userns: user namespaces: convert several capable() calls

CAP_IPC_OWNER and CAP_IPC_LOCK can be checked against current_user_ns(),
because the resource comes from current's own ipc namespace.

setuid/setgid are to uids in own namespace, so again checks can be against
current_user_ns().

Changelog:
	Jan 11: Use task_ns_capable() in place of sched_capable().
	Jan 11: Use nsown_capable() as suggested by Bastian Blank.
	Jan 11: Clarify (hopefully) some logic in futex and sched.c
	Feb 15: use ns_capable for ipc, not nsown_capable
	Feb 23: let copy_ipcs handle setting ipc_ns->user_ns
	Feb 23: pass ns down rather than taking it from current

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Daniel Lezcano <daniel.lezcano@free.fr>
Acked-by: David Howells <dhowells@redhat.com>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 29 insertions, 13 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index bda4157..6570c459f 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2418,10 +2418,19 @@ SYSCALL_DEFINE3(get_robust_list, int, pid,
 			goto err_unlock;
 		ret = -EPERM;
 		pcred = __task_cred(p);
+		/* If victim is in different user_ns, then uids are not
+		   comparable, so we must have CAP_SYS_PTRACE */
+		if (cred->user->user_ns != pcred->user->user_ns) {
+			if (!ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
+				goto err_unlock;
+			goto ok;
+		}
+		/* If victim is in same user_ns, then uids are comparable */
 		if (cred->euid != pcred->euid &&
 		    cred->euid != pcred->uid &&
-		    !capable(CAP_SYS_PTRACE))
+		    !ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
 			goto err_unlock;
+ok:
 		head = p->robust_list;
 		rcu_read_unlock();
 	}
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index a7934ac..5f9e689 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -153,10 +153,19 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 			goto err_unlock;
 		ret = -EPERM;
 		pcred = __task_cred(p);
+		/* If victim is in different user_ns, then uids are not
+		   comparable, so we must have CAP_SYS_PTRACE */
+		if (cred->user->user_ns != pcred->user->user_ns) {
+			if (!ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
+				goto err_unlock;
+			goto ok;
+		}
+		/* If victim is in same user_ns, then uids are comparable */
 		if (cred->euid != pcred->euid &&
 		    cred->euid != pcred->uid &&
-		    !capable(CAP_SYS_PTRACE))
+		    !ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
 			goto err_unlock;
+ok:
 		head = p->compat_robust_list;
 		rcu_read_unlock();
 	}
diff --git a/kernel/groups.c b/kernel/groups.c
index 253dc0f..1cc476d 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 (!capable(CAP_SETGID))
+	if (!nsown_capable(CAP_SETGID))
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index ac8a56e..a05d191 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -75,16 +75,11 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 		goto out_uts;
 	}
 
-	new_nsp->ipc_ns = copy_ipcs(flags, tsk->nsproxy->ipc_ns);
+	new_nsp->ipc_ns = copy_ipcs(flags, tsk);
 	if (IS_ERR(new_nsp->ipc_ns)) {
 		err = PTR_ERR(new_nsp->ipc_ns);
 		goto out_ipc;
 	}
-	if (new_nsp->ipc_ns != tsk->nsproxy->ipc_ns) {
-		put_user_ns(new_nsp->ipc_ns->user_ns);
-		new_nsp->ipc_ns->user_ns = task_cred_xxx(tsk, user)->user_ns;
-		get_user_ns(new_nsp->ipc_ns->user_ns);
-	}
 
 	new_nsp->pid_ns = copy_pid_ns(flags, task_active_pid_ns(tsk));
 	if (IS_ERR(new_nsp->pid_ns)) {
diff --git a/kernel/sched.c b/kernel/sched.c
index a172494..480adeb 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4892,8 +4892,11 @@ static bool check_same_owner(struct task_struct *p)
 
 	rcu_read_lock();
 	pcred = __task_cred(p);
-	match = (cred->euid == pcred->euid ||
-		 cred->euid == pcred->uid);
+	if (cred->user->user_ns == pcred->user->user_ns)
+		match = (cred->euid == pcred->euid ||
+			 cred->euid == pcred->uid);
+	else
+		match = false;
 	rcu_read_unlock();
 	return match;
 }
@@ -5221,7 +5224,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 		goto out_free_cpus_allowed;
 	}
 	retval = -EPERM;
-	if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
+	if (!check_same_owner(p) && !task_ns_capable(p, CAP_SYS_NICE))
 		goto out_unlock;
 
 	retval = security_task_setscheduler(p);
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 4192098..51c6e89 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -189,7 +189,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!capable(CAP_SETGID))
+	if (!nsown_capable(CAP_SETGID))
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;