#ifdef CONFIG_NUMA
/**
* has_intersects_mems_allowed() - check task eligiblity for kill
- * @tsk: task struct of which task to consider
+ * @start: task struct of which task to consider
* @mask: nodemask passed to page allocator for mempolicy ooms
*
* 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.
*/
-static bool has_intersects_mems_allowed(struct task_struct *tsk,
+static bool has_intersects_mems_allowed(struct task_struct *start,
const nodemask_t *mask)
{
- struct task_struct *start = tsk;
+ struct task_struct *tsk;
+ bool ret = false;
- do {
+ rcu_read_lock();
+ for_each_thread(start, tsk) {
if (mask) {
/*
* If this is a mempolicy constrained oom, tsk's
* mempolicy intersects current, otherwise it may be
* needlessly killed.
*/
- if (mempolicy_nodemask_intersects(tsk, mask))
- return true;
+ ret = mempolicy_nodemask_intersects(tsk, mask);
} else {
/*
* This is not a mempolicy constrained oom, so only
* check the mems of tsk's cpuset.
*/
- if (cpuset_mems_allowed_intersects(current, tsk))
- return true;
+ ret = cpuset_mems_allowed_intersects(current, tsk);
}
- } while_each_thread(start, tsk);
+ if (ret)
+ break;
+ }
+ rcu_read_unlock();
- return false;
+ return ret;
}
#else
static bool has_intersects_mems_allowed(struct task_struct *tsk,
*/
struct task_struct *find_lock_task_mm(struct task_struct *p)
{
- struct task_struct *t = p;
+ struct task_struct *t;
- do {
+ rcu_read_lock();
+
+ for_each_thread(p, t) {
task_lock(t);
if (likely(t->mm))
- return t;
+ goto found;
task_unlock(t);
- } while_each_thread(p, t);
+ }
+ t = NULL;
+found:
+ rcu_read_unlock();
- return NULL;
+ return t;
}
/* return true if the task is not adequate as candidate victim task. */
* implementation used by LSMs.
*/
if (has_capability_noaudit(p, CAP_SYS_ADMIN))
- adj -= 30;
+ points -= (points * 3) / 100;
/* Normalize to oom_score_adj units */
adj *= totalpages / 1000;
unsigned long totalpages, const nodemask_t *nodemask,
bool force_kill)
{
- if (task->exit_state)
- return OOM_SCAN_CONTINUE;
if (oom_unkillable_task(task, NULL, nodemask))
return OOM_SCAN_CONTINUE;
unsigned long chosen_points = 0;
rcu_read_lock();
- do_each_thread(g, p) {
+ for_each_process_thread(g, p) {
unsigned int points;
switch (oom_scan_process_thread(p, totalpages, nodemask,
break;
};
points = oom_badness(p, NULL, nodemask, totalpages);
- if (points > chosen_points) {
- chosen = p;
- chosen_points = points;
- }
- } while_each_thread(g, p);
+ if (!points || points < chosen_points)
+ continue;
+ /* Prefer thread group leaders for display purposes */
+ if (points == chosen_points && thread_group_leader(chosen))
+ continue;
+
+ chosen = p;
+ chosen_points = points;
+ }
if (chosen)
get_task_struct(chosen);
rcu_read_unlock();
{
struct task_struct *victim = p;
struct task_struct *child;
- struct task_struct *t = p;
+ struct task_struct *t;
struct mm_struct *mm;
unsigned int victim_points = 0;
static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
* still freeing memory.
*/
read_lock(&tasklist_lock);
- do {
+ for_each_thread(p, t) {
list_for_each_entry(child, &t->children, sibling) {
unsigned int child_points;
get_task_struct(victim);
}
}
- } while_each_thread(p, t);
+ }
read_unlock(&tasklist_lock);
- rcu_read_lock();
p = find_lock_task_mm(victim);
if (!p) {
- rcu_read_unlock();
put_task_struct(victim);
return;
} else if (victim != p) {
* That thread will now get access to memory reserves since it has a
* pending fatal signal.
*/
+ rcu_read_lock();
for_each_process(p)
if (p->mm == mm && !same_thread_group(p, victim) &&
!(p->flags & PF_KTHREAD)) {
* if a parallel OOM killing is already taking place that includes a zone in
* the zonelist. Otherwise, locks all zones in the zonelist and returns 1.
*/
-int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
+bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_mask)
{
struct zoneref *z;
struct zone *zone;
- int ret = 1;
+ bool ret = true;
spin_lock(&zone_scan_lock);
- for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
+ for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
if (zone_is_oom_locked(zone)) {
- ret = 0;
+ ret = false;
goto out;
}
- }
- for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
- /*
- * Lock each zone in the zonelist under zone_scan_lock so a
- * parallel invocation of try_set_zonelist_oom() doesn't succeed
- * when it shouldn't.
- */
+ /*
+ * Lock each zone in the zonelist under zone_scan_lock so a parallel
+ * call to oom_zonelist_trylock() doesn't succeed when it shouldn't.
+ */
+ for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
zone_set_flag(zone, ZONE_OOM_LOCKED);
- }
out:
spin_unlock(&zone_scan_lock);
* allocation attempts with zonelists containing them may now recall the OOM
* killer, if necessary.
*/
-void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
+void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask)
{
struct zoneref *z;
struct zone *zone;
spin_lock(&zone_scan_lock);
- for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
+ for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
zone_clear_flag(zone, ZONE_OOM_LOCKED);
- }
spin_unlock(&zone_scan_lock);
}
if (mem_cgroup_oom_synchronize(true))
return;
- zonelist = node_zonelist(first_online_node, GFP_KERNEL);
- if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) {
+ zonelist = node_zonelist(first_memory_node, GFP_KERNEL);
+ if (oom_zonelist_trylock(zonelist, GFP_KERNEL)) {
out_of_memory(NULL, 0, 0, NULL, false);
- clear_zonelist_oom(zonelist, GFP_KERNEL);
+ oom_zonelist_unlock(zonelist, GFP_KERNEL);
}
}