xen/sched: prepare per-cpupool scheduling granularity

On- and offlining cpus with core scheduling is rather complicated as
the cpus are taken on- or offline one by one, but scheduling wants them
rather to be handled per core.

As the future plan is to be able to select scheduling granularity per
cpupool prepare that by storing the granularity in struct
sched_resource (we need it there for free cpus which are not
associated to any cpupool). Free cpus will always use granularity 1.

Store the selected granularity option (cpu, core or socket) in the
cpupool , as we will need it to select the appropriate cpu mask when
populating the cpupool with cpus.

This will make on- and offlining of cpus much easier and avoids
writing code which would needed to be thrown away later.

Move the granularity related variables to cpupool.c as they are now
used form there only.

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

xen/common/cpupool.c

@@ -34,6 +34,14 @@ static cpumask_t cpupool_locked_cpus;
 
 static DEFINE_SPINLOCK(cpupool_lock);
 
+static enum sched_gran __read_mostly opt_sched_granularity = SCHED_GRAN_cpu;
+static unsigned int __read_mostly sched_granularity = 1;
+
+unsigned int cpupool_get_granularity(const struct cpupool *c)
+{
+    return c ? sched_granularity : 1;
+}
+
 static void free_cpupool_struct(struct cpupool *c)
 {
     if ( c )
@@ -173,6 +181,7 @@ static struct cpupool *cpupool_create(
             return NULL;
         }
     }
+    c->gran = opt_sched_granularity;
 
     *q = c;
 

xen/common/schedule.c

@@ -62,7 +62,6 @@ int sched_ratelimit_us = SCHED_DEFAULT_RATELIMIT_US;
 integer_param("sched_ratelimit_us", sched_ratelimit_us);
 
 /* Number of vcpus per struct sched_unit. */
-static unsigned int __read_mostly sched_granularity = 1;
 bool __read_mostly sched_disable_smt_switching;
 const cpumask_t *sched_res_mask = &cpumask_all;
 
@@ -435,10 +434,10 @@ static struct sched_unit *sched_alloc_unit(struct vcpu *v)
 {
     struct sched_unit *unit, **prev_unit;
     struct domain *d = v->domain;
+    unsigned int gran = cpupool_get_granularity(d->cpupool);
 
     for_each_sched_unit ( d, unit )
-        if ( unit->unit_id / sched_granularity ==
-             v->vcpu_id / sched_granularity )
+        if ( unit->unit_id / gran == v->vcpu_id / gran )
             break;
 
     if ( unit )
@@ -593,6 +592,7 @@ int sched_move_domain(struct domain *d, struct cpupool *c)
     void *unitdata;
     struct scheduler *old_ops;
     void *old_domdata;
+    unsigned int gran = cpupool_get_granularity(c);
 
     for_each_vcpu ( d, v )
     {
@@ -604,8 +604,7 @@ int sched_move_domain(struct domain *d, struct cpupool *c)
     if ( IS_ERR(domdata) )
         return PTR_ERR(domdata);
 
-    unit_priv = xzalloc_array(void *,
-                              DIV_ROUND_UP(d->max_vcpus, sched_granularity));
+    unit_priv = xzalloc_array(void *, DIV_ROUND_UP(d->max_vcpus, gran));
     if ( unit_priv == NULL )
     {
         sched_free_domdata(c->sched, domdata);
@@ -1850,11 +1849,11 @@ static void sched_switch_units(struct sched_resource *sr,
         if ( is_idle_unit(prev) )
         {
             prev->runstate_cnt[RUNSTATE_running] = 0;
-            prev->runstate_cnt[RUNSTATE_runnable] = sched_granularity;
+            prev->runstate_cnt[RUNSTATE_runnable] = sr->granularity;
         }
         if ( is_idle_unit(next) )
         {
-            next->runstate_cnt[RUNSTATE_running] = sched_granularity;
+            next->runstate_cnt[RUNSTATE_running] = sr->granularity;
             next->runstate_cnt[RUNSTATE_runnable] = 0;
         }
     }
@@ -2003,7 +2002,7 @@ void sched_context_switched(struct vcpu *vprev, struct vcpu *vnext)
     else
     {
         vcpu_context_saved(vprev, vnext);
-        if ( sched_granularity == 1 )
+        if ( sr->granularity == 1 )
             unit_context_saved(sr);
     }
 
@@ -2123,11 +2122,12 @@ static struct sched_unit *sched_wait_rendezvous_in(struct sched_unit *prev,
 {
     struct sched_unit *next;
     struct vcpu *v;
+    unsigned int gran = get_sched_res(cpu)->granularity;
 
     if ( !--prev->rendezvous_in_cnt )
     {
         next = do_schedule(prev, now, cpu);
-        atomic_set(&next->rendezvous_out_cnt, sched_granularity + 1);
+        atomic_set(&next->rendezvous_out_cnt, gran + 1);
         return next;
     }
 
@@ -2255,6 +2255,7 @@ static void schedule(void)
     struct sched_resource *sr;
     spinlock_t           *lock;
     int cpu = smp_processor_id();
+    unsigned int          gran = get_sched_res(cpu)->granularity;
 
     ASSERT_NOT_IN_ATOMIC();
 
@@ -2280,11 +2281,11 @@ static void schedule(void)
 
     now = NOW();
 
-    if ( sched_granularity > 1 )
+    if ( gran > 1 )
     {
         cpumask_t mask;
 
-        prev->rendezvous_in_cnt = sched_granularity;
+        prev->rendezvous_in_cnt = gran;
         cpumask_andnot(&mask, sr->cpus, cpumask_of(cpu));
         cpumask_raise_softirq(&mask, SCHED_SLAVE_SOFTIRQ);
         next = sched_wait_rendezvous_in(prev, &lock, cpu, now);
@@ -2352,6 +2353,9 @@ static int cpu_schedule_up(unsigned int cpu)
     init_timer(&sr->s_timer, s_timer_fn, NULL, cpu);
     atomic_set(&per_cpu(sched_urgent_count, cpu), 0);
 
+    /* We start with cpu granularity. */
+    sr->granularity = 1;
+
     /* Boot CPU is dealt with later in scheduler_init(). */
     if ( cpu == 0 )
         return 0;
@@ -2642,6 +2646,7 @@ int schedule_cpu_switch(unsigned int cpu, struct cpupool *c)
     sched_free_udata(old_ops, vpriv_old);
     sched_free_pdata(old_ops, ppriv_old, cpu);
 
+    get_sched_res(cpu)->granularity = cpupool_get_granularity(c);
     get_sched_res(cpu)->cpupool = c;
     /* When a cpu is added to a pool, trigger it to go pick up some work */
     if ( c != NULL )

xen/include/xen/sched-if.h

@@ -25,6 +25,13 @@ extern int sched_ratelimit_us;
 /* Scheduling resource mask. */
 extern const cpumask_t *sched_res_mask;
 
+/* Number of vcpus per struct sched_unit. */
+enum sched_gran {
+    SCHED_GRAN_cpu,
+    SCHED_GRAN_core,
+    SCHED_GRAN_socket
+};
+
 /*
  * In order to allow a scheduler to remap the lock->cpu mapping,
  * we have a per-cpu pointer, along with a pre-allocated set of
@@ -48,6 +55,7 @@ struct sched_resource {
 
     /* Cpu with lowest id in scheduling resource. */
     unsigned int        master_cpu;
+    unsigned int        granularity;
     const cpumask_t    *cpus;           /* cpus covered by this struct     */
 };
 
@@ -546,6 +554,7 @@ struct cpupool
     struct cpupool   *next;
     struct scheduler *sched;
     atomic_t         refcnt;
+    enum sched_gran  gran;
 };
 
 #define cpupool_online_cpumask(_pool) \
@@ -561,6 +570,8 @@ static inline cpumask_t *cpupool_domain_master_cpumask(const struct domain *d)
     return d->cpupool->res_valid;
 }
 
+unsigned int cpupool_get_granularity(const struct cpupool *c);
+
 /*
  * Hard and soft affinity load balancing.
  *