[PATCH net-next] net: inet: Support UID-based routing

[PATCH net-next] net: inet: Support UID-based routing

[Lorenzo Colitti]

This patchset adds support for per-UID routing. It allows the
administrator to configure rules such as:

  ip rule add uidrange 100-200 lookup 123

This functionality has been in use by all Android devices since
5.0, which was released in late 2014. It is primarily used to
impose per-app routing policies (on Android, every app has its
own UID) without having to resort to rerouting packets in
iptables, which breaks getsockname() and MTU/MSS calculation,
and generally disrupts end-to-end connectivity.

This patch series is similar to the code currently used on
Android, but has better correctness and performance because
it stores the UID in the socket instead of calling sock_i_uid.
This avoids contention on sk->sk_callback_lock, and makes it
possible to correctly route a socket on which userspace has
called close(), for which sock_i_uid will return 0.

[PATCH net-next 1/3] net: core: Add a UID field to struct sock.

[Lorenzo Colitti]

Protocol sockets (struct sock) don't have UIDs, but most of the
time, they map 1:1 to userspace sockets (struct socket) which do.

Various operations such as the iptables xt_owner match need
access to the "UID of a socket", and do so by following the
backpointer to the struct socket. This involves taking
sk_callback_lock and doesn't work when there is no socket
because userspace has already called close().

Simplify this by adding a sk_uid field to struct sock whose value
matches the UID of the corresponding struct socket. The semantics
are as follows:

1. Whenever sk_socket is non-null: sk_uid is the same as the UID
   in sk_socket, i.e., matches the return value of sock_i_uid.
   Specifically, the UID is set when userspace calls socket(),
   fchown(), or accept().
2. When sk_socket is null, sk_uid is defined as follows:
   - For a socket that no longer has a sk_socket because
     userspace has called close(): the previous UID.
   - For a cloned socket (e.g., an incoming connection that is
     established but on which userspace has not yet called
     accept): the UID of the socket it was cloned from.
   - For a socket that has never had an sk_socket (e.g., a kernel
     ICMP socket): UID 0 inside the user namespace corresponding
     to the network namespace the socket belongs to. This is
     arguably better than GLOBAL_ROOT_UID because it allows
     "--owner-uid 0" to match kernel-originated packets in
     non-root namespaces.

Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
---
 include/net/sock.h |  7 +++++++
 net/core/sock.c    |  6 +++++-
 net/socket.c       | 14 ++++++++++++++
 3 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 2764895..2086922 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -417,6 +417,7 @@ struct sock {
 	u32			sk_max_ack_backlog;
 	__u32			sk_priority;
 	__u32			sk_mark;
+	kuid_t			sk_uid;
 	struct pid		*sk_peer_pid;
 	const struct cred	*sk_peer_cred;
 	long			sk_rcvtimeo;
@@ -1651,6 +1652,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 	sk->sk_wq = parent->wq;
 	parent->sk = sk;
 	sk_set_socket(sk, parent);
+	sk->sk_uid = SOCK_INODE(parent)->i_uid;
 	security_sock_graft(sk, parent);
 	write_unlock_bh(&sk->sk_callback_lock);
 }
@@ -1658,6 +1660,11 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 kuid_t sock_i_uid(struct sock *sk);
 unsigned long sock_i_ino(struct sock *sk);
 
+static inline kuid_t sock_net_uid(struct net *net, const struct sock *sk)
+{
+	return sk ? sk->sk_uid : make_kuid(net->user_ns, 0);
+}
+
 static inline u32 net_tx_rndhash(void)
 {
 	u32 v = prandom_u32();
diff --git a/net/core/sock.c b/net/core/sock.c
index d8e4532e..831e4e8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1570,6 +1570,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 */
 		sk_refcnt_debug_inc(newsk);
 		sk_set_socket(newsk, NULL);
+		newsk->sk_uid = sk->sk_uid;
 		newsk->sk_wq = NULL;
 
 		if (newsk->sk_prot->sockets_allocated)
@@ -2460,8 +2461,11 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 		sk->sk_type	=	sock->type;
 		sk->sk_wq	=	sock->wq;
 		sock->sk	=	sk;
-	} else
+		sk->sk_uid	=	SOCK_INODE(sock)->i_uid;
+	} else {
 		sk->sk_wq	=	NULL;
+		sk->sk_uid	=	make_kuid(sock_net(sk)->user_ns, 0);
+	}
 
 	rwlock_init(&sk->sk_callback_lock);
 	lockdep_set_class_and_name(&sk->sk_callback_lock,
diff --git a/net/socket.c b/net/socket.c
index 5a9bf5e..5a4747e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -518,8 +518,22 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer,
 	return used;
 }
 
+int sockfs_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+	int err = simple_setattr(dentry, iattr);
+
+	if (!err) {
+		struct socket *sock = SOCKET_I(d_inode(dentry));
+
+		sock->sk->sk_uid = iattr->ia_uid;
+	}
+
+	return err;
+}
+
 static const struct inode_operations sockfs_inode_ops = {
 	.listxattr = sockfs_listxattr,
+	.setattr = sockfs_setattr,
 };
 
 /**
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH net-next 1/3] net: core: Add a UID field to struct sock.

[Eric Dumazet]

On Fri, 2016-10-28 at 02:20 +0900, Lorenzo Colitti wrote:

> diff --git a/net/core/sock.c b/net/core/sock.c
> index d8e4532e..831e4e8 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
> @@ -1570,6 +1570,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
>  		 */
>  		sk_refcnt_debug_inc(newsk);
>  		sk_set_socket(newsk, NULL);
> +		newsk->sk_uid = sk->sk_uid;

Not sure why this is needed ?

sk_clone_lock() already copies sk to newsk, using sock_copy(newsk, sk);

>  		newsk->sk_wq = NULL;
>  
>  		if (newsk->sk_prot->sockets_allocated)
> @@ -2460,8 +2461,11 @@ void sock_init_data(struct socket *sock, struct sock *sk)

Re: [PATCH net-next 1/3] net: core: Add a UID field to struct sock.

[David Miller]

From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 27 Oct 2016 10:36:26 -0700

> On Fri, 2016-10-28 at 02:20 +0900, Lorenzo Colitti wrote:
> 
>> diff --git a/net/core/sock.c b/net/core/sock.c
>> index d8e4532e..831e4e8 100644
>> --- a/net/core/sock.c
>> +++ b/net/core/sock.c
>> @@ -1570,6 +1570,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
>>  		 */
>>  		sk_refcnt_debug_inc(newsk);
>>  		sk_set_socket(newsk, NULL);
>> +		newsk->sk_uid = sk->sk_uid;
> 
> Not sure why this is needed ?
> 
> sk_clone_lock() already copies sk to newsk, using sock_copy(newsk, sk);

Agreed.

Re: [PATCH net-next 1/3] net: core: Add a UID field to struct sock.

[kbuild test robot]

[-- Attachment #1: Type: text/plain, Size: 3050 bytes --]

Hi Lorenzo,

[auto build test WARNING on net-next/master]

url:    https://github.com/0day-ci/linux/commits/Lorenzo-Colitti/net-core-Add-a-UID-field-to-struct-sock/20161028-020552
reproduce: make htmldocs

All warnings (new ones prefixed by >>):

   include/linux/skbuff.h:947: warning: No description found for parameter 'sk'
   include/net/sock.h:450: warning: No description found for parameter 'sk_padding'
>> include/net/sock.h:450: warning: No description found for parameter 'sk_uid'
   include/net/sock.h:450: warning: No description found for parameter 'sk_rcu'
   include/linux/netdevice.h:1902: warning: No description found for parameter 'prio_tc_map[TC_BITMASK + 1]'

vim +/sk_uid +450 include/net/sock.h

ef64a54f6 Pavel Emelyanov 2012-02-21  434  	__s32			sk_peek_off;
^1da177e4 Linus Torvalds  2005-04-16  435  	int			sk_write_pending;
d5f642384 Alexey Dobriyan 2008-11-04  436  #ifdef CONFIG_SECURITY
^1da177e4 Linus Torvalds  2005-04-16  437  	void			*sk_security;
d5f642384 Alexey Dobriyan 2008-11-04  438  #endif
2a56a1fec Tejun Heo       2015-12-07  439  	struct sock_cgroup_data	sk_cgrp_data;
baac50bbc Johannes Weiner 2016-01-14  440  	struct mem_cgroup	*sk_memcg;
^1da177e4 Linus Torvalds  2005-04-16  441  	void			(*sk_state_change)(struct sock *sk);
676d23690 David S. Miller 2014-04-11  442  	void			(*sk_data_ready)(struct sock *sk);
^1da177e4 Linus Torvalds  2005-04-16  443  	void			(*sk_write_space)(struct sock *sk);
^1da177e4 Linus Torvalds  2005-04-16  444  	void			(*sk_error_report)(struct sock *sk);
^1da177e4 Linus Torvalds  2005-04-16  445  	int			(*sk_backlog_rcv)(struct sock *sk,
^1da177e4 Linus Torvalds  2005-04-16  446  						  struct sk_buff *skb);
^1da177e4 Linus Torvalds  2005-04-16  447  	void                    (*sk_destruct)(struct sock *sk);
ef456144d Craig Gallek    2016-01-04  448  	struct sock_reuseport __rcu	*sk_reuseport_cb;
a4298e452 Eric Dumazet    2016-04-01  449  	struct rcu_head		sk_rcu;
^1da177e4 Linus Torvalds  2005-04-16 @450  };
^1da177e4 Linus Torvalds  2005-04-16  451  
559835ea7 Pravin B Shelar 2013-09-24  452  #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
559835ea7 Pravin B Shelar 2013-09-24  453  
559835ea7 Pravin B Shelar 2013-09-24  454  #define rcu_dereference_sk_user_data(sk)	rcu_dereference(__sk_user_data((sk)))
559835ea7 Pravin B Shelar 2013-09-24  455  #define rcu_assign_sk_user_data(sk, ptr)	rcu_assign_pointer(__sk_user_data((sk)), ptr)
559835ea7 Pravin B Shelar 2013-09-24  456  
4a17fd522 Pavel Emelyanov 2012-04-19  457  /*
4a17fd522 Pavel Emelyanov 2012-04-19  458   * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK

:::::: The code at line 450 was first introduced by commit
:::::: 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 Linux-2.6.12-rc2

:::::: TO: Linus Torvalds <torvalds@ppc970.osdl.org>
:::::: CC: Linus Torvalds <torvalds@ppc970.osdl.org>

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 6440 bytes --]

[PATCH net-next 2/3] net: core: add UID to flows, rules, and routes

[Lorenzo Colitti]

- Define a new FIB rule attributes, FRA_UID_RANGE, to describe a
  range of UIDs.
- Define a RTA_UID attribute for per-UID route lookups and dumps.
- Support passing these attributes to and from userspace via
  rtnetlink. The value INVALID_UID indicates no UID was
  specified.
- Add a UID field to the flow structures.

Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
---
 include/net/fib_rules.h        |  9 ++++-
 include/net/flow.h             |  5 +++
 include/uapi/linux/fib_rules.h |  6 ++++
 include/uapi/linux/rtnetlink.h |  1 +
 net/core/fib_rules.c           | 74 ++++++++++++++++++++++++++++++++++++++++--
 net/ipv4/fib_frontend.c        |  1 +
 net/ipv4/route.c               | 11 +++++++
 net/ipv6/route.c               |  7 ++++
 8 files changed, 111 insertions(+), 3 deletions(-)

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 456e4a6..8dbfdf7 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -8,6 +8,11 @@
 #include <net/flow.h>
 #include <net/rtnetlink.h>
 
+struct fib_kuid_range {
+	kuid_t start;
+	kuid_t end;
+};
+
 struct fib_rule {
 	struct list_head	list;
 	int			iifindex;
@@ -30,6 +35,7 @@ struct fib_rule {
 	int			suppress_prefixlen;
 	char			iifname[IFNAMSIZ];
 	char			oifname[IFNAMSIZ];
+	struct fib_kuid_range	uid_range;
 	struct rcu_head		rcu;
 };
 
@@ -92,7 +98,8 @@ struct fib_rules_ops {
 	[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \
 	[FRA_GOTO]	= { .type = NLA_U32 }, \
-	[FRA_L3MDEV]	= { .type = NLA_U8 }
+	[FRA_L3MDEV]	= { .type = NLA_U8 }, \
+	[FRA_UID_RANGE]	= { .len = sizeof(struct fib_rule_uid_range) }
 
 static inline void fib_rule_get(struct fib_rule *rule)
 {
diff --git a/include/net/flow.h b/include/net/flow.h
index 035aa77..51373f3 100644
--- a/include/net/flow.h
+++ b/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
@@ -37,6 +38,7 @@ struct flowi_common {
 #define FLOWI_FLAG_SKIP_NH_OIF		0x04
 	__u32	flowic_secid;
 	struct flowi_tunnel flowic_tun_key;
+	kuid_t  flowic_uid;
 };
 
 union flowi_uli {
@@ -74,6 +76,7 @@ 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;
@@ -131,6 +134,7 @@ 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;
 	/* Note: flowi6_tos is encoded in flowlabel, too. */
@@ -176,6 +180,7 @@ 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)
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 14404b3..bbf02a6 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -29,6 +29,11 @@ struct fib_rule_hdr {
 	__u32		flags;
 };
 
