Merge tag 'acpi-5.12-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael...

[platform/kernel/linux-starfive.git] / 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;
}

/**
 * Check whether unreclaimable slab amount is greater than
 * all user memory(LRU pages).
 * dump_unreclaimable_slab() could help in the case that
 * oom due to too much unreclaimable slab used by kernel.
*/
static bool should_dump_unreclaim_slab(void)
{
        unsigned long nr_lru;

        nr_lru = global_node_page_state(NR_ACTIVE_ANON) +
                 global_node_page_state(NR_INACTIVE_ANON) +
                 global_node_page_state(NR_ACTIVE_FILE) +
                 global_node_page_state(NR_INACTIVE_FILE) +
                 global_node_page_state(NR_ISOLATED_ANON) +
                 global_node_page_state(NR_ISOLATED_FILE) +
                 global_node_page_state(NR_UNEVICTABLE);

        return (global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B) > nr_lru);
}

/**
 * oom_badness - heuristic function to determine which candidate task to kill
 * @p: task struct of which task we should calculate
 * @totalpages: total present RAM allowed for page allocation
 *
 * The heuristic for determining which task to kill is made to be as simple and
 * predictable as possible.  The goal is to return the highest value for the
 * task consuming the most memory to avoid subsequent oom failures.
 */
long oom_badness(struct task_struct *p, unsigned long totalpages)
{
        long points;
        long adj;

        if (oom_unkillable_task(p))
                return LONG_MIN;

        p = find_lock_task_mm(p);
        if (!p)
                return LONG_MIN;

        /*
         * Do not even consider tasks which are explicitly marked oom
         * unkillable or have been already oom reaped or the are in
         * the middle of vfork
         */
        adj = (long)p->signal->oom_score_adj;
        if (adj == OOM_SCORE_ADJ_MIN ||
                        test_bit(MMF_OOM_SKIP, &p->mm->flags) ||
                        in_vfork(p)) {
                task_unlock(p);
                return LONG_MIN;
        }

        /*
         * The baseline for the badness score is the proportion of RAM that each
         * task's rss, pagetable and swap space use.
         */
        points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) +
                mm_pgtables_bytes(p->mm) / PAGE_SIZE;
        task_unlock(p);

        /* Normalize to oom_score_adj units */
        adj *= totalpages / 1000;
        points += adj;

        return points;
}

static const char * const oom_constraint_text[] = {
        [CONSTRAINT_NONE] = "CONSTRAINT_NONE",
        [CONSTRAINT_CPUSET] = "CONSTRAINT_CPUSET",
        [CONSTRAINT_MEMORY_POLICY] = "CONSTRAINT_MEMORY_POLICY",
        [CONSTRAINT_MEMCG] = "CONSTRAINT_MEMCG",
};

/*
 * Determine the type of allocation constraint.
 */
static enum oom_constraint constrained_alloc(struct oom_control *oc)
{
        struct zone *zone;
        struct zoneref *z;
        enum zone_type highest_zoneidx = gfp_zone(oc->gfp_mask);
        bool cpuset_limited = false;
        int nid;

        if (is_memcg_oom(oc)) {
                oc->totalpages = mem_cgroup_get_max(oc->memcg) ?: 1;
                return CONSTRAINT_MEMCG;
        }

        /* Default to all available memory */
        oc->totalpages = totalram_pages() + total_swap_pages;

        if (!IS_ENABLED(CONFIG_NUMA))
                return CONSTRAINT_NONE;

        if (!oc->zonelist)
                return CONSTRAINT_NONE;
        /*
         * Reach here only when __GFP_NOFAIL is used. So, we should avoid
         * to kill current.We have to random task kill in this case.
         * Hopefully, CONSTRAINT_THISNODE...but no way to handle it, now.
         */
        if (oc->gfp_mask & __GFP_THISNODE)
                return CONSTRAINT_NONE;

        /*
         * This is not a __GFP_THISNODE allocation, so a truncated nodemask in
         * the page allocator means a mempolicy is in effect.  Cpuset policy
         * is enforced in get_page_from_freelist().
         */
        if (oc->nodemask &&
            !nodes_subset(node_states[N_MEMORY], *oc->nodemask)) {
                oc->totalpages = total_swap_pages;
                for_each_node_mask(nid, *oc->nodemask)
                        oc->totalpages += node_present_pages(nid);
                return CONSTRAINT_MEMORY_POLICY;
        }

        /* Check this allocation failure is caused by cpuset's wall function */
        for_each_zone_zonelist_nodemask(zone, z, oc->zonelist,
                        highest_zoneidx, oc->nodemask)
                if (!cpuset_zone_allowed(zone, oc->gfp_mask))
                        cpuset_limited = true;

        if (cpuset_limited) {
                oc->totalpages = total_swap_pages;
                for_each_node_mask(nid, cpuset_current_mems_allowed)
                        oc->totalpages += node_present_pages(nid);
                return CONSTRAINT_CPUSET;
        }
        return CONSTRAINT_NONE;
}

static int oom_evaluate_task(struct task_struct *task, void *arg)
{
        struct oom_control *oc = arg;
        long points;

        if (oom_unkillable_task(task))
                goto next;

        /* p may not have freeable memory in nodemask */
        if (!is_memcg_oom(oc) && !oom_cpuset_eligible(task, oc))
                goto next;

        /*
         * This task already has access to memory reserves and is being killed.
         * Don't allow any other task to have access to the reserves unless
         * the task has MMF_OOM_SKIP because chances that it would release
         * any memory is quite low.
         */
        if (!is_sysrq_oom(oc) && tsk_is_oom_victim(task)) {
                if (test_bit(MMF_OOM_SKIP, &task->signal->oom_mm->flags))
                        goto next;
                goto abort;
        }

        /*
         * If task is allocating a lot of memory and has been marked to be
         * killed first if it triggers an oom, then select it.
         */
        if (oom_task_origin(task)) {
                points = LONG_MAX;
                goto select;
        }

        points = oom_badness(task, oc->totalpages);
        if (points == LONG_MIN || points < oc->chosen_points)
                goto next;

select:
        if (oc->chosen)
                put_task_struct(oc->chosen);
        get_task_struct(task);
        oc->chosen = task;
        oc->chosen_points = points;
next:
        return 0;
abort:
        if (oc->chosen)
                put_task_struct(oc->chosen);
        oc->chosen = (void *)-1UL;
        return 1;
}

/*
 * Simple selection loop. We choose the process with the highest number of
 * 'points'. In case scan was aborted, oc->chosen is set to -1.
 */
static void select_bad_process(struct oom_control *oc)
{
        oc->chosen_points = LONG_MIN;

        if (is_memcg_oom(oc))
                mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc);
        else {
                struct task_struct *p;

                rcu_read_lock();
                for_each_process(p)
                        if (oom_evaluate_task(p, oc))
                                break;
                rcu_read_unlock();
        }
}

static int dump_task(struct task_struct *p, void *arg)
{
        struct oom_control *oc = arg;
        struct task_struct *task;

        if (oom_unkillable_task(p))
                return 0;

        /* p may not have freeable memory in nodemask */
        if (!is_memcg_oom(oc) && !oom_cpuset_eligible(p, oc))
                return 0;

        task = find_lock_task_mm(p);
        if (!task) {
                /*
                 * This is a kthread or all of p's threads have already
                 * detached their mm's.  There's no need to report
                 * them; they can't be oom killed anyway.
                 */
                return 0;
        }

        pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu         %5hd %s\n",
                task->pid, from_kuid(&init_user_ns, task_uid(task)),
                task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
                mm_pgtables_bytes(task->mm),
                get_mm_counter(task->mm, MM_SWAPENTS),
                task->signal->oom_score_adj, task->comm);
        task_unlock(task);

        return 0;
}

/**
 * dump_tasks - dump current memory state of all system tasks
 * @oc: pointer to struct oom_control
 *
 * Dumps the current memory state of all eligible tasks.  Tasks not in the same
 * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
 * are not shown.
 * State information includes task's pid, uid, tgid, vm size, rss,
 * pgtables_bytes, swapents, oom_score_adj value, and name.
 */
static void dump_tasks(struct oom_control *oc)
{
        pr_info("Tasks state (memory values in pages):\n");
        pr_info("[  pid  ]   uid  tgid total_vm      rss pgtables_bytes swapents oom_score_adj name\n");

        if (is_memcg_oom(oc))
                mem_cgroup_scan_tasks(oc->memcg, dump_task, oc);
        else {
                struct task_struct *p;

                rcu_read_lock();
                for_each_process(p)
                        dump_task(p, oc);
                rcu_read_unlock();
        }
}

static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim)
{
        /* one line summary of the oom killer context. */
        pr_info("oom-kill:constraint=%s,nodemask=%*pbl",
                        oom_constraint_text[oc->constraint],
                        nodemask_pr_args(oc->nodemask));
        cpuset_print_current_mems_allowed();
        mem_cgroup_print_oom_context(oc->memcg, victim);
        pr_cont(",task=%s,pid=%d,uid=%d\n", victim->comm, victim->pid,
                from_kuid(&init_user_ns, task_uid(victim)));
}

static void dump_header(struct oom_control *oc, struct task_struct *p)
{
        pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), order=%d, oom_score_adj=%hd\n",
                current->comm, oc->gfp_mask, &oc->gfp_mask, oc->order,
                        current->signal->oom_score_adj);
        if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order)
                pr_warn("COMPACTION is disabled!!!\n");

        dump_stack();
        if (is_memcg_oom(oc))
                mem_cgroup_print_oom_meminfo(oc->memcg);
        else {
                show_mem(SHOW_MEM_FILTER_NODES, oc->nodemask);
                if (should_dump_unreclaim_slab())
                        dump_unreclaimable_slab();
        }
        if (sysctl_oom_dump_tasks)
                dump_tasks(oc);
        if (p)
                dump_oom_summary(oc, p);
}

/*
 * Number of OOM victims in flight
 */
static atomic_t oom_victims = ATOMIC_INIT(0);
static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait);

static bool oom_killer_disabled __read_mostly;

#define K(x) ((x) << (PAGE_SHIFT-10))

/*
 * task->mm can be NULL if the task is the exited group leader.  So to
 * determine whether the task is using a particular mm, we examine all the
 * task's threads: if one of those is using this mm then this task was also
 * using it.
 */
bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
{
        struct task_struct *t;

        for_each_thread(p, t) {
                struct mm_struct *t_mm = READ_ONCE(t->mm);
                if (t_mm)
                        return t_mm == mm;
        }
        return false;
}

#ifdef CONFIG_MMU
/*
 * OOM Reaper kernel thread which tries to reap the memory used by the OOM
 * victim (if that is possible) to help the OOM killer to move on.
 */
static struct task_struct *oom_reaper_th;
static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
static struct task_struct *oom_reaper_list;
static DEFINE_SPINLOCK(oom_reaper_lock);

bool __oom_reap_task_mm(struct mm_struct *mm)
{
        struct vm_area_struct *vma;
        bool ret = true;

        /*
         * Tell all users of get_user/copy_from_user etc... that the content
         * is no longer stable. No barriers really needed because unmapping
         * should imply barriers already and the reader would hit a page fault
         * if it stumbled over a reaped memory.
         */
        set_bit(MMF_UNSTABLE, &mm->flags);

        for (vma = mm->mmap ; vma; vma = vma->vm_next) {
                if (!can_madv_lru_vma(vma))
                        continue;

                /*
                 * Only anonymous pages have a good chance to be dropped
                 * without additional steps which we cannot afford as we
                 * are OOM already.
                 *
                 * We do not even care about fs backed pages because all
                 * which are reclaimable have already been reclaimed and
                 * we do not want to block exit_mmap by keeping mm ref
                 * count elevated without a good reason.
                 */
                if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
                        struct mmu_notifier_range range;
                        struct mmu_gather tlb;

                        mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0,
                                                vma, mm, vma->vm_start,
                                                vma->vm_end);
                        tlb_gather_mmu(&tlb, mm);
                        if (mmu_notifier_invalidate_range_start_nonblock(&range)) {
                                tlb_finish_mmu(&tlb);
                                ret = false;
                                continue;
                        }
                        unmap_page_range(&tlb, vma, range.start, range.end, NULL);
                        mmu_notifier_invalidate_range_end(&range);
                        tlb_finish_mmu(&tlb);
                }
        }

        return ret;
}

/*
 * Reaps the address space of the give task.
 *
 * Returns true on success and false if none or part of the address space
 * has been reclaimed and the caller should retry later.
 */
static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
{
        bool ret = true;

        if (!mmap_read_trylock(mm)) {
                trace_skip_task_reaping(tsk->pid);
                return false;
        }

        /*
         * MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't
         * work on the mm anymore. The check for MMF_OOM_SKIP must run
         * under mmap_lock for reading because it serializes against the
         * mmap_write_lock();mmap_write_unlock() cycle in exit_mmap().
         */
        if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
                trace_skip_task_reaping(tsk->pid);
                goto out_unlock;
        }

        trace_start_task_reaping(tsk->pid);

        /* failed to reap part of the address space. Try again later */
        ret = __oom_reap_task_mm(mm);
        if (!ret)
                goto out_finish;

        pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
                        task_pid_nr(tsk), tsk->comm,
                        K(get_mm_counter(mm, MM_ANONPAGES)),
                        K(get_mm_counter(mm, MM_FILEPAGES)),
                        K(get_mm_counter(mm, MM_SHMEMPAGES)));
out_finish:
        trace_finish_task_reaping(tsk->pid);
out_unlock:
        mmap_read_unlock(mm);

        return ret;
}

#define MAX_OOM_REAP_RETRIES 10
static void oom_reap_task(struct task_struct *tsk)
{
        int attempts = 0;
        struct mm_struct *mm = tsk->signal->oom_mm;

        /* Retry the mmap_read_trylock(mm) a few times */
        while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm))
                schedule_timeout_idle(HZ/10);

        if (attempts <= MAX_OOM_REAP_RETRIES ||
            test_bit(MMF_OOM_SKIP, &mm->flags))
                goto done;

        pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
                task_pid_nr(tsk), tsk->comm);
        sched_show_task(tsk);
        debug_show_all_locks();

done:
        tsk->oom_reaper_list = NULL;

        /*
         * Hide this mm from OOM killer because it has been either reaped or
         * somebody can't call mmap_write_unlock(mm).
         */
        set_bit(MMF_OOM_SKIP, &mm->flags);

        /* Drop a reference taken by wake_oom_reaper */
        put_task_struct(tsk);
}

static int oom_reaper(void *unused)
{
        while (true) {
                struct task_struct *tsk = NULL;

                wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL);
                spin_lock(&oom_reaper_lock);
                if (oom_reaper_list != NULL) {
                        tsk = oom_reaper_list;
                        oom_reaper_list = tsk->oom_reaper_list;
                }
                spin_unlock(&oom_reaper_lock);

                if (tsk)
                        oom_reap_task(tsk);
        }

        return 0;
}

static void wake_oom_reaper(struct task_struct *tsk)
{
        /* mm is already queued? */
        if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags))
                return;

        get_task_struct(tsk);

        spin_lock(&oom_reaper_lock);
        tsk->oom_reaper_list = oom_reaper_list;
        oom_reaper_list = tsk;
        spin_unlock(&oom_reaper_lock);
        trace_wake_reaper(tsk->pid);
        wake_up(&oom_reaper_wait);
}

static int __init oom_init(void)
{
        oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
        return 0;
}
subsys_initcall(oom_init)
#else
static inline void wake_oom_reaper(struct task_struct *tsk)
{
}
#endif /* CONFIG_MMU */

/**
 * mark_oom_victim - mark the given task as OOM victim
 * @tsk: task to mark
 *
 * Has to be called with oom_lock held and never after
 * oom has been disabled already.
 *
 * tsk->mm has to be non NULL and caller has to guarantee it is stable (either
 * under task_lock or operate on the current).
 */
static void mark_oom_victim(struct task_struct *tsk)
{
        struct mm_struct *mm = tsk->mm;

        WARN_ON(oom_killer_disabled);
        /* OOM killer might race with memcg OOM */
        if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE))
                return;

        /* oom_mm is bound to the signal struct life time. */
        if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) {
                mmgrab(tsk->signal->oom_mm);
                set_bit(MMF_OOM_VICTIM, &mm->flags);
        }

        /*
         * Make sure that the task is woken up from uninterruptible sleep
         * if it is frozen because OOM killer wouldn't be able to free
         * any memory and livelock. freezing_slow_path will tell the freezer
         * that TIF_MEMDIE tasks should be ignored.
         */
        __thaw_task(tsk);
        atomic_inc(&oom_victims);
        trace_mark_victim(tsk->pid);
}

/**
 * exit_oom_victim - note the exit of an OOM victim
 */
void exit_oom_victim(void)
{
        clear_thread_flag(TIF_MEMDIE);

        if (!atomic_dec_return(&oom_victims))
                wake_up_all(&oom_victims_wait);
}

/**
 * oom_killer_enable - enable OOM killer
 */
void oom_killer_enable(void)
{
        oom_killer_disabled = false;
        pr_info("OOM killer enabled.\n");
}

/**
 * oom_killer_disable - disable OOM killer
 * @timeout: maximum timeout to wait for oom victims in jiffies
 *
 * Forces all page allocations to fail rather than trigger OOM killer.
 * Will block and wait until all OOM victims are killed or the given
 * timeout expires.
 *
 * The function cannot be called when there are runnable user tasks because
 * the userspace would see unexpected allocation failures as a result. Any
 * new usage of this function should be consulted with MM people.
 *
 * Returns true if successful and false if the OOM killer cannot be
 * disabled.
 */
bool oom_killer_disable(signed long timeout)
{
        signed long ret;

        /*
         * Make sure to not race with an ongoing OOM killer. Check that the
         * current is not killed (possibly due to sharing the victim's memory).
         */
        if (mutex_lock_killable(&oom_lock))
                return false;
        oom_killer_disabled = true;
        mutex_unlock(&oom_lock);

        ret = wait_event_interruptible_timeout(oom_victims_wait,
                        !atomic_read(&oom_victims), timeout);
        if (ret <= 0) {
                oom_killer_enable();
                return false;
        }
        pr_info("OOM killer disabled.\n");

        return true;
}

static inline bool __task_will_free_mem(struct task_struct *task)
{
        struct signal_struct *sig = task->signal;

        /*
         * A coredumping process may sleep for an extended period in exit_mm(),
         * so the oom killer cannot assume that the process will promptly exit
         * and release memory.
         */
        if (sig->flags & SIGNAL_GROUP_COREDUMP)
                return false;

        if (sig->flags & SIGNAL_GROUP_EXIT)
                return true;

        if (thread_group_empty(task) && (task->flags & PF_EXITING))
                return true;

        return false;
}

/*
 * Checks whether the given task is dying or exiting and likely to
 * release its address space. This means that all threads and processes
 * sharing the same mm have to be killed or exiting.
 * Caller has to make sure that task->mm is stable (hold task_lock or
 * it operates on the current).
 */
static bool task_will_free_mem(struct task_struct *task)
{
        struct mm_struct *mm = task->mm;
        struct task_struct *p;
        bool ret = true;

        /*
         * Skip tasks without mm because it might have passed its exit_mm and
         * exit_oom_victim. oom_reaper could have rescued that but do not rely
         * on that for now. We can consider find_lock_task_mm in future.
         */
        if (!mm)
                return false;

        if (!__task_will_free_mem(task))
                return false;

        /*
         * This task has already been drained by the oom reaper so there are
         * only small chances it will free some more
         */
        if (test_bit(MMF_OOM_SKIP, &mm->flags))
                return false;

        if (atomic_read(&mm->mm_users) <= 1)
                return true;

        /*
         * Make sure that all tasks which share the mm with the given tasks
         * are dying as well to make sure that a) nobody pins its mm and
         * b) the task is also reapable by the oom reaper.
         */
        rcu_read_lock();
        for_each_process(p) {
                if (!process_shares_mm(p, mm))
                        continue;
                if (same_thread_group(task, p))
                        continue;
                ret = __task_will_free_mem(p);
                if (!ret)
                        break;
        }
        rcu_read_unlock();

        return ret;
}

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;
                        set_bit(MMF_OOM_SKIP, &mm->flags);
                        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 kthead_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)
                wake_oom_reaper(victim);

        mmdrop(mm);
        put_task_struct(victim);
}
#undef K

/*
 * Kill provided task unless it's secured by setting
 * oom_score_adj to OOM_SCORE_ADJ_MIN.
 */
static int oom_kill_memcg_member(struct task_struct *task, void *message)
{
        if (task->signal->oom_score_adj != OOM_SCORE_ADJ_MIN &&
            !is_global_init(task)) {
                get_task_struct(task);
                __oom_kill_process(task, message);
        }
        return 0;
}

static void oom_kill_process(struct oom_control *oc, const char *message)
{
        struct task_struct *victim = oc->chosen;
        struct mem_cgroup *oom_group;
        static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
                                              DEFAULT_RATELIMIT_BURST);

        /*
         * If the task is already exiting, don't alarm the sysadmin or kill
         * its children or threads, just give it access to memory reserves
         * so it can die quickly
         */
        task_lock(victim);
        if (task_will_free_mem(victim)) {
                mark_oom_victim(victim);
                wake_oom_reaper(victim);
                task_unlock(victim);
                put_task_struct(victim);
                return;
        }
        task_unlock(victim);

        if (__ratelimit(&oom_rs))
                dump_header(oc, victim);

        /*
         * Do we need to kill the entire memory cgroup?
         * Or even one of the ancestor memory cgroups?
         * Check this out before killing the victim task.
         */
        oom_group = mem_cgroup_get_oom_group(victim, oc->memcg);

        __oom_kill_process(victim, message);

        /*
         * If necessary, kill all tasks in the selected memory cgroup.
         */
        if (oom_group) {
                mem_cgroup_print_oom_group(oom_group);
                mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member,
                                      (void*)message);
                mem_cgroup_put(oom_group);
        }
}

/*
 * Determines whether the kernel must panic because of the panic_on_oom sysctl.
 */
static void check_panic_on_oom(struct oom_control *oc)
{
        if (likely(!sysctl_panic_on_oom))
                return;
        if (sysctl_panic_on_oom != 2) {
                /*
                 * panic_on_oom == 1 only affects CONSTRAINT_NONE, the kernel
                 * does not panic for cpuset, mempolicy, or memcg allocation
                 * failures.
                 */
                if (oc->constraint != CONSTRAINT_NONE)
                        return;
        }
        /* Do not panic for oom kills triggered by sysrq */
        if (is_sysrq_oom(oc))
                return;
        dump_header(oc, NULL);
        panic("Out of memory: %s panic_on_oom is enabled\n",
                sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
}

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);

/**
 * out_of_memory - kill the "best" process when we run out of memory
 * @oc: pointer to struct oom_control
 *
 * 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.
 */
bool out_of_memory(struct oom_control *oc)
{
        unsigned long freed = 0;

        if (oom_killer_disabled)
                return false;

        if (!is_memcg_oom(oc)) {
                blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
                if (freed > 0)
                        /* Got some memory back in the last second. */
                        return true;
        }

        /*
         * If current has a pending SIGKILL or is exiting, then automatically
         * select it.  The goal is to allow it to allocate so that it may
         * quickly exit and free its memory.
         */
        if (task_will_free_mem(current)) {
                mark_oom_victim(current);
                wake_oom_reaper(current);
                return true;
        }

        /*
         * The OOM killer does not compensate for IO-less reclaim.
         * pagefault_out_of_memory lost its gfp context so we have to
         * make sure exclude 0 mask - all other users should have at least
         * ___GFP_DIRECT_RECLAIM to get here. But mem_cgroup_oom() has to
         * invoke the OOM killer even if it is a GFP_NOFS allocation.
         */
        if (oc->gfp_mask && !(oc->gfp_mask & __GFP_FS) && !is_memcg_oom(oc))
                return true;

        /*
         * Check if there were limitations on the allocation (only relevant for
         * NUMA and memcg) that may require different handling.
         */
        oc->constraint = constrained_alloc(oc);
        if (oc->constraint != CONSTRAINT_MEMORY_POLICY)
                oc->nodemask = NULL;
        check_panic_on_oom(oc);

        if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task &&
            current->mm && !oom_unkillable_task(current) &&
            oom_cpuset_eligible(current, oc) &&
            current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
                get_task_struct(current);
                oc->chosen = current;
                oom_kill_process(oc, "Out of memory (oom_kill_allocating_task)");
                return true;
        }

        select_bad_process(oc);
        /* Found nothing?!?! */
        if (!oc->chosen) {
                dump_header(oc, NULL);
                pr_warn("Out of memory and no killable processes...\n");
                /*
                 * If we got here due to an actual allocation at the
                 * system level, we cannot survive this and will enter
                 * an endless loop in the allocator. Bail out now.
                 */
                if (!is_sysrq_oom(oc) && !is_memcg_oom(oc))
                        panic("System is deadlocked on memory\n");
        }
        if (oc->chosen && oc->chosen != (void *)-1UL)
                oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" :
                                 "Memory cgroup out of memory");
        return !!oc->chosen;
}

/*
 * The pagefault handler calls here because it is out of memory, so kill a
 * memory-hogging task. If oom_lock is held by somebody else, a parallel oom
 * killing is already in progress so do nothing.
 */
void pagefault_out_of_memory(void)
{
        struct oom_control oc = {
                .zonelist = NULL,
                .nodemask = NULL,
                .memcg = NULL,
                .gfp_mask = 0,
                .order = 0,
        };

        if (mem_cgroup_oom_synchronize(true))
                return;

        if (!mutex_trylock(&oom_lock))
                return;
        out_of_memory(&oc);
        mutex_unlock(&oom_lock);
}