linux_old1/net/ipv4/ip_vti.c

661 lines
15 KiB
C
Raw Normal View History

/*
* Linux NET3: IP/IP protocol decoder modified to support
* virtual tunnel interface
*
* Authors:
* Saurabh Mohan (saurabh.mohan@vyatta.com) 05/07/2012
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
*/
/*
This version of net/ipv4/ip_vti.c is cloned of net/ipv4/ipip.c
For comments look at net/ipv4/ip_gre.c --ANK
*/
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/netfilter_ipv4.h>
#include <linux/if_ether.h>
#include <linux/icmpv6.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
static struct rtnl_link_ops vti_link_ops __read_mostly;
netns: make struct pernet_operations::id unsigned int Make struct pernet_operations::id unsigned. There are 2 reasons to do so: 1) This field is really an index into an zero based array and thus is unsigned entity. Using negative value is out-of-bound access by definition. 2) On x86_64 unsigned 32-bit data which are mixed with pointers via array indexing or offsets added or subtracted to pointers are preffered to signed 32-bit data. "int" being used as an array index needs to be sign-extended to 64-bit before being used. void f(long *p, int i) { g(p[i]); } roughly translates to movsx rsi, esi mov rdi, [rsi+...] call g MOVSX is 3 byte instruction which isn't necessary if the variable is unsigned because x86_64 is zero extending by default. Now, there is net_generic() function which, you guessed it right, uses "int" as an array index: static inline void *net_generic(const struct net *net, int id) { ... ptr = ng->ptr[id - 1]; ... } And this function is used a lot, so those sign extensions add up. Patch snipes ~1730 bytes on allyesconfig kernel (without all junk messing with code generation): add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) Unfortunately some functions actually grow bigger. This is a semmingly random artefact of code generation with register allocator being used differently. gcc decides that some variable needs to live in new r8+ registers and every access now requires REX prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be used which is longer than [r8] However, overall balance is in negative direction: add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) function old new delta nfsd4_lock 3886 3959 +73 tipc_link_build_proto_msg 1096 1140 +44 mac80211_hwsim_new_radio 2776 2808 +32 tipc_mon_rcv 1032 1058 +26 svcauth_gss_legacy_init 1413 1429 +16 tipc_bcbase_select_primary 379 392 +13 nfsd4_exchange_id 1247 1260 +13 nfsd4_setclientid_confirm 782 793 +11 ... put_client_renew_locked 494 480 -14 ip_set_sockfn_get 730 716 -14 geneve_sock_add 829 813 -16 nfsd4_sequence_done 721 703 -18 nlmclnt_lookup_host 708 686 -22 nfsd4_lockt 1085 1063 -22 nfs_get_client 1077 1050 -27 tcf_bpf_init 1106 1076 -30 nfsd4_encode_fattr 5997 5930 -67 Total: Before=154856051, After=154854321, chg -0.00% Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 09:58:21 +08:00
static unsigned int vti_net_id __read_mostly;
static int vti_tunnel_init(struct net_device *dev);
static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
int encap_type)
{
struct ip_tunnel *tunnel;
const struct iphdr *iph = ip_hdr(skb);
struct net *net = dev_net(skb->dev);
struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->saddr, iph->daddr, 0);
if (tunnel) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
return xfrm_input(skb, nexthdr, spi, encap_type);
}
return -EINVAL;
drop:
kfree_skb(skb);
return 0;
}
static int vti_rcv(struct sk_buff *skb)
{
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
}
static int vti_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
struct net_device *dev;
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
struct xfrm_mode *inner_mode;
struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
u32 orig_mark = skb->mark;
int ret;
if (!tunnel)
return 1;
dev = tunnel->dev;
if (err) {
dev->stats.rx_errors++;
dev->stats.rx_dropped++;
return 0;
}
x = xfrm_input_state(skb);
inner_mode = x->inner_mode;
if (x->sel.family == AF_UNSPEC) {
inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
if (inner_mode == NULL) {
XFRM_INC_STATS(dev_net(skb->dev),
LINUX_MIB_XFRMINSTATEMODEERROR);
return -EINVAL;
}
}
family = inner_mode->afinfo->family;
skb->mark = be32_to_cpu(tunnel->parms.i_key);
ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
skb->mark = orig_mark;
if (!ret)
return -EPERM;
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
skb->dev = dev;
tstats = this_cpu_ptr(dev->tstats);
u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
return 0;
}
static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src)
{
xfrm_address_t *daddr = (xfrm_address_t *)&dst;
xfrm_address_t *saddr = (xfrm_address_t *)&src;
/* if there is no transform then this tunnel is not functional.
