diff mbox series

[v2,07/48] xen/sched: move per cpu scheduler private data into struct sched_resource

Message ID 20190809145833.1020-8-jgross@suse.com (mailing list archive)
State Superseded
Headers show
Series xen: add core scheduling support | expand

Commit Message

Jürgen Groß Aug. 9, 2019, 2:57 p.m. UTC
This prepares support of larger scheduling granularities, e.g. core
scheduling.

While at it move sched_has_urgent_vcpu() from include/asm-x86/cpuidle.h
into schedule.c removing the need for including sched-if.h in
cpuidle.h and multiple other C sources.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Dario Faggioli <dfaggioli@suse.com>
---
V1:
- move sched_has_urgent_vcpu()
V2:
- make sched_has_urgent_vcpu() return bool (Jan Beulich)
---
 xen/arch/x86/acpi/cpu_idle.c      |  1 -
 xen/arch/x86/cpu/mcheck/mce.c     |  1 -
 xen/arch/x86/cpu/mcheck/mctelem.c |  1 -
 xen/arch/x86/setup.c              |  1 -
 xen/arch/x86/smpboot.c            |  1 -
 xen/common/sched_arinc653.c       |  4 +--
 xen/common/sched_credit.c         | 10 +++----
 xen/common/sched_credit2.c        | 21 +++++++-------
 xen/common/sched_null.c           |  4 +--
 xen/common/sched_rt.c             |  9 +++---
 xen/common/schedule.c             | 60 ++++++++++++++++++++++-----------------
 xen/include/asm-x86/cpuidle.h     | 11 -------
 xen/include/xen/sched-if.h        | 20 ++++++-------
 xen/include/xen/sched.h           |  1 +
 14 files changed, 68 insertions(+), 77 deletions(-)

Comments

Jan Beulich Sept. 4, 2019, 1:48 p.m. UTC | #1
On 09.08.2019 16:57, Juergen Gross wrote:
> This prepares support of larger scheduling granularities, e.g. core
> scheduling.
> 
> While at it move sched_has_urgent_vcpu() from include/asm-x86/cpuidle.h
> into schedule.c removing the need for including sched-if.h in
> cpuidle.h and multiple other C sources.

Looking again, the #include-s in .c files should have been unnecessary
altogether (and dropping of them could, if it was a separate patch, go
in right away), because of ...

> --- a/xen/include/asm-x86/cpuidle.h
> +++ b/xen/include/asm-x86/cpuidle.h
> @@ -4,7 +4,6 @@
>  #include <xen/cpuidle.h>
>  #include <xen/notifier.h>
>  #include <xen/sched.h>
> -#include <xen/sched-if.h>

... this.

> @@ -27,14 +26,4 @@ void update_idle_stats(struct acpi_processor_power *,
>  void update_last_cx_stat(struct acpi_processor_power *,
>                           struct acpi_processor_cx *, uint64_t);
>  
> -/*
> - * vcpu is urgent if vcpu is polling event channel
> - *
> - * if urgent vcpu exists, CPU should not enter deep C state
> - */
> -static inline int sched_has_urgent_vcpu(void)
> -{
> -    return atomic_read(&this_cpu(schedule_data).urgent_count);
> -}

And then, despite my previous ack, I'm slightly unhappy about this
very short function becoming an out-of-line one, when the only
users of it would preferably have as low latency as possible. I
don't suppose there's a way to keep it inline but still drop the
unwanted #include above?

Jan
Jürgen Groß Sept. 5, 2019, 7:13 a.m. UTC | #2
On 04.09.19 15:48, Jan Beulich wrote:
> On 09.08.2019 16:57, Juergen Gross wrote:
>> This prepares support of larger scheduling granularities, e.g. core
>> scheduling.
>>
>> While at it move sched_has_urgent_vcpu() from include/asm-x86/cpuidle.h
>> into schedule.c removing the need for including sched-if.h in
>> cpuidle.h and multiple other C sources.
> 
> Looking again, the #include-s in .c files should have been unnecessary
> altogether (and dropping of them could, if it was a separate patch, go
> in right away), because of ...

Patch sent.

> 
>> --- a/xen/include/asm-x86/cpuidle.h
>> +++ b/xen/include/asm-x86/cpuidle.h
>> @@ -4,7 +4,6 @@
>>   #include <xen/cpuidle.h>
>>   #include <xen/notifier.h>
>>   #include <xen/sched.h>
>> -#include <xen/sched-if.h>
> 
> ... this.
> 
>> @@ -27,14 +26,4 @@ void update_idle_stats(struct acpi_processor_power *,
>>   void update_last_cx_stat(struct acpi_processor_power *,
>>                            struct acpi_processor_cx *, uint64_t);
>>   
>> -/*
>> - * vcpu is urgent if vcpu is polling event channel
>> - *
>> - * if urgent vcpu exists, CPU should not enter deep C state
>> - */
>> -static inline int sched_has_urgent_vcpu(void)
>> -{
>> -    return atomic_read(&this_cpu(schedule_data).urgent_count);
>> -}
> 
> And then, despite my previous ack, I'm slightly unhappy about this
> very short function becoming an out-of-line one, when the only
> users of it would preferably have as low latency as possible. I
> don't suppose there's a way to keep it inline but still drop the
> unwanted #include above?

The only alternatives I could think of are:

- Passing the "urgent" indicator via parameter to idle (you didn't
   like that)

- Make urgent_count a plain percpu variable


Juergen
Jan Beulich Sept. 5, 2019, 7:38 a.m. UTC | #3
On 05.09.2019 09:13, Juergen Gross wrote:
> On 04.09.19 15:48, Jan Beulich wrote:
>> On 09.08.2019 16:57, Juergen Gross wrote:
>>> This prepares support of larger scheduling granularities, e.g. core
>>> scheduling.
>>>
>>> While at it move sched_has_urgent_vcpu() from include/asm-x86/cpuidle.h
>>> into schedule.c removing the need for including sched-if.h in
>>> cpuidle.h and multiple other C sources.
>>
>> Looking again, the #include-s in .c files should have been unnecessary
>> altogether (and dropping of them could, if it was a separate patch, go
>> in right away), because of ...
> 
> Patch sent.

Thanks. I'll go apply this in a minute.

>>> --- a/xen/include/asm-x86/cpuidle.h
>>> +++ b/xen/include/asm-x86/cpuidle.h
>>> @@ -4,7 +4,6 @@
>>>   #include <xen/cpuidle.h>
>>>   #include <xen/notifier.h>
>>>   #include <xen/sched.h>
>>> -#include <xen/sched-if.h>
>>
>> ... this.
>>
>>> @@ -27,14 +26,4 @@ void update_idle_stats(struct acpi_processor_power *,
>>>   void update_last_cx_stat(struct acpi_processor_power *,
>>>                            struct acpi_processor_cx *, uint64_t);
>>>   
>>> -/*
>>> - * vcpu is urgent if vcpu is polling event channel
>>> - *
>>> - * if urgent vcpu exists, CPU should not enter deep C state
>>> - */
>>> -static inline int sched_has_urgent_vcpu(void)
>>> -{
>>> -    return atomic_read(&this_cpu(schedule_data).urgent_count);
>>> -}
>>
>> And then, despite my previous ack, I'm slightly unhappy about this
>> very short function becoming an out-of-line one, when the only
>> users of it would preferably have as low latency as possible. I
>> don't suppose there's a way to keep it inline but still drop the
>> unwanted #include above?
> 
> The only alternatives I could think of are:
> 
> - Passing the "urgent" indicator via parameter to idle (you didn't
>    like that)
> 
> - Make urgent_count a plain percpu variable

Named sched_urgent_count or some such, this latter option doesn't
look too bad to me; not sure what the scheduler maintainers think
of this, though.

Jan
Dario Faggioli Sept. 9, 2019, 1:03 p.m. UTC | #4
On Thu, 2019-09-05 at 09:38 +0200, Jan Beulich wrote:
> On 05.09.2019 09:13, Juergen Gross wrote:
> > On 04.09.19 15:48, Jan Beulich wrote:
> > > On 09.08.2019 16:57, Juergen Gross wrote:
> > > >   
> > > > -/*
> > > > - * vcpu is urgent if vcpu is polling event channel
> > > > - *
> > > > - * if urgent vcpu exists, CPU should not enter deep C state
> > > > - */
> > > > -static inline int sched_has_urgent_vcpu(void)
> > > > -{
> > > > -    return atomic_read(&this_cpu(schedule_data).urgent_count);
> > > > -}
> > > 
> > > I
> > > don't suppose there's a way to keep it inline but still drop the
> > > unwanted #include above?
> > 
> > The only alternatives I could think of are:
> > 
> > - Passing the "urgent" indicator via parameter to idle (you didn't
> >    like that)
> > 
> > - Make urgent_count a plain percpu variable
> 
> Named sched_urgent_count or some such, this latter option doesn't
> look too bad to me; not sure what the scheduler maintainers think
> of this, though.
> 
This is ok for me as well.

Regards
diff mbox series

Patch

diff --git a/xen/arch/x86/acpi/cpu_idle.c b/xen/arch/x86/acpi/cpu_idle.c
index 8f7b6e9b8c..836f524ef4 100644
--- a/xen/arch/x86/acpi/cpu_idle.c
+++ b/xen/arch/x86/acpi/cpu_idle.c
@@ -38,7 +38,6 @@ 
 #include <xen/guest_access.h>
 #include <xen/keyhandler.h>
 #include <xen/trace.h>
-#include <xen/sched-if.h>
 #include <xen/irq.h>
 #include <asm/cache.h>
 #include <asm/io.h>
diff --git a/xen/arch/x86/cpu/mcheck/mce.c b/xen/arch/x86/cpu/mcheck/mce.c
index 28ad7dd659..4b2b6de191 100644
--- a/xen/arch/x86/cpu/mcheck/mce.c
+++ b/xen/arch/x86/cpu/mcheck/mce.c
@@ -10,7 +10,6 @@ 
 #include <xen/errno.h>
 #include <xen/console.h>
 #include <xen/sched.h>
-#include <xen/sched-if.h>
 #include <xen/cpumask.h>
 #include <xen/event.h>
 #include <xen/guest_access.h>
diff --git a/xen/arch/x86/cpu/mcheck/mctelem.c b/xen/arch/x86/cpu/mcheck/mctelem.c
index 3bb13e5265..012a9b95e5 100644
--- a/xen/arch/x86/cpu/mcheck/mctelem.c
+++ b/xen/arch/x86/cpu/mcheck/mctelem.c
@@ -18,7 +18,6 @@ 
 #include <xen/smp.h>
 #include <xen/errno.h>
 #include <xen/sched.h>
-#include <xen/sched-if.h>
 #include <xen/cpumask.h>
 #include <xen/event.h>
 
diff --git a/xen/arch/x86/setup.c b/xen/arch/x86/setup.c
index d2011910fa..28c35bbac9 100644
--- a/xen/arch/x86/setup.c
+++ b/xen/arch/x86/setup.c
@@ -3,7 +3,6 @@ 
 #include <xen/err.h>
 #include <xen/grant_table.h>
 #include <xen/sched.h>
-#include <xen/sched-if.h>
 #include <xen/domain.h>
 #include <xen/serial.h>
 #include <xen/softirq.h>
diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c
index 8d5fef0012..27b78a0b61 100644
--- a/xen/arch/x86/smpboot.c
+++ b/xen/arch/x86/smpboot.c
@@ -25,7 +25,6 @@ 
 #include <xen/domain.h>
 #include <xen/domain_page.h>
 #include <xen/sched.h>
-#include <xen/sched-if.h>
 #include <xen/irq.h>
 #include <xen/delay.h>
 #include <xen/softirq.h>
diff --git a/xen/common/sched_arinc653.c b/xen/common/sched_arinc653.c
index 34b1f235a2..25fbc42f74 100644
--- a/xen/common/sched_arinc653.c
+++ b/xen/common/sched_arinc653.c
@@ -475,7 +475,7 @@  a653sched_unit_sleep(const struct scheduler *ops, struct sched_unit *unit)
      * If the VCPU being put to sleep is the same one that is currently
      * running, raise a softirq to invoke the scheduler to switch domains.
      */
-    if ( per_cpu(schedule_data, vc->processor).curr == unit )
+    if ( get_sched_res(vc->processor)->curr == unit )
         cpu_raise_softirq(vc->processor, SCHEDULE_SOFTIRQ);
 }
 
@@ -642,7 +642,7 @@  static spinlock_t *
 a653_switch_sched(struct scheduler *new_ops, unsigned int cpu,
                   void *pdata, void *vdata)
 {
-    struct schedule_data *sd = &per_cpu(schedule_data, cpu);
+    struct sched_resource *sd = get_sched_res(cpu);
     arinc653_vcpu_t *svc = vdata;
 
     ASSERT(!pdata && svc && is_idle_vcpu(svc->vc));
diff --git a/xen/common/sched_credit.c b/xen/common/sched_credit.c
index 7c3dbae892..261d2083c7 100644
--- a/xen/common/sched_credit.c
+++ b/xen/common/sched_credit.c
@@ -82,7 +82,7 @@ 
 #define CSCHED_PRIV(_ops)   \
     ((struct csched_private *)((_ops)->sched_data))
 #define CSCHED_PCPU(_c)     \
-    ((struct csched_pcpu *)per_cpu(schedule_data, _c).sched_priv)
+    ((struct csched_pcpu *)get_sched_res(_c)->sched_priv)
 #define CSCHED_UNIT(unit)   ((struct csched_unit *) (unit)->priv)
 #define CSCHED_DOM(_dom)    ((struct csched_dom *) (_dom)->sched_priv)
 #define RUNQ(_cpu)          (&(CSCHED_PCPU(_cpu)->runq))
@@ -250,7 +250,7 @@  static inline bool_t is_runq_idle(unsigned int cpu)
     /*
      * We're peeking at cpu's runq, we must hold the proper lock.
      */
-    ASSERT(spin_is_locked(per_cpu(schedule_data, cpu).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(cpu)->schedule_lock));
 
     return list_empty(RUNQ(cpu)) ||
            is_idle_vcpu(__runq_elem(RUNQ(cpu)->next)->vcpu);
@@ -259,7 +259,7 @@  static inline bool_t is_runq_idle(unsigned int cpu)
 static inline void
 inc_nr_runnable(unsigned int cpu)
 {
-    ASSERT(spin_is_locked(per_cpu(schedule_data, cpu).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(cpu)->schedule_lock));
     CSCHED_PCPU(cpu)->nr_runnable++;
 
