The core idle loop now takes care of it.
Signed-off-by: Nicolas Pitre <[email protected]>
---
arch/powerpc/platforms/powernv/setup.c | 13 +------------
1 file changed, 1 insertion(+), 12 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 21166f65c9..a932feb290 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -26,7 +26,6 @@
#include <linux/of_fdt.h>
#include <linux/interrupt.h>
#include <linux/bug.h>
-#include <linux/cpuidle.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
@@ -217,16 +216,6 @@ static int __init pnv_probe(void)
return 1;
}
-void powernv_idle(void)
-{
- /* Hook to cpuidle framework if available, else
- * call on default platform idle code
- */
- if (cpuidle_idle_call()) {
- power7_idle();
- }
-}
-
define_machine(powernv) {
.name = "PowerNV",
.probe = pnv_probe,
@@ -236,7 +225,7 @@ define_machine(powernv) {
.show_cpuinfo = pnv_show_cpuinfo,
.progress = pnv_progress,
.machine_shutdown = pnv_shutdown,
- .power_save = powernv_idle,
+ .power_save = power7_idle,
.calibrate_decr = generic_calibrate_decr,
#ifdef CONFIG_KEXEC
.kexec_cpu_down = pnv_kexec_cpu_down,
--
1.8.4.108.g55ea5f6
The core idle loop now takes care of it.
Signed-off-by: Nicolas Pitre <[email protected]>
---
arch/arm64/kernel/process.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 1c0a9be2ff..9cce0098f4 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -33,7 +33,6 @@
#include <linux/kallsyms.h>
#include <linux/init.h>
#include <linux/cpu.h>
-#include <linux/cpuidle.h>
#include <linux/elfcore.h>
#include <linux/pm.h>
#include <linux/tick.h>
@@ -94,10 +93,8 @@ void arch_cpu_idle(void)
* This should do all the clock switching and wait for interrupt
* tricks
*/
- if (cpuidle_idle_call()) {
- cpu_do_idle();
- local_irq_enable();
- }
+ cpu_do_idle();
+ local_irq_enable();
}
#ifdef CONFIG_HOTPLUG_CPU
--
1.8.4.108.g55ea5f6
An Thu, 6 Feb 2014, Nicolas Pitre wrote:
> The core idle loop now takes care of it.
>
> Signed-off-by: Nicolas Pitre <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
On Thu, 6 Feb 2014, Nicolas Pitre wrote:
> The core idle loop now takes care of it.
>
> Signed-off-by: Nicolas Pitre <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
On 02/06/2014 07:46 PM, Nicolas Pitre wrote:
> The core idle loop now takes care of it.
>
> Signed-off-by: Nicolas Pitre <[email protected]>
> ---
> arch/powerpc/platforms/powernv/setup.c | 13 +------------
> 1 file changed, 1 insertion(+), 12 deletions(-)
>
> diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
> index 21166f65c9..a932feb290 100644
> --- a/arch/powerpc/platforms/powernv/setup.c
> +++ b/arch/powerpc/platforms/powernv/setup.c
> @@ -26,7 +26,6 @@
> #include <linux/of_fdt.h>
> #include <linux/interrupt.h>
> #include <linux/bug.h>
> -#include <linux/cpuidle.h>
>
> #include <asm/machdep.h>
> #include <asm/firmware.h>
> @@ -217,16 +216,6 @@ static int __init pnv_probe(void)
> return 1;
> }
>
> -void powernv_idle(void)
> -{
> - /* Hook to cpuidle framework if available, else
> - * call on default platform idle code
> - */
> - if (cpuidle_idle_call()) {
> - power7_idle();
> - }
> -}
> -
> define_machine(powernv) {
> .name = "PowerNV",
> .probe = pnv_probe,
> @@ -236,7 +225,7 @@ define_machine(powernv) {
> .show_cpuinfo = pnv_show_cpuinfo,
> .progress = pnv_progress,
> .machine_shutdown = pnv_shutdown,
> - .power_save = powernv_idle,
> + .power_save = power7_idle,
> .calibrate_decr = generic_calibrate_decr,
> #ifdef CONFIG_KEXEC
> .kexec_cpu_down = pnv_kexec_cpu_down,
>
Reviewed-by: Preeti U Murthy <[email protected]>
Hi Nicolas,
powernv in the subject of the patch?
Regards
Preeti U Murthy
On 02/06/2014 07:46 PM, Nicolas Pitre wrote:
> The core idle loop now takes care of it.
>
> Signed-off-by: Nicolas Pitre <[email protected]>
> ---
> arch/arm64/kernel/process.c | 7 ++-----
> 1 file changed, 2 insertions(+), 5 deletions(-)
>
> diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> index 1c0a9be2ff..9cce0098f4 100644
> --- a/arch/arm64/kernel/process.c
> +++ b/arch/arm64/kernel/process.c
> @@ -33,7 +33,6 @@
> #include <linux/kallsyms.h>
> #include <linux/init.h>
> #include <linux/cpu.h>
> -#include <linux/cpuidle.h>
> #include <linux/elfcore.h>
> #include <linux/pm.h>
> #include <linux/tick.h>
> @@ -94,10 +93,8 @@ void arch_cpu_idle(void)
> * This should do all the clock switching and wait for interrupt
> * tricks
> */
> - if (cpuidle_idle_call()) {
> - cpu_do_idle();
> - local_irq_enable();
> - }
> + cpu_do_idle();
> + local_irq_enable();
> }
>
> #ifdef CONFIG_HOTPLUG_CPU
>
On Thu, 6 Feb 2014, Preeti U Murthy wrote:
> Hi Nicolas,
>
> powernv in the subject of the patch?
Crap. You're right.
That's what you get when posting patches while attending a meeting.
>
> Regards
> Preeti U Murthy
> On 02/06/2014 07:46 PM, Nicolas Pitre wrote:
> > The core idle loop now takes care of it.
> >
> > Signed-off-by: Nicolas Pitre <[email protected]>
> > ---
> > arch/arm64/kernel/process.c | 7 ++-----
> > 1 file changed, 2 insertions(+), 5 deletions(-)
> >
> > diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> > index 1c0a9be2ff..9cce0098f4 100644
> > --- a/arch/arm64/kernel/process.c
> > +++ b/arch/arm64/kernel/process.c
> > @@ -33,7 +33,6 @@
> > #include <linux/kallsyms.h>
> > #include <linux/init.h>
> > #include <linux/cpu.h>
> > -#include <linux/cpuidle.h>
> > #include <linux/elfcore.h>
> > #include <linux/pm.h>
> > #include <linux/tick.h>
> > @@ -94,10 +93,8 @@ void arch_cpu_idle(void)
> > * This should do all the clock switching and wait for interrupt
> > * tricks
> > */
> > - if (cpuidle_idle_call()) {
> > - cpu_do_idle();
> > - local_irq_enable();
> > - }
> > + cpu_do_idle();
> > + local_irq_enable();
> > }
> >
> > #ifdef CONFIG_HOTPLUG_CPU
> >
>
Hi Daniel,
On 02/06/2014 09:55 PM, Daniel Lezcano wrote:
> Hi Nico,
>
>
> On 6 February 2014 14:16, Nicolas Pitre <[email protected]> wrote:
>
>> The core idle loop now takes care of it.
>>
>> Signed-off-by: Nicolas Pitre <[email protected]>
>> ---
>> arch/powerpc/platforms/powernv/setup.c | 13 +------------
>> 1 file changed, 1 insertion(+), 12 deletions(-)
>>
>> diff --git a/arch/powerpc/platforms/powernv/setup.c
>> b/arch/powerpc/platforms/powernv/setup.c
>> index 21166f65c9..a932feb290 100644
>> --- a/arch/powerpc/platforms/powernv/setup.c
>> +++ b/arch/powerpc/platforms/powernv/setup.c
>> @@ -26,7 +26,6 @@
>> #include <linux/of_fdt.h>
>> #include <linux/interrupt.h>
>> #include <linux/bug.h>
>> -#include <linux/cpuidle.h>
>>
>> #include <asm/machdep.h>
>> #include <asm/firmware.h>
>> @@ -217,16 +216,6 @@ static int __init pnv_probe(void)
>> return 1;
>> }
>>
>> -void powernv_idle(void)
>> -{
>> - /* Hook to cpuidle framework if available, else
>> - * call on default platform idle code
>> - */
>> - if (cpuidle_idle_call()) {
>> - power7_idle();
>> - }
>>
>
> The cpuidle_idle_call is called from arch_cpu_idle in
> arch/powerpc/kernel/idle.c between a ppc64_runlatch_off|on section.
> Shouldn't the cpuidle-powernv driver call these functions when entering
> idle ?
Yes they should, I will send out a patch that does that ontop of this.
There have been cpuidle driver cleanups for powernv and pseries in this
merge window. While no change would be required in the pseries cpuidle
driver as a result of Nicolas's cleanup, we would need to add the
ppc64_runlatch_on and off functions before and after the entry into the
powernv idle states.
Thanks
Regards
Preeti U Murthy
>
> -- Daniel
>
>
>> -}
>> -
>> define_machine(powernv) {
>> .name = "PowerNV",
>> .probe = pnv_probe,
>> @@ -236,7 +225,7 @@ define_machine(powernv) {
>> .show_cpuinfo = pnv_show_cpuinfo,
>> .progress = pnv_progress,
>> .machine_shutdown = pnv_shutdown,
>> - .power_save = powernv_idle,
>> + .power_save = power7_idle,
>> .calibrate_decr = generic_calibrate_decr,
>> #ifdef CONFIG_KEXEC
>> .kexec_cpu_down = pnv_kexec_cpu_down,
>> --
>> 1.8.4.108.g55ea5f6
>>
>>
>
On Thu, 6 Feb 2014, Preeti U Murthy wrote:
> Hi Daniel,
>
> On 02/06/2014 09:55 PM, Daniel Lezcano wrote:
> > Hi Nico,
> >
> >
> > On 6 February 2014 14:16, Nicolas Pitre <[email protected]> wrote:
> >
> >> The core idle loop now takes care of it.
> >>
> >> Signed-off-by: Nicolas Pitre <[email protected]>
> >> ---
> >> arch/powerpc/platforms/powernv/setup.c | 13 +------------
> >> 1 file changed, 1 insertion(+), 12 deletions(-)
> >>
> >> diff --git a/arch/powerpc/platforms/powernv/setup.c
> >> b/arch/powerpc/platforms/powernv/setup.c
> >> index 21166f65c9..a932feb290 100644
> >> --- a/arch/powerpc/platforms/powernv/setup.c
> >> +++ b/arch/powerpc/platforms/powernv/setup.c
> >> @@ -26,7 +26,6 @@
> >> #include <linux/of_fdt.h>
> >> #include <linux/interrupt.h>
> >> #include <linux/bug.h>
> >> -#include <linux/cpuidle.h>
> >>
> >> #include <asm/machdep.h>
> >> #include <asm/firmware.h>
> >> @@ -217,16 +216,6 @@ static int __init pnv_probe(void)
> >> return 1;
> >> }
> >>
> >> -void powernv_idle(void)
> >> -{
> >> - /* Hook to cpuidle framework if available, else
> >> - * call on default platform idle code
> >> - */
> >> - if (cpuidle_idle_call()) {
> >> - power7_idle();
> >> - }
> >>
> >
> > The cpuidle_idle_call is called from arch_cpu_idle in
> > arch/powerpc/kernel/idle.c between a ppc64_runlatch_off|on section.
> > Shouldn't the cpuidle-powernv driver call these functions when entering
> > idle ?
>
> Yes they should, I will send out a patch that does that ontop of this.
> There have been cpuidle driver cleanups for powernv and pseries in this
> merge window. While no change would be required in the pseries cpuidle
> driver as a result of Nicolas's cleanup, we would need to add the
> ppc64_runlatch_on and off functions before and after the entry into the
> powernv idle states.
What about creating arch_cpu_idle_enter() and arch_cpu_idle_exit() in
arch/powerpc/kernel/idle.c and calling ppc64_runlatch_off() and
ppc64_runlatch_on() respectively from there instead? Would that work?
That would make the idle consolidation much easier afterwards.
Nicolas
Hi Nicolas,
On 02/07/2014 06:47 AM, Nicolas Pitre wrote:
> On Thu, 6 Feb 2014, Preeti U Murthy wrote:
>
>> Hi Daniel,
>>
>> On 02/06/2014 09:55 PM, Daniel Lezcano wrote:
>>> Hi Nico,
>>>
>>>
>>> On 6 February 2014 14:16, Nicolas Pitre <[email protected]> wrote:
>>>
>>>> The core idle loop now takes care of it.
>>>>
>>>> Signed-off-by: Nicolas Pitre <[email protected]>
>>>> ---
>>>> arch/powerpc/platforms/powernv/setup.c | 13 +------------
>>>> 1 file changed, 1 insertion(+), 12 deletions(-)
>>>>
>>>> diff --git a/arch/powerpc/platforms/powernv/setup.c
>>>> b/arch/powerpc/platforms/powernv/setup.c
>>>> index 21166f65c9..a932feb290 100644
>>>> --- a/arch/powerpc/platforms/powernv/setup.c
>>>> +++ b/arch/powerpc/platforms/powernv/setup.c
>>>> @@ -26,7 +26,6 @@
>>>> #include <linux/of_fdt.h>
>>>> #include <linux/interrupt.h>
>>>> #include <linux/bug.h>
>>>> -#include <linux/cpuidle.h>
>>>>
>>>> #include <asm/machdep.h>
>>>> #include <asm/firmware.h>
>>>> @@ -217,16 +216,6 @@ static int __init pnv_probe(void)
>>>> return 1;
>>>> }
>>>>
>>>> -void powernv_idle(void)
>>>> -{
>>>> - /* Hook to cpuidle framework if available, else
>>>> - * call on default platform idle code
>>>> - */
>>>> - if (cpuidle_idle_call()) {
>>>> - power7_idle();
>>>> - }
>>>>
>>>
>>> The cpuidle_idle_call is called from arch_cpu_idle in
>>> arch/powerpc/kernel/idle.c between a ppc64_runlatch_off|on section.
>>> Shouldn't the cpuidle-powernv driver call these functions when entering
>>> idle ?
>>
>> Yes they should, I will send out a patch that does that ontop of this.
>> There have been cpuidle driver cleanups for powernv and pseries in this
>> merge window. While no change would be required in the pseries cpuidle
>> driver as a result of Nicolas's cleanup, we would need to add the
>> ppc64_runlatch_on and off functions before and after the entry into the
>> powernv idle states.
>
> What about creating arch_cpu_idle_enter() and arch_cpu_idle_exit() in
> arch/powerpc/kernel/idle.c and calling ppc64_runlatch_off() and
> ppc64_runlatch_on() respectively from there instead? Would that work?
> That would make the idle consolidation much easier afterwards.
I would not suggest doing this. The ppc64_runlatch_*() routines need to
be called when we are sure that the cpu is about to enter or has exit an
idle state. Moving the ppc64_runlatch_on() routine to
arch_cpu_idle_enter() for instance is not a good idea because there are
places where the cpu can decide not to enter any idle state before the
call to cpuidle_idle_call() itself. In that case communicating
prematurely that we are in an idle state would not be a good idea.
So its best to add the ppc64_runlatch_* calls in the powernv cpuidle
driver IMO. We could however create idle_loop_prologue/epilogue()
variants inside it so that in addition to the runlatch routines we could
potentially add more such similar routines that are powernv specific.
If there are cases where there is work to be done prior to and post an
entry into an idle state common to both pseries and powernv, we will
probably put them in arch_cpu_idle_enter/exit(). But the runlatch
routines are not suitable to be moved there as far as I can see.
Thank you
Regards
Preeti U Murthy
>
>
> Nicolas
> _______________________________________________
> Linuxppc-dev mailing list
> [email protected]
> https://lists.ozlabs.org/listinfo/linuxppc-dev
>
Hi Nicolas,
Find below the patch that will need to be squashed with this one.
