Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

18 files changed, 200 insertions, 57 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index d15c0ee..addf773 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -102,7 +102,7 @@ static int check_free_space(struct bsd_acct_struct *acct)
 {
 	struct kstatfs sbuf;
 
-	if (time_is_before_jiffies(acct->needcheck))
+	if (time_is_after_jiffies(acct->needcheck))
 		goto out;
 
 	/* May block */
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 01aaef1..5bb5e49 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -368,7 +368,45 @@ out:
 	putname(pname);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(bpf_obj_get_user);
+
+static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type)
+{
+	struct bpf_prog *prog;
+	int ret = inode_permission(inode, MAY_READ | MAY_WRITE);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (inode->i_op == &bpf_map_iops)
+		return ERR_PTR(-EINVAL);
+	if (inode->i_op != &bpf_prog_iops)
+		return ERR_PTR(-EACCES);
+
+	prog = inode->i_private;
+
+	ret = security_bpf_prog(prog);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	if (!bpf_prog_get_ok(prog, &type, false))
+		return ERR_PTR(-EINVAL);
+
+	return bpf_prog_inc(prog);
+}
+
+struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type)
+{
+	struct bpf_prog *prog;
+	struct path path;
+	int ret = kern_path(name, LOOKUP_FOLLOW, &path);
+	if (ret)
+		return ERR_PTR(ret);
+	prog = __get_prog_inode(d_backing_inode(path.dentry), type);
+	if (!IS_ERR(prog))
+		touch_atime(&path);
+	path_put(&path);
+	return prog;
+}
+EXPORT_SYMBOL(bpf_prog_get_type_path);
 
 static void bpf_evict_inode(struct inode *inode)
 {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ebf0fb2..2bac0dc 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1068,7 +1068,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero);
 
-static bool bpf_prog_get_ok(struct bpf_prog *prog,
+bool bpf_prog_get_ok(struct bpf_prog *prog,
 			    enum bpf_prog_type *attach_type, bool attach_drv)
 {
 	/* not an attachment, just a refcount inc, always allow */
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 024085d..a2c05d2 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -123,7 +123,11 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 	 */
 	do {
 		css_task_iter_start(&from->self, 0, &it);
-		task = css_task_iter_next(&it);
+
+		do {
+			task = css_task_iter_next(&it);
+		} while (task && (task->flags & PF_EXITING));
+
 		if (task)
 			get_task_struct(task);
 		css_task_iter_end(&it);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 0b1ffe1..2cf06c2 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1397,7 +1397,7 @@ static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
 			 cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
 			 cft->name);
 	else
-		strncpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
+		strlcpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
 	return buf;
 }
 
@@ -1864,9 +1864,9 @@ void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts)
 
 	root->flags = opts->flags;
 	if (opts->release_agent)
-		strcpy(root->release_agent_path, opts->release_agent);
+		strlcpy(root->release_agent_path, opts->release_agent, PATH_MAX);
 	if (opts->name)
-		strcpy(root->name, opts->name);
+		strlcpy(root->name, opts->name, MAX_CGROUP_ROOT_NAMELEN);
 	if (opts->cpuset_clone_children)
 		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
 }
@@ -4125,26 +4125,24 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 
 static void css_task_iter_advance(struct css_task_iter *it)
 {
-	struct list_head *l = it->task_pos;
+	struct list_head *next;
 
 	lockdep_assert_held(&css_set_lock);
-	WARN_ON_ONCE(!l);
-
 repeat:
 	/*
 	 * Advance iterator to find next entry.  cset->tasks is consumed
 	 * first and then ->mg_tasks.  After ->mg_tasks, we move onto the
 	 * next cset.
 	 */
-	l = l->next;
+	next = it->task_pos->next;
 
-	if (l == it->tasks_head)
-		l = it->mg_tasks_head->next;
+	if (next == it->tasks_head)
+		next = it->mg_tasks_head->next;
 
-	if (l == it->mg_tasks_head)
+	if (next == it->mg_tasks_head)
 		css_task_iter_advance_css_set(it);
 	else
-		it->task_pos = l;
+		it->task_pos = next;
 
 	/* if PROCS, skip over tasks which aren't group leaders */
 	if ((it->flags & CSS_TASK_ITER_PROCS) && it->task_pos &&
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 41376c3..53f7dc6 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -80,19 +80,19 @@ static struct lockdep_map cpuhp_state_down_map =
 	STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map);
 
 
-static void inline cpuhp_lock_acquire(bool bringup)
+static inline void cpuhp_lock_acquire(bool bringup)
 {
 	lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
 }
 
-static void inline cpuhp_lock_release(bool bringup)
+static inline void cpuhp_lock_release(bool bringup)
 {
 	lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
 }
 #else
 
-static void inline cpuhp_lock_acquire(bool bringup) { }
-static void inline cpuhp_lock_release(bool bringup) { }
+static inline void cpuhp_lock_acquire(bool bringup) { }
+static inline void cpuhp_lock_release(bool bringup) { }
 
 #endif
 
@@ -1277,9 +1277,9 @@ static struct cpuhp_step cpuhp_bp_states[] = {
 	 * before blk_mq_queue_reinit_notify() from notify_dead(),
 	 * otherwise a RCU stall occurs.
 	 */
-	[CPUHP_TIMERS_DEAD] = {
+	[CPUHP_TIMERS_PREPARE] = {
 		.name			= "timers:dead",
-		.startup.single		= NULL,
+		.startup.single		= timers_prepare_cpu,
 		.teardown.single	= timers_dead_cpu,
 	},
 	/* Kicks the plugged cpu into life */
diff --git a/kernel/exit.c b/kernel/exit.c
index df0c91d..995453d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1763,3 +1763,4 @@ __weak void abort(void)
 	/* if that doesn't kill us, halt */
 	panic("Oops failed to kill thread");
 }
+EXPORT_SYMBOL(abort);
diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h
index 17f05ef..e4d3819 100644
--- a/kernel/irq/debug.h
+++ b/kernel/irq/debug.h
@@ -12,6 +12,11 @@
 
 static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 {
+	static DEFINE_RATELIMIT_STATE(ratelimit, 5 * HZ, 5);
+
+	if (!__ratelimit(&ratelimit))
+		return;
+
 	printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n",
 		irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled);
 	printk("->handle_irq():  %p, ", desc->handle_irq);
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index 7f608ac..acfaaef 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -113,6 +113,7 @@ static const struct irq_bit_descr irqdata_states[] = {
 	BIT_MASK_DESCR(IRQD_SETAFFINITY_PENDING),
 	BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED),
 	BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN),
+	BIT_MASK_DESCR(IRQD_CAN_RESERVE),
 
 	BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU),
 
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index c26c5bb..508c03d 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -364,10 +364,11 @@ irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq)
 EXPORT_SYMBOL_GPL(irq_get_domain_generic_chip);
 
 /*
- * Separate lockdep class for interrupt chip which can nest irq_desc
- * lock.
+ * Separate lockdep classes for interrupt chip which can nest irq_desc
+ * lock and request mutex.
  */
 static struct lock_class_key irq_nested_lock_class;
+static struct lock_class_key irq_nested_request_class;
 
 /*
  * irq_map_generic_chip - Map a generic chip for an irq domain
@@ -409,7 +410,8 @@ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq,
 	set_bit(idx, &gc->installed);
 
 	if (dgc->gc_flags & IRQ_GC_INIT_NESTED_LOCK)
-		irq_set_lockdep_class(virq, &irq_nested_lock_class);
+		irq_set_lockdep_class(virq, &irq_nested_lock_class,
+				      &irq_nested_request_class);
 
 	if (chip->irq_calc_mask)
 		chip->irq_calc_mask(data);
@@ -479,7 +481,8 @@ void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk,
 			continue;
 
 		if (flags & IRQ_GC_INIT_NESTED_LOCK)
-			irq_set_lockdep_class(i, &irq_nested_lock_class);
+			irq_set_lockdep_class(i, &irq_nested_lock_class,
+					      &irq_nested_request_class);
 
 		if (!(flags & IRQ_GC_NO_MASK)) {
 			struct irq_data *d = irq_get_irq_data(i);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 07d08ca..ab19371 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -440,7 +440,7 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear)
 #endif /* !CONFIG_GENERIC_PENDING_IRQ */
 
 #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY)
-static inline int irq_domain_activate_irq(struct irq_data *data, bool early)
+static inline int irq_domain_activate_irq(struct irq_data *data, bool reserve)
 {
 	irqd_set_activated(data);
 	return 0;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 4f4f600..62068ad 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1693,7 +1693,7 @@ static void __irq_domain_deactivate_irq(struct irq_data *irq_data)
 	}
 }
 
-static int __irq_domain_activate_irq(struct irq_data *irqd, bool early)
+static int __irq_domain_activate_irq(struct irq_data *irqd, bool reserve)
 {
 	int ret = 0;
 
@@ -1702,9 +1702,9 @@ static int __irq_domain_activate_irq(struct irq_data *irqd, bool early)
 
 		if (irqd->parent_data)
 			ret = __irq_domain_activate_irq(irqd->parent_data,
-							early);
+							reserve);
 		if (!ret && domain->ops->activate) {
-			ret = domain->ops->activate(domain, irqd, early);
+			ret = domain->ops->activate(domain, irqd, reserve);
 			/* Rollback in case of error */
 			if (ret && irqd->parent_data)
 				__irq_domain_deactivate_irq(irqd->parent_data);
@@ -1716,17 +1716,18 @@ static int __irq_domain_activate_irq(struct irq_data *irqd, bool early)
 /**
  * irq_domain_activate_irq - Call domain_ops->activate recursively to activate
  *			     interrupt
- * @irq_data:	outermost irq_data associated with interrupt
+ * @irq_data:	Outermost irq_data associated with interrupt
+ * @reserve:	If set only reserve an interrupt vector instead of assigning one
  *
  * This is the second step to call domain_ops->activate to program interrupt
  * controllers, so the interrupt could actually get delivered.
  */
-int irq_domain_activate_irq(struct irq_data *irq_data, bool early)
+int irq_domain_activate_irq(struct irq_data *irq_data, bool reserve)
 {
 	int ret = 0;
 
 	if (!irqd_is_activated(irq_data))
-		ret = __irq_domain_activate_irq(irq_data, early);
+		ret = __irq_domain_activate_irq(irq_data, reserve);
 	if (!ret)
 		irqd_set_activated(irq_data);
 	return ret;
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index edb987b..2f3c4f5 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -339,6 +339,40 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev,
 	return ret;
 }
 
+/*
+ * Carefully check whether the device can use reservation mode. If
+ * reservation mode is enabled then the early activation will assign a
+ * dummy vector to the device. If the PCI/MSI device does not support
+ * masking of the entry then this can result in spurious interrupts when
+ * the device driver is not absolutely careful. But even then a malfunction
+ * of the hardware could result in a spurious interrupt on the dummy vector
+ * and render the device unusable. If the entry can be masked then the core
+ * logic will prevent the spurious interrupt and reservation mode can be
+ * used. For now reservation mode is restricted to PCI/MSI.
+ */
+static bool msi_check_reservation_mode(struct irq_domain *domain,
+				       struct msi_domain_info *info,
+				       struct device *dev)
+{
+	struct msi_desc *desc;
+
+	if (domain->bus_token != DOMAIN_BUS_PCI_MSI)
+		return false;
+
+	if (!(info->flags & MSI_FLAG_MUST_REACTIVATE))
+		return false;
+
+	if (IS_ENABLED(CONFIG_PCI_MSI) && pci_msi_ignore_mask)
+		return false;
+
+	/*
+	 * Checking the first MSI descriptor is sufficient. MSIX supports
+	 * masking and MSI does so when the maskbit is set.
+	 */
+	desc = first_msi_entry(dev);
+	return desc->msi_attrib.is_msix || desc->msi_attrib.maskbit;
+}
+
 /**
  * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain
  * @domain:	The domain to allocate from
@@ -353,9 +387,11 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 {
 	struct msi_domain_info *info = domain->host_data;
 	struct msi_domain_ops *ops = info->ops;
-	msi_alloc_info_t arg;
+	struct irq_data *irq_data;
 	struct msi_desc *desc;
+	msi_alloc_info_t arg;
 	int i, ret, virq;
+	bool can_reserve;
 
 	ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg);
 	if (ret)
@@ -385,6 +421,8 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 	if (ops->msi_finish)
 		ops->msi_finish(&arg, 0);
 
+	can_reserve = msi_check_reservation_mode(domain, info, dev);
+
 	for_each_msi_entry(desc, dev) {
 		virq = desc->irq;
 		if (desc->nvec_used == 1)
@@ -397,15 +435,25 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 		 * the MSI entries before the PCI layer enables MSI in the
 		 * card. Otherwise the card latches a random msi message.
 		 */
-		if (info->flags & MSI_FLAG_ACTIVATE_EARLY) {
-			struct irq_data *irq_data;
+		if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY))
+			continue;
 
+		irq_data = irq_domain_get_irq_data(domain, desc->irq);
+		if (!can_reserve)
+			irqd_clr_can_reserve(irq_data);
+		ret = irq_domain_activate_irq(irq_data, can_reserve);
+		if (ret)
+			goto cleanup;
+	}
+
+	/*
+	 * If these interrupts use reservation mode, clear the activated bit
+	 * so request_irq() will assign the final vector.
+	 */
+	if (can_reserve) {
+		for_each_msi_entry(desc, dev) {
 			irq_data = irq_domain_get_irq_data(domain, desc->irq);
-			ret = irq_domain_activate_irq(irq_data, true);
-			if (ret)
-				goto cleanup;
-			if (info->flags & MSI_FLAG_MUST_REACTIVATE)
-				irqd_clr_activated(irq_data);
+			irqd_clr_activated(irq_data);
 		}
 	}
 	return 0;
diff --git a/kernel/pid.c b/kernel/pid.c
index b13b624..1e8bb65 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -193,10 +193,8 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 	}
 
 	if (unlikely(is_child_reaper(pid))) {
-		if (pid_ns_prepare_proc(ns)) {
-			disable_pid_allocation(ns);
+		if (pid_ns_prepare_proc(ns))
 			goto out_free;
-		}
 	}
 
 	get_pid_ns(ns);
@@ -226,6 +224,10 @@ out_free:
 	while (++i <= ns->level)
 		idr_remove(&ns->idr, (pid->numbers + i)->nr);
 
+	/* On failure to allocate the first pid, reset the state */
+	if (ns->pid_allocated == PIDNS_ADDING)
+		idr_set_cursor(&ns->idr, 0);
+
 	spin_unlock_irq(&pidmap_lock);
 
 	kmem_cache_free(ns->pid_cachep, pid);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 2f52ec0..d6717a3 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -244,7 +244,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
 #ifdef CONFIG_NO_HZ_COMMON
 static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
 {
-	unsigned long idle_calls = tick_nohz_get_idle_calls();
+	unsigned long idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu);
 	bool ret = idle_calls == sg_cpu->saved_idle_calls;
 
 	sg_cpu->saved_idle_calls = idle_calls;
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index e776fc8..f6b5f19 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -95,6 +95,7 @@ config NO_HZ_FULL
 	select RCU_NOCB_CPU
 	select VIRT_CPU_ACCOUNTING_GEN
 	select IRQ_WORK
+	select CPU_ISOLATION
 	help
 	 Adaptively try to shutdown the tick whenever possible, even when
 	 the CPU is running tasks. Typically this requires running a single
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 99578f0..f7cc7ab 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -650,6 +650,11 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 	ts->next_tick = 0;
 }
 
+static inline bool local_timer_softirq_pending(void)
+{
+	return local_softirq_pending() & TIMER_SOFTIRQ;
+}
+
 static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 					 ktime_t now, int cpu)
 {
@@ -666,8 +671,18 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	} while (read_seqretry(&jiffies_lock, seq));
 	ts->last_jiffies = basejiff;
 
-	if (rcu_needs_cpu(basemono, &next_rcu) ||
-	    arch_needs_cpu() || irq_work_needs_cpu()) {
+	/*
+	 * Keep the periodic tick, when RCU, architecture or irq_work
+	 * requests it.
+	 * Aside of that check whether the local timer softirq is
+	 * pending. If so its a bad idea to call get_next_timer_interrupt()
+	 * because there is an already expired timer, so it will request
+	 * immeditate expiry, which rearms the hardware timer with a
+	 * minimal delta which brings us back to this place
+	 * immediately. Lather, rinse and repeat...
+	 */
+	if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() ||
+	    irq_work_needs_cpu() || local_timer_softirq_pending()) {
 		next_tick = basemono + TICK_NSEC;
 	} else {
 		/*
@@ -986,6 +1001,19 @@ ktime_t tick_nohz_get_sleep_length(void)
 }
 
 /**
+ * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value
+ * for a particular CPU.
+ *
+ * Called from the schedutil frequency scaling governor in scheduler context.
+ */
+unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
+{
+	struct tick_sched *ts = tick_get_tick_sched(cpu);
+
+	return ts->idle_calls;
+}
+
+/**
  * tick_nohz_get_idle_calls - return the current idle calls counter value
  *
  * Called from the schedutil frequency scaling governor in scheduler context.
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index ffebcf8..89a9e1b 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -823,11 +823,10 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
 	struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu);
 
 	/*
-	 * If the timer is deferrable and nohz is active then we need to use
-	 * the deferrable base.
+	 * If the timer is deferrable and NO_HZ_COMMON is set then we need
+	 * to use the deferrable base.
 	 */
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
-	    (tflags & TIMER_DEFERRABLE))
+	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
 		base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu);
 	return base;
 }
@@ -837,11 +836,10 @@ static inline struct timer_base *get_timer_this_cpu_base(u32 tflags)
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
 
 	/*
-	 * If the timer is deferrable and nohz is active then we need to use
-	 * the deferrable base.
+	 * If the timer is deferrable and NO_HZ_COMMON is set then we need
+	 * to use the deferrable base.
 	 */
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
-	    (tflags & TIMER_DEFERRABLE))
+	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
 		base = this_cpu_ptr(&timer_bases[BASE_DEF]);
 	return base;
 }
@@ -1009,8 +1007,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 	if (!ret && (options & MOD_TIMER_PENDING_ONLY))
 		goto out_unlock;
 
-	debug_activate(timer, expires);
-
 	new_base = get_target_base(base, timer->flags);
 
 	if (base != new_base) {
@@ -1034,6 +1030,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 		}
 	}
 
+	debug_activate(timer, expires);
+
 	timer->expires = expires;
 	/*
 	 * If 'idx' was calculated above and the base time did not advance
@@ -1684,7 +1682,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 	base->must_forward_clk = false;
 
 	__run_timers(base);
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
+	if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
 		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
 }
 
@@ -1855,6 +1853,21 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h
 	}
 }
 
+int timers_prepare_cpu(unsigned int cpu)
+{
+	struct timer_base *base;
+	int b;
+
+	for (b = 0; b < NR_BASES; b++) {
+		base = per_cpu_ptr(&timer_bases[b], cpu);
+		base->clk = jiffies;
+		base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
+		base->is_idle = false;
+		base->must_forward_clk = true;
+	}
+	return 0;
+}
+
 int timers_dead_cpu(unsigned int cpu)
 {
 	struct timer_base *old_base;