19 files changed, 430 insertions, 206 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5946460b2425..614614821f00 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -64,8 +64,17 @@ static void remote_function(void *data)
 	struct task_struct *p = tfc->p;
 
 	if (p) {
-		tfc->ret = -EAGAIN;
-		if (task_cpu(p) != smp_processor_id() || !task_curr(p))
+		/* -EAGAIN */
+		if (task_cpu(p) != smp_processor_id())
+			return;
+
+		/*
+		 * Now that we're on right CPU with IRQs disabled, we can test
+		 * if we hit the right task without races.
+		 */
+
+		tfc->ret = -ESRCH; /* No such (running) process */
+		if (p != current)
 			return;
 	}
 
@@ -92,13 +101,17 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info)
 		.p	= p,
 		.func	= func,
 		.info	= info,
-		.ret	= -ESRCH, /* No such (running) process */
+		.ret	= -EAGAIN,
 	};
+	int ret;
 
-	if (task_curr(p))
-		smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+	do {
+		ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+		if (!ret)
+			ret = data.ret;
+	} while (ret == -EAGAIN);
 
-	return data.ret;
+	return ret;
 }
 
 /**
@@ -169,19 +182,6 @@ static bool is_kernel_event(struct perf_event *event)
  *    rely on ctx->is_active and therefore cannot use event_function_call().
  *    See perf_install_in_context().
  *
- * This is because we need a ctx->lock serialized variable (ctx->is_active)
- * to reliably determine if a particular task/context is scheduled in. The
- * task_curr() use in task_function_call() is racy in that a remote context
- * switch is not a single atomic operation.
- *
- * As is, the situation is 'safe' because we set rq->curr before we do the
- * actual context switch. This means that task_curr() will fail early, but
- * we'll continue spinning on ctx->is_active until we've passed
- * perf_event_task_sched_out().
- *
- * Without this ctx->lock serialized variable we could have race where we find
- * the task (and hence the context) would not be active while in fact they are.
- *
  * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set.
  */
 
@@ -212,7 +212,7 @@ static int event_function(void *info)
 	 */
 	if (ctx->task) {
 		if (ctx->task != current) {
-			ret = -EAGAIN;
+			ret = -ESRCH;
 			goto unlock;
 		}
 
@@ -276,10 +276,10 @@ static void event_function_call(struct perf_event *event, event_f func, void *da
 		return;
 	}
 
-again:
 	if (task == TASK_TOMBSTONE)
 		return;
 
+again:
 	if (!task_function_call(task, event_function, &efs))
 		return;
 
@@ -289,13 +289,15 @@ again:
 	 * a concurrent perf_event_context_sched_out().
 	 */
 	task = ctx->task;
-	if (task != TASK_TOMBSTONE) {
-		if (ctx->is_active) {
-			raw_spin_unlock_irq(&ctx->lock);
-			goto again;
-		}
-		func(event, NULL, ctx, data);
+	if (task == TASK_TOMBSTONE) {
+		raw_spin_unlock_irq(&ctx->lock);
+		return;
 	}
+	if (ctx->is_active) {
+		raw_spin_unlock_irq(&ctx->lock);
+		goto again;
+	}
+	func(event, NULL, ctx, data);
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
@@ -314,6 +316,7 @@ again:
 enum event_type_t {
 	EVENT_FLEXIBLE = 0x1,
 	EVENT_PINNED = 0x2,
+	EVENT_TIME = 0x4,
 	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
 };
 
@@ -321,7 +324,13 @@ enum event_type_t {
  * perf_sched_events : >0 events exist
  * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
  */
-struct static_key_deferred perf_sched_events __read_mostly;
+
+static void perf_sched_delayed(struct work_struct *work);
+DEFINE_STATIC_KEY_FALSE(perf_sched_events);
+static DECLARE_DELAYED_WORK(perf_sched_work, perf_sched_delayed);
+static DEFINE_MUTEX(perf_sched_mutex);
+static atomic_t perf_sched_count;
+
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
 static DEFINE_PER_CPU(int, perf_sched_cb_usages);
 
@@ -1288,16 +1297,18 @@ static u64 perf_event_time(struct perf_event *event)
 
 /*
  * Update the total_time_enabled and total_time_running fields for a event.
- * The caller of this function needs to hold the ctx->lock.
  */
 static void update_event_times(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
 	u64 run_end;
 
+	lockdep_assert_held(&ctx->lock);
+
 	if (event->state < PERF_EVENT_STATE_INACTIVE ||
 	    event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
 		return;
+
 	/*
 	 * in cgroup mode, time_enabled represents
 	 * the time the event was enabled AND active
@@ -1645,7 +1656,7 @@ out:
 
 static bool is_orphaned_event(struct perf_event *event)
 {
-	return event->state == PERF_EVENT_STATE_EXIT;
+	return event->state == PERF_EVENT_STATE_DEAD;
 }
 
 static inline int pmu_filter_match(struct perf_event *event)
@@ -1690,14 +1701,14 @@ event_sched_out(struct perf_event *event,
 
 	perf_pmu_disable(event->pmu);
 
+	event->tstamp_stopped = tstamp;
+	event->pmu->del(event, 0);
+	event->oncpu = -1;
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	if (event->pending_disable) {
 		event->pending_disable = 0;
 		event->state = PERF_EVENT_STATE_OFF;
 	}
-	event->tstamp_stopped = tstamp;
-	event->pmu->del(event, 0);
-	event->oncpu = -1;
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu--;
@@ -1732,7 +1743,6 @@ group_sched_out(struct perf_event *group_event,
 }
 
 #define DETACH_GROUP	0x01UL
-#define DETACH_STATE	0x02UL
 
 /*
  * Cross CPU call to remove a performance event
@@ -1752,8 +1762,6 @@ __perf_remove_from_context(struct perf_event *event,
 	if (flags & DETACH_GROUP)
 		perf_group_detach(event);
 	list_del_event(event, ctx);
-	if (flags & DETACH_STATE)
-		event->state = PERF_EVENT_STATE_EXIT;
 
 	if (!ctx->nr_events && ctx->is_active) {
 		ctx->is_active = 0;
@@ -2063,14 +2071,27 @@ static void add_event_to_ctx(struct perf_event *event,
 	event->tstamp_stopped = tstamp;
 }
 
-static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
-			       struct perf_event_context *ctx);
+static void ctx_sched_out(struct perf_event_context *ctx,
+			  struct perf_cpu_context *cpuctx,
+			  enum event_type_t event_type);
 static void
 ctx_sched_in(struct perf_event_context *ctx,
 	     struct perf_cpu_context *cpuctx,
 	     enum event_type_t event_type,
 	     struct task_struct *task);
 
+static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
+			       struct perf_event_context *ctx)
+{
+	if (!cpuctx->task_ctx)
+		return;
+
+	if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
+		return;
+
+	ctx_sched_out(ctx, cpuctx, EVENT_ALL);
+}
+
 static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
 				struct perf_event_context *ctx,
 				struct task_struct *task)
@@ -2097,49 +2118,68 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 /*
  * Cross CPU call to install and enable a performance event
  *
- * Must be called with ctx->mutex held
+ * Very similar to remote_function() + event_function() but cannot assume that
+ * things like ctx->is_active and cpuctx->task_ctx are set.
  */
 static int  __perf_install_in_context(void *info)
 {
-	struct perf_event_context *ctx = info;
+	struct perf_event *event = info;
+	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	struct perf_event_context *task_ctx = cpuctx->task_ctx;
+	bool activate = true;
+	int ret = 0;
 
 	raw_spin_lock(&cpuctx->ctx.lock);
 	if (ctx->task) {
 		raw_spin_lock(&ctx->lock);
-		/*
-		 * If we hit the 'wrong' task, we've since scheduled and
-		 * everything should be sorted, nothing to do!
-		 */
 		task_ctx = ctx;
-		if (ctx->task != current)
+
+		/* If we're on the wrong CPU, try again */
+		if (task_cpu(ctx->task) != smp_processor_id()) {
+			ret = -ESRCH;
 			goto unlock;
+		}
 
 		/*
-		 * If task_ctx is set, it had better be to us.
+		 * If we're on the right CPU, see if the task we target is
+		 * current, if not we don't have to activate the ctx, a future
+		 * context switch will do that for us.
 		 */
-		WARN_ON_ONCE(cpuctx->task_ctx != ctx && cpuctx->task_ctx);
+		if (ctx->task != current)
+			activate = false;
+		else
+			WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx);
+
 	} else if (task_ctx) {
 		raw_spin_lock(&task_ctx->lock);
 	}
 
-	ctx_resched(cpuctx, task_ctx);
+	if (activate) {
+		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
+		add_event_to_ctx(event, ctx);
+		ctx_resched(cpuctx, task_ctx);
+	} else {
+		add_event_to_ctx(event, ctx);
+	}
+
 unlock:
 	perf_ctx_unlock(cpuctx, task_ctx);
 
-	return 0;
+	return ret;
 }
 
 /*
- * Attach a performance event to a context
+ * Attach a performance event to a context.
+ *
+ * Very similar to event_function_call, see comment there.
  */
 static void
 perf_install_in_context(struct perf_event_context *ctx,
 			struct perf_event *event,
 			int cpu)
 {
-	struct task_struct *task = NULL;
+	struct task_struct *task = READ_ONCE(ctx->task);
 
 	lockdep_assert_held(&ctx->mutex);
 
@@ -2147,40 +2187,46 @@ perf_install_in_context(struct perf_event_context *ctx,
 	if (event->cpu != -1)
 		event->cpu = cpu;
 
+	if (!task) {
+		cpu_function_call(cpu, __perf_install_in_context, event);
+		return;
+	}
+
+	/*
+	 * Should not happen, we validate the ctx is still alive before calling.
+	 */
+	if (WARN_ON_ONCE(task == TASK_TOMBSTONE))
+		return;
+
 	/*
 	 * Installing events is tricky because we cannot rely on ctx->is_active
 	 * to be set in case this is the nr_events 0 -> 1 transition.
-	 *
-	 * So what we do is we add the event to the list here, which will allow
-	 * a future context switch to DTRT and then send a racy IPI. If the IPI
-	 * fails to hit the right task, this means a context switch must have
-	 * happened and that will have taken care of business.
 	 */
-	raw_spin_lock_irq(&ctx->lock);
-	task = ctx->task;
+again:
 	/*
-	 * Worse, we cannot even rely on the ctx actually existing anymore. If
-	 * between find_get_context() and perf_install_in_context() the task
-	 * went through perf_event_exit_task() its dead and we should not be
-	 * adding new events.
+	 * Cannot use task_function_call() because we need to run on the task's
+	 * CPU regardless of whether its current or not.
 	 */
-	if (task == TASK_TOMBSTONE) {
+	if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event))
+		return;
+
+	raw_spin_lock_irq(&ctx->lock);
+	task = ctx->task;
+	if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) {
+		/*
+		 * Cannot happen because we already checked above (which also
+		 * cannot happen), and we hold ctx->mutex, which serializes us
+		 * against perf_event_exit_task_context().
+		 */
 		raw_spin_unlock_irq(&ctx->lock);
 		return;
 	}
-	update_context_time(ctx);
+	raw_spin_unlock_irq(&ctx->lock);
 	/*
-	 * Update cgrp time only if current cgrp matches event->cgrp.
-	 * Must be done before calling add_event_to_ctx().
+	 * Since !ctx->is_active doesn't mean anything, we must IPI
+	 * unconditionally.
 	 */
-	update_cgrp_time_from_event(event);
-	add_event_to_ctx(event, ctx);
-	raw_spin_unlock_irq(&ctx->lock);
-
-	if (task)
-		task_function_call(task, __perf_install_in_context, ctx);
-	else
-		cpu_function_call(cpu, __perf_install_in_context, ctx);
+	goto again;
 }
 
 /*
@@ -2219,17 +2265,18 @@ static void __perf_event_enable(struct perf_event *event,
 	    event->state <= PERF_EVENT_STATE_ERROR)
 		return;
 
-	update_context_time(ctx);
+	if (ctx->is_active)
+		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
+
 	__perf_event_mark_enabled(event);
 
 	if (!ctx->is_active)
 		return;
 
 	if (!event_filter_match(event)) {
-		if (is_cgroup_event(event)) {
-			perf_cgroup_set_timestamp(current, ctx); // XXX ?
+		if (is_cgroup_event(event))
 			perf_cgroup_defer_enabled(event);
-		}
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
 		return;
 	}
 
@@ -2237,8 +2284,10 @@ static void __perf_event_enable(struct perf_event *event,
 	 * If the event is in a group and isn't the group leader,
 	 * then don't put it on unless the group is on.
 	 */
-	if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE)
+	if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) {
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
 		return;
+	}
 
 	task_ctx = cpuctx->task_ctx;
 	if (ctx->task)
@@ -2344,24 +2393,33 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	}
 
 	ctx->is_active &= ~event_type;
+	if (!(ctx->is_active & EVENT_ALL))
+		ctx->is_active = 0;
+
 	if (ctx->task) {
 		WARN_ON_ONCE(cpuctx->task_ctx != ctx);
 		if (!ctx->is_active)
 			cpuctx->task_ctx = NULL;
 	}
 
-	update_context_time(ctx);
-	update_cgrp_time_from_cpuctx(cpuctx);
-	if (!ctx->nr_active)
+	is_active ^= ctx->is_active; /* changed bits */
+
+	if (is_active & EVENT_TIME) {
+		/* update (and stop) ctx time */
+		update_context_time(ctx);
+		update_cgrp_time_from_cpuctx(cpuctx);
+	}
+
+	if (!ctx->nr_active || !(is_active & EVENT_ALL))
 		return;
 
 	perf_pmu_disable(ctx->pmu);
-	if ((is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) {
+	if (is_active & EVENT_PINNED) {
 		list_for_each_entry(event, &ctx->pinned_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
 	}
 
-	if ((is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) {
+	if (is_active & EVENT_FLEXIBLE) {
 		list_for_each_entry(event, &ctx->flexible_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
 	}
@@ -2641,18 +2699,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
 		perf_cgroup_sched_out(task, next);
 }
 
-static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
-			       struct perf_event_context *ctx)
-{
-	if (!cpuctx->task_ctx)
-		return;
-
-	if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
-		return;
-
-	ctx_sched_out(ctx, cpuctx, EVENT_ALL);
-}
-
 /*
  * Called with IRQs disabled
  */
@@ -2735,7 +2781,7 @@ ctx_sched_in(struct perf_event_context *ctx,
 	if (likely(!ctx->nr_events))
 		return;
 
-	ctx->is_active |= event_type;
+	ctx->is_active |= (event_type | EVENT_TIME);
 	if (ctx->task) {
 		if (!is_active)
 			cpuctx->task_ctx = ctx;
@@ -2743,18 +2789,24 @@ ctx_sched_in(struct perf_event_context *ctx,
 			WARN_ON_ONCE(cpuctx->task_ctx != ctx);
 	}
 
-	now = perf_clock();
-	ctx->timestamp = now;
-	perf_cgroup_set_timestamp(task, ctx);
+	is_active ^= ctx->is_active; /* changed bits */
+
+	if (is_active & EVENT_TIME) {
+		/* start ctx time */
+		now = perf_clock();
+		ctx->timestamp = now;
+		perf_cgroup_set_timestamp(task, ctx);
+	}
+
 	/*
 	 * First go through the list and put on any pinned groups
 	 * in order to give them the best chance of going on.
 	 */
-	if (!(is_active & EVENT_PINNED) && (event_type & EVENT_PINNED))
+	if (is_active & EVENT_PINNED)
 		ctx_pinned_sched_in(ctx, cpuctx);
 
 	/* Then walk through the lower prio flexible groups */
-	if (!(is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE))
+	if (is_active & EVENT_FLEXIBLE)
 		ctx_flexible_sched_in(ctx, cpuctx);
 }
 
@@ -3120,6 +3172,7 @@ static void perf_event_enable_on_exec(int ctxn)
 
 	cpuctx = __get_cpu_context(ctx);
 	perf_ctx_lock(cpuctx, ctx);
+	ctx_sched_out(ctx, cpuctx, EVENT_TIME);
 	list_for_each_entry(event, &ctx->event_list, event_entry)
 		enabled |= event_enable_on_exec(event, ctx);
 
