net: convert ipv6_stub to ip6_dst_lookup_flow
Subsystems (9)
cover net: convert ipv6_stub to ip6_dst_lookup_flow
Xiumei Mu reported a bug in a VXLAN over IPsec setup:
IPv6 | ESP | VXLAN
Using this setup, packets go out unencrypted, because VXLAN over IPv6 gets its route from ipv6_stub->ipv6_dst_lookup (in vxlan6_get_route), which doesn't perform an XFRM lookup.
This patchset first makes ip6_dst_lookup_flow suitable for some existing users of ipv6_stub->ipv6_dst_lookup by adding a 'net' argument, then converts all those users.
Sabrina Dubroca (2):
net: ipv6: add net argument to ip6_dst_lookup_flow
net: ipv6_stub: use ip6_dst_lookup_flow instead of ip6_dst_lookup
drivers/infiniband/core/addr.c | 7 +++---- drivers/infiniband/sw/rxe/rxe_net.c | 8 +++++--- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 8 ++++---- drivers/net/geneve.c | 4 +++- drivers/net/vxlan.c | 8 +++----- include/net/ipv6.h | 2 +- include/net/ipv6_stubs.h | 6 ++++-- net/core/lwt_bpf.c | 4 +--- net/dccp/ipv6.c | 6 +++--- net/ipv6/addrconf_core.c | 11 ++++++----- net/ipv6/af_inet6.c | 4 ++-- net/ipv6/datagram.c | 2 +- net/ipv6/inet6_connection_sock.c | 4 ++-- net/ipv6/ip6_output.c | 8 ++++---- net/ipv6/raw.c | 2 +- net/ipv6/syncookies.c | 2 +- net/ipv6/tcp_ipv6.c | 4 ++-- net/l2tp/l2tp_ip6.c | 2 +- net/mpls/af_mpls.c | 7 +++---- net/sctp/ipv6.c | 4 ++-- net/tipc/udp_media.c | 9 ++++++--- 21 files changed, 58 insertions(+), 54 deletions(-)
Signature · 1 line
2.23.0
PATCH 1/2 net: ipv6: add net argument to ip6_dst_lookup_flow
This will be used in the conversion of ipv6_stub to ip6_dst_lookup_flow, as some modules currently pass a net argument without a socket to ip6_dst_lookup. This is equivalent to commit 343d60aada5a ("ipv6: change ipv6_stub_impl.ipv6_dst_lookup to take net argument").
--- include/net/ipv6.h | 2 +- net/dccp/ipv6.c | 6 +++--- net/ipv6/af_inet6.c | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/inet6_connection_sock.c | 4 ++-- net/ipv6/ip6_output.c | 8 ++++---- net/ipv6/raw.c | 2 +- net/ipv6/syncookies.c | 2 +- net/ipv6/tcp_ipv6.c | 4 ++-- net/l2tp/l2tp_ip6.c | 2 +- net/sctp/ipv6.c | 4 ++-- 11 files changed, 19 insertions(+), 19 deletions(-)
include/net/ipv6.h +1 -1
@@ -1022,7 +1022,7 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk)int ip6_dst_lookup (struct net *net,struct sock *sk,struct dst_entry **dst,struct flowi6 *fl6); -struct dst_entry *ip6_dst_lookup_flow (const struct sock *sk,struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow (struct net *net,const struct sock *sk,struct flowi6 *fl6,const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst,
net/dccp/ipv6.c +3 -3
@@ -210,7 +210,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req final_p =fl6_update_dst (&fl6,rcu_dereference (np->opt), &final);rcu_read_unlock (); - dst =ip6_dst_lookup_flow (sk, &fl6, final_p); + dst =ip6_dst_lookup_flow (sock_net (sk), sk, &fl6, final_p);if (IS_ERR (dst)) { err =PTR_ERR (dst); dst =NULL ;
