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

Pull namespace changes from Eric Biederman:
 "This is an assorted mishmash of small cleanups, enhancements and bug
  fixes.

  The major theme is user namespace mount restrictions.  nsown_capable
  is killed as it encourages not thinking about details that need to be
  considered.  A very hard to hit pid namespace exiting bug was finally
  tracked and fixed.  A couple of cleanups to the basic namespace
  infrastructure.

  Finally there is an enhancement that makes per user namespace
  capabilities usable as capabilities, and an enhancement that allows
  the per userns root to nice other processes in the user namespace"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  userns:  Kill nsown_capable it makes the wrong thing easy
  capabilities: allow nice if we are privileged
  pidns: Don't have unshare(CLONE_NEWPID) imply CLONE_THREAD
  userns: Allow PR_CAPBSET_DROP in a user namespace.
  namespaces: Simplify copy_namespaces so it is clear what is going on.
  pidns: Fix hang in zap_pid_ns_processes by sending a potentially extra wakeup
  sysfs: Restrict mounting sysfs
  userns: Better restrictions on when proc and sysfs can be mounted
  vfs: Don't copy mount bind mounts of /proc/<pid>/ns/mnt between namespaces
  kernel/nsproxy.c: Improving a snippet of code.
  proc: Restrict mounting the proc filesystem
  vfs: Lock in place mounts from more privileged users

11 files changed, 27 insertions, 59 deletions

diff --git a/kernel/capability.c b/kernel/capability.c
index f6c2ce5..6fc1c8a 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -433,18 +433,6 @@ bool capable(int cap)
 EXPORT_SYMBOL(capable);
 
 /**
- * nsown_capable - Check superior capability to one's own user_ns
- * @cap: The capability in question
- *
- * Return true if the current task has the given superior capability
- * targeted at its own user namespace.
- */
-bool nsown_capable(int cap)
-{
-	return ns_capable(current_user_ns(), cap);
-}
-
-/**
  * inode_capable - Check superior capability over inode
  * @inode: The inode in question
  * @cap: The capability in question
diff --git a/kernel/fork.c b/kernel/fork.c
index bf46287..c9eaf201 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1825,11 +1825,6 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 	if (unshare_flags & CLONE_NEWUSER)
 		unshare_flags |= CLONE_THREAD | CLONE_FS;
 	/*
-	 * If unsharing a pid namespace must also unshare the thread.
-	 */
-	if (unshare_flags & CLONE_NEWPID)
-		unshare_flags |= CLONE_THREAD;
-	/*
 	 * If unsharing a thread from a thread group, must also unshare vm.
 	 */
 	if (unshare_flags & CLONE_THREAD)
diff --git a/kernel/groups.c b/kernel/groups.c
index 6b2588d..90cf1c3 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -233,7 +233,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!nsown_capable(CAP_SETGID))
+	if (!ns_capable(current_user_ns(), CAP_SETGID))
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 997cbb9..8e78110 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -126,22 +126,16 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 	struct nsproxy *old_ns = tsk->nsproxy;
 	struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns);
 	struct nsproxy *new_ns;
-	int err = 0;
 
-	if (!old_ns)
+	if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
+			      CLONE_NEWPID | CLONE_NEWNET)))) {
+		get_nsproxy(old_ns);
 		return 0;
-
-	get_nsproxy(old_ns);
-
-	if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
-				CLONE_NEWPID | CLONE_NEWNET)))
-		return 0;
-
-	if (!ns_capable(user_ns, CAP_SYS_ADMIN)) {
-		err = -EPERM;
-		goto out;
 	}
 
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
 	/*
 	 * CLONE_NEWIPC must detach from the undolist: after switching
 	 * to a new ipc namespace, the semaphore arrays from the old
@@ -149,22 +143,16 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 	 * means share undolist with parent, so we must forbid using
 	 * it along with CLONE_NEWIPC.
 	 */
-	if ((flags & CLONE_NEWIPC) && (flags & CLONE_SYSVSEM)) {
-		err = -EINVAL;
-		goto out;
-	}
+	if ((flags & (CLONE_NEWIPC | CLONE_SYSVSEM)) ==
+		(CLONE_NEWIPC | CLONE_SYSVSEM)) 
+		return -EINVAL;
 
 	new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs);
-	if (IS_ERR(new_ns)) {
-		err = PTR_ERR(new_ns);
-		goto out;
-	}
+	if (IS_ERR(new_ns))
+		return  PTR_ERR(new_ns);
 
 	tsk->nsproxy = new_ns;
-
-out:
-	put_nsproxy(old_ns);
-	return err;
+	return 0;
 }
 
 void free_nsproxy(struct nsproxy *ns)
diff --git a/kernel/pid.c b/kernel/pid.c
index 66505c1..ebe5e80 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -265,6 +265,7 @@ void free_pid(struct pid *pid)
 		struct pid_namespace *ns = upid->ns;
 		hlist_del_rcu(&upid->pid_chain);
 		switch(--ns->nr_hashed) {
+		case 2:
 		case 1:
 			/* When all that is left in the pid namespace
 			 * is the reaper wake up the reaper.  The reaper
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 601bb36..4208655 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -329,7 +329,7 @@ static int pidns_install(struct nsproxy *nsproxy, void *ns)
 	struct pid_namespace *ancestor, *new = ns;
 
 	if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) ||
-	    !nsown_capable(CAP_SYS_ADMIN))
+	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
 		return -EPERM;
 
 	/*
diff --git a/kernel/sys.c b/kernel/sys.c
index 771129b..c18ecca 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -337,7 +337,7 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
 	if (rgid != (gid_t) -1) {
 		if (gid_eq(old->gid, krgid) ||
 		    gid_eq(old->egid, krgid) ||
-		    nsown_capable(CAP_SETGID))
+		    ns_capable(old->user_ns, CAP_SETGID))
 			new->gid = krgid;
 		else
 			goto error;
@@ -346,7 +346,7 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
 		if (gid_eq(old->gid, kegid) ||
 		    gid_eq(old->egid, kegid) ||
 		    gid_eq(old->sgid, kegid) ||
-		    nsown_capable(CAP_SETGID))
+		    ns_capable(old->user_ns, CAP_SETGID))
 			new->egid = kegid;
 		else
 			goto error;
@@ -387,7 +387,7 @@ SYSCALL_DEFINE1(setgid, gid_t, gid)
 	old = current_cred();
 
 	retval = -EPERM;
-	if (nsown_capable(CAP_SETGID))
+	if (ns_capable(old->user_ns, CAP_SETGID))
 		new->gid = new->egid = new->sgid = new->fsgid = kgid;
 	else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid))
 		new->egid = new->fsgid = kgid;
@@ -471,7 +471,7 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
 		new->uid = kruid;
 		if (!uid_eq(old->uid, kruid) &&
 		    !uid_eq(old->euid, kruid) &&
-		    !nsown_capable(CAP_SETUID))
+		    !ns_capable(old->user_ns, CAP_SETUID))
 			goto error;
 	}
 
@@ -480,7 +480,7 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
 		if (!uid_eq(old->uid, keuid) &&
 		    !uid_eq(old->euid, keuid) &&
 		    !uid_eq(old->suid, keuid) &&
-		    !nsown_capable(CAP_SETUID))
+		    !ns_capable(old->user_ns, CAP_SETUID))
 			goto error;
 	}
 
@@ -534,7 +534,7 @@ SYSCALL_DEFINE1(setuid, uid_t, uid)
 	old = current_cred();
 
 	retval = -EPERM;
-	if (nsown_capable(CAP_SETUID)) {
+	if (ns_capable(old->user_ns, CAP_SETUID)) {
 		new->suid = new->uid = kuid;
 		if (!uid_eq(kuid, old->uid)) {
 			retval = set_user(new);
@@ -591,7 +591,7 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
 	old = current_cred();
 
 	retval = -EPERM;
-	if (!nsown_capable(CAP_SETUID)) {
+	if (!ns_capable(old->user_ns, CAP_SETUID)) {
 		if (ruid != (uid_t) -1        && !uid_eq(kruid, old->uid) &&
 		    !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid))
 			goto error;
@@ -673,7 +673,7 @@ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
 	old = current_cred();
 
 	retval = -EPERM;
-	if (!nsown_capable(CAP_SETGID)) {
+	if (!ns_capable(old->user_ns, CAP_SETGID)) {
 		if (rgid != (gid_t) -1        && !gid_eq(krgid, old->gid) &&
 		    !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid))
 			goto error;
@@ -744,7 +744,7 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid)
 
 	if (uid_eq(kuid, old->uid)  || uid_eq(kuid, old->euid)  ||
 	    uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) ||
-	    nsown_capable(CAP_SETUID)) {
+	    ns_capable(old->user_ns, CAP_SETUID)) {
 		if (!uid_eq(kuid, old->fsuid)) {
 			new->fsuid = kuid;
 			if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
@@ -783,7 +783,7 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid)
 
 	if (gid_eq(kgid, old->gid)  || gid_eq(kgid, old->egid)  ||
 	    gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) ||
-	    nsown_capable(CAP_SETGID)) {
+	    ns_capable(old->user_ns, CAP_SETGID)) {
 		if (!gid_eq(kgid, old->fsgid)) {
 			new->fsgid = kgid;
 			goto change_okay;
diff --git a/kernel/uid16.c b/kernel/uid16.c
index f6c83d7..602e5bb 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -176,7 +176,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!nsown_capable(CAP_SETGID))
+	if (!ns_capable(current_user_ns(), CAP_SETGID))
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/kernel/user.c b/kernel/user.c
index 69b4c3d..5bbb919 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,8 +51,6 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
-	.may_mount_sysfs = true,
-	.may_mount_proc = true,
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 9064b91..13fb113 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -101,8 +101,6 @@ int create_user_ns(struct cred *new)
 
 	set_cred_user_ns(new, ns);
 
-	update_mnt_policy(ns);
-
 	return 0;
 }
 
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 2fc8576..fd39312 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -114,7 +114,7 @@ static int utsns_install(struct nsproxy *nsproxy, void *new)
 	struct uts_namespace *ns = new;
 
 	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
-	    !nsown_capable(CAP_SYS_ADMIN))
+	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
 		return -EPERM;
 
 	get_uts_ns(ns);