* Or if the xfrm is not mode tunnel.
*/
if (!x || x->props.mode != XFRM_MODE_TUNNEL ||
x->props.family != AF_INET)
return false;
if (!dst)
return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET);
if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET))
return false;
return true;
}
static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
struct flowi *fl)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct ip_tunnel_parm *parms = &tunnel->parms;
struct dst_entry *dst = skb_dst(skb);
struct net_device *tdev; /* Device to other host */
int err;
int mtu;
if (!dst) {
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
dst_hold(dst);
dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0);
if (IS_ERR(dst)) {
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) {
dev->stats.tx_carrier_errors++;
dst_release(dst);
goto tx_error_icmp;
}
tdev = dst->dev;
if (tdev == dev) {
dst_release(dst);
dev->stats.collisions++;
goto tx_error;
}
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
mtu = dst_mtu(dst);
if (skb->len > mtu) {
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
if (skb->protocol == htons(ETH_P_IP)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
} else {
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
}
dst_release(dst);
goto tx_error;
}
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
err = dst_output(tunnel->net, skb->sk, skb);
if (net_xmit_eval(err) == 0)
err = skb->len;
iptunnel_xmit_stats(dev, err);
return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
dev->stats.tx_errors++;
kfree_skb(skb);
return NETDEV_TX_OK;
}
/* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct flowi fl;
memset(&fl, 0, sizeof(fl));
switch (skb->protocol) {
case htons(ETH_P_IP):
xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
break;
case htons(ETH_P_IPV6):
xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
break;
default:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
/* override mark with tunnel output key */
fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
return vti_xmit(skb, dev, &fl);
}
static int vti4_err(struct sk_buff *skb, u32 info)
{
__be32 spi;
__u32 mark;
struct xfrm_state *x;
struct ip_tunnel *tunnel;
struct ip_esp_hdr *esph;
struct ip_auth_hdr *ah ;
struct ip_comp_hdr *ipch;
struct net *net = dev_net(skb->dev);
const struct iphdr *iph = (const struct iphdr *)skb->data;
int protocol = iph->protocol;
struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->daddr, iph->saddr, 0);
if (!tunnel)
return -1;
mark = be32_to_cpu(tunnel->parms.o_key);
switch (protocol) {
case IPPROTO_ESP:
esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
spi = esph->spi;
break;
case IPPROTO_AH:
ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
spi = ah->spi;
break;
case IPPROTO_COMP:
ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
spi = htonl(ntohs(ipch->cpi));
break;
default:
return 0;
}
switch (icmp_hdr(skb)->type) {
case ICMP_DEST_UNREACH:
if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
return 0;
case ICMP_REDIRECT:
break;
default:
return 0;
}
x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
spi, protocol, AF_INET);
if (!x)
return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0);
else
ipv4_redirect(skb, net, 0, 0, protocol, 0);
xfrm_state_put(x);
return 0;
}
static int
vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
int err = 0;
struct ip_tunnel_parm p;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
return -EFAULT;
if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
p.iph.ihl != 5)
return -EINVAL;
}
if (!(p.i_flags & GRE_KEY))
p.i_key = 0;
if (!(p.o_flags & GRE_KEY))
p.o_key = 0;
p.i_flags = VTI_ISVTI;
err = ip_tunnel_ioctl(dev, &p, cmd);
if (err)
return err;
if (cmd != SIOCDELTUNNEL) {
p.i_flags |= GRE_KEY;
p.o_flags |= GRE_KEY;
}
if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
return -EFAULT;
return 0;
}
static const struct net_device_ops vti_netdev_ops = {
.ndo_init = vti_tunnel_init,
.ndo_uninit = ip_tunnel_uninit,
.ndo_start_xmit = vti_tunnel_xmit,
.ndo_do_ioctl = vti_tunnel_ioctl,
.ndo_change_mtu = ip_tunnel_change_mtu,
.ndo_get_stats64 = ip_tunnel_get_stats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
};
static void vti_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &vti_netdev_ops;
dev->type = ARPHRD_TUNNEL;
ip_tunnel_setup(dev, vti_net_id);
}
static int vti_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
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;
dev->features |= NETIF_F_LLTX;
netif_keep_dst(dev);
return ip_tunnel_init(dev);
}
static void __net_init vti_fb_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
iph->version = 4;
iph->protocol = IPPROTO_IPIP;
iph->ihl = 5;
}
static struct xfrm4_protocol vti_esp4_protocol __read_mostly = {
.handler = vti_rcv,
.input_handler = vti_input,
.cb_handler = vti_rcv_cb,
.err_handler = vti4_err,
.priority = 100,
};
static struct xfrm4_protocol vti_ah4_protocol __read_mostly = {
.handler = vti_rcv,
.input_handler = vti_input,
.cb_handler = vti_rcv_cb,
.err_handler = vti4_err,
.priority = 100,
};
static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
.handler = vti_rcv,
.input_handler = vti_input,
.cb_handler = vti_rcv_cb,
.err_handler = vti4_err,
.priority = 100,
};
static int __net_init vti_init_net(struct net *net)
{
int err;
struct ip_tunnel_net *itn;
err = ip_tunnel_init_net(net, vti_net_id, &vti_link_ops, "ip_vti0");
if (err)
return err;
itn = net_generic(net, vti_net_id);
vti_fb_tunnel_init(itn->fb_tunnel_dev);
return 0;
}
static void __net_exit vti_exit_net(struct net *net)
{
struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
ip_tunnel_delete_net(itn, &vti_link_ops);
}
static struct pernet_operations vti_net_ops = {
.init = vti_init_net,
.exit = vti_exit_net,
.id = &vti_net_id,
.size = sizeof(struct ip_tunnel_net),
};
static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
{
return 0;
}
static void vti_netlink_parms(struct nlattr *data[],
struct ip_tunnel_parm *parms)
{
memset(parms, 0, sizeof(*parms));
parms->iph.protocol = IPPROTO_IPIP;
if (!data)
return;
parms->i_flags = VTI_ISVTI;
if (data[IFLA_VTI_LINK])
parms->link = nla_get_u32(data[IFLA_VTI_LINK]);
if (data[IFLA_VTI_IKEY])
parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]);
if (data[IFLA_VTI_OKEY])
parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]);
if (data[IFLA_VTI_LOCAL])
parms->iph.saddr = nla_get_in_addr(data[IFLA_VTI_LOCAL]);
if (data[IFLA_VTI_REMOTE])
parms->iph.daddr = nla_get_in_addr(data[IFLA_VTI_REMOTE]);
}
static int vti_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
struct ip_tunnel_parm parms;
vti_netlink_parms(data, &parms);
return ip_tunnel_newlink(dev, tb, &parms);
}
static int vti_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
{
struct ip_tunnel_parm p;
vti_netlink_parms(data, &p);
return ip_tunnel_changelink(dev, tb, &p);
}
static size_t vti_get_size(const struct net_device *dev)
{
return
/* IFLA_VTI_LINK */
nla_total_size(4) +
/* IFLA_VTI_IKEY */
nla_total_size(4) +
/* IFLA_VTI_OKEY */
nla_total_size(4) +
/* IFLA_VTI_LOCAL */
nla_total_size(4) +
/* IFLA_VTI_REMOTE */
nla_total_size(4) +
0;
}
static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct ip_tunnel *t = netdev_priv(dev);
struct ip_tunnel_parm *p = &t->parms;
nla_put_u32(skb, IFLA_VTI_LINK, p->link);
nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key);
nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key);
nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr);
nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr);
return 0;
}
static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = {
[IFLA_VTI_LINK] = { .type = NLA_U32 },
[IFLA_VTI_IKEY] = { .type = NLA_U32 },
[IFLA_VTI_OKEY] = { .type = NLA_U32 },
[IFLA_VTI_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) },
[IFLA_VTI_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) },
};
static struct rtnl_link_ops vti_link_ops __read_mostly = {
.kind = "vti",
.maxtype = IFLA_VTI_MAX,
.policy = vti_policy,
.priv_size = sizeof(struct ip_tunnel),
.setup = vti_tunnel_setup,
.validate = vti_tunnel_validate,
.newlink = vti_newlink,
.changelink = vti_changelink,
ip_tunnel: the lack of vti_link_ops' dellink() cause kernel panic Now the vti_link_ops do not point the .dellink, for fb tunnel device (ip_vti0), the net_device will be removed as the default .dellink is unregister_netdevice_queue,but the tunnel still in the tunnel list, then if we add a new vti tunnel, in ip_tunnel_find(): hlist_for_each_entry_rcu(t, head, hash_node) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && link == t->parms.link && ==> type == t->dev->type && ip_tunnel_key_match(&t->parms, flags, key)) break; } the panic will happen, cause dev of ip_tunnel *t is null: [ 3835.072977] IP: [<ffffffffa04103fd>] ip_tunnel_find+0x9d/0xc0 [ip_tunnel] [ 3835.073008] PGD b2c21067 PUD b7277067 PMD 0 [ 3835.073008] Oops: 0000 [#1] SMP ..... [ 3835.073008] Stack: [ 3835.073008] ffff8800b72d77f0 ffffffffa0411924 ffff8800bb956000 ffff8800b72d78e0 [ 3835.073008] ffff8800b72d78a0 0000000000000000 ffffffffa040d100 ffff8800b72d7858 [ 3835.073008] ffffffffa040b2e3 0000000000000000 0000000000000000 0000000000000000 [ 3835.073008] Call Trace: [ 3835.073008] [<ffffffffa0411924>] ip_tunnel_newlink+0x64/0x160 [ip_tunnel] [ 3835.073008] [<ffffffffa040b2e3>] vti_newlink+0x43/0x70 [ip_vti] [ 3835.073008] [<ffffffff8150d4da>] rtnl_newlink+0x4fa/0x5f0 [ 3835.073008] [<ffffffff812f68bb>] ? nla_strlcpy+0x5b/0x70 [ 3835.073008] [<ffffffff81508fb0>] ? rtnl_link_ops_get+0x40/0x60 [ 3835.073008] [<ffffffff8150d11f>] ? rtnl_newlink+0x13f/0x5f0 [ 3835.073008] [<ffffffff81509cf4>] rtnetlink_rcv_msg+0xa4/0x270 [ 3835.073008] [<ffffffff8126adf5>] ? sock_has_perm+0x75/0x90 [ 3835.073008] [<ffffffff81509c50>] ? rtnetlink_rcv+0x30/0x30 [ 3835.073008] [<ffffffff81529e39>] netlink_rcv_skb+0xa9/0xc0 [ 3835.073008] [<ffffffff81509c48>] rtnetlink_rcv+0x28/0x30 .... modprobe ip_vti ip link del ip_vti0 type vti ip link add ip_vti0 type vti rmmod ip_vti do that one or more times, kernel will panic. fix it by assigning ip_tunnel_dellink to vti_link_ops' dellink, in which we skip the unregister of fb tunnel device. do the same on ip6_vti. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-23 15:04:11 +08:00
.dellink = ip_tunnel_dellink,
.get_size = vti_get_size,
.fill_info = vti_fill_info,
.get_link_net = ip_tunnel_get_link_net,
};
vti: flush x-netns xfrm cache when vti interface is removed When executing the script included below, the netns delete operation hangs with the following message (repeated at 10 second intervals): kernel:unregister_netdevice: waiting for lo to become free. Usage count = 1 This occurs because a reference to the lo interface in the "secure" netns is still held by a dst entry in the xfrm bundle cache in the init netns. Address this problem by garbage collecting the tunnel netns flow cache when a cross-namespace vti interface receives a NETDEV_DOWN notification. A more detailed description of the problem scenario (referencing commands in the script below): (1) ip link add vti_test type vti local 1.1.1.1 remote 1.1.1.2 key 1 The vti_test interface is created in the init namespace. vti_tunnel_init() attaches