Linux-libre 4.7.1-gnupck-4.7.1-gnu

1 files changed, 123 insertions, 49 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 86349586e..ddf74487f 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -174,8 +174,13 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	if (!p)
 		return 0;
 
+	/*
+	 * Do not even consider tasks which are explicitly marked oom
+	 * unkillable or have been already oom reaped.
+	 */
 	adj = (long)p->signal->oom_score_adj;
-	if (adj == OOM_SCORE_ADJ_MIN) {
+	if (adj == OOM_SCORE_ADJ_MIN ||
+			test_bit(MMF_OOM_REAPED, &p->mm->flags)) {
 		task_unlock(p);
 		return 0;
 	}
@@ -278,12 +283,8 @@ 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.
 	 */
-	if (test_tsk_thread_flag(task, TIF_MEMDIE)) {
-		if (!is_sysrq_oom(oc))
-			return OOM_SCAN_ABORT;
-	}
-	if (!task->mm)
-		return OOM_SCAN_CONTINUE;
+	if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims))
+		return OOM_SCAN_ABORT;
 
 	/*
 	 * If task is allocating a lot of memory and has been marked to be
@@ -302,12 +303,12 @@ enum oom_scan_t oom_scan_process_thread(struct oom_control *oc,
 static struct task_struct *select_bad_process(struct oom_control *oc,
 		unsigned int *ppoints, unsigned long totalpages)
 {
-	struct task_struct *g, *p;
+	struct task_struct *p;
 	struct task_struct *chosen = NULL;
 	unsigned long chosen_points = 0;
 
 	rcu_read_lock();
-	for_each_process_thread(g, p) {
+	for_each_process(p) {
 		unsigned int points;
 
 		switch (oom_scan_process_thread(oc, p, totalpages)) {
@@ -326,9 +327,6 @@ static struct task_struct *select_bad_process(struct oom_control *oc,
 		points = oom_badness(p, NULL, oc->nodemask, totalpages);
 		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;
@@ -412,6 +410,25 @@ bool oom_killer_disabled __read_mostly;
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
 
+/*
+ * task->mm can be NULL if the task is the exited group leader.  So to
+ * determine whether the task is using a particular mm, we examine all the
+ * 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)
+{
+	struct task_struct *t;
+
+	for_each_thread(p, t) {
+		struct mm_struct *t_mm = READ_ONCE(t->mm);
+		if (t_mm)
+			return t_mm == mm;
+	}
+	return false;
+}
+
+
 #ifdef CONFIG_MMU
 /*
  * OOM Reaper kernel thread which tries to reap the memory used by the OOM
@@ -422,18 +439,33 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
 static struct task_struct *oom_reaper_list;
 static DEFINE_SPINLOCK(oom_reaper_lock);
 
-
 static bool __oom_reap_task(struct task_struct *tsk)
 {
 	struct mmu_gather tlb;
 	struct vm_area_struct *vma;
-	struct mm_struct *mm;
+	struct mm_struct *mm = NULL;
 	struct task_struct *p;
 	struct zap_details details = {.check_swap_entries = true,
 				      .ignore_dirty = true};
 	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		exit_mm
+	 *   atomic_inc_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);
+
+	/*
 	 * Make sure we find the associated mm_struct even when the particular
 	 * thread has already terminated and cleared its mm.
 	 * We might have race with exit path so consider our work done if there
@@ -441,19 +473,14 @@ static bool __oom_reap_task(struct task_struct *tsk)
 	 */
 	p = find_lock_task_mm(tsk);
 	if (!p)
-		return true;
-
+		goto unlock_oom;
 	mm = p->mm;
-	if (!atomic_inc_not_zero(&mm->mm_users)) {
-		task_unlock(p);
-		return true;
-	}
-
+	atomic_inc(&mm->mm_users);
 	task_unlock(p);
 
 	if (!down_read_trylock(&mm->mmap_sem)) {
 		ret = false;
-		goto out;
+		goto unlock_oom;
 	}
 
 	tlb_gather_mmu(&tlb, mm, 0, -1);
@@ -491,16 +518,19 @@ static bool __oom_reap_task(struct task_struct *tsk)
 	up_read(&mm->mmap_sem);
 
