mm: oom_kill: simplify OOM killer locking

The zonelist locking and the oom_sem are two overlapping locks that are
used to serialize global OOM killing against different things.

The historical zonelist locking serializes OOM kills from allocations with
overlapping zonelists against each other to prevent killing more tasks
than necessary in the same memory domain.  Only when neither tasklists nor
zonelists from two concurrent OOM kills overlap (tasks in separate memcgs
bound to separate nodes) are OOM kills allowed to execute in parallel.

The younger oom_sem is a read-write lock to serialize OOM killing against
the PM code trying to disable the OOM killer altogether.

However, the OOM killer is a fairly cold error path, there is really no
reason to optimize for highly performant and concurrent OOM kills.  And
the oom_sem is just flat-out redundant.

Replace both locking schemes with a single global mutex serializing OOM
kills regardless of context.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d3490b0..5cfda39 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -42,7 +42,8 @@
 int sysctl_panic_on_oom;
 int sysctl_oom_kill_allocating_task;
 int sysctl_oom_dump_tasks = 1;
-static DEFINE_SPINLOCK(zone_scan_lock);
+
+DEFINE_MUTEX(oom_lock);
 
 #ifdef CONFIG_NUMA
 /**
@@ -405,13 +406,12 @@
 static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait);
 
 bool oom_killer_disabled __read_mostly;
-static DECLARE_RWSEM(oom_sem);
 
 /**
  * mark_oom_victim - mark the given task as OOM victim
  * @tsk: task to mark
  *
- * Has to be called with oom_sem taken for read and never after
+ * Has to be called with oom_lock held and never after
  * oom has been disabled already.
  */
 void mark_oom_victim(struct task_struct *tsk)
@@ -460,14 +460,14 @@
 	 * Make sure to not race with an ongoing OOM killer
 	 * and that the current is not the victim.
 	 */
-	down_write(&oom_sem);
+	mutex_lock(&oom_lock);
 	if (test_thread_flag(TIF_MEMDIE)) {
-		up_write(&oom_sem);
+		mutex_unlock(&oom_lock);
 		return false;
 	}
 
 	oom_killer_disabled = true;
-	up_write(&oom_sem);
+	mutex_unlock(&oom_lock);
 
 	wait_event(oom_victims_wait, !atomic_read(&oom_victims));
 
@@ -634,52 +634,6 @@
 }
 EXPORT_SYMBOL_GPL(unregister_oom_notifier);
 
-/*
- * Try to acquire the OOM killer lock for the zones in zonelist.  Returns zero
- * if a parallel OOM killing is already taking place that includes a zone in
- * the zonelist.  Otherwise, locks all zones in the zonelist and returns 1.
- */
-bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_mask)
-{
-	struct zoneref *z;
-	struct zone *zone;
-	bool ret = true;
-
-	spin_lock(&zone_scan_lock);
-	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
-		if (test_bit(ZONE_OOM_LOCKED, &zone->flags)) {
-			ret = false;
-			goto out;
-		}
-
-	/*
-	 * Lock each zone in the zonelist under zone_scan_lock so a parallel
-	 * call to oom_zonelist_trylock() doesn't succeed when it shouldn't.
-	 */
-	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
-		set_bit(ZONE_OOM_LOCKED, &zone->flags);
-
-out:
-	spin_unlock(&zone_scan_lock);
-	return ret;
-}
-
-/*
- * Clears the ZONE_OOM_LOCKED flag for all zones in the zonelist so that failed
- * allocation attempts with zonelists containing them may now recall the OOM
- * killer, if necessary.
- */
-void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask)
-{
-	struct zoneref *z;
-	struct zone *zone;
-
-	spin_lock(&zone_scan_lock);
-	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
-		clear_bit(ZONE_OOM_LOCKED, &zone->flags);
-	spin_unlock(&zone_scan_lock);
-}
-
 /**
  * __out_of_memory - kill the "best" process when we run out of memory
  * @zonelist: zonelist pointer
@@ -693,8 +647,8 @@
  * OR try to be smart about which process to kill. Note that we
  * don't have to be perfect here, we just have to be good.
  */
-static void __out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
-		int order, nodemask_t *nodemask, bool force_kill)
+bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
+		   int order, nodemask_t *nodemask, bool force_kill)
 {
 	const nodemask_t *mpol_mask;
 	struct task_struct *p;
@@ -704,10 +658,13 @@
 	enum oom_constraint constraint = CONSTRAINT_NONE;
 	int killed = 0;
 
+	if (oom_killer_disabled)
+		return false;
+
 	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
 	if (freed > 0)
 		/* Got some memory back in the last second. */
-		return;
+		goto out;
 
 	/*
 	 * If current has a pending SIGKILL or is exiting, then automatically
@@ -720,7 +677,7 @@
 	if (current->mm &&
 	    (fatal_signal_pending(current) || task_will_free_mem(current))) {
 		mark_oom_victim(current);
-		return;
+		goto out;
 	}
 
 	/*
@@ -760,32 +717,8 @@
 	 */
 	if (killed)
 		schedule_timeout_killable(1);
-}
 
-/**
- * out_of_memory -  tries to invoke OOM killer.
- * @zonelist: zonelist pointer
- * @gfp_mask: memory allocation flags
- * @order: amount of memory being requested as a power of 2
- * @nodemask: nodemask passed to page allocator
- * @force_kill: true if a task must be killed, even if others are exiting
- *
- * invokes __out_of_memory if the OOM is not disabled by oom_killer_disable()
- * when it returns false. Otherwise returns true.
- */
-bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
-		int order, nodemask_t *nodemask, bool force_kill)
-{
-	bool ret = false;
-
-	down_read(&oom_sem);
-	if (!oom_killer_disabled) {
-		__out_of_memory(zonelist, gfp_mask, order, nodemask, force_kill);
-		ret = true;
-	}
-	up_read(&oom_sem);
-
-	return ret;
+	return true;
 }
 
 /*
@@ -795,27 +728,21 @@
  */
 void pagefault_out_of_memory(void)
 {
-	struct zonelist *zonelist;
-
-	down_read(&oom_sem);
 	if (mem_cgroup_oom_synchronize(true))
-		goto unlock;
+		return;
 
-	zonelist = node_zonelist(first_memory_node, GFP_KERNEL);
-	if (oom_zonelist_trylock(zonelist, GFP_KERNEL)) {
-		if (!oom_killer_disabled)
-			__out_of_memory(NULL, 0, 0, NULL, false);
-		else
-			/*
-			 * There shouldn't be any user tasks runable 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));
+	if (!mutex_trylock(&oom_lock))
+		return;
 
-		oom_zonelist_unlock(zonelist, GFP_KERNEL);
+	if (!out_of_memory(NULL, 0, 0, NULL, false)) {
+		/*
+		 * 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));
 	}
-unlock:
-	up_read(&oom_sem);
+
+	mutex_unlock(&oom_lock);
 }