diff mbox series

[13/60] xen/sched: move some per-vcpu items to struct sched_unit

Message ID 20190528103313.1343-14-jgross@suse.com (mailing list archive)
State New, archived
Headers show
Series xen: add core scheduling support | expand

Commit Message

Jürgen Groß May 28, 2019, 10:32 a.m. UTC
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.

vcpu->last_run_time is primarily used by sched_credit, so move it to
struct sched_unit, too.

Signed-off-by: Juergen Gross <jgross@suse.com>
---
 xen/arch/x86/pv/emul-priv-op.c |   1 +
 xen/arch/x86/pv/traps.c        |   5 +-
 xen/arch/x86/traps.c           |   9 ++--
 xen/common/domain.c            |  19 ++-----
 xen/common/domctl.c            |  13 +++--
 xen/common/keyhandler.c        |   4 +-
 xen/common/sched_credit.c      |  20 ++++----
 xen/common/sched_credit2.c     |  42 ++++++++--------
 xen/common/sched_null.c        |  16 +++---
 xen/common/sched_rt.c          |   9 ++--
 xen/common/schedule.c          | 110 ++++++++++++++++++++++++-----------------
 xen/common/wait.c              |   4 +-
 xen/include/xen/sched-if.h     |  17 ++++---
 xen/include/xen/sched.h        |  36 +++++++-------
 14 files changed, 163 insertions(+), 142 deletions(-)

Comments

Andrii Anisov June 13, 2019, 7:18 a.m. UTC | #1
Hello Juergen,

Please note that this patch will clash with [1].

On 28.05.19 13:32, Juergen Gross wrote:
> vcpu->last_run_time is primarily used by sched_credit, so move it to
> struct sched_unit, too.

`last_run_time` is moved to credit privates as for current staging.


[1] https://xenbits.xen.org/gitweb/?p=xen.git;a=commit;h=608639ffa0a0d6f219e14ba7397ab2cc018b93c9
Jürgen Groß June 13, 2019, 7:29 a.m. UTC | #2
Hi Andrii,

On 13.06.19 09:18, Andrii Anisov wrote:
> Hello Juergen,
> 
> Please note that this patch will clash with [1].
> 
> On 28.05.19 13:32, Juergen Gross wrote:
>> vcpu->last_run_time is primarily used by sched_credit, so move it to
>> struct sched_unit, too.
> 
> `last_run_time` is moved to credit privates as for current staging.

Thanks for the heads up, but I've rebased already. :-)


Juergen
Andrii Anisov June 13, 2019, 7:34 a.m. UTC | #3
On 13.06.19 10:29, Juergen Gross wrote:
> Thanks for the heads up, but I've rebased already. :-)

Oh, great. I'm just wondering if you put it already on your github?
I'm playing with scheduling on my site, and I have a strong feeling I should be based on your series ;)
Jürgen Groß June 13, 2019, 8:39 a.m. UTC | #4
On 13.06.19 09:34, Andrii Anisov wrote:
> 
> 
> On 13.06.19 10:29, Juergen Gross wrote:
>> Thanks for the heads up, but I've rebased already. :-)
> 
> Oh, great. I'm just wondering if you put it already on your github?

github.com/jgross1/xen sched-v1-rebase

Only compile tested on x86 up to now, but rebase was rather easy.


Juergen
Andrii Anisov June 13, 2019, 8:49 a.m. UTC | #5
чт, 13 черв. 2019 о 11:39 Juergen Gross <jgross@suse.com> пише:

> github.com/jgross1/xen sched-v1-rebase
>
> Only compile tested on x86 up to now, but rebase was rather easy.
>

Cool, will take it and check for ARM.
Thank you.

Sincerely,
Andrii Anisov.
<div dir="ltr"><div dir="ltr"><br clear="all"><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><br></div></div></div><div class="gmail_quote"><div dir="ltr" class="gmail_attr">чт, 13 черв. 2019 о 11:39 Juergen Gross &lt;<a href="mailto:jgross@suse.com">jgross@suse.com</a>&gt; пише:</div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<a href="http://github.com/jgross1/xen" rel="noreferrer" target="_blank">github.com/jgross1/xen</a> sched-v1-rebase<br>
<br>
Only compile tested on x86 up to now, but rebase was rather easy.<br></blockquote><div><br></div><div>Cool, will take it and check for ARM.</div><div>Thank you.</div><div><br></div>Sincerely,<div>Andrii Anisov. </div></div></div>
diff mbox series

Patch

diff --git a/xen/arch/x86/pv/emul-priv-op.c b/xen/arch/x86/pv/emul-priv-op.c
index b20d79c7a3..a7a24a2053 100644
--- a/xen/arch/x86/pv/emul-priv-op.c
+++ b/xen/arch/x86/pv/emul-priv-op.c
@@ -23,6 +23,7 @@ 
 #include <xen/event.h>
 #include <xen/guest_access.h>
 #include <xen/iocap.h>
+#include <xen/sched.h>
 #include <xen/spinlock.h>
 #include <xen/trace.h>
 
diff --git a/xen/arch/x86/pv/traps.c b/xen/arch/x86/pv/traps.c
index 1740784ff2..419abc3d95 100644
--- a/xen/arch/x86/pv/traps.c
+++ b/xen/arch/x86/pv/traps.c
@@ -22,6 +22,7 @@ 
 #include <xen/event.h>
 #include <xen/hypercall.h>
 #include <xen/lib.h>
+#include <xen/sched.h>
 #include <xen/trace.h>
 #include <xen/softirq.h>
 
@@ -155,8 +156,8 @@  static void nmi_mce_softirq(void)
      * Set the tmp value unconditionally, so that the check in the iret
      * hypercall works.
      */
-    cpumask_copy(st->vcpu->cpu_hard_affinity_tmp,
-                 st->vcpu->cpu_hard_affinity);
+    cpumask_copy(st->vcpu->sched_unit->cpu_hard_affinity_tmp,
+                 st->vcpu->sched_unit->cpu_hard_affinity);
 
     if ( (cpu != st->processor) ||
          (st->processor != st->vcpu->processor) )
diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c
index 05ddc39bfe..c3b39d6296 100644
--- a/xen/arch/x86/traps.c
+++ b/xen/arch/x86/traps.c
@@ -1594,16 +1594,17 @@  static void pci_serr_softirq(void)
 void async_exception_cleanup(struct vcpu *curr)
 {
     int trap;
+    struct sched_unit *unit = curr->sched_unit;
 
     if ( !curr->async_exception_mask )
         return;
 
     /* Restore affinity.  */
-    if ( !cpumask_empty(curr->cpu_hard_affinity_tmp) &&
-         !cpumask_equal(curr->cpu_hard_affinity_tmp, curr->cpu_hard_affinity) )
+    if ( !cpumask_empty(unit->cpu_hard_affinity_tmp) &&
+         !cpumask_equal(unit->cpu_hard_affinity_tmp, unit->cpu_hard_affinity) )
     {
-        vcpu_set_hard_affinity(curr, curr->cpu_hard_affinity_tmp);
-        cpumask_clear(curr->cpu_hard_affinity_tmp);
+        vcpu_set_hard_affinity(curr, unit->cpu_hard_affinity_tmp);
+        cpumask_clear(unit->cpu_hard_affinity_tmp);
     }
 
     if ( !(curr->async_exception_mask & (curr->async_exception_mask - 1)) )
diff --git a/xen/common/domain.c b/xen/common/domain.c
index 90c66079f9..c200e9024f 100644
--- a/xen/common/domain.c
+++ b/xen/common/domain.c
@@ -125,11 +125,6 @@  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_tmp);
-    free_cpumask_var(v->cpu_hard_affinity_saved);
-    free_cpumask_var(v->cpu_soft_affinity);
-
     free_vcpu_struct(v);
 }
 
@@ -153,12 +148,6 @@  struct vcpu *vcpu_create(
 
     grant_table_init_vcpu(v);
 
