Merge branch 'akpm' (patchbomb from Andrew)

Merge first patchbomb from Andrew Morton:
 - a few minor cifs fixes
 - dma-debug upadtes
 - ocfs2
 - slab
 - about half of MM
 - procfs
 - kernel/exit.c
 - panic.c tweaks
 - printk upates
 - lib/ updates
 - checkpatch updates
 - fs/binfmt updates
 - the drivers/rtc tree
 - nilfs
 - kmod fixes
 - more kernel/exit.c
 - various other misc tweaks and fixes

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (190 commits)
  exit: pidns: fix/update the comments in zap_pid_ns_processes()
  exit: pidns: alloc_pid() leaks pid_namespace if child_reaper is exiting
  exit: exit_notify: re-use "dead" list to autoreap current
  exit: reparent: call forget_original_parent() under tasklist_lock
  exit: reparent: avoid find_new_reaper() if no children
  exit: reparent: introduce find_alive_thread()
  exit: reparent: introduce find_child_reaper()
  exit: reparent: document the ->has_child_subreaper checks
  exit: reparent: s/while_each_thread/for_each_thread/ in find_new_reaper()
  exit: reparent: fix the cross-namespace PR_SET_CHILD_SUBREAPER reparenting
  exit: reparent: fix the dead-parent PR_SET_CHILD_SUBREAPER reparenting
  exit: proc: don't try to flush /proc/tgid/task/tgid
  exit: release_task: fix the comment about group leader accounting
  exit: wait: drop tasklist_lock before psig->c* accounting
  exit: wait: don't use zombie->real_parent
  exit: wait: cleanup the ptrace_reparented() checks
  usermodehelper: kill the kmod_thread_locker logic
  usermodehelper: don't use CLONE_VFORK for ____call_usermodehelper()
  fs/hfs/catalog.c: fix comparison bug in hfs_cat_keycmp
  nilfs2: fix the nilfs_iget() vs. nilfs_new_inode() races
  ...

12 files changed, 205 insertions, 424 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 17ea6d4a9a24..a59481a3fa6c 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -57,7 +57,6 @@ obj-$(CONFIG_UTS_NS) += utsname.o
 obj-$(CONFIG_USER_NS) += user_namespace.o
 obj-$(CONFIG_PID_NS) += pid_namespace.o
 obj-$(CONFIG_IKCONFIG) += configs.o
-obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
 obj-$(CONFIG_SMP) += stop_machine.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
diff --git a/kernel/exit.c b/kernel/exit.c
index 232c4bc8bcc9..8714e5ded8b4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -118,13 +118,10 @@ static void __exit_signal(struct task_struct *tsk)
 	}
 
 	/*
-	 * Accumulate here the counters for all threads but the group leader
-	 * as they die, so they can be added into the process-wide totals
-	 * when those are taken.  The group leader stays around as a zombie as
-	 * long as there are other threads.  When it gets reaped, the exit.c
-	 * code will add its counts into these totals.  We won't ever get here
-	 * for the group leader, since it will have been the last reference on
-	 * the signal_struct.
+	 * Accumulate here the counters for all threads as they die. We could
+	 * skip the group leader because it is the last user of signal_struct,
+	 * but we want to avoid the race with thread_group_cputime() which can
+	 * see the empty ->thread_head list.
 	 */
 	task_cputime(tsk, &utime, &stime);
 	write_seqlock(&sig->stats_lock);
@@ -462,6 +459,44 @@ static void exit_mm(struct task_struct *tsk)
 	clear_thread_flag(TIF_MEMDIE);
 }
 
+static struct task_struct *find_alive_thread(struct task_struct *p)
+{
+	struct task_struct *t;
+
+	for_each_thread(p, t) {
+		if (!(t->flags & PF_EXITING))
+			return t;
+	}
+	return NULL;
+}
+
+static struct task_struct *find_child_reaper(struct task_struct *father)
+	__releases(&tasklist_lock)
+	__acquires(&tasklist_lock)
+{
+	struct pid_namespace *pid_ns = task_active_pid_ns(father);
+	struct task_struct *reaper = pid_ns->child_reaper;
+
+	if (likely(reaper != father))
+		return reaper;
+
+	reaper = find_alive_thread(father);
+	if (reaper) {
+		pid_ns->child_reaper = reaper;
+		return reaper;
+	}
+
+	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);
+	}
+	zap_pid_ns_processes(pid_ns);
+	write_lock_irq(&tasklist_lock);
+
+	return father;
+}
+
 /*
  * When we die, we re-parent all our children, and try to:
  * 1. give them to another thread in our thread group, if such a member exists
@@ -469,58 +504,36 @@ static void exit_mm(struct task_struct *tsk)
  *    child_subreaper for its children (like a service manager)
  * 3. give it to the init process (PID 1) in our pid namespace
  */
-static struct task_struct *find_new_reaper(struct task_struct *father)
-	__releases(&tasklist_lock)
-	__acquires(&tasklist_lock)
+static struct task_struct *find_new_reaper(struct task_struct *father,
+					   struct task_struct *child_reaper)
 {
-	struct pid_namespace *pid_ns = task_active_pid_ns(father);
-	struct task_struct *thread;
+	struct task_struct *thread, *reaper;
 
-	thread = father;
-	while_each_thread(father, thread) {
-		if (thread->flags & PF_EXITING)
-			continue;
-		if (unlikely(pid_ns->child_reaper == father))
-			pid_ns->child_reaper = thread;
+	thread = find_alive_thread(father);
+	if (thread)
 		return thread;
-	}
-
-	if (unlikely(pid_ns->child_reaper == 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);
-		}
-
-		zap_pid_ns_processes(pid_ns);
-		write_lock_irq(&tasklist_lock);
-	} else if (father->signal->has_child_subreaper) {
-		struct task_struct *reaper;
 
+	if (father->signal->has_child_subreaper) {
 		/*
-		 * Find the first ancestor marked as child_subreaper.
-		 * Note that the code below checks same_thread_group(reaper,
-		 * pid_ns->child_reaper).  This is what we need to DTRT in a
-		 * PID namespace. However we still need the check above, see
-		 * http://marc.info/?l=linux-kernel&m=131385460420380
+		 * Find the first ->is_child_subreaper ancestor in our pid_ns.
+		 * We start from father to ensure we can not look into another
+		 * namespace, this is safe because all its threads are dead.
 		 */
-		for (reaper = father->real_parent;
-		     reaper != &init_task;
+		for (reaper = father;
+		     !same_thread_group(reaper, child_reaper);
 		     reaper = reaper->real_parent) {
-			if (same_thread_group(reaper, pid_ns->child_reaper))
+			/* call_usermodehelper() descendants need this check */
+			if (reaper == &init_task)
 				break;
 			if (!reaper->signal->is_child_subreaper)
 				continue;
-			thread = reaper;
-			do {
-				if (!(thread->flags & PF_EXITING))
-					return reaper;
-			} while_each_thread(reaper, thread);
+			thread = find_alive_thread(reaper);
+			if (thread)
+				return thread;
 		}
 	}
 
-	return pid_ns->child_reaper;
+	return child_reaper;
 }
 
 /*
@@ -529,15 +542,7 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 static void reparent_leader(struct task_struct *father, struct task_struct *p,
 				struct list_head *dead)
 {
-	list_move_tail(&p->sibling, &p->real_parent->children);
-
-	if (p->exit_state == EXIT_DEAD)
-		return;
-	/*
-	 * If this is a threaded reparent there is no need to
-	 * notify anyone anything has happened.
-	 */
-	if (same_thread_group(p->real_parent, father))
+	if (unlikely(p->exit_state == EXIT_DEAD))
 		return;
 
 	/* We don't want people slaying init. */
@@ -548,49 +553,53 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
 		if (do_notify_parent(p, p->exit_signal)) {
 			p->exit_state = EXIT_DEAD;
-			list_move_tail(&p->sibling, dead);
+			list_add(&p->ptrace_entry, dead);
 		}
 	}
 
 	kill_orphaned_pgrp(p, father);
 }
 
-static void forget_original_parent(struct task_struct *father)
+/*
+ * This does two things:
+ *
+ * A.  Make init inherit all the child processes
+ * B.  Check to see if any process groups have become orphaned
+ *	as a result of our exiting, and if they have any stopped
+ *	jobs, send them a SIGHUP and then a SIGCONT.  (POSIX 3.2.2.2)
+ */
+static void forget_original_parent(struct task_struct *father,
+					struct list_head *dead)
 {
-	struct task_struct *p, *n, *reaper;
-	LIST_HEAD(dead_children);
+	struct task_struct *p, *t, *reaper;
 
-	write_lock_irq(&tasklist_lock);
-	/*
-	 * Note that exit_ptrace() and find_new_reaper() might
-	 * drop tasklist_lock and reacquire it.
-	 */
-	exit_ptrace(father);
-	reaper = find_new_reaper(father);
+	if (unlikely(!list_empty(&father->ptraced)))
+		exit_ptrace(father, dead);
 
-	list_for_each_entry_safe(p, n, &father->children, sibling) {
-		struct task_struct *t = p;
+	/* Can drop and reacquire tasklist_lock */
+	reaper = find_child_reaper(father);
+	if (list_empty(&father->children))
+		return;
 
-		do {
+	reaper = find_new_reaper(father, reaper);
+	list_for_each_entry(p, &father->children, sibling) {
+		for_each_thread(p, t) {
 			t->real_parent = reaper;
-			if (t->parent == father) {
-				BUG_ON(t->ptrace);
+			BUG_ON((!t->ptrace) != (t->parent == father));
+			if (likely(!t->ptrace))
 				t->parent = t->real_parent;
-			}
 			if (t->pdeath_signal)
 				group_send_sig_info(t->pdeath_signal,
 						    SEND_SIG_NOINFO, t);
-		} while_each_thread(p, t);
-		reparent_leader(father, p, &dead_children);
-	}
-	write_unlock_irq(&tasklist_lock);
-
-	BUG_ON(!list_empty(&father->children));
-
-	list_for_each_entry_safe(p, n, &dead_children, sibling) {
-		list_del_init(&p->sibling);
-		release_task(p);
+		}
+		/*
+		 * If this is a threaded reparent there is no need to
+		 * notify anyone anything has happened.
+		 */
+		if (!same_thread_group(reaper, father))
+			reparent_leader(father, p, dead);
 	}
+	list_splice_tail_init(&father->children, &reaper->children);
 }
 
 /*
@@ -600,18 +609,12 @@ static void forget_original_parent(struct task_struct *father)
 static void exit_notify(struct task_struct *tsk, int group_dead)
 {
 	bool autoreap;
-
-	/*
-	 * This does two things:
-	 *
-	 * A.  Make init inherit all the child processes
-	 * B.  Check to see if any process groups have become orphaned
-	 *	as a result of our exiting, and if they have any stopped
-	 *	jobs, send them a SIGHUP and then a SIGCONT.  (POSIX 3.2.2.2)
-	 */
-	forget_original_parent(tsk);
+	struct task_struct *p, *n;
+	LIST_HEAD(dead);
 
 	write_lock_irq(&tasklist_lock);
+	forget_original_parent(tsk, &dead);
+
 	if (group_dead)
 		kill_orphaned_pgrp(tsk->group_leader, NULL);
 
@@ -629,15 +632,18 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 	}
 
 	tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE;
+	if (tsk->exit_state == EXIT_DEAD)
+		list_add(&tsk->ptrace_entry, &dead);
 
 	/* mt-exec, de_thread() is waiting for group leader */
 	if (unlikely(tsk->signal->notify_count < 0))
 		wake_up_process(tsk->signal->group_exit_task);
 	write_unlock_irq(&tasklist_lock);
 
-	/* If the process is dead, release it - nobody will wait for it */
-	if (autoreap)
-		release_task(tsk);
+	list_for_each_entry_safe(p, n, &dead, ptrace_entry) {
+		list_del_init(&p->ptrace_entry);
+		release_task(p);
+	}
 }
 
 #ifdef CONFIG_DEBUG_STACK_USAGE
@@ -982,8 +988,7 @@ static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p,
  */
 static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 {
-	unsigned long state;
-	int retval, status, traced;
+	int state, retval, status;
 	pid_t pid = task_pid_vnr(p);
 	uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p));
 	struct siginfo __user *infop;
@@ -1008,21 +1013,25 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		}
 		return wait_noreap_copyout(wo, p, pid, uid, why, status);
 	}
-
-	traced = ptrace_reparented(p);
 	/*
 	 * Move the task's state to DEAD/TRACE, only one thread can do this.
 	 */
-	state = traced && thread_group_leader(p) ? EXIT_TRACE : EXIT_DEAD;
+	state = (ptrace_reparented(p) && thread_group_leader(p)) ?
+		EXIT_TRACE : EXIT_DEAD;
 	if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE)
 		return 0;
 	/*
-	 * It can be ptraced but not reparented, check
-	 * thread_group_leader() to filter out sub-threads.
+	 * We own this thread, nobody else can reap it.
 	 */
-	if (likely(!traced) && thread_group_leader(p)) {
-		struct signal_struct *psig;
-		struct signal_struct *sig;
+	read_unlock(&tasklist_lock);
+	sched_annotate_sleep();
+
+	/*
+	 * Check thread_group_leader() to exclude the traced sub-threads.
+	 */
+	if (state == EXIT_DEAD && thread_group_leader(p)) {
+		struct signal_struct *sig = p->signal;
+		struct signal_struct *psig = current->signal;
 		unsigned long maxrss;
 		cputime_t tgutime, tgstime;
 
@@ -1034,21 +1043,20 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * accumulate in the parent's signal_struct c* fields.
 		 *
 		 * We don't bother to take a lock here to protect these
-		 * p->signal fields, because they are only touched by
-		 * __exit_signal, which runs with tasklist_lock
-		 * write-locked anyway, and so is excluded here.  We do
-		 * need to protect the access to parent->signal fields,
-		 * as other threads in the parent group can be right
-		 * here reaping other children at the same time.
+		 * p->signal fields because the whole thread group is dead
+		 * and nobody can change them.
+		 *
+		 * psig->stats_lock also protects us from our sub-theads
+		 * which can reap other children at the same time. Until
+		 * we change k_getrusage()-like users to rely on this lock
+		 * we have to take ->siglock as well.
 		 *
 		 * We use thread_group_cputime_adjusted() to get times for
 		 * the thread group, which consolidates times for all threads
 		 * in the group including the group leader.
 		 */
 		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
-		spin_lock_irq(&p->real_parent->sighand->siglock);
-		psig = p->real_parent->signal;
-		sig = p->signal;
+		spin_lock_irq(&current->sighand->siglock);
 		write_seqlock(&psig->stats_lock);
 		psig->cutime += tgutime + sig->cutime;
 		psig->cstime += tgstime + sig->cstime;
@@ -1073,16 +1081,9 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		task_io_accounting_add(&psig->ioac, &p->ioac);
 		task_io_accounting_add(&psig->ioac, &sig->ioac);
 		write_sequnlock(&psig->stats_lock);
-		spin_unlock_irq(&p->real_parent->sighand->siglock);
+		spin_unlock_irq(&current->sighand->siglock);
 	}
 
-	/*
-	 * Now we are sure this task is interesting, and no other
-	 * thread can reap it because we its state == DEAD/TRACE.
-	 */
-	read_unlock(&tasklist_lock);
-	sched_annotate_sleep();
-
 	retval = wo->wo_rusage
 		? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
 	status = (p->signal->flags & SIGNAL_GROUP_EXIT)
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 80f7a6d00519..2777f40a9c7b 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -47,13 +47,6 @@ extern int max_threads;
 
 static struct workqueue_struct *khelper_wq;
 
-/*
- * kmod_thread_locker is used for deadlock avoidance.  There is no explicit
- * locking to protect this global - it is private to the singleton khelper
- * thread and should only ever be modified by that thread.
- */
-static const struct task_struct *kmod_thread_locker;
-
 #define CAP_BSET	(void *)1
 #define CAP_PI		(void *)2
 
@@ -223,7 +216,6 @@ static void umh_complete(struct subprocess_info *sub_info)
 static int ____call_usermodehelper(void *data)
 {
 	struct subprocess_info *sub_info = data;
-	int wait = sub_info->wait & ~UMH_KILLABLE;
 	struct cred *new;
 	int retval;
 
@@ -267,20 +259,13 @@ static int ____call_usermodehelper(void *data)
 out:
 	sub_info->retval = retval;
 	/* wait_for_helper() will call umh_complete if UHM_WAIT_PROC. */
-	if (wait != UMH_WAIT_PROC)
+	if (!(sub_info->wait & UMH_WAIT_PROC))
 		umh_complete(sub_info);
 	if (!retval)
 		return 0;
 	do_exit(0);
 }
 
-static int call_helper(void *data)
-{
-	/* Worker thread started blocking khelper thread. */
-	kmod_thread_locker = current;
-	return ____call_usermodehelper(data);
-}
-
 /* Keventd can't block, but this (a child) can. */
 static int wait_for_helper(void *data)
 {
@@ -323,21 +308,14 @@ static void __call_usermodehelper(struct work_struct *work)
 {
 	struct subprocess_info *sub_info =
 		container_of(work, struct subprocess_info, work);
-	int wait = sub_info->wait & ~UMH_KILLABLE;
 	pid_t pid;
 
-	/* CLONE_VFORK: wait until the usermode helper has execve'd
-	 * successfully We need the data structures to stay around
-	 * until that is done.  */
-	if (wait == UMH_WAIT_PROC)
+	if (sub_info->wait & UMH_WAIT_PROC)
 		pid = kernel_thread(wait_for_helper, sub_info,
 				    CLONE_FS | CLONE_FILES | SIGCHLD);
-	else {
-		pid = kernel_thread(call_helper, sub_info,
-				    CLONE_VFORK | SIGCHLD);
-		/* Worker thread stopped blocking khelper thread. */
-		kmod_thread_locker = NULL;
-	}
+	else
+		pid = kernel_thread(____call_usermodehelper, sub_info,
+				    SIGCHLD);
 
 	if (pid < 0) {
 		sub_info->retval = pid;
@@ -571,17 +549,6 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 		goto out;
 	}
 	/*
-	 * Worker thread must not wait for khelper thread at below
-	 * wait_for_completion() if the thread was created with CLONE_VFORK
-	 * flag, for khelper thread is already waiting for the thread at
-	 * wait_for_completion() in do_fork().
-	 */
-	if (wait != UMH_NO_WAIT && current == kmod_thread_locker) {
-		retval = -EBUSY;
-		goto out;
-	}
-
-	/*
 	 * Set the completion pointer only if there is a waiter.
 	 * This makes it possible to use umh_complete to free
 	 * the data structure in case of UMH_NO_WAIT.
diff --git a/kernel/panic.c b/kernel/panic.c
index cf80672b7924..4d8d6f906dec 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -33,6 +33,7 @@ static int pause_on_oops;
 static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
 static bool crash_kexec_post_notifiers;
+int panic_on_warn __read_mostly;
 
 int panic_timeout = CONFIG_PANIC_TIMEOUT;
 EXPORT_SYMBOL_GPL(panic_timeout);
@@ -428,6 +429,17 @@ static void warn_slowpath_common(const char *file, int line, void *caller,
 	if (args)
 		vprintk(args->fmt, args->args);
 
+	if (panic_on_warn) {
+		/*
+		 * This thread may hit another WARN() in the panic path.
+		 * Resetting this prevents additional WARN() from panicking the
+		 * system on this thread.  Other threads are blocked by the
+		 * panic_mutex in panic().
+		 */
+		panic_on_warn = 0;
+		panic("panic_on_warn set ...\n");
+	}
+
 	print_modules();
 	dump_stack();
 	print_oops_end_marker();
@@ -485,6 +497,7 @@ EXPORT_SYMBOL(__stack_chk_fail);
 
 core_param(panic, panic_timeout, int, 0644);
 core_param(pause_on_oops, pause_on_oops, int, 0644);
+core_param(panic_on_warn, panic_on_warn, int, 0644);
 
 static int __init setup_crash_kexec_post_notifiers(char *s)
 {
diff --git a/kernel/pid.c b/kernel/pid.c
index 9b9a26698144..82430c858d69 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -341,6 +341,8 @@ out:
 
 out_unlock:
 	spin_unlock_irq(&pidmap_lock);
+	put_pid_ns(ns);
+
 out_free:
 	while (++i <= ns->level)
 		free_pidmap(pid->numbers + i);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index db95d8eb761b..bc6d6a89b6e6 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -190,7 +190,11 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	/* Don't allow any more processes into the pid namespace */
 	disable_pid_allocation(pid_ns);
 
-	/* Ignore SIGCHLD causing any terminated children to autoreap */
+	/*
+	 * Ignore SIGCHLD causing any terminated children to autoreap.
+	 * This speeds up the namespace shutdown, plus see the comment
+	 * below.
+	 */
 	spin_lock_irq(&me->sighand->siglock);
 	me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN;
 	spin_unlock_irq(&me->sighand->siglock);
@@ -223,15 +227,31 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	}
 	read_unlock(&tasklist_lock);
 
-	/* Firstly reap the EXIT_ZOMBIE children we may have. */
+	/*
+	 * Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD.
+	 * sys_wait4() will also block until our children traced from the
+	 * parent namespace are detached and become EXIT_DEAD.
+	 */
 	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 free_pid().
+	 * sys_wait4() above can't reap the EXIT_DEAD children but we do not
+	 * really care, we could reparent them to the global init. We could
+	 * exit and reap ->child_reaper even if it is not the last thread in
+	 * this pid_ns, free_pid(nr_hashed == 0) calls proc_cleanup_work(),
+	 * pid_ns can not go away until proc_kill_sb() drops the reference.
+	 *
+	 * But this ns can also have other tasks injected by setns()+fork().
+	 * Again, ignoring the user visible semantics we do not really need
+	 * to wait until they are all reaped, but they can be reparented to
+	 * us and thus we need to ensure that pid->child_reaper stays valid
+	 * until they all go away. See free_pid()->wake_up_process().
+	 *
+	 * We rely on ignored SIGCHLD, an injected zombie must be autoreaped
+	 * if reparented.
 	 */
 	for (;;) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index c8755e7e1dba..ea27c019655a 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -62,9 +62,6 @@ int console_printk[4] = {
 	CONSOLE_LOGLEVEL_DEFAULT,	/* default_console_loglevel */
 };
 
-/* Deferred messaged from sched code are marked by this special level */
-#define SCHED_MESSAGE_LOGLEVEL -2
-
 /*
  * Low level drivers may need that to know if they can schedule in
  * their unblank() callback or not. So let's export it.
@@ -1259,7 +1256,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 int do_syslog(int type, char __user *buf, int len, bool from_file)
 {
 	bool clear = false;
-	static int saved_console_loglevel = -1;
+	static int saved_console_loglevel = LOGLEVEL_DEFAULT;
 	int error;
 
 	error = check_syslog_permissions(type, from_file);
@@ -1316,15 +1313,15 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 		break;
 	/* Disable logging to console */
 	case SYSLOG_ACTION_CONSOLE_OFF:
-		if (saved_console_loglevel == -1)
+		if (saved_console_loglevel == LOGLEVEL_DEFAULT)
 			saved_console_loglevel = console_loglevel;
 		console_loglevel = minimum_console_loglevel;
 		break;
 	/* Enable logging to console */
 	case SYSLOG_ACTION_CONSOLE_ON:
-		if (saved_console_loglevel != -1) {
+		if (saved_console_loglevel != LOGLEVEL_DEFAULT) {
 			console_loglevel = saved_console_loglevel;
-			saved_console_loglevel = -1;
+			saved_console_loglevel = LOGLEVEL_DEFAULT;
 		}
 		break;
 	/* Set level of messages printed to console */
@@ -1336,7 +1333,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 			len = minimum_console_loglevel;
 		console_loglevel = len;
 		/* Implicitly re-enable logging to console */
-		saved_console_loglevel = -1;
+		saved_console_loglevel = LOGLEVEL_DEFAULT;
 		error = 0;
 		break;
 	/* Number of chars in the log buffer */
@@ -1627,10 +1624,10 @@ asmlinkage int vprintk_emit(int facility, int level,
 	int printed_len = 0;
 	bool in_sched = false;
 	/* cpu currently holding logbuf_lock in this function */
-	static volatile unsigned int logbuf_cpu = UINT_MAX;
+	static unsigned int logbuf_cpu = UINT_MAX;
 
-	if (level == SCHED_MESSAGE_LOGLEVEL) {
-		level = -1;
+	if (level == LOGLEVEL_SCHED) {
+		level = LOGLEVEL_DEFAULT;
 		in_sched = true;
 	}
 
@@ -1695,8 +1692,9 @@ asmlinkage int vprintk_emit(int facility, int level,
 			const char *end_of_header = printk_skip_level(text);
 			switch (kern_level) {
 			case '0' ... '7':
-				if (level == -1)
+				if (level == LOGLEVEL_DEFAULT)
 					level = kern_level - '0';
+				/* fallthrough */
 			case 'd':	/* KERN_DEFAULT */
 				lflags |= LOG_PREFIX;
 			}
@@ -1710,7 +1708,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 		}
 	}
 
-	if (level == -1)
+	if (level == LOGLEVEL_DEFAULT)
 		level = default_message_loglevel;
 
 	if (dict)
@@ -1788,7 +1786,7 @@ EXPORT_SYMBOL(vprintk_emit);
 
 asmlinkage int vprintk(const char *fmt, va_list args)
 {
-	return vprintk_emit(0, -1, NULL, 0, fmt, args);
+	return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
 }
 EXPORT_SYMBOL(vprintk);
 
@@ -1842,7 +1840,7 @@ asmlinkage __visible int printk(const char *fmt, ...)
 	}
 #endif
 	va_start(args, fmt);
-	r = vprintk_emit(0, -1, NULL, 0, fmt, args);
+	r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
 	va_end(args);
 
 	return r;
@@ -1881,23 +1879,20 @@ static size_t cont_print_text(char *text, size_t size) { return 0; }
 #ifdef CONFIG_EARLY_PRINTK
 struct console *early_console;
 
-void early_vprintk(const char *fmt, va_list ap)
-{
-	if (early_console) {
-		char buf[512];
-		int n = vscnprintf(buf, sizeof(buf), fmt, ap);
-
-		early_console->write(early_console, buf, n);
-	}
-}
-
 asmlinkage __visible void early_printk(const char *fmt, ...)
 {
 	va_list ap;
+	char buf[512];
+	int n;
+
+	if (!early_console)
+		return;
 
 	va_start(ap, fmt);
-	early_vprintk(fmt, ap);
+	n = vscnprintf(buf, sizeof(buf), fmt, ap);
 	va_end(ap);
+
+	early_console->write(early_console, buf, n);
 }
 #endif
 
@@ -2634,7 +2629,7 @@ int printk_deferred(const char *fmt, ...)
 
 	preempt_disable();
 	va_start(args, fmt);
-	r = vprintk_emit(0, SCHED_MESSAGE_LOGLEVEL, NULL, 0, fmt, args);
+	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
 	va_end(args);
 
 	__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 54e75226c2c4..1eb9d90c3af9 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -485,36 +485,19 @@ static int ptrace_detach(struct task_struct *child, unsigned int data)
 
 /*
  * Detach all tasks we were using ptrace on. Called with tasklist held
- * for writing, and returns with it held too. But note it can release
- * and reacquire the lock.
+ * for writing.
  */
-void exit_ptrace(struct task_struct *tracer)
-	__releases(&tasklist_lock)
-	__acquires(&tasklist_lock)
+void exit_ptrace(struct task_struct *tracer, struct list_head *dead)
 {
 	struct task_struct *p, *n;
-	LIST_HEAD(ptrace_dead);
-
-	if (likely(list_empty(&tracer->ptraced)))
-		return;
 
 	list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) {
 		if (unlikely(p->ptrace & PT_EXITKILL))
 			send_sig_info(SIGKILL, SEND_SIG_FORCED, p);
 
 		if (__ptrace_detach(tracer, p))
-			list_add(&p->ptrace_entry, &ptrace_dead);
-	}
-
-	write_unlock_irq(&tasklist_lock);
-	BUG_ON(!list_empty(&tracer->ptraced));
-
-	list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_entry) {
-		list_del_init(&p->ptrace_entry);
-		release_task(p);
+			list_add(&p->ptrace_entry, dead);
 	}
-
-	write_lock_irq(&tasklist_lock);
 }
 
 int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len)
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
deleted file mode 100644
index e791130f85a7..000000000000
--- a/kernel/res_counter.c
+++ /dev/null
@@ -1,211 +0,0 @@
-/*
- * resource cgroups
- *
- * Copyright 2007 OpenVZ SWsoft Inc
- *
- * Author: Pavel Emelianov <xemul@openvz.org>
- *
- */
-
-#include <linux/types.h>
-#include <linux/parser.h>
-#include <linux/fs.h>
-#include <linux/res_counter.h>
-#include <linux/uaccess.h>
-#include <linux/mm.h>
-
-void res_counter_init(struct res_counter *counter, struct res_counter *parent)
-{
-	spin_lock_init(&counter->lock);
-	counter->limit = RES_COUNTER_MAX;
-	counter->soft_limit = RES_COUNTER_MAX;
-	counter->parent = parent;
-}
-
-static u64 res_counter_uncharge_locked(struct res_counter *counter,
-				       unsigned long val)
-{
-	if (WARN_ON(counter->usage < val))
-		val = counter->usage;
-
-	counter->usage -= val;
-	return counter->usage;
-}
-
-static int res_counter_charge_locked(struct res_counter *counter,
-				     unsigned long val, bool force)
-{
-	int ret = 0;
-
-	if (counter->usage + val > counter->limit) {
-		counter->failcnt++;
-		ret = -ENOMEM;
-		if (!force)
-			return ret;
-	}
-
-	counter->usage += val;
-	if (counter->usage > counter->max_usage)
-		counter->max_usage = counter->usage;
-	return ret;
-}
-
-static int __res_counter_charge(struct res_counter *counter, unsigned long val,
-				struct res_counter **limit_fail_at, bool force)
-{
-	int ret, r;
-	unsigned long flags;
-	struct res_counter *c, *u;
-
-	r = ret = 0;
-	*limit_fail_at = NULL;
-	local_irq_save(flags);
-	for (c = counter; c != NULL; c = c->parent) {
-		spin_lock(&c->lock);
-		r = res_counter_charge_locked(c, val, force);
-		spin_unlock(&c->lock);
-		if (r < 0 && !ret) {
-			ret = r;
-			*limit_fail_at = c;
-			if (!force)
-				break;
-		}
-	}
-
-	if (ret < 0 && !force) {
-		for (u = counter; u != c; u = u->parent) {
-			spin_lock(&u->lock);
-			res_counter_uncharge_locked(u, val);
-			spin_unlock(&u->lock);
-		}
-	}
-	local_irq_restore(flags);
-
-	return ret;
-}
-
-int res_counter_charge(struct res_counter *counter, unsigned long val,
-			struct res_counter **limit_fail_at)
-{
-	return __res_counter_charge(counter, val, limit_fail_at, false);
-}
-
-int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
-			      struct res_counter **limit_fail_at)
-{
-	return __res_counter_charge(counter, val, limit_fail_at, true);
-}
-
-u64 res_counter_uncharge_until(struct res_counter *counter,
-			       struct res_counter *top,
-			       unsigned long val)
-{
-	unsigned long flags;
-	struct res_counter *c;
-	u64 ret = 0;
-
-	local_irq_save(flags);
-	for (c = counter; c != top; c = c->parent) {
-		u64 r;
-		spin_lock(&c->lock);
-		r = res_counter_uncharge_locked(c, val);
-		if (c == counter)
-			ret = r;
-		spin_unlock(&c->lock);
-	}
-	local_irq_restore(flags);
-	return ret;
-}
-
-u64 res_counter_uncharge(struct res_counter *counter, unsigned long val)
-{
-	return res_counter_uncharge_until(counter, NULL, val);
-}
-
-static inline unsigned long long *
-res_counter_member(struct res_counter *counter, int member)
-{
-	switch (member) {
-	case RES_USAGE:
-		return &counter->usage;
-	case RES_MAX_USAGE:
-		return &counter->max_usage;
-	case RES_LIMIT:
-		return &counter->limit;
-	case RES_FAILCNT:
-		return &counter->failcnt;
-	case RES_SOFT_LIMIT:
-		return &counter->soft_limit;
-	};
-
-	BUG();
-	return NULL;
-}
-
-ssize_t res_counter_read(struct res_counter *counter, int member,
-		const char __user *userbuf, size_t nbytes, loff_t *pos,
-		int (*read_strategy)(unsigned long long val, char *st_buf))
-{
-	unsigned long long *val;
-	char buf[64], *s;
-
-	s = buf;
-	val = res_counter_member(counter, member);
-	if (read_strategy)
-		s += read_strategy(*val, s);
-	else
-		s += sprintf(s, "%llu\n", *val);
-	return simple_read_from_buffer((void __user *)userbuf, nbytes,
-			pos, buf, s - buf);
-}
-
-#if BITS_PER_LONG == 32
-u64 res_counter_read_u64(struct res_counter *counter, int member)
-{
-	unsigned long flags;
-	u64 ret;
-
-	spin_lock_irqsave(&counter->lock, flags);
-	ret = *res_counter_member(counter, member);
-	spin_unlock_irqrestore(&counter->lock, flags);
-
-	return ret;
-}
-#else
-u64 res_counter_read_u64(struct res_counter *counter, int member)
-{
-	return *res_counter_member(counter, member);
-}
-#endif
-
-int res_counter_memparse_write_strategy(const char *buf,
-					unsigned long long *resp)
-{
-	char *end;
-	unsigned long long res;
-
-	/* return RES_COUNTER_MAX(unlimited) if "-1" is specified */
-	if (*buf == '-') {
-		int rc = kstrtoull(buf + 1, 10, &res);
-
-		if (rc)
-			return rc;
-		if (res != 1)
-			return -EINVAL;
-		*resp = RES_COUNTER_MAX;
-		return 0;
-	}
-
-	res = memparse(buf, &end);
-	if (*end != '\0')
-		return -EINVAL;
-
-	if (PAGE_ALIGN(res) >= res)
-		res = PAGE_ALIGN(res);
-	else
-		res = RES_COUNTER_MAX;
-
-	*resp = res;
-
-	return 0;
-}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bb398c0c5f08..b5797b78add6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4527,8 +4527,10 @@ void sched_show_task(struct task_struct *p)
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	free = stack_not_used(p);
 #endif
+	ppid = 0;
 	rcu_read_lock();
-	ppid = task_pid_nr(rcu_dereference(p->real_parent));
+	if (pid_alive(p))
+		ppid = task_pid_nr(rcu_dereference(p->real_parent));
 	rcu_read_unlock();
 	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
 		task_pid_nr(p), ppid,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 15f2511a1b7c..7c54ff79afd7 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1104,6 +1104,15 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
+	{
+		.procname	= "panic_on_warn",
+		.data		= &panic_on_warn,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{ }
 };
 
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 9a4f750a2963..7e7746a42a62 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -137,6 +137,7 @@ static const struct bin_table bin_kern_table[] = {
 	{ CTL_INT,	KERN_COMPAT_LOG,		"compat-log" },
 	{ CTL_INT,	KERN_MAX_LOCK_DEPTH,		"max_lock_depth" },
 	{ CTL_INT,	KERN_PANIC_ON_NMI,		"panic_on_unrecovered_nmi" },
+	{ CTL_INT,	KERN_PANIC_ON_WARN,		"panic_on_warn" },
 	{}
 };