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

Pull namespace updates from Eric Biederman:
 "Life has been busy and I have not gotten half as much done this round
  as I would have liked. I delayed it so that a minor conflict
  resolution with the mips tree could spend a little time in linux-next
  before I sent this pull request.

  This includes two long delayed user namespace changes from Kirill
  Tkhai. It also includes a very useful change from Serge Hallyn that
  allows the security capability attribute to be used inside of user
  namespaces. The practical effect of this is people can now untar
  tarballs and install rpms in user namespaces. It had been suggested to
  generalize this and encode some of the namespace information
  information in the xattr name. Upon close inspection that makes the
  things that should be hard easy and the things that should be easy
  more expensive.

  Then there is my bugfix/cleanup for signal injection that removes the
  magic encoding of the siginfo union member from the kernel internal
  si_code. The mips folks reported the case where I had used FPE_FIXME
  me is impossible so I have remove FPE_FIXME from mips, while at the
  same time including a return statement in that case to keep gcc from
  complaining about unitialized variables.

  I almost finished the work to get make copy_siginfo_to_user a trivial
  copy to user. The code is available at:

     git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace.git neuter-copy_siginfo_to_user-v3

  But I did not have time/energy to get the code posted and reviewed
  before the merge window opened.

  I was able to see that the security excuse for just copying fields
  that we know are initialized doesn't work in practice there are buggy
  initializations that don't initialize the proper fields in siginfo. So
  we still sometimes copy unitialized data to userspace"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  Introduce v3 namespaced file capabilities
  mips/signal: In force_fcr31_sig return in the impossible case
  signal: Remove kernel interal si_code magic
  fcntl: Don't use ambiguous SIG_POLL si_codes
  prctl: Allow local CAP_SYS_ADMIN changing exe_file
  security: Use user_namespace::level to avoid redundant iterations in cap_capable()
  userns,pidns: Verify the userns for new pid namespaces
  signal/testing: Don't look for __SI_FAULT in userspace
  signal/mips: Document a conflict with SI_USER with SIGFPE
  signal/sparc: Document a conflict with SI_USER with SIGFPE
  signal/ia64: Document a conflict with SI_USER with SIGFPE
  signal/alpha: Document a conflict with SI_USER for SIGTRAP

6 files changed, 77 insertions, 37 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index a35d8a1..3481aba 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1615,7 +1615,7 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
-	unsafe_put_user((short)info.cause, &infop->si_code, Efault);
+	unsafe_put_user(info.cause, &infop->si_code, Efault);
 	unsafe_put_user(info.pid, &infop->si_pid, Efault);
 	unsafe_put_user(info.uid, &infop->si_uid, Efault);
 	unsafe_put_user(info.status, &infop->si_status, Efault);
@@ -1741,7 +1741,7 @@ COMPAT_SYSCALL_DEFINE5(waitid,
 	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
-	unsafe_put_user((short)info.cause, &infop->si_code, Efault);
+	unsafe_put_user(info.cause, &infop->si_code, Efault);
 	unsafe_put_user(info.pid, &infop->si_pid, Efault);
 	unsafe_put_user(info.uid, &infop->si_uid, Efault);
 	unsafe_put_user(info.status, &infop->si_status, Efault);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 74a5a72..4918314 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -101,6 +101,10 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 	int i;
 	int err;
 
+	err = -EINVAL;
+	if (!in_userns(parent_pid_ns->user_ns, user_ns))
+		goto out;
+
 	err = -ENOSPC;
 	if (level > MAX_PID_NS_LEVEL)
 		goto out;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 60f356d..84b1367 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -728,8 +728,7 @@ static int ptrace_peek_siginfo(struct task_struct *child,
 		if (unlikely(in_compat_syscall())) {
 			compat_siginfo_t __user *uinfo = compat_ptr(data);
 
-			if (copy_siginfo_to_user32(uinfo, &info) ||
-			    __put_user(info.si_code, &uinfo->si_code)) {
+			if (copy_siginfo_to_user32(uinfo, &info)) {
 				ret = -EFAULT;
 				break;
 			}
@@ -739,8 +738,7 @@ static int ptrace_peek_siginfo(struct task_struct *child,
 		{
 			siginfo_t __user *uinfo = (siginfo_t __user *) data;
 
-			if (copy_siginfo_to_user(uinfo, &info) ||
-			    __put_user(info.si_code, &uinfo->si_code)) {
+			if (copy_siginfo_to_user(uinfo, &info)) {
 				ret = -EFAULT;
 				break;
 			}
diff --git a/kernel/signal.c b/kernel/signal.c
index ed804a4..800a18f 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2686,6 +2686,51 @@ COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset,
 }
 #endif
 
