diff mbox series

[SRU,jammy:linux] cpufreq: intel_pstate: Enable HWP IO boost for all servers

Message ID 20240209173328.322721-1-philip.cox@canonical.com
State New
Headers show
Series [SRU,jammy:linux] cpufreq: intel_pstate: Enable HWP IO boost for all servers | expand

Commit Message

Philip Cox Feb. 9, 2024, 5:33 p.m. UTC 
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>

BugLink: https://bugs.launchpad.net/bugs/2052817

The HWP IO boost results in slight improvements for IO performance on
both Ice Lake and Sapphire Rapid servers.

Currently there is a CPU model check for Skylake desktop and server along
with the ACPI PM profile for performance and enterprise servers to enable
IO boost.

Remove the CPU model check, so that all current server models enable HWP
IO boost by default.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
(cherry picked from commit 1f5e62f5fb217f2c1e003236be7d03cf606c26c4)
Signed-off-by: Philip Cox <philip.cox@canonical.com>
---
 drivers/cpufreq/intel_pstate.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

Comments

Andrei Gherzan Feb. 12, 2024, 11:46 a.m. UTC | #1 
On 24/02/09 12:33PM, Philip Cox wrote:
> From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
> 
> BugLink: https://bugs.launchpad.net/bugs/2052817
> 
> The HWP IO boost results in slight improvements for IO performance on
> both Ice Lake and Sapphire Rapid servers.
> 
> Currently there is a CPU model check for Skylake desktop and server along
> with the ACPI PM profile for performance and enterprise servers to enable
> IO boost.
> 
> Remove the CPU model check, so that all current server models enable HWP
> IO boost by default.
> 
> Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> (cherry picked from commit 1f5e62f5fb217f2c1e003236be7d03cf606c26c4)
> Signed-off-by: Philip Cox <philip.cox@canonical.com>
> ---
>  drivers/cpufreq/intel_pstate.c | 11 +----------
>  1 file changed, 1 insertion(+), 10 deletions(-)
> 
> diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
> index 7cd614a803a1..c54c1fcfb7a5 100644
> --- a/drivers/cpufreq/intel_pstate.c
> +++ b/drivers/cpufreq/intel_pstate.c
> @@ -2281,12 +2281,6 @@ static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
>  	{}
>  };
>  
> -static const struct x86_cpu_id intel_pstate_hwp_boost_ids[] = {
> -	X86_MATCH(SKYLAKE_X,		core_funcs),
> -	X86_MATCH(SKYLAKE,		core_funcs),
> -	{}
> -};
> -
>  static int intel_pstate_init_cpu(unsigned int cpunum)
>  {
>  	struct cpudata *cpu;
> @@ -2305,12 +2299,9 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
>  		cpu->epp_default = -EINVAL;
>  
>  		if (hwp_active) {
> -			const struct x86_cpu_id *id;
> -
>  			intel_pstate_hwp_enable(cpu);
>  
> -			id = x86_match_cpu(intel_pstate_hwp_boost_ids);
> -			if (id && intel_pstate_acpi_pm_profile_server())
> +			if (intel_pstate_acpi_pm_profile_server())
>  				hwp_boost = true;
>  		}
>  	} else if (hwp_active) {

I know that this is a clean cherry-pick, and it does look alright -
patch-wise. Even so, I still consider that a cover letter would be
minimum friction and in line with our contribution guidelines.

Again, patch looks good to me so:

Acked-by: Andrei Gherzan <andrei.gherzan@canonical.com>
Thibault Ferrante Feb. 13, 2024, 11:30 a.m. UTC | #2 
Acked-by: Thibault Ferrante <thibault.ferrante@canonical.com>


On 09-02-2024 18:33, Philip Cox wrote:
> From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
> 
> BugLink: https://bugs.launchpad.net/bugs/2052817
> 
> The HWP IO boost results in slight improvements for IO performance on
> both Ice Lake and Sapphire Rapid servers.
> 
> Currently there is a CPU model check for Skylake desktop and server along
> with the ACPI PM profile for performance and enterprise servers to enable
> IO boost.
> 
> Remove the CPU model check, so that all current server models enable HWP
> IO boost by default.
> 
> Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> (cherry picked from commit 1f5e62f5fb217f2c1e003236be7d03cf606c26c4)
> Signed-off-by: Philip Cox <philip.cox@canonical.com>
> ---
>   drivers/cpufreq/intel_pstate.c | 11 +----------
>   1 file changed, 1 insertion(+), 10 deletions(-)
> 
> diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
> index 7cd614a803a1..c54c1fcfb7a5 100644
> --- a/drivers/cpufreq/intel_pstate.c
> +++ b/drivers/cpufreq/intel_pstate.c
> @@ -2281,12 +2281,6 @@ static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
>   	{}
>   };
>   
> -static const struct x86_cpu_id intel_pstate_hwp_boost_ids[] = {
> -	X86_MATCH(SKYLAKE_X,		core_funcs),
> -	X86_MATCH(SKYLAKE,		core_funcs),
> -	{}
> -};
> -
>   static int intel_pstate_init_cpu(unsigned int cpunum)
>   {
>   	struct cpudata *cpu;
> @@ -2305,12 +2299,9 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
>   		cpu->epp_default = -EINVAL;
>   
>   		if (hwp_active) {
> -			const struct x86_cpu_id *id;
> -
>   			intel_pstate_hwp_enable(cpu);
>   
> -			id = x86_match_cpu(intel_pstate_hwp_boost_ids);
> -			if (id && intel_pstate_acpi_pm_profile_server())
> +			if (intel_pstate_acpi_pm_profile_server())
>   				hwp_boost = true;
>   		}
>   	} else if (hwp_active) {
Stefan Bader Feb. 19, 2024, 11:10 a.m. UTC | #3 
On 09.02.24 18:33, Philip Cox wrote:
> From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
> 
> BugLink: https://bugs.launchpad.net/bugs/2052817
> 
> The HWP IO boost results in slight improvements for IO performance on
> both Ice Lake and Sapphire Rapid servers.
> 
> Currently there is a CPU model check for Skylake desktop and server along
> with the ACPI PM profile for performance and enterprise servers to enable
> IO boost.
> 
> Remove the CPU model check, so that all current server models enable HWP
> IO boost by default.
> 
> Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> (cherry picked from commit 1f5e62f5fb217f2c1e003236be7d03cf606c26c4)
> Signed-off-by: Philip Cox <philip.cox@canonical.com>
> ---

Applied to jammy:linux/master-next. Thanks.

-Stefan

>   drivers/cpufreq/intel_pstate.c | 11 +----------
>   1 file changed, 1 insertion(+), 10 deletions(-)
> 
> diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
> index 7cd614a803a1..c54c1fcfb7a5 100644
> --- a/drivers/cpufreq/intel_pstate.c
> +++ b/drivers/cpufreq/intel_pstate.c
> @@ -2281,12 +2281,6 @@ static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
>   	{}
>   };
>   
> -static const struct x86_cpu_id intel_pstate_hwp_boost_ids[] = {
> -	X86_MATCH(SKYLAKE_X,		core_funcs),
> -	X86_MATCH(SKYLAKE,		core_funcs),
> -	{}
> -};
> -
>   static int intel_pstate_init_cpu(unsigned int cpunum)
>   {
>   	struct cpudata *cpu;
> @@ -2305,12 +2299,9 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
>   		cpu->epp_default = -EINVAL;
>   
>   		if (hwp_active) {
> -			const struct x86_cpu_id *id;
> -
>   			intel_pstate_hwp_enable(cpu);
>   
> -			id = x86_match_cpu(intel_pstate_hwp_boost_ids);
> -			if (id && intel_pstate_acpi_pm_profile_server())
> +			if (intel_pstate_acpi_pm_profile_server())
>   				hwp_boost = true;
>   		}
>   	} else if (hwp_active) {
diff mbox series

Patch

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 7cd614a803a1..c54c1fcfb7a5 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2281,12 +2281,6 @@  static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
 	{}
 };
 
-static const struct x86_cpu_id intel_pstate_hwp_boost_ids[] = {
-	X86_MATCH(SKYLAKE_X,		core_funcs),
-	X86_MATCH(SKYLAKE,		core_funcs),
-	{}
-};
-
 static int intel_pstate_init_cpu(unsigned int cpunum)
 {
 	struct cpudata *cpu;
@@ -2305,12 +2299,9 @@  static int intel_pstate_init_cpu(unsigned int cpunum)
 		cpu->epp_default = -EINVAL;
 
 		if (hwp_active) {
-			const struct x86_cpu_id *id;
-
 			intel_pstate_hwp_enable(cpu);
 
-			id = x86_match_cpu(intel_pstate_hwp_boost_ids);
-			if (id && intel_pstate_acpi_pm_profile_server())
+			if (intel_pstate_acpi_pm_profile_server())
 				hwp_boost = true;
 		}
 	} else if (hwp_active) {