Merge branch 'sched/urgent' into sched/core

Pick up fixes before queueing up new changes.

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/events/core.c

@@ -7856,14 +7856,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 static void __perf_event_exit_context(void *__info)
 {
 	struct perf_event_context *ctx = __info;
-	struct perf_event *event, *tmp;
+	struct perf_event *event;
 
 	perf_pmu_rotate_stop(ctx->pmu);
 
-	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
-		__perf_remove_from_context(event);
-	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
 		__perf_remove_from_context(event);
+	rcu_read_unlock();
 }
 
 static void perf_event_exit_cpu_context(int cpu)
@@ -7887,11 +7887,11 @@ static void perf_event_exit_cpu(int cpu)
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
+	perf_event_exit_cpu_context(cpu);
+
 	mutex_lock(&swhash->hlist_mutex);
 	swevent_hlist_release(swhash);
 	mutex_unlock(&swhash->hlist_mutex);
-
-	perf_event_exit_cpu_context(cpu);
 }
 #else
 static inline void perf_event_exit_cpu(int cpu) { }

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/clock.c

@@ -301,14 +301,14 @@ u64 sched_clock_cpu(int cpu)
 	if (unlikely(!sched_clock_running))
 		return 0ull;
 
-	preempt_disable();
+	preempt_disable_notrace();
 	scd = cpu_sdc(cpu);
 
 	if (cpu != smp_processor_id())
 		clock = sched_clock_remote(scd);
 	else
 		clock = sched_clock_local(scd);
-	preempt_enable();
+	preempt_enable_notrace();
 
 	return clock;
 }

kernel/sched/core.c

@@ -1954,7 +1954,7 @@ static int dl_overflow(struct task_struct *p, int policy,
 {
 
 	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-	u64 period = attr->sched_period;
+	u64 period = attr->sched_period ?: attr->sched_deadline;
 	u64 runtime = attr->sched_runtime;
 	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
 	int cpus, err = -1;
@@ -3328,6 +3328,15 @@ recheck:
 				return -EPERM;
 		}
 
+		 /*
+		  * Can't set/change SCHED_DEADLINE policy at all for now
+		  * (safest behavior); in the future we would like to allow
+		  * unprivileged DL tasks to increase their relative deadline
+		  * or reduce their runtime (both ways reducing utilization)
+		  */
+		if (dl_policy(policy))
+			return -EPERM;
+
 		/*
 		 * Treat SCHED_IDLE as nice 20. Only allow a switch to
 		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
@@ -3673,13 +3682,14 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
  */
-SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
+SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
+			       unsigned int, flags)
 {
 	struct sched_attr attr;
 	struct task_struct *p;
 	int retval;
 
-	if (!uattr || pid < 0)
+	if (!uattr || pid < 0 || flags)
 		return -EINVAL;
 
 	if (sched_copy_attr(uattr, &attr))
@@ -3798,7 +3808,7 @@ static int sched_read_attr(struct sched_attr __user *uattr,
 		attr->size = usize;
 	}
 
-	ret = copy_to_user(uattr, attr, usize);
+	ret = copy_to_user(uattr, attr, attr->size);
 	if (ret)
 		return -EFAULT;
 
@@ -3816,8 +3826,8 @@ err_size:
  * @uattr: structure containing the extended parameters.
  * @size: sizeof(attr) for fwd/bwd comp.
  */
-SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
-		unsigned int, size)
+SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+		unsigned int, size, unsigned int, flags)
 {
 	struct sched_attr attr = {
 		.size = sizeof(struct sched_attr),
@@ -3826,7 +3836,7 @@ SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	int retval;
 
 	if (!uattr || pid < 0 || size > PAGE_SIZE ||
-	    size < SCHED_ATTR_SIZE_VER0)
+	    size < SCHED_ATTR_SIZE_VER0 || flags)
 		return -EINVAL;
 
 	rcu_read_lock();
@@ -7461,6 +7471,7 @@ static int sched_dl_global_constraints(void)
 	u64 period = global_rt_period();
 	u64 new_bw = to_ratio(period, runtime);
 	int cpu, ret = 0;
+	unsigned long flags;
 
 	/*
 	 * Here we want to check the bandwidth not being set to some
@@ -7474,10 +7485,10 @@ static int sched_dl_global_constraints(void)
 	for_each_possible_cpu(cpu) {
 		struct dl_bw *dl_b = dl_bw_of(cpu);
 
-		raw_spin_lock(&dl_b->lock);
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
 		if (new_bw < dl_b->total_bw)
 			ret = -EBUSY;
-		raw_spin_unlock(&dl_b->lock);
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
 		if (ret)
 			break;
@@ -7490,6 +7501,7 @@ static void sched_dl_do_global(void)
 {
 	u64 new_bw = -1;
 	int cpu;
+	unsigned long flags;
 
 	def_dl_bandwidth.dl_period = global_rt_period();
 	def_dl_bandwidth.dl_runtime = global_rt_runtime();
@@ -7503,9 +7515,9 @@ static void sched_dl_do_global(void)
 	for_each_possible_cpu(cpu) {
 		struct dl_bw *dl_b = dl_bw_of(cpu);
 
-		raw_spin_lock(&dl_b->lock);
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
 		dl_b->bw = new_bw;
-		raw_spin_unlock(&dl_b->lock);
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 	}
 }
 
@@ -7514,7 +7526,8 @@ static int sched_rt_global_validate(void)
 	if (sysctl_sched_rt_period <= 0)
 		return -EINVAL;
 
-	if (sysctl_sched_rt_runtime > sysctl_sched_rt_period)
+	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
+		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
 		return -EINVAL;
 
 	return 0;

