Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - fsnotify fix

 - poll() timeout fix

 - a few scripts/ tweaks

 - debugobjects updates

 - the (small) ocfs2 queue

 - Minor fixes to kernel/padata.c

 - Maybe half of the MM queue

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (117 commits)
  mm, page_alloc: restore the original nodemask if the fast path allocation failed
  mm, page_alloc: uninline the bad page part of check_new_page()
  mm, page_alloc: don't duplicate code in free_pcp_prepare
  mm, page_alloc: defer debugging checks of pages allocated from the PCP
  mm, page_alloc: defer debugging checks of freed pages until a PCP drain
  cpuset: use static key better and convert to new API
  mm, page_alloc: inline pageblock lookup in page free fast paths
  mm, page_alloc: remove unnecessary variable from free_pcppages_bulk
  mm, page_alloc: pull out side effects from free_pages_check
  mm, page_alloc: un-inline the bad part of free_pages_check
  mm, page_alloc: check multiple page fields with a single branch
  mm, page_alloc: remove field from alloc_context
  mm, page_alloc: avoid looking up the first zone in a zonelist twice
  mm, page_alloc: shortcut watermark checks for order-0 pages
  mm, page_alloc: reduce cost of fair zone allocation policy retry
  mm, page_alloc: shorten the page allocator fast path
  mm, page_alloc: check once if a zone has isolated pageblocks
  mm, page_alloc: move __GFP_HARDWALL modifications out of the fastpath
  mm, page_alloc: simplify last cpupid reset
  mm, page_alloc: remove unnecessary initialisation from __alloc_pages_nodemask()
  ...

1 files changed, 88 insertions, 24 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 86349586eacb..415f7eb913fa 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -412,6 +412,25 @@ 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
@@ -491,14 +510,10 @@ 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);
 	return ret;
@@ -519,6 +534,15 @@ 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 +587,53 @@ 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) {
+			bool exiting;
+
+			if (!process_shares_mm(p, mm))
+				continue;
+			if (same_thread_group(p, tsk))
+				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.
+			 */
+			spin_lock_irq(&p->sighand->siglock);
+			exiting = signal_group_exit(p->signal);
+			spin_unlock_irq(&p->sighand->siglock);
+			if (exiting)
+				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");
@@ -653,24 +724,6 @@ 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 +747,7 @@ 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 +927,20 @@ 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.
 	 */