[PATCH 1/2] OOM, PM: make OOM detection in the freezer path raceless

[Michal Hocko]

5695be142e20 (OOM, PM: OOM killed task shouldn't escape PM suspend)
has left a race window when OOM killer manages to note_oom_kill after
freeze_processes checks the counter. The race window is quite small and
really unlikely and partial solution deemed sufficient at the time of
submission.

Tejun wasn't happy about this partial solution though and insisted on
a full solution. That requires the full OOM and freezer exclusion,
though. This is done by this patch which introduces oom_sem RW lock
and gets rid of oom_killer_disabled global flag.

The PM code uses oom_killer_{disable,enable} which takes the lock
for write and excludes all the OOM killer invocation from any
out_of_memory users which newly returns a success status. It fails
only if the oom_sem cannot be taken for read which indicates that
OOM has been disabled. This is done by read trylock so we can never
deadlock.

The caller has to take an appropriate action when the out_of_memory
fails.

The allocation path simply fails the allocation request the same
way as previously. Sysrq path notes that the OOM didn't happen due to
OOM disable.

The page fault path ignored oom disabled flag previously with an
assumption that the page fault path cannot enter the fridge. As per
Tejun the freezing point used to be deep in the fs code. Therefore it
is safer and more robust to include pagefault_out_of_memory as well.
The task will be refaulting until there is some memory freed or PM
freezer fails because the said task cannot be frozen and re-enable OOM
killer when the OOM eventually happens if the memory still short.

There is no need to recheck all the processes with the full
synchronization anymore.

Suggested-by: Tejun Heo <tj@xxxxxxxxxx>
Signed-off-by: Michal Hocko <mhocko@xxxxxxx>

fold me
---
 drivers/tty/sysrq.c    |  6 ++++--
 include/linux/oom.h    | 25 +++++++++++++----------
 kernel/power/process.c | 50 ++++++++--------------------------------------
 mm/oom_kill.c          | 54 ++++++++++++++++++++++++++++++++------------------
 mm/page_alloc.c        | 32 +++++++++++++++---------------
 5 files changed, 77 insertions(+), 90 deletions(-)

diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 42bad18c66c9..14f3d7fd961f 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -355,8 +355,10 @@ static struct sysrq_key_op sysrq_term_op = {
 
 static void moom_callback(struct work_struct *ignored)
 {
-	out_of_memory(node_zonelist(first_memory_node, GFP_KERNEL), GFP_KERNEL,
-		      0, NULL, true);
+	if (!out_of_memory(node_zonelist(first_memory_node, GFP_KERNEL),
+			   GFP_KERNEL, 0, NULL, true)) {
+		printk(KERN_INFO "OOM killer disabled\n");
+	}
 }
 
 static DECLARE_WORK(moom_work, moom_callback);
diff --git a/include/linux/oom.h b/include/linux/oom.h
index e8d6e1058723..04b892ddca7d 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -68,22 +68,25 @@ extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 		unsigned long totalpages, const nodemask_t *nodemask,
 		bool force_kill);
 
-extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
+extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		int order, nodemask_t *mask, bool force_kill);
 extern int register_oom_notifier(struct notifier_block *nb);
 extern int unregister_oom_notifier(struct notifier_block *nb);
 
-extern bool oom_killer_disabled;
-
-static inline void oom_killer_disable(void)
-{
-	oom_killer_disabled = true;
-}
+/**
+ * oom_killer_disable - disable OOM killer in page allocator
+ *
+ * Forces all page allocations to fail rather than trigger OOM killer.
+ *
+ * This function should be used with an extreme care and any new usage
+ * should be consulted with MM people.
+ */
+extern void oom_killer_disable(void);
 
-static inline void oom_killer_enable(void)
-{
-	oom_killer_disabled = false;
-}
+/**
+ * oom_killer_enable - enable OOM killer
+ */
+extern void oom_killer_enable(void);
 
 static inline bool oom_gfp_allowed(gfp_t gfp_mask)
 {
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 5a6ec8678b9a..7d08d56cbf3f 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -108,30 +108,6 @@ 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
@@ -142,7 +118,6 @@ static bool check_frozen_processes(void)
 int freeze_processes(void)
 {
 	int error;
-	int oom_kills_saved;
 
 	error = __usermodehelper_disable(UMH_FREEZING);
 	if (error)
@@ -157,27 +132,18 @@ int freeze_processes(void)
 	pm_wakeup_clear();
 	printk("Freezing user space processes ... ");
 	pm_freezing = true;
-	oom_kills_saved = oom_kills_count();
+
+	/*
+	 * Need to exlude OOM killer from triggering while tasks are
+	 * getting frozen to make sure none of them gets killed after
+	 * try_to_freeze_tasks is done.
+	 */
+	oom_killer_disable();
 	error = try_to_freeze_tasks(true);
 	if (!error) {
 		__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("done.\n");
 	}
-	printk("\n");
 	BUG_ON(in_atomic());
 
 	if (error)
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 5340f6b91312..7f88ddd55f80 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -404,23 +404,6 @@ 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
@@ -615,8 +598,20 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask)
 	spin_unlock(&zone_scan_lock);
 }
 
+static DECLARE_RWSEM(oom_sem);
+
+void oom_killer_disable(void)
+{
+	down_write(&oom_sem);
+}
+
+void oom_killer_enable(void)
+{
+	up_write(&oom_sem);
+}
+
 /**
- * out_of_memory - kill the "best" process when we run out of memory
+ * __out_of_memory - kill the "best" process when we run out of memory
  * @zonelist: zonelist pointer
  * @gfp_mask: memory allocation flags
  * @order: amount of memory being requested as a power of 2
@@ -628,7 +623,7 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask)
  * 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.
  */
-void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
+static void __out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		int order, nodemask_t *nodemask, bool force_kill)
 {
 	const nodemask_t *mpol_mask;
@@ -693,6 +688,27 @@ out:
 		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)
+{
+	if (!down_read_trylock(&oom_sem))
+		return false;
+	__out_of_memory(zonelist, gfp_mask, order, nodemask, force_kill);
+	up_read(&oom_sem);
+
+	return true;
+}
+
 /*
  * The pagefault handler calls here because it is out of memory, so kill a
  * memory-hogging task.  If any populated zone has ZONE_OOM_LOCKED set, a
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9cd36b822444..d44d69aa7b70 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -242,8 +242,6 @@ void set_pageblock_migratetype(struct page *page, int migratetype)
 					PB_migrate, PB_migrate_end);
 }
 
-bool oom_killer_disabled __read_mostly;
-
 #ifdef CONFIG_DEBUG_VM
 static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
 {
@@ -2241,10 +2239,11 @@ static inline struct page *
 __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, struct zone *preferred_zone,
-	int classzone_idx, int migratetype)
+	int classzone_idx, int migratetype, bool *oom_failed)
 {
 	struct page *page;
 
+	*oom_failed = false;
 	/* Acquire the per-zone oom lock for each zone */
 	if (!oom_zonelist_trylock(zonelist, gfp_mask)) {
 		schedule_timeout_uninterruptible(1);
@@ -2252,14 +2251,6 @@ __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.
@@ -2289,8 +2280,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 			goto out;
 	}
 	/* Exhausted what can be done so it's blamo time */
-	out_of_memory(zonelist, gfp_mask, order, nodemask, false);
-
+	if (!out_of_memory(zonelist, gfp_mask, order, nodemask, false))
+		*oom_failed = true;
 out:
 	oom_zonelist_unlock(zonelist, gfp_mask);
 	return page;
@@ -2716,8 +2707,8 @@ rebalance:
 	 */
 	if (!did_some_progress) {
 		if (oom_gfp_allowed(gfp_mask)) {
-			if (oom_killer_disabled)
-				goto nopage;
+			bool oom_failed;
+
 			/* Coredumps can quickly deplete all memory reserves */
 			if ((current->flags & PF_DUMPCORE) &&
 			    !(gfp_mask & __GFP_NOFAIL))
@@ -2725,10 +2716,19 @@ rebalance:
 			page = __alloc_pages_may_oom(gfp_mask, order,
 					zonelist, high_zoneidx,
 					nodemask, preferred_zone,
-					classzone_idx, migratetype);
+					classzone_idx, migratetype,
+					&oom_failed);
+
 			if (page)
 				goto got_pg;
 
+			/*
+			 * OOM killer might be disabled and then we have to
+			 * fail the allocation
+			 */
+			if (oom_failed)
+				goto nopage;
+
 			if (!(gfp_mask & __GFP_NOFAIL)) {
 				/*
 				 * The oom killer is not called for high-order
-- 
2.1.1

-- 
Michal Hocko
SUSE Labs
--
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/