path: root/mm/oom_kill.c

// 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.
 */

#include <linux/oom.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/task.h>
#include <linux/sched/debug.h>
#include <linux/swap.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/cpuset.h>
#include <linux/export.h>
#include <linux/notifier.h>
#include <linux/memcontrol.h>
#include <linux/mempolicy.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/freezer.h>
#include <linux/ftrace.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
#include <linux/init.h>
#include <linux/mmu_notifier.h>

#include <asm/tlb.h>
#include "internal.h"
#include "slab.h"

#define CREATE_TRACE_POINTS
#include <trace/events/oom.h>

int sysctl_panic_on_oom;
int sysctl_oom_kill_allocating_task;
int sysctl_oom_dump_tasks = 1;

/*
 * Serializes oom killer invocations (out_of_memory()) from all contexts to
 * prevent from over eager oom killing (e.g. when the oom killer is invoked
 * from different domains).
 *
 * oom_killer_disable() relies on this lock to stabilize oom_killer_disabled
 * and mark_oom_victim
 */
DEFINE_MUTEX(oom_lock);
/* Serializes oom_score_adj and oom_score_adj_min updates */
DEFINE_MUTEX(oom_adj_mutex);

static inline bool is_memcg_oom(struct oom_control *oc)
{
	return oc->memcg != NULL;
}

#ifdef CONFIG_NUMA
/**
 * oom_cpuset_eligible() - check task eligiblity for kill
 * @start: task struct of which task to consider
 * @oc: pointer to struct oom_control
 *
 * Task eligibility is determined by whether or not a candidate task, @tsk,
 * shares the same mempolicy nodes as current if it is bound by such a policy
 * and whether or not it has the same set of allowed cpuset nodes.
 *
 * This function is assuming oom-killer context and 'current' has triggered
 * the oom-killer.
 */
static bool oom_cpuset_eligible(struct task_struct *start,
				struct oom_control *oc)
{
	struct task_struct *tsk;
	bool ret = false;
	const nodemask_t *mask = oc->nodemask;

	if (is_memcg_oom(oc))
		return true;

	rcu_read_lock();
	for_each_thread(start, tsk) {
		if (mask) {
			/*
			 * If this is a mempolicy constrained oom, tsk's
			 * cpuset is irrelevant.  Only return true if its
			 * mempolicy intersects current, otherwise it may be
			 * needlessly killed.
			 */
			ret = mempolicy_nodemask_intersects(tsk, mask);
		} else {
			/*
			 * This is not a mempolicy constrained oom, so only
			 * check the mems of tsk's cpuset.
			 */
			ret = cpuset_mems_allowed_intersects(current, tsk);
		}
		if (ret)
			break;
	}
	rcu_read_unlock();

	return ret;
}
#else
static bool oom_cpuset_eligible(struct task_struct *tsk, struct oom_control *oc)
{
	return true;
}
#endif /* CONFIG_NUMA */

/*
 * The process p may have detached its own ->mm while exiting or through
 * kthread_use_mm(), but one or more of its subthreads may still have a valid
 * pointer.  Return p, or any of its subthreads with a valid ->mm, with
 * task_lock() held.
 */
struct task_struct *find_lock_task_mm(struct task_struct *p)
{
	struct task_struct *t;

	rcu_read_lock();

	for_each_thread(p, t) {
		task_lock(t);
		if (likely(t->mm))
			goto found;
		task_unlock(t);
	}
	t = NULL;
found:
	rcu_read_unlock();

	return t;
}

/*
 * order == -1 means the oom kill is required by sysrq, otherwise only
 * for display purposes.
 */
static inline bool is_sysrq_oom(struct oom_control *oc)
{
	return oc->order == -1;
}

/* return true if the task is not adequate as candidate victim task. */
static bool oom_unkillable_task(struct task_struct *p)
{
	if (is_global_init(p))
		return true;
	if (p->flags & PF_KTHREAD)
		return true;
	return false;
}

/*
 * Print out unreclaimble slabs info when unreclaimable slabs amount is greater
 * than all user memory (LRU pages)
 */
static bool is_dump_unreclaim_slabs(void)
{
	unsigned long nr_lru;

	nr_lru = global_node_page_state(