1 files changed, 478 insertions, 226 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 727150f28103..3485e5fc499e 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -25,7 +25,6 @@
 #include <linux/acct.h>
 #include <linux/tsacct_kern.h>
 #include <linux/file.h>
-#include <linux/fdtable.h>
 #include <linux/freezer.h>
 #include <linux/binfmts.h>
 #include <linux/nsproxy.h>
@@ -48,9 +47,9 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/audit.h> /* for audit_free() */
 #include <linux/resource.h>
-#include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
-#include <linux/tracehook.h>
+#include <linux/blkdev.h>
+#include <linux/task_work.h>
 #include <linux/fs_struct.h>
 #include <linux/init_task.h>
 #include <linux/perf_event.h>
@@ -60,14 +59,69 @@
 #include <linux/writeback.h>
 #include <linux/shm.h>
 #include <linux/kcov.h>
+#include <linux/kmsan.h>
 #include <linux/random.h>
 #include <linux/rcuwait.h>
 #include <linux/compat.h>
-
+#include <linux/io_uring.h>
+#include <linux/kprobes.h>
+#include <linux/rethook.h>
+#include <linux/sysfs.h>
+#include <linux/user_events.h>
 #include <linux/uaccess.h>
+
+#include <uapi/linux/wait.h>
+
 #include <asm/unistd.h>
 #include <asm/mmu_context.h>
 
+#include "exit.h"
+
+/*
+ * The default value should be high enough to not crash a system that randomly
+ * crashes its kernel from time to time, but low enough to at least not permit
+ * overflowing 32-bit refcounts or the ldsem writer count.
+ */
+static unsigned int oops_limit = 10000;
+
+#ifdef CONFIG_SYSCTL
+static const struct ctl_table kern_exit_table[] = {
+	{
+		.procname       = "oops_limit",
+		.data           = &oops_limit,
+		.maxlen         = sizeof(oops_limit),
+		.mode           = 0644,
+		.proc_handler   = proc_douintvec,
+	},
+};
+
+static __init int kernel_exit_sysctls_init(void)
+{
+	register_sysctl_init("kernel", kern_exit_table);
+	return 0;
+}
+late_initcall(kernel_exit_sysctls_init);
+#endif
+
+static atomic_t oops_count = ATOMIC_INIT(0);
+
+#ifdef CONFIG_SYSFS
+static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr,
+			       char *page)
+{
+	return sysfs_emit(page, "%d\n", atomic_read(&oops_count));
+}
+
+static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count);
+
+static __init int kernel_exit_sysfs_init(void)
+{
+	sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL);
+	return 0;
+}
+late_initcall(kernel_exit_sysfs_init);
+#endif
+
 static void __unhash_process(struct task_struct *p, bool group_dead)
 {
 	nr_threads--;
@@ -81,7 +135,6 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
 		list_del_init(&p->sibling);
 		__this_cpu_dec(process_counts);
 	}
-	list_del_rcu(&p->thread_group);
 	list_del_rcu(&p->thread_node);
 }
 
@@ -93,7 +146,7 @@ static void __exit_signal(struct task_struct *tsk)
 	struct signal_struct *sig = tsk->signal;
 	bool group_dead = thread_group_leader(tsk);
 	struct sighand_struct *sighand;
-	struct tty_struct *uninitialized_var(tty);
+	struct tty_struct *tty;
 	u64 utime, stime;
 
 	sighand = rcu_dereference_check(tsk->sighand,
@@ -115,7 +168,7 @@ static void __exit_signal(struct task_struct *tsk)
 		 * then notify it:
 		 */
 		if (sig->notify_count > 0 && !--sig->notify_count)
-			wake_up_process(sig->group_exit_task);
+			wake_up_process(sig->group_exec_task);
 
 		if (tsk == sig->curr_target)
 			sig->curr_target = next_thread(tsk);
@@ -167,6 +220,8 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
 
+	kprobe_flush_task(tsk);
+	rethook_flush_task(tsk);
 	perf_event_delayed_put(tsk);
 	trace_sched_process_free(tsk);
 	put_task_struct(tsk);
@@ -178,6 +233,10 @@ void put_task_struct_rcu_user(struct task_struct *task)
 		call_rcu(&task->rcu, delayed_put_task_struct);
 }
 
