Merge branch 'perf/urgent' into perf/core

Merge the latest fixes.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/audit_tree.c

@@ -916,7 +916,7 @@ static int audit_tree_handle_event(struct fsnotify_group *group,
 				   struct fsnotify_mark *inode_mark,
 				   struct fsnotify_mark *vfsmount_mark,
 				   u32 mask, void *data, int data_type,
-				   const unsigned char *file_name)
+				   const unsigned char *file_name, u32 cookie)
 {
 	return 0;
 }

kernel/audit_watch.c

@@ -471,7 +471,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
 				    struct fsnotify_mark *inode_mark,
 				    struct fsnotify_mark *vfsmount_mark,
 				    u32 mask, void *data, int data_type,
-				    const unsigned char *dname)
+				    const unsigned char *dname, u32 cookie)
 {
 	struct inode *inode;
 	struct audit_parent *parent;

kernel/cpuset.c

@@ -974,12 +974,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
  *    Temporarilly set tasks mems_allowed to target nodes of migration,
  *    so that the migration code can allocate pages on these nodes.
  *
- *    Call holding cpuset_mutex, so current's cpuset won't change
- *    during this call, as manage_mutex holds off any cpuset_attach()
- *    calls.  Therefore we don't need to take task_lock around the
- *    call to guarantee_online_mems(), as we know no one is changing
- *    our task's cpuset.
- *
  *    While the mm_struct we are migrating is typically from some
  *    other task, the task_struct mems_allowed that we are hacking
  *    is for our current task, which must allocate new pages for that
@@ -996,8 +990,10 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 
 	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
 
+	rcu_read_lock();
 	mems_cs = effective_nodemask_cpuset(task_cs(tsk));
 	guarantee_online_mems(mems_cs, &tsk->mems_allowed);
+	rcu_read_unlock();
 }
 
 /*
@@ -2486,9 +2482,9 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
 
 	task_lock(current);
 	cs = nearest_hardwall_ancestor(task_cs(current));
+	allowed = node_isset(node, cs->mems_allowed);
 	task_unlock(current);
 
-	allowed = node_isset(node, cs->mems_allowed);
 	mutex_unlock(&callback_mutex);
 	return allowed;
 }

kernel/irq/irqdomain.c

@@ -10,6 +10,7 @@
 #include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/of_irq.h>
 #include <linux/topology.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>

kernel/irq/manage.c

@@ -802,8 +802,7 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc,
 
 static void wake_threads_waitq(struct irq_desc *desc)
 {
-	if (atomic_dec_and_test(&desc->threads_active) &&
-	    waitqueue_active(&desc->wait_for_threads))
+	if (atomic_dec_and_test(&desc->threads_active))
 		wake_up(&desc->wait_for_threads);
 }
 

kernel/profile.c

@@ -549,14 +549,14 @@ static int create_hash_tables(void)
 		struct page *page;
 
 		page = alloc_pages_exact_node(node,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				0);
 		if (!page)
 			goto out_cleanup;
 		per_cpu(cpu_profile_hits, cpu)[1]
 				= (struct profile_hit *)page_address(page);
 		page = alloc_pages_exact_node(node,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				0);
 		if (!page)
 			goto out_cleanup;

kernel/sched/cpudeadline.c

@@ -70,7 +70,7 @@ static void cpudl_heapify(struct cpudl *cp, int idx)
 
 static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
 {
-	WARN_ON(!cpu_present(idx) || idx == IDX_INVALID);
+	WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
 
 	if (dl_time_before(new_dl, cp->elements[idx].dl)) {
 		cp->elements[idx].dl = new_dl;
@@ -117,7 +117,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	}
 
 out:
-	WARN_ON(!cpu_present(best_cpu) && best_cpu != -1);
+	WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
 
 	return best_cpu;
 }

kernel/sched/deadline.c

@@ -135,7 +135,6 @@ static void update_dl_migration(struct dl_rq *dl_rq)
 static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	struct task_struct *p = dl_task_of(dl_se);
-	dl_rq = &rq_of_dl_rq(dl_rq)->dl;
 
 	if (p->nr_cpus_allowed > 1)
 		dl_rq->dl_nr_migratory++;
@@ -146,7 +145,6 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	struct task_struct *p = dl_task_of(dl_se);
-	dl_rq = &rq_of_dl_rq(dl_rq)->dl;
 
 	if (p->nr_cpus_allowed > 1)
 		dl_rq->dl_nr_migratory--;
@@ -564,6 +562,8 @@ int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
 	return 1;
 }
 
+extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
+
 /*
  * Update the current task's runtime statistics (provided it is still
  * a -deadline task and has not been removed from the dl_rq).
@@ -627,11 +627,13 @@ static void update_curr_dl(struct rq *rq)
 		struct rt_rq *rt_rq = &rq->rt;
 
 		raw_spin_lock(&rt_rq->rt_runtime_lock);
-		rt_rq->rt_time += delta_exec;
 		/*
 		 * We'll let actual RT tasks worry about the overflow here, we
-		 * have our own CBS to keep us inline -- see above.
+		 * have our own CBS to keep us inline; only account when RT
+		 * bandwidth is relevant.
 		 */
+		if (sched_rt_bandwidth_account(rt_rq))
+			rt_rq->rt_time += delta_exec;
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 	}
 }

kernel/sched/fair.c

@@ -7001,15 +7001,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 	/*
-	 * Ensure the task's vruntime is normalized, so that when its
+	 * Ensure the task's vruntime is normalized, so that when it's
 	 * switched back to the fair class the enqueue_entity(.flags=0) will
 	 * do the right thing.
 	 *
-	 * If it was on_rq, then the dequeue_entity(.flags=0) will already
-	 * have normalized the vruntime, if it was !on_rq, then only when
+	 * If it's on_rq, then the dequeue_entity(.flags=0) will already
+	 * have normalized the vruntime, if it's !on_rq, then only when
 	 * the task is sleeping will it still have non-normalized vruntime.
 	 */
-	if (!se->on_rq && p->state != TASK_RUNNING) {
+	if (!p->on_rq && p->state != TASK_RUNNING) {
 		/*
 		 * Fix up our vruntime so that the current sleep doesn't
 		 * cause 'unlimited' sleep bonus.

kernel/sched/rt.c

@@ -538,6 +538,14 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
 
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
+{
+	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+	return (hrtimer_active(&rt_b->rt_period_timer) ||
+		rt_rq->rt_time < rt_b->rt_runtime);
+}
+
 #ifdef CONFIG_SMP
 /*
  * We ran out of runtime, see if we can borrow some from our neighbours.

kernel/trace/trace_events.c

@@ -1777,6 +1777,16 @@ static void trace_module_add_events(struct module *mod)
 {
 	struct ftrace_event_call **call, **start, **end;
 
+	if (!mod->num_trace_events)
+		return;
+
+	/* Don't add infrastructure for mods without tracepoints */
+	if (trace_module_has_bad_taint(mod)) {
+		pr_err("%s: module has bad taint, not creating trace events\n",
+		       mod->name);
+		return;
+	}
+
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
 

kernel/tracepoint.c

@@ -631,6 +631,11 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter)
 EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
 
 #ifdef CONFIG_MODULES
+bool trace_module_has_bad_taint(struct module *mod)
+{
+	return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP));
+}
+
 static int tracepoint_module_coming(struct module *mod)
 {
 	struct tp_module *tp_mod, *iter;
@@ -641,7 +646,7 @@ static int tracepoint_module_coming(struct module *mod)
 	 * module headers (for forced load), to make sure we don't cause a crash.
 	 * Staging and out-of-tree GPL modules are fine.
 	 */
-	if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)))
+	if (trace_module_has_bad_taint(mod))
 		return 0;
 	mutex_lock(&tracepoints_mutex);
 	tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);