mm: revert "oom: move oom_adj value"

The commit 2ff05b2b (oom: move oom_adj value) moveed the oom_adj value to
the mm_struct.  It was a very good first step for sanitize OOM.

However Paul Menage reported the commit makes regression to his job
scheduler.  Current OOM logic can kill OOM_DISABLED process.

Why? His program has the code of similar to the following.

	...
	set_oom_adj(OOM_DISABLE); /* The job scheduler never killed by oom */
	...
	if (vfork() == 0) {
		set_oom_adj(0); /* Invoked child can be killed */
		execve("foo-bar-cmd");
	}
	....

vfork() parent and child are shared the same mm_struct.  then above
set_oom_adj(0) doesn't only change oom_adj for vfork() child, it's also
change oom_adj for vfork() parent.  Then, vfork() parent (job scheduler)
lost OOM immune and it was killed.

Actually, fork-setting-exec idiom is very frequently used in userland program.
We must not break this assumption.

Then, this patch revert commit 2ff05b2b and related commit.

Reverted commit list
---------------------
- commit 2ff05b2b4e (oom: move oom_adj value from task_struct to mm_struct)
- commit 4d8b9135c3 (oom: avoid unnecessary mm locking and scanning for OOM_DISABLE)
- commit 8123681022 (oom: only oom kill exiting tasks with attached memory)
- commit 933b787b57 (mm: copy over oom_adj value at fork time)

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Paul Menage <menage@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 39 insertions, 25 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 175a67a78a9..a7b2460e922 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -58,7 +58,6 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	unsigned long points, cpu_time, run_time;
 	struct mm_struct *mm;
 	struct task_struct *child;
-	int oom_adj;
 
 	task_lock(p);
 	mm = p->mm;
@@ -66,11 +65,6 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 		task_unlock(p);
 		return 0;
 	}
-	oom_adj = mm->oom_adj;
-	if (oom_adj == OOM_DISABLE) {
-		task_unlock(p);
-		return 0;
-	}
 
 	/*
 	 * The memory size of the process is the basis for the badness.
@@ -154,15 +148,15 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 		points /= 8;
 
 	/*
-	 * Adjust the score by oom_adj.
+	 * Adjust the score by oomkilladj.
 	 */
-	if (oom_adj) {
-		if (oom_adj > 0) {
+	if (p->oomkilladj) {
+		if (p->oomkilladj > 0) {
 			if (!points)
 				points = 1;
-			points <<= oom_adj;
+			points <<= p->oomkilladj;
 		} else
-			points >>= -(oom_adj);
+			points >>= -(p->oomkilladj);
 	}
 
 #ifdef DEBUG
@@ -257,8 +251,11 @@ static struct task_struct *select_bad_process(unsigned long *ppoints,
 			*ppoints = ULONG_MAX;
 		}
 
+		if (p->oomkilladj == OOM_DISABLE)
+			continue;
+
 		points = badness(p, uptime.tv_sec);
-		if (points > *ppoints) {
+		if (points > *ppoints || !chosen) {
 			chosen = p;
 			*ppoints = points;
 		}
@@ -307,7 +304,8 @@ static void dump_tasks(const struct mem_cgroup *mem)
 		}
 		printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d     %3d %s\n",
 		       p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm,
-		       get_mm_rss(mm), (int)task_cpu(p), mm->oom_adj, p->comm);
+		       get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj,
+		       p->comm);
 		task_unlock(p);
 	} while_each_thread(g, p);
 }
@@ -325,8 +323,11 @@ static void __oom_kill_task(struct task_struct *p, int verbose)
 		return;
 	}
 
-	if (!p->mm)
+	if (!p->mm) {
+		WARN_ON(1);
+		printk(KERN_WARNING "tried to kill an mm-less task!\n");
 		return;
+	}
 
 	if (verbose)
 		printk(KERN_ERR "Killed process %d (%s)\n",
@@ -348,13 +349,28 @@ static int oom_kill_task(struct task_struct *p)
 	struct mm_struct *mm;
 	struct task_struct *g, *q;
 
-	task_lock(p);
 	mm = p->mm;
-	if (!mm || mm->oom_adj == OOM_DISABLE) {
-		task_unlock(p);
+
+	/* WARNING: mm may not be dereferenced since we did not obtain its
+	 * value from get_task_mm(p).  This is OK since all we need to do is
+	 * compare mm to q->mm below.
+	 *
+	 * Furthermore, even if mm contains a non-NULL value, p->mm may
+	 * change to NULL at any time since we do not hold task_lock(p).
+	 * However, this is of no concern to us.
+	 */
+
+	if (mm == NULL)
 		return 1;
-	}
-	task_unlock(p);
+
+	/*
+	 * Don't kill the process if any threads are set to OOM_DISABLE
+	 */
+	do_each_thread(g, q) {
+		if (q->mm == mm && q->oomkilladj == OOM_DISABLE)
+			return 1;
+	} while_each_thread(g, q);
+
 	__oom_kill_task(p, 1);
 
 	/*
@@ -377,11 +393,10 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	struct task_struct *c;
 
 	if (printk_ratelimit()) {
-		task_lock(current);
 		printk(KERN_WARNING "%s invoked oom-killer: "
-			"gfp_mask=0x%x, order=%d, oom_adj=%d\n",
-			current->comm, gfp_mask, order,
-			current->mm ? current->mm->oom_adj : OOM_DISABLE);
+			"gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
+			current->comm, gfp_mask, order, current->oomkilladj);
+		task_lock(current);
 		cpuset_print_task_mems_allowed(current);
 		task_unlock(current);
 		dump_stack();
@@ -394,9 +409,8 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	/*
 	 * If the task is already exiting, don't alarm the sysadmin or kill
 	 * its children or threads, just set TIF_MEMDIE so it can die quickly
-	 * if its mm is still attached.
 	 */
-	if (p->mm && (p->flags & PF_EXITING)) {
+	if (p->flags & PF_EXITING) {
 		__oom_kill_task(p, 0);
 		return 0;
 	}