1 files changed, 132 insertions, 107 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 84081e77bc51..b5b25e4dcbbb 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -53,6 +53,14 @@ int sysctl_panic_on_oom;
 int sysctl_oom_kill_allocating_task;
 int sysctl_oom_dump_tasks = 1;
 
+/*
+ * Serializes oom killer invocations (out_of_memory()) from all contexts to
+ * prevent from over eager oom killing (e.g. when the oom killer is invoked
+ * from different domains).
+ *
+ * oom_killer_disable() relies on this lock to stabilize oom_killer_disabled
+ * and mark_oom_victim
+ */
 DEFINE_MUTEX(oom_lock);
 
 #ifdef CONFIG_NUMA
@@ -392,7 +400,8 @@ 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 pgtables_bytes swapents oom_score_adj name\n");
+	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))
@@ -408,7 +417,7 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 			continue;
 		}
 
-		pr_info("[%5d] %5d %5d %8lu %8lu %8ld %8lu         %5hd %s\n",
+		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),
@@ -479,9 +488,10 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
 static struct task_struct *oom_reaper_list;
 static DEFINE_SPINLOCK(oom_reaper_lock);
 
-void __oom_reap_task_mm(struct mm_struct *mm)
+bool __oom_reap_task_mm(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma;
+	bool ret = true;
 
 	/*
 	 * Tell all users of get_user/copy_from_user etc... that the content
@@ -511,50 +521,32 @@ void __oom_reap_task_mm(struct mm_struct *mm)
 			struct mmu_gather tlb;
 
 			tlb_gather_mmu(&tlb, mm, start, end);
-			mmu_notifier_invalidate_range_start(mm, start, end);
+			if (mmu_notifier_invalidate_range_start_nonblock(mm, start, end)) {
+				ret = false;
+				continue;
+			}
 			unmap_page_range(&tlb, vma, start, end, NULL);
 			mmu_notifier_invalidate_range_end(mm, start, end);
 			tlb_finish_mmu(&tlb, start, end);
 		}
 	}
+
+	return ret;
 }
 
+/*
+ * Reaps the address space of the give task.
+ *
+ * Returns true on success and false if none or part of the address space
+ * has been reclaimed and the caller should retry later.
+ */
 static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 {
 	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_mm		exit_mm
-	 *   mmget_not_zero
-	 *				  mmput
-	 *				    atomic_dec_and_test
-	 *				  exit_oom_victim
-	 *				[...]
-	 *				out_of_memory
-	 *				  select_bad_process
-	 *				    # no TIF_MEMDIE task selects new victim
-	 *  unmap_page_range # frees some memory
-	 */
-	mutex_lock(&oom_lock);
-
 	if (!down_read_trylock(&mm->mmap_sem)) {
-		ret = false;
 		trace_skip_task_reaping(tsk->pid);
-		goto unlock_oom;
-	}
-
-	/*
-	 * If the mm has invalidate_{start,end}() notifiers that could block,
-	 * sleep to give the oom victim some more time.
-	 * TODO: we really want to get rid of this ugly hack and make sure that
-	 * notifiers cannot block for unbounded amount of time
-	 */
-	if (mm_has_blockable_invalidate_notifiers(mm)) {
-		up_read(&mm->mmap_sem);
-		schedule_timeout_idle(HZ);
-		goto unlock_oom;
+		return false;
 	}
 
 	/*
@@ -564,25 +556,27 @@ static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 	 * down_write();up_write() cycle in exit_mmap().
 	 */
 	if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
-		up_read(&mm->mmap_sem);
 		trace_skip_task_reaping(tsk->pid);
-		goto unlock_oom;
+		goto out_unlock;
 	}
 
 	trace_start_task_reaping(tsk->pid);
 
-	__oom_reap_task_mm(mm);
+	/* failed to reap part of the address space. Try again later */
+	ret = __oom_reap_task_mm(mm);
+	if (!ret)
+		goto out_finish;
 
 	pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
 			task_pid_nr(tsk), tsk->comm,
 			K(get_mm_counter(mm, MM_ANONPAGES)),
 			K(get_mm_counter(mm, MM_FILEPAGES)),
 			K(get_mm_counter(mm, MM_SHMEMPAGES)));
+out_finish:
+	trace_finish_task_reaping(tsk->pid);
+out_unlock:
 	up_read(&mm->mmap_sem);
 
-	trace_finish_task_reaping(tsk->pid);
-unlock_oom:
-	mutex_unlock(&oom_lock);
 	return ret;
 }
 
@@ -835,68 +829,12 @@ static bool task_will_free_mem(struct task_struct *task)
 	return ret;
 }
 
-static void oom_kill_process(struct oom_control *oc, const char *message)
+static void __oom_kill_process(struct task_struct *victim)
 {
-	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;
+	struct task_struct *p;
 	struct mm_struct *mm;
-	unsigned int victim_points = 0;
-	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
-					      DEFAULT_RATELIMIT_BURST);
 	bool can_oom_reap = true;
 
-	/*
-	 * If the task is already exiting, don't alarm the sysadmin or kill
-	 * its children or threads, just give it access to memory reserves
-	 * so it can die quickly
-	 */
-	task_lock(p);
-	if (task_will_free_mem(p)) {
-		mark_oom_victim(p);
-		wake_oom_reaper(p);
-		task_unlock(p);
-		put_task_struct(p);
-		return;
-	}
-	task_unlock(p);
-
-	if (__ratelimit(&oom_rs))
-		dump_header(oc, p);
-
-	pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
-		message, task_pid_nr(p), p->comm, points);
-
-	/*
-	 * If any of p's children has a different mm and is eligible for kill,
-	 * 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.
-	 */
-	read_lock(&tasklist_lock);
-	for_each_thread(p, t) {
-		list_for_each_entry(child, &t->children, sibling) {
-			unsigned int child_points;
-
-			if (process_shares_mm(child, p->mm))
-				continue;
-			/*
-			 * oom_badness() returns 0 if the thread is unkillable
-			 */
-			child_points = oom_badness(child,
-				oc->memcg, oc->nodemask, oc->totalpages);
-			if (child_points > victim_points) {
-				put_task_struct(victim);
-				victim = child;
-				victim_points = child_points;
-				get_task_struct(victim);
-			}
-		}
-	}
-	read_unlock(&tasklist_lock);
-
 	p = find_lock_task_mm(victim);
 	if (!p) {
 		put_task_struct(victim);
@@ -920,7 +858,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 	 * in order to prevent the OOM victim from depleting the memory
 	 * reserves from the user space under its control.
 	 */
-	do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
+	do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, PIDTYPE_TGID);
 	mark_oom_victim(victim);
 	pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
 		task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
@@ -958,7 +896,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 		 */
 		if (unlikely(p->flags & PF_KTHREAD))
 			continue;
-		do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
+		do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, PIDTYPE_TGID);
 	}
 	rcu_read_unlock();
 
@@ -971,6 +909,99 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 #undef K
 
 /*
+ * Kill provided task unless it's secured by setting
+ * oom_score_adj to OOM_SCORE_ADJ_MIN.
+ */
+static int oom_kill_memcg_member(struct task_struct *task, void *unused)
+{
+	if (task->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
+		get_task_struct(task);
+		__oom_kill_process(task);
+	}
+	return 0;
+}
+
+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;
+	struct mem_cgroup *oom_group;
+	unsigned int victim_points = 0;
+	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
+	 * its children or threads, just give it access to memory reserves
+	 * so it can die quickly
+	 */
+	task_lock(p);
+	if (task_will_free_mem(p)) {
+		mark_oom_victim(p);
+		wake_oom_reaper(p);
+		task_unlock(p);
+		put_task_struct(p);
+		return;
+	}
+	task_unlock(p);
+
+	if (__ratelimit(&oom_rs))
+		dump_header(oc, p);
+
+	pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
+		message, task_pid_nr(p), p->comm, points);
+
+	/*
+	 * If any of p's children has a different mm and is eligible for kill,
+	 * 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.
+	 */
+	read_lock(&tasklist_lock);
+	for_each_thread(p, t) {
+		list_for_each_entry(child, &t->children, sibling) {
+			unsigned int child_points;
+
+			if (process_shares_mm(child, p->mm))
+				continue;
+			/*
+			 * oom_badness() returns 0 if the thread is unkillable
+			 */
+			child_points = oom_badness(child,
+				oc->memcg, oc->nodemask, oc->totalpages);
+			if (child_points > victim_points) {
+				put_task_struct(victim);
+				victim = child;
+				victim_points = child_points;
+				get_task_struct(victim);
+			}
+		}
+	}
+	read_unlock(&tasklist_lock);
+
+	/*
+	 * Do we need to kill the entire memory cgroup?
+	 * Or even one of the ancestor memory cgroups?
+	 * Check this out before killing the victim task.
+	 */
+	oom_group = mem_cgroup_get_oom_group(victim, oc->memcg);
+
+	__oom_kill_process(victim);
+
+	/*
+	 * If necessary, kill all tasks in the selected memory cgroup.
+	 */
+	if (oom_group) {
+		mem_cgroup_print_oom_group(oom_group);
+		mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member, NULL);
+		mem_cgroup_put(oom_group);
+	}
+}
+
+/*
  * Determines whether the kernel must panic because of the panic_on_oom sysctl.
  */
 static void check_panic_on_oom(struct oom_control *oc,
@@ -1077,15 +1108,9 @@ bool out_of_memory(struct oom_control *oc)
 		dump_header(oc, NULL);
 		panic("Out of memory and no killable processes...\n");
 	}
-	if (oc->chosen && oc->chosen != (void *)-1UL) {
+	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 !!oc->chosen;
 }