@@ -282,7 +282,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)security_skb_classify_flow (rxskb,flowi6_to_flowi (&fl6));/* sk = NULL, but it is safe for now. RST socket required. */ - dst =ip6_dst_lookup_flow (ctl_sk, &fl6,NULL ); + dst =ip6_dst_lookup_flow (sock_net (ctl_sk), ctl_sk, &fl6,NULL );if (!IS_ERR (dst)) {skb_dst_set (skb, dst);ip6_xmit (ctl_sk, skb, &fl6,0 ,NULL ,0 ,0 );
@@ -912,7 +912,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, opt =rcu_dereference_protected (np->opt,lockdep_sock_is_held (sk)); final_p =fl6_update_dst (&fl6, opt, &final); - dst =ip6_dst_lookup_flow (sk, &fl6, final_p); + dst =ip6_dst_lookup_flow (sock_net (sk), sk, &fl6, final_p);if (IS_ERR (dst)) { err =PTR_ERR (dst); goto failure;
net/ipv6/af_inet6.c +1 -1
@@ -765,7 +765,7 @@ int inet6_sk_rebuild_header(struct sock *sk) &final);rcu_read_unlock (); - dst =ip6_dst_lookup_flow (sk, &fl6, final_p); + dst =ip6_dst_lookup_flow (sock_net (sk), sk, &fl6, final_p);if (IS_ERR (dst)) { sk->sk_route_caps =0 ; sk->sk_err_soft = -PTR_ERR (dst);
net/ipv6/datagram.c +1 -1
@@ -85,7 +85,7 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr) final_p =fl6_update_dst (&fl6, opt, &final);rcu_read_unlock (); - dst =ip6_dst_lookup_flow (sk, &fl6, final_p); + dst =ip6_dst_lookup_flow (sock_net (sk), sk, &fl6, final_p);if (IS_ERR (dst)) { err =PTR_ERR (dst); goto out;
net/ipv6/inet6_connection_sock.c +2 -2
@@ -48,7 +48,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk, fl6->flowi6_uid = sk->sk_uid;security_req_classify_flow (req,flowi6_to_flowi (fl6)); - dst =ip6_dst_lookup_flow (sk, fl6, final_p); + dst =ip6_dst_lookup_flow (sock_net (sk), sk, fl6, final_p);if (IS_ERR (dst))return NULL ;
@@ -103,7 +103,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, dst =__inet6_csk_dst_check (sk, np->dst_cookie);if (!dst) { - dst =ip6_dst_lookup_flow (sk, fl6, final_p); + dst =ip6_dst_lookup_flow (sock_net (sk), sk, fl6, final_p);if (!IS_ERR (dst))ip6_dst_store (sk, dst,NULL ,NULL );
net/ipv6/ip6_output.c +4 -4
@@ -1144,19 +1144,19 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);* It returns a valid dst pointer on success, or a pointer encoded * error code. */ -struct dst_entry *ip6_dst_lookup_flow (const struct sock *sk,struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow (struct net *net,const struct sock *sk,struct flowi6 *fl6,const struct in6_addr *final_dst) {struct dst_entry *dst =NULL ;int err; - err =ip6_dst_lookup_tail (sock_net (sk), sk, &dst, fl6); + err =ip6_dst_lookup_tail (net, sk, &dst, fl6);if (err)return ERR_PTR (err);if (final_dst) fl6->daddr = *final_dst; -return xfrm_lookup_route (sock_net (sk), dst,flowi6_to_flowi (fl6), sk,0 ); +return xfrm_lookup_route (net, dst,flowi6_to_flowi (fl6), sk,0 ); }EXPORT_SYMBOL_GPL (ip6_dst_lookup_flow);
@@ -1188,7 +1188,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,if (dst)return dst; - dst =ip6_dst_lookup_flow (sk, fl6, final_dst); + dst =ip6_dst_lookup_flow (sock_net (sk), sk, fl6, final_dst);if (connected && !IS_ERR (dst))ip6_sk_dst_store_flow (sk,dst_clone (dst), fl6);
net/ipv6/raw.c +1 -1
@@ -925,7 +925,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowlabel =ip6_make_flowinfo (ipc6.tclass, fl6.flowlabel); - dst =ip6_dst_lookup_flow (sk, &fl6, final_p); + dst =ip6_dst_lookup_flow (sock_net (sk), sk, &fl6, final_p);if (IS_ERR (dst)) { err =PTR_ERR (dst); goto out;
net/ipv6/syncookies.c +1 -1
@@ -235,7 +235,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) fl6.flowi6_uid = sk->sk_uid;security_req_classify_flow (req,flowi6_to_flowi (&fl6)); - dst =ip6_dst_lookup_flow (sk, &fl6, final_p); + dst =ip6_dst_lookup_flow (sock_net (sk), sk, &fl6, final_p);if (IS_ERR (dst)) goto out_free; }
net/ipv6/tcp_ipv6.c +2 -2
@@ -275,7 +275,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,security_sk_classify_flow (sk,flowi6_to_flowi (&fl6)); - dst =ip6_dst_lookup_flow (sk, &fl6, final_p); + dst =ip6_dst_lookup_flow (sock_net (sk), sk, &fl6, final_p);if (IS_ERR (dst)) { err =PTR_ERR (dst); goto failure;
@@ -906,7 +906,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32* Underlying function will use this to retrieve the network * namespace */ - dst =ip6_dst_lookup_flow (ctl_sk, &fl6,NULL ); + dst =ip6_dst_lookup_flow (sock_net (ctl_sk), ctl_sk, &fl6,NULL );if (!IS_ERR (dst)) {skb_dst_set (buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass,
net/l2tp/l2tp_ip6.c +1 -1
@@ -615,7 +615,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowlabel =ip6_make_flowinfo (ipc6.tclass, fl6.flowlabel); - dst =ip6_dst_lookup_flow (sk, &fl6, final_p); + dst =ip6_dst_lookup_flow (sock_net (sk), sk, &fl6, final_p);if (IS_ERR (dst)) { err =PTR_ERR (dst); goto out;
net/sctp/ipv6.c +2 -2
@@ -275,7 +275,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, final_p =fl6_update_dst (fl6,rcu_dereference (np->opt), &final);rcu_read_unlock (); - dst =ip6_dst_lookup_flow (sk, fl6, final_p); + dst =ip6_dst_lookup_flow (sock_net (sk), sk, fl6, final_p);if (!asoc || saddr) goto out;
@@ -328,7 +328,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl6->saddr = laddr->a.v6.sin6_addr; fl6->fl6_sport = laddr->a.v6.sin6_port; final_p =fl6_update_dst (fl6,rcu_dereference (np->opt), &final); - bdst =ip6_dst_lookup_flow (sk, fl6, final_p); + bdst =ip6_dst_lookup_flow (sock_net (sk), sk, fl6, final_p);if (IS_ERR (bdst))continue ;
Signature · 1 line
2.23.0
PATCH 2/2 net: ipv6_stub: use ip6_dst_lookup_flow instead of ip6_dst_lookup
In reply to Sabrina Dubrocaipv6_stub uses the ip6_dst_lookup function to allow other modules to perform IPv6 lookups. However, this function skips the XFRM layer entirely.
All users of ipv6_stub->ip6_dst_lookup use ip_route_output_flow (via the ip_route_output_key and ip_route_output helpers) for their IPv4 lookups, which calls xfrm_lookup_route(). This patch fixes this inconsistent behavior by switching the stub to ip6_dst_lookup_flow, which also calls xfrm_lookup_route().
This requires some changes in all the callers, as these two functions take different arguments and have different return types.
--- drivers/infiniband/core/addr.c | 7 +++---- drivers/infiniband/sw/rxe/rxe_net.c | 8 +++++--- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 8 ++++---- drivers/net/geneve.c | 4 +++- drivers/net/vxlan.c | 8 +++----- include/net/ipv6_stubs.h | 6 ++++-- net/core/lwt_bpf.c | 4 +--- net/ipv6/addrconf_core.c | 11 ++++++----- net/ipv6/af_inet6.c | 2 +- net/mpls/af_mpls.c | 7 +++---- net/tipc/udp_media.c | 9 ++++++--- 11 files changed, 39 insertions(+), 35 deletions(-)
drivers/infiniband/core/addr.c +3 -4
@@ -421,16 +421,15 @@ static int addr6_resolve(struct sockaddr *src_sock, (const struct sockaddr_in6 *)dst_sock;struct flowi6 fl6;struct dst_entry *dst; -int ret;memset (&fl6,0 ,sizeof fl6); fl6.daddr = dst_in->sin6_addr; fl6.saddr = src_in->sin6_addr; fl6.flowi6_oif = addr->bound_dev_if; - ret = ipv6_stub->ipv6_dst_lookup (addr->net,NULL , &dst, &fl6); -if (ret <0 ) -return ret; + dst = ipv6_stub->ipv6_dst_lookup_flow (addr->net,NULL , &fl6,NULL ); +if (IS_ERR (dst)) +return PTR_ERR (dst);if (ipv6_addr_any (&src_in->sin6_addr)) src_in->sin6_addr = fl6.saddr;
drivers/infiniband/sw/rxe/rxe_net.c +5 -3
@@ -117,10 +117,12 @@ static struct dst_entry *rxe_find_route6(struct net_device *ndev,memcpy (&fl6.daddr, daddr,sizeof (*daddr)); fl6.flowi6_proto =IPPROTO_UDP ; -if (unlikely (ipv6_stub->ipv6_dst_lookup (sock_net (recv_sockets.sk6->sk), - recv_sockets.sk6->sk, &ndst, &fl6))) { + ndst = ipv6_stub->ipv6_dst_lookup_flow (sock_net (recv_sockets.sk6->sk), + recv_sockets.sk6->sk, &fl6, +NULL ); +if (unlikely (IS_ERR (ndst))) {pr_err_ratelimited ("no route to %pI6\n" , daddr); - goto put; +return NULL ; }if (unlikely (ndst->error)) {
drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +4 -4
@@ -297,10 +297,10 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,int ret; - ret = ipv6_stub->ipv6_dst_lookup (dev_net (mirred_dev),NULL , &dst, - fl6); -if (ret <0 ) -return ret; + dst = ipv6_stub->ipv6_dst_lookup_flow (dev_net (mirred_dev),NULL , fl6, +NULL ); +if (IS_ERR (dst)) +return PTR_ERR (dst);if (!(*out_ttl)) *out_ttl =ip6_dst_hoplimit (dst);
drivers/net/geneve.c +3 -1
@@ -853,7 +853,9 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,if (dst)return dst; } -if (ipv6_stub->ipv6_dst_lookup (geneve->net, gs6->sock->sk, &dst, fl6)) { + dst = ipv6_stub->ipv6_dst_lookup_flow (geneve->net, gs6->sock->sk, fl6, +NULL ); +if (IS_ERR (dst)) {netdev_dbg (dev,"no route to %pI6\n" , &fl6->daddr);return ERR_PTR (-ENETUNREACH ); }
drivers/net/vxlan.c +3 -5
@@ -2275,7 +2275,6 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,bool use_cache =ip_tunnel_dst_cache_usable (skb, info);struct dst_entry *ndst;struct flowi6 fl6; -int err;if (!sock6)return ERR_PTR (-EIO );
@@ -2298,10 +2297,9 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, fl6.fl6_dport = dport; fl6.fl6_sport = sport; - err = ipv6_stub->ipv6_dst_lookup (vxlan->net, - sock6->sock->sk, - &ndst, &fl6); -if (unlikely (err <0 )) { + ndst = ipv6_stub->ipv6_dst_lookup_flow (vxlan->net, sock6->sock->sk, + &fl6,NULL ); +if (unlikely (IS_ERR (ndst))) {netdev_dbg (dev,"no route to %pI6\n" , daddr);return ERR_PTR (-ENETUNREACH ); }
include/net/ipv6_stubs.h +4 -2
@@ -24,8 +24,10 @@ struct ipv6_stub { const struct in6_addr *addr);int (*ipv6_sock_mc_drop)(struct sock *sk,int ifindex,const struct in6_addr *addr); -int (*ipv6_dst_lookup)(struct net *net,struct sock *sk, -struct dst_entry **dst,struct flowi6 *fl6); +struct dst_entry *(*ipv6_dst_lookup_flow)(struct net *net, +const struct sock *sk, +struct flowi6 *fl6, +const struct in6_addr *final_dst);int (*ipv6_route_input)(struct sk_buff *skb);struct fib6_table *(*fib6_get_table)(struct net *net,u32 id);
net/core/lwt_bpf.c +1 -3
@@ -230,9 +230,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb) fl6.daddr = iph6->daddr; fl6.saddr = iph6->saddr; - err = ipv6_stub->ipv6_dst_lookup (net, skb->sk, &dst, &fl6); -if (unlikely (err)) - goto err; + dst = ipv6_stub->ipv6_dst_lookup_flow (net, skb->sk, &fl6,NULL );if (IS_ERR (dst)) { err =PTR_ERR (dst); goto err;
net/ipv6/addrconf_core.c +6 -5
@@ -129,11 +129,12 @@ int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) }EXPORT_SYMBOL (inet6addr_validator_notifier_call_chain); -static int eafnosupport_ipv6_dst_lookup (struct net *net,struct sock *u1, -struct dst_entry **u2, -struct flowi6 *u3) +static struct dst_entry *eafnosupport_ipv6_dst_lookup_flow (struct net *net, +const struct sock *sk, +struct flowi6 *fl6, +const struct in6_addr *final_dst) { -return -EAFNOSUPPORT ; +return ERR_PTR (-EAFNOSUPPORT ); }static int eafnosupport_ipv6_route_input (struct sk_buff *skb)
@@ -190,7 +191,7 @@ static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt) }const struct ipv6_stub *ipv6_stub__read_mostly = &(struct ipv6_stub ) { - .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup, + .ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow, .ipv6_route_input = eafnosupport_ipv6_route_input, .fib6_get_table = eafnosupport_fib6_get_table, .fib6_table_lookup = eafnosupport_fib6_table_lookup,
net/ipv6/af_inet6.c +1 -1
@@ -946,7 +946,7 @@ static int ipv6_route_input(struct sk_buff *skb)static const struct ipv6_stub ipv6_stub_impl = { .ipv6_sock_mc_join = ipv6_sock_mc_join, .ipv6_sock_mc_drop = ipv6_sock_mc_drop, - .ipv6_dst_lookup = ip6_dst_lookup, + .ipv6_dst_lookup_flow = ip6_dst_lookup_flow, .ipv6_route_input = ipv6_route_input, .fib6_get_table = fib6_get_table, .fib6_table_lookup = fib6_table_lookup,
net/mpls/af_mpls.c +3 -4
@@ -617,16 +617,15 @@ static struct net_device *inet6_fib_lookup_dev(struct net *net,struct net_device *dev;struct dst_entry *dst;struct flowi6 fl6; -int err;if (!ipv6_stub)return ERR_PTR (-EAFNOSUPPORT );memset (&fl6,0 ,sizeof (fl6));memcpy (&fl6.daddr, addr,sizeof (struct in6_addr )); - err = ipv6_stub->ipv6_dst_lookup (net,NULL , &dst, &fl6); -if (err) -return ERR_PTR (err); + dst = ipv6_stub->ipv6_dst_lookup_flow (net,NULL , &fl6,NULL ); +if (IS_ERR (dst)) +return ERR_CAST (dst); dev = dst->dev;dev_hold (dev);
net/tipc/udp_media.c +6 -3
@@ -195,10 +195,13 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, .saddr = src->ipv6, .flowi6_proto = IPPROTO_UDP }; - err = ipv6_stub->ipv6_dst_lookup (net, ub->ubsock->sk, - &ndst, &fl6); -if (err) + ndst = ipv6_stub->ipv6_dst_lookup_flow (net, + ub->ubsock->sk, + &fl6,NULL ); +if (IS_ERR (ndst)) { + err =PTR_ERR (ndst); goto tx_error; + }dst_cache_set_ip6 (cache, ndst, &fl6.saddr); } ttl =ip6_dst_hoplimit (ndst);
Signature · 1 line
2.23.0
David Miller
maintainerFrom: Sabrina Dubroca <[email protected]>
Date: Wed, 4 Dec 2019 15:35:51 +0100
Quoted 11 lines
Xiumei Mu reported a bug in a VXLAN over IPsec setup:
IPv6 | ESP | VXLAN
Using this setup, packets go out unencrypted, because VXLAN over IPv6 gets its route from
ipv6_stub->ipv6_dst_lookup(invxlan6_get_route), which doesn't perform an XFRM lookup.This patchset first makes
ip6_dst_lookup_flowsuitable for some existing users ofipv6_stub->ipv6_dst_lookupby adding a 'net' argument, then converts all those users.
Series applied, thanks.