+enum siginfo_layout siginfo_layout(int sig, int si_code)
+{
+	enum siginfo_layout layout = SIL_KILL;
+	if ((si_code > SI_USER) && (si_code < SI_KERNEL)) {
+		static const struct {
+			unsigned char limit, layout;
+		} filter[] = {
+			[SIGILL]  = { NSIGILL,  SIL_FAULT },
+			[SIGFPE]  = { NSIGFPE,  SIL_FAULT },
+			[SIGSEGV] = { NSIGSEGV, SIL_FAULT },
+			[SIGBUS]  = { NSIGBUS,  SIL_FAULT },
+			[SIGTRAP] = { NSIGTRAP, SIL_FAULT },
+#if defined(SIGMET) && defined(NSIGEMT)
+			[SIGEMT]  = { NSIGEMT,  SIL_FAULT },
+#endif
+			[SIGCHLD] = { NSIGCHLD, SIL_CHLD },
+			[SIGPOLL] = { NSIGPOLL, SIL_POLL },
+#ifdef __ARCH_SIGSYS
+			[SIGSYS]  = { NSIGSYS,  SIL_SYS },
+#endif
+		};
+		if ((sig < ARRAY_SIZE(filter)) && (si_code <= filter[sig].limit))
+			layout = filter[sig].layout;
+		else if (si_code <= NSIGPOLL)
+			layout = SIL_POLL;
+	} else {
+		if (si_code == SI_TIMER)
+			layout = SIL_TIMER;
+		else if (si_code == SI_SIGIO)
+			layout = SIL_POLL;
+		else if (si_code < 0)
+			layout = SIL_RT;
+		/* Tests to support buggy kernel ABIs */
+#ifdef TRAP_FIXME
+		if ((sig == SIGTRAP) && (si_code == TRAP_FIXME))
+			layout = SIL_FAULT;
+#endif
+#ifdef FPE_FIXME
+		if ((sig == SIGFPE) && (si_code == FPE_FIXME))
+			layout = SIL_FAULT;
+#endif
+	}
+	return layout;
+}
+
 #ifndef HAVE_ARCH_COPY_SIGINFO_TO_USER
 
 int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
@@ -2708,22 +2753,20 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
 	 */
 	err = __put_user(from->si_signo, &to->si_signo);
 	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user((short)from->si_code, &to->si_code);
-	switch (from->si_code & __SI_MASK) {
-	case __SI_KILL:
+	err |= __put_user(from->si_code, &to->si_code);
+	switch (siginfo_layout(from->si_signo, from->si_code)) {
+	case SIL_KILL:
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
 		break;
-	case __SI_TIMER:
-		 err |= __put_user(from->si_tid, &to->si_tid);
-		 err |= __put_user(from->si_overrun, &to->si_overrun);
-		 err |= __put_user(from->si_ptr, &to->si_ptr);
+	case SIL_TIMER:
+		/* Unreached SI_TIMER is negative */
 		break;
-	case __SI_POLL:
+	case SIL_POLL:
 		err |= __put_user(from->si_band, &to->si_band);
 		err |= __put_user(from->si_fd, &to->si_fd);
 		break;
-	case __SI_FAULT:
+	case SIL_FAULT:
 		err |= __put_user(from->si_addr, &to->si_addr);
 #ifdef __ARCH_SI_TRAPNO
 		err |= __put_user(from->si_trapno, &to->si_trapno);
@@ -2748,30 +2791,25 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
 			err |= __put_user(from->si_pkey, &to->si_pkey);
 #endif
 		break;
-	case __SI_CHLD:
+	case SIL_CHLD:
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
 		err |= __put_user(from->si_status, &to->si_status);
 		err |= __put_user(from->si_utime, &to->si_utime);
 		err |= __put_user(from->si_stime, &to->si_stime);
 		break;
-	case __SI_RT: /* This is not generated by the kernel as of now. */
-	case __SI_MESGQ: /* But this is */
+	case SIL_RT:
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
 		err |= __put_user(from->si_ptr, &to->si_ptr);
 		break;
 #ifdef __ARCH_SIGSYS
-	case __SI_SYS:
+	case SIL_SYS:
 		err |= __put_user(from->si_call_addr, &to->si_call_addr);
 		err |= __put_user(from->si_syscall, &to->si_syscall);
 		err |= __put_user(from->si_arch, &to->si_arch);
 		break;
 #endif
-	default: /* this is just in case for now ... */
-		err |= __put_user(from->si_pid, &to->si_pid);
-		err |= __put_user(from->si_uid, &to->si_uid);
-		break;
 	}
 	return err;
 }
diff --git a/kernel/sys.c b/kernel/sys.c
index 2855ee7..9aebc29 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1896,15 +1896,11 @@ static int validate_prctl_map(struct prctl_mm_map *prctl_map)
 
 	/*
 	 * Finally, make sure the caller has the rights to
-	 * change /proc/pid/exe link: only local root should
+	 * change /proc/pid/exe link: only local sys admin should
 	 * be allowed to.
 	 */
 	if (prctl_map->exe_fd != (u32)-1) {
-		struct user_namespace *ns = current_user_ns();
-		const struct cred *cred = current_cred();
-
-		if (!uid_eq(cred->uid, make_kuid(ns, 0)) ||
-		    !gid_eq(cred->gid, make_kgid(ns, 0)))
+		if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN))
 			goto out;
 	}
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 2f735cb..c490f1e 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -986,17 +986,21 @@ bool userns_may_setgroups(const struct user_namespace *ns)
 }
 
 /*
- * Returns true if @ns is the same namespace as or a descendant of
- * @target_ns.
+ * Returns true if @child is the same namespace or a descendant of
+ * @ancestor.
  */
+bool in_userns(const struct user_namespace *ancestor,
+	       const struct user_namespace *child)
+{
+	const struct user_namespace *ns;
+	for (ns = child; ns->level > ancestor->level; ns = ns->parent)
+		;
+	return (ns == ancestor);
+}
+
 bool current_in_userns(const struct user_namespace *target_ns)
 {
-	struct user_namespace *ns;
-	for (ns = current_user_ns(); ns; ns = ns->parent) {
-		if (ns == target_ns)
-			return true;
-	}
-	return false;
+	return in_userns(target_ns, current_user_ns());
 }
 
 static inline struct user_namespace *to_user_ns(struct ns_common *ns)