[Xen-devel] [PATCH v3 04/47] xen/sched: introduce struct sched_resource

[Juergen Gross <jgross@suse.com>]

Add a scheduling abstraction layer between physical processors and the
schedulers by introducing a struct sched_resource. Each scheduler unit
running is active on such a scheduler resource. For the time being
there is one struct sched_resource per cpu, but in future there might
be one for each core or socket only.

Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Dario Faggioli <dfaggioli@suse.com>
---
V1:
- add accessor functions
- use DEFINE_PER_CPU_READ_MOSTLY (Dario Faggioli)
V3:
- don't pre-define struct sched_resource in sched.h (Jan Beulich)
- rename res->processor to res->master_cpu (Jan Beulich)
---
 xen/common/sched_credit.c  |  2 ++
 xen/common/sched_credit2.c |  7 +++++++
 xen/common/sched_null.c    |  3 +++
 xen/common/sched_rt.c      |  2 ++
 xen/common/schedule.c      | 19 ++++++++++++++++++-
 xen/include/xen/sched-if.h | 18 ++++++++++++++++++
 xen/include/xen/sched.h    |  1 +
 7 files changed, 51 insertions(+), 1 deletion(-)

diff --git a/xen/common/sched_credit.c b/xen/common/sched_credit.c
index f4371d7c5e..2bc7fa9220 100644
--- a/xen/common/sched_credit.c
+++ b/xen/common/sched_credit.c
@@ -1026,6 +1026,7 @@ csched_unit_insert(const struct scheduler *ops, struct sched_unit *unit)
     lock = vcpu_schedule_lock_irq(vc);
 
     vc->processor = csched_cpu_pick(ops, unit);
+    unit->res = get_sched_res(vc->processor);
 
     spin_unlock_irq(lock);
 
@@ -1662,6 +1663,7 @@ csched_runq_steal(int peer_cpu, int cpu, int pri, int balance_step)
             WARN_ON(vc->is_urgent);
             runq_remove(speer);
             vc->processor = cpu;
+            vc->sched_unit->res = get_sched_res(cpu);
             /*
              * speer will start executing directly on cpu, without having to
              * go through runq_insert(). So we must update the runnable count
diff --git a/xen/common/sched_credit2.c b/xen/common/sched_credit2.c
index 2852a220c4..200de63bee 100644
--- a/xen/common/sched_credit2.c
+++ b/xen/common/sched_credit2.c
@@ -2520,6 +2520,7 @@ static void migrate(const struct scheduler *ops,
                     &trqd->active);
         svc->vcpu->processor = cpumask_cycle(trqd->pick_bias,
                                              cpumask_scratch_cpu(cpu));
+        svc->vcpu->sched_unit->res = get_sched_res(svc->vcpu->processor);
         trqd->pick_bias = svc->vcpu->processor;
         ASSERT(svc->vcpu->processor < nr_cpu_ids);
 
@@ -2775,6 +2776,7 @@ csched2_unit_migrate(
         }
         _runq_deassign(svc);
         vc->processor = new_cpu;
+        unit->res = get_sched_res(new_cpu);
         return;
     }
 
@@ -2795,7 +2797,10 @@ csched2_unit_migrate(
     if ( trqd != svc->rqd )
         migrate(ops, svc, trqd, now);
     else
+    {
         vc->processor = new_cpu;
+        unit->res = get_sched_res(new_cpu);
+    }
 }
 
 static int
@@ -3120,6 +3125,7 @@ csched2_unit_insert(const struct scheduler *ops, struct sched_unit *unit)
     lock = vcpu_schedule_lock_irq(vc);
 
     vc->processor = csched2_cpu_pick(ops, unit);
+    unit->res = get_sched_res(vc->processor);
 
     spin_unlock_irq(lock);
 
@@ -3597,6 +3603,7 @@ csched2_schedule(
         {
             snext->credit += CSCHED2_MIGRATE_COMPENSATION;
             snext->vcpu->processor = cpu;
+            snext->vcpu->sched_unit->res = get_sched_res(cpu);
             SCHED_STAT_CRANK(migrated);
             ret.migrated = 1;
         }
diff --git a/xen/common/sched_null.c b/xen/common/sched_null.c
index bb9fed8aab..c30fe2e443 100644
--- a/xen/common/sched_null.c
+++ b/xen/common/sched_null.c
@@ -337,6 +337,7 @@ static void vcpu_assign(struct null_private *prv, struct vcpu *v,
 
     per_cpu(npc, cpu).vcpu = v;
     v->processor = cpu;
+    v->sched_unit->res = get_sched_res(cpu);
     cpumask_clear_cpu(cpu, &prv->cpus_free);
 
     dprintk(XENLOG_G_INFO, "%d <-- %pv\n", cpu, v);
@@ -457,6 +458,7 @@ static void null_unit_insert(const struct scheduler *ops,
 
  retry:
     cpu = v->processor = pick_cpu(prv, v);
+    unit->res = get_sched_res(cpu);
 
     spin_unlock(lock);
 
@@ -749,6 +751,7 @@ static void null_unit_migrate(const struct scheduler *ops,
      */
  out:
     v->processor = new_cpu;
+    unit->res = get_sched_res(new_cpu);
 }
 
 #ifndef NDEBUG
diff --git a/xen/common/sched_rt.c b/xen/common/sched_rt.c
index dd51613845..3ba76f1c4a 100644
--- a/xen/common/sched_rt.c
+++ b/xen/common/sched_rt.c
@@ -893,6 +893,7 @@ rt_unit_insert(const struct scheduler *ops, struct sched_unit *unit)
 
     /* This is safe because vc isn't yet being scheduled */
     vc->processor = rt_cpu_pick(ops, unit);
+    unit->res = get_sched_res(vc->processor);
 
     lock = vcpu_schedule_lock_irq(vc);
 
@@ -1123,6 +1124,7 @@ rt_schedule(const struct scheduler *ops, s_time_t now, bool_t tasklet_work_sched
         if ( snext->vcpu->processor != cpu )
         {
             snext->vcpu->processor = cpu;
+            snext->vcpu->sched_unit->res = get_sched_res(cpu);
             ret.migrated = 1;
         }
         ret.time = snext->cur_budget; /* invoke the scheduler next time */
diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 614df9d226..2bf7966476 100644
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -67,6 +67,7 @@ static void poll_timer_fn(void *data);
 /* This is global for now so that private implementations can reach it */
 DEFINE_PER_CPU(struct schedule_data, schedule_data);
 DEFINE_PER_CPU(struct scheduler *, scheduler);
+DEFINE_PER_CPU_READ_MOSTLY(struct sched_resource *, sched_res);
 
 /* Scratch space for cpumasks. */
 DEFINE_PER_CPU(cpumask_t, cpumask_scratch);
@@ -89,7 +90,7 @@ sched_idle_switch_sched(struct scheduler *new_ops, unsigned int cpu,
 static int
 sched_idle_cpu_pick(const struct scheduler *ops, const struct sched_unit *unit)
 {
-    return unit->vcpu_list->processor;
+    return unit->res->master_cpu;
 }
 
 static void *
@@ -363,6 +364,7 @@ int sched_init_vcpu(struct vcpu *v, unsigned int processor)
     if ( (unit = sched_alloc_unit(v)) == NULL )
         return 1;
 
+    unit->res = get_sched_res(processor);
     /* Initialise the per-vcpu timers. */
     spin_lock_init(&v->periodic_timer_lock);
     init_timer(&v->periodic_timer, vcpu_periodic_timer_fn,
@@ -478,6 +480,7 @@ int sched_move_domain(struct domain *d, struct cpupool *c)
         sched_set_affinity(v, &cpumask_all, &cpumask_all);
 
         v->processor = new_p;
+        v->sched_unit->res = get_sched_res(new_p);
         /*
          * With v->processor modified we must not
          * - make any further changes assuming we hold the scheduler lock,
@@ -830,12 +833,14 @@ void restore_vcpu_affinity(struct domain *d)
         }
 
         v->processor = cpumask_any(cpumask_scratch_cpu(cpu));
+        v->sched_unit->res = get_sched_res(v->processor);
 
         spin_unlock_irq(lock);
 
         /* v->processor might have changed, so reacquire the lock. */
         lock = vcpu_schedule_lock_irq(v);
         v->processor = sched_pick_cpu(vcpu_scheduler(v), v->sched_unit);
+        v->sched_unit->res = get_sched_res(v->processor);
         spin_unlock_irq(lock);
 
         if ( old_cpu != v->processor )
@@ -1709,6 +1714,13 @@ static void poll_timer_fn(void *data)
 static int cpu_schedule_up(unsigned int cpu)
 {
     struct schedule_data *sd = &per_cpu(schedule_data, cpu);
+    struct sched_resource *res;
+
+    res = xzalloc(struct sched_resource);
+    if ( res == NULL )
+        return -ENOMEM;
+    res->master_cpu = cpu;
+    set_sched_res(cpu, res);
 
     per_cpu(scheduler, cpu) = &sched_idle_ops;
     spin_lock_init(&sd->_lock);
@@ -1722,6 +1734,8 @@ static int cpu_schedule_up(unsigned int cpu)
 
     if ( idle_vcpu[cpu] == NULL )
         vcpu_create(idle_vcpu[0]->domain, cpu, cpu);
+    else
+        idle_vcpu[cpu]->sched_unit->res = res;
 
     if ( idle_vcpu[cpu] == NULL )
         return -ENOMEM;
@@ -1744,6 +1758,9 @@ static void cpu_schedule_down(unsigned int cpu)
     struct schedule_data *sd = &per_cpu(schedule_data, cpu);
 
     kill_timer(&sd->s_timer);
+
+    set_sched_res(cpu, NULL);
+    xfree(sd);
 }
 
 void sched_rm_cpu(unsigned int cpu)
diff --git a/xen/include/xen/sched-if.h b/xen/include/xen/sched-if.h
index 0af89fbd02..b9e2920c66 100644
--- a/xen/include/xen/sched-if.h
+++ b/xen/include/xen/sched-if.h
@@ -44,9 +44,24 @@ struct schedule_data {
 
 #define curr_on_cpu(c)    (per_cpu(schedule_data, c).curr)
 
+struct sched_resource {
+    unsigned int master_cpu;  /* Cpu with lowest id in scheduling resource. */
+};
+
 DECLARE_PER_CPU(struct schedule_data, schedule_data);
 DECLARE_PER_CPU(struct scheduler *, scheduler);
 DECLARE_PER_CPU(struct cpupool *, cpupool);
+DECLARE_PER_CPU(struct sched_resource *, sched_res);
+
+static inline struct sched_resource *get_sched_res(unsigned int cpu)
+{
+    return per_cpu(sched_res, cpu);
+}
+
+static inline void set_sched_res(unsigned int cpu, struct sched_resource *res)
+{
+    per_cpu(sched_res, cpu) = res;
+}
 
 /*
  * Scratch space, for avoiding having too many cpumask_t on the stack.
@@ -334,7 +349,10 @@ static inline void sched_migrate(const struct scheduler *s,
     if ( s->migrate )
         s->migrate(s, unit, cpu);
     else
+    {
         unit->vcpu_list->processor = cpu;
+        unit->res = get_sched_res(cpu);
+    }
 }
 
 static inline int sched_pick_cpu(const struct scheduler *s,
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index 89038337b4..999e43e8cc 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -278,6 +278,7 @@ struct sched_unit {
     struct vcpu           *vcpu_list;
     void                  *priv;      /* scheduler private data */
     struct sched_unit     *next_in_list;
+    struct sched_resource *res;
     unsigned int           unit_id;
 };
 
-- 
2.16.4


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