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(idx > num_present_cpus() || 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(best_cpu > num_present_cpus() && best_cpu != -1);
+	WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
 
 	return best_cpu;
 }
@@ -137,7 +137,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
 	int old_idx, new_cpu;
 	unsigned long flags;
 
-	WARN_ON(cpu > num_present_cpus());
+	WARN_ON(!cpu_present(cpu));
 
 	raw_spin_lock_irqsave(&cp->lock, flags);
 	old_idx = cp->cpu_to_idx[cpu];

kernel/sched/deadline.c

@@ -121,7 +121,7 @@ static inline void dl_clear_overload(struct rq *rq)
 
 static void update_dl_migration(struct dl_rq *dl_rq)
 {
-	if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) {
+	if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) {
 		if (!dl_rq->overloaded) {
 			dl_set_overload(rq_of_dl_rq(dl_rq));
 			dl_rq->overloaded = 1;
@@ -135,9 +135,7 @@ 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;
 
-	dl_rq->dl_nr_total++;
 	if (p->nr_cpus_allowed > 1)
 		dl_rq->dl_nr_migratory++;
 
@@ -147,9 +145,7 @@ 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;
 
-	dl_rq->dl_nr_total--;
 	if (p->nr_cpus_allowed > 1)
 		dl_rq->dl_nr_migratory--;
 
@@ -589,6 +585,8 @@ 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).
@@ -652,11 +650,13 @@ 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);
 	}
 }
@@ -740,6 +740,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 
 	WARN_ON(!dl_prio(prio));
 	dl_rq->dl_nr_running++;
+	inc_nr_running(rq_of_dl_rq(dl_rq));
 
 	inc_dl_deadline(dl_rq, deadline);
 	inc_dl_migration(dl_se, dl_rq);
@@ -753,6 +754,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 	WARN_ON(!dl_prio(prio));
 	WARN_ON(!dl_rq->dl_nr_running);
 	dl_rq->dl_nr_running--;
+	dec_nr_running(rq_of_dl_rq(dl_rq));
 
 	dec_dl_deadline(dl_rq, dl_se->deadline);
 	dec_dl_migration(dl_se, dl_rq);
@@ -859,8 +861,6 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
-
-	inc_nr_running(rq);
 }
 
 static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -873,8 +873,6 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_curr_dl(rq);
 	__dequeue_task_dl(rq, p, flags);
-
-	dec_nr_running(rq);
 }
 
 /*

kernel/sched/fair.c

@@ -1914,6 +1914,8 @@ void task_numa_work(struct callback_head *work)
 			start = end;
 			if (pages <= 0)
 				goto out;
+
+			cond_resched();
 		} while (end != vma->vm_end);
 	}
 
@@ -7316,15 +7318,15 @@ 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

@@ -568,6 +568,14 @@ 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/sched/sched.h

@@ -444,7 +444,6 @@ struct dl_rq {
 	} earliest_dl;
 
 	unsigned long dl_nr_migratory;
-	unsigned long dl_nr_total;
 	int overloaded;
 
 	/*

kernel/stop_machine.c

@@ -293,7 +293,7 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 	 */
 	smp_call_function_single(min(cpu1, cpu2),
 				 &irq_cpu_stop_queue_work,
-				 &call_args, 0);
+				 &call_args, 1);
 	lg_local_unlock(&stop_cpus_lock);
 	preempt_enable();
 

kernel/time/sched_clock.c

@@ -116,20 +116,42 @@ static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt)
 void __init sched_clock_register(u64 (*read)(void), int bits,
 				 unsigned long rate)
 {
+	u64 res, wrap, new_mask, new_epoch, cyc, ns;
+	u32 new_mult, new_shift;
+	ktime_t new_wrap_kt;
 	unsigned long r;
-	u64 res, wrap;
 	char r_unit;
 
 	if (cd.rate > rate)
 		return;
 
 	WARN_ON(!irqs_disabled());
-	read_sched_clock = read;
-	sched_clock_mask = CLOCKSOURCE_MASK(bits);
-	cd.rate = rate;
 
 	/* calculate the mult/shift to convert counter ticks to ns. */
-	clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 3600);
+	clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
+
+	new_mask = CLOCKSOURCE_MASK(bits);
+
+	/* calculate how many ns until we wrap */
+	wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask);
+	new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
+
+	/* update epoch for new counter and update epoch_ns from old counter*/
+	new_epoch = read();
+	cyc = read_sched_clock();
+	ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
+			  cd.mult, cd.shift);
+
+	raw_write_seqcount_begin(&cd.seq);
+	read_sched_clock = read;
+	sched_clock_mask = new_mask;
+	cd.rate = rate;
+	cd.wrap_kt = new_wrap_kt;
+	cd.mult = new_mult;
+	cd.shift = new_shift;
+	cd.epoch_cyc = new_epoch;
+	cd.epoch_ns = ns;
+	raw_write_seqcount_end(&cd.seq);
 
 	r = rate;
 	if (r >= 4000000) {
@@ -141,22 +163,12 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
 	} else
 		r_unit = ' ';
 
-	/* calculate how many ns until we wrap */
-	wrap = clocks_calc_max_nsecs(cd.mult, cd.shift, 0, sched_clock_mask);
-	cd.wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
-
 	/* calculate the ns resolution of this counter */
-	res = cyc_to_ns(1ULL, cd.mult, cd.shift);
+	res = cyc_to_ns(1ULL, new_mult, new_shift);
+
 	pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
 		bits, r, r_unit, res, wrap);
 
-	update_sched_clock();
-
-	/*
-	 * Ensure that sched_clock() starts off at 0ns
-	 */
-	cd.epoch_ns = 0;
-
 	/* Enable IRQ time accounting if we have a fast enough sched_clock */
 	if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
 		enable_sched_clock_irqtime();

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);