net: support marking accepting TCP sockets
When using mark-based routing, sockets returned from accept()
may need to be marked differently depending on the incoming
connection request.
This is the case, for example, if different socket marks identify
different networks: a listening socket may want to accept
connections from all networks, but each connection should be
marked with the network that the request came in on, so that
subsequent packets are sent on the correct network.
This patch adds a sysctl to mark TCP sockets based on the fwmark
of the incoming SYN packet. If enabled, and an unmarked socket
receives a SYN, then the SYN packet's fwmark is written to the
connection's inet_request_sock, and later written back to the
accepted socket when the connection is established. If the
socket already has a nonzero mark, then the behaviour is the same
as it is today, i.e., the listening socket's fwmark is used.
Black-box tested using user-mode linux:
- IPv4/IPv6 SYN+ACK, FIN, etc. packets are routed based on the
mark of the incoming SYN packet.
- The socket returned by accept() is marked with the mark of the
incoming SYN packet.
- Tested with syncookies=1 and syncookies=2.
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index a56b8e6..12e502c 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -408,7 +408,7 @@
struct net *net = sock_net(sk);
int flags = inet_sk_flowi_flags(sk);
- flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+ flowi4_init_output(fl4, sk->sk_bound_dev_if, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol,
flags,
@@ -445,7 +445,7 @@
rcu_read_lock();
opt = rcu_dereference(newinet->inet_opt);
- flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+ flowi4_init_output(fl4, sk->sk_bound_dev_if, inet_rsk(req)->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
@@ -680,6 +680,8 @@
inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num);
newsk->sk_write_space = sk_stream_write_space;
+ newsk->sk_mark = inet_rsk(req)->ir_mark;
+
newicsk->icsk_retransmits = 0;
newicsk->icsk_backoff = 0;
newicsk->icsk_probes_out = 0;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index f2ed13c..c86624b 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -303,6 +303,7 @@
ireq->ir_rmt_port = th->source;
ireq->ir_loc_addr = ip_hdr(skb)->daddr;
ireq->ir_rmt_addr = ip_hdr(skb)->saddr;
+ ireq->ir_mark = inet_request_mark(sk, skb);
ireq->ecn_ok = ecn_ok;
ireq->snd_wscale = tcp_opt.snd_wscale;
ireq->sack_ok = tcp_opt.sack_ok;
@@ -339,7 +340,7 @@
* hasn't changed since we received the original syn, but I see
* no easy way to do this.
*/
- flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark,
+ flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
inet_sk_flowi_flags(sk),
(opt && opt->srr) ? opt->faddr : ireq->ir_rmt_addr,
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index f50d51850..a33b9fb 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -845,6 +845,13 @@
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "tcp_fwmark_accept",
+ .data = &init_net.ipv4.sysctl_tcp_fwmark_accept,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
{ }
};
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a2780e5..77cccda 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1318,6 +1318,7 @@
ireq->ir_rmt_addr = saddr;
ireq->no_srccheck = inet_sk(sk)->transparent;
ireq->opt = tcp_v4_save_options(skb);
+ ireq->ir_mark = inet_request_mark(sk, skb);
if (security_inet_conn_request(sk, skb, req))
goto drop_and_free;
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index d4ade34..a245e5d 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -81,7 +81,7 @@
final_p = fl6_update_dst(fl6, np->opt, &final);
fl6->saddr = ireq->ir_v6_loc_addr;
fl6->flowi6_oif = ireq->ir_iif;
- fl6->flowi6_mark = sk->sk_mark;
+ fl6->flowi6_mark = ireq->ir_mark;
fl6->fl6_dport = ireq->ir_rmt_port;
fl6->fl6_sport = htons(ireq->ir_num);
security_req_classify_flow(req, flowi6_to_flowi(fl6));
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index bb53a5e7..a822b88 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -216,6 +216,8 @@
ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq->ir_iif = inet6_iif(skb);
+ ireq->ir_mark = inet_request_mark(sk, skb);
+
req->expires = 0UL;
req->num_retrans = 0;
ireq->ecn_ok = ecn_ok;
@@ -242,7 +244,7 @@
final_p = fl6_update_dst(&fl6, np->opt, &final);
fl6.saddr = ireq->ir_v6_loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
- fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_mark = ireq->ir_mark;
fl6.fl6_dport = ireq->ir_rmt_port;
fl6.fl6_sport = inet_sk(sk)->inet_sport;
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c54976a..f07b2ab 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1034,6 +1034,7 @@
TCP_ECN_create_request(req, skb, sock_net(sk));
ireq->ir_iif = sk->sk_bound_dev_if;
+ ireq->ir_mark = inet_request_mark(sk, skb);
/* So that link locals have meaning */
if (!sk->sk_bound_dev_if &&