[Xen-devel] [PATCH v3 21/47] xen/sched: use sched_resource cpu instead smp_processor_id in schedulers

[Juergen Gross <jgross@suse.com>]

Especially in the do_schedule() functions of the different schedulers
using smp_processor_id() for the local cpu number is correct only if
the sched_unit is a single vcpu. As soon as larger sched_units are
used most uses should be replaced by the master_cpu number of the local
sched_resource instead.

Add a helper to get that sched_resource master_cpu and modify the
schedulers to use it in a correct way.

Signed-off-by: Juergen Gross <jgross@suse.com>
---
V3:
- style correction (Jan Beulich)
- rename cpu to cur_cpu when introducing sched_cpu in same function
  (Jan Beulich)
- undo change in sched_idle_schedule() (Jan Beulich)
---
 xen/common/sched_arinc653.c |  2 +-
 xen/common/sched_credit.c   | 23 ++++++++++---------
 xen/common/sched_credit2.c  | 55 +++++++++++++++++++++++----------------------
 xen/common/sched_null.c     | 25 +++++++++++----------
 xen/common/sched_rt.c       | 19 ++++++++--------
 xen/include/xen/sched-if.h  |  5 +++++
 6 files changed, 69 insertions(+), 60 deletions(-)

diff --git a/xen/common/sched_arinc653.c b/xen/common/sched_arinc653.c
index 8c431e6edd..a4db34843b 100644
--- a/xen/common/sched_arinc653.c
+++ b/xen/common/sched_arinc653.c
@@ -513,7 +513,7 @@ a653sched_do_schedule(
     static unsigned int sched_index = 0;
     static s_time_t next_switch_time;
     a653sched_priv_t *sched_priv = SCHED_PRIV(ops);
-    const unsigned int cpu = smp_processor_id();
+    const unsigned int cpu = sched_get_resource_cpu(smp_processor_id());
     unsigned long flags;
 
     spin_lock_irqsave(&sched_priv->lock, flags);
diff --git a/xen/common/sched_credit.c b/xen/common/sched_credit.c
index dcaa9f9557..203c5decef 100644
--- a/xen/common/sched_credit.c
+++ b/xen/common/sched_credit.c
@@ -1684,7 +1684,7 @@ csched_load_balance(struct csched_private *prv, int cpu,
     int peer_cpu, first_cpu, peer_node, bstep;
     int node = cpu_to_node(cpu);
 
-    BUG_ON( cpu != sched_unit_cpu(snext->unit) );
+    BUG_ON(sched_get_resource_cpu(cpu) != sched_unit_cpu(snext->unit));
     online = cpupool_online_cpumask(c);
 
     /*
@@ -1825,8 +1825,9 @@ static struct task_slice
 csched_schedule(
     const struct scheduler *ops, s_time_t now, bool_t tasklet_work_scheduled)
 {
-    const int cpu = smp_processor_id();
-    struct list_head * const runq = RUNQ(cpu);
+    const unsigned int cur_cpu = smp_processor_id();
+    const unsigned int sched_cpu = sched_get_resource_cpu(cur_cpu);
+    struct list_head * const runq = RUNQ(sched_cpu);
     struct sched_unit *unit = current->sched_unit;
     struct csched_unit * const scurr = CSCHED_UNIT(unit);
     struct csched_private *prv = CSCHED_PRIV(ops);
@@ -1847,7 +1848,7 @@ csched_schedule(
         struct {
             unsigned cpu:16, tasklet:8, idle:8;
         } d;
-        d.cpu = cpu;
+        d.cpu = cur_cpu;
         d.tasklet = tasklet_work_scheduled;
         d.idle = is_idle_unit(unit);
         __trace_var(TRC_CSCHED_SCHEDULE, 1, sizeof(d),
@@ -1937,7 +1938,7 @@ csched_schedule(
     {
         BUG_ON( is_idle_unit(unit) || list_empty(runq) );
         /* Current has blocked. Update the runnable counter for this cpu. */
-        dec_nr_runnable(cpu);
+        dec_nr_runnable(sched_cpu);
     }
 
     snext = __runq_elem(runq->next);
@@ -1947,7 +1948,7 @@ csched_schedule(
     if ( tasklet_work_scheduled )
     {
         TRACE_0D(TRC_CSCHED_SCHED_TASKLET);
-        snext = CSCHED_UNIT(sched_idle_unit(cpu));
+        snext = CSCHED_UNIT(sched_idle_unit(sched_cpu));
         snext->pri = CSCHED_PRI_TS_BOOST;
     }
 
@@ -1967,7 +1968,7 @@ csched_schedule(
     if ( snext->pri > CSCHED_PRI_TS_OVER )
         __runq_remove(snext);
     else
-        snext = csched_load_balance(prv, cpu, snext, &ret.migrated);
+        snext = csched_load_balance(prv, sched_cpu, snext, &ret.migrated);
 
     /*
      * Update idlers mask if necessary. When we're idling, other CPUs
@@ -1975,12 +1976,12 @@ csched_schedule(
      */
     if ( !tasklet_work_scheduled && snext->pri == CSCHED_PRI_IDLE )
     {
-        if ( !cpumask_test_cpu(cpu, prv->idlers) )
-            cpumask_set_cpu(cpu, prv->idlers);
+        if ( !cpumask_test_cpu(sched_cpu, prv->idlers) )
+            cpumask_set_cpu(sched_cpu, prv->idlers);
     }
-    else if ( cpumask_test_cpu(cpu, prv->idlers) )
+    else if ( cpumask_test_cpu(sched_cpu, prv->idlers) )
     {
-        cpumask_clear_cpu(cpu, prv->idlers);
+        cpumask_clear_cpu(sched_cpu, prv->idlers);
     }
 
     if ( !is_idle_unit(snext->unit) )
diff --git a/xen/common/sched_credit2.c b/xen/common/sched_credit2.c
index 0d1ba97dbc..cf0559e964 100644
--- a/xen/common/sched_credit2.c
+++ b/xen/common/sched_credit2.c
@@ -3448,7 +3448,8 @@ static struct task_slice
 csched2_schedule(
     const struct scheduler *ops, s_time_t now, bool tasklet_work_scheduled)
 {
-    const int cpu = smp_processor_id();
+    const unsigned int cur_cpu = smp_processor_id();
+    const unsigned int sched_cpu = sched_get_resource_cpu(cur_cpu);
     struct csched2_runqueue_data *rqd;
     struct sched_unit *currunit = current->sched_unit;
     struct csched2_unit * const scurr = csched2_unit(currunit);
@@ -3460,22 +3461,22 @@ csched2_schedule(
     SCHED_STAT_CRANK(schedule);
     CSCHED2_UNIT_CHECK(currunit);
 
-    BUG_ON(!cpumask_test_cpu(cpu, &csched2_priv(ops)->initialized));
+    BUG_ON(!cpumask_test_cpu(sched_cpu, &csched2_priv(ops)->initialized));
 
-    rqd = c2rqd(ops, cpu);
-    BUG_ON(!cpumask_test_cpu(cpu, &rqd->active));
+    rqd = c2rqd(ops, sched_cpu);
+    BUG_ON(!cpumask_test_cpu(sched_cpu, &rqd->active));
 
-    ASSERT(spin_is_locked(get_sched_res(cpu)->schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(sched_cpu)->schedule_lock));
 
     BUG_ON(!is_idle_unit(currunit) && scurr->rqd != rqd);
 
     /* Clear "tickled" bit now that we've been scheduled */
-    tickled = cpumask_test_cpu(cpu, &rqd->tickled);
+    tickled = cpumask_test_cpu(sched_cpu, &rqd->tickled);
     if ( tickled )
     {
-        __cpumask_clear_cpu(cpu, &rqd->tickled);
+        __cpumask_clear_cpu(sched_cpu, &rqd->tickled);
         cpumask_andnot(cpumask_scratch, &rqd->idle, &rqd->tickled);
-        smt_idle_mask_set(cpu, cpumask_scratch, &rqd->smt_idle);
+        smt_idle_mask_set(sched_cpu, cpumask_scratch, &rqd->smt_idle);
     }
 
     if ( unlikely(tb_init_done) )
@@ -3484,11 +3485,11 @@ csched2_schedule(
             unsigned cpu:16, rq_id:16;
             unsigned tasklet:8, idle:8, smt_idle:8, tickled:8;
         } d;
-        d.cpu = cpu;
-        d.rq_id = c2r(cpu);
+        d.cpu = cur_cpu;
+        d.rq_id = c2r(sched_cpu);
         d.tasklet = tasklet_work_scheduled;
         d.idle = is_idle_unit(currunit);
-        d.smt_idle = cpumask_test_cpu(cpu, &rqd->smt_idle);
+        d.smt_idle = cpumask_test_cpu(sched_cpu, &rqd->smt_idle);
         d.tickled = tickled;
         __trace_var(TRC_CSCHED2_SCHEDULE, 1,
                     sizeof(d),
@@ -3528,10 +3529,10 @@ csched2_schedule(
     {
         __clear_bit(__CSFLAG_unit_yield, &scurr->flags);
         trace_var(TRC_CSCHED2_SCHED_TASKLET, 1, 0, NULL);
-        snext = csched2_unit(sched_idle_unit(cpu));
+        snext = csched2_unit(sched_idle_unit(sched_cpu));
     }
     else
-        snext = runq_candidate(rqd, scurr, cpu, now, &skipped_units);
+        snext = runq_candidate(rqd, scurr, sched_cpu, now, &skipped_units);
 
     /* If switching from a non-idle runnable unit, put it
      * back on the runqueue. */
@@ -3556,10 +3557,10 @@ csched2_schedule(
         }
 
         /* Clear the idle mask if necessary */
-        if ( cpumask_test_cpu(cpu, &rqd->idle) )
+        if ( cpumask_test_cpu(sched_cpu, &rqd->idle) )
         {
-            __cpumask_clear_cpu(cpu, &rqd->idle);
-            smt_idle_mask_clear(cpu, &rqd->smt_idle);
+            __cpumask_clear_cpu(sched_cpu, &rqd->idle);
+            smt_idle_mask_clear(sched_cpu, &rqd->smt_idle);
         }
 
         /*
@@ -3578,18 +3579,18 @@ csched2_schedule(
          */
         if ( skipped_units == 0 && snext->credit <= CSCHED2_CREDIT_RESET )
         {
-            reset_credit(ops, cpu, now, snext);
-            balance_load(ops, cpu, now);
+            reset_credit(ops, sched_cpu, now, snext);
+            balance_load(ops, sched_cpu, now);
         }
 
         snext->start_time = now;
         snext->tickled_cpu = -1;
 
         /* Safe because lock for old processor is held */
-        if ( sched_unit_cpu(snext->unit) != cpu )
+        if ( sched_unit_cpu(snext->unit) != sched_cpu )
         {
             snext->credit += CSCHED2_MIGRATE_COMPENSATION;
-            sched_set_res(snext->unit, get_sched_res(cpu));
+            sched_set_res(snext->unit, get_sched_res(sched_cpu));
             SCHED_STAT_CRANK(migrated);
             ret.migrated = 1;
         }
@@ -3602,17 +3603,17 @@ csched2_schedule(
          */
         if ( tasklet_work_scheduled )
         {
-            if ( cpumask_test_cpu(cpu, &rqd->idle) )
+            if ( cpumask_test_cpu(sched_cpu, &rqd->idle) )
             {
-                __cpumask_clear_cpu(cpu, &rqd->idle);
-                smt_idle_mask_clear(cpu, &rqd->smt_idle);
+                __cpumask_clear_cpu(sched_cpu, &rqd->idle);
+                smt_idle_mask_clear(sched_cpu, &rqd->smt_idle);
             }
         }
-        else if ( !cpumask_test_cpu(cpu, &rqd->idle) )
+        else if ( !cpumask_test_cpu(sched_cpu, &rqd->idle) )
         {
-            __cpumask_set_cpu(cpu, &rqd->idle);
+            __cpumask_set_cpu(sched_cpu, &rqd->idle);
             cpumask_andnot(cpumask_scratch, &rqd->idle, &rqd->tickled);
-            smt_idle_mask_set(cpu, cpumask_scratch, &rqd->smt_idle);
+            smt_idle_mask_set(sched_cpu, cpumask_scratch, &rqd->smt_idle);
         }
         /* Make sure avgload gets updated periodically even
          * if there's no activity */
@@ -3622,7 +3623,7 @@ csched2_schedule(
     /*
      * Return task to run next...
      */
-    ret.time = csched2_runtime(ops, cpu, snext, now);
+    ret.time = csched2_runtime(ops, sched_cpu, snext, now);
     ret.task = snext->unit;
 
     CSCHED2_UNIT_CHECK(ret.task);
diff --git a/xen/common/sched_null.c b/xen/common/sched_null.c
index c3666c9f56..4131df0db3 100644
--- a/xen/common/sched_null.c
+++ b/xen/common/sched_null.c
@@ -784,7 +784,8 @@ static struct task_slice null_schedule(const struct scheduler *ops,
                                        bool_t tasklet_work_scheduled)
 {
     unsigned int bs;
-    const unsigned int cpu = smp_processor_id();
+    const unsigned int cur_cpu = smp_processor_id();
+    const unsigned int sched_cpu = sched_get_resource_cpu(cur_cpu);
     struct null_private *prv = null_priv(ops);
     struct null_unit *wvc;
     struct task_slice ret;
@@ -798,16 +799,16 @@ static struct task_slice null_schedule(const struct scheduler *ops,
             uint16_t tasklet, cpu;
             int16_t unit, dom;
         } d;
-        d.cpu = cpu;
+        d.cpu = cur_cpu;
         d.tasklet = tasklet_work_scheduled;
-        if ( per_cpu(npc, cpu).unit == NULL )
+        if ( per_cpu(npc, sched_cpu).unit == NULL )
         {
             d.unit = d.dom = -1;
         }
         else
         {
-            d.unit = per_cpu(npc, cpu).unit->unit_id;
-            d.dom = per_cpu(npc, cpu).unit->domain->domain_id;
+            d.unit = per_cpu(npc, sched_cpu).unit->unit_id;
+            d.dom = per_cpu(npc, sched_cpu).unit->domain->domain_id;
         }
         __trace_var(TRC_SNULL_SCHEDULE, 1, sizeof(d), &d);
     }
@@ -815,10 +816,10 @@ static struct task_slice null_schedule(const struct scheduler *ops,
     if ( tasklet_work_scheduled )
     {
         trace_var(TRC_SNULL_TASKLET, 1, 0, NULL);
-        ret.task = sched_idle_unit(cpu);
+        ret.task = sched_idle_unit(sched_cpu);
     }
     else
-        ret.task = per_cpu(npc, cpu).unit;
+        ret.task = per_cpu(npc, sched_cpu).unit;
     ret.migrated = 0;
     ret.time = -1;
 
@@ -849,9 +850,9 @@ static struct task_slice null_schedule(const struct scheduler *ops,
                      !has_soft_affinity(wvc->unit) )
                     continue;
 
-                if ( unit_check_affinity(wvc->unit, cpu, bs) )
+                if ( unit_check_affinity(wvc->unit, sched_cpu, bs) )
                 {
-                    unit_assign(prv, wvc->unit, cpu);
+                    unit_assign(prv, wvc->unit, sched_cpu);
                     list_del_init(&wvc->waitq_elem);
                     ret.task = wvc->unit;
                     goto unlock;
@@ -861,12 +862,12 @@ static struct task_slice null_schedule(const struct scheduler *ops,
  unlock:
         spin_unlock(&prv->waitq_lock);
 
-        if ( ret.task == NULL && !cpumask_test_cpu(cpu, &prv->cpus_free) )
-            cpumask_set_cpu(cpu, &prv->cpus_free);
+        if ( ret.task == NULL && !cpumask_test_cpu(sched_cpu, &prv->cpus_free) )
+            cpumask_set_cpu(sched_cpu, &prv->cpus_free);
     }
 
     if ( unlikely(ret.task == NULL || !unit_runnable(ret.task)) )
-        ret.task = sched_idle_unit(cpu);
+        ret.task = sched_idle_unit(sched_cpu);
 
     NULL_UNIT_CHECK(ret.task);
     return ret;
diff --git a/xen/common/sched_rt.c b/xen/common/sched_rt.c
index 7a72cfb86c..ab48d4bb1d 100644
--- a/xen/common/sched_rt.c
+++ b/xen/common/sched_rt.c
@@ -1057,7 +1057,8 @@ runq_pick(const struct scheduler *ops, const cpumask_t *mask)
 static struct task_slice
 rt_schedule(const struct scheduler *ops, s_time_t now, bool_t tasklet_work_scheduled)
 {
-    const int cpu = smp_processor_id();
+    const unsigned int cur_cpu = smp_processor_id();
+    const unsigned int sched_cpu = sched_get_resource_cpu(cur_cpu);
     struct rt_private *prv = rt_priv(ops);
     struct rt_unit *const scurr = rt_unit(current->sched_unit);
     struct rt_unit *snext = NULL;
@@ -1069,9 +1070,9 @@ rt_schedule(const struct scheduler *ops, s_time_t now, bool_t tasklet_work_sched
         struct __packed {
             unsigned cpu:16, tasklet:8, tickled:4, idle:4;
         } d;
-        d.cpu = cpu;
+        d.cpu = cur_cpu;
         d.tasklet = tasklet_work_scheduled;
-        d.tickled = cpumask_test_cpu(cpu, &prv->tickled);
+        d.tickled = cpumask_test_cpu(sched_cpu, &prv->tickled);
         d.idle = is_idle_unit(currunit);
         trace_var(TRC_RTDS_SCHEDULE, 1,
                   sizeof(d),
@@ -1079,7 +1080,7 @@ rt_schedule(const struct scheduler *ops, s_time_t now, bool_t tasklet_work_sched
     }
 
     /* clear ticked bit now that we've been scheduled */
-    cpumask_clear_cpu(cpu, &prv->tickled);
+    cpumask_clear_cpu(sched_cpu, &prv->tickled);
 
     /* burn_budget would return for IDLE UNIT */
     burn_budget(ops, scurr, now);
@@ -1087,13 +1088,13 @@ rt_schedule(const struct scheduler *ops, s_time_t now, bool_t tasklet_work_sched
     if ( tasklet_work_scheduled )
     {
         trace_var(TRC_RTDS_SCHED_TASKLET, 1, 0,  NULL);
-        snext = rt_unit(sched_idle_unit(cpu));
+        snext = rt_unit(sched_idle_unit(sched_cpu));
     }
     else
     {
-        snext = runq_pick(ops, cpumask_of(cpu));
+        snext = runq_pick(ops, cpumask_of(sched_cpu));
         if ( snext == NULL )
-            snext = rt_unit(sched_idle_unit(cpu));
+            snext = rt_unit(sched_idle_unit(sched_cpu));
 
         /* if scurr has higher priority and budget, still pick scurr */
         if ( !is_idle_unit(currunit) &&
@@ -1118,9 +1119,9 @@ rt_schedule(const struct scheduler *ops, s_time_t now, bool_t tasklet_work_sched
             q_remove(snext);
             __set_bit(__RTDS_scheduled, &snext->flags);
         }
-        if ( sched_unit_cpu(snext->unit) != cpu )
+        if ( sched_unit_cpu(snext->unit) != sched_cpu )
         {
-            sched_set_res(snext->unit, get_sched_res(cpu));
+            sched_set_res(snext->unit, get_sched_res(sched_cpu));
             ret.migrated = 1;
         }
         ret.time = snext->cur_budget; /* invoke the scheduler next time */
diff --git a/xen/include/xen/sched-if.h b/xen/include/xen/sched-if.h
index f70182dd4e..8429e9e287 100644
--- a/xen/include/xen/sched-if.h
+++ b/xen/include/xen/sched-if.h
@@ -116,6 +116,11 @@ static inline struct sched_unit *sched_idle_unit(unsigned int cpu)
     return idle_vcpu[cpu]->sched_unit;
 }
 
+static inline unsigned int sched_get_resource_cpu(unsigned int cpu)
+{
+    return get_sched_res(cpu)->master_cpu;
+}
+
 /*
  * Scratch space, for avoiding having too many cpumask_t on the stack.
  * Within each scheduler, when using the scratch mask of one pCPU:
-- 
2.16.4


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel