Merge branch 'perf/urgent' into perf/core, to pick up fixes before applying new changes

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

8 files changed, 150 insertions, 116 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 55b0f7c..f87b434 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1243,11 +1243,7 @@ static inline void perf_event__state_init(struct perf_event *event)
 					      PERF_EVENT_STATE_INACTIVE;
 }
 
-/*
- * Called at perf_event creation and when events are attached/detached from a
- * group.
- */
-static void perf_event__read_size(struct perf_event *event)
+static void __perf_event_read_size(struct perf_event *event, int nr_siblings)
 {
 	int entry = sizeof(u64); /* value */
 	int size = 0;
@@ -1263,7 +1259,7 @@ static void perf_event__read_size(struct perf_event *event)
 		entry += sizeof(u64);
 
 	if (event->attr.read_format & PERF_FORMAT_GROUP) {
-		nr += event->group_leader->nr_siblings;
+		nr += nr_siblings;
 		size += sizeof(u64);
 	}
 
@@ -1271,14 +1267,11 @@ static void perf_event__read_size(struct perf_event *event)
 	event->read_size = size;
 }
 
-static void perf_event__header_size(struct perf_event *event)
+static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 {
 	struct perf_sample_data *data;
-	u64 sample_type = event->attr.sample_type;
 	u16 size = 0;
 
-	perf_event__read_size(event);
-
 	if (sample_type & PERF_SAMPLE_IP)
 		size += sizeof(data->ip);
 
@@ -1303,6 +1296,17 @@ static void perf_event__header_size(struct perf_event *event)
 	event->header_size = size;
 }
 
+/*
+ * Called at perf_event creation and when events are attached/detached from a
+ * group.
+ */
+static void perf_event__header_size(struct perf_event *event)
+{
+	__perf_event_read_size(event,
+			       event->group_leader->nr_siblings);
+	__perf_event_header_size(event, event->attr.sample_type);
+}
+
 static void perf_event__id_header_size(struct perf_event *event)
 {
 	struct perf_sample_data *data;
@@ -1330,6 +1334,27 @@ static void perf_event__id_header_size(struct perf_event *event)
 	event->id_header_size = size;
 }
 
+static bool perf_event_validate_size(struct perf_event *event)
+{
+	/*
+	 * The values computed here will be over-written when we actually
+	 * attach the event.
+	 */
+	__perf_event_read_size(event, event->group_leader->nr_siblings + 1);
+	__perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ);
+	perf_event__id_header_size(event);
+
+	/*
+	 * Sum the lot; should not exceed the 64k limit we have on records.
+	 * Conservative limit to allow for callchains and other variable fields.
+	 */
+	if (event->read_size + event->header_size +
+	    event->id_header_size + sizeof(struct perf_event_header) >= 16*1024)
+		return false;
+
+	return true;
+}
+
 static void perf_group_attach(struct perf_event *event)
 {
 	struct perf_event *group_leader = event->group_leader, *pos;
@@ -8411,13 +8436,35 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	if (move_group) {
 		gctx = group_leader->ctx;
+		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+	} else {
+		mutex_lock(&ctx->mutex);
+	}
 
+	if (!perf_event_validate_size(event)) {
+		err = -E2BIG;
+		goto err_locked;
+	}
+
+	/*
+	 * Must be under the same ctx::mutex as perf_install_in_context(),
+	 * because we need to serialize with concurrent event creation.
+	 */
+	if (!exclusive_event_installable(event, ctx)) {
+		/* exclusive and group stuff are assumed mutually exclusive */
+		WARN_ON_ONCE(move_group);
+
+		err = -EBUSY;
+		goto err_locked;
+	}
+
+	WARN_ON_ONCE(ctx->parent_ctx);
+
+	if (move_group) {
 		/*
 		 * See perf_event_ctx_lock() for comments on the details
 		 * of swizzling perf_event::ctx.
 		 */
-		mutex_lock_double(&gctx->mutex, &ctx->mutex);
-
 		perf_remove_from_context(group_leader, false);
 
 		list_for_each_entry(sibling, &group_leader->sibling_list,
@@ -8425,13 +8472,7 @@ SYSCALL_DEFINE5(perf_event_open,
 			perf_remove_from_context(sibling, false);
 			put_ctx(gctx);
 		}
-	} else {
-		mutex_lock(&ctx->mutex);
-	}
 
-	WARN_ON_ONCE(ctx->parent_ctx);
-
-	if (move_group) {
 		/*
 		 * Wait for everybody to stop referencing the events through
 		 * the old lists, before installing it on new lists.
@@ -8463,22 +8504,29 @@ SYSCALL_DEFINE5(perf_event_open,
 		perf_event__state_init(group_leader);
 		perf_install_in_context(ctx, group_leader, group_leader->cpu);
 		get_ctx(ctx);
-	}
 
-	if (!exclusive_event_installable(event, ctx)) {
-		err = -EBUSY;
-		mutex_unlock(&ctx->mutex);
-		fput(event_file);
-		goto err_context;
+		/*
+		 * Now that all events are installed in @ctx, nothing
+		 * references @gctx anymore, so drop the last reference we have
+		 * on it.
+		 */
+		put_ctx(gctx);
 	}
 
+	/*
+	 * Precalculate sample_data sizes; do while holding ctx::mutex such
+	 * that we're serialized against further additions and before
+	 * perf_install_in_context() which is the point the event is active and
+	 * can use these values.
+	 */
+	perf_event__header_size(event);
+	perf_event__id_header_size(event);
+
 	perf_install_in_context(ctx, event, event->cpu);
 	perf_unpin_context(ctx);
 
-	if (move_group) {
+	if (move_group)
 		mutex_unlock(&gctx->mutex);
-		put_ctx(gctx);
-	}
 	mutex_unlock(&ctx->mutex);
 
 	put_online_cpus();
@@ -8490,12 +8538,6 @@ SYSCALL_DEFINE5(perf_event_open,
 	mutex_unlock(&current->perf_event_mutex);
 
 	/*
-	 * Precalculate sample_data sizes
-	 */
-	perf_event__header_size(event);
-	perf_event__id_header_size(event);
-
-	/*
 	 * Drop the reference on the group_event after placing the
 	 * new event on the sibling_list. This ensures destruction
 	 * of the group leader will find the pointer to itself in
@@ -8505,6 +8547,12 @@ SYSCALL_DEFINE5(perf_event_open,
 	fd_install(event_fd, event_file);
 	return event_fd;
 
+err_locked:
+	if (move_group)
+		mutex_unlock(&gctx->mutex);
+	mutex_unlock(&ctx->mutex);
+/* err_file: */
+	fput(event_file);
 err_context:
 	perf_unpin_context(ctx);
 	put_ctx(ctx);
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 337c881..87e9ce6a 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -289,7 +289,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	if (pv_enabled())
 		goto queue;
 
-	if (virt_queued_spin_lock(lock))
+	if (virt_spin_lock(lock))
 		return;
 
 	/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3595403..97d276f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -621,18 +621,21 @@ int get_nohz_timer_target(void)
 	int i, cpu = smp_processor_id();
 	struct sched_domain *sd;
 
-	if (!idle_cpu(cpu))
+	if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu))
 		return cpu;
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
 		for_each_cpu(i, sched_domain_span(sd)) {
-			if (!idle_cpu(i)) {
+			if (!idle_cpu(i) && is_housekeeping_cpu(cpu)) {
 				cpu = i;
 				goto unlock;
 			}
 		}
 	}
+
+	if (!is_housekeeping_cpu(cpu))
+		cpu = housekeeping_any_cpu();
 unlock:
 	rcu_read_unlock();
 	return cpu;
@@ -5178,24 +5181,47 @@ static void migrate_tasks(struct rq *dead_rq)
 			break;
 
 		/*
-		 * Ensure rq->lock covers the entire task selection
-		 * until the migration.
+		 * pick_next_task assumes pinned rq->lock.
 		 */
 		lockdep_pin_lock(&rq->lock);
 		next = pick_next_task(rq, &fake_task);
 		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
 
+		/*
+		 * Rules for changing task_struct::cpus_allowed are holding
+		 * both pi_lock and rq->lock, such that holding either
+		 * stabilizes the mask.
+		 *
+		 * Drop rq->lock is not quite as disastrous as it usually is
+		 * because !cpu_active at this point, which means load-balance
+		 * will not interfere. Also, stop-machine.
+		 */
+		lockdep_unpin_lock(&rq->lock);
+		raw_spin_unlock(&rq->lock);
+		raw_spin_lock(&next->pi_lock);
+		raw_spin_lock(&rq->lock);
+
+		/*
+		 * Since we're inside stop-machine, _nothing_ should have
+		 * changed the task, WARN if weird stuff happened, because in
+		 * that case the above rq->lock drop is a fail too.
+		 */
+		if (WARN_ON(task_rq(next) != rq || !task_on_rq_queued(next))) {
+			raw_spin_unlock(&next->pi_lock);
+			continue;
+		}
+
 		/* Find suitable destination for @next, with force if needed. */
 		dest_cpu = select_fallback_rq(dead_rq->cpu, next);
 
-		lockdep_unpin_lock(&rq->lock);
 		rq = __migrate_task(rq, next, dest_cpu);
 		if (rq != dead_rq) {
 			raw_spin_unlock(&rq->lock);
 			rq = dead_rq;
 			raw_spin_lock(&rq->lock);
 		}
+		raw_spin_unlock(&next->pi_lock);
 	}
 
 	rq->stop = stop;
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 50eb107..a9b76a4 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -97,20 +97,6 @@ EXPORT_SYMBOL_GPL(clockevent_delta2ns);
 static int __clockevents_switch_state(struct clock_event_device *dev,
 				      enum clock_event_state state)
 {
-	/* Transition with legacy set_mode() callback */
-	if (dev->set_mode) {
-		/* Legacy callback doesn't support new modes */
-		if (state > CLOCK_EVT_STATE_ONESHOT)
-			return -ENOSYS;
-		/*
-		 * 'clock_event_state' and 'clock_event_mode' have 1-to-1
-		 * mapping until *_ONESHOT, and so a simple cast will work.
-		 */
-		dev->set_mode((enum clock_event_mode)state, dev);
-		dev->mode = (enum clock_event_mode)state;
-		return 0;
-	}
-
 	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
 		return 0;
 
@@ -204,12 +190,8 @@ int clockevents_tick_resume(struct clock_event_device *dev)
 {
 	int ret = 0;
 
-	if (dev->set_mode) {
-		dev->set_mode(CLOCK_EVT_MODE_RESUME, dev);
-		dev->mode = CLOCK_EVT_MODE_RESUME;
-	} else if (dev->tick_resume) {
+	if (dev->tick_resume)
 		ret = dev->tick_resume(dev);
-	}
 
 	return ret;
 }
@@ -460,26 +442,6 @@ int clockevents_unbind_device(struct clock_event_device *ced, int cpu)
 }
 EXPORT_SYMBOL_GPL(clockevents_unbind_device);
 
-/* Sanity check of state transition callbacks */
-static int clockevents_sanity_check(struct clock_event_device *dev)
-{
-	/* Legacy set_mode() callback */
-	if (dev->set_mode) {
-		/* We shouldn't be supporting new modes now */
-		WARN_ON(dev->set_state_periodic || dev->set_state_oneshot ||
-			dev->set_state_shutdown || dev->tick_resume ||
-			dev->set_state_oneshot_stopped);
-
-		BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
-		return 0;
-	}
-
-	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
-		return 0;
-
-	return 0;
-}
-
 /**
  * clockevents_register_device - register a clock event device
  * @dev:	device to register
@@ -488,8 +450,6 @@ void clockevents_register_device(struct clock_event_device *dev)
 {
 	unsigned long flags;
 
-	BUG_ON(clockevents_sanity_check(dev));
-
 	/* Initialize state to DETACHED */
 	clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index d11c55b..4fcd99e 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -398,7 +398,6 @@ void tick_shutdown(unsigned int cpu)
 		 * the set mode function!
 		 */
 		clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
-		dev->mode = CLOCK_EVT_MODE_UNUSED;
 		clockevents_exchange_device(dev, NULL);
 		dev->event_handler = clockevents_handle_noop;
 		td->evtdev = NULL;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3319e16..7c7ec45 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -290,16 +290,17 @@ static int __init tick_nohz_full_setup(char *str)
 __setup("nohz_full=", tick_nohz_full_setup);
 
 static int tick_nohz_cpu_down_callback(struct notifier_block *nfb,
-						 unsigned long action,
-						 void *hcpu)
+				       unsigned long action,
+				       void *hcpu)
 {
 	unsigned int cpu = (unsigned long)hcpu;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_DOWN_PREPARE:
 		/*
-		 * If we handle the timekeeping duty for full dynticks CPUs,
-		 * we can't safely shutdown that CPU.
+		 * The boot CPU handles housekeeping duty (unbound timers,
+		 * workqueues, timekeeping, ...) on behalf of full dynticks
+		 * CPUs. It must remain online when nohz full is enabled.
 		 */
 		if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
 			return NOTIFY_BAD;
@@ -370,6 +371,12 @@ void __init tick_nohz_init(void)
 	cpu_notifier(tick_nohz_cpu_down_callback, 0);
 	pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n",
 		cpumask_pr_args(tick_nohz_full_mask));
+
+	/*
+	 * We need at least one CPU to handle housekeeping work such
+	 * as timekeeping, unbound timers, workqueues, ...
+	 */
+	WARN_ON_ONCE(cpumask_empty(housekeeping_mask));
 }
 #endif
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index f6ee2e6..3739ac6 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1614,7 +1614,7 @@ static __always_inline void timekeeping_freqadjust(struct timekeeper *tk,
 	negative = (tick_error < 0);
 
 	/* Sort out the magnitude of the correction */
-	tick_error = abs(tick_error);
+	tick_error = abs64(tick_error);
 	for (adj = 0; tick_error > interval; adj++)
 		tick_error >>= 1;
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 129c960..f75e35b 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -225,7 +225,7 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 		   (unsigned long long) dev->min_delta_ns);
 	SEQ_printf(m, " mult:           %u\n", dev->mult);
 	SEQ_printf(m, " shift:          %u\n", dev->shift);
-	SEQ_printf(m, " mode:           %d\n", dev->mode);
+	SEQ_printf(m, " mode:           %d\n", clockevent_get_state(dev));
 	SEQ_printf(m, " next_event:     %Ld nsecs\n",
 		   (unsigned long long) ktime_to_ns(dev->next_event));
 
@@ -233,40 +233,34 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 	print_name_offset(m, dev->set_next_event);
 	SEQ_printf(m, "\n");
 
-	if (dev->set_mode) {
-		SEQ_printf(m, " set_mode:       ");
-		print_name_offset(m, dev->set_mode);
+	if (dev->set_state_shutdown) {
+		SEQ_printf(m, " shutdown: ");
+		print_name_offset(m, dev->set_state_shutdown);
 		SEQ_printf(m, "\n");
-	} else {
-		if (dev->set_state_shutdown) {
-			SEQ_printf(m, " shutdown: ");
-			print_name_offset(m, dev->set_state_shutdown);
-			SEQ_printf(m, "\n");
-		}
+	}
 
-		if (dev->set_state_periodic) {
-			SEQ_printf(m, " periodic: ");
-			print_name_offset(m, dev->set_state_periodic);
-			SEQ_printf(m, "\n");
-		}
+	if (dev->set_state_periodic) {
+		SEQ_printf(m, " periodic: ");
+		print_name_offset(m, dev->set_state_periodic);
+		SEQ_printf(m, "\n");
+	}
 
-		if (dev->set_state_oneshot) {
-			SEQ_printf(m, " oneshot:  ");
-			print_name_offset(m, dev->set_state_oneshot);
-			SEQ_printf(m, "\n");
-		}
+	if (dev->set_state_oneshot) {
+		SEQ_printf(m, " oneshot:  ");
+		print_name_offset(m, dev->set_state_oneshot);
+		SEQ_printf(m, "\n");
+	}
 
-		if (dev->set_state_oneshot_stopped) {
-			SEQ_printf(m, " oneshot stopped: ");
-			print_name_offset(m, dev->set_state_oneshot_stopped);
-			SEQ_printf(m, "\n");
-		}
+	if (dev->set_state_oneshot_stopped) {
+		SEQ_printf(m, " oneshot stopped: ");
+		print_name_offset(m, dev->set_state_oneshot_stopped);
+		SEQ_printf(m, "\n");
+	}
 
-		if (dev->tick_resume) {
-			SEQ_printf(m, " resume:   ");
-			print_name_offset(m, dev->tick_resume);
-			SEQ_printf(m, "\n");
-		}
+	if (dev->tick_resume) {
+		SEQ_printf(m, " resume:   ");
+		print_name_offset(m, dev->tick_resume);
+		SEQ_printf(m, "\n");
 	}
 
 	SEQ_printf(m, " event_handler:  ");