/* 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)
+ struct mem_cgroup *memcg, const nodemask_t *nodemask)
{
if (is_global_init(p))
return true;
* 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) + atomic_long_read(&p->mm->nr_ptes) +
- get_mm_counter(p->mm, MM_SWAPENTS);
+ points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) +
+ atomic_long_read(&p->mm->nr_ptes) + mm_nr_pmds(p->mm);
task_unlock(p);
/*
/* Check this allocation failure is caused by cpuset's wall function */
for_each_zone_zonelist_nodemask(zone, z, zonelist,
high_zoneidx, nodemask)
- if (!cpuset_zone_allowed_softwall(zone, gfp_mask))
+ if (!cpuset_zone_allowed(zone, gfp_mask))
cpuset_limited = true;
if (cpuset_limited) {
* Don't allow any other task to have access to the reserves.
*/
if (test_tsk_thread_flag(task, TIF_MEMDIE)) {
- if (unlikely(frozen(task)))
- __thaw_task(task);
if (!force_kill)
return OOM_SCAN_ABORT;
}
if (oom_task_origin(task))
return OOM_SCAN_SELECT;
- if (task->flags & PF_EXITING && !force_kill) {
- /*
- * If this task is not being ptraced on exit, then wait for it
- * to finish before killing some other task unnecessarily.
- */
- if (!(task->group_leader->ptrace & PT_TRACE_EXIT))
- return OOM_SCAN_ABORT;
- }
+ if (task_will_free_mem(task) && !force_kill)
+ return OOM_SCAN_ABORT;
+
return OOM_SCAN_OK;
}
* State information includes task's pid, uid, tgid, vm size, rss, nr_ptes,
* swapents, oom_score_adj value, and name.
*/
-static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemask)
+static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
{
struct task_struct *p;
struct task_struct *task;
- pr_info("[ pid ] uid tgid total_vm rss nr_ptes swapents oom_score_adj name\n");
+ pr_info("[ pid ] uid tgid total_vm rss nr_ptes nr_pmds swapents oom_score_adj name\n");
rcu_read_lock();
for_each_process(p) {
if (oom_unkillable_task(p, memcg, nodemask))
continue;
}
- pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu %5hd %s\n",
+ pr_info("[%5d] %5d %5d %8lu %8lu %7ld %7ld %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),
atomic_long_read(&task->mm->nr_ptes),
+ mm_nr_pmds(task->mm),
get_mm_counter(task->mm, MM_SWAPENTS),
task->signal->oom_score_adj, task->comm);
task_unlock(task);
}
/*
- * Number of OOM killer invocations (including memcg OOM killer).
- * Primarily used by PM freezer to check for potential races with
- * OOM killed frozen task.
+ * Number of OOM victims in flight
*/
-static atomic_t oom_kills = ATOMIC_INIT(0);
+static atomic_t oom_victims = ATOMIC_INIT(0);
+static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait);
+
+bool oom_killer_disabled __read_mostly;
+static DECLARE_RWSEM(oom_sem);
-int oom_kills_count(void)
+/**
+ * mark_tsk_oom_victim - marks the given taks as OOM victim.
+ * @tsk: task to mark
+ *
+ * Has to be called with oom_sem taken for read and never after
+ * oom has been disabled already.
+ */
+void mark_tsk_oom_victim(struct task_struct *tsk)
{
- return atomic_read(&oom_kills);
+ WARN_ON(oom_killer_disabled);
+ /* OOM killer might race with memcg OOM */
+ if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE))
+ return;
+ /*
+ * 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);
}
-void note_oom_kill(void)
+/**
+ * unmark_oom_victim - unmarks the current task as OOM victim.
+ *
+ * Wakes up all waiters in oom_killer_disable()
+ */
+void unmark_oom_victim(void)
{
- atomic_inc(&oom_kills);
+ if (!test_and_clear_thread_flag(TIF_MEMDIE))
+ return;
+
+ down_read(&oom_sem);
+ /*
+ * There is no need to signal the lasst oom_victim if there
+ * is nobody who cares.
+ */
+ if (!atomic_dec_return(&oom_victims) && oom_killer_disabled)
+ wake_up_all(&oom_victims_wait);
+ up_read(&oom_sem);
+}
+
+/**
+ * oom_killer_disable - disable OOM killer
+ *
+ * Forces all page allocations to fail rather than trigger OOM killer.
+ * Will block and wait until all OOM victims are killed.
+ *
+ * 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(void)
+{
+ /*
+ * Make sure to not race with an ongoing OOM killer
+ * and that the current is not the victim.
+ */
+ down_write(&oom_sem);
+ if (test_thread_flag(TIF_MEMDIE)) {
+ up_write(&oom_sem);
+ return false;
+ }
+
+ oom_killer_disabled = true;
+ up_write(&oom_sem);
+
+ wait_event(oom_victims_wait, !atomic_read(&oom_victims));
+
+ return true;
+}
+
+/**
+ * oom_killer_enable - enable OOM killer
+ */
+void oom_killer_enable(void)
+{
+ down_write(&oom_sem);
+ oom_killer_disabled = false;
+ up_write(&oom_sem);
}
#define K(x) ((x) << (PAGE_SHIFT-10))
* 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) {
- set_tsk_thread_flag(p, TIF_MEMDIE);
+ task_lock(p);
+ if (p->mm && task_will_free_mem(p)) {
+ mark_tsk_oom_victim(p);
+ task_unlock(p);
put_task_struct(p);
return;
}
+ task_unlock(p);
if (__ratelimit(&oom_rs))
dump_header(p, gfp_mask, order, memcg, nodemask);
/* mm cannot safely be dereferenced after task_unlock(victim) */
mm = victim->mm;
+ mark_tsk_oom_victim(victim);
pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
K(get_mm_counter(victim->mm, MM_ANONPAGES)),
}
rcu_read_unlock();
- set_tsk_thread_flag(victim, TIF_MEMDIE);
do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
put_task_struct(victim);
}
}
/**
- * out_of_memory - kill the "best" process when we run out of memory
+ * __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
* 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,
+static void __out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
int order, nodemask_t *nodemask, bool force_kill)
{
const nodemask_t *mpol_mask;
* 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.
+ *
+ * But don't select if current has already released its mm and cleared
+ * TIF_MEMDIE flag at exit_mm(), otherwise an OOM livelock may occur.
*/
- if (fatal_signal_pending(current) || current->flags & PF_EXITING) {
- set_thread_flag(TIF_MEMDIE);
+ if (current->mm &&
+ (fatal_signal_pending(current) || task_will_free_mem(current))) {
+ mark_tsk_oom_victim(current);
return;
}
schedule_timeout_killable(1);
}
+/**
+ * out_of_memory - tries to invoke OOM killer.
+ * @zonelist: zonelist pointer
+ * @gfp_mask: memory allocation flags
+ * @order: amount of memory being requested as a power of 2
+ * @nodemask: nodemask passed to page allocator
+ * @force_kill: true if a task must be killed, even if others are exiting
+ *
+ * invokes __out_of_memory if the OOM is not disabled by oom_killer_disable()
+ * when it returns false. Otherwise returns true.
+ */
+bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
+ int order, nodemask_t *nodemask, bool force_kill)
+{
+ bool ret = false;
+
+ down_read(&oom_sem);
+ if (!oom_killer_disabled) {
+ __out_of_memory(zonelist, gfp_mask, order, nodemask, force_kill);
+ ret = true;
+ }
+ up_read(&oom_sem);
+
+ return ret;
+}
+
/*
* The pagefault handler calls here because it is out of memory, so kill a
* memory-hogging task. If any populated zone has ZONE_OOM_LOCKED set, a
{
struct zonelist *zonelist;
+ down_read(&oom_sem);
if (mem_cgroup_oom_synchronize(true))
- return;
+ goto unlock;
zonelist = node_zonelist(first_memory_node, GFP_KERNEL);
if (oom_zonelist_trylock(zonelist, GFP_KERNEL)) {
- out_of_memory(NULL, 0, 0, NULL, false);
+ if (!oom_killer_disabled)
+ __out_of_memory(NULL, 0, 0, NULL, false);
+ else
+ /*
+ * There shouldn't be any user tasks runable while the
+ * OOM killer is disabled so the current task has to
+ * be a racing OOM victim for which oom_killer_disable()
+ * is waiting for.
+ */
+ WARN_ON(test_thread_flag(TIF_MEMDIE));
+
oom_zonelist_unlock(zonelist, GFP_KERNEL);
}
+unlock:
+ up_read(&oom_sem);
}