xen/sched: move some per-vcpu items to struct sched_unit

Affinities are scheduler specific attributes, they should be per
scheduling unit. So move all affinity related fields in struct vcpu
to struct sched_unit. While at it switch affinity related functions in
sched-if.h to use a pointer to sched_unit instead to vcpu as parameter.

The affinity_broken flag must be kept per vcpu as it is related to
guest actions on specific vcpus. When support of multiple vcpus per
sched_unit is being added, a unit is regarded as being subject to
"broken affinity" when any of its vcpus has the affinity_broken flag
set.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Dario Faggioli <dfaggioli@suse.com>

xen/common/domain.c

@@ -132,10 +132,6 @@ static void vcpu_info_reset(struct vcpu *v)
 
 static void vcpu_destroy(struct vcpu *v)
 {
-    free_cpumask_var(v->cpu_hard_affinity);
-    free_cpumask_var(v->cpu_hard_affinity_saved);
-    free_cpumask_var(v->cpu_soft_affinity);
-
     free_vcpu_struct(v);
 }
 
@@ -159,11 +155,6 @@ struct vcpu *vcpu_create(
 
     grant_table_init_vcpu(v);
 
-    if ( !zalloc_cpumask_var(&v->cpu_hard_affinity) ||
-         !zalloc_cpumask_var(&v->cpu_hard_affinity_saved) ||
-         !zalloc_cpumask_var(&v->cpu_soft_affinity) )
-        goto fail;
-
     if ( is_idle_domain(d) )
     {
         v->runstate.state = RUNSTATE_running;
@@ -203,7 +194,6 @@ struct vcpu *vcpu_create(
     sched_destroy_vcpu(v);
  fail_wq:
     destroy_waitqueue_vcpu(v);
- fail:
     vcpu_destroy(v);
 
     return NULL;
@@ -614,9 +604,10 @@ void domain_update_node_affinity(struct domain *d)
          */
         for_each_vcpu ( d, v )
         {
-            cpumask_or(dom_cpumask, dom_cpumask, v->cpu_hard_affinity);
+            cpumask_or(dom_cpumask, dom_cpumask,
+                       v->sched_unit->cpu_hard_affinity);
             cpumask_or(dom_cpumask_soft, dom_cpumask_soft,
-                       v->cpu_soft_affinity);
+                       v->sched_unit->cpu_soft_affinity);
         }
         /* Filter out non-online cpus */
         cpumask_and(dom_cpumask, dom_cpumask, online);

xen/common/domctl.c

@@ -606,6 +606,7 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
     case XEN_DOMCTL_getvcpuaffinity:
     {
         struct vcpu *v;
+        const struct sched_unit *unit;
         struct xen_domctl_vcpuaffinity *vcpuaff = &op->u.vcpuaffinity;
 
         ret = -EINVAL;
@@ -616,6 +617,7 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
         if ( (v = d->vcpu[vcpuaff->vcpu]) == NULL )
             break;
 
+        unit = v->sched_unit;
         ret = -EINVAL;
         if ( vcpuaffinity_params_invalid(vcpuaff) )
             break;
@@ -635,7 +637,7 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
                 ret = -ENOMEM;
                 break;
             }
-            cpumask_copy(old_affinity, v->cpu_hard_affinity);
+            cpumask_copy(old_affinity, unit->cpu_hard_affinity);
 
             if ( !alloc_cpumask_var(&new_affinity) )
             {
@@ -668,7 +670,7 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
                  * For hard affinity, what we return is the intersection of
                  * cpupool's online mask and the new hard affinity.
                  */
-                cpumask_and(new_affinity, online, v->cpu_hard_affinity);
+                cpumask_and(new_affinity, online, unit->cpu_hard_affinity);
                 ret = cpumask_to_xenctl_bitmap(&vcpuaff->cpumap_hard,
                                                new_affinity);
             }
@@ -697,7 +699,8 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
                  * hard affinity.
                  */
                 cpumask_and(new_affinity, new_affinity, online);
-                cpumask_and(new_affinity, new_affinity, v->cpu_hard_affinity);
+                cpumask_and(new_affinity, new_affinity,
+                            unit->cpu_hard_affinity);
                 ret = cpumask_to_xenctl_bitmap(&vcpuaff->cpumap_soft,
                                                new_affinity);
             }
@@ -710,10 +713,10 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
         {
             if ( vcpuaff->flags & XEN_VCPUAFFINITY_HARD )
                 ret = cpumask_to_xenctl_bitmap(&vcpuaff->cpumap_hard,
-                                               v->cpu_hard_affinity);
+                                               unit->cpu_hard_affinity);
             if ( vcpuaff->flags & XEN_VCPUAFFINITY_SOFT )
                 ret = cpumask_to_xenctl_bitmap(&vcpuaff->cpumap_soft,
-                                               v->cpu_soft_affinity);
+                                               unit->cpu_soft_affinity);
         }
         break;
     }

xen/common/keyhandler.c

@@ -251,6 +251,7 @@ static void reboot_machine(unsigned char key, struct cpu_user_regs *regs)
 static void dump_domains(unsigned char key)
 {
     struct domain *d;
+    const struct sched_unit *unit;
     struct vcpu   *v;
     s_time_t       now = NOW();
 
@@ -297,33 +298,38 @@ static void dump_domains(unsigned char key)
 
         printk("VCPU information and callbacks for domain %u:\n",
                d->domain_id);
-        for_each_vcpu ( d, v )
+
+        for_each_sched_unit ( d, unit )
         {
-            if ( !(v->vcpu_id & 0x3f) )
+            printk("  UNIT%d affinities: hard={%*pbl} soft={%*pbl}\n",
-                process_pending_softirqs();
+                   unit->unit_id, CPUMASK_PR(unit->cpu_hard_affinity),
+                   CPUMASK_PR(unit->cpu_soft_affinity));
 
-            printk("    VCPU%d: CPU%d [has=%c] poll=%d "
+            for_each_sched_unit_vcpu ( unit, v )
-                   "upcall_pend=%02x upcall_mask=%02x ",
+            {
-                   v->vcpu_id, v->processor,
+                if ( !(v->vcpu_id & 0x3f) )
-                   v->is_running ? 'T':'F', v->poll_evtchn,
+                    process_pending_softirqs();
-                   vcpu_info(v, evtchn_upcall_pending),
-                   !vcpu_event_delivery_is_enabled(v));
-            if ( vcpu_cpu_dirty(v) )
-                printk("dirty_cpu=%u", v->dirty_cpu);
-            printk("\n");
-            printk("    cpu_hard_affinity={%*pbl} cpu_soft_affinity={%*pbl}\n",
-                   CPUMASK_PR(v->cpu_hard_affinity),
-                   CPUMASK_PR(v->cpu_soft_affinity));
-            printk("    pause_count=%d pause_flags=%lx\n",
-                   atomic_read(&v->pause_count), v->pause_flags);
-            arch_dump_vcpu_info(v);
 
-            if ( v->periodic_period == 0 )
+                printk("    VCPU%d: CPU%d [has=%c] poll=%d "
-                printk("No periodic timer\n");
+                       "upcall_pend=%02x upcall_mask=%02x ",
-            else
+                       v->vcpu_id, v->processor,
-                printk("%"PRI_stime" Hz periodic timer (period %"PRI_stime" ms)\n",
+                       v->is_running ? 'T':'F', v->poll_evtchn,
-                       1000000000 / v->periodic_period,
+                       vcpu_info(v, evtchn_upcall_pending),
-                       v->periodic_period / 1000000);
+                       !vcpu_event_delivery_is_enabled(v));
+                if ( vcpu_cpu_dirty(v) )
+                    printk("dirty_cpu=%u", v->dirty_cpu);
+                printk("\n");
+                printk("    pause_count=%d pause_flags=%lx\n",
+                       atomic_read(&v->pause_count), v->pause_flags);
+                arch_dump_vcpu_info(v);
+
+                if ( v->periodic_period == 0 )
+                    printk("No periodic timer\n");
+                else
+                    printk("%"PRI_stime" Hz periodic timer (period %"PRI_stime" ms)\n",
+                           1000000000 / v->periodic_period,
+                           v->periodic_period / 1000000);
+            }
         }
     }
 

xen/common/sched_credit.c

@@ -352,6 +352,7 @@ DEFINE_PER_CPU(unsigned int, last_tickle_cpu);
 static inline void __runq_tickle(struct csched_unit *new)
 {
     unsigned int cpu = new->vcpu->processor;
+    struct sched_unit *unit = new->vcpu->sched_unit;
     struct csched_unit * const cur = CSCHED_UNIT(curr_on_cpu(cpu));
     struct csched_private *prv = CSCHED_PRIV(per_cpu(scheduler, cpu));
     cpumask_t mask, idle_mask, *online;
@@ -377,7 +378,7 @@ static inline void __runq_tickle(struct csched_unit *new)
     if ( unlikely(test_bit(CSCHED_FLAG_VCPU_PINNED, &new->flags) &&
                   cpumask_test_cpu(cpu, &idle_mask)) )
     {
-        ASSERT(cpumask_cycle(cpu, new->vcpu->cpu_hard_affinity) == cpu);
+        ASSERT(cpumask_cycle(cpu, unit->cpu_hard_affinity) == cpu);
         SCHED_STAT_CRANK(tickled_idle_cpu_excl);
         __cpumask_set_cpu(cpu, &mask);
         goto tickle;
@@ -412,11 +413,11 @@ static inline void __runq_tickle(struct csched_unit *new)
             int new_idlers_empty;
 
             if ( balance_step == BALANCE_SOFT_AFFINITY
-                 && !has_soft_affinity(new->vcpu) )
+                 && !has_soft_affinity(unit) )
                 continue;
 
             /* Are there idlers suitable for new (for this balance step)? */
-            affinity_balance_cpumask(new->vcpu, balance_step,
+            affinity_balance_cpumask(unit, balance_step,
                                      cpumask_scratch_cpu(cpu));
             cpumask_and(cpumask_scratch_cpu(cpu),
                         cpumask_scratch_cpu(cpu), &idle_mask);
@@ -445,8 +446,7 @@ static inline void __runq_tickle(struct csched_unit *new)
              */
             if ( new_idlers_empty && new->pri > cur->pri )
             {
-                if ( cpumask_intersects(cur->vcpu->cpu_hard_affinity,
+                if ( cpumask_intersects(unit->cpu_hard_affinity, &idle_mask) )
-                                        &idle_mask) )
                 {
                     SCHED_VCPU_STAT_CRANK(cur, kicked_away);
                     SCHED_VCPU_STAT_CRANK(cur, migrate_r);
@@ -728,7 +728,7 @@ _csched_cpu_pick(const struct scheduler *ops, struct vcpu *vc, bool_t commit)
 
     for_each_affinity_balance_step( balance_step )
     {
-        affinity_balance_cpumask(vc, balance_step, cpus);
+        affinity_balance_cpumask(vc->sched_unit, balance_step, cpus);
         cpumask_and(cpus, online, cpus);
         /*
          * We want to pick up a pcpu among the ones that are online and
@@ -747,7 +747,7 @@ _csched_cpu_pick(const struct scheduler *ops, struct vcpu *vc, bool_t commit)
          * balancing step all together.
          */
         if ( balance_step == BALANCE_SOFT_AFFINITY &&
-             (!has_soft_affinity(vc) || cpumask_empty(cpus)) )
+             (!has_soft_affinity(vc->sched_unit) || cpumask_empty(cpus)) )
             continue;
 
         /* If present, prefer vc's current processor */
@@ -1647,10 +1647,10 @@ csched_runq_steal(int peer_cpu, int cpu, int pri, int balance_step)
          * or counter.
          */
         if ( vc->is_running || (balance_step == BALANCE_SOFT_AFFINITY &&
-                                !has_soft_affinity(vc)) )
+                                !has_soft_affinity(vc->sched_unit)) )
             continue;
 
-        affinity_balance_cpumask(vc, balance_step, cpumask_scratch);
+        affinity_balance_cpumask(vc->sched_unit, balance_step, cpumask_scratch);
         if ( __csched_vcpu_is_migrateable(prv, vc, cpu, cpumask_scratch) )
         {
             /* We got a candidate. Grab it! */

xen/common/sched_credit2.c

@@ -700,10 +700,10 @@ static int get_fallback_cpu(struct csched2_unit *svc)
     {
         int cpu = v->processor;
 
-        if ( bs == BALANCE_SOFT_AFFINITY && !has_soft_affinity(v) )
+        if ( bs == BALANCE_SOFT_AFFINITY && !has_soft_affinity(v->sched_unit) )
             continue;
 
-        affinity_balance_cpumask(v, bs, cpumask_scratch_cpu(cpu));
+        affinity_balance_cpumask(v->sched_unit, bs, cpumask_scratch_cpu(cpu));
         cpumask_and(cpumask_scratch_cpu(cpu), cpumask_scratch_cpu(cpu),
                     cpupool_domain_cpumask(v->domain));
 
@@ -1391,10 +1391,10 @@ static s_time_t tickle_score(const struct scheduler *ops, s_time_t now,
      */
     if ( score > 0 )
     {
-        if ( cpumask_test_cpu(cpu, new->vcpu->cpu_soft_affinity) )
+        if ( cpumask_test_cpu(cpu, new->vcpu->sched_unit->cpu_soft_affinity) )
             score += CSCHED2_CREDIT_INIT;
 
-        if ( !cpumask_test_cpu(cpu, cur->vcpu->cpu_soft_affinity) )
+        if ( !cpumask_test_cpu(cpu, cur->vcpu->sched_unit->cpu_soft_affinity) )
             score += CSCHED2_CREDIT_INIT;
     }
 
@@ -1437,6 +1437,7 @@ runq_tickle(const struct scheduler *ops, struct csched2_unit *new, s_time_t now)
 {
     int i, ipid = -1;
     s_time_t max = 0;
+    struct sched_unit *unit = new->vcpu->sched_unit;
     unsigned int bs, cpu = new->vcpu->processor;
     struct csched2_runqueue_data *rqd = c2rqd(ops, cpu);
     cpumask_t *online = cpupool_domain_cpumask(new->vcpu->domain);
@@ -1474,7 +1475,7 @@ runq_tickle(const struct scheduler *ops, struct csched2_unit *new, s_time_t now)
                   cpumask_test_cpu(cpu, &rqd->idle) &&
                   !cpumask_test_cpu(cpu, &rqd->tickled)) )
     {
-        ASSERT(cpumask_cycle(cpu, new->vcpu->cpu_hard_affinity) == cpu);
+        ASSERT(cpumask_cycle(cpu, unit->cpu_hard_affinity) == cpu);
         SCHED_STAT_CRANK(tickled_idle_cpu_excl);
         ipid = cpu;
         goto tickle;
@@ -1483,10 +1484,10 @@ runq_tickle(const struct scheduler *ops, struct csched2_unit *new, s_time_t now)
     for_each_affinity_balance_step( bs )
     {
         /* Just skip first step, if we don't have a soft affinity */
-        if ( bs == BALANCE_SOFT_AFFINITY && !has_soft_affinity(new->vcpu) )
+        if ( bs == BALANCE_SOFT_AFFINITY && !has_soft_affinity(unit) )
             continue;
 
-        affinity_balance_cpumask(new->vcpu, bs, cpumask_scratch_cpu(cpu));
+        affinity_balance_cpumask(unit, bs, cpumask_scratch_cpu(cpu));
 
         /*
          * First of all, consider idle cpus, checking if we can just
@@ -1558,7 +1559,7 @@ runq_tickle(const struct scheduler *ops, struct csched2_unit *new, s_time_t now)
             ipid = cpu;
 
             /* If this is in new's soft affinity, just take it */
-            if ( cpumask_test_cpu(cpu, new->vcpu->cpu_soft_affinity) )
+            if ( cpumask_test_cpu(cpu, unit->cpu_soft_affinity) )
             {
                 SCHED_STAT_CRANK(tickled_busy_cpu);
                 goto tickle;
@@ -2244,7 +2245,7 @@ csched2_res_pick(const struct scheduler *ops, const struct sched_unit *unit)
         goto out;
     }
 
-    cpumask_and(cpumask_scratch_cpu(cpu), vc->cpu_hard_affinity,
+    cpumask_and(cpumask_scratch_cpu(cpu), unit->cpu_hard_affinity,
                 cpupool_domain_cpumask(vc->domain));
 
     /*
@@ -2289,7 +2290,7 @@ csched2_res_pick(const struct scheduler *ops, const struct sched_unit *unit)
      *
      * Find both runqueues in one pass.
      */
-    has_soft = has_soft_affinity(vc);
+    has_soft = has_soft_affinity(unit);
     for_each_cpu(i, &prv->active_queues)
     {
         struct csched2_runqueue_data *rqd;
@@ -2336,7 +2337,7 @@ csched2_res_pick(const struct scheduler *ops, const struct sched_unit *unit)
             cpumask_t mask;
 
             cpumask_and(&mask, cpumask_scratch_cpu(cpu), &rqd->active);
-            if ( cpumask_intersects(&mask, svc->vcpu->cpu_soft_affinity) )
+            if ( cpumask_intersects(&mask, unit->cpu_soft_affinity) )
             {
                 min_s_avgload = rqd_avgload;
                 min_s_rqi = i;
@@ -2358,9 +2359,9 @@ csched2_res_pick(const struct scheduler *ops, const struct sched_unit *unit)
          * Note that, to obtain the soft-affinity mask, we "just" put what we
          * have in cpumask_scratch in && with vc->cpu_soft_affinity. This is
          * ok because:
-         * - we know that vc->cpu_hard_affinity and vc->cpu_soft_affinity have
+         * - we know that unit->cpu_hard_affinity and ->cpu_soft_affinity have
          *   a non-empty intersection (because has_soft is true);
-         * - we have vc->cpu_hard_affinity & cpupool_domain_cpumask() already
+         * - we have unit->cpu_hard_affinity & cpupool_domain_cpumask() already
          *   in cpumask_scratch, we do save a lot doing like this.
          *
          * It's kind of like open coding affinity_balance_cpumask() but, in
@@ -2368,7 +2369,7 @@ csched2_res_pick(const struct scheduler *ops, const struct sched_unit *unit)
          * cpumask operations.
          */
         cpumask_and(cpumask_scratch_cpu(cpu), cpumask_scratch_cpu(cpu),
-                    vc->cpu_soft_affinity);
+                    unit->cpu_soft_affinity);
         cpumask_and(cpumask_scratch_cpu(cpu), cpumask_scratch_cpu(cpu),
                     &prv->rqd[min_s_rqi].active);
     }
@@ -2476,6 +2477,7 @@ static void migrate(const struct scheduler *ops,
                     s_time_t now)
 {
     int cpu = svc->vcpu->processor;
+    struct sched_unit *unit = svc->vcpu->sched_unit;
 
     if ( unlikely(tb_init_done) )
     {
@@ -2513,7 +2515,7 @@ static void migrate(const struct scheduler *ops,
         }
         _runq_deassign(svc);
 
-        cpumask_and(cpumask_scratch_cpu(cpu), svc->vcpu->cpu_hard_affinity,
+        cpumask_and(cpumask_scratch_cpu(cpu), unit->cpu_hard_affinity,
                     cpupool_domain_cpumask(svc->vcpu->domain));
         cpumask_and(cpumask_scratch_cpu(cpu), cpumask_scratch_cpu(cpu),
                     &trqd->active);
@@ -2547,7 +2549,7 @@ static bool vcpu_is_migrateable(struct csched2_unit *svc,
     struct vcpu *v = svc->vcpu;
     int cpu = svc->vcpu->processor;
 
-    cpumask_and(cpumask_scratch_cpu(cpu), v->cpu_hard_affinity,
+    cpumask_and(cpumask_scratch_cpu(cpu), v->sched_unit->cpu_hard_affinity,
                 cpupool_domain_cpumask(v->domain));
 
     return !(svc->flags & CSFLAG_runq_migrate_request) &&
@@ -2781,7 +2783,7 @@ csched2_unit_migrate(
 
     /* If here, new_cpu must be a valid Credit2 pCPU, and in our affinity. */
     ASSERT(cpumask_test_cpu(new_cpu, &csched2_priv(ops)->initialized));
-    ASSERT(cpumask_test_cpu(new_cpu, vc->cpu_hard_affinity));
+    ASSERT(cpumask_test_cpu(new_cpu, unit->cpu_hard_affinity));
 
     trqd = c2rqd(ops, new_cpu);
 
@@ -3321,9 +3323,9 @@ runq_candidate(struct csched2_runqueue_data *rqd,
     }
 
     /* If scurr has a soft-affinity, let's check whether cpu is part of it */
-    if ( has_soft_affinity(scurr->vcpu) )
+    if ( has_soft_affinity(scurr->vcpu->sched_unit) )
     {
-        affinity_balance_cpumask(scurr->vcpu, BALANCE_SOFT_AFFINITY,
+        affinity_balance_cpumask(scurr->vcpu->sched_unit, BALANCE_SOFT_AFFINITY,
                                  cpumask_scratch);
         if ( unlikely(!cpumask_test_cpu(cpu, cpumask_scratch)) )
         {
@@ -3378,7 +3380,7 @@ runq_candidate(struct csched2_runqueue_data *rqd,
         }
 
         /* Only consider vcpus that are allowed to run on this processor. */
-        if ( !cpumask_test_cpu(cpu, svc->vcpu->cpu_hard_affinity) )
+        if ( !cpumask_test_cpu(cpu, svc->vcpu->sched_unit->cpu_hard_affinity) )
         {
             (*skipped)++;
             continue;

xen/common/sched_null.c

@@ -122,7 +122,8 @@ static inline struct null_unit *null_unit(const struct sched_unit *unit)
 static inline bool vcpu_check_affinity(struct vcpu *v, unsigned int cpu,
                                        unsigned int balance_step)
 {
-    affinity_balance_cpumask(v, balance_step, cpumask_scratch_cpu(cpu));
+    affinity_balance_cpumask(v->sched_unit, balance_step,
+                             cpumask_scratch_cpu(cpu));
     cpumask_and(cpumask_scratch_cpu(cpu), cpumask_scratch_cpu(cpu),
                 cpupool_domain_cpumask(v->domain));
 
@@ -273,10 +274,10 @@ pick_res(struct null_private *prv, const struct sched_unit *unit)
 
     for_each_affinity_balance_step( bs )
     {
-        if ( bs == BALANCE_SOFT_AFFINITY && !has_soft_affinity(v) )
+        if ( bs == BALANCE_SOFT_AFFINITY && !has_soft_affinity(unit) )
             continue;
 
-        affinity_balance_cpumask(v, bs, cpumask_scratch_cpu(cpu));
+        affinity_balance_cpumask(unit, bs, cpumask_scratch_cpu(cpu));
         cpumask_and(cpumask_scratch_cpu(cpu), cpumask_scratch_cpu(cpu), cpus);
 
         /*
@@ -313,7 +314,7 @@ pick_res(struct null_private *prv, const struct sched_unit *unit)
      * as we will actually assign the vCPU to the pCPU we return from here,
      * only if the pCPU is free.
      */
-    cpumask_and(cpumask_scratch_cpu(cpu), cpus, v->cpu_hard_affinity);
+    cpumask_and(cpumask_scratch_cpu(cpu), cpus, unit->cpu_hard_affinity);
     new_cpu = cpumask_any(cpumask_scratch_cpu(cpu));
 
  out:
@@ -396,7 +397,8 @@ static bool vcpu_deassign(struct null_private *prv, struct vcpu *v)
     {
         list_for_each_entry( wvc, &prv->waitq, waitq_elem )
         {
-            if ( bs == BALANCE_SOFT_AFFINITY && !has_soft_affinity(wvc->vcpu) )
+            if ( bs == BALANCE_SOFT_AFFINITY &&
+                 !has_soft_affinity(wvc->vcpu->sched_unit) )
                 continue;
 
             if ( vcpu_check_affinity(wvc->vcpu, cpu, bs) )
@@ -466,7 +468,7 @@ static void null_unit_insert(const struct scheduler *ops,
 
     lock = unit_schedule_lock(unit);
 
-    cpumask_and(cpumask_scratch_cpu(cpu), v->cpu_hard_affinity,
+    cpumask_and(cpumask_scratch_cpu(cpu), unit->cpu_hard_affinity,
                 cpupool_domain_cpumask(v->domain));
 
     /* If the pCPU is free, we assign v to it */
@@ -579,7 +581,7 @@ static void null_unit_wake(const struct scheduler *ops,
         list_add_tail(&nvc->waitq_elem, &prv->waitq);
         spin_unlock(&prv->waitq_lock);
 
-        cpumask_and(cpumask_scratch_cpu(cpu), v->cpu_hard_affinity,
+        cpumask_and(cpumask_scratch_cpu(cpu), unit->cpu_hard_affinity,
                     cpupool_domain_cpumask(v->domain));
 
         if ( !cpumask_intersects(&prv->cpus_free, cpumask_scratch_cpu(cpu)) )
@@ -848,7 +850,7 @@ static struct task_slice null_schedule(const struct scheduler *ops,
             list_for_each_entry( wvc, &prv->waitq, waitq_elem )
             {
                 if ( bs == BALANCE_SOFT_AFFINITY &&
-                     !has_soft_affinity(wvc->vcpu) )
+                     !has_soft_affinity(wvc->vcpu->sched_unit) )
                     continue;
 
                 if ( vcpu_check_affinity(wvc->vcpu, cpu, bs) )

xen/common/sched_rt.c

@@ -327,7 +327,7 @@ rt_dump_vcpu(const struct scheduler *ops, const struct rt_unit *svc)
     mask = cpumask_scratch_cpu(svc->vcpu->processor);
 
     cpupool_mask = cpupool_domain_cpumask(svc->vcpu->domain);
-    cpumask_and(mask, cpupool_mask, svc->vcpu->cpu_hard_affinity);
+    cpumask_and(mask, cpupool_mask, svc->vcpu->sched_unit->cpu_hard_affinity);
     printk("[%5d.%-2u] cpu %u, (%"PRI_stime", %"PRI_stime"),"
            " cur_b=%"PRI_stime" cur_d=%"PRI_stime" last_start=%"PRI_stime"\n"
            " \t\t priority_level=%d has_extratime=%d\n"
@@ -644,7 +644,7 @@ rt_res_pick(const struct scheduler *ops, const struct sched_unit *unit)
     int cpu;
 
     online = cpupool_domain_cpumask(vc->domain);
-    cpumask_and(&cpus, online, vc->cpu_hard_affinity);
+    cpumask_and(&cpus, online, unit->cpu_hard_affinity);
 
     cpu = cpumask_test_cpu(vc->processor, &cpus)
             ? vc->processor
@@ -1021,7 +1021,8 @@ runq_pick(const struct scheduler *ops, const cpumask_t *mask)
 
         /* mask cpu_hard_affinity & cpupool & mask */
         online = cpupool_domain_cpumask(iter_svc->vcpu->domain);
-        cpumask_and(&cpu_common, online, iter_svc->vcpu->cpu_hard_affinity);
+        cpumask_and(&cpu_common, online,
+                    iter_svc->vcpu->sched_unit->cpu_hard_affinity);
         cpumask_and(&cpu_common, mask, &cpu_common);
         if ( cpumask_empty(&cpu_common) )
             continue;
@@ -1190,7 +1191,7 @@ runq_tickle(const struct scheduler *ops, struct rt_unit *new)
         return;
 
     online = cpupool_domain_cpumask(new->vcpu->domain);
-    cpumask_and(&not_tickled, online, new->vcpu->cpu_hard_affinity);
+    cpumask_and(&not_tickled, online, new->vcpu->sched_unit->cpu_hard_affinity);
     cpumask_andnot(&not_tickled, &not_tickled, &prv->tickled);
 
     /*

xen/common/schedule.c

@@ -329,6 +329,11 @@ static void sched_free_unit(struct sched_unit *unit)
     }
 
     unit->vcpu_list->sched_unit = NULL;
+
+    free_cpumask_var(unit->cpu_hard_affinity);
+    free_cpumask_var(unit->cpu_hard_affinity_saved);
+    free_cpumask_var(unit->cpu_soft_affinity);
+
     xfree(unit);
 }
 
@@ -353,9 +358,18 @@ static struct sched_unit *sched_alloc_unit(struct vcpu *v)
     unit->next_in_list = *prev_unit;
     *prev_unit = unit;
 
+    if ( !zalloc_cpumask_var(&unit->cpu_hard_affinity) ||
+         !zalloc_cpumask_var(&unit->cpu_hard_affinity_saved) ||
+         !zalloc_cpumask_var(&unit->cpu_soft_affinity) )
+        goto fail;
+
     v->sched_unit = unit;
 
     return unit;
+
+ fail:
+    sched_free_unit(unit);
+    return NULL;
 }
 
 int sched_init_vcpu(struct vcpu *v, unsigned int processor)
@@ -745,7 +759,7 @@ static void vcpu_migrate_finish(struct vcpu *v)
              */
             if ( pick_called &&
                  (new_lock == get_sched_res(new_cpu)->schedule_lock) &&
-                 cpumask_test_cpu(new_cpu, v->cpu_hard_affinity) &&
+                 cpumask_test_cpu(new_cpu, v->sched_unit->cpu_hard_affinity) &&
                  cpumask_test_cpu(new_cpu, v->domain->cpupool->cpu_valid) )
                 break;
 
@@ -803,6 +817,7 @@ void restore_vcpu_affinity(struct domain *d)
     {
         spinlock_t *lock;
         unsigned int old_cpu = v->processor;
+        struct sched_unit *unit = v->sched_unit;
 
         ASSERT(!vcpu_runnable(v));
 
@@ -814,17 +829,17 @@ void restore_vcpu_affinity(struct domain *d)
          * set v->processor of each of their vCPUs to something that will
          * make sense for the scheduler of the cpupool in which they are in.
          */
-        lock = unit_schedule_lock_irq(v->sched_unit);
+        lock = unit_schedule_lock_irq(unit);
 
-        cpumask_and(cpumask_scratch_cpu(cpu), v->cpu_hard_affinity,
+        cpumask_and(cpumask_scratch_cpu(cpu), unit->cpu_hard_affinity,
                     cpupool_domain_cpumask(d));
         if ( cpumask_empty(cpumask_scratch_cpu(cpu)) )
         {
             if ( v->affinity_broken )
             {
-                sched_set_affinity(v, v->cpu_hard_affinity_saved, NULL);
+                sched_set_affinity(v, unit->cpu_hard_affinity_saved, NULL);
                 v->affinity_broken = 0;
-                cpumask_and(cpumask_scratch_cpu(cpu), v->cpu_hard_affinity,
+                cpumask_and(cpumask_scratch_cpu(cpu), unit->cpu_hard_affinity,
                             cpupool_domain_cpumask(d));
             }
 
@@ -832,21 +847,20 @@ void restore_vcpu_affinity(struct domain *d)
             {
                 printk(XENLOG_DEBUG "Breaking affinity for %pv\n", v);
                 sched_set_affinity(v, &cpumask_all, NULL);
-                cpumask_and(cpumask_scratch_cpu(cpu), v->cpu_hard_affinity,
+                cpumask_and(cpumask_scratch_cpu(cpu), unit->cpu_hard_affinity,
                             cpupool_domain_cpumask(d));
             }
         }
 
         v->processor = cpumask_any(cpumask_scratch_cpu(cpu));
-        v->sched_unit->res = get_sched_res(v->processor);
+        unit->res = get_sched_res(v->processor);
 
         spin_unlock_irq(lock);
 
         /* v->processor might have changed, so reacquire the lock. */
-        lock = unit_schedule_lock_irq(v->sched_unit);
+        lock = unit_schedule_lock_irq(unit);
-        v->sched_unit->res = sched_pick_resource(vcpu_scheduler(v),
+        unit->res = sched_pick_resource(vcpu_scheduler(v), unit);
-                                                 v->sched_unit);
+        v->processor = unit->res->master_cpu;
-        v->processor = v->sched_unit->res->master_cpu;
         spin_unlock_irq(lock);
 
         if ( old_cpu != v->processor )
@@ -878,16 +892,17 @@ int cpu_disable_scheduler(unsigned int cpu)
         for_each_vcpu ( d, v )
         {
             unsigned long flags;
-            spinlock_t *lock = unit_schedule_lock_irqsave(v->sched_unit, &flags);
+            struct sched_unit *unit = v->sched_unit;
+            spinlock_t *lock = unit_schedule_lock_irqsave(unit, &flags);
 
-            cpumask_and(&online_affinity, v->cpu_hard_affinity, c->cpu_valid);
+            cpumask_and(&online_affinity, unit->cpu_hard_affinity, c->cpu_valid);
             if ( cpumask_empty(&online_affinity) &&
-                 cpumask_test_cpu(cpu, v->cpu_hard_affinity) )
+                 cpumask_test_cpu(cpu, unit->cpu_hard_affinity) )
             {
                 if ( v->affinity_broken )
                 {
                     /* The vcpu is temporarily pinned, can't move it. */
-                    unit_schedule_unlock_irqrestore(lock, flags, v->sched_unit);
+                    unit_schedule_unlock_irqrestore(lock, flags, unit);
                     ret = -EADDRINUSE;
                     break;
                 }
@@ -900,7 +915,7 @@ int cpu_disable_scheduler(unsigned int cpu)
             if ( v->processor != cpu )
             {
                 /* The vcpu is not on this cpu, so we can move on. */
-                unit_schedule_unlock_irqrestore(lock, flags, v->sched_unit);
+                unit_schedule_unlock_irqrestore(lock, flags, unit);
                 continue;
             }
 
@@ -913,7 +928,7 @@ int cpu_disable_scheduler(unsigned int cpu)
              *    things would have failed before getting in here.
              */
             vcpu_migrate_start(v);
-            unit_schedule_unlock_irqrestore(lock, flags, v->sched_unit);
+            unit_schedule_unlock_irqrestore(lock, flags, unit);
 
             vcpu_migrate_finish(v);
 
@@ -958,26 +973,29 @@ static int cpu_disable_scheduler_check(unsigned int cpu)
 void sched_set_affinity(
     struct vcpu *v, const cpumask_t *hard, const cpumask_t *soft)
 {
-    sched_adjust_affinity(dom_scheduler(v->domain), v->sched_unit, hard, soft);
+    struct sched_unit *unit = v->sched_unit;
+
+    sched_adjust_affinity(dom_scheduler(v->domain), unit, hard, soft);
 
     if ( hard )
-        cpumask_copy(v->cpu_hard_affinity, hard);
+        cpumask_copy(unit->cpu_hard_affinity, hard);
     if ( soft )
-        cpumask_copy(v->cpu_soft_affinity, soft);
+        cpumask_copy(unit->cpu_soft_affinity, soft);
 
-    v->soft_aff_effective = !cpumask_subset(v->cpu_hard_affinity,
+    unit->soft_aff_effective = !cpumask_subset(unit->cpu_hard_affinity,
-                                            v->cpu_soft_affinity) &&
+                                               unit->cpu_soft_affinity) &&
-                            cpumask_intersects(v->cpu_soft_affinity,
+                               cpumask_intersects(unit->cpu_soft_affinity,
-                                               v->cpu_hard_affinity);
+                                                  unit->cpu_hard_affinity);
 }
 
 static int vcpu_set_affinity(
     struct vcpu *v, const cpumask_t *affinity, const cpumask_t *which)
 {
+    struct sched_unit *unit = v->sched_unit;
     spinlock_t *lock;
     int ret = 0;
 
-    lock = unit_schedule_lock_irq(v->sched_unit);
+    lock = unit_schedule_lock_irq(unit);
 
     if ( v->affinity_broken )
         ret = -EBUSY;
@@ -987,19 +1005,19 @@ static int vcpu_set_affinity(
          * Tell the scheduler we changes something about affinity,
          * and ask to re-evaluate vcpu placement.
          */
-        if ( which == v->cpu_hard_affinity )
+        if ( which == unit->cpu_hard_affinity )
         {
             sched_set_affinity(v, affinity, NULL);
         }
         else
         {
-            ASSERT(which == v->cpu_soft_affinity);
+            ASSERT(which == unit->cpu_soft_affinity);
             sched_set_affinity(v, NULL, affinity);
         }
         vcpu_migrate_start(v);
     }
 
-    unit_schedule_unlock_irq(lock, v->sched_unit);
+    unit_schedule_unlock_irq(lock, unit);
 
     domain_update_node_affinity(v->domain);
 
@@ -1018,12 +1036,12 @@ int vcpu_set_hard_affinity(struct vcpu *v, const cpumask_t *affinity)
     if ( cpumask_empty(&online_affinity) )
         return -EINVAL;
 
-    return vcpu_set_affinity(v, affinity, v->cpu_hard_affinity);
+    return vcpu_set_affinity(v, affinity, v->sched_unit->cpu_hard_affinity);
 }
 
 int vcpu_set_soft_affinity(struct vcpu *v, const cpumask_t *affinity)
 {
-    return vcpu_set_affinity(v, affinity, v->cpu_soft_affinity);
+    return vcpu_set_affinity(v, affinity, v->sched_unit->cpu_soft_affinity);
 }
 
 /* Block the currently-executing domain until a pertinent event occurs. */
@@ -1227,11 +1245,12 @@ void watchdog_domain_destroy(struct domain *d)
  */
 int vcpu_temporary_affinity(struct vcpu *v, unsigned int cpu, uint8_t reason)
 {
+    struct sched_unit *unit = v->sched_unit;
     spinlock_t *lock;
     int ret = -EINVAL;
     bool migrate;
 
-    lock = unit_schedule_lock_irq(v->sched_unit);
+    lock = unit_schedule_lock_irq(unit);
 
     if ( cpu == NR_CPUS )
     {
@@ -1241,7 +1260,7 @@ int vcpu_temporary_affinity(struct vcpu *v, unsigned int cpu, uint8_t reason)
             v->affinity_broken &= ~reason;
         }
         if ( !ret && !v->affinity_broken )
-            sched_set_affinity(v, v->cpu_hard_affinity_saved, NULL);
+            sched_set_affinity(v, unit->cpu_hard_affinity_saved, NULL);
     }
     else if ( cpu < nr_cpu_ids )
     {
@@ -1252,7 +1271,8 @@ int vcpu_temporary_affinity(struct vcpu *v, unsigned int cpu, uint8_t reason)
         {
             if ( !v->affinity_broken )
             {
-                cpumask_copy(v->cpu_hard_affinity_saved, v->cpu_hard_affinity);
+                cpumask_copy(unit->cpu_hard_affinity_saved,
+                             unit->cpu_hard_affinity);
                 sched_set_affinity(v, cpumask_of(cpu), NULL);
             }
             v->affinity_broken |= reason;
@@ -1260,11 +1280,11 @@ int vcpu_temporary_affinity(struct vcpu *v, unsigned int cpu, uint8_t reason)
         }
     }
 
-    migrate = !ret && !cpumask_test_cpu(v->processor, v->cpu_hard_affinity);
+    migrate = !ret && !cpumask_test_cpu(v->processor, unit->cpu_hard_affinity);
     if ( migrate )
         vcpu_migrate_start(v);
 
-    unit_schedule_unlock_irq(lock, v->sched_unit);
+    unit_schedule_unlock_irq(lock, unit);
 
     if ( migrate )
         vcpu_migrate_finish(v);

xen/include/xen/sched-if.h

@@ -442,11 +442,11 @@ static inline cpumask_t* cpupool_domain_cpumask(struct domain *d)
  * * The hard affinity is not a subset of soft affinity
  * * There is an overlap between the soft and hard affinity masks
  */
-static inline int has_soft_affinity(const struct vcpu *v)
+static inline int has_soft_affinity(const struct sched_unit *unit)
 {
-    return v->soft_aff_effective &&
+    return unit->soft_aff_effective &&
-           !cpumask_subset(cpupool_domain_cpumask(v->domain),
+           !cpumask_subset(cpupool_domain_cpumask(unit->domain),
-                           v->cpu_soft_affinity);
+                           unit->cpu_soft_affinity);
 }
 
 /*
@@ -456,17 +456,18 @@ static inline int has_soft_affinity(const struct vcpu *v)
  * to avoid running a vcpu where it would like, but is not allowed to!
  */
 static inline void
-affinity_balance_cpumask(const struct vcpu *v, int step, cpumask_t *mask)
+affinity_balance_cpumask(const struct sched_unit *unit, int step,
+                         cpumask_t *mask)
 {
     if ( step == BALANCE_SOFT_AFFINITY )
     {
-        cpumask_and(mask, v->cpu_soft_affinity, v->cpu_hard_affinity);
+        cpumask_and(mask, unit->cpu_soft_affinity, unit->cpu_hard_affinity);
 
         if ( unlikely(cpumask_empty(mask)) )
-            cpumask_copy(mask, v->cpu_hard_affinity);
+            cpumask_copy(mask, unit->cpu_hard_affinity);
     }
     else /* step == BALANCE_HARD_AFFINITY */
-        cpumask_copy(mask, v->cpu_hard_affinity);
+        cpumask_copy(mask, unit->cpu_hard_affinity);
 }
 
 void sched_rm_cpu(unsigned int cpu);

xen/include/xen/sched.h

@@ -212,9 +212,6 @@ struct vcpu
     bool             hcall_compat;
 #endif
 
-    /* Does soft affinity actually play a role (given hard affinity)? */
-    bool             soft_aff_effective;
-
     /* The CPU, if any, which is holding onto this VCPU's state. */
 #define VCPU_CPU_CLEAN (~0u)
     unsigned int     dirty_cpu;
@@ -246,14 +243,6 @@ struct vcpu
     evtchn_port_t    virq_to_evtchn[NR_VIRQS];
     spinlock_t       virq_lock;
 
-    /* Bitmask of CPUs on which this VCPU may run. */
-    cpumask_var_t    cpu_hard_affinity;
-    /* Used to save affinity during temporary pinning. */
-    cpumask_var_t    cpu_hard_affinity_saved;
-
-    /* Bitmask of CPUs on which this VCPU prefers to run. */
-    cpumask_var_t    cpu_soft_affinity;
-
     /* Tasklet for continue_hypercall_on_cpu(). */
     struct tasklet   continue_hypercall_tasklet;
 
@@ -280,6 +269,15 @@ struct sched_unit {
     struct sched_unit     *next_in_list;
     struct sched_resource *res;
     unsigned int           unit_id;
+
+    /* Does soft affinity actually play a role (given hard affinity)? */
+    bool                   soft_aff_effective;
+    /* Bitmask of CPUs on which this VCPU may run. */
+    cpumask_var_t          cpu_hard_affinity;
+    /* Used to save affinity during temporary pinning. */
+    cpumask_var_t          cpu_hard_affinity_saved;
+    /* Bitmask of CPUs on which this VCPU prefers to run. */
+    cpumask_var_t          cpu_soft_affinity;
 };
 
 #define for_each_sched_unit(d, u)                                         \
@@ -998,7 +996,7 @@ static inline bool hap_enabled(const struct domain *d)
 static inline bool is_hwdom_pinned_vcpu(const struct vcpu *v)
 {
     return (is_hardware_domain(v->domain) &&
-            cpumask_weight(v->cpu_hard_affinity) == 1);
+            cpumask_weight(v->sched_unit->cpu_hard_affinity) == 1);
 }
 
 static inline bool is_vcpu_online(const struct vcpu *v)