[PATCH] cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode

[PATCH] cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode

[Srinivas Pandruvada]

When turbo mode is unavailable on a Skylake-X system, executing the
command:
"echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo"
results in an unchecked MSR access error: WRMSR to 0x199
(attempted to write 0x0000000100001300).

This issue was reproduced on an OEM (Original Equipment Manufacturer)
system and is not a common problem across all Skylake-X systems.

This error occurs because the MSR 0x199 Turbo Engage Bit (bit 32) is set
when turbo mode is disabled. The issue arises when intel_pstate fails to
detect that turbo mode is disabled. Here intel_pstate relies on
MSR_IA32_MISC_ENABLE bit 38 to determine the status of turbo mode.
However, on this system, bit 38 is not set even when turbo mode is
disabled.

According to the Intel Software Developer's Manual (SDM), the BIOS sets
this bit during platform initialization to enable or disable
opportunistic processor performance operations. Logically, this bit
should be set in such cases. However, the SDM also specifies that "OS and
applications must use CPUID leaf 06H to detect processors with
opportunistic processor performance operations enabled."

Therefore, in addition to checking MSR_IA32_MISC_ENABLE bit 38, verify
that CPUID.06H:EAX[1] is 0 to accurately determine if turbo mode is
disabled.

Fixes: 4521e1a0ce17 ("cpufreq: intel_pstate: Reflect current no_turbo state correctly")
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: stable@vger.kernel.org
---
 drivers/cpufreq/intel_pstate.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index f41ed0b9e610..ba9bf06f1c77 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -598,6 +598,9 @@ static bool turbo_is_disabled(void)
 {
 	u64 misc_en;
 
+	if (!cpu_feature_enabled(X86_FEATURE_IDA))
+		return true;
+
 	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
 
 	return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
-- 
2.48.1

Re: [PATCH] cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode

[Rafael J. Wysocki]

On Tue, Apr 29, 2025 at 11:07 PM Srinivas Pandruvada
<srinivas.pandruvada@linux.intel.com> wrote:
>
> When turbo mode is unavailable on a Skylake-X system, executing the
> command:
> "echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo"
> results in an unchecked MSR access error: WRMSR to 0x199
> (attempted to write 0x0000000100001300).
>
> This issue was reproduced on an OEM (Original Equipment Manufacturer)
> system and is not a common problem across all Skylake-X systems.
>
> This error occurs because the MSR 0x199 Turbo Engage Bit (bit 32) is set
> when turbo mode is disabled. The issue arises when intel_pstate fails to
> detect that turbo mode is disabled. Here intel_pstate relies on
> MSR_IA32_MISC_ENABLE bit 38 to determine the status of turbo mode.
> However, on this system, bit 38 is not set even when turbo mode is
> disabled.
>
> According to the Intel Software Developer's Manual (SDM), the BIOS sets
> this bit during platform initialization to enable or disable
> opportunistic processor performance operations. Logically, this bit
> should be set in such cases. However, the SDM also specifies that "OS and
> applications must use CPUID leaf 06H to detect processors with
> opportunistic processor performance operations enabled."
>
> Therefore, in addition to checking MSR_IA32_MISC_ENABLE bit 38, verify
> that CPUID.06H:EAX[1] is 0 to accurately determine if turbo mode is
> disabled.
>
> Fixes: 4521e1a0ce17 ("cpufreq: intel_pstate: Reflect current no_turbo state correctly")
> Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
> Cc: stable@vger.kernel.org
> ---
>  drivers/cpufreq/intel_pstate.c | 3 +++
>  1 file changed, 3 insertions(+)
>
> diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
> index f41ed0b9e610..ba9bf06f1c77 100644
> --- a/drivers/cpufreq/intel_pstate.c
> +++ b/drivers/cpufreq/intel_pstate.c
> @@ -598,6 +598,9 @@ static bool turbo_is_disabled(void)
>  {
>         u64 misc_en;
>
> +       if (!cpu_feature_enabled(X86_FEATURE_IDA))
> +               return true;
> +
>         rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
>
>         return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
> --

Applied as a fix for 6.15-rc, thanks!

[REGRESSION] Intel Turbo Boost stuck disabled on some Clevo machines (was: [PATCH] cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode)

[Aaron Rainbolt]

On Wed, 30 Apr 2025 16:29:09 +0200
"Rafael J. Wysocki" <rafael@kernel.org> wrote:

> On Tue, Apr 29, 2025 at 11:07 PM Srinivas Pandruvada
> <srinivas.pandruvada@linux.intel.com> wrote:
> >
> > When turbo mode is unavailable on a Skylake-X system, executing the
> > command:
> > "echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo"
> > results in an unchecked MSR access error: WRMSR to 0x199
> > (attempted to write 0x0000000100001300).
> >
> > This issue was reproduced on an OEM (Original Equipment
> > Manufacturer) system and is not a common problem across all
> > Skylake-X systems.
> >
> > This error occurs because the MSR 0x199 Turbo Engage Bit (bit 32)
> > is set when turbo mode is disabled. The issue arises when
> > intel_pstate fails to detect that turbo mode is disabled. Here
> > intel_pstate relies on MSR_IA32_MISC_ENABLE bit 38 to determine the
> > status of turbo mode. However, on this system, bit 38 is not set
> > even when turbo mode is disabled.
> >
> > According to the Intel Software Developer's Manual (SDM), the BIOS
> > sets this bit during platform initialization to enable or disable
> > opportunistic processor performance operations. Logically, this bit
> > should be set in such cases. However, the SDM also specifies that
> > "OS and applications must use CPUID leaf 06H to detect processors
> > with opportunistic processor performance operations enabled."
> >
> > Therefore, in addition to checking MSR_IA32_MISC_ENABLE bit 38,
> > verify that CPUID.06H:EAX[1] is 0 to accurately determine if turbo
> > mode is disabled.
> >
> > Fixes: 4521e1a0ce17 ("cpufreq: intel_pstate: Reflect current
> > no_turbo state correctly") Signed-off-by: Srinivas Pandruvada
> > <srinivas.pandruvada@linux.intel.com> Cc: stable@vger.kernel.org
> > ---
> >  drivers/cpufreq/intel_pstate.c | 3 +++
> >  1 file changed, 3 insertions(+)
> >
> > diff --git a/drivers/cpufreq/intel_pstate.c
> > b/drivers/cpufreq/intel_pstate.c index f41ed0b9e610..ba9bf06f1c77
> > 100644 --- a/drivers/cpufreq/intel_pstate.c
> > +++ b/drivers/cpufreq/intel_pstate.c
> > @@ -598,6 +598,9 @@ static bool turbo_is_disabled(void)
> >  {
> >         u64 misc_en;
> >
> > +       if (!cpu_feature_enabled(X86_FEATURE_IDA))
> > +               return true;
> > +
> >         rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
> >
> >         return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
> > --  
> 
> Applied as a fix for 6.15-rc, thanks!
> 

FYI, this seems to have broken turbo boost on some Clevo systems with
an Intel Core i9-14900HX CPU. These CPUs obviously support turbo boost,
and kernels without this commit have turbo boost working properly, but
after this commit turbo boost is stuck disabled and cannot be
enabled by writing to /sys/devices/system/cpu/intel_pstate/no_turbo. I
made a bug report about this against Ubuntu's kernel at [1], which is
the only report I know that is able to point to this commit as having
broken things. However, it looks like an Arch Linux user [2] and a
Gentoo user [3] are running into the same thing.

[1] https://bugs.launchpad.net/ubuntu/+source/linux-hwe-6.14/+bug/2122531

[2] https://bbs.archlinux.org/viewtopic.php?id=305564

[3] https://forums.gentoo.org/viewtopic-p-8866128.html?sid=e97619cff0d9c79c2eea2cfe8f60b0d3

Re: [REGRESSION] Intel Turbo Boost stuck disabled on some Clevo machines (was: [PATCH] cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode)

[srinivas pandruvada]

On Wed, 2025-09-10 at 11:36 -0500, Aaron Rainbolt wrote:
> On Wed, 30 Apr 2025 16:29:09 +0200
> "Rafael J. Wysocki" <rafael@kernel.org> wrote:
> 
> > On Tue, Apr 29, 2025 at 11:07 PM Srinivas Pandruvada
> > <srinivas.pandruvada@linux.intel.com> wrote:
> > > 
> > > When turbo mode is unavailable on a Skylake-X system, executing
> > > the
> > > command:
> > > "echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo"
> > > results in an unchecked MSR access error: WRMSR to 0x199
> > > (attempted to write 0x0000000100001300).
> > > 
> > > This issue was reproduced on an OEM (Original Equipment
> > > Manufacturer) system and is not a common problem across all
> > > Skylake-X systems.
> > > 
> > > This error occurs because the MSR 0x199 Turbo Engage Bit (bit 32)
> > > is set when turbo mode is disabled. The issue arises when
> > > intel_pstate fails to detect that turbo mode is disabled. Here
> > > intel_pstate relies on MSR_IA32_MISC_ENABLE bit 38 to determine
> > > the
> > > status of turbo mode. However, on this system, bit 38 is not set
> > > even when turbo mode is disabled.
> > > 
> > > According to the Intel Software Developer's Manual (SDM), the
> > > BIOS
> > > sets this bit during platform initialization to enable or disable
> > > opportunistic processor performance operations. Logically, this
> > > bit
> > > should be set in such cases. However, the SDM also specifies that
> > > "OS and applications must use CPUID leaf 06H to detect processors
> > > with opportunistic processor performance operations enabled."
> > > 
> > > Therefore, in addition to checking MSR_IA32_MISC_ENABLE bit 38,
> > > verify that CPUID.06H:EAX[1] is 0 to accurately determine if
> > > turbo
> > > mode is disabled.
> > > 
> > > Fixes: 4521e1a0ce17 ("cpufreq: intel_pstate: Reflect current
> > > no_turbo state correctly") Signed-off-by: Srinivas Pandruvada
> > > <srinivas.pandruvada@linux.intel.com> Cc: stable@vger.kernel.org
> > > ---
> > >  drivers/cpufreq/intel_pstate.c | 3 +++
> > >  1 file changed, 3 insertions(+)
> > > 
> > > diff --git a/drivers/cpufreq/intel_pstate.c
> > > b/drivers/cpufreq/intel_pstate.c index f41ed0b9e610..ba9bf06f1c77
> > > 100644 --- a/drivers/cpufreq/intel_pstate.c
> > > +++ b/drivers/cpufreq/intel_pstate.c
> > > @@ -598,6 +598,9 @@ static bool turbo_is_disabled(void)
> > >  {
> > >         u64 misc_en;
> > > 
> > > +       if (!cpu_feature_enabled(X86_FEATURE_IDA))
> > > +               return true;
> > > +
> > >         rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
> > > 
> > >         return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
> > > --  
> > 
> > Applied as a fix for 6.15-rc, thanks!
> > 
> 
> FYI, this seems to have broken turbo boost on some Clevo systems with
> an Intel Core i9-14900HX CPU. These CPUs obviously support turbo
> boost,
> and kernels without this commit have turbo boost working properly,
> but
> after this commit turbo boost is stuck disabled and cannot be
> enabled by writing to /sys/devices/system/cpu/intel_pstate/no_turbo.
> I
> made a bug report about this against Ubuntu's kernel at [1], which is
> the only report I know that is able to point to this commit as having
> broken things. However, it looks like an Arch Linux user [2] and a
> Gentoo user [3] are running into the same thing.
> 

As the bug report suggested, the system boots with no turbo, it must be
forcefully turned ON by writing to this attribute.
I wonder if there is a BIOS option to turn ON turbo on this system?

This processor itself is capable of up to 5.8 GHz turbo.


I will try to find contact at Clevo.

We can try to reduce scope of this change to non HWP only where there
is unchecked MSR issue.

Thanks,
Srinivas

> [1]
> https://bugs.launchpad.net/ubuntu/+source/linux-hwe-6.14/+bug/2122531
> 
> [2] https://bbs.archlinux.org/viewtopic.php?id=305564
> 
> [3]
> https://forums.gentoo.org/viewtopic-p-8866128.html?sid=e97619cff0d9c79c2eea2cfe8f60b0d3

Re: [REGRESSION] Intel Turbo Boost stuck disabled on some Clevo machines (was: [PATCH] cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode)

[Aaron Rainbolt]

On Wed, 10 Sep 2025 10:15:00 -0700
srinivas pandruvada <srinivas.pandruvada@linux.intel.com> wrote:

> On Wed, 2025-09-10 at 11:36 -0500, Aaron Rainbolt wrote:
> > On Wed, 30 Apr 2025 16:29:09 +0200
> > "Rafael J. Wysocki" <rafael@kernel.org> wrote:
> >   
> > > On Tue, Apr 29, 2025 at 11:07 PM Srinivas Pandruvada
> > > <srinivas.pandruvada@linux.intel.com> wrote:  
> > > > 
> > > > When turbo mode is unavailable on a Skylake-X system, executing
> > > > the
> > > > command:
> > > > "echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo"
> > > > results in an unchecked MSR access error: WRMSR to 0x199
> > > > (attempted to write 0x0000000100001300).
> > > > 
> > > > This issue was reproduced on an OEM (Original Equipment
> > > > Manufacturer) system and is not a common problem across all
> > > > Skylake-X systems.
> > > > 
> > > > This error occurs because the MSR 0x199 Turbo Engage Bit (bit
> > > > 32) is set when turbo mode is disabled. The issue arises when
> > > > intel_pstate fails to detect that turbo mode is disabled. Here
> > > > intel_pstate relies on MSR_IA32_MISC_ENABLE bit 38 to determine
> > > > the
> > > > status of turbo mode. However, on this system, bit 38 is not set
> > > > even when turbo mode is disabled.
> > > > 
> > > > According to the Intel Software Developer's Manual (SDM), the
> > > > BIOS
> > > > sets this bit during platform initialization to enable or
> > > > disable opportunistic processor performance operations.
> > > > Logically, this bit
> > > > should be set in such cases. However, the SDM also specifies
> > > > that "OS and applications must use CPUID leaf 06H to detect
> > > > processors with opportunistic processor performance operations
> > > > enabled."
> > > > 
> > > > Therefore, in addition to checking MSR_IA32_MISC_ENABLE bit 38,
> > > > verify that CPUID.06H:EAX[1] is 0 to accurately determine if
> > > > turbo
> > > > mode is disabled.
> > > > 
> > > > Fixes: 4521e1a0ce17 ("cpufreq: intel_pstate: Reflect current
> > > > no_turbo state correctly") Signed-off-by: Srinivas Pandruvada
> > > > <srinivas.pandruvada@linux.intel.com> Cc: stable@vger.kernel.org
> > > > ---
> > > >  drivers/cpufreq/intel_pstate.c | 3 +++
> > > >  1 file changed, 3 insertions(+)
> > > > 
> > > > diff --git a/drivers/cpufreq/intel_pstate.c
> > > > b/drivers/cpufreq/intel_pstate.c index
> > > > f41ed0b9e610..ba9bf06f1c77 100644 ---
> > > > a/drivers/cpufreq/intel_pstate.c +++
> > > > b/drivers/cpufreq/intel_pstate.c @@ -598,6 +598,9 @@ static
> > > > bool turbo_is_disabled(void) {
> > > >         u64 misc_en;
> > > > 
> > > > +       if (!cpu_feature_enabled(X86_FEATURE_IDA))
> > > > +               return true;
> > > > +
> > > >         rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
> > > > 
> > > >         return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
> > > > --    
> > > 
> > > Applied as a fix for 6.15-rc, thanks!
> > >   
> > 
> > FYI, this seems to have broken turbo boost on some Clevo systems
> > with an Intel Core i9-14900HX CPU. These CPUs obviously support
> > turbo boost,
> > and kernels without this commit have turbo boost working properly,
> > but
> > after this commit turbo boost is stuck disabled and cannot be
> > enabled by writing to /sys/devices/system/cpu/intel_pstate/no_turbo.
> > I
> > made a bug report about this against Ubuntu's kernel at [1], which
> > is the only report I know that is able to point to this commit as
> > having broken things. However, it looks like an Arch Linux user [2]
> > and a Gentoo user [3] are running into the same thing.
> >   
> 
> As the bug report suggested, the system boots with no turbo, it must
> be forcefully turned ON by writing to this attribute.
> I wonder if there is a BIOS option to turn ON turbo on this system?

I just double-checked the BIOS settings, there does not appear to be
any setting related to turbo boost there. The closest there is, is
overclocking settings, which comes with warnings about possibly causing
the system to become unbootable, thus I think those settings are for
true overclocking and not turbo boost.

> This processor itself is capable of up to 5.8 GHz turbo.
> 
> 
> I will try to find contact at Clevo.
> 
> We can try to reduce scope of this change to non HWP only where there
> is unchecked MSR issue.

That sounds like a good idea to me.

> Thanks,
> Srinivas
> 
> > [1]
> > https://bugs.launchpad.net/ubuntu/+source/linux-hwe-6.14/+bug/2122531
> > 
> > [2] https://bbs.archlinux.org/viewtopic.php?id=305564
> > 
> > [3]
> > https://forums.gentoo.org/viewtopic-p-8866128.html?sid=e97619cff0d9c79c2eea2cfe8f60b0d3
> >  
> 

Re: [REGRESSION] Intel Turbo Boost stuck disabled on some Clevo machines (was: [PATCH] cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode)

[srinivas pandruvada]

[-- Attachment #1: Type: text/plain, Size: 873 bytes --]

Hi Aaron,

On Wed, 2025-09-10 at 15:33 -0500, Aaron Rainbolt wrote:
> On Wed, 10 Sep 2025 10:15:00 -0700
> srinivas pandruvada <srinivas.pandruvada@linux.intel.com> wrote:
> 
> > On Wed, 2025-09-10 at 11:36 -0500, Aaron Rainbolt wrote:
> > > On Wed, 30 Apr 2025 16:29:09 +0200
> > > "Rafael J. Wysocki" <rafael@kernel.org> wrote:
> > >   
> > > > On Tue, Apr 29, 2025 at 11:07 PM Srinivas Pandruvada
> > > > <srinivas.pandruvada@linux.intel.com> wrote:  
> > > > > 
> > > > > When turbo mode is unavailable on a Skylake-X system,
> > > > > executing
> > > > > the
> > > > > command:
> > > > > "echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo"
> > > > > results in an unchecked MSR access error: WRMSR to 0x199
> > > > > (attempted to write 0x0000000100001300).
Please try the attached patch, if this address this issue.

Thanks,
Srinivas

[-- Attachment #2: 0001-cpufreq-intel_pstate-Reevaluate-IDA-presence-on-no_t.patch --]
[-- Type: text/x-patch, Size: 1494 bytes --]

From 405d27e871f7bc85a786f84877a35da54c813b39 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Wed, 5 Nov 2025 09:57:03 -0800
Subject: [PATCH] cpufreq: intel_pstate: Reevaluate IDA presence on no_turbo
 attribute change

If hardware disabled IDA (Intel Dynamic Acceleration technology) feature
before OS boot, turbo mode support will be disabled permanently. In this
case CPUID.06H: EAX[1] reports 0 and attribute
"/sys/devices/system/cpu/intel_pstate/no_turbo" will show "1" and status
can't be changed to "0".

When no_turbo is written with 0, in this case evaluate CPUID.06H: EAX[1]
again. If the feature status is changed to 1 post OS boot then allow to
enable turbo mode.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
---
 drivers/cpufreq/intel_pstate.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 43e847e9f741..0ec45a610b45 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -596,10 +596,15 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu)
 
 static bool turbo_is_disabled(void)
 {
+	unsigned int eax, ebx, ecx, edx;
 	u64 misc_en;
 
-	if (!cpu_feature_enabled(X86_FEATURE_IDA))
+	eax = 0;
+	cpuid(6, &eax, &ebx, &ecx, &edx);
+	if (!(eax & BIT(1))) {
+		pr_info("Turbo is disabled\n");
 		return true;
+	}
 
 	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
 
-- 
2.43.0

Re: [REGRESSION] Intel Turbo Boost stuck disabled on some Clevo machines (was: [PATCH] cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode)

[Aaron Rainbolt]

On Thu, 06 Nov 2025 07:23:14 -0800
srinivas pandruvada <srinivas.pandruvada@linux.intel.com> wrote:

> Hi Aaron,
> 
> On Wed, 2025-09-10 at 15:33 -0500, Aaron Rainbolt wrote:
> > On Wed, 10 Sep 2025 10:15:00 -0700
> > srinivas pandruvada <srinivas.pandruvada@linux.intel.com> wrote:
> >   
> > > On Wed, 2025-09-10 at 11:36 -0500, Aaron Rainbolt wrote:  
> > > > On Wed, 30 Apr 2025 16:29:09 +0200
> > > > "Rafael J. Wysocki" <rafael@kernel.org> wrote:
> > > >     
> > > > > On Tue, Apr 29, 2025 at 11:07 PM Srinivas Pandruvada
> > > > > <srinivas.pandruvada@linux.intel.com> wrote:    
> > > > > > 
> > > > > > When turbo mode is unavailable on a Skylake-X system,
> > > > > > executing
> > > > > > the
> > > > > > command:
> > > > > > "echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo"
> > > > > > results in an unchecked MSR access error: WRMSR to 0x199
> > > > > > (attempted to write 0x0000000100001300).  
> Please try the attached patch, if this address this issue.

I can confirm that this patch does resolve the issue when applied to
Kubuntu Focus's 6.14 kernel. CPU frequencies are available that require
turbo boost, and `cat /sys/devices/system/cpu/intel_pstate` returns
`0`. The logs from `dmesg` also indicate that turbo was disabled
earlier in boot, but the warnings about turbo being disabled stop
appearing later on, even when manipulating the `no_turbo` file:

[   25.893012] intel_pstate: Turbo is disabled
[   25.893019] intel_pstate: Turbo disabled by BIOS or unavailable on processor
[   25.950587] NET: Registered PF_QIPCRTR protocol family
[   26.599013] Realtek Internal NBASE-T PHY r8169-0-6c00:00: attached PHY driver (mii_bus:phy_addr=r8169-0-6c00:00, irq=MAC)
[   26.725959] ACPI BIOS Error (bug): Could not resolve symbol [\_TZ.ETMD], AE_NOT_FOUND (20240827/psargs-332)

[   26.725976] No Local Variables are initialized for Method [_OSC]

[   26.725978] Initialized Arguments for Method [_OSC]:  (4 arguments defined for method invocation)
[   26.725979]   Arg0:   0000000030ddf166 <Obj>           Buffer(16) 5D A8 3B B2 B7 C8 42 35
[   26.725991]   Arg1:   0000000002bd3ac4 <Obj>           Integer 0000000000000001
[   26.725996]   Arg2:   0000000033eb047e <Obj>           Integer 0000000000000002
[   26.725999]   Arg3:   00000000de6cf5f1 <Obj>           Buffer(8) 00 00 00 00 05 00 00 00

[   26.726010] ACPI Error: Aborting method \_SB.IETM._OSC due to previous error (AE_NOT_FOUND) (20240827/psparse-529)
[   26.726056] Consider using thermal netlink events interface
[   26.769209] r8169 0000:6c:00.0 enp108s0: Link is Down
[   26.857318] zram0: detected capacity change from 0 to 195035136
[   26.864390] vboxdrv: Found 32 processor cores/threads
[   26.873227] Adding 97517564k swap on /dev/zram0.  Priority:-2 extents:1 across:97517564k SS
[   26.880588] vboxdrv: TSC mode is Invariant, tentative frequency 2419194640 Hz
[   26.880592] vboxdrv: Successfully loaded version 7.2.4 r170995 (interface 0x00340001)
[   26.895725] intel_pstate: Turbo is disabled
[   26.895730] intel_pstate: Turbo disabled by BIOS or unavailable on processor
[   26.943715] iwlwifi 0000:00:14.3: WFPM_UMAC_PD_NOTIFICATION: 0x20
[   26.943746] iwlwifi 0000:00:14.3: WFPM_LMAC2_PD_NOTIFICATION: 0x1f
[   26.943755] iwlwifi 0000:00:14.3: WFPM_AUTH_KEY_0: 0x90
[   26.943765] iwlwifi 0000:00:14.3: CNVI_SCU_SEQ_DATA_DW9: 0x0
[   26.944901] iwlwifi 0000:00:14.3: RFIm is deactivated, reason = 5
[   27.045437] iwlwifi 0000:00:14.3: Registered PHC clock: iwlwifi-PTP, with index: 0
[   27.098590] VBoxNetFlt: Successfully started.
[   27.101687] VBoxNetAdp: Successfully started.
[   27.153602] bridge: filtering via arp/ip/ip6tables is no longer available by default. Update your scripts to load br_netfilter if you need this.
[   27.851014] loop14: detected capacity change from 0 to 8
[   27.895706] r8169 0000:6c:00.0: invalid VPD tag 0xff (size 0) at offset 0; assume missing optional EEPROM
[   28.898015] intel_pstate: Turbo is disabled
[   28.898021] intel_pstate: Turbo disabled by BIOS or unavailable on processor
[   31.900781] intel_pstate: Turbo is disabled
[   31.900788] intel_pstate: Turbo disabled by BIOS or unavailable on processor
[   33.959448] Bluetooth: RFCOMM TTY layer initialized
[   33.959456] Bluetooth: RFCOMM socket layer initialized
[   33.959462] Bluetooth: RFCOMM ver 1.11
[   36.903768] intel_pstate: Turbo is disabled
[   36.903777] intel_pstate: Turbo disabled by BIOS or unavailable on processor
[   38.054345] systemd-journald[883]: /var/log/journal/a9e8e3d2041547169b107e1e1a23f2ce/user-1000.journal: Journal file uses a different sequence number ID, rotating.
[   39.799560] warning: `kded5' uses wireless extensions which will stop working for Wi-Fi 7 hardware; use nl80211
[   40.884365] wlp0s20f3: authenticate with 18:ee:86:8b:16:a2 (local address=98:bd:80:8a:e9:27)
[   40.885147] wlp0s20f3: send auth to 18:ee:86:8b:16:a2 (try 1/3)
[   40.968595] wlp0s20f3: authenticate with 18:ee:86:8b:16:a2 (local address=98:bd:80:8a:e9:27)
[   40.968603] wlp0s20f3: send auth to 18:ee:86:8b:16:a2 (try 1/3)
[   40.980941] wlp0s20f3: authenticated
[   40.981904] wlp0s20f3: associate with 18:ee:86:8b:16:a2 (try 1/3)
[   41.042933] wlp0s20f3: RX AssocResp from 18:ee:86:8b:16:a2 (capab=0x1431 status=0 aid=14)
[   41.046917] wlp0s20f3: associated

If you post the patch, I'm happy to add a `Tested-by` tag for it.
Thank you for your help!

> Thanks,
> Srinivas

Re: [REGRESSION] Intel Turbo Boost stuck disabled on some Clevo machines (was: [PATCH] cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode)

[srinivas pandruvada]

On Thu, 2025-11-06 at 11:31 -0600, Aaron Rainbolt wrote:
> On Thu, 06 Nov 2025 07:23:14 -0800
> srinivas pandruvada <srinivas.pandruvada@linux.intel.com> wrote:
> 
> > Hi Aaron,
> > 
> > On Wed, 2025-09-10 at 15:33 -0500, Aaron Rainbolt wrote:
> > > On Wed, 10 Sep 2025 10:15:00 -0700
> > > srinivas pandruvada <srinivas.pandruvada@linux.intel.com> wrote:
> > >   
> > > > On Wed, 2025-09-10 at 11:36 -0500, Aaron Rainbolt wrote:  
> > > > > On Wed, 30 Apr 2025 16:29:09 +0200
> > > > > "Rafael J. Wysocki" <rafael@kernel.org> wrote:
> > > > >     
> > > > > > On Tue, Apr 29, 2025 at 11:07 PM Srinivas Pandruvada
> > > > > > <srinivas.pandruvada@linux.intel.com> wrote:    
> > > > > > > 
> > > > > > > When turbo mode is unavailable on a Skylake-X system,
> > > > > > > executing
> > > > > > > the
> > > > > > > command:
> > > > > > > "echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo"
> > > > > > > results in an unchecked MSR access error: WRMSR to 0x199
> > > > > > > (attempted to write 0x0000000100001300).  
> > Please try the attached patch, if this address this issue.
> 
> I can confirm that this patch does resolve the issue when applied to
> Kubuntu Focus's 6.14 kernel. CPU frequencies are available that
> require
> turbo boost, and `cat /sys/devices/system/cpu/intel_pstate` returns
> `0`. The logs from `dmesg` also indicate that turbo was disabled
> earlier in boot, but the warnings about turbo being disabled stop
> appearing later on, even when manipulating the `no_turbo` file:

Thanks for test. I am waiting for some other reporters from Suse to
confirm.
I will add your tested by tag.


- Srinivas

> 
> [   25.893012] intel_pstate: Turbo is disabled
> [   25.893019] intel_pstate: Turbo disabled by BIOS or unavailable on
> processor
> [   25.950587] NET: Registered PF_QIPCRTR protocol family
> [   26.599013] Realtek Internal NBASE-T PHY r8169-0-6c00:00: attached
> PHY driver (mii_bus:phy_addr=r8169-0-6c00:00, irq=MAC)
> [   26.725959] ACPI BIOS Error (bug): Could not resolve symbol
> [\_TZ.ETMD], AE_NOT_FOUND (20240827/psargs-332)
> 
> [   26.725976] No Local Variables are initialized for Method [_OSC]
> 
> [   26.725978] Initialized Arguments for Method [_OSC]:  (4 arguments
> defined for method invocation)
> [   26.725979]   Arg0:   0000000030ddf166 <Obj>           Buffer(16)
> 5D A8 3B B2 B7 C8 42 35
> [   26.725991]   Arg1:   0000000002bd3ac4 <Obj>           Integer
> 0000000000000001
> [   26.725996]   Arg2:   0000000033eb047e <Obj>           Integer
> 0000000000000002
> [   26.725999]   Arg3:   00000000de6cf5f1 <Obj>           Buffer(8)
> 00 00 00 00 05 00 00 00
> 
> [   26.726010] ACPI Error: Aborting method \_SB.IETM._OSC due to
> previous error (AE_NOT_FOUND) (20240827/psparse-529)
> [   26.726056] Consider using thermal netlink events interface
> [   26.769209] r8169 0000:6c:00.0 enp108s0: Link is Down
> [   26.857318] zram0: detected capacity change from 0 to 195035136
> [   26.864390] vboxdrv: Found 32 processor cores/threads
> [   26.873227] Adding 97517564k swap on /dev/zram0.  Priority:-2
> extents:1 across:97517564k SS
> [   26.880588] vboxdrv: TSC mode is Invariant, tentative frequency
> 2419194640 Hz
> [   26.880592] vboxdrv: Successfully loaded version 7.2.4 r170995
> (interface 0x00340001)
> [   26.895725] intel_pstate: Turbo is disabled
> [   26.895730] intel_pstate: Turbo disabled by BIOS or unavailable on
> processor
> [   26.943715] iwlwifi 0000:00:14.3: WFPM_UMAC_PD_NOTIFICATION: 0x20
> [   26.943746] iwlwifi 0000:00:14.3: WFPM_LMAC2_PD_NOTIFICATION: 0x1f
> [   26.943755] iwlwifi 0000:00:14.3: WFPM_AUTH_KEY_0: 0x90
> [   26.943765] iwlwifi 0000:00:14.3: CNVI_SCU_SEQ_DATA_DW9: 0x0
> [   26.944901] iwlwifi 0000:00:14.3: RFIm is deactivated, reason = 5
> [   27.045437] iwlwifi 0000:00:14.3: Registered PHC clock: iwlwifi-
> PTP, with index: 0
> [   27.098590] VBoxNetFlt: Successfully started.
> [   27.101687] VBoxNetAdp: Successfully started.
> [   27.153602] bridge: filtering via arp/ip/ip6tables is no longer
> available by default. Update your scripts to load br_netfilter if you
> need this.
> [   27.851014] loop14: detected capacity change from 0 to 8
> [   27.895706] r8169 0000:6c:00.0: invalid VPD tag 0xff (size 0) at
> offset 0; assume missing optional EEPROM
> [   28.898015] intel_pstate: Turbo is disabled
> [   28.898021] intel_pstate: Turbo disabled by BIOS or unavailable on
> processor
> [   31.900781] intel_pstate: Turbo is disabled
> [   31.900788] intel_pstate: Turbo disabled by BIOS or unavailable on
> processor
> [   33.959448] Bluetooth: RFCOMM TTY layer initialized
> [   33.959456] Bluetooth: RFCOMM socket layer initialized
> [   33.959462] Bluetooth: RFCOMM ver 1.11
> [   36.903768] intel_pstate: Turbo is disabled
> [   36.903777] intel_pstate: Turbo disabled by BIOS or unavailable on
> processor
> [   38.054345] systemd-journald[883]:
> /var/log/journal/a9e8e3d2041547169b107e1e1a23f2ce/user-1000.journal:
> Journal file uses a different sequence number ID, rotating.
> [   39.799560] warning: `kded5' uses wireless extensions which will
> stop working for Wi-Fi 7 hardware; use nl80211
> [   40.884365] wlp0s20f3: authenticate with 18:ee:86:8b:16:a2 (local
> address=98:bd:80:8a:e9:27)
> [   40.885147] wlp0s20f3: send auth to 18:ee:86:8b:16:a2 (try 1/3)
> [   40.968595] wlp0s20f3: authenticate with 18:ee:86:8b:16:a2 (local
> address=98:bd:80:8a:e9:27)
> [   40.968603] wlp0s20f3: send auth to 18:ee:86:8b:16:a2 (try 1/3)
> [   40.980941] wlp0s20f3: authenticated
> [   40.981904] wlp0s20f3: associate with 18:ee:86:8b:16:a2 (try 1/3)
> [   41.042933] wlp0s20f3: RX AssocResp from 18:ee:86:8b:16:a2
> (capab=0x1431 status=0 aid=14)
> [   41.046917] wlp0s20f3: associated
> 
> If you post the patch, I'm happy to add a `Tested-by` tag for it.
> Thank you for your help!
> 
> > Thanks,
> > Srinivas
> 

Re: [REGRESSION] Intel Turbo Boost stuck disabled on some Clevo machines (was: [PATCH] cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode)

[srinivas pandruvada]

[-- Attachment #1: Type: text/plain, Size: 6120 bytes --]

Hi Aaron,

Please again verify this change. This limits the scope.
Patch attached.

Thanks,
Srinivas

On Thu, 2025-11-06 at 11:31 -0600, Aaron Rainbolt wrote:
> On Thu, 06 Nov 2025 07:23:14 -0800
> srinivas pandruvada <srinivas.pandruvada@linux.intel.com> wrote:
> 
> > Hi Aaron,
> > 
> > On Wed, 2025-09-10 at 15:33 -0500, Aaron Rainbolt wrote:
> > > On Wed, 10 Sep 2025 10:15:00 -0700
> > > srinivas pandruvada <srinivas.pandruvada@linux.intel.com> wrote:
> > >   
> > > > On Wed, 2025-09-10 at 11:36 -0500, Aaron Rainbolt wrote:  
> > > > > On Wed, 30 Apr 2025 16:29:09 +0200
> > > > > "Rafael J. Wysocki" <rafael@kernel.org> wrote:
> > > > >     
> > > > > > On Tue, Apr 29, 2025 at 11:07 PM Srinivas Pandruvada
> > > > > > <srinivas.pandruvada@linux.intel.com> wrote:    
> > > > > > > 
> > > > > > > When turbo mode is unavailable on a Skylake-X system,
> > > > > > > executing
> > > > > > > the
> > > > > > > command:
> > > > > > > "echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo"
> > > > > > > results in an unchecked MSR access error: WRMSR to 0x199
> > > > > > > (attempted to write 0x0000000100001300).  
> > Please try the attached patch, if this address this issue.
> 
> I can confirm that this patch does resolve the issue when applied to
> Kubuntu Focus's 6.14 kernel. CPU frequencies are available that
> require
> turbo boost, and `cat /sys/devices/system/cpu/intel_pstate` returns
> `0`. The logs from `dmesg` also indicate that turbo was disabled
> earlier in boot, but the warnings about turbo being disabled stop
> appearing later on, even when manipulating the `no_turbo` file:
> 
> [   25.893012] intel_pstate: Turbo is disabled
> [   25.893019] intel_pstate: Turbo disabled by BIOS or unavailable on
> processor
> [   25.950587] NET: Registered PF_QIPCRTR protocol family
> [   26.599013] Realtek Internal NBASE-T PHY r8169-0-6c00:00: attached
> PHY driver (mii_bus:phy_addr=r8169-0-6c00:00, irq=MAC)
> [   26.725959] ACPI BIOS Error (bug): Could not resolve symbol
> [\_TZ.ETMD], AE_NOT_FOUND (20240827/psargs-332)
> 
> [   26.725976] No Local Variables are initialized for Method [_OSC]
> 
> [   26.725978] Initialized Arguments for Method [_OSC]:  (4 arguments
> defined for method invocation)
> [   26.725979]   Arg0:   0000000030ddf166 <Obj>           Buffer(16)
> 5D A8 3B B2 B7 C8 42 35
> [   26.725991]   Arg1:   0000000002bd3ac4 <Obj>           Integer
> 0000000000000001
> [   26.725996]   Arg2:   0000000033eb047e <Obj>           Integer
> 0000000000000002
> [   26.725999]   Arg3:   00000000de6cf5f1 <Obj>           Buffer(8)
> 00 00 00 00 05 00 00 00
> 
> [   26.726010] ACPI Error: Aborting method \_SB.IETM._OSC due to
> previous error (AE_NOT_FOUND) (20240827/psparse-529)
> [   26.726056] Consider using thermal netlink events interface
> [   26.769209] r8169 0000:6c:00.0 enp108s0: Link is Down
> [   26.857318] zram0: detected capacity change from 0 to 195035136
> [   26.864390] vboxdrv: Found 32 processor cores/threads
> [   26.873227] Adding 97517564k swap on /dev/zram0.  Priority:-2
> extents:1 across:97517564k SS
> [   26.880588] vboxdrv: TSC mode is Invariant, tentative frequency
> 2419194640 Hz
> [   26.880592] vboxdrv: Successfully loaded version 7.2.4 r170995
> (interface 0x00340001)
> [   26.895725] intel_pstate: Turbo is disabled
> [   26.895730] intel_pstate: Turbo disabled by BIOS or unavailable on
> processor
> [   26.943715] iwlwifi 0000:00:14.3: WFPM_UMAC_PD_NOTIFICATION: 0x20
> [   26.943746] iwlwifi 0000:00:14.3: WFPM_LMAC2_PD_NOTIFICATION: 0x1f
> [   26.943755] iwlwifi 0000:00:14.3: WFPM_AUTH_KEY_0: 0x90
> [   26.943765] iwlwifi 0000:00:14.3: CNVI_SCU_SEQ_DATA_DW9: 0x0
> [   26.944901] iwlwifi 0000:00:14.3: RFIm is deactivated, reason = 5
> [   27.045437] iwlwifi 0000:00:14.3: Registered PHC clock: iwlwifi-
> PTP, with index: 0
> [   27.098590] VBoxNetFlt: Successfully started.
> [   27.101687] VBoxNetAdp: Successfully started.
> [   27.153602] bridge: filtering via arp/ip/ip6tables is no longer
> available by default. Update your scripts to load br_netfilter if you
> need this.
> [   27.851014] loop14: detected capacity change from 0 to 8
> [   27.895706] r8169 0000:6c:00.0: invalid VPD tag 0xff (size 0) at
> offset 0; assume missing optional EEPROM
> [   28.898015] intel_pstate: Turbo is disabled
> [   28.898021] intel_pstate: Turbo disabled by BIOS or unavailable on
> processor
> [   31.900781] intel_pstate: Turbo is disabled
> [   31.900788] intel_pstate: Turbo disabled by BIOS or unavailable on
> processor
> [   33.959448] Bluetooth: RFCOMM TTY layer initialized
> [   33.959456] Bluetooth: RFCOMM socket layer initialized
> [   33.959462] Bluetooth: RFCOMM ver 1.11
> [   36.903768] intel_pstate: Turbo is disabled
> [   36.903777] intel_pstate: Turbo disabled by BIOS or unavailable on
> processor
> [   38.054345] systemd-journald[883]:
> /var/log/journal/a9e8e3d2041547169b107e1e1a23f2ce/user-1000.journal:
> Journal file uses a different sequence number ID, rotating.
> [   39.799560] warning: `kded5' uses wireless extensions which will
> stop working for Wi-Fi 7 hardware; use nl80211
> [   40.884365] wlp0s20f3: authenticate with 18:ee:86:8b:16:a2 (local
> address=98:bd:80:8a:e9:27)
> [   40.885147] wlp0s20f3: send auth to 18:ee:86:8b:16:a2 (try 1/3)
> [   40.968595] wlp0s20f3: authenticate with 18:ee:86:8b:16:a2 (local
> address=98:bd:80:8a:e9:27)
> [   40.968603] wlp0s20f3: send auth to 18:ee:86:8b:16:a2 (try 1/3)
> [   40.980941] wlp0s20f3: authenticated
> [   40.981904] wlp0s20f3: associate with 18:ee:86:8b:16:a2 (try 1/3)
> [   41.042933] wlp0s20f3: RX AssocResp from 18:ee:86:8b:16:a2
> (capab=0x1431 status=0 aid=14)
> [   41.046917] wlp0s20f3: associated
> 
> If you post the patch, I'm happy to add a `Tested-by` tag for it.
> Thank you for your help!
> 
> > Thanks,
> > Srinivas
> 
> 


[-- Attachment #2: 0001-cpufreq-intel_pstate-Check-IDA-feature-only-during-M.patch --]
[-- Type: text/x-patch, Size: 2331 bytes --]

From 14a7225dea86df0f288f94df174e3d1fcd0a18ed Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Thu, 6 Nov 2025 17:34:09 -0800
Subject: [PATCH] cpufreq: intel_pstate: Check IDA feature only during MSR
 0x199 write

Commit 0fb5be7fea98 ("cpufreq: intel_pstate: Unchecked MSR aceess in
legacy mode") introduced a check for feature X86_FEATURE_IDA to verify
turbo mode support. Although this is the correct way to check for turbo
mode, it causes issues on some platforms that disable turbo during OS
boot but enable it later. Without this feature check, users were able to
write 0 to /sys/devices/system/cpu/intel_pstate/no_turbo post-boot to
get turbo mode frequencies.

To restore the old behavior while still addressing the unchecked MSR
issue on some Skylake-X systems, limit the X86_FEATURE_IDA check to only
when setting MSR 0x199 Turbo Engage Bit (bit 32).

Fixes: 0fb5be7fea98 ("cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode")
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
---
 drivers/cpufreq/intel_pstate.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 43e847e9f741..38a8e877f222 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -598,9 +598,6 @@ static bool turbo_is_disabled(void)
 {
 	u64 misc_en;
 
-	if (!cpu_feature_enabled(X86_FEATURE_IDA))
-		return true;
-
 	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
 
 	return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
@@ -2014,7 +2011,8 @@ static u64 atom_get_val(struct cpudata *cpudata, int pstate)
 	u32 vid;
 
 	val = (u64)pstate << 8;
-	if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled))
+	if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) &&
+	    cpu_feature_enabled(X86_FEATURE_IDA))
 		val |= (u64)1 << 32;
 
 	vid_fp = cpudata->vid.min + mul_fp(
@@ -2179,7 +2177,8 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate)
 	u64 val;
 
 	val = (u64)pstate << 8;
-	if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled))
+	if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) &&
+	    cpu_feature_enabled(X86_FEATURE_IDA))
 		val |= (u64)1 << 32;
 
 	return val;
-- 
2.43.0

Re: [REGRESSION] Intel Turbo Boost stuck disabled on some Clevo machines (was: [PATCH] cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode)

[srinivas pandruvada]

[-- Attachment #1: Type: text/plain, Size: 6652 bytes --]

+ Thomas

Please verify so that I can post the patch.

Thanks,
Srinivas


On Thu, 2025-11-06 at 17:48 -0800, srinivas pandruvada wrote:
> Hi Aaron,
> 
> Please again verify this change. This limits the scope.
> Patch attached.
> 
> Thanks,
> Srinivas
> 
> On Thu, 2025-11-06 at 11:31 -0600, Aaron Rainbolt wrote:
> > On Thu, 06 Nov 2025 07:23:14 -0800
> > srinivas pandruvada <srinivas.pandruvada@linux.intel.com> wrote:
> > 
> > > Hi Aaron,
> > > 
> > > On Wed, 2025-09-10 at 15:33 -0500, Aaron Rainbolt wrote:
> > > > On Wed, 10 Sep 2025 10:15:00 -0700
> > > > srinivas pandruvada <srinivas.pandruvada@linux.intel.com>
> > > > wrote:
> > > >   
> > > > > On Wed, 2025-09-10 at 11:36 -0500, Aaron Rainbolt wrote:  
> > > > > > On Wed, 30 Apr 2025 16:29:09 +0200
> > > > > > "Rafael J. Wysocki" <rafael@kernel.org> wrote:
> > > > > >     
> > > > > > > On Tue, Apr 29, 2025 at 11:07 PM Srinivas Pandruvada
> > > > > > > <srinivas.pandruvada@linux.intel.com> wrote:    
> > > > > > > > 
> > > > > > > > When turbo mode is unavailable on a Skylake-X system,
> > > > > > > > executing
> > > > > > > > the
> > > > > > > > command:
> > > > > > > > "echo 1 >
> > > > > > > > /sys/devices/system/cpu/intel_pstate/no_turbo"
> > > > > > > > results in an unchecked MSR access error: WRMSR to
> > > > > > > > 0x199
> > > > > > > > (attempted to write 0x0000000100001300).  
> > > Please try the attached patch, if this address this issue.
> > 
> > I can confirm that this patch does resolve the issue when applied
> > to
> > Kubuntu Focus's 6.14 kernel. CPU frequencies are available that
> > require
> > turbo boost, and `cat /sys/devices/system/cpu/intel_pstate` returns
> > `0`. The logs from `dmesg` also indicate that turbo was disabled
> > earlier in boot, but the warnings about turbo being disabled stop
> > appearing later on, even when manipulating the `no_turbo` file:
> > 
> > [   25.893012] intel_pstate: Turbo is disabled
> > [   25.893019] intel_pstate: Turbo disabled by BIOS or unavailable
> > on
> > processor
> > [   25.950587] NET: Registered PF_QIPCRTR protocol family
> > [   26.599013] Realtek Internal NBASE-T PHY r8169-0-6c00:00:
> > attached
> > PHY driver (mii_bus:phy_addr=r8169-0-6c00:00, irq=MAC)
> > [   26.725959] ACPI BIOS Error (bug): Could not resolve symbol
> > [\_TZ.ETMD], AE_NOT_FOUND (20240827/psargs-332)
> > 
> > [   26.725976] No Local Variables are initialized for Method [_OSC]
> > 
> > [   26.725978] Initialized Arguments for Method [_OSC]:  (4
> > arguments
> > defined for method invocation)
> > [   26.725979]   Arg0:   0000000030ddf166 <Obj>          
> > Buffer(16)
> > 5D A8 3B B2 B7 C8 42 35
> > [   26.725991]   Arg1:   0000000002bd3ac4 <Obj>           Integer
> > 0000000000000001
> > [   26.725996]   Arg2:   0000000033eb047e <Obj>           Integer
> > 0000000000000002
> > [   26.725999]   Arg3:   00000000de6cf5f1 <Obj>           Buffer(8)
> > 00 00 00 00 05 00 00 00
> > 
> > [   26.726010] ACPI Error: Aborting method \_SB.IETM._OSC due to
> > previous error (AE_NOT_FOUND) (20240827/psparse-529)
> > [   26.726056] Consider using thermal netlink events interface
> > [   26.769209] r8169 0000:6c:00.0 enp108s0: Link is Down
> > [   26.857318] zram0: detected capacity change from 0 to 195035136
> > [   26.864390] vboxdrv: Found 32 processor cores/threads
> > [   26.873227] Adding 97517564k swap on /dev/zram0.  Priority:-2
> > extents:1 across:97517564k SS
> > [   26.880588] vboxdrv: TSC mode is Invariant, tentative frequency
> > 2419194640 Hz
> > [   26.880592] vboxdrv: Successfully loaded version 7.2.4 r170995
> > (interface 0x00340001)
> > [   26.895725] intel_pstate: Turbo is disabled
> > [   26.895730] intel_pstate: Turbo disabled by BIOS or unavailable
> > on
> > processor
> > [   26.943715] iwlwifi 0000:00:14.3: WFPM_UMAC_PD_NOTIFICATION:
> > 0x20
> > [   26.943746] iwlwifi 0000:00:14.3: WFPM_LMAC2_PD_NOTIFICATION:
> > 0x1f
> > [   26.943755] iwlwifi 0000:00:14.3: WFPM_AUTH_KEY_0: 0x90
> > [   26.943765] iwlwifi 0000:00:14.3: CNVI_SCU_SEQ_DATA_DW9: 0x0
> > [   26.944901] iwlwifi 0000:00:14.3: RFIm is deactivated, reason =
> > 5
> > [   27.045437] iwlwifi 0000:00:14.3: Registered PHC clock: iwlwifi-
> > PTP, with index: 0
> > [   27.098590] VBoxNetFlt: Successfully started.
> > [   27.101687] VBoxNetAdp: Successfully started.
> > [   27.153602] bridge: filtering via arp/ip/ip6tables is no longer
> > available by default. Update your scripts to load br_netfilter if
> > you
> > need this.
> > [   27.851014] loop14: detected capacity change from 0 to 8
> > [   27.895706] r8169 0000:6c:00.0: invalid VPD tag 0xff (size 0) at
> > offset 0; assume missing optional EEPROM
> > [   28.898015] intel_pstate: Turbo is disabled
> > [   28.898021] intel_pstate: Turbo disabled by BIOS or unavailable
> > on
> > processor
> > [   31.900781] intel_pstate: Turbo is disabled
> > [   31.900788] intel_pstate: Turbo disabled by BIOS or unavailable
> > on
> > processor
> > [   33.959448] Bluetooth: RFCOMM TTY layer initialized
> > [   33.959456] Bluetooth: RFCOMM socket layer initialized
> > [   33.959462] Bluetooth: RFCOMM ver 1.11
> > [   36.903768] intel_pstate: Turbo is disabled
> > [   36.903777] intel_pstate: Turbo disabled by BIOS or unavailable
> > on
> > processor
> > [   38.054345] systemd-journald[883]:
> > /var/log/journal/a9e8e3d2041547169b107e1e1a23f2ce/user-
> > 1000.journal:
> > Journal file uses a different sequence number ID, rotating.
> > [   39.799560] warning: `kded5' uses wireless extensions which will
> > stop working for Wi-Fi 7 hardware; use nl80211
> > [   40.884365] wlp0s20f3: authenticate with 18:ee:86:8b:16:a2
> > (local
> > address=98:bd:80:8a:e9:27)
> > [   40.885147] wlp0s20f3: send auth to 18:ee:86:8b:16:a2 (try 1/3)
> > [   40.968595] wlp0s20f3: authenticate with 18:ee:86:8b:16:a2
> > (local
> > address=98:bd:80:8a:e9:27)
> > [   40.968603] wlp0s20f3: send auth to 18:ee:86:8b:16:a2 (try 1/3)
> > [   40.980941] wlp0s20f3: authenticated
> > [   40.981904] wlp0s20f3: associate with 18:ee:86:8b:16:a2 (try
> > 1/3)
> > [   41.042933] wlp0s20f3: RX AssocResp from 18:ee:86:8b:16:a2
> > (capab=0x1431 status=0 aid=14)
> > [   41.046917] wlp0s20f3: associated
> > 
> > If you post the patch, I'm happy to add a `Tested-by` tag for it.
> > Thank you for your help!
> > 
> > > Thanks,
> > > Srinivas
> > 
> > 

[-- Attachment #2: 0001-cpufreq-intel_pstate-Check-IDA-feature-only-during-M.patch --]
[-- Type: text/x-patch, Size: 2331 bytes --]

From 14a7225dea86df0f288f94df174e3d1fcd0a18ed Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Thu, 6 Nov 2025 17:34:09 -0800
Subject: [PATCH] cpufreq: intel_pstate: Check IDA feature only during MSR
 0x199 write

Commit 0fb5be7fea98 ("cpufreq: intel_pstate: Unchecked MSR aceess in
legacy mode") introduced a check for feature X86_FEATURE_IDA to verify
turbo mode support. Although this is the correct way to check for turbo
mode, it causes issues on some platforms that disable turbo during OS
boot but enable it later. Without this feature check, users were able to
write 0 to /sys/devices/system/cpu/intel_pstate/no_turbo post-boot to
get turbo mode frequencies.

To restore the old behavior while still addressing the unchecked MSR
issue on some Skylake-X systems, limit the X86_FEATURE_IDA check to only
when setting MSR 0x199 Turbo Engage Bit (bit 32).

Fixes: 0fb5be7fea98 ("cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode")
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
---
 drivers/cpufreq/intel_pstate.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 43e847e9f741..38a8e877f222 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -598,9 +598,6 @@ static bool turbo_is_disabled(void)
 {
 	u64 misc_en;
 
-	if (!cpu_feature_enabled(X86_FEATURE_IDA))
-		return true;
-
 	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
 
 	return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
@@ -2014,7 +2011,8 @@ static u64 atom_get_val(struct cpudata *cpudata, int pstate)
 	u32 vid;
 
 	val = (u64)pstate << 8;
-	if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled))
+	if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) &&
+	    cpu_feature_enabled(X86_FEATURE_IDA))
 		val |= (u64)1 << 32;
 
 	vid_fp = cpudata->vid.min + mul_fp(
@@ -2179,7 +2177,8 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate)
 	u64 val;
 
 	val = (u64)pstate << 8;
-	if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled))
+	if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) &&
+	    cpu_feature_enabled(X86_FEATURE_IDA))
 		val |= (u64)1 << 32;
 
 	return val;
-- 
2.43.0

Re: [REGRESSION] Intel Turbo Boost stuck disabled on some Clevo machines (was: [PATCH] cpufreq: intel_pstate: Unchecked MSR aceess in legacy mode)

[Aaron Rainbolt]

On Mon, 10 Nov 2025 08:58:55 -0800
srinivas pandruvada <srinivas.pandruvada@linux.intel.com> wrote:

> + Thomas
> 
> Please verify so that I can post the patch.
> 
> Thanks,
> Srinivas

Hi Srinivas,

I have tested the newest patch against KFocus's 6.14 kernel on