+struct fib_rule_uid_range {
+	__u32		start;
+	__u32		end;
+};
+
 enum {
 	FRA_UNSPEC,
 	FRA_DST,	/* destination address */
@@ -51,6 +56,7 @@ enum {
 	FRA_OIFNAME,
 	FRA_PAD,
 	FRA_L3MDEV,	/* iif or oif is l3mdev goto its table */
+	FRA_UID_RANGE,	/* UID range */
 	__FRA_MAX
 };
 
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 262f037..bb85e78 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -318,6 +318,7 @@ enum rtattr_type_t {
 	RTA_ENCAP,
 	RTA_EXPIRES,
 	RTA_PAD,
+	RTA_UID,
 	__RTA_MAX
 };
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index be4629c..5de436a 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -18,6 +18,11 @@
 #include <net/fib_rules.h>
 #include <net/ip_tunnels.h>
 
+static const struct fib_kuid_range fib_kuid_range_unset = {
+	KUIDT_INIT(0),
+	KUIDT_INIT(~0),
+};
+
 int fib_default_rule_add(struct fib_rules_ops *ops,
 			 u32 pref, u32 table, u32 flags)
 {
@@ -33,6 +38,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 	r->table = table;
 	r->flags = flags;
 	r->fr_net = ops->fro_net;
+	r->uid_range = fib_kuid_range_unset;
 
 	r->suppress_prefixlen = -1;
 	r->suppress_ifgroup = -1;
@@ -172,6 +178,34 @@ void fib_rules_unregister(struct fib_rules_ops *ops)
 }
 EXPORT_SYMBOL_GPL(fib_rules_unregister);
 
+static int uid_range_set(struct fib_kuid_range *range)
+{
+	return uid_valid(range->start) && uid_valid(range->end);
+}
+
+static struct fib_kuid_range nla_get_kuid_range(struct nlattr **tb)
+{
+	struct fib_rule_uid_range *in;
+	struct fib_kuid_range out;
+
+	in = (struct fib_rule_uid_range *)nla_data(tb[FRA_UID_RANGE]);
+
+	out.start = make_kuid(current_user_ns(), in->start);
+	out.end = make_kuid(current_user_ns(), in->end);
+
+	return out;
+}
+
+static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range)
+{
+	struct fib_rule_uid_range out = {
+		from_kuid_munged(current_user_ns(), range->start),
+		from_kuid_munged(current_user_ns(), range->end)
+	};
+
+	return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out);
+}
+
 static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 			  struct flowi *fl, int flags,
 			  struct fib_lookup_arg *arg)
@@ -193,6 +227,10 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 	if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg))
 		goto out;
 
+	if (uid_lt(fl->flowi_uid, rule->uid_range.start) ||
+	    uid_gt(fl->flowi_uid, rule->uid_range.end))
+		goto out;
+
 	ret = ops->match(rule, fl, flags);
 out:
 	return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
@@ -429,6 +467,21 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (rule->l3mdev && rule->table)
 		goto errout_free;
 
+	if (tb[FRA_UID_RANGE]) {
+		if (current_user_ns() != net->user_ns) {
+			err = -EPERM;
+			goto errout_free;
+		}
+
+		rule->uid_range = nla_get_kuid_range(tb);
+
+		if (!uid_range_set(&rule->uid_range) ||
+		    !uid_lte(rule->uid_range.start, rule->uid_range.end))
+			goto errout_free;
+	} else {
+		rule->uid_range = fib_kuid_range_unset;
+	}
+
 	if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
 	    rule_exists(ops, frh, tb, rule)) {
 		err = -EEXIST;
@@ -497,6 +550,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct fib_rules_ops *ops = NULL;
 	struct fib_rule *rule, *tmp;
 	struct nlattr *tb[FRA_MAX+1];
+	struct fib_kuid_range range;
 	int err = -EINVAL;
 
