1 files changed, 77 insertions, 145 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 79e0f3e2483..3291e82d435 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -44,64 +44,24 @@ int sysctl_oom_kill_allocating_task;
 int sysctl_oom_dump_tasks = 1;
 static DEFINE_SPINLOCK(zone_scan_lock);
 
-/*
- * compare_swap_oom_score_adj() - compare and swap current's oom_score_adj
- * @old_val: old oom_score_adj for compare
- * @new_val: new oom_score_adj for swap
- *
- * Sets the oom_score_adj value for current to @new_val iff its present value is
- * @old_val.  Usually used to reinstate a previous value to prevent racing with
- * userspacing tuning the value in the interim.
- */
-void compare_swap_oom_score_adj(int old_val, int new_val)
-{
-	struct sighand_struct *sighand = current->sighand;
-
-	spin_lock_irq(&sighand->siglock);
-	if (current->signal->oom_score_adj == old_val)
-		current->signal->oom_score_adj = new_val;
-	trace_oom_score_adj_update(current);
-	spin_unlock_irq(&sighand->siglock);
-}
-
-/**
- * test_set_oom_score_adj() - set current's oom_score_adj and return old value
- * @new_val: new oom_score_adj value
- *
- * Sets the oom_score_adj value for current to @new_val with proper
- * synchronization and returns the old value.  Usually used to temporarily
- * set a value, save the old value in the caller, and then reinstate it later.
- */
-int test_set_oom_score_adj(int new_val)
-{
-	struct sighand_struct *sighand = current->sighand;
-	int old_val;
-
-	spin_lock_irq(&sighand->siglock);
-	old_val = current->signal->oom_score_adj;
-	current->signal->oom_score_adj = new_val;
-	trace_oom_score_adj_update(current);
-	spin_unlock_irq(&sighand->siglock);
-
-	return old_val;
-}
-
 #ifdef CONFIG_NUMA
 /**
  * has_intersects_mems_allowed() - check task eligiblity for kill
- * @tsk: task struct of which task to consider
+ * @start: task struct of which task to consider
  * @mask: nodemask passed to page allocator for mempolicy ooms
  *
  * Task eligibility is determined by whether or not a candidate task, @tsk,
  * shares the same mempolicy nodes as current if it is bound by such a policy
  * and whether or not it has the same set of allowed cpuset nodes.
  */
-static bool has_intersects_mems_allowed(struct task_struct *tsk,
+static bool has_intersects_mems_allowed(struct task_struct *start,
 					const nodemask_t *mask)
 {
-	struct task_struct *start = tsk;
+	struct task_struct *tsk;
+	bool ret = false;
 
-	do {
+	rcu_read_lock();
+	for_each_thread(start, tsk) {
 		if (mask) {
 			/*
 			 * If this is a mempolicy constrained oom, tsk's
@@ -109,19 +69,20 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
 			 * mempolicy intersects current, otherwise it may be
 			 * needlessly killed.
 			 */
-			if (mempolicy_nodemask_intersects(tsk, mask))
-				return true;
+			ret = mempolicy_nodemask_intersects(tsk, mask);
 		} else {
 			/*
 			 * This is not a mempolicy constrained oom, so only
 			 * check the mems of tsk's cpuset.
 			 */
-			if (cpuset_mems_allowed_intersects(current, tsk))
-				return true;
+			ret = cpuset_mems_allowed_intersects(current, tsk);
 		}
-	} while_each_thread(start, tsk);
+		if (ret)
+			break;
+	}
+	rcu_read_unlock();
 
-	return false;
+	return ret;
 }
 #else
 static bool has_intersects_mems_allowed(struct task_struct *tsk,
@@ -139,16 +100,21 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk,
  */
 struct task_struct *find_lock_task_mm(struct task_struct *p)
 {
-	struct task_struct *t = p;
+	struct task_struct *t;
 
-	do {
+	rcu_read_lock();
+
+	for_each_thread(p, t) {
 		task_lock(t);
 		if (likely(t->mm))
-			return t;
+			goto found;
 		task_unlock(t);
-	} while_each_thread(p, t);
+	}
+	t = NULL;
+found:
+	rcu_read_unlock();
 
-	return NULL;
+	return t;
 }
 
 /* return true if the task is not adequate as candidate victim task. */
@@ -193,7 +159,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	if (!p)
 		return 0;
 
-	adj = p->signal->oom_score_adj;
+	adj = (long)p->signal->oom_score_adj;
 	if (adj == OOM_SCORE_ADJ_MIN) {
 		task_unlock(p);
 		return 0;
@@ -203,7 +169,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 * The baseline for the badness score is the proportion of RAM that each
 	 * task's rss, pagetable and swap space use.
 	 */
-	points = get_mm_rss(p->mm) + p->mm->nr_ptes +
+	points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) +
 		 get_mm_counter(p->mm, MM_SWAPENTS);
 	task_unlock(p);
 
@@ -212,7 +178,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 * implementation used by LSMs.
 	 */
 	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
-		adj -= 30;
+		points -= (points * 3) / 100;
 
 	/* Normalize to oom_score_adj units */
 	adj *= totalpages / 1000;
@@ -257,7 +223,7 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 	 * the page allocator means a mempolicy is in effect.  Cpuset policy
 	 * is enforced in get_page_from_freelist().
 	 */
-	if (nodemask && !nodes_subset(node_states[N_HIGH_MEMORY], *nodemask)) {
+	if (nodemask && !nodes_subset(node_states[N_MEMORY], *nodemask)) {
 		*totalpages = total_swap_pages;
 		for_each_node_mask(nid, *nodemask)
 			*totalpages += node_spanned_pages(nid);
@@ -310,33 +276,27 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 	if (!task->mm)
 		return OOM_SCAN_CONTINUE;
 
-	if (task->flags & PF_EXITING) {
+	/*
+	 * If task is allocating a lot of memory and has been marked to be
+	 * killed first if it triggers an oom, then select it.
+	 */
+	if (oom_task_origin(task))
+		return OOM_SCAN_SELECT;
+
+	if (task->flags & PF_EXITING && !force_kill) {
 		/*
-		 * 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 this task is not being ptraced on exit, then wait for it
+		 * to finish before killing some other task unnecessarily.
 		 */
-		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;
-		}
+		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'.
+ * number of 'points'.  Returns -1 on scan abort.
  *
  * (not docbooked, we don't want this one cluttering up the manual)
  */
@@ -349,7 +309,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 	unsigned long chosen_points = 0;
 
 	rcu_read_lock();
-	do_each_thread(g, p) {
+	for_each_process_thread(g, p) {
 		unsigned int points;
 
 		switch (oom_scan_process_thread(p, totalpages, nodemask,
@@ -362,16 +322,20 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 			continue;
 		case OOM_SCAN_ABORT:
 			rcu_read_unlock();
-			return ERR_PTR(-1UL);
+			return (struct task_struct *)(-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 (!points || points < chosen_points)
+			continue;
+		/* Prefer thread group leaders for display purposes */
+		if (points == chosen_points && thread_group_leader(chosen))
+			continue;
+
+		chosen = p;
+		chosen_points = points;
+	}
 	if (chosen)
 		get_task_struct(chosen);
 	rcu_read_unlock();
@@ -412,10 +376,10 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas
 			continue;
 		}
 
-		pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu         %5d %s\n",
+		pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu         %5hd %s\n",
 			task->pid, from_kuid(&init_user_ns, task_uid(task)),
 			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
-			task->mm->nr_ptes,
+			atomic_long_read(&task->mm->nr_ptes),
 			get_mm_counter(task->mm, MM_SWAPENTS),
 			task->signal->oom_score_adj, task->comm);
 		task_unlock(task);
@@ -428,14 +392,16 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 {
 	task_lock(current);
 	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
-		"oom_score_adj=%d\n",
+		"oom_score_adj=%hd\n",
 		current->comm, gfp_mask, order,
 		current->signal->oom_score_adj);
 	cpuset_print_task_mems_allowed(current);
 	task_unlock(current);
 	dump_stack();
-	mem_cgroup_print_oom_info(memcg, p);
-	show_mem(SHOW_MEM_FILTER_NODES);
+	if (memcg)
+		mem_cgroup_print_oom_info(memcg, p);
+	else
+		show_mem(SHOW_MEM_FILTER_NODES);
 	if (sysctl_oom_dump_tasks)
 		dump_tasks(memcg, nodemask);
 }
@@ -452,7 +418,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 {
 	struct task_struct *victim = p;
 	struct task_struct *child;
-	struct task_struct *t = p;
+	struct task_struct *t;
 	struct mm_struct *mm;
 	unsigned int victim_points = 0;
 	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
@@ -483,7 +449,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 * still freeing memory.
 	 */
 	read_lock(&tasklist_lock);
-	do {
+	for_each_thread(p, t) {
 		list_for_each_entry(child, &t->children, sibling) {
 			unsigned int child_points;
 
