Implement vcpu soft affinity for credit1

index 8161585..3883f68 100644
@@ -3173,7 +3173,8 @@ 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_affinity_tmp, st->vcpu->cpu_affinity);
+    cpumask_copy(st->vcpu->cpu_hard_affinity_tmp,
+                 st->vcpu->cpu_hard_affinity);
 
     if ((cpu != st->processor)
        || (st->processor != st->vcpu->processor))

@@ -3208,11 +3209,11 @@ void async_exception_cleanup(struct vcpu *curr)
         return;
 
     /* Restore affinity.  */
-    if ( !cpumask_empty(curr->cpu_affinity_tmp) &&
-         !cpumask_equal(curr->cpu_affinity_tmp, curr->cpu_affinity) )
+    if ( !cpumask_empty(curr->cpu_hard_affinity_tmp) &&
+         !cpumask_equal(curr->cpu_hard_affinity_tmp, curr->cpu_hard_affinity) )
     {
-        vcpu_set_affinity(curr, curr->cpu_affinity_tmp);
-        cpumask_clear(curr->cpu_affinity_tmp);
+        vcpu_set_affinity(curr, curr->cpu_hard_affinity_tmp);
+        cpumask_clear(curr->cpu_hard_affinity_tmp);
     }
 
     if ( !(curr->async_exception_mask & (curr->async_exception_mask - 1)) )

index bc57174..141a5dc 100644
@@ -125,9 +125,9 @@ struct vcpu *alloc_vcpu(
 
     tasklet_init(&v->continue_hypercall_tasklet, NULL, 0);
 
-    if ( !zalloc_cpumask_var(&v->cpu_affinity) ||
-         !zalloc_cpumask_var(&v->cpu_affinity_tmp) ||
-         !zalloc_cpumask_var(&v->cpu_affinity_saved) ||
+    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->vcpu_dirty_cpumask) )
         goto fail_free;
 

@@ -156,9 +156,9 @@ struct vcpu *alloc_vcpu(
  fail_wq:
         destroy_waitqueue_vcpu(v);
  fail_free:
-        free_cpumask_var(v->cpu_affinity);
-        free_cpumask_var(v->cpu_affinity_tmp);
-        free_cpumask_var(v->cpu_affinity_saved);
+        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->vcpu_dirty_cpumask);
         free_vcpu_struct(v);
         return NULL;

@@ -427,7 +427,7 @@ void domain_update_node_affinity(struct domain *d)
 
     for_each_vcpu ( d, v )
     {
-        cpumask_and(online_affinity, v->cpu_affinity, online);
+        cpumask_and(online_affinity, v->cpu_hard_affinity, online);
         cpumask_or(cpumask, cpumask, online_affinity);
     }
 

@@ -792,9 +792,9 @@ static void complete_domain_destroy(struct rcu_head *head)
     for ( i = d->max_vcpus - 1; i >= 0; i-- )
         if ( (v = d->vcpu[i]) != NULL )
         {
-            free_cpumask_var(v->cpu_affinity);
-            free_cpumask_var(v->cpu_affinity_tmp);
-            free_cpumask_var(v->cpu_affinity_saved);
+            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->vcpu_dirty_cpumask);
             free_vcpu_struct(v);
         }

@@ -934,7 +934,7 @@ 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_affinity_tmp);
+    cpumask_clear(v->cpu_hard_affinity_tmp);
     clear_bit(_VPF_blocked, &v->pause_flags);
     clear_bit(_VPF_in_reset, &v->pause_flags);
 

index 4774277..b5c5c6c 100644
@@ -625,7 +625,7 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
         else
         {
             ret = cpumask_to_xenctl_bitmap(
-                &op->u.vcpuaffinity.cpumap, v->cpu_affinity);
+                &op->u.vcpuaffinity.cpumap, v->cpu_hard_affinity);
         }
     }
     break;

index 5afcfef..d6eb026 100644
@@ -295,7 +295,7 @@ static void dump_domains(unsigned char key)
                    !vcpu_event_delivery_is_enabled(v));
             cpuset_print(tmpstr, sizeof(tmpstr), v->vcpu_dirty_cpumask);
             printk("dirty_cpus=%s ", tmpstr);
-            cpuset_print(tmpstr, sizeof(tmpstr), v->cpu_affinity);
+            cpuset_print(tmpstr, sizeof(tmpstr), v->cpu_hard_affinity);
             printk("cpu_affinity=%s\n", tmpstr);
             printk("    pause_count=%d pause_flags=%lx\n",
                    atomic_read(&v->pause_count), v->pause_flags);

index db5512e..c6a2560 100644
@@ -332,13 +332,13 @@ csched_balance_cpumask(const struct vcpu *vc, int step, cpumask_t *mask)
     if ( step == CSCHED_BALANCE_NODE_AFFINITY )
     {
         cpumask_and(mask, CSCHED_DOM(vc->domain)->node_affinity_cpumask,
-                    vc->cpu_affinity);
+                    vc->cpu_hard_affinity);
 
         if ( unlikely(cpumask_empty(mask)) )
-            cpumask_copy(mask, vc->cpu_affinity);
+            cpumask_copy(mask, vc->cpu_hard_affinity);
     }
     else /* step == CSCHED_BALANCE_CPU_AFFINITY */
-        cpumask_copy(mask, vc->cpu_affinity);
+        cpumask_copy(mask, vc->cpu_hard_affinity);
 }
 
 static void burn_credits(struct csched_vcpu *svc, s_time_t now)

@@ -407,7 +407,7 @@ __runq_tickle(unsigned int cpu, struct csched_vcpu *new)
 
             if ( balance_step == CSCHED_BALANCE_NODE_AFFINITY
                  && !__vcpu_has_node_affinity(new->vcpu,
-                                              new->vcpu->cpu_affinity) )
+                                              new->vcpu->cpu_hard_affinity) )
                 continue;
 
             /* Are there idlers suitable for new (for this balance step)? */

@@ -642,7 +642,7 @@ _csched_cpu_pick(const struct scheduler *ops, struct vcpu *vc, bool_t commit)
 
     /* Store in cpus the mask of online cpus on which the domain can run */
     online = cpupool_scheduler_cpumask(vc->domain->cpupool);
-    cpumask_and(&cpus, vc->cpu_affinity, online);
+    cpumask_and(&cpus, vc->cpu_hard_affinity, online);
 
     for_each_csched_balance_step( balance_step )
     {

@@ -1498,7 +1498,7 @@ csched_runq_steal(int peer_cpu, int cpu, int pri, int balance_step)
              * or counter.
              */
             if ( balance_step == CSCHED_BALANCE_NODE_AFFINITY
-                 && !__vcpu_has_node_affinity(vc, vc->cpu_affinity) )
+                 && !__vcpu_has_node_affinity(vc, vc->cpu_hard_affinity) )
                 continue;
 
             csched_balance_cpumask(vc, balance_step, csched_balance_mask);

index 0c9011a..7c80bad 100644
@@ -384,7 +384,7 @@ static int sedf_pick_cpu(const struct scheduler *ops, struct vcpu *v)
     cpumask_t *online;
 
     online = cpupool_scheduler_cpumask(v->domain->cpupool);
-    cpumask_and(&online_affinity, v->cpu_affinity, online);
+    cpumask_and(&online_affinity, v->cpu_hard_affinity, online);
     return cpumask_cycle(v->vcpu_id % cpumask_weight(&online_affinity) - 1,
                          &online_affinity);
 }

index c174c41..4c633da 100644
@@ -194,9 +194,9 @@ int sched_init_vcpu(struct vcpu *v, unsigned int processor)
      */
     v->processor = processor;
     if ( is_idle_domain(d) || d->is_pinned )
-        cpumask_copy(v->cpu_affinity, cpumask_of(processor));
+        cpumask_copy(v->cpu_hard_affinity, cpumask_of(processor));
     else
-        cpumask_setall(v->cpu_affinity);
+        cpumask_setall(v->cpu_hard_affinity);
 
     /* Initialise the per-vcpu timers. */
     init_timer(&v->periodic_timer, vcpu_periodic_timer_fn,

@@ -285,7 +285,7 @@ int sched_move_domain(struct domain *d, struct cpupool *c)
         migrate_timer(&v->singleshot_timer, new_p);
         migrate_timer(&v->poll_timer, new_p);
 
-        cpumask_setall(v->cpu_affinity);
+        cpumask_setall(v->cpu_hard_affinity);
 
         lock = vcpu_schedule_lock_irq(v);
         v->processor = new_p;

@@ -457,7 +457,7 @@ static void vcpu_migrate(struct vcpu *v)
              */
             if ( pick_called &&
                  (new_lock == per_cpu(schedule_data, new_cpu).schedule_lock) &&
-                 cpumask_test_cpu(new_cpu, v->cpu_affinity) &&
+                 cpumask_test_cpu(new_cpu, v->cpu_hard_affinity) &&
                  cpumask_test_cpu(new_cpu, v->domain->cpupool->cpu_valid) )
                 break;
 

@@ -560,7 +560,7 @@ void restore_vcpu_affinity(struct domain *d)
         if ( v->affinity_broken )
         {
             printk(XENLOG_DEBUG "Restoring affinity for %pv\n", v);
-            cpumask_copy(v->cpu_affinity, v->cpu_affinity_saved);
+            cpumask_copy(v->cpu_hard_affinity, v->cpu_hard_affinity_saved);
             v->affinity_broken = 0;
         }
 

@@ -603,19 +603,20 @@ int cpu_disable_scheduler(unsigned int cpu)
             unsigned long flags;
             spinlock_t *lock = vcpu_schedule_lock_irqsave(v, &flags);
 
-            cpumask_and(&online_affinity, v->cpu_affinity, c->cpu_valid);
+            cpumask_and(&online_affinity, v->cpu_hard_affinity, c->cpu_valid);
             if ( cpumask_empty(&online_affinity) &&
-                 cpumask_test_cpu(cpu, v->cpu_affinity) )
+                 cpumask_test_cpu(cpu, v->cpu_hard_affinity) )
             {
                 printk(XENLOG_DEBUG "Breaking affinity for %pv\n", v);
 
                 if (system_state == SYS_STATE_suspend)
                 {
-                    cpumask_copy(v->cpu_affinity_saved, v->cpu_affinity);
+                    cpumask_copy(v->cpu_hard_affinity_saved,
+                                 v->cpu_hard_affinity);
                     v->affinity_broken = 1;
                 }
 
-                cpumask_setall(v->cpu_affinity);
+                cpumask_setall(v->cpu_hard_affinity);
             }
 
             if ( v->processor == cpu )

@@ -663,7 +664,7 @@ int vcpu_set_affinity(struct vcpu *v, const cpumask_t *affinity)
 
     lock = vcpu_schedule_lock_irq(v);
 
-    cpumask_copy(v->cpu_affinity, affinity);
+    cpumask_copy(v->cpu_hard_affinity, affinity);
 
     /* Always ask the scheduler to re-evaluate placement
      * when changing the affinity */

index 3c9366c..3f6ff41 100644
@@ -134,7 +134,7 @@ 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_affinity);
+    cpumask_copy(&wqv->saved_affinity, curr->cpu_hard_affinity);
     if ( vcpu_set_affinity(curr, cpumask_of(wqv->wakeup_cpu)) )
     {
         gdprintk(XENLOG_ERR, "Unable to set vcpu affinity\n");

@@ -183,7 +183,7 @@ 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_affinity);
+        cpumask_copy(&wqv->saved_affinity, curr->cpu_hard_affinity);
         if ( vcpu_set_affinity(curr, cpumask_of(wqv->wakeup_cpu)) )
         {
             gdprintk(XENLOG_ERR, "Unable to set vcpu affinity\n");

index 44851ae..6f91abd 100644
@@ -219,11 +219,11 @@ struct vcpu
     spinlock_t       virq_lock;
 
     /* Bitmask of CPUs on which this VCPU may run. */
-    cpumask_var_t    cpu_affinity;
+    cpumask_var_t    cpu_hard_affinity;
     /* Used to change affinity temporarily. */
-    cpumask_var_t    cpu_affinity_tmp;
+    cpumask_var_t    cpu_hard_affinity_tmp;
     /* Used to restore affinity across S3. */
-    cpumask_var_t    cpu_affinity_saved;
+    cpumask_var_t    cpu_hard_affinity_saved;
 
     /* Bitmask of CPUs which are holding onto this VCPU's state. */
     cpumask_var_t    vcpu_dirty_cpumask;

@@ -819,7 +819,7 @@ void watchdog_domain_destroy(struct domain *d);
 #define has_hvm_container_domain(d) ((d)->guest_type != guest_type_pv)
 #define has_hvm_container_vcpu(v)   (has_hvm_container_domain((v)->domain))
 #define is_pinned_vcpu(v) ((v)->domain->is_pinned || \
-                           cpumask_weight((v)->cpu_affinity) == 1)
+                           cpumask_weight((v)->cpu_hard_affinity) == 1)
 #ifdef HAS_PASSTHROUGH
 #define need_iommu(d)    ((d)->need_iommu)
 #else

index 141a5dc..e20d3bf 100644
@@ -128,6 +128,7 @@ struct vcpu *alloc_vcpu(
     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) ||
          !zalloc_cpumask_var(&v->vcpu_dirty_cpumask) )
         goto fail_free;
 

@@ -159,6 +160,7 @@ struct vcpu *alloc_vcpu(
         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_cpumask_var(v->vcpu_dirty_cpumask);
         free_vcpu_struct(v);
         return NULL;

@@ -446,8 +448,6 @@ void domain_update_node_affinity(struct domain *d)
                 node_set(node, d->node_affinity);
     }
 
-    sched_set_node_affinity(d, &d->node_affinity);
-
     spin_unlock(&d->node_affinity_lock);
 
     free_cpumask_var(online_affinity);

@@ -795,6 +795,7 @@ static void complete_domain_destroy(struct rcu_head *head)
             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_cpumask_var(v->vcpu_dirty_cpumask);
             free_vcpu_struct(v);
         }

index d6eb026..809378c 100644
@@ -297,6 +297,8 @@ static void dump_domains(unsigned char key)
             printk("dirty_cpus=%s ", tmpstr);
             cpuset_print(tmpstr, sizeof(tmpstr), v->cpu_hard_affinity);
             printk("cpu_affinity=%s\n", tmpstr);
+            cpuset_print(tmpstr, sizeof(tmpstr), v->cpu_soft_affinity);
+            printk("cpu_soft_affinity=%s\n", tmpstr);
             printk("    pause_count=%d pause_flags=%lx\n",
                    atomic_read(&v->pause_count), v->pause_flags);
             arch_dump_vcpu_info(v);

283 lines not on this page · raw message

index 4c633da..6499954 100644
@@ -198,6 +198,8 @@ int sched_init_vcpu(struct vcpu *v, unsigned int processor)
     else
         cpumask_setall(v->cpu_hard_affinity);
 
+    cpumask_setall(v->cpu_soft_affinity);
+
     /* Initialise the per-vcpu timers. */
     init_timer(&v->periodic_timer, vcpu_periodic_timer_fn,
                v, v->processor);

@@ -286,6 +288,7 @@ int sched_move_domain(struct domain *d, struct cpupool *c)
         migrate_timer(&v->poll_timer, new_p);
 
         cpumask_setall(v->cpu_hard_affinity);
+        cpumask_setall(v->cpu_soft_affinity);
 
         lock = vcpu_schedule_lock_irq(v);
         v->processor = new_p;

@@ -644,11 +647,6 @@ int cpu_disable_scheduler(unsigned int cpu)
     return ret;
 }
 
-void sched_set_node_affinity(struct domain *d, nodemask_t *mask)
-{
-    SCHED_OP(DOM2OP(d), set_node_affinity, d, mask);
-}
-
 int vcpu_set_affinity(struct vcpu *v, const cpumask_t *affinity)
 {
     cpumask_t online_affinity;

index d95e254..4164dff 100644
@@ -158,8 +158,6 @@ struct scheduler {
                                     struct xen_domctl_scheduler_op *);
     int          (*adjust_global)  (const struct scheduler *,
                                     struct xen_sysctl_scheduler_op *);
-    void         (*set_node_affinity) (const struct scheduler *,
-                                       struct domain *, nodemask_t *);
     void         (*dump_settings)  (const struct scheduler *);
     void         (*dump_cpu_state) (const struct scheduler *, int);
 

index 6f91abd..445b659 100644
@@ -225,6 +225,9 @@ struct vcpu
     /* 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;
+
     /* Bitmask of CPUs which are holding onto this VCPU's state. */
     cpumask_var_t    vcpu_dirty_cpumask;
 

@@ -627,7 +630,6 @@ void sched_destroy_domain(struct domain *d);
 int sched_move_domain(struct domain *d, struct cpupool *c);
 long sched_adjust(struct domain *, struct xen_domctl_scheduler_op *);
 long sched_adjust_global(struct xen_sysctl_scheduler_op *);
-void sched_set_node_affinity(struct domain *, nodemask_t *);
 int  sched_id(void);
 void sched_tick_suspend(void);
 void sched_tick_resume(void);

index e20d3bf..c3a576e 100644
@@ -409,17 +409,17 @@ struct domain *domain_create(
 
 void domain_update_node_affinity(struct domain *d)
 {
-    cpumask_var_t cpumask;
-    cpumask_var_t online_affinity;
+    cpumask_var_t dom_cpumask, dom_cpumask_soft;
+    cpumask_t *dom_affinity;
     const cpumask_t *online;
     struct vcpu *v;
-    unsigned int node;
+    unsigned int cpu;
 
-    if ( !zalloc_cpumask_var(&cpumask) )
+    if ( !zalloc_cpumask_var(&dom_cpumask) )
         return;
-    if ( !alloc_cpumask_var(&online_affinity) )
+    if ( !zalloc_cpumask_var(&dom_cpumask_soft) )
     {
-        free_cpumask_var(cpumask);
+        free_cpumask_var(dom_cpumask);
         return;
     }
 

@@ -427,31 +427,48 @@ void domain_update_node_affinity(struct domain *d)
 
     spin_lock(&d->node_affinity_lock);
 
-    for_each_vcpu ( d, v )
-    {
-        cpumask_and(online_affinity, v->cpu_hard_affinity, online);
-        cpumask_or(cpumask, cpumask, online_affinity);
-    }
-
     /*
-     * If d->auto_node_affinity is true, the domain's node-affinity mask
-     * (d->node_affinity) is automaically computed from all the domain's
-     * vcpus' vcpu-affinity masks (the union of which we have just built
-     * above in cpumask). OTOH, if d->auto_node_affinity is false, we
-     * must leave the node-affinity of the domain alone.
+     * If d->auto_node_affinity is true, let's compute the domain's
+     * node-affinity and update d->node_affinity accordingly. if false,
+     * just leave d->auto_node_affinity alone.
      */
     if ( d->auto_node_affinity )
     {
+        /*
+         * We want the narrowest possible set of pcpus (to get the narowest
+         * possible set of nodes). What we need is the cpumask of where the
+         * domain can run (the union of the hard affinity of all its vcpus),
+         * and the full mask of where it would prefer to run (the union of
+         * the soft affinity of all its various vcpus). Let's build them.
+         */
+        for_each_vcpu ( d, v )
+        {
+            cpumask_or(dom_cpumask, dom_cpumask, v->cpu_hard_affinity);
+            cpumask_or(dom_cpumask_soft, dom_cpumask_soft,
+                       v->cpu_soft_affinity);
+        }
+        /* Filter out non-online cpus */
+        cpumask_and(dom_cpumask, dom_cpumask, online);
+        ASSERT(!cpumask_empty(dom_cpumask));
+        /* And compute the intersection between hard, online and soft */
+        cpumask_and(dom_cpumask_soft, dom_cpumask_soft, dom_cpumask);
+
+        /*
+         * If not empty, the intersection of hard, soft and online is the
+         * narrowest set we want. If empty, we fall back to hard&online.
+         */
+        dom_affinity = cpumask_empty(dom_cpumask_soft) ?
+                           dom_cpumask : dom_cpumask_soft;
+
         nodes_clear(d->node_affinity);
-        for_each_online_node ( node )
-            if ( cpumask_intersects(&node_to_cpumask(node), cpumask) )
-                node_set(node, d->node_affinity);
+        for_each_cpu ( cpu, dom_affinity )
+            node_set(cpu_to_node(cpu), d->node_affinity);
     }
 
     spin_unlock(&d->node_affinity_lock);
 
-    free_cpumask_var(online_affinity);
-    free_cpumask_var(cpumask);
+    free_cpumask_var(dom_cpumask_soft);
+    free_cpumask_var(dom_cpumask);
 }
 
 

index 6499954..5abefa1 100644
@@ -309,7 +309,9 @@ int sched_move_domain(struct domain *d, struct cpupool *c)
         SCHED_OP(old_ops, free_vdata, vcpudata);
     }
 
-    domain_update_node_affinity(d);
+    /* Do we have vcpus already? If not, no need to update node-affinity */
+    if ( d->vcpu )
+        domain_update_node_affinity(d);
 
     domain_unpause(d);

index 37ed141..861b471 100644
@@ -225,13 +225,14 @@ int xc_vcpu_setaffinity(xc_interface *xch,
 
     domctl.cmd = XEN_DOMCTL_setvcpuaffinity;
     domctl.domain = (domid_t)domid;
-    domctl.u.vcpuaffinity.vcpu    = vcpu;
+    domctl.u.vcpuaffinity.vcpu = vcpu;
+    domctl.u.vcpuaffinity.flags = XEN_VCPUAFFINITY_HARD;
 
     memcpy(local, cpumap, cpusize);
 
-    set_xen_guest_handle(domctl.u.vcpuaffinity.cpumap.bitmap, local);
+    set_xen_guest_handle(domctl.u.vcpuaffinity.cpumap_hard.bitmap, local);
 
-    domctl.u.vcpuaffinity.cpumap.nr_bits = cpusize * 8;
+    domctl.u.vcpuaffinity.cpumap_hard.nr_bits = cpusize * 8;
 
     ret = do_domctl(xch, &domctl);
 

@@ -269,9 +270,10 @@ int xc_vcpu_getaffinity(xc_interface *xch,
     domctl.cmd = XEN_DOMCTL_getvcpuaffinity;
     domctl.domain = (domid_t)domid;
     domctl.u.vcpuaffinity.vcpu = vcpu;
+    domctl.u.vcpuaffinity.flags = XEN_VCPUAFFINITY_HARD;
 
-    set_xen_guest_handle(domctl.u.vcpuaffinity.cpumap.bitmap, local);
-    domctl.u.vcpuaffinity.cpumap.nr_bits = cpusize * 8;
+    set_xen_guest_handle(domctl.u.vcpuaffinity.cpumap_hard.bitmap, local);
+    domctl.u.vcpuaffinity.cpumap_hard.nr_bits = cpusize * 8;
 
     ret = do_domctl(xch, &domctl);
 

index 3883f68..c3eec8e 100644
@@ -3183,7 +3183,7 @@ static void nmi_mce_softirq(void)
          * Make sure to wakeup the vcpu on the
          * specified processor.
          */
-        vcpu_set_affinity(st->vcpu, cpumask_of(st->processor));
+        vcpu_set_hard_affinity(st->vcpu, cpumask_of(st->processor));
 
         /* Affinity is restored in the iret hypercall. */
     }

@@ -3212,7 +3212,7 @@ void async_exception_cleanup(struct vcpu *curr)
     if ( !cpumask_empty(curr->cpu_hard_affinity_tmp) &&
          !cpumask_equal(curr->cpu_hard_affinity_tmp, curr->cpu_hard_affinity) )
     {
-        vcpu_set_affinity(curr, curr->cpu_hard_affinity_tmp);
+        vcpu_set_hard_affinity(curr, curr->cpu_hard_affinity_tmp);
         cpumask_clear(curr->cpu_hard_affinity_tmp);
     }
 

134 lines not on this page · raw message

index 5abefa1..6a726af 100644
@@ -649,22 +649,14 @@ int cpu_disable_scheduler(unsigned int cpu)
     return ret;
 }
 
-int vcpu_set_affinity(struct vcpu *v, const cpumask_t *affinity)
+static int vcpu_set_affinity(
+    struct vcpu *v, const cpumask_t *affinity, cpumask_t *which)
 {
-    cpumask_t online_affinity;
-    cpumask_t *online;
     spinlock_t *lock;
 
-    if ( v->domain->is_pinned )
-        return -EINVAL;
-    online = VCPU2ONLINE(v);
-    cpumask_and(&online_affinity, affinity, online);
-    if ( cpumask_empty(&online_affinity) )
-        return -EINVAL;
-
     lock = vcpu_schedule_lock_irq(v);
 
-    cpumask_copy(v->cpu_hard_affinity, affinity);
+    cpumask_copy(which, affinity);
 
     /* Always ask the scheduler to re-evaluate placement
      * when changing the affinity */

@@ -683,6 +675,27 @@ int vcpu_set_affinity(struct vcpu *v, const cpumask_t *affinity)
     return 0;
 }
 
+int vcpu_set_hard_affinity(struct vcpu *v, const cpumask_t *affinity)
+{
+    cpumask_t online_affinity;
+    cpumask_t *online;
+
+    if ( v->domain->is_pinned )
+        return -EINVAL;
+
+    online = VCPU2ONLINE(v);
+    cpumask_and(&online_affinity, affinity, online);
+    if ( cpumask_empty(&online_affinity) )
+        return -EINVAL;
+
+    return vcpu_set_affinity(v, affinity, v->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);
+}
+
 /* Block the currently-executing domain until a pertinent event occurs. */
 void vcpu_block(void)
 {

index 3f6ff41..1f6b597 100644
@@ -135,7 +135,7 @@ 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);
-    if ( vcpu_set_affinity(curr, cpumask_of(wqv->wakeup_cpu)) )
+    if ( vcpu_set_hard_affinity(curr, cpumask_of(wqv->wakeup_cpu)) )
     {
         gdprintk(XENLOG_ERR, "Unable to set vcpu affinity\n");
         domain_crash_synchronous();

@@ -166,7 +166,7 @@ static void __prepare_to_wait(struct waitqueue_vcpu *wqv)
 static void __finish_wait(struct waitqueue_vcpu *wqv)
 {
     wqv->esp = NULL;
-    (void)vcpu_set_affinity(current, &wqv->saved_affinity);
+    (void)vcpu_set_hard_affinity(current, &wqv->saved_affinity);
 }
 
 void check_wakeup_from_wait(void)

@@ -184,7 +184,7 @@ 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);
-        if ( vcpu_set_affinity(curr, cpumask_of(wqv->wakeup_cpu)) )
+        if ( vcpu_set_hard_affinity(curr, cpumask_of(wqv->wakeup_cpu)) )
         {
             gdprintk(XENLOG_ERR, "Unable to set vcpu affinity\n");
             domain_crash_synchronous();

index 385b053..365446f 100644
@@ -300,8 +300,33 @@ DEFINE_XEN_GUEST_HANDLE(xen_domctl_nodeaffinity_t);
 /* XEN_DOMCTL_setvcpuaffinity */
 /* XEN_DOMCTL_getvcpuaffinity */
 struct xen_domctl_vcpuaffinity {
-    uint32_t  vcpu;              /* IN */
-    struct xenctl_bitmap cpumap; /* IN/OUT */
+    /* IN variables. */
+    uint32_t  vcpu;
+ /* Set/get the hard affinity for vcpu */
+#define _XEN_VCPUAFFINITY_HARD  0
+#define XEN_VCPUAFFINITY_HARD   (1U<<_XEN_VCPUAFFINITY_HARD)
+ /* Set/get the soft affinity for vcpu */
+#define _XEN_VCPUAFFINITY_SOFT  1
+#define XEN_VCPUAFFINITY_SOFT   (1U<<_XEN_VCPUAFFINITY_SOFT)
+    uint32_t flags;
+    /*
+     * IN/OUT variables.
+     *
+     * Both are IN/OUT for XEN_DOMCTL_setvcpuaffinity, in which case they
+     * contain effective hard or/and soft affinity. That is, upon successful
+     * return, cpumap_soft, contains the intersection of the soft affinity,
+     * hard affinity and the cpupool's online CPUs for the domain (if
+     * XEN_VCPUAFFINITY_SOFT was set in flags). cpumap_hard contains the
+     * intersection between hard affinity and the cpupool's online CPUs (if
+     * XEN_VCPUAFFINITY_HARD was set in flags).
+     *
+     * Both are OUT-only for XEN_DOMCTL_getvcpuaffinity, in which case they
+     * contain the plain hard and/or soft affinity masks that were set during
+     * previous successful calls to XEN_DOMCTL_setvcpuaffinity (or the
+     * default values), without intersecting or altering them in any way.
+     */
+    struct xenctl_bitmap cpumap_hard;
+    struct xenctl_bitmap cpumap_soft;
 };
 typedef struct xen_domctl_vcpuaffinity xen_domctl_vcpuaffinity_t;
 DEFINE_XEN_GUEST_HANDLE(xen_domctl_vcpuaffinity_t);

index 445b659..f920e1a 100644
@@ -781,7 +781,8 @@ void scheduler_free(struct scheduler *sched);
 int schedule_cpu_switch(unsigned int cpu, struct cpupool *c);
 void vcpu_force_reschedule(struct vcpu *v);
 int cpu_disable_scheduler(unsigned int cpu);
-int vcpu_set_affinity(struct vcpu *v, const cpumask_t *affinity);
+int vcpu_set_hard_affinity(struct vcpu *v, const cpumask_t *affinity);
+int vcpu_set_soft_affinity(struct vcpu *v, const cpumask_t *affinity);
 void restore_vcpu_affinity(struct domain *d);
 
 void vcpu_runstate_get(struct vcpu *v, struct vcpu_runstate_info *runstate);

index 861b471..20ed127 100644
@@ -202,10 +202,15 @@ int xc_domain_node_getaffinity(xc_interface *xch,
 int xc_vcpu_setaffinity(xc_interface *xch,
                         uint32_t domid,
                         int vcpu,
-                        xc_cpumap_t cpumap)
+                        xc_cpumap_t cpumap_hard_inout,
+                        xc_cpumap_t cpumap_soft_inout,
+                        uint32_t flags)
 {
     DECLARE_DOMCTL;
-    DECLARE_HYPERCALL_BUFFER(uint8_t, local);
+    DECLARE_HYPERCALL_BOUNCE(cpumap_hard_inout, 0,
+                             XC_HYPERCALL_BUFFER_BOUNCE_BOTH);
+    DECLARE_HYPERCALL_BOUNCE(cpumap_soft_inout, 0,
+                             XC_HYPERCALL_BUFFER_BOUNCE_BOTH);
     int ret = -1;
     int cpusize;
 

@@ -213,32 +218,37 @@ int xc_vcpu_setaffinity(xc_interface *xch,
     if (cpusize <= 0)
     {
         PERROR("Could not get number of cpus");
-        goto out;
+        return -1;
     }
 
-    local = xc_hypercall_buffer_alloc(xch, local, cpusize);
-    if ( local == NULL )
+    HYPERCALL_BOUNCE_SET_SIZE(cpumap_hard_inout, cpusize);
+    HYPERCALL_BOUNCE_SET_SIZE(cpumap_soft_inout, cpusize);
+
+    if ( xc_hypercall_bounce_pre(xch, cpumap_hard_inout) ||
+         xc_hypercall_bounce_pre(xch, cpumap_soft_inout) )
     {
-        PERROR("Could not allocate memory for setvcpuaffinity domctl hypercall");
+        PERROR("Could not allocate hcall buffers for DOMCTL_setvcpuaffinity");
         goto out;
     }
 
     domctl.cmd = XEN_DOMCTL_setvcpuaffinity;
     domctl.domain = (domid_t)domid;
     domctl.u.vcpuaffinity.vcpu = vcpu;
-    domctl.u.vcpuaffinity.flags = XEN_VCPUAFFINITY_HARD;
-
-    memcpy(local, cpumap, cpusize);
-
-    set_xen_guest_handle(domctl.u.vcpuaffinity.cpumap_hard.bitmap, local);
+    domctl.u.vcpuaffinity.flags = flags;
 
+    set_xen_guest_handle(domctl.u.vcpuaffinity.cpumap_hard.bitmap,
+                         cpumap_hard_inout);
     domctl.u.vcpuaffinity.cpumap_hard.nr_bits = cpusize * 8;
+    set_xen_guest_handle(domctl.u.vcpuaffinity.cpumap_soft.bitmap,
+                         cpumap_soft_inout);
+    domctl.u.vcpuaffinity.cpumap_soft.nr_bits = cpusize * 8;
 
     ret = do_domctl(xch, &domctl);
 
-    xc_hypercall_buffer_free(xch, local);
-
  out:
+    xc_hypercall_bounce_post(xch, cpumap_hard_inout);
+    xc_hypercall_bounce_post(xch, cpumap_soft_inout);
+
     return ret;
 }
 

@@ -246,10 +256,13 @@ int xc_vcpu_setaffinity(xc_interface *xch,
 int xc_vcpu_getaffinity(xc_interface *xch,
                         uint32_t domid,
                         int vcpu,
-                        xc_cpumap_t cpumap)
+                        xc_cpumap_t cpumap_hard,
+                        xc_cpumap_t cpumap_soft,
+                        uint32_t flags)
 {
     DECLARE_DOMCTL;
-    DECLARE_HYPERCALL_BUFFER(uint8_t, local);
+    DECLARE_HYPERCALL_BOUNCE(cpumap_hard, 0, XC_HYPERCALL_BUFFER_BOUNCE_OUT);
+    DECLARE_HYPERCALL_BOUNCE(cpumap_soft, 0, XC_HYPERCALL_BUFFER_BOUNCE_OUT);
     int ret = -1;
     int cpusize;
 

@@ -257,30 +270,37 @@ int xc_vcpu_getaffinity(xc_interface *xch,
     if (cpusize <= 0)
     {
         PERROR("Could not get number of cpus");
-        goto out;
+        return -1;
     }
 
-    local = xc_hypercall_buffer_alloc(xch, local, cpusize);
-    if (local == NULL)
+    HYPERCALL_BOUNCE_SET_SIZE(cpumap_hard, cpusize);
+    HYPERCALL_BOUNCE_SET_SIZE(cpumap_soft, cpusize);
+
+    if ( xc_hypercall_bounce_pre(xch, cpumap_hard) ||
+         xc_hypercall_bounce_pre(xch, cpumap_soft) )
     {
-        PERROR("Could not allocate memory for getvcpuaffinity domctl hypercall");
+        PERROR("Could not allocate hcall buffers for DOMCTL_getvcpuaffinity");
         goto out;
     }
 
     domctl.cmd = XEN_DOMCTL_getvcpuaffinity;
     domctl.domain = (domid_t)domid;
     domctl.u.vcpuaffinity.vcpu = vcpu;
-    domctl.u.vcpuaffinity.flags = XEN_VCPUAFFINITY_HARD;
+    domctl.u.vcpuaffinity.flags = flags;
 
-    set_xen_guest_handle(domctl.u.vcpuaffinity.cpumap_hard.bitmap, local);
+    set_xen_guest_handle(domctl.u.vcpuaffinity.cpumap_hard.bitmap,
+                         cpumap_hard);
     domctl.u.vcpuaffinity.cpumap_hard.nr_bits = cpusize * 8;
+    set_xen_guest_handle(domctl.u.vcpuaffinity.cpumap_soft.bitmap,
+                         cpumap_soft);
+    domctl.u.vcpuaffinity.cpumap_soft.nr_bits = cpusize * 8;
 
     ret = do_domctl(xch, &domctl);
 
-    memcpy(cpumap, local, cpusize);
+ out:
+    xc_hypercall_bounce_post(xch, cpumap_hard);
+    xc_hypercall_bounce_post(xch, cpumap_soft);
 
-    xc_hypercall_buffer_free(xch, local);
-out:
     return ret;
 }
 

67 lines not on this page · raw message

index 900b8d4..ec79645 100644
@@ -4582,7 +4582,8 @@ libxl_vcpuinfo *libxl_list_vcpu(libxl_ctx *ctx, uint32_t domid,
             goto err;
         }
         if (xc_vcpu_getaffinity(ctx->xch, domid, *nr_vcpus_out,
-                                ptr->cpumap.map) == -1) {
+                                ptr->cpumap.map, NULL,
+                                XEN_VCPUAFFINITY_HARD) == -1) {
             LOGE(ERROR, "getting vcpu affinity");
             goto err;
         }

@@ -4606,7 +4607,8 @@ err:
 int libxl_set_vcpuaffinity(libxl_ctx *ctx, uint32_t domid, uint32_t vcpuid,
                            libxl_bitmap *cpumap)
 {
-    if (xc_vcpu_setaffinity(ctx->xch, domid, vcpuid, cpumap->map)) {
+    if (xc_vcpu_setaffinity(ctx->xch, domid, vcpuid, cpumap->map, NULL,
+                            XEN_VCPUAFFINITY_HARD)) {
         LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, "setting vcpu affinity");
         return ERROR_FAIL;
     }

index ff29b47..f0810eb 100644
@@ -438,7 +438,9 @@ CAMLprim value stub_xc_vcpu_setaffinity(value xch, value domid,
 			c_cpumap[i/8] |= 1 << (i&7);
 	}
 	retval = xc_vcpu_setaffinity(_H(xch), _D(domid),
-	                             Int_val(vcpu), c_cpumap);
+				     Int_val(vcpu),
+				     c_cpumap, NULL,
+				     XEN_VCPUAFFINITY_HARD);
 	free(c_cpumap);
 
 	if (retval < 0)

@@ -460,7 +462,9 @@ CAMLprim value stub_xc_vcpu_getaffinity(value xch, value domid,
 		failwith_xc(_H(xch));
 
 	retval = xc_vcpu_getaffinity(_H(xch), _D(domid),
-	                             Int_val(vcpu), c_cpumap);
+				     Int_val(vcpu),
+				     c_cpumap, NULL,
+				     XEN_VCPUAFFINITY_HARD);
 	if (retval < 0) {
 		free(c_cpumap);
 		failwith_xc(_H(xch));

index cb34446..54e8799 100644
@@ -256,7 +256,8 @@ static PyObject *pyxc_vcpu_setaffinity(XcObject *self,
         }
     }
   
-    if ( xc_vcpu_setaffinity(self->xc_handle, dom, vcpu, cpumap) != 0 )
+    if ( xc_vcpu_setaffinity(self->xc_handle, dom, vcpu, cpumap,
+                             NULL, XEN_VCPUAFFINITY_HARD) != 0 )
     {
         free(cpumap);
         return pyxc_error_to_exception(self->xc_handle);

@@ -403,7 +404,8 @@ static PyObject *pyxc_vcpu_getinfo(XcObject *self,
     if(cpumap == NULL)
         return pyxc_error_to_exception(self->xc_handle);
 
-    rc = xc_vcpu_getaffinity(self->xc_handle, dom, vcpu, cpumap);
+    rc = xc_vcpu_getaffinity(self->xc_handle, dom, vcpu, cpumap,
+                             NULL, XEN_VCPUAFFINITY_HARD);
     if ( rc < 0 )
     {
         free(cpumap);

index ec79645..2cb7174 100644
@@ -4577,13 +4577,17 @@ libxl_vcpuinfo *libxl_list_vcpu(libxl_ctx *ctx, uint32_t domid,
         libxl_bitmap_init(&ptr->cpumap);
         if (libxl_cpu_bitmap_alloc(ctx, &ptr->cpumap, 0))
             goto err;
+        libxl_bitmap_init(&ptr->cpumap_soft);
+        if (libxl_cpu_bitmap_alloc(ctx, &ptr->cpumap_soft, 0))
+            goto err;
         if (xc_vcpu_getinfo(ctx->xch, domid, *nr_vcpus_out, &vcpuinfo) == -1) {
             LOGE(ERROR, "getting vcpu info");
             goto err;
         }
+
         if (xc_vcpu_getaffinity(ctx->xch, domid, *nr_vcpus_out,
-                                ptr->cpumap.map, NULL,
-                                XEN_VCPUAFFINITY_HARD) == -1) {
+                                ptr->cpumap.map, ptr->cpumap_soft.map,
+                                XEN_VCPUAFFINITY_SOFT|XEN_VCPUAFFINITY_HARD) == -1) {
             LOGE(ERROR, "getting vcpu affinity");
             goto err;
         }

@@ -4599,34 +4603,105 @@ libxl_vcpuinfo *libxl_list_vcpu(libxl_ctx *ctx, uint32_t domid,
 
 err:
     libxl_bitmap_dispose(&ptr->cpumap);
+    libxl_bitmap_dispose(&ptr->cpumap_soft);
     free(ret);
     GC_FREE;
     return NULL;
 }
 
 int libxl_set_vcpuaffinity(libxl_ctx *ctx, uint32_t domid, uint32_t vcpuid,
-                           libxl_bitmap *cpumap)
+                           const libxl_bitmap *cpumap_hard,
+                           const libxl_bitmap *cpumap_soft)
 {
-    if (xc_vcpu_setaffinity(ctx->xch, domid, vcpuid, cpumap->map, NULL,
-                            XEN_VCPUAFFINITY_HARD)) {
-        LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, "setting vcpu affinity");
-        return ERROR_FAIL;
+    GC_INIT(ctx);
+    libxl_bitmap hard, soft;
+    int rc, flags = 0;
+
+    libxl_bitmap_init(&hard);
+    libxl_bitmap_init(&soft);
+
+    if (!cpumap_hard && !cpumap_soft) {
+        rc = ERROR_INVAL;
+        goto out;
     }
-    return 0;
+
+    /*
+     * Xen wants writable hard and/or soft cpumaps, to put back in them
+     * the effective hard and/or soft affinity that will be used.
+     */
+    if (cpumap_hard) {
+        rc = libxl_cpu_bitmap_alloc(ctx, &hard, 0);
+        if (rc)
+            goto out;
+
+        libxl_bitmap_copy(ctx, &hard, cpumap_hard);
+        flags = XEN_VCPUAFFINITY_HARD;
+    }
+    if (cpumap_soft) {
+        rc = libxl_cpu_bitmap_alloc(ctx, &soft, 0);
+        if (rc)
+            goto out;
+
+        libxl_bitmap_copy(ctx, &soft, cpumap_soft);
+        flags |= XEN_VCPUAFFINITY_SOFT;
+    }
+
+    if (xc_vcpu_setaffinity(ctx->xch, domid, vcpuid,
+                            cpumap_hard ? hard.map : NULL,
+                            cpumap_soft ? soft.map : NULL,
+                            flags)) {
+        LOGE(ERROR, "setting vcpu affinity");
+        rc = ERROR_FAIL;
+        goto out;
+    }
+
+    /*
+     * Let's check the results. Hard affinity will never be empty, but it
+     * is possible that Xen will use something different from what we asked
+     * for various reasons. If that's the case, report it.
+     */
+    if (cpumap_hard &&
+        !libxl_bitmap_equal(cpumap_hard, &hard, 0))
+        LOG(DEBUG, "New hard affinity for vcpu %d has unreachable cpus",
+        vcpuid);
+    /*
+     * Soft affinity can both be different from what asked and empty. Check
+     * for (and report) both.
+     */
+    if (cpumap_soft) {
+        if (!libxl_bitmap_equal(cpumap_soft, &soft, 0))
+            LOG(DEBUG, "New soft affinity for vcpu %d has unreachable cpus",
+                vcpuid);
+        if (libxl_bitmap_is_empty(&soft))
+            LOG(WARN, "all cpus in soft affinity of vcpu %d are unreachable."
+                " Only hard affinity will be considered for scheduling",
+                vcpuid);
+    }
+
+    rc = 0;
+ out:
+    libxl_bitmap_dispose(&hard);
+    libxl_bitmap_dispose(&soft);
+    GC_FREE;
+    return rc;
 }
 
 int libxl_set_vcpuaffinity_all(libxl_ctx *ctx, uint32_t domid,
-                               unsigned int max_vcpus, libxl_bitmap *cpumap)
+                               unsigned int max_vcpus,
+                               const libxl_bitmap *cpumap_hard,
+                               const libxl_bitmap *cpumap_soft)
 {
+    GC_INIT(ctx);
     int i, rc = 0;
 
     for (i = 0; i < max_vcpus; i++) {
-        if (libxl_set_vcpuaffinity(ctx, domid, i, cpumap)) {
-            LIBXL__LOG(ctx, LIBXL__LOG_WARNING,
-                       "failed to set affinity for %d", i);
+        if (libxl_set_vcpuaffinity(ctx, domid, i, cpumap_hard, cpumap_soft)) {
+            LOG(WARN, "failed to set affinity for %d", i);
             rc = ERROR_FAIL;
         }
     }
+
+    GC_FREE;
     return rc;
 }
 

index 80947c3..e549db8 100644
@@ -82,6 +82,15 @@
 #define LIBXL_HAVE_DOMAIN_NODEAFFINITY 1
 
 /*
+ * LIBXL_HAVE_SOFT_AFFINITY indicates that a 'cpumap_soft'
+ * field (of libxl_bitmap type) is present in:
+ *  - libxl_vcpuinfo, containing the soft affinity of a vcpu;
+ *  - libxl_domain_build_info, for setting the soft affinity of
+ *    all vcpus while creating the domain.
+ */
+#define LIBXL_HAVE_SOFT_AFFINITY 1
+
+/*
  * LIBXL_HAVE_BUILDINFO_HVM_VENDOR_DEVICE indicates that the
  * libxl_vendor_device field is present in the hvm sections of
  * libxl_domain_build_info. This field tells libxl which

@@ -1097,9 +1106,22 @@ int libxl_userdata_retrieve(libxl_ctx *ctx, uint32_t domid,
 
 int libxl_get_physinfo(libxl_ctx *ctx, libxl_physinfo *physinfo);
 int libxl_set_vcpuaffinity(libxl_ctx *ctx, uint32_t domid, uint32_t vcpuid,
-                           libxl_bitmap *cpumap);
+                           const libxl_bitmap *cpumap_hard,
+                           const libxl_bitmap *cpumap_soft);
 int libxl_set_vcpuaffinity_all(libxl_ctx *ctx, uint32_t domid,
-                               unsigned int max_vcpus, libxl_bitmap *cpumap);
+                               unsigned int max_vcpus,
+                               const libxl_bitmap *cpumap_hard,
+                               const libxl_bitmap *cpumap_soft);
+
+#if defined (LIBXL_API_VERSION) && LIBXL_API_VERSION < 0x040500
+
+#define libxl_set_vcpuaffinity(ctx, domid, vcpuid, map) \
+    libxl_set_vcpuaffinity((ctx), (domid), (vcpuid), (map), NULL)
+#define libxl_set_vcpuaffinity_all(ctx, domid, max_vcpus, map) \
+    libxl_set_vcpuaffinity_all((ctx), (domid), (max_vcpus), (map), NULL)
+
+#endif
+
 int libxl_domain_set_nodeaffinity(libxl_ctx *ctx, uint32_t domid,
                                   libxl_bitmap *nodemap);
 int libxl_domain_get_nodeaffinity(libxl_ctx *ctx, uint32_t domid,

index d015cf4..49a01a7 100644
@@ -193,6 +193,12 @@ int libxl__domain_build_info_setdefault(libxl__gc *gc,
         libxl_bitmap_set_any(&b_info->cpumap);
     }
 
+    if (!b_info->cpumap_soft.size) {
+        if (libxl_cpu_bitmap_alloc(CTX, &b_info->cpumap_soft, 0))
+            return ERROR_FAIL;
+        libxl_bitmap_set_any(&b_info->cpumap_soft);
+    }
+
     libxl_defbool_setdefault(&b_info->numa_placement, true);
 
     if (!b_info->nodemap.size) {

index 661999c..91af7f8 100644
@@ -261,7 +261,8 @@ int libxl__build_pre(libxl__gc *gc, uint32_t domid,
             return rc;
     }
     libxl_domain_set_nodeaffinity(ctx, domid, &info->nodemap);
-    libxl_set_vcpuaffinity_all(ctx, domid, info->max_vcpus, &info->cpumap);
+    libxl_set_vcpuaffinity_all(ctx, domid, info->max_vcpus, &info->cpumap,
+                               &info->cpumap_soft);
 
     if (xc_domain_setmaxmem(ctx->xch, domid, info->target_memkb +
         LIBXL_MAXMEM_CONSTANT) < 0) {

index e37fb89..014f1f6 100644
@@ -98,6 +98,31 @@ static inline int libxl_bitmap_cpu_valid(libxl_bitmap *bitmap, int bit)
 #define libxl_for_each_set_bit(v, m) for (v = 0; v < (m).size * 8; v++) \
                                              if (libxl_bitmap_test(&(m), v))
 
+/*
+ * Compares two bitmaps bit by bit, up to nr_bits or, if nr_bits is 0, up
+ * to the size of the lagest bitmap. If sizes does not match, bits past the
+ * of a bitmap are considered as being 0, which matches with the semantic and
+ * implementation of libxl_bitmap_test I think().
+ *
+ * So, basically, [0,1,0] and [0,1] are considered equal, while [0,1,1] and
+ * [0,1] are different.
+ */
+static inline int libxl_bitmap_equal(const libxl_bitmap *ba,
+                                     const libxl_bitmap *bb,
+                                     int nr_bits)
+{
+    int i;
+
+    if (nr_bits == 0)
+        nr_bits = ba->size > bb->size ? ba->size * 8 : bb->size * 8;
+
+    for (i = 0; i < nr_bits; i++) {
+        if (libxl_bitmap_test(ba, i) != libxl_bitmap_test(bb, i))
+            return 0;
+    }
+    return 1;
+}
+
 int libxl_cpu_bitmap_alloc(libxl_ctx *ctx, libxl_bitmap *cpumap, int max_cpus);
 int libxl_node_bitmap_alloc(libxl_ctx *ctx, libxl_bitmap *nodemap,
                             int max_nodes);

index 5195914..fa5ab8e 100644
@@ -2269,7 +2269,7 @@ start:
             } else {
                 libxl_bitmap_set_any(&vcpu_cpumap);
             }
-            if (libxl_set_vcpuaffinity(ctx, domid, i, &vcpu_cpumap)) {
+            if (libxl_set_vcpuaffinity(ctx, domid, i, &vcpu_cpumap, NULL)) {
                 fprintf(stderr, "setting affinity failed on vcpu `%d'.\n", i);
                 libxl_bitmap_dispose(&vcpu_cpumap);
                 free(vcpu_to_pcpu);

@@ -4700,7 +4700,7 @@ static int vcpupin(uint32_t domid, const char *vcpu, char *cpu)
     }
 
     if (vcpuid != -1) {
-        if (libxl_set_vcpuaffinity(ctx, domid, vcpuid, &cpumap) == -1) {
+        if (libxl_set_vcpuaffinity(ctx, domid, vcpuid, &cpumap, NULL)) {
             fprintf(stderr, "Could not set affinity for vcpu `%u'.\n", vcpuid);
             goto out;
         }

@@ -4712,7 +4712,7 @@ static int vcpupin(uint32_t domid, const char *vcpu, char *cpu)
         }
         for (i = 0; i < nb_vcpu; i++) {
             if (libxl_set_vcpuaffinity(ctx, domid, vcpuinfo[i].vcpuid,
-                                       &cpumap) == -1) {
+                                       &cpumap, NULL)) {
                 fprintf(stderr, "libxl_set_vcpuaffinity failed"
                                 " on vcpu `%u'.\n", vcpuinfo[i].vcpuid);
             }

159 lines not on this page · raw message

index 4279b9f..7b7fa92 100644
@@ -218,7 +218,7 @@ struct cmd_spec cmd_table[] = {
     { "vcpu-pin",
       &main_vcpupin, 1, 1,
       "Set which CPUs a VCPU can use",
-      "<Domain> <VCPU|all> <CPUs|all>",
+      "<Domain> <VCPU|all> <Hard affinity|-|all> <Soft affinity|-|all>",
     },
     { "vcpu-set",
       &main_vcpuset, 0, 1,

259 lines not on this page · raw message

index 91af7f8..3511756 100644
@@ -248,17 +248,33 @@ int libxl__build_pre(libxl__gc *gc, uint32_t domid,
      * some weird error manifests) the subsequent call to
      * libxl_domain_set_nodeaffinity() will do the actual placement,
      * whatever that turns out to be.
+     *
+     * As far as scheduling is concerned, we achieve NUMA-aware scheduling
+     * by having the results of placement affect the soft affinity of all
+     * the vcpus of the domain. Of course, we want that iff placement is
+     * enabled and actually happens, so we only change info->cpumap_soft to
+     * reflect the placement result if that is the case
      */
     if (libxl_defbool_val(info->numa_placement)) {
-        if (!libxl_bitmap_is_full(&info->cpumap)) {
+        /* We require both hard and soft affinity not to be set */
+        if (!libxl_bitmap_is_full(&info->cpumap) ||
+            !libxl_bitmap_is_full(&info->cpumap_soft)) {
             LOG(ERROR, "Can run NUMA placement only if no vcpu "
-                       "affinity is specified");
+                       "(hard or soft) affinity is specified");
             return ERROR_INVAL;
         }
 
         rc = numa_place_domain(gc, domid, info);
         if (rc)
             return rc;
+
+        /*
+         * We change the soft affinity in domain_build_info here, of course
+         * after converting the result of placement from nodes to cpus. the
+         * following call to libxl_set_vcpuaffinity_all_soft() will do the
+         * actual updating of the domain's vcpus' soft affinity.
+         */
+        libxl_nodemap_to_cpumap(ctx, &info->nodemap, &info->cpumap_soft);
     }
     libxl_domain_set_nodeaffinity(ctx, domid, &info->nodemap);
     libxl_set_vcpuaffinity_all(ctx, domid, info->max_vcpus, &info->cpumap,