Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/kernel/cpu.c b/kernel/cpu.c
index e2cad3e..06c0094 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -3,6 +3,7 @@
*
* This code is licenced under the GPL.
*/
+#include <linux/sched/mm.h>
#include <linux/proc_fs.h>
#include <linux/smp.h>
#include <linux/init.h>
@@ -31,6 +32,7 @@
#include <linux/relay.h>
#include <linux/slab.h>
#include <linux/percpu-rwsem.h>
+#include <linux/cpuset.h>
#include <trace/events/power.h>
#define CREATE_TRACE_POINTS
@@ -525,8 +527,7 @@
if (WARN_ON_ONCE((!cpu_online(cpu))))
return -ECANCELED;
- /* Unpark the stopper thread and the hotplug thread of the target cpu */
- stop_machine_unpark(cpu);
+ /* Unpark the hotplug thread of the target cpu */
kthread_unpark(st->thread);
/*
@@ -565,6 +566,21 @@
return bringup_wait_for_ap(cpu);
}
+static int finish_cpu(unsigned int cpu)
+{
+ struct task_struct *idle = idle_thread_get(cpu);
+ struct mm_struct *mm = idle->active_mm;
+
+ /*
+ * idle_task_exit() will have switched to &init_mm, now
+ * clean up any remaining active_mm state.
+ */
+ if (mm != &init_mm)
+ idle->active_mm = &init_mm;
+ mmdrop(mm);
+ return 0;
+}
+
/*
* Hotplug state machine related functions
*/
@@ -799,7 +815,57 @@
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))
+#endif
+
/**
* clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
* @cpu: a CPU id
@@ -835,7 +901,7 @@
t = find_lock_task_mm(p);
if (!t)
continue;
- cpumask_clear_cpu(cpu, mm_cpumask(t->mm));
+ arch_clear_mm_cpumask_cpu(cpu, t->mm);
task_unlock(t);
}
rcu_read_unlock();
@@ -1032,6 +1098,7 @@
*/
lockup_detector_cleanup();
arch_smt_update();
+ cpu_up_down_serialize_trainwrecks(tasks_frozen);
return ret;
}
@@ -1089,8 +1156,8 @@
/*
* Called from the idle task. Wake up the controlling task which brings the
- * stopper and the hotplug thread of the upcoming CPU up and then delegates
- * the rest of the online bringup to the hotplug thread.
+ * hotplug thread of the upcoming CPU up and then delegates the rest of the
+ * online bringup to the hotplug thread.
*/
void cpuhp_online_idle(enum cpuhp_state state)
{
@@ -1100,6 +1167,12 @@
if (state != CPUHP_AP_ONLINE_IDLE)
return;
+ /*
+ * Unpart the stopper thread before we start the idle loop (and start
+ * scheduling); this ensures the stopper task is always available.
+ */
+ stop_machine_unpark(smp_processor_id());
+
st->state = CPUHP_AP_ONLINE_IDLE;
complete_ap_thread(st, true);
}
@@ -1161,6 +1234,7 @@
out:
cpus_write_unlock();
arch_smt_update();
+ cpu_up_down_serialize_trainwrecks(tasks_frozen);
return ret;
}
@@ -1207,7 +1281,7 @@
#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;
@@ -1232,7 +1306,7 @@
if (cpu == primary)
continue;
- if (pm_wakeup_pending()) {
+ if (suspend && pm_wakeup_pending()) {
pr_info("Wakeup pending. Abort CPU freeze\n");
error = -EBUSY;
break;
@@ -1429,7 +1503,7 @@
[CPUHP_BRINGUP_CPU] = {
.name = "cpu:bringup",
.startup.single = bringup_cpu,
- .teardown.single = NULL,
+ .teardown.single = finish_cpu,
.cant_stop = true,
},
/* Final state before CPU kills itself */
@@ -1909,6 +1983,78 @@
}
EXPORT_SYMBOL(__cpuhp_remove_state);
+#ifdef CONFIG_HOTPLUG_SMT
+static void cpuhp_offline_cpu_device(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
+
+ dev->offline = true;
+ /* Tell user space about the state change */
+ kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+}
+
+static void cpuhp_online_cpu_device(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
+
+ dev->offline = false;
+ /* Tell user space about the state change */
+ kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+{
+ int cpu, ret = 0;
+
+ cpu_maps_update_begin();
+ for_each_online_cpu(cpu) {
+ if (topology_is_primary_thread(cpu))
+ continue;
+ ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+ if (ret)
+ break;
+ /*
+ * As this needs to hold the cpu maps lock it's impossible
+ * to call device_offline() because that ends up calling
+ * cpu_down() which takes cpu maps lock. cpu maps lock
+ * needs to be held as this might race against in kernel
+ * abusers of the hotplug machinery (thermal management).
+ *
+ * So nothing would update device:offline state. That would
+ * leave the sysfs entry stale and prevent onlining after
+ * smt control has been changed to 'off' again. This is
+ * called under the sysfs hotplug lock, so it is properly
+ * serialized against the regular offline usage.
+ */
+ cpuhp_offline_cpu_device(cpu);
+ }
+ if (!ret)
+ cpu_smt_control = ctrlval;
+ cpu_maps_update_done();
+ return ret;
+}
+
+int cpuhp_smt_enable(void)
+{
+ int cpu, ret = 0;
+
+ cpu_maps_update_begin();
+ cpu_smt_control = CPU_SMT_ENABLED;
+ for_each_present_cpu(cpu) {
+ /* Skip online CPUs and CPUs on offline nodes */
+ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+ continue;
+ ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+ if (ret)
+ break;
+ /* See comment in cpuhp_smt_disable() */
+ cpuhp_online_cpu_device(cpu);
+ }
+ cpu_maps_update_done();
+ return ret;
+}
+#endif
+
#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
static ssize_t show_cpuhp_state(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -2063,77 +2209,6 @@
#ifdef CONFIG_HOTPLUG_SMT
-static void cpuhp_offline_cpu_device(unsigned int cpu)
-{
- struct device *dev = get_cpu_device(cpu);
-
- dev->offline = true;
- /* Tell user space about the state change */
- kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
-}
-
-static void cpuhp_online_cpu_device(unsigned int cpu)
-{
- struct device *dev = get_cpu_device(cpu);
-
- dev->offline = false;
- /* Tell user space about the state change */
- kobject_uevent(&dev->kobj, KOBJ_ONLINE);
-}
-
-int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
-{
- int cpu, ret = 0;
-
- cpu_maps_update_begin();
- for_each_online_cpu(cpu) {
- if (topology_is_primary_thread(cpu))
- continue;
- ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
- if (ret)
- break;
- /*
- * As this needs to hold the cpu maps lock it's impossible
- * to call device_offline() because that ends up calling
- * cpu_down() which takes cpu maps lock. cpu maps lock
- * needs to be held as this might race against in kernel
- * abusers of the hotplug machinery (thermal management).
- *
- * So nothing would update device:offline state. That would
- * leave the sysfs entry stale and prevent onlining after
- * smt control has been changed to 'off' again. This is
- * called under the sysfs hotplug lock, so it is properly
- * serialized against the regular offline usage.
- */
- cpuhp_offline_cpu_device(cpu);
- }
- if (!ret)
- cpu_smt_control = ctrlval;
- cpu_maps_update_done();
- return ret;
-}
-
-int cpuhp_smt_enable(void)
-{
- int cpu, ret = 0;
-
- cpu_maps_update_begin();
- cpu_smt_control = CPU_SMT_ENABLED;
- for_each_present_cpu(cpu) {
- /* Skip online CPUs and CPUs on offline nodes */
- if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
- continue;
- ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
- if (ret)
- break;
- /* See comment in cpuhp_smt_disable() */
- cpuhp_online_cpu_device(cpu);
- }
- cpu_maps_update_done();
- return ret;
-}
-
-
static ssize_t
__store_smt_control(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)