#include "locking.h"
#include "tree-log.h"
#include "inode-map.h"
+#include "volumes.h"
#define BTRFS_ROOT_TRANS_TAG 0
if (atomic_dec_and_test(&transaction->use_count)) {
BUG_ON(!list_empty(&transaction->list));
WARN_ON(transaction->delayed_refs.root.rb_node);
- WARN_ON(!list_empty(&transaction->delayed_refs.seq_head));
memset(transaction, 0, sizeof(*transaction));
kmem_cache_free(btrfs_transaction_cachep, transaction);
}
static noinline int join_transaction(struct btrfs_root *root, int nofail)
{
struct btrfs_transaction *cur_trans;
+ struct btrfs_fs_info *fs_info = root->fs_info;
- spin_lock(&root->fs_info->trans_lock);
+ spin_lock(&fs_info->trans_lock);
loop:
/* The file system has been taken offline. No new transactions. */
- if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
- spin_unlock(&root->fs_info->trans_lock);
+ if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+ spin_unlock(&fs_info->trans_lock);
return -EROFS;
}
- if (root->fs_info->trans_no_join) {
+ if (fs_info->trans_no_join) {
if (!nofail) {
- spin_unlock(&root->fs_info->trans_lock);
+ spin_unlock(&fs_info->trans_lock);
return -EBUSY;
}
}
- cur_trans = root->fs_info->running_transaction;
+ cur_trans = fs_info->running_transaction;
if (cur_trans) {
- if (cur_trans->aborted)
+ if (cur_trans->aborted) {
+ spin_unlock(&fs_info->trans_lock);
return cur_trans->aborted;
+ }
atomic_inc(&cur_trans->use_count);
atomic_inc(&cur_trans->num_writers);
cur_trans->num_joined++;
- spin_unlock(&root->fs_info->trans_lock);
+ spin_unlock(&fs_info->trans_lock);
return 0;
}
- spin_unlock(&root->fs_info->trans_lock);
+ spin_unlock(&fs_info->trans_lock);
cur_trans = kmem_cache_alloc(btrfs_transaction_cachep, GFP_NOFS);
if (!cur_trans)
return -ENOMEM;
- spin_lock(&root->fs_info->trans_lock);
- if (root->fs_info->running_transaction) {
+ spin_lock(&fs_info->trans_lock);
+ if (fs_info->running_transaction) {
/*
* someone started a transaction after we unlocked. Make sure
* to redo the trans_no_join checks above
*/
kmem_cache_free(btrfs_transaction_cachep, cur_trans);
- cur_trans = root->fs_info->running_transaction;
+ cur_trans = fs_info->running_transaction;
goto loop;
+ } else if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+ spin_unlock(&root->fs_info->trans_lock);
+ kmem_cache_free(btrfs_transaction_cachep, cur_trans);
+ return -EROFS;
}
atomic_set(&cur_trans->num_writers, 1);
cur_trans->delayed_refs.num_heads = 0;
cur_trans->delayed_refs.flushing = 0;
cur_trans->delayed_refs.run_delayed_start = 0;
- cur_trans->delayed_refs.seq = 1;
- init_waitqueue_head(&cur_trans->delayed_refs.seq_wait);
+
+ /*
+ * although the tree mod log is per file system and not per transaction,
+ * the log must never go across transaction boundaries.
+ */
+ smp_mb();
+ if (!list_empty(&fs_info->tree_mod_seq_list)) {
+ printk(KERN_ERR "btrfs: tree_mod_seq_list not empty when "
+ "creating a fresh transaction\n");
+ WARN_ON(1);
+ }
+ if (!RB_EMPTY_ROOT(&fs_info->tree_mod_log)) {
+ printk(KERN_ERR "btrfs: tree_mod_log rb tree not empty when "
+ "creating a fresh transaction\n");
+ WARN_ON(1);
+ }
+ atomic_set(&fs_info->tree_mod_seq, 0);
+
spin_lock_init(&cur_trans->commit_lock);
spin_lock_init(&cur_trans->delayed_refs.lock);
- INIT_LIST_HEAD(&cur_trans->delayed_refs.seq_head);
INIT_LIST_HEAD(&cur_trans->pending_snapshots);
- list_add_tail(&cur_trans->list, &root->fs_info->trans_list);
+ list_add_tail(&cur_trans->list, &fs_info->trans_list);
extent_io_tree_init(&cur_trans->dirty_pages,
- root->fs_info->btree_inode->i_mapping);
- root->fs_info->generation++;
- cur_trans->transid = root->fs_info->generation;
- root->fs_info->running_transaction = cur_trans;
+ fs_info->btree_inode->i_mapping);
+ fs_info->generation++;
+ cur_trans->transid = fs_info->generation;
+ fs_info->running_transaction = cur_trans;
cur_trans->aborted = 0;
- spin_unlock(&root->fs_info->trans_lock);
+ spin_unlock(&fs_info->trans_lock);
return 0;
}
struct btrfs_transaction *cur_trans;
u64 num_bytes = 0;
int ret;
+ u64 qgroup_reserved = 0;
if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
return ERR_PTR(-EROFS);
* the appropriate flushing if need be.
*/
if (num_items > 0 && root != root->fs_info->chunk_root) {
+ if (root->fs_info->quota_enabled &&
+ is_fstree(root->root_key.objectid)) {
+ qgroup_reserved = num_items * root->leafsize;
+ ret = btrfs_qgroup_reserve(root, qgroup_reserved);
+ if (ret)
+ return ERR_PTR(ret);
+ }
+
num_bytes = btrfs_calc_trans_metadata_size(root, num_items);
ret = btrfs_block_rsv_add(root,
&root->fs_info->trans_block_rsv,
h->transaction = cur_trans;
h->blocks_used = 0;
h->bytes_reserved = 0;
+ h->root = root;
h->delayed_ref_updates = 0;
h->use_count = 1;
h->block_rsv = NULL;
h->orig_rsv = NULL;
h->aborted = 0;
+ h->qgroup_reserved = qgroup_reserved;
+ h->delayed_ref_elem.seq = 0;
+ INIT_LIST_HEAD(&h->qgroup_ref_list);
smp_mb();
if (cur_trans->blocked && may_wait_transaction(root, type)) {
struct btrfs_transaction *cur_trans = trans->transaction;
struct btrfs_fs_info *info = root->fs_info;
int count = 0;
+ int err = 0;
if (--trans->use_count) {
trans->block_rsv = trans->orig_rsv;
return 0;
}
+ /*
+ * do the qgroup accounting as early as possible
+ */
+ err = btrfs_delayed_refs_qgroup_accounting(trans, info);
+
btrfs_trans_release_metadata(trans, root);
trans->block_rsv = NULL;
+ /*
+ * the same root has to be passed to start_transaction and
+ * end_transaction. Subvolume quota depends on this.
+ */
+ WARN_ON(trans->root != root);
+
+ if (trans->qgroup_reserved) {
+ btrfs_qgroup_free(root, trans->qgroup_reserved);
+ trans->qgroup_reserved = 0;
+ }
+
while (count < 2) {
unsigned long cur = trans->delayed_ref_updates;
trans->delayed_ref_updates = 0;
if (current->journal_info == trans)
current->journal_info = NULL;
- memset(trans, 0, sizeof(*trans));
- kmem_cache_free(btrfs_trans_handle_cachep, trans);
if (throttle)
btrfs_run_delayed_iputs(root);
if (trans->aborted ||
root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
- return -EIO;
+ err = -EIO;
}
+ assert_qgroups_uptodate(trans);
- return 0;
+ memset(trans, 0, sizeof(*trans));
+ kmem_cache_free(btrfs_trans_handle_cachep, trans);
+ return err;
}
int btrfs_end_transaction(struct btrfs_trans_handle *trans,
if (ret)
return ret;
+ ret = btrfs_run_dev_stats(trans, root->fs_info);
+ BUG_ON(ret);
+
+ ret = btrfs_run_qgroups(trans, root->fs_info);
+ BUG_ON(ret);
+
+ /* run_qgroups might have added some more refs */
+ ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
+ BUG_ON(ret);
+
while (!list_empty(&fs_info->dirty_cowonly_roots)) {
next = fs_info->dirty_cowonly_roots.next;
list_del_init(next);
}
}
+ ret = btrfs_qgroup_inherit(trans, fs_info, root->root_key.objectid,
+ objectid, pending->inherit);
+ kfree(pending->inherit);
+ if (ret) {
+ pending->error = ret;
+ goto fail;
+ }
+
key.objectid = objectid;
key.offset = (u64)-1;
key.type = BTRFS_ROOT_ITEM_KEY;
static void cleanup_transaction(struct btrfs_trans_handle *trans,
- struct btrfs_root *root)
+ struct btrfs_root *root, int err)
{
struct btrfs_transaction *cur_trans = trans->transaction;
WARN_ON(trans->use_count > 1);
+ btrfs_abort_transaction(trans, root, err);
+
spin_lock(&root->fs_info->trans_lock);
list_del_init(&cur_trans->list);
+ if (cur_trans == root->fs_info->running_transaction) {
+ root->fs_info->running_transaction = NULL;
+ root->fs_info->trans_no_join = 0;
+ }
spin_unlock(&root->fs_info->trans_lock);
btrfs_cleanup_one_transaction(trans->transaction, root);
if (ret)
goto cleanup_transaction;
+ /*
+ * running the delayed items may have added new refs. account
+ * them now so that they hinder processing of more delayed refs
+ * as little as possible.
+ */
+ btrfs_delayed_refs_qgroup_accounting(trans, root->fs_info);
+
/*
* rename don't use btrfs_join_transaction, so, once we
* set the transaction to blocked above, we aren't going
ret = commit_fs_roots(trans, root);
if (ret) {
mutex_unlock(&root->fs_info->tree_log_mutex);
+ mutex_unlock(&root->fs_info->reloc_mutex);
goto cleanup_transaction;
}
ret = commit_cowonly_roots(trans, root);
if (ret) {
mutex_unlock(&root->fs_info->tree_log_mutex);
+ mutex_unlock(&root->fs_info->reloc_mutex);
goto cleanup_transaction;
}
root->fs_info->chunk_root->node);
switch_commit_root(root->fs_info->chunk_root);
+ assert_qgroups_uptodate(trans);
update_super_roots(root);
if (!root->fs_info->log_root_recovering) {
// WARN_ON(1);
if (current->journal_info == trans)
current->journal_info = NULL;
- cleanup_transaction(trans, root);
+ cleanup_transaction(trans, root, ret);
return ret;
}