From patchwork Wed Apr 29 02:29:08 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Qu Wenruo X-Patchwork-Id: 6293561 Return-Path: X-Original-To: patchwork-linux-btrfs@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork2.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork2.web.kernel.org (Postfix) with ESMTP id 36EA6BEEE1 for ; Wed, 29 Apr 2015 02:32:13 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id A97DB202FE for ; Wed, 29 Apr 2015 02:32:10 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 2A26720320 for ; Wed, 29 Apr 2015 02:32:08 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1031579AbbD2Cb6 (ORCPT ); Tue, 28 Apr 2015 22:31:58 -0400 Received: from cn.fujitsu.com ([59.151.112.132]:15215 "EHLO heian.cn.fujitsu.com" rhost-flags-OK-FAIL-OK-FAIL) by vger.kernel.org with ESMTP id S1031478AbbD2Cbc (ORCPT ); Tue, 28 Apr 2015 22:31:32 -0400 X-IronPort-AV: E=Sophos;i="5.04,848,1406563200"; d="scan'208";a="91395657" Received: from unknown (HELO edo.cn.fujitsu.com) ([10.167.33.5]) by heian.cn.fujitsu.com with ESMTP; 29 Apr 2015 10:27:38 +0800 Received: from G08CNEXCHPEKD02.g08.fujitsu.local (localhost.localdomain [127.0.0.1]) by edo.cn.fujitsu.com (8.14.3/8.13.1) with ESMTP id t3T2UF4p018353 for ; Wed, 29 Apr 2015 10:30:15 +0800 Received: from localhost.localdomain (10.167.226.33) by G08CNEXCHPEKD02.g08.fujitsu.local (10.167.33.89) with Microsoft SMTP Server (TLS) id 14.3.181.6; Wed, 29 Apr 2015 10:31:34 +0800 From: Qu Wenruo To: Subject: [PATCH v2 15/18] btrfs: qgroup: Cleanup the old ref_node-oriented mechanism. Date: Wed, 29 Apr 2015 10:29:08 +0800 Message-ID: <1430274551-9277-16-git-send-email-quwenruo@cn.fujitsu.com> X-Mailer: git-send-email 2.3.6 In-Reply-To: <1430274551-9277-1-git-send-email-quwenruo@cn.fujitsu.com> References: <1430274551-9277-1-git-send-email-quwenruo@cn.fujitsu.com> MIME-Version: 1.0 X-Originating-IP: [10.167.226.33] Sender: linux-btrfs-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-btrfs@vger.kernel.org X-Spam-Status: No, score=-6.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, T_RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=ham version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Goodbye, the old mechanisim. Signed-off-by: Qu Wenruo --- v2: None --- fs/btrfs/ctree.h | 2 +- fs/btrfs/extent-tree.c | 5 - fs/btrfs/qgroup.c | 905 +------------------------------------------ fs/btrfs/qgroup.h | 49 --- include/trace/events/btrfs.h | 55 --- 5 files changed, 3 insertions(+), 1013 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f9c89ca..be6f9ce 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1703,7 +1703,7 @@ struct btrfs_fs_info { /* list of dirty qgroups to be written at next commit */ struct list_head dirty_qgroups; - /* used by btrfs_qgroup_record_ref for an efficient tree traversal */ + /* used by qgroup for an efficient tree traversal */ u64 qgroup_seq; /* qgroup rescan items */ diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 70723dc..265c36b 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1981,7 +1981,6 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, u64 refs; int ret; int no_quota = node->no_quota; - enum btrfs_qgroup_operation_type type = BTRFS_QGROUP_OPER_ADD_EXCL; path = btrfs_alloc_path(); if (!path) @@ -2009,8 +2008,6 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); refs = btrfs_extent_refs(leaf, item); - if (refs) - type = BTRFS_QGROUP_OPER_ADD_SHARED; btrfs_set_extent_refs(leaf, item, refs + refs_to_add); if (extent_op) __run_delayed_extent_op(extent_op, leaf, item); @@ -5799,7 +5796,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, u64 bytenr = node->bytenr; u64 num_bytes = node->num_bytes; int last_ref = 0; - enum btrfs_qgroup_operation_type type = BTRFS_QGROUP_OPER_SUB_EXCL; bool skinny_metadata = btrfs_fs_incompat(root->fs_info, SKINNY_METADATA); @@ -5980,7 +5976,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, refs -= refs_to_drop; if (refs > 0) { - type = BTRFS_QGROUP_OPER_SUB_SHARED; if (extent_op) __run_delayed_extent_op(extent_op, leaf, ei); /* diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 2e86bea..c2f1273 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -34,6 +34,7 @@ #include "extent_io.h" #include "qgroup.h" + /* TODO XXX FIXME * - subvol delete -> delete when ref goes to 0? delete limits also? * - reorganize keys @@ -1237,172 +1238,6 @@ out: return ret; } -static int comp_oper_exist(struct btrfs_qgroup_operation *oper1, - struct btrfs_qgroup_operation *oper2) -{ - /* - * Ignore seq and type here, we're looking for any operation - * at all related to this extent on that root. - */ - if (oper1->bytenr < oper2->bytenr) - return -1; - if (oper1->bytenr > oper2->bytenr) - return 1; - if (oper1->ref_root < oper2->ref_root) - return -1; - if (oper1->ref_root > oper2->ref_root) - return 1; - return 0; -} - -static int qgroup_oper_exists(struct btrfs_fs_info *fs_info, - struct btrfs_qgroup_operation *oper) -{ - struct rb_node *n; - struct btrfs_qgroup_operation *cur; - int cmp; - - spin_lock(&fs_info->qgroup_op_lock); - n = fs_info->qgroup_op_tree.rb_node; - while (n) { - cur = rb_entry(n, struct btrfs_qgroup_operation, n); - cmp = comp_oper_exist(cur, oper); - if (cmp < 0) { - n = n->rb_right; - } else if (cmp) { - n = n->rb_left; - } else { - spin_unlock(&fs_info->qgroup_op_lock); - return -EEXIST; - } - } - spin_unlock(&fs_info->qgroup_op_lock); - return 0; -} - -static int comp_oper(struct btrfs_qgroup_operation *oper1, - struct btrfs_qgroup_operation *oper2) -{ - if (oper1->bytenr < oper2->bytenr) - return -1; - if (oper1->bytenr > oper2->bytenr) - return 1; - if (oper1->seq < oper2->seq) - return -1; - if (oper1->seq > oper2->seq) - return 1; - if (oper1->ref_root < oper2->ref_root) - return -1; - if (oper1->ref_root > oper2->ref_root) - return 1; - if (oper1->type < oper2->type) - return -1; - if (oper1->type > oper2->type) - return 1; - return 0; -} - -static int insert_qgroup_oper(struct btrfs_fs_info *fs_info, - struct btrfs_qgroup_operation *oper) -{ - struct rb_node **p; - struct rb_node *parent = NULL; - struct btrfs_qgroup_operation *cur; - int cmp; - - spin_lock(&fs_info->qgroup_op_lock); - p = &fs_info->qgroup_op_tree.rb_node; - while (*p) { - parent = *p; - cur = rb_entry(parent, struct btrfs_qgroup_operation, n); - cmp = comp_oper(cur, oper); - if (cmp < 0) { - p = &(*p)->rb_right; - } else if (cmp) { - p = &(*p)->rb_left; - } else { - spin_unlock(&fs_info->qgroup_op_lock); - return -EEXIST; - } - } - rb_link_node(&oper->n, parent, p); - rb_insert_color(&oper->n, &fs_info->qgroup_op_tree); - spin_unlock(&fs_info->qgroup_op_lock); - return 0; -} - -/* - * Record a quota operation for processing later on. - * @trans: the transaction we are adding the delayed op to. - * @fs_info: the fs_info for this fs. - * @ref_root: the root of the reference we are acting on, - * @bytenr: the bytenr we are acting on. - * @num_bytes: the number of bytes in the reference. - * @type: the type of operation this is. - * @mod_seq: do we need to get a sequence number for looking up roots. - * - * We just add it to our trans qgroup_ref_list and carry on and process these - * operations in order at some later point. If the reference root isn't a fs - * root then we don't bother with doing anything. - * - * MUST BE HOLDING THE REF LOCK. - */ -int btrfs_qgroup_record_ref(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 ref_root, - u64 bytenr, u64 num_bytes, - enum btrfs_qgroup_operation_type type, int mod_seq) -{ - struct btrfs_qgroup_operation *oper; - int ret; - - if (!is_fstree(ref_root) || !fs_info->quota_enabled) - return 0; - - oper = kmalloc(sizeof(*oper), GFP_NOFS); - if (!oper) - return -ENOMEM; - - oper->ref_root = ref_root; - oper->bytenr = bytenr; - oper->num_bytes = num_bytes; - oper->type = type; - oper->seq = atomic_inc_return(&fs_info->qgroup_op_seq); - INIT_LIST_HEAD(&oper->elem.list); - oper->elem.seq = 0; - - trace_btrfs_qgroup_record_ref(oper); - - if (type == BTRFS_QGROUP_OPER_SUB_SUBTREE) { - /* - * If any operation for this bytenr/ref_root combo - * exists, then we know it's not exclusively owned and - * shouldn't be queued up. - * - * This also catches the case where we have a cloned - * extent that gets queued up multiple times during - * drop snapshot. - */ - if (qgroup_oper_exists(fs_info, oper)) { - kfree(oper); - return 0; - } - } - - ret = insert_qgroup_oper(fs_info, oper); - if (ret) { - /* Shouldn't happen so have an assert for developers */ - ASSERT(0); - kfree(oper); - return ret; - } - list_add_tail(&oper->list, &trans->qgroup_ref_list); - - if (mod_seq) - btrfs_get_tree_mod_seq(fs_info, &oper->elem); - - return 0; -} - int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { @@ -1456,305 +1291,6 @@ struct btrfs_qgroup_extent_record return NULL; } -/* - * The easy accounting, if we are adding/removing the only ref for an extent - * then this qgroup and all of the parent qgroups get their refrence and - * exclusive counts adjusted. - */ -static int qgroup_excl_accounting(struct btrfs_fs_info *fs_info, - struct btrfs_qgroup_operation *oper) -{ - struct btrfs_qgroup *qgroup; - struct ulist *tmp; - struct btrfs_qgroup_list *glist; - struct ulist_node *unode; - struct ulist_iterator uiter; - int sign = 0; - int ret = 0; - - tmp = ulist_alloc(GFP_NOFS); - if (!tmp) - return -ENOMEM; - - spin_lock(&fs_info->qgroup_lock); - if (!fs_info->quota_root) - goto out; - qgroup = find_qgroup_rb(fs_info, oper->ref_root); - if (!qgroup) - goto out; - switch (oper->type) { - case BTRFS_QGROUP_OPER_ADD_EXCL: - sign = 1; - break; - case BTRFS_QGROUP_OPER_SUB_EXCL: - sign = -1; - break; - default: - ASSERT(0); - } - qgroup->rfer += sign * oper->num_bytes; - qgroup->rfer_cmpr += sign * oper->num_bytes; - - WARN_ON(sign < 0 && qgroup->excl < oper->num_bytes); - qgroup->excl += sign * oper->num_bytes; - qgroup->excl_cmpr += sign * oper->num_bytes; - - qgroup_dirty(fs_info, qgroup); - - /* Get all of the parent groups that contain this qgroup */ - list_for_each_entry(glist, &qgroup->groups, next_group) { - ret = ulist_add(tmp, glist->group->qgroupid, - ptr_to_u64(glist->group), GFP_ATOMIC); - if (ret < 0) - goto out; - } - - /* Iterate all of the parents and adjust their reference counts */ - ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(tmp, &uiter))) { - qgroup = u64_to_ptr(unode->aux); - qgroup->rfer += sign * oper->num_bytes; - qgroup->rfer_cmpr += sign * oper->num_bytes; - WARN_ON(sign < 0 && qgroup->excl < oper->num_bytes); - qgroup->excl += sign * oper->num_bytes; - qgroup->excl_cmpr += sign * oper->num_bytes; - qgroup_dirty(fs_info, qgroup); - - /* Add any parents of the parents */ - list_for_each_entry(glist, &qgroup->groups, next_group) { - ret = ulist_add(tmp, glist->group->qgroupid, - ptr_to_u64(glist->group), GFP_ATOMIC); - if (ret < 0) - goto out; - } - } - ret = 0; -out: - spin_unlock(&fs_info->qgroup_lock); - ulist_free(tmp); - return ret; -} - -/* - * Walk all of the roots that pointed to our bytenr and adjust their refcnts as - * properly. - */ -static int qgroup_calc_old_refcnt(struct btrfs_fs_info *fs_info, - u64 root_to_skip, struct ulist *tmp, - struct ulist *roots, struct ulist *qgroups, - u64 seq, int *old_roots, int rescan) -{ - struct ulist_node *unode; - struct ulist_iterator uiter; - struct ulist_node *tmp_unode; - struct ulist_iterator tmp_uiter; - struct btrfs_qgroup *qg; - int ret; - - ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(roots, &uiter))) { - /* We don't count our current root here */ - if (unode->val == root_to_skip) - continue; - qg = find_qgroup_rb(fs_info, unode->val); - if (!qg) - continue; - /* - * We could have a pending removal of this same ref so we may - * not have actually found our ref root when doing - * btrfs_find_all_roots, so we need to keep track of how many - * old roots we find in case we removed ours and added a - * different one at the same time. I don't think this could - * happen in practice but that sort of thinking leads to pain - * and suffering and to the dark side. - */ - (*old_roots)++; - - ulist_reinit(tmp); - ret = ulist_add(qgroups, qg->qgroupid, ptr_to_u64(qg), - GFP_ATOMIC); - if (ret < 0) - return ret; - ret = ulist_add(tmp, qg->qgroupid, ptr_to_u64(qg), GFP_ATOMIC); - if (ret < 0) - return ret; - ULIST_ITER_INIT(&tmp_uiter); - while ((tmp_unode = ulist_next(tmp, &tmp_uiter))) { - struct btrfs_qgroup_list *glist; - int mod; - - qg = u64_to_ptr(tmp_unode->aux); - /* - * We use this sequence number to keep from having to - * run the whole list and 0 out the refcnt every time. - * We basically use sequnce as the known 0 count and - * then add 1 everytime we see a qgroup. This is how we - * get how many of the roots actually point up to the - * upper level qgroups in order to determine exclusive - * counts. - * - * For rescan none of the extent is recorded before so - * we just don't add old_refcnt. - */ - if (rescan) - mod = 0; - else - mod = 1; - btrfs_qgroup_update_old_refcnt(qg, seq, mod); - btrfs_qgroup_update_new_refcnt(qg, seq, 1); - list_for_each_entry(glist, &qg->groups, next_group) { - ret = ulist_add(qgroups, glist->group->qgroupid, - ptr_to_u64(glist->group), - GFP_ATOMIC); - if (ret < 0) - return ret; - ret = ulist_add(tmp, glist->group->qgroupid, - ptr_to_u64(glist->group), - GFP_ATOMIC); - if (ret < 0) - return ret; - } - } - } - return 0; -} - -/* - * We need to walk forward in our operation tree and account for any roots that - * were deleted after we made this operation. - */ -static int qgroup_account_deleted_refs(struct btrfs_fs_info *fs_info, - struct btrfs_qgroup_operation *oper, - struct ulist *tmp, - struct ulist *qgroups, u64 seq, - int *old_roots) -{ - struct ulist_node *unode; - struct ulist_iterator uiter; - struct btrfs_qgroup *qg; - struct btrfs_qgroup_operation *tmp_oper; - struct rb_node *n; - int ret; - - ulist_reinit(tmp); - - /* - * We only walk forward in the tree since we're only interested in - * removals that happened _after_ our operation. - */ - spin_lock(&fs_info->qgroup_op_lock); - n = rb_next(&oper->n); - spin_unlock(&fs_info->qgroup_op_lock); - if (!n) - return 0; - tmp_oper = rb_entry(n, struct btrfs_qgroup_operation, n); - while (tmp_oper->bytenr == oper->bytenr) { - /* - * If it's not a removal we don't care, additions work out - * properly with our refcnt tracking. - */ - if (tmp_oper->type != BTRFS_QGROUP_OPER_SUB_SHARED && - tmp_oper->type != BTRFS_QGROUP_OPER_SUB_EXCL) - goto next; - qg = find_qgroup_rb(fs_info, tmp_oper->ref_root); - if (!qg) - goto next; - ret = ulist_add(qgroups, qg->qgroupid, ptr_to_u64(qg), - GFP_ATOMIC); - if (ret) { - if (ret < 0) - return ret; - /* - * We only want to increase old_roots if this qgroup is - * not already in the list of qgroups. If it is already - * there then that means it must have been re-added or - * the delete will be discarded because we had an - * existing ref that we haven't looked up yet. In this - * case we don't want to increase old_roots. So if ret - * == 1 then we know that this is the first time we've - * seen this qgroup and we can bump the old_roots. - */ - (*old_roots)++; - ret = ulist_add(tmp, qg->qgroupid, ptr_to_u64(qg), - GFP_ATOMIC); - if (ret < 0) - return ret; - } -next: - spin_lock(&fs_info->qgroup_op_lock); - n = rb_next(&tmp_oper->n); - spin_unlock(&fs_info->qgroup_op_lock); - if (!n) - break; - tmp_oper = rb_entry(n, struct btrfs_qgroup_operation, n); - } - - /* Ok now process the qgroups we found */ - ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(tmp, &uiter))) { - struct btrfs_qgroup_list *glist; - - qg = u64_to_ptr(unode->aux); - btrfs_qgroup_update_old_refcnt(qg, seq, 1); - btrfs_qgroup_update_new_refcnt(qg, seq, 1); - list_for_each_entry(glist, &qg->groups, next_group) { - ret = ulist_add(qgroups, glist->group->qgroupid, - ptr_to_u64(glist->group), GFP_ATOMIC); - if (ret < 0) - return ret; - ret = ulist_add(tmp, glist->group->qgroupid, - ptr_to_u64(glist->group), GFP_ATOMIC); - if (ret < 0) - return ret; - } - } - return 0; -} - -/* Add refcnt for the newly added reference. */ -static int qgroup_calc_new_refcnt(struct btrfs_fs_info *fs_info, - struct btrfs_qgroup_operation *oper, - struct btrfs_qgroup *qgroup, - struct ulist *tmp, struct ulist *qgroups, - u64 seq) -{ - struct ulist_node *unode; - struct ulist_iterator uiter; - struct btrfs_qgroup *qg; - int ret; - - ulist_reinit(tmp); - ret = ulist_add(qgroups, qgroup->qgroupid, ptr_to_u64(qgroup), - GFP_ATOMIC); - if (ret < 0) - return ret; - ret = ulist_add(tmp, qgroup->qgroupid, ptr_to_u64(qgroup), - GFP_ATOMIC); - if (ret < 0) - return ret; - ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(tmp, &uiter))) { - struct btrfs_qgroup_list *glist; - - qg = u64_to_ptr(unode->aux); - if (oper->type == BTRFS_QGROUP_OPER_ADD_SHARED) - btrfs_qgroup_update_new_refcnt(qg, seq, 1); - else - btrfs_qgroup_update_old_refcnt(qg, seq, 1); - list_for_each_entry(glist, &qg->groups, next_group) { - ret = ulist_add(tmp, glist->group->qgroupid, - ptr_to_u64(glist->group), GFP_ATOMIC); - if (ret < 0) - return ret; - ret = ulist_add(qgroups, glist->group->qgroupid, - ptr_to_u64(glist->group), GFP_ATOMIC); - if (ret < 0) - return ret; - } - } - return 0; -} - #define UPDATE_NEW 0 #define UPDATE_OLD 1 /* @@ -1816,6 +1352,7 @@ static int qgroup_update_refcnt(struct btrfs_fs_info *fs_info, /* * Update qgroup rfer/excl counters. * Rfer update is easy, codes can explain themselves. + * * Excl update is tricky, the update is split into 2 part. * Part 1: Possible exclusive <-> sharing detect: * | A | !A | @@ -1933,419 +1470,6 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info, return 0; } -/* - * This adjusts the counters for all referenced qgroups if need be. - */ -static int qgroup_adjust_counters(struct btrfs_fs_info *fs_info, - u64 root_to_skip, u64 num_bytes, - struct ulist *qgroups, u64 seq, - int old_roots, int new_roots, int rescan) -{ - struct ulist_node *unode; - struct ulist_iterator uiter; - struct btrfs_qgroup *qg; - u64 cur_new_count, cur_old_count; - - ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(qgroups, &uiter))) { - bool dirty = false; - - qg = u64_to_ptr(unode->aux); - cur_old_count = btrfs_qgroup_get_old_refcnt(qg, seq); - cur_new_count = btrfs_qgroup_get_new_refcnt(qg, seq); - - /* - * Wasn't referenced before but is now, add to the reference - * counters. - */ - if (cur_old_count == 0 && cur_new_count > 0) { - qg->rfer += num_bytes; - qg->rfer_cmpr += num_bytes; - dirty = true; - } - - /* - * Was referenced before but isn't now, subtract from the - * reference counters. - */ - if (cur_old_count > 0 && cur_new_count == 0) { - qg->rfer -= num_bytes; - qg->rfer_cmpr -= num_bytes; - dirty = true; - } - - /* - * If our refcount was the same as the roots previously but our - * new count isn't the same as the number of roots now then we - * went from having a exclusive reference on this range to not. - */ - if (old_roots && cur_old_count == old_roots && - (cur_new_count != new_roots || new_roots == 0)) { - WARN_ON(cur_new_count != new_roots && new_roots == 0); - qg->excl -= num_bytes; - qg->excl_cmpr -= num_bytes; - dirty = true; - } - - /* - * If we didn't reference all the roots before but now we do we - * have an exclusive reference to this range. - */ - if ((!old_roots || (old_roots && cur_old_count != old_roots)) - && cur_new_count == new_roots) { - qg->excl += num_bytes; - qg->excl_cmpr += num_bytes; - dirty = true; - } - - if (dirty) - qgroup_dirty(fs_info, qg); - } - return 0; -} - -/* - * If we removed a data extent and there were other references for that bytenr - * then we need to lookup all referenced roots to make sure we still don't - * reference this bytenr. If we do then we can just discard this operation. - */ -static int check_existing_refs(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, - struct btrfs_qgroup_operation *oper) -{ - struct ulist *roots = NULL; - struct ulist_node *unode; - struct ulist_iterator uiter; - int ret = 0; - - ret = btrfs_find_all_roots(trans, fs_info, oper->bytenr, - oper->elem.seq, &roots); - if (ret < 0) - return ret; - ret = 0; - - ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(roots, &uiter))) { - if (unode->val == oper->ref_root) { - ret = 1; - break; - } - } - ulist_free(roots); - btrfs_put_tree_mod_seq(fs_info, &oper->elem); - - return ret; -} - -/* - * If we share a reference across multiple roots then we may need to adjust - * various qgroups referenced and exclusive counters. The basic premise is this - * - * 1) We have seq to represent a 0 count. Instead of looping through all of the - * qgroups and resetting their refcount to 0 we just constantly bump this - * sequence number to act as the base reference count. This means that if - * anybody is equal to or below this sequence they were never referenced. We - * jack this sequence up by the number of roots we found each time in order to - * make sure we don't have any overlap. - * - * 2) We first search all the roots that reference the area _except_ the root - * we're acting on currently. This makes up the old_refcnt of all the qgroups - * before. - * - * 3) We walk all of the qgroups referenced by the root we are currently acting - * on, and will either adjust old_refcnt in the case of a removal or the - * new_refcnt in the case of an addition. - * - * 4) Finally we walk all the qgroups that are referenced by this range - * including the root we are acting on currently. We will adjust the counters - * based on the number of roots we had and will have after this operation. - * - * Take this example as an illustration - * - * [qgroup 1/0] - * / | \ - * [qg 0/0] [qg 0/1] [qg 0/2] - * \ | / - * [ extent ] - * - * Say