Merge branch 'sched/urgent' into sched/core, to resolve conflicts

The following fix in sched/urgent:

  e08d007f9d81 ("sched/debug: Fix avg_vruntime() usage")

is in conflict with this pending commit in sched/core:

  4823725d9d1d ("sched/fair: Increase weight bits for avg_vruntime")

Both modify the same variable definition and initialization blocks,
resolve it by merging the two.

 Conflicts:
	kernel/sched/debug.c

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

5 files changed, 101 insertions, 30 deletions

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8df69e702706..413310912609 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6606,9 +6606,9 @@ int update_ftrace_direct_mod(struct ftrace_ops *ops, struct ftrace_hash *hash, b
 	if (!orig_hash)
 		goto unlock;
 
-	/* Enable the tmp_ops to have the same functions as the direct ops */
+	/* Enable the tmp_ops to have the same functions as the hash object. */
 	ftrace_ops_init(&tmp_ops);
-	tmp_ops.func_hash = ops->func_hash;
+	tmp_ops.func_hash->filter_hash = hash;
 
 	err = register_ftrace_function_nolock(&tmp_ops);
 	if (err)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 17d0ea0cc3e6..170170bd83bd 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2053,7 +2053,7 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 
 		entries += ret;
 		entry_bytes += local_read(&head_page->page->commit);
-		local_set(&cpu_buffer->head_page->entries, ret);
+		local_set(&head_page->entries, ret);
 
 		if (head_page == cpu_buffer->commit_page)
 			break;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ebd996f8710e..a626211ceb9a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -555,7 +555,7 @@ static bool update_marker_trace(struct trace_array *tr, int enabled)
 	lockdep_assert_held(&event_mutex);
 
 	if (enabled) {
-		if (!list_empty(&tr->marker_list))
+		if (tr->trace_flags & TRACE_ITER(COPY_MARKER))
 			return false;
 
 		list_add_rcu(&tr->marker_list, &marker_copies);
@@ -563,10 +563,10 @@ static bool update_marker_trace(struct trace_array *tr, int enabled)
 		return true;
 	}
 
-	if (list_empty(&tr->marker_list))
+	if (!(tr->trace_flags & TRACE_ITER(COPY_MARKER)))
 		return false;
 
-	list_del_init(&tr->marker_list);
+	list_del_rcu(&tr->marker_list);
 	tr->trace_flags &= ~TRACE_ITER(COPY_MARKER);
 	return true;
 }
@@ -6784,6 +6784,23 @@ char *trace_user_fault_read(struct trace_user_buf_info *tinfo,
 
 	do {
 		/*
+		 * It is possible that something is trying to migrate this
+		 * task. What happens then, is when preemption is enabled,
+		 * the migration thread will preempt this task, try to
+		 * migrate it, fail, then let it run again. That will
+		 * cause this to loop again and never succeed.
+		 * On failures, enabled and disable preemption with
+		 * migration enabled, to allow the migration thread to
+		 * migrate this task.
+		 */
+		if (trys) {
+			preempt_enable_notrace();
+			preempt_disable_notrace();
+			cpu = smp_processor_id();
+			buffer = per_cpu_ptr(tinfo->tbuf, cpu)->buf;
+		}
+
+		/*
 		 * If for some reason, copy_from_user() always causes a context
 		 * switch, this would then cause an infinite loop.
 		 * If this task is preempted by another user space task, it
@@ -9744,18 +9761,19 @@ static int __remove_instance(struct trace_array *tr)
 
 	list_del(&tr->list);
 
-	/* Disable all the flags that were enabled coming in */
-	for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++) {
-		if ((1ULL << i) & ZEROED_TRACE_FLAGS)
-			set_tracer_flag(tr, 1ULL << i, 0);
-	}
-
 	if (printk_trace == tr)
 		update_printk_trace(&global_trace);
 
+	/* Must be done before disabling all the flags */
 	if (update_marker_trace(tr, 0))
 		synchronize_rcu();
 
+	/* Disable all the flags that were enabled coming in */
+	for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++) {
+		if ((1ULL << i) & ZEROED_TRACE_FLAGS)
+			set_tracer_flag(tr, 1ULL << i, 0);
+	}
+
 	tracing_set_nop(tr);
 	clear_ftrace_function_probes(tr);
 	event_trace_del_tracer(tr);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d5230b759a2d..655db2e82513 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -22,6 +22,39 @@ static struct task_struct *trigger_kthread;
 static struct llist_head trigger_data_free_list;
 static DEFINE_MUTEX(trigger_data_kthread_mutex);
 
+static int trigger_kthread_fn(void *ignore);
+
+static void trigger_create_kthread_locked(void)
+{
+	lockdep_assert_held(&trigger_data_kthread_mutex);
+
+	if (!trigger_kthread) {
+		struct task_struct *kthread;
+
+		kthread = kthread_create(trigger_kthread_fn, NULL,
+					 "trigger_data_free");
+		if (!IS_ERR(kthread))
+			WRITE_ONCE(trigger_kthread, kthread);
+	}
+}
+
+static void trigger_data_free_queued_locked(void)
+{
+	struct event_trigger_data *data, *tmp;
+	struct llist_node *llnodes;
+
+	lockdep_assert_held(&trigger_data_kthread_mutex);
+
+	llnodes = llist_del_all(&trigger_data_free_list);
+	if (!llnodes)
+		return;
+
+	tracepoint_synchronize_unregister();
+
+	llist_for_each_entry_safe(data, tmp, llnodes, llist)
+		kfree(data);
+}
+
 /* Bulk garbage collection of event_trigger_data elements */
 static int trigger_kthread_fn(void *ignore)
 {
@@ -56,30 +89,50 @@ void trigger_data_free(struct event_trigger_data *data)
 	if (data->cmd_ops->set_filter)
 		data->cmd_ops->set_filter(NULL, data, NULL);
 
+	/*
+	 * Boot-time trigger registration can fail before kthread creation
+	 * works. Keep the deferred-free semantics during boot and let late
+	 * init start the kthread to drain the list.
+	 */
+	if (system_state == SYSTEM_BOOTING && !trigger_kthread) {
+		llist_add(&data->llist, &trigger_data_free_list);
+		return;
+	}
+
 	if (unlikely(!trigger_kthread)) {
 		guard(mutex)(&trigger_data_kthread_mutex);
+
+		trigger_create_kthread_locked();
 		/* Check again after taking mutex */
 		if (!trigger_kthread) {
-			struct task_struct *kthread;
-
-			kthread = kthread_create(trigger_kthread_fn, NULL,
-						 "trigger_data_free");
-			if (!IS_ERR(kthread))
-				WRITE_ONCE(trigger_kthread, kthread);
+			llist_add(&data->llist, &trigger_data_free_list);
+			/* Drain the queued frees synchronously if creation failed. */
+			trigger_data_free_queued_locked();
+			return;
 		}
 	}
 
-	if (!trigger_kthread) {
-		/* Do it the slow way */
-		tracepoint_synchronize_unregister();
-		kfree(data);
-		return;
-	}
-
 	llist_add(&data->llist, &trigger_data_free_list);
 	wake_up_process(trigger_kthread);
 }
 
+static int __init trigger_data_free_init(void)
+{
+	guard(mutex)(&trigger_data_kthread_mutex);
+
+	if (llist_empty(&trigger_data_free_list))
+		return 0;
+
+	trigger_create_kthread_locked();
+	if (trigger_kthread)
+		wake_up_process(trigger_kthread);
+	else
+		trigger_data_free_queued_locked();
+
+	return 0;
+}
+late_initcall(trigger_data_free_init);
+
 static inline void data_ops_trigger(struct event_trigger_data *data,
 				    struct trace_buffer *buffer,  void *rec,
 				    struct ring_buffer_event *event)
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index dee610e465b9..be6cf0bb3c03 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -2073,8 +2073,8 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy)
 	if (!osnoise_has_registered_instances())
 		return;
 
-	guard(mutex)(&interface_lock);
 	guard(cpus_read_lock)();
+	guard(mutex)(&interface_lock);
 
 	if (!cpu_online(cpu))
 		return;
@@ -2237,11 +2237,11 @@ static ssize_t osnoise_options_write(struct file *filp, const char __user *ubuf,
 	if (running)
 		stop_per_cpu_kthreads();
 
-	mutex_lock(&interface_lock);
 	/*
 	 * avoid CPU hotplug operations that might read options.
 	 */
 	cpus_read_lock();
+	mutex_lock(&interface_lock);
 
 	retval = cnt;
 
@@ -2257,8 +2257,8 @@ static ssize_t osnoise_options_write(struct file *filp, const char __user *ubuf,
 			clear_bit(option, &osnoise_options);
 	}
 
-	cpus_read_unlock();
 	mutex_unlock(&interface_lock);
+	cpus_read_unlock();
 
 	if (running)
 		start_per_cpu_kthreads();
@@ -2345,16 +2345,16 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count,
 	if (running)
 		stop_per_cpu_kthreads();
 
-	mutex_lock(&interface_lock);
 	/*
 	 * osnoise_cpumask is read by CPU hotplug operations.
 	 */
 	cpus_read_lock();
+	mutex_lock(&interface_lock);
 
 	cpumask_copy(&osnoise_cpumask, osnoise_cpumask_new);
 
-	cpus_read_unlock();
 	mutex_unlock(&interface_lock);
+	cpus_read_unlock();
 
 	if (running)
 		start_per_cpu_kthreads();