linux/net/ipv4/fou.c

1307 lines
28 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/skbuff.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/udp.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <net/genetlink.h>
#include <net/gue.h>
#include <net/fou.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/udp.h>
#include <net/udp_tunnel.h>
#include <net/xfrm.h>
#include <uapi/linux/fou.h>
#include <uapi/linux/genetlink.h>
struct fou {
struct socket *sock;
u8 protocol;
u8 flags;
__be16 port;
u8 family;
u16 type;
struct list_head list;
struct rcu_head rcu;
};
#define FOU_F_REMCSUM_NOPARTIAL BIT(0)
struct fou_cfg {
u16 type;
u8 protocol;
u8 flags;
struct udp_port_cfg udp_config;
};
static unsigned int fou_net_id;
struct fou_net {
struct list_head fou_list;
struct mutex fou_lock;
};
static inline struct fou *fou_from_sock(struct sock *sk)
{
return sk->sk_user_data;
}
static int fou_recv_pull(struct sk_buff *skb, struct fou *fou, size_t len)
{
/* Remove 'len' bytes from the packet (UDP header and
* FOU header if present).
*/
if (fou->family == AF_INET)
ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
else
ipv6_hdr(skb)->payload_len =
htons(ntohs(ipv6_hdr(skb)->payload_len) - len);
__skb_pull(skb, len);
skb_postpull_rcsum(skb, udp_hdr(skb), len);
skb_reset_transport_header(skb);
return iptunnel_pull_offloads(skb);
}
static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
{
struct fou *fou = fou_from_sock(sk);
if (!fou)
return 1;
if (fou_recv_pull(skb, fou, sizeof(struct udphdr)))
goto drop;
return -fou->protocol;
drop:
kfree_skb(skb);
return 0;
}
static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
void *data, size_t hdrlen, u8 ipproto,
bool nopartial)
{
__be16 *pd = data;
size_t start = ntohs(pd[0]);
size_t offset = ntohs(pd[1]);
size_t plen = sizeof(struct udphdr) + hdrlen +
max_t(size_t, offset + sizeof(u16), start);
if (skb->remcsum_offload)
return guehdr;
if (!pskb_may_pull(skb, plen))
return NULL;
guehdr = (struct guehdr *)&udp_hdr(skb)[1];
skb_remcsum_process(skb, (void *)guehdr + hdrlen,
start, offset, nopartial);
return guehdr;
}
static int gue_control_message(struct sk_buff *skb, struct guehdr *guehdr)
{
/* No support yet */
kfree_skb(skb);
return 0;
}
static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
{
struct fou *fou = fou_from_sock(sk);
size_t len, optlen, hdrlen;
struct guehdr *guehdr;
void *data;
u16 doffset = 0;
u8 proto_ctype;
if (!fou)
return 1;
len = sizeof(struct udphdr) + sizeof(struct guehdr);
if (!pskb_may_pull(skb, len))
goto drop;
guehdr = (struct guehdr *)&udp_hdr(skb)[1];
switch (guehdr->version) {
case 0: /* Full GUE header present */
break;
case 1: {
/* Direct encapsulation of IPv4 or IPv6 */
int prot;
switch (((struct iphdr *)guehdr)->version) {
case 4:
prot = IPPROTO_IPIP;
break;
case 6:
prot = IPPROTO_IPV6;
break;
default:
goto drop;
}
if (fou_recv_pull(skb, fou, sizeof(struct udphdr)))
goto drop;
return -prot;
}
default: /* Undefined version */
goto drop;
}
optlen = guehdr->hlen << 2;
len += optlen;
if (!pskb_may_pull(skb, len))
goto drop;
/* guehdr may change after pull */
guehdr = (struct guehdr *)&udp_hdr(skb)[1];
if (validate_gue_flags(guehdr, optlen))
goto drop;
hdrlen = sizeof(struct guehdr) + optlen;
if (fou->family == AF_INET)
ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
else
ipv6_hdr(skb)->payload_len =
htons(ntohs(ipv6_hdr(skb)->payload_len) - len);
/* Pull csum through the guehdr now . This can be used if
* there is a remote checksum offload.
*/
skb_postpull_rcsum(skb, udp_hdr(skb), len);
data = &guehdr[1];
if (guehdr->flags & GUE_FLAG_PRIV) {
__be32 flags = *(__be32 *)(data + doffset);
doffset += GUE_LEN_PRIV;
if (flags & GUE_PFLAG_REMCSUM) {
guehdr = gue_remcsum(skb, guehdr, data + doffset,
hdrlen, guehdr->proto_ctype,
!!(fou->flags &
FOU_F_REMCSUM_NOPARTIAL));
if (!guehdr)
goto drop;
data = &guehdr[1];
doffset += GUE_PLEN_REMCSUM;
}
}
if (unlikely(guehdr->control))
return gue_control_message(skb, guehdr);
proto_ctype = guehdr->proto_ctype;
__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
skb_reset_transport_header(skb);
if (iptunnel_pull_offloads(skb))
goto drop;
return -proto_ctype;
drop:
kfree_skb(skb);
return 0;
}
static struct sk_buff *fou_gro_receive(struct sock *sk,
struct list_head *head,
struct sk_buff *skb)
{
u8 proto = fou_from_sock(sk)->protocol;
const struct net_offload **offloads;
const struct net_offload *ops;
struct sk_buff *pp = NULL;
/* We can clear the encap_mark for FOU as we are essentially doing
* one of two possible things. We are either adding an L4 tunnel
* header to the outer L3 tunnel header, or we are are simply
* treating the GRE tunnel header as though it is a UDP protocol
* specific header such as VXLAN or GENEVE.
*/
NAPI_GRO_CB(skb)->encap_mark = 0;
/* Flag this frame as already having an outer encap header */
NAPI_GRO_CB(skb)->is_fou = 1;
rcu_read_lock();
offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
ops = rcu_dereference(offloads[proto]);
if (!ops || !ops->callbacks.gro_receive)
goto out_unlock;
pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
out_unlock:
rcu_read_unlock();
return pp;
}
static int fou_gro_complete(struct sock *sk, struct sk_buff *skb,
int nhoff)
{
const struct net_offload *ops;
u8 proto = fou_from_sock(sk)->protocol;
int err = -ENOSYS;
const struct net_offload **offloads;
rcu_read_lock();
offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
ops = rcu_dereference(offloads[proto]);
if (WARN_ON(!ops || !ops->callbacks.gro_complete))
goto out_unlock;
err = ops->callbacks.gro_complete(skb, nhoff);
skb_set_inner_mac_header(skb, nhoff);
out_unlock:
rcu_read_unlock();
return err;
}
static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
struct guehdr *guehdr, void *data,
size_t hdrlen, struct gro_remcsum *grc,
bool nopartial)
{
__be16 *pd = data;
size_t start = ntohs(pd[0]);
size_t offset = ntohs(pd[1]);
if (skb->remcsum_offload)
return guehdr;
if (!NAPI_GRO_CB(skb)->csum_valid)
return NULL;
guehdr = skb_gro_remcsum_process(skb, (void *)guehdr, off, hdrlen,
start, offset, grc, nopartial);
skb->remcsum_offload = 1;
return guehdr;
}
static struct sk_buff *gue_gro_receive(struct sock *sk,
struct list_head *head,
struct sk_buff *skb)
{
const struct net_offload **offloads;
const struct net_offload *ops;
struct sk_buff *pp = NULL;
struct sk_buff *p;
struct guehdr *guehdr;
size_t len, optlen, hdrlen, off;
void *data;
u16 doffset = 0;
int flush = 1;
struct fou *fou = fou_from_sock(sk);
struct gro_remcsum grc;
u8 proto;
skb_gro_remcsum_init(&grc);
off = skb_gro_offset(skb);
len = off + sizeof(*guehdr);
guehdr = skb_gro_header_fast(skb, off);
if (skb_gro_header_hard(skb, len)) {
guehdr = skb_gro_header_slow(skb, len, off);
if (unlikely(!guehdr))
goto out;
}
switch (guehdr->version) {
case 0:
break;
case 1:
switch (((struct iphdr *)guehdr)->version) {
case 4:
proto = IPPROTO_IPIP;
break;
case 6:
proto = IPPROTO_IPV6;
break;
default:
goto out;
}
goto next_proto;
default:
goto out;
}
optlen = guehdr->hlen << 2;
len += optlen;
if (skb_gro_header_hard(skb, len)) {
guehdr = skb_gro_header_slow(skb, len, off);
if (unlikely(!guehdr))
goto out;
}
if (unlikely(guehdr->control) || guehdr->version != 0 ||
validate_gue_flags(guehdr, optlen))
goto out;
hdrlen = sizeof(*guehdr) + optlen;
/* Adjust NAPI_GRO_CB(skb)->csum to account for guehdr,
* this is needed if there is a remote checkcsum offload.
*/
skb_gro_postpull_rcsum(skb, guehdr, hdrlen);
data = &guehdr[1];
if (guehdr->flags & GUE_FLAG_PRIV) {
__be32 flags = *(__be32 *)(data + doffset);
doffset += GUE_LEN_PRIV;
if (flags & GUE_PFLAG_REMCSUM) {
guehdr = gue_gro_remcsum(skb, off, guehdr,
data + doffset, hdrlen, &grc,
!!(fou->flags &
FOU_F_REMCSUM_NOPARTIAL));
if (!guehdr)
goto out;
data = &guehdr[1];
doffset += GUE_PLEN_REMCSUM;
}
}
skb_gro_pull(skb, hdrlen);
list_for_each_entry(p, head, list) {
const struct guehdr *guehdr2;
if (!NAPI_GRO_CB(p)->same_flow)
continue;
guehdr2 = (struct guehdr *)(p->data + off);
/* Compare base GUE header to be equal (covers
* hlen, version, proto_ctype, and flags.
*/
if (guehdr->word != guehdr2->word) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
/* Compare optional fields are the same. */
if (guehdr->hlen && memcmp(&guehdr[1], &guehdr2[1],
guehdr->hlen << 2)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
}
proto = guehdr->proto_ctype;
next_proto:
/* We can clear the encap_mark for GUE as we are essentially doing
* one of two possible things. We are either adding an L4 tunnel
* header to the outer L3 tunnel header, or we are are simply
* treating the GRE tunnel header as though it is a UDP protocol
* specific header such as VXLAN or GENEVE.
*/
NAPI_GRO_CB(skb)->encap_mark = 0;
/* Flag this frame as already having an outer encap header */
NAPI_GRO_CB(skb)->is_fou = 1;
rcu_read_lock();
offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
ops = rcu_dereference(offloads[proto]);
if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive))
goto out_unlock;
pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
flush = 0;
out_unlock:
rcu_read_unlock();
out:
skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
return pp;
}
static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
{
const struct net_offload **offloads;
struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff);
const struct net_offload *ops;
unsigned int guehlen = 0;
u8 proto;
int err = -ENOENT;
switch (guehdr->version) {
case 0:
proto = guehdr->proto_ctype;
guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);
break;
case 1:
switch (((struct iphdr *)guehdr)->version) {
case 4:
proto = IPPROTO_IPIP;
break;
case 6:
proto = IPPROTO_IPV6;
break;
default:
return err;
}
break;
default:
return err;
}
rcu_read_lock();
offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
ops = rcu_dereference(offloads[proto]);
if (WARN_ON(!ops || !ops->callbacks.gro_complete))
goto out_unlock;
err = ops->callbacks.gro_complete(skb, nhoff + guehlen);
skb_set_inner_mac_header(skb, nhoff + guehlen);
out_unlock:
rcu_read_unlock();
return err;
}
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
static bool fou_cfg_cmp(struct fou *fou, struct fou_cfg *cfg)
{
struct sock *sk = fou->sock->sk;
struct udp_port_cfg *udp_cfg = &cfg->udp_config;
if (fou->family != udp_cfg->family ||
fou->port != udp_cfg->local_udp_port ||
sk->sk_dport != udp_cfg->peer_udp_port ||
sk->sk_bound_dev_if != udp_cfg->bind_ifindex)
return false;
if (fou->family == AF_INET) {
if (sk->sk_rcv_saddr != udp_cfg->local_ip.s_addr ||
sk->sk_daddr != udp_cfg->peer_ip.s_addr)
return false;
else
return true;
#if IS_ENABLED(CONFIG_IPV6)
} else {
if (ipv6_addr_cmp(&sk->sk_v6_rcv_saddr, &udp_cfg->local_ip6) ||
ipv6_addr_cmp(&sk->sk_v6_daddr, &udp_cfg->peer_ip6))
return false;
else
return true;
#endif
}
return false;
}
static int fou_add_to_port_list(struct net *net, struct fou *fou,
struct fou_cfg *cfg)
{
struct fou_net *fn = net_generic(net, fou_net_id);
struct fou *fout;
mutex_lock(&fn->fou_lock);
list_for_each_entry(fout, &fn->fou_list, list) {
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
if (fou_cfg_cmp(fout, cfg)) {
mutex_unlock(&fn->fou_lock);
return -EALREADY;
}
}
list_add(&fou->list, &fn->fou_list);
mutex_unlock(&fn->fou_lock);
return 0;
}
static void fou_release(struct fou *fou)
{
struct socket *sock = fou->sock;
list_del(&fou->list);
udp_tunnel_sock_release(sock);
kfree_rcu(fou, rcu);
}
static int fou_create(struct net *net, struct fou_cfg *cfg,
struct socket **sockp)
{
struct socket *sock = NULL;
struct fou *fou = NULL;
struct sock *sk;
struct udp_tunnel_sock_cfg tunnel_cfg;
int err;
/* Open UDP socket */
err = udp_sock_create(net, &cfg->udp_config, &sock);
if (err < 0)
goto error;
/* Allocate FOU port structure */
fou = kzalloc(sizeof(*fou), GFP_KERNEL);
if (!fou) {
err = -ENOMEM;
goto error;
}
sk = sock->sk;
fou->port = cfg->udp_config.local_udp_port;
fou->family = cfg->udp_config.family;
fou->flags = cfg->flags;
fou->type = cfg->type;
fou->sock = sock;
memset(&tunnel_cfg, 0, sizeof(tunnel_cfg));
tunnel_cfg.encap_type = 1;
tunnel_cfg.sk_user_data = fou;
tunnel_cfg.encap_destroy = NULL;
/* Initial for fou type */
switch (cfg->type) {
case FOU_ENCAP_DIRECT:
tunnel_cfg.encap_rcv = fou_udp_recv;
tunnel_cfg.gro_receive = fou_gro_receive;
tunnel_cfg.gro_complete = fou_gro_complete;
fou->protocol = cfg->protocol;
break;
case FOU_ENCAP_GUE:
tunnel_cfg.encap_rcv = gue_udp_recv;
tunnel_cfg.gro_receive = gue_gro_receive;
tunnel_cfg.gro_complete = gue_gro_complete;
break;
default:
err = -EINVAL;
goto error;
}
setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
sk->sk_allocation = GFP_ATOMIC;
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
err = fou_add_to_port_list(net, fou, cfg);
if (err)
goto error;
if (sockp)
*sockp = sock;
return 0;
error:
kfree(fou);
if (sock)
udp_tunnel_sock_release(sock);
return err;
}
static int fou_destroy(struct net *net, struct fou_cfg *cfg)
{
struct fou_net *fn = net_generic(net, fou_net_id);
int err = -EINVAL;
struct fou *fou;
mutex_lock(&fn->fou_lock);
list_for_each_entry(fou, &fn->fou_list, list) {
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
if (fou_cfg_cmp(fou, cfg)) {
fou_release(fou);
err = 0;
break;
}
}
mutex_unlock(&fn->fou_lock);
return err;
}
static struct genl_family fou_nl_family;
static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
[FOU_ATTR_PORT] = { .type = NLA_U16, },
[FOU_ATTR_AF] = { .type = NLA_U8, },
[FOU_ATTR_IPPROTO] = { .type = NLA_U8, },
[FOU_ATTR_TYPE] = { .type = NLA_U8, },
[FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, },
[FOU_ATTR_LOCAL_V4] = { .type = NLA_U32, },
[FOU_ATTR_PEER_V4] = { .type = NLA_U32, },
[FOU_ATTR_LOCAL_V6] = { .type = sizeof(struct in6_addr), },
[FOU_ATTR_PEER_V6] = { .type = sizeof(struct in6_addr), },
[FOU_ATTR_PEER_PORT] = { .type = NLA_U16, },
[FOU_ATTR_IFINDEX] = { .type = NLA_S32, },
};
static int parse_nl_config(struct genl_info *info,
struct fou_cfg *cfg)
{
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
bool has_local = false, has_peer = false;
struct nlattr *attr;
int ifindex;
__be16 port;
memset(cfg, 0, sizeof(*cfg));
cfg->udp_config.family = AF_INET;
if (info->attrs[FOU_ATTR_AF]) {
u8 family = nla_get_u8(info->attrs[FOU_ATTR_AF]);
switch (family) {
case AF_INET:
break;
case AF_INET6:
cfg->udp_config.ipv6_v6only = 1;
break;
default:
return -EAFNOSUPPORT;
}
cfg->udp_config.family = family;
}