 	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh)))
@@ -516,6 +570,14 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (err < 0)
 		goto errout;
 
+	if (tb[FRA_UID_RANGE]) {
+		range = nla_get_kuid_range(tb);
+		if (!uid_range_set(&range))
+			goto errout;
+	} else {
+		range = fib_kuid_range_unset;
+	}
+
 	list_for_each_entry(rule, &ops->rules_list, list) {
 		if (frh->action && (frh->action != rule->action))
 			continue;
@@ -552,6 +614,11 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 		    (rule->l3mdev != nla_get_u8(tb[FRA_L3MDEV])))
 			continue;
 
+		if (uid_range_set(&range) &&
+		    (!uid_eq(rule->uid_range.start, range.start) ||
+		     !uid_eq(rule->uid_range.end, range.end)))
+			continue;
+
 		if (!ops->compare(rule, frh, tb))
 			continue;
 
@@ -619,7 +686,8 @@ 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_64bit(8); /* FRA_TUN_ID */
+			 + nla_total_size_64bit(8) /* FRA_TUN_ID */
+			 + nla_total_size(sizeof(struct fib_kuid_range));
 
 	if (ops->nlmsg_payload)
 		payload += ops->nlmsg_payload(rule);
@@ -679,7 +747,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	    (rule->tun_id &&
 	     nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) ||
 	    (rule->l3mdev &&
-	     nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)))
+	     nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) ||
+	    (uid_range_set(&rule->uid_range) &&
+	     nla_put_uid_range(skb, &rule->uid_range)))
 		goto nla_put_failure;
 
 	if (rule->suppress_ifgroup != -1) {
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c3b8047..d93eea8 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -610,6 +610,7 @@ 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,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 62d4d90..0a42dc0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2493,6 +2493,11 @@ 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)) {
@@ -2545,6 +2550,7 @@ 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)
@@ -2572,6 +2578,10 @@ 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;
@@ -2579,6 +2589,7 @@ 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 (iif) {
 		struct net_device *dev;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index bdbc38e..cd84ded 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2767,6 +2767,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_ENCAP_TYPE]	= { .type = NLA_U16 },
 	[RTA_ENCAP]		= { .type = NLA_NESTED },
 	[RTA_EXPIRES]		= { .type = NLA_U32 },
+	[RTA_UID]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -3341,6 +3342,12 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	if (tb[RTA_MARK])
 		fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
 
+	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;
-- 
2.8.0.rc3.226.g39d4020

[PATCH net-next 3/3] net: inet: Support UID-based routing in IP protocols.

[Lorenzo Colitti]

- 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.

Tested: compiles allnoconfig, allyesconfig, allmodconfig
Tested: https://android-review.googlesource.com/253302
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
---
 include/net/flow.h               |  4 +++-
 include/net/ip.h                 |  1 +
 include/net/ip6_route.h          |  2 +-
 include/net/route.h              |  5 +++--
 net/ipv4/icmp.c                  |  9 ++++++---
 net/ipv4/inet_connection_sock.c  |  4 ++--
 net/ipv4/ip_output.c             |  3 ++-
 net/ipv4/ping.c                  |  3 ++-
 net/ipv4/raw.c                   |  2 +-
 net/ipv4/route.c                 | 31 +++++++++++++++++--------------
 net/ipv4/syncookies.c            |  2 +-
 net/ipv4/tcp_ipv4.c              |  1 +
 net/ipv4/udp.c                   |  3 ++-
 net/ipv6/af_inet6.c              |  1 +
 net/ipv6/ah6.c                   |  2 +-
 net/ipv6/datagram.c              |  1 +
 net/ipv6/esp6.c                  |  2 +-
 net/ipv6/icmp.c                  |  4 +++-
 net/ipv6/inet6_connection_sock.c |  2 ++
 net/ipv6/ip6_gre.c               |  4 ++++
 net/ipv6/ip6_tunnel.c            |  4 ++++
 net/ipv6/ip6_vti.c               |  3 ++-
 net/ipv6/ipcomp6.c               |  2 +-
 net/ipv6/netfilter.c             |  1 +
 net/ipv6/ping.c                  |  1 +
 net/ipv6/raw.c                   |  1 +
 net/ipv6/route.c                 |  7 +++++--
 net/ipv6/syncookies.c            |  1 +
 net/ipv6/tcp_ipv6.c              |  2 ++
 net/ipv6/udp.c                   |  1 +
 net/l2tp/l2tp_ip6.c              |  1 +
 31 files changed, 75 insertions(+), 35 deletions(-)

diff --git a/include/net/flow.h b/include/net/flow.h
index 51373f3..6bbbca8 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -96,7 +96,8 @@ 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;
@@ -107,6 +108,7 @@ 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;
diff --git a/include/net/ip.h b/include/net/ip.h
index bc43c0f..f4182b1 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -173,6 +173,7 @@ struct ip_reply_arg {
 				/* -1 if not needed */ 
 	int	    bound_dev_if;
 	u8  	    tos;
+	kuid_t	    uid;
 }; 
 
 #define IP_REPLY_ARG_NOSRCCHECK 1
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index e0cd318..8498e19 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -139,7 +139,7 @@ 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,
diff --git a/include/net/route.h b/include/net/route.h
index 0429d47..c0874c8 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -153,7 +153,7 @@ 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);
@@ -269,7 +269,8 @@ 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,
+			   sk->sk_uid);
 }
 
 static inline struct rtable *ip_route_connect(struct flowi4 *fl4,
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 38abe70..7455987 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -425,6 +425,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
 	fl4.flowi4_mark = mark;
+	fl4.flowi4_uid = sk->sk_uid;
 	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
 	fl4.flowi4_proto = IPPROTO_ICMP;
 	fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
@@ -460,7 +461,8 @@ static struct rtable *icmp_route_lookup(struct net *net,
 					struct flowi4 *fl4,
 					struct sk_buff *skb_in,
 					const struct iphdr *iph,
-					__be32 saddr, u8 tos, u32 mark,
+					__be32 saddr, u8 tos,
+					const struct sock *sk,
 					int type, int code,
 					struct icmp_bxm *param)
 {
@@ -472,7 +474,8 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->daddr = (param->replyopts.opt.opt.srr ?
 		      param->replyopts.opt.opt.faddr : iph->saddr);
 	fl4->saddr = saddr;
-	fl4->flowi4_mark = mark;
+	fl4->flowi4_mark = sk->sk_mark;
+	fl4->flowi4_uid = sk->sk_uid;
 	fl4->flowi4_tos = RT_TOS(tos);
 	fl4->flowi4_proto = IPPROTO_ICMP;
 	fl4->fl4_icmp_type = type;
@@ -701,7 +704,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	ipc.ttl = 0;
 	ipc.tos = -1;
 
-	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
+	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, sk,
 			       type, code, icmp_param);
 	if (IS_ERR(rt))
 		goto out_unlock;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 61a9dee..d5d3ead 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -415,7 +415,7 @@ 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), sk->sk_uid);
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -452,7 +452,7 @@ 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), sk->sk_uid);
 	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 05d1058..37f0138 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1590,7 +1590,8 @@ 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))
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 7cf7d6e..146be157 100644
--- a/net/ipv4/ping.c
+++ b/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,
+			   sk->sk_uid);
 
 	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 03618ed..3a7bc93 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -606,7 +606,7 @@ 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, sk->sk_uid);
 
 	if (!inet->hdrincl) {
 		rfv.msg = msg;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0a42dc0..b0f2a21 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -507,7 +507,8 @@ 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 net *net, struct flowi4 *fl4,
+			     struct sock *sk,
 			     const struct iphdr *iph,
 			     int oif, u8 tos,
 			     u8 prot, u32 mark, int flow_flags)
@@ -523,11 +524,11 @@ 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, sk->sk_uid);
 }
 
 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;
@@ -535,10 +536,10 @@ static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
 	u8 prot = iph->protocol;
 	u32 mark = skb->mark;
 
-	__build_flow_key(fl4, sk, iph, oif, tos, prot, mark, 0);
+	__build_flow_key(sock_net(sk), 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;
@@ -552,11 +553,11 @@ 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, sk->sk_uid);
 	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)
@@ -800,7 +801,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
 
 	rt = (struct rtable *) dst;
 
-	__build_flow_key(&fl4, sk, iph, oif, tos, prot, mark, 0);
+	__build_flow_key(sock_net(sk), &fl4, sk, iph, oif, tos, prot, mark, 0);
 	__ip_do_redirect(rt, skb, &fl4, true);
 }
 
@@ -1018,7 +1019,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
 	if (!mark)
 		mark = IP4_REPLY_MARK(net, skb->mark);
 
-	__build_flow_key(&fl4, NULL, iph, oif,
+	__build_flow_key(net, &fl4, NULL, iph, oif,
 			 RT_TOS(iph->tos), protocol, mark, flow_flags);
 	rt = __ip_route_output_key(net, &fl4);
 	if (!IS_ERR(rt)) {
@@ -1034,7 +1035,7 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	struct flowi4 fl4;
 	struct rtable *rt;
 
-	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+	__build_flow_key(sock_net(sk), &fl4, sk, iph, 0, 0, 0, 0, 0);
 
 	if (!fl4.flowi4_mark)
 		fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark);
@@ -1053,6 +1054,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	struct rtable *rt;
 	struct dst_entry *odst = NULL;
 	bool new = false;
+	struct net *net = sock_net(sk);
 
 	bh_lock_sock(sk);
 
@@ -1066,7 +1068,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 		goto out;
 	}
 
-	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+	__build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
 
 	rt = (struct rtable *)odst;
 	if (odst->obsolete && !odst->ops->check(odst, 0)) {
@@ -1106,7 +1108,7 @@ void ipv4_redirect(struct sk_buff *skb, struct net *net,
 	struct flowi4 fl4;
 	struct rtable *rt;
 
-	__build_flow_key(&fl4, NULL, iph, oif,
+	__build_flow_key(net, &fl4, NULL, iph, oif,
 			 RT_TOS(iph->tos), protocol, mark, flow_flags);
 	rt = __ip_route_output_key(net, &fl4);
 	if (!IS_ERR(rt)) {
@@ -1121,9 +1123,10 @@ void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk)
 	const struct iphdr *iph = (const struct iphdr *) skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
+	struct net *net = sock_net(sk);
 
-	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
-	rt = __ip_route_output_key(sock_net(sk), &fl4);
+	__build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
+	rt = __ip_route_output_key(net, &fl4);
 	if (!IS_ERR(rt)) {
 		__ip_do_redirect(rt, skb, &fl4, false);
 		ip_rt_put(rt);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index e3c4043..0dc6286 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -372,7 +372,7 @@ 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->srr ? opt->faddr : ireq->ir_rmt_addr,
-			   ireq->ir_loc_addr, th->source, th->dest);
+			   ireq->ir_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)) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 83b3d0b..a5da319 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -692,6 +692,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 		     offsetof(struct inet_timewait_sock, tw_bound_dev_if));
 
 	arg.tos = ip_hdr(skb)->tos;
+	arg.uid = sock_net_uid(net, sk);
 	local_bh_disable();
 	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c833271..36dae6a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1019,7 +1019,8 @@ 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,
+				   sk->sk_uid);
 
 		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 46ad699..c86911b 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -678,6 +678,7 @@ 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();
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 0630a4d5..466d624 100644
--- a/net/ipv6/ah6.c
+++ b/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, sock_net_uid(net, NULL));
 	xfrm_state_put(x);
 
 	return 0;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 37874e2..6d8a66a 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -54,6 +54,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
 	fl6->fl6_dport = inet->inet_dport;
 	fl6->fl6_sport = inet->inet_sport;
 	fl6->flowlabel = np->flow_label;
+	fl6->flowi6_uid = sk->sk_uid;
 
 	if (!fl6->flowi6_oif)
 		fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 060a60b..ad360ee 100644
--- a/net/ipv6/esp6.c
+++ b/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, sock_net_uid(net, NULL));
 	xfrm_state_put(x);
 
 	return 0;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index bd59c34..db01af2 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -92,7 +92,7 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	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, sock_net_uid(net, NULL));
 	else if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0);
 
@@ -507,6 +507,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 
 	ipc6.tclass = np->tclass;
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+	fl6.flowi6_uid = sk->sk_uid;
 
 	dst = icmpv6_route_lookup(net, skb, sk, &fl6);
 	if (IS_ERR(dst))
@@ -670,6 +671,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 		fl6.flowi6_oif = np->mcast_oif;
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
+	fl6.flowi6_uid = sock_net_uid(net, NULL);
 
 	err = ip6_dst_lookup(net, sk, &dst, &fl6);
 	if (err)
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 532c3ef..1c86c47 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -88,6 +88,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
 	fl6->flowi6_mark = ireq->ir_mark;
 	fl6->fl6_dport = ireq->ir_rmt_port;
 	fl6->fl6_sport = htons(ireq->ir_num);
+	fl6->flowi6_uid = sk->sk_uid;
 	security_req_classify_flow(req, flowi6_to_flowi(fl6));
 
 	dst = ip6_dst_lookup_flow(sk, fl6, final_p);
@@ -136,6 +137,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 	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();
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index d7d6d3a..710bc79 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -548,6 +548,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 		fl6.flowi6_mark = skb->mark;
 
+	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
 	err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM));
 	if (err)
 		return -1;
@@ -602,6 +604,8 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 		fl6.flowi6_mark = skb->mark;
 
+	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
 	if (gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)))
 		return -1;
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 3a70567..ae23a5c 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1237,6 +1237,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 			fl6.flowi6_mark = skb->mark;
 	}
 
+	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
 
@@ -1315,6 +1317,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 			fl6.flowi6_mark = skb->mark;
 	}
 
+	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
 
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 35c5b2d..79ec327 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -610,7 +610,8 @@ static int vti6_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,
+				sock_net_uid(net, skb->sk));
 	xfrm_state_put(x);
 
 	return 0;
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 1b9316e..313ef6b 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -76,7 +76,7 @@ static int ipcomp6_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, sock_net_uid(net, NULL));
 	xfrm_state_put(x);
 
 	return 0;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index d11c468..39970e2 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -26,6 +26,7 @@ int ip6_route_me_harder(struct net *net, 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,
 	};
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 0e983b6..f196779 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -113,6 +113,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl6.daddr = *daddr;
 	fl6.flowi6_oif = oif;
 	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));
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index d7e8b95..16e4123 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -776,6 +776,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	memset(&fl6, 0, sizeof(fl6));
 
 	fl6.flowi6_mark = sk->sk_mark;
+	fl6.flowi6_uid = sk->sk_uid;
 
 	ipc6.hlimit = -1;
 	ipc6.tclass = -1;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index cd84ded..0582a8b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1401,7 +1401,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 }
 
 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;
@@ -1413,6 +1413,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 	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)
@@ -1426,7 +1427,7 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 	struct dst_entry *dst;
 
 	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);
 
 	dst = __sk_dst_get(sk);
 	if (!dst || !dst->obsolete ||
@@ -1531,6 +1532,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
 	fl6.daddr = iph->daddr;
 	fl6.saddr = iph->saddr;
 	fl6.flowlabel = ip6_flowinfo(iph);
+	fl6.flowi6_uid = sock_net_uid(net, NULL);
 
 	dst = ip6_route_redirect(net, &fl6, &ipv6_hdr(skb)->saddr);
 	rt6_do_redirect(dst, NULL, skb);
@@ -1552,6 +1554,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
 	fl6.flowi6_mark = mark;
 	fl6.daddr = msg->dest;
 	fl6.saddr = iph->daddr;
+	fl6.flowi6_uid = sock_net_uid(net, NULL);
 
 	dst = ip6_route_redirect(net, &fl6, &iph->saddr);
 	rt6_do_redirect(dst, NULL, skb);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 59c4839..97830a6 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -227,6 +227,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		fl6.flowi6_mark = ireq->ir_mark;
 		fl6.fl6_dport = ireq->ir_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);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5a27ab4..8a544eb 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -233,6 +233,7 @@ 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, lockdep_sock_is_held(sk));
 	final_p = fl6_update_dst(&fl6, opt, &final);
@@ -824,6 +825,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	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, (struct sock *)sk);
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	/* Pass a socket to ip6_dst_lookup either it is for RST
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 71963b2..b05f722 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1137,6 +1137,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
 
 	fl6.flowi6_mark = sk->sk_mark;
+	fl6.flowi6_uid = sk->sk_uid;
 	sockc.tsflags = sk->sk_tsflags;
 
 	if (msg->msg_controllen) {
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index ea2ae66..a244439 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -519,6 +519,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	memset(&fl6, 0, sizeof(fl6));
 
 	fl6.flowi6_mark = sk->sk_mark;
+	fl6.flowi6_uid = sk->sk_uid;
 
 	ipc6.hlimit = -1;
 	ipc6.tclass = -1;
-- 
2.8.0.rc3.226.g39d4020