Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 3f8c786..2593a73 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -54,17 +54,18 @@
static noinline int __cpuidle cpu_idle_poll(void)
{
- rcu_idle_enter();
- trace_cpu_idle_rcuidle(0, smp_processor_id());
- local_irq_enable();
+ trace_cpu_idle(0, smp_processor_id());
stop_critical_timings();
+ rcu_idle_enter();
+ local_irq_enable();
while (!tif_need_resched() &&
- (cpu_idle_force_poll || tick_check_broadcast_expired()))
+ (cpu_idle_force_poll || tick_check_broadcast_expired()))
cpu_relax();
- start_critical_timings();
- trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
+
rcu_idle_exit();
+ start_critical_timings();
+ trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
return 1;
}
@@ -77,7 +78,7 @@
void __weak arch_cpu_idle(void)
{
cpu_idle_force_poll = 1;
- local_irq_enable();
+ raw_local_irq_enable();
}
/**
@@ -90,12 +91,52 @@
if (current_clr_polling_and_test()) {
local_irq_enable();
} else {
+
+ trace_cpu_idle(1, smp_processor_id());
stop_critical_timings();
+
+ /*
+ * arch_cpu_idle() is supposed to enable IRQs, however
+ * we can't do that because of RCU and tracing.
+ *
+ * Trace IRQs enable here, then switch off RCU, and have
+ * arch_cpu_idle() use raw_local_irq_enable(). Note that
+ * rcu_idle_enter() relies on lockdep IRQ state, so switch that
+ * last -- this is very similar to the entry code.
+ */
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare(_THIS_IP_);
+ rcu_idle_enter();
+ lockdep_hardirqs_on(_THIS_IP_);
+
arch_cpu_idle();
+
+ /*
+ * OK, so IRQs are enabled here, but RCU needs them disabled to
+ * turn itself back on.. funny thing is that disabling IRQs
+ * will cause tracing, which needs RCU. Jump through hoops to
+ * make it 'work'.
+ */
+ raw_local_irq_disable();
+ lockdep_hardirqs_off(_THIS_IP_);
+ rcu_idle_exit();
+ lockdep_hardirqs_on(_THIS_IP_);
+ raw_local_irq_enable();
+
start_critical_timings();
+ trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
}
}
+static int call_cpuidle_s2idle(struct cpuidle_driver *drv,
+ struct cpuidle_device *dev)
+{
+ if (current_clr_polling_and_test())
+ return -EBUSY;
+
+ return cpuidle_enter_s2idle(drv, dev);
+}
+
static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
int next_state)
{
@@ -104,7 +145,7 @@
* update no idle residency and return.
*/
if (current_clr_polling_and_test()) {
- dev->last_residency = 0;
+ dev->last_residency_ns = 0;
local_irq_enable();
return -EBUSY;
}
@@ -149,7 +190,6 @@
if (cpuidle_not_available(drv, dev)) {
tick_nohz_idle_stop_tick();
- rcu_idle_enter();
default_idle_call();
goto exit_idle;
@@ -158,30 +198,30 @@
/*
* Suspend-to-idle ("s2idle") is a system state in which all user space
* has been frozen, all I/O devices have been suspended and the only
- * activity happens here and in iterrupts (if any). In that case bypass
+ * activity happens here and in interrupts (if any). In that case bypass
* the cpuidle governor and go stratight for the deepest idle state
* available. Possibly also suspend the local tick and the entire
* timekeeping to prevent timer interrupts from kicking us out of idle
* until a proper wakeup interrupt happens.
*/
- if (idle_should_enter_s2idle() || dev->use_deepest_state) {
+ if (idle_should_enter_s2idle() || dev->forced_idle_latency_limit_ns) {
+ u64 max_latency_ns;
+
if (idle_should_enter_s2idle()) {
- rcu_idle_enter();
- entered_state = cpuidle_enter_s2idle(drv, dev);
- if (entered_state > 0) {
- local_irq_enable();
+ entered_state = call_cpuidle_s2idle(drv, dev);
+ if (entered_state > 0)
goto exit_idle;
- }
- rcu_idle_exit();
+ max_latency_ns = U64_MAX;
+ } else {
+ max_latency_ns = dev->forced_idle_latency_limit_ns;
}
tick_nohz_idle_stop_tick();
- rcu_idle_enter();
- next_state = cpuidle_find_deepest_state(drv, dev);
+ next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
call_cpuidle(drv, dev, next_state);
} else {
bool stop_tick = true;
@@ -196,8 +236,6 @@
else
tick_nohz_idle_retain_tick();
- rcu_idle_enter();
-
entered_state = call_cpuidle(drv, dev, next_state);
/*
* Give the governor an opportunity to reflect on the outcome
@@ -213,8 +251,6 @@
*/
if (WARN_ON_ONCE(irqs_disabled()))
local_irq_enable();
-
- rcu_idle_exit();
}
/*
@@ -284,7 +320,11 @@
*/
smp_mb__after_atomic();
- sched_ttwu_pending();
+ /*
+ * RCU relies on this call to be done outside of an RCU read-side
+ * critical section.
+ */
+ flush_smp_call_function_from_idle();
schedule_idle();
if (unlikely(klp_patch_pending(current)))
@@ -312,7 +352,7 @@
return HRTIMER_NORESTART;
}
-void play_idle(unsigned long duration_us)
+void play_idle_precise(u64 duration_ns, u64 latency_ns)
{
struct idle_timer it;
@@ -324,29 +364,29 @@
WARN_ON_ONCE(current->nr_cpus_allowed != 1);
WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
- WARN_ON_ONCE(!duration_us);
+ WARN_ON_ONCE(!duration_ns);
rcu_sleep_check();
preempt_disable();
current->flags |= PF_IDLE;
- cpuidle_use_deepest_state(true);
+ cpuidle_use_deepest_state(latency_ns);
it.done = 0;
- hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
it.timer.function = idle_inject_timer_fn;
- hrtimer_start(&it.timer, ns_to_ktime(duration_us * NSEC_PER_USEC),
- HRTIMER_MODE_REL_PINNED);
+ hrtimer_start(&it.timer, ns_to_ktime(duration_ns),
+ HRTIMER_MODE_REL_PINNED_HARD);
while (!READ_ONCE(it.done))
do_idle();
- cpuidle_use_deepest_state(false);
+ cpuidle_use_deepest_state(0);
current->flags &= ~PF_IDLE;
preempt_fold_need_resched();
preempt_enable();
}
-EXPORT_SYMBOL_GPL(play_idle);
+EXPORT_SYMBOL_GPL(play_idle_precise);
void cpu_startup_entry(enum cpuhp_state state)
{
@@ -392,14 +432,10 @@
schedstat_inc(rq->sched_goidle);
}
-static struct task_struct *
-pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+struct task_struct *pick_next_task_idle(struct rq *rq)
{
struct task_struct *next = rq->idle;
- if (prev)
- put_prev_task(rq, prev);
-
set_next_task_idle(rq, next, true);
return next;
@@ -441,11 +477,6 @@
BUG();
}
-static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
-{
- return 0;
-}
-
static void update_curr_idle(struct rq *rq)
{
}
@@ -453,8 +484,8 @@
/*
* Simple, special scheduling class for the per-CPU idle tasks:
*/
-const struct sched_class idle_sched_class = {
- /* .next is NULL */
+const struct sched_class idle_sched_class
+ __section("__idle_sched_class") = {
/* no enqueue/yield_task for idle tasks */
/* dequeue is not valid, we print a debug message there: */
@@ -474,8 +505,6 @@
.task_tick = task_tick_idle,
- .get_rr_interval = get_rr_interval_idle,
-
.prio_changed = prio_changed_idle,
.switched_to = switched_to_idle,
.update_curr = update_curr_idle,