[v4,45/46] xen/sched: disable scheduling when entering ACPI deep sleep states

Commit Message

Jürgen Groß Sept. 27, 2019, 7 a.m. UTC

When entering deep sleep states all domains are paused resulting in
all cpus only running idle vcpus. This enables us to stop scheduling
completely in order to avoid synchronization problems with core
scheduling when individual cpus are offlined.

Disabling the scheduler is done by replacing the softirq handler
with a dummy scheduling routine only enabling tasklets to run.

Signed-off-by: Juergen Gross <[e-mail]>
Acked-by: Jan Beulich <[e-mail]>
Reviewed-by: Dario Faggioli <[e-mail]>
---
V2: new patch
---
 xen/arch/x86/acpi/power.c |  4 ++++
 xen/common/schedule.c     | 31 +++++++++++++++++++++++++++++--
 xen/include/xen/sched.h   |  2 ++
 3 files changed, 35 insertions(+), 2 deletions(-)

Patch

diff --git a/xen/arch/x86/acpi/power.c b/xen/arch/x86/acpi/power.c
index 269b1408d4..47a6c47bbf 100644
--- a/xen/arch/x86/acpi/power.c
+++ b/xen/arch/x86/acpi/power.c
@@ -145,12 +145,16 @@  static void freeze_domains(void)
     for_each_domain ( d )
         domain_pause(d);
     rcu_read_unlock(&domlist_read_lock);
+
+    scheduler_disable();
 }
 
 static void thaw_domains(void)
 {
     struct domain *d;
 
+    scheduler_enable();
+
     rcu_read_lock(&domlist_read_lock);
     for_each_domain ( d )
     {
diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index d2133558c8..ac840b9dfd 100644
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -89,6 +89,8 @@  extern const struct scheduler *__start_schedulers_array[], *__end_schedulers_arr
 
 static struct scheduler __read_mostly ops;
 
+static bool scheduler_active;
+
 static void sched_set_affinity(
     struct sched_unit *unit, const cpumask_t *hard, const cpumask_t *soft);
 
@@ -2260,6 +2262,13 @@  static struct sched_unit *sched_wait_rendezvous_in(struct sched_unit *prev,
         cpu_relax();
 
         *lock = pcpu_schedule_lock_irq(cpu);
+
+        if ( unlikely(!scheduler_active) )
+        {
+            ASSERT(is_idle_unit(prev));
+            atomic_set(&prev->next_task->rendezvous_out_cnt, 0);
+            prev->rendezvous_in_cnt = 0;
+        }
     }
 
     return prev->next_task;
@@ -2614,14 +2623,32 @@  const cpumask_t *sched_get_opt_cpumask(enum sched_gran opt, unsigned int cpu)
     return mask;
 }
 
+static void schedule_dummy(void)
+{
+    sched_tasklet_check_cpu(smp_processor_id());
+}
+
+void scheduler_disable(void)
+{
+    scheduler_active = false;
+    open_softirq(SCHEDULE_SOFTIRQ, schedule_dummy);
+    open_softirq(SCHED_SLAVE_SOFTIRQ, schedule_dummy);
+}
+
+void scheduler_enable(void)
+{
+    open_softirq(SCHEDULE_SOFTIRQ, schedule);
+    open_softirq(SCHED_SLAVE_SOFTIRQ, sched_slave);
+    scheduler_active = true;
+}
+
 /* Initialise the data structures. */
 void __init scheduler_init(void)
 {
     struct domain *idle_domain;
     int i;
 
-    open_softirq(SCHEDULE_SOFTIRQ, schedule);
-    open_softirq(SCHED_SLAVE_SOFTIRQ, sched_slave);
+    scheduler_enable();
 
     for ( i = 0; i < NUM_SCHEDULERS; i++)
     {
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index a40bd5fb56..629a4c52e0 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -933,6 +933,8 @@  void restore_vcpu_affinity(struct domain *d);
 void vcpu_runstate_get(struct vcpu *v, struct vcpu_runstate_info *runstate);
 uint64_t get_cpu_idle_time(unsigned int cpu);
 void sched_guest_idle(void (*idle) (void), unsigned int cpu);
+void scheduler_enable(void);
+void scheduler_disable(void);
 
 /*
  * Used by idle loop to decide whether there is work to do: