From patchwork Fri Dec 28 00:24:47 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Florian Westphal X-Patchwork-Id: 1019030 X-Patchwork-Delegate: pablo@netfilter.org Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netfilter-devel-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=none (p=none dis=none) header.from=strlen.de Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43Qnjd3HGZz9s2P for ; Fri, 28 Dec 2018 11:32:53 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1730398AbeL1Acx (ORCPT ); Thu, 27 Dec 2018 19:32:53 -0500 Received: from Chamillionaire.breakpoint.cc ([146.0.238.67]:34936 "EHLO Chamillionaire.breakpoint.cc" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726868AbeL1Acw (ORCPT ); Thu, 27 Dec 2018 19:32:52 -0500 Received: from fw by Chamillionaire.breakpoint.cc with local (Exim 4.89) (envelope-from ) id 1gcg53-0001TL-K5; Fri, 28 Dec 2018 01:32:49 +0100 From: Florian Westphal To: Cc: sbohrer@cloudflare.com, Pablo Neira Ayuso , Florian Westphal Subject: [PATCH nf 6/8] netfilter: nf_conncount: move all list iterations under spinlock Date: Fri, 28 Dec 2018 01:24:47 +0100 Message-Id: <20181228002450.18611-7-fw@strlen.de> X-Mailer: git-send-email 2.19.2 In-Reply-To: <20181228002450.18611-1-fw@strlen.de> References: <20181228002450.18611-1-fw@strlen.de> MIME-Version: 1.0 Sender: netfilter-devel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Pablo Neira Ayuso Two CPUs may race to remove a connection from the list, the existing conn->dead will result in a use-after-free. Use the per-list spinlock to protect list iterations. As all accesses to the list now happen while holding the per-list lock, we no longer need to delay free operations with rcu. Joint work with Florian. Fixes: 5c789e131cbb9 ("netfilter: nf_conncount: Add list lock and gc worker, and RCU for init tree search") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conncount.c | 46 ++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 26 deletions(-) diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index ce7f7d1212a6..d0fd195b19a8 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -43,8 +43,6 @@ struct nf_conncount_tuple { struct nf_conntrack_zone zone; int cpu; u32 jiffies32; - bool dead; - struct rcu_head rcu_head; }; struct nf_conncount_rb { @@ -83,36 +81,21 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen) return memcmp(a, b, klen * sizeof(u32)); } -static void __conn_free(struct rcu_head *h) -{ - struct nf_conncount_tuple *conn; - - conn = container_of(h, struct nf_conncount_tuple, rcu_head); - kmem_cache_free(conncount_conn_cachep, conn); -} - static bool conn_free(struct nf_conncount_list *list, struct nf_conncount_tuple *conn) { bool free_entry = false; - spin_lock_bh(&list->list_lock); - - if (conn->dead) { - spin_unlock_bh(&list->list_lock); - return free_entry; - } + lockdep_assert_held(&list->list_lock); list->count--; - conn->dead = true; - list_del_rcu(&conn->node); + list_del(&conn->node); if (list->count == 0) { list->dead = true; free_entry = true; } - spin_unlock_bh(&list->list_lock); - call_rcu(&conn->rcu_head, __conn_free); + kmem_cache_free(conncount_conn_cachep, conn); return free_entry; } @@ -242,7 +225,7 @@ void nf_conncount_list_init(struct nf_conncount_list *list) } EXPORT_SYMBOL_GPL(nf_conncount_list_init); -/* Return true if the list is empty */ +/* Return true if the list is empty. Must be called with BH disabled. */ bool nf_conncount_gc_list(struct net *net, struct nf_conncount_list *list) { @@ -253,12 +236,18 @@ bool nf_conncount_gc_list(struct net *net, bool free_entry = false; bool ret = false; + /* don't bother if other cpu is already doing GC */ + if (!spin_trylock(&list->list_lock)) + return false; + list_for_each_entry_safe(conn, conn_n, &list->head, node) { found = find_or_evict(net, list, conn, &free_entry); if (IS_ERR(found)) { if (PTR_ERR(found) == -ENOENT) { - if (free_entry) + if (free_entry) { + spin_unlock(&list->list_lock); return true; + } collected++; } continue; @@ -271,23 +260,24 @@ bool nf_conncount_gc_list(struct net *net, * closed already -> ditch it */ nf_ct_put(found_ct); - if (conn_free(list, conn)) + if (conn_free(list, conn)) { + spin_unlock(&list->list_lock); return true; + } collected++; continue; } nf_ct_put(found_ct); if (collected > CONNCOUNT_GC_MAX_NODES) - return false; + break; } - spin_lock_bh(&list->list_lock); if (!list->count) { list->dead = true; ret = true; } - spin_unlock_bh(&list->list_lock); + spin_unlock(&list->list_lock); return ret; } @@ -478,6 +468,7 @@ static void tree_gc_worker(struct work_struct *work) tree = data->gc_tree % CONNCOUNT_SLOTS; root = &data->root[tree]; + local_bh_disable(); rcu_read_lock(); for (node = rb_first(root); node != NULL; node = rb_next(node)) { rbconn = rb_entry(node, struct nf_conncount_rb, node); @@ -485,6 +476,9 @@ static void tree_gc_worker(struct work_struct *work) gc_count++; } rcu_read_unlock(); + local_bh_enable(); + + cond_resched(); spin_lock_bh(&nf_conncount_locks[tree]); if (gc_count < ARRAY_SIZE(gc_nodes))