static int oom_evaluate_task(struct task_struct *task, void *arg)
{
struct oom_control *oc = arg;
unsigned long points;
if (oom_unkillable_task(task, NULL, oc->nodemask))
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 = ULONG_MAX;
goto select;
}
points = oom_badness(task, NULL, oc->nodemask, oc->totalpages);
if (!points || points < oc->chosen_points)
goto next;
/* Prefer thread group leaders for display purposes */
if (points == oc->chosen_points && thread_group_leader(oc->chosen))
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;
}
/*
* Determines whether the kernel must panic because of the panic_on_oom sysctl.
*/
static void check_panic_on_oom(struct oom_control *oc,
enum oom_constraint constraint)
{
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 (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");
}
enum oom_scan_t oom_scan_process_thread(struct oom_control *oc,
struct task_struct *task, unsigned long totalpages)
{
if (oom_unkillable_task(task, NULL, oc->nodemask))
return OOM_SCAN_CONTINUE;
/*
* This task already has access to memory reserves and is being killed.
* Don't allow any other task to have access to the reserves.
*/
if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims))
return OOM_SCAN_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))
return OOM_SCAN_SELECT;
return OOM_SCAN_OK;
}
/**
* 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;
enum oom_constraint constraint = CONSTRAINT_NONE;
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.
*/
if (oc->gfp_mask && !(oc->gfp_mask & __GFP_FS))
return true;
/*
* Check if there were limitations on the allocation (only relevant for
* NUMA and memcg) that may require different handling.
*/
constraint = constrained_alloc(oc);
if (constraint != CONSTRAINT_MEMORY_POLICY)
oc->nodemask = NULL;
check_panic_on_oom(oc, constraint);
if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task &&
current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) &&
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;
}