return oc->order == -1;
}
+static inline bool is_memcg_oom(struct oom_control *oc)
+{
+ return oc->memcg != NULL;
+}
+
/* return true if the task is not adequate as candidate victim task. */
static bool oom_unkillable_task(struct task_struct *p,
struct mem_cgroup *memcg, const nodemask_t *nodemask)
*/
adj = (long)p->signal->oom_score_adj;
if (adj == OOM_SCORE_ADJ_MIN ||
- test_bit(MMF_OOM_REAPED, &p->mm->flags) ||
+ test_bit(MMF_OOM_SKIP, &p->mm->flags) ||
in_vfork(p)) {
task_unlock(p);
return 0;
return points > 0 ? points : 1;
}
+enum oom_constraint {
+ CONSTRAINT_NONE,
+ CONSTRAINT_CPUSET,
+ CONSTRAINT_MEMORY_POLICY,
+ CONSTRAINT_MEMCG,
+};
+
/*
* Determine the type of allocation constraint.
*/
-#ifdef CONFIG_NUMA
-static enum oom_constraint constrained_alloc(struct oom_control *oc,
- unsigned long *totalpages)
+static enum oom_constraint constrained_alloc(struct oom_control *oc)
{
struct zone *zone;
struct zoneref *z;
bool cpuset_limited = false;
int nid;
+ if (is_memcg_oom(oc)) {
+ oc->totalpages = mem_cgroup_get_limit(oc->memcg) ?: 1;
+ return CONSTRAINT_MEMCG;
+ }
+
/* Default to all available memory */
- *totalpages = totalram_pages + total_swap_pages;
+ oc->totalpages = totalram_pages + total_swap_pages;
+
+ if (!IS_ENABLED(CONFIG_NUMA))
+ return CONSTRAINT_NONE;
if (!oc->zonelist)
return CONSTRAINT_NONE;
*/
if (oc->nodemask &&
!nodes_subset(node_states[N_MEMORY], *oc->nodemask)) {
- *totalpages = total_swap_pages;
+ oc->totalpages = total_swap_pages;
for_each_node_mask(nid, *oc->nodemask)
- *totalpages += node_spanned_pages(nid);
+ oc->totalpages += node_spanned_pages(nid);
return CONSTRAINT_MEMORY_POLICY;
}
cpuset_limited = true;
if (cpuset_limited) {
- *totalpages = total_swap_pages;
+ oc->totalpages = total_swap_pages;
for_each_node_mask(nid, cpuset_current_mems_allowed)
- *totalpages += node_spanned_pages(nid);
+ oc->totalpages += node_spanned_pages(nid);
return CONSTRAINT_CPUSET;
}
return CONSTRAINT_NONE;
}
-#else
-static enum oom_constraint constrained_alloc(struct oom_control *oc,
- unsigned long *totalpages)
-{
- *totalpages = totalram_pages + total_swap_pages;
- return CONSTRAINT_NONE;
-}
-#endif
-enum oom_scan_t oom_scan_process_thread(struct oom_control *oc,
- struct task_struct *task)
+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))
- return OOM_SCAN_CONTINUE;
+ 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_REAPED because chances that it would release
+ * the task has MMF_OOM_SKIP because chances that it would release
* any memory is quite low.
*/
- if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims)) {
- struct task_struct *p = find_lock_task_mm(task);
- enum oom_scan_t ret = OOM_SCAN_ABORT;
-
- if (p) {
- if (test_bit(MMF_OOM_REAPED, &p->mm->flags))
- ret = OOM_SCAN_CONTINUE;
- task_unlock(p);
- }
-
- return ret;
+ 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))
- return OOM_SCAN_SELECT;
+ if (oom_task_origin(task)) {
+ points = ULONG_MAX;
+ goto select;
+ }
- return OOM_SCAN_OK;
+ 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;
}
/*
- * Simple selection loop. We chose the process with the highest
- * number of 'points'. Returns -1 on scan abort.
+ * 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 struct task_struct *select_bad_process(struct oom_control *oc,
- unsigned int *ppoints, unsigned long totalpages)
+static void select_bad_process(struct oom_control *oc)
{
- struct task_struct *p;
- struct task_struct *chosen = NULL;
- unsigned long chosen_points = 0;
-
- rcu_read_lock();
- for_each_process(p) {
- unsigned int points;
-
- switch (oom_scan_process_thread(oc, p)) {
- case OOM_SCAN_SELECT:
- chosen = p;
- chosen_points = ULONG_MAX;
- /* fall through */
- case OOM_SCAN_CONTINUE:
- continue;
- case OOM_SCAN_ABORT:
- rcu_read_unlock();
- return (struct task_struct *)(-1UL);
- case OOM_SCAN_OK:
- break;
- };
- points = oom_badness(p, NULL, oc->nodemask, totalpages);
- if (!points || points < chosen_points)
- continue;
+ if (is_memcg_oom(oc))
+ mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc);
+ else {
+ struct task_struct *p;
- chosen = p;
- chosen_points = points;
+ rcu_read_lock();
+ for_each_process(p)
+ if (oom_evaluate_task(p, oc))
+ break;
+ rcu_read_unlock();
}
- if (chosen)
- get_task_struct(chosen);
- rcu_read_unlock();
- *ppoints = chosen_points * 1000 / totalpages;
- return chosen;
+ oc->chosen_points = oc->chosen_points * 1000 / oc->totalpages;
}
/**
static atomic_t oom_victims = ATOMIC_INIT(0);
static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait);
-bool oom_killer_disabled __read_mostly;
+static bool oom_killer_disabled __read_mostly;
#define K(x) ((x) << (PAGE_SHIFT-10))
static struct task_struct *oom_reaper_list;
static DEFINE_SPINLOCK(oom_reaper_lock);
-static bool __oom_reap_task(struct task_struct *tsk)
+static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
{
struct mmu_gather tlb;
struct vm_area_struct *vma;
- struct mm_struct *mm = NULL;
- struct task_struct *p;
struct zap_details details = {.check_swap_entries = true,
.ignore_dirty = true};
bool ret = true;
/*
* We have to make sure to not race with the victim exit path
* and cause premature new oom victim selection:
- * __oom_reap_task exit_mm
+ * __oom_reap_task_mm exit_mm
* mmget_not_zero
* mmput
* atomic_dec_and_test
*/
mutex_lock(&oom_lock);
- /*
- * Make sure we find the associated mm_struct even when the particular
- * thread has already terminated and cleared its mm.
- * We might have race with exit path so consider our work done if there
- * is no mm.
- */
- p = find_lock_task_mm(tsk);
- if (!p)
- goto unlock_oom;
- mm = p->mm;
- atomic_inc(&mm->mm_count);
- task_unlock(p);
-
if (!down_read_trylock(&mm->mmap_sem)) {
ret = false;
- goto mm_drop;
+ goto unlock_oom;
}
/*
*/
if (!mmget_not_zero(mm)) {
up_read(&mm->mmap_sem);
- goto mm_drop;
+ goto unlock_oom;
}
tlb_gather_mmu(&tlb, mm, 0, -1);
K(get_mm_counter(mm, MM_SHMEMPAGES)));
up_read(&mm->mmap_sem);
- /*
- * This task can be safely ignored because we cannot do much more
- * to release its memory.
- */
- set_bit(MMF_OOM_REAPED, &mm->flags);
/*
* Drop our reference but make sure the mmput slow path is called from a
* different context because we shouldn't risk we get stuck there and
* put the oom_reaper out of the way.
*/
mmput_async(mm);
-mm_drop:
- mmdrop(mm);
unlock_oom:
mutex_unlock(&oom_lock);
return ret;
static void oom_reap_task(struct task_struct *tsk)
{
int attempts = 0;
+ struct mm_struct *mm = tsk->signal->oom_mm;
/* Retry the down_read_trylock(mmap_sem) a few times */
- while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task(tsk))
+ while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task_mm(tsk, mm))
schedule_timeout_idle(HZ/10);
- if (attempts > MAX_OOM_REAP_RETRIES) {
- struct task_struct *p;
-
- pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
- task_pid_nr(tsk), tsk->comm);
+ if (attempts <= MAX_OOM_REAP_RETRIES)
+ goto done;
- /*
- * If we've already tried to reap this task in the past and
- * failed it probably doesn't make much sense to try yet again
- * so hide the mm from the oom killer so that it can move on
- * to another task with a different mm struct.
- */
- p = find_lock_task_mm(tsk);
- if (p) {
- if (test_and_set_bit(MMF_OOM_NOT_REAPABLE, &p->mm->flags)) {
- pr_info("oom_reaper: giving up pid:%d (%s)\n",
- task_pid_nr(tsk), tsk->comm);
- set_bit(MMF_OOM_REAPED, &p->mm->flags);
- }
- task_unlock(p);
- }
- debug_show_all_locks();
- }
+ pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
+ task_pid_nr(tsk), tsk->comm);
+ debug_show_all_locks();
+done:
/*
* Clear TIF_MEMDIE because the task shouldn't be sitting on a
* reasonably reclaimable memory anymore or it is not a good candidate
tsk->oom_reaper_list = NULL;
exit_oom_victim(tsk);
+ /*
+ * Hide this mm from OOM killer because it has been either reaped or
+ * somebody can't call up_write(mmap_sem).
+ */
+ set_bit(MMF_OOM_SKIP, &mm->flags);
+
/* Drop a reference taken by wake_oom_reaper */
put_task_struct(tsk);
}
return 0;
}
-void wake_oom_reaper(struct task_struct *tsk)
+static void wake_oom_reaper(struct task_struct *tsk)
{
if (!oom_reaper_th)
return;
return 0;
}
subsys_initcall(oom_init)
-#endif
+#else
+static inline void wake_oom_reaper(struct task_struct *tsk)
+{
+}
+#endif /* CONFIG_MMU */
/**
* mark_oom_victim - mark the given task as OOM victim
*
* 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).
*/
-void mark_oom_victim(struct task_struct *tsk)
+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;
- atomic_inc(&tsk->signal->oom_victims);
+
+ /* oom_mm is bound to the signal struct life time. */
+ if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm))
+ atomic_inc(&tsk->signal->oom_mm->mm_count);
+
/*
* Make sure that the task is woken up from uninterruptible sleep
* if it is frozen because OOM killer wouldn't be able to free
{
if (!test_and_clear_tsk_thread_flag(tsk, TIF_MEMDIE))
return;
- atomic_dec(&tsk->signal->oom_victims);
if (!atomic_dec_return(&oom_victims))
wake_up_all(&oom_victims_wait);
* Caller has to make sure that task->mm is stable (hold task_lock or
* it operates on the current).
*/
-bool task_will_free_mem(struct task_struct *task)
+static bool task_will_free_mem(struct task_struct *task)
{
struct mm_struct *mm = task->mm;
struct task_struct *p;
* 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_REAPED, &mm->flags))
+ if (test_bit(MMF_OOM_SKIP, &mm->flags))
return false;
if (atomic_read(&mm->mm_users) <= 1)
return true;
/*
- * This is really pessimistic but we do not have any reliable way
- * to check that external processes share with our mm
+ * 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) {
return ret;
}
-/*
- * Must be called while holding a reference to p, which will be released upon
- * returning.
- */
-void oom_kill_process(struct oom_control *oc, struct task_struct *p,
- unsigned int points, unsigned long totalpages,
- const char *message)
+static void oom_kill_process(struct oom_control *oc, const char *message)
{
+ struct task_struct *p = oc->chosen;
+ unsigned int points = oc->chosen_points;
struct task_struct *victim = p;
struct task_struct *child;
struct task_struct *t;
* oom_badness() returns 0 if the thread is unkillable
*/
child_points = oom_badness(child,
- oc->memcg, oc->nodemask, totalpages);
+ oc->memcg, oc->nodemask, oc->totalpages);
if (child_points > victim_points) {
put_task_struct(victim);
victim = child;
* killer to guarantee OOM forward progress.
*/
can_oom_reap = false;
- set_bit(MMF_OOM_REAPED, &mm->flags);
+ 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);
/*
* Determines whether the kernel must panic because of the panic_on_oom sysctl.
*/
-void check_panic_on_oom(struct oom_control *oc, enum oom_constraint constraint)
+static void check_panic_on_oom(struct oom_control *oc,
+ enum oom_constraint constraint)
{
if (likely(!sysctl_panic_on_oom))
return;
*/
bool out_of_memory(struct oom_control *oc)
{
- struct task_struct *p;
- unsigned long totalpages;
unsigned long freed = 0;
- unsigned int uninitialized_var(points);
enum oom_constraint constraint = CONSTRAINT_NONE;
if (oom_killer_disabled)
return false;
- blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
- if (freed > 0)
- /* Got some memory back in the last second. */
- return true;
+ 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
/*
* Check if there were limitations on the allocation (only relevant for
- * NUMA) that may require different handling.
+ * NUMA and memcg) that may require different handling.
*/
- constraint = constrained_alloc(oc, &totalpages);
+ constraint = constrained_alloc(oc);
if (constraint != CONSTRAINT_MEMORY_POLICY)
oc->nodemask = NULL;
check_panic_on_oom(oc, constraint);
- if (sysctl_oom_kill_allocating_task && current->mm &&
- !oom_unkillable_task(current, NULL, oc->nodemask) &&
+ 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);
- oom_kill_process(oc, current, 0, totalpages,
- "Out of memory (oom_kill_allocating_task)");
+ oc->chosen = current;
+ oom_kill_process(oc, "Out of memory (oom_kill_allocating_task)");
return true;
}
- p = select_bad_process(oc, &points, totalpages);
+ select_bad_process(oc);
/* Found nothing?!?! Either we hang forever, or we panic. */
- if (!p && !is_sysrq_oom(oc)) {
+ if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
dump_header(oc, NULL);
panic("Out of memory and no killable processes...\n");
}
- if (p && p != (void *)-1UL) {
- oom_kill_process(oc, p, points, totalpages, "Out of memory");
+ if (oc->chosen && oc->chosen != (void *)-1UL) {
+ oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" :
+ "Memory cgroup out of memory");
/*
* Give the killed process a good chance to exit before trying
* to allocate memory again.
*/
schedule_timeout_killable(1);
}
- return true;
+ return !!oc->chosen;
}
/*
projects / cascardo / linux.git / blobdiff