 }
@@ -267,7 +267,7 @@  inc_nr_runnable(unsigned int cpu)
 static inline void
 dec_nr_runnable(unsigned int cpu)
 {
-    ASSERT(spin_is_locked(per_cpu(schedule_data, cpu).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(cpu)->schedule_lock));
     ASSERT(CSCHED_PCPU(cpu)->nr_runnable >= 1);
     CSCHED_PCPU(cpu)->nr_runnable--;
 }
@@ -628,7 +628,7 @@  static spinlock_t *
 csched_switch_sched(struct scheduler *new_ops, unsigned int cpu,
                     void *pdata, void *vdata)
 {
-    struct schedule_data *sd = &per_cpu(schedule_data, cpu);
+    struct sched_resource *sd = get_sched_res(cpu);
     struct csched_private *prv = CSCHED_PRIV(new_ops);
     struct csched_unit *svc = vdata;
 
diff --git a/xen/common/sched_credit2.c b/xen/common/sched_credit2.c
index f856293371..02e2855d8d 100644
--- a/xen/common/sched_credit2.c
+++ b/xen/common/sched_credit2.c
@@ -568,7 +568,7 @@  static inline struct csched2_private *csched2_priv(const struct scheduler *ops)
 
 static inline struct csched2_pcpu *csched2_pcpu(unsigned int cpu)
 {
-    return per_cpu(schedule_data, cpu).sched_priv;
+    return get_sched_res(cpu)->sched_priv;
 }
 
 static inline struct csched2_unit *csched2_unit(const struct sched_unit *unit)
@@ -1277,7 +1277,7 @@  runq_insert(const struct scheduler *ops, struct csched2_unit *svc)
     struct list_head * runq = &c2rqd(ops, cpu)->runq;
     int pos = 0;
 
-    ASSERT(spin_is_locked(per_cpu(schedule_data, cpu).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(cpu)->schedule_lock));
 
     ASSERT(!vcpu_on_runq(svc));
     ASSERT(c2r(cpu) == c2r(svc->vcpu->processor));
@@ -1798,7 +1798,7 @@  static bool vcpu_grab_budget(struct csched2_unit *svc)
     struct csched2_dom *sdom = svc->sdom;
     unsigned int cpu = svc->vcpu->processor;
 
-    ASSERT(spin_is_locked(per_cpu(schedule_data, cpu).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(cpu)->schedule_lock));
 
     if ( svc->budget > 0 )
         return true;
@@ -1845,7 +1845,7 @@  vcpu_return_budget(struct csched2_unit *svc, struct list_head *parked)
     struct csched2_dom *sdom = svc->sdom;
     unsigned int cpu = svc->vcpu->processor;
 
-    ASSERT(spin_is_locked(per_cpu(schedule_data, cpu).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(cpu)->schedule_lock));
     ASSERT(list_empty(parked));
 
     /* budget_lock nests inside runqueue lock. */
@@ -2102,7 +2102,7 @@  csched2_unit_wake(const struct scheduler *ops, struct sched_unit *unit)
     unsigned int cpu = vc->processor;
     s_time_t now;
 
-    ASSERT(spin_is_locked(per_cpu(schedule_data, cpu).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(cpu)->schedule_lock));
 
     ASSERT(!is_idle_vcpu(vc));
 
@@ -2230,7 +2230,7 @@  csched2_res_pick(const struct scheduler *ops, struct sched_unit *unit)
      * just grab the prv lock.  Instead, we'll have to trylock, and
      * do something else reasonable if we fail.
      */
-    ASSERT(spin_is_locked(per_cpu(schedule_data, cpu).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(cpu)->schedule_lock));
 
     if ( !read_trylock(&prv->lock) )
     {
@@ -2570,7 +2570,7 @@  static void balance_load(const struct scheduler *ops, int cpu, s_time_t now)
      * on either side may be empty).
      */
 
-    ASSERT(spin_is_locked(per_cpu(schedule_data, cpu).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(cpu)->schedule_lock));
     st.lrqd = c2rqd(ops, cpu);
 
     update_runq_load(ops, st.lrqd, 0, now);
@@ -3476,7 +3476,7 @@  csched2_schedule(
     rqd = c2rqd(ops, cpu);
     BUG_ON(!cpumask_test_cpu(cpu, &rqd->active));
 
-    ASSERT(spin_is_locked(per_cpu(schedule_data, cpu).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(cpu)->schedule_lock));
 
     BUG_ON(!is_idle_vcpu(scurr->vcpu) && scurr->rqd != rqd);
 
@@ -3867,7 +3867,7 @@  csched2_init_pdata(const struct scheduler *ops, void *pdata, int cpu)
 
     rqi = init_pdata(prv, pdata, cpu);
     /* Move the scheduler lock to the new runq lock. */
-    per_cpu(schedule_data, cpu).schedule_lock = &prv->rqd[rqi].lock;
+    get_sched_res(cpu)->schedule_lock = &prv->rqd[rqi].lock;
 
     /* _Not_ pcpu_schedule_unlock(): schedule_lock may have changed! */
     spin_unlock(old_lock);
@@ -3881,6 +3881,7 @@  csched2_switch_sched(struct scheduler *new_ops, unsigned int cpu,
 {
     struct csched2_private *prv = csched2_priv(new_ops);
     struct csched2_unit *svc = vdata;
+    struct sched_resource *sd = get_sched_res(cpu);
     unsigned rqi;
 
     ASSERT(pdata && svc && is_idle_vcpu(svc->vcpu));
@@ -3906,7 +3907,7 @@  csched2_switch_sched(struct scheduler *new_ops, unsigned int cpu,
      * this scheduler, and so it's safe to have taken it /before/ our
      * private global lock.
      */
-    ASSERT(per_cpu(schedule_data, cpu).schedule_lock != &prv->rqd[rqi].lock);
+    ASSERT(sd->schedule_lock != &prv->rqd[rqi].lock);
 
     write_unlock(&prv->lock);
 
diff --git a/xen/common/sched_null.c b/xen/common/sched_null.c
index 4dc0356f80..5f0356c7f8 100644
--- a/xen/common/sched_null.c
+++ b/xen/common/sched_null.c
@@ -269,7 +269,7 @@  pick_res(struct null_private *prv, struct sched_unit *unit)
     unsigned int cpu = v->processor, new_cpu;
     cpumask_t *cpus = cpupool_domain_cpumask(v->domain);
 
-    ASSERT(spin_is_locked(per_cpu(schedule_data, cpu).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(cpu)->schedule_lock));
 
     for_each_affinity_balance_step( bs )
     {
@@ -419,7 +419,7 @@  static spinlock_t *null_switch_sched(struct scheduler *new_ops,
                                      unsigned int cpu,
                                      void *pdata, void *vdata)
 {
-    struct schedule_data *sd = &per_cpu(schedule_data, cpu);
+    struct sched_resource *sd = get_sched_res(cpu);
     struct null_private *prv = null_priv(new_ops);
     struct null_unit *nvc = vdata;
 
diff --git a/xen/common/sched_rt.c b/xen/common/sched_rt.c
index 06f63176ee..3ce85122cc 100644
--- a/xen/common/sched_rt.c
+++ b/xen/common/sched_rt.c
@@ -75,7 +75,7 @@ 
 /*
  * Locking:
  * A global system lock is used to protect the RunQ and DepletedQ.
- * The global lock is referenced by schedule_data.schedule_lock
+ * The global lock is referenced by sched_res->schedule_lock
  * from all physical cpus.
  *
  * The lock is already grabbed when calling wake/sleep/schedule/ functions
@@ -176,7 +176,7 @@  static void repl_timer_handler(void *data);
 
 /*
  * System-wide private data, include global RunQueue/DepletedQ
- * Global lock is referenced by schedule_data.schedule_lock from all
+ * Global lock is referenced by sched_res->schedule_lock from all
  * physical cpus. It can be grabbed via vcpu_schedule_lock_irq()
  */
 struct rt_private {
@@ -722,7 +722,7 @@  rt_init_pdata(const struct scheduler *ops, void *pdata, int cpu)
     }
 
     /* Move the scheduler lock to our global runqueue lock.  */
-    per_cpu(schedule_data, cpu).schedule_lock = &prv->lock;
+    get_sched_res(cpu)->schedule_lock = &prv->lock;
 
     /* _Not_ pcpu_schedule_unlock(): per_cpu().schedule_lock changed! */
     spin_unlock_irqrestore(old_lock, flags);
@@ -735,6 +735,7 @@  rt_switch_sched(struct scheduler *new_ops, unsigned int cpu,
 {
     struct rt_private *prv = rt_priv(new_ops);
     struct rt_unit *svc = vdata;
+    struct sched_resource *sd = get_sched_res(cpu);
 
     ASSERT(!pdata && svc && is_idle_vcpu(svc->vcpu));
 
@@ -744,7 +745,7 @@  rt_switch_sched(struct scheduler *new_ops, unsigned int cpu,
      * another scheduler, but that is how things need to be, for
      * preventing races.
      */
-    ASSERT(per_cpu(schedule_data, cpu).schedule_lock != &prv->lock);
+    ASSERT(sd->schedule_lock != &prv->lock);
 