we are adding a reference that is covered by qg 0/0. The first step - * would give a refcnt of 1 to qg 0/1 and 0/2 and a refcnt of 2 to qg 1/0 with - * old_roots being 2. Because it is adding new_roots will be 1. We then go - * through qg 0/0 which will get the new_refcnt set to 1 and add 1 to qg 1/0's - * new_refcnt, bringing it to 3. We then walk through all of the qgroups, we - * notice that the old refcnt for qg 0/0 < the new refcnt, so we added a - * reference and thus must add the size to the referenced bytes. Everything - * else is the same so nothing else changes. - */ -static int qgroup_shared_accounting(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, - struct btrfs_qgroup_operation *oper) -{ - struct ulist *roots = NULL; - struct ulist *qgroups, *tmp; - struct btrfs_qgroup *qgroup; - struct seq_list elem = {}; - u64 seq; - int old_roots = 0; - int new_roots = 0; - int ret = 0; - - if (oper->elem.seq) { - ret = check_existing_refs(trans, fs_info, oper); - if (ret < 0) - return ret; - if (ret) - return 0; - } - - qgroups = ulist_alloc(GFP_NOFS); - if (!qgroups) - return -ENOMEM; - - tmp = ulist_alloc(GFP_NOFS); - if (!tmp) { - ulist_free(qgroups); - return -ENOMEM; - } - - btrfs_get_tree_mod_seq(fs_info, &elem); - ret = btrfs_find_all_roots(trans, fs_info, oper->bytenr, elem.seq, - &roots); - btrfs_put_tree_mod_seq(fs_info, &elem); - if (ret < 0) { - ulist_free(qgroups); - ulist_free(tmp); - return ret; - } - spin_lock(&fs_info->qgroup_lock); - qgroup = find_qgroup_rb(fs_info, oper->ref_root); - if (!qgroup) - goto out; - seq = fs_info->qgroup_seq; - - /* - * So roots is the list of all the roots currently pointing at the - * bytenr, including the ref we are adding if we are adding, or not if - * we are removing a ref. So we pass in the ref_root to skip that root - * in our calculations. We set old_refnct and new_refcnt cause who the - * hell knows what everything looked like before, and it doesn't matter - * except... - */ - ret = qgroup_calc_old_refcnt(fs_info, oper->ref_root, tmp, roots, qgroups, - seq, &old_roots, 0); - if (ret < 0) - goto out; - - /* - * Now adjust the refcounts of the qgroups that care about this - * reference, either the old_count in the case of removal or new_count - * in the case of an addition. - */ - ret = qgroup_calc_new_refcnt(fs_info, oper, qgroup, tmp, qgroups, - seq); - if (ret < 0) - goto out; - - /* - * ...in the case of removals. If we had a removal before we got around - * to processing this operation then we need to find that guy and count - * his references as if they really existed so we don't end up screwing - * up the exclusive counts. Then whenever we go to process the delete - * everything will be grand and we can account for whatever exclusive - * changes need to be made there. We also have to pass in old_roots so - * we have an accurate count of the roots as it pertains to this - * operations view of the world. - */ - ret = qgroup_account_deleted_refs(fs_info, oper, tmp, qgroups, seq, - &old_roots); - if (ret < 0) - goto out; - - /* - * We are adding our root, need to adjust up the number of roots, - * otherwise old_roots is the number of roots we want. - */ - if (oper->type == BTRFS_QGROUP_OPER_ADD_SHARED) { - new_roots = old_roots + 1; - } else { - new_roots = old_roots; - old_roots++; - } - - /* - * Bump qgroup_seq to avoid seq overlap - * XXX: This makes qgroup_seq mismatch with oper->seq. - */ - fs_info->qgroup_seq += old_roots + 1; - - - /* - * And now the magic happens, bless Arne for having a pretty elegant - * solution for this. - */ - qgroup_adjust_counters(fs_info, oper->ref_root, oper->num_bytes, - qgroups, seq, old_roots, new_roots, 0); -out: - spin_unlock(&fs_info->qgroup_lock); - ulist_free(qgroups); - ulist_free(roots); - ulist_free(tmp); - return ret; -} - -/* - * Process a reference to a shared subtree. This type of operation is - * queued during snapshot removal when we encounter extents which are - * shared between more than one root. - */ -static int qgroup_subtree_accounting(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, - struct btrfs_qgroup_operation *oper) -{ - struct ulist *roots = NULL; - struct ulist_node *unode; - struct ulist_iterator uiter; - struct btrfs_qgroup_list *glist; - struct ulist *parents; - int ret = 0; - int err; - struct btrfs_qgroup *qg; - u64 root_obj = 0; - struct seq_list elem = {}; - - parents = ulist_alloc(GFP_NOFS); - if (!parents) - return -ENOMEM; - - btrfs_get_tree_mod_seq(fs_info, &elem); - ret = btrfs_find_all_roots(trans, fs_info, oper->bytenr, - elem.seq, &roots); - btrfs_put_tree_mod_seq(fs_info, &elem); - if (ret < 0) - goto out; - - if (roots->nnodes != 1) - goto out; - - ULIST_ITER_INIT(&uiter); - unode = ulist_next(roots, &uiter); /* Only want 1 so no need to loop */ - /* - * If we find our ref root then that means all refs - * this extent has to the root have not yet been - * deleted. In that case, we do nothing and let the - * last ref for this bytenr drive our update. - * - * This can happen for example if an extent is - * referenced multiple times in a snapshot (clone, - * etc). If we are in the middle of snapshot removal, - * queued updates for such an extent will find the - * root if we have not yet finished removing the - * snapshot. - */ - if (unode->val == oper->ref_root) - goto out; - - root_obj = unode->val; - BUG_ON(!root_obj); - - spin_lock(&fs_info->qgroup_lock); - qg = find_qgroup_rb(fs_info, root_obj); - if (!qg) - goto out_unlock; - - qg->excl += oper->num_bytes; - qg->excl_cmpr += oper->num_bytes; - qgroup_dirty(fs_info, qg); - - /* - * Adjust counts for parent groups. First we find all - * parents, then in the 2nd loop we do the adjustment - * while adding parents of the parents to our ulist. - */ - list_for_each_entry(glist, &qg->groups, next_group) { - err = ulist_add(parents, glist->group->qgroupid, - ptr_to_u64(glist->group), GFP_ATOMIC); - if (err < 0) { - ret = err; - goto out_unlock; - } - } - - ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(parents, &uiter))) { - qg = u64_to_ptr(unode->aux); - qg->excl += oper->num_bytes; - qg->excl_cmpr += oper->num_bytes; - qgroup_dirty(fs_info, qg); - - /* Add any parents of the parents */ - list_for_each_entry(glist, &qg->groups, next_group) { - err = ulist_add(parents, glist->group->qgroupid, - ptr_to_u64(glist->group), GFP_ATOMIC); - if (err < 0) { - ret = err; - goto out_unlock; - } - } - } - -out_unlock: - spin_unlock(&fs_info->qgroup_lock); - -out: - ulist_free(roots); - ulist_free(parents); - return ret; -} - -/* - * btrfs_qgroup_account_ref is called for every ref that is added to or deleted - * from the fs. First, all roots referencing the extent are searched, and - * then the space is accounted accordingly to the different roots. The - * accounting algorithm works in 3 steps documented inline. - */ -static int btrfs_qgroup_account(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, - struct btrfs_qgroup_operation *oper) -{ - int ret = 0; - - if (!fs_info->quota_enabled) - return 0; - - BUG_ON(!fs_info->quota_root); - - mutex_lock(&fs_info->qgroup_rescan_lock); - if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) { - if (fs_info->qgroup_rescan_progress.objectid <= oper->bytenr) { - mutex_unlock(&fs_info->qgroup_rescan_lock); - return 0; - } - } - mutex_unlock(&fs_info->qgroup_rescan_lock); - - ASSERT(is_fstree(oper->ref_root)); - - trace_btrfs_qgroup_account(oper); - - switch (oper->type) { - case BTRFS_QGROUP_OPER_ADD_EXCL: - case BTRFS_QGROUP_OPER_SUB_EXCL: - ret = qgroup_excl_accounting(fs_info, oper); - break; - case BTRFS_QGROUP_OPER_ADD_SHARED: - case BTRFS_QGROUP_OPER_SUB_SHARED: - ret = qgroup_shared_accounting(trans, fs_info, oper); - break; - case BTRFS_QGROUP_OPER_SUB_SUBTREE: - ret = qgroup_subtree_accounting(trans, fs_info, oper); - break; - default: - ASSERT(0); - } - return ret; -} - int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, @@ -2463,31 +1587,6 @@ cleanup: } /* - * Needs to be called everytime we run delayed refs, even if there is an error - * in order to cleanup outstanding operations. - */ -int btrfs_delayed_qgroup_accounting(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) -{ - struct btrfs_qgroup_operation *oper; - int ret = 0; - - while (!list_empty(&trans->qgroup_ref_list)) { - oper = list_first_entry(&trans->qgroup_ref_list, - struct btrfs_qgroup_operation, list); - list_del_init(&oper->list); - if (!ret || !trans->aborted) - ret = btrfs_qgroup_account(trans, fs_info, oper); - spin_lock(&fs_info->qgroup_op_lock); - rb_erase(&oper->n, &fs_info->qgroup_op_tree); - spin_unlock(&fs_info->qgroup_op_lock); - btrfs_put_tree_mod_seq(fs_info, &oper->elem); - kfree(oper); - } - return ret; -} - -/* * called from commit_transaction. Writes all changed qgroups to disk. */ int btrfs_run_qgroups(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 80d7df8..236567f 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -23,45 +23,6 @@ #include "delayed-ref.h" /* - * A description of the operations, all of these operations only happen when we - * are adding the 1st reference for that subvolume in the case of adding space - * or on the last reference delete in the case of subtraction. The only - * exception is the last one, which is added for confusion. - * - * BTRFS_QGROUP_OPER_ADD_EXCL: adding bytes where this subvolume is the only - * one pointing at the bytes we are adding. This is called on the first - * allocation. - * - * BTRFS_QGROUP_OPER_ADD_SHARED: adding bytes where this bytenr is going to be - * shared between subvols. This is called on the creation of a ref that already - * has refs from a different subvolume, so basically reflink. - * - * BTRFS_QGROUP_OPER_SUB_EXCL: removing bytes where this subvolume is the only - * one referencing the range. - * - * BTRFS_QGROUP_OPER_SUB_SHARED: removing bytes where this subvolume shares with - * refs with other subvolumes. - */ -enum btrfs_qgroup_operation_type { - BTRFS_QGROUP_OPER_ADD_EXCL, - BTRFS_QGROUP_OPER_ADD_SHARED, - BTRFS_QGROUP_OPER_SUB_EXCL, - BTRFS_QGROUP_OPER_SUB_SHARED, - BTRFS_QGROUP_OPER_SUB_SUBTREE, -}; - -struct btrfs_qgroup_operation { - u64 ref_root; - u64 bytenr; - u64 num_bytes; - u64 seq; - enum btrfs_qgroup_operation_type type; - struct seq_list elem; - struct rb_node n; - struct list_head list; -}; - -/* * Record a dirty extent, and info qgroup to update quota on it * TODO: Use kmem cache to alloc it. */ @@ -94,11 +55,6 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info); void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info); struct btrfs_delayed_extent_op; -int btrfs_qgroup_record_ref(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 ref_root, - u64 bytenr, u64 num_bytes, - enum btrfs_qgroup_operation_type type, - int mod_seq); int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); struct btrfs_qgroup_extent_record @@ -111,11 +67,6 @@ btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, struct ulist *old_roots, struct ulist *new_roots); int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); -int btrfs_delayed_qgroup_accounting(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info); -void btrfs_remove_qgroup_operation(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, - struct btrfs_qgroup_operation *oper); int btrfs_run_qgroups(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 1faecea..c494060 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -1117,61 +1117,6 @@ DEFINE_EVENT(btrfs__workqueue_done, btrfs_workqueue_destroy, TP_ARGS(wq) ); -#define show_oper_type(type) \ - __print_symbolic(type, \ - { BTRFS_QGROUP_OPER_ADD_EXCL, "OPER_ADD_EXCL" }, \ - { BTRFS_QGROUP_OPER_ADD_SHARED, "OPER_ADD_SHARED" }, \ - { BTRFS_QGROUP_OPER_SUB_EXCL, "OPER_SUB_EXCL" }, \ - { BTRFS_QGROUP_OPER_SUB_SHARED, "OPER_SUB_SHARED" }) - -DECLARE_EVENT_CLASS(btrfs_qgroup_oper, - - TP_PROTO(struct btrfs_qgroup_operation *oper), - - TP_ARGS(oper), - - TP_STRUCT__entry( - __field( u64, ref_root ) - __field( u64, bytenr ) - __field( u64, num_bytes ) - __field( u64, seq ) - __field( int, type ) - __field( u64, elem_seq ) - ), - - TP_fast_assign( - __entry->ref_root = oper->ref_root; - __entry->bytenr = oper->bytenr, - __entry->num_bytes = oper->num_bytes; - __entry->seq = oper->seq; - __entry->type = oper->type; - __entry->elem_seq = oper->elem.seq; - ), - - TP_printk("ref_root = %llu, bytenr = %llu, num_bytes = %llu, " - "seq = %llu, elem.seq = %llu, type = %s", - (unsigned long long)__entry->ref_root, - (unsigned long long)__entry->bytenr, - (unsigned long long)__entry->num_bytes, - (unsigned long long)__entry->seq, - (unsigned long long)__entry->elem_seq, - show_oper_type(__entry->type)) -); - -DEFINE_EVENT(btrfs_qgroup_oper, btrfs_qgroup_account, - - TP_PROTO(struct btrfs_qgroup_operation *oper), - - TP_ARGS(oper) -); - -DEFINE_EVENT(btrfs_qgroup_oper, btrfs_qgroup_record_ref, - - TP_PROTO(struct btrfs_qgroup_operation *oper), - - TP_ARGS(oper) -); - #endif /* _TRACE_BTRFS_H */ /* This part must be outside protection */