Merging upstream version 6.10.6.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

26 files changed, 193 insertions, 128 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6b422c275f..a8845cc299 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7716,6 +7716,13 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
 	int err;
 
+	if (reg->type != PTR_TO_STACK && reg->type != CONST_PTR_TO_DYNPTR) {
+		verbose(env,
+			"arg#%d expected pointer to stack or const struct bpf_dynptr\n",
+			regno);
+		return -EINVAL;
+	}
+
 	/* MEM_UNINIT and MEM_RDONLY are exclusive, when applied to an
 	 * ARG_PTR_TO_DYNPTR (or ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_*):
 	 */
@@ -9465,6 +9472,10 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
 				return -EINVAL;
 			}
 		} else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) {
+			ret = check_func_arg_reg_off(env, reg, regno, ARG_PTR_TO_DYNPTR);
+			if (ret)
+				return ret;
+
 			ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0);
 			if (ret)
 				return ret;
@@ -11958,12 +11969,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			enum bpf_arg_type dynptr_arg_type = ARG_PTR_TO_DYNPTR;
 			int clone_ref_obj_id = 0;
 
-			if (reg->type != PTR_TO_STACK &&
-			    reg->type != CONST_PTR_TO_DYNPTR) {
-				verbose(env, "arg#%d expected pointer to stack or dynptr_ptr\n", i);
-				return -EINVAL;
-			}
-
 			if (reg->type == CONST_PTR_TO_DYNPTR)
 				dynptr_arg_type |= MEM_RDONLY;
 
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 07e99c936b..1dee88ba0a 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -530,6 +530,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 				flags = IRQD_AFFINITY_MANAGED |
 					IRQD_MANAGED_SHUTDOWN;
 			}
+			flags |= IRQD_AFFINITY_SET;
 			mask = &affinity->mask;
 			node = cpu_to_node(cpumask_first(mask));
 			affinity++;
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 1f05a19918..c6ac0d0377 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -231,7 +231,7 @@ void static_key_disable_cpuslocked(struct static_key *key)
 	}
 
 	jump_label_lock();
-	if (atomic_cmpxchg(&key->enabled, 1, 0))
+	if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
 		jump_label_update(key);
 	jump_label_unlock();
 }
@@ -284,7 +284,7 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key)
 		return;
 
 	guard(mutex)(&jump_label_mutex);
-	if (atomic_cmpxchg(&key->enabled, 1, 0))
+	if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
 		jump_label_update(key);
 	else
 		WARN_ON_ONCE(!static_key_slow_try_dec(key));
diff --git a/kernel/kcov.c b/kernel/kcov.c
index f0a69d4020..274b6b7c71 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -161,6 +161,15 @@ static void kcov_remote_area_put(struct kcov_remote_area *area,
 	kmsan_unpoison_memory(&area->list, sizeof(area->list));
 }
 
+/*
+ * Unlike in_serving_softirq(), this function returns false when called during
+ * a hardirq or an NMI that happened in the softirq context.
+ */
+static inline bool in_softirq_really(void)
+{
+	return in_serving_softirq() && !in_hardirq() && !in_nmi();
+}
+
 static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
 {
 	unsigned int mode;
@@ -170,7 +179,7 @@ static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_stru
 	 * so we ignore code executed in interrupts, unless we are in a remote
 	 * coverage collection section in a softirq.
 	 */
-	if (!in_task() && !(in_serving_softirq() && t->kcov_softirq))
+	if (!in_task() && !(in_softirq_really() && t->kcov_softirq))
 		return false;
 	mode = READ_ONCE(t->kcov_mode);
 	/*
@@ -849,7 +858,7 @@ void kcov_remote_start(u64 handle)
 
 	if (WARN_ON(!kcov_check_handle(handle, true, true, true)))
 		return;
-	if (!in_task() && !in_serving_softirq())
+	if (!in_task() && !in_softirq_really())
 		return;
 
 	local_lock_irqsave(&kcov_percpu_data.lock, flags);
@@ -991,7 +1000,7 @@ void kcov_remote_stop(void)
 	int sequence;
 	unsigned long flags;
 
-	if (!in_task() && !in_serving_softirq())
+	if (!in_task() && !in_softirq_really())
 		return;
 
 	local_lock_irqsave(&kcov_percpu_data.lock, flags);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 6a76a81000..85251c254d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1557,8 +1557,8 @@ static bool is_cfi_preamble_symbol(unsigned long addr)
 	if (lookup_symbol_name(addr, symbuf))
 		return false;
 
-	return str_has_prefix("__cfi_", symbuf) ||
-		str_has_prefix("__pfx_", symbuf);
+	return str_has_prefix(symbuf, "__cfi_") ||
+		str_has_prefix(symbuf, "__pfx_");
 }
 
 static int check_kprobe_address_safe(struct kprobe *p,
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index f5a36e67b5..ac2e225027 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -357,7 +357,7 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 {
 	struct pv_node *pn = (struct pv_node *)node;
-	enum vcpu_state old = vcpu_halted;
+	u8 old = vcpu_halted;
 	/*
 	 * If the vCPU is indeed halted, advance its state to match that of
 	 * pv_wait_node(). If OTOH this fails, the vCPU was running and will
diff --git a/kernel/module/main.c b/kernel/module/main.c
index d18a94b973..3f9da53702 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -3101,7 +3101,7 @@ static bool idempotent(struct idempotent *u, const void *cookie)
 	struct idempotent *existing;
 	bool first;
 
-	u->ret = 0;
+	u->ret = -EINTR;
 	u->cookie = cookie;
 	init_completion(&u->complete);
 
@@ -3137,7 +3137,7 @@ static int idempotent_complete(struct idempotent *u, int ret)
 	hlist_for_each_entry_safe(pos, next, head, entry) {
 		if (pos->cookie != cookie)
 			continue;
-		hlist_del(&pos->entry);
+		hlist_del_init(&pos->entry);
 		pos->ret = ret;
 		complete(&pos->complete);
 	}
@@ -3145,6 +3145,28 @@ static int idempotent_complete(struct idempotent *u, int ret)
 	return ret;
 }
 
+/*
+ * Wait for the idempotent worker.
+ *
+ * If we get interrupted, we need to remove ourselves from the
+ * the idempotent list, and the completion may still come in.
+ *
+ * The 'idem_lock' protects against the race, and 'idem.ret' was
+ * initialized to -EINTR and is thus always the right return
+ * value even if the idempotent work then completes between
+ * the wait_for_completion and the cleanup.
+ */
+static int idempotent_wait_for_completion(struct idempotent *u)
+{
+	if (wait_for_completion_interruptible(&u->complete)) {
+		spin_lock(&idem_lock);
+		if (!hlist_unhashed(&u->entry))
+			hlist_del(&u->entry);
+		spin_unlock(&idem_lock);
+	}
+	return u->ret;
+}
+
 static int init_module_from_file(struct file *f, const char __user * uargs, int flags)
 {
 	struct load_info info = { };
@@ -3180,15 +3202,16 @@ static int idempotent_init_module(struct file *f, const char __user * uargs, int
 	if (!f || !(f->f_mode & FMODE_READ))
 		return -EBADF;
 
-	/* See if somebody else is doing the operation? */
-	if (idempotent(&idem, file_inode(f))) {
-		wait_for_completion(&idem.complete);
-		return idem.ret;
+	/* Are we the winners of the race and get to do this? */
+	if (!idempotent(&idem, file_inode(f))) {
+		int ret = init_module_from_file(f, uargs, flags);
+		return idempotent_complete(&idem, ret);
 	}
 
-	/* Otherwise, we'll do it and complete others */
-	return idempotent_complete(&idem,
-		init_module_from_file(f, uargs, flags));
+	/*
+	 * Somebody else won the race and is loading the module.
+	 */
+	return idempotent_wait_for_completion(&idem);
 }
 
 SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
diff --git a/kernel/padata.c b/kernel/padata.c
index 53f4bc9127..0fa6c28954 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -517,6 +517,13 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
 	ps.chunk_size = max(ps.chunk_size, job->min_chunk);
 	ps.chunk_size = roundup(ps.chunk_size, job->align);
 
+	/*
+	 * chunk_size can be 0 if the caller sets min_chunk to 0. So force it
+	 * to at least 1 to prevent divide-by-0 panic in padata_mt_helper().`
+	 */
+	if (!ps.chunk_size)
+		ps.chunk_size = 1U;
+
 	list_for_each_entry(pw, &works, pw_list)
 		if (job->numa_aware) {
 			int old_node = atomic_read(&last_used_nid);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 25f3cf679b..bdf0087d64 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -249,24 +249,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (pid_ns->pid_allocated == init_pids)
 			break;
-		/*
-		 * Release tasks_rcu_exit_srcu to avoid following deadlock:
-		 *
-		 * 1) TASK A unshare(CLONE_NEWPID)
-		 * 2) TASK A fork() twice -> TASK B (child reaper for new ns)
-		 *    and TASK C
-		 * 3) TASK B exits, kills TASK C, waits for TASK A to reap it
-		 * 4) TASK A calls synchronize_rcu_tasks()
-		 *                   -> synchronize_srcu(tasks_rcu_exit_srcu)
-		 * 5) *DEADLOCK*
-		 *
-		 * It is considered safe to release tasks_rcu_exit_srcu here
-		 * because we assume the current task can not be concurrently
-		 * reaped at this point.
-		 */
-		exit_tasks_rcu_stop();
 		schedule();
-		exit_tasks_rcu_start();
 	}
 	__set_current_state(TASK_RUNNING);
 
diff --git a/kernel/profile.c b/kernel/profile.c
index 2b775cc5c2..f2bb82c69f 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -57,20 +57,11 @@ static DEFINE_MUTEX(profile_flip_mutex);
 int profile_setup(char *str)
 {
 	static const char schedstr[] = "schedule";
-	static const char sleepstr[] = "sleep";
 	static const char kvmstr[] = "kvm";
 	const char *select = NULL;
 	int par;
 
-	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
-#ifdef CONFIG_SCHEDSTATS
-		force_schedstat_enabled();
-		prof_on = SLEEP_PROFILING;
-		select = sleepstr;
-#else
-		pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
-#endif /* CONFIG_SCHEDSTATS */
-	} else if (!strncmp(str, schedstr, strlen(schedstr))) {
+	if (!strncmp(str, schedstr, strlen(schedstr))) {
 		prof_on = SCHED_PROFILING;
 		select = schedstr;
 	} else if (!strncmp(str, kvmstr, strlen(kvmstr))) {
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 807fbf6123..251cead744 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -2626,7 +2626,7 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
 	spin_lock_irqsave(&rfp->rcu_fwd_lock, flags);
 	rfcpp = rfp->rcu_fwd_cb_tail;
 	rfp->rcu_fwd_cb_tail = &rfcp->rfc_next;
-	WRITE_ONCE(*rfcpp, rfcp);
+	smp_store_release(rfcpp, rfcp);
 	WRITE_ONCE(rfp->n_launders_cb, rfp->n_launders_cb + 1);
 	i = ((jiffies - rfp->rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV));
 	if (i >= ARRAY_SIZE(rfp->n_launders_hist))
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 098e82bcc4..ba3440a45b 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -858,7 +858,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 //	not know to synchronize with this RCU Tasks grace period) have
 //	completed exiting.  The synchronize_rcu() in rcu_tasks_postgp()
 //	will take care of any tasks stuck in the non-preemptible region
-//	of do_exit() following its call to exit_tasks_rcu_stop().
+//	of do_exit() following its call to exit_tasks_rcu_finish().
 // check_all_holdout_tasks(), repeatedly until holdout list is empty:
 //	Scans the holdout list, attempting to identify a quiescent state
 //	for each task on the list.  If there is a quiescent state, the
@@ -1220,7 +1220,7 @@ void exit_tasks_rcu_start(void)
  * Remove the task from the "yet another list" because do_exit() is now
  * non-preemptible, allowing synchronize_rcu() to wait beyond this point.
  */
-void exit_tasks_rcu_stop(void)
+void exit_tasks_rcu_finish(void)
 {
 	unsigned long flags;
 	struct rcu_tasks_percpu *rtpcp;
@@ -1231,22 +1231,12 @@ void exit_tasks_rcu_stop(void)
 	raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
 	list_del_init(&t->rcu_tasks_exit_list);
 	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
-}
 
-/*
- * Contribute to protect against tasklist scan blind spot while the
- * task is exiting and may be removed from the tasklist. See
- * corresponding synchronize_srcu() for further details.
- */
-void exit_tasks_rcu_finish(void)
-{
-	exit_tasks_rcu_stop();
-	exit_tasks_rcu_finish_trace(current);
+	exit_tasks_rcu_finish_trace(t);
 }
 
