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: I81bd31dae655de9cce7d7a1f9a905dc1c2feba7c
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 0e91311..a40a876 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -31,6 +31,8 @@
r->pref = pref;
r->table = table;
r->flags = flags;
+ r->uid_start = INVALID_UID;
+ r->uid_end = INVALID_UID;
r->fr_net = hold_net(ops->fro_net);
/* The lock is not required here, the list in unreacheable
@@ -179,6 +181,23 @@
}
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)
{
@@ -193,6 +212,9 @@
if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
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;
@@ -363,6 +385,19 @@
} 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;
@@ -469,6 +504,14 @@
(rule->mark_mask != nla_get_u32(tb[FRA_FWMASK])))
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;
@@ -525,7 +568,9 @@
+ nla_total_size(4) /* FRA_PRIORITY */
+ nla_total_size(4) /* FRA_TABLE */
+ nla_total_size(4) /* FRA_FWMARK */
- + nla_total_size(4); /* FRA_FWMASK */
+ + nla_total_size(4) /* FRA_FWMASK */
+ + nla_total_size(4) /* FRA_UID_START */
+ + nla_total_size(4); /* FRA_UID_END */
if (ops->nlmsg_payload)
payload += ops->nlmsg_payload(rule);
@@ -579,7 +624,11 @@
((rule->mark_mask || rule->mark) &&
nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) ||
(rule->target &&
- nla_put_u32(skb, FRA_GOTO, rule->target)))
+ nla_put_u32(skb, FRA_GOTO, rule->target)) ||
+ (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 (ops->fill(rule, skb, frh) < 0)
goto nla_put_failure;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c7629a2..ffffeb4 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -531,6 +531,7 @@
[RTA_METRICS] = { .type = NLA_NESTED },
[RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
[RTA_FLOW] = { .type = NLA_U32 },
+ [RTA_UID] = { .type = NLA_U32 },
};
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 442087d..6dfec2f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -422,7 +422,8 @@
sk->sk_protocol,
flags,
(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,
+ 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))
@@ -458,7 +459,8 @@
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,
+ 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))
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c2ee385..8e20e94 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1503,7 +1503,8 @@
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))
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 111e5a4..b83d829 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -768,7 +768,8 @@
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);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index dd44e0a..b828733 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -572,7 +572,8 @@
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,
+ sock_i_uid(sk));
if (!inet->hdrincl) {
err = raw_probe_proto_opt(&fl4, msg);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c043591..ef2fe9d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -500,7 +500,7 @@
}
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 @@
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 @@
__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 @@
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)
@@ -2287,6 +2289,11 @@
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)) {
@@ -2336,6 +2343,7 @@
int err;
int mark;
struct sk_buff *skb;
+ kuid_t uid;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
if (err < 0)
@@ -2363,6 +2371,10 @@
dst = tb[RTA_DST] ? nla_get_be32(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;
@@ -2370,6 +2382,7 @@
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 (iif) {
struct net_device *dev;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 5abb45e..c94032b 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -353,7 +353,8 @@
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,
+ 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)) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0bf5d39..35ab330 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -962,7 +962,8 @@
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,
+ sock_i_uid(sk));
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index a4cfde6..d29ae19 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -694,6 +694,7 @@
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));
final_p = fl6_update_dst(&fl6, np->opt, &final);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index bb02e17..b903e19 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -630,7 +630,7 @@
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, 0, 0);
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
xfrm_state_put(x);
}
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 4b56cbb..00b4a5f 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -162,6 +162,7 @@
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;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 40ffd72..fdc81cb 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -449,7 +449,7 @@
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, 0, 0);
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
xfrm_state_put(x);
}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 28da400..12b1a94 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -90,7 +90,7 @@
struct net *net = dev_net(skb->dev);
if (type == ICMPV6_PKT_TOOBIG)
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
else if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, 0, 0);
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index f149313..65a4605 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -84,6 +84,7 @@
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 = sock_i_uid(sk);
security_req_classify_flow(req, flowi6_to_flowi(fl6));
dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
@@ -211,6 +212,7 @@
fl6->flowi6_mark = sk->sk_mark;
fl6->fl6_sport = inet->inet_sport;
fl6->fl6_dport = inet->inet_dport;
+ fl6->flowi6_uid = sock_i_uid(sk);
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
final_p = fl6_update_dst(fl6, np->opt, &final);
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 7af5aee..a1beb59 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -78,7 +78,7 @@
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, 0, 0);
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
xfrm_state_put(x);
}
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index d4edfce..38ceca8 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -159,6 +159,7 @@
fl6.saddr = np->saddr;
fl6.daddr = *daddr;
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sock_i_uid(sk);
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));
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index eedff8c..dfef315 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -761,6 +761,7 @@
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sock_i_uid(sk);
if (sin6) {
if (addr_len < SIN6_LEN_RFC2133)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8ecf44a..bad3646 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1099,7 +1099,7 @@
}
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;
@@ -1112,6 +1112,7 @@
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
+ fl6.flowi6_uid = uid;
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
@@ -1123,7 +1124,7 @@
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, sock_i_uid(sk));
}
EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
@@ -2199,6 +2200,7 @@
[RTA_PRIORITY] = { .type = NLA_U32 },
[RTA_METRICS] = { .type = NLA_NESTED },
[RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
+ [RTA_UID] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -2585,6 +2587,12 @@
if (tb[RTA_OIF])
oif = nla_get_u32(tb[RTA_OIF]);
+ if (tb[RTA_UID])
+ fl6.flowi6_uid = make_kuid(current_user_ns(),
+ nla_get_u32(tb[RTA_UID]));
+ else
+ fl6.flowi6_uid = iif ? INVALID_UID : current_uid();
+
if (iif) {
struct net_device *dev;
int flags = 0;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 1efbc6f..ba8622d 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -243,6 +243,7 @@
fl6.flowi6_mark = ireq->ir_mark;
fl6.fl6_dport = inet_rsk(req)->rmt_port;
fl6.fl6_sport = inet_sk(sk)->inet_sport;
+ fl6.flowi6_uid = sock_i_uid(sk);
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 6e882da..a4fc647 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -252,6 +252,7 @@
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sock_i_uid(sk);
final_p = fl6_update_dst(&fl6, np->opt, &final);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 42923b1..e6dd85d 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1147,6 +1147,7 @@
fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sock_i_uid(sk);
if (msg->msg_controllen) {
opt = &opt_space;