net: inet: Support UID-based routing in IP protocols.

- Use the UID in routing lookups made by protocol connect() and
  sendmsg() functions.
- Make sure that routing lookups triggered by incoming packets
  (e.g., Path MTU discovery) take the UID of the socket into
  account.
- For packets not associated with a userspace socket, (e.g., ping
  replies) use UID 0 inside the user namespace corresponding to
  the network namespace the socket belongs to. This allows
  all namespaces to apply routing and iptables rules to
  kernel-originated traffic in that namespaces by matching UID 0.
  This is better than using the UID of the kernel socket that is
  sending the traffic, because the UID of kernel sockets created
  at namespace creation time (e.g., the per-processor ICMP and
  TCP sockets) is the UID of the user that created the socket,
  which might not be mapped in the namespace.

Bug: 16355602
Change-Id: I910504b508948057912bc188fd1e8aca28294de3
Tested: compiles allnoconfig, allyesconfig, allmodconfig
Tested: https://android-review.googlesource.com/253302
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Kevin F. Haggerty <haggertk@lineageos.org>

include/net/flow.h

@@ -89,7 +89,8 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
 				      __u32 mark, __u8 tos, __u8 scope,
 				      __u8 proto, __u8 flags,
 				      __be32 daddr, __be32 saddr,
-				      __be16 dport, __be16 sport)
+				      __be16 dport, __be16 sport,
+				      kuid_t uid)
 {
 	fl4->flowi4_oif = oif;
 	fl4->flowi4_iif = LOOPBACK_IFINDEX;
@@ -99,6 +100,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
 	fl4->flowi4_proto = proto;
 	fl4->flowi4_flags = flags;
 	fl4->flowi4_secid = 0;
+	fl4->flowi4_uid = uid;
 	fl4->daddr = daddr;
 	fl4->saddr = saddr;
 	fl4->fl4_dport = dport;

include/net/ip.h

@@ -169,6 +169,7 @@ struct ip_reply_arg {
 				/* -1 if not needed */ 
 	int	    bound_dev_if;
 	u8  	    tos;
+	kuid_t	    uid;
 }; 
 
 #define IP_REPLY_ARG_NOSRCCHECK 1

include/net/ip6_route.h

@@ -137,7 +137,7 @@ extern void			rt6_redirect(const struct in6_addr *dest,
 					     int on_link);
 
 extern void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
-			    int oif, u32 mark);
+			    int oif, u32 mark, kuid_t uid);
 extern void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk,
 			       __be32 mtu);
 

include/net/route.h

@@ -146,7 +146,7 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi
 	flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos,
 			   RT_SCOPE_UNIVERSE, proto,
 			   sk ? inet_sk_flowi_flags(sk) : 0,
-			   daddr, saddr, dport, sport);
+			   daddr, saddr, dport, sport, sock_net_uid(net, sk));
 	if (sk)
 		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
 	return ip_route_output_flow(net, fl4, sk);
@@ -250,7 +250,8 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32
 		flow_flags |= FLOWI_FLAG_CAN_SLEEP;
 
 	flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
-			   protocol, flow_flags, dst, src, dport, sport);
+			   protocol, flow_flags, dst, src, dport, sport,
+			   sk->sk_uid);
 }
 
 static inline struct rtable *ip_route_connect(struct flowi4 *fl4,

net/ipv4/icmp.c

@@ -361,6 +361,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	fl4.daddr = daddr;
 	fl4.saddr = rt->rt_spec_dst;
 	fl4.flowi4_mark = mark;
+	fl4.flowi4_uid = sock_net_uid(net, NULL);
 	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
 	fl4.flowi4_proto = IPPROTO_ICMP;
 	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
@@ -392,6 +393,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 		      param->replyopts.opt.opt.faddr : iph->saddr);
 	fl4->saddr = saddr;
 	fl4->flowi4_mark = mark;
+	fl4->flowi4_uid = sock_net_uid(net, NULL);
 	fl4->flowi4_tos = RT_TOS(tos);
 	fl4->flowi4_proto = IPPROTO_ICMP;
 	fl4->fl4_icmp_type = type;

net/ipv4/inet_connection_sock.c

@@ -365,7 +365,8 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
-			   ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport);
+			   ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport,
+			   sk->sk_uid);
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -398,7 +399,8 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
-			   ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport);
+			   ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport,
+			   sk->sk_uid);
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))

net/ipv4/ip_output.c

@@ -1506,7 +1506,8 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr,
 			   RT_SCOPE_UNIVERSE, sk->sk_protocol,
 			   ip_reply_arg_flowi_flags(arg),
 			   daddr, rt->rt_spec_dst,
-			   tcp_hdr(skb)->source, tcp_hdr(skb)->dest);
+			   tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
+			   arg->uid);
 	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_key(sock_net(sk), &fl4);
 	if (IS_ERR(rt))

net/ipv4/ping.c

@@ -786,7 +786,8 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
 			   RT_SCOPE_UNIVERSE, sk->sk_protocol,
-			   inet_sk_flowi_flags(sk), faddr, saddr, 0, 0);
+			   inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
+			   sk->sk_uid);
 
 	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);

net/ipv4/raw.c

@@ -569,7 +569,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			   RT_SCOPE_UNIVERSE,
 			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP,
-			   daddr, saddr, 0, 0);
+			   daddr, saddr, 0, 0, sk->sk_uid);
 
 	if (!inet->hdrincl) {
 		err = raw_probe_proto_opt(&fl4, msg);

net/ipv4/syncookies.c

@@ -352,7 +352,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
 			   inet_sk_flowi_flags(sk),
 			   (opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
-			   ireq->loc_addr, th->source, th->dest);
+			   ireq->loc_addr, th->source, th->dest, sk->sk_uid);
 	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_key(sock_net(sk), &fl4);
 	if (IS_ERR(rt)) {

net/ipv4/tcp_ipv4.c

@@ -689,6 +689,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 		arg.bound_dev_if = sk->sk_bound_dev_if;
 
 	arg.tos = ip_hdr(skb)->tos;
+	arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
 	ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
 		      &arg, arg.iov[0].iov_len);
 
@@ -708,7 +709,8 @@ release_sk1:
    outside socket context is ugly, certainly. What can I do?
  */
 
-static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
+static void tcp_v4_send_ack(const struct sock *sk, struct sk_buff *skb,
+			    u32 seq, u32 ack,
 			    u32 win, u32 ts, int oif,
 			    struct tcp_md5sig_key *key,
 			    int reply_flags, u8 tos)
@@ -723,7 +725,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 			];
 	} rep;
 	struct ip_reply_arg arg;
-	struct net *net = dev_net(skb_dst(skb)->dev);
+	struct net *net = sock_net(sk);
 
 	memset(&rep.th, 0, sizeof(struct tcphdr));
 	memset(&arg, 0, sizeof(arg));
@@ -772,6 +774,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 	if (oif)
 		arg.bound_dev_if = oif;
 	arg.tos = tos;
+	arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
 	ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
 		      &arg, arg.iov[0].iov_len);
 
@@ -783,7 +786,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
 
-	tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+	tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcptw->tw_ts_recent,
 			tw->tw_bound_dev_if,
@@ -798,7 +801,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req)
 {
-	tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1,
+	tcp_v4_send_ack(sk, skb, tcp_rsk(req)->snt_isn + 1,
 			tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
 			req->ts_recent,
 			0,

net/ipv4/udp.c

@@ -932,7 +932,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
 				   RT_SCOPE_UNIVERSE, sk->sk_protocol,
 				   inet_sk_flowi_flags(sk)|FLOWI_FLAG_CAN_SLEEP,
-				   faddr, saddr, dport, inet->inet_sport);
+				   faddr, saddr, dport, inet->inet_sport,
+				   sk->sk_uid);
 
 		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
 		rt = ip_route_output_flow(net, fl4, sk);

net/ipv6/af_inet6.c

@@ -711,6 +711,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		fl6.flowi6_mark = sk->sk_mark;
 		fl6.fl6_dport = inet->inet_dport;
 		fl6.fl6_sport = inet->inet_sport;
+		fl6.flowi6_uid = sk->sk_uid;
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
 		rcu_read_lock();

net/ipv6/ah6.c

@@ -620,7 +620,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/%pI6\n",
 		 ntohl(ah->spi), &iph->daddr);
-	ip6_update_pmtu(skb, net, info, 0, 0);
+	ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
 	xfrm_state_put(x);
 }
 

net/ipv6/datagram.c

@@ -160,6 +160,7 @@ ipv4_connected:
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_dport = inet->inet_dport;
 	fl6.fl6_sport = inet->inet_sport;
+	fl6.flowi6_uid = sk->sk_uid;
 
 	if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
 		fl6.flowi6_oif = np->mcast_oif;

net/ipv6/esp6.c

@@ -441,7 +441,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		return;
 	printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%pI6\n",
 			ntohl(esph->spi), &iph->daddr);
-	ip6_update_pmtu(skb, net, info, 0, 0);
+	ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
 	xfrm_state_put(x);
 }
 

net/ipv6/icmp.c

@@ -466,6 +466,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	fl6.flowi6_oif = iif;
 	fl6.fl6_icmp_type = type;
 	fl6.fl6_icmp_code = code;
+	fl6.flowi6_uid = sock_net_uid(net, NULL);
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
@@ -564,6 +565,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	fl6.flowi6_oif = skb->dev->ifindex;
 	fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
 	fl6.flowi6_mark = mark;
+	fl6.flowi6_uid = sock_net_uid(net, NULL);
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);

net/ipv6/inet6_connection_sock.c

@@ -74,6 +74,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	fl6.flowi6_mark = inet_rsk(req)->ir_mark;
 	fl6.fl6_dport = inet_rsk(req)->rmt_port;
 	fl6.fl6_sport = inet_rsk(req)->loc_port;
+	fl6.flowi6_uid = sk->sk_uid;
 	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
@@ -225,6 +226,7 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused)
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_sport = inet->inet_sport;
 	fl6.fl6_dport = inet->inet_dport;
+	fl6.flowi6_uid = sk->sk_uid;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
         rcu_read_lock();

net/ipv6/ip6_tunnel.c

@@ -1038,6 +1038,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	memcpy(&fl6, &t->fl.u.ip6, sizeof (fl6));
 	fl6.flowi6_proto = IPPROTO_IPIP;
 
+	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
 	dsfield = ipv4_get_dsfield(iph);
 
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
@@ -1089,6 +1091,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	memcpy(&fl6, &t->fl.u.ip6, sizeof (fl6));
 	fl6.flowi6_proto = IPPROTO_IPV6;
+	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
 
 	dsfield = ipv6_get_dsfield(ipv6h);
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)

net/ipv6/ipcomp6.c

@@ -72,7 +72,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	printk(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/%pI6\n",
 			spi, &iph->daddr);
-	ip6_update_pmtu(skb, net, info, 0, 0);
+	ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
 	xfrm_state_put(x);
 }
 

net/ipv6/netfilter.c

@@ -19,6 +19,7 @@ int ip6_route_me_harder(struct sk_buff *skb)
 	struct flowi6 fl6 = {
 		.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
 		.flowi6_mark = skb->mark,
+		.flowi6_uid = sock_net_uid(net, skb->sk),
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
 	};

net/ipv6/ping.c

@@ -162,6 +162,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	fl6.saddr = np->saddr;
 	fl6.daddr = *daddr;
 	fl6.flowi6_mark = sk->sk_mark;
+	fl6.flowi6_uid = sk->sk_uid;
 	fl6.fl6_icmp_type = user_icmph.icmp6_type;
 	fl6.fl6_icmp_code = user_icmph.icmp6_code;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));

net/ipv6/raw.c

@@ -760,6 +760,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	memset(&fl6, 0, sizeof(fl6));
 
 	fl6.flowi6_mark = sk->sk_mark;
+	fl6.flowi6_uid = sk->sk_uid;
 
 	if (sin6) {
 		if (addr_len < SIN6_LEN_RFC2133)

net/ipv6/route.c

@@ -1094,7 +1094,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 }
 
 void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
-		     int oif, u32 mark)
+		     int oif, u32 mark, kuid_t uid)
 {
 	const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
 	struct dst_entry *dst;
@@ -1107,6 +1107,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 	fl6.daddr = iph->daddr;
 	fl6.saddr = iph->saddr;
 	fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK;
+	fl6.flowi6_uid = uid;
 
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (!dst->error)
@@ -1118,7 +1119,7 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
 void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 {
 	ip6_update_pmtu(skb, sock_net(sk), mtu,
-			sk->sk_bound_dev_if, sk->sk_mark);
+			sk->sk_bound_dev_if, sk->sk_mark, sk->sk_uid);
 }
 EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
 

net/ipv6/syncookies.c

@@ -246,6 +246,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		fl6.flowi6_mark = inet_rsk(req)->ir_mark;
 		fl6.fl6_dport = inet_rsk(req)->rmt_port;
 		fl6.fl6_sport = inet_sk(sk)->inet_sport;
+		fl6.flowi6_uid = sk->sk_uid;
 		security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);

net/ipv6/tcp_ipv6.c

@@ -252,6 +252,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
+	fl6.flowi6_uid = sk->sk_uid;
 
 	opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
 	final_p = fl6_update_dst(&fl6, opt, &final);
@@ -406,6 +407,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			fl6.flowi6_mark = sk->sk_mark;
 			fl6.fl6_dport = inet->inet_dport;
 			fl6.fl6_sport = inet->inet_sport;
+			fl6.flowi6_uid = sk->sk_uid;
 			security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 			dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
@@ -907,6 +909,7 @@ static void tcp_v6_send_response(struct sock *sk, struct sk_buff *skb, u32 seq,
 	fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
 	fl6.fl6_dport = t1->dest;
 	fl6.fl6_sport = t1->source;
+	fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	/* Pass a socket to ip6_dst_lookup either it is for RST

net/ipv6/udp.c

@@ -1094,6 +1094,7 @@ do_udp_sendmsg:
 		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
 
 	fl6.flowi6_mark = sk->sk_mark;
+	fl6.flowi6_uid = sk->sk_uid;
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;