1 files changed, 254 insertions, 313 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 7dcca55ede7..3291e82d435 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -26,11 +26,18 @@
 #include <linux/timex.h>
 #include <linux/jiffies.h>
 #include <linux/cpuset.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/notifier.h>
 #include <linux/memcontrol.h>
 #include <linux/mempolicy.h>
 #include <linux/security.h>
+#include <linux/ptrace.h>
+#include <linux/freezer.h>
+#include <linux/ftrace.h>
+#include <linux/ratelimit.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/oom.h>
 
 int sysctl_panic_on_oom;
 int sysctl_oom_kill_allocating_task;
@@ -40,19 +47,21 @@ static DEFINE_SPINLOCK(zone_scan_lock);
 #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
@@ -60,19 +69,20 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
 			 * 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,
@@ -83,24 +93,6 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
 #endif /* CONFIG_NUMA */
 
 /*
- * If this is a system OOM (not a memcg OOM) and the task selected to be
- * killed is not already running at high (RT) priorities, speed up the
- * recovery by boosting the dying task to the lowest FIFO priority.
- * That helps with the recovery and avoids interfering with RT tasks.
- */
-static void boost_dying_task_prio(struct task_struct *p,
-				  struct mem_cgroup *mem)
-{
-	struct sched_param param = { .sched_priority = 1 };
-
-	if (mem)
-		return;
-
-	if (!rt_task(p))
-		sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
-}
-
-/*
  * The process p may have detached its own ->mm while exiting or through
  * use_mm(), but one or more of its subthreads may still have a valid
  * pointer.  Return p, or any of its subthreads with a valid ->mm, with
@@ -108,21 +100,26 @@ static void boost_dying_task_prio(struct task_struct *p,
  */
 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. */
 static bool oom_unkillable_task(struct task_struct *p,
-		const struct mem_cgroup *mem, const nodemask_t *nodemask)
+		const struct mem_cgroup *memcg, const nodemask_t *nodemask)
 {
 	if (is_global_init(p))
 		return true;
@@ -130,7 +127,7 @@ static bool oom_unkillable_task(struct task_struct *p,
 		return true;
 
 	/* When mem_cgroup_out_of_memory() and p is not member of the group */
-	if (mem && !task_in_mem_cgroup(p, mem))
+	if (memcg && !task_in_mem_cgroup(p, memcg))
 		return true;
 
 	/* p may not have freeable memory in nodemask */
@@ -149,50 +146,31 @@ static bool oom_unkillable_task(struct task_struct *p,
  * predictable as possible.  The goal is to return the highest value for the
  * task consuming the most memory to avoid subsequent oom failures.
  */
-unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
-		      const nodemask_t *nodemask, unsigned long totalpages)
+unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
+			  const nodemask_t *nodemask, unsigned long totalpages)
 {
-	int points;
+	long points;
+	long adj;
 
-	if (oom_unkillable_task(p, mem, nodemask))
+	if (oom_unkillable_task(p, memcg, nodemask))
 		return 0;
 
 	p = find_lock_task_mm(p);
 	if (!p)
 		return 0;
 
-	/*
-	 * Shortcut check for a thread sharing p->mm that is OOM_SCORE_ADJ_MIN
-	 * so the entire heuristic doesn't need to be executed for something
-	 * that cannot be killed.
-	 */
-	if (atomic_read(&p->mm->oom_disable_count)) {
+	adj = (long)p->signal->oom_score_adj;
+	if (adj == OOM_SCORE_ADJ_MIN) {
 		task_unlock(p);
 		return 0;
 	}
 
 	/*
-	 * When the PF_OOM_ORIGIN bit is set, it indicates the task should have
-	 * priority for oom killing.
-	 */
-	if (p->flags & PF_OOM_ORIGIN) {
-		task_unlock(p);
-		return 1000;
-	}
-
-	/*
-	 * The memory controller may have a limit of 0 bytes, so avoid a divide
-	 * by zero, if necessary.
-	 */
-	if (!totalpages)
-		totalpages = 1;
-
-	/*
 	 * The baseline for the badness score is the proportion of RAM that each
-	 * task's rss and swap space use.
+	 * task's rss, pagetable and swap space use.
 	 */
-	points = (get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS)) * 1000 /
-			totalpages;
+	points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) +
+		 get_mm_counter(p->mm, MM_SWAPENTS);
 	task_unlock(p);
 
