Merge tag 'v4.4.73' into toradex_vf_4.4-nextColibri-VF_LXDE-Image_2.7b3-20170630

This is the 4.4.73 stable release

17 files changed, 199 insertions, 49 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 127c63e02d52..4cb94b678e9f 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2752,11 +2752,12 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 		tsk = tsk->group_leader;
 
 	/*
-	 * Workqueue threads may acquire PF_NO_SETAFFINITY and become
-	 * trapped in a cpuset, or RT worker may be born in a cgroup
-	 * with no rt_runtime allocated.  Just say no.
+	 * kthreads may acquire PF_NO_SETAFFINITY during initialization.
+	 * If userland migrates such a kthread to a non-root cgroup, it can
+	 * become trapped in a cpuset, or RT kthread may be born in a
+	 * cgroup with no rt_runtime allocated.  Just say no.
 	 */
-	if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
+	if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) {
 		ret = -EINVAL;
 		goto out_unlock_rcu;
 	}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b271353d5202..3b5e5430f5d0 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -173,9 +173,9 @@ typedef enum {
 } cpuset_flagbits_t;
 
 /* convenient tests for these bits */
-static inline bool is_cpuset_online(const struct cpuset *cs)
+static inline bool is_cpuset_online(struct cpuset *cs)
 {
-	return test_bit(CS_ONLINE, &cs->flags);
+	return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css);
 }
 
 static inline int is_cpu_exclusive(const struct cpuset *cs)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e4b5494f05f8..22350b15b4e7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6410,6 +6410,21 @@ static void perf_log_itrace_start(struct perf_event *event)
 	perf_output_end(&handle);
 }
 
+static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
+{
+	/*
+	 * Due to interrupt latency (AKA "skid"), we may enter the
+	 * kernel before taking an overflow, even if the PMU is only
+	 * counting user events.
+	 * To avoid leaking information to userspace, we must always
+	 * reject kernel samples when exclude_kernel is set.
+	 */
+	if (event->attr.exclude_kernel && !user_mode(regs))
+		return false;
+
+	return true;
+}
+
 /*
  * Generic event overflow handling, sampling.
  */
@@ -6457,6 +6472,12 @@ static int __perf_event_overflow(struct perf_event *event,
 	}
 
 	/*
+	 * For security, drop the skid kernel samples if necessary.
+	 */
+	if (!sample_is_allowed(event, regs))
+		return ret;
+
+	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
 	 */
@@ -8250,6 +8271,37 @@ static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id)
 	return 0;
 }
 
+/*
+ * Variation on perf_event_ctx_lock_nested(), except we take two context
+ * mutexes.
+ */
+static struct perf_event_context *
+__perf_event_ctx_lock_double(struct perf_event *group_leader,
+			     struct perf_event_context *ctx)
+{
+	struct perf_event_context *gctx;
+
+again:
+	rcu_read_lock();
+	gctx = READ_ONCE(group_leader->ctx);
+	if (!atomic_inc_not_zero(&gctx->refcount)) {
+		rcu_read_unlock();
+		goto again;
+	}
+	rcu_read_unlock();
+
+	mutex_lock_double(&gctx->mutex, &ctx->mutex);
+
+	if (group_leader->ctx != gctx) {
+		mutex_unlock(&ctx->mutex);
+		mutex_unlock(&gctx->mutex);
+		put_ctx(gctx);
+		goto again;
+	}
+
+	return gctx;
+}
+
 /**
  * sys_perf_event_open - open a performance event, associate it to a task/cpu
  *
@@ -8486,8 +8538,26 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	if (move_group) {
-		gctx = group_leader->ctx;
-		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+		gctx = __perf_event_ctx_lock_double(group_leader, ctx);
+
+		/*
+		 * Check if we raced against another sys_perf_event_open() call
+		 * moving the software group underneath us.
+		 */
+		if (!(group_leader->group_flags & PERF_GROUP_SOFTWARE)) {
+			/*
+			 * If someone moved the group out from under us, check
+			 * if this new event wound up on the same ctx, if so
+			 * its the regular !move_group case, otherwise fail.
+			 */
+			if (gctx != ctx) {
+				err = -EINVAL;
+				goto err_locked;
+			} else {
+				perf_event_ctx_unlock(group_leader, gctx);
+				move_group = 0;
+			}
+		}
 	} else {
 		mutex_lock(&ctx->mutex);
 	}
@@ -8582,7 +8652,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	perf_unpin_context(ctx);
 
 	if (move_group)
-		mutex_unlock(&gctx->mutex);
+		perf_event_ctx_unlock(group_leader, gctx);
 	mutex_unlock(&ctx->mutex);
 
 	if (task) {
@@ -8610,7 +8680,7 @@ SYSCALL_DEFINE5(perf_event_open,
 
 err_locked:
 	if (move_group)
-		mutex_unlock(&gctx->mutex);
+		perf_event_ctx_unlock(group_leader, gctx);
 	mutex_unlock(&ctx->mutex);
 /* err_file: */
 	fput(event_file);
diff --git a/kernel/fork.c b/kernel/fork.c
index 278a2ddad351..68cfda1c1800 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -368,7 +368,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	set_task_stack_end_magic(tsk);
 
 #ifdef CONFIG_CC_STACKPROTECTOR
-	tsk->stack_canary = get_random_int();
+	tsk->stack_canary = get_random_long();
 #endif
 
 	/*
@@ -1590,11 +1590,13 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	*/
 	recalc_sigpending();
 	if (signal_pending(current)) {
-		spin_unlock(&current->sighand->siglock);
-		write_unlock_irq(&tasklist_lock);
 		retval = -ERESTARTNOINTR;
 		goto bad_fork_cancel_cgroup;
 	}
+	if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) {
+		retval = -ENOMEM;
+		goto bad_fork_cancel_cgroup;
+	}
 
 	if (likely(p->pid)) {
 		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
@@ -1645,6 +1647,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	return p;
 
 bad_fork_cancel_cgroup:
+	spin_unlock(&current->sighand->siglock);
+	write_unlock_irq(&tasklist_lock);
 	cgroup_cancel_fork(p, cgrp_ss_priv);
 bad_fork_free_pid:
 	threadgroup_change_end(current);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 15206453b12a..e4453d9f788c 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -810,8 +810,8 @@ irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle,
 	if (!desc)
 		return;
 
-	__irq_do_set_handler(desc, handle, 1, NULL);
 	desc->irq_common_data.handler_data = data;
+	__irq_do_set_handler(desc, handle, 1, NULL);
 
 	irq_put_desc_busunlock(desc, flags);
 }
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d10ab6b9b5e0..695763516908 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -563,7 +563,7 @@ static void kprobe_optimizer(struct work_struct *work)
 }
 
 /* Wait for completing optimization and unoptimization */
-static void wait_for_kprobe_optimizer(void)
+void wait_for_kprobe_optimizer(void)
 {
 	mutex_lock(&kprobe_mutex);
 
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 9ff173dca1ae..850b255649a2 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -18,6 +18,7 @@
 #include <linux/freezer.h>
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
+#include <linux/cgroup.h>
 #include <trace/events/sched.h>
 
 static DEFINE_SPINLOCK(kthread_create_lock);
@@ -205,6 +206,7 @@ static int kthread(void *_create)
 	ret = -EINTR;
 
 	if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) {
+		cgroup_kthread_ready();
 		__kthread_parkme(&self);
 		ret = threadfn(data);
 	}
@@ -510,6 +512,7 @@ int kthreadd(void *unused)
 	set_mems_allowed(node_states[N_MEMORY]);
 
 	current->flags |= PF_NOFREEZE;
+	cgroup_init_kthreadd();
 
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
diff --git a/kernel/padata.c b/kernel/padata.c
index b38bea9c466a..ecc7b3f452c7 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -189,19 +189,20 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd)
 
 	reorder = &next_queue->reorder;
 
+	spin_lock(&reorder->lock);
 	if (!list_empty(&reorder->list)) {
 		padata = list_entry(reorder->list.next,
 				    struct padata_priv, list);
 
-		spin_lock(&reorder->lock);
 		list_del_init(&padata->list);
 		atomic_dec(&pd->reorder_objects);
-		spin_unlock(&reorder->lock);
 
 		pd->processed++;
 
+		spin_unlock(&reorder->lock);
 		goto out;
 	}
+	spin_unlock(&reorder->lock);
 
 	if (__this_cpu_read(pd->pqueue->cpu_index) == next_queue->cpu_index) {
 		padata = ERR_PTR(-ENODATA);
@@ -356,7 +357,7 @@ static int padata_setup_cpumasks(struct parallel_data *pd,
 
 	cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_online_mask);
 	if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) {
-		free_cpumask_var(pd->cpumask.cbcpu);
+		free_cpumask_var(pd->cpumask.pcpu);
 		return -ENOMEM;
 	}
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index a65ba137fd15..567ecc826bc8 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -255,7 +255,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	 * if reparented.
 	 */
 	for (;;) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_INTERRUPTIBLE);
 		if (pid_ns->nr_hashed == init_pids)
 			break;
 		schedule();
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index a46c40bfb5f6..5e2cd1030702 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -28,19 +28,25 @@
 #include <linux/compat.h>
 
 
+void __ptrace_link(struct task_struct *child, struct task_struct *new_parent,
+		   const struct cred *ptracer_cred)
+{
+	BUG_ON(!list_empty(&child->ptrace_entry));
+	list_add(&child->ptrace_entry, &new_parent->ptraced);
+	child->parent = new_parent;
+	child->ptracer_cred = get_cred(ptracer_cred);
+}
+
 /*
  * ptrace a task: make the debugger its new parent and
  * move it to the ptrace list.
  *
  * Must be called with the tasklist lock write-held.
  */
-void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
+static void ptrace_link(struct task_struct *child, struct task_struct *new_parent)
 {
-	BUG_ON(!list_empty(&child->ptrace_entry));
-	list_add(&child->ptrace_entry, &new_parent->ptraced);
-	child->parent = new_parent;
 	rcu_read_lock();
-	child->ptracer_cred = get_cred(__task_cred(new_parent));
+	__ptrace_link(child, new_parent, __task_cred(new_parent));
 	rcu_read_unlock();
 }
 
@@ -151,11 +157,17 @@ static void ptrace_unfreeze_traced(struct task_struct *task)
 
 	WARN_ON(!task->ptrace || task->parent != current);
 
+	/*
+	 * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely.
+	 * Recheck state under the lock to close this race.
+	 */
 	spin_lock_irq(&task->sighand->siglock);
-	if (__fatal_signal_pending(task))
-		wake_up_state(task, __TASK_TRACED);
-	else
-		task->state = TASK_TRACED;
+	if (task->state == __TASK_TRACED) {
+		if (__fatal_signal_pending(task))
+			wake_up_state(task, __TASK_TRACED);
+		else
+			task->state = TASK_TRACED;
+	}
 	spin_unlock_irq(&task->sighand->siglock);
 }
 
@@ -347,7 +359,7 @@ static int ptrace_attach(struct task_struct *task, long request,
 		flags |= PT_SEIZED;
 	task->ptrace = flags;
 
-	__ptrace_link(task, current);
+	ptrace_link(task, current);
 
 	/* SEIZE doesn't trap tracee on attach */
 	if (!seize)
@@ -414,7 +426,7 @@ static int ptrace_traceme(void)
 		 */
 		if (!ret && !(current->real_parent->flags & PF_EXITING)) {
 			current->ptrace = PT_PTRACED;
-			__ptrace_link(current, current->real_parent);
+			ptrace_link(current, current->real_parent);
 		}
 	}
 	write_unlock_irq(&tasklist_lock);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8f258f437ac2..812069b66f47 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3918,6 +3918,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
 	if (!cfs_bandwidth_used())
 		return;
 
+	/* Synchronize hierarchical throttle counter: */
+	if (unlikely(!cfs_rq->throttle_uptodate)) {
+		struct rq *rq = rq_of(cfs_rq);
+		struct cfs_rq *pcfs_rq;
+		struct task_group *tg;
+
+		cfs_rq->throttle_uptodate = 1;
+
+		/* Get closest up-to-date node, because leaves go first: */
+		for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
+			pcfs_rq = tg->cfs_rq[cpu_of(rq)];
+			if (pcfs_rq->throttle_uptodate)
+				break;
+		}
+		if (tg) {
+			cfs_rq->throttle_count = pcfs_rq->throttle_count;
+			cfs_rq->throttled_clock_task = rq_clock_task(rq);
+		}
+	}
+
 	/* an active group must be handled by the update_curr()->put() path */
 	if (!cfs_rq->runtime_enabled || cfs_rq->curr)
 		return;
@@ -4233,15 +4253,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
+			/* Avoid re-evaluating load for this entity: */
+			se = parent_entity(se);
 			/*
 			 * Bias pick_next to pick a task from this cfs_rq, as
 			 * p is sleeping when it is within its sched_slice.
 			 */
-			if (task_sleep && parent_entity(se))
-				set_next_buddy(parent_entity(se));
-
-			/* avoid re-evaluating load for this entity */
-			se = parent_entity(se);
+			if (task_sleep && se && !throttled_hierarchy(cfs_rq))
+				set_next_buddy(se);
 			break;
 		}
 		flags |= DEQUEUE_SLEEP;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0517abd7dd73..4e5db65d1aab 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -417,7 +417,7 @@ struct cfs_rq {
 
 	u64 throttled_clock, throttled_clock_task;
 	u64 throttled_clock_task_time;
-	int throttled, throttle_count;
+	int throttled, throttle_count, throttle_uptodate;
 	struct list_head throttled_list;
 #endif /* CONFIG_CFS_BANDWIDTH */
 #endif /* CONFIG_FAIR_GROUP_SCHED */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2f0d157258a2..300d64162aff 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -65,6 +65,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/kexec.h>
 #include <linux/bpf.h>
+#include <linux/mount.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -1749,6 +1750,14 @@ static struct ctl_table fs_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
 	},
+	{
+		.procname	= "mount-max",
+		.data		= &sysctl_mount_max,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+	},
 	{ }
 };
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 3f743b147247..34b2a0d5cf1a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3677,23 +3677,24 @@ static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash)
 	ftrace_probe_registered = 1;
 }
 
-static void __disable_ftrace_function_probe(void)
+static bool __disable_ftrace_function_probe(void)
 {
 	int i;
 
 	if (!ftrace_probe_registered)
-		return;
+		return false;
 
 	for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
 		struct hlist_head *hhd = &ftrace_func_hash[i];
 		if (hhd->first)
-			return;
+			return false;
 	}
 
 	/* no more funcs left */
 	ftrace_shutdown(&trace_probe_ops, 0);
 
 	ftrace_probe_registered = 0;
+	return true;
 }
 
 
@@ -3820,6 +3821,7 @@ static void
 __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 				  void *data, int flags)
 {
+	struct ftrace_ops_hash old_hash_ops;
 	struct ftrace_func_entry *rec_entry;
 	struct ftrace_func_probe *entry;
 	struct ftrace_func_probe *p;
@@ -3831,6 +3833,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	struct hlist_node *tmp;
 	char str[KSYM_SYMBOL_LEN];
 	int i, ret;
+	bool disabled;
 
 	if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
 		func_g.search = NULL;
@@ -3849,6 +3852,10 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 
 	mutex_lock(&trace_probe_ops.func_hash->regex_lock);
 
+	old_hash_ops.filter_hash = old_hash;
+	/* Probes only have filters */
+	old_hash_ops.notrace_hash = NULL;
+
 	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
 	if (!hash)
 		/* Hmm, should report this somehow */
@@ -3886,12 +3893,17 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 		}
 	}
 	mutex_lock(&ftrace_lock);
-	__disable_ftrace_function_probe();
+	disabled = __disable_ftrace_function_probe();
 	/*
 	 * Remove after the disable is called. Otherwise, if the last
 	 * probe is removed, a null hash means *all enabled*.
 	 */
 	ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+
+	/* still need to update the function call sites */
+	if (ftrace_enabled && !disabled)
+		ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS,
+				       &old_hash_ops);
 	synchronize_sched();
 	if (!ret)
 		free_ftrace_hash_rcu(old_hash);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index acbb0e73d3a2..1275175b0946 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3440,11 +3440,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);
 int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	struct buffer_page *reader;
+	struct buffer_page *head_page;
+	struct buffer_page *commit_page;
+	unsigned commit;
 
 	cpu_buffer = iter->cpu_buffer;
 
-	return iter->head_page == cpu_buffer->commit_page &&
-		iter->head == rb_commit_index(cpu_buffer);
+	/* Remember, trace recording is off when iterator is in use */
+	reader = cpu_buffer->reader_page;
+	head_page = cpu_buffer->head_page;
+	commit_page = cpu_buffer->commit_page;
+	commit = rb_page_commit(commit_page);
+
+	return ((iter->head_page == commit_page && iter->head == commit) ||
+		(iter->head_page == reader && commit_page == head_page &&
+		 head_page->read == commit &&
+		 iter->head == rb_page_commit(cpu_buffer->reader_page)));
 }
 EXPORT_SYMBOL_GPL(ring_buffer_iter_empty);
 
@@ -4875,9 +4887,9 @@ static __init int test_ringbuffer(void)
 		rb_data[cpu].cnt = cpu;
 		rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu],
 						 "rbtester/%d", cpu);
-		if (WARN_ON(!rb_threads[cpu])) {
+		if (WARN_ON(IS_ERR(rb_threads[cpu]))) {
 			pr_cont("FAILED\n");
-			ret = -1;
+			ret = PTR_ERR(rb_threads[cpu]);
 			goto out_free;
 		}
 
@@ -4887,9 +4899,9 @@ static __init int test_ringbuffer(void)
 
 	/* Now create the rb hammer! */
 	rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer");
-	if (WARN_ON(!rb_hammer)) {
+	if (WARN_ON(IS_ERR(rb_hammer))) {
 		pr_cont("FAILED\n");
-		ret = -1;
+		ret = PTR_ERR(rb_hammer);
 		goto out_free;
 	}
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 059233abcfcf..4c21c0b7dc91 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6060,11 +6060,13 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash,
 		return ret;
 
  out_reg:
-	ret = register_ftrace_function_probe(glob, ops, count);
+	ret = alloc_snapshot(&global_trace);
+	if (ret < 0)
+		goto out;
 
-	if (ret >= 0)
-		alloc_snapshot(&global_trace);
+	ret = register_ftrace_function_probe(glob, ops, count);
 
+ out:
 	return ret < 0 ? ret : 0;
 }
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c9956440d0e6..12ea4ea619ee 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1471,6 +1471,11 @@ static __init int kprobe_trace_self_tests_init(void)
 
 end:
 	release_all_trace_kprobes();
+	/*
+	 * Wait for the optimizer work to finish. Otherwise it might fiddle
+	 * with probes in already freed __init text.
+	 */
+	wait_for_kprobe_optimizer();
 	if (warn)
 		pr_cont("NG: Some tests are failed. Please check them.\n");
 	else