This patch is based on the mainline.Adding Deepthi, the author of
the patch which introduced the powernv cpuidle driver. Deepthi,
do you think the below patch looks right? We do not need to do an
explicit local_irq_enable() since we are in the call path of
cpuidle driver and that explicitly enables irqs on exit from
idle states.
On 02/07/2014 06:47 AM, Nicolas Pitre wrote:
> On Thu, 6 Feb 2014, Preeti U Murthy wrote:
>
>> Hi Daniel,
>>
>> On 02/06/2014 09:55 PM, Daniel Lezcano wrote:
>>> Hi Nico,
>>>
>>>
>>> On 6 February 2014 14:16, Nicolas Pitre <[email protected]> wrote:
>>>
>>>> The core idle loop now takes care of it.
>>>>
>>>> Signed-off-by: Nicolas Pitre <[email protected]>
>>>> ---
>>>> arch/powerpc/platforms/powernv/setup.c | 13 +------------
>>>> 1 file changed, 1 insertion(+), 12 deletions(-)
>>>>
>>>> diff --git a/arch/powerpc/platforms/powernv/setup.c
>>>> b/arch/powerpc/platforms/powernv/setup.c
>>>> index 21166f65c9..a932feb290 100644
>>>> --- a/arch/powerpc/platforms/powernv/setup.c
>>>> +++ b/arch/powerpc/platforms/powernv/setup.c
>>>> @@ -26,7 +26,6 @@
>>>> #include <linux/of_fdt.h>
>>>> #include <linux/interrupt.h>
>>>> #include <linux/bug.h>
>>>> -#include <linux/cpuidle.h>
>>>>
>>>> #include <asm/machdep.h>
>>>> #include <asm/firmware.h>
>>>> @@ -217,16 +216,6 @@ static int __init pnv_probe(void)
>>>> return 1;
>>>> }
>>>>
>>>> -void powernv_idle(void)
>>>> -{
>>>> - /* Hook to cpuidle framework if available, else
>>>> - * call on default platform idle code
>>>> - */
>>>> - if (cpuidle_idle_call()) {
>>>> - power7_idle();
>>>> - }
>>>>
drivers/cpuidle/cpuidle-powernv.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 78fd174..130f081 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -31,11 +31,13 @@ static int snooze_loop(struct cpuidle_device *dev,
set_thread_flag(TIF_POLLING_NRFLAG);
while (!need_resched()) {
+ ppc64_runlatch_off();
HMT_low();
HMT_very_low();
}
HMT_medium();
+ ppc64_runlatch_on();
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb();
return index;
@@ -45,7 +47,9 @@ static int nap_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
+ ppc64_runlatch_off();
power7_idle();
+ ppc64_runlatch_on();
return index;
}
Thanks
Regards
Preeti U Murthy
Hi Preeti,
Thanks for the patch.
On 02/07/2014 12:31 PM, Preeti U Murthy wrote:
> Hi Nicolas,
>
> Find below the patch that will need to be squashed with this one.
> This patch is based on the mainline.Adding Deepthi, the author of
> the patch which introduced the powernv cpuidle driver. Deepthi,
> do you think the below patch looks right? We do not need to do an
> explicit local_irq_enable() since we are in the call path of
> cpuidle driver and that explicitly enables irqs on exit from
> idle states.
Yes, We enable irqs explicitly while entering snooze loop and we always
have interrupts enabled in the snooze state.
For NAP state, we exit out of this state with interrupts enabled so we
do not need an explicit enable of irqs.
> On 02/07/2014 06:47 AM, Nicolas Pitre wrote:
>> On Thu, 6 Feb 2014, Preeti U Murthy wrote:
>>
>>> Hi Daniel,
>>>
>>> On 02/06/2014 09:55 PM, Daniel Lezcano wrote:
>>>> Hi Nico,
>>>>
>>>>
>>>> On 6 February 2014 14:16, Nicolas Pitre <[email protected]> wrote:
>>>>
>>>>> The core idle loop now takes care of it.
>>>>>
>>>>> Signed-off-by: Nicolas Pitre <[email protected]>
>>>>> ---
>>>>> arch/powerpc/platforms/powernv/setup.c | 13 +------------
>>>>> 1 file changed, 1 insertion(+), 12 deletions(-)
>>>>>
>>>>> diff --git a/arch/powerpc/platforms/powernv/setup.c
>>>>> b/arch/powerpc/platforms/powernv/setup.c
>>>>> index 21166f65c9..a932feb290 100644
>>>>> --- a/arch/powerpc/platforms/powernv/setup.c
>>>>> +++ b/arch/powerpc/platforms/powernv/setup.c
>>>>> @@ -26,7 +26,6 @@
>>>>> #include <linux/of_fdt.h>
>>>>> #include <linux/interrupt.h>
>>>>> #include <linux/bug.h>
>>>>> -#include <linux/cpuidle.h>
>>>>>
>>>>> #include <asm/machdep.h>
>>>>> #include <asm/firmware.h>
>>>>> @@ -217,16 +216,6 @@ static int __init pnv_probe(void)
>>>>> return 1;
>>>>> }
>>>>>
>>>>> -void powernv_idle(void)
>>>>> -{
>>>>> - /* Hook to cpuidle framework if available, else
>>>>> - * call on default platform idle code
>>>>> - */
>>>>> - if (cpuidle_idle_call()) {
>>>>> - power7_idle();
>>>>> - }
>>>>>
>
> drivers/cpuidle/cpuidle-powernv.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
> index 78fd174..130f081 100644
> --- a/drivers/cpuidle/cpuidle-powernv.c
> +++ b/drivers/cpuidle/cpuidle-powernv.c
> @@ -31,11 +31,13 @@ static int snooze_loop(struct cpuidle_device *dev,
> set_thread_flag(TIF_POLLING_NRFLAG);
>
> while (!need_resched()) {
> + ppc64_runlatch_off();
^^^^^^^^^^^^^^^
We could move this before the while() loop.
It would ideal to turn off latch when we enter snooze and
turn it on when we are about to exit, rather than doing
it over and over in the while loop.
> HMT_low();
> HMT_very_low();
> }
>
> HMT_medium();
> + ppc64_runlatch_on();
> clear_thread_flag(TIF_POLLING_NRFLAG);
> smp_mb();
> return index;
> @@ -45,7 +47,9 @@ static int nap_loop(struct cpuidle_device *dev,
> struct cpuidle_driver *drv,
> int index)
> {
> + ppc64_runlatch_off();
> power7_idle();
> + ppc64_runlatch_on();
> return index;
> }
>
> Thanks
>
> Regards
> Preeti U Murthy
>
Regards,
Deepthi
On 6 February 2014 14:16, Nicolas Pitre <[email protected]> wrote:
> The core idle loop now takes care of it.
>
> Signed-off-by: Nicolas Pitre <[email protected]>
Acked-by: Catalin Marinas <[email protected]>
On Fri, 7 Feb 2014, Preeti U Murthy wrote:
> Hi Nicolas,
>
> On 02/07/2014 06:47 AM, Nicolas Pitre wrote:
> >
> > What about creating arch_cpu_idle_enter() and arch_cpu_idle_exit() in
> > arch/powerpc/kernel/idle.c and calling ppc64_runlatch_off() and
> > ppc64_runlatch_on() respectively from there instead? Would that work?
> > That would make the idle consolidation much easier afterwards.
>
> I would not suggest doing this. The ppc64_runlatch_*() routines need to
> be called when we are sure that the cpu is about to enter or has exit an
> idle state. Moving the ppc64_runlatch_on() routine to
> arch_cpu_idle_enter() for instance is not a good idea because there are
> places where the cpu can decide not to enter any idle state before the
> call to cpuidle_idle_call() itself. In that case communicating
> prematurely that we are in an idle state would not be a good idea.
>
> So its best to add the ppc64_runlatch_* calls in the powernv cpuidle
> driver IMO. We could however create idle_loop_prologue/epilogue()
> variants inside it so that in addition to the runlatch routines we could
> potentially add more such similar routines that are powernv specific.
> If there are cases where there is work to be done prior to and post an
> entry into an idle state common to both pseries and powernv, we will
> probably put them in arch_cpu_idle_enter/exit(). But the runlatch
> routines are not suitable to be moved there as far as I can see.
OK.
However, one thing we need to do as much as possible is to remove those
loops based on need_resched() from idle backend drivers. A somewhat
common pattern is:
my_idle()
{
/* interrupts disabled on entry */
while (!need_resched()) {
lowpower_wait_for_interrupts();
local_irq_enable();
/* IRQ serviced from here */
local_irq_disable();
}
local_irq_enable();
/* interrupts enabled on exit */
}
To be able to keep statistics on the actual idleness of the CPU we'd
need for all idle backends to always return to generic code on every
interrupt similar to this:
my_idle()
{
/* interrupts disabled on entry */
lowpower_wait_for_interrupts();
local_irq_enable();
/* interrupts enabled on exit */
}
The generic code would be responsible for dealing with need_resched()
and call back into the backend right away if necessary after updating
some stats.
Do you see a problem with the runlatch calls happening around each
interrrupt from such a simplified idle backend?
Nicolas
Hi Deepthi,
On 02/07/2014 03:15 PM, Deepthi Dharwar wrote:
> Hi Preeti,
>
> Thanks for the patch.
>
> On 02/07/2014 12:31 PM, Preeti U Murthy wrote:
>> Hi Nicolas,
>>
>> Find below the patch that will need to be squashed with this one.
>> This patch is based on the mainline.Adding Deepthi, the author of
>> the patch which introduced the powernv cpuidle driver. Deepthi,
>> do you think the below patch looks right? We do not need to do an
>> explicit local_irq_enable() since we are in the call path of
>> cpuidle driver and that explicitly enables irqs on exit from
>> idle states.
>
> Yes, We enable irqs explicitly while entering snooze loop and we always
> have interrupts enabled in the snooze state.
> For NAP state, we exit out of this state with interrupts enabled so we
> do not need an explicit enable of irqs.
>
>> On 02/07/2014 06:47 AM, Nicolas Pitre wrote:
>>> On Thu, 6 Feb 2014, Preeti U Murthy wrote:
>>>
>>>> Hi Daniel,
>>>>
>>>> On 02/06/2014 09:55 PM, Daniel Lezcano wrote:
>>>>> Hi Nico,
>>>>>
>>>>>
>>>>> On 6 February 2014 14:16, Nicolas Pitre <[email protected]> wrote:
>>>>>
>>>>>> The core idle loop now takes care of it.
>>>>>>
>>>>>> Signed-off-by: Nicolas Pitre <[email protected]>
>>>>>> ---
>>>>>> arch/powerpc/platforms/powernv/setup.c | 13 +------------
>>>>>> 1 file changed, 1 insertion(+), 12 deletions(-)
>>>>>>
>>>>>> diff --git a/arch/powerpc/platforms/powernv/setup.c
>>>>>> b/arch/powerpc/platforms/powernv/setup.c
>>>>>> index 21166f65c9..a932feb290 100644
>>>>>> --- a/arch/powerpc/platforms/powernv/setup.c
>>>>>> +++ b/arch/powerpc/platforms/powernv/setup.c
>>>>>> @@ -26,7 +26,6 @@
>>>>>> #include <linux/of_fdt.h>
>>>>>> #include <linux/interrupt.h>
>>>>>> #include <linux/bug.h>
>>>>>> -#include <linux/cpuidle.h>
>>>>>>
>>>>>> #include <asm/machdep.h>
>>>>>> #include <asm/firmware.h>
>>>>>> @@ -217,16 +216,6 @@ static int __init pnv_probe(void)
>>>>>> return 1;
>>>>>> }
>>>>>>
>>>>>> -void powernv_idle(void)
>>>>>> -{
>>>>>> - /* Hook to cpuidle framework if available, else
>>>>>> - * call on default platform idle code
>>>>>> - */
>>>>>> - if (cpuidle_idle_call()) {
>>>>>> - power7_idle();
>>>>>> - }
>>>>>>
>>
>> drivers/cpuidle/cpuidle-powernv.c | 4 ++++
>> 1 file changed, 4 insertions(+)
>>
>> diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
>> index 78fd174..130f081 100644
>> --- a/drivers/cpuidle/cpuidle-powernv.c
>> +++ b/drivers/cpuidle/cpuidle-powernv.c
>> @@ -31,11 +31,13 @@ static int snooze_loop(struct cpuidle_device *dev,
>> set_thread_flag(TIF_POLLING_NRFLAG);
>>
>> while (!need_resched()) {
>> + ppc64_runlatch_off();
> ^^^^^^^^^^^^^^^
> We could move this before the while() loop.
> It would ideal to turn off latch when we enter snooze and
> turn it on when we are about to exit, rather than doing
> it over and over in the while loop.
You are right, this can be moved out of the loop.
Thanks
Regards
Preeti U Murthy
Hi Nicolas,
On 02/07/2014 04:18 PM, Nicolas Pitre wrote:
> On Fri, 7 Feb 2014, Preeti U Murthy wrote:
>
>> Hi Nicolas,
>>
>> On 02/07/2014 06:47 AM, Nicolas Pitre wrote:
>>>
>>> What about creating arch_cpu_idle_enter() and arch_cpu_idle_exit() in
>>> arch/powerpc/kernel/idle.c and calling ppc64_runlatch_off() and
>>> ppc64_runlatch_on() respectively from there instead? Would that work?
>>> That would make the idle consolidation much easier afterwards.
>>
>> I would not suggest doing this. The ppc64_runlatch_*() routines need to
>> be called when we are sure that the cpu is about to enter or has exit an
>> idle state. Moving the ppc64_runlatch_on() routine to
>> arch_cpu_idle_enter() for instance is not a good idea because there are
>> places where the cpu can decide not to enter any idle state before the
>> call to cpuidle_idle_call() itself. In that case communicating
>> prematurely that we are in an idle state would not be a good idea.
>>
>> So its best to add the ppc64_runlatch_* calls in the powernv cpuidle
>> driver IMO. We could however create idle_loop_prologue/epilogue()
>> variants inside it so that in addition to the runlatch routines we could
>> potentially add more such similar routines that are powernv specific.
>> If there are cases where there is work to be done prior to and post an
>> entry into an idle state common to both pseries and powernv, we will
>> probably put them in arch_cpu_idle_enter/exit(). But the runlatch
>> routines are not suitable to be moved there as far as I can see.
>
> OK.
>
> However, one thing we need to do as much as possible is to remove those
> loops based on need_resched() from idle backend drivers. A somewhat
> common pattern is:
>
> my_idle()
> {
> /* interrupts disabled on entry */
> while (!need_resched()) {
> lowpower_wait_for_interrupts();
> local_irq_enable();
> /* IRQ serviced from here */
> local_irq_disable();
> }
> local_irq_enable();
> /* interrupts enabled on exit */
> }
>
> To be able to keep statistics on the actual idleness of the CPU we'd
> need for all idle backends to always return to generic code on every
> interrupt similar to this:
>
> my_idle()
> {
> /* interrupts disabled on entry */
> lowpower_wait_for_interrupts();
You can do this for the idle states which do not have the polling
nature. IOW, these idle states are capable of doing what you describe as
"wait_for_interrupts". They do some kind of spinning at the hardware
level with interrupts enabled. A reschedule IPI or any other interrupt
will wake them up to enter the generic idle loop where they check for
the cause of the interrupt.
But observe the idle state "snooze" on powerpc. The power that this idle
state saves is through the lowering of the thread priority of the CPU.
After it lowers the thread priority, it is done. It cannot
"wait_for_interrupts". It will exit my_idle(). It is now upto the
generic idle loop to increase the thread priority if the need_resched
flag is set. Only an interrupt routine can increase the thread priority.
Else we will need to do it explicitly. And in such states which have a
polling nature, the cpu will not receive a reschedule IPI.
