X-Git-Url: http://git.cascardo.eti.br/?a=blobdiff_plain;f=mm%2Foom_kill.c;h=ec9f11d4f094467e98b8190b7195379174d6be0a;hb=10e15a639caac3be3c142f8837a17520da84db9f;hp=87fad956c96bbb2c9bfd977c7c75860cedcb2eea;hpb=7ebffa45551fe7db86a2b32bf586f124ef484e6e;p=cascardo%2Flinux.git

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 87fad956c96b..ec9f11d4f094 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -186,7 +186,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 */
 	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_SKIP, &p->mm->flags) ||
 			in_vfork(p)) {
 		task_unlock(p);
 		return 0;
@@ -296,18 +296,11 @@ static int oom_evaluate_task(struct task_struct *task, void *arg)
 	/*
 	 * This task already has access to memory reserves and is being killed.
 	 * 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
+	 * the task has MMF_OOM_SKIP because chances that it would release
 	 * any memory is quite low.
 	 */
-	if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims)) {
-		struct task_struct *p = find_lock_task_mm(task);
-		bool reaped = false;
-
-		if (p) {
-			reaped = test_bit(MMF_OOM_REAPED, &p->mm->flags);
-			task_unlock(p);
-		}
-		if (reaped)
+	if (!is_sysrq_oom(oc) && tsk_is_oom_victim(task)) {
+		if (test_bit(MMF_OOM_SKIP, &task->signal->oom_mm->flags))
 			goto next;
 		goto abort;
 	}
@@ -410,9 +403,14 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 
 static void dump_header(struct oom_control *oc, struct task_struct *p)
 {
-	pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), order=%d, oom_score_adj=%hd\n",
-		current->comm, oc->gfp_mask, &oc->gfp_mask, oc->order,
+	nodemask_t *nm = (oc->nodemask) ? oc->nodemask : &cpuset_current_mems_allowed;
+
+	pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), nodemask=%*pbl, order=%d, oom_score_adj=%hd\n",
+		current->comm, oc->gfp_mask, &oc->gfp_mask,
+		nodemask_pr_args(nm), oc->order,
 		current->signal->oom_score_adj);
+	if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order)
+		pr_warn("COMPACTION is disabled!!!\n");
 
 	cpuset_print_current_mems_allowed();
 	dump_stack();
@@ -502,6 +500,14 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 		goto unlock_oom;
 	}
 
+	/*
+	 * Tell all users of get_user/copy_from_user etc... that the content
+	 * is no longer stable. No barriers really needed because unmapping
+	 * should imply barriers already and the reader would hit a page fault
+	 * if it stumbled over a reaped memory.
+	 */
+	set_bit(MMF_UNSTABLE, &mm->flags);
+
 	tlb_gather_mmu(&tlb, mm, 0, -1);
 	for (vma = mm->mmap ; vma; vma = vma->vm_next) {
 		if (is_vm_hugetlb_page(vma))
@@ -536,11 +542,6 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 			K(get_mm_counter(mm, MM_SHMEMPAGES)));
 	up_read(&mm->mmap_sem);
 
-	/*
-	 * This task can be safely ignored because we cannot do much more
-	 * to release its memory.
-	 */
-	set_bit(MMF_OOM_REAPED, &mm->flags);
 	/*
 	 * 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
@@ -556,20 +557,7 @@ unlock_oom:
 static void oom_reap_task(struct task_struct *tsk)
 {
 	int attempts = 0;
-	struct mm_struct *mm = NULL;
-	struct task_struct *p = find_lock_task_mm(tsk);
-
-	/*
-	 * 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
-	 * is no mm.
-	 */
-	if (!p)
-		goto done;
-	mm = p->mm;
-	atomic_inc(&mm->mm_count);
-	task_unlock(p);
+	struct mm_struct *mm = tsk->signal->oom_mm;
 
 	/* Retry the down_read_trylock(mmap_sem) a few times */
 	while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task_mm(tsk, mm))
@@ -578,43 +566,26 @@ static void oom_reap_task(struct task_struct *tsk)
 	if (attempts <= MAX_OOM_REAP_RETRIES)
 		goto done;
 
+
 	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.
-	 */
-	if (test_and_set_bit(MMF_OOM_NOT_REAPABLE, &mm->flags)) {
-		pr_info("oom_reaper: giving up pid:%d (%s)\n",
-			task_pid_nr(tsk), tsk->comm);
-		set_bit(MMF_OOM_REAPED, &mm->flags);
-	}
 	debug_show_all_locks();
 
 done:
+	tsk->oom_reaper_list = NULL;
+
 	/*
-	 * 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.
+	 * Hide this mm from OOM killer because it has been either reaped or
+	 * somebody can't call up_write(mmap_sem).
 	 */
-	tsk->oom_reaper_list = NULL;
-	exit_oom_victim(tsk);
+	set_bit(MMF_OOM_SKIP, &mm->flags);
 
