Merge commit '4ac2b983648e' of github.com/Freescale/linux-fslctoradex_5.15-2.2.x-imx

Sync with linux-fslc branch 5.15-2.2.x-imx up to commit 4ac2b983648e
which includes the v5.15.196 stable update.

Signed-off-by: Vitor Soares <vitor.soares@toradex.com>

21 files changed, 212 insertions, 124 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 2788da290c21..dc42970dda97 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1044,7 +1044,6 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
 	INIT_WORK(&aux->work, prog_array_map_clear_deferred);
 	INIT_LIST_HEAD(&aux->poke_progs);
 	mutex_init(&aux->poke_mutex);
-	spin_lock_init(&aux->owner.lock);
 
 	map = array_map_alloc(attr);
 	if (IS_ERR(map)) {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 1ded3eb492b8..73a1c66e5417 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1832,31 +1832,74 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
 }
 #endif
 
-bool bpf_prog_array_compatible(struct bpf_array *array,
-			       const struct bpf_prog *fp)
+static bool __bpf_prog_map_compatible(struct bpf_map *map,
+				      const struct bpf_prog *fp)
 {
-	bool ret;
+	enum bpf_prog_type prog_type = fp->aux->dst_prog ? fp->aux->dst_prog->type : fp->type;
+	struct bpf_prog_aux *aux = fp->aux;
+	enum bpf_cgroup_storage_type i;
+	bool ret = false;
+	u64 cookie;
 
 	if (fp->kprobe_override)
-		return false;
-
-	spin_lock(&array->aux->owner.lock);
+		return ret;
 
-	if (!array->aux->owner.type) {
-		/* There's no owner yet where we could check for
-		 * compatibility.
-		 */
-		array->aux->owner.type  = fp->type;
-		array->aux->owner.jited = fp->jited;
+	spin_lock(&map->owner_lock);
+	/* There's no owner yet where we could check for compatibility. */
+	if (!map->owner) {
+		map->owner = bpf_map_owner_alloc(map);
+		if (!map->owner)
+			goto err;
+		map->owner->type  = prog_type;
+		map->owner->jited = fp->jited;
+		/* Note: xdp_has_frags doesn't exist in aux yet in our branch */
+		/* map->owner->xdp_has_frags = aux->xdp_has_frags; */
+		map->owner->attach_func_proto = aux->attach_func_proto;
+		for_each_cgroup_storage_type(i) {
+			map->owner->storage_cookie[i] =
+				aux->cgroup_storage[i] ?
+				aux->cgroup_storage[i]->cookie : 0;
+		}
 		ret = true;
 	} else {
-		ret = array->aux->owner.type  == fp->type &&
-		      array->aux->owner.jited == fp->jited;
+		ret = map->owner->type  == prog_type &&
+		      map->owner->jited == fp->jited;
+		/* Note: xdp_has_frags check would go here when available */
+		/* && map->owner->xdp_has_frags == aux->xdp_has_frags; */
+		for_each_cgroup_storage_type(i) {
+			if (!ret)
+				break;
+			cookie = aux->cgroup_storage[i] ?
+				 aux->cgroup_storage[i]->cookie : 0;
+			ret = map->owner->storage_cookie[i] == cookie ||
+			      !cookie;
+		}
+		if (ret &&
+		    map->owner->attach_func_proto != aux->attach_func_proto) {
+			switch (prog_type) {
+			case BPF_PROG_TYPE_TRACING:
+			case BPF_PROG_TYPE_LSM:
+			case BPF_PROG_TYPE_EXT:
+			case BPF_PROG_TYPE_STRUCT_OPS:
+				ret = false;
+				break;
+			default:
+				break;
+			}
+		}
 	}
-	spin_unlock(&array->aux->owner.lock);
+err:
+	spin_unlock(&map->owner_lock);
 	return ret;
 }
 
+bool bpf_prog_array_compatible(struct bpf_array *array,
+			       const struct bpf_prog *fp)
+{
+	struct bpf_map *map = &array->map;
+	return __bpf_prog_map_compatible(map, fp);
+}
+
 static int bpf_check_tail_call(const struct bpf_prog *fp)
 {
 	struct bpf_prog_aux *aux = fp->aux;
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 5a8d9f7467bf..849df8268af5 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -610,7 +610,7 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
-static void bpf_free_inode(struct inode *inode)
+static void bpf_destroy_inode(struct inode *inode)
 {
 	enum bpf_type type;
 
@@ -625,7 +625,7 @@ static const struct super_operations bpf_super_ops = {
 	.statfs		= simple_statfs,
 	.drop_inode	= generic_delete_inode,
 	.show_options	= bpf_show_options,
-	.free_inode	= bpf_free_inode,
+	.destroy_inode	= bpf_destroy_inode,
 };
 
 enum {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 6f309248f13f..b80d125dcea9 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -31,6 +31,7 @@
 #include <linux/bpf-netns.h>
 #include <linux/rcupdate_trace.h>
 #include <linux/memcontrol.h>
+#include <linux/cookie.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
@@ -43,6 +44,7 @@
 #define BPF_OBJ_FLAG_MASK   (BPF_F_RDONLY | BPF_F_WRONLY)
 
 DEFINE_PER_CPU(int, bpf_prog_active);
+DEFINE_COOKIE(bpf_map_cookie);
 static DEFINE_IDR(prog_idr);
 static DEFINE_SPINLOCK(prog_idr_lock);
 static DEFINE_IDR(map_idr);
@@ -475,6 +477,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
 
 	security_bpf_map_free(map);
 	bpf_map_release_memcg(map);
+	bpf_map_owner_free(map);
 	/* implementation dependent freeing */
 	map->ops->map_free(map);
 }
@@ -574,17 +577,15 @@ static unsigned long bpf_map_memory_footprint(const struct bpf_map *map)
 
 static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 {
-	const struct bpf_map *map = filp->private_data;
-	const struct bpf_array *array;
+	struct bpf_map *map = filp->private_data;
 	u32 type = 0, jited = 0;
 
-	if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
-		array = container_of(map, struct bpf_array, map);
-		spin_lock(&array->aux->owner.lock);
-		type  = array->aux->owner.type;
-		jited = array->aux->owner.jited;
-		spin_unlock(&array->aux->owner.lock);
+	spin_lock(&map->owner_lock);
+	if (map->owner) {
+		type  = map->owner->type;
+		jited = map->owner->jited;
 	}
+	spin_unlock(&map->owner_lock);
 
 	seq_printf(m,
 		   "map_type:\t%u\n"
@@ -886,9 +887,14 @@ static int map_create(union bpf_attr *attr)
 	if (err < 0)
 		goto free_map;
 
+	preempt_disable();
+	map->cookie = gen_cookie_next(&bpf_map_cookie);
+	preempt_enable();
+
 	atomic64_set(&map->refcnt, 1);
 	atomic64_set(&map->usercnt, 1);
 	mutex_init(&map->freeze_mutex);
+	spin_lock_init(&map->owner_lock);
 
 	map->spin_lock_off = -EINVAL;
 	map->timer_off = -EINVAL;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 89b4fa815a9b..4b7c9a60a735 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5071,6 +5071,10 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno,
 		verbose(env, "verifier bug. Two map pointers in a timer helper\n");
 		return -EFAULT;
 	}
+	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+		verbose(env, "bpf_timer cannot be used for PREEMPT_RT.\n");
+		return -EOPNOTSUPP;
+	}
 	meta->map_uid = reg->map_uid;
 	meta->map_ptr = map;
 	return 0;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 1a3b2e1436db..e5fe4ffff7cd 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -122,8 +122,31 @@ DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem);
  * of concurrent destructions.  Use a separate workqueue so that cgroup
  * destruction work items don't end up filling up max_active of system_wq
  * which may lead to deadlock.
+ *
+ * A cgroup destruction should enqueue work sequentially to:
+ * cgroup_offline_wq: use for css offline work
+ * cgroup_release_wq: use for css release work
+ * cgroup_free_wq: use for free work
+ *
+ * Rationale for using separate workqueues:
+ * The cgroup root free work may depend on completion of other css offline
+ * operations. If all tasks were enqueued to a single workqueue, this could
+ * create a deadlock scenario where:
+ * - Free work waits for other css offline work to complete.
+ * - But other css offline work is queued after free work in the same queue.
+ *
+ * Example deadlock scenario with single workqueue (cgroup_destroy_wq):
+ * 1. umount net_prio
+ * 2. net_prio root destruction enqueues work to cgroup_destroy_wq (CPUx)
+ * 3. perf_event CSS A offline enqueues work to same cgroup_destroy_wq (CPUx)
+ * 4. net_prio cgroup_destroy_root->cgroup_lock_and_drain_offline.
+ * 5. net_prio root destruction blocks waiting for perf_event CSS A offline,
+ *    which can never complete as it's behind in the same queue and
+ *    workqueue's max_active is 1.
  */
-static struct workqueue_struct *cgroup_destroy_wq;
+static struct workqueue_struct *cgroup_offline_wq;
+static struct workqueue_struct *cgroup_release_wq;
+static struct workqueue_struct *cgroup_free_wq;
 
 /* generate an array of cgroup subsystem pointers */
 #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,
@@ -5263,7 +5286,7 @@ static void css_release_work_fn(struct work_struct *work)
 	mutex_unlock(&cgroup_mutex);
 
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
-	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
+	queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);
 }
 
 static void css_release(struct percpu_ref *ref)
@@ -5272,7 +5295,7 @@ static void css_release(struct percpu_ref *ref)
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
 	INIT_WORK(&css->destroy_work, css_release_work_fn);
-	queue_work(cgroup_destroy_wq, &css->destroy_work);
+	queue_work(cgroup_release_wq, &css->destroy_work);
 }
 
 static void init_and_link_css(struct cgroup_subsys_state *css,
@@ -5394,7 +5417,7 @@ err_list_del:
 err_free_css:
 	list_del_rcu(&css->rstat_css_node);
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
-	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
+	queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);
 	return ERR_PTR(err);
 }
 
@@ -5631,7 +5654,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
 
 	if (atomic_dec_and_test(&css->online_cnt)) {
 		INIT_WORK(&css->destroy_work, css_killed_work_fn);
-		queue_work(cgroup_destroy_wq, &css->destroy_work);
+		queue_work(cgroup_offline_wq, &css->destroy_work);
 	}
 }
 
@@ -6008,8 +6031,14 @@ static int __init cgroup_wq_init(void)
 	 * We would prefer to do this in cgroup_init() above, but that
 	 * is called before init_workqueues(): so leave this until after.
 	 */
-	cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
-	BUG_ON(!cgroup_destroy_wq);
+	cgroup_offline_wq = alloc_workqueue("cgroup_offline", 0, 1);
+	BUG_ON(!cgroup_offline_wq);
+
+	cgroup_release_wq = alloc_workqueue("cgroup_release", 0, 1);
+	BUG_ON(!cgroup_release_wq);
+
+	cgroup_free_wq = alloc_workqueue("cgroup_free", 0, 1);
+	BUG_ON(!cgroup_free_wq);
 	return 0;
 }
 core_initcall(cgroup_wq_init);
diff --git a/kernel/fork.c b/kernel/fork.c
index 2fd9c431bf45..2c99d39e2bc0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1595,7 +1595,7 @@ static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
 	return 0;
 }
 
-static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
+static int copy_sighand(u64 clone_flags, struct task_struct *tsk)
 {
 	struct sighand_struct *sig;
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index b46fbfbb929f..ce0433446a8e 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -501,7 +501,8 @@ int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
 }
 EXPORT_SYMBOL_GPL(irq_force_affinity);
 
-int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
+int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m,
+			      bool setaffinity)
 {
 	unsigned long flags;
 	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
@@ -510,12 +511,11 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
 		return -EINVAL;
 	desc->affinity_hint = m;
 	irq_put_desc_unlock(desc, flags);
-	/* set the initial affinity to prevent every interrupt being on CPU0 */
-	if (m)
+	if (m && setaffinity)
 		__irq_set_affinity(irq, m, false);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
+EXPORT_SYMBOL_GPL(__irq_apply_affinity_hint);
 
 static void irq_affinity_notify(struct work_struct *work)
 {
diff --git a/kernel/padata.c b/kernel/padata.c
index b443e19e64cf..5453f5750906 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -282,7 +282,11 @@ static struct padata_priv *padata_find_next(struct parallel_data *pd,
 	if (remove_object) {
 		list_del_init(&padata->list);
 		++pd->processed;
-		pd->cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu, -1, false);
+		/* When sequence wraps around, reset to the first CPU. */
+		if (unlikely(pd->processed == 0))
+			pd->cpu = cpumask_first(pd->cpumask.pcpu);
+		else
+			pd->cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu, -1, false);
 	}
 
 	spin_unlock(&reorder->lock);
diff --git a/kernel/pid.c b/kernel/pid.c
index efe87db44683..61f6649568b2 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -474,7 +474,7 @@ pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns)
 	struct upid *upid;
 	pid_t nr = 0;
 
-	if (pid && ns->level <= pid->level) {
+	if (pid && ns && ns->level <= pid->level) {
 		upid = &pid->numbers[ns->level];
 		if (upid->ns == ns)
 			nr = upid->nr;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 519f742d44f4..954a85b8c275 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -89,9 +89,20 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 	if (!cpufreq_this_cpu_can_update(sg_policy->policy))
 		return false;
 
-	if (unlikely(sg_policy->limits_changed)) {
-		sg_policy->limits_changed = false;
+	if (unlikely(READ_ONCE(sg_policy->limits_changed))) {
+		WRITE_ONCE(sg_policy->limits_changed, false);
 		sg_policy->need_freq_update = true;
+
+		/*
+		 * The above limits_changed update must occur before the reads
+		 * of policy limits in cpufreq_driver_resolve_freq() or a policy
+		 * limits update might be missed, so use a memory barrier to
+		 * ensure it.
+		 *
+		 * This pairs with the write memory barrier in sugov_limits().
+		 */
+		smp_mb();
+
 		return true;
 	}
 
@@ -326,7 +337,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
 {
 	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
-		sg_cpu->sg_policy->limits_changed = true;
+		WRITE_ONCE(sg_cpu->sg_policy->limits_changed, true);
 }
 
 static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
@@ -826,7 +837,16 @@ static void sugov_limits(struct cpufreq_policy *policy)
 		mutex_unlock(&sg_policy->work_lock);
 	}
 
-	sg_policy->limits_changed = true;
+	/*
+	 * The limits_changed update below must take place before the updates
+	 * of policy limits in cpufreq_set_policy() or a policy limits update
+	 * might be missed, so use a memory barrier to ensure it.
+	 *
+	 * This pairs with the memory barrier in sugov_should_update_freq().
+	 */
+	smp_wmb();
+
+	WRITE_ONCE(sg_policy->limits_changed, true);
 }
 
 struct cpufreq_governor schedutil_gov = {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ea707ee9ddac..87f32cf8aa02 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3959,7 +3959,7 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
 	return cfs_rq->avg.load_avg;
 }
 
-static int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
+static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf);
 
 static inline unsigned long task_util(struct task_struct *p)
 {
@@ -4291,7 +4291,7 @@ attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void
 detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 
-static inline int newidle_balance(struct rq *rq, struct rq_flags *rf)
+static inline int sched_balance_newidle(struct rq *rq, struct rq_flags *rf)
 {
 	return 0;
 }
@@ -7280,7 +7280,7 @@ balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	if (rq->nr_running)
 		return 1;
 
-	return newidle_balance(rq, rf) != 0;
+	return sched_balance_newidle(rq, rf) != 0;
 }
 #endif /* CONFIG_SMP */
 
@@ -7613,21 +7613,21 @@ done: __maybe_unused;
 	return p;
 
 idle:
-	if (!rf)
-		return NULL;
-
-	new_tasks = newidle_balance(rq, rf);
+	if (rf) {
+		new_tasks = sched_balance_newidle(rq, rf);
 
-	/*
-	 * Because newidle_balance() releases (and re-acquires) rq->lock, it is
-	 * possible for any higher priority task to appear. In that case we
-	 * must re-start the pick_next_entity() loop.
-	 */
-	if (new_tasks < 0)
-		return RETRY_TASK;
+		/*
+		 * Because sched_balance_newidle() releases (and re-acquires)
+		 * rq->lock, it is possible for any higher priority task to
+		 * appear. In that case we must re-start the pick_next_entity()
+		 * loop.
+		 */
+		if (new_tasks < 0)
+			return RETRY_TASK;
 
-	if (new_tasks > 0)
-		goto again;
+		if (new_tasks > 0)
+			goto again;
+	}
 
 	/*
 	 * rq is about to be idle, check if we need to update the
@@ -10427,7 +10427,7 @@ out_one_pinned:
 	ld_moved = 0;
 
 	/*
-	 * newidle_balance() disregards balance intervals, so we could
+	 * sched_balance_newidle() disregards balance intervals, so we could
 	 * repeatedly reach this code, which would lead to balance_interval
 	 * skyrocketing in a short amount of time. Skip the balance_interval
 	 * increase logic to avoid that.
@@ -11155,7 +11155,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
 /*
- * newidle_balance is called by schedule() if this_cpu is about to become
+ * sched_balance_newidle is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  *
  * Returns:
@@ -11163,7 +11163,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { }
  *     0 - failed, no new tasks
  *   > 0 - success, new (fair) tasks present
  */
-static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
+static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 {
 	unsigned long next_balance = jiffies + HZ;
 	int this_cpu = this_rq->cpu;
diff --git a/kernel/smp.c b/kernel/smp.c
index b60525b34ab0..387df30ca560 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -976,16 +976,15 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
  * @mask: The set of cpus to run on (only runs on online subset).
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
- * @wait: Bitmask that controls the operation. If %SCF_WAIT is set, wait
- *        (atomically) until function has completed on other CPUs. If
- *        %SCF_RUN_LOCAL is set, the function will also be run locally
- *        if the local CPU is set in the @cpumask.
- *
- * If @wait is true, then returns once @func has returned.
+ * @wait: If true, wait (atomically) until function has completed
+ *        on other CPUs.
  *
  * You must not call this function with disabled interrupts or from a
  * hardware interrupt handler or from a bottom half handler. Preemption
  * must be disabled when calling this function.
+ *
+ * @func is not called on the local CPU even if @mask contains it.  Consider
+ * using on_each_cpu_cond_mask() instead if this is not desirable.
  */
 void smp_call_function_many(const struct cpumask *mask,
 			    smp_call_func_t func, void *info, bool wait)
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 2e4b63f3c6dd..7e2ed34e9803 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -631,17 +631,12 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
 /*
  * Is the high resolution mode active ?
  */
-static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
+static inline int hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
 {
 	return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ?
 		cpu_base->hres_active : 0;
 }
 
-static inline int hrtimer_hres_active(void)
-{
-	return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases));
-}
-
 static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base,
 				struct hrtimer *next_timer,
 				ktime_t expires_next)
@@ -665,7 +660,7 @@ static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base,
 	 * set. So we'd effectively block all timers until the T2 event
 	 * fires.
 	 */
-	if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
+	if (!hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
 		return;
 
 	tick_program_event(expires_next, 1);
@@ -775,13 +770,13 @@ static void retrigger_next_event(void *arg)
 	 * of the next expiring timer is enough. The return from the SMP
 	 * function call will take care of the reprogramming in case the
 	 * CPU was in a NOHZ idle sleep.
+	 *
+	 * In periodic low resolution mode, the next softirq expiration
+	 * must also be updated.
 	 */
-	if (!__hrtimer_hres_active(base) && !tick_nohz_active)
-		return;
-
 	raw_spin_lock(&base->lock);
 	hrtimer_update_base(base);
-	if (__hrtimer_hres_active(base))
+	if (hrtimer_hres_active(base))
 		hrtimer_force_reprogram(base, 0);
 	else
 		hrtimer_update_next_event(base);
@@ -938,7 +933,7 @@ void clock_was_set(unsigned int bases)
 	cpumask_var_t mask;
 	int cpu;
 
-	if (!__hrtimer_hres_active(cpu_base) && !tick_nohz_active)
+	if (!hrtimer_hres_active(cpu_base) && !tick_nohz_active)
 		goto out_timerfd;
 
 	if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
@@ -1489,7 +1484,7 @@ u64 hrtimer_get_next_event(void)
 
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
-	if (!__hrtimer_hres_active(cpu_base))
+	if (!hrtimer_hres_active(cpu_base))
 		expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
 
 	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
@@ -1512,7 +1507,7 @@ u64 hrtimer_next_event_without(const struct hrtimer *exclude)
 
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
-	if (__hrtimer_hres_active(cpu_base)) {
+	if (hrtimer_hres_active(cpu_base)) {
 		unsigned int active;
 
 		if (!cpu_base->softirq_activated) {
@@ -1873,25 +1868,7 @@ retry:
 	tick_program_event(expires_next, 1);
 	pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta));
 }
-
-/* called with interrupts disabled */
-static inline void __hrtimer_peek_ahead_timers(void)
-{
-	struct tick_device *td;
-
-	if (!hrtimer_hres_active())
-		return;
-
-	td = this_cpu_ptr(&tick_cpu_device);
-	if (td && td->evtdev)
-		hrtimer_interrupt(td->evtdev);
-}
-
-#else /* CONFIG_HIGH_RES_TIMERS */
-
-static inline void __hrtimer_peek_ahead_timers(void) { }
-
-#endif	/* !CONFIG_HIGH_RES_TIMERS */
+#endif /* !CONFIG_HIGH_RES_TIMERS */
 
 /*
  * Called from run_local_timers in hardirq context every jiffy
@@ -1902,7 +1879,7 @@ void hrtimer_run_queues(void)
 	unsigned long flags;
 	ktime_t now;
 
-	if (__hrtimer_hres_active(cpu_base))
+	if (hrtimer_hres_active(cpu_base))
 		return;
 
 	/*
@@ -2252,11 +2229,6 @@ int hrtimers_cpu_dying(unsigned int dying_cpu)
 				     &new_base->clock_base[i]);
 	}
 
-	/*
-	 * The migration might have changed the first expiring softirq
-	 * timer on this CPU. Update it.
-	 */
-	__hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT);
 	/* Tell the other CPU to retrigger the next event */
 	smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
 
diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c
index 8af92dbe98f0..acb0c971a408 100644
--- a/kernel/trace/preemptirq_delay_test.c
+++ b/kernel/trace/preemptirq_delay_test.c
@@ -34,8 +34,6 @@ MODULE_PARM_DESC(cpu_affinity, "Cpu num test is running on");
 
 static struct completion done;
 
-#define MIN(x, y) ((x) < (y) ? (x) : (y))
-
 static void busy_wait(ulong time)
 {
 	u64 start, end;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7af8bbc57531..a6040a707abb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7233,7 +7233,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	entry = ring_buffer_event_data(event);
 	entry->ip = _THIS_IP_;
 
-	len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt);
+	len = copy_from_user_nofault(&entry->buf, ubuf, cnt);
 	if (len) {
 		memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE);
 		cnt = FAULTED_SIZE;
@@ -7308,7 +7308,7 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 
 	entry = ring_buffer_event_data(event);
 
-	len = __copy_from_user_inatomic(&entry->id, ubuf, cnt);
+	len = copy_from_user_nofault(&entry->id, ubuf, cnt);
 	if (len) {
 		entry->id = -1;
 		memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE);
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index 6d0e9f869ad6..3d8ffa81a1fa 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -239,6 +239,10 @@ static int dyn_event_open(struct inode *inode, struct file *file)
 {
 	int ret;
 
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	ret = tracing_check_open_get_tr(NULL);
 	if (ret)
 		return ret;
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index ab54810bd8d9..62d146254f47 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -364,13 +364,11 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
 				str_field = (char *)entry + data_offset;
 
 				trace_seq_printf(s, print_fmt, se->fields[i]->name,
-						 STR_VAR_LEN_MAX,
 						 str_field,
 						 i == se->n_fields - 1 ? "" : " ");
 				n_u64++;
 			} else {
 				trace_seq_printf(s, print_fmt, se->fields[i]->name,
-						 STR_VAR_LEN_MAX,
 						 (char *)&entry->fields[n_u64],
 						 i == se->n_fields - 1 ? "" : " ");
 				n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index e062f4efec8d..03d4ac41d903 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1722,14 +1722,15 @@ static int kprobe_register(struct trace_event_call *event,
 static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 {
 	struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);
+	unsigned int flags = trace_probe_load_flag(&tk->tp);
 	int ret = 0;
 
 	raw_cpu_inc(*tk->nhit);
 
-	if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE))
+	if (flags & TP_FLAG_TRACE)
 		kprobe_trace_func(tk, regs);
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tk->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		ret = kprobe_perf_func(tk, regs);
 #endif
 	return ret;
@@ -1741,6 +1742,7 @@ kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	struct kretprobe *rp = get_kretprobe(ri);
 	struct trace_kprobe *tk;
+	unsigned int flags;
 
 	/*
 	 * There is a small chance that get_kretprobe(ri) returns NULL when
@@ -1753,10 +1755,11 @@ kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 	tk = container_of(rp, struct trace_kprobe, rp);
 	raw_cpu_inc(*tk->nhit);
 
-	if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE))
+	flags = trace_probe_load_flag(&tk->tp);
+	if (flags & TP_FLAG_TRACE)
 		kretprobe_trace_func(tk, ri, regs);
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tk->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		kretprobe_perf_func(tk, ri, regs);
 #endif
 	return 0;	/* We don't tweak kernel, so just return 0 */
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 82e1df8aefcb..b08aa3946868 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -258,16 +258,21 @@ struct event_file_link {
 	struct list_head		list;
 };
 
+static inline unsigned int trace_probe_load_flag(struct trace_probe *tp)
+{
+	return smp_load_acquire(&tp->event->flags);
+}
+
 static inline bool trace_probe_test_flag(struct trace_probe *tp,
 					 unsigned int flag)
 {
-	return !!(tp->event->flags & flag);
+	return !!(trace_probe_load_flag(tp) & flag);
 }
 
 static inline void trace_probe_set_flag(struct trace_probe *tp,
 					unsigned int flag)
 {
-	tp->event->flags |= flag;
+	smp_store_release(&tp->event->flags, tp->event->flags | flag);
 }
 
 static inline void trace_probe_clear_flag(struct trace_probe *tp,
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 322d56661d04..707c5373476a 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1485,6 +1485,7 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 	struct uprobe_dispatch_data udd;
 	struct uprobe_cpu_buffer *ucb;
 	int dsize, esize;
+	unsigned int flags;
 	int ret = 0;
 
 
@@ -1505,11 +1506,12 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 	ucb = uprobe_buffer_get();
 	store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize);
 
-	if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE))
+	flags = trace_probe_load_flag(&tu->tp);
+	if (flags & TP_FLAG_TRACE)
 		ret |= uprobe_trace_func(tu, regs, ucb, dsize);
 
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		ret |= uprobe_perf_func(tu, regs, ucb, dsize);
 #endif
 	uprobe_buffer_put(ucb);
@@ -1523,6 +1525,7 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con,
 	struct uprobe_dispatch_data udd;
 	struct uprobe_cpu_buffer *ucb;
 	int dsize, esize;
+	unsigned int flags;
 
 	tu = container_of(con, struct trace_uprobe, consumer);
 
@@ -1540,11 +1543,12 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con,
 	ucb = uprobe_buffer_get();
 	store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize);
 
-	if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE))
+	flags = trace_probe_load_flag(&tu->tp);
+	if (flags & TP_FLAG_TRACE)
 		uretprobe_trace_func(tu, func, regs, ucb, dsize);
 
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		uretprobe_perf_func(tu, func, regs, ucb, dsize);
 #endif
 	uprobe_buffer_put(ucb);