@@ -310,6 +310,36 @@ struct csched2_dom {
uint16_t nr_vcpus;
};
+/*
+ * When a hard affinity change occurs, we may not be able to check some
+ * (any!) of the other runqueues, when looking for the best new processor
+ * for svc (as trylock-s in choose_cpu() can fail). If that happens, we
+ * pick, in order of decreasing preference:
+ * - svc's current pcpu;
+ * - another pcpu from svc's current runq;
+ * - any cpu.
+ */
+static int get_fallback_cpu(struct csched2_vcpu *svc)
+{
+ int cpu;
+
+ if ( likely(cpumask_test_cpu(svc->vcpu->processor,
+ svc->vcpu->cpu_hard_affinity)) )
+ return svc->vcpu->processor;
+
+ cpumask_and(cpumask_scratch, svc->vcpu->cpu_hard_affinity,
+ &svc->rqd->active);
+ cpu = cpumask_first(cpumask_scratch);
+ if ( likely(cpu < nr_cpu_ids) )
+ return cpu;
+
+ cpumask_and(cpumask_scratch, svc->vcpu->cpu_hard_affinity,
+ cpupool_domain_cpumask(svc->vcpu->domain));
+
+ ASSERT(!cpumask_empty(cpumask_scratch));
+
+ return cpumask_first(cpumask_scratch);
+}
/*
* Time-to-credit, credit-to-time.
@@ -543,8 +573,9 @@ runq_tickle(const struct scheduler *ops, unsigned int cpu, struct csched2_vcpu *
goto tickle;
}
- /* Get a mask of idle, but not tickled */
+ /* Get a mask of idle, but not tickled, that new is allowed to run on. */
cpumask_andnot(&mask, &rqd->idle, &rqd->tickled);
+ cpumask_and(&mask, &mask, new->vcpu->cpu_hard_affinity);
/* If it's not empty, choose one */
i = cpumask_cycle(cpu, &mask);
@@ -555,9 +586,11 @@ runq_tickle(const struct scheduler *ops, unsigned int cpu, struct csched2_vcpu *
}
/* Otherwise, look for the non-idle cpu with the lowest credit,
- * skipping cpus which have been tickled but not scheduled yet */
+ * skipping cpus which have been tickled but not scheduled yet,
+ * that new is allowed to run on. */
cpumask_andnot(&mask, &rqd->active, &rqd->idle);
cpumask_andnot(&mask, &mask, &rqd->tickled);
+ cpumask_and(&mask, &mask, new->vcpu->cpu_hard_affinity);
for_each_cpu(i, &mask)
{
@@ -1107,9 +1140,8 @@ choose_cpu(const struct scheduler *ops, struct vcpu *vc)
d2printk("%pv -\n", svc->vcpu);
clear_bit(__CSFLAG_runq_migrate_request, &svc->flags);
}
- /* Leave it where it is for now. When we actually pay attention
- * to affinity we'll have to figure something out... */
- return vc->processor;
+
+ return get_fallback_cpu(svc);
}
/* First check to see if we're here because someone else suggested a place
@@ -1120,45 +1152,56 @@ choose_cpu(const struct scheduler *ops, struct vcpu *vc)
{
printk("%s: Runqueue migrate aborted because target runqueue disappeared!\n",
__func__);
- /* Fall-through to normal cpu pick */
}
else
{
- d2printk("%pv +\n", svc->vcpu);
- new_cpu = cpumask_cycle(vc->processor, &svc->migrate_rqd->active);
- goto out_up;
+ cpumask_and(cpumask_scratch, vc->cpu_hard_affinity,
+ &svc->migrate_rqd->active);
+ new_cpu = cpumask_any(cpumask_scratch);
+ if ( new_cpu < nr_cpu_ids )
+ {
+ d2printk("%pv +\n", svc->vcpu);
+ goto out_up;
+ }
}
+ /* Fall-through to normal cpu pick */
}
- /* FIXME: Pay attention to cpu affinity */
-
min_avgload = MAX_LOAD;
/* Find the runqueue with the lowest instantaneous load */
for_each_cpu(i, &prv->active_queues)
{
struct csched2_runqueue_data *rqd;
- s_time_t rqd_avgload;
+ s_time_t rqd_avgload = MAX_LOAD;
rqd = prv->rqd + i;
- /* If checking a different runqueue, grab the lock,
- * read the avg, and then release the lock.
+ /*
+ * If checking a different runqueue, grab the lock, check hard
+ * affinity, read the avg, and then release the lock.
*
* If on our own runqueue, don't grab or release the lock;
* but subtract our own load from the runqueue load to simulate
- * impartiality */
+ * impartiality.
+ *
+ * Note that, if svc's hard affinity has changed, this is the
+ * first time when we see such change, so it is indeed possible
+ * that none of the cpus in svc's current runqueue is in our
+ * (new) hard affinity!
+ */
if ( rqd == svc->rqd )
{
- rqd_avgload = rqd->b_avgload - svc->avgload;
+ if ( cpumask_intersects(vc->cpu_hard_affinity, &rqd->active) )
+ rqd_avgload = rqd->b_avgload - svc->avgload;
}
else if ( spin_trylock(&rqd->lock) )
{
- rqd_avgload = rqd->b_avgload;
+ if ( cpumask_intersects(vc->cpu_hard_affinity, &rqd->active) )
+ rqd_avgload = rqd->b_avgload;
+
spin_unlock(&rqd->lock);
}
- else
- continue;
if ( rqd_avgload < min_avgload )
{
@@ -1167,12 +1210,14 @@ choose_cpu(const struct scheduler *ops, struct vcpu *vc)
}
}
- /* We didn't find anyone (most likely because of spinlock contention); leave it where it is */
+ /* We didn't find anyone (most likely because of spinlock contention). */
if ( min_rqi == -1 )
- new_cpu = vc->processor;
+ new_cpu = get_fallback_cpu(svc);
else
{
- new_cpu = cpumask_cycle(vc->processor, &prv->rqd[min_rqi].active);
+ cpumask_and(cpumask_scratch, vc->cpu_hard_affinity,
+ &prv->rqd[min_rqi].active);
+ new_cpu = cpumask_any(cpumask_scratch);
BUG_ON(new_cpu >= nr_cpu_ids);
}
@@ -1252,7 +1297,12 @@ static void migrate(const struct scheduler *ops,
on_runq=1;
}
__runq_deassign(svc);
- svc->vcpu->processor = cpumask_any(&trqd->active);
+
+ cpumask_and(cpumask_scratch, svc->vcpu->cpu_hard_affinity,
+ &trqd->active);
+ svc->vcpu->processor = cpumask_any(cpumask_scratch);
+ BUG_ON(svc->vcpu->processor >= nr_cpu_ids);
+
__runq_assign(svc, trqd);
if ( on_runq )
{
@@ -1266,6 +1316,17 @@ static void migrate(const struct scheduler *ops,
}
}
+/*
+ * It makes sense considering migrating svc to rqd, if:
+ * - svc is not already flagged to migrate,
+ * - if svc is allowed to run on at least one of the pcpus of rqd.
+ */
+static bool_t vcpu_is_migrateable(struct csched2_vcpu *svc,
+ struct csched2_runqueue_data *rqd)
+{
+ return !(svc->flags & CSFLAG_runq_migrate_request) &&
+ cpumask_intersects(svc->vcpu->cpu_hard_affinity, &rqd->active);
+}
static void balance_load(const struct scheduler *ops, int cpu, s_time_t now)
{
@@ -1374,8 +1435,7 @@ retry:
__update_svc_load(ops, push_svc, 0, now);
- /* Skip this one if it's already been flagged to migrate */
- if ( push_svc->flags & CSFLAG_runq_migrate_request )
+ if ( !vcpu_is_migrateable(push_svc, st.orqd) )
continue;
list_for_each( pull_iter, &st.orqd->svc )
@@ -1387,8 +1447,7 @@ retry:
__update_svc_load(ops, pull_svc, 0, now);
}
- /* Skip this one if it's already been flagged to migrate */
- if ( pull_svc->flags & CSFLAG_runq_migrate_request )
+ if ( !vcpu_is_migrateable(pull_svc, st.lrqd) )
continue;
consider(&st, push_svc, pull_svc);
@@ -1404,8 +1463,7 @@ retry:
{
struct csched2_vcpu * pull_svc = list_entry(pull_iter, struct csched2_vcpu, rqd_elem);
- /* Skip this one if it's already been flagged to migrate */
- if ( pull_svc->flags & CSFLAG_runq_migrate_request )
+ if ( !vcpu_is_migrateable(pull_svc, st.lrqd) )
continue;
/* Consider pull only */
@@ -1444,11 +1502,22 @@ csched2_vcpu_migrate(
/* Check if new_cpu is valid */
BUG_ON(!cpumask_test_cpu(new_cpu, &CSCHED2_PRIV(ops)->initialized));
+ ASSERT(cpumask_test_cpu(new_cpu, vc->cpu_hard_affinity));
trqd = RQD(ops, new_cpu);
+ /*
+ * Do the actual movement toward new_cpu, and update vc->processor.
+ * If we are changing runqueue, migrate() takes care of everything.
+ * If we are not changing runqueue, we need to update vc->processor
+ * here. In fact, if, for instance, we are here because the vcpu's
+ * hard affinity changed, we don't want to risk leaving vc->processor
+ * pointing to a pcpu where we can't run any longer.
+ */
if ( trqd != svc->rqd )
migrate(ops, svc, trqd, NOW());
+ else
+ vc->processor = new_cpu;
}
static int
@@ -1671,6 +1740,10 @@ runq_candidate(struct csched2_runqueue_data *rqd,
{
struct csched2_vcpu * svc = list_entry(iter, struct csched2_vcpu, runq_elem);
+ /* Only consider vcpus that are allowed to run on this processor. */
+ if ( !cpumask_test_cpu(cpu, svc->vcpu->cpu_hard_affinity) )
+ continue;
+
/* If this is on a different processor, don't pull it unless
* its credit is at least CSCHED2_MIGRATE_RESIST higher. */
if ( svc->vcpu->processor != cpu