+void __weak release_thread(struct task_struct *dead_task)
+{
+}
+
 void release_task(struct task_struct *p)
 {
 	struct task_struct *leader;
@@ -187,7 +246,7 @@ repeat:
 	/* don't need to get the RCU readlock here - the process is dead and
 	 * can't be modifying its own credentials. But shut RCU-lockdep up */
 	rcu_read_lock();
-	atomic_dec(&__task_cred(p)->user->processes);
+	dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
 	rcu_read_unlock();
 
 	cgroup_release(p);
@@ -337,15 +396,87 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
 	}
 }
 
+static void coredump_task_exit(struct task_struct *tsk)
+{
+	struct core_state *core_state;
+
+	/*
+	 * Serialize with any possible pending coredump.
+	 * We must hold siglock around checking core_state
+	 * and setting PF_POSTCOREDUMP.  The core-inducing thread
+	 * will increment ->nr_threads for each thread in the
+	 * group without PF_POSTCOREDUMP set.
+	 */
+	spin_lock_irq(&tsk->sighand->siglock);
+	tsk->flags |= PF_POSTCOREDUMP;
+	core_state = tsk->signal->core_state;
+	spin_unlock_irq(&tsk->sighand->siglock);
+	if (core_state) {
+		struct core_thread self;
+
+		self.task = current;
+		if (self.task->flags & PF_SIGNALED)
+			self.next = xchg(&core_state->dumper.next, &self);
+		else
+			self.task = NULL;
+		/*
+		 * Implies mb(), the result of xchg() must be visible
+		 * to core_state->dumper.
+		 */
+		if (atomic_dec_and_test(&core_state->nr_threads))
+			complete(&core_state->startup);
+
+		for (;;) {
+			set_current_state(TASK_IDLE|TASK_FREEZABLE);
+			if (!self.task) /* see coredump_finish() */
+				break;
+			schedule();
+		}
+		__set_current_state(TASK_RUNNING);
+	}
+}
+
 #ifdef CONFIG_MEMCG
+/* drops tasklist_lock if succeeds */
+static bool __try_to_set_owner(struct task_struct *tsk, struct mm_struct *mm)
+{
+	bool ret = false;
+
+	task_lock(tsk);
+	if (likely(tsk->mm == mm)) {
+		/* tsk can't pass exit_mm/exec_mmap and exit */
+		read_unlock(&tasklist_lock);
+		WRITE_ONCE(mm->owner, tsk);
+		lru_gen_migrate_mm(mm);
+		ret = true;
+	}
+	task_unlock(tsk);
+	return ret;
+}
+
+static bool try_to_set_owner(struct task_struct *g, struct mm_struct *mm)
+{
+	struct task_struct *t;
+
+	for_each_thread(g, t) {
+		struct mm_struct *t_mm = READ_ONCE(t->mm);
+		if (t_mm == mm) {
+			if (__try_to_set_owner(t, mm))
+				return true;
+		} else if (t_mm)
+			break;
+	}
+
+	return false;
+}
+
 /*
  * A task is exiting.   If it owned this mm, find a new owner for the mm.
  */
 void mm_update_next_owner(struct mm_struct *mm)
 {
-	struct task_struct *c, *g, *p = current;
+	struct task_struct *g, *p = current;
 
-retry:
 	/*
 	 * If the exiting or execing task is not the owner, it's
 	 * someone else's problem.
@@ -366,31 +497,27 @@ retry:
 	/*
 	 * Search in the children
 	 */
-	list_for_each_entry(c, &p->children, sibling) {
-		if (c->mm == mm)
-			goto assign_new_owner;
+	list_for_each_entry(g, &p->children, sibling) {
+		if (try_to_set_owner(g, mm))
+			goto ret;
 	}
-
 	/*
 	 * Search in the siblings
 	 */
-	list_for_each_entry(c, &p->real_parent->children, sibling) {
-		if (c->mm == mm)
-			goto assign_new_owner;
+	list_for_each_entry(g, &p->real_parent->children, sibling) {
+		if (try_to_set_owner(g, mm))
+			goto ret;
 	}
-
 	/*
 	 * Search through everything else, we should not get here often.
 	 */
 	for_each_process(g) {
+		if (atomic_read(&mm->mm_users) <= 1)
+			break;
 		if (g->flags & PF_KTHREAD)
 			continue;
-		for_each_thread(g, c) {
-			if (c->mm == mm)
-				goto assign_new_owner;
-			if (c->mm)
-				break;
-		}
+		if (try_to_set_owner(g, mm))
+			goto ret;
 	}
 	read_unlock(&tasklist_lock);
 	/*
@@ -399,29 +526,9 @@ retry:
 	 * ptrace or page migration (get_task_mm()).  Mark owner as NULL.
 	 */
 	WRITE_ONCE(mm->owner, NULL);
+ ret:
 	return;
 
-assign_new_owner:
-	BUG_ON(c == p);
-	get_task_struct(c);
-	/*
-	 * The task_lock protects c->mm from changing.
-	 * We always want mm->owner->mm == mm
-	 */
-	task_lock(c);
-	/*
-	 * Delay read_unlock() till we have the task_lock()
-	 * to ensure that c does not slip away underneath us
-	 */
-	read_unlock(&tasklist_lock);
-	if (c->mm != mm) {
-		task_unlock(c);
-		put_task_struct(c);
-		goto retry;
-	}
-	WRITE_ONCE(mm->owner, c);
-	task_unlock(c);
-	put_task_struct(c);
 }
 #endif /* CONFIG_MEMCG */
 
@@ -432,52 +539,33 @@ assign_new_owner:
 static void exit_mm(void)
 {
 	struct mm_struct *mm = current->mm;
-	struct core_state *core_state;
 
 	exit_mm_release(current, mm);
 	if (!mm)
 		return;
-	sync_mm_rss(mm);
-	/*
-	 * Serialize with any possible pending coredump.
-	 * We must hold mmap_lock around checking core_state
-	 * and clearing tsk->mm.  The core-inducing thread
-	 * will increment ->nr_threads for each thread in the
-	 * group with ->mm != NULL.
-	 */
 	mmap_read_lock(mm);
-	core_state = mm->core_state;
-	if (core_state) {
-		struct core_thread self;
-
-		mmap_read_unlock(mm);
-
-		self.task = current;
-		self.next = xchg(&core_state->dumper.next, &self);
-		/*
-		 * Implies mb(), the result of xchg() must be visible
-		 * to core_state->dumper.
-		 */
-		if (atomic_dec_and_test(&core_state->nr_threads))
-			complete(&core_state->startup);
-
-		for (;;) {
-			set_current_state(TASK_UNINTERRUPTIBLE);
-			if (!self.task) /* see coredump_finish() */
-				break;
-			freezable_schedule();
-		}
-		__set_current_state(TASK_RUNNING);
-		mmap_read_lock(mm);
-	}
-	mmgrab(mm);
+	mmgrab_lazy_tlb(mm);
 	BUG_ON(mm != current->active_mm);
 	/* more a memory barrier than a real lock */
 	task_lock(current);
+	/*
+	 * When a thread stops operating on an address space, the loop
+	 * in membarrier_private_expedited() may not observe that
+	 * tsk->mm, and the loop in membarrier_global_expedited() may
+	 * not observe a MEMBARRIER_STATE_GLOBAL_EXPEDITED
+	 * rq->membarrier_state, so those would not issue an IPI.
+	 * Membarrier requires a memory barrier after accessing
+	 * user-space memory, before clearing tsk->mm or the
+	 * rq->membarrier_state.
+	 */
+	smp_mb__after_spinlock();
+	local_irq_disable();
 	current->mm = NULL;
-	mmap_read_unlock(mm);
+	membarrier_update_current_mm(NULL);
 	enter_lazy_tlb(mm, current);
+	local_irq_enable();
 	task_unlock(current);
+	mmap_read_unlock(mm);
 	mm_update_next_owner(mm);
 	mmput(mm);
 	if (test_thread_flag(TIF_MEMDIE))
@@ -652,6 +740,13 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 		kill_orphaned_pgrp(tsk->group_leader, NULL);
 
 	tsk->exit_state = EXIT_ZOMBIE;
+	/*
+	 * sub-thread or delay_group_leader(), wake up the
+	 * PIDFD_THREAD waiters.
+	 */
+	if (!thread_group_empty(tsk))
+		do_notify_pidfd(tsk);
+
 	if (unlikely(tsk->ptrace)) {
 		int sig = thread_group_leader(tsk) &&
 				thread_group_empty(tsk) &&
@@ -672,7 +767,7 @@ static void exit_notify(struct task_struct *tsk, int group_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);
+		wake_up_process(tsk->signal->group_exec_task);
 	write_unlock_irq(&tasklist_lock);
 
 	list_for_each_entry_safe(p, n, &dead, ptrace_entry) {
@@ -682,6 +777,62 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 }
 
 #ifdef CONFIG_DEBUG_STACK_USAGE
+unsigned long stack_not_used(struct task_struct *p)
+{
+	unsigned long *n = end_of_stack(p);
+
+	do {	/* Skip over canary */
+# ifdef CONFIG_STACK_GROWSUP
+		n--;
+# else
+		n++;
+# endif
+	} while (!*n);
+
+# ifdef CONFIG_STACK_GROWSUP
+	return (unsigned long)end_of_stack(p) - (unsigned long)n;
+# else
+	return (unsigned long)n - (unsigned long)end_of_stack(p);
+# endif
+}
+
+/* Count the maximum pages reached in kernel stacks */
+static inline void kstack_histogram(unsigned long used_stack)
+{
+#ifdef CONFIG_VM_EVENT_COUNTERS
+	if (used_stack <= 1024)
+		count_vm_event(KSTACK_1K);
+#if THREAD_SIZE > 1024
+	else if (used_stack <= 2048)
+		count_vm_event(KSTACK_2K);
+#endif
+#if THREAD_SIZE > 2048
+	else if (used_stack <= 4096)
+		count_vm_event(KSTACK_4K);
+#endif
+#if THREAD_SIZE > 4096
+	else if (used_stack <= 8192)
+		count_vm_event(KSTACK_8K);
+#endif
+#if THREAD_SIZE > 8192
+	else if (used_stack <= 16384)
+		count_vm_event(KSTACK_16K);
+#endif
+#if THREAD_SIZE > 16384
+	else if (used_stack <= 32768)
+		count_vm_event(KSTACK_32K);
+#endif
+#if THREAD_SIZE > 32768
+	else if (used_stack <= 65536)
+		count_vm_event(KSTACK_64K);
+#endif
+#if THREAD_SIZE > 65536
+	else
+		count_vm_event(KSTACK_REST);
+#endif
+#endif /* CONFIG_VM_EVENT_COUNTERS */
+}
+
 static void check_stack_usage(void)
 {
 	static DEFINE_SPINLOCK(low_water_lock);
@@ -689,6 +840,7 @@ static void check_stack_usage(void)
 	unsigned long free;
 
 	free = stack_not_used(current);
+	kstack_histogram(THREAD_SIZE - free);
 
 	if (free >= lowest_to_date)
 		return;
@@ -705,64 +857,45 @@ static void check_stack_usage(void)
 static inline void check_stack_usage(void) {}
 #endif
 
+static void synchronize_group_exit(struct task_struct *tsk, long code)
+{
+	struct sighand_struct *sighand = tsk->sighand;
+	struct signal_struct *signal = tsk->signal;
+
+	spin_lock_irq(&sighand->siglock);
+	signal->quick_threads--;
+	if ((signal->quick_threads == 0) &&
+	    !(signal->flags & SIGNAL_GROUP_EXIT)) {
+		signal->flags = SIGNAL_GROUP_EXIT;
+		signal->group_exit_code = code;
+		signal->group_stop_count = 0;
+	}
+	spin_unlock_irq(&sighand->siglock);
+}
+
 void __noreturn do_exit(long code)
 {
 	struct task_struct *tsk = current;
 	int group_dead;
 
-	/*
-	 * We can get here from a kernel oops, sometimes with preemption off.
-	 * Start by checking for critical errors.
-	 * Then fix up important state like USER_DS and preemption.
-	 * Then do everything else.
-	 */
-
-	WARN_ON(blk_needs_flush_plug(tsk));
-
-	if (unlikely(in_interrupt()))
-		panic("Aiee, killing interrupt handler!");
-	if (unlikely(!tsk->pid))
-		panic("Attempted to kill the idle task!");
+	WARN_ON(irqs_disabled());
 
-	/*
-	 * If do_exit is called because this processes oopsed, it's possible
-	 * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before
-	 * continuing. Amongst other possible reasons, this is to prevent
-	 * mm_release()->clear_child_tid() from writing to a user-controlled
-	 * kernel address.
-	 */
-	set_fs(USER_DS);
+	synchronize_group_exit(tsk, code);
 
-	if (unlikely(in_atomic())) {
-		pr_info("note: %s[%d] exited with preempt_count %d\n",
-			current->comm, task_pid_nr(current),
-			preempt_count());
-		preempt_count_set(PREEMPT_ENABLED);
-	}
+	WARN_ON(tsk->plug);
 
-	profile_task_exit(tsk);
 	kcov_task_exit(tsk);
+	kmsan_task_exit(tsk);
 
+	coredump_task_exit(tsk);
 	ptrace_event(PTRACE_EVENT_EXIT, code);
+	user_events_exit(tsk);
 
-	validate_creds_for_do_exit(tsk);
-
-	/*
-	 * We're taking recursive faults here in do_exit. Safest is to just
-	 * leave this task alone and wait for reboot.
-	 */
-	if (unlikely(tsk->flags & PF_EXITING)) {
-		pr_alert("Fixing recursive fault but reboot is needed!\n");
-		futex_exit_recursive(tsk);
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		schedule();
-	}
-
+	io_uring_files_cancel();
 	exit_signals(tsk);  /* sets PF_EXITING */
 
-	/* sync mm's RSS info before statistics gathering */
-	if (tsk->mm)
-		sync_mm_rss(tsk->mm);
+	seccomp_filter_release(tsk);
+
 	acct_update_integrals(tsk);
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
@@ -776,7 +909,7 @@ void __noreturn do_exit(long code)
 
 #ifdef CONFIG_POSIX_TIMERS
 		hrtimer_cancel(&tsk->signal->real_timer);
-		exit_itimers(tsk->signal);
+		exit_itimers(tsk);
 #endif
 		if (tsk->mm)
 			setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
@@ -804,7 +937,6 @@ void __noreturn do_exit(long code)
 	exit_task_namespaces(tsk);
 	exit_task_work(tsk);
 	exit_thread(tsk);
-	exit_umh(tsk);
 
 	/*
 	 * Flush inherited counters to the parent - before the parent
@@ -844,7 +976,7 @@ void __noreturn do_exit(long code)
 	if (tsk->task_frag.page)
 		put_page(tsk->task_frag.page);
 
-	validate_creds_for_do_exit(tsk);
+	exit_task_stack_account(tsk);
 
 	check_stack_usage();
 	preempt_disable();
@@ -856,16 +988,66 @@ void __noreturn do_exit(long code)
 	lockdep_free_task(tsk);
 	do_task_dead();
 }
-EXPORT_SYMBOL_GPL(do_exit);
 
-void complete_and_exit(struct completion *comp, long code)
+void __noreturn make_task_dead(int signr)
 {
-	if (comp)
-		complete(comp);
+	/*
+	 * Take the task off the cpu after something catastrophic has
+	 * happened.
+	 *
+	 * We can get here from a kernel oops, sometimes with preemption off.
+	 * Start by checking for critical errors.
+	 * Then fix up important state like USER_DS and preemption.
+	 * Then do everything else.
+	 */
+	struct task_struct *tsk = current;
+	unsigned int limit;
+
+	if (unlikely(in_interrupt()))
+		panic("Aiee, killing interrupt handler!");
+	if (unlikely(!tsk->pid))
+		panic("Attempted to kill the idle task!");
 
-	do_exit(code);
+	if (unlikely(irqs_disabled())) {
+		pr_info("note: %s[%d] exited with irqs disabled\n",
+			current->comm, task_pid_nr(current));
+		local_irq_enable();
+	}
+	if (unlikely(in_atomic())) {
+		pr_info("note: %s[%d] exited with preempt_count %d\n",
+			current->comm, task_pid_nr(current),
+			preempt_count());
+		preempt_count_set(PREEMPT_ENABLED);
+	}
+
+	/*
+	 * Every time the system oopses, if the oops happens while a reference
+	 * to an object was held, the reference leaks.
+	 * If the oops doesn't also leak memory, repeated oopsing can cause
+	 * reference counters to wrap around (if they're not using refcount_t).
+	 * This means that repeated oopsing can make unexploitable-looking bugs
+	 * exploitable through repeated oopsing.
+	 * To make sure this can't happen, place an upper bound on how often the
+	 * kernel may oops without panic().
+	 */
+	limit = READ_ONCE(oops_limit);
+	if (atomic_inc_return(&oops_count) >= limit && limit)
+		panic("Oopsed too often (kernel.oops_limit is %d)", limit);
+
+	/*
+	 * We're taking recursive faults here in make_task_dead. Safest is to just
+	 * leave this task alone and wait for reboot.
+	 */
+	if (unlikely(tsk->flags & PF_EXITING)) {
+		pr_alert("Fixing recursive fault but reboot is needed!\n");
+		futex_exit_recursive(tsk);
+		tsk->exit_state = EXIT_DEAD;
+		refcount_inc(&tsk->rcu_users);
+		do_task_dead();
+	}
+
+	do_exit(signr);
 }
-EXPORT_SYMBOL(complete_and_exit);
 
 SYSCALL_DEFINE1(exit, int, error_code)
 {
@@ -876,22 +1058,24 @@ SYSCALL_DEFINE1(exit, int, error_code)
  * Take down every thread in the group.  This is called by fatal signals
  * as well as by sys_exit_group (below).
  */
-void
+void __noreturn
 do_group_exit(int exit_code)
 {
 	struct signal_struct *sig = current->signal;
 
-	BUG_ON(exit_code & 0x80); /* core dumps don't get here */
-
-	if (signal_group_exit(sig))
+	if (sig->flags & SIGNAL_GROUP_EXIT)
 		exit_code = sig->group_exit_code;
-	else if (!thread_group_empty(current)) {
+	else if (sig->group_exec_task)
+		exit_code = 0;
+	else {
 		struct sighand_struct *const sighand = current->sighand;
 
 		spin_lock_irq(&sighand->siglock);
-		if (signal_group_exit(sig))
+		if (sig->flags & SIGNAL_GROUP_EXIT)
 			/* Another thread got here before we took the lock.  */
 			exit_code = sig->group_exit_code;
+		else if (sig->group_exec_task)
+			exit_code = 0;
 		else {
 			sig->group_exit_code = exit_code;
 			sig->flags = SIGNAL_GROUP_EXIT;
@@ -916,26 +1100,6 @@ SYSCALL_DEFINE1(exit_group, int, error_code)
 	return 0;
 }
 
-struct waitid_info {
-	pid_t pid;
-	uid_t uid;
-	int status;
-	int cause;
-};
-
-struct wait_opts {
-	enum pid_type		wo_type;
-	int			wo_flags;
-	struct pid		*wo_pid;
-
-	struct waitid_info	*wo_info;
-	int			wo_stat;
-	struct rusage		*wo_rusage;
-
-	wait_queue_entry_t		child_wait;
-	int			notask_error;
-};
-
 static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
 {
 	return	wo->wo_type == PIDTYPE_MAX ||
@@ -986,7 +1150,8 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		return 0;
 
 	if (unlikely(wo->wo_flags & WNOWAIT)) {
-		status = p->exit_code;
+		status = (p->signal->flags & SIGNAL_GROUP_EXIT)
+			? p->signal->group_exit_code : p->exit_code;
 		get_task_struct(p);
 		read_unlock(&tasklist_lock);
 		sched_annotate_sleep();
@@ -1028,18 +1193,15 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * 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.
+		 * psig->stats_lock also protects us from our sub-threads
+		 * which can reap other children at the same time.
 		 *
 		 * 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(&current->sighand->siglock);
-		write_seqlock(&psig->stats_lock);
+		write_seqlock_irq(&psig->stats_lock);
 		psig->cutime += tgutime + sig->cutime;
 		psig->cstime += tgstime + sig->cstime;
 		psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime;
@@ -1062,8 +1224,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 			psig->cmaxrss = maxrss;
 		task_io_accounting_add(&psig->ioac, &p->ioac);
 		task_io_accounting_add(&psig->ioac, &sig->ioac);
-		write_sequnlock(&psig->stats_lock);
-		spin_unlock_irq(&current->sighand->siglock);
+		write_sequnlock_irq(&psig->stats_lock);
 	}
 
 	if (wo->wo_rusage)
@@ -1398,6 +1559,17 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
 	return 0;
 }
 
+bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p)
+{
+	if (!eligible_pid(wo, p))
+		return false;
+
+	if ((wo->wo_flags & __WNOTHREAD) && wo->child_wait.private != p->parent)
+		return false;
+
+	return true;
+}
+
 static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
 				int sync, void *key)
 {
@@ -1405,13 +1577,10 @@ static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
 						child_wait);
 	struct task_struct *p = key;
 
-	if (!eligible_pid(wo, p))
-		return 0;
-
-	if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
-		return 0;
+	if (pid_child_should_wake(wo, p))
+		return default_wake_function(wait, mode, sync, key);
 
-	return default_wake_function(wait, mode, sync, key);
+	return 0;
 }
 
 void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
@@ -1420,17 +1589,50 @@ void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
 			   TASK_INTERRUPTIBLE, p);
 }
 
-static long do_wait(struct wait_opts *wo)
+static bool is_effectively_child(struct wait_opts *wo, bool ptrace,
+				 struct task_struct *target)
 {
-	struct task_struct *tsk;
+	struct task_struct *parent =
+		!ptrace ? target->real_parent : target->parent;
+
+	return current == parent || (!(wo->wo_flags & __WNOTHREAD) &&
+				     same_thread_group(current, parent));
+}
+
+/*
+ * Optimization for waiting on PIDTYPE_PID. No need to iterate through child
+ * and tracee lists to find the target task.
+ */
+static int do_wait_pid(struct wait_opts *wo)
+{
+	bool ptrace;
+	struct task_struct *target;
 	int retval;
 
-	trace_sched_process_wait(wo->wo_pid);
+	ptrace = false;
+	target = pid_task(wo->wo_pid, PIDTYPE_TGID);
+	if (target && is_effectively_child(wo, ptrace, target)) {
+		retval = wait_consider_task(wo, ptrace, target);
+		if (retval)
+			return retval;
+	}
+
+	ptrace = true;
+	target = pid_task(wo->wo_pid, PIDTYPE_PID);
+	if (target && target->ptrace &&
+	    is_effectively_child(wo, ptrace, target)) {
+		retval = wait_consider_task(wo, ptrace, target);
+		if (retval)
+			return retval;
+	}
+
+	return 0;
+}
+
+long __do_wait(struct wait_opts *wo)
+{
+	long retval;
 
-	init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
-	wo->child_wait.private = current;
-	add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
-repeat:
 	/*
 	 * If there is nothing that can match our criteria, just get out.
 	 * We will clear ->notask_error to zero if we see any child that
@@ -1442,62 +1644,70 @@ repeat:
 	   (!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type)))
 		goto notask;
 
-	set_current_state(TASK_INTERRUPTIBLE);
 	read_lock(&tasklist_lock);
-	tsk = current;
-	do {
-		retval = do_wait_thread(wo, tsk);
-		if (retval)
-			goto end;
 
-		retval = ptrace_do_wait(wo, tsk);
+	if (wo->wo_type == PIDTYPE_PID) {
+		retval = do_wait_pid(wo);
 		if (retval)
-			goto end;
+			return retval;
+	} else {
+		struct task_struct *tsk = current;
 
-		if (wo->wo_flags & __WNOTHREAD)
-			break;
-	} while_each_thread(current, tsk);
+		do {
+			retval = do_wait_thread(wo, tsk);
+			if (retval)
+				return retval;
+
+			retval = ptrace_do_wait(wo, tsk);
+			if (retval)
+				return retval;
+
+			if (wo->wo_flags & __WNOTHREAD)
+				break;
+		} while_each_thread(current, tsk);
+	}
 	read_unlock(&tasklist_lock);
 
 notask:
 	retval = wo->notask_error;
-	if (!retval && !(wo->wo_flags & WNOHANG)) {
-		retval = -ERESTARTSYS;
-		if (!signal_pending(current)) {
-			schedule();
-			goto repeat;
-		}
-	}
-end:
-	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
+	if (!retval && !(wo->wo_flags & WNOHANG))
+		return -ERESTARTSYS;
+
 	return retval;
 }
 
-static struct pid *pidfd_get_pid(unsigned int fd)
+static long do_wait(struct wait_opts *wo)
 {
-	struct fd f;
-	struct pid *pid;
+	int retval;
 
-	f = fdget(fd);
-	if (!f.file)
-		return ERR_PTR(-EBADF);
+	trace_sched_process_wait(wo->wo_pid);
 
-	pid = pidfd_pid(f.file);
-	if (!IS_ERR(pid))
-		get_pid(pid);
+	init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
+	wo->child_wait.private = current;
+	add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
 
-	fdput(f);
-	return pid;
+	do {
+		set_current_state(TASK_INTERRUPTIBLE);
+		retval = __do_wait(wo);
+		if (retval != -ERESTARTSYS)
+			break;
+		if (signal_pending(current))
+			break;
+		schedule();
+	} while (1);
+
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
+	return retval;
 }
 
-static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
-			  int options, struct rusage *ru)
+int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid,
+			  struct waitid_info *infop, int options,
+			  struct rusage *ru)
 {
-	struct wait_opts wo;
+	unsigned int f_flags = 0;
 	struct pid *pid = NULL;
 	enum pid_type type;
-	long ret;
 
 	if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED|
 			__WNOTHREAD|__WCLONE|__WALL))
@@ -1531,22 +1741,41 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 		if (upid < 0)
 			return -EINVAL;
 
-		pid = pidfd_get_pid(upid);
+		pid = pidfd_get_pid(upid, &f_flags);
 		if (IS_ERR(pid))
 			return PTR_ERR(pid);
+
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	wo.wo_type	= type;
-	wo.wo_pid	= pid;
-	wo.wo_flags	= options;
-	wo.wo_info	= infop;
-	wo.wo_rusage	= ru;
+	wo->wo_type	= type;
+	wo->wo_pid	= pid;
+	wo->wo_flags	= options;
+	wo->wo_info	= infop;
+	wo->wo_rusage	= ru;
+	if (f_flags & O_NONBLOCK)
+		wo->wo_flags |= WNOHANG;
+
+	return 0;
+}
+
+static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
+			  int options, struct rusage *ru)
+{
+	struct wait_opts wo;
+	long ret;
+
+	ret = kernel_waitid_prepare(&wo, which, upid, infop, options, ru);
+	if (ret)
+		return ret;
+
 	ret = do_wait(&wo);
+	if (!ret && !(options & WNOHANG) && (wo.wo_flags & WNOHANG))
+		ret = -EAGAIN;
 
-	put_pid(pid);
+	put_pid(wo.wo_pid);
 	return ret;
 }
 
@@ -1626,6 +1855,22 @@ long kernel_wait4(pid_t upid, int __user *stat_addr, int options,
 	return ret;
 }
 
+int kernel_wait(pid_t pid, int *stat)
+{
+	struct wait_opts wo = {
+		.wo_type	= PIDTYPE_PID,
+		.wo_pid		= find_get_pid(pid),
+		.wo_flags	= WEXITED,
+	};
+	int ret;
+
+	ret = do_wait(&wo);
+	if (ret > 0 && wo.wo_stat)
+		*stat = wo.wo_stat;
+	put_pid(wo.wo_pid);
+	return ret;
+}
+
 SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
 		int, options, struct rusage __user *, ru)
 {
@@ -1711,7 +1956,14 @@ Efault:
 }
 #endif
 
-__weak void abort(void)
+/*
+ * This needs to be __function_aligned as GCC implicitly makes any
+ * implementation of abort() cold and drops alignment specified by
+ * -falign-functions=N.
+ *
+ * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345#c11
+ */
+__weak __function_aligned void abort(void)
 {
 	BUG();