Merge branch 'freezer'

* freezer:
  PM / freezer: Clean up code after recent fixes
  PM: convert do_each_thread to for_each_process_thread
  OOM, PM: OOM killed task shouldn't escape PM suspend
  freezer: remove obsolete comments in __thaw_task()
  freezer: Do not freeze tasks killed by OOM killer

5 files changed, 79 insertions, 15 deletions

diff --git a/include/linux/oom.h b/include/linux/oom.h
index 647395a1a550..e8d6e1058723 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -50,6 +50,9 @@ static inline bool oom_task_origin(const struct task_struct *p)
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
 		unsigned long totalpages);
+
+extern int oom_kills_count(void);
+extern void note_oom_kill(void);
 extern 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,
diff --git a/kernel/freezer.c b/kernel/freezer.c
index aa6a8aadb911..a8900a3bc27a 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -42,6 +42,9 @@ bool freezing_slow_path(struct task_struct *p)
 	if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK))
 		return false;
 
+	if (test_thread_flag(TIF_MEMDIE))
+		return false;
+
 	if (pm_nosig_freezing || cgroup_freezing(p))
 		return true;
 
@@ -147,12 +150,6 @@ void __thaw_task(struct task_struct *p)
 {
 	unsigned long flags;
 
-	/*
-	 * Clear freezing and kick @p if FROZEN.  Clearing is guaranteed to
-	 * be visible to @p as waking up implies wmb.  Waking up inside
-	 * freezer_lock also prevents wakeups from leaking outside
-	 * refrigerator.
-	 */
 	spin_lock_irqsave(&freezer_lock, flags);
 	if (frozen(p))
 		wake_up_process(p);
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 7b323221b9ee..5a6ec8678b9a 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -46,13 +46,13 @@ static int try_to_freeze_tasks(bool user_only)
 	while (true) {
 		todo = 0;
 		read_lock(&tasklist_lock);
-		do_each_thread(g, p) {
+		for_each_process_thread(g, p) {
 			if (p == current || !freeze_task(p))
 				continue;
 
 			if (!freezer_should_skip(p))
 				todo++;
-		} while_each_thread(g, p);
+		}
 		read_unlock(&tasklist_lock);
 
 		if (!user_only) {
@@ -93,11 +93,11 @@ static int try_to_freeze_tasks(bool user_only)
 
 		if (!wakeup) {
 			read_lock(&tasklist_lock);
-			do_each_thread(g, p) {
+			for_each_process_thread(g, p) {
 				if (p != current && !freezer_should_skip(p)
 				    && freezing(p) && !frozen(p))
 					sched_show_task(p);
-			} while_each_thread(g, p);
+			}
 			read_unlock(&tasklist_lock);
 		}
 	} else {
@@ -108,6 +108,30 @@ static int try_to_freeze_tasks(bool user_only)
 	return todo ? -EBUSY : 0;
 }
 
+static bool __check_frozen_processes(void)
+{
+	struct task_struct *g, *p;
+
+	for_each_process_thread(g, p)
+		if (p != current && !freezer_should_skip(p) && !frozen(p))
+			return false;
+
+	return true;
+}
+
+/*
+ * Returns true if all freezable tasks (except for current) are frozen already
+ */
+static bool check_frozen_processes(void)
+{
+	bool ret;
+
+	read_lock(&tasklist_lock);
+	ret = __check_frozen_processes();
+	read_unlock(&tasklist_lock);
+	return ret;
+}
+
 /**
  * freeze_processes - Signal user space processes to enter the refrigerator.
  * The current thread will not be frozen.  The same process that calls
@@ -118,6 +142,7 @@ static int try_to_freeze_tasks(bool user_only)
 int freeze_processes(void)
 {
 	int error;
+	int oom_kills_saved;
 
 	error = __usermodehelper_disable(UMH_FREEZING);
 	if (error)
@@ -132,11 +157,25 @@ int freeze_processes(void)
 	pm_wakeup_clear();
 	printk("Freezing user space processes ... ");
 	pm_freezing = true;
+	oom_kills_saved = oom_kills_count();
 	error = try_to_freeze_tasks(true);
 	if (!error) {
-		printk("done.");
 		__usermodehelper_set_disable_depth(UMH_DISABLED);
 		oom_killer_disable();
+
+		/*
+		 * There might have been an OOM kill while we were
+		 * freezing tasks and the killed task might be still
+		 * on the way out so we have to double check for race.
+		 */
+		if (oom_kills_count() != oom_kills_saved &&
+		    !check_frozen_processes()) {
+			__usermodehelper_set_disable_depth(UMH_ENABLED);
+			printk("OOM in progress.");
+			error = -EBUSY;
+		} else {
+			printk("done.");
+		}
 	}
 	printk("\n");
 	BUG_ON(in_atomic());
@@ -191,11 +230,11 @@ void thaw_processes(void)
 	thaw_workqueues();
 
 	read_lock(&tasklist_lock);
-	do_each_thread(g, p) {
+	for_each_process_thread(g, p) {
 		/* No other threads should have PF_SUSPEND_TASK set */
 		WARN_ON((p != curr) && (p->flags & PF_SUSPEND_TASK));
 		__thaw_task(p);
-	} while_each_thread(g, p);
+	}
 	read_unlock(&tasklist_lock);
 
 	WARN_ON(!(curr->flags & PF_SUSPEND_TASK));
@@ -218,10 +257,10 @@ void thaw_kernel_threads(void)
 	thaw_workqueues();
 
 	read_lock(&tasklist_lock);
-	do_each_thread(g, p) {
+	for_each_process_thread(g, p) {
 		if (p->flags & (PF_KTHREAD | PF_WQ_WORKER))
 			__thaw_task(p);
-	} while_each_thread(g, p);
+	}
 	read_unlock(&tasklist_lock);
 
 	schedule();
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index bbf405a3a18f..5340f6b91312 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -404,6 +404,23 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 		dump_tasks(memcg, nodemask);
 }
 
+/*
+ * Number of OOM killer invocations (including memcg OOM killer).
+ * Primarily used by PM freezer to check for potential races with
+ * OOM killed frozen task.
+ */
+static atomic_t oom_kills = ATOMIC_INIT(0);
+
+int oom_kills_count(void)
+{
+	return atomic_read(&oom_kills);
+}
+
+void note_oom_kill(void)
+{
+	atomic_inc(&oom_kills);
+}
+
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /*
  * Must be called while holding a reference to p, which will be released upon
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 736d8e1b6381..9cd36b822444 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2252,6 +2252,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	}
 
 	/*
+	 * PM-freezer should be notified that there might be an OOM killer on
+	 * its way to kill and wake somebody up. This is too early and we might
+	 * end up not killing anything but false positives are acceptable.
+	 * See freeze_processes.
+	 */
+	note_oom_kill();
+
+	/*
 	 * Go through the zonelist yet one more time, keep very high watermark
 	 * here, this is only to catch a parallel oom killing, we must fail if
 	 * we're still under heavy pressure.