oom_kill.c

最新最稳定的Linux内存管理模块源代码

	if (!p->mm) {
		WARN_ON(1);
		printk(KERN_WARNING "tried to kill an mm-less task!\n");
		return;
	}

	if (verbose)
		printk(KERN_ERR "Killed process %d (%s)\n",
				task_pid_nr(p), p->comm);

	/*
	 * We give our sacrificial lamb high priority and access to
	 * all the memory it needs. That way it should be able to
	 * exit() and clear out its resources quickly...
	 */
	p->rt.time_slice = HZ;
	set_tsk_thread_flag(p, TIF_MEMDIE);

	force_sig(SIGKILL, p);
}

static int oom_kill_task(struct task_struct *p)
{
	struct mm_struct *mm;
	struct task_struct *g, *q;

	mm = p->mm;

	/* WARNING: mm may not be dereferenced since we did not obtain its
	 * value from get_task_mm(p).  This is OK since all we need to do is
	 * compare mm to q->mm below.
	 *
	 * Furthermore, even if mm contains a non-NULL value, p->mm may
	 * change to NULL at any time since we do not hold task_lock(p).
	 * However, this is of no concern to us.
	 */

	if (mm == NULL)
		return 1;

	/*
	 * Don't kill the process if any threads are set to OOM_DISABLE
	 */
	do_each_thread(g, q) {
		if (q->mm == mm && q->oomkilladj == OOM_DISABLE)
			return 1;
	} while_each_thread(g, q);

	__oom_kill_task(p, 1);

	/*
	 * kill all processes that share the ->mm (i.e. all threads),
	 * but are in a different thread group. Don't let them have access
	 * to memory reserves though, otherwise we might deplete all memory.
	 */
	do_each_thread(g, q) {
		if (q->mm == mm && !same_thread_group(q, p))
			force_sig(SIGKILL, q);
	} while_each_thread(g, q);

	return 0;
}

static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
			    unsigned long points, struct mem_cgroup *mem,
			    const char *message)
{
	struct task_struct *c;

	if (printk_ratelimit()) {
		printk(KERN_WARNING "%s invoked oom-killer: "
			"gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
			current->comm, gfp_mask, order, current->oomkilladj);
		task_lock(current);
		cpuset_print_task_mems_allowed(current);
		task_unlock(current);
		dump_stack();
		show_mem();
		if (sysctl_oom_dump_tasks)
			dump_tasks(mem);
	}

	/*
	 * If the task is already exiting, don't alarm the sysadmin or kill
	 * its children or threads, just set TIF_MEMDIE so it can die quickly
	 */
	if (p->flags & PF_EXITING) {
		__oom_kill_task(p, 0);
		return 0;
	}

	printk(KERN_ERR "%s: kill process %d (%s) score %li or a child\n",
					message, task_pid_nr(p), p->comm, points);

	/* Try to kill a child first */
	list_for_each_entry(c, &p->children, sibling) {
		if (c->mm == p->mm)
			continue;
		if (!oom_kill_task(c))
			return 0;
	}
	return oom_kill_task(p);
}

#ifdef CONFIG_CGROUP_MEM_RES_CTLR
void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask)
{
	unsigned long points = 0;
	struct task_struct *p;

	read_lock(&tasklist_lock);
retry:
	p = select_bad_process(&points, mem);
	if (PTR_ERR(p) == -1UL)
		goto out;

	if (!p)
		p = current;

	if (oom_kill_process(p, gfp_mask, 0, points, mem,
				"Memory cgroup out of memory"))
		goto retry;
out:
	read_unlock(&tasklist_lock);
}
#endif

static BLOCKING_NOTIFIER_HEAD(oom_notify_list);

int register_oom_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&oom_notify_list, nb);
}
EXPORT_SYMBOL_GPL(register_oom_notifier);

int unregister_oom_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_unregister(&oom_notify_list, nb);
}
EXPORT_SYMBOL_GPL(unregister_oom_notifier);

/*
 * Try to acquire the OOM killer lock for the zones in zonelist.  Returns zero
 * if a parallel OOM killing is already taking place that includes a zone in
 * the zonelist.  Otherwise, locks all zones in the zonelist and returns 1.
 */
int try_set_zone_oom(struct zonelist *zonelist, gfp_t gfp_mask)
{
	struct zoneref *z;
	struct zone *zone;
	int ret = 1;

	spin_lock(&zone_scan_lock);
	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
		if (zone_is_oom_locked(zone)) {
			ret = 0;
			goto out;
		}
	}

	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
		/*
		 * Lock each zone in the zonelist under zone_scan_lock so a
		 * parallel invocation of try_set_zone_oom() doesn't succeed
		 * when it shouldn't.
		 */
		zone_set_flag(zone, ZONE_OOM_LOCKED);
	}

out:
	spin_unlock(&zone_scan_lock);
	return ret;
}

/*
 * Clears the ZONE_OOM_LOCKED flag for all zones in the zonelist so that failed
 * allocation attempts with zonelists containing them may now recall the OOM
 * killer, if necessary.
 */
void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
{
	struct zoneref *z;
	struct zone *zone;

	spin_lock(&zone_scan_lock);
	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
		zone_clear_flag(zone, ZONE_OOM_LOCKED);
	}
	spin_unlock(&zone_scan_lock);
}

/*
 * Must be called with tasklist_lock held for read.
 */
static void __out_of_memory(gfp_t gfp_mask, int order)
{
	if (sysctl_oom_kill_allocating_task) {
		oom_kill_process(current, gfp_mask, order, 0, NULL,
				"Out of memory (oom_kill_allocating_task)");

	} else {
		unsigned long points;
		struct task_struct *p;

retry:
		/*
		 * Rambo mode: Shoot down a process and hope it solves whatever
		 * issues we may have.
		 */
		p = select_bad_process(&points, NULL);

		if (PTR_ERR(p) == -1UL)
			return;

		/* Found nothing?!?! Either we hang forever, or we panic. */
		if (!p) {
			read_unlock(&tasklist_lock);
			panic("Out of memory and no killable processes...\n");
		}

		if (oom_kill_process(p, gfp_mask, order, points, NULL,
				     "Out of memory"))
			goto retry;
	}
}

/*
 * pagefault handler calls into here because it is out of memory but
 * doesn't know exactly how or why.
 */
void pagefault_out_of_memory(void)
{
	unsigned long freed = 0;

	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
	if (freed > 0)
		/* Got some memory back in the last second. */
		return;

	/*
	 * If this is from memcg, oom-killer is already invoked.
	 * and not worth to go system-wide-oom.
	 */
	if (mem_cgroup_oom_called(current))
		goto rest_and_return;

	if (sysctl_panic_on_oom)
		panic("out of memory from page fault. panic_on_oom is selected.\n");

	read_lock(&tasklist_lock);
	__out_of_memory(0, 0); /* unknown gfp_mask and order */
	read_unlock(&tasklist_lock);

	/*
	 * Give "p" a good chance of killing itself before we
	 * retry to allocate memory.
	 */
rest_and_return:
	if (!test_thread_flag(TIF_MEMDIE))
		schedule_timeout_uninterruptible(1);
}

/**
 * out_of_memory - kill the "best" process when we run out of memory
 * @zonelist: zonelist pointer
 * @gfp_mask: memory allocation flags
 * @order: amount of memory being requested as a power of 2
 *
 * If we run out of memory, we have the choice between either
 * killing a random task (bad), letting the system crash (worse)
 * OR try to be smart about which process to kill. Note that we
 * don't have to be perfect here, we just have to be good.
 */
void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
{
	unsigned long freed = 0;
	enum oom_constraint constraint;

	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
	if (freed > 0)
		/* Got some memory back in the last second. */
		return;

	if (sysctl_panic_on_oom == 2)
		panic("out of memory. Compulsory panic_on_oom is selected.\n");

	/*
	 * Check if there were limitations on the allocation (only relevant for
	 * NUMA) that may require different handling.
	 */
	constraint = constrained_alloc(zonelist, gfp_mask);
	read_lock(&tasklist_lock);

	switch (constraint) {
	case CONSTRAINT_MEMORY_POLICY:
		oom_kill_process(current, gfp_mask, order, 0, NULL,
				"No available memory (MPOL_BIND)");
		break;

	case CONSTRAINT_NONE:
		if (sysctl_panic_on_oom)
			panic("out of memory. panic_on_oom is selected\n");
		/* Fall-through */
	case CONSTRAINT_CPUSET:
		__out_of_memory(gfp_mask, order);
		break;
	}

	read_unlock(&tasklist_lock);

	/*
	 * Give "p" a good chance of killing itself before we
	 * retry to allocate memory unless "p" is current
	 */
	if (!test_thread_flag(TIF_MEMDIE))
		schedule_timeout_uninterruptible(1);
}