memcontrol: move oom task exclusion to tasklist scan

Creates a helper function to return non-zero if a task is a member of a
memory controller:

	int task_in_mem_cgroup(const struct task_struct *task,
			       const struct mem_cgroup *mem);

When the OOM killer is constrained by the memory controller, the exclusion
of tasks that are not a member of that controller was previously misplaced
and appeared in the badness scoring function.  It should be excluded
during the tasklist scan in select_bad_process() instead.

[akpm@linux-foundation.org: build fix]
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 19 insertions, 7 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 4f58026..42536c7 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -48,6 +48,7 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
 extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 					gfp_t gfp_mask);
+int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
 
 static inline struct mem_cgroup *mm_cgroup(const struct mm_struct *mm)
 {
@@ -110,6 +111,12 @@ static inline struct mem_cgroup *mm_cgroup(const struct mm_struct *mm)
 	return NULL;
 }
 
+static inline int task_in_mem_cgroup(struct task_struct *task,
+				     const struct mem_cgroup *mem)
+{
+	return 1;
+}
+
 #endif /* CONFIG_CGROUP_MEM_CONT */
 
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f6cdbf7..2fadd48 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -170,6 +170,16 @@ static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
 		list_move(&pc->lru, &pc->mem_cgroup->inactive_list);
 }
 
+int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
+{
+	int ret;
+
+	task_lock(task);
+	ret = task->mm && mm_cgroup(task->mm) == mem;
+	task_unlock(task);
+	return ret;
+}
+
 /*
  * This routine assumes that the appropriate zone's lru lock is already held
  */
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 64751dc..ef5084d 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -65,13 +65,6 @@ unsigned long badness(struct task_struct *p, unsigned long uptime,
 		return 0;
 	}
 
-#ifdef CONFIG_CGROUP_MEM_CONT
-	if (mem != NULL && mm->mem_cgroup != mem) {
-		task_unlock(p);
-		return 0;
-	}
-#endif
-
 	/*
 	 * The memory size of the process is the basis for the badness.
 	 */
@@ -223,6 +216,8 @@ static struct task_struct *select_bad_process(unsigned long *ppoints,
 		/* skip the init task */
 		if (is_global_init(p))
 			continue;
+		if (mem && !task_in_mem_cgroup(p, mem))
+			continue;
 
 		/*
 		 * This task already has access to memory reserves and is