summaryrefslogtreecommitdiffstats
path: root/kernel/cpu.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/cpu.c')
-rw-r--r--kernel/cpu.c74
1 files changed, 13 insertions, 61 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c
index bac70ea54e..563877d6c2 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -54,7 +54,6 @@
* @rollback: Perform a rollback
* @single: Single callback invocation
* @bringup: Single callback bringup or teardown selector
- * @cpu: CPU number
* @node: Remote CPU node; for multi-instance, do a
* single entry callback for install/remove
* @last: For multi-instance rollback, remember how far we got
@@ -1209,52 +1208,6 @@ void __init cpuhp_threads_init(void)
kthread_unpark(this_cpu_read(cpuhp_state.thread));
}
-/*
- *
- * Serialize hotplug trainwrecks outside of the cpu_hotplug_lock
- * protected region.
- *
- * The operation is still serialized against concurrent CPU hotplug via
- * cpu_add_remove_lock, i.e. CPU map protection. But it is _not_
- * serialized against other hotplug related activity like adding or
- * removing of state callbacks and state instances, which invoke either the
- * startup or the teardown callback of the affected state.
- *
- * This is required for subsystems which are unfixable vs. CPU hotplug and
- * evade lock inversion problems by scheduling work which has to be
- * completed _before_ cpu_up()/_cpu_down() returns.
- *
- * Don't even think about adding anything to this for any new code or even
- * drivers. It's only purpose is to keep existing lock order trainwrecks
- * working.
- *
- * For cpu_down() there might be valid reasons to finish cleanups which are
- * not required to be done under cpu_hotplug_lock, but that's a different
- * story and would be not invoked via this.
- */
-static void cpu_up_down_serialize_trainwrecks(bool tasks_frozen)
-{
- /*
- * cpusets delegate hotplug operations to a worker to "solve" the
- * lock order problems. Wait for the worker, but only if tasks are
- * _not_ frozen (suspend, hibernate) as that would wait forever.
- *
- * The wait is required because otherwise the hotplug operation
- * returns with inconsistent state, which could even be observed in
- * user space when a new CPU is brought up. The CPU plug uevent
- * would be delivered and user space reacting on it would fail to
- * move tasks to the newly plugged CPU up to the point where the
- * work has finished because up to that point the newly plugged CPU
- * is not assignable in cpusets/cgroups. On unplug that's not
- * necessarily a visible issue, but it is still inconsistent state,
- * which is the real problem which needs to be "fixed". This can't
- * prevent the transient state between scheduling the work and
- * returning from waiting for it.
- */
- if (!tasks_frozen)
- cpuset_wait_for_hotplug();
-}
-
#ifdef CONFIG_HOTPLUG_CPU
#ifndef arch_clear_mm_cpumask_cpu
#define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm))
@@ -1324,10 +1277,6 @@ static int take_cpu_down(void *_param)
*/
cpuhp_invoke_callback_range_nofail(false, cpu, st, target);
- /* Give up timekeeping duties */
- tick_handover_do_timer();
- /* Remove CPU from timer broadcasting */
- tick_offline_cpu(cpu);
/* Park the stopper thread */
stop_machine_park(cpu);
return 0;
@@ -1403,6 +1352,7 @@ void cpuhp_report_idle_dead(void)
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
BUG_ON(st->state != CPUHP_AP_OFFLINE);
+ tick_assert_timekeeping_handover();
rcutree_report_cpu_dead();
st->state = CPUHP_AP_IDLE_DEAD;
/*
@@ -1498,7 +1448,6 @@ out:
*/
lockup_detector_cleanup();
arch_smt_update();
- cpu_up_down_serialize_trainwrecks(tasks_frozen);
return ret;
}
@@ -1732,7 +1681,6 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
out:
cpus_write_unlock();
arch_smt_update();
- cpu_up_down_serialize_trainwrecks(tasks_frozen);
return ret;
}
@@ -1909,14 +1857,14 @@ static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus)
static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; }
#endif /* CONFIG_HOTPLUG_PARALLEL */
-void __init bringup_nonboot_cpus(unsigned int setup_max_cpus)
+void __init bringup_nonboot_cpus(unsigned int max_cpus)
{
/* Try parallel bringup optimization if enabled */
- if (cpuhp_bringup_cpus_parallel(setup_max_cpus))
+ if (cpuhp_bringup_cpus_parallel(max_cpus))
return;
/* Full per CPU serialized bringup */
- cpuhp_bringup_mask(cpu_present_mask, setup_max_cpus, CPUHP_ONLINE);
+ cpuhp_bringup_mask(cpu_present_mask, max_cpus, CPUHP_ONLINE);
}
#ifdef CONFIG_PM_SLEEP_SMP
@@ -2205,7 +2153,11 @@ static struct cpuhp_step cpuhp_hp_states[] = {
.startup.single = NULL,
.teardown.single = hrtimers_cpu_dying,
},
-
+ [CPUHP_AP_TICK_DYING] = {
+ .name = "tick:dying",
+ .startup.single = NULL,
+ .teardown.single = tick_cpu_dying,
+ },
/* Entry state on starting. Interrupts enabled from here on. Transient
* state for synchronsization */
[CPUHP_AP_ONLINE] = {
@@ -3005,7 +2957,7 @@ static ssize_t control_show(struct device *dev,
return sysfs_emit(buf, "%d\n", cpu_smt_num_threads);
#endif
- return snprintf(buf, PAGE_SIZE - 2, "%s\n", state);
+ return sysfs_emit(buf, "%s\n", state);
}
static ssize_t control_store(struct device *dev, struct device_attribute *attr,
@@ -3018,7 +2970,7 @@ static DEVICE_ATTR_RW(control);
static ssize_t active_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active());
+ return sysfs_emit(buf, "%d\n", sched_smt_active());
}
static DEVICE_ATTR_RO(active);
@@ -3107,10 +3059,10 @@ const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
EXPORT_SYMBOL(cpu_all_bits);
#ifdef CONFIG_INIT_ALL_POSSIBLE
-struct cpumask __cpu_possible_mask __read_mostly
+struct cpumask __cpu_possible_mask __ro_after_init
= {CPU_BITS_ALL};
#else
-struct cpumask __cpu_possible_mask __read_mostly;
+struct cpumask __cpu_possible_mask __ro_after_init;
#endif
EXPORT_SYMBOL(__cpu_possible_mask);