 #else /* #ifdef CONFIG_TASKS_RCU */
 void exit_tasks_rcu_start(void) { }
-void exit_tasks_rcu_stop(void) { }
 void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 28c7031711..63fb007bee 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -5110,11 +5110,15 @@ void rcutree_migrate_callbacks(int cpu)
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	bool needwake;
 
-	if (rcu_rdp_is_offloaded(rdp) ||
-	    rcu_segcblist_empty(&rdp->cblist))
-		return;  /* No callbacks to migrate. */
+	if (rcu_rdp_is_offloaded(rdp))
+		return;
 
 	raw_spin_lock_irqsave(&rcu_state.barrier_lock, flags);
+	if (rcu_segcblist_empty(&rdp->cblist)) {
+		raw_spin_unlock_irqrestore(&rcu_state.barrier_lock, flags);
+		return;  /* No callbacks to migrate. */
+	}
+
 	WARN_ON_ONCE(rcu_rdp_cpu_online(rdp));
 	rcu_barrier_entrain(rdp);
 	my_rdp = this_cpu_ptr(&rcu_data);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ebf21373f6..3e84a3b7b7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9604,6 +9604,30 @@ void set_rq_offline(struct rq *rq)
 	}
 }
 
+static inline void sched_set_rq_online(struct rq *rq, int cpu)
+{
+	struct rq_flags rf;
+
+	rq_lock_irqsave(rq, &rf);
+	if (rq->rd) {
+		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+		set_rq_online(rq);
+	}
+	rq_unlock_irqrestore(rq, &rf);
+}
+
+static inline void sched_set_rq_offline(struct rq *rq, int cpu)
+{
+	struct rq_flags rf;
+
+	rq_lock_irqsave(rq, &rf);
+	if (rq->rd) {
+		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+		set_rq_offline(rq);
+	}
+	rq_unlock_irqrestore(rq, &rf);
+}
+
 /*
  * used to mark begin/end of suspend/resume:
  */
@@ -9654,10 +9678,25 @@ static int cpuset_cpu_inactive(unsigned int cpu)
 	return 0;
 }
 
+static inline void sched_smt_present_inc(int cpu)
+{
+#ifdef CONFIG_SCHED_SMT
+	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+		static_branch_inc_cpuslocked(&sched_smt_present);
+#endif
+}
+
+static inline void sched_smt_present_dec(int cpu)
+{
+#ifdef CONFIG_SCHED_SMT
+	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+		static_branch_dec_cpuslocked(&sched_smt_present);
+#endif
+}
+
 int sched_cpu_activate(unsigned int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct rq_flags rf;
 
 	/*
 	 * Clear the balance_push callback and prepare to schedule
@@ -9665,13 +9704,10 @@ int sched_cpu_activate(unsigned int cpu)
 	 */
 	balance_push_set(cpu, false);
 
-#ifdef CONFIG_SCHED_SMT
 	/*
 	 * When going up, increment the number of cores with SMT present.
 	 */
-	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
-		static_branch_inc_cpuslocked(&sched_smt_present);
-#endif
+	sched_smt_present_inc(cpu);
 	set_cpu_active(cpu, true);
 
 	if (sched_smp_initialized) {
@@ -9689,12 +9725,7 @@ int sched_cpu_activate(unsigned int cpu)
 	 * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
 	 *    domains.
 	 */
-	rq_lock_irqsave(rq, &rf);
-	if (rq->rd) {
-		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
-		set_rq_online(rq);
-	}
-	rq_unlock_irqrestore(rq, &rf);
+	sched_set_rq_online(rq, cpu);
 
 	return 0;
 }
@@ -9702,7 +9733,6 @@ int sched_cpu_activate(unsigned int cpu)
 int sched_cpu_deactivate(unsigned int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct rq_flags rf;
 	int ret;
 
 	/*
@@ -9733,20 +9763,14 @@ int sched_cpu_deactivate(unsigned int cpu)
 	 */
 	synchronize_rcu();
 
-	rq_lock_irqsave(rq, &rf);
-	if (rq->rd) {
-		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
-		set_rq_offline(rq);
-	}
-	rq_unlock_irqrestore(rq, &rf);
+	sched_set_rq_offline(rq, cpu);
 
-#ifdef CONFIG_SCHED_SMT
 	/*
 	 * When going down, decrement the number of cores with SMT present.
 	 */
-	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
-		static_branch_dec_cpuslocked(&sched_smt_present);
+	sched_smt_present_dec(cpu);
 
+#ifdef CONFIG_SCHED_SMT
 	sched_core_cpu_deactivate(cpu);
 #endif
 
@@ -9756,6 +9780,8 @@ int sched_cpu_deactivate(unsigned int cpu)
 	sched_update_numa(cpu, false);
 	ret = cpuset_cpu_inactive(cpu);
 	if (ret) {
+		sched_smt_present_inc(cpu);
+		sched_set_rq_online(rq, cpu);
 		balance_push_set(cpu, false);
 		set_cpu_active(cpu, true);
 		sched_update_numa(cpu, true);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index aa48b2ec87..4feef0d4e4 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -582,6 +582,12 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
 	}
 
 	stime = mul_u64_u64_div_u64(stime, rtime, stime + utime);
+	/*
+	 * Because mul_u64_u64_div_u64() can approximate on some
+	 * achitectures; enforce the constraint that: a*b/(b+c) <= a.
+	 */
+	if (unlikely(stime > rtime))
+		stime = rtime;
 
 update:
 	/*
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 78e48f5426..eb0cdcd4d9 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -92,16 +92,6 @@ void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
 
 			trace_sched_stat_blocked(p, delta);
 
-			/*
-			 * Blocking time is in units of nanosecs, so shift by
-			 * 20 to get a milliseconds-range estimation of the
-			 * amount of time that the task spent sleeping:
-			 */
-			if (unlikely(prof_on == SLEEP_PROFILING)) {
-				profile_hits(SLEEP_PROFILING,
-					     (void *)get_wchan(p),
-					     delta >> 20);
-			}
 			account_scheduler_latency(p, delta >> 10, 0);
 		}
 	}
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index d25ba49e31..d0538a75f4 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -246,7 +246,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow,
 
 		wd_delay = cycles_to_nsec_safe(watchdog, *wdnow, wd_end);
 		if (wd_delay <= WATCHDOG_MAX_SKEW) {
-			if (nretries > 1 || nretries >= max_retries) {
+			if (nretries > 1 && nretries >= max_retries) {
 				pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n",
 					smp_processor_id(), watchdog->name, nretries);
 			}
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 406dccb79c..8d2dd214ec 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -727,17 +727,16 @@ static inline void process_adjtimex_modes(const struct __kernel_timex *txc,
 	}
 
 	if (txc->modes & ADJ_MAXERROR)
-		time_maxerror = txc->maxerror;
+		time_maxerror = clamp(txc->maxerror, 0, NTP_PHASE_LIMIT);
 
 	if (txc->modes & ADJ_ESTERROR)
-		time_esterror = txc->esterror;
+		time_esterror = clamp(txc->esterror, 0, NTP_PHASE_LIMIT);
 
 	if (txc->modes & ADJ_TIMECONST) {
-		time_constant = txc->constant;
+		time_constant = clamp(txc->constant, 0, MAXTC);
 		if (!(time_status & STA_NANO))
 			time_constant += 4;
-		time_constant = min(time_constant, (long)MAXTC);
-		time_constant = max(time_constant, 0l);
+		time_constant = clamp(time_constant, 0, MAXTC);
 	}
 
 	if (txc->modes & ADJ_TAI &&
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index b4843099a8..ed58eebb4e 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -1141,7 +1141,6 @@ void tick_broadcast_switch_to_oneshot(void)
 #ifdef CONFIG_HOTPLUG_CPU
 void hotplug_cpu__broadcast_tick_pull(int deadcpu)
 {
-	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	struct clock_event_device *bc;
 	unsigned long flags;
 
@@ -1167,6 +1166,8 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
 		 * device to avoid the starvation.
 		 */
 		if (tick_check_broadcast_expired()) {
+			struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+
 			cpumask_clear_cpu(smp_processor_id(), tick_broadcast_force_mask);
 			tick_program_event(td->evtdev->next_event, 1);
 		}
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4e18db1819..0381366c54 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2479,7 +2479,7 @@ int do_adjtimex(struct __kernel_timex *txc)
 		clock_set |= timekeeping_advance(TK_ADV_FREQ);
 
 	if (clock_set)
-		clock_was_set(CLOCK_REALTIME);
+		clock_was_set(CLOCK_SET_WALL);
 
 	ntp_notify_cmos_timer();
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 749a182dab..8edab43580 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1573,6 +1573,29 @@ static inline void *event_file_data(struct file *filp)
 extern struct mutex event_mutex;
 extern struct list_head ftrace_events;
 
+/*
+ * When the trace_event_file is the filp->i_private pointer,
+ * it must be taken under the event_mutex lock, and then checked
+ * if the EVENT_FILE_FL_FREED flag is set. If it is, then the
+ * data pointed to by the trace_event_file can not be trusted.
+ *
+ * Use the event_file_file() to access the trace_event_file from
+ * the filp the first time under the event_mutex and check for
+ * NULL. If it is needed to be retrieved again and the event_mutex
+ * is still held, then the event_file_data() can be used and it
+ * is guaranteed to be valid.
+ */
+static inline struct trace_event_file *event_file_file(struct file *filp)
+{
+	struct trace_event_file *file;
+
+	lockdep_assert_held(&event_mutex);
+	file = READ_ONCE(file_inode(filp)->i_private);
+	if (!file || file->flags & EVENT_FILE_FL_FREED)
+		return NULL;
+	return file;
+}
+
 extern const struct file_operations event_trigger_fops;
 extern const struct file_operations event_hist_fops;
 extern const struct file_operations event_hist_debug_fops;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 6ef29eba90..f08fbaf8ca 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1386,12 +1386,12 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 	char buf[4] = "0";
 
 	mutex_lock(&event_mutex);
-	file = event_file_data(filp);
+	file = event_file_file(filp);
 	if (likely(file))
 		flags = file->flags;
 	mutex_unlock(&event_mutex);
 
-	if (!file || flags & EVENT_FILE_FL_FREED)
+	if (!file)
 		return -ENODEV;
 
 	if (flags & EVENT_FILE_FL_ENABLED &&
@@ -1424,8 +1424,8 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	case 1:
 		ret = -ENODEV;
 		mutex_lock(&event_mutex);
-		file = event_file_data(filp);
-		if (likely(file && !(file->flags & EVENT_FILE_FL_FREED))) {
+		file = event_file_file(filp);
+		if (likely(file)) {
 			ret = tracing_update_buffers(file->tr);
 			if (ret < 0) {
 				mutex_unlock(&event_mutex);
@@ -1540,7 +1540,8 @@ enum {
 
 static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct trace_event_call *call = event_file_data(m->private);
+	struct trace_event_file *file = event_file_data(m->private);
+	struct trace_event_call *call = file->event_call;
 	struct list_head *common_head = &ftrace_common_fields;
 	struct list_head *head = trace_get_fields(call);
 	struct list_head *node = v;
@@ -1572,7 +1573,8 @@ static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 
 static int f_show(struct seq_file *m, void *v)
 {
-	struct trace_event_call *call = event_file_data(m->private);
+	struct trace_event_file *file = event_file_data(m->private);
+	struct trace_event_call *call = file->event_call;
 	struct ftrace_event_field *field;
 	const char *array_descriptor;
 
@@ -1627,12 +1629,14 @@ static int f_show(struct seq_file *m, void *v)
 
 static void *f_start(struct seq_file *m, loff_t *pos)
 {
+	struct trace_event_file *file;
 	void *p = (void *)FORMAT_HEADER;
 	loff_t l = 0;
 
 	/* ->stop() is called even if ->start() fails */
 	mutex_lock(&event_mutex);
-	if (!event_file_data(m->private))
+	file = event_file_file(m->private);
+	if (!file)
 		return ERR_PTR(-ENODEV);
 
 	while (l < *pos && p)
@@ -1706,8 +1710,8 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 	trace_seq_init(s);
 
 	mutex_lock(&event_mutex);
-	file = event_file_data(filp);
-	if (file && !(file->flags & EVENT_FILE_FL_FREED))
+	file = event_file_file(filp);
+	if (file)
 		print_event_filter(file, s);
 	mutex_unlock(&event_mutex);
 
@@ -1736,9 +1740,13 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		return PTR_ERR(buf);
 
 	mutex_lock(&event_mutex);
-	file = event_file_data(filp);
-	if (file)
-		err = apply_event_filter(file, buf);
+	file = event_file_file(filp);
+	if (file) {
+		if (file->flags & EVENT_FILE_FL_FREED)
+			err = -ENODEV;
+		else
+			err = apply_event_filter(file, buf);
+	}
 	mutex_unlock(&event_mutex);
 
 	kfree(buf);
@@ -2485,7 +2493,6 @@ static int event_callback(const char *name, umode_t *mode, void **data,
 	if (strcmp(name, "format") == 0) {
 		*mode = TRACE_MODE_READ;
 		*fops = &ftrace_event_format_fops;
-		*data = call;
 		return 1;
 	}
 
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 6ece1308d3..5f9119eb7c 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5601,7 +5601,7 @@ static int hist_show(struct seq_file *m, void *v)
 
 	mutex_lock(&event_mutex);
 
-	event_file = event_file_data(m->private);
+	event_file = event_file_file(m->private);
 	if (unlikely(!event_file)) {
 		ret = -ENODEV;
 		goto out_unlock;
@@ -5880,7 +5880,7 @@ static int hist_debug_show(struct seq_file *m, void *v)
 
 	mutex_lock(&event_mutex);
 
-	event_file = event_file_data(m->private);
+	event_file = event_file_file(m->private);
 	if (unlikely(!event_file)) {
 		ret = -ENODEV;
 		goto out_unlock;
diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c
index 8650562bda..a8f076809d 100644
--- a/kernel/trace/trace_events_inject.c
+++ b/kernel/trace/trace_events_inject.c
@@ -299,7 +299,7 @@ event_inject_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	strim(buf);
 
 	mutex_lock(&event_mutex);
-	file = event_file_data(filp);
+	file = event_file_file(filp);
 	if (file) {
 		call = file->event_call;
 		size = parse_entry(buf, call, &entry);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 4bec043c86..a5e3d6acf1 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -159,7 +159,7 @@ static void *trigger_start(struct seq_file *m, loff_t *pos)
 
 	/* ->stop() is called even if ->start() fails */
 	mutex_lock(&event_mutex);
-	event_file = event_file_data(m->private);
+	event_file = event_file_file(m->private);
 	if (unlikely(!event_file))
 		return ERR_PTR(-ENODEV);
 
@@ -213,7 +213,7 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file)
 
 	mutex_lock(&event_mutex);
 
-	if (unlikely(!event_file_data(file))) {
+	if (unlikely(!event_file_file(file))) {
 		mutex_unlock(&event_mutex);
 		return -ENODEV;
 	}
@@ -293,7 +293,7 @@ static ssize_t event_trigger_regex_write(struct file *file,
 	strim(buf);
 
 	mutex_lock(&event_mutex);
-	event_file = event_file_data(file);
+	event_file = event_file_file(file);
 	if (unlikely(!event_file)) {
 		mutex_unlock(&event_mutex);
 		kfree(buf);
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index a4dcf0f243..3a56e7c8aa 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -454,7 +454,7 @@ static struct tracing_map_elt *get_free_elt(struct tracing_map *map)
 	struct tracing_map_elt *elt = NULL;
 	int idx;
 
-	idx = atomic_inc_return(&map->next_elt);
+	idx = atomic_fetch_add_unless(&map->next_elt, 1, map->max_elts);
 	if (idx < map->max_elts) {
 		elt = *(TRACING_MAP_ELT(map->elts, idx));
 		if (map->ops && map->ops->elt_init)
@@ -699,7 +699,7 @@ void tracing_map_clear(struct tracing_map *map)
 {
 	unsigned int i;
 
-	atomic_set(&map->next_elt, -1);
+	atomic_set(&map->next_elt, 0);
 	atomic64_set(&map->hits, 0);
 	atomic64_set(&map->drops, 0);
 
@@ -783,7 +783,7 @@ struct tracing_map *tracing_map_create(unsigned int map_bits,
 
 	map->map_bits = map_bits;
 	map->max_elts = (1 << map_bits);
-	atomic_set(&map->next_elt, -1);
+	atomic_set(&map->next_elt, 0);
 
 	map->map_size = (1 << (map_bits + 1));
 	map->ops = ops;