diff --git a/xen/arch/arm/domain_build.c b/xen/arch/arm/domain_build.c
index b84a4483cc..337a89e518 100644
--- a/xen/arch/arm/domain_build.c
+++ b/xen/arch/arm/domain_build.c
@@ -80,7 +80,7 @@ unsigned int __init dom0_max_vcpus(void)
 
 struct vcpu *__init alloc_dom0_vcpu0(struct domain *dom0)
 {
-    return vcpu_create(dom0, 0, 0);
+    return vcpu_create(dom0, 0);
 }
 
 static unsigned int __init get_allocation_size(paddr_t size)
@@ -1940,7 +1940,7 @@ static void __init find_gnttab_region(struct domain *d,
 
 static int __init construct_domain(struct domain *d, struct kernel_info *kinfo)
 {
-    int i, cpu;
+    unsigned int i;
     struct vcpu *v = d->vcpu[0];
     struct cpu_user_regs *regs = &v->arch.cpu_info->guest_cpu_user_regs;
 
@@ -2003,12 +2003,11 @@ static int __init construct_domain(struct domain *d, struct kernel_info *kinfo)
     }
 #endif
 
-    for ( i = 1, cpu = 0; i < d->max_vcpus; i++ )
+    for ( i = 1; i < d->max_vcpus; i++ )
     {
-        cpu = cpumask_cycle(cpu, &cpu_online_map);
-        if ( vcpu_create(d, i, cpu) == NULL )
+        if ( vcpu_create(d, i) == NULL )
         {
-            printk("Failed to allocate dom0 vcpu %d on pcpu %d\n", i, cpu);
+            printk("Failed to allocate d0v%u\n", i);
             break;
         }
 
@@ -2043,7 +2042,7 @@ static int __init construct_domU(struct domain *d,
 
     kinfo.vpl011 = dt_property_read_bool(node, "vpl011");
 
-    if ( vcpu_create(d, 0, 0) == NULL )
+    if ( vcpu_create(d, 0) == NULL )
         return -ENOMEM;
     d->max_pages = ~0U;
 
diff --git a/xen/arch/x86/dom0_build.c b/xen/arch/x86/dom0_build.c
index 454cf632d7..28b964e018 100644
--- a/xen/arch/x86/dom0_build.c
+++ b/xen/arch/x86/dom0_build.c
@@ -165,7 +165,7 @@ custom_param("dom0_max_vcpus", parse_dom0_max_vcpus);
 static __initdata unsigned int dom0_nr_pxms;
 static __initdata unsigned int dom0_pxms[MAX_NUMNODES] =
     { [0 ... MAX_NUMNODES - 1] = ~0 };
-static __initdata bool dom0_affinity_relaxed;
+bool __initdata dom0_affinity_relaxed;
 
 static int __init parse_dom0_nodes(const char *s)
 {
@@ -196,32 +196,7 @@ static int __init parse_dom0_nodes(const char *s)
 }
 custom_param("dom0_nodes", parse_dom0_nodes);
 
-static cpumask_t __initdata dom0_cpus;
-
-struct vcpu *__init dom0_setup_vcpu(struct domain *d,
-                                    unsigned int vcpu_id,
-                                    unsigned int prev_cpu)
-{
-    unsigned int cpu = cpumask_cycle(prev_cpu, &dom0_cpus);
-    struct vcpu *v = vcpu_create(d, vcpu_id, cpu);
-
-    if ( v )
-    {
-        if ( pv_shim )
-        {
-            sched_set_affinity(v, cpumask_of(vcpu_id), cpumask_of(vcpu_id));
-        }
-        else
-        {
-            if ( !opt_dom0_vcpus_pin && !dom0_affinity_relaxed )
-                sched_set_affinity(v, &dom0_cpus, NULL);
-            sched_set_affinity(v, NULL, &dom0_cpus);
-        }
-    }
-
-    return v;
-}
-
+cpumask_t __initdata dom0_cpus;
 static nodemask_t __initdata dom0_nodes;
 
 unsigned int __init dom0_max_vcpus(void)
@@ -273,8 +248,7 @@ struct vcpu *__init alloc_dom0_vcpu0(struct domain *dom0)
     dom0->node_affinity = dom0_nodes;
     dom0->auto_node_affinity = !dom0_nr_pxms;
 
-    return dom0_setup_vcpu(dom0, 0,
-                           cpumask_last(&dom0_cpus) /* so it wraps around to first pcpu */);
+    return vcpu_create(dom0, 0);
 }
 
 #ifdef CONFIG_SHADOW_PAGING
diff --git a/xen/arch/x86/hvm/dom0_build.c b/xen/arch/x86/hvm/dom0_build.c
index 8845399ae9..831325150b 100644
--- a/xen/arch/x86/hvm/dom0_build.c
+++ b/xen/arch/x86/hvm/dom0_build.c
@@ -614,7 +614,6 @@ static int __init pvh_setup_cpus(struct domain *d, paddr_t entry,
                                  paddr_t start_info)
 {
     struct vcpu *v = d->vcpu[0];
-    unsigned int cpu = v->processor, i;
     int rc;
     /*
      * This sets the vCPU state according to the state described in
@@ -635,15 +634,7 @@ static int __init pvh_setup_cpus(struct domain *d, paddr_t entry,
         .cpu_regs.x86_32.tr_ar = 0x8b,
     };
 
-    for ( i = 1; i < d->max_vcpus; i++ )
-    {
-        const struct vcpu *p = dom0_setup_vcpu(d, i, cpu);
-
-        if ( p )
-            cpu = p->processor;
-    }
-
-    domain_update_node_affinity(d);
+    sched_setup_dom0_vcpus(d);
 
     rc = arch_set_info_hvm_guest(v, &cpu_ctx);
     if ( rc )
diff --git a/xen/arch/x86/pv/dom0_build.c b/xen/arch/x86/pv/dom0_build.c
index 1bd53e9c08..9a97cf4abf 100644
--- a/xen/arch/x86/pv/dom0_build.c
+++ b/xen/arch/x86/pv/dom0_build.c
@@ -285,7 +285,7 @@ int __init dom0_construct_pv(struct domain *d,
                              module_t *initrd,
                              char *cmdline)
 {
-    int i, cpu, rc, compatible, order, machine;
+    int i, rc, compatible, order, machine;
     struct cpu_user_regs *regs;
     unsigned long pfn, mfn;
     unsigned long nr_pages;
@@ -694,16 +694,8 @@ int __init dom0_construct_pv(struct domain *d,
 
     printk("Dom%u has maximum %u VCPUs\n", d->domain_id, d->max_vcpus);
 
-    cpu = v->processor;
-    for ( i = 1; i < d->max_vcpus; i++ )
-    {
-        const struct vcpu *p = dom0_setup_vcpu(d, i, cpu);
+    sched_setup_dom0_vcpus(d);
 
-        if ( p )
-            cpu = p->processor;
-    }
-
-    domain_update_node_affinity(d);
     d->arch.paging.mode = 0;
 
     /* Set up CR3 value for write_ptbase */
diff --git a/xen/common/domain.c b/xen/common/domain.c
index 3665dfe0bd..cea88e7e56 100644
--- a/xen/common/domain.c
+++ b/xen/common/domain.c
@@ -135,8 +135,7 @@ static void vcpu_destroy(struct vcpu *v)
     free_vcpu_struct(v);
 }
 
-struct vcpu *vcpu_create(
-    struct domain *d, unsigned int vcpu_id, unsigned int cpu_id)
+struct vcpu *vcpu_create(struct domain *d, unsigned int vcpu_id)
 {
     struct vcpu *v;
 
@@ -168,7 +167,7 @@ struct vcpu *vcpu_create(
         init_waitqueue_vcpu(v);
     }
 
-    if ( sched_init_vcpu(v, cpu_id) != 0 )
+    if ( sched_init_vcpu(v) != 0 )
         goto fail_wq;
 
     if ( arch_vcpu_create(v) != 0 )
diff --git a/xen/common/domctl.c b/xen/common/domctl.c
index 2f9768f08f..8a694e0d37 100644
--- a/xen/common/domctl.c
+++ b/xen/common/domctl.c
@@ -532,8 +532,7 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
 
     case XEN_DOMCTL_max_vcpus:
     {
-        unsigned int i, max = op->u.max_vcpus.max, cpu;
-        cpumask_t *online;
+        unsigned int i, max = op->u.max_vcpus.max;
 
         ret = -EINVAL;
         if ( (d == current->domain) || /* no domain_pause() */
@@ -544,18 +543,13 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
         domain_pause(d);
 
         ret = -ENOMEM;
-        online = cpupool_domain_cpumask(d);
 
         for ( i = 0; i < max; i++ )
         {
             if ( d->vcpu[i] != NULL )
                 continue;
 
-            cpu = (i == 0) ?
-                cpumask_any(online) :
-                cpumask_cycle(d->vcpu[i-1]->processor, online);
-
-            if ( vcpu_create(d, i, cpu) == NULL )
+            if ( vcpu_create(d, i) == NULL )
                 goto maxvcpu_out;
         }
 
diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index b027c084bf..c5e0a585e2 100644
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -38,6 +38,12 @@
 #include <xsm/xsm.h>
 #include <xen/err.h>
 
