1 files changed, 383 insertions, 220 deletions

diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index c09f2955ae30..3fe6b0c99f3d 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * kernel/stop_machine.c
  *
@@ -5,9 +6,8 @@
  * Copyright (C) 2008, 2005	Rusty Russell rusty@rustcorp.com.au
  * Copyright (C) 2010		SUSE Linux Products GmbH
  * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
- *
- * This file is released under the GPLv2 and any later version.
  */
+#include <linux/compiler.h>
 #include <linux/completion.h>
 #include <linux/cpu.h>
 #include <linux/init.h>
@@ -20,6 +20,8 @@
 #include <linux/kallsyms.h>
 #include <linux/smpboot.h>
 #include <linux/atomic.h>
+#include <linux/nmi.h>
+#include <linux/sched/wake_q.h>
 
 /*
  * Structure to determine completion condition and record errors.  May
@@ -27,22 +29,44 @@
  */
 struct cpu_stop_done {
 	atomic_t		nr_todo;	/* nr left to execute */
-	bool			executed;	/* actually executed? */
 	int			ret;		/* collected return value */
 	struct completion	completion;	/* fired if nr_todo reaches 0 */
 };
 
 /* the actual stopper, one per every possible cpu, enabled on online cpus */
 struct cpu_stopper {
-	spinlock_t		lock;
+	struct task_struct	*thread;
+
+	raw_spinlock_t		lock;
 	bool			enabled;	/* is this stopper enabled? */
 	struct list_head	works;		/* list of pending works */
+
+	struct cpu_stop_work	stop_work;	/* for stop_cpus */
+	unsigned long		caller;
+	cpu_stop_fn_t		fn;
 };
 
 static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
-static DEFINE_PER_CPU(struct task_struct *, cpu_stopper_task);
 static bool stop_machine_initialized = false;
 
+void print_stop_info(const char *log_lvl, struct task_struct *task)
+{
+	/*
+	 * If @task is a stopper task, it cannot migrate and task_cpu() is
+	 * stable.
+	 */
+	struct cpu_stopper *stopper = per_cpu_ptr(&cpu_stopper, task_cpu(task));
+
+	if (task != stopper->thread)
+		return;
+
+	printk("%sStopper: %pS <- %pS\n", log_lvl, stopper->fn, (void *)stopper->caller);
+}
+
+/* static data for stop_cpus */
+static DEFINE_MUTEX(stop_cpus_mutex);
+static bool stop_cpus_in_progress;
+
 static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
 {
 	memset(done, 0, sizeof(*done));
@@ -51,33 +75,39 @@ static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
 }
 
 /* signal completion unless @done is NULL */
-static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed)
+static void cpu_stop_signal_done(struct cpu_stop_done *done)
 {
-	if (done) {
-		if (executed)
-			done->executed = true;
-		if (atomic_dec_and_test(&done->nr_todo))
-			complete(&done->completion);
-	}
+	if (atomic_dec_and_test(&done->nr_todo))
+		complete(&done->completion);
+}
+
+static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
+				  struct cpu_stop_work *work)
+{
+	list_add_tail(&work->list, &stopper->works);
 }
 
 /* queue @work to @stopper.  if offline, @work is completed immediately */
-static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
+static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
-	struct task_struct *p = per_cpu(cpu_stopper_task, cpu);
-
 	unsigned long flags;
+	bool enabled;
 
-	spin_lock_irqsave(&stopper->lock, flags);
-
-	if (stopper->enabled) {
-		list_add_tail(&work->list, &stopper->works);
-		wake_up_process(p);
-	} else
-		cpu_stop_signal_done(work->done, false);
+	preempt_disable();
+	raw_spin_lock_irqsave(&stopper->lock, flags);
+	enabled = stopper->enabled;
+	if (enabled)
+		__cpu_stop_queue_work(stopper, work);
+	else if (work->done)
+		cpu_stop_signal_done(work->done);
+	raw_spin_unlock_irqrestore(&stopper->lock, flags);
+
+	if (enabled)
+		wake_up_process(stopper->thread);
+	preempt_enable();
 
-	spin_unlock_irqrestore(&stopper->lock, flags);
+	return enabled;
 }
 
 /**
@@ -107,12 +137,231 @@ static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
 {
 	struct cpu_stop_done done;
-	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done };
+	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done, .caller = _RET_IP_ };
 
 	cpu_stop_init_done(&done, 1);
-	cpu_stop_queue_work(cpu, &work);
+	if (!cpu_stop_queue_work(cpu, &work))
+		return -ENOENT;
+	/*
+	 * In case @cpu == smp_proccessor_id() we can avoid a sleep+wakeup
+	 * cycle by doing a preemption:
+	 */
+	cond_resched();
+	wait_for_completion(&done.completion);
+	return done.ret;
+}
+
+/* This controls the threads on each CPU. */
+enum multi_stop_state {
+	/* Dummy starting state for thread. */
+	MULTI_STOP_NONE,
+	/* Awaiting everyone to be scheduled. */
+	MULTI_STOP_PREPARE,
+	/* Disable interrupts. */
+	MULTI_STOP_DISABLE_IRQ,
+	/* Run the function */
+	MULTI_STOP_RUN,
+	/* Exit */
+	MULTI_STOP_EXIT,
+};
+
+struct multi_stop_data {
+	cpu_stop_fn_t		fn;
+	void			*data;
+	/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
+	unsigned int		num_threads;
+	const struct cpumask	*active_cpus;
+
+	enum multi_stop_state	state;
+	atomic_t		thread_ack;
+};
+
+static void set_state(struct multi_stop_data *msdata,
+		      enum multi_stop_state newstate)
+{
+	/* Reset ack counter. */
+	atomic_set(&msdata->thread_ack, msdata->num_threads);
+	smp_wmb();
+	WRITE_ONCE(msdata->state, newstate);
+}
+
+/* Last one to ack a state moves to the next state. */
+static void ack_state(struct multi_stop_data *msdata)
+{
+	if (atomic_dec_and_test(&msdata->thread_ack))
+		set_state(msdata, msdata->state + 1);
+}
+
+notrace void __weak stop_machine_yield(const struct cpumask *cpumask)
+{
+	cpu_relax();
+}
+
+/* This is the cpu_stop function which stops the CPU. */
+static int multi_cpu_stop(void *data)
+{
+	struct multi_stop_data *msdata = data;
+	enum multi_stop_state newstate, curstate = MULTI_STOP_NONE;
+	int cpu = smp_processor_id(), err = 0;
+	const struct cpumask *cpumask;
+	unsigned long flags;
+	bool is_active;
+
+	/*
+	 * When called from stop_machine_from_inactive_cpu(), irq might
+	 * already be disabled.  Save the state and restore it on exit.
+	 */
+	local_save_flags(flags);
+
+	if (!msdata->active_cpus) {
+		cpumask = cpu_online_mask;
+		is_active = cpu == cpumask_first(cpumask);
+	} else {
+		cpumask = msdata->active_cpus;
+		is_active = cpumask_test_cpu(cpu, cpumask);
+	}
+
+	/* Simple state machine */
+	do {
+		/* Chill out and ensure we re-read multi_stop_state. */
+		stop_machine_yield(cpumask);
+		newstate = READ_ONCE(msdata->state);
+		if (newstate != curstate) {
+			curstate = newstate;
+			switch (curstate) {
+			case MULTI_STOP_DISABLE_IRQ:
+				local_irq_disable();
+				hard_irq_disable();
+				break;
+			case MULTI_STOP_RUN:
+				if (is_active)
+					err = msdata->fn(msdata->data);
+				break;
+			default:
+				break;
+			}
+			ack_state(msdata);
+		} else if (curstate > MULTI_STOP_PREPARE) {
+			/*
+			 * At this stage all other CPUs we depend on must spin
+			 * in the same loop. Any reason for hard-lockup should
+			 * be detected and reported on their side.
+			 */
+			touch_nmi_watchdog();
+			/* Also suppress RCU CPU stall warnings. */
+			rcu_momentary_eqs();
+		}
+	} while (curstate != MULTI_STOP_EXIT);
+
+	local_irq_restore(flags);
+	return err;
+}
+
+static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
+				    int cpu2, struct cpu_stop_work *work2)
+{
+	struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);
+	struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
+	int err;
+
+retry:
+	/*
+	 * The waking up of stopper threads has to happen in the same
+	 * scheduling context as the queueing.  Otherwise, there is a
+	 * possibility of one of the above stoppers being woken up by another
+	 * CPU, and preempting us. This will cause us to not wake up the other
+	 * stopper forever.
+	 */
+	preempt_disable();
+	raw_spin_lock_irq(&stopper1->lock);
+	raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
+
+	if (!stopper1->enabled || !stopper2->enabled) {
+		err = -ENOENT;
+		goto unlock;
+	}
+
+	/*
+	 * Ensure that if we race with __stop_cpus() the stoppers won't get
+	 * queued up in reverse order leading to system deadlock.
+	 *
+	 * We can't miss stop_cpus_in_progress if queue_stop_cpus_work() has
+	 * queued a work on cpu1 but not on cpu2, we hold both locks.
+	 *
+	 * It can be falsely true but it is safe to spin until it is cleared,
+	 * queue_stop_cpus_work() does everything under preempt_disable().
+	 */
+	if (unlikely(stop_cpus_in_progress)) {
+		err = -EDEADLK;
+		goto unlock;
+	}
+
+	err = 0;
+	__cpu_stop_queue_work(stopper1, work1);
+	__cpu_stop_queue_work(stopper2, work2);
+
+unlock:
+	raw_spin_unlock(&stopper2->lock);
+	raw_spin_unlock_irq(&stopper1->lock);
+
+	if (unlikely(err == -EDEADLK)) {
+		preempt_enable();
+
+		while (stop_cpus_in_progress)
+			cpu_relax();
+
+		goto retry;
+	}
+
+	if (!err) {
+		wake_up_process(stopper1->thread);
+		wake_up_process(stopper2->thread);
+	}
+	preempt_enable();
+
+	return err;
+}
+/**
+ * stop_two_cpus - stops two cpus
+ * @cpu1: the cpu to stop
+ * @cpu2: the other cpu to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Stops both the current and specified CPU and runs @fn on one of them.
+ *
+ * returns when both are completed.
+ */
+int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg)
+{
+	struct cpu_stop_done done;
+	struct cpu_stop_work work1, work2;
+	struct multi_stop_data msdata;
+
+	msdata = (struct multi_stop_data){
+		.fn = fn,
+		.data = arg,
+		.num_threads = 2,
+		.active_cpus = cpumask_of(cpu1),
+	};
+
+	work1 = work2 = (struct cpu_stop_work){
+		.fn = multi_cpu_stop,
+		.arg = &msdata,
+		.done = &done,
+		.caller = _RET_IP_,
+	};
+
+	cpu_stop_init_done(&done, 2);
+	set_state(&msdata, MULTI_STOP_PREPARE);
+
+	if (cpu1 > cpu2)
+		swap(cpu1, cpu2);
+	if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2))
+		return -ENOENT;
+
 	wait_for_completion(&done.completion);
-	return done.executed ? done.ret : -ENOENT;
+	return done.ret;
 }
 
 /**
@@ -120,6 +369,7 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
  * @cpu: cpu to stop
  * @fn: function to execute
  * @arg: argument to @fn
+ * @work_buf: pointer to cpu_stop_work structure
  *
  * Similar to stop_one_cpu() but doesn't wait for completion.  The
  * caller is responsible for ensuring @work_buf is currently unused
@@ -127,32 +377,25 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
  *
  * CONTEXT:
  * Don't care.
+ *
+ * RETURNS:
+ * true if cpu_stop_work was queued successfully and @fn will be called,
+ * false otherwise.
  */
-void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
+bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			struct cpu_stop_work *work_buf)
 {
-	*work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, };
-	cpu_stop_queue_work(cpu, work_buf);
+	*work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, .caller = _RET_IP_, };
+	return cpu_stop_queue_work(cpu, work_buf);
 }
 
-/* static data for stop_cpus */
-static DEFINE_MUTEX(stop_cpus_mutex);
-static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work);
-
-static void queue_stop_cpus_work(const struct cpumask *cpumask,
+static bool queue_stop_cpus_work(const struct cpumask *cpumask,
 				 cpu_stop_fn_t fn, void *arg,
 				 struct cpu_stop_done *done)
 {
 	struct cpu_stop_work *work;
 	unsigned int cpu;
-
-	/* initialize works and done */
-	for_each_cpu(cpu, cpumask) {
-		work = &per_cpu(stop_cpus_work, cpu);
-		work->fn = fn;
-		work->arg = arg;
-		work->done = done;
-	}
+	bool queued = false;
 
 	/*
 	 * Disable preemption while queueing to avoid getting
@@ -160,9 +403,22 @@ static void queue_stop_cpus_work(const struct cpumask *cpumask,
 	 * to enter @fn which can lead to deadlock.
 	 */
 	preempt_disable();
-	for_each_cpu(cpu, cpumask)
-		cpu_stop_queue_work(cpu, &per_cpu(stop_cpus_work, cpu));
+	stop_cpus_in_progress = true;
+	barrier();
+	for_each_cpu(cpu, cpumask) {
+		work = &per_cpu(cpu_stopper.stop_work, cpu);
+		work->fn = fn;
+		work->arg = arg;
+		work->done = done;
+		work->caller = _RET_IP_;
+		if (cpu_stop_queue_work(cpu, work))
+			queued = true;
+	}
+	barrier();
+	stop_cpus_in_progress = false;
 	preempt_enable();
+
+	return queued;
 }
 
 static int __stop_cpus(const struct cpumask *cpumask,
@@ -171,9 +427,10 @@ static int __stop_cpus(const struct cpumask *cpumask,
 	struct cpu_stop_done done;
 
 	cpu_stop_init_done(&done, cpumask_weight(cpumask));
-	queue_stop_cpus_work(cpumask, fn, arg, &done);
+	if (!queue_stop_cpus_work(cpumask, fn, arg, &done))
+		return -ENOENT;
 	wait_for_completion(&done.completion);
-	return done.executed ? done.ret : -ENOENT;
+	return done.ret;
 }
 
 /**
@@ -204,7 +461,7 @@ static int __stop_cpus(const struct cpumask *cpumask,
  * @cpumask were offline; otherwise, 0 if all executions of @fn
  * returned 0, any non zero return value if any returned non zero.
  */
-int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
+static int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
 {
 	int ret;
 
@@ -215,45 +472,15 @@ int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
 	return ret;
 }
 
-/**
- * try_stop_cpus - try to stop multiple cpus
- * @cpumask: cpus to stop
- * @fn: function to execute
- * @arg: argument to @fn
- *
- * Identical to stop_cpus() except that it fails with -EAGAIN if
- * someone else is already using the facility.
- *
- * CONTEXT:
- * Might sleep.
- *
- * RETURNS:
- * -EAGAIN if someone else is already stopping cpus, -ENOENT if
- * @fn(@arg) was not executed at all because all cpus in @cpumask were
- * offline; otherwise, 0 if all executions of @fn returned 0, any non
- * zero return value if any returned non zero.
- */
-int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
-{
-	int ret;
-
-	/* static works are used, process one request at a time */
-	if (!mutex_trylock(&stop_cpus_mutex))
-		return -EAGAIN;
-	ret = __stop_cpus(cpumask, fn, arg);
-	mutex_unlock(&stop_cpus_mutex);
-	return ret;
-}
-
 static int cpu_stop_should_run(unsigned int cpu)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 	unsigned long flags;
 	int run;
 
-	spin_lock_irqsave(&stopper->lock, flags);
+	raw_spin_lock_irqsave(&stopper->lock, flags);
 	run = !list_empty(&stopper->works);
-	spin_unlock_irqrestore(&stopper->lock, flags);
+	raw_spin_unlock_irqrestore(&stopper->lock, flags);
 	return run;
 }
 
@@ -261,82 +488,81 @@ static void cpu_stopper_thread(unsigned int cpu)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 	struct cpu_stop_work *work;
-	int ret;
 
 repeat:
 	work = NULL;
-	spin_lock_irq(&stopper->lock);
+	raw_spin_lock_irq(&stopper->lock);
 	if (!list_empty(&stopper->works)) {
 		work = list_first_entry(&stopper->works,
 					struct cpu_stop_work, list);
 		list_del_init(&work->list);
 	}
-	spin_unlock_irq(&stopper->lock);
+	raw_spin_unlock_irq(&stopper->lock);
 
 	if (work) {
 		cpu_stop_fn_t fn = work->fn;
 		void *arg = work->arg;
 		struct cpu_stop_done *done = work->done;
-		char ksym_buf[KSYM_NAME_LEN] __maybe_unused;
-
-		/* cpu stop callbacks are not allowed to sleep */
-		preempt_disable();
+		int ret;
 
+		/* cpu stop callbacks must not sleep, make in_atomic() == T */
+		stopper->caller = work->caller;
+		stopper->fn = fn;
+		preempt_count_inc();
 		ret = fn(arg);
-		if (ret)
-			done->ret = ret;
-
-		/* restore preemption and check it's still balanced */
-		preempt_enable();
+		if (done) {
+			if (ret)
+				done->ret = ret;
+			cpu_stop_signal_done(done);
+		}
+		preempt_count_dec();
+		stopper->fn = NULL;
+		stopper->caller = 0;
 		WARN_ONCE(preempt_count(),
-			  "cpu_stop: %s(%p) leaked preempt count\n",
-			  kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL,
-					  ksym_buf), arg);
-
-		cpu_stop_signal_done(done, true);
+			  "cpu_stop: %ps(%p) leaked preempt count\n", fn, arg);
 		goto repeat;
 	}
 }
 
-extern void sched_set_stop_task(int cpu, struct task_struct *stop);
+void stop_machine_park(int cpu)
+{
+	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+	/*
+	 * Lockless. cpu_stopper_thread() will take stopper->lock and flush
+	 * the pending works before it parks, until then it is fine to queue
+	 * the new works.
+	 */
+	stopper->enabled = false;
+	kthread_park(stopper->thread);
+}
 
 static void cpu_stop_create(unsigned int cpu)
 {
-	sched_set_stop_task(cpu, per_cpu(cpu_stopper_task, cpu));
+	sched_set_stop_task(cpu, per_cpu(cpu_stopper.thread, cpu));
 }
 
 static void cpu_stop_park(unsigned int cpu)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
-	struct cpu_stop_work *work;
-	unsigned long flags;
 
-	/* drain remaining works */
-	spin_lock_irqsave(&stopper->lock, flags);
-	list_for_each_entry(work, &stopper->works, list)
-		cpu_stop_signal_done(work->done, false);
-	stopper->enabled = false;
-	spin_unlock_irqrestore(&stopper->lock, flags);
+	WARN_ON(!list_empty(&stopper->works));
 }
 
-static void cpu_stop_unpark(unsigned int cpu)
+void stop_machine_unpark(int cpu)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 
-	spin_lock_irq(&stopper->lock);
 	stopper->enabled = true;
-	spin_unlock_irq(&stopper->lock);
+	kthread_unpark(stopper->thread);
 }
 
 static struct smp_hotplug_thread cpu_stop_threads = {
-	.store			= &cpu_stopper_task,
+	.store			= &cpu_stopper.thread,
 	.thread_should_run	= cpu_stop_should_run,
 	.thread_fn		= cpu_stopper_thread,
 	.thread_comm		= "migration/%u",
 	.create			= cpu_stop_create,
-	.setup			= cpu_stop_unpark,
 	.park			= cpu_stop_park,
-	.pre_unpark		= cpu_stop_unpark,
 	.selfparking		= true,
 };
 
@@ -347,110 +573,28 @@ static int __init cpu_stop_init(void)
 	for_each_possible_cpu(cpu) {
 		struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 
-		spin_lock_init(&stopper->lock);
+		raw_spin_lock_init(&stopper->lock);
 		INIT_LIST_HEAD(&stopper->works);
 	}
 
 	BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads));
+	stop_machine_unpark(raw_smp_processor_id());
 	stop_machine_initialized = true;
 	return 0;
 }
 early_initcall(cpu_stop_init);
 
-#ifdef CONFIG_STOP_MACHINE
-
-/* This controls the threads on each CPU. */
-enum stopmachine_state {
-	/* Dummy starting state for thread. */
-	STOPMACHINE_NONE,
-	/* Awaiting everyone to be scheduled. */
-	STOPMACHINE_PREPARE,
-	/* Disable interrupts. */
-	STOPMACHINE_DISABLE_IRQ,
-	/* Run the function */
-	STOPMACHINE_RUN,
-	/* Exit */
-	STOPMACHINE_EXIT,
-};
-
-struct stop_machine_data {
-	int			(*fn)(void *);
-	void			*data;
-	/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
-	unsigned int		num_threads;
-	const struct cpumask	*active_cpus;
-
-	enum stopmachine_state	state;
-	atomic_t		thread_ack;
-};
-
-static void set_state(struct stop_machine_data *smdata,
-		      enum stopmachine_state newstate)
-{
-	/* Reset ack counter. */
-	atomic_set(&smdata->thread_ack, smdata->num_threads);
-	smp_wmb();
-	smdata->state = newstate;
-}
-
-/* Last one to ack a state moves to the next state. */
-static void ack_state(struct stop_machine_data *smdata)
-{
-	if (atomic_dec_and_test(&smdata->thread_ack))
-		set_state(smdata, smdata->state + 1);
-}
-
-/* This is the cpu_stop function which stops the CPU. */
-static int stop_machine_cpu_stop(void *data)
+int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data,
+			    const struct cpumask *cpus)
 {
-	struct stop_machine_data *smdata = data;
-	enum stopmachine_state curstate = STOPMACHINE_NONE;
-	int cpu = smp_processor_id(), err = 0;
-	unsigned long flags;
-	bool is_active;
-
-	/*
-	 * When called from stop_machine_from_inactive_cpu(), irq might
-	 * already be disabled.  Save the state and restore it on exit.
-	 */
-	local_save_flags(flags);
+	struct multi_stop_data msdata = {
+		.fn = fn,
+		.data = data,
+		.num_threads = num_online_cpus(),
+		.active_cpus = cpus,
+	};
 
-	if (!smdata->active_cpus)
-		is_active = cpu == cpumask_first(cpu_online_mask);
-	else
-		is_active = cpumask_test_cpu(cpu, smdata->active_cpus);
-
-	/* Simple state machine */
-	do {
-		/* Chill out and ensure we re-read stopmachine_state. */
-		cpu_relax();
-		if (smdata->state != curstate) {
-			curstate = smdata->state;
-			switch (curstate) {
-			case STOPMACHINE_DISABLE_IRQ:
-				local_irq_disable();
-				hard_irq_disable();
-				break;
-			case STOPMACHINE_RUN:
-				if (is_active)
-					err = smdata->fn(smdata->data);
-				break;
-			default:
-				break;
-			}
-			ack_state(smdata);
-		}
-	} while (curstate != STOPMACHINE_EXIT);
-
-	local_irq_restore(flags);
-	return err;
-}
-
-int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
-{
-	struct stop_machine_data smdata = { .fn = fn, .data = data,
-					    .num_threads = num_online_cpus(),
-					    .active_cpus = cpus };
+	lockdep_assert_cpus_held();
 
 	if (!stop_machine_initialized) {
 		/*
@@ -461,7 +605,7 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 		unsigned long flags;
 		int ret;
 
-		WARN_ON_ONCE(smdata.num_threads != 1);
+		WARN_ON_ONCE(msdata.num_threads != 1);
 
 		local_irq_save(flags);
 		hard_irq_disable();
@@ -472,22 +616,43 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 	}
 
 	/* Set the initial state and stop all online cpus. */
-	set_state(&smdata, STOPMACHINE_PREPARE);
-	return stop_cpus(cpu_online_mask, stop_machine_cpu_stop, &smdata);
+	set_state(&msdata, MULTI_STOP_PREPARE);
+	return stop_cpus(cpu_online_mask, multi_cpu_stop, &msdata);
 }
 
-int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
+int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
 {
 	int ret;
 
 	/* No CPUs can come up or down during this. */
-	get_online_cpus();
-	ret = __stop_machine(fn, data, cpus);
-	put_online_cpus();
+	cpus_read_lock();
+	ret = stop_machine_cpuslocked(fn, data, cpus);
+	cpus_read_unlock();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(stop_machine);
 
+#ifdef CONFIG_SCHED_SMT
+int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data)
+{
+	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
+
+	struct multi_stop_data msdata = {
+		.fn = fn,
+		.data = data,
+		.num_threads = cpumask_weight(smt_mask),
+		.active_cpus = smt_mask,
+	};
+
+	lockdep_assert_cpus_held();
+
+	/* Set the initial state and stop all online cpus. */
+	set_state(&msdata, MULTI_STOP_PREPARE);
+	return stop_cpus(smt_mask, multi_cpu_stop, &msdata);
+}
+EXPORT_SYMBOL_GPL(stop_core_cpuslocked);
+#endif
+
 /**
  * stop_machine_from_inactive_cpu - stop_machine() from inactive CPU
  * @fn: the function to run
@@ -510,28 +675,28 @@ EXPORT_SYMBOL_GPL(stop_machine);
  * 0 if all executions of @fn returned 0, any non zero return value if any
  * returned non zero.
  */
-int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
+int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 				  const struct cpumask *cpus)
 {
-	struct stop_machine_data smdata = { .fn = fn, .data = data,
+	struct multi_stop_data msdata = { .fn = fn, .data = data,
 					    .active_cpus = cpus };
 	struct cpu_stop_done done;
 	int ret;
 
 	/* Local CPU must be inactive and CPU hotplug in progress. */
 	BUG_ON(cpu_active(raw_smp_processor_id()));
-	smdata.num_threads = num_active_cpus() + 1;	/* +1 for local */
+	msdata.num_threads = num_active_cpus() + 1;	/* +1 for local */
 
 	/* No proper task established and can't sleep - busy wait for lock. */
 	while (!mutex_trylock(&stop_cpus_mutex))
 		cpu_relax();
 
 	/* Schedule work on other CPUs and execute directly for local CPU */
-	set_state(&smdata, STOPMACHINE_PREPARE);
+	set_state(&msdata, MULTI_STOP_PREPARE);
 	cpu_stop_init_done(&done, num_active_cpus());
-	queue_stop_cpus_work(cpu_active_mask, stop_machine_cpu_stop, &smdata,
+	queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata,
 			     &done);
-	ret = stop_machine_cpu_stop(&smdata);
+	ret = multi_cpu_stop(&msdata);
 
 	/* Busy wait for completion. */
 	while (!completion_done(&done.completion))
@@ -540,5 +705,3 @@ int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
 	mutex_unlock(&stop_cpus_mutex);
 	return ret ?: done.ret;
 }
-
-#endif	/* CONFIG_STOP_MACHINE */