[PATCH 11/12] oom: remove special handling for pagefault ooms

[KOSAKI Motohiro]

From: David Rientjes <rientjes@xxxxxxxxxx>

It is possible to remove the special pagefault oom handler by simply oom
locking all system zones and then calling directly into out_of_memory().

All populated zones must have ZONE_OOM_LOCKED set, otherwise there is a
parallel oom killing in progress that will lead to eventual memory
freeing so it's not necessary to needlessly kill another task.  The context
in which the pagefault is allocating memory is unknown to the oom killer,
so this is done on a system-wide level.

If a task has already been oom killed and hasn't fully exited yet, this
will be a no-op since select_bad_process() recognizes tasks across the
system with TIF_MEMDIE set.

Acked-by: Nick Piggin <npiggin@xxxxxxx>
Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
---
 mm/oom_kill.c |   86 +++++++++++++++++++++++++++++++++++++--------------------
 1 files changed, 56 insertions(+), 30 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index e4c6141..67b5fa5 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -540,6 +540,43 @@ void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
 }
 
 /*
+ * Try to acquire the oom killer lock for all system zones.  Returns zero if a
+ * parallel oom killing is taking place, otherwise locks all zones and returns
+ * non-zero.
+ */
+static int try_set_system_oom(void)
+{
+	struct zone *zone;
+	int ret = 1;
+
+	spin_lock(&zone_scan_lock);
+	for_each_populated_zone(zone)
+		if (zone_is_oom_locked(zone)) {
+			ret = 0;
+			goto out;
+		}
+	for_each_populated_zone(zone)
+		zone_set_flag(zone, ZONE_OOM_LOCKED);
+out:
+	spin_unlock(&zone_scan_lock);
+	return ret;
+}
+
+/*
+ * Clears ZONE_OOM_LOCKED for all system zones so that failed allocation
+ * attempts or page faults may now recall the oom killer, if necessary.
+ */
+static void clear_system_oom(void)
+{
+	struct zone *zone;
+
+	spin_lock(&zone_scan_lock);
+	for_each_populated_zone(zone)
+		zone_clear_flag(zone, ZONE_OOM_LOCKED);
+	spin_unlock(&zone_scan_lock);
+}
+
+/*
  * Must be called with tasklist_lock held for read.
  */
 static void __out_of_memory(gfp_t gfp_mask, int order)
@@ -573,34 +610,6 @@ retry:
 		goto retry;
 }
 
-/*
- * pagefault handler calls into here because it is out of memory but
- * doesn't know exactly how or why.
- */
-void pagefault_out_of_memory(void)
-{
-	unsigned long freed = 0;
-
-	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
-	if (freed > 0)
-		/* Got some memory back in the last second. */
-		return;
-
-	if (sysctl_panic_on_oom)
-		panic("out of memory from page fault. panic_on_oom is selected.\n");
-
-	read_lock(&tasklist_lock);
-	__out_of_memory(0, 0); /* unknown gfp_mask and order */
-	read_unlock(&tasklist_lock);
-
-	/*
-	 * Give "p" a good chance of killing itself before we
-	 * retry to allocate memory.
-	 */
-	if (!test_thread_flag(TIF_MEMDIE))
-		schedule_timeout_uninterruptible(1);
-}
-
 /**
  * out_of_memory - kill the "best" process when we run out of memory
  * @zonelist: zonelist pointer
@@ -616,7 +625,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		int order, nodemask_t *nodemask)
 {
 	unsigned long freed = 0;
-	enum oom_constraint constraint;
+	enum oom_constraint constraint = CONSTRAINT_NONE;
 
 	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
 	if (freed > 0)
@@ -632,7 +641,8 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	 * Check if there were limitations on the allocation (only relevant for
 	 * NUMA) that may require different handling.
 	 */
-	constraint = constrained_alloc(zonelist, gfp_mask, nodemask);
+	if (zonelist)
+		constraint = constrained_alloc(zonelist, gfp_mask, nodemask);
 	read_lock(&tasklist_lock);
 
 	switch (constraint) {
@@ -661,3 +671,19 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	if (!test_thread_flag(TIF_MEMDIE))
 		schedule_timeout_uninterruptible(1);
 }
+
+/*
+ * The pagefault handler calls here because it is out of memory, so kill a
+ * memory-hogging task.  If a populated zone has ZONE_OOM_LOCKED set, a parallel
+ * oom killing is already in progress so do nothing.  If a task is found with
+ * TIF_MEMDIE set, it has been killed so do nothing and allow it to exit.
+ */
+void pagefault_out_of_memory(void)
+{
+	if (try_set_system_oom()) {
+		out_of_memory(NULL, 0, 0, NULL);
+		clear_system_oom();
+	}
+	if (!test_thread_flag(TIF_MEMDIE))
+		schedule_timeout_uninterruptible(1);
+}
-- 
1.6.5.2



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/