+#ifdef CONFIG_XEN_GUEST
+#include <asm/guest.h>
+#else
+#define pv_shim false
+#endif
+
 /* opt_sched: scheduler - default to configured value */
 static char __initdata opt_sched[10] = CONFIG_SCHED_DEFAULT;
 string_param("sched", opt_sched);
@@ -80,6 +86,9 @@ extern const struct scheduler *__start_schedulers_array[], *__end_schedulers_arr
 
 static struct scheduler __read_mostly ops;
 
+static void sched_set_affinity(
+    struct sched_unit *unit, const cpumask_t *hard, const cpumask_t *soft);
+
 static spinlock_t *
 sched_idle_switch_sched(struct scheduler *new_ops, unsigned int cpu,
                         void *pdata, void *vdata)
@@ -372,14 +381,52 @@ static struct sched_unit *sched_alloc_unit(struct vcpu *v)
     return NULL;
 }
 
-int sched_init_vcpu(struct vcpu *v, unsigned int processor)
+static unsigned int sched_select_initial_cpu(const struct vcpu *v)
+{
+    const struct domain *d = v->domain;
+    nodeid_t node;
+    spinlock_t *lock;
+    unsigned long flags;
+    unsigned int cpu_ret, cpu = smp_processor_id();
+    cpumask_t *cpus = cpumask_scratch_cpu(cpu);
+
+    lock = pcpu_schedule_lock_irqsave(cpu, &flags);
+    cpumask_clear(cpus);
+    for_each_node_mask ( node, d->node_affinity )
+        cpumask_or(cpus, cpus, &node_to_cpumask(node));
+    cpumask_and(cpus, cpus, cpupool_domain_cpumask(d));
+    if ( cpumask_empty(cpus) )
+        cpumask_copy(cpus, cpupool_domain_cpumask(d));
+
+    if ( v->vcpu_id == 0 )
+        cpu_ret = cpumask_first(cpus);
+    else
+    {
+        /* We can rely on previous vcpu being available. */
+        ASSERT(!is_idle_domain(d));
+
+        cpu_ret = cpumask_cycle(d->vcpu[v->vcpu_id - 1]->processor, cpus);
+    }
+
+    pcpu_schedule_unlock_irqrestore(lock, flags, cpu);
+
+    return cpu_ret;
+}
+
+int sched_init_vcpu(struct vcpu *v)
 {
     struct domain *d = v->domain;
     struct sched_unit *unit;
+    unsigned int processor;
 
     if ( (unit = sched_alloc_unit(v)) == NULL )
         return 1;
 
+    if ( is_idle_domain(d) )
+        processor = v->vcpu_id;
+    else
+        processor = sched_select_initial_cpu(v);
+
     sched_set_res(unit, get_sched_res(processor));
 
     /* Initialise the per-vcpu timers. */
@@ -403,9 +450,9 @@ int sched_init_vcpu(struct vcpu *v, unsigned int processor)
      * domain-0 VCPUs, are pinned onto their respective physical CPUs.
      */
     if ( is_idle_domain(d) || (is_hardware_domain(d) && opt_dom0_vcpus_pin) )
-        sched_set_affinity(v, cpumask_of(processor), &cpumask_all);
+        sched_set_affinity(unit, cpumask_of(processor), &cpumask_all);
     else
-        sched_set_affinity(v, &cpumask_all, &cpumask_all);
+        sched_set_affinity(unit, &cpumask_all, &cpumask_all);
 
     /* Idle VCPUs are scheduled immediately, so don't put them in runqueue. */
     if ( is_idle_domain(d) )
@@ -496,7 +543,7 @@ int sched_move_domain(struct domain *d, struct cpupool *c)
 
         lock = unit_schedule_lock_irq(v->sched_unit);
 
-        sched_set_affinity(v, &cpumask_all, &cpumask_all);
+        sched_set_affinity(v->sched_unit, &cpumask_all, &cpumask_all);
 
