1 files changed, 125 insertions, 62 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d4a929d..7d0a275 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -176,11 +176,13 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 
 	/*
 	 * Do not even consider tasks which are explicitly marked oom
-	 * unkillable or have been already oom reaped.
+	 * unkillable or have been already oom reaped or the are in
+	 * the middle of vfork
 	 */
 	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_REAPED, &p->mm->flags) ||
+			in_vfork(p)) {
 		task_unlock(p);
 		return 0;
 	}
@@ -281,10 +283,22 @@ enum oom_scan_t oom_scan_process_thread(struct oom_control *oc,
 
 	/*
 	 * This task already has access to memory reserves and is being killed.
-	 * Don't allow any other task to have access to the reserves.
+	 * 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
+	 * any memory is quite low.
 	 */
-	if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims))
-		return OOM_SCAN_ABORT;
+	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 task is allocating a lot of memory and has been marked to be
@@ -415,7 +429,7 @@ bool oom_killer_disabled __read_mostly;
  * task's threads: if one of those is using this mm then this task was also
  * using it.
  */
-static bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
+bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
 {
 	struct task_struct *t;
 
@@ -554,8 +568,27 @@ static void oom_reap_task(struct task_struct *tsk)
 		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 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();
 	}
 
@@ -594,7 +627,7 @@ static int oom_reaper(void *unused)
 	return 0;
 }
 
-static void wake_oom_reaper(struct task_struct *tsk)
+void wake_oom_reaper(struct task_struct *tsk)
 {
 	if (!oom_reaper_th)
 		return;
@@ -612,46 +645,6 @@ static void wake_oom_reaper(struct task_struct *tsk)
 	wake_up(&oom_reaper_wait);
 }
 
-/* Check if we can reap the given task. This has to be called with stable
- * tsk->mm
- */
-void try_oom_reaper(struct task_struct *tsk)
-{
-	struct mm_struct *mm = tsk->mm;
-	struct task_struct *p;
-
-	if (!mm)
-		return;
-
-	/*
-	 * There might be other threads/processes which are either not
-	 * dying or even not killable.
-	 */
-	if (atomic_read(&mm->mm_users) > 1) {
-		rcu_read_lock();
-		for_each_process(p) {
-			if (!process_shares_mm(p, mm))
-				continue;
-			if (fatal_signal_pending(p))
-				continue;
-
-			/*
-			 * If the task is exiting make sure the whole thread group
-			 * is exiting and cannot acces mm anymore.
-			 */
-			if (signal_group_exit(p->signal))
-				continue;
-
-			/* Give up */
-			rcu_read_unlock();
-			return;
-		}
-		rcu_read_unlock();
-	}
-
-	wake_oom_reaper(tsk);
-}
-
 static int __init oom_init(void)
 {
 	oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
@@ -663,10 +656,6 @@ static int __init oom_init(void)
 	return 0;
 }
 subsys_initcall(oom_init)
-#else
-static void wake_oom_reaper(struct task_struct *tsk)
-{
-}
 #endif
 
 /**
@@ -743,6 +732,80 @@ void oom_killer_enable(void)
 	oom_killer_disabled = false;
 }
 
+static inline bool __task_will_free_mem(struct task_struct *task)
+{
+	struct signal_struct *sig = task->signal;
+
+	/*
+	 * A coredumping process may sleep for an extended period in exit_mm(),
+	 * so the oom killer cannot assume that the process will promptly exit
+	 * and release memory.
+	 */
+	if (sig->flags & SIGNAL_GROUP_COREDUMP)
+		return false;
+
+	if (sig->flags & SIGNAL_GROUP_EXIT)
+		return true;
+
+	if (thread_group_empty(task) && (task->flags & PF_EXITING))
+		return true;
+
+	return false;
+}
+
+/*
+ * Checks whether the given task is dying or exiting and likely to
+ * release its address space. This means that all threads and processes
+ * sharing the same mm have to be killed or exiting.
+ * 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)
+{
+	struct mm_struct *mm = task->mm;
+	struct task_struct *p;
+	bool ret;
+
+	/*
+	 * Skip tasks without mm because it might have passed its exit_mm and
+	 * exit_oom_victim. oom_reaper could have rescued that but do not rely
+	 * on that for now. We can consider find_lock_task_mm in future.
+	 */
+	if (!mm)
+		return false;
+
+	if (!__task_will_free_mem(task))
+		return false;
+
+	/*
+	 * 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))
+		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
+	 */
+	rcu_read_lock();
+	for_each_process(p) {
+		if (!process_shares_mm(p, mm))
+			continue;
+		if (same_thread_group(task, p))
+			continue;
+		ret = __task_will_free_mem(p);
+		if (!ret)
+			break;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 /*
  * Must be called while holding a reference to p, which will be released upon
  * returning.
@@ -765,9 +828,9 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 	 * its children or threads, just set TIF_MEMDIE so it can die quickly
 	 */
 	task_lock(p);
-	if (p->mm && task_will_free_mem(p)) {
+	if (task_will_free_mem(p)) {
 		mark_oom_victim(p);
-		try_oom_reaper(p);
+		wake_oom_reaper(p);
 		task_unlock(p);
 		put_task_struct(p);
 		return;
@@ -850,14 +913,18 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 			continue;
 		if (same_thread_group(p, victim))
 			continue;
-		if (unlikely(p->flags & PF_KTHREAD) || is_global_init(p) ||
-		    p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+		if (unlikely(p->flags & PF_KTHREAD) || is_global_init(p)) {
 			/*
 			 * We cannot use oom_reaper for the mm shared by this
 			 * process because it wouldn't get killed and so the
-			 * memory might be still used.
+			 * memory might be still used. Hide the mm from the oom
+			 * killer to guarantee OOM forward progress.
 			 */
 			can_oom_reap = false;
+			set_bit(MMF_OOM_REAPED, &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);
 			continue;
 		}
 		do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
@@ -939,14 +1006,10 @@ bool out_of_memory(struct oom_control *oc)
 	 * 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.
-	 *
-	 * But don't select if current has already released its mm and cleared
-	 * TIF_MEMDIE flag at exit_mm(), otherwise an OOM livelock may occur.
 	 */
-	if (current->mm &&
-	    (fatal_signal_pending(current) || task_will_free_mem(current))) {
+	if (task_will_free_mem(current)) {
 		mark_oom_victim(current);
-		try_oom_reaper(current);
+		wake_oom_reaper(current);
 		return true;
 	}