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
  ...

4 files changed, 49 insertions, 15 deletions

diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 5cfb5bedb2b8..8cfc401e197e 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -55,6 +55,7 @@ struct nfulnl_instance {
 	unsigned int qlen;		/* number of nlmsgs in skb */
 	struct sk_buff *skb;		/* pre-allocatd skb */
 	struct timer_list timer;
+	struct user_namespace *peer_user_ns;	/* User namespace of the peer process */
 	int peer_pid;			/* PID of the peer process */
 
 	/* configurable parameters */
@@ -132,7 +133,7 @@ instance_put(struct nfulnl_instance *inst)
 static void nfulnl_timer(unsigned long data);
 
 static struct nfulnl_instance *
-instance_create(u_int16_t group_num, int pid)
+instance_create(u_int16_t group_num, int pid, struct user_namespace *user_ns)
 {
 	struct nfulnl_instance *inst;
 	int err;
@@ -162,6 +163,7 @@ instance_create(u_int16_t group_num, int pid)
 
 	setup_timer(&inst->timer, nfulnl_timer, (unsigned long)inst);
 
+	inst->peer_user_ns = user_ns;
 	inst->peer_pid = pid;
 	inst->group_num = group_num;
 
@@ -505,8 +507,10 @@ __build_packet_message(struct nfulnl_instance *inst,
 		read_lock_bh(&sk->sk_callback_lock);
 		if (sk->sk_socket && sk->sk_socket->file) {
 			struct file *file = sk->sk_socket->file;
-			__be32 uid = htonl(file->f_cred->fsuid);
-			__be32 gid = htonl(file->f_cred->fsgid);
+			const struct cred *cred = file->f_cred;
+			struct user_namespace *user_ns = inst->peer_user_ns;
+			__be32 uid = htonl(from_kuid_munged(user_ns, cred->fsuid));
+			__be32 gid = htonl(from_kgid_munged(user_ns, cred->fsgid));
 			read_unlock_bh(&sk->sk_callback_lock);
 			if (nla_put_be32(inst->skb, NFULA_UID, uid) ||
 			    nla_put_be32(inst->skb, NFULA_GID, gid))
@@ -785,7 +789,8 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb,
 			}
 
 			inst = instance_create(group_num,
-					       NETLINK_CB(skb).pid);
+					       NETLINK_CB(skb).pid,
+					       sk_user_ns(NETLINK_CB(skb).ssk));
 			if (IS_ERR(inst)) {
 				ret = PTR_ERR(inst);
 				goto out;
diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c
index 91e9af4d1f42..fa40096940a1 100644
--- a/net/netfilter/xt_LOG.c
+++ b/net/netfilter/xt_LOG.c
@@ -151,10 +151,12 @@ static void dump_sk_uid_gid(struct sbuff *m, struct sock *sk)
 		return;
 
 	read_lock_bh(&sk->sk_callback_lock);
-	if (sk->sk_socket && sk->sk_socket->file)
+	if (sk->sk_socket && sk->sk_socket->file) {
+		const struct cred *cred = sk->sk_socket->file->f_cred;
 		sb_add(m, "UID=%u GID=%u ",
-			sk->sk_socket->file->f_cred->fsuid,
-			sk->sk_socket->file->f_cred->fsgid);
+			from_kuid_munged(&init_user_ns, cred->fsuid),
+			from_kgid_munged(&init_user_ns, cred->fsgid));
+	}
 	read_unlock_bh(&sk->sk_callback_lock);
 }
 
diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c
index 772d7389b337..ca2e577ed8ac 100644
--- a/net/netfilter/xt_owner.c
+++ b/net/netfilter/xt_owner.c
@@ -17,6 +17,17 @@
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/xt_owner.h>
 
+static int owner_check(const struct xt_mtchk_param *par)
+{
+	struct xt_owner_match_info *info = par->matchinfo;
+
+	/* For now only allow adding matches from the initial user namespace */
+	if ((info->match & (XT_OWNER_UID|XT_OWNER_GID)) &&
+	    (current_user_ns() != &init_user_ns))
+		return -EINVAL;
+	return 0;
+}
+
 static bool
 owner_mt(const struct sk_buff *skb, struct xt_action_param *par)
 {
@@ -37,17 +48,23 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par)
 		return ((info->match ^ info->invert) &
 		       (XT_OWNER_UID | XT_OWNER_GID)) == 0;
 
-	if (info->match & XT_OWNER_UID)
-		if ((filp->f_cred->fsuid >= info->uid_min &&
-		    filp->f_cred->fsuid <= info->uid_max) ^
+	if (info->match & XT_OWNER_UID) {
+		kuid_t uid_min = make_kuid(&init_user_ns, info->uid_min);
+		kuid_t uid_max = make_kuid(&init_user_ns, info->uid_max);
+		if ((uid_gte(filp->f_cred->fsuid, uid_min) &&
+		     uid_lte(filp->f_cred->fsuid, uid_max)) ^
 		    !(info->invert & XT_OWNER_UID))
 			return false;
+	}
 
-	if (info->match & XT_OWNER_GID)
-		if ((filp->f_cred->fsgid >= info->gid_min &&
-		    filp->f_cred->fsgid <= info->gid_max) ^
+	if (info->match & XT_OWNER_GID) {
+		kgid_t gid_min = make_kgid(&init_user_ns, info->gid_min);
+		kgid_t gid_max = make_kgid(&init_user_ns, info->gid_max);
+		if ((gid_gte(filp->f_cred->fsgid, gid_min) &&
+		     gid_lte(filp->f_cred->fsgid, gid_max)) ^
 		    !(info->invert & XT_OWNER_GID))
 			return false;
+	}
 
 	return true;
 }
@@ -56,6 +73,7 @@ static struct xt_match owner_mt_reg __read_mostly = {
 	.name       = "owner",
 	.revision   = 1,
 	.family     = NFPROTO_UNSPEC,
+	.checkentry = owner_check,
 	.match      = owner_mt,
 	.matchsize  = sizeof(struct xt_owner_match_info),
 	.hooks      = (1 << NF_INET_LOCAL_OUT) |
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index ae2ad1eec8d0..4635c9b00459 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -317,6 +317,8 @@ static int recent_mt_check(const struct xt_mtchk_param *par,
 	struct recent_table *t;
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry *pde;
+	kuid_t uid;
+	kgid_t gid;
 #endif
 	unsigned int i;
 	int ret = -EINVAL;
@@ -372,6 +374,13 @@ static int recent_mt_check(const struct xt_mtchk_param *par,
 	for (i = 0; i < ip_list_hash_size; i++)
 		INIT_LIST_HEAD(&t->iphash[i]);
 #ifdef CONFIG_PROC_FS
+	uid = make_kuid(&init_user_ns, ip_list_uid);
+	gid = make_kgid(&init_user_ns, ip_list_gid);
+	if (!uid_valid(uid) || !gid_valid(gid)) {
+		kfree(t);
+		ret = -EINVAL;
+		goto out;
+	}
 	pde = proc_create_data(t->name, ip_list_perms, recent_net->xt_recent,
 		  &recent_mt_fops, t);
 	if (pde == NULL) {
@@ -379,8 +388,8 @@ static int recent_mt_check(const struct xt_mtchk_param *par,
 		ret = -ENOMEM;
 		goto out;
 	}
-	pde->uid = ip_list_uid;
-	pde->gid = ip_list_gid;
+	pde->uid = uid;
+	pde->gid = gid;
 #endif
 	spin_lock_bh(&recent_lock);
 	list_add_tail(&t->list, &recent_net->tables);