if (info->attrs[FOU_ATTR_PORT]) {
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
port = nla_get_be16(info->attrs[FOU_ATTR_PORT]);
cfg->udp_config.local_udp_port = port;
}
if (info->attrs[FOU_ATTR_IPPROTO])
cfg->protocol = nla_get_u8(info->attrs[FOU_ATTR_IPPROTO]);
if (info->attrs[FOU_ATTR_TYPE])
cfg->type = nla_get_u8(info->attrs[FOU_ATTR_TYPE]);
if (info->attrs[FOU_ATTR_REMCSUM_NOPARTIAL])
cfg->flags |= FOU_F_REMCSUM_NOPARTIAL;
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
if (cfg->udp_config.family == AF_INET) {
if (info->attrs[FOU_ATTR_LOCAL_V4]) {
attr = info->attrs[FOU_ATTR_LOCAL_V4];
cfg->udp_config.local_ip.s_addr = nla_get_in_addr(attr);
has_local = true;
}
if (info->attrs[FOU_ATTR_PEER_V4]) {
attr = info->attrs[FOU_ATTR_PEER_V4];
cfg->udp_config.peer_ip.s_addr = nla_get_in_addr(attr);
has_peer = true;
}
#if IS_ENABLED(CONFIG_IPV6)
} else {
if (info->attrs[FOU_ATTR_LOCAL_V6]) {
attr = info->attrs[FOU_ATTR_LOCAL_V6];
cfg->udp_config.local_ip6 = nla_get_in6_addr(attr);
has_local = true;
}
if (info->attrs[FOU_ATTR_PEER_V6]) {
attr = info->attrs[FOU_ATTR_PEER_V6];
cfg->udp_config.peer_ip6 = nla_get_in6_addr(attr);
has_peer = true;
}
#endif
}
if (has_peer) {
if (info->attrs[FOU_ATTR_PEER_PORT]) {
port = nla_get_be16(info->attrs[FOU_ATTR_PEER_PORT]);
cfg->udp_config.peer_udp_port = port;
} else {
return -EINVAL;
}
}
if (info->attrs[FOU_ATTR_IFINDEX]) {
if (!has_local)
return -EINVAL;
ifindex = nla_get_s32(info->attrs[FOU_ATTR_IFINDEX]);
cfg->udp_config.bind_ifindex = ifindex;
}
return 0;
}
static int fou_nl_cmd_add_port(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = genl_info_net(info);
struct fou_cfg cfg;
int err;
err = parse_nl_config(info, &cfg);
if (err)
return err;
return fou_create(net, &cfg, NULL);
}
static int fou_nl_cmd_rm_port(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = genl_info_net(info);
struct fou_cfg cfg;
int err;
err = parse_nl_config(info, &cfg);
if (err)
return err;
return fou_destroy(net, &cfg);
}
static int fou_fill_info(struct fou *fou, struct sk_buff *msg)
{
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
struct sock *sk = fou->sock->sk;
if (nla_put_u8(msg, FOU_ATTR_AF, fou->sock->sk->sk_family) ||
nla_put_be16(msg, FOU_ATTR_PORT, fou->port) ||
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
nla_put_be16(msg, FOU_ATTR_PEER_PORT, sk->sk_dport) ||
nla_put_u8(msg, FOU_ATTR_IPPROTO, fou->protocol) ||
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
nla_put_u8(msg, FOU_ATTR_TYPE, fou->type) ||
nla_put_s32(msg, FOU_ATTR_IFINDEX, sk->sk_bound_dev_if))
return -1;
if (fou->flags & FOU_F_REMCSUM_NOPARTIAL)
if (nla_put_flag(msg, FOU_ATTR_REMCSUM_NOPARTIAL))
return -1;
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
if (fou->sock->sk->sk_family == AF_INET) {
if (nla_put_in_addr(msg, FOU_ATTR_LOCAL_V4, sk->sk_rcv_saddr))
return -1;
if (nla_put_in_addr(msg, FOU_ATTR_PEER_V4, sk->sk_daddr))
return -1;
#if IS_ENABLED(CONFIG_IPV6)
} else {
if (nla_put_in6_addr(msg, FOU_ATTR_LOCAL_V6,
&sk->sk_v6_rcv_saddr))
return -1;
if (nla_put_in6_addr(msg, FOU_ATTR_PEER_V6, &sk->sk_v6_daddr))
return -1;
#endif
}
return 0;
}
static int fou_dump_info(struct fou *fou, u32 portid, u32 seq,
u32 flags, struct sk_buff *skb, u8 cmd)
{
void *hdr;
hdr = genlmsg_put(skb, portid, seq, &fou_nl_family, flags, cmd);
if (!hdr)
return -ENOMEM;
if (fou_fill_info(fou, skb) < 0)
goto nla_put_failure;
genlmsg_end(skb, hdr);
return 0;
nla_put_failure:
genlmsg_cancel(skb, hdr);
return -EMSGSIZE;
}
static int fou_nl_cmd_get_port(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = genl_info_net(info);
struct fou_net *fn = net_generic(net, fou_net_id);
struct sk_buff *msg;
struct fou_cfg cfg;
struct fou *fout;
__be16 port;
u8 family;
int ret;
ret = parse_nl_config(info, &cfg);
if (ret)
return ret;
port = cfg.udp_config.local_udp_port;
if (port == 0)
return -EINVAL;
family = cfg.udp_config.family;
if (family != AF_INET && family != AF_INET6)
return -EINVAL;
msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!msg)
return -ENOMEM;
ret = -ESRCH;
mutex_lock(&fn->fou_lock);
list_for_each_entry(fout, &fn->fou_list, list) {
fou: Support binding FoU socket An FoU socket is currently bound to the wildcard-address. While this works fine, there are several use-cases where the use of the wildcard-address is not desirable. For example, I use FoU on some multi-homed servers and would like to use FoU on only one of the interfaces. This commit adds support for binding FoU sockets to a given source address/interface, as well as connecting the socket to a given destination address/port. udp_tunnel already provides the required infrastructure, so most of the code added is for exposing and setting the different attributes (local address, peer address, etc.). The lookups performed when we add, delete or get an FoU-socket has also been updated to compare all the attributes a user can set. Since the comparison now involves several elements, I have added a separate comparison-function instead of open-coding. In order to test the code and ensure that the new comparison code works correctly, I started by creating a wildcard socket bound to port 1234 on my machine. I then tried to create a non-wildcarded socket bound to the same port, as well as fetching and deleting the socket (including source address, peer address or interface index in the netlink request). Both the create, fetch and delete request failed. Deleting/fetching the socket was only successful when my netlink request attributes matched those used to create the socket. I then repeated the tests, but with a socket bound to a local ip address, a socket bound to a local address + interface, and a bound socket that was also «connected» to a peer. Add only worked when no socket with the matching source address/interface (or wildcard) existed, while fetch/delete was only successful when all attributes matched. In addition to testing that the new code work, I also checked that the current behavior is kept. If none of the new attributes are provided, then an FoU-socket is configured as before (i.e., wildcarded). If any of the new attributes are provided, the FoU-socket is configured as expected. v1->v2: * Fixed building with IPv6 disabled (kbuild). * Fixed a return type warning and make the ugly comparison function more readable (kbuild). * Describe more in detail what has been tested (thanks David Miller). * Make peer port required if peer address is specified. Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 10:16:03 +00:00
if (fou_cfg_cmp(fout, &cfg)) {
ret = fou_dump_info(fout, info->snd_portid,
info->snd_seq, 0, msg,
info->genlhdr->cmd);
break;
}
}
mutex_unlock(&fn->fou_lock);
if (ret < 0)
goto out_free;
return genlmsg_reply(msg, info);
out_free:
nlmsg_free(msg);
return ret;
}
static int fou_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct fou_net *fn = net_generic(net, fou_net_id);
struct fou *fout;
int idx = 0, ret;
mutex_lock(&fn->fou_lock);
list_for_each_entry(fout, &fn->fou_list, list) {