-    if ( !zalloc_cpumask_var(&v->cpu_hard_affinity) ||
-         !zalloc_cpumask_var(&v->cpu_hard_affinity_tmp) ||
-         !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;
@@ -198,7 +187,6 @@  struct vcpu *vcpu_create(
     sched_destroy_vcpu(v);
  fail_wq:
     destroy_waitqueue_vcpu(v);
- fail:
     vcpu_destroy(v);
 
     return NULL;
@@ -557,9 +545,10 @@  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);
@@ -1226,7 +1215,7 @@  int vcpu_reset(struct vcpu *v)
     v->async_exception_mask = 0;
     memset(v->async_exception_state, 0, sizeof(v->async_exception_state));
 #endif
-    cpumask_clear(v->cpu_hard_affinity_tmp);
+    cpumask_clear(v->sched_unit->cpu_hard_affinity_tmp);
     clear_bit(_VPF_blocked, &v->pause_flags);
     clear_bit(_VPF_in_reset, &v->pause_flags);
 
diff --git a/xen/common/domctl.c b/xen/common/domctl.c
index bade9a63b1..bc986d131d 100644
--- a/xen/common/domctl.c
+++ b/xen/common/domctl.c
@@ -614,6 +614,7 @@  long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
     case XEN_DOMCTL_getvcpuaffinity:
     {
         struct vcpu *v;
+        struct sched_unit *unit;
         struct xen_domctl_vcpuaffinity *vcpuaff = &op->u.vcpuaffinity;
 
         ret = -EINVAL;
@@ -624,6 +625,7 @@  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;
@@ -643,7 +645,7 @@  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) )
             {
@@ -676,7 +678,7 @@  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);
             }
@@ -705,7 +707,8 @@  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);
             }
@@ -718,10 +721,10 @@  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;
     }
diff --git a/xen/common/keyhandler.c b/xen/common/keyhandler.c
index 4f4a660b0c..1729f73af0 100644
--- a/xen/common/keyhandler.c
+++ b/xen/common/keyhandler.c
@@ -312,8 +312,8 @@  static void dump_domains(unsigned char key)
                 printk("dirty_cpu=%u", v->dirty_cpu);
             printk("\n");
             printk("    cpu_hard_affinity={%*pbl} cpu_soft_affinity={%*pbl}\n",
-                   nr_cpu_ids, cpumask_bits(v->cpu_hard_affinity),
-                   nr_cpu_ids, cpumask_bits(v->cpu_soft_affinity));
+                   nr_cpu_ids, cpumask_bits(v->sched_unit->cpu_hard_affinity),
+                   nr_cpu_ids, cpumask_bits(v->sched_unit->cpu_soft_affinity));
             printk("    pause_count=%d pause_flags=%lx\n",
                    atomic_read(&v->pause_count), v->pause_flags);
             arch_dump_vcpu_info(v);
diff --git a/xen/common/sched_credit.c b/xen/common/sched_credit.c
index 74c85df334..ffac2f4bbb 100644
--- a/xen/common/sched_credit.c
+++ b/xen/common/sched_credit.c
@@ -350,6 +350,7 @@  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;
@@ -375,7 +376,7 @@  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;
@@ -410,11 +411,11 @@  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);
@@ -443,8 +444,7 @@  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,
-                                        &idle_mask) )
+                if ( cpumask_intersects(unit->cpu_hard_affinity, &idle_mask) )
                 {
                     SCHED_VCPU_STAT_CRANK(cur, kicked_away);
                     SCHED_VCPU_STAT_CRANK(cur, migrate_r);
@@ -695,7 +695,7 @@  static inline bool
 __csched_vcpu_is_cache_hot(const struct csched_private *prv, struct vcpu *v)
 {
     bool hot = prv->vcpu_migr_delay &&
-               (NOW() - v->last_run_time) < prv->vcpu_migr_delay;
+               (NOW() - v->sched_unit->last_run_time) < prv->vcpu_migr_delay;
 
     if ( hot )
         SCHED_STAT_CRANK(vcpu_hot);
@@ -733,7 +733,7 @@  _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
@@ -752,7 +752,7 @@  _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 */
@@ -1652,10 +1652,10 @@  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! */
diff --git a/xen/common/sched_credit2.c b/xen/common/sched_credit2.c
index 562e73d99e..dabd5636f5 100644
--- a/xen/common/sched_credit2.c
+++ b/xen/common/sched_credit2.c
@@ -699,10 +699,10 @@  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));
 
@@ -1390,10 +1390,10 @@  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;
     }
 
@@ -1436,6 +1436,7 @@  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);
@@ -1473,7 +1474,7 @@  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;
@@ -1482,10 +1483,10 @@  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
@@ -1557,7 +1558,7 @@  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;
@@ -2243,7 +2244,7 @@  csched2_res_pick(const struct scheduler *ops, 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));
 
     /*
@@ -2288,7 +2289,7 @@  csched2_res_pick(const struct scheduler *ops, 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;
@@ -2335,7 +2336,7 @@  csched2_res_pick(const struct scheduler *ops, 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;
@@ -2357,9 +2358,9 @@  csched2_res_pick(const struct scheduler *ops, 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
@@ -2367,7 +2368,7 @@  csched2_res_pick(const struct scheduler *ops, 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);
     }
@@ -2475,6 +2476,7 @@  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) )
     {
@@ -2512,7 +2514,7 @@  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);
@@ -2546,7 +2548,7 @@  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) &&
@@ -2780,7 +2782,7 @@  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);
 
@@ -3320,9 +3322,9 @@  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)) )
         {
@@ -3377,7 +3379,7 @@  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;
diff --git a/xen/common/sched_null.c b/xen/common/sched_null.c
index ee3a8cf064..56b0055a42 100644
--- a/xen/common/sched_null.c
+++ b/xen/common/sched_null.c
@@ -123,7 +123,8 @@  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));
 
@@ -281,10 +282,10 @@  pick_res(struct null_private *prv, 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);
 
         /*
@@ -321,7 +322,7 @@  pick_res(struct null_private *prv, 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:
@@ -430,7 +431,7 @@  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 */
@@ -488,7 +489,8 @@  static void _vcpu_remove(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) )
@@ -767,7 +769,7 @@  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) )
diff --git a/xen/common/sched_rt.c b/xen/common/sched_rt.c
index cd737131a3..d640d87b43 100644
--- a/xen/common/sched_rt.c
+++ b/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"
@@ -645,7 +645,7 @@  rt_res_pick(const struct scheduler *ops, 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
@@ -1023,7 +1023,8 @@  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;
@@ -1192,7 +1193,7 @@  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);
 
     /*
diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 1321c86111..212c1e637f 100644
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -270,6 +270,12 @@  static void sched_free_unit(struct sched_unit *unit)
     }
 
     unit->vcpu->sched_unit = NULL;
+
+    free_cpumask_var(unit->cpu_hard_affinity);
+    free_cpumask_var(unit->cpu_hard_affinity_tmp);
+    free_cpumask_var(unit->cpu_hard_affinity_saved);
+    free_cpumask_var(unit->cpu_soft_affinity);
+
     xfree(unit);
 }
 
@@ -293,7 +299,17 @@  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_tmp) ||
+         !zalloc_cpumask_var(&unit->cpu_hard_affinity_saved) ||
+         !zalloc_cpumask_var(&unit->cpu_soft_affinity) )
+        goto fail;
+
     return unit;
+
+ fail:
+    sched_free_unit(unit);
+    return NULL;
 }
 
 int sched_init_vcpu(struct vcpu *v, unsigned int processor)
@@ -363,7 +379,7 @@  int sched_move_domain(struct domain *d, struct cpupool *c)
 
     for_each_vcpu ( d, v )
     {
-        if ( v->affinity_broken )
+        if ( v->sched_unit->affinity_broken )
             return -EBUSY;
     }
 
@@ -682,7 +698,7 @@  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;
 
@@ -758,6 +774,7 @@  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));
 
@@ -769,15 +786,15 @@  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.
          */
-        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 )
+            if ( unit->affinity_broken )
             {
-                sched_set_affinity(v, v->cpu_hard_affinity_saved, NULL);
-                v->affinity_broken = 0;
-                cpumask_and(cpumask_scratch_cpu(cpu), v->cpu_hard_affinity,
+                sched_set_affinity(v, unit->cpu_hard_affinity_saved, NULL);
+                unit->affinity_broken = 0;
+                cpumask_and(cpumask_scratch_cpu(cpu), unit->cpu_hard_affinity,
                             cpupool_domain_cpumask(d));
             }
 
