// SPDX-License-Identifier: GPL-2.0-only
/*
 *  linux/mm/oom_kill.c
 *
 *  Copyright (C)  1998,2000  Rik van Riel
 *	Thanks go out to Claus Fischer for some serious inspiration and
 *	for goading me into coding this file...
 *  Copyright (C)  2010  Google, Inc.
 *	Rewritten by David Rientjes
 *
 *  The routines in this file are used to kill a process when
 *  we're seriously out of memory. This gets called from __alloc_pages()
 *  in mm/page_alloc.c when we really run out of memory.
 *
 *  Since we won't call these routines often (on a well-configured
 *  machine) this file will double as a 'coding guide' and a signpost
 *  for newbie kernel hackers. It features several pointers to major
 *  kernel subsystems and hints as to where to find out what things do.
 */

/*
 * Official Linux v6.18: mm/oom_kill.c
 * https://github.com/torvalds/linux/blob/v6.18/mm/oom_kill.c#L927
 * Complete upstream scope, not an elided book-code reconstruction.
 * See GPL-2.0.txt. Not a standalone translation unit.
 */

static void __oom_kill_process(struct task_struct *victim, const char *message)
{
	struct task_struct *p;
	struct mm_struct *mm;
	bool can_oom_reap = true;

	p = find_lock_task_mm(victim);
	if (!p) {
		pr_info("%s: OOM victim %d (%s) is already exiting. Skip killing the task\n",
			message, task_pid_nr(victim), victim->comm);
		put_task_struct(victim);
		return;
	} else if (victim != p) {
		get_task_struct(p);
		put_task_struct(victim);
		victim = p;
	}

	/* Get a reference to safely compare mm after task_unlock(victim) */
	mm = victim->mm;
	mmgrab(mm);

	/* Raise event before sending signal: task reaper must see this */
	count_vm_event(OOM_KILL);
	memcg_memory_event_mm(mm, MEMCG_OOM_KILL);

	/*
	 * We should send SIGKILL before granting access to memory reserves
	 * in order to prevent the OOM victim from depleting the memory
	 * reserves from the user space under its control.
	 */
	do_send_sig_info(SIGKILL, SEND_SIG_PRIV, victim, PIDTYPE_TGID);
	mark_oom_victim(victim);
	pr_err("%s: Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB, UID:%u pgtables:%lukB oom_score_adj:%hd\n",
		message, task_pid_nr(victim), victim->comm, K(mm->total_vm),
		K(get_mm_counter(mm, MM_ANONPAGES)),
		K(get_mm_counter(mm, MM_FILEPAGES)),
		K(get_mm_counter(mm, MM_SHMEMPAGES)),
		from_kuid(&init_user_ns, task_uid(victim)),
		mm_pgtables_bytes(mm) >> 10, victim->signal->oom_score_adj);
	task_unlock(victim);

	/*
	 * Kill all user processes sharing victim->mm in other thread groups, if
	 * any.  They don't get access to memory reserves, though, to avoid
	 * depletion of all memory.  This prevents mm->mmap_lock livelock when an
	 * oom killed thread cannot exit because it requires the semaphore and
	 * its contended by another thread trying to allocate memory itself.
	 * That thread will now get access to memory reserves since it has a
	 * pending fatal signal.
	 */
	rcu_read_lock();
	for_each_process(p) {
		if (!process_shares_mm(p, mm))
			continue;
		if (same_thread_group(p, victim))
			continue;
		if (is_global_init(p)) {
			can_oom_reap = false;
			mm_flags_set(MMF_OOM_SKIP, mm);
			pr_info("oom killer %d (%s) has mm pinned by %d (%s)\n",
					task_pid_nr(victim), victim->comm,
					task_pid_nr(p), p->comm);
			continue;
		}
		/*
		 * No kthread_use_mm() user needs to read from the userspace so
		 * we are ok to reap it.
		 */
		if (unlikely(p->flags & PF_KTHREAD))
			continue;
		do_send_sig_info(SIGKILL, SEND_SIG_PRIV, p, PIDTYPE_TGID);
	}
	rcu_read_unlock();

	if (can_oom_reap)
		queue_oom_reaper(victim);

	mmdrop(mm);
	put_task_struct(victim);
}