public inbox for linux-acpi@vger.kernel.org
 help / color / mirror / Atom feed
* [PATCH] Enable bit 11 in _PDC to advertise hw coord
@ 2009-02-02 19:57 Pallipadi, Venkatesh
  2009-02-04  8:57 ` Jens Axboe
  2009-02-07  4:10 ` Len Brown
  0 siblings, 2 replies; 7+ messages in thread
From: Pallipadi, Venkatesh @ 2009-02-02 19:57 UTC (permalink / raw)
  To: Len Brown; +Cc: linux-acpi, Jens Axboe, Chris Mason


Bit 11 in intel PDC definitions is meant for OS capability to handle
hardware coordination of P-states. In Linux we have always supported
hwardware coordination of P-states. Just let the BIOSes know that we
support it, by setting this bit.

Some BIOSes use this bit to choose between hardware or software coordination
and without this change below, BIOSes switch to software coordination, which
is not very optimal in terms of power consumption and extra wakeups from idle.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>

---
 include/acpi/pdc_intel.h |    2 ++
 1 file changed, 2 insertions(+)

Index: linux-2.6/include/acpi/pdc_intel.h
===================================================================
--- linux-2.6.orig/include/acpi/pdc_intel.h	2009-01-20 16:11:20.000000000 -0800
+++ linux-2.6/include/acpi/pdc_intel.h	2009-02-02 10:32:06.000000000 -0800
@@ -14,6 +14,7 @@
 #define ACPI_PDC_SMP_T_SWCOORD		(0x0080)
 #define ACPI_PDC_C_C1_FFH		(0x0100)
 #define ACPI_PDC_C_C2C3_FFH		(0x0200)
+#define ACPI_PDC_SMP_P_HWCOORD		(0x0800)
 
 #define ACPI_PDC_EST_CAPABILITY_SMP	(ACPI_PDC_SMP_C1PT | \
 					 ACPI_PDC_C_C1_HALT | \
@@ -22,6 +23,7 @@
 #define ACPI_PDC_EST_CAPABILITY_SWSMP	(ACPI_PDC_SMP_C1PT | \
 					 ACPI_PDC_C_C1_HALT | \
 					 ACPI_PDC_SMP_P_SWCOORD | \
+					 ACPI_PDC_SMP_P_HWCOORD | \
 					 ACPI_PDC_P_FFH)
 
 #define ACPI_PDC_C_CAPABILITY_SMP	(ACPI_PDC_SMP_C2C3  | \

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH] Enable bit 11 in _PDC to advertise hw coord
  2009-02-02 19:57 [PATCH] Enable bit 11 in _PDC to advertise hw coord Pallipadi, Venkatesh
@ 2009-02-04  8:57 ` Jens Axboe
  2009-02-04 19:53   ` Henrique de Moraes Holschuh
  2009-02-07  4:10 ` Len Brown
  1 sibling, 1 reply; 7+ messages in thread
From: Jens Axboe @ 2009-02-04  8:57 UTC (permalink / raw)
  To: Pallipadi, Venkatesh; +Cc: Len Brown, linux-acpi, Chris Mason

On Mon, Feb 02 2009, Pallipadi, Venkatesh wrote:
> 
> Bit 11 in intel PDC definitions is meant for OS capability to handle
> hardware coordination of P-states. In Linux we have always supported
> hwardware coordination of P-states. Just let the BIOSes know that we
> support it, by setting this bit.
> 
> Some BIOSes use this bit to choose between hardware or software coordination
> and without this change below, BIOSes switch to software coordination, which
> is not very optimal in terms of power consumption and extra wakeups from idle.

I can confirm that this fixes the excessive reschedule ipi count on an
x60 with the ondemand governor. Can we please get this into 2.6.29?

> 
> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
> 
> ---
>  include/acpi/pdc_intel.h |    2 ++
>  1 file changed, 2 insertions(+)
> 
> Index: linux-2.6/include/acpi/pdc_intel.h
> ===================================================================
> --- linux-2.6.orig/include/acpi/pdc_intel.h	2009-01-20 16:11:20.000000000 -0800
> +++ linux-2.6/include/acpi/pdc_intel.h	2009-02-02 10:32:06.000000000 -0800
> @@ -14,6 +14,7 @@
>  #define ACPI_PDC_SMP_T_SWCOORD		(0x0080)
>  #define ACPI_PDC_C_C1_FFH		(0x0100)
>  #define ACPI_PDC_C_C2C3_FFH		(0x0200)
> +#define ACPI_PDC_SMP_P_HWCOORD		(0x0800)
>  
>  #define ACPI_PDC_EST_CAPABILITY_SMP	(ACPI_PDC_SMP_C1PT | \
>  					 ACPI_PDC_C_C1_HALT | \
> @@ -22,6 +23,7 @@
>  #define ACPI_PDC_EST_CAPABILITY_SWSMP	(ACPI_PDC_SMP_C1PT | \
>  					 ACPI_PDC_C_C1_HALT | \
>  					 ACPI_PDC_SMP_P_SWCOORD | \
> +					 ACPI_PDC_SMP_P_HWCOORD | \
>  					 ACPI_PDC_P_FFH)
>  
>  #define ACPI_PDC_C_CAPABILITY_SMP	(ACPI_PDC_SMP_C2C3  | \

-- 
Jens Axboe


^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH] Enable bit 11 in _PDC to advertise hw coord
  2009-02-04  8:57 ` Jens Axboe
@ 2009-02-04 19:53   ` Henrique de Moraes Holschuh
  2009-02-04 20:06     ` Pallipadi, Venkatesh
  0 siblings, 1 reply; 7+ messages in thread
From: Henrique de Moraes Holschuh @ 2009-02-04 19:53 UTC (permalink / raw)
  To: Jens Axboe; +Cc: Pallipadi, Venkatesh, Len Brown, linux-acpi, Chris Mason

On Wed, 04 Feb 2009, Jens Axboe wrote:
> On Mon, Feb 02 2009, Pallipadi, Venkatesh wrote:
> > 
> > Bit 11 in intel PDC definitions is meant for OS capability to handle
> > hardware coordination of P-states. In Linux we have always supported
> > hwardware coordination of P-states. Just let the BIOSes know that we
> > support it, by setting this bit.
> > 
> > Some BIOSes use this bit to choose between hardware or software coordination
> > and without this change below, BIOSes switch to software coordination, which
> > is not very optimal in terms of power consumption and extra wakeups from idle.
> 
> I can confirm that this fixes the excessive reschedule ipi count on an
> x60 with the ondemand governor. Can we please get this into 2.6.29?

And, after that, -stable?

-- 
  "One disk to rule them all, One disk to find them. One disk to bring
  them all and in the darkness grind them. In the Land of Redmond
  where the shadows lie." -- The Silicon Valley Tarot
  Henrique Holschuh

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH] Enable bit 11 in _PDC to advertise hw coord
  2009-02-04 19:53   ` Henrique de Moraes Holschuh
@ 2009-02-04 20:06     ` Pallipadi, Venkatesh
  2009-02-04 20:40       ` Greg KH
  0 siblings, 1 reply; 7+ messages in thread
From: Pallipadi, Venkatesh @ 2009-02-04 20:06 UTC (permalink / raw)
  To: Henrique de Moraes Holschuh
  Cc: Jens Axboe, Len Brown, linux-acpi@vger.kernel.org, Chris Mason,
	Greg KH, stable kernel

On Wed, 2009-02-04 at 11:53 -0800, Henrique de Moraes Holschuh wrote:
> On Wed, 04 Feb 2009, Jens Axboe wrote:
> > On Mon, Feb 02 2009, Pallipadi, Venkatesh wrote:
> > > 
> > > Bit 11 in intel PDC definitions is meant for OS capability to handle
> > > hardware coordination of P-states. In Linux we have always supported
> > > hwardware coordination of P-states. Just let the BIOSes know that we
> > > support it, by setting this bit.
> > > 
> > > Some BIOSes use this bit to choose between hardware or software coordination
> > > and without this change below, BIOSes switch to software coordination, which
> > > is not very optimal in terms of power consumption and extra wakeups from idle.
> > 
> > I can confirm that this fixes the excessive reschedule ipi count on an
> > x60 with the ondemand governor. Can we please get this into 2.6.29?
> 
> And, after that, -stable?
> 

Agreed. This should also go to -stable once it gets into mainline.

Thanks,
Venki


^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH] Enable bit 11 in _PDC to advertise hw coord
  2009-02-04 20:06     ` Pallipadi, Venkatesh
@ 2009-02-04 20:40       ` Greg KH
  2009-02-08 19:51         ` [stable] " Greg KH
  0 siblings, 1 reply; 7+ messages in thread
From: Greg KH @ 2009-02-04 20:40 UTC (permalink / raw)
  To: Pallipadi, Venkatesh
  Cc: Henrique de Moraes Holschuh, Jens Axboe, Len Brown,
	linux-acpi@vger.kernel.org, Chris Mason, stable kernel

On Wed, Feb 04, 2009 at 12:06:42PM -0800, Pallipadi, Venkatesh wrote:
> On Wed, 2009-02-04 at 11:53 -0800, Henrique de Moraes Holschuh wrote:
> > On Wed, 04 Feb 2009, Jens Axboe wrote:
> > > On Mon, Feb 02 2009, Pallipadi, Venkatesh wrote:
> > > > 
> > > > Bit 11 in intel PDC definitions is meant for OS capability to handle
> > > > hardware coordination of P-states. In Linux we have always supported
> > > > hwardware coordination of P-states. Just let the BIOSes know that we
> > > > support it, by setting this bit.
> > > > 
> > > > Some BIOSes use this bit to choose between hardware or software coordination
> > > > and without this change below, BIOSes switch to software coordination, which
> > > > is not very optimal in terms of power consumption and extra wakeups from idle.
> > > 
> > > I can confirm that this fixes the excessive reschedule ipi count on an
> > > x60 with the ondemand governor. Can we please get this into 2.6.29?
> > 
> > And, after that, -stable?
> > 
> 
> Agreed. This should also go to -stable once it gets into mainline.

Can someone send stable@kernel.org the git commit id when it goes into
Linus's tree?

thanks,

greg k-h

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH] Enable bit 11 in _PDC to advertise hw coord
  2009-02-02 19:57 [PATCH] Enable bit 11 in _PDC to advertise hw coord Pallipadi, Venkatesh
  2009-02-04  8:57 ` Jens Axboe
@ 2009-02-07  4:10 ` Len Brown
  1 sibling, 0 replies; 7+ messages in thread
From: Len Brown @ 2009-02-07  4:10 UTC (permalink / raw)
  To: Pallipadi, Venkatesh; +Cc: linux-acpi, Jens Axboe, Chris Mason

applied
thanks,
--
Len Brown, Intel Open Source Technology Center

On Mon, 2 Feb 2009, Pallipadi, Venkatesh wrote:

> 
> Bit 11 in intel PDC definitions is meant for OS capability to handle
> hardware coordination of P-states. In Linux we have always supported
> hwardware coordination of P-states. Just let the BIOSes know that we
> support it, by setting this bit.
> 
> Some BIOSes use this bit to choose between hardware or software coordination
> and without this change below, BIOSes switch to software coordination, which
> is not very optimal in terms of power consumption and extra wakeups from idle.
> 
> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
> 
> ---
>  include/acpi/pdc_intel.h |    2 ++
>  1 file changed, 2 insertions(+)
> 
> Index: linux-2.6/include/acpi/pdc_intel.h
> ===================================================================
> --- linux-2.6.orig/include/acpi/pdc_intel.h	2009-01-20 16:11:20.000000000 -0800
> +++ linux-2.6/include/acpi/pdc_intel.h	2009-02-02 10:32:06.000000000 -0800
> @@ -14,6 +14,7 @@
>  #define ACPI_PDC_SMP_T_SWCOORD		(0x0080)
>  #define ACPI_PDC_C_C1_FFH		(0x0100)
>  #define ACPI_PDC_C_C2C3_FFH		(0x0200)
> +#define ACPI_PDC_SMP_P_HWCOORD		(0x0800)
>  
>  #define ACPI_PDC_EST_CAPABILITY_SMP	(ACPI_PDC_SMP_C1PT | \
>  					 ACPI_PDC_C_C1_HALT | \
> @@ -22,6 +23,7 @@
>  #define ACPI_PDC_EST_CAPABILITY_SWSMP	(ACPI_PDC_SMP_C1PT | \
>  					 ACPI_PDC_C_C1_HALT | \
>  					 ACPI_PDC_SMP_P_SWCOORD | \
> +					 ACPI_PDC_SMP_P_HWCOORD | \
>  					 ACPI_PDC_P_FFH)
>  
>  #define ACPI_PDC_C_CAPABILITY_SMP	(ACPI_PDC_SMP_C2C3  | \
> --
> To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [stable] [PATCH] Enable bit 11 in _PDC to advertise hw coord
  2009-02-04 20:40       ` Greg KH
@ 2009-02-08 19:51         ` Greg KH
  0 siblings, 0 replies; 7+ messages in thread
From: Greg KH @ 2009-02-08 19:51 UTC (permalink / raw)
  To: Greg KH
  Cc: Pallipadi, Venkatesh, linux-acpi@vger.kernel.org,
	Henrique de Moraes Holschuh, Jens Axboe, stable kernel,
	Chris Mason, Len Brown

On Wed, Feb 04, 2009 at 12:40:36PM -0800, Greg KH wrote:
> On Wed, Feb 04, 2009 at 12:06:42PM -0800, Pallipadi, Venkatesh wrote:
> > On Wed, 2009-02-04 at 11:53 -0800, Henrique de Moraes Holschuh wrote:
> > > On Wed, 04 Feb 2009, Jens Axboe wrote:
> > > > On Mon, Feb 02 2009, Pallipadi, Venkatesh wrote:
> > > > > 
> > > > > Bit 11 in intel PDC definitions is meant for OS capability to handle
> > > > > hardware coordination of P-states. In Linux we have always supported
> > > > > hwardware coordination of P-states. Just let the BIOSes know that we
> > > > > support it, by setting this bit.
> > > > > 
> > > > > Some BIOSes use this bit to choose between hardware or software coordination
> > > > > and without this change below, BIOSes switch to software coordination, which
> > > > > is not very optimal in terms of power consumption and extra wakeups from idle.
> > > > 
> > > > I can confirm that this fixes the excessive reschedule ipi count on an
> > > > x60 with the ondemand governor. Can we please get this into 2.6.29?
> > > 
> > > And, after that, -stable?
> > > 
> > 
> > Agreed. This should also go to -stable once it gets into mainline.
> 
> Can someone send stable@kernel.org the git commit id when it goes into
> Linus's tree?

It's d96f94c604453f87fe24154b87e1e9a3a72511f8, I got it now.

thanks,

greg k-h

^ permalink raw reply	[flat|nested] 7+ messages in thread

end of thread, other threads:[~2009-02-08 20:29 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2009-02-02 19:57 [PATCH] Enable bit 11 in _PDC to advertise hw coord Pallipadi, Venkatesh
2009-02-04  8:57 ` Jens Axboe
2009-02-04 19:53   ` Henrique de Moraes Holschuh
2009-02-04 20:06     ` Pallipadi, Venkatesh
2009-02-04 20:40       ` Greg KH
2009-02-08 19:51         ` [stable] " Greg KH
2009-02-07  4:10 ` Len Brown

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox