1 files changed, 112 insertions, 111 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index ac300c99baf6..198600861638 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -288,76 +288,93 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 }
 #endif
 
+enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
+		unsigned long totalpages, const nodemask_t *nodemask,
+		bool force_kill)
+{
+	if (task->exit_state)
+		return OOM_SCAN_CONTINUE;
+	if (oom_unkillable_task(task, NULL, nodemask))
+		return OOM_SCAN_CONTINUE;
+
+	/*
+	 * This task already has access to memory reserves and is being killed.
+	 * Don't allow any other task to have access to the reserves.
+	 */
+	if (test_tsk_thread_flag(task, TIF_MEMDIE)) {
+		if (unlikely(frozen(task)))
+			__thaw_task(task);
+		if (!force_kill)
+			return OOM_SCAN_ABORT;
+	}
+	if (!task->mm)
+		return OOM_SCAN_CONTINUE;
+
+	if (task->flags & PF_EXITING) {
+		/*
+		 * If task is current and is in the process of releasing memory,
+		 * allow the "kill" to set TIF_MEMDIE, which will allow it to
+		 * access memory reserves.  Otherwise, it may stall forever.
+		 *
+		 * The iteration isn't broken here, however, in case other
+		 * threads are found to have already been oom killed.
+		 */
+		if (task == current)
+			return OOM_SCAN_SELECT;
+		else if (!force_kill) {
+			/*
+			 * If this task is not being ptraced on exit, then wait
+			 * for it to finish before killing some other task
+			 * unnecessarily.
+			 */
+			if (!(task->group_leader->ptrace & PT_TRACE_EXIT))
+				return OOM_SCAN_ABORT;
+		}
+	}
+	return OOM_SCAN_OK;
+}
+
 /*
  * Simple selection loop. We chose the process with the highest
- * number of 'points'. We expect the caller will lock the tasklist.
+ * number of 'points'.
  *
  * (not docbooked, we don't want this one cluttering up the manual)
  */
 static struct task_struct *select_bad_process(unsigned int *ppoints,
-		unsigned long totalpages, struct mem_cgroup *memcg,
-		const nodemask_t *nodemask, bool force_kill)
+		unsigned long totalpages, const nodemask_t *nodemask,
+		bool force_kill)
 {
 	struct task_struct *g, *p;
 	struct task_struct *chosen = NULL;
 	unsigned long chosen_points = 0;
 
+	rcu_read_lock();
 	do_each_thread(g, p) {
 		unsigned int points;
 
-		if (p->exit_state)
-			continue;
-		if (oom_unkillable_task(p, memcg, nodemask))
-			continue;
-
-		/*
-		 * This task already has access to memory reserves and is
-		 * being killed. Don't allow any other task access to the
-		 * memory reserve.
-		 *
-		 * Note: this may have a chance of deadlock if it gets
-		 * blocked waiting for another task which itself is waiting
-		 * for memory. Is there a better alternative?
-		 */
-		if (test_tsk_thread_flag(p, TIF_MEMDIE)) {
-			if (unlikely(frozen(p)))
-				__thaw_task(p);
-			if (!force_kill)
-				return ERR_PTR(-1UL);
-		}
-		if (!p->mm)
+		switch (oom_scan_process_thread(p, totalpages, nodemask,
+						force_kill)) {
+		case OOM_SCAN_SELECT:
+			chosen = p;
+			chosen_points = ULONG_MAX;
+			/* fall through */
+		case OOM_SCAN_CONTINUE:
 			continue;
-
-		if (p->flags & PF_EXITING) {
-			/*
-			 * If p is the current task and is in the process of
-			 * releasing memory, we allow the "kill" to set
-			 * TIF_MEMDIE, which will allow it to gain access to
-			 * memory reserves.  Otherwise, it may stall forever.
-			 *
-			 * The loop isn't broken here, however, in case other
-			 * threads are found to have already been oom killed.
-			 */
-			if (p == current) {
-				chosen = p;
-				chosen_points = ULONG_MAX;
-			} else if (!force_kill) {
-				/*
-				 * If this task is not being ptraced on exit,
-				 * then wait for it to finish before killing
-				 * some other task unnecessarily.
-				 */
-				if (!(p->group_leader->ptrace & PT_TRACE_EXIT))
-					return ERR_PTR(-1UL);
-			}
-		}
-
-		points = oom_badness(p, memcg, nodemask, totalpages);
+		case OOM_SCAN_ABORT:
+			rcu_read_unlock();
+			return ERR_PTR(-1UL);
+		case OOM_SCAN_OK:
+			break;
+		};
+		points = oom_badness(p, NULL, nodemask, totalpages);
 		if (points > chosen_points) {
 			chosen = p;
 			chosen_points = points;
 		}
 	} while_each_thread(g, p);
+	if (chosen)
+		get_task_struct(chosen);
+	rcu_read_unlock();
 
 	*ppoints = chosen_points * 1000 / totalpages;
 	return chosen;
@@ -371,17 +388,16 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
  * Dumps the current memory state of all eligible tasks.  Tasks not in the same
  * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
  * are not shown.
- * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj
- * value, oom_score_adj value, and name.
- *
- * Call with tasklist_lock read-locked.
+ * State information includes task's pid, uid, tgid, vm size, rss, nr_ptes,
+ * swapents, oom_score_adj value, and name.
  */
 static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemask)
 {
 	struct task_struct *p;
 	struct task_struct *task;
 
-	pr_info("[ pid ]   uid  tgid total_vm      rss cpu oom_adj oom_score_adj name\n");
+	pr_info("[ pid ]   uid  tgid total_vm      rss nr_ptes swapents oom_score_adj name\n");
+	rcu_read_lock();
 	for_each_process(p) {
 		if (oom_unkillable_task(p, memcg, nodemask))
 			continue;
@@ -396,13 +412,15 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas
 			continue;
 		}
 
-		pr_info("[%5d] %5d %5d %8lu %8lu %3u     %3d         %5d %s\n",
+		pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu         %5d %s\n",
 			task->pid, from_kuid(&init_user_ns, task_uid(task)),
 			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
-			task_cpu(task), task->signal->oom_adj,
+			task->mm->nr_ptes,
+			get_mm_counter(task->mm, MM_SWAPENTS),
 			task->signal->oom_score_adj, task->comm);
 		task_unlock(task);
 	}
+	rcu_read_unlock();
 }
 
 static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
@@ -423,10 +441,14 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 }
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
-static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
-			     unsigned int points, unsigned long totalpages,
-			     struct mem_cgroup *memcg, nodemask_t *nodemask,
-			     const char *message)
+/*
+ * Must be called while holding a reference to p, which will be released upon
+ * returning.
+ */
+void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
+		      unsigned int points, unsigned long totalpages,
+		      struct mem_cgroup *memcg, nodemask_t *nodemask,
+		      const char *message)
 {
 	struct task_struct *victim = p;
 	struct task_struct *child;
@@ -442,6 +464,7 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 */
 	if (p->flags & PF_EXITING) {
 		set_tsk_thread_flag(p, TIF_MEMDIE);
+		put_task_struct(p);
 		return;
 	}
 
@@ -459,6 +482,7 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 * parent.  This attempts to lose the minimal amount of work done while
 	 * still freeing memory.
 	 */
+	read_lock(&tasklist_lock);
 	do {
 		list_for_each_entry(child, &t->children, sibling) {
 			unsigned int child_points;
@@ -471,15 +495,26 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 			child_points = oom_badness(child, memcg, nodemask,
 								totalpages);
 			if (child_points > victim_points) {
+				put_task_struct(victim);
 				victim = child;
 				victim_points = child_points;
+				get_task_struct(victim);
 			}
 		}
 	} while_each_thread(p, t);
+	read_unlock(&tasklist_lock);
 
-	victim = find_lock_task_mm(victim);
-	if (!victim)
+	rcu_read_lock();
+	p = find_lock_task_mm(victim);
+	if (!p) {
+		rcu_read_unlock();
+		put_task_struct(victim);
 		return;
+	} else if (victim != p) {
+		get_task_struct(p);
+		put_task_struct(victim);
+		victim = p;
+	}
 
 	/* mm cannot safely be dereferenced after task_unlock(victim) */
 	mm = victim->mm;
@@ -510,17 +545,19 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 			task_unlock(p);
 			do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
 		}
+	rcu_read_unlock();
 
 	set_tsk_thread_flag(victim, TIF_MEMDIE);
 	do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
+	put_task_struct(victim);
 }
 #undef K
 
 /*
  * Determines whether the kernel must panic because of the panic_on_oom sysctl.
  */
-static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
-				int order, const nodemask_t *nodemask)
+void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
+			int order, const nodemask_t *nodemask)
 {
 	if (likely(!sysctl_panic_on_oom))
 		return;
@@ -533,42 +570,11 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
 		if (constraint != CONSTRAINT_NONE)
 			return;
 	}
-	read_lock(&tasklist_lock);
 	dump_header(NULL, gfp_mask, order, NULL, nodemask);
-	read_unlock(&tasklist_lock);
 	panic("Out of memory: %s panic_on_oom is enabled\n",
 		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
 }
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
-			      int order)
-{
-	unsigned long limit;
-	unsigned int points = 0;
-	struct task_struct *p;
-
-	/*
-	 * If current has a pending SIGKILL, then automatically select it.  The
-	 * goal is to allow it to allocate so that it may quickly exit and free
-	 * its memory.
-	 */
-	if (fatal_signal_pending(current)) {
-		set_thread_flag(TIF_MEMDIE);
-		return;
-	}
-
-	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
-	limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
-	read_lock(&tasklist_lock);
-	p = select_bad_process(&points, limit, memcg, NULL, false);
-	if (p && PTR_ERR(p) != -1UL)
-		oom_kill_process(p, gfp_mask, order, points, limit, memcg, NULL,
-				 "Memory cgroup out of memory");
-	read_unlock(&tasklist_lock);
-}
-#endif
-
 static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
 
 int register_oom_notifier(struct notifier_block *nb)
@@ -690,7 +696,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	struct task_struct *p;
 	unsigned long totalpages;
 	unsigned long freed = 0;
-	unsigned int points;
+	unsigned int uninitialized_var(points);
 	enum oom_constraint constraint = CONSTRAINT_NONE;
 	int killed = 0;
 
@@ -718,22 +724,20 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL;
 	check_panic_on_oom(constraint, gfp_mask, order, mpol_mask);
 
-	read_lock(&tasklist_lock);
-	if (sysctl_oom_kill_allocating_task &&
+	if (sysctl_oom_kill_allocating_task && current->mm &&
 	    !oom_unkillable_task(current, NULL, nodemask) &&
-	    current->mm) {
+	    current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
+		get_task_struct(current);
 		oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL,
 				 nodemask,
 				 "Out of memory (oom_kill_allocating_task)");
 		goto out;
 	}
 
-	p = select_bad_process(&points, totalpages, NULL, mpol_mask,
-			       force_kill);
+	p = select_bad_process(&points, totalpages, mpol_mask, force_kill);
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!p) {
 		dump_header(NULL, gfp_mask, order, NULL, mpol_mask);
-		read_unlock(&tasklist_lock);
 		panic("Out of memory and no killable processes...\n");
 	}
 	if (PTR_ERR(p) != -1UL) {
@@ -742,14 +746,12 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		killed = 1;
 	}
 out:
-	read_unlock(&tasklist_lock);
-
 	/*
-	 * Give "p" a good chance of killing itself before we
-	 * retry to allocate memory unless "p" is current
+	 * Give the killed threads a good chance of exiting before trying to
+	 * allocate memory again.
 	 */
-	if (killed && !test_thread_flag(TIF_MEMDIE))
-		schedule_timeout_uninterruptible(1);
+	if (killed)
+		schedule_timeout_killable(1);
 }
 
 /*
@@ -764,6 +766,5 @@ void pagefault_out_of_memory(void)
 		out_of_memory(NULL, 0, 0, NULL, false);
 		clear_system_oom();
 	}
-	if (!test_thread_flag(TIF_MEMDIE))
-		schedule_timeout_uninterruptible(1);
+	schedule_timeout_killable(1);
 }