[Xen-devel] [PATCH v3 13/47] xen/sched: add is_running indicator to struct sched_unit

[Juergen Gross <jgross@xxxxxxxx>]

Add an is_running indicator to struct sched_unit which will be set
whenever the unit is being scheduled. Switch scheduler code to use
unit->is_running instead of vcpu->is_running for scheduling decisions.

At the same time introduce a state_entry_time field in struct
sched_unit being updated whenever the is_running indicator is changed.
Use that new field in the schedulers instead of the similar vcpu field.

Signed-off-by: Juergen Gross <jgross@xxxxxxxx>
---
RFC V2:
- fix arm build, don't drop v->is_running
V3:
- avoid holes in structures (Jan Beulich)
---
 xen/common/sched_credit.c  | 12 +++++++-----
 xen/common/sched_credit2.c | 18 +++++++++---------
 xen/common/sched_rt.c      |  2 +-
 xen/common/schedule.c      | 13 ++++++++++---
 xen/include/xen/sched.h    |  6 ++++++
 5 files changed, 33 insertions(+), 18 deletions(-)

diff --git a/xen/common/sched_credit.c b/xen/common/sched_credit.c
index 2bf11b0616..c0f6ef831e 100644
--- a/xen/common/sched_credit.c
+++ b/xen/common/sched_credit.c
@@ -709,7 +709,7 @@ __csched_vcpu_is_migrateable(const struct csched_private 
*prv, struct vcpu *vc,
      * The caller is supposed to have already checked that vc is also
      * not running.
      */
-    ASSERT(!vc->is_running);
+    ASSERT(!vc->sched_unit->is_running);
 
     return !__csched_vcpu_is_cache_hot(prv, svc) &&
            cpumask_test_cpu(dest_cpu, mask);
@@ -1033,7 +1033,8 @@ csched_unit_insert(const struct scheduler *ops, struct 
sched_unit *unit)
 
     lock = unit_schedule_lock_irq(unit);
 
-    if ( !__vcpu_on_runq(svc) && vcpu_runnable(vc) && !vc->is_running )
+    if ( !__vcpu_on_runq(svc) && vcpu_runnable(vc) &&
+         !vc->sched_unit->is_running )
         runq_insert(svc);
 
     unit_schedule_unlock_irq(lock, unit);
@@ -1646,8 +1647,9 @@ csched_runq_steal(int peer_cpu, int cpu, int pri, int 
balance_step)
          * vCPUs with useful soft affinities in some sort of bitmap
          * or counter.
          */
-        if ( vc->is_running || (balance_step == BALANCE_SOFT_AFFINITY &&
-                                !has_soft_affinity(vc->sched_unit)) )
+        if ( vc->sched_unit->is_running ||
+             (balance_step == BALANCE_SOFT_AFFINITY &&
+              !has_soft_affinity(vc->sched_unit)) )
             continue;
 
         affinity_balance_cpumask(vc->sched_unit, balance_step, 
cpumask_scratch);
@@ -1855,7 +1857,7 @@ csched_schedule(
                     (unsigned char *)&d);
     }
 
-    runtime = now - current->runstate.state_entry_time;
+    runtime = now - current->sched_unit->state_entry_time;
     if ( runtime < 0 ) /* Does this ever happen? */
         runtime = 0;
 
diff --git a/xen/common/sched_credit2.c b/xen/common/sched_credit2.c
index 910440d5d9..a6083289f6 100644
--- a/xen/common/sched_credit2.c
+++ b/xen/common/sched_credit2.c
@@ -1284,7 +1284,7 @@ runq_insert(const struct scheduler *ops, struct 
csched2_unit *svc)
 
     ASSERT(&svc->rqd->runq == runq);
     ASSERT(!is_idle_vcpu(svc->vcpu));
-    ASSERT(!svc->vcpu->is_running);
+    ASSERT(!svc->vcpu->sched_unit->is_running);
     ASSERT(!(svc->flags & CSFLAG_scheduled));
 
     list_for_each( iter, runq )
@@ -1341,8 +1341,8 @@ static inline bool is_preemptable(const struct 
csched2_unit *svc,
     if ( ratelimit <= CSCHED2_RATELIMIT_TICKLE_TOLERANCE )
         return true;
 
-    ASSERT(svc->vcpu->is_running);
-    return now - svc->vcpu->runstate.state_entry_time >
+    ASSERT(svc->vcpu->sched_unit->is_running);
+    return now - svc->vcpu->sched_unit->state_entry_time >
            ratelimit - CSCHED2_RATELIMIT_TICKLE_TOLERANCE;
 }
 
@@ -2932,7 +2932,7 @@ csched2_dom_cntl(
                 {
                     svc = csched2_unit(v->sched_unit);
                     lock = unit_schedule_lock(svc->vcpu->sched_unit);
-                    if ( v->is_running )
+                    if ( v->sched_unit->is_running )
                     {
                         unsigned int cpu = v->processor;
                         struct csched2_runqueue_data *rqd = c2rqd(ops, cpu);
@@ -3205,8 +3205,8 @@ csched2_runtime(const struct scheduler *ops, int cpu,
     if ( prv->ratelimit_us )
     {
         s_time_t ratelimit_min = MICROSECS(prv->ratelimit_us);
-        if ( snext->vcpu->is_running )
-            ratelimit_min = snext->vcpu->runstate.state_entry_time +
+        if ( snext->vcpu->sched_unit->is_running )
+            ratelimit_min = snext->vcpu->sched_unit->state_entry_time +
                             MICROSECS(prv->ratelimit_us) - now;
         if ( ratelimit_min > min_time )
             min_time = ratelimit_min;
@@ -3303,7 +3303,7 @@ runq_candidate(struct csched2_runqueue_data *rqd,
      * no point forcing it to do so until rate limiting expires.
      */
     if ( !yield && prv->ratelimit_us && vcpu_runnable(scurr->vcpu) &&
-         (now - scurr->vcpu->runstate.state_entry_time) <
+         (now - scurr->vcpu->sched_unit->state_entry_time) <
           MICROSECS(prv->ratelimit_us) )
     {
         if ( unlikely(tb_init_done) )
@@ -3314,7 +3314,7 @@ runq_candidate(struct csched2_runqueue_data *rqd,
             } d;
             d.dom = scurr->vcpu->domain->domain_id;
             d.vcpu = scurr->vcpu->vcpu_id;
-            d.runtime = now - scurr->vcpu->runstate.state_entry_time;
+            d.runtime = now - scurr->vcpu->sched_unit->state_entry_time;
             __trace_var(TRC_CSCHED2_RATELIMIT, 1,
                         sizeof(d),
                         (unsigned char *)&d);
@@ -3562,7 +3562,7 @@ csched2_schedule(
         if ( snext != scurr )
         {
             ASSERT(snext->rqd == rqd);
-            ASSERT(!snext->vcpu->is_running);
+            ASSERT(!snext->vcpu->sched_unit->is_running);
 
             runq_remove(snext);
             __set_bit(__CSFLAG_scheduled, &snext->flags);
diff --git a/xen/common/sched_rt.c b/xen/common/sched_rt.c
index 8b5ae159b2..a47cc598a9 100644
--- a/xen/common/sched_rt.c
+++ b/xen/common/sched_rt.c
@@ -906,7 +906,7 @@ rt_unit_insert(const struct scheduler *ops, struct 
sched_unit *unit)
     {
         replq_insert(ops, svc);
 
-        if ( !vc->is_running )
+        if ( !unit->is_running )
             runq_insert(ops, svc);
     }
     unit_schedule_unlock_irq(lock, unit);
diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 92a74b731b..05bc42d7e9 100644
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -411,6 +411,8 @@ int sched_init_vcpu(struct vcpu *v, unsigned int processor)
     {
         get_sched_res(v->processor)->curr = unit;
         v->is_running = 1;
+        unit->is_running = 1;
+        unit->state_entry_time = NOW();
     }
     else
     {
@@ -731,7 +733,8 @@ static void vcpu_migrate_finish(struct vcpu *v)
      * context_saved(); and in any case, if the bit is cleared, then
      * someone else has already done the work so we don't need to.
      */
-    if ( v->is_running || !test_bit(_VPF_migrating, &v->pause_flags) )
+    if ( v->sched_unit->is_running ||
+         !test_bit(_VPF_migrating, &v->pause_flags) )
         return;
 
     old_cpu = new_cpu = v->processor;
@@ -785,7 +788,7 @@ static void vcpu_migrate_finish(struct vcpu *v)
      * because they both happen in (different) spinlock regions, and those
      * regions are strictly serialised.
      */
-    if ( v->is_running ||
+    if ( v->sched_unit->is_running ||
          !test_and_clear_bit(_VPF_migrating, &v->pause_flags) )
     {
         sched_spin_unlock_double(old_lock, new_lock, flags);
@@ -1673,8 +1676,10 @@ static void schedule(void)
      * switch, else lost_records resume will not work properly.
      */
 
-    ASSERT(!next->is_running);
+    ASSERT(!next->sched_unit->is_running);
     next->is_running = 1;
+    next->sched_unit->is_running = 1;
+    next->sched_unit->state_entry_time = now;
 
     pcpu_schedule_unlock_irq(lock, cpu);
 
@@ -1696,6 +1701,8 @@ void context_saved(struct vcpu *prev)
     smp_wmb();
 
     prev->is_running = 0;
+    prev->sched_unit->is_running = 0;
+    prev->sched_unit->state_entry_time = NOW();
 
     /* Check for migration request /after/ clearing running flag. */
     smp_mb();
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index 949bb6b696..d4698b3f0d 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -270,8 +270,14 @@ struct sched_unit {
     struct sched_resource *res;
     unsigned int           unit_id;
 
+    /* Currently running on a CPU? */
+    bool                   is_running;
     /* Does soft affinity actually play a role (given hard affinity)? */
     bool                   soft_aff_effective;
+
+    /* Last time unit got (de-)scheduled. */
+    uint64_t               state_entry_time;
+
     /* Bitmask of CPUs on which this VCPU may run. */
     cpumask_var_t          cpu_hard_affinity;
     /* Used to save affinity during temporary pinning. */
-- 
2.16.4


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel