for-linus-2020-01-03

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCXg9C5wAKCRCRxhvAZXjc
 oiZXAPsGFXyDCWlKnShBpKufdFh6XugADlyZK0Si2ISWQoJJsgD/Ri1g3zg6V7YC
 HBG0sz8+vSk/Ys55yDQz+K1d1MTkdQ4=
 =8uQe
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-2020-01-03' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull thread fixes from Christian Brauner:
 "Here are two fixes:

   - Panic earlier when global init exits to generate useable coredumps.

     Currently, when global init and all threads in its thread-group
     have exited we panic via:

       do_exit()
       -> exit_notify()
          -> forget_original_parent()
             -> find_child_reaper()

     This makes it hard to extract a useable coredump for global init
     from a kernel crashdump because by the time we panic exit_mm() will
     have already released global init's mm. We now panic slightly
     earlier. This has been a problem in certain environments such as
     Android.

   - Fix a race in assigning and reading taskstats for thread-groups
     with more than one thread.

     This patch has been waiting for quite a while since people
     disagreed on what the correct fix was at first"

* tag 'for-linus-2020-01-03' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  exit: panic before exit_mm() on global init exit
  taskstats: fix data-race

kernel/exit.c

@@ -517,10 +517,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father,
 	}
 
 	write_unlock_irq(&tasklist_lock);
-	if (unlikely(pid_ns == &init_pid_ns)) {
-		panic("Attempted to kill init! exitcode=0x%08x\n",
-			father->signal->group_exit_code ?: father->exit_code);
-	}
 
 	list_for_each_entry_safe(p, n, dead, ptrace_entry) {
 		list_del_init(&p->ptrace_entry);
@@ -766,6 +762,14 @@ void __noreturn do_exit(long code)
 	acct_update_integrals(tsk);
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
+		/*
+		 * If the last thread of global init has exited, panic
+		 * immediately to get a useable coredump.
+		 */
+		if (unlikely(is_global_init(tsk)))
+			panic("Attempted to kill init! exitcode=0x%08x\n",
+				tsk->signal->group_exit_code ?: (int)code);
+
 #ifdef CONFIG_POSIX_TIMERS
 		hrtimer_cancel(&tsk->signal->real_timer);
 		exit_itimers(tsk->signal);

kernel/taskstats.c

@@ -554,25 +554,33 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
 {
 	struct signal_struct *sig = tsk->signal;
-	struct taskstats *stats;
+	struct taskstats *stats_new, *stats;
 
-	if (sig->stats || thread_group_empty(tsk))
-		goto ret;
+	/* Pairs with smp_store_release() below. */
+	stats = smp_load_acquire(&sig->stats);
+	if (stats || thread_group_empty(tsk))
+		return stats;
 
 	/* No problem if kmem_cache_zalloc() fails */
-	stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
+	stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
 
 	spin_lock_irq(&tsk->sighand->siglock);
-	if (!sig->stats) {
-		sig->stats = stats;
-		stats = NULL;
+	stats = sig->stats;
+	if (!stats) {
+		/*
+		 * Pairs with smp_store_release() above and order the
+		 * kmem_cache_zalloc().
+		 */
+		smp_store_release(&sig->stats, stats_new);
+		stats = stats_new;
+		stats_new = NULL;
 	}
 	spin_unlock_irq(&tsk->sighand->siglock);
 
-	if (stats)
-		kmem_cache_free(taskstats_cache, stats);
-ret:
-	return sig->stats;
+	if (stats_new)
+		kmem_cache_free(taskstats_cache, stats_new);
+
+	return stats;
 }
 
 /* Send pid data out on exit */