oom: /proc/<pid>/oom_score treat kernel thread honestly

If a kernel thread is using use_mm(), badness() returns a positive value.
This is not a big issue because caller take care of it correctly.  But
there is one exception, /proc/<pid>/oom_score calls badness() directly and
doesn't care that the task is a regular process.

Another example, /proc/1/oom_score return !0 value.  But it's unkillable.
This incorrectness makes administration a little confusing.

This patch fixes it.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/proc/base.c b/fs/proc/base.c
index acb7ef8..fc23f62 100644 (file)
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -428,7 +428,8 @@ static const struct file_operations proc_lstats_operations = {
 #endif
 
 /* The badness from the OOM killer */
-unsigned long badness(struct task_struct *p, unsigned long uptime);
+unsigned long badness(struct task_struct *p, struct mem_cgroup *mem,
+                     nodemask_t *nodemask, unsigned long uptime);
 static int proc_oom_score(struct task_struct *task, char *buffer)
 {
        unsigned long points = 0;
@@ -437,7 +438,7 @@ static int proc_oom_score(struct task_struct *task, char *buffer)
        do_posix_clock_monotonic_gettime(&uptime);
        read_lock(&tasklist_lock);
        if (pid_alive(task))
-               points = badness(task, uptime.tv_sec);
+               points = badness(task, NULL, NULL, uptime.tv_sec);
        read_unlock(&tasklist_lock);
        return sprintf(buffer, "%lu\n", points);
 }

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 3999747..867bd26 100644 (file)
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -139,8 +139,8 @@ static bool oom_unkillable_task(struct task_struct *p, struct mem_cgroup *mem,
  *    algorithm has been meticulously tuned to meet the principle
  *    of least surprise ... (be careful when you change it)
  */
-
-unsigned long badness(struct task_struct *p, unsigned long uptime)
+unsigned long badness(struct task_struct *p, struct mem_cgroup *mem,
+                     const nodemask_t *nodemask, unsigned long uptime)
 {
        unsigned long points, cpu_time, run_time;
        struct task_struct *child;
@@ -150,6 +150,8 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
        unsigned long utime;
        unsigned long stime;
 
+       if (oom_unkillable_task(p, mem, nodemask))
+               return 0;
        if (oom_adj == OOM_DISABLE)
                return 0;
 
@@ -351,7 +353,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints,
                if (p->signal->oom_adj == OOM_DISABLE)
                        continue;
 
-               points = badness(p, uptime.tv_sec);
+               points = badness(p, mem, nodemask, uptime.tv_sec);
                if (points > *ppoints || !chosen) {
                        chosen = p;
                        *ppoints = points;
@@ -482,11 +484,10 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 
                        if (child->mm == p->mm)
                                continue;
-                       if (oom_unkillable_task(p, mem, nodemask))
-                               continue;
 
                        /* badness() returns 0 if the thread is unkillable */
-                       child_points = badness(child, uptime.tv_sec);
+                       child_points = badness(child, mem, nodemask,
+                                              uptime.tv_sec);
                        if (child_points > victim_points) {
                                victim = child;
                                victim_points = child_points;