Merge branch 'akpm' (Andrew's patch-bomb)

* emailed from Andrew Morton <akpm@linux-foundation.org>: (21 patches)
  mm/memblock: fix overlapping allocation when doubling reserved array
  c/r: prctl: Move PR_GET_TID_ADDRESS to a proper place
  pidns: find_new_reaper() can no longer switch to init_pid_ns.child_reaper
  pidns: guarantee that the pidns init will be the last pidns process reaped
  fault-inject: avoid call to random32() if fault injection is disabled
  Viresh has moved
  get_maintainer: Fix --help warning
  mm/memory.c: fix kernel-doc warnings
  mm: fix kernel-doc warnings
  mm: correctly synchronize rss-counters at exit/exec
  mm, thp: print useful information when mmap_sem is unlocked in zap_pmd_range
  h8300: use the declarations provided by <asm/sections.h>
  h8300: fix use of extinct _sbss and _ebss
  xtensa: use the declarations provided by <asm/sections.h>
  xtensa: use "test -e" instead of bashism "test -a"
  xtensa: replace xtensa-specific _f{data,text} by _s{data,text}
  memcg: fix use_hierarchy css_is_ancestor oops regression
  mm, oom: fix and cleanup oom score calculations
  nilfs2: ensure proper cache clearing for gc-inodes
  thp: avoid atomic64_read in pmd_read_atomic for 32bit PAE
  ...

3 files changed, 36 insertions, 9 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 34867cc5b42a..2f59cc334516 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -72,6 +72,18 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
 		list_del_rcu(&p->tasks);
 		list_del_init(&p->sibling);
 		__this_cpu_dec(process_counts);
+		/*
+		 * If we are the last child process in a pid namespace to be
+		 * reaped, notify the reaper sleeping zap_pid_ns_processes().
+		 */
+		if (IS_ENABLED(CONFIG_PID_NS)) {
+			struct task_struct *parent = p->real_parent;
+
+			if ((task_active_pid_ns(parent)->child_reaper == parent) &&
+			    list_empty(&parent->children) &&
+			    (parent->flags & PF_EXITING))
+				wake_up_process(parent);
+		}
 	}
 	list_del_rcu(&p->thread_group);
 }
@@ -643,6 +655,7 @@ static void exit_mm(struct task_struct * tsk)
 	mm_release(tsk, mm);
 	if (!mm)
 		return;
+	sync_mm_rss(mm);
 	/*
 	 * Serialize with any possible pending coredump.
 	 * We must hold mmap_sem around checking core_state
@@ -719,12 +732,6 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 
 		zap_pid_ns_processes(pid_ns);
 		write_lock_irq(&tasklist_lock);
-		/*
-		 * We can not clear ->child_reaper or leave it alone.
-		 * There may by stealth EXIT_DEAD tasks on ->children,
-		 * forget_original_parent() must move them somewhere.
-		 */
-		pid_ns->child_reaper = init_pid_ns.child_reaper;
 	} else if (father->signal->has_child_subreaper) {
 		struct task_struct *reaper;
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 16b20e38c4a1..b3c7fd554250 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -184,11 +184,31 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	}
 	read_unlock(&tasklist_lock);
 
+	/* Firstly reap the EXIT_ZOMBIE children we may have. */
 	do {
 		clear_thread_flag(TIF_SIGPENDING);
 		rc = sys_wait4(-1, NULL, __WALL, NULL);
 	} while (rc != -ECHILD);
 
+	/*
+	 * sys_wait4() above can't reap the TASK_DEAD children.
+	 * Make sure they all go away, see __unhash_process().
+	 */
+	for (;;) {
+		bool need_wait = false;
+
+		read_lock(&tasklist_lock);
+		if (!list_empty(&current->children)) {
+			__set_current_state(TASK_UNINTERRUPTIBLE);
+			need_wait = true;
+		}
+		read_unlock(&tasklist_lock);
+
+		if (!need_wait)
+			break;
+		schedule();
+	}
+
 	if (pid_ns->reboot)
 		current->signal->group_exit_code = pid_ns->reboot;
 
diff --git a/kernel/sys.c b/kernel/sys.c
index f0ec44dcd415..e0c8ffc50d7f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2127,9 +2127,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 				else
 					return -EINVAL;
 				break;
-		case PR_GET_TID_ADDRESS:
-			error = prctl_get_tid_address(me, (int __user **)arg2);
-			break;
 			default:
 				return -EINVAL;
 			}
@@ -2147,6 +2144,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		case PR_SET_MM:
 			error = prctl_set_mm(arg2, arg3, arg4, arg5);
 			break;
+		case PR_GET_TID_ADDRESS:
+			error = prctl_get_tid_address(me, (int __user **)arg2);
+			break;
 		case PR_SET_CHILD_SUBREAPER:
 			me->signal->is_child_subreaper = !!arg2;
 			error = 0;