X-Git-Url: https://bbs.cooldavid.org/git/?a=blobdiff_plain;f=mm%2Foom_kill.c;h=7dcca55ede7ca1493df615af994f6ba23c1bb129;hb=bba14de98753cb6599a2dae0e520714b2153522d;hp=4029583a10241aaa84e3937ee216740e0a88a363;hpb=02f36038c568111ad4fc433f6fa760ff5e38fab4;p=net-next-2.6.git

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 4029583a102..7dcca55ede7 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -162,10 +162,11 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 		return 0;
 
 	/*
-	 * Shortcut check for OOM_SCORE_ADJ_MIN so the entire heuristic doesn't
-	 * need to be executed for something that cannot be killed.
+	 * Shortcut check for a thread sharing p->mm that is OOM_SCORE_ADJ_MIN
+	 * so the entire heuristic doesn't need to be executed for something
+	 * that cannot be killed.
 	 */
-	if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+	if (atomic_read(&p->mm->oom_disable_count)) {
 		task_unlock(p);
 		return 0;
 	}
@@ -403,16 +404,40 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 #define K(x) ((x) << (PAGE_SHIFT-10))
 static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem)
 {
+	struct task_struct *q;
+	struct mm_struct *mm;
+
 	p = find_lock_task_mm(p);
 	if (!p)
 		return 1;
 
+	/* mm cannot be safely dereferenced after task_unlock(p) */
+	mm = p->mm;
+
 	pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
 		task_pid_nr(p), p->comm, K(p->mm->total_vm),
 		K(get_mm_counter(p->mm, MM_ANONPAGES)),
 		K(get_mm_counter(p->mm, MM_FILEPAGES)));
 	task_unlock(p);
 
+	/*
+	 * Kill all processes sharing p->mm in other thread groups, if any.
+	 * They don't get access to memory reserves or a higher scheduler
+	 * priority, though, to avoid depletion of all memory or task
+	 * starvation.  This prevents mm->mmap_sem livelock when an oom killed
+	 * task cannot exit because it requires the semaphore and its contended
+	 * by another thread trying to allocate memory itself.  That thread will
+	 * now get access to memory reserves since it has a pending fatal
+	 * signal.
+	 */
+	for_each_process(q)
+		if (q->mm == mm && !same_thread_group(q, p)) {
+			task_lock(q);	/* Protect ->comm from prctl() */
+			pr_err("Kill process %d (%s) sharing same memory\n",
+				task_pid_nr(q), q->comm);
+			task_unlock(q);
+			force_sig(SIGKILL, q);
+		}
 
 	set_tsk_thread_flag(p, TIF_MEMDIE);
 	force_sig(SIGKILL, p);
@@ -680,7 +705,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	read_lock(&tasklist_lock);
 	if (sysctl_oom_kill_allocating_task &&
 	    !oom_unkillable_task(current, NULL, nodemask) &&
-	    (current->signal->oom_adj != OOM_DISABLE)) {
+	    current->mm && !atomic_read(&current->mm->oom_disable_count)) {
 		/*
 		 * oom_kill_process() needs tasklist_lock held.  If it returns
 		 * non-zero, current could not be killed so we must fallback to