write_lock(fs_info);
spin_lock(&fs_info->tree_mod_seq_lock);
if (!elem->seq) {
- elem->seq = btrfs_inc_tree_mod_seq_major(fs_info);
+ elem->seq = btrfs_inc_tree_mod_seq(fs_info);
list_add_tail(&elem->list, &fs_info->tree_mod_seq_list);
}
- seq = btrfs_inc_tree_mod_seq_minor(fs_info);
spin_unlock(&fs_info->tree_mod_seq_lock);
tree_mod_log_write_unlock(fs_info);
- return seq;
+ return elem->seq;
}
void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
BUG_ON(!tm);
- spin_lock(&fs_info->tree_mod_seq_lock);
- tm->seq = btrfs_inc_tree_mod_seq_minor(fs_info);
- spin_unlock(&fs_info->tree_mod_seq_lock);
+ tm->seq = btrfs_inc_tree_mod_seq(fs_info);
tm_root = &fs_info->tree_mod_log;
new = &tm_root->rb_node;
* snapshot and the block was not allocated by tree relocation,
* we know the block is not shared.
*/
- if (root->ref_cows &&
+ if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
buf != root->node && buf != root->commit_root &&
(btrfs_header_generation(buf) <=
btrfs_root_last_snapshot(&root->root_item) ||
btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
return 1;
#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
- if (root->ref_cows &&
+ if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
return 1;
#endif
btrfs_assert_tree_locked(buf);
- WARN_ON(root->ref_cows && trans->transid !=
- root->fs_info->running_transaction->transid);
- WARN_ON(root->ref_cows && trans->transid != root->last_trans);
+ WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+ trans->transid != root->fs_info->running_transaction->transid);
+ WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+ trans->transid != root->last_trans);
level = btrfs_header_level(buf);
return ret;
}
- if (root->ref_cows) {
+ if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) {
ret = btrfs_reloc_cow_block(trans, root, buf, cow);
if (ret)
return ret;
struct btrfs_root *root,
struct extent_buffer *buf)
{
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+ if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+ return 0;
+#endif
/* ensure we can see the force_cow */
smp_rmb();
!btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) &&
!(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) &&
- !root->force_cow)
+ !test_bit(BTRFS_ROOT_FORCE_COW, &root->state))
return 0;
return 1;
}
return ret;
btrfs_item_key(path->nodes[0], &found_key, 0);
ret = comp_keys(&found_key, &key);
- if (ret < 0)
+ /*
+ * We might have had an item with the previous key in the tree right
+ * before we released our path. And after we released our path, that
+ * item might have been pushed to the first slot (0) of the leaf we
+ * were holding due to a tree balance. Alternatively, an item with the
+ * previous key can exist as the only element of a leaf (big fat item).
+ * Therefore account for these 2 cases, so that our callers (like
+ * btrfs_previous_item) don't miss an existing item with a key matching
+ * the previous key we computed above.
+ */
+ if (ret <= 0)
return 0;
return 1;
}
ret = 0;
goto done;
}
+ /*
+ * So the above check misses one case:
+ * - after releasing the path above, someone has removed the item that
+ * used to be at the very end of the block, and balance between leafs
+ * gets another one with bigger key.offset to replace it.
+ *
+ * This one should be returned as well, or we can get leaf corruption
+ * later(esp. in __btrfs_drop_extents()).
+ *
+ * And a bit more explanation about this check,
+ * with ret > 0, the key isn't found, the path points to the slot
+ * where it should be inserted, so the path->slots[0] item must be the
+ * bigger one.
+ */
+ if (nritems > 0 && ret > 0 && path->slots[0] == nritems - 1) {
+ ret = 0;
+ goto done;
+ }
while (level < BTRFS_MAX_LEVEL) {
if (!path->nodes[level]) {