From patchwork Thu Aug 11 15:20:11 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alexander Mikhalitsyn X-Patchwork-Id: 12941539 X-Patchwork-Delegate: kuba@kernel.org Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id A0E54C19F2A for ; Thu, 11 Aug 2022 15:21:14 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235657AbiHKPVN (ORCPT ); Thu, 11 Aug 2022 11:21:13 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39138 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234338AbiHKPVM (ORCPT ); Thu, 11 Aug 2022 11:21:12 -0400 Received: from relay.virtuozzo.com (relay.virtuozzo.com [130.117.225.111]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 2DACE5A8A5; Thu, 11 Aug 2022 08:21:10 -0700 (PDT) Received: from dev010.ch-qa.sw.ru ([172.29.1.15]) by relay.virtuozzo.com with esmtp (Exim 4.95) (envelope-from ) id 1oM9xk-00FExA-MG; Thu, 11 Aug 2022 17:20:19 +0200 From: Alexander Mikhalitsyn To: netdev@vger.kernel.org Cc: "Denis V. Lunev" , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Daniel Borkmann , David Ahern , Yajun Deng , Roopa Prabhu , Christian Brauner , linux-kernel@vger.kernel.org, Alexey Kuznetsov , Alexander Mikhalitsyn , Konstantin Khorenko , kernel@openvz.org, devel@openvz.org Subject: [PATCH v3 1/2] neigh: fix possible DoS due to net iface start/stop loop Date: Thu, 11 Aug 2022 18:20:11 +0300 Message-Id: <20220811152012.319641-2-alexander.mikhalitsyn@virtuozzo.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220811152012.319641-1-alexander.mikhalitsyn@virtuozzo.com> References: <20220729103559.215140-1-alexander.mikhalitsyn@virtuozzo.com> <20220811152012.319641-1-alexander.mikhalitsyn@virtuozzo.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org From: "Denis V. Lunev" Normal processing of ARP request (usually this is Ethernet broadcast packet) coming to the host is looking like the following: * the packet comes to arp_process() call and is passed through routing procedure * the request is put into the queue using pneigh_enqueue() if corresponding ARP record is not local (common case for container records on the host) * the request is processed by timer (within 80 jiffies by default) and ARP reply is sent from the same arp_process() using NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED condition (flag is set inside pneigh_enqueue()) And here the problem comes. Linux kernel calls pneigh_queue_purge() which destroys the whole queue of ARP requests on ANY network interface start/stop event through __neigh_ifdown(). This is actually not a problem within the original world as network interface start/stop was accessible to the host 'root' only, which could do more destructive things. But the world is changed and there are Linux containers available. Here container 'root' has an access to this API and could be considered as untrusted user in the hosting (container's) world. Thus there is an attack vector to other containers on node when container's root will endlessly start/stop interfaces. We have observed similar situation on a real production node when docker container was doing such activity and thus other containers on the node become not accessible. The patch proposed doing very simple thing. It drops only packets from the same namespace in the pneigh_queue_purge() where network interface state change is detected. This is enough to prevent the problem for the whole node preserving original semantics of the code. v2: - do del_timer_sync() if queue is empty after pneigh_queue_purge() v3: - rebase to net tree Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Daniel Borkmann Cc: David Ahern Cc: Yajun Deng Cc: Roopa Prabhu Cc: Christian Brauner Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Alexey Kuznetsov Cc: Alexander Mikhalitsyn Cc: Konstantin Khorenko Cc: kernel@openvz.org Cc: devel@openvz.org Investigated-by: Alexander Mikhalitsyn Signed-off-by: Denis V. Lunev --- net/core/neighbour.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6a8c2596ebab..0e38a05d5b23 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -307,14 +307,23 @@ static int neigh_del_timer(struct neighbour *n) return 0; } -static void pneigh_queue_purge(struct sk_buff_head *list) +static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) { + unsigned long flags; struct sk_buff *skb; - while ((skb = skb_dequeue(list)) != NULL) { - dev_put(skb->dev); - kfree_skb(skb); + spin_lock_irqsave(&list->lock, flags); + skb = skb_peek(list); + while (skb != NULL) { + struct sk_buff *skb_next = skb_peek_next(skb, list); + if (net == NULL || net_eq(dev_net(skb->dev), net)) { + __skb_unlink(skb, list); + dev_put(skb->dev); + kfree_skb(skb); + } + skb = skb_next; } + spin_unlock_irqrestore(&list->lock, flags); } static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev, @@ -385,9 +394,9 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); - - del_timer_sync(&tbl->proxy_timer); - pneigh_queue_purge(&tbl->proxy_queue); + pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev)); + if (skb_queue_empty_lockless(&tbl->proxy_queue)) + del_timer_sync(&tbl->proxy_timer); return 0; } @@ -1787,7 +1796,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); - pneigh_queue_purge(&tbl->proxy_queue); + pneigh_queue_purge(&tbl->proxy_queue, NULL); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) pr_crit("neighbour leakage\n"); From patchwork Thu Aug 11 15:20:12 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alexander Mikhalitsyn X-Patchwork-Id: 12941540 X-Patchwork-Delegate: kuba@kernel.org Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 73073C3F6B0 for ; Thu, 11 Aug 2022 15:21:15 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235665AbiHKPVO (ORCPT ); Thu, 11 Aug 2022 11:21:14 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39160 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235451AbiHKPVM (ORCPT ); Thu, 11 Aug 2022 11:21:12 -0400 Received: from relay.virtuozzo.com (relay.virtuozzo.com [130.117.225.111]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id D1AA55D0F4; Thu, 11 Aug 2022 08:21:10 -0700 (PDT) Received: from dev010.ch-qa.sw.ru ([172.29.1.15]) by relay.virtuozzo.com with esmtp (Exim 4.95) (envelope-from ) id 1oM9xm-00FExA-CC; Thu, 11 Aug 2022 17:20:21 +0200 From: Alexander Mikhalitsyn To: netdev@vger.kernel.org Cc: Alexander Mikhalitsyn , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Daniel Borkmann , David Ahern , Yajun Deng , Roopa Prabhu , Christian Brauner , linux-kernel@vger.kernel.org, Alexey Kuznetsov , Konstantin Khorenko , kernel@openvz.org, devel@openvz.org, "Denis V . Lunev" Subject: [PATCH v3 2/2] neighbour: make proxy_queue.qlen limit per-device Date: Thu, 11 Aug 2022 18:20:12 +0300 Message-Id: <20220811152012.319641-3-alexander.mikhalitsyn@virtuozzo.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220811152012.319641-1-alexander.mikhalitsyn@virtuozzo.com> References: <20220729103559.215140-1-alexander.mikhalitsyn@virtuozzo.com> <20220811152012.319641-1-alexander.mikhalitsyn@virtuozzo.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org Right now we have a neigh_param PROXY_QLEN which specifies maximum length of neigh_table->proxy_queue. But in fact, this limitation doesn't work well because check condition looks like: tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN) The problem is that p (struct neigh_parms) is a per-device thing, but tbl (struct neigh_table) is a system-wide global thing. It seems reasonable to make proxy_queue limit per-device based. v2: - nothing changed in this patch v3: - rebase to net tree Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Daniel Borkmann Cc: David Ahern Cc: Yajun Deng Cc: Roopa Prabhu Cc: Christian Brauner Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Alexey Kuznetsov Cc: Alexander Mikhalitsyn Cc: Konstantin Khorenko Cc: kernel@openvz.org Cc: devel@openvz.org Suggested-by: Denis V. Lunev Signed-off-by: Alexander Mikhalitsyn Reviewed-by: Denis V. Lunev --- include/net/neighbour.h | 1 + net/core/neighbour.c | 25 ++++++++++++++++++++++--- 2 files changed, 23 insertions(+), 3 deletions(-) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 9f0bab0589d9..3827a6b395fd 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -83,6 +83,7 @@ struct neigh_parms { struct rcu_head rcu_head; int reachable_time; + int qlen; int data[NEIGH_VAR_DATA_MAX]; DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX); }; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 0e38a05d5b23..5b669eb80270 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -316,9 +316,18 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) skb = skb_peek(list); while (skb != NULL) { struct sk_buff *skb_next = skb_peek_next(skb, list); - if (net == NULL || net_eq(dev_net(skb->dev), net)) { + struct net_device *dev = skb->dev; + if (net == NULL || net_eq(dev_net(dev), net)) { + struct in_device *in_dev; + + rcu_read_lock(); + in_dev = __in_dev_get_rcu(dev); + if (in_dev) + in_dev->arp_parms->qlen--; + rcu_read_unlock(); __skb_unlink(skb, list); - dev_put(skb->dev); + + dev_put(dev); kfree_skb(skb); } skb = skb_next; @@ -1606,8 +1615,15 @@ static void neigh_proxy_process(struct timer_list *t) if (tdif <= 0) { struct net_device *dev = skb->dev; + struct in_device *in_dev; + rcu_read_lock(); + in_dev = __in_dev_get_rcu(dev); + if (in_dev) + in_dev->arp_parms->qlen--; + rcu_read_unlock(); __skb_unlink(skb, &tbl->proxy_queue); + if (tbl->proxy_redo && netif_running(dev)) { rcu_read_lock(); tbl->proxy_redo(skb); @@ -1632,7 +1648,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, unsigned long sched_next = jiffies + prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY)); - if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) { + if (p->qlen > NEIGH_VAR(p, PROXY_QLEN)) { kfree_skb(skb); return; } @@ -1648,6 +1664,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, skb_dst_drop(skb); dev_hold(skb->dev); __skb_queue_tail(&tbl->proxy_queue, skb); + p->qlen++; mod_timer(&tbl->proxy_timer, sched_next); spin_unlock(&tbl->proxy_queue.lock); } @@ -1680,6 +1697,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, refcount_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); + p->qlen = 0; netdev_hold(dev, &p->dev_tracker, GFP_KERNEL); p->dev = dev; write_pnet(&p->net, net); @@ -1745,6 +1763,7 @@ void neigh_table_init(int index, struct neigh_table *tbl) refcount_set(&tbl->parms.refcnt, 1); tbl->parms.reachable_time = neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME)); + tbl->parms.qlen = 0; tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats)