Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull user namespace changes from Eric Biederman:
 "This is a mostly modest set of changes to enable basic user namespace
  support.  This allows the code to code to compile with user namespaces
  enabled and removes the assumption there is only the initial user
  namespace.  Everything is converted except for the most complex of the
  filesystems: autofs4, 9p, afs, ceph, cifs, coda, fuse, gfs2, ncpfs,
  nfs, ocfs2 and xfs as those patches need a bit more review.

  The strategy is to push kuid_t and kgid_t values are far down into
  subsystems and filesystems as reasonable.  Leaving the make_kuid and
  from_kuid operations to happen at the edge of userspace, as the values
  come off the disk, and as the values come in from the network.
  Letting compile type incompatible compile errors (present when user
  namespaces are enabled) guide me to find the issues.

  The most tricky areas have been the places where we had an implicit
  union of uid and gid values and were storing them in an unsigned int.
  Those places were converted into explicit unions.  I made certain to
  handle those places with simple trivial patches.

  Out of that work I discovered we have generic interfaces for storing
  quota by projid.  I had never heard of the project identifiers before.
  Adding full user namespace support for project identifiers accounts
  for most of the code size growth in my git tree.

  Ultimately there will be work to relax privlige checks from
  "capable(FOO)" to "ns_capable(user_ns, FOO)" where it is safe allowing
  root in a user names to do those things that today we only forbid to
  non-root users because it will confuse suid root applications.

  While I was pushing kuid_t and kgid_t changes deep into the audit code
  I made a few other cleanups.  I capitalized on the fact we process
  netlink messages in the context of the message sender.  I removed
  usage of NETLINK_CRED, and started directly using current->tty.

  Some of these patches have also made it into maintainer trees, with no
  problems from identical code from different trees showing up in
  linux-next.

  After reading through all of this code I feel like I might be able to
  win a game of kernel trivial pursuit."

Fix up some fairly trivial conflicts in netfilter uid/git logging code.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (107 commits)
  userns: Convert the ufs filesystem to use kuid/kgid where appropriate
  userns: Convert the udf filesystem to use kuid/kgid where appropriate
  userns: Convert ubifs to use kuid/kgid
  userns: Convert squashfs to use kuid/kgid where appropriate
  userns: Convert reiserfs to use kuid and kgid where appropriate
  userns: Convert jfs to use kuid/kgid where appropriate
  userns: Convert jffs2 to use kuid and kgid where appropriate
  userns: Convert hpfs to use kuid and kgid where appropriate
  userns: Convert btrfs to use kuid/kgid where appropriate
  userns: Convert bfs to use kuid/kgid where appropriate
  userns: Convert affs to use kuid/kgid wherwe appropriate
  userns: On alpha modify linux_to_osf_stat to use convert from kuids and kgids
  userns: On ia64 deal with current_uid and current_gid being kuid and kgid
  userns: On ppc convert current_uid from a kuid before printing.
  userns: Convert s390 getting uid and gid system calls to use kuid and kgid
  userns: Convert s390 hypfs to use kuid and kgid where appropriate
  userns: Convert binder ipc to use kuids
  userns: Teach security_path_chown to take kuids and kgids
  userns: Add user namespace support to IMA
  userns: Convert EVM to deal with kuids and kgids in it's hmac computation
  ...

7 files changed, 64 insertions, 40 deletions

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 570e61f9611f..8bc005b1435f 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -69,6 +69,7 @@ static inline void inet_diag_unlock_handler(
 
 int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			      struct sk_buff *skb, struct inet_diag_req_v2 *req,
+			      struct user_namespace *user_ns,		      	
 			      u32 pid, u32 seq, u16 nlmsg_flags,
 			      const struct nlmsghdr *unlh)
 {
@@ -124,7 +125,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 	}
 #endif
 
-	r->idiag_uid = sock_i_uid(sk);
+	r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
 	r->idiag_inode = sock_i_ino(sk);
 
 	if (ext & (1 << (INET_DIAG_MEMINFO - 1))) {
@@ -199,11 +200,12 @@ EXPORT_SYMBOL_GPL(inet_sk_diag_fill);
 
 static int inet_csk_diag_fill(struct sock *sk,
 			      struct sk_buff *skb, struct inet_diag_req_v2 *req,
+			      struct user_namespace *user_ns,
 			      u32 pid, u32 seq, u16 nlmsg_flags,
 			      const struct nlmsghdr *unlh)
 {
 	return inet_sk_diag_fill(sk, inet_csk(sk),
-			skb, req, pid, seq, nlmsg_flags, unlh);
+			skb, req, user_ns, pid, seq, nlmsg_flags, unlh);
 }
 
 static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
@@ -256,14 +258,16 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 }
 
 static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
-			struct inet_diag_req_v2 *r, u32 pid, u32 seq, u16 nlmsg_flags,
+			struct inet_diag_req_v2 *r,
+			struct user_namespace *user_ns,
+			u32 pid, u32 seq, u16 nlmsg_flags,
 			const struct nlmsghdr *unlh)
 {
 	if (sk->sk_state == TCP_TIME_WAIT)
 		return inet_twsk_diag_fill((struct inet_timewait_sock *)sk,
 					   skb, r, pid, seq, nlmsg_flags,
 					   unlh);
-	return inet_csk_diag_fill(sk, skb, r, pid, seq, nlmsg_flags, unlh);
+	return inet_csk_diag_fill(sk, skb, r, user_ns, pid, seq, nlmsg_flags, unlh);
 }
 
 int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb,
@@ -311,6 +315,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s
 	}
 
 	err = sk_diag_fill(sk, rep, req,
+			   sk_user_ns(NETLINK_CB(in_skb).ssk),
 			   NETLINK_CB(in_skb).pid,
 			   nlh->nlmsg_seq, 0, nlh);
 	if (err < 0) {
@@ -551,6 +556,7 @@ static int inet_csk_diag_dump(struct sock *sk,
 		return 0;
 
 	return inet_csk_diag_fill(sk, skb, r,
+				  sk_user_ns(NETLINK_CB(cb->skb).ssk),
 				  NETLINK_CB(cb->skb).pid,
 				  cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
 }
@@ -591,7 +597,9 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
 }
 
 static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
-			      struct request_sock *req, u32 pid, u32 seq,
+			      struct request_sock *req,
+			      struct user_namespace *user_ns,
+			      u32 pid, u32 seq,
 			      const struct nlmsghdr *unlh)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
@@ -625,7 +633,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 	r->idiag_expires = jiffies_to_msecs(tmo);
 	r->idiag_rqueue = 0;
 	r->idiag_wqueue = 0;
-	r->idiag_uid = sock_i_uid(sk);
+	r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
 	r->idiag_inode = 0;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (r->idiag_family == AF_INET6) {
@@ -702,6 +710,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 			}
 
 			err = inet_diag_fill_req(skb, sk, req,
+					       sk_user_ns(NETLINK_CB(cb->skb).ssk),
 					       NETLINK_CB(cb->skb).pid,
 					       cb->nlh->nlmsg_seq, cb->nlh);
 			if (err < 0) {
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 6232d476f37e..8f3d05424a3e 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -185,10 +185,10 @@ exit:
 	return sk;
 }
 
-static void inet_get_ping_group_range_net(struct net *net, gid_t *low,
-					  gid_t *high)
+static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
+					  kgid_t *high)
 {
-	gid_t *data = net->ipv4.sysctl_ping_group_range;
+	kgid_t *data = net->ipv4.sysctl_ping_group_range;
 	unsigned int seq;
 
 	do {
@@ -203,19 +203,13 @@ static void inet_get_ping_group_range_net(struct net *net, gid_t *low,
 static int ping_init_sock(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
-	gid_t group = current_egid();
-	gid_t range[2];
+	kgid_t group = current_egid();
 	struct group_info *group_info = get_current_groups();
 	int i, j, count = group_info->ngroups;
 	kgid_t low, high;
 
-	inet_get_ping_group_range_net(net, range, range+1);
-	low = make_kgid(&init_user_ns, range[0]);
-	high = make_kgid(&init_user_ns, range[1]);
-	if (!gid_valid(low) || !gid_valid(high) || gid_lt(high, low))
-		return -EACCES;
-
-	if (range[0] <= group && group <= range[1])
+	inet_get_ping_group_range_net(net, &low, &high);
+	if (gid_lte(low, group) && gid_lte(group, high))
 		return 0;
 
 	for (i = 0; i < group_info->nblocks; i++) {
@@ -845,7 +839,9 @@ static void ping_format_sock(struct sock *sp, struct seq_file *f,
 		bucket, src, srcp, dest, destp, sp->sk_state,
 		sk_wmem_alloc_get(sp),
 		sk_rmem_alloc_get(sp),
-		0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp),
+		0, 0L, 0,
+		from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
+		0, sock_i_ino(sp),
 		atomic_read(&sp->sk_refcnt), sp,
 		atomic_read(&sp->sk_drops), len);
 }
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index d23c6571ba1c..73d1e4df4bf6 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -994,7 +994,9 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
 		i, src, srcp, dest, destp, sp->sk_state,
 		sk_wmem_alloc_get(sp),
 		sk_rmem_alloc_get(sp),
-		0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp),
+		0, 0L, 0,
+		from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
+		0, sock_i_ino(sp),
 		atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops));
 }
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1b5ce96707a3..3e78c79b5586 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -76,9 +76,9 @@ static int ipv4_local_port_range(ctl_table *table, int write,
 }
 
 
-static void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t *high)
+static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high)
 {
-	gid_t *data = table->data;
+	kgid_t *data = table->data;
 	unsigned int seq;
 	do {
 		seq = read_seqbegin(&sysctl_local_ports.lock);
@@ -89,12 +89,12 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low,
 }
 
 /* Update system visible IP port range */
-static void set_ping_group_range(struct ctl_table *table, gid_t range[2])
+static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high)
 {
-	gid_t *data = table->data;
+	kgid_t *data = table->data;
 	write_seqlock(&sysctl_local_ports.lock);
-	data[0] = range[0];
-	data[1] = range[1];
+	data[0] = low;
+	data[1] = high;
 	write_sequnlock(&sysctl_local_ports.lock);
 }
 
@@ -103,21 +103,33 @@ static int ipv4_ping_group_range(ctl_table *table, int write,
 				 void __user *buffer,
 				 size_t *lenp, loff_t *ppos)
 {
+	struct user_namespace *user_ns = current_user_ns();
 	int ret;
-	gid_t range[2];
+	gid_t urange[2];
+	kgid_t low, high;
 	ctl_table tmp = {
-		.data = &range,
-		.maxlen = sizeof(range),
+		.data = &urange,
+		.maxlen = sizeof(urange),
 		.mode = table->mode,
 		.extra1 = &ip_ping_group_range_min,
 		.extra2 = &ip_ping_group_range_max,
 	};
 
-	inet_get_ping_group_range_table(table, range, range + 1);
+	inet_get_ping_group_range_table(table, &low, &high);
+	urange[0] = from_kgid_munged(user_ns, low);
+	urange[1] = from_kgid_munged(user_ns, high);
 	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
 
-	if (write && ret == 0)
-		set_ping_group_range(table, range);
+	if (write && ret == 0) {
+		low = make_kgid(user_ns, urange[0]);
+		high = make_kgid(user_ns, urange[1]);
+		if (!gid_valid(low) || !gid_valid(high) ||
+		    (urange[1] < urange[0]) || gid_lt(high, low)) {
+			low = make_kgid(&init_user_ns, 1);
+			high = make_kgid(&init_user_ns, 0);
+		}
+		set_ping_group_range(table, low, high);
+	}
 
 	return ret;
 }
@@ -786,7 +798,7 @@ static struct ctl_table ipv4_net_table[] = {
 	{
 		.procname	= "ping_group_range",
 		.data		= &init_net.ipv4.sysctl_ping_group_range,
-		.maxlen		= sizeof(init_net.ipv4.sysctl_ping_group_range),
+		.maxlen		= sizeof(gid_t)*2,
 		.mode		= 0644,
 		.proc_handler	= ipv4_ping_group_range,
 	},
@@ -830,8 +842,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 	 * Sane defaults - nobody may create ping sockets.
 	 * Boot scripts should set this to distro-specific group.
 	 */
-	net->ipv4.sysctl_ping_group_range[0] = 1;
-	net->ipv4.sysctl_ping_group_range[1] = 0;
+	net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1);
+	net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0);
 
 	tcp_init_mem(net);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 00a748d14062..be23a0b7b89e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2393,7 +2393,7 @@ void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
 EXPORT_SYMBOL(tcp_proc_unregister);
 
 static void get_openreq4(const struct sock *sk, const struct request_sock *req,
-			 struct seq_file *f, int i, int uid, int *len)
+			 struct seq_file *f, int i, kuid_t uid, int *len)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	int ttd = req->expires - jiffies;
@@ -2410,7 +2410,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req,
 		1,    /* timers active (only the expire timer) */
 		jiffies_to_clock_t(ttd),
 		req->retrans,
-		uid,
+		from_kuid_munged(seq_user_ns(f), uid),
 		0,  /* non standard timer */
 		0, /* open_requests have no inode */
 		atomic_read(&sk->sk_refcnt),
@@ -2461,7 +2461,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len)
 		timer_active,
 		jiffies_to_clock_t(timer_expires - jiffies),
 		icsk->icsk_retransmits,
-		sock_i_uid(sk),
+		from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)),
 		icsk->icsk_probes_out,
 		sock_i_ino(sk),
 		atomic_read(&sk->sk_refcnt), sk,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 2814f66dac64..79c8dbe59b54 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2115,7 +2115,9 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f,
 		bucket, src, srcp, dest, destp, sp->sk_state,
 		sk_wmem_alloc_get(sp),
 		sk_rmem_alloc_get(sp),
-		0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp),
+		0, 0L, 0,
+		from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
+		0, sock_i_ino(sp),
 		atomic_read(&sp->sk_refcnt), sp,
 		atomic_read(&sp->sk_drops), len);
 }
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 16d0960062be..d2f336ea82ca 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -24,7 +24,9 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
 	if (!inet_diag_bc_sk(bc, sk))
 		return 0;
 
-	return inet_sk_diag_fill(sk, NULL, skb, req, NETLINK_CB(cb->skb).pid,
+	return inet_sk_diag_fill(sk, NULL, skb, req,
+			sk_user_ns(NETLINK_CB(cb->skb).ssk),
+			NETLINK_CB(cb->skb).pid,
 			cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
 }
 
@@ -69,6 +71,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
 		goto out;
 
 	err = inet_sk_diag_fill(sk, NULL, rep, req,
+			   sk_user_ns(NETLINK_CB(in_skb).ssk),
 			   NETLINK_CB(in_skb).pid,
 			   nlh->nlmsg_seq, 0, nlh);
 	if (err < 0) {