net: core: Support UID-based routing.

This contains the following commits:

1. cc2f522 net: core: Add a UID range to fib rules.
2. d7ed2bd net: core: Use the socket UID in routing lookups.
3. 2f9306a net: core: Add a RTA_UID attribute to routes.
    This is so that userspace can do per-UID route lookups.
4. 8e46efb net: ipv6: Use the UID in IPv6 PMTUD
    IPv4 PMTUD already does this because ipv4_sk_update_pmtu
    uses __build_flow_key, which includes the UID.

Bug: 15413527
Change-Id: Iae3d4ca3979d252b6cec989bdc1a6875f811f03a
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>

include/net/fib_rules.h

@@ -29,6 +29,8 @@ struct fib_rule {
 	int			suppress_prefixlen;
 	char			iifname[IFNAMSIZ];
 	char			oifname[IFNAMSIZ];
+	kuid_t			uid_start;
+	kuid_t			uid_end;
 	struct rcu_head		rcu;
 };
 
@@ -87,6 +89,9 @@ struct fib_rules_ops {
 	[FRA_FWMARK]	= { .type = NLA_U32 }, \
 	[FRA_FWMASK]	= { .type = NLA_U32 }, \
 	[FRA_TABLE]     = { .type = NLA_U32 }, \
+	[FRA_GOTO]	= { .type = NLA_U32 }, \
+	[FRA_UID_START]	= { .type = NLA_U32 }, \
+	[FRA_UID_END]	= { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \
 	[FRA_GOTO]	= { .type = NLA_U32 }

include/net/flow.h

@@ -11,6 +11,7 @@
 #include <linux/in6.h>
 #include <linux/atomic.h>
 #include <net/flow_dissector.h>
+#include <linux/uidgid.h>
 
 /*
  * ifindex generation is per-net namespace, and loopback is
@@ -38,6 +39,7 @@ struct flowi_common {
 #define FLOWI_FLAG_SKIP_NH_OIF		0x08
 	__u32	flowic_secid;
 	struct flowi_tunnel flowic_tun_key;
+	kuid_t  flowic_uid;
 };
 
 union flowi_uli {
@@ -75,6 +77,7 @@ struct flowi4 {
 #define flowi4_flags		__fl_common.flowic_flags
 #define flowi4_secid		__fl_common.flowic_secid
 #define flowi4_tun_key		__fl_common.flowic_tun_key
+#define flowi4_uid		__fl_common.flowic_uid
 
 	/* (saddr,daddr) must be grouped, same order as in IP header */
 	__be32			saddr;
@@ -94,7 +97,8 @@ 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;
@@ -105,6 +109,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
 	fl4->flowi4_flags = flags;
 	fl4->flowi4_secid = 0;
 	fl4->flowi4_tun_key.tun_id = 0;
+	fl4->flowi4_uid = uid;
 	fl4->daddr = daddr;
 	fl4->saddr = saddr;
 	fl4->fl4_dport = dport;
@@ -133,6 +138,7 @@ struct flowi6 {
 #define flowi6_flags		__fl_common.flowic_flags
 #define flowi6_secid		__fl_common.flowic_secid
 #define flowi6_tun_key		__fl_common.flowic_tun_key
+#define flowi6_uid		__fl_common.flowic_uid
 	struct in6_addr		daddr;
 	struct in6_addr		saddr;
 	__be32			flowlabel;
@@ -177,6 +183,7 @@ struct flowi {
 #define flowi_flags	u.__fl_common.flowic_flags
 #define flowi_secid	u.__fl_common.flowic_secid
 #define flowi_tun_key	u.__fl_common.flowic_tun_key
+#define flowi_uid	u.__fl_common.flowic_uid
 } __attribute__((__aligned__(BITS_PER_LONG/8)));
 
 static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)

include/net/ip.h

@@ -170,6 +170,7 @@ 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

@@ -108,7 +108,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 		  const struct in6_addr *gwaddr);
 
 void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif,
-		     u32 mark);
+		     u32 mark, kuid_t uid);
 void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu);
 void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark);
 void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,

include/net/route.h

@@ -154,7 +154,7 @@ 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_i_uid(sk));
 	if (sk)
 		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
 	return ip_route_output_flow(net, fl4, sk);
@@ -267,7 +267,8 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32
 		flow_flags |= FLOWI_FLAG_ANYSRC;
 
 	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,
+			   sock_i_uid(sk));
 }
 
 static inline struct rtable *ip_route_connect(struct flowi4 *fl4,

include/uapi/linux/fib_rules.h

@@ -49,6 +49,8 @@ enum {
 	FRA_TABLE,	/* Extended table id */
 	FRA_FWMASK,	/* mask for netfilter mark */
 	FRA_OIFNAME,
+	FRA_UID_START,	/* UID range */
+	FRA_UID_END,
 	__FRA_MAX
 };
 

include/uapi/linux/rtnetlink.h

@@ -311,6 +311,7 @@ enum rtattr_type_t {
 	RTA_PREF,
 	RTA_ENCAP_TYPE,
 	RTA_ENCAP,
+	RTA_UID,
 	__RTA_MAX
 };
 

net/core/fib_rules.c

@@ -33,6 +33,8 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 	r->table = table;
 	r->flags = flags;
 	r->fr_net = ops->fro_net;
+	r->uid_start = INVALID_UID;
+	r->uid_end = INVALID_UID;
 
 	r->suppress_prefixlen = -1;
 	r->suppress_ifgroup = -1;
@@ -172,6 +174,23 @@ void fib_rules_unregister(struct fib_rules_ops *ops)
 }
 EXPORT_SYMBOL_GPL(fib_rules_unregister);
 
+static inline kuid_t fib_nl_uid(struct nlattr *nla)
+{
+	return make_kuid(current_user_ns(), nla_get_u32(nla));
+}
+
+static int nla_put_uid(struct sk_buff *skb, int idx, kuid_t uid)
+{
+	return nla_put_u32(skb, idx, from_kuid_munged(current_user_ns(), uid));
+}
+
+static int fib_uid_range_match(struct flowi *fl, struct fib_rule *rule)
+{
+	return (!uid_valid(rule->uid_start) && !uid_valid(rule->uid_end)) ||
+	       (uid_gte(fl->flowi_uid, rule->uid_start) &&
+		uid_lte(fl->flowi_uid, rule->uid_end));
+}
+
 static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 			  struct flowi *fl, int flags)
 {
@@ -189,6 +208,9 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 	if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id))
 		goto out;
 
+	if (!fib_uid_range_match(fl, rule))
+		goto out;
+
 	ret = ops->match(rule, fl, flags);
 out:
 	return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
@@ -371,6 +393,19 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 	} else if (rule->action == FR_ACT_GOTO)
 		goto errout_free;
 
+	/* UID start and end must either both be valid or both unspecified. */
+	rule->uid_start = rule->uid_end = INVALID_UID;
+	if (tb[FRA_UID_START] || tb[FRA_UID_END]) {
+		if (tb[FRA_UID_START] && tb[FRA_UID_END]) {
+			rule->uid_start = fib_nl_uid(tb[FRA_UID_START]);
+			rule->uid_end = fib_nl_uid(tb[FRA_UID_END]);
+		}
+		if (!uid_valid(rule->uid_start) ||
+		    !uid_valid(rule->uid_end) ||
+		    !uid_lte(rule->uid_start, rule->uid_end))
+		goto errout_free;
+	}
+
 	err = ops->configure(rule, skb, frh, tb);
 	if (err < 0)
 		goto errout_free;
@@ -483,6 +518,14 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 		    (rule->tun_id != nla_get_be64(tb[FRA_TUN_ID])))
 			continue;
 