That is why in the snooze_loop() we poll on need_resched. If it is set
we up the priority of the thread using HMT_MEDIUM() and then exit the
my_idle() loop. In case of interrupts, the priority gets automatically
increased.
This might not be required to be done for similar idle routines on other
archs but this is the consequence of applying this idea of simplified
cpuidle backend driver on powerpc.
I would say you could let the backend cpuidle drivers be in this regard,
it could complicate the generic idle loop IMO depending on how the
polling states are implemented in each architecture.
> The generic code would be responsible for dealing with need_resched()
> and call back into the backend right away if necessary after updating
> some stats.
>
> Do you see a problem with the runlatch calls happening around each
> interrrupt from such a simplified idle backend?
The runlatch calls could be moved outside the loop.They do not need to
be called each time.
Thanks
Regards
Preeti U Murthy
>
>
> Nicolas
>
On Fri, Feb 07, 2014 at 05:11:26PM +0530, Preeti U Murthy wrote:
> But observe the idle state "snooze" on powerpc. The power that this idle
> state saves is through the lowering of the thread priority of the CPU.
> After it lowers the thread priority, it is done. It cannot
> "wait_for_interrupts". It will exit my_idle(). It is now upto the
> generic idle loop to increase the thread priority if the need_resched
> flag is set. Only an interrupt routine can increase the thread priority.
> Else we will need to do it explicitly. And in such states which have a
> polling nature, the cpu will not receive a reschedule IPI.
>
> That is why in the snooze_loop() we poll on need_resched. If it is set
> we up the priority of the thread using HMT_MEDIUM() and then exit the
> my_idle() loop. In case of interrupts, the priority gets automatically
> increased.
You can poll without setting TS_POLLING/TIF_POLLING_NRFLAGS just fine
and get the IPI if that is what you want.
Depending on how horribly unprovisioned the thread gets at the lowest
priority, that might actually be faster than polling and raising the
prio whenever it does get ran.
Hi Peter,
On 02/07/2014 06:11 PM, Peter Zijlstra wrote:
> On Fri, Feb 07, 2014 at 05:11:26PM +0530, Preeti U Murthy wrote:
>> But observe the idle state "snooze" on powerpc. The power that this idle
>> state saves is through the lowering of the thread priority of the CPU.
>> After it lowers the thread priority, it is done. It cannot
>> "wait_for_interrupts". It will exit my_idle(). It is now upto the
>> generic idle loop to increase the thread priority if the need_resched
>> flag is set. Only an interrupt routine can increase the thread priority.
>> Else we will need to do it explicitly. And in such states which have a
>> polling nature, the cpu will not receive a reschedule IPI.
>>
>> That is why in the snooze_loop() we poll on need_resched. If it is set
>> we up the priority of the thread using HMT_MEDIUM() and then exit the
>> my_idle() loop. In case of interrupts, the priority gets automatically
>> increased.
>
> You can poll without setting TS_POLLING/TIF_POLLING_NRFLAGS just fine
> and get the IPI if that is what you want.
>
> Depending on how horribly unprovisioned the thread gets at the lowest
> priority, that might actually be faster than polling and raising the
> prio whenever it does get ran.
So I am assuming you mean something like the below:
my_idle()
{
local_irq_enable();
/* Remove the setting of the polling flag */
HMT_low();
return index;
}
And then exit into the generic idle loop. But the issue I see here is
that the TS_POLLING/TIF_POLLING_NRFLAGS gets set immediately. So, if on
testing need_resched() immediately after this returns that the
TIF_NEED_RESCHED flag is set, the thread will exit at low priority right?
We could raise the priority of the thread in arch_cpu_idle_exit() soon
after setting the polling flag but that would mean for cases where the
TIF_NEED_RESCHED flag is not set we unnecessarily raise the priority of
the thread.
Thanks
Regards
Preeti U Murthy
>
Hi Nicolas,
You will have to include the below patch with yours. You
could squash the two I guess, I have added the changelog
just for clarity. And you also might want to change the subject to
cpuidle/powernv. It gives a better picture.
Thanks
Regards
Preeti U Murthy
cpuidle/powernv: Add ppc64_runlatch_off/on() to idle routines
Following moving of cpuidle_idle_call() to the generic idle loop, we need to
add the runlatch functions to the idle routines on powernv which was earlier
taken care of by the arch specific idle routine.
Signed-off-by: Preeti U Murthy <[email protected]>
---
drivers/cpuidle/cpuidle-powernv.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 78fd174..f48607c 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -14,6 +14,7 @@
#include <asm/machdep.h>
#include <asm/firmware.h>
+#include <asm/runlatch.h>
struct cpuidle_driver powernv_idle_driver = {
.name = "powernv_idle",
@@ -30,12 +31,14 @@ static int snooze_loop(struct cpuidle_device *dev,
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
+ ppc64_runlatch_off();
while (!need_resched()) {
HMT_low();
HMT_very_low();
}
HMT_medium();
+ ppc64_runlatch_on();
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb();
return index;
@@ -45,7 +48,9 @@ static int nap_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
+ ppc64_runlatch_off();
power7_idle();
+ ppc64_runlatch_on();
return index;
}
On 02/06/2014 07:46 PM, Nicolas Pitre wrote:
> The core idle loop now takes care of it.
