linux/net/ipv4/udp_tunnel_core.c

208 lines
5.1 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/socket.h>
#include <linux/kernel.h>
#include <net/dst_metadata.h>
#include <net/udp.h>
#include <net/udp_tunnel.h>
int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
struct socket **sockp)
{
int err;
struct socket *sock = NULL;
struct sockaddr_in udp_addr;
err = sock_create_kern(net, AF_INET, SOCK_DGRAM, 0, &sock);
if (err < 0)
goto error;
if (cfg->bind_ifindex) {
err = sock_bindtoindex(sock->sk, cfg->bind_ifindex, true);
if (err < 0)
goto error;
}
udp_addr.sin_family = AF_INET;
udp_addr.sin_addr = cfg->local_ip;
udp_addr.sin_port = cfg->local_udp_port;
err = kernel_bind(sock, (struct sockaddr *)&udp_addr,
sizeof(udp_addr));
if (err < 0)
goto error;
if (cfg->peer_udp_port) {
udp_addr.sin_family = AF_INET;
udp_addr.sin_addr = cfg->peer_ip;
udp_addr.sin_port = cfg->peer_udp_port;
err = kernel_connect(sock, (struct sockaddr *)&udp_addr,
sizeof(udp_addr), 0);
if (err < 0)
goto error;
}
sock->sk->sk_no_check_tx = !cfg->use_udp_checksums;
*sockp = sock;
return 0;
error:
if (sock) {
kernel_sock_shutdown(sock, SHUT_RDWR);
sock_release(sock);
}
*sockp = NULL;
return err;
}
EXPORT_SYMBOL(udp_sock_create4);
void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
struct udp_tunnel_sock_cfg *cfg)
{
struct sock *sk = sock->sk;
/* Disable multicast loopback */
inet_sk(sk)->mc_loop = 0;
/* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
inet_inc_convert_csum(sk);
rcu_assign_sk_user_data(sk, cfg->sk_user_data);
udp_sk(sk)->encap_type = cfg->encap_type;
udp_sk(sk)->encap_rcv = cfg->encap_rcv;
udp_sk(sk)->encap_err_rcv = cfg->encap_err_rcv;
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 11:19:14 +00:00
udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup;
udp_sk(sk)->encap_destroy = cfg->encap_destroy;
udp_sk(sk)->gro_receive = cfg->gro_receive;
udp_sk(sk)->gro_complete = cfg->gro_complete;
udp_tunnel_encap_enable(sock);
}
EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
unsigned short type)
{
struct sock *sk = sock->sk;
struct udp_tunnel_info ti;
ti.type = type;
ti.sa_family = sk->sk_family;
ti.port = inet_sk(sk)->inet_sport;
udp_tunnel_nic_add_port(dev, &ti);
}
EXPORT_SYMBOL_GPL(udp_tunnel_push_rx_port);
void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock,
unsigned short type)
{
struct sock *sk = sock->sk;
struct udp_tunnel_info ti;
ti.type = type;
ti.sa_family = sk->sk_family;
ti.port = inet_sk(sk)->inet_sport;
udp_tunnel_nic_del_port(dev, &ti);
}
EXPORT_SYMBOL_GPL(udp_tunnel_drop_rx_port);
/* Notify netdevs that UDP port started listening */
void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
struct udp_tunnel_info ti;
struct net_device *dev;
ti.type = type;
ti.sa_family = sk->sk_family;
ti.port = inet_sk(sk)->inet_sport;
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
udp_tunnel_nic_add_port(dev, &ti);
}
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(udp_tunnel_notify_add_rx_port);
/* Notify netdevs that UDP port is no more listening */
void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
struct udp_tunnel_info ti;
struct net_device *dev;
ti.type = type;
ti.sa_family = sk->sk_family;
ti.port = inet_sk(sk)->inet_sport;
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
udp_tunnel_nic_del_port(dev, &ti);
}
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(udp_tunnel_notify_del_rx_port);
void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 tos, __u8 ttl,
__be16 df, __be16 src_port, __be16 dst_port,
bool xnet, bool nocheck)
{
struct udphdr *uh;
__skb_push(skb, sizeof(*uh));
skb_reset_transport_header(skb);
uh = udp_hdr(skb);
uh->dest = dst_port;
uh->source = src_port;
uh->len = htons(skb->len);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
udp_set_csum(nocheck, skb, src, dst, skb->len);
iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet);
}
EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb);
void udp_tunnel_sock_release(struct socket *sock)
{
rcu_assign_sk_user_data(sock->sk, NULL);
net/tunnel: wait until all sk_user_data reader finish before releasing the sock There is a race condition in vxlan that when deleting a vxlan device during receiving packets, there is a possibility that the sock is released after getting vxlan_sock vs from sk_user_data. Then in later vxlan_ecn_decapsulate(), vxlan_get_sk_family() we will got NULL pointer dereference. e.g. #0 [ffffa25ec6978a38] machine_kexec at ffffffff8c669757 #1 [ffffa25ec6978a90] __crash_kexec at ffffffff8c7c0a4d #2 [ffffa25ec6978b58] crash_kexec at ffffffff8c7c1c48 #3 [ffffa25ec6978b60] oops_end at ffffffff8c627f2b #4 [ffffa25ec6978b80] page_fault_oops at ffffffff8c678fcb #5 [ffffa25ec6978bd8] exc_page_fault at ffffffff8d109542 #6 [ffffa25ec6978c00] asm_exc_page_fault at ffffffff8d200b62 [exception RIP: vxlan_ecn_decapsulate+0x3b] RIP: ffffffffc1014e7b RSP: ffffa25ec6978cb0 RFLAGS: 00010246 RAX: 0000000000000008 RBX: ffff8aa000888000 RCX: 0000000000000000 RDX: 000000000000000e RSI: ffff8a9fc7ab803e RDI: ffff8a9fd1168700 RBP: ffff8a9fc7ab803e R8: 0000000000700000 R9: 00000000000010ae R10: ffff8a9fcb748980 R11: 0000000000000000 R12: ffff8a9fd1168700 R13: ffff8aa000888000 R14: 00000000002a0000 R15: 00000000000010ae ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 #7 [ffffa25ec6978ce8] vxlan_rcv at ffffffffc10189cd [vxlan] #8 [ffffa25ec6978d90] udp_queue_rcv_one_skb at ffffffff8cfb6507 #9 [ffffa25ec6978dc0] udp_unicast_rcv_skb at ffffffff8cfb6e45 #10 [ffffa25ec6978dc8] __udp4_lib_rcv at ffffffff8cfb8807 #11 [ffffa25ec6978e20] ip_protocol_deliver_rcu at ffffffff8cf76951 #12 [ffffa25ec6978e48] ip_local_deliver at ffffffff8cf76bde #13 [ffffa25ec6978ea0] __netif_receive_skb_one_core at ffffffff8cecde9b #14 [ffffa25ec6978ec8] process_backlog at ffffffff8cece139 #15 [ffffa25ec6978f00] __napi_poll at ffffffff8ceced1a #16 [ffffa25ec6978f28] net_rx_action at ffffffff8cecf1f3 #17 [ffffa25ec6978fa0] __softirqentry_text_start at ffffffff8d4000ca #18 [ffffa25ec6978ff0] do_softirq at ffffffff8c6fbdc3 Reproducer: https://github.com/Mellanox/ovs-tests/blob/master/test-ovs-vxlan-remove-tunnel-during-traffic.sh Fix this by waiting for all sk_user_data reader to finish before releasing the sock. Reported-by: Jianlin Shi <jishi@redhat.com> Suggested-by: Jakub Sitnicki <jakub@cloudflare.com> Fixes: 6a93cc905274 ("udp-tunnel: Add a few more UDP tunnel APIs") Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Reviewed-by: Jiri Pirko <jiri@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-12-08 12:04:52 +00:00
synchronize_rcu();
kernel_sock_shutdown(sock, SHUT_RDWR);
sock_release(sock);
}
EXPORT_SYMBOL_GPL(udp_tunnel_sock_release);
struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family,
__be16 flags, __be64 tunnel_id, int md_size)
{
struct metadata_dst *tun_dst;
struct ip_tunnel_info *info;
if (family == AF_INET)
tun_dst = ip_tun_rx_dst(skb, flags, tunnel_id, md_size);
else
tun_dst = ipv6_tun_rx_dst(skb, flags, tunnel_id, md_size);
if (!tun_dst)
return NULL;
info = &tun_dst->u.tun_info;
info->key.tp_src = udp_hdr(skb)->source;
info->key.tp_dst = udp_hdr(skb)->dest;
if (udp_hdr(skb)->check)
info->key.tun_flags |= TUNNEL_CSUM;
return tun_dst;
}
EXPORT_SYMBOL_GPL(udp_tun_rx_dst);
MODULE_LICENSE("GPL");