From 46c0ef6e1eb95f619d9f62da4332749153db92f7 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Fri, 16 Mar 2018 11:35:51 +0900 Subject: [PATCH 1/8] xfrm: fix rcu_read_unlock usage in xfrm_local_error In the xfrm_local_error, rcu_read_unlock should be called when afinfo is not NULL. because xfrm_state_get_afinfo calls rcu_read_unlock if afinfo is NULL. Fixes: af5d27c4e12b ("xfrm: remove xfrm_state_put_afinfo") Signed-off-by: Taehee Yoo Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_output.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 23468672a767..89b178a78dc7 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -285,8 +285,9 @@ void xfrm_local_error(struct sk_buff *skb, int mtu) return; afinfo = xfrm_state_get_afinfo(proto); - if (afinfo) + if (afinfo) { afinfo->local_error(skb, mtu); - rcu_read_unlock(); + rcu_read_unlock(); + } } EXPORT_SYMBOL_GPL(xfrm_local_error); From dd1df24737727e119c263acf1be2a92763938297 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Thu, 15 Mar 2018 17:16:27 +0100 Subject: [PATCH 2/8] vti4: Don't count header length twice on tunnel setup This re-introduces the effect of commit a32452366b72 ("vti4: Don't count header length twice.") which was accidentally reverted by merge commit f895f0cfbb77 ("Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec"). The commit message from Steffen Klassert said: We currently count the size of LL_MAX_HEADER and struct iphdr twice for vti4 devices, this leads to a wrong device mtu. The size of LL_MAX_HEADER and struct iphdr is already counted in ip_tunnel_bind_dev(), so don't do it again in vti_tunnel_init(). And this is still the case now: ip_tunnel_bind_dev() already accounts for the header length of the link layer (not necessarily LL_MAX_HEADER, if the output device is found), plus one IP header. For example, with a vti device on top of veth, with MTU of 1500, the existing implementation would set the initial vti MTU to 1332, accounting once for LL_MAX_HEADER (128, included in hard_header_len by vti) and twice for the same IP header (once from hard_header_len, once from ip_tunnel_bind_dev()). It should instead be 1480, because ip_tunnel_bind_dev() is able to figure out that the output device is veth, so no additional link layer header is attached, and will properly count one single IP header. The existing issue had the side effect of avoiding PMTUD for most xfrm policies, by arbitrarily lowering the initial MTU. However, the only way to get a consistent PMTU value is to let the xfrm PMTU discovery do its course, and commit d6af1a31cc72 ("vti: Add pmtu handling to vti_xmit.") now takes care of local delivery cases where the application ignores local socket notifications. Fixes: b9959fd3b0fa ("vti: switch to new ip tunnel code") Fixes: f895f0cfbb77 ("Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec") Signed-off-by: Stefano Brivio Acked-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- net/ipv4/ip_vti.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 51b1669334fe..502e5222eaa9 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -387,7 +387,6 @@ static int vti_tunnel_init(struct net_device *dev) memcpy(dev->dev_addr, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); - dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); dev->mtu = ETH_DATA_LEN; dev->flags = IFF_NOARP; dev->addr_len = 4; From 24fc79798b8ddfd46f2dd363a8d29072c083b977 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Thu, 15 Mar 2018 17:16:28 +0100 Subject: [PATCH 3/8] ip_tunnel: Clamp MTU to bounds on new link Otherwise, it's possible to specify invalid MTU values directly on creation of a link (via 'ip link add'). This is already prevented on subsequent MTU changes by commit b96f9afee4eb ("ipv4/6: use core net MTU range checking"). Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.") Signed-off-by: Stefano Brivio Acked-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- net/ipv4/ip_tunnel.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 6d21068f9b55..7c76dd17b6b9 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1108,8 +1108,14 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], eth_hw_addr_random(dev); mtu = ip_tunnel_bind_dev(dev); - if (!tb[IFLA_MTU]) + if (tb[IFLA_MTU]) { + unsigned int max = 0xfff8 - dev->hard_header_len - nt->hlen; + + dev->mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, + (unsigned int)(max - sizeof(struct iphdr))); + } else { dev->mtu = mtu; + } ip_tunnel_add(itn, nt); out: From 03080e5ec72740c1a62e6730f2a5f3f114f11b19 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Thu, 15 Mar 2018 17:16:29 +0100 Subject: [PATCH 4/8] vti4: Don't override MTU passed on link creation via IFLA_MTU Don't hardcode a MTU value on vti tunnel initialization, ip_tunnel_newlink() is able to deal with this already. See also commit ffc2b6ee4174 ("ip_gre: fix IFLA_MTU ignored on NEWLINK"). Fixes: 1181412c1a67 ("net/ipv4: VTI support new module for ip_vti.") Signed-off-by: Stefano Brivio Acked-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- net/ipv4/ip_vti.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 502e5222eaa9..3f091ccad9af 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -387,7 +387,6 @@ static int vti_tunnel_init(struct net_device *dev) memcpy(dev->dev_addr, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); - dev->mtu = ETH_DATA_LEN; dev->flags = IFF_NOARP; dev->addr_len = 4; dev->features |= NETIF_F_LLTX; From c6741fbed6dc0f183d26c4b6bca4517672f92e6c Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Thu, 15 Mar 2018 17:17:11 +0100 Subject: [PATCH 5/8] vti6: Properly adjust vti6 MTU from MTU of lower device If a lower device is found, we don't need to subtract LL_MAX_HEADER to calculate our MTU: just use its MTU, the link layer headers are already taken into account by it. If the lower device is not found, start from ETH_DATA_LEN instead, and only in this case subtract a worst-case LL_MAX_HEADER. We then need to subtract our additional IPv6 header from the calculation. While at it, note that vti6 doesn't have a hardware header, so it doesn't need to set dev->hard_header_len. And as vti6_link_config() now always sets the MTU, there's no need to set a default value in vti6_dev_setup(). This makes the behaviour consistent with IPv4 vti, after commit a32452366b72 ("vti4: Don't count header length twice."), which was accidentally reverted by merge commit f895f0cfbb77 ("Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec"). While commit 53c81e95df17 ("ip6_vti: adjust vti mtu according to mtu of lower device") improved on the original situation, this was still not ideal. As reported in that commit message itself, if we start from an underlying veth MTU of 9000, we end up with an MTU of 8832, that is, 9000 - LL_MAX_HEADER - sizeof(ipv6hdr). This should simply be 8880, or 9000 - sizeof(ipv6hdr) instead: we found the lower device (veth) and we know we don't have any additional link layer header, so there's no need to subtract an hypothetical worst-case number. Fixes: 53c81e95df17 ("ip6_vti: adjust vti mtu according to mtu of lower device") Signed-off-by: Stefano Brivio Acked-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- net/ipv6/ip6_vti.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index fa3ae1cb50d3..2ceef41cc097 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -627,6 +627,7 @@ static void vti6_link_config(struct ip6_tnl *t) struct net_device *dev = t->dev; struct __ip6_tnl_parm *p = &t->parms; struct net_device *tdev = NULL; + int mtu; memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); @@ -656,8 +657,11 @@ static void vti6_link_config(struct ip6_tnl *t) tdev = __dev_get_by_index(t->net, p->link); if (tdev) - dev->mtu = max_t(int, tdev->mtu - dev->hard_header_len, - IPV6_MIN_MTU); + mtu = tdev->mtu - sizeof(struct ipv6hdr); + else + mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr); + + dev->mtu = max_t(int, mtu, IPV6_MIN_MTU); } /** @@ -866,8 +870,6 @@ static void vti6_dev_setup(struct net_device *dev) dev->priv_destructor = vti6_dev_free; dev->type = ARPHRD_TUNNEL6; - dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr); - dev->mtu = ETH_DATA_LEN; dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP_MAX_MTU; dev->flags |= IFF_NOARP; From 7a67e69a339a6824be2fc483073782ab2f47fcd2 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Thu, 15 Mar 2018 17:17:12 +0100 Subject: [PATCH 6/8] vti6: Keep set MTU on link creation or change, validate it In vti6_link_config(), if MTU is already given on link creation or change, validate and use it instead of recomputing it. To do that, we need to propagate the knowledge that MTU was set by userspace all the way down to vti6_link_config(). To keep this simple, vti6_dev_init() sets the new 'keep_mtu' argument of vti6_link_config() to true: on initialization, we don't have convenient access to netlink attributes there, but we will anyway check whether dev->mtu is set in vti6_link_config(). If it's non-zero, it was set to the value of the IFLA_MTU attribute during creation. Otherwise, determine a reasonable value. Fixes: ed1efb2aefbb ("ipv6: Add support for IPsec virtual tunnel interfaces") Fixes: 53c81e95df17 ("ip6_vti: adjust vti mtu according to mtu of lower device") Signed-off-by: Stefano Brivio Acked-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- net/ipv6/ip6_vti.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 2ceef41cc097..971175142e14 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -622,7 +622,7 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return 0; } -static void vti6_link_config(struct ip6_tnl *t) +static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu) { struct net_device *dev = t->dev; struct __ip6_tnl_parm *p = &t->parms; @@ -641,6 +641,11 @@ static void vti6_link_config(struct ip6_tnl *t) else dev->flags &= ~IFF_POINTOPOINT; + if (keep_mtu && dev->mtu) { + dev->mtu = clamp(dev->mtu, dev->min_mtu, dev->max_mtu); + return; + } + if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); @@ -668,12 +673,14 @@ static void vti6_link_config(struct ip6_tnl *t) * vti6_tnl_change - update the tunnel parameters * @t: tunnel to be changed * @p: tunnel configuration parameters + * @keep_mtu: MTU was set from userspace, don't re-compute it * * Description: * vti6_tnl_change() updates the tunnel parameters **/ static int -vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) +vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p, + bool keep_mtu) { t->parms.laddr = p->laddr; t->parms.raddr = p->raddr; @@ -683,11 +690,12 @@ vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) t->parms.proto = p->proto; t->parms.fwmark = p->fwmark; dst_cache_reset(&t->dst_cache); - vti6_link_config(t); + vti6_link_config(t, keep_mtu); return 0; } -static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) +static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p, + bool keep_mtu) { struct net *net = dev_net(t->dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); @@ -695,7 +703,7 @@ static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) vti6_tnl_unlink(ip6n, t); synchronize_net(); - err = vti6_tnl_change(t, p); + err = vti6_tnl_change(t, p, keep_mtu); vti6_tnl_link(ip6n, t); netdev_state_change(t->dev); return err; @@ -808,7 +816,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } else t = netdev_priv(dev); - err = vti6_update(t, &p1); + err = vti6_update(t, &p1, false); } if (t) { err = 0; @@ -907,7 +915,7 @@ static int vti6_dev_init(struct net_device *dev) if (err) return err; - vti6_link_config(t); + vti6_link_config(t, true); return 0; } @@ -1012,7 +1020,7 @@ static int vti6_changelink(struct net_device *dev, struct nlattr *tb[], } else t = netdev_priv(dev); - return vti6_update(t, &p); + return vti6_update(t, &p, tb && tb[IFLA_MTU]); } static size_t vti6_get_size(const struct net_device *dev) From f8a554b4aa9686bb2c12f6bae516e58783289a03 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Thu, 15 Mar 2018 17:17:13 +0100 Subject: [PATCH 7/8] vti6: Fix dev->max_mtu setting We shouldn't allow a tunnel to have IP_MAX_MTU as MTU, because another IPv6 header is going on top of our packets. Without this patch, we might end up building packets bigger than IP_MAX_MTU. Fixes: b96f9afee4eb ("ipv4/6: use core net MTU range checking") Signed-off-by: Stefano Brivio Acked-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- net/ipv6/ip6_vti.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 971175142e14..ce18cd20389d 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -879,7 +879,7 @@ static void vti6_dev_setup(struct net_device *dev) dev->type = ARPHRD_TUNNEL6; dev->min_mtu = IPV6_MIN_MTU; - dev->max_mtu = IP_MAX_MTU; + dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr); dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); netif_keep_dst(dev); From 9a3fb9fb84cc30577c1b012a6a3efda944684291 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Mon, 19 Mar 2018 07:15:39 +0100 Subject: [PATCH 8/8] xfrm: Fix transport mode skb control buffer usage. A recent commit introduced a new struct xfrm_trans_cb that is used with the sk_buff control buffer. Unfortunately it placed the structure in front of the control buffer and overlooked that the IPv4/IPv6 control buffer is still needed for some layer 4 protocols. As a result the IPv4/IPv6 control buffer is overwritten with this structure. Fix this by setting a apropriate header in front of the structure. Fixes acf568ee859f ("xfrm: Reinject transport-mode packets ...") Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_input.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 1472c0857975..81788105c164 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -26,6 +26,12 @@ struct xfrm_trans_tasklet { }; struct xfrm_trans_cb { + union { + struct inet_skb_parm h4; +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_skb_parm h6; +#endif + } header; int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb); };