1 files changed, 75 insertions, 68 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 5a58778c91d4..eda2e2a0bdc6 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -64,21 +64,33 @@ int sysctl_oom_dump_tasks = 1;
  */
 DEFINE_MUTEX(oom_lock);
 
+static inline bool is_memcg_oom(struct oom_control *oc)
+{
+	return oc->memcg != NULL;
+}
+
 #ifdef CONFIG_NUMA
 /**
- * has_intersects_mems_allowed() - check task eligiblity for kill
+ * oom_cpuset_eligible() - check task eligiblity for kill
  * @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.
+ *
+ * This function is assuming oom-killer context and 'current' has triggered
+ * the oom-killer.
  */
-static bool has_intersects_mems_allowed(struct task_struct *start,
-					const nodemask_t *mask)
+static bool oom_cpuset_eligible(struct task_struct *start,
+				struct oom_control *oc)
 {
 	struct task_struct *tsk;
 	bool ret = false;
+	const nodemask_t *mask = oc->nodemask;
+
+	if (is_memcg_oom(oc))
+		return true;
 
 	rcu_read_lock();
 	for_each_thread(start, tsk) {
@@ -105,8 +117,7 @@ static bool has_intersects_mems_allowed(struct task_struct *start,
 	return ret;
 }
 #else
-static bool has_intersects_mems_allowed(struct task_struct *tsk,
-					const nodemask_t *mask)
+static bool oom_cpuset_eligible(struct task_struct *tsk, struct oom_control *oc)
 {
 	return true;
 }
@@ -146,28 +157,13 @@ static inline bool is_sysrq_oom(struct oom_control *oc)
 	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)
+static bool oom_unkillable_task(struct task_struct *p)
 {
 	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;
 }
 
@@ -194,20 +190,17 @@ static bool is_dump_unreclaim_slabs(void)
  * 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
- * @memcg: task's memory controller, if constrained
- * @nodemask: nodemask passed to page allocator for mempolicy ooms
  *
  * 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 long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
-			  const nodemask_t *nodemask, unsigned long totalpages)
+unsigned long oom_badness(struct task_struct *p, unsigned long totalpages)
 {
 	long points;
 	long adj;
 
-	if (oom_unkillable_task(p, memcg, nodemask))
+	if (oom_unkillable_task(p))
 		return 0;
 
 	p = find_lock_task_mm(p);
@@ -318,7 +311,11 @@ 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))
+	if (oom_unkillable_task(task))
+		goto next;
+
+	/* p may not have freeable memory in nodemask */
+	if (!is_memcg_oom(oc) && !oom_cpuset_eligible(task, oc))
 		goto next;
 
 	/*
@@ -342,13 +339,10 @@ static int oom_evaluate_task(struct task_struct *task, void *arg)
 		goto select;
 	}
 
-	points = oom_badness(task, NULL, oc->nodemask, oc->totalpages);
+	points = oom_badness(task, 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);
@@ -381,14 +375,44 @@ static void select_bad_process(struct oom_control *oc)
 				break;
 		rcu_read_unlock();
 	}
+}
 
-	oc->chosen_points = oc->chosen_points * 1000 / oc->totalpages;
+static int dump_task(struct task_struct *p, void *arg)
+{
+	struct oom_control *oc = arg;
+	struct task_struct *task;
+
+	if (oom_unkillable_task(p))
+		return 0;
+
+	/* p may not have freeable memory in nodemask */
+	if (!is_memcg_oom(oc) && !oom_cpuset_eligible(p, oc))
+		return 0;
+
+	task = find_lock_task_mm(p);
+	if (!task) {
+		/*
+		 * This is a kthread or all of p's threads have already
+		 * detached their mm's.  There's no need to report
+		 * them; they can't be oom killed anyway.
+		 */
+		return 0;
+	}
+
+	pr_info("[%7d] %5d %5d %8lu %8lu %8ld %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),
+		mm_pgtables_bytes(task->mm),
+		get_mm_counter(task->mm, MM_SWAPENTS),
+		task->signal->oom_score_adj, task->comm);
+	task_unlock(task);
+
+	return 0;
 }
 
