From 1086bbe97a074844188c6c988fa0b1a98c3ccbb9 Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Tue, 19 May 2015 20:55:17 -0400 Subject: netfilter: ensure number of counters is >0 in do_replace() After improving setsockopt() coverage in trinity, I started triggering vmalloc failures pretty reliably from this code path: warn_alloc_failed+0xe9/0x140 __vmalloc_node_range+0x1be/0x270 vzalloc+0x4b/0x50 __do_replace+0x52/0x260 [ip_tables] do_ipt_set_ctl+0x15d/0x1d0 [ip_tables] nf_setsockopt+0x65/0x90 ip_setsockopt+0x61/0xa0 raw_setsockopt+0x16/0x60 sock_common_setsockopt+0x14/0x20 SyS_setsockopt+0x71/0xd0 It turns out we don't validate that the num_counters field in the struct we pass in from userspace is initialized. The same problem also exists in ebtables, arptables, ipv6, and the compat variants. Signed-off-by: Dave Jones Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebtables.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/bridge') diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 91180a7fc943..24c7c96bf5f8 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1117,6 +1117,8 @@ static int do_replace(struct net *net, const void __user *user, return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; tmp.name[sizeof(tmp.name) - 1] = 0; @@ -2159,6 +2161,8 @@ static int compat_copy_ebt_replace_from_user(struct ebt_replace *repl, return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; memcpy(repl, &tmp, offsetof(struct ebt_replace, hook_entry)); -- cgit v1.2.3 From faecbb45ebefb20260ad4a631e011e93c896cb73 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 20 May 2015 13:42:25 +0200 Subject: Revert "netfilter: bridge: query conntrack about skb dnat" This reverts commit c055d5b03bb4cb69d349d787c9787c0383abd8b2. There are two issues: 'dnat_took_place' made me think that this is related to -j DNAT/MASQUERADE. But thats only one part of the story. This is also relevant for SNAT when we undo snat translation in reverse/reply direction. Furthermore, I originally wanted to do this mainly to avoid storing ipv6 addresses once we make DNAT/REDIRECT work for ipv6 on bridges. However, I forgot about SNPT/DNPT which is stateless. So we can't escape storing address for ipv6 anyway. Might as well do it for ipv4 too. Reported-and-tested-by: Bernhard Thaler Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/skbuff.h | 1 + net/bridge/br_netfilter.c | 27 +++++++++------------------ 2 files changed, 10 insertions(+), 18 deletions(-) (limited to 'net/bridge') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 66e374d62f64..f15154a879c7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -176,6 +176,7 @@ struct nf_bridge_info { struct net_device *physindev; struct net_device *physoutdev; char neigh_header[8]; + __be32 ipv4_daddr; }; #endif diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index ab55e2472beb..60ddfbeb47f5 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -37,10 +37,6 @@ #include #include -#if IS_ENABLED(CONFIG_NF_CONNTRACK) -#include -#endif - #include #include "br_private.h" #ifdef CONFIG_SYSCTL @@ -350,24 +346,15 @@ free_skb: return 0; } -static bool dnat_took_place(const struct sk_buff *skb) +static bool daddr_was_changed(const struct sk_buff *skb, + const struct nf_bridge_info *nf_bridge) { -#if IS_ENABLED(CONFIG_NF_CONNTRACK) - enum ip_conntrack_info ctinfo; - struct nf_conn *ct; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct || nf_ct_is_untracked(ct)) - return false; - - return test_bit(IPS_DST_NAT_BIT, &ct->status); -#else - return false; -#endif + return ip_hdr(skb)->daddr != nf_bridge->ipv4_daddr; } /* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. + * This is also true when SNAT takes place (for the reply direction). * * There are two cases to consider: * 1. The packet was DNAT'ed to a device in the same bridge @@ -421,7 +408,7 @@ static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb) nf_bridge->pkt_otherhost = false; } nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; - if (dnat_took_place(skb)) { + if (daddr_was_changed(skb, nf_bridge)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -632,6 +619,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { + struct nf_bridge_info *nf_bridge; struct net_bridge_port *p; struct net_bridge *br; __u32 len = nf_bridge_encap_header_len(skb); @@ -669,6 +657,9 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, if (!setup_pre_routing(skb)) return NF_DROP; + nf_bridge = nf_bridge_info_get(skb); + nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr; + skb->protocol = htons(ETH_P_IP); NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->sk, skb, -- cgit v1.2.3 From 47cc84ce0c2fe75c99ea5963c4b5704dd78ead54 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Fri, 22 May 2015 12:18:59 -0300 Subject: bridge: fix parsing of MLDv2 reports When more than a multicast address is present in a MLDv2 report, all but the first address is ignored, because the code breaks out of the loop if there has not been an error adding that address. This has caused failures when two guests connected through the bridge tried to communicate using IPv6. Neighbor discoveries would not be transmitted to the other guest when both used a link-local address and a static address. This only happens when there is a MLDv2 querier in the network. The fix will only break out of the loop when there is a failure adding a multicast address. The mdb before the patch: dev ovirtmgmt port vnet0 grp ff02::1:ff7d:6603 temp dev ovirtmgmt port vnet1 grp ff02::1:ff7d:6604 temp dev ovirtmgmt port bond0.86 grp ff02::2 temp After the patch: dev ovirtmgmt port vnet0 grp ff02::1:ff7d:6603 temp dev ovirtmgmt port vnet1 grp ff02::1:ff7d:6604 temp dev ovirtmgmt port bond0.86 grp ff02::fb temp dev ovirtmgmt port bond0.86 grp ff02::2 temp dev ovirtmgmt port bond0.86 grp ff02::d temp dev ovirtmgmt port vnet0 grp ff02::1:ff00:76 temp dev ovirtmgmt port bond0.86 grp ff02::16 temp dev ovirtmgmt port vnet1 grp ff02::1:ff00:77 temp dev ovirtmgmt port bond0.86 grp ff02::1:ff00:def temp dev ovirtmgmt port bond0.86 grp ff02::1:ffa1:40bf temp Fixes: 08b202b67264 ("bridge br_multicast: IPv6 MLD support.") Reported-by: Rik Theys Signed-off-by: Thadeu Lima de Souza Cascardo Tested-by: Rik Theys Signed-off-by: David S. Miller --- net/bridge/br_multicast.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/bridge') diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 4b6722f8f179..a3abe6ed111e 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1072,7 +1072,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, vid); - if (!err) + if (err) break; } -- cgit v1.2.3 From 93a33a584e2a49a217118148125944fd02d47b54 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 21 May 2015 13:28:29 -0700 Subject: bridge: fix lockdep splat Following lockdep splat was reported : [ 29.382286] =============================== [ 29.382315] [ INFO: suspicious RCU usage. ] [ 29.382344] 4.1.0-0.rc0.git11.1.fc23.x86_64 #1 Not tainted [ 29.382380] ------------------------------- [ 29.382409] net/bridge/br_private.h:626 suspicious rcu_dereference_check() usage! [ 29.382455] other info that might help us debug this: [ 29.382507] rcu_scheduler_active = 1, debug_locks = 0 [ 29.382549] 2 locks held by swapper/0/0: [ 29.382576] #0: (((&p->forward_delay_timer))){+.-...}, at: [] call_timer_fn+0x5/0x4f0 [ 29.382660] #1: (&(&br->lock)->rlock){+.-...}, at: [] br_forward_delay_timer_expired+0x31/0x140 [bridge] [ 29.382754] stack backtrace: [ 29.382787] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.1.0-0.rc0.git11.1.fc23.x86_64 #1 [ 29.382838] Hardware name: LENOVO 422916G/LENOVO, BIOS A1KT53AUS 04/07/2015 [ 29.382882] 0000000000000000 3ebfc20364115825 ffff880666603c48 ffffffff81892d4b [ 29.382943] 0000000000000000 ffffffff81e124e0 ffff880666603c78 ffffffff8110bcd7 [ 29.383004] ffff8800785c9d00 ffff88065485ac58 ffff880c62002800 ffff880c5fc88ac0 [ 29.383065] Call Trace: [ 29.383084] [] dump_stack+0x4c/0x65 [ 29.383130] [] lockdep_rcu_suspicious+0xe7/0x120 [ 29.383178] [] br_fill_ifinfo+0x4a9/0x6a0 [bridge] [ 29.383225] [] br_ifinfo_notify+0x11b/0x4b0 [bridge] [ 29.383271] [] ? br_hold_timer_expired+0x70/0x70 [bridge] [ 29.383320] [] br_forward_delay_timer_expired+0x58/0x140 [bridge] [ 29.383371] [] ? br_hold_timer_expired+0x70/0x70 [bridge] [ 29.383416] [] call_timer_fn+0xc3/0x4f0 [ 29.383454] [] ? call_timer_fn+0x5/0x4f0 [ 29.383493] [] ? lock_release_holdtime.part.29+0xf/0x200 [ 29.383541] [] ? br_hold_timer_expired+0x70/0x70 [bridge] [ 29.383587] [] run_timer_softirq+0x244/0x490 [ 29.383629] [] __do_softirq+0xec/0x670 [ 29.383666] [] irq_exit+0x145/0x150 [ 29.383703] [] smp_apic_timer_interrupt+0x46/0x60 [ 29.383744] [] apic_timer_interrupt+0x73/0x80 [ 29.383782] [] ? cpuidle_enter_state+0x5f/0x2f0 [ 29.383832] [] ? cpuidle_enter_state+0x5b/0x2f0 Problem here is that br_forward_delay_timer_expired() is a timer handler, calling br_ifinfo_notify() which assumes either rcu_read_lock() or RTNL are held. Simplest fix seems to add rcu read lock section. Signed-off-by: Eric Dumazet Reported-by: Josh Boyer Reported-by: Dominick Grift Cc: Vlad Yasevich Signed-off-by: David S. Miller --- net/bridge/br_stp_timer.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/bridge') diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 4fcaa67750fd..7caf7fae2d5b 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -97,7 +97,9 @@ static void br_forward_delay_timer_expired(unsigned long arg) netif_carrier_on(br->dev); } br_log_state(p); + rcu_read_lock(); br_ifinfo_notify(RTM_NEWLINK, p); + rcu_read_unlock(); spin_unlock(&br->lock); } -- cgit v1.2.3