@@ -3537,12 +3590,22 @@ static void unaccount_event(struct perf_event *event)
 	if (has_branch_stack(event))
 		dec = true;
 
-	if (dec)
-		static_key_slow_dec_deferred(&perf_sched_events);
+	if (dec) {
+		if (!atomic_add_unless(&perf_sched_count, -1, 1))
+			schedule_delayed_work(&perf_sched_work, HZ);
+	}
 
 	unaccount_event_cpu(event, event->cpu);
 }
 
+static void perf_sched_delayed(struct work_struct *work)
+{
+	mutex_lock(&perf_sched_mutex);
+	if (atomic_dec_and_test(&perf_sched_count))
+		static_branch_disable(&perf_sched_events);
+	mutex_unlock(&perf_sched_mutex);
+}
+
 /*
  * The following implement mutual exclusion of events on "exclusive" pmus
  * (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled
@@ -3752,30 +3815,42 @@ static void put_event(struct perf_event *event)
  */
 int perf_event_release_kernel(struct perf_event *event)
 {
-	struct perf_event_context *ctx;
+	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *child, *tmp;
 
+	/*
+	 * If we got here through err_file: fput(event_file); we will not have
+	 * attached to a context yet.
+	 */
+	if (!ctx) {
+		WARN_ON_ONCE(event->attach_state &
+				(PERF_ATTACH_CONTEXT|PERF_ATTACH_GROUP));
+		goto no_ctx;
+	}
+
 	if (!is_kernel_event(event))
 		perf_remove_from_owner(event);
 
 	ctx = perf_event_ctx_lock(event);
 	WARN_ON_ONCE(ctx->parent_ctx);
-	perf_remove_from_context(event, DETACH_GROUP | DETACH_STATE);
-	perf_event_ctx_unlock(event, ctx);
+	perf_remove_from_context(event, DETACH_GROUP);
 
+	raw_spin_lock_irq(&ctx->lock);
 	/*
-	 * At this point we must have event->state == PERF_EVENT_STATE_EXIT,
-	 * either from the above perf_remove_from_context() or through
-	 * perf_event_exit_event().
+	 * Mark this even as STATE_DEAD, there is no external reference to it
+	 * anymore.
 	 *
-	 * Therefore, anybody acquiring event->child_mutex after the below
-	 * loop _must_ also see this, most importantly inherit_event() which
-	 * will avoid placing more children on the list.
+	 * Anybody acquiring event->child_mutex after the below loop _must_
+	 * also see this, most importantly inherit_event() which will avoid
+	 * placing more children on the list.
 	 *
 	 * Thus this guarantees that we will in fact observe and kill _ALL_
 	 * child events.
 	 */
-	WARN_ON_ONCE(event->state != PERF_EVENT_STATE_EXIT);
+	event->state = PERF_EVENT_STATE_DEAD;
+	raw_spin_unlock_irq(&ctx->lock);
+
+	perf_event_ctx_unlock(event, ctx);
 
 again:
 	mutex_lock(&event->child_mutex);
@@ -3830,8 +3905,8 @@ again:
 	}
 	mutex_unlock(&event->child_mutex);
 
-	/* Must be the last reference */
-	put_event(event);
+no_ctx:
+	put_event(event); /* Must be the 'last' reference */
 	return 0;
 }
 EXPORT_SYMBOL_GPL(perf_event_release_kernel);
@@ -3988,7 +4063,7 @@ static bool is_event_hup(struct perf_event *event)
 {
 	bool no_children;
 
-	if (event->state != PERF_EVENT_STATE_EXIT)
+	if (event->state > PERF_EVENT_STATE_EXIT)
 		return false;
 
 	mutex_lock(&event->child_mutex);
@@ -7769,8 +7844,28 @@ static void account_event(struct perf_event *event)
 	if (is_cgroup_event(event))
 		inc = true;
 
-	if (inc)
-		static_key_slow_inc(&perf_sched_events.key);
+	if (inc) {
+		if (atomic_inc_not_zero(&perf_sched_count))
+			goto enabled;
+
+		mutex_lock(&perf_sched_mutex);
+		if (!atomic_read(&perf_sched_count)) {
+			static_branch_enable(&perf_sched_events);
+			/*
+			 * Guarantee that all CPUs observe they key change and
+			 * call the perf scheduling hooks before proceeding to
+			 * install events that need them.
+			 */
+			synchronize_sched();
+		}
+		/*
+		 * Now that we have waited for the sync_sched(), allow further
+		 * increments to by-pass the mutex.
+		 */
+		atomic_inc(&perf_sched_count);
+		mutex_unlock(&perf_sched_mutex);
+	}
+enabled:
 
 	account_event_cpu(event, event->cpu);
 }
@@ -8389,10 +8484,19 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (move_group) {
 		gctx = group_leader->ctx;
 		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+		if (gctx->task == TASK_TOMBSTONE) {
+			err = -ESRCH;
+			goto err_locked;
+		}
 	} else {
 		mutex_lock(&ctx->mutex);
 	}
 
+	if (ctx->task == TASK_TOMBSTONE) {
+		err = -ESRCH;
+		goto err_locked;
+	}
+
 	if (!perf_event_validate_size(event)) {
 		err = -E2BIG;
 		goto err_locked;
@@ -8509,7 +8613,12 @@ err_context:
 	perf_unpin_context(ctx);
 	put_ctx(ctx);
 err_alloc:
-	free_event(event);
+	/*
+	 * If event_file is set, the fput() above will have called ->release()
+	 * and that will take care of freeing the event.
+	 */
+	if (!event_file)
+		free_event(event);
 err_cpus:
 	put_online_cpus();
 err_task:
@@ -8563,12 +8672,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
+	if (ctx->task == TASK_TOMBSTONE) {
+		err = -ESRCH;
+		goto err_unlock;
+	}
+
 	if (!exclusive_event_installable(event, ctx)) {
-		mutex_unlock(&ctx->mutex);
-		perf_unpin_context(ctx);
-		put_ctx(ctx);
 		err = -EBUSY;
-		goto err_free;
+		goto err_unlock;
 	}
 
 	perf_install_in_context(ctx, event, cpu);
@@ -8577,6 +8688,10 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 
 	return event;
 
+err_unlock:
+	mutex_unlock(&ctx->mutex);
+	perf_unpin_context(ctx);
+	put_ctx(ctx);
 err_free:
 	free_event(event);
 err:
@@ -8695,7 +8810,7 @@ perf_event_exit_event(struct perf_event *child_event,
 	if (parent_event)
 		perf_group_detach(child_event);
 	list_del_event(child_event, child_ctx);
-	child_event->state = PERF_EVENT_STATE_EXIT; /* see perf_event_release_kernel() */
+	child_event->state = PERF_EVENT_STATE_EXIT; /* is_event_hup() */
 	raw_spin_unlock_irq(&child_ctx->lock);
 
 	/*
@@ -9206,7 +9321,7 @@ static void perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
-	if (swhash->hlist_refcount > 0) {
+	if (swhash->hlist_refcount > 0 && !swevent_hlist_deref(swhash)) {
 		struct swevent_hlist *hlist;
 
 		hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu));
@@ -9282,11 +9397,9 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 	switch (action & ~CPU_TASKS_FROZEN) {
 
 	case CPU_UP_PREPARE:
-	case CPU_DOWN_FAILED:
 		perf_event_init_cpu(cpu);
 		break;
 
-	case CPU_UP_CANCELED:
 	case CPU_DOWN_PREPARE:
 		perf_event_exit_cpu(cpu);
 		break;
@@ -9315,9 +9428,6 @@ void __init perf_event_init(void)
 	ret = init_hw_breakpoint();
 	WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
 
-	/* do not patch jump label more than once per second */
-	jump_label_rate_limit(&perf_sched_events, HZ);
-
 	/*
 	 * Build time assertion that we keep the data_head at the intended
 	 * location.  IOW, validation we got the __reserved[] size right.
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 841187239adc..e79e60f50bce 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1609,6 +1609,9 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	struct irq_desc *desc;
 	int retval;
 
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
 	/*
 	 * Sanity-check: shared interrupts must pass in a real dev-ID,
 	 * otherwise we'll have trouble later trying to figure out
@@ -1699,9 +1702,13 @@ EXPORT_SYMBOL(request_threaded_irq);
 int request_any_context_irq(unsigned int irq, irq_handler_t handler,
 			    unsigned long flags, const char *name, void *dev_id)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc;
 	int ret;
 
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
+	desc = irq_to_desc(irq);
 	if (!desc)
 		return -EINVAL;
 
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 2c468dea60bc..6cf54615a9c4 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -29,10 +29,10 @@ __weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size)
 
 static void *try_ram_remap(resource_size_t offset, size_t size)
 {
-	struct page *page = pfn_to_page(offset >> PAGE_SHIFT);
+	unsigned long pfn = PHYS_PFN(offset);
 
 	/* In the simple case just return the existing linear address */
-	if (!PageHighMem(page))
+	if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)))
 		return __va(offset);
 	return NULL; /* fallback to ioremap_cache */
 }
@@ -114,7 +114,7 @@ EXPORT_SYMBOL(memunmap);
 
 static void devm_memremap_release(struct device *dev, void *res)
 {
-	memunmap(res);
+	memunmap(*(void **)res);
 }
 
 static int devm_memremap_match(struct device *dev, void *res, void *match_data)
@@ -136,8 +136,10 @@ void *devm_memremap(struct device *dev, resource_size_t offset,
 	if (addr) {
 		*ptr = addr;
 		devres_add(dev, ptr);
-	} else
+	} else {
 		devres_free(ptr);
+		return ERR_PTR(-ENXIO);
+	}
 
 	return addr;
 }
@@ -268,13 +270,16 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 void *devm_memremap_pages(struct device *dev, struct resource *res,
 		struct percpu_ref *ref, struct vmem_altmap *altmap)
 {
-	int is_ram = region_intersects(res->start, resource_size(res),
-			"System RAM");
 	resource_size_t key, align_start, align_size, align_end;
 	struct dev_pagemap *pgmap;
 	struct page_map *page_map;
+	int error, nid, is_ram;
 	unsigned long pfn;
-	int error, nid;
+
+	align_start = res->start & ~(SECTION_SIZE - 1);
+	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
+		- align_start;
+	is_ram = region_intersects(align_start, align_size, "System RAM");
 
 	if (is_ram == REGION_MIXED) {
 		WARN_ONCE(1, "%s attempted on mixed region %pr\n",
@@ -312,8 +317,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 
 	mutex_lock(&pgmap_lock);
 	error = 0;
-	align_start = res->start & ~(SECTION_SIZE - 1);
-	align_size = ALIGN(resource_size(res), SECTION_SIZE);
 	align_end = align_start + align_size - 1;
 	for (key = align_start; key <= align_end; key += SECTION_SIZE) {
 		struct dev_pagemap *dup;
@@ -349,8 +352,13 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	for_each_device_pfn(pfn, page_map) {
 		struct page *page = pfn_to_page(pfn);
 
-		/* ZONE_DEVICE pages must never appear on a slab lru */
-		list_force_poison(&page->lru);
+		/*
+		 * ZONE_DEVICE pages union ->lru with a ->pgmap back
+		 * pointer.  It is a bug if a ZONE_DEVICE page is ever
+		 * freed or placed on a driver-private list.  Seed the
+		 * storage with LIST_POISON* values.
+		 */
+		list_del(&page->lru);
 		page->pgmap = pgmap;
 	}
 	devres_add(dev, page_map);
diff --git a/kernel/module.c b/kernel/module.c
index 9537da37ce87..794ebe8e878d 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -984,6 +984,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		mod->exit();
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_GOING, mod);
+	ftrace_release_mod(mod);
+
 	async_synchronize_full();
 
 	/* Store the name of the last unloaded module for diagnostic purposes */
@@ -3313,6 +3315,7 @@ fail:
 	module_put(mod);
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_GOING, mod);
+	ftrace_release_mod(mod);
 	free_module(mod);
 	wake_up_all(&module_wq);
 	return ret;
@@ -3389,6 +3392,7 @@ static int complete_formation(struct module *mod, struct load_info *info)
 	mod->state = MODULE_STATE_COMING;
 	mutex_unlock(&module_mutex);
 
+	ftrace_module_enable(mod);
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_COMING, mod);
 	return 0;
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 564f786df470..df058bed53ce 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -30,13 +30,12 @@ static int try_to_freeze_tasks(bool user_only)
 	unsigned long end_time;
 	unsigned int todo;
 	bool wq_busy = false;
-	struct timeval start, end;
-	u64 elapsed_msecs64;
+	ktime_t start, end, elapsed;
 	unsigned int elapsed_msecs;
 	bool wakeup = false;
 	int sleep_usecs = USEC_PER_MSEC;
 
-	do_gettimeofday(&start);
+	start = ktime_get_boottime();
 
 	end_time = jiffies + msecs_to_jiffies(freeze_timeout_msecs);
 
@@ -78,10 +77,9 @@ static int try_to_freeze_tasks(bool user_only)
 			sleep_usecs *= 2;
 	}
 
-	do_gettimeofday(&end);
-	elapsed_msecs64 = timeval_to_ns(&end) - timeval_to_ns(&start);
-	do_div(elapsed_msecs64, NSEC_PER_MSEC);
-	elapsed_msecs = elapsed_msecs64;
+	end = ktime_get_boottime();
+	elapsed = ktime_sub(end, start);
+	elapsed_msecs = ktime_to_ms(elapsed);
 
 	if (todo) {
 		pr_cont("\n");
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index f9fe133c13e2..230a77225e2e 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -248,7 +248,7 @@ static int suspend_test(int level)
 {
 #ifdef CONFIG_PM_DEBUG
 	if (pm_test_level == level) {
-		printk(KERN_INFO "suspend debug: Waiting for %d second(s).\n",
+		pr_info("suspend debug: Waiting for %d second(s).\n",
 				pm_test_delay);
 		mdelay(pm_test_delay * 1000);
 		return 1;
@@ -320,7 +320,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 
 	error = dpm_suspend_late(PMSG_SUSPEND);
 	if (error) {
-		printk(KERN_ERR "PM: late suspend of devices failed\n");
+		pr_err("PM: late suspend of devices failed\n");
 		goto Platform_finish;
 	}
 	error = platform_suspend_prepare_late(state);
@@ -329,7 +329,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 
 	error = dpm_suspend_noirq(PMSG_SUSPEND);
 	if (error) {
-		printk(KERN_ERR "PM: noirq suspend of devices failed\n");
+		pr_err("PM: noirq suspend of devices failed\n");
 		goto Platform_early_resume;
 	}
 	error = platform_suspend_prepare_noirq(state);
diff --git a/kernel/resource.c b/kernel/resource.c
index 09c0597840b0..3669d1bfc425 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1083,9 +1083,10 @@ struct resource * __request_region(struct resource *parent,
 		if (!conflict)
 			break;
 		if (conflict != parent) {
-			parent = conflict;
-			if (!(conflict->flags & IORESOURCE_BUSY))
+			if (!(conflict->flags & IORESOURCE_BUSY)) {
+				parent = conflict;
 				continue;
+			}
 		}
 		if (conflict->flags & flags & IORESOURCE_MUXED) {
 			add_wait_queue(&muxed_resource_wait, &wait);
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 67687973ce80..9507522164ac 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -19,3 +19,4 @@ obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
+obj-$(CONFIG_CPU_FREQ) += cpufreq.o
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9503d590e5ef..41f6b2215aa8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -26,6 +26,7 @@
  *              Thomas Gleixner, Mike Kravetz
  */
 
+#include <linux/kasan.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/nmi.h>
@@ -5096,6 +5097,8 @@ void init_idle(struct task_struct *idle, int cpu)
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
 