if (idx++ < cb->args[0])
continue;
ret = fou_dump_info(fout, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
skb, FOU_CMD_GET);
if (ret)
break;
}
mutex_unlock(&fn->fou_lock);
cb->args[0] = idx;
return skb->len;
}
static const struct genl_ops fou_nl_ops[] = {
{
.cmd = FOU_CMD_ADD,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = fou_nl_cmd_add_port,
.flags = GENL_ADMIN_PERM,
},
{
.cmd = FOU_CMD_DEL,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = fou_nl_cmd_rm_port,
.flags = GENL_ADMIN_PERM,
},
{
.cmd = FOU_CMD_GET,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = fou_nl_cmd_get_port,
.dumpit = fou_nl_dump,
},
};
static struct genl_family fou_nl_family __ro_after_init = {
.hdrsize = 0,
.name = FOU_GENL_NAME,
.version = FOU_GENL_VERSION,
.maxattr = FOU_ATTR_MAX,
.policy = fou_nl_policy,
.netnsok = true,
.module = THIS_MODULE,
.ops = fou_nl_ops,
.n_ops = ARRAY_SIZE(fou_nl_ops),
};
size_t fou_encap_hlen(struct ip_tunnel_encap *e)
{
return sizeof(struct udphdr);
}
EXPORT_SYMBOL(fou_encap_hlen);
size_t gue_encap_hlen(struct ip_tunnel_encap *e)
{
size_t len;
bool need_priv = false;
len = sizeof(struct udphdr) + sizeof(struct guehdr);
if (e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) {
len += GUE_PLEN_REMCSUM;
need_priv = true;
}
len += need_priv ? GUE_LEN_PRIV : 0;
return len;
}
EXPORT_SYMBOL(gue_encap_hlen);
int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
u8 *protocol, __be16 *sport, int type)
{
int err;
err = iptunnel_handle_offloads(skb, type);
if (err)
return err;
*sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
skb, 0, 0, false);
return 0;
}
EXPORT_SYMBOL(__fou_build_header);
int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
u8 *protocol, __be16 *sport, int type)
{
struct guehdr *guehdr;
size_t hdrlen, optlen = 0;
void *data;
bool need_priv = false;
int err;
if ((e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) &&
skb->ip_summed == CHECKSUM_PARTIAL) {
optlen += GUE_PLEN_REMCSUM;
type |= SKB_GSO_TUNNEL_REMCSUM;
need_priv = true;
}
optlen += need_priv ? GUE_LEN_PRIV : 0;
err = iptunnel_handle_offloads(skb, type);
if (err)
return err;
/* Get source port (based on flow hash) before skb_push */
*sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
skb, 0, 0, false);
hdrlen = sizeof(struct guehdr) + optlen;
skb_push(skb, hdrlen);
guehdr = (struct guehdr *)skb->data;
guehdr->control = 0;
guehdr->version = 0;
guehdr->hlen = optlen >> 2;
guehdr->flags = 0;
guehdr->proto_ctype = *protocol;
data = &guehdr[1];
if (need_priv) {
__be32 *flags = data;
guehdr->flags |= GUE_FLAG_PRIV;
*flags = 0;
data += GUE_LEN_PRIV;
if (type & SKB_GSO_TUNNEL_REMCSUM) {
u16 csum_start = skb_checksum_start_offset(skb);
__be16 *pd = data;
if (csum_start < hdrlen)
return -EINVAL;
csum_start -= hdrlen;
pd[0] = htons(csum_start);
pd[1] = htons(csum_start + skb->csum_offset);
if (!skb_is_gso(skb)) {
skb->ip_summed = CHECKSUM_NONE;
skb->encapsulation = 0;
}
*flags |= GUE_PFLAG_REMCSUM;
data += GUE_PLEN_REMCSUM;
}
}
return 0;
}
EXPORT_SYMBOL(__gue_build_header);
#ifdef CONFIG_NET_FOU_IP_TUNNELS
static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e,
struct flowi4 *fl4, u8 *protocol, __be16 sport)
{
struct udphdr *uh;
skb_push(skb, sizeof(struct udphdr));
skb_reset_transport_header(skb);
uh = udp_hdr(skb);
uh->dest = e->dport;
uh->source = sport;
uh->len = htons(skb->len);
udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb,
fl4->saddr, fl4->daddr, skb->len);
*protocol = IPPROTO_UDP;
}
static int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
u8 *protocol, struct flowi4 *fl4)
{
int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM :
SKB_GSO_UDP_TUNNEL;
__be16 sport;
int err;
err = __fou_build_header(skb, e, protocol, &sport, type);
if (err)
return err;
fou_build_udp(skb, e, fl4, protocol, sport);
return 0;
}
static int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
u8 *protocol, struct flowi4 *fl4)
{
int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM :
SKB_GSO_UDP_TUNNEL;
__be16 sport;
int err;
err = __gue_build_header(skb, e, protocol, &sport, type);
if (err)
return err;
fou_build_udp(skb, e, fl4, protocol, sport);
return 0;
}
static int gue_err_proto_handler(int proto, struct sk_buff *skb, u32 info)
{
const struct net_protocol *ipprot = rcu_dereference(inet_protos[proto]);
if (ipprot && ipprot->err_handler) {
if (!ipprot->err_handler(skb, info))
return 0;
}
return -ENOENT;
}
static int gue_err(struct sk_buff *skb, u32 info)
{
int transport_offset = skb_transport_offset(skb);
struct guehdr *guehdr;
fou, fou6: do not assume linear skbs Both gue_err() and gue6_err() incorrectly assume linear skbs. Fix them to use pskb_may_pull(). BUG: KMSAN: uninit-value in gue6_err+0x475/0xc40 net/ipv6/fou6.c:101 CPU: 0 PID: 18083 Comm: syz-executor1 Not tainted 5.0.0-rc1+ #7 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:600 __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:313 gue6_err+0x475/0xc40 net/ipv6/fou6.c:101 __udp6_lib_err_encap_no_sk net/ipv6/udp.c:434 [inline] __udp6_lib_err_encap net/ipv6/udp.c:491 [inline] __udp6_lib_err+0x18d0/0x2590 net/ipv6/udp.c:522 udplitev6_err+0x118/0x130 net/ipv6/udplite.c:27 icmpv6_notify+0x462/0x9f0 net/ipv6/icmp.c:784 icmpv6_rcv+0x18ac/0x3fa0 net/ipv6/icmp.c:872 ip6_protocol_deliver_rcu+0xb5a/0x23a0 net/ipv6/ip6_input.c:394 ip6_input_finish net/ipv6/ip6_input.c:434 [inline] NF_HOOK include/linux/netfilter.h:289 [inline] ip6_input+0x2b6/0x350 net/ipv6/ip6_input.c:443 dst_input include/net/dst.h:450 [inline] ip6_rcv_finish+0x4e7/0x6d0 net/ipv6/ip6_input.c:76 NF_HOOK include/linux/netfilter.h:289 [inline] ipv6_rcv+0x34b/0x3f0 net/ipv6/ip6_input.c:272 __netif_receive_skb_one_core net/core/dev.c:4973 [inline] __netif_receive_skb net/core/dev.c:5083 [inline] process_backlog+0x756/0x10e0 net/core/dev.c:5923 napi_poll net/core/dev.c:6346 [inline] net_rx_action+0x78b/0x1a60 net/core/dev.c:6412 __do_softirq+0x53f/0x93a kernel/softirq.c:293 do_softirq_own_stack+0x49/0x80 arch/x86/entry/entry_64.S:1039 </IRQ> do_softirq kernel/softirq.c:338 [inline] __local_bh_enable_ip+0x16f/0x1a0 kernel/softirq.c:190 local_bh_enable+0x36/0x40 include/linux/bottom_half.h:32 rcu_read_unlock_bh include/linux/rcupdate.h:696 [inline] ip6_finish_output2+0x1d64/0x25f0 net/ipv6/ip6_output.c:121 ip6_finish_output+0xae4/0xbc0 net/ipv6/ip6_output.c:154 NF_HOOK_COND include/linux/netfilter.h:278 [inline] ip6_output+0x5ca/0x710 net/ipv6/ip6_output.c:171 dst_output include/net/dst.h:444 [inline] ip6_local_out+0x164/0x1d0 net/ipv6/output_core.c:176 ip6_send_skb+0xfa/0x390 net/ipv6/ip6_output.c:1727 udp_v6_send_skb+0x1733/0x1d20 net/ipv6/udp.c:1169 udpv6_sendmsg+0x424e/0x45d0 net/ipv6/udp.c:1466 inet_sendmsg+0x54a/0x720 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xdb9/0x11b0 net/socket.c:2116 __sys_sendmmsg+0x580/0xad0 net/socket.c:2211 __do_sys_sendmmsg net/socket.c:2240 [inline] __se_sys_sendmmsg+0xbd/0xe0 net/socket.c:2237 __x64_sys_sendmmsg+0x56/0x70 net/socket.c:2237 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x457ec9 Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f4a5204fc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 0000000000457ec9 RDX: 00000000040001ab RSI: 0000000020000240 RDI: 0000000000000003 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f4a520506d4 R13: 00000000004c4ce5 R14: 00000000004d85d8 R15: 00000000ffffffff Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:205 [inline] kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:159 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185 slab_post_alloc_hook mm/slab.h:446 [inline] slab_alloc_node mm/slub.c:2754 [inline] __kmalloc_node_track_caller+0xe9e/0xff0 mm/slub.c:4377 __kmalloc_reserve net/core/skbuff.c:140 [inline] __alloc_skb+0x309/0xa20 net/core/skbuff.c:208 alloc_skb include/linux/skbuff.h:1012 [inline] alloc_skb_with_frags+0x1c7/0xac0 net/core/skbuff.c:5288 sock_alloc_send_pskb+0xafd/0x10a0 net/core/sock.c:2091 sock_alloc_send_skb+0xca/0xe0 net/core/sock.c:2108 __ip6_append_data+0x42ed/0x5dc0 net/ipv6/ip6_output.c:1443 ip6_append_data+0x3c2/0x650 net/ipv6/ip6_output.c:1619 icmp6_send+0x2f5c/0x3c40 net/ipv6/icmp.c:574 icmpv6_send+0xe5/0x110 net/ipv6/ip6_icmp.c:43 ip6_link_failure+0x5c/0x2c0 net/ipv6/route.c:2231 dst_link_failure include/net/dst.h:427 [inline] vti_xmit net/ipv4/ip_vti.c:229 [inline] vti_tunnel_xmit+0xf3b/0x1ea0 net/ipv4/ip_vti.c:265 __netdev_start_xmit include/linux/netdevice.h:4382 [inline] netdev_start_xmit include/linux/netdevice.h:4391 [inline] xmit_one net/core/dev.c:3278 [inline] dev_hard_start_xmit+0x604/0xc40 net/core/dev.c:3294 __dev_queue_xmit+0x2e48/0x3b80 net/core/dev.c:3864 dev_queue_xmit+0x4b/0x60 net/core/dev.c:3897 neigh_direct_output+0x42/0x50 net/core/neighbour.c:1511 neigh_output include/net/neighbour.h:508 [inline] ip6_finish_output2+0x1d4e/0x25f0 net/ipv6/ip6_output.c:120 ip6_finish_output+0xae4/0xbc0 net/ipv6/ip6_output.c:154 NF_HOOK_COND include/linux/netfilter.h:278 [inline] ip6_output+0x5ca/0x710 net/ipv6/ip6_output.c:171 dst_output include/net/dst.h:444 [inline] ip6_local_out+0x164/0x1d0 net/ipv6/output_core.c:176 ip6_send_skb+0xfa/0x390 net/ipv6/ip6_output.c:1727 udp_v6_send_skb+0x1733/0x1d20 net/ipv6/udp.c:1169 udpv6_sendmsg+0x424e/0x45d0 net/ipv6/udp.c:1466 inet_sendmsg+0x54a/0x720 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xdb9/0x11b0 net/socket.c:2116 __sys_sendmmsg+0x580/0xad0 net/socket.c:2211 __do_sys_sendmmsg net/socket.c:2240 [inline] __se_sys_sendmmsg+0xbd/0xe0 net/socket.c:2237 __x64_sys_sendmmsg+0x56/0x70 net/socket.c:2237 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 Fixes: b8a51b38e4d4 ("fou, fou6: ICMP error handlers for FoU and GUE") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Stefano Brivio <sbrivio@redhat.com> Cc: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-11 14:27:35 +00:00
size_t len, optlen;
int ret;
fou, fou6: do not assume linear skbs Both gue_err() and gue6_err() incorrectly assume linear skbs. Fix them to use pskb_may_pull(). BUG: KMSAN: uninit-value in gue6_err+0x475/0xc40 net/ipv6/fou6.c:101 CPU: 0 PID: 18083 Comm: syz-executor1 Not tainted 5.0.0-rc1+ #7 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:600 __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:313 gue6_err+0x475/0xc40 net/ipv6/fou6.c:101 __udp6_lib_err_encap_no_sk net/ipv6/udp.c:434 [inline] __udp6_lib_err_encap net/ipv6/udp.c:491 [inline] __udp6_lib_err+0x18d0/0x2590 net/ipv6/udp.c:522 udplitev6_err+0x118/0x130 net/ipv6/udplite.c:27 icmpv6_notify+0x462/0x9f0 net/ipv6/icmp.c:784 icmpv6_rcv+0x18ac/0x3fa0 net/ipv6/icmp.c:872 ip6_protocol_deliver_rcu+0xb5a/0x23a0 net/ipv6/ip6_input.c:394 ip6_input_finish net/ipv6/ip6_input.c:434 [inline] NF_HOOK include/linux/netfilter.h:289 [inline] ip6_input+0x2b6/0x350 net/ipv6/ip6_input.c:443 dst_input include/net/dst.h:450 [inline] ip6_rcv_finish+0x4e7/0x6d0 net/ipv6/ip6_input.c:76 NF_HOOK include/linux/netfilter.h:289 [inline] ipv6_rcv+0x34b/0x3f0 net/ipv6/ip6_input.c:272 __netif_receive_skb_one_core net/core/dev.c:4973 [inline] __netif_receive_skb net/core/dev.c:5083 [inline] process_backlog+0x756/0x10e0 net/core/dev.c:5923 napi_poll net/core/dev.c:6346 [inline] net_rx_action+0x78b/0x1a60 net/core/dev.c:6412 __do_softirq+0x53f/0x93a kernel/softirq.c:293 do_softirq_own_stack+0x49/0x80 arch/x86/entry/entry_64.S:1039 </IRQ> do_softirq kernel/softirq.c:338 [inline] __local_bh_enable_ip+0x16f/0x1a0 kernel/softirq.c:190 local_bh_enable+0x36/0x40 include/linux/bottom_half.h:32 rcu_read_unlock_bh include/linux/rcupdate.h:696 [inline] ip6_finish_output2+0x1d64/0x25f0 net/ipv6/ip6_output.c:121 ip6_finish_output+0xae4/0xbc0 net/ipv6/ip6_output.c:154 NF_HOOK_COND include/linux/netfilter.h:278 [inline] ip6_output+0x5ca/0x710 net/ipv6/ip6_output.c:171 dst_output include/net/dst.h:444 [inline] ip6_local_out+0x164/0x1d0 net/ipv6/output_core.c:176 ip6_send_skb+0xfa/0x390 net/ipv6/ip6_output.c:1727 udp_v6_send_skb+0x1733/0x1d20 net/ipv6/udp.c:1169 udpv6_sendmsg+0x424e/0x45d0 net/ipv6/udp.c:1466 inet_sendmsg+0x54a/0x720 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xdb9/0x11b0 net/socket.c:2116 __sys_sendmmsg+0x580/0xad0 net/socket.c:2211 __do_sys_sendmmsg net/socket.c:2240 [inline] __se_sys_sendmmsg+0xbd/0xe0 net/socket.c:2237 __x64_sys_sendmmsg+0x56/0x70 net/socket.c:2237 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x457ec9 Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f4a5204fc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 0000000000457ec9 RDX: 00000000040001ab RSI: 0000000020000240 RDI: 0000000000000003 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f4a520506d4 R13: 00000000004c4ce5 R14: 00000000004d85d8 R15: 00000000ffffffff Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:205 [inline] kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:159 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185 slab_post_alloc_hook mm/slab.h:446 [inline] slab_alloc_node mm/slub.c:2754 [inline] __kmalloc_node_track_caller+0xe9e/0xff0 mm/slub.c:4377 __kmalloc_reserve net/core/skbuff.c:140 [inline] __alloc_skb+0x309/0xa20 net/core/skbuff.c:208 alloc_skb include/linux/skbuff.h:1012 [inline] alloc_skb_with_frags+0x1c7/0xac0 net/core/skbuff.c:5288 sock_alloc_send_pskb+0xafd/0x10a0 net/core/sock.c:2091 sock_alloc_send_skb+0xca/0xe0 net/core/sock.c:2108 __ip6_append_data+0x42ed/0x5dc0 net/ipv6/ip6_output.c:1443 ip6_append_data+0x3c2/0x650 net/ipv6/ip6_output.c:1619 icmp6_send+0x2f5c/0x3c40 net/ipv6/icmp.c:574 icmpv6_send+0xe5/0x110 net/ipv6/ip6_icmp.c:43 ip6_link_failure+0x5c/0x2c0 net/ipv6/route.c:2231 dst_link_failure include/net/dst.h:427 [inline] vti_xmit net/ipv4/ip_vti.c:229 [inline] vti_tunnel_xmit+0xf3b/0x1ea0 net/ipv4/ip_vti.c:265 __netdev_start_xmit include/linux/netdevice.h:4382 [inline] netdev_start_xmit include/linux/netdevice.h:4391 [inline] xmit_one net/core/dev.c:3278 [inline] dev_hard_start_xmit+0x604/0xc40 net/core/dev.c:3294 __dev_queue_xmit+0x2e48/0x3b80 net/core/dev.c:3864 dev_queue_xmit+0x4b/0x60 net/core/dev.c:3897 neigh_direct_output+0x42/0x50 net/core/neighbour.c:1511 neigh_output include/net/neighbour.h:508 [inline] ip6_finish_output2+0x1d4e/0x25f0 net/ipv6/ip6_output.c:120 ip6_finish_output+0xae4/0xbc0 net/ipv6/ip6_output.c:154 NF_HOOK_COND include/linux/netfilter.h:278 [inline] ip6_output+0x5ca/0x710 net/ipv6/ip6_output.c:171 dst_output include/net/dst.h:444 [inline] ip6_local_out+0x164/0x1d0 net/ipv6/output_core.c:176 ip6_send_skb+0xfa/0x390 net/ipv6/ip6_output.c:1727 udp_v6_send_skb+0x1733/0x1d20 net/ipv6/udp.c:1169 udpv6_sendmsg+0x424e/0x45d0 net/ipv6/udp.c:1466 inet_sendmsg+0x54a/0x720 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xdb9/0x11b0 net/socket.c:2116 __sys_sendmmsg+0x580/0xad0 net/socket.c:2211 __do_sys_sendmmsg net/socket.c:2240 [inline] __se_sys_sendmmsg+0xbd/0xe0 net/socket.c:2237 __x64_sys_sendmmsg+0x56/0x70 net/socket.c:2237 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 Fixes: b8a51b38e4d4 ("fou, fou6: ICMP error handlers for FoU and GUE") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Stefano Brivio <sbrivio@redhat.com> Cc: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-11 14:27:35 +00:00
len = sizeof(struct udphdr) + sizeof(struct guehdr);
fou, fou6: avoid uninit-value in gue_err() and gue6_err() My prior commit missed the fact that these functions were using udp_hdr() (aka skb_transport_header()) to get access to GUE header. Since pskb_transport_may_pull() does not exist yet, we have to add transport_offset to our pskb_may_pull() calls. BUG: KMSAN: uninit-value in gue_err+0x514/0xfa0 net/ipv4/fou.c:1032 CPU: 1 PID: 10648 Comm: syz-executor.1 Not tainted 5.0.0+ #11 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:600 __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:313 gue_err+0x514/0xfa0 net/ipv4/fou.c:1032 __udp4_lib_err_encap_no_sk net/ipv4/udp.c:571 [inline] __udp4_lib_err_encap net/ipv4/udp.c:626 [inline] __udp4_lib_err+0x12e6/0x1d40 net/ipv4/udp.c:665 udp_err+0x74/0x90 net/ipv4/udp.c:737 icmp_socket_deliver net/ipv4/icmp.c:767 [inline] icmp_unreach+0xb65/0x1070 net/ipv4/icmp.c:884 icmp_rcv+0x11a1/0x1950 net/ipv4/icmp.c:1066 ip_protocol_deliver_rcu+0x584/0xbb0 net/ipv4/ip_input.c:208 ip_local_deliver_finish net/ipv4/ip_input.c:234 [inline] NF_HOOK include/linux/netfilter.h:289 [inline] ip_local_deliver+0x624/0x7b0 net/ipv4/ip_input.c:255 dst_input include/net/dst.h:450 [inline] ip_rcv_finish net/ipv4/ip_input.c:414 [inline] NF_HOOK include/linux/netfilter.h:289 [inline] ip_rcv+0x6bd/0x740 net/ipv4/ip_input.c:524 __netif_receive_skb_one_core net/core/dev.c:4973 [inline] __netif_receive_skb net/core/dev.c:5083 [inline] process_backlog+0x756/0x10e0 net/core/dev.c:5923 napi_poll net/core/dev.c:6346 [inline] net_rx_action+0x78b/0x1a60 net/core/dev.c:6412 __do_softirq+0x53f/0x93a kernel/softirq.c:293 invoke_softirq kernel/softirq.c:375 [inline] irq_exit+0x214/0x250 kernel/softirq.c:416 exiting_irq+0xe/0x10 arch/x86/include/asm/apic.h:536 smp_apic_timer_interrupt+0x48/0x70 arch/x86/kernel/apic/apic.c:1064 apic_timer_interrupt+0x2e/0x40 arch/x86/entry/entry_64.S:814 </IRQ> RIP: 0010:finish_lock_switch+0x2b/0x40 kernel/sched/core.c:2597 Code: 48 89 e5 53 48 89 fb e8 63 e7 95 00 8b b8 88 0c 00 00 48 8b 00 48 85 c0 75 12 48 89 df e8 dd db 95 00 c6 00 00 c6 03 00 fb 5b <5d> c3 e8 4e e6 95 00 eb e7 66 90 66 2e 0f 1f 84 00 00 00 00 00 55 RSP: 0018:ffff888081a0fc80 EFLAGS: 00000296 ORIG_RAX: ffffffffffffff13 RAX: ffff88821fd6bd80 RBX: ffff888027898000 RCX: ccccccccccccd000 RDX: ffff88821fca8d80 RSI: ffff888000000000 RDI: 00000000000004a0 RBP: ffff888081a0fc80 R08: 0000000000000002 R09: ffff888081a0fb08 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001 R13: ffff88811130e388 R14: ffff88811130da00 R15: ffff88812fdb7d80 finish_task_switch+0xfc/0x2d0 kernel/sched/core.c:2698 context_switch kernel/sched/core.c:2851 [inline] __schedule+0x6cc/0x800 kernel/sched/core.c:3491 schedule+0x15b/0x240 kernel/sched/core.c:3535 freezable_schedule include/linux/freezer.h:172 [inline] do_nanosleep+0x2ba/0x980 kernel/time/hrtimer.c:1679 hrtimer_nanosleep kernel/time/hrtimer.c:1733 [inline] __do_sys_nanosleep kernel/time/hrtimer.c:1767 [inline] __se_sys_nanosleep+0x746/0x960 kernel/time/hrtimer.c:1754 __x64_sys_nanosleep+0x3e/0x60 kernel/time/hrtimer.c:1754 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x4855a0 Code: 00 00 48 c7 c0 d4 ff ff ff 64 c7 00 16 00 00 00 31 c0 eb be 66 0f 1f 44 00 00 83 3d b1 11 5d 00 00 75 14 b8 23 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 04 e2 f8 ff c3 48 83 ec 08 e8 3a 55 fd ff RSP: 002b:0000000000a4fd58 EFLAGS: 00000246 ORIG_RAX: 0000000000000023 RAX: ffffffffffffffda RBX: 0000000000085780 RCX: 00000000004855a0 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000a4fd60 RBP: 00000000000007ec R08: 0000000000000001 R09: 0000000000ceb940 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000008 R13: 0000000000a4fdb0 R14: 0000000000085711 R15: 0000000000a4fdc0 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:205 [inline] kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:159 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185 slab_post_alloc_hook mm/slab.h:445 [inline] slab_alloc_node mm/slub.c:2773 [inline] __kmalloc_node_track_caller+0xe9e/0xff0 mm/slub.c:4398 __kmalloc_reserve net/core/skbuff.c:140 [inline] __alloc_skb+0x309/0xa20 net/core/skbuff.c:208 alloc_skb include/linux/skbuff.h:1012 [inline] alloc_skb_with_frags+0x186/0xa60 net/core/skbuff.c:5287 sock_alloc_send_pskb+0xafd/0x10a0 net/core/sock.c:2091 sock_alloc_send_skb+0xca/0xe0 net/core/sock.c:2108 __ip_append_data+0x34cd/0x5000 net/ipv4/ip_output.c:998 ip_append_data+0x324/0x480 net/ipv4/ip_output.c:1220 icmp_push_reply+0x23d/0x7e0 net/ipv4/icmp.c:375 __icmp_send+0x2ea3/0x30f0 net/ipv4/icmp.c:737 icmp_send include/net/icmp.h:47 [inline] ipv4_link_failure+0x6d/0x230 net/ipv4/route.c:1190 dst_link_failure include/net/dst.h:427 [inline] arp_error_report+0x106/0x1a0 net/ipv4/arp.c:297 neigh_invalidate+0x359/0x8e0 net/core/neighbour.c:992 neigh_timer_handler+0xdf2/0x1280 net/core/neighbour.c:1078 call_timer_fn+0x285/0x600 kernel/time/timer.c:1325 expire_timers kernel/time/timer.c:1362 [inline] __run_timers+0xdb4/0x11d0 kernel/time/timer.c:1681 run_timer_softirq+0x2e/0x50 kernel/time/timer.c:1694 __do_softirq+0x53f/0x93a kernel/softirq.c:293 Fixes: 26fc181e6cac ("fou, fou6: do not assume linear skbs") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Stefano Brivio <sbrivio@redhat.com> Cc: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Stefano Brivio <sbrivio@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-06 18:41:00 +00:00
if (!pskb_may_pull(skb, transport_offset + len))
return -EINVAL;
guehdr = (struct guehdr *)&udp_hdr(skb)[1];
switch (guehdr->version) {
case 0: /* Full GUE header present */
break;
case 1: {
/* Direct encapsulation of IPv4 or IPv6 */
skb_set_transport_header(skb, -(int)sizeof(struct icmphdr));
switch (((struct iphdr *)guehdr)->version) {
case 4:
ret = gue_err_proto_handler(IPPROTO_IPIP, skb, info);
goto out;
#if IS_ENABLED(CONFIG_IPV6)
case 6:
ret = gue_err_proto_handler(IPPROTO_IPV6, skb, info);
goto out;
#endif
default:
ret = -EOPNOTSUPP;
goto out;
}
}
default: /* Undefined version */
return -EOPNOTSUPP;
}
if (guehdr->control)
return -ENOENT;
optlen = guehdr->hlen << 2;
fou, fou6: avoid uninit-value in gue_err() and gue6_err() My prior commit missed the fact that these functions were using udp_hdr() (aka skb_transport_header()) to get access to GUE header. Since pskb_transport_may_pull() does not exist yet, we have to add transport_offset to our pskb_may_pull() calls. BUG: KMSAN: uninit-value in gue_err+0x514/0xfa0 net/ipv4/fou.c:1032 CPU: 1 PID: 10648 Comm: syz-executor.1 Not tainted 5.0.0+ #11 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:600 __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:313 gue_err+0x514/0xfa0 net/ipv4/fou.c:1032 __udp4_lib_err_encap_no_sk net/ipv4/udp.c:571 [inline] __udp4_lib_err_encap net/ipv4/udp.c:626 [inline] __udp4_lib_err+0x12e6/0x1d40 net/ipv4/udp.c:665 udp_err+0x74/0x90 net/ipv4/udp.c:737 icmp_socket_deliver net/ipv4/icmp.c:767 [inline] icmp_unreach+0xb65/0x1070 net/ipv4/icmp.c:884 icmp_rcv+0x11a1/0x1950 net/ipv4/icmp.c:1066 ip_protocol_deliver_rcu+0x584/0xbb0 net/ipv4/ip_input.c:208 ip_local_deliver_finish net/ipv4/ip_input.c:234 [inline] NF_HOOK include/linux/netfilter.h:289 [inline] ip_local_deliver+0x624/0x7b0 net/ipv4/ip_input.c:255 dst_input include/net/dst.h:450 [inline] ip_rcv_finish net/ipv4/ip_input.c:414 [inline] NF_HOOK include/linux/netfilter.h:289 [inline] ip_rcv+0x6bd/0x740 net/ipv4/ip_input.c:524 __netif_receive_skb_one_core net/core/dev.c:4973 [inline] __netif_receive_skb net/core/dev.c:5083 [inline] process_backlog+0x756/0x10e0 net/core/dev.c:5923 napi_poll net/core/dev.c:6346 [inline] net_rx_action+0x78b/0x1a60 net/core/dev.c:6412 __do_softirq+0x53f/0x93a kernel/softirq.c:293 invoke_softirq kernel/softirq.c:375 [inline] irq_exit+0x214/0x250 kernel/softirq.c:416 exiting_irq+0xe/0x10 arch/x86/include/asm/apic.h:536 smp_apic_timer_interrupt+0x48/0x70 arch/x86/kernel/apic/apic.c:1064 apic_timer_interrupt+0x2e/0x40 arch/x86/entry/entry_64.S:814 </IRQ> RIP: 0010:finish_lock_switch+0x2b/0x40 kernel/sched/core.c:2597 Code: 48 89 e5 53 48 89 fb e8 63 e7 95 00 8b b8 88 0c 00 00 48 8b 00 48 85 c0 75 12 48 89 df e8 dd db 95 00 c6 00 00 c6 03 00 fb 5b <5d> c3 e8 4e e6 95 00 eb e7 66 90 66 2e 0f 1f 84 00 00 00 00 00 55 RSP: 0018:ffff888081a0fc80 EFLAGS: 00000296 ORIG_RAX: ffffffffffffff13 RAX: ffff88821fd6bd80 RBX: ffff888027898000 RCX: ccccccccccccd000 RDX: ffff88821fca8d80 RSI: ffff888000000000 RDI: 00000000000004a0 RBP: ffff888081a0fc80 R08: 0000000000000002 R09: ffff888081a0fb08 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001 R13: ffff88811130e388 R14: ffff88811130da00 R15: ffff88812fdb7d80 finish_task_switch+0xfc/0x2d0 kernel/sched/core.c:2698 context_switch kernel/sched/core.c:2851 [inline] __schedule+0x6cc/0x800 kernel/sched/core.c:3491 schedule+0x15b/0x240 kernel/sched/core.c:3535 freezable_schedule include/linux/freezer.h:172 [inline] do_nanosleep+0x2ba/0x980 kernel/time/hrtimer.c:1679 hrtimer_nanosleep kernel/time/hrtimer.c:1733 [inline] __do_sys_nanosleep kernel/time/hrtimer.c:1767 [inline] __se_sys_nanosleep+0x746/0x960 kernel/time/hrtimer.c:1754 __x64_sys_nanosleep+0x3e/0x60 kernel/time/hrtimer.c:1754 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x4855a0 Code: 00 00 48 c7 c0 d4 ff ff ff 64 c7 00 16 00 00 00 31 c0 eb be 66 0f 1f 44 00 00 83 3d b1 11 5d 00 00 75 14 b8 23 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 04 e2 f8 ff c3 48 83 ec 08 e8 3a 55 fd ff RSP: 002b:0000000000a4fd58 EFLAGS: 00000246 ORIG_RAX: 0000000000000023 RAX: ffffffffffffffda RBX: 0000000000085780 RCX: 00000000004855a0 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000a4fd60 RBP: 00000000000007ec R08: 0000000000000001 R09: 0000000000ceb940 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000008 R13: 0000000000a4fdb0 R14: 0000000000085711 R15: 0000000000a4fdc0 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:205 [inline] kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:159 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185 slab_post_alloc_hook mm/slab.h:445 [inline] slab_alloc_node mm/slub.c:2773 [inline] __kmalloc_node_track_caller+0xe9e/0xff0 mm/slub.c:4398 __kmalloc_reserve net/core/skbuff.c:140 [inline] __alloc_skb+0x309/0xa20 net/core/skbuff.c:208 alloc_skb include/linux/skbuff.h:1012 [inline] alloc_skb_with_frags+0x186/0xa60 net/core/skbuff.c:5287 sock_alloc_send_pskb+0xafd/0x10a0 net/core/sock.c:2091 sock_alloc_send_skb+0xca/0xe0 net/core/sock.c:2108 __ip_append_data+0x34cd/0x5000 net/ipv4/ip_output.c:998 ip_append_data+0x324/0x480 net/ipv4/ip_output.c:1220 icmp_push_reply+0x23d/0x7e0 net/ipv4/icmp.c:375 __icmp_send+0x2ea3/0x30f0 net/ipv4/icmp.c:737 icmp_send include/net/icmp.h:47 [inline] ipv4_link_failure+0x6d/0x230 net/ipv4/route.c:1190 dst_link_failure include/net/dst.h:427 [inline] arp_error_report+0x106/0x1a0 net/ipv4/arp.c:297 neigh_invalidate+0x359/0x8e0 net/core/neighbour.c:992 neigh_timer_handler+0xdf2/0x1280 net/core/neighbour.c:1078 call_timer_fn+0x285/0x600 kernel/time/timer.c:1325 expire_timers kernel/time/timer.c:1362 [inline] __run_timers+0xdb4/0x11d0 kernel/time/timer.c:1681 run_timer_softirq+0x2e/0x50 kernel/time/timer.c:1694 __do_softirq+0x53f/0x93a kernel/softirq.c:293 Fixes: 26fc181e6cac ("fou, fou6: do not assume linear skbs") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Stefano Brivio <sbrivio@redhat.com> Cc: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Stefano Brivio <sbrivio@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-06 18:41:00 +00:00
if (!pskb_may_pull(skb, transport_offset + len + optlen))
fou, fou6: do not assume linear skbs Both gue_err() and gue6_err() incorrectly assume linear skbs. Fix them to use pskb_may_pull(). BUG: KMSAN: uninit-value in gue6_err+0x475/0xc40 net/ipv6/fou6.c:101 CPU: 0 PID: 18083 Comm: syz-executor1 Not tainted 5.0.0-rc1+ #7 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:600 __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:313 gue6_err+0x475/0xc40 net/ipv6/fou6.c:101 __udp6_lib_err_encap_no_sk net/ipv6/udp.c:434 [inline] __udp6_lib_err_encap net/ipv6/udp.c:491 [inline] __udp6_lib_err+0x18d0/0x2590 net/ipv6/udp.c:522 udplitev6_err+0x118/0x130 net/ipv6/udplite.c:27 icmpv6_notify+0x462/0x9f0 net/ipv6/icmp.c:784 icmpv6_rcv+0x18ac/0x3fa0 net/ipv6/icmp.c:872 ip6_protocol_deliver_rcu+0xb5a/0x23a0 net/ipv6/ip6_input.c:394 ip6_input_finish net/ipv6/ip6_input.c:434 [inline] NF_HOOK include/linux/netfilter.h:289 [inline] ip6_input+0x2b6/0x350 net/ipv6/ip6_input.c:443 dst_input include/net/dst.h:450 [inline] ip6_rcv_finish+0x4e7/0x6d0 net/ipv6/ip6_input.c:76 NF_HOOK include/linux/netfilter.h:289 [inline] ipv6_rcv+0x34b/0x3f0 net/ipv6/ip6_input.c:272 __netif_receive_skb_one_core net/core/dev.c:4973 [inline] __netif_receive_skb net/core/dev.c:5083 [inline] process_backlog+0x756/0x10e0 net/core/dev.c:5923 napi_poll net/core/dev.c:6346 [inline] net_rx_action+0x78b/0x1a60 net/core/dev.c:6412 __do_softirq+0x53f/0x93a kernel/softirq.c:293 do_softirq_own_stack+0x49/0x80 arch/x86/entry/entry_64.S:1039 </IRQ> do_softirq kernel/softirq.c:338 [inline] __local_bh_enable_ip+0x16f/0x1a0 kernel/softirq.c:190 local_bh_enable+0x36/0x40 include/linux/bottom_half.h:32 rcu_read_unlock_bh include/linux/rcupdate.h:696 [inline] ip6_finish_output2+0x1d64/0x25f0 net/ipv6/ip6_output.c:121 ip6_finish_output+0xae4/0xbc0 net/ipv6/ip6_output.c:154 NF_HOOK_COND include/linux/netfilter.h:278 [inline] ip6_output+0x5ca/0x710 net/ipv6/ip6_output.c:171 dst_output include/net/dst.h:444 [inline] ip6_local_out+0x164/0x1d0 net/ipv6/output_core.c:176 ip6_send_skb+0xfa/0x390 net/ipv6/ip6_output.c:1727 udp_v6_send_skb+0x1733/0x1d20 net/ipv6/udp.c:1169 udpv6_sendmsg+0x424e/0x45d0 net/ipv6/udp.c:1466 inet_sendmsg+0x54a/0x720 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xdb9/0x11b0 net/socket.c:2116 __sys_sendmmsg+0x580/0xad0 net/socket.c:2211 __do_sys_sendmmsg net/socket.c:2240 [inline] __se_sys_sendmmsg+0xbd/0xe0 net/socket.c:2237 __x64_sys_sendmmsg+0x56/0x70 net/socket.c:2237 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x457ec9 Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f4a5204fc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 0000000000457ec9 RDX: 00000000040001ab RSI: 0000000020000240 RDI: 0000000000000003 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f4a520506d4 R13: 00000000004c4ce5 R14: 00000000004d85d8 R15: 00000000ffffffff Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:205 [inline] kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:159 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185 slab_post_alloc_hook mm/slab.h:446 [inline] slab_alloc_node mm/slub.c:2754 [inline] __kmalloc_node_track_caller+0xe9e/0xff0 mm/slub.c:4377 __kmalloc_reserve net/core/skbuff.c:140 [inline] __alloc_skb+0x309/0xa20 net/core/skbuff.c:208 alloc_skb include/linux/skbuff.h:1012 [inline] alloc_skb_with_frags+0x1c7/0xac0 net/core/skbuff.c:5288 sock_alloc_send_pskb+0xafd/0x10a0 net/core/sock.c:2091 sock_alloc_send_skb+0xca/0xe0 net/core/sock.c:2108 __ip6_append_data+0x42ed/0x5dc0 net/ipv6/ip6_output.c:1443 ip6_append_data+0x3c2/0x650 net/ipv6/ip6_output.c:1619 icmp6_send+0x2f5c/0x3c40 net/ipv6/icmp.c:574 icmpv6_send+0xe5/0x110 net/ipv6/ip6_icmp.c:43 ip6_link_failure+0x5c/0x2c0 net/ipv6/route.c:2231 dst_link_failure include/net/dst.h:427 [inline] vti_xmit net/ipv4/ip_vti.c:229 [inline] vti_tunnel_xmit+0xf3b/0x1ea0 net/ipv4/ip_vti.c:265 __netdev_start_xmit include/linux/netdevice.h:4382 [inline] netdev_start_xmit include/linux/netdevice.h:4391 [inline] xmit_one net/core/dev.c:3278 [inline] dev_hard_start_xmit+0x604/0xc40 net/core/dev.c:3294 __dev_queue_xmit+0x2e48/0x3b80 net/core/dev.c:3864 dev_queue_xmit+0x4b/0x60 net/core/dev.c:3897 neigh_direct_output+0x42/0x50 net/core/neighbour.c:1511 neigh_output include/net/neighbour.h:508 [inline] ip6_finish_output2+0x1d4e/0x25f0 net/ipv6/ip6_output.c:120 ip6_finish_output+0xae4/0xbc0 net/ipv6/ip6_output.c:154 NF_HOOK_COND include/linux/netfilter.h:278 [inline] ip6_output+0x5ca/0x710 net/ipv6/ip6_output.c:171 dst_output include/net/dst.h:444 [inline] ip6_local_out+0x164/0x1d0 net/ipv6/output_core.c:176 ip6_send_skb+0xfa/0x390 net/ipv6/ip6_output.c:1727 udp_v6_send_skb+0x1733/0x1d20 net/ipv6/udp.c:1169 udpv6_sendmsg+0x424e/0x45d0 net/ipv6/udp.c:1466 inet_sendmsg+0x54a/0x720 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xdb9/0x11b0 net/socket.c:2116 __sys_sendmmsg+0x580/0xad0 net/socket.c:2211 __do_sys_sendmmsg net/socket.c:2240 [inline] __se_sys_sendmmsg+0xbd/0xe0 net/socket.c:2237 __x64_sys_sendmmsg+0x56/0x70 net/socket.c:2237 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 Fixes: b8a51b38e4d4 ("fou, fou6: ICMP error handlers for FoU and GUE") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Stefano Brivio <sbrivio@redhat.com> Cc: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-11 14:27:35 +00:00
return -EINVAL;
guehdr = (struct guehdr *)&udp_hdr(skb)[1];
if (validate_gue_flags(guehdr, optlen))
return -EINVAL;
/* Handling exceptions for direct UDP encapsulation in GUE would lead to
* recursion. Besides, this kind of encapsulation can't even be
* configured currently. Discard this.
*/
if (guehdr->proto_ctype == IPPROTO_UDP ||
guehdr->proto_ctype == IPPROTO_UDPLITE)
return -EOPNOTSUPP;
skb_set_transport_header(skb, -(int)sizeof(struct icmphdr));
ret = gue_err_proto_handler(guehdr->proto_ctype, skb, info);
out:
skb_set_transport_header(skb, transport_offset);
return ret;
}
static const struct ip_tunnel_encap_ops fou_iptun_ops = {
.encap_hlen = fou_encap_hlen,
.build_header = fou_build_header,
.err_handler = gue_err,
};
static const struct ip_tunnel_encap_ops gue_iptun_ops = {
.encap_hlen = gue_encap_hlen,
.build_header = gue_build_header,
.err_handler = gue_err,
};
static int ip_tunnel_encap_add_fou_ops(void)
{
int ret;
ret = ip_tunnel_encap_add_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU);
if (ret < 0) {
pr_err("can't add fou ops\n");
return ret;
}
ret = ip_tunnel_encap_add_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE);
if (ret < 0) {
pr_err("can't add gue ops\n");
ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU);
return ret;
}
return 0;
}
static void ip_tunnel_encap_del_fou_ops(void)
{
ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU);
ip_tunnel_encap_del_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE);
}
#else
static int ip_tunnel_encap_add_fou_ops(void)
{
return 0;
}
static void ip_tunnel_encap_del_fou_ops(void)
{
}
#endif
static __net_init int fou_init_net(struct net *net)
{
struct fou_net *fn = net_generic(net, fou_net_id);
INIT_LIST_HEAD(&fn->fou_list);
mutex_init(&fn->fou_lock);
return 0;
}
static __net_exit void fou_exit_net(struct net *net)
{
struct fou_net *fn = net_generic(net, fou_net_id);
struct fou *fou, *next;
/* Close all the FOU sockets */
mutex_lock(&fn->fou_lock);
list_for_each_entry_safe(fou, next, &fn->fou_list, list)
fou_release(fou);
mutex_unlock(&fn->fou_lock);
}
static struct pernet_operations fou_net_ops = {
.init = fou_init_net,
.exit = fou_exit_net,
.id = &fou_net_id,
.size = sizeof(struct fou_net),
};
static int __init fou_init(void)
{
int ret;
ret = register_pernet_device(&fou_net_ops);
if (ret)
goto exit;
ret = genl_register_family(&fou_nl_family);
if (ret < 0)
goto unregister;
ret = ip_tunnel_encap_add_fou_ops();
if (ret == 0)
return 0;
genl_unregister_family(&fou_nl_family);
unregister:
unregister_pernet_device(&fou_net_ops);
exit:
return ret;
}
static void __exit fou_fini(void)
{
ip_tunnel_encap_del_fou_ops();
genl_unregister_family(&fou_nl_family);
unregister_pernet_device(&fou_net_ops);
}
module_init(fou_init);
module_exit(fou_fini);
MODULE_AUTHOR("Tom Herbert <therbert@google.com>");
MODULE_LICENSE("GPL");