[RESEND PATCH] prctl: add PR_[GS]ET_PDEATHSIG_PROC

[JÃrg Billeter]

PR_SET_PDEATHSIG sets a parent death signal that the calling process
will get when its parent thread dies, even when the result of getppid()
doesn't change because the calling process is reparented to a different
thread in the same parent process. When managing multiple processes, a
process-based parent death signal is much more useful. E.g., to avoid
stray child processes.

PR_SET_PDEATHSIG_PROC sets a process-based death signal. Unlike
PR_SET_PDEATHSIG, this is inherited across fork to allow killing a whole
subtree without race conditions.

This can be used for sandboxing when combined with a seccomp filter.

There have been previous attempts to support this by changing the
behavior of PR_SET_PDEATHSIG. However, that would break existing
applications. See https://marc.info/?l=linux-kernel&m=117621804801689
and https://bugzilla.kernel.org/show_bug.cgi?id=43300

Signed-off-by: JÃrg Billeter <j@xxxxxxxxx>
---

Previous discussion: https://patchwork.kernel.org/patch/9945315/

 fs/exec.c                    |  1 +
 include/linux/sched/signal.h |  3 +++
 include/uapi/linux/prctl.h   |  4 ++++
 kernel/cred.c                |  1 +
 kernel/exit.c                |  4 ++++
 kernel/fork.c                |  2 ++
 kernel/sys.c                 | 11 +++++++++++
 security/apparmor/lsm.c      |  1 +
 security/selinux/hooks.c     |  1 +
 9 files changed, 28 insertions(+)

diff --git a/fs/exec.c b/fs/exec.c
index ac34d9724684..7045f0223140 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1334,6 +1334,7 @@ void setup_new_exec(struct linux_binprm * bprm)
 	if (bprm->secureexec) {
 		/* Make sure parent cannot signal privileged process. */
 		current->pdeath_signal = 0;
+		current->signal->pdeath_signal_proc = 0;
 
 		/*
 		 * For secureexec, reset the stack limit to sane default to
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 2a0dd40b15db..c5c137e5ef39 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -103,6 +103,9 @@ struct signal_struct {
 	int			group_stop_count;
 	unsigned int		flags; /* see SIGNAL_* flags below */
 
+	/* The signal sent when the parent dies: */
+	int			pdeath_signal_proc;
+
 	/*
 	 * PR_SET_CHILD_SUBREAPER marks a process, like a service
 	 * manager, to re-parent orphan (double-forking) child processes
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index a8d0759a9e40..04508e81d4f2 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -197,4 +197,8 @@ struct prctl_mm_map {
 # define PR_CAP_AMBIENT_LOWER		3
 # define PR_CAP_AMBIENT_CLEAR_ALL	4
 
+/* Process-based variant of PDEATHSIG */
+#define PR_SET_PDEATHSIG_PROC		48
+#define PR_GET_PDEATHSIG_PROC		49
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/cred.c b/kernel/cred.c
index ecf03657e71c..0192a94670e1 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -448,6 +448,7 @@ int commit_creds(struct cred *new)
 		if (task->mm)
 			set_dumpable(task->mm, suid_dumpable);
 		task->pdeath_signal = 0;
+		task->signal->pdeath_signal_proc = 0;
 		smp_wmb();
 	}
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 3481ababd06a..9b6fbb0128d7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -635,6 +635,10 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	if (unlikely(p->exit_state == EXIT_DEAD))
 		return;
 
+	if (p->signal->pdeath_signal_proc)
+		group_send_sig_info(p->signal->pdeath_signal_proc,
+				    SEND_SIG_NOINFO, p);
+
 	/* We don't want people slaying init. */
 	p->exit_signal = SIGCHLD;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 10646182440f..264936c367e3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1415,6 +1415,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 
 	mutex_init(&sig->cred_guard_mutex);
 
+	sig->pdeath_signal_proc = current->signal->pdeath_signal_proc;
+
 	return 0;
 }
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 9aebc2935013..dcb9a535404e 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2206,6 +2206,17 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_GET_PDEATHSIG:
 		error = put_user(me->pdeath_signal, (int __user *)arg2);
 		break;
+	case PR_SET_PDEATHSIG_PROC:
+		if (!valid_signal(arg2)) {
+			error = -EINVAL;
+			break;
+		}
+		me->signal->pdeath_signal_proc = arg2;
+		break;
+	case PR_GET_PDEATHSIG_PROC:
+		error = put_user(me->signal->pdeath_signal_proc,
+				 (int __user *)arg2);
+		break;
 	case PR_GET_DUMPABLE:
 		error = get_dumpable(me->mm);
 		break;
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 72b915dfcaf7..98cd937c337d 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -689,6 +689,7 @@ static void apparmor_bprm_committing_creds(struct linux_binprm *bprm)
 	aa_inherit_files(bprm->cred, current->files);
 
 	current->pdeath_signal = 0;
+	current->signal->pdeath_signal_proc = 0;
 
 	/* reset soft limits and set hard limits for the new label */
 	__aa_transition_rlimits(label, new_ctx->label);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index f5d304736852..19d97d5acdb9 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2547,6 +2547,7 @@ static void selinux_bprm_committing_creds(struct linux_binprm *bprm)
 
 	/* Always clear parent death signal on SID transitions. */
 	current->pdeath_signal = 0;
+	current->signal->pdeath_signal_proc = 0;
 
 	/* Check whether the new SID can inherit resource limits from the old
 	 * SID.  If not, reset all soft limits to the lower of the current
-- 
2.14.1