Merge tag 'v4.9.207' of git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable into odroidg12-4.9.y

This is the 4.9.207 stable release

kernel/audit_watch.c

@@ -365,12 +365,12 @@ static int audit_get_nd(struct audit_watch *watch, struct path *parent)
 	struct dentry *d = kern_path_locked(watch->path, parent);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
-	inode_unlock(d_backing_inode(parent->dentry));
 	if (d_is_positive(d)) {
 		/* update watch filter fields */
 		watch->dev = d->d_sb->s_dev;
 		watch->ino = d_backing_inode(d)->i_ino;
 	}
+	inode_unlock(d_backing_inode(parent->dentry));
 	dput(d);
 	return 0;
 }

kernel/cgroup_pids.c

@@ -48,7 +48,7 @@ struct pids_cgroup {
 	 * %PIDS_MAX = (%PID_MAX_LIMIT + 1).
 	 */
 	atomic64_t			counter;
-	int64_t				limit;
+	atomic64_t			limit;
 
 	/* Handle for "pids.events" */
 	struct cgroup_file		events_file;
@@ -76,8 +76,8 @@ pids_css_alloc(struct cgroup_subsys_state *parent)
 	if (!pids)
 		return ERR_PTR(-ENOMEM);
 
-	pids->limit = PIDS_MAX;
 	atomic64_set(&pids->counter, 0);
+	atomic64_set(&pids->limit, PIDS_MAX);
 	atomic64_set(&pids->events_limit, 0);
 	return &pids->css;
 }
@@ -149,13 +149,14 @@ static int pids_try_charge(struct pids_cgroup *pids, int num)
 
 	for (p = pids; parent_pids(p); p = parent_pids(p)) {
 		int64_t new = atomic64_add_return(num, &p->counter);
+		int64_t limit = atomic64_read(&p->limit);
 
 		/*
 		 * Since new is capped to the maximum number of pid_t, if
 		 * p->limit is %PIDS_MAX then we know that this test will never
 		 * fail.
 		 */
-		if (new > p->limit)
+		if (new > limit)
 			goto revert;
 	}
 
@@ -280,7 +281,7 @@ set_limit:
 	 * Limit updates don't need to be mutex'd, since it isn't
 	 * critical that any racing fork()s follow the new limit.
 	 */
-	pids->limit = limit;
+	atomic64_set(&pids->limit, limit);
 	return nbytes;
 }
 
@@ -288,7 +289,7 @@ static int pids_max_show(struct seq_file *sf, void *v)
 {
 	struct cgroup_subsys_state *css = seq_css(sf);
 	struct pids_cgroup *pids = css_pids(css);
-	int64_t limit = pids->limit;
+	int64_t limit = atomic64_read(&pids->limit);
 
 	if (limit >= PIDS_MAX)
 		seq_printf(sf, "%s\n", PIDS_MAX_STR);

kernel/module.c

@@ -995,6 +995,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 	strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module));
 
 	free_module(mod);
+	/* someone could wait for the module in add_unformed_module() */
+	wake_up_all(&module_wq);
 	return 0;
 out:
 	mutex_unlock(&module_mutex);

kernel/sched/fair.c

@@ -4649,20 +4649,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 		if (++count > 3) {
 			u64 new, old = ktime_to_ns(cfs_b->period);
 
-			new = (old * 147) / 128; /* ~115% */
-			new = min(new, max_cfs_quota_period);
+			/*
+			 * Grow period by a factor of 2 to avoid losing precision.
+			 * Precision loss in the quota/period ratio can cause __cfs_schedulable
+			 * to fail.
+			 */
+			new = old * 2;
+			if (new < max_cfs_quota_period) {
+				cfs_b->period = ns_to_ktime(new);
+				cfs_b->quota *= 2;
 
-			cfs_b->period = ns_to_ktime(new);
-
-			/* since max is 1s, this is limited to 1e9^2, which fits in u64 */
-			cfs_b->quota *= new;
-			cfs_b->quota = div64_u64(cfs_b->quota, old);
-
-			pr_warn_ratelimited(
-        "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
-	                        smp_processor_id(),
-	                        div_u64(new, NSEC_PER_USEC),
-                                div_u64(cfs_b->quota, NSEC_PER_USEC));
+				pr_warn_ratelimited(
+	"cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+					smp_processor_id(),
+					div_u64(new, NSEC_PER_USEC),
+					div_u64(cfs_b->quota, NSEC_PER_USEC));
+			} else {
+				pr_warn_ratelimited(
+	"cfs_period_timer[cpu%d]: period too short, but cannot scale up without losing precision (cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+					smp_processor_id(),
+					div_u64(old, NSEC_PER_USEC),
+					div_u64(cfs_b->quota, NSEC_PER_USEC));
+			}
 
 			/* reset count so we don't come right back in here */
 			count = 0;

kernel/workqueue.c

@@ -2363,8 +2363,14 @@ repeat:
 			 */
 			if (need_to_create_worker(pool)) {
 				spin_lock(&wq_mayday_lock);
-				get_pwq(pwq);
-				list_move_tail(&pwq->mayday_node, &wq->maydays);
+				/*
+				 * Queue iff we aren't racing destruction
+				 * and somebody else hasn't queued it already.
+				 */
+				if (wq->rescuer && list_empty(&pwq->mayday_node)) {
+					get_pwq(pwq);
+					list_add_tail(&pwq->mayday_node, &wq->maydays);
+				}
 				spin_unlock(&wq_mayday_lock);
 			}
 		}
@@ -4050,9 +4056,29 @@ void destroy_workqueue(struct workqueue_struct *wq)
 	struct pool_workqueue *pwq;
 	int node;
 
+	/*
+	 * Remove it from sysfs first so that sanity check failure doesn't
+	 * lead to sysfs name conflicts.
+	 */
+	workqueue_sysfs_unregister(wq);
+
 	/* drain it before proceeding with destruction */
 	drain_workqueue(wq);
 
+	/* kill rescuer, if sanity checks fail, leave it w/o rescuer */
+	if (wq->rescuer) {
+		struct worker *rescuer = wq->rescuer;
+
+		/* this prevents new queueing */
+		spin_lock_irq(&wq_mayday_lock);
+		wq->rescuer = NULL;
+		spin_unlock_irq(&wq_mayday_lock);
+
+		/* rescuer will empty maydays list before exiting */
+		kthread_stop(rescuer->task);
+		kfree(rescuer);
+	}
+
 	/* sanity checks */
 	mutex_lock(&wq->mutex);
 	for_each_pwq(pwq, wq) {
@@ -4082,11 +4108,6 @@ void destroy_workqueue(struct workqueue_struct *wq)
 	list_del_rcu(&wq->list);
 	mutex_unlock(&wq_pool_mutex);
 
-	workqueue_sysfs_unregister(wq);
-
-	if (wq->rescuer)
-		kthread_stop(wq->rescuer->task);
-
 	if (!(wq->flags & WQ_UNBOUND)) {
 		/*
 		 * The base ref is never dropped on per-cpu pwqs.  Directly
@@ -4363,7 +4384,8 @@ static void show_pwq(struct pool_workqueue *pwq)
 	pr_info("  pwq %d:", pool->id);
 	pr_cont_pool_info(pool);
 
-	pr_cont(" active=%d/%d%s\n", pwq->nr_active, pwq->max_active,
+	pr_cont(" active=%d/%d refcnt=%d%s\n",
+		pwq->nr_active, pwq->max_active, pwq->refcnt,
 		!list_empty(&pwq->mayday_node) ? " MAYDAY" : "");
 
 	hash_for_each(pool->busy_hash, bkt, worker, hentry) {