 	/*
@@ -200,23 +178,17 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 	 * implementation used by LSMs.
 	 */
 	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
-		points -= 30;
+		points -= (points * 3) / 100;
 
-	/*
-	 * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may
-	 * either completely disable oom killing or always prefer a certain
-	 * task.
-	 */
-	points += p->signal->oom_score_adj;
+	/* Normalize to oom_score_adj units */
+	adj *= totalpages / 1000;
+	points += adj;
 
 	/*
-	 * Never return 0 for an eligible task that may be killed since it's
-	 * possible that no single user task uses more than 0.1% of memory and
-	 * no single admin tasks uses more than 3.0%.
+	 * Never return 0 for an eligible task regardless of the root bonus and
+	 * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
 	 */
-	if (points <= 0)
-		return 1;
-	return (points < 1000) ? points : 1000;
+	return points > 0 ? points : 1;
 }
 
 /*
@@ -251,7 +223,7 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 	 * the page allocator means a mempolicy is in effect.  Cpuset policy
 	 * is enforced in get_page_from_freelist().
 	 */
-	if (nodemask && !nodes_subset(node_states[N_HIGH_MEMORY], *nodemask)) {
+	if (nodemask && !nodes_subset(node_states[N_MEMORY], *nodemask)) {
 		*totalpages = total_swap_pages;
 		for_each_node_mask(nid, *nodemask)
 			*totalpages += node_spanned_pages(nid);
@@ -282,87 +254,116 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 }
 #endif
 
+enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
+		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;
+
+	/*
+	 * 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 (test_tsk_thread_flag(task, TIF_MEMDIE)) {
+		if (unlikely(frozen(task)))
+			__thaw_task(task);
+		if (!force_kill)
+			return OOM_SCAN_ABORT;
+	}
+	if (!task->mm)
+		return OOM_SCAN_CONTINUE;
+
+	/*
+	 * 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 (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;
+	}
+	return OOM_SCAN_OK;
+}
+
 /*
  * Simple selection loop. We chose the process with the highest
- * number of 'points'. We expect the caller will lock the tasklist.
+ * number of 'points'.  Returns -1 on scan abort.
  *
  * (not docbooked, we don't want this one cluttering up the manual)
  */
 static struct task_struct *select_bad_process(unsigned int *ppoints,
-		unsigned long totalpages, struct mem_cgroup *mem,
-		const nodemask_t *nodemask)
+		unsigned long totalpages, const nodemask_t *nodemask,
+		bool force_kill)
 {
-	struct task_struct *p;
+	struct task_struct *g, *p;
 	struct task_struct *chosen = NULL;
-	*ppoints = 0;
+	unsigned long chosen_points = 0;
 
-	for_each_process(p) {
+	rcu_read_lock();
+	for_each_process_thread(g, p) {
 		unsigned int points;
 
-		if (oom_unkillable_task(p, mem, nodemask))
-			continue;
-
-		/*
-		 * This task already has access to memory reserves and is
-		 * being killed. Don't allow any other task access to the
-		 * memory reserve.
-		 *
-		 * Note: this may have a chance of deadlock if it gets
-		 * blocked waiting for another task which itself is waiting
-		 * for memory. Is there a better alternative?
-		 */
-		if (test_tsk_thread_flag(p, TIF_MEMDIE))
-			return ERR_PTR(-1UL);
-
-		/*
-		 * This is in the process of releasing memory so wait for it
-		 * to finish before killing some other task by mistake.
-		 *
-		 * However, if p is the current task, we allow the 'kill' to
-		 * go ahead if it is exiting: this will simply set TIF_MEMDIE,
-		 * which will allow it to gain access to memory reserves in
-		 * the process of exiting and releasing its resources.
-		 * Otherwise we could get an easy OOM deadlock.
-		 */
-		if (thread_group_empty(p) && (p->flags & PF_EXITING) && p->mm) {
-			if (p != current)
-				return ERR_PTR(-1UL);
-
+		switch (oom_scan_process_thread(p, totalpages, nodemask,
+						force_kill)) {
+		case OOM_SCAN_SELECT:
 			chosen = p;
-			*ppoints = 1000;
-		}
+			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, nodemask, totalpages);
+		if (!points || points < chosen_points)
+			continue;
+		/* Prefer thread group leaders for display purposes */
+		if (points == chosen_points && thread_group_leader(chosen))
+			continue;
 
-		points = oom_badness(p, mem, nodemask, totalpages);
-		if (points > *ppoints) {
-			chosen = p;
-			*ppoints = points;
-		}
+		chosen = p;
+		chosen_points = points;
 	}
+	if (chosen)
+		get_task_struct(chosen);
+	rcu_read_unlock();
 
+	*ppoints = chosen_points * 1000 / totalpages;
 	return chosen;
 }
 
 /**
  * dump_tasks - dump current memory state of all system tasks
- * @mem: current's memory controller, if constrained
+ * @memcg: current's memory controller, if constrained
  * @nodemask: nodemask passed to page allocator for mempolicy ooms
  *
  * 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
  * are not shown.
- * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj
- * value, oom_score_adj value, and name.
- *
- * Call with tasklist_lock read-locked.
+ * 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 *mem, const nodemask_t *nodemask)
+static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemask)
 {
 	struct task_struct *p;
 	struct task_struct *task;
 
-	pr_info("[ pid ]   uid  tgid total_vm      rss cpu oom_adj oom_score_adj name\n");
+	pr_info("[ pid ]   uid  tgid total_vm      rss nr_ptes swapents oom_score_adj name\n");
+	rcu_read_lock();
 	for_each_process(p) {
-		if (oom_unkillable_task(p, mem, nodemask))
+		if (oom_unkillable_task(p, memcg, nodemask))
 			continue;
 
 		task = find_lock_task_mm(p);
@@ -375,96 +376,53 @@ static void dump_tasks(const struct mem_cgroup *mem, const nodemask_t *nodemask)
 			continue;
 		}
 
-		pr_info("[%5d] %5d %5d %8lu %8lu %3u     %3d         %5d %s\n",
-			task->pid, task_uid(task), task->tgid,
-			task->mm->total_vm, get_mm_rss(task->mm),
-			task_cpu(task), task->signal->oom_adj,
+		pr_info("[%5d] %5d %5d %8lu %8lu %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),
+			get_mm_counter(task->mm, MM_SWAPENTS),
 			task->signal->oom_score_adj, task->comm);
 		task_unlock(task);
 	}
+	rcu_read_unlock();
 }
 
 static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
-			struct mem_cgroup *mem, const nodemask_t *nodemask)
+			struct mem_cgroup *memcg, const nodemask_t *nodemask)
 {
 	task_lock(current);
 	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
-		"oom_adj=%d, oom_score_adj=%d\n",
-		current->comm, gfp_mask, order, current->signal->oom_adj,
+		"oom_score_adj=%hd\n",
+		current->comm, gfp_mask, order,
 		current->signal->oom_score_adj);
 	cpuset_print_task_mems_allowed(current);
 	task_unlock(current);
 	dump_stack();
-	mem_cgroup_print_oom_info(mem, p);
-	show_mem();
+	if (memcg)
+		mem_cgroup_print_oom_info(memcg, p);
+	else
+		show_mem(SHOW_MEM_FILTER_NODES);
 	if (sysctl_oom_dump_tasks)
-		dump_tasks(mem, nodemask);
+		dump_tasks(memcg, nodemask);
 }
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
-static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem)
-{
-	struct task_struct *q;
-	struct mm_struct *mm;
-
-	p = find_lock_task_mm(p);
-	if (!p)
-		return 1;
-
-	/* mm cannot be safely dereferenced after task_unlock(p) */
-	mm = p->mm;
-
-	pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
-		task_pid_nr(p), p->comm, K(p->mm->total_vm),
-		K(get_mm_counter(p->mm, MM_ANONPAGES)),
-		K(get_mm_counter(p->mm, MM_FILEPAGES)));
-	task_unlock(p);
-
-	/*
-	 * Kill all processes sharing p->mm in other thread groups, if any.
-	 * They don't get access to memory reserves or a higher scheduler
-	 * priority, though, to avoid depletion of all memory or task
-	 * starvation.  This prevents mm->mmap_sem livelock when an oom killed
-	 * task cannot exit because it requires the semaphore and its contended
-	 * by another thread trying to allocate memory itself.  That thread will
-	 * now get access to memory reserves since it has a pending fatal
-	 * signal.
-	 */
-	for_each_process(q)
-		if (q->mm == mm && !same_thread_group(q, p)) {
-			task_lock(q);	/* Protect ->comm from prctl() */
-			pr_err("Kill process %d (%s) sharing same memory\n",
-				task_pid_nr(q), q->comm);
-			task_unlock(q);
-			force_sig(SIGKILL, q);
-		}
-
-	set_tsk_thread_flag(p, TIF_MEMDIE);
-	force_sig(SIGKILL, p);
-
-	/*
-	 * We give our sacrificial lamb high priority and access to
-	 * all the memory it needs. That way it should be able to
-	 * exit() and clear out its resources quickly...
-	 */
-	boost_dying_task_prio(p, mem);
-
-	return 0;
-}
-#undef K
-
-static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
-			    unsigned int points, unsigned long totalpages,
-			    struct mem_cgroup *mem, nodemask_t *nodemask,
-			    const char *message)
+/*
+ * Must be called while holding a reference to p, which will be released upon
+ * returning.
+ */
+void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
+		      unsigned int points, unsigned long totalpages,
+		      struct mem_cgroup *memcg, nodemask_t *nodemask,
+		      const char *message)
 {
 	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;
-
-	if (printk_ratelimit())
-		dump_header(p, gfp_mask, order, mem, nodemask);
+	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
+					      DEFAULT_RATELIMIT_BURST);
 
 	/*
 	 * If the task is already exiting, don't alarm the sysadmin or kill
@@ -472,10 +430,13 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 */
 	if (p->flags & PF_EXITING) {
 		set_tsk_thread_flag(p, TIF_MEMDIE);
-		boost_dying_task_prio(p, mem);
-		return 0;
+		put_task_struct(p);
+		return;
 	}
 
+	if (__ratelimit(&oom_rs))
+		dump_header(p, gfp_mask, order, memcg, nodemask);
+
 	task_lock(p);
 	pr_err("%s: Kill process %d (%s) score %d or sacrifice child\n",
 		message, task_pid_nr(p), p->comm, points);
@@ -483,34 +444,85 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 
 	/*
 	 * If any of p's children has a different mm and is eligible for kill,
-	 * the one with the highest badness() score is sacrificed for its
+	 * the one with the highest oom_badness() score is sacrificed for its
 	 * parent.  This attempts to lose the minimal amount of work done while
 	 * still freeing memory.
 	 */
-	do {
+	read_lock(&tasklist_lock);
+	for_each_thread(p, t) {
 		list_for_each_entry(child, &t->children, sibling) {
 			unsigned int child_points;
 
+			if (child->mm == p->mm)
+				continue;
 			/*
 			 * oom_badness() returns 0 if the thread is unkillable
 			 */
-			child_points = oom_badness(child, mem, nodemask,
+			child_points = oom_badness(child, memcg, nodemask,
 								totalpages);
 			if (child_points > victim_points) {
+				put_task_struct(victim);
 				victim = child;
 				victim_points = child_points;
+				get_task_struct(victim);
 			}
 		}
-	} while_each_thread(p, t);
+	}
+	read_unlock(&tasklist_lock);
+
+	p = find_lock_task_mm(victim);
+	if (!p) {
+		put_task_struct(victim);
+		return;
+	} else if (victim != p) {
+		get_task_struct(p);
+		put_task_struct(victim);
+		victim = p;
+	}
+
+	/* mm cannot safely be dereferenced after task_unlock(victim) */
+	mm = victim->mm;
+	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)),
+		K(get_mm_counter(victim->mm, MM_FILEPAGES)));
+	task_unlock(victim);
 
