Merge branch 'akpm' (patches from Andrew)

Merge patch-bomb from Andrew Morton:

 - inotify tweaks

 - some ocfs2 updates (many more are awaiting review)

 - various misc bits

 - kernel/watchdog.c updates

 - Some of mm.  I have a huge number of MM patches this time and quite a
   lot of it is quite difficult and much will be held over to next time.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (162 commits)
  selftests: vm: add tests for lock on fault
  mm: mlock: add mlock flags to enable VM_LOCKONFAULT usage
  mm: introduce VM_LOCKONFAULT
  mm: mlock: add new mlock system call
  mm: mlock: refactor mlock, munlock, and munlockall code
  kasan: always taint kernel on report
  mm, slub, kasan: enable user tracking by default with KASAN=y
  kasan: use IS_ALIGNED in memory_is_poisoned_8()
  kasan: Fix a type conversion error
  lib: test_kasan: add some testcases
  kasan: update reference to kasan prototype repo
  kasan: move KASAN_SANITIZE in arch/x86/boot/Makefile
  kasan: various fixes in documentation
  kasan: update log messages
  kasan: accurately determine the type of the bad access
  kasan: update reported bug types for kernel memory accesses
  kasan: update reported bug types for not user nor kernel memory accesses
  mm/kasan: prevent deadlock in kasan reporting
  mm/kasan: don't use kasan shadow pointer in generic functions
  mm/kasan: MODULE_VADDR is not available on all archs
  ...

1 files changed, 40 insertions, 19 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 1ecc0bcaecc5..e4778285d8d1 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -377,13 +377,11 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 static void dump_header(struct oom_control *oc, struct task_struct *p,
 			struct mem_cgroup *memcg)
 {
-	task_lock(current);
 	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
 		"oom_score_adj=%hd\n",
 		current->comm, oc->gfp_mask, oc->order,
 		current->signal->oom_score_adj);
-	cpuset_print_task_mems_allowed(current);
-	task_unlock(current);
+	cpuset_print_current_mems_allowed();
 	dump_stack();
 	if (memcg)
 		mem_cgroup_print_oom_info(memcg, p);
@@ -476,6 +474,24 @@ void oom_killer_enable(void)
 	oom_killer_disabled = false;
 }
 
+/*
+ * task->mm can be NULL if the task is the exited group leader.  So to
+ * determine whether the task is using a particular mm, we examine all the
+ * task's threads: if one of those is using this mm then this task was also
+ * using it.
+ */
+static bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
+{
+	struct task_struct *t;
+
+	for_each_thread(p, t) {
+		struct mm_struct *t_mm = READ_ONCE(t->mm);
+		if (t_mm)
+			return t_mm == mm;
+	}
+	return false;
+}
+
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /*
  * Must be called while holding a reference to p, which will be released upon
@@ -509,10 +525,8 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 	if (__ratelimit(&oom_rs))
 		dump_header(oc, p, memcg);
 
-	task_lock(p);
 	pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
 		message, task_pid_nr(p), p->comm, points);
-	task_unlock(p);
 
 	/*
 	 * If any of p's children has a different mm and is eligible for kill,
@@ -525,7 +539,7 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 		list_for_each_entry(child, &t->children, sibling) {
 			unsigned int child_points;
 
-			if (child->mm == p->mm)
+			if (process_shares_mm(child, p->mm))
 				continue;
 			/*
 			 * oom_badness() returns 0 if the thread is unkillable
@@ -552,8 +566,15 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 		victim = p;
 	}
 
-	/* mm cannot safely be dereferenced after task_unlock(victim) */
+	/* Get a reference to safely compare mm after task_unlock(victim) */
 	mm = victim->mm;
+	atomic_inc(&mm->mm_count);
+	/*
+	 * We should send SIGKILL before setting TIF_MEMDIE in order to prevent
+	 * the OOM victim from depleting the memory reserves from the user
+	 * space under its control.
+	 */
+	do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
 	mark_oom_victim(victim);
 	pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
 		task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
@@ -571,21 +592,21 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 	 * pending fatal signal.
 	 */
 	rcu_read_lock();
-	for_each_process(p)
-		if (p->mm == mm && !same_thread_group(p, victim) &&
-		    !(p->flags & PF_KTHREAD)) {
-			if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
-				continue;
+	for_each_process(p) {
+		if (!process_shares_mm(p, mm))
+			continue;
+		if (same_thread_group(p, victim))
+			continue;
+		if (unlikely(p->flags & PF_KTHREAD))
+			continue;
+		if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+			continue;
 
-			task_lock(p);	/* Protect ->comm from prctl() */
-			pr_err("Kill process %d (%s) sharing same memory\n",
-				task_pid_nr(p), p->comm);
-			task_unlock(p);
-			do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
-		}
+		do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
+	}
 	rcu_read_unlock();
 
-	do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
+	mmdrop(mm);
 	put_task_struct(victim);
 }
 #undef K