diff options
Diffstat (limited to 'fs/bcachefs/btree_trans_commit.c')
| -rw-r--r-- | fs/bcachefs/btree_trans_commit.c | 120 |
1 files changed, 50 insertions, 70 deletions
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index c4f524b2ca9a..7d7e52ddde02 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -164,6 +164,7 @@ bool bch2_btree_bset_insert_key(struct btree_trans *trans, EBUG_ON(bpos_gt(insert->k.p, b->data->max_key)); EBUG_ON(insert->k.u64s > bch2_btree_keys_u64s_remaining(b)); EBUG_ON(!b->c.level && !bpos_eq(insert->k.p, path->pos)); + kmsan_check_memory(insert, bkey_bytes(&insert->k)); k = bch2_btree_node_iter_peek_all(node_iter, b); if (k && bkey_cmp_left_packed(b, k, &insert->k.p)) @@ -336,6 +337,7 @@ static inline void btree_insert_entry_checks(struct btree_trans *trans, BUG_ON(i->cached != path->cached); BUG_ON(i->level != path->level); BUG_ON(i->btree_id != path->btree_id); + BUG_ON(i->bkey_type != __btree_node_type(path->level, path->btree_id)); EBUG_ON(!i->level && btree_type_has_snapshots(i->btree_id) && !(i->flags & BTREE_UPDATE_internal_snapshot_node) && @@ -517,69 +519,45 @@ static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_ } } -static int run_btree_triggers(struct btree_trans *trans, enum btree_id btree_id, - unsigned *btree_id_updates_start) +static int bch2_trans_commit_run_triggers(struct btree_trans *trans) { - bool trans_trigger_run; + unsigned sort_id_start = 0; - /* - * Running triggers will append more updates to the list of updates as - * we're walking it: - */ - do { - trans_trigger_run = false; + while (sort_id_start < trans->nr_updates) { + unsigned i, sort_id = trans->updates[sort_id_start].sort_order; + bool trans_trigger_run; - for (unsigned i = *btree_id_updates_start; - i < trans->nr_updates && trans->updates[i].btree_id <= btree_id; - i++) { - if (trans->updates[i].btree_id < btree_id) { - *btree_id_updates_start = i; - continue; + /* + * For a given btree, this algorithm runs insert triggers before + * overwrite triggers: this is so that when extents are being + * moved (e.g. by FALLOCATE_FL_INSERT_RANGE), we don't drop + * references before they are re-added. + * + * Running triggers will append more updates to the list of + * updates as we're walking it: + */ + do { + trans_trigger_run = false; + + for (i = sort_id_start; + i < trans->nr_updates && trans->updates[i].sort_order <= sort_id; + i++) { + if (trans->updates[i].sort_order < sort_id) { + sort_id_start = i; + continue; + } + + int ret = run_one_trans_trigger(trans, trans->updates + i); + if (ret < 0) + return ret; + if (ret) + trans_trigger_run = true; } + } while (trans_trigger_run); - int ret = run_one_trans_trigger(trans, trans->updates + i); - if (ret < 0) - return ret; - if (ret) - trans_trigger_run = true; - } - } while (trans_trigger_run); - - trans_for_each_update(trans, i) - BUG_ON(!(i->flags & BTREE_TRIGGER_norun) && - i->btree_id == btree_id && - btree_node_type_has_trans_triggers(i->bkey_type) && - (!i->insert_trigger_run || !i->overwrite_trigger_run)); - - return 0; -} - -static int bch2_trans_commit_run_triggers(struct btree_trans *trans) -{ - unsigned btree_id = 0, btree_id_updates_start = 0; - int ret = 0; - - /* - * - * For a given btree, this algorithm runs insert triggers before - * overwrite triggers: this is so that when extents are being moved - * (e.g. by FALLOCATE_FL_INSERT_RANGE), we don't drop references before - * they are re-added. - */ - for (btree_id = 0; btree_id < BTREE_ID_NR; btree_id++) { - if (btree_id == BTREE_ID_alloc) - continue; - - ret = run_btree_triggers(trans, btree_id, &btree_id_updates_start); - if (ret) - return ret; + sort_id_start = i; } - btree_id_updates_start = 0; - ret = run_btree_triggers(trans, BTREE_ID_alloc, &btree_id_updates_start); - if (ret) - return ret; - #ifdef CONFIG_BCACHEFS_DEBUG trans_for_each_update(trans, i) BUG_ON(!(i->flags & BTREE_TRIGGER_norun) && @@ -903,18 +881,7 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags, struct bch_fs *c = trans->c; enum bch_watermark watermark = flags & BCH_WATERMARK_MASK; - switch (ret) { - case -BCH_ERR_btree_insert_btree_node_full: - ret = bch2_btree_split_leaf(trans, i->path, flags); - if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) - trace_and_count(c, trans_restart_btree_node_split, trans, - trace_ip, trans->paths + i->path); - break; - case -BCH_ERR_btree_insert_need_mark_replicas: - ret = drop_locks_do(trans, - bch2_accounting_update_sb(trans)); - break; - case -BCH_ERR_journal_res_get_blocked: + if (bch2_err_matches(ret, BCH_ERR_journal_res_blocked)) { /* * XXX: this should probably be a separate BTREE_INSERT_NONBLOCK * flag @@ -922,13 +889,26 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags, if ((flags & BCH_TRANS_COMMIT_journal_reclaim) && watermark < BCH_WATERMARK_reclaim) { ret = -BCH_ERR_journal_reclaim_would_deadlock; - break; + goto out; } ret = drop_locks_do(trans, bch2_trans_journal_res_get(trans, (flags & BCH_WATERMARK_MASK)| JOURNAL_RES_GET_CHECK)); + goto out; + } + + switch (ret) { + case -BCH_ERR_btree_insert_btree_node_full: + ret = bch2_btree_split_leaf(trans, i->path, flags); + if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) + trace_and_count(c, trans_restart_btree_node_split, trans, + trace_ip, trans->paths + i->path); + break; + case -BCH_ERR_btree_insert_need_mark_replicas: + ret = drop_locks_do(trans, + bch2_accounting_update_sb(trans)); break; case -BCH_ERR_btree_insert_need_journal_reclaim: bch2_trans_unlock(trans); @@ -950,7 +930,7 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags, BUG_ON(ret >= 0); break; } - +out: BUG_ON(bch2_err_matches(ret, BCH_ERR_transaction_restart) != !!trans->restarted); bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOSPC) && |