         sched_set_res(v->sched_unit, get_sched_res(new_p));
         /*
@@ -839,7 +886,7 @@ void restore_vcpu_affinity(struct domain *d)
         {
             if ( v->affinity_broken )
             {
-                sched_set_affinity(v, unit->cpu_hard_affinity_saved, NULL);
+                sched_set_affinity(unit, unit->cpu_hard_affinity_saved, NULL);
                 v->affinity_broken = 0;
                 cpumask_and(cpumask_scratch_cpu(cpu), unit->cpu_hard_affinity,
                             cpupool_domain_cpumask(d));
@@ -848,7 +895,7 @@ void restore_vcpu_affinity(struct domain *d)
             if ( cpumask_empty(cpumask_scratch_cpu(cpu)) )
             {
                 printk(XENLOG_DEBUG "Breaking affinity for %pv\n", v);
-                sched_set_affinity(v, &cpumask_all, NULL);
+                sched_set_affinity(unit, &cpumask_all, NULL);
                 cpumask_and(cpumask_scratch_cpu(cpu), unit->cpu_hard_affinity,
                             cpupool_domain_cpumask(d));
             }
@@ -911,7 +958,7 @@ int cpu_disable_scheduler(unsigned int cpu)
 
                 printk(XENLOG_DEBUG "Breaking affinity for %pv\n", v);
 
-                sched_set_affinity(v, &cpumask_all, NULL);
+                sched_set_affinity(unit, &cpumask_all, NULL);
             }
 
             if ( v->processor != cpu )
@@ -970,14 +1017,12 @@ static int cpu_disable_scheduler_check(unsigned int cpu)
  * adjust_affinity hook may want to modify the vCPU state. However, when the
  * vCPU is being initialized (either for dom0 or domU) there is no risk of
  * races, and it's fine to not take the look (we're talking about
- * dom0_setup_vcpu() an sched_init_vcpu()).
+ * sched_setup_dom0_vcpus() an sched_init_vcpu()).
  */
-void sched_set_affinity(
-    struct vcpu *v, const cpumask_t *hard, const cpumask_t *soft)
+static void sched_set_affinity(
+    struct sched_unit *unit, const cpumask_t *hard, const cpumask_t *soft)
 {
-    struct sched_unit *unit = v->sched_unit;
-
-    sched_adjust_affinity(dom_scheduler(v->domain), unit, hard, soft);
+    sched_adjust_affinity(dom_scheduler(unit->domain), unit, hard, soft);
 
     if ( hard )
         cpumask_copy(unit->cpu_hard_affinity, hard);
@@ -1009,12 +1054,12 @@ static int vcpu_set_affinity(
          */
         if ( which == unit->cpu_hard_affinity )
         {
-            sched_set_affinity(v, affinity, NULL);
+            sched_set_affinity(unit, affinity, NULL);
         }
         else
         {
             ASSERT(which == unit->cpu_soft_affinity);
-            sched_set_affinity(v, NULL, affinity);
+            sched_set_affinity(unit, NULL, affinity);
         }
         vcpu_migrate_start(v);
     }
@@ -1262,7 +1307,7 @@ 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, unit->cpu_hard_affinity_saved, NULL);
+            sched_set_affinity(unit, unit->cpu_hard_affinity_saved, NULL);
     }
     else if ( cpu < nr_cpu_ids )
     {
@@ -1275,7 +1320,7 @@ int vcpu_temporary_affinity(struct vcpu *v, unsigned int cpu, uint8_t reason)
             {
                 cpumask_copy(unit->cpu_hard_affinity_saved,
                              unit->cpu_hard_affinity);
-                sched_set_affinity(v, cpumask_of(cpu), NULL);
+                sched_set_affinity(unit, cpumask_of(cpu), NULL);
             }
             v->affinity_broken |= reason;
             ret = 0;
@@ -1764,7 +1809,7 @@ static int cpu_schedule_up(unsigned int cpu)
         return 0;
 
     if ( idle_vcpu[cpu] == NULL )
-        vcpu_create(idle_vcpu[0]->domain, cpu, cpu);
+        vcpu_create(idle_vcpu[0]->domain, cpu);
     else
         idle_vcpu[cpu]->sched_unit->res = sr;
 
@@ -1943,7 +1988,7 @@ void __init scheduler_init(void)
     BUG_ON(nr_cpu_ids > ARRAY_SIZE(idle_vcpu));
     idle_domain->vcpu = idle_vcpu;
     idle_domain->max_vcpus = nr_cpu_ids;
-    if ( vcpu_create(idle_domain, 0, 0) == NULL )
+    if ( vcpu_create(idle_domain, 0) == NULL )
         BUG();
     get_sched_res(0)->curr = idle_vcpu[0]->sched_unit;
 }
@@ -2145,6 +2190,33 @@ void wait(void)
     schedule();
 }
 
+#ifdef CONFIG_X86
+void __init sched_setup_dom0_vcpus(struct domain *d)
+{
+    unsigned int i;
+    struct sched_unit *unit;
+
+    for ( i = 1; i < d->max_vcpus; i++ )
+        vcpu_create(d, i);
+
+    for_each_sched_unit ( d, unit )
+    {
+        unsigned int id = unit->unit_id;
+
+        if ( pv_shim )
+            sched_set_affinity(unit, cpumask_of(id), cpumask_of(id));
+        else
+        {
+            if ( !opt_dom0_vcpus_pin && !dom0_affinity_relaxed )
+                sched_set_affinity(unit, &dom0_cpus, NULL);
+            sched_set_affinity(unit, NULL, &dom0_cpus);
+        }
+    }
+
+    domain_update_node_affinity(d);
+}
+#endif
+
 #ifdef CONFIG_COMPAT
 #include "compat/schedule.c"
 #endif
diff --git a/xen/include/asm-x86/dom0_build.h b/xen/include/asm-x86/dom0_build.h
index 33a5483739..0b797b5806 100644
--- a/xen/include/asm-x86/dom0_build.h
+++ b/xen/include/asm-x86/dom0_build.h
@@ -11,8 +11,6 @@ extern unsigned int dom0_memflags;
 unsigned long dom0_compute_nr_pages(struct domain *d,
                                     struct elf_dom_parms *parms,
                                     unsigned long initrd_len);
-struct vcpu *dom0_setup_vcpu(struct domain *d, unsigned int vcpu_id,
-                             unsigned int cpu);
 int dom0_setup_permissions(struct domain *d);
 
 int dom0_construct_pv(struct domain *d, const module_t *image,
diff --git a/xen/include/xen/domain.h b/xen/include/xen/domain.h
index 3f09cb66c0..769302057b 100644
--- a/xen/include/xen/domain.h
+++ b/xen/include/xen/domain.h
@@ -13,8 +13,7 @@ typedef union {
     struct compat_vcpu_guest_context *cmp;
 } vcpu_guest_context_u __attribute__((__transparent_union__));
 
-struct vcpu *vcpu_create(
-    struct domain *d, unsigned int vcpu_id, unsigned int cpu_id);
+struct vcpu *vcpu_create(struct domain *d, unsigned int vcpu_id);
 
 unsigned int dom0_max_vcpus(void);
 struct vcpu *alloc_dom0_vcpu0(struct domain *dom0);
@@ -107,6 +106,8 @@ int continue_hypercall_on_cpu(
 extern unsigned int xen_processor_pmbits;
 
 extern bool_t opt_dom0_vcpus_pin;
+extern cpumask_t dom0_cpus;
+extern bool dom0_affinity_relaxed;
 
 /* vnuma topology per domain. */
 struct vnuma_info {
diff --git a/xen/include/xen/sched-if.h b/xen/include/xen/sched-if.h
index 45ac03f0f8..4797ba3f2b 100644
--- a/xen/include/xen/sched-if.h
+++ b/xen/include/xen/sched-if.h
@@ -498,7 +498,7 @@ struct cpupool
 #define cpupool_online_cpumask(_pool) \
     (((_pool) == NULL) ? &cpu_online_map : (_pool)->cpu_valid)
 
-static inline cpumask_t* cpupool_domain_cpumask(struct domain *d)
+static inline cpumask_t *cpupool_domain_cpumask(const struct domain *d)
 {
     /*
      * d->cpupool is NULL only for the idle domain, and no one should
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index 5646d620c3..6de9ddaaa9 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -661,7 +661,7 @@ void __domain_crash(struct domain *d);
 void noreturn asm_domain_crash_synchronous(unsigned long addr);
 
 void scheduler_init(void);
-int  sched_init_vcpu(struct vcpu *v, unsigned int processor);
+int  sched_init_vcpu(struct vcpu *v);
 void sched_destroy_vcpu(struct vcpu *v);
 int  sched_init_domain(struct domain *d, int poolid);
 void sched_destroy_domain(struct domain *d);
@@ -906,9 +906,7 @@ void scheduler_free(struct scheduler *sched);
 int schedule_cpu_switch(unsigned int cpu, struct cpupool *c);
 void vcpu_set_periodic_timer(struct vcpu *v, s_time_t value);
 int cpu_disable_scheduler(unsigned int cpu);
-/* We need it in dom0_setup_vcpu */
-void sched_set_affinity(struct vcpu *v, const cpumask_t *hard,
-                        const cpumask_t *soft);
+void sched_setup_dom0_vcpus(struct domain *d);
 int vcpu_temporary_affinity(struct vcpu *v, unsigned int cpu, uint8_t reason);
 int vcpu_set_hard_affinity(struct vcpu *v, const cpumask_t *affinity);
 int vcpu_set_soft_affinity(struct vcpu *v, const cpumask_t *affinity);