From 628c1bcba204052d19b686b5bac149a644cdb72e Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 17 Nov 2017 15:30:01 -0800 Subject: kernel/signal.c: protect the traced SIGNAL_UNKILLABLE tasks from SIGKILL The comment in sig_ignored() says "Tracers may want to know about even ignored signals" but SIGKILL can not be reported to debugger and it is just wrong to return 0 in this case: SIGKILL should only kill the SIGNAL_UNKILLABLE task if it comes from the parent ns. Change sig_ignored() to ignore ->ptrace if sig == SIGKILL and rely on sig_task_ignored(). SISGTOP coming from within the namespace is not really right too but at least debugger can intercept it, and we can't drop it here because this will break "gdb -p 1": ptrace_attach() won't work. Perhaps we will add another ->ptrace check later, we will see. Link: http://lkml.kernel.org/r/20171103184206.GB21036@redhat.com Signed-off-by: Oleg Nesterov Tested-by: Kyle Huey Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'kernel/signal.c') diff --git a/kernel/signal.c b/kernel/signal.c index aa1fb9f905db..be5913134742 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -94,13 +94,15 @@ static int sig_ignored(struct task_struct *t, int sig, bool force) if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig)) return 0; - if (!sig_task_ignored(t, sig, force)) - return 0; - /* - * Tracers may want to know about even ignored signals. + * Tracers may want to know about even ignored signal unless it + * is SIGKILL which can't be reported anyway but can be ignored + * by SIGNAL_UNKILLABLE task. */ - return !t->ptrace; + if (t->ptrace && sig != SIGKILL) + return 0; + + return sig_task_ignored(t, sig, force); } /* -- cgit v1.2.3 From ac25385089f673560867eb5179228a44ade0cfc1 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 17 Nov 2017 15:30:04 -0800 Subject: kernel/signal.c: protect the SIGNAL_UNKILLABLE tasks from !sig_kernel_only() signals Change sig_task_ignored() to drop the SIG_DFL && !sig_kernel_only() signals even if force == T. This simplifies the next change and this matches the same check in get_signal() which will drop these signals anyway. Link: http://lkml.kernel.org/r/20171103184227.GC21036@redhat.com Signed-off-by: Oleg Nesterov Tested-by: Kyle Huey Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/signal.c') diff --git a/kernel/signal.c b/kernel/signal.c index be5913134742..01ba166a5e3a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -78,7 +78,7 @@ static int sig_task_ignored(struct task_struct *t, int sig, bool force) handler = sig_handler(t, sig); if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) && - handler == SIG_DFL && !force) + handler == SIG_DFL && !(force && sig_kernel_only(sig))) return 1; return sig_handler_ignored(handler, sig); -- cgit v1.2.3 From 426915796ccaf9c2bd9bb06dc5702225957bc2e5 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 17 Nov 2017 15:30:08 -0800 Subject: kernel/signal.c: remove the no longer needed SIGNAL_UNKILLABLE check in complete_signal() complete_signal() checks SIGNAL_UNKILLABLE before it starts to destroy the thread group, today this is wrong in many ways. If nothing else, fatal_signal_pending() should always imply that the whole thread group (except ->group_exit_task if it is not NULL) is killed, this check breaks the rule. After the previous changes we can rely on sig_task_ignored(); sig_fatal(sig) && SIGNAL_UNKILLABLE can only be true if we actually want to kill this task and sig == SIGKILL OR it is traced and debugger can intercept the signal. This should hopefully fix the problem reported by Dmitry. This test-case static int init(void *arg) { for (;;) pause(); } int main(void) { char stack[16 * 1024]; for (;;) { int pid = clone(init, stack + sizeof(stack)/2, CLONE_NEWPID | SIGCHLD, NULL); assert(pid > 0); assert(ptrace(PTRACE_ATTACH, pid, 0, 0) == 0); assert(waitpid(-1, NULL, WSTOPPED) == pid); assert(ptrace(PTRACE_DETACH, pid, 0, SIGSTOP) == 0); assert(syscall(__NR_tkill, pid, SIGKILL) == 0); assert(pid == wait(NULL)); } } triggers the WARN_ON_ONCE(!(task->jobctl & JOBCTL_STOP_PENDING)) in task_participate_group_stop(). do_signal_stop()->signal_group_exit() checks SIGNAL_GROUP_EXIT and return false, but task_set_jobctl_pending() checks fatal_signal_pending() and does not set JOBCTL_STOP_PENDING. And his should fix the minor security problem reported by Kyle, SECCOMP_RET_TRACE can miss fatal_signal_pending() the same way if the task is the root of a pid namespace. Link: http://lkml.kernel.org/r/20171103184246.GD21036@redhat.com Signed-off-by: Oleg Nesterov Reported-by: Dmitry Vyukov Reported-by: Kyle Huey Reviewed-by: Kees Cook Tested-by: Kyle Huey Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/signal.c') diff --git a/kernel/signal.c b/kernel/signal.c index 01ba166a5e3a..6895f6bb98a7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -931,9 +931,9 @@ static void complete_signal(int sig, struct task_struct *p, int group) * then start taking the whole group down immediately. */ if (sig_fatal(p, sig) && - !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) && + !(signal->flags & SIGNAL_GROUP_EXIT) && !sigismember(&t->real_blocked, sig) && - (sig == SIGKILL || !t->ptrace)) { + (sig == SIGKILL || !p->ptrace)) { /* * This signal will be fatal to the whole group. */ -- cgit v1.2.3