/* return true if the task is not adequate as candidate victim task. */
static bool oom_unkillable_task(struct task_struct *p,
const struct mem_cgroup *memcg, const nodemask_t *nodemask)
{
if (is_global_init(p))
return true;
if (p->flags & PF_KTHREAD)
return true;
/* When mem_cgroup_out_of_memory() and p is not member of the group */
if (memcg && !task_in_mem_cgroup(p, memcg))
return true;
/* p may not have freeable memory in nodemask */
if (!has_intersects_mems_allowed(p, nodemask))
return true;
return false;
}
/*
* If this is a system OOM (not a memcg OOM) and the task selected to be
* killed is not already running at high (RT) priorities, speed up the
* recovery by boosting the dying task to the lowest FIFO priority.
* That helps with the recovery and avoids interfering with RT tasks.
*/
static void boost_dying_task_prio(struct task_struct *p,
struct mem_cgroup *mem)
{
struct sched_param param = { .sched_priority = 1 };
if (mem)
return;
if (!rt_task(p))
sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m);
}
/*
* The process p may have detached its own ->mm while exiting or through
* 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 = p;
do {
task_lock(t);
if (likely(t->mm))
return t;
task_unlock(t);
} while_each_thread(p, t);
return NULL;
}
/* return true if the task is not adequate as candidate victim task. */
static bool oom_unkillable_task(struct task_struct *p,
const struct mem_cgroup *mem, const nodemask_t *nodemask)
{
if (is_global_init(p))
return true;
if (p->flags & PF_KTHREAD)
return true;
/* When mem_cgroup_out_of_memory() and p is not member of the group */
if (mem && !task_in_mem_cgroup(p, mem))
return true;
/* p may not have freeable memory in nodemask */
if (!has_intersects_mems_allowed(p, nodemask))
return true;
return false;
}
/**
* 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.
*/
unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
const nodemask_t *nodemask, unsigned long totalpages)
{
long points;
if (oom_unkillable_task(p, mem, nodemask))
return 0;
p = find_lock_task_mm(p);
if (!p)
return 0;
/*
* Shortcut check for a thread sharing p->mm that is OOM_SCORE_ADJ_MIN
* so the entire heuristic doesn't need to be executed for something
* that cannot be killed.
*/
if (atomic_read(&p->mm->oom_disable_count)) {
task_unlock(p);
return 0;
}
/*
* The memory controller may have a limit of 0 bytes, so avoid a divide
* by zero, if necessary.
*/
if (!totalpages)
totalpages = 1;
/*
* 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) + p->mm->nr_ptes;
points += get_mm_counter(p->mm, swap_usage);
points *= 1000;
points /= totalpages;
task_unlock(p);
/*
* Root processes get 3% bonus, just like the __vm_enough_memory()
* implementation used by LSMs.
*/
if (has_capability_noaudit(p, CAP_SYS_ADMIN))
points -= 30;
/*
* /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may
* either completely disable oom killing or always prefer a certain
* task.
*/
points += p->signal->oom_score_adj;
/*
* Never return 0 for an eligible task that may be killed since it's
* possible that no single user task uses more than 0.1% of memory and
* no single admin tasks uses more than 3.0%.
*/
if (points <= 0)
return 1;
return (points < 1000) ? points : 1000;
}