 	/* Drop a reference taken by wake_oom_reaper */
 	put_task_struct(tsk);
-	/* Drop a reference taken above. */
-	if (mm)
-		mmdrop(mm);
 }
 
 static int oom_reaper(void *unused)
 {
-	set_freezable();
-
 	while (true) {
 		struct task_struct *tsk = NULL;
 
@@ -674,14 +645,23 @@ static inline void wake_oom_reaper(struct task_struct *tsk)
  *
  * Has to be called with oom_lock held and never after
  * oom has been disabled already.
+ *
+ * tsk->mm has to be non NULL and caller has to guarantee it is stable (either
+ * under task_lock or operate on the current).
  */
 static void mark_oom_victim(struct task_struct *tsk)
 {
+	struct mm_struct *mm = tsk->mm;
+
 	WARN_ON(oom_killer_disabled);
 	/* OOM killer might race with memcg OOM */
 	if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE))
 		return;
-	atomic_inc(&tsk->signal->oom_victims);
+
+	/* oom_mm is bound to the signal struct life time. */
+	if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm))
+		atomic_inc(&tsk->signal->oom_mm->mm_count);
+
 	/*
 	 * Make sure that the task is woken up from uninterruptible sleep
 	 * if it is frozen because OOM killer wouldn't be able to free
@@ -695,21 +675,29 @@ static void mark_oom_victim(struct task_struct *tsk)
 /**
  * exit_oom_victim - note the exit of an OOM victim
  */
-void exit_oom_victim(struct task_struct *tsk)
+void exit_oom_victim(void)
 {
-	if (!test_and_clear_tsk_thread_flag(tsk, TIF_MEMDIE))
-		return;
-	atomic_dec(&tsk->signal->oom_victims);
+	clear_thread_flag(TIF_MEMDIE);
 
 	if (!atomic_dec_return(&oom_victims))
 		wake_up_all(&oom_victims_wait);
 }
 
+/**
+ * oom_killer_enable - enable OOM killer
+ */
+void oom_killer_enable(void)
+{
+	oom_killer_disabled = false;
+}
+
 /**
  * oom_killer_disable - disable OOM killer
+ * @timeout: maximum timeout to wait for oom victims in jiffies
  *
  * Forces all page allocations to fail rather than trigger OOM killer.
- * Will block and wait until all OOM victims are killed.
+ * Will block and wait until all OOM victims are killed or the given
+ * timeout expires.
  *
  * The function cannot be called when there are runnable user tasks because
  * the userspace would see unexpected allocation failures as a result. Any
@@ -718,8 +706,10 @@ void exit_oom_victim(struct task_struct *tsk)
  * Returns true if successful and false if the OOM killer cannot be
  * disabled.
  */
-bool oom_killer_disable(void)
+bool oom_killer_disable(signed long timeout)
 {
+	signed long ret;
+
 	/*
 	 * Make sure to not race with an ongoing OOM killer. Check that the
 	 * current is not killed (possibly due to sharing the victim's memory).
@@ -729,19 +719,16 @@ bool oom_killer_disable(void)
 	oom_killer_disabled = true;
 	mutex_unlock(&oom_lock);
 
-	wait_event(oom_victims_wait, !atomic_read(&oom_victims));
+	ret = wait_event_interruptible_timeout(oom_victims_wait,
+			!atomic_read(&oom_victims), timeout);
+	if (ret <= 0) {
+		oom_killer_enable();
+		return false;
+	}
 
 	return true;
 }
 
-/**
- * oom_killer_enable - enable OOM killer
- */
-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;
@@ -791,7 +778,7 @@ static bool task_will_free_mem(struct task_struct *task)
 	 * 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))
+	if (test_bit(MMF_OOM_SKIP, &mm->flags))
 		return false;
 
 	if (atomic_read(&mm->mm_users) <= 1)
@@ -920,20 +907,20 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 			continue;
 		if (same_thread_group(p, victim))
 			continue;
-		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. Hide the mm from the oom
-			 * killer to guarantee OOM forward progress.
-			 */
+		if (is_global_init(p)) {
 			can_oom_reap = false;
-			set_bit(MMF_OOM_REAPED, &mm->flags);
+			set_bit(MMF_OOM_SKIP, &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;
 		}
+		/*
+		 * No use_mm() user needs to read from the userspace so we are
+		 * ok to reap it.
+		 */
+		if (unlikely(p->flags & PF_KTHREAD))
+			continue;
 		do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
 	}
 	rcu_read_unlock();
@@ -1085,16 +1072,6 @@ void pagefault_out_of_memory(void)
 
 	if (!mutex_trylock(&oom_lock))
 		return;
-
-	if (!out_of_memory(&oc)) {
-		/*
-		 * There shouldn't be any user tasks runnable while the
-		 * OOM killer is disabled, so the current task has to
-		 * be a racing OOM victim for which oom_killer_disable()
-		 * is waiting for.
-		 */
-		WARN_ON(test_thread_flag(TIF_MEMDIE));
-	}
-
+	out_of_memory(&oc);
 	mutex_unlock(&oom_lock);
 }