-	return oom_kill_task(victim, mem);
+	/*
+	 * Kill all user processes sharing victim->mm in other thread groups, if
+	 * any.  They don't get access to memory reserves, though, to avoid
+	 * depletion of all memory.  This prevents mm->mmap_sem livelock when an
+	 * oom killed thread cannot exit because it requires the semaphore and
+	 * its contended by another thread trying to allocate memory itself.
+	 * 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 (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+				continue;
+
+			task_lock(p);	/* Protect ->comm from prctl() */
+			pr_err("Kill process %d (%s) sharing same memory\n",
+				task_pid_nr(p), p->comm);
+			task_unlock(p);
+			do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
+		}
+	rcu_read_unlock();
+
+	set_tsk_thread_flag(victim, TIF_MEMDIE);
+	do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
+	put_task_struct(victim);
 }
+#undef K
 
 /*
  * Determines whether the kernel must panic because of the panic_on_oom sysctl.
  */
-static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
-				int order, const nodemask_t *nodemask)
+void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
+			int order, const nodemask_t *nodemask)
 {
 	if (likely(!sysctl_panic_on_oom))
 		return;
@@ -523,36 +535,11 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
 		if (constraint != CONSTRAINT_NONE)
 			return;
 	}
-	read_lock(&tasklist_lock);
 	dump_header(NULL, gfp_mask, order, NULL, nodemask);
-	read_unlock(&tasklist_lock);
 	panic("Out of memory: %s panic_on_oom is enabled\n",
 		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
 }
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask)
-{
-	unsigned long limit;
-	unsigned int points = 0;
-	struct task_struct *p;
-
-	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0, NULL);
-	limit = mem_cgroup_get_limit(mem) >> PAGE_SHIFT;
-	read_lock(&tasklist_lock);
-retry:
-	p = select_bad_process(&points, limit, mem, NULL);
-	if (!p || PTR_ERR(p) == -1UL)
-		goto out;
-
-	if (oom_kill_process(p, gfp_mask, 0, points, limit, mem, NULL,
-				"Memory cgroup out of memory"))
-		goto retry;
-out:
-	read_unlock(&tasklist_lock);
-}
-#endif
-
 static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
 
 int register_oom_notifier(struct notifier_block *nb)
@@ -617,49 +604,13 @@ void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
 	spin_unlock(&zone_scan_lock);
 }
 
-/*
- * Try to acquire the oom killer lock for all system zones.  Returns zero if a
- * parallel oom killing is taking place, otherwise locks all zones and returns
- * non-zero.
- */
-static int try_set_system_oom(void)
-{
-	struct zone *zone;
-	int ret = 1;
-
-	spin_lock(&zone_scan_lock);
-	for_each_populated_zone(zone)
-		if (zone_is_oom_locked(zone)) {
-			ret = 0;
-			goto out;
-		}
-	for_each_populated_zone(zone)
-		zone_set_flag(zone, ZONE_OOM_LOCKED);
-out:
-	spin_unlock(&zone_scan_lock);
-	return ret;
-}
-
-/*
- * Clears ZONE_OOM_LOCKED for all system zones so that failed allocation
- * attempts or page faults may now recall the oom killer, if necessary.
- */
-static void clear_system_oom(void)
-{
-	struct zone *zone;
-
-	spin_lock(&zone_scan_lock);
-	for_each_populated_zone(zone)
-		zone_clear_flag(zone, ZONE_OOM_LOCKED);
-	spin_unlock(&zone_scan_lock);
-}
-
 /**
  * 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
  * @nodemask: nodemask passed to page allocator
+ * @force_kill: true if a task must be killed, even if others are exiting
  *
  * If we run out of memory, we have the choice between either
  * killing a random task (bad), letting the system crash (worse)
@@ -667,13 +618,13 @@ static void clear_system_oom(void)
  * don't have to be perfect here, we just have to be good.
  */
 void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
-		int order, nodemask_t *nodemask)
+		int order, nodemask_t *nodemask, bool force_kill)
 {
 	const nodemask_t *mpol_mask;
 	struct task_struct *p;
 	unsigned long totalpages;
 	unsigned long freed = 0;
-	unsigned int points;
+	unsigned int uninitialized_var(points);
 	enum oom_constraint constraint = CONSTRAINT_NONE;
 	int killed = 0;
 
@@ -683,13 +634,12 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		return;
 
 	/*
-	 * If current has a pending SIGKILL, then automatically select it.  The
-	 * goal is to allow it to allocate so that it may quickly exit and free
-	 * its memory.
+	 * 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 (fatal_signal_pending(current)) {
+	if (fatal_signal_pending(current) || current->flags & PF_EXITING) {
 		set_thread_flag(TIF_MEMDIE);
-		boost_dying_task_prio(current, NULL);
 		return;
 	}
 
@@ -702,60 +652,51 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL;
 	check_panic_on_oom(constraint, gfp_mask, order, mpol_mask);
 
-	read_lock(&tasklist_lock);
-	if (sysctl_oom_kill_allocating_task &&
+	if (sysctl_oom_kill_allocating_task && current->mm &&
 	    !oom_unkillable_task(current, NULL, nodemask) &&
-	    current->mm && !atomic_read(&current->mm->oom_disable_count)) {
-		/*
-		 * oom_kill_process() needs tasklist_lock held.  If it returns
-		 * non-zero, current could not be killed so we must fallback to
-		 * the tasklist scan.
-		 */
-		if (!oom_kill_process(current, gfp_mask, order, 0, totalpages,
-				NULL, nodemask,
-				"Out of memory (oom_kill_allocating_task)"))
-			goto out;
-	}
-
-retry:
-	p = select_bad_process(&points, totalpages, NULL, mpol_mask);
-	if (PTR_ERR(p) == -1UL)
+	    current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
+		get_task_struct(current);
+		oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL,
+				 nodemask,
+				 "Out of memory (oom_kill_allocating_task)");
 		goto out;
+	}
 
+	p = select_bad_process(&points, totalpages, mpol_mask, force_kill);
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!p) {
 		dump_header(NULL, gfp_mask, order, NULL, mpol_mask);
-		read_unlock(&tasklist_lock);
 		panic("Out of memory and no killable processes...\n");
 	}
-
-	if (oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
-				nodemask, "Out of memory"))
-		goto retry;
-	killed = 1;
+	if (p != (void *)-1UL) {
+		oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
+				 nodemask, "Out of memory");
+		killed = 1;
+	}
 out:
-	read_unlock(&tasklist_lock);
-
 	/*
-	 * Give "p" a good chance of killing itself before we
-	 * retry to allocate memory unless "p" is current
+	 * Give the killed threads a good chance of exiting before trying to
+	 * allocate memory again.
 	 */
-	if (killed && !test_thread_flag(TIF_MEMDIE))
-		schedule_timeout_uninterruptible(1);
+	if (killed)
+		schedule_timeout_killable(1);
 }
 
 /*
  * The pagefault handler calls here because it is out of memory, so kill a
- * memory-hogging task.  If a populated zone has ZONE_OOM_LOCKED set, a parallel
- * oom killing is already in progress so do nothing.  If a task is found with
- * TIF_MEMDIE set, it has been killed so do nothing and allow it to exit.
+ * memory-hogging task.  If any populated zone has ZONE_OOM_LOCKED set, a
+ * parallel oom killing is already in progress so do nothing.
  */
 void pagefault_out_of_memory(void)
 {
-	if (try_set_system_oom()) {
-		out_of_memory(NULL, 0, 0, NULL);
-		clear_system_oom();
+	struct zonelist *zonelist;
+
+	if (mem_cgroup_oom_synchronize(true))
+		return;
+
+	zonelist = node_zonelist(first_online_node, GFP_KERNEL);
+	if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) {
+		out_of_memory(NULL, 0, 0, NULL, false);
+		clear_zonelist_oom(zonelist, GFP_KERNEL);
 	}
-	if (!test_thread_flag(TIF_MEMDIE))
-		schedule_timeout_uninterruptible(1);
 }