Merge tag 'smp-core-2020-03-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core SMP updates from Thomas Gleixner:
 "CPU (hotplug) updates:

   - Support for locked CSD objects in smp_call_function_single_async()
     which allows to simplify callsites in the scheduler core and MIPS

   - Treewide consolidation of CPU hotplug functions which ensures the
     consistency between the sysfs interface and kernel state. The low
     level functions cpu_up/down() are now confined to the core code and
     not longer accessible from random code"

* tag 'smp-core-2020-03-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits)
  cpu/hotplug: Ignore pm_wakeup_pending() for disable_nonboot_cpus()
  cpu/hotplug: Hide cpu_up/down()
  cpu/hotplug: Move bringup of secondary CPUs out of smp_init()
  torture: Replace cpu_up/down() with add/remove_cpu()
  firmware: psci: Replace cpu_up/down() with add/remove_cpu()
  xen/cpuhotplug: Replace cpu_up/down() with device_online/offline()
  parisc: Replace cpu_up/down() with add/remove_cpu()
  sparc: Replace cpu_up/down() with add/remove_cpu()
  powerpc: Replace cpu_up/down() with add/remove_cpu()
  x86/smp: Replace cpu_up/down() with add/remove_cpu()
  arm64: hibernate: Use bringup_hibernate_cpu()
  cpu/hotplug: Provide bringup_hibernate_cpu()
  arm64: Use reboot_cpu instead of hardconding it to 0
  arm64: Don't use disable_nonboot_cpus()
  ARM: Use reboot_cpu instead of hardcoding it to 0
  ARM: Don't use disable_nonboot_cpus()
  ia64: Replace cpu_down() with smp_shutdown_nonboot_cpus()
  cpu/hotplug: Create a new function to shutdown nonboot cpus
  cpu/hotplug: Add new {add,remove}_cpu() functions
  sched/core: Remove rq.hrtick_csd_pending
  ...

kernel/cpu.c

@@ -1041,7 +1041,7 @@ static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
 	return _cpu_down(cpu, 0, target);
 }
 
-static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
+static int cpu_down(unsigned int cpu, enum cpuhp_state target)
 {
 	int err;
 
@@ -1051,11 +1051,72 @@ static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
 	return err;
 }
 
-int cpu_down(unsigned int cpu)
+/**
+ * cpu_device_down - Bring down a cpu device
+ * @dev: Pointer to the cpu device to offline
+ *
+ * This function is meant to be used by device core cpu subsystem only.
+ *
+ * Other subsystems should use remove_cpu() instead.
+ */
+int cpu_device_down(struct device *dev)
 {
-	return do_cpu_down(cpu, CPUHP_OFFLINE);
+	return cpu_down(dev->id, CPUHP_OFFLINE);
+}
+
+int remove_cpu(unsigned int cpu)
+{
+	int ret;
+
+	lock_device_hotplug();
+	ret = device_offline(get_cpu_device(cpu));
+	unlock_device_hotplug();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(remove_cpu);
+
+void smp_shutdown_nonboot_cpus(unsigned int primary_cpu)
+{
+	unsigned int cpu;
+	int error;
+
+	cpu_maps_update_begin();
+
+	/*
+	 * Make certain the cpu I'm about to reboot on is online.
+	 *
+	 * This is inline to what migrate_to_reboot_cpu() already do.
+	 */
+	if (!cpu_online(primary_cpu))
+		primary_cpu = cpumask_first(cpu_online_mask);
+
+	for_each_online_cpu(cpu) {
+		if (cpu == primary_cpu)
+			continue;
+
+		error = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+		if (error) {
+			pr_err("Failed to offline CPU%d - error=%d",
+				cpu, error);
+			break;
+		}
+	}
+
+	/*
+	 * Ensure all but the reboot CPU are offline.
+	 */
+	BUG_ON(num_online_cpus() > 1);
+
+	/*
+	 * Make sure the CPUs won't be enabled by someone else after this
+	 * point. Kexec will reboot to a new kernel shortly resetting
+	 * everything along the way.
+	 */
+	cpu_hotplug_disabled++;
+
+	cpu_maps_update_done();
 }
-EXPORT_SYMBOL(cpu_down);
 
 #else
 #define takedown_cpu		NULL
@@ -1124,8 +1185,8 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
 	}
 
 	/*
-	 * The caller of do_cpu_up might have raced with another
-	 * caller. Ignore it for now.
+	 * The caller of cpu_up() might have raced with another
+	 * caller. Nothing to do.
 	 */
 	if (st->state >= target)
 		goto out;
@@ -1169,7 +1230,7 @@ out:
 	return ret;
 }
 
-static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
+static int cpu_up(unsigned int cpu, enum cpuhp_state target)
 {
 	int err = 0;
 
@@ -1203,16 +1264,70 @@ out:
 	return err;
 }
 
-int cpu_up(unsigned int cpu)
+/**
+ * cpu_device_up - Bring up a cpu device
+ * @dev: Pointer to the cpu device to online
+ *
+ * This function is meant to be used by device core cpu subsystem only.
+ *
+ * Other subsystems should use add_cpu() instead.
+ */
+int cpu_device_up(struct device *dev)
 {
-	return do_cpu_up(cpu, CPUHP_ONLINE);
+	return cpu_up(dev->id, CPUHP_ONLINE);
+}
+
+int add_cpu(unsigned int cpu)
+{
+	int ret;
+
+	lock_device_hotplug();
+	ret = device_online(get_cpu_device(cpu));
+	unlock_device_hotplug();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(add_cpu);
+
+/**
+ * bringup_hibernate_cpu - Bring up the CPU that we hibernated on
+ * @sleep_cpu: The cpu we hibernated on and should be brought up.
+ *
+ * On some architectures like arm64, we can hibernate on any CPU, but on
+ * wake up the CPU we hibernated on might be offline as a side effect of
+ * using maxcpus= for example.
+ */
+int bringup_hibernate_cpu(unsigned int sleep_cpu)
+{
+	int ret;
+
+	if (!cpu_online(sleep_cpu)) {
+		pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n");
+		ret = cpu_up(sleep_cpu, CPUHP_ONLINE);
+		if (ret) {
+			pr_err("Failed to bring hibernate-CPU up!\n");
+			return ret;
+		}
+	}
+	return 0;
+}
+
+void bringup_nonboot_cpus(unsigned int setup_max_cpus)
+{
+	unsigned int cpu;
+
+	for_each_present_cpu(cpu) {
+		if (num_online_cpus() >= setup_max_cpus)
+			break;
+		if (!cpu_online(cpu))
+			cpu_up(cpu, CPUHP_ONLINE);
+	}
 }
-EXPORT_SYMBOL_GPL(cpu_up);
 
 #ifdef CONFIG_PM_SLEEP_SMP
 static cpumask_var_t frozen_cpus;
 
-int freeze_secondary_cpus(int primary)
+int __freeze_secondary_cpus(int primary, bool suspend)
 {
 	int cpu, error = 0;
 
@@ -1237,7 +1352,7 @@ int freeze_secondary_cpus(int primary)
 		if (cpu == primary)
 			continue;
 
-		if (pm_wakeup_pending()) {
+		if (suspend && pm_wakeup_pending()) {
 			pr_info("Wakeup pending. Abort CPU freeze\n");
 			error = -EBUSY;
 			break;
@@ -2028,9 +2143,9 @@ static ssize_t write_cpuhp_target(struct device *dev,
 		goto out;
 
 	if (st->state < target)
-		ret = do_cpu_up(dev->id, target);
+		ret = cpu_up(dev->id, target);
 	else
-		ret = do_cpu_down(dev->id, target);
+		ret = cpu_down(dev->id, target);
 out:
 	unlock_device_hotplug();
 	return ret ? ret : count;

kernel/sched/core.c

@@ -269,7 +269,6 @@ static void __hrtick_start(void *arg)
 
 	rq_lock(rq, &rf);
 	__hrtick_restart(rq);
-	rq->hrtick_csd_pending = 0;
 	rq_unlock(rq, &rf);
 }
 
@@ -293,12 +292,10 @@ void hrtick_start(struct rq *rq, u64 delay)
 
 	hrtimer_set_expires(timer, time);
 
-	if (rq == this_rq()) {
+	if (rq == this_rq())
 		__hrtick_restart(rq);
-	} else if (!rq->hrtick_csd_pending) {
+	else
 		smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
-		rq->hrtick_csd_pending = 1;
-	}
 }
 
 #else
@@ -322,8 +319,6 @@ void hrtick_start(struct rq *rq, u64 delay)
 static void hrtick_rq_init(struct rq *rq)
 {
 #ifdef CONFIG_SMP
-	rq->hrtick_csd_pending = 0;
-
 	rq->hrtick_csd.flags = 0;
 	rq->hrtick_csd.func = __hrtick_start;
 	rq->hrtick_csd.info = rq;

kernel/sched/sched.h

@@ -992,7 +992,6 @@ struct rq {
 
 #ifdef CONFIG_SCHED_HRTICK
 #ifdef CONFIG_SMP
-	int			hrtick_csd_pending;
 	call_single_data_t	hrtick_csd;
 #endif
 	struct hrtimer		hrtick_timer;

kernel/smp.c

@@ -329,6 +329,11 @@ EXPORT_SYMBOL(smp_call_function_single);
  * (ie: embedded in an object) and is responsible for synchronizing it
  * such that the IPIs performed on the @csd are strictly serialized.
  *
+ * If the function is called with one csd which has not yet been
+ * processed by previous call to smp_call_function_single_async(), the
+ * function will return immediately with -EBUSY showing that the csd
+ * object is still in progress.
+ *
  * NOTE: Be careful, there is unfortunately no current debugging facility to
  * validate the correctness of this serialization.
  */
@@ -338,14 +343,17 @@ int smp_call_function_single_async(int cpu, call_single_data_t *csd)
 
 	preempt_disable();
 
-	/* We could deadlock if we have to wait here with interrupts disabled! */
-	if (WARN_ON_ONCE(csd->flags & CSD_FLAG_LOCK))
-		csd_lock_wait(csd);
+	if (csd->flags & CSD_FLAG_LOCK) {
+		err = -EBUSY;
+		goto out;
+	}
 
 	csd->flags = CSD_FLAG_LOCK;
 	smp_wmb();
 
 	err = generic_exec_single(cpu, csd, csd->func, csd->info);
+
+out:
 	preempt_enable();
 
 	return err;
@@ -589,20 +597,13 @@ void __init setup_nr_cpu_ids(void)
 void __init smp_init(void)
 {
 	int num_nodes, num_cpus;
-	unsigned int cpu;
 
 	idle_threads_init();
 	cpuhp_threads_init();
 
 	pr_info("Bringing up secondary CPUs ...\n");
 
-	/* FIXME: This should be done in userspace --RR */
-	for_each_present_cpu(cpu) {
-		if (num_online_cpus() >= setup_max_cpus)
-			break;
-		if (!cpu_online(cpu))
-			cpu_up(cpu);
-	}
+	bringup_nonboot_cpus(setup_max_cpus);
 
 	num_nodes = num_online_nodes();
 	num_cpus  = num_online_cpus();

kernel/torture.c

@@ -101,7 +101,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 			 torture_type, cpu);
 	starttime = jiffies;
 	(*n_offl_attempts)++;
-	ret = cpu_down(cpu);
+	ret = remove_cpu(cpu);
 	if (ret) {
 		s = "";
 		if (!rcu_inkernel_boot_has_ended() && ret == -EBUSY) {
@@ -159,7 +159,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
 			 torture_type, cpu);
 	starttime = jiffies;
 	(*n_onl_attempts)++;
-	ret = cpu_up(cpu);
+	ret = add_cpu(cpu);
 	if (ret) {
 		s = "";
 		if (!rcu_inkernel_boot_has_ended() && ret == -EBUSY) {
@@ -209,17 +209,18 @@ torture_onoff(void *arg)
 	for_each_online_cpu(cpu)
 		maxcpu = cpu;
 	WARN_ON(maxcpu < 0);
-	if (!IS_MODULE(CONFIG_TORTURE_TEST))
+	if (!IS_MODULE(CONFIG_TORTURE_TEST)) {
 		for_each_possible_cpu(cpu) {
 			if (cpu_online(cpu))
 				continue;
-			ret = cpu_up(cpu);
+			ret = add_cpu(cpu);
 			if (ret && verbose) {
 				pr_alert("%s" TORTURE_FLAG
 					 "%s: Initial online %d: errno %d\n",
 					 __func__, torture_type, cpu, ret);
 			}
 		}
+	}
 
 	if (maxcpu == 0) {
 		VERBOSE_TOROUT_STRING("Only one CPU, so CPU-hotplug testing is disabled");