+		if (tb[FRA_UID_START] &&
+		    !uid_eq(rule->uid_start, fib_nl_uid(tb[FRA_UID_START])))
+			continue;
+
+		if (tb[FRA_UID_END] &&
+		    !uid_eq(rule->uid_end, fib_nl_uid(tb[FRA_UID_END])))
+			continue;
+
 		if (!ops->compare(rule, frh, tb))
 			continue;
 
@@ -549,7 +592,9 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
 			 + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */
 			 + nla_total_size(4) /* FRA_FWMARK */
 			 + nla_total_size(4) /* FRA_FWMASK */
-			 + nla_total_size(8); /* FRA_TUN_ID */
+			 + nla_total_size(8) /* FRA_TUN_ID */
+			 + nla_total_size(4) /* FRA_UID_START */
+			 + nla_total_size(4); /* FRA_UID_END */
 
 	if (ops->nlmsg_payload)
 		payload += ops->nlmsg_payload(rule);
@@ -607,7 +652,11 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	    (rule->target &&
 	     nla_put_u32(skb, FRA_GOTO, rule->target)) ||
 	    (rule->tun_id &&
-	     nla_put_be64(skb, FRA_TUN_ID, rule->tun_id)))
+	     nla_put_be64(skb, FRA_TUN_ID, rule->tun_id)) ||
+	    (uid_valid(rule->uid_start) &&
+	     nla_put_uid(skb, FRA_UID_START, rule->uid_start)) ||
+	    (uid_valid(rule->uid_end) &&
+	     nla_put_uid(skb, FRA_UID_END, rule->uid_end)))
 		goto nla_put_failure;
 
 	if (rule->suppress_ifgroup != -1) {

net/ipv4/fib_frontend.c

@@ -629,6 +629,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
 	[RTA_FLOW]		= { .type = NLA_U32 },
 	[RTA_ENCAP_TYPE]	= { .type = NLA_U16 },
 	[RTA_ENCAP]		= { .type = NLA_NESTED },
+	[RTA_UID]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,

net/ipv4/inet_connection_sock.c

@@ -420,7 +420,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, ireq->ir_rmt_port,
-			   htons(ireq->ir_num));
+			   htons(ireq->ir_num), sock_i_uid(sk));
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -457,7 +457,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, ireq->ir_rmt_port,
-			   htons(ireq->ir_num));
+			   htons(ireq->ir_num), sock_i_uid(sk));
 	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

@@ -1573,7 +1573,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
 			   ip_reply_arg_flowi_flags(arg),
 			   daddr, saddr,
-			   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(net, &fl4);
 	if (IS_ERR(rt))

net/ipv4/ping.c

@@ -789,7 +789,8 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	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,
+			   sock_i_uid(sk));
 
 	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);

net/ipv4/raw.c

@@ -599,7 +599,8 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk) |
 			    (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
-			   daddr, saddr, 0, 0);
+			   daddr, saddr, 0, 0,
+			   sock_i_uid(sk));
 
 	if (!saddr && ipc.oif) {
 		err = l3mdev_get_saddr(net, ipc.oif, &fl4);

net/ipv4/route.c

@@ -500,7 +500,7 @@ void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
 }
 EXPORT_SYMBOL(__ip_select_ident);
 
-static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void __build_flow_key(struct flowi4 *fl4, struct sock *sk,
 			     const struct iphdr *iph,
 			     int oif, u8 tos,
 			     u8 prot, u32 mark, int flow_flags)
@@ -516,11 +516,12 @@ static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
 	flowi4_init_output(fl4, oif, mark, tos,
 			   RT_SCOPE_UNIVERSE, prot,
 			   flow_flags,
-			   iph->daddr, iph->saddr, 0, 0);
+			   iph->daddr, iph->saddr, 0, 0,
+			   sock_i_uid(sk));
 }
 
 static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
-			       const struct sock *sk)
+			       struct sock *sk)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	int oif = skb->dev->ifindex;
@@ -531,7 +532,7 @@ static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
 	__build_flow_key(fl4, sk, iph, oif, tos, prot, mark, 0);
 }
 
-static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
+static void build_sk_flow_key(struct flowi4 *fl4, struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 	const struct ip_options_rcu *inet_opt;
@@ -545,11 +546,12 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk),
-			   daddr, inet->inet_saddr, 0, 0);
+			   daddr, inet->inet_saddr, 0, 0,
+			   sock_i_uid(sk));
 	rcu_read_unlock();
 }
 
-static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void ip_rt_build_flow_key(struct flowi4 *fl4, struct sock *sk,
 				 const struct sk_buff *skb)
 {
 	if (skb)
@@ -2422,6 +2424,11 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 	    nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark))
 		goto nla_put_failure;
 
+	if (!uid_eq(fl4->flowi4_uid, INVALID_UID) &&
+	    nla_put_u32(skb, RTA_UID,
+			from_kuid_munged(current_user_ns(), fl4->flowi4_uid)))
+		goto nla_put_failure;
+
 	error = rt->dst.error;
 
 	if (rt_is_input_route(rt)) {
@@ -2473,6 +2480,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	int mark;
 	struct sk_buff *skb;
 	u32 table_id = RT_TABLE_MAIN;
+	kuid_t uid;
 
 	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
 	if (err < 0)
@@ -2500,6 +2508,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
 	iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
 	mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
+	if (tb[RTA_UID])
+		uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID]));
+	else
+		uid = (iif ? INVALID_UID : current_uid());
 
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = dst;
@@ -2507,6 +2519,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	fl4.flowi4_tos = rtm->rtm_tos;
 	fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
 	fl4.flowi4_mark = mark;
+	fl4.flowi4_uid = uid;
 
 	if (netif_index_is_l3_master(net, fl4.flowi4_oif))
 		fl4.flowi4_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF;

net/ipv4/syncookies.c

@@ -374,8 +374,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	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->srr ? opt->faddr : ireq->ir_rmt_addr,
-			   ireq->ir_loc_addr, th->source, th->dest);
+			   (opt && opt->srr) ? opt->faddr : ireq->ir_rmt_addr,
+			   ireq->ir_loc_addr, th->source, th->dest,
+			   sock_i_uid(sk));
 	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_key(sock_net(sk), &fl4);
 	if (IS_ERR(rt)) {

net/ipv4/udp.c

@@ -1023,7 +1023,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
 				   RT_SCOPE_UNIVERSE, sk->sk_protocol,
 				   flow_flags,
-				   faddr, saddr, dport, inet->inet_sport);
+				   faddr, saddr, dport, inet->inet_sport,
+				   sock_i_uid(sk));
 
 		if (!saddr && ipc.oif) {
 			err = l3mdev_get_saddr(net, ipc.oif, fl4);

net/ipv6/af_inet6.c

@@ -695,6 +695,7 @@ 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 = sock_i_uid(sk);
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
 		rcu_read_lock();

net/ipv6/ah6.c

@@ -664,7 +664,7 @@ static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0);
 	else
-		ip6_update_pmtu(skb, net, info, 0, 0);
+		ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
 	xfrm_state_put(x);
 
 	return 0;

net/ipv6/datagram.c

@@ -161,6 +161,7 @@ ipv4_connected:
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_dport = inet->inet_dport;
 	fl6.fl6_sport = inet->inet_sport;
+	fl6.flowi6_uid = sock_i_uid(sk);
 
 	if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
 		fl6.flowi6_oif = np->mcast_oif;

net/ipv6/esp6.c

@@ -476,7 +476,7 @@ static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0);
 	else
-		ip6_update_pmtu(skb, net, info, 0, 0);
+		ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
 	xfrm_state_put(x);
 
 	return 0;