     /*
      * If we are the absolute first cpu being switched toward this
diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 45394e6c2e..c167eb23f2 100644
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -65,7 +65,6 @@  static void vcpu_singleshot_timer_fn(void *data);
 static void poll_timer_fn(void *data);
 
 /* This is global for now so that private implementations can reach it */
-DEFINE_PER_CPU(struct schedule_data, schedule_data);
 DEFINE_PER_CPU(struct scheduler *, scheduler);
 DEFINE_PER_CPU_READ_MOSTLY(struct sched_resource *, sched_res);
 
@@ -213,7 +212,7 @@  static inline void vcpu_urgent_count_update(struct vcpu *v)
              !test_bit(v->vcpu_id, v->domain->poll_mask) )
         {
             v->is_urgent = 0;
-            atomic_dec(&per_cpu(schedule_data,v->processor).urgent_count);
+            atomic_dec(&get_sched_res(v->processor)->urgent_count);
         }
     }
     else
@@ -222,7 +221,7 @@  static inline void vcpu_urgent_count_update(struct vcpu *v)
              unlikely(test_bit(v->vcpu_id, v->domain->poll_mask)) )
         {
             v->is_urgent = 1;
-            atomic_inc(&per_cpu(schedule_data,v->processor).urgent_count);
+            atomic_inc(&get_sched_res(v->processor)->urgent_count);
         }
     }
 }
@@ -233,7 +232,7 @@  static inline void vcpu_runstate_change(
     s_time_t delta;
 
     ASSERT(v->runstate.state != new_state);
-    ASSERT(spin_is_locked(per_cpu(schedule_data,v->processor).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(v->processor)->schedule_lock));
 
     vcpu_urgent_count_update(v);
 
@@ -392,7 +391,7 @@  int sched_init_vcpu(struct vcpu *v, unsigned int processor)
     /* Idle VCPUs are scheduled immediately, so don't put them in runqueue. */
     if ( is_idle_domain(d) )
     {
-        per_cpu(schedule_data, v->processor).curr = unit;
+        get_sched_res(v->processor)->curr = unit;
         v->is_running = 1;
     }
     else
@@ -517,7 +516,7 @@  void sched_destroy_vcpu(struct vcpu *v)
     kill_timer(&v->singleshot_timer);
     kill_timer(&v->poll_timer);
     if ( test_and_clear_bool(v->is_urgent) )
-        atomic_dec(&per_cpu(schedule_data, v->processor).urgent_count);
+        atomic_dec(&get_sched_res(v->processor)->urgent_count);
     sched_remove_unit(vcpu_scheduler(v), unit);
     sched_free_vdata(vcpu_scheduler(v), unit->priv);
     sched_free_unit(unit);
@@ -564,7 +563,7 @@  void sched_destroy_domain(struct domain *d)
 
 void vcpu_sleep_nosync_locked(struct vcpu *v)
 {
-    ASSERT(spin_is_locked(per_cpu(schedule_data,v->processor).schedule_lock));
+    ASSERT(spin_is_locked(get_sched_res(v->processor)->schedule_lock));
 
     if ( likely(!vcpu_runnable(v)) )
     {
@@ -659,8 +658,8 @@  static void vcpu_move_locked(struct vcpu *v, unsigned int new_cpu)
      */
     if ( unlikely(v->is_urgent) && (old_cpu != new_cpu) )
     {
-        atomic_inc(&per_cpu(schedule_data, new_cpu).urgent_count);
-        atomic_dec(&per_cpu(schedule_data, old_cpu).urgent_count);
+        atomic_inc(&get_sched_res(new_cpu)->urgent_count);
+        atomic_dec(&get_sched_res(old_cpu)->urgent_count);
     }
 
     /*
@@ -726,20 +725,20 @@  static void vcpu_migrate_finish(struct vcpu *v)
          * are not correct any longer after evaluating old and new cpu holding
          * the locks.
          */
-        old_lock = per_cpu(schedule_data, old_cpu).schedule_lock;
-        new_lock = per_cpu(schedule_data, new_cpu).schedule_lock;
+        old_lock = get_sched_res(old_cpu)->schedule_lock;
+        new_lock = get_sched_res(new_cpu)->schedule_lock;
 
         sched_spin_lock_double(old_lock, new_lock, &flags);
 
         old_cpu = v->processor;
-        if ( old_lock == per_cpu(schedule_data, old_cpu).schedule_lock )
+        if ( old_lock == get_sched_res(old_cpu)->schedule_lock )
         {
             /*
              * If we selected a CPU on the previosu iteration, check if it
              * remains suitable for running this vCPU.
              */
             if ( pick_called &&
-                 (new_lock == per_cpu(schedule_data, new_cpu).schedule_lock) &&
+                 (new_lock == get_sched_res(new_cpu)->schedule_lock) &&
                  cpumask_test_cpu(new_cpu, v->cpu_hard_affinity) &&
                  cpumask_test_cpu(new_cpu, v->domain->cpupool->cpu_valid) )
                 break;
@@ -747,7 +746,7 @@  static void vcpu_migrate_finish(struct vcpu *v)
             /* Select a new CPU. */
             new_cpu = sched_pick_resource(vcpu_scheduler(v),
                                           v->sched_unit)->processor;
-            if ( (new_lock == per_cpu(schedule_data, new_cpu).schedule_lock) &&
+            if ( (new_lock == get_sched_res(new_cpu)->schedule_lock) &&
                  cpumask_test_cpu(new_cpu, v->domain->cpupool->cpu_valid) )
                 break;
             pick_called = 1;
@@ -1558,7 +1557,7 @@  static void schedule(void)
     struct scheduler     *sched;
     unsigned long        *tasklet_work = &this_cpu(tasklet_work_to_do);
     bool_t                tasklet_work_scheduled = 0;
-    struct schedule_data *sd;
+    struct sched_resource *sd;
     spinlock_t           *lock;
     struct task_slice     next_slice;
     int cpu = smp_processor_id();
@@ -1567,7 +1566,7 @@  static void schedule(void)
 
     SCHED_STAT_CRANK(sched_run);
 
-    sd = &this_cpu(schedule_data);
+    sd = get_sched_res(cpu);
 
     /* Update tasklet scheduling status. */
     switch ( *tasklet_work )
@@ -1708,14 +1707,13 @@  static void poll_timer_fn(void *data)
 
 static int cpu_schedule_up(unsigned int cpu)
 {
-    struct schedule_data *sd = &per_cpu(schedule_data, cpu);
-    struct sched_resource *res;
+    struct sched_resource *sd;
 
-    res = xzalloc(struct sched_resource);
-    if ( res == NULL )
+    sd = xzalloc(struct sched_resource);
+    if ( sd == NULL )
         return -ENOMEM;
-    res->processor = cpu;
-    set_sched_res(cpu, res);
+    sd->processor = cpu;
+    set_sched_res(cpu, sd);
 
     per_cpu(scheduler, cpu) = &sched_idle_ops;
     spin_lock_init(&sd->_lock);
@@ -1730,7 +1728,7 @@  static int cpu_schedule_up(unsigned int cpu)
     if ( idle_vcpu[cpu] == NULL )
         vcpu_create(idle_vcpu[0]->domain, cpu, cpu);
     else
-        idle_vcpu[cpu]->sched_unit->res = res;
+        idle_vcpu[cpu]->sched_unit->res = sd;
 
     if ( idle_vcpu[cpu] == NULL )
         return -ENOMEM;
@@ -1750,7 +1748,7 @@  static int cpu_schedule_up(unsigned int cpu)
 
 static void cpu_schedule_down(unsigned int cpu)
 {
-    struct schedule_data *sd = &per_cpu(schedule_data, cpu);
+    struct sched_resource *sd = get_sched_res(cpu);
 
     kill_timer(&sd->s_timer);
 
@@ -1909,7 +1907,7 @@  void __init scheduler_init(void)
     idle_domain->max_vcpus = nr_cpu_ids;
     if ( vcpu_create(idle_domain, 0, 0) == NULL )
         BUG();
-    this_cpu(schedule_data).curr = idle_vcpu[0]->sched_unit;
+    get_sched_res(0)->curr = idle_vcpu[0]->sched_unit;
 }
 
 /*
@@ -1926,7 +1924,7 @@  int schedule_cpu_switch(unsigned int cpu, struct cpupool *c)
     struct scheduler *old_ops = per_cpu(scheduler, cpu);
     struct scheduler *new_ops = (c == NULL) ? &sched_idle_ops : c->sched;
     struct cpupool *old_pool = per_cpu(cpupool, cpu);
-    struct schedule_data *sd = &per_cpu(schedule_data, cpu);
+    struct sched_resource *sd = get_sched_res(cpu);
     spinlock_t *old_lock, *new_lock;
     unsigned long flags;
 
@@ -2109,6 +2107,16 @@  void wait(void)
     schedule();
 }
 
+/*
+ * vcpu is urgent if vcpu is polling event channel
+ *
+ * if urgent vcpu exists, CPU should not enter deep C state
+ */
+bool sched_has_urgent_vcpu(void)
+{
+    return atomic_read(&get_sched_res(smp_processor_id())->urgent_count);
+}
+
 #ifdef CONFIG_COMPAT
 #include "compat/schedule.c"
 #endif
diff --git a/xen/include/asm-x86/cpuidle.h b/xen/include/asm-x86/cpuidle.h
index 488f708305..5d7dffd228 100644
--- a/xen/include/asm-x86/cpuidle.h
+++ b/xen/include/asm-x86/cpuidle.h
@@ -4,7 +4,6 @@ 
 #include <xen/cpuidle.h>
 #include <xen/notifier.h>
 #include <xen/sched.h>
-#include <xen/sched-if.h>
 
 extern struct acpi_processor_power *processor_powers[];
 
@@ -27,14 +26,4 @@  void update_idle_stats(struct acpi_processor_power *,
 void update_last_cx_stat(struct acpi_processor_power *,
                          struct acpi_processor_cx *, uint64_t);
 
-/*
- * vcpu is urgent if vcpu is polling event channel
- *
- * if urgent vcpu exists, CPU should not enter deep C state
- */
-static inline int sched_has_urgent_vcpu(void)
-{
-    return atomic_read(&this_cpu(schedule_data).urgent_count);
-}
-
 #endif /* __X86_ASM_CPUIDLE_H__ */
diff --git a/xen/include/xen/sched-if.h b/xen/include/xen/sched-if.h
index 69aedd2210..212c612374 100644
--- a/xen/include/xen/sched-if.h
+++ b/xen/include/xen/sched-if.h
@@ -33,22 +33,18 @@  extern int sched_ratelimit_us;
  * For cache betterness, keep the actual lock in the same cache area
  * as the rest of the struct.  Just have the scheduler point to the
  * one it wants (This may be the one right in front of it).*/
-struct schedule_data {
+struct sched_resource {
     spinlock_t         *schedule_lock,
                        _lock;
     struct sched_unit  *curr;           /* current task                    */
     void               *sched_priv;
     struct timer        s_timer;        /* scheduling timer                */
     atomic_t            urgent_count;   /* how many urgent vcpus           */
+    unsigned int        processor;
 };
 
-#define curr_on_cpu(c)    (per_cpu(schedule_data, c).curr)
-
-struct sched_resource {
-    unsigned int processor;
-};
+#define curr_on_cpu(c)    (get_sched_res(c)->curr)
 
-DECLARE_PER_CPU(struct schedule_data, schedule_data);
 DECLARE_PER_CPU(struct scheduler *, scheduler);
 DECLARE_PER_CPU(struct cpupool *, cpupool);
 DECLARE_PER_CPU(struct sched_resource *, sched_res);
@@ -79,7 +75,7 @@  static inline spinlock_t *kind##_schedule_lock##irq(param EXTRA_TYPE(arg)) \
 { \
     for ( ; ; ) \
     { \
-        spinlock_t *lock = per_cpu(schedule_data, cpu).schedule_lock; \
+        spinlock_t *lock = get_sched_res(cpu)->schedule_lock; \
         /* \
          * v->processor may change when grabbing the lock; but \
          * per_cpu(v->processor) may also change, if changing cpu pool \
@@ -89,7 +85,7 @@  static inline spinlock_t *kind##_schedule_lock##irq(param EXTRA_TYPE(arg)) \
          * lock may be the same; this will succeed in that case. \
          */ \
         spin_lock##irq(lock, ## arg); \
-        if ( likely(lock == per_cpu(schedule_data, cpu).schedule_lock) ) \
+        if ( likely(lock == get_sched_res(cpu)->schedule_lock) ) \
             return lock; \
         spin_unlock##irq(lock, ## arg); \
     } \
@@ -99,7 +95,7 @@  static inline spinlock_t *kind##_schedule_lock##irq(param EXTRA_TYPE(arg)) \
 static inline void kind##_schedule_unlock##irq(spinlock_t *lock \
                                                EXTRA_TYPE(arg), param) \
 { \
-    ASSERT(lock == per_cpu(schedule_data, cpu).schedule_lock); \
+    ASSERT(lock == get_sched_res(cpu)->schedule_lock); \
     spin_unlock##irq(lock, ## arg); \
 }
 
@@ -128,11 +124,11 @@  sched_unlock(vcpu, const struct vcpu *v, v->processor, _irqrestore, flags)
 
 static inline spinlock_t *pcpu_schedule_trylock(unsigned int cpu)
 {
-    spinlock_t *lock = per_cpu(schedule_data, cpu).schedule_lock;
+    spinlock_t *lock = get_sched_res(cpu)->schedule_lock;
 
     if ( !spin_trylock(lock) )
         return NULL;
-    if ( lock == per_cpu(schedule_data, cpu).schedule_lock )
+    if ( lock == get_sched_res(cpu)->schedule_lock )
         return lock;
     spin_unlock(lock);
     return NULL;
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index 2ab1b13c63..575ce9a245 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -903,6 +903,7 @@  void restore_vcpu_affinity(struct domain *d);
 
 void vcpu_runstate_get(struct vcpu *v, struct vcpu_runstate_info *runstate);
 uint64_t get_cpu_idle_time(unsigned int cpu);
+bool sched_has_urgent_vcpu(void);
 
 /*
  * Used by idle loop to decide whether there is work to do: