[PATCH][REPOST] Don't export sched_mc_power_savings on multi-socket single core system

[PATCH][REPOST] Don't export sched_mc_power_savings on multi-socket single core system

[Mahesh Jagannath Salgaonkar]

My previous post got lost somewhere in lkml list. Hence reposting this 
patch again.

Fix to prevent sched_mc_power_saving from being exported through sysfs
for multi-scoket single core system. Max cores should be always greater than
one (1). My earlier patch that introduced fix for not exporting
'sched_mc_power_saving' on laptops  broke it on multi-socket single core
system. This fix addresses issue on both laptop and multi-socket single 
core system.
Below are the Test results:

1. Single socket - multi-core
       Before Patch: Does not export 'sched_mc_power_saving'
       After Patch: Does not export 'sched_mc_power_saving'
       Result: Pass

2. Multi Socket - single core
      Before Patch: exports 'sched_mc_power_saving'
      After Patch: Does not export 'sched_mc_power_saving'
      Result: Pass

3. Multi Socket - Multi core
      Before Patch: exports 'sched_mc_power_saving'
      After Patch: exports 'sched_mc_power_saving'


Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>

Index: linux-2.6/arch/x86/include/asm/topology.h
===================================================================
--- linux-2.6.orig/arch/x86/include/asm/topology.h
+++ linux-2.6/arch/x86/include/asm/topology.h
@@ -203,7 +203,8 @@ struct pci_bus;
  void x86_pci_root_bus_res_quirks(struct pci_bus *b);

  #ifdef CONFIG_SMP
-#define mc_capable()	(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
+#define mc_capable()	(boot_cpu_data.x86_max_cores > 1) && \
+			(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
  #define smt_capable()			(smp_num_siblings > 1)
  #endif

Re: [PATCH][REPOST] Don't export sched_mc_power_savings on multi-socket single core system

[Ingo Molnar]

* Mahesh Jagannath Salgaonkar <mahesh@linux.vnet.ibm.com> wrote:

> My previous post got lost somewhere in lkml list. Hence reposting 
> this patch again.

no, it did not get lost, i gave you the feedback below more than a 
month ago. FYI, this resubmission has the same corrupted-patch 
problem.

	Ingo

----- Forwarded message from Ingo Molnar <mingo@elte.hu> -----

Date: Wed, 8 Apr 2009 13:42:03 +0200
From: Ingo Molnar <mingo@elte.hu>
To: Mahesh Jagannath Salgaonkar <mahesh@linux.vnet.ibm.com>
Subject: Re: [PATCH] Don't export sched_mc_power_savings on multi-socket
	single core system
Cc: Linux Kernel <linux-kernel@vger.kernel.org>,
	Suresh B Siddha <suresh.b.siddha@intel.com>,
	Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>,
	svaidy@linux.vnet.ibm.com, balbir@linux.vnet.ibm.com,
	dipankar@in.ibm.com, Peter Zijlstra <a.p.zijlstra@chello.nl>


* Mahesh Jagannath Salgaonkar <mahesh@linux.vnet.ibm.com> wrote:

> Fix to prevent sched_mc_power_saving from being exported through 
> sysfs for multi-scoket single core system. Max cores should be 
> always greater than one (1). My earlier patch that introduced fix 
> for not exporting 'sched_mc_power_saving' on laptops broke it on 
> multi-socket single core system. This fix addresses issue on both 
> laptop and multi-socket single core system. Below are the Test 
> results:

> +#define mc_capable()   (boot_cpu_data.x86_max_cores > 1) && \
> +                       (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
> #define smt_capable()                  (smp_num_siblings > 1)

patch looks good but is whitespace damaged (all tabs were converted 
to spaces). See Documentation/email-clients.txt about how to set up 
your client.

	Ingo

----- End forwarded message -----

Re: [PATCH][REPOST] Don't export sched_mc_power_savings onmulti-socket single core system

[Vaidyanathan Srinivasan]

* Ingo Molnar <mingo@elte.hu> [2009-05-11 14:35:29]:

> 
> * Mahesh Jagannath Salgaonkar <mahesh@linux.vnet.ibm.com> wrote:
> 
> > My previous post got lost somewhere in lkml list. Hence reposting 
> > this patch again.
> 
> no, it did not get lost, i gave you the feedback below more than a 
> month ago. FYI, this resubmission has the same corrupted-patch 
> problem.

Hi Ingo,

My copy of the [REPOST] seem to have tabs correct.  Anyways I have
added an extra parentheses also in the #define. Please check and
apply.

Thanks,
Vaidy

Don't export sched_mc_power_savings on multi-socket single core system

Fix to prevent sched_mc_power_saving from being exported through sysfs
for multi-scoket single core system. Max cores should be always greater than
one (1). My earlier patch that introduced fix for not exporting
'sched_mc_power_saving' on laptops  broke it on multi-socket single core
system. This fix addresses issue on both laptop and multi-socket single
core system.
Below are the Test results:

1. Single socket - multi-core
       Before Patch: Does not export 'sched_mc_power_saving'
       After Patch: Does not export 'sched_mc_power_saving'
       Result: Pass

2. Multi Socket - single core
      Before Patch: exports 'sched_mc_power_saving'
      After Patch: Does not export 'sched_mc_power_saving'
      Result: Pass

3. Multi Socket - Multi core
      Before Patch: exports 'sched_mc_power_saving'
      After Patch: exports 'sched_mc_power_saving'


Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---

 arch/x86/include/asm/topology.h |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)


diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index f44b49a..066ef59 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -203,7 +203,8 @@ struct pci_bus;
 void x86_pci_root_bus_res_quirks(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
-#define mc_capable()	(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
+#define mc_capable()	((boot_cpu_data.x86_max_cores > 1) && \
+			(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids))
 #define smt_capable()			(smp_num_siblings > 1)
 #endif
 

[tip:sched/core] sched: Don't export sched_mc_power_savings on multi-socket single core system

[tip-bot for Vaidyanathan Srinivasan]

Commit-ID:  33faf60cb97fee37b0e60a68c171f9099c576dec
Gitweb:     http://git.kernel.org/tip/33faf60cb97fee37b0e60a68c171f9099c576dec
Author:     Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
AuthorDate: Mon, 11 May 2009 20:09:14 +0530
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Mon, 11 May 2009 17:05:57 +0200

sched: Don't export sched_mc_power_savings on multi-socket single core system

Fix to prevent sched_mc_power_saving from being exported through sysfs
for multi-scoket single core system. Max cores should be always greater than
one (1). My earlier patch that introduced fix for not exporting
'sched_mc_power_saving' on laptops  broke it on multi-socket single core
system. This fix addresses issue on both laptop and multi-socket single
core system.
Below are the Test results:

1. Single socket - multi-core
       Before Patch: Does not export 'sched_mc_power_saving'
       After Patch: Does not export 'sched_mc_power_saving'
       Result: Pass

2. Multi Socket - single core
      Before Patch: exports 'sched_mc_power_saving'
      After Patch: Does not export 'sched_mc_power_saving'
      Result: Pass

3. Multi Socket - Multi core
      Before Patch: exports 'sched_mc_power_saving'
      After Patch: exports 'sched_mc_power_saving'

[ Impact: make the sched_mc_power_saving control available more consistently ]

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Suresh B Siddha <suresh.b.siddha@intel.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20090511143914.GB4853@dirshya.in.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 arch/x86/include/asm/topology.h |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index f44b49a..066ef59 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -203,7 +203,8 @@ struct pci_bus;
 void x86_pci_root_bus_res_quirks(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
-#define mc_capable()	(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
+#define mc_capable()	((boot_cpu_data.x86_max_cores > 1) && \
+			(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids))
 #define smt_capable()			(smp_num_siblings > 1)
 #endif
 

[tip:sched/core] sched: Don't export sched_mc_power_savings on multi-socket single core system

[tip-bot for Vaidyanathan Srinivasan]

Commit-ID:  2ff799d3cff1ecb274049378b28120ee5c1c5e5f
Gitweb:     http://git.kernel.org/tip/2ff799d3cff1ecb274049378b28120ee5c1c5e5f
Author:     Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
AuthorDate: Mon, 11 May 2009 20:09:14 +0530
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Mon, 11 May 2009 23:57:56 +0200

sched: Don't export sched_mc_power_savings on multi-socket single core system

Fix to prevent sched_mc_power_saving from being exported through sysfs
for multi-scoket single core system. Max cores should be always greater than
one (1). My earlier patch that introduced fix for not exporting
'sched_mc_power_saving' on laptops  broke it on multi-socket single core
system. This fix addresses issue on both laptop and multi-socket single
core system.
Below are the Test results:

1. Single socket - multi-core
       Before Patch: Does not export 'sched_mc_power_saving'
       After Patch: Does not export 'sched_mc_power_saving'
       Result: Pass

2. Multi Socket - single core
      Before Patch: exports 'sched_mc_power_saving'
      After Patch: Does not export 'sched_mc_power_saving'
      Result: Pass

3. Multi Socket - Multi core
      Before Patch: exports 'sched_mc_power_saving'
      After Patch: exports 'sched_mc_power_saving'

[ Impact: make the sched_mc_power_saving control available more consistently ]

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Suresh B Siddha <suresh.b.siddha@intel.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20090511143914.GB4853@dirshya.in.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 arch/x86/include/asm/topology.h |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index f44b49a..066ef59 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -203,7 +203,8 @@ struct pci_bus;
 void x86_pci_root_bus_res_quirks(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
-#define mc_capable()	(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
+#define mc_capable()	((boot_cpu_data.x86_max_cores > 1) && \
+			(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids))
 #define smt_capable()			(smp_num_siblings > 1)
 #endif