 /**
  * dump_tasks - dump current memory state of all system tasks
- * @memcg: current's memory controller, if constrained
- * @nodemask: nodemask passed to page allocator for mempolicy ooms
+ * @oc: pointer to struct oom_control
  *
  * Dumps the current memory state of all eligible tasks.  Tasks not in the same
  * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
@@ -396,37 +420,21 @@ static void select_bad_process(struct oom_control *oc)
  * State information includes task's pid, uid, tgid, vm size, rss,
  * pgtables_bytes, swapents, oom_score_adj value, and name.
  */
-static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
+static void dump_tasks(struct oom_control *oc)
 {
-	struct task_struct *p;
-	struct task_struct *task;
-
 	pr_info("Tasks state (memory values in pages):\n");
 	pr_info("[  pid  ]   uid  tgid total_vm      rss pgtables_bytes swapents oom_score_adj name\n");
-	rcu_read_lock();
-	for_each_process(p) {
-		if (oom_unkillable_task(p, memcg, nodemask))
-			continue;
 
-		task = find_lock_task_mm(p);
-		if (!task) {
-			/*
-			 * This is a kthread or all of p's threads have already
-			 * detached their mm's.  There's no need to report
-			 * them; they can't be oom killed anyway.
-			 */
-			continue;
-		}
+	if (is_memcg_oom(oc))
+		mem_cgroup_scan_tasks(oc->memcg, dump_task, oc);
+	else {
+		struct task_struct *p;
 
-		pr_info("[%7d] %5d %5d %8lu %8lu %8ld %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),
-			mm_pgtables_bytes(task->mm),
-			get_mm_counter(task->mm, MM_SWAPENTS),
-			task->signal->oom_score_adj, task->comm);
-		task_unlock(task);
+		rcu_read_lock();
+		for_each_process(p)
+			dump_task(p, oc);
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
 }
 
 static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim)
@@ -458,7 +466,7 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
 			dump_unreclaimable_slab();
 	}
 	if (sysctl_oom_dump_tasks)
-		dump_tasks(oc->memcg, oc->nodemask);
+		dump_tasks(oc);
 	if (p)
 		dump_oom_summary(oc, p);
 }
@@ -987,8 +995,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 /*
  * 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)
+static void check_panic_on_oom(struct oom_control *oc)
 {
 	if (likely(!sysctl_panic_on_oom))
 		return;
@@ -998,7 +1005,7 @@ static void check_panic_on_oom(struct oom_control *oc,
 		 * does not panic for cpuset, mempolicy, or memcg allocation
 		 * failures.
 		 */
-		if (constraint != CONSTRAINT_NONE)
+		if (oc->constraint != CONSTRAINT_NONE)
 			return;
 	}
 	/* Do not panic for oom kills triggered by sysrq */
@@ -1035,7 +1042,6 @@ EXPORT_SYMBOL_GPL(unregister_oom_notifier);
 bool out_of_memory(struct oom_control *oc)
 {
 	unsigned long freed = 0;
-	enum oom_constraint constraint = CONSTRAINT_NONE;
 
 	if (oom_killer_disabled)
 		return false;
@@ -1071,13 +1077,14 @@ bool out_of_memory(struct oom_control *oc)
 	 * 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->constraint = constrained_alloc(oc);
+	if (oc->constraint != CONSTRAINT_MEMORY_POLICY)
 		oc->nodemask = NULL;
-	check_panic_on_oom(oc, constraint);
+	check_panic_on_oom(oc);
 
 	if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task &&
-	    current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) &&
+	    current->mm && !oom_unkillable_task(current) &&
+	    oom_cpuset_eligible(current, oc) &&
 	    current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
 		get_task_struct(current);
 		oc->chosen = current;