@@ -501,13 +467,11 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 				get_task_struct(victim);
 			}
 		}
-	} while_each_thread(p, t);
+	}
 	read_unlock(&tasklist_lock);
 
-	rcu_read_lock();
 	p = find_lock_task_mm(victim);
 	if (!p) {
-		rcu_read_unlock();
 		put_task_struct(victim);
 		return;
 	} else if (victim != p) {
@@ -533,6 +497,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 * That thread will now get access to memory reserves since it has a
 	 * pending fatal signal.
 	 */
+	rcu_read_lock();
 	for_each_process(p)
 		if (p->mm == mm && !same_thread_group(p, victim) &&
 		    !(p->flags & PF_KTHREAD)) {
@@ -639,43 +604,6 @@ void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
 	spin_unlock(&zone_scan_lock);
 }
 
-/*
- * Try to acquire the oom killer lock for all system zones.  Returns zero if a
- * parallel oom killing is taking place, otherwise locks all zones and returns
- * non-zero.
- */
-static int try_set_system_oom(void)
-{
-	struct zone *zone;
-	int ret = 1;
-
-	spin_lock(&zone_scan_lock);
-	for_each_populated_zone(zone)
-		if (zone_is_oom_locked(zone)) {
-			ret = 0;
-			goto out;
-		}
-	for_each_populated_zone(zone)
-		zone_set_flag(zone, ZONE_OOM_LOCKED);
-out:
-	spin_unlock(&zone_scan_lock);
-	return ret;
-}
-
-/*
- * Clears ZONE_OOM_LOCKED for all system zones so that failed allocation
- * attempts or page faults may now recall the oom killer, if necessary.
- */
-static void clear_system_oom(void)
-{
-	struct zone *zone;
-
-	spin_lock(&zone_scan_lock);
-	for_each_populated_zone(zone)
-		zone_clear_flag(zone, ZONE_OOM_LOCKED);
-	spin_unlock(&zone_scan_lock);
-}
-
 /**
  * out_of_memory - kill the "best" process when we run out of memory
  * @zonelist: zonelist pointer
@@ -706,11 +634,11 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		return;
 
 	/*
-	 * 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 current has a pending SIGKILL or is exiting, 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)) {
+	if (fatal_signal_pending(current) || current->flags & PF_EXITING) {
 		set_thread_flag(TIF_MEMDIE);
 		return;
 	}
@@ -740,7 +668,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		dump_header(NULL, gfp_mask, order, NULL, mpol_mask);
 		panic("Out of memory and no killable processes...\n");
 	}
-	if (PTR_ERR(p) != -1UL) {
+	if (p != (void *)-1UL) {
 		oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
 				 nodemask, "Out of memory");
 		killed = 1;
@@ -756,15 +684,19 @@ out:
 
 /*
  * The pagefault handler calls here because it is out of memory, so kill a
- * memory-hogging task.  If a populated zone has ZONE_OOM_LOCKED set, a parallel
- * oom killing is already in progress so do nothing.  If a task is found with
- * TIF_MEMDIE set, it has been killed so do nothing and allow it to exit.
+ * memory-hogging task.  If any populated zone has ZONE_OOM_LOCKED set, a
+ * parallel oom killing is already in progress so do nothing.
  */
 void pagefault_out_of_memory(void)
 {
-	if (try_set_system_oom()) {
+	struct zonelist *zonelist;
+
+	if (mem_cgroup_oom_synchronize(true))
+		return;
+
+	zonelist = node_zonelist(first_online_node, GFP_KERNEL);
+	if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) {
 		out_of_memory(NULL, 0, 0, NULL, false);
-		clear_system_oom();
+		clear_zonelist_oom(zonelist, GFP_KERNEL);
 	}
-	schedule_timeout_killable(1);
 }