+	kasan_unpoison_task_stack(idle);
+
 #ifdef CONFIG_SMP
 	/*
 	 * Its possible that init_idle() gets called multiple times on a task,
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
new file mode 100644
index 000000000000..928c4ba32f68
--- /dev/null
+++ b/kernel/sched/cpufreq.c
@@ -0,0 +1,37 @@
+/*
+ * Scheduler code and data structures related to cpufreq.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "sched.h"
+
+DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_set_update_util_data - Populate the CPU's update_util_data pointer.
+ * @cpu: The CPU to set the pointer for.
+ * @data: New pointer value.
+ *
+ * Set and publish the update_util_data pointer for the given CPU.  That pointer
+ * points to a struct update_util_data object containing a callback function
+ * to call from cpufreq_update_util().  That function will be called from an RCU
+ * read-side critical section, so it must not sleep.
+ *
+ * Callers must use RCU-sched callbacks to free any memory that might be
+ * accessed via the old update_util_data pointer or invoke synchronize_sched()
+ * right after this function to avoid use-after-free.
+ */
+void cpufreq_set_update_util_data(int cpu, struct update_util_data *data)
+{
+	if (WARN_ON(data && !data->func))
+		return;
+
+	rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data);
+}
+EXPORT_SYMBOL_GPL(cpufreq_set_update_util_data);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index cd64c979d0e1..2037cf432a45 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -420,7 +420,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 	 * entity.
 	 */
 	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
-		printk_deferred_once("sched: DL replenish lagged to much\n");
+		printk_deferred_once("sched: DL replenish lagged too much\n");
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 		dl_se->runtime = pi_se->dl_runtime;
 	}
@@ -726,6 +726,10 @@ static void update_curr_dl(struct rq *rq)
 	if (!dl_task(curr) || !on_dl_rq(dl_se))
 		return;
 
+	/* Kick cpufreq (see the comment in linux/cpufreq.h). */
+	if (cpu_of(rq) == smp_processor_id())
+		cpufreq_trigger_update(rq_clock(rq));
+
 	/*
 	 * Consumed budget is computed considering the time as
 	 * observed by schedulable tasks (excluding time spent
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 56b7d4b83947..e2987a7e489d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2824,7 +2824,8 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	u64 now = cfs_rq_clock_task(cfs_rq);
-	int cpu = cpu_of(rq_of(cfs_rq));
+	struct rq *rq = rq_of(cfs_rq);
+	int cpu = cpu_of(rq);
 
 	/*
 	 * Track task load average for carrying it to new CPU after migrated, and
@@ -2836,6 +2837,29 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
 
 	if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
 		update_tg_load_avg(cfs_rq, 0);
+
+	if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) {
+		unsigned long max = rq->cpu_capacity_orig;
+
+		/*
+		 * There are a few boundary cases this might miss but it should
+		 * get called often enough that that should (hopefully) not be
+		 * a real problem -- added to that it only calls on the local
+		 * CPU, so if we enqueue remotely we'll miss an update, but
+		 * the next tick/schedule should update.
+		 *
+		 * It will not get called when we go idle, because the idle
+		 * thread is a different class (!fair), nor will the utilization
+		 * number include things like RT tasks.
+		 *
+		 * As is, the util number is not freq-invariant (we'd have to
+		 * implement arch_scale_freq_capacity() for that).
+		 *
+		 * See cpu_util().
+		 */
+		cpufreq_update_util(rq_clock(rq),
+				    min(cfs_rq->avg.util_avg, max), max);
+	}
 }
 
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 8ec86abe0ea1..27f5b03cbdbe 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -945,6 +945,10 @@ static void update_curr_rt(struct rq *rq)
 	if (curr->sched_class != &rt_sched_class)
 		return;
 
+	/* Kick cpufreq (see the comment in linux/cpufreq.h). */
+	if (cpu_of(rq) == smp_processor_id())
+		cpufreq_trigger_update(rq_clock(rq));
+
 	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
 	if (unlikely((s64)delta_exec <= 0))
 		return;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 10f16374df7f..faf7e2758dd0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1738,3 +1738,51 @@ static inline u64 irq_time_read(int cpu)
 }
 #endif /* CONFIG_64BIT */
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+#ifdef CONFIG_CPU_FREQ
+DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_update_util - Take a note about CPU utilization changes.
+ * @time: Current time.
+ * @util: Current utilization.
+ * @max: Utilization ceiling.
+ *
+ * This function is called by the scheduler on every invocation of
+ * update_load_avg() on the CPU whose utilization is being updated.
+ *
+ * It can only be called from RCU-sched read-side critical sections.
+ */
+static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max)
+{
+       struct update_util_data *data;
+
+       data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
+       if (data)
+               data->func(data, time, util, max);
+}
+
+/**
+ * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed.
+ * @time: Current time.
+ *
+ * The way cpufreq is currently arranged requires it to evaluate the CPU
+ * performance state (frequency/voltage) on a regular basis to prevent it from
+ * being stuck in a completely inadequate performance level for too long.
+ * That is not guaranteed to happen if the updates are only triggered from CFS,
+ * though, because they may not be coming in if RT or deadline tasks are active
+ * all the time (or there are RT and DL tasks only).
+ *
+ * As a workaround for that issue, this function is called by the RT and DL
+ * sched classes to trigger extra cpufreq updates to prevent it from stalling,
+ * but that really is a band-aid.  Going forward it should be replaced with
+ * solutions targeted more specifically at RT and DL tasks.
+ */
+static inline void cpufreq_trigger_update(u64 time)
+{
+	cpufreq_update_util(time, ULONG_MAX, 0);
+}
+#else
+static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {}
+static inline void cpufreq_trigger_update(u64 time) {}
+#endif /* CONFIG_CPU_FREQ */
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index eca592f977b2..57a6eea84694 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4961,7 +4961,7 @@ void ftrace_release_mod(struct module *mod)
 	mutex_unlock(&ftrace_lock);
 }
 
-static void ftrace_module_enable(struct module *mod)
+void ftrace_module_enable(struct module *mod)
 {
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;
@@ -5038,38 +5038,8 @@ void ftrace_module_init(struct module *mod)
 	ftrace_process_locs(mod, mod->ftrace_callsites,
 			    mod->ftrace_callsites + mod->num_ftrace_callsites);
 }
-
-static int ftrace_module_notify(struct notifier_block *self,
-				unsigned long val, void *data)
-{
-	struct module *mod = data;
-
-	switch (val) {
-	case MODULE_STATE_COMING:
-		ftrace_module_enable(mod);
-		break;
-	case MODULE_STATE_GOING:
-		ftrace_release_mod(mod);
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
-#else
-static int ftrace_module_notify(struct notifier_block *self,
-				unsigned long val, void *data)
-{
-	return 0;
-}
 #endif /* CONFIG_MODULES */
 
-struct notifier_block ftrace_module_nb = {
-	.notifier_call = ftrace_module_notify,
-	.priority = INT_MIN,	/* Run after anything that can remove kprobes */
-};
-
 void __init ftrace_init(void)
 {
 	extern unsigned long __start_mcount_loc[];
@@ -5098,10 +5068,6 @@ void __init ftrace_init(void)
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
-	ret = register_module_notifier(&ftrace_module_nb);
-	if (ret)
-		pr_warning("Failed to register trace ftrace module exit notifier\n");
-
 	set_ftrace_early_filters();
 
 	return;
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index eb4220a132ec..81b87451c0ea 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -15,4 +15,5 @@
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume);
 EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
+EXPORT_TRACEPOINT_SYMBOL_GPL(powernv_throttle);
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f333e57c4614..05ddc0820771 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -97,16 +97,16 @@ trace_find_event_field(struct trace_event_call *call, char *name)
 	struct ftrace_event_field *field;
 	struct list_head *head;
 
-	field = __find_event_field(&ftrace_generic_fields, name);
+	head = trace_get_fields(call);
+	field = __find_event_field(head, name);
 	if (field)
 		return field;
 
-	field = __find_event_field(&ftrace_common_fields, name);
+	field = __find_event_field(&ftrace_generic_fields, name);
 	if (field)
 		return field;
 
-	head = trace_get_fields(call);
-	return __find_event_field(head, name);
+	return __find_event_field(&ftrace_common_fields, name);
 }
 
 static int __trace_define_field(struct list_head *head, const char *type,
@@ -171,8 +171,10 @@ static int trace_define_generic_fields(void)
 {
 	int ret;
 
-	__generic_field(int, cpu, FILTER_OTHER);
-	__generic_field(char *, comm, FILTER_PTR_STRING);
+	__generic_field(int, CPU, FILTER_CPU);
+	__generic_field(int, cpu, FILTER_CPU);
+	__generic_field(char *, COMM, FILTER_COMM);
+	__generic_field(char *, comm, FILTER_COMM);
 
 	return ret;
 }
@@ -869,7 +871,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 		 * The ftrace subsystem is for showing formats only.
 		 * They can not be enabled or disabled via the event files.
 		 */
-		if (call->class && call->class->reg)
+		if (call->class && call->class->reg &&
+		    !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
 			return file;
 	}
 
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index f93a219b18da..6816302542b2 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1043,13 +1043,14 @@ static int init_pred(struct filter_parse_state *ps,
 		return -EINVAL;
 	}
 
-	if (is_string_field(field)) {
+	if (field->filter_type == FILTER_COMM) {
+		filter_build_regex(pred);
+		fn = filter_pred_comm;
+		pred->regex.field_len = TASK_COMM_LEN;
+	} else if (is_string_field(field)) {
 		filter_build_regex(pred);
 
-		if (!strcmp(field->name, "comm")) {
-			fn = filter_pred_comm;
-			pred->regex.field_len = TASK_COMM_LEN;
-		} else if (field->filter_type == FILTER_STATIC_STRING) {
+		if (field->filter_type == FILTER_STATIC_STRING) {
 			fn = filter_pred_string;
 			pred->regex.field_len = field->size;
 		} else if (field->filter_type == FILTER_DYN_STRING)
@@ -1072,7 +1073,7 @@ static int init_pred(struct filter_parse_state *ps,
 		}
 		pred->val = val;
 
-		if (!strcmp(field->name, "cpu"))
+		if (field->filter_type == FILTER_CPU)
 			fn = filter_pred_cpu;
 		else
 			fn = select_comparison_fn(pred->op, field->size,
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 202df6cffcca..2a1abbaca10e 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -156,7 +156,11 @@ check_stack(unsigned long ip, unsigned long *stack)
 		for (; p < top && i < stack_trace_max.nr_entries; p++) {
 			if (stack_dump_trace[i] == ULONG_MAX)
 				break;
-			if (*p == stack_dump_trace[i]) {
+			/*
+			 * The READ_ONCE_NOCHECK is used to let KASAN know that
+			 * this is not a stack-out-of-bounds error.
+			 */
+			if ((READ_ONCE_NOCHECK(*p)) == stack_dump_trace[i]) {
 				stack_dump_trace[x] = stack_dump_trace[i++];
 				this_size = stack_trace_index[x++] =
 					(top - p) * sizeof(unsigned long);