@@ -785,18 +802,17 @@  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);
 
-        lock = unit_schedule_lock_irq(v->sched_unit);
-        v->sched_unit->res = sched_pick_resource(vcpu_scheduler(v),
-                                                 v->sched_unit);
-        v->processor = v->sched_unit->res->processor;
+        lock = unit_schedule_lock_irq(unit);
+        unit->res = sched_pick_resource(vcpu_scheduler(v), unit);
+        v->processor = unit->res->processor;
         spin_unlock_irq(lock);
 
         if ( old_cpu != v->processor )
@@ -828,16 +844,17 @@  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 )
+                if ( unit->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;
                 }
@@ -850,7 +867,7 @@  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;
             }
 
@@ -863,7 +880,7 @@  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);
 
@@ -892,7 +909,7 @@  static int cpu_disable_scheduler_check(unsigned int cpu)
 
     for_each_domain_in_cpupool ( d, c )
         for_each_vcpu ( d, v )
-            if ( v->affinity_broken )
+            if ( v->sched_unit->affinity_broken )
                 return -EADDRINUSE;
 
     return 0;
@@ -908,28 +925,31 @@  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,
-                                            v->cpu_soft_affinity) &&
-                            cpumask_intersects(v->cpu_soft_affinity,
-                                               v->cpu_hard_affinity);
+    unit->soft_aff_effective = !cpumask_subset(unit->cpu_hard_affinity,
+                                               unit->cpu_soft_affinity) &&
+                               cpumask_intersects(unit->cpu_soft_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 )
+    if ( unit->affinity_broken )
         ret = -EBUSY;
     else
     {
@@ -937,19 +957,19 @@  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);
 
@@ -968,12 +988,12 @@  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. */
@@ -1167,28 +1187,30 @@  void watchdog_domain_destroy(struct domain *d)
 
 int vcpu_pin_override(struct vcpu *v, int cpu)
 {
+    struct sched_unit *unit = v->sched_unit;
     spinlock_t *lock;
     int ret = -EINVAL;
 
-    lock = unit_schedule_lock_irq(v->sched_unit);
+    lock = unit_schedule_lock_irq(unit);
 
     if ( cpu < 0 )
     {
-        if ( v->affinity_broken )
+        if ( unit->affinity_broken )
         {
-            sched_set_affinity(v, v->cpu_hard_affinity_saved, NULL);
-            v->affinity_broken = 0;
+            sched_set_affinity(v, unit->cpu_hard_affinity_saved, NULL);
+            unit->affinity_broken = 0;
             ret = 0;
         }
     }
     else if ( cpu < nr_cpu_ids )
     {
-        if ( v->affinity_broken )
+        if ( unit->affinity_broken )
             ret = -EBUSY;
         else if ( cpumask_test_cpu(cpu, VCPU2ONLINE(v)) )
         {
-            cpumask_copy(v->cpu_hard_affinity_saved, v->cpu_hard_affinity);
-            v->affinity_broken = 1;
+            cpumask_copy(unit->cpu_hard_affinity_saved,
+                         unit->cpu_hard_affinity);
+            unit->affinity_broken = 1;
             sched_set_affinity(v, cpumask_of(cpu), NULL);
             ret = 0;
         }
@@ -1197,7 +1219,7 @@  int vcpu_pin_override(struct vcpu *v, int cpu)
     if ( ret == 0 )
         vcpu_migrate_start(v);
 
-    unit_schedule_unlock_irq(lock, v->sched_unit);
+    unit_schedule_unlock_irq(lock, unit);
 
     domain_update_node_affinity(v->domain);
 
@@ -1549,7 +1571,7 @@  static void schedule(void)
         ((prev->pause_flags & VPF_blocked) ? RUNSTATE_blocked :
          (vcpu_runnable(prev) ? RUNSTATE_runnable : RUNSTATE_offline)),
         now);
-    prev->last_run_time = now;
+    prev->sched_unit->last_run_time = now;
 
     ASSERT(next->runstate.state != RUNSTATE_running);
     vcpu_runstate_change(next, RUNSTATE_running, now);
diff --git a/xen/common/wait.c b/xen/common/wait.c
index 4f830a14e8..37e9e0d016 100644
--- a/xen/common/wait.c
+++ b/xen/common/wait.c
@@ -132,7 +132,7 @@  static void __prepare_to_wait(struct waitqueue_vcpu *wqv)
 
     /* Save current VCPU affinity; force wakeup on *this* CPU only. */
     wqv->wakeup_cpu = smp_processor_id();
-    cpumask_copy(&wqv->saved_affinity, curr->cpu_hard_affinity);
+    cpumask_copy(&wqv->saved_affinity, curr->sched_unit->cpu_hard_affinity);
     if ( vcpu_set_hard_affinity(curr, cpumask_of(wqv->wakeup_cpu)) )
     {
         gdprintk(XENLOG_ERR, "Unable to set vcpu affinity\n");
@@ -199,7 +199,7 @@  void check_wakeup_from_wait(void)
     {
         /* Re-set VCPU affinity and re-enter the scheduler. */
         struct vcpu *curr = current;
-        cpumask_copy(&wqv->saved_affinity, curr->cpu_hard_affinity);
+        cpumask_copy(&wqv->saved_affinity, curr->sched_unit->cpu_hard_affinity);
         if ( vcpu_set_hard_affinity(curr, cpumask_of(wqv->wakeup_cpu)) )
         {
             gdprintk(XENLOG_ERR, "Unable to set vcpu affinity\n");
diff --git a/xen/include/xen/sched-if.h b/xen/include/xen/sched-if.h
index 20e36ea39b..17c01abc25 100644
--- a/xen/include/xen/sched-if.h
+++ b/xen/include/xen/sched-if.h
@@ -438,11 +438,11 @@  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 &&
-           !cpumask_subset(cpupool_domain_cpumask(v->domain),
-                           v->cpu_soft_affinity);
+    return unit->soft_aff_effective &&
+           !cpumask_subset(cpupool_domain_cpumask(unit->vcpu->domain),
+                           unit->cpu_soft_affinity);
 }
 
 /*
@@ -452,17 +452,18 @@  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);
 }
 
 #endif /* __XEN_SCHED_IF_H__ */
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index ee316cddd7..13c99a9194 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -175,9 +175,6 @@  struct vcpu
     } runstate_guest; /* guest address */
 #endif
 
-    /* last time when vCPU is scheduled out */
-    uint64_t last_run_time;
-
     /* Has the FPU been initialised? */
     bool             fpu_initialised;
     /* Has the FPU been used since it was last saved? */
@@ -203,8 +200,6 @@  struct vcpu
     bool             defer_shutdown;
     /* VCPU is paused following shutdown request (d->is_shutting_down)? */
     bool             paused_for_shutdown;
-    /* VCPU need affinity restored */
-    bool             affinity_broken;
 
     /* A hypercall has been preempted. */
     bool             hcall_preempted;
@@ -213,9 +208,6 @@  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;
@@ -247,16 +239,6 @@  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 change affinity temporarily. */
-    cpumask_var_t    cpu_hard_affinity_tmp;
-    /* Used to restore affinity across S3. */
-    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;
 
@@ -283,6 +265,22 @@  struct sched_unit {
     void                  *priv;      /* scheduler private data */
     struct sched_unit     *next_in_list;
     struct sched_resource *res;
+
+    /* Last time when unit has been scheduled out. */
+    uint64_t               last_run_time;
+
+    /* Item needs affinity restored. */
+    bool                   affinity_broken;
+    /* 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 change affinity temporarily. */
+    cpumask_var_t          cpu_hard_affinity_tmp;
+    /* Used to restore affinity across S3. */
+    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, e)                                         \
@@ -980,7 +978,7 @@  static inline bool is_hvm_vcpu(const struct vcpu *v)
 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);
 }
 
 #ifdef CONFIG_HAS_PASSTHROUGH