 	/*
-	 * Clear TIF_MEMDIE because the task shouldn't be sitting on a
-	 * reasonably reclaimable memory anymore. OOM killer can continue
-	 * by selecting other victim if unmapping hasn't led to any
-	 * improvements. This also means that selecting this task doesn't
-	 * make any sense.
+	 * This task can be safely ignored because we cannot do much more
+	 * to release its memory.
 	 */
-	tsk->signal->oom_score_adj = OOM_SCORE_ADJ_MIN;
-	exit_oom_victim(tsk);
-out:
-	mmput(mm);
+	set_bit(MMF_OOM_REAPED, &mm->flags);
+unlock_oom:
+	mutex_unlock(&oom_lock);
+	/*
+	 * Drop our reference but make sure the mmput slow path is called from a
+	 * different context because we shouldn't risk we get stuck there and
+	 * put the oom_reaper out of the way.
+	 */
+	if (mm)
+		mmput_async(mm);
 	return ret;
 }
 
@@ -519,6 +549,15 @@ static void oom_reap_task(struct task_struct *tsk)
 		debug_show_all_locks();
 	}
 
+	/*
+	 * Clear TIF_MEMDIE because the task shouldn't be sitting on a
+	 * reasonably reclaimable memory anymore or it is not a good candidate
+	 * for the oom victim right now because it cannot release its memory
+	 * itself nor by the oom reaper.
+	 */
+	tsk->oom_reaper_list = NULL;
+	exit_oom_victim(tsk);
+
 	/* Drop a reference taken by wake_oom_reaper */
 	put_task_struct(tsk);
 }
@@ -563,6 +602,46 @@ 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");
@@ -593,6 +672,7 @@ void mark_oom_victim(struct task_struct *tsk)
 	/* OOM killer might race with memcg OOM */
 	if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE))
 		return;
+	atomic_inc(&tsk->signal->oom_victims);
 	/*
 	 * Make sure that the task is woken up from uninterruptible sleep
 	 * if it is frozen because OOM killer wouldn't be able to free
@@ -610,6 +690,7 @@ void exit_oom_victim(struct task_struct *tsk)
 {
 	if (!test_and_clear_tsk_thread_flag(tsk, TIF_MEMDIE))
 		return;
+	atomic_dec(&tsk->signal->oom_victims);
 
 	if (!atomic_dec_return(&oom_victims))
 		wake_up_all(&oom_victims_wait);
@@ -653,24 +734,6 @@ void oom_killer_enable(void)
 }
 
 /*
- * task->mm can be NULL if the task is the exited group leader.  So to
- * determine whether the task is using a particular mm, we examine all the
- * 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)
-{
-	struct task_struct *t;
-
-	for_each_thread(p, t) {
-		struct mm_struct *t_mm = READ_ONCE(t->mm);
-		if (t_mm)
-			return t_mm == mm;
-	}
-	return false;
-}
-
-/*
  * Must be called while holding a reference to p, which will be released upon
  * returning.
  */
@@ -694,6 +757,7 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 	task_lock(p);
 	if (p->mm && task_will_free_mem(p)) {
 		mark_oom_victim(p);
+		try_oom_reaper(p);
 		task_unlock(p);
 		put_task_struct(p);
 		return;
@@ -873,10 +937,20 @@ bool out_of_memory(struct oom_control *oc)
 	if (current->mm &&
 	    (fatal_signal_pending(current) || task_will_free_mem(current))) {
 		mark_oom_victim(current);
+		try_oom_reaper(current);
 		return true;
 	}
 
 	/*
+	 * The OOM killer does not compensate for IO-less reclaim.
+	 * pagefault_out_of_memory lost its gfp context so we have to
+	 * make sure exclude 0 mask - all other users should have at least
+	 * ___GFP_DIRECT_RECLAIM to get here.
+	 */
+	if (oc->gfp_mask && !(oc->gfp_mask & (__GFP_FS|__GFP_NOFAIL)))
+		return true;
+
+	/*
 	 * Check if there were limitations on the allocation (only relevant for
 	 * NUMA) that may require different handling.
 	 */