From ccd27f05ae7b8ebc40af5b004e94517a919aa862 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 6 Jul 2021 11:13:35 +0200 Subject: ipv6: fix 'disable_policy' for fwd packets The goal of commit df789fe75206 ("ipv6: Provide ipv6 version of "disable_policy" sysctl") was to have the disable_policy from ipv4 available on ipv6. However, it's not exactly the same mechanism. On IPv4, all packets coming from an interface, which has disable_policy set, bypass the policy check. For ipv6, this is done only for local packets, ie for packets destinated to an address configured on the incoming interface. Let's align ipv6 with ipv4 so that the 'disable_policy' sysctl has the same effect for both protocols. My first approach was to create a new kind of route cache entries, to be able to set DST_NOPOLICY without modifying routes. This would have added a lot of code. Because the local delivery path is already handled, I choose to focus on the forwarding path to minimize code churn. Fixes: df789fe75206 ("ipv6: Provide ipv6 version of "disable_policy" sysctl") Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/ipv6/ip6_output.c') diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 984050f35c61..d4ee2169afd8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -479,7 +479,9 @@ int ip6_forward(struct sk_buff *skb) if (skb_warn_if_lro(skb)) goto drop; - if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { + if (!net->ipv6.devconf_all->disable_policy && + !idev->cnf.disable_policy && + !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } -- cgit v1.2.3 From 5796015fa968a3349027a27dcd04c71d95c53ba5 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Mon, 12 Jul 2021 09:45:06 +0300 Subject: ipv6: allocate enough headroom in ip6_finish_output2() When TEE target mirrors traffic to another interface, sk_buff may not have enough headroom to be processed correctly. ip_finish_output2() detect this situation for ipv4 and allocates new skb with enogh headroom. However ipv6 lacks this logic in ip_finish_output2 and it leads to skb_under_panic: skbuff: skb_under_panic: text:ffffffffc0866ad4 len:96 put:24 head:ffff97be85e31800 data:ffff97be85e317f8 tail:0x58 end:0xc0 dev:gre0 ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:110! invalid opcode: 0000 [#1] SMP PTI CPU: 2 PID: 393 Comm: kworker/2:2 Tainted: G OE 5.13.0 #13 Hardware name: Virtuozzo KVM, BIOS 1.11.0-2.vz7.4 04/01/2014 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:skb_panic+0x48/0x4a Call Trace: skb_push.cold.111+0x10/0x10 ipgre_header+0x24/0xf0 [ip_gre] neigh_connected_output+0xae/0xf0 ip6_finish_output2+0x1a8/0x5a0 ip6_output+0x5c/0x110 nf_dup_ipv6+0x158/0x1000 [nf_dup_ipv6] tee_tg6+0x2e/0x40 [xt_TEE] ip6t_do_table+0x294/0x470 [ip6_tables] nf_hook_slow+0x44/0xc0 nf_hook.constprop.34+0x72/0xe0 ndisc_send_skb+0x20d/0x2e0 ndisc_send_ns+0xd1/0x210 addrconf_dad_work+0x3c8/0x540 process_one_work+0x1d1/0x370 worker_thread+0x30/0x390 kthread+0x116/0x130 ret_from_fork+0x22/0x30 Signed-off-by: Vasily Averin Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'net/ipv6/ip6_output.c') diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d4ee2169afd8..01bea76e3891 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -60,10 +60,38 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; + unsigned int hh_len = LL_RESERVED_SPACE(dev); + int delta = hh_len - skb_headroom(skb); const struct in6_addr *nexthop; struct neighbour *neigh; int ret; + /* Be paranoid, rather than too clever. */ + if (unlikely(delta > 0) && dev->header_ops) { + /* pskb_expand_head() might crash, if skb is shared */ + if (skb_shared(skb)) { + struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + + if (likely(nskb)) { + if (skb->sk) + skb_set_owner_w(skb, skb->sk); + consume_skb(skb); + } else { + kfree_skb(skb); + } + skb = nskb; + } + if (skb && + pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { + kfree_skb(skb); + skb = NULL; + } + if (!skb) { + IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); + return -ENOMEM; + } + } + if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); -- cgit v1.2.3