a struct ip_tunnel to the vti interface's netdev_priv(dev), setting the tunnel net to &init_net. (2) ip link set vti_test netns secure The vti_test interface is moved to the "secure" netns. Note that the associated struct ip_tunnel still has tunnel->net set to &init_net. (3) ip netns exec secure ping -c 4 -i 0.02 -I 192.168.100.1 192.168.200.1 The first packet sent using the vti device causes xfrm_lookup() to be called as follows: dst = xfrm_lookup(tunnel->net, skb_dst(skb), fl, NULL, 0); Note that tunnel->net is the init namespace, while skb_dst(skb) references the vti_test interface in the "secure" namespace. The returned dst references an interface in the init namespace. Also note that the first parameter to xfrm_lookup() determines which flow cache is used to store the computed xfrm bundle, so after xfrm_lookup() returns there will be a cached bundle in the init namespace flow cache with a dst referencing a device in the "secure" namespace. (4) ip netns del secure Kernel begins to delete the "secure" namespace. At some point the vti_test interface is deleted, at which point dst_ifdown() changes the dst->dev in the cached xfrm bundle flow from vti_test to lo (still in the "secure" namespace however). Since nothing has happened to cause the init namespace's flow cache to be garbage collected, this dst remains attached to the flow cache, so the kernel loops waiting for the last reference to lo to go away. <Begin script> ip link add br1 type bridge ip link set dev br1 up ip addr add dev br1 1.1.1.1/8 ip netns add secure ip link add vti_test type vti local 1.1.1.1 remote 1.1.1.2 key 1 ip link set vti_test netns secure ip netns exec secure ip link set vti_test up ip netns exec secure ip link s lo up ip netns exec secure ip addr add dev lo 192.168.100.1/24 ip netns exec secure ip route add 192.168.200.0/24 dev vti_test ip xfrm policy flush ip xfrm state flush ip xfrm policy add dir out tmpl src 1.1.1.1 dst 1.1.1.2 \ proto esp mode tunnel mark 1 ip xfrm policy add dir in tmpl src 1.1.1.2 dst 1.1.1.1 \ proto esp mode tunnel mark 1 ip xfrm state add src 1.1.1.1 dst 1.1.1.2 proto esp spi 1 \ mode tunnel enc des3_ede 0x112233445566778811223344556677881122334455667788 ip xfrm state add src 1.1.1.2 dst 1.1.1.1 proto esp spi 1 \ mode tunnel enc des3_ede 0x112233445566778811223344556677881122334455667788 ip netns exec secure ping -c 4 -i 0.02 -I 192.168.100.1 192.168.200.1 ip netns del secure <End script> Reported-by: Hangbin Liu <haliu@redhat.com> Reported-by: Jan Tluka <jtluka@redhat.com> Signed-off-by: Lance Richardson <lrichard@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-10 03:29:42 +08:00
static bool is_vti_tunnel(const struct net_device *dev)
{
return dev->netdev_ops == &vti_netdev_ops;
}
static int vti_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct ip_tunnel *tunnel = netdev_priv(dev);
if (!is_vti_tunnel(dev))
return NOTIFY_DONE;
switch (event) {
case NETDEV_DOWN:
if (!net_eq(tunnel->net, dev_net(dev)))
xfrm_garbage_collect(tunnel->net);
break;
}
return NOTIFY_DONE;
}
static struct notifier_block vti_notifier_block __read_mostly = {
.notifier_call = vti_device_event,
};
static int __init vti_init(void)
{
const char *msg;
int err;
pr_info("IPv4 over IPsec tunneling driver\n");
vti: flush x-netns xfrm cache when vti interface is removed When executing the script included below, the netns delete operation hangs with the following message (repeated at 10 second intervals): kernel:unregister_netdevice: waiting for lo to become free. Usage count = 1 This occurs because a reference to the lo interface in the "secure" netns is still held by a dst entry in the xfrm bundle cache in the init netns. Address this problem by garbage collecting the tunnel netns flow cache when a cross-namespace vti interface receives a NETDEV_DOWN notification. A more detailed description of the problem scenario (referencing commands in the script below): (1) ip link add vti_test type vti local 1.1.1.1 remote 1.1.1.2 key 1 The vti_test interface is created in the init namespace. vti_tunnel_init() attaches a struct ip_tunnel to the vti interface's netdev_priv(dev), setting the tunnel net to &init_net. (2) ip link set vti_test netns secure The vti_test interface is moved to the "secure" netns. Note that the associated struct ip_tunnel still has tunnel->net set to &init_net. (3) ip netns exec secure ping -c 4 -i 0.02 -I 192.168.100.1 192.168.200.1 The first packet sent using the vti device causes xfrm_lookup() to be called as follows: dst = xfrm_lookup(tunnel->net, skb_dst(skb), fl, NULL, 0); Note that tunnel->net is the init namespace, while skb_dst(skb) references the vti_test interface in the "secure" namespace. The returned dst references an interface in the init namespace. Also note that the first parameter to xfrm_lookup() determines which flow cache is used to store the computed xfrm bundle, so after xfrm_lookup() returns there will be a cached bundle in the init namespace flow cache with a dst referencing a device in the "secure" namespace. (4) ip netns del secure Kernel begins to delete the "secure" namespace. At some point the vti_test interface is deleted, at which point dst_ifdown() changes the dst->dev in the cached xfrm bundle flow from vti_test to lo (still in the "secure" namespace however). Since nothing has happened to cause the init namespace's flow cache to be garbage collected, this dst remains attached to the flow cache, so the kernel loops waiting for the last reference to lo to go away. <Begin script> ip link add br1 type bridge ip link set dev br1 up ip addr add dev br1 1.1.1.1/8 ip netns add secure ip link add vti_test type vti local 1.1.1.1 remote 1.1.1.2 key 1 ip link set vti_test netns secure ip netns exec secure ip link set vti_test up ip netns exec secure ip link s lo up ip netns exec secure ip addr add dev lo 192.168.100.1/24 ip netns exec secure ip route add 192.168.200.0/24 dev vti_test ip xfrm policy flush ip xfrm state flush ip xfrm policy add dir out tmpl src 1.1.1.1 dst 1.1.1.2 \ proto esp mode tunnel mark 1 ip xfrm policy add dir in tmpl src 1.1.1.2 dst 1.1.1.1 \ proto esp mode tunnel mark 1 ip xfrm state add src 1.1.1.1 dst 1.1.1.2 proto esp spi 1 \ mode tunnel enc des3_ede 0x112233445566778811223344556677881122334455667788 ip xfrm state add src 1.1.1.2 dst 1.1.1.1 proto esp spi 1 \ mode tunnel enc des3_ede 0x112233445566778811223344556677881122334455667788 ip netns exec secure ping -c 4 -i 0.02 -I 192.168.100.1 192.168.200.1 ip netns del secure <End script> Reported-by: Hangbin Liu <haliu@redhat.com> Reported-by: Jan Tluka <jtluka@redhat.com> Signed-off-by: Lance Richardson <lrichard@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-10 03:29:42 +08:00
register_netdevice_notifier(&vti_notifier_block);
msg = "tunnel device";
err = register_pernet_device(&vti_net_ops);
if (err < 0)
goto pernet_dev_failed;
msg = "tunnel protocols";
err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP);
if (err < 0)
goto xfrm_proto_esp_failed;
err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH);
if (err < 0)
goto xfrm_proto_ah_failed;
err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP);
if (err < 0)
goto xfrm_proto_comp_failed;
msg = "netlink interface";
err = rtnl_link_register(&vti_link_ops);
if (err < 0)
goto rtnl_link_failed;
return err;
rtnl_link_failed:
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
xfrm_proto_comp_failed:
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
xfrm_proto_esp_failed:
unregister_pernet_device(&vti_net_ops);
pernet_dev_failed:
vti: flush x-netns xfrm cache when vti interface is removed When executing the script included below, the netns delete operation hangs with the following message (repeated at 10 second intervals): kernel:unregister_netdevice: waiting for lo to become free. Usage count = 1 This occurs because a reference to the lo interface in the "secure" netns is still held by a dst entry in the xfrm bundle cache in the init netns. Address this problem by garbage collecting the tunnel netns flow cache when a cross-namespace vti interface receives a NETDEV_DOWN notification. A more detailed description of the problem scenario (referencing commands in the script below): (1) ip link add vti_test type vti local 1.1.1.1 remote 1.1.1.2 key 1 The vti_test interface is created in the init namespace. vti_tunnel_init() attaches a struct ip_tunnel to the vti interface's netdev_priv(dev), setting the tunnel net to &init_net. (2) ip link set vti_test netns secure The vti_test interface is moved to the "secure" netns. Note that the associated struct ip_tunnel still has tunnel->net set to &init_net. (3) ip netns exec secure ping -c 4 -i 0.02 -I 192.168.100.1 192.168.200.1 The first packet sent using the vti device causes xfrm_lookup() to be called as follows: dst = xfrm_lookup(tunnel->net, skb_dst(skb), fl, NULL, 0); Note that tunnel->net is the init namespace, while skb_dst(skb) references the vti_test interface in the "secure" namespace. The returned dst references an interface in the init namespace. Also note that the first parameter to xfrm_lookup() determines which flow cache is used to store the computed xfrm bundle, so after xfrm_lookup() returns there will be a cached bundle in the init namespace flow cache with a dst referencing a device in the "secure" namespace. (4) ip netns del secure Kernel begins to delete the "secure" namespace. At some point the vti_test interface is deleted, at which point dst_ifdown() changes the dst->dev in the cached xfrm bundle flow from vti_test to lo (still in the "secure" namespace however). Since nothing has happened to cause the init namespace's flow cache to be garbage collected, this dst remains attached to the flow cache, so the kernel loops waiting for the last reference to lo to go away. <Begin script> ip link add br1 type bridge ip link set dev br1 up ip addr add dev br1 1.1.1.1/8 ip netns add secure ip link add vti_test type vti local 1.1.1.1 remote 1.1.1.2 key 1 ip link set vti_test netns secure ip netns exec secure ip link set vti_test up ip netns exec secure ip link s lo up ip netns exec secure ip addr add dev lo 192.168.100.1/24 ip netns exec secure ip route add 192.168.200.0/24 dev vti_test ip xfrm policy flush ip xfrm state flush ip xfrm policy add dir out tmpl src 1.1.1.1 dst 1.1.1.2 \ proto esp mode tunnel mark 1 ip xfrm policy add dir in tmpl src 1.1.1.2 dst 1.1.1.1 \ proto esp mode tunnel mark 1 ip xfrm state add src 1.1.1.1 dst 1.1.1.2 proto esp spi 1 \ mode tunnel enc des3_ede 0x112233445566778811223344556677881122334455667788 ip xfrm state add src 1.1.1.2 dst 1.1.1.1 proto esp spi 1 \ mode tunnel enc des3_ede 0x112233445566778811223344556677881122334455667788 ip netns exec secure ping -c 4 -i 0.02 -I 192.168.100.1 192.168.200.1 ip netns del secure <End script> Reported-by: Hangbin Liu <haliu@redhat.com> Reported-by: Jan Tluka <jtluka@redhat.com> Signed-off-by: Lance Richardson <lrichard@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-10 03:29:42 +08:00
unregister_netdevice_notifier(&vti_notifier_block);
pr_err("vti init: failed to register %s\n", msg);
return err;
}
static void __exit vti_fini(void)
{
rtnl_link_unregister(&vti_link_ops);
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
unregister_pernet_device(&vti_net_ops);
vti: flush x-netns xfrm cache when vti interface is removed When executing the script included below, the netns delete operation hangs with the following message (repeated at 10 second intervals): kernel:unregister_netdevice: waiting for lo to become free. Usage count = 1 This occurs because a reference to the lo interface in the "secure" netns is still held by a dst entry in the xfrm bundle cache in the init netns. Address this problem by garbage collecting the tunnel netns flow cache when a cross-namespace vti interface receives a NETDEV_DOWN notification. A more detailed description of the problem scenario (referencing commands in the script below): (1) ip link add vti_test type vti local 1.1.1.1 remote 1.1.1.2 key 1 The vti_test interface is created in the init namespace. vti_tunnel_init() attaches a struct ip_tunnel to the vti interface's netdev_priv(dev), setting the tunnel net to &init_net. (2) ip link set vti_test netns secure The vti_test interface is moved to the "secure" netns. Note that the associated struct ip_tunnel still has tunnel->net set to &init_net. (3) ip netns exec secure ping -c 4 -i 0.02 -I 192.168.100.1 192.168.200.1 The first packet sent using the vti device causes xfrm_lookup() to be called as follows: dst = xfrm_lookup(tunnel->net, skb_dst(skb), fl, NULL, 0); Note that tunnel->net is the init namespace, while skb_dst(skb) references the vti_test interface in the "secure" namespace. The returned dst references an interface in the init namespace. Also note that the first parameter to xfrm_lookup() determines which flow cache is used to store the computed xfrm bundle, so after xfrm_lookup() returns there will be a cached bundle in the init namespace flow cache with a dst referencing a device in the "secure" namespace. (4) ip netns del secure Kernel begins to delete the "secure" namespace. At some point the vti_test interface is deleted, at which point dst_ifdown() changes the dst->dev in the cached xfrm bundle flow from vti_test to lo (still in the "secure" namespace however). Since nothing has happened to cause the init namespace's flow cache to be garbage collected, this dst remains attached to the flow cache, so the kernel loops waiting for the last reference to lo to go away. <Begin script> ip link add br1 type bridge ip link set dev br1 up ip addr add dev br1 1.1.1.1/8 ip netns add secure ip link add vti_test type vti local 1.1.1.1 remote 1.1.1.2 key 1 ip link set vti_test netns secure ip netns exec secure ip link set vti_test up ip netns exec secure ip link s lo up ip netns exec secure ip addr add dev lo 192.168.100.1/24 ip netns exec secure ip route add 192.168.200.0/24 dev vti_test ip xfrm policy flush ip xfrm state flush ip xfrm policy add dir out tmpl src 1.1.1.1 dst 1.1.1.2 \ proto esp mode tunnel mark 1 ip xfrm policy add dir in tmpl src 1.1.1.2 dst 1.1.1.1 \ proto esp mode tunnel mark 1 ip xfrm state add src 1.1.1.1 dst 1.1.1.2 proto esp spi 1 \ mode tunnel enc des3_ede 0x112233445566778811223344556677881122334455667788 ip xfrm state add src 1.1.1.2 dst 1.1.1.1 proto esp spi 1 \ mode tunnel enc des3_ede 0x112233445566778811223344556677881122334455667788 ip netns exec secure ping -c 4 -i 0.02 -I 192.168.100.1 192.168.200.1 ip netns del secure <End script> Reported-by: Hangbin Liu <haliu@redhat.com> Reported-by: Jan Tluka <jtluka@redhat.com> Signed-off-by: Lance Richardson <lrichard@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-10 03:29:42 +08:00
unregister_netdevice_notifier(&vti_notifier_block);
}
module_init(vti_init);
module_exit(vti_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("vti");
MODULE_ALIAS_NETDEV("ip_vti0");