>
> Signed-off-by: Nicolas Pitre <[email protected]>
> ---
> arch/powerpc/platforms/powernv/setup.c | 13 +------------
> 1 file changed, 1 insertion(+), 12 deletions(-)
>
> diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
> index 21166f65c9..a932feb290 100644
> --- a/arch/powerpc/platforms/powernv/setup.c
> +++ b/arch/powerpc/platforms/powernv/setup.c
> @@ -26,7 +26,6 @@
> #include <linux/of_fdt.h>
> #include <linux/interrupt.h>
> #include <linux/bug.h>
> -#include <linux/cpuidle.h>
>
> #include <asm/machdep.h>
> #include <asm/firmware.h>
> @@ -217,16 +216,6 @@ static int __init pnv_probe(void)
> return 1;
> }
>
> -void powernv_idle(void)
> -{
> - /* Hook to cpuidle framework if available, else
> - * call on default platform idle code
> - */
> - if (cpuidle_idle_call()) {
> - power7_idle();
> - }
> -}
> -
> define_machine(powernv) {
> .name = "PowerNV",
> .probe = pnv_probe,
> @@ -236,7 +225,7 @@ define_machine(powernv) {
> .show_cpuinfo = pnv_show_cpuinfo,
> .progress = pnv_progress,
> .machine_shutdown = pnv_shutdown,
> - .power_save = powernv_idle,
> + .power_save = power7_idle,
> .calibrate_decr = generic_calibrate_decr,
> #ifdef CONFIG_KEXEC
> .kexec_cpu_down = pnv_kexec_cpu_down,
>
On 02/14/2014 04:47 PM, Preeti U Murthy wrote:
> Hi Nicolas,
>
> You will have to include the below patch with yours. You
> could squash the two I guess, I have added the changelog
> just for clarity. And you also might want to change the subject to
> cpuidle/powernv. It gives a better picture.
>
> Thanks
>
> Regards
> Preeti U Murthy
>
>
> cpuidle/powernv: Add ppc64_runlatch_off/on() to idle routines
>
> Following moving of cpuidle_idle_call() to the generic idle loop, we need to
> add the runlatch functions to the idle routines on powernv which was earlier
> taken care of by the arch specific idle routine.
>
> Signed-off-by: Preeti U Murthy <[email protected]>
Reviewed-by: Deepthi Dharwar <[email protected]>
> ---
> drivers/cpuidle/cpuidle-powernv.c | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
> index 78fd174..f48607c 100644
> --- a/drivers/cpuidle/cpuidle-powernv.c
> +++ b/drivers/cpuidle/cpuidle-powernv.c
> @@ -14,6 +14,7 @@
>
> #include <asm/machdep.h>
> #include <asm/firmware.h>
> +#include <asm/runlatch.h>
>
> struct cpuidle_driver powernv_idle_driver = {
> .name = "powernv_idle",
> @@ -30,12 +31,14 @@ static int snooze_loop(struct cpuidle_device *dev,
> local_irq_enable();
> set_thread_flag(TIF_POLLING_NRFLAG);
>
> + ppc64_runlatch_off();
> while (!need_resched()) {
> HMT_low();
> HMT_very_low();
> }
>
> HMT_medium();
> + ppc64_runlatch_on();
> clear_thread_flag(TIF_POLLING_NRFLAG);
> smp_mb();
> return index;
> @@ -45,7 +48,9 @@ static int nap_loop(struct cpuidle_device *dev,
> struct cpuidle_driver *drv,
> int index)
> {
> + ppc64_runlatch_off();
> power7_idle();
> + ppc64_runlatch_on();
> return index;
> }
>
>
> On 02/06/2014 07:46 PM, Nicolas Pitre wrote:
>> The core idle loop now takes care of it.
>>
>> Signed-off-by: Nicolas Pitre <[email protected]>
>> ---
>> arch/powerpc/platforms/powernv/setup.c | 13 +------------
>> 1 file changed, 1 insertion(+), 12 deletions(-)
>>
>> diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
>> index 21166f65c9..a932feb290 100644
>> --- a/arch/powerpc/platforms/powernv/setup.c
>> +++ b/arch/powerpc/platforms/powernv/setup.c
>> @@ -26,7 +26,6 @@
>> #include <linux/of_fdt.h>
>> #include <linux/interrupt.h>
>> #include <linux/bug.h>
>> -#include <linux/cpuidle.h>
>>
>> #include <asm/machdep.h>
>> #include <asm/firmware.h>
>> @@ -217,16 +216,6 @@ static int __init pnv_probe(void)
>> return 1;
>> }
>>
>> -void powernv_idle(void)
>> -{
>> - /* Hook to cpuidle framework if available, else
>> - * call on default platform idle code
>> - */
>> - if (cpuidle_idle_call()) {
>> - power7_idle();
>> - }
>> -}
>> -
>> define_machine(powernv) {
>> .name = "PowerNV",
>> .probe = pnv_probe,
>> @@ -236,7 +225,7 @@ define_machine(powernv) {
>> .show_cpuinfo = pnv_show_cpuinfo,
>> .progress = pnv_progress,
>> .machine_shutdown = pnv_shutdown,
>> - .power_save = powernv_idle,
>> + .power_save = power7_idle,
>> .calibrate_decr = generic_calibrate_decr,
>> #ifdef CONFIG_KEXEC
>> .kexec_cpu_down = pnv_kexec_cpu_down,
>>
>
> _______________________________________________
> Linuxppc-dev mailing list
> [email protected]
> https://lists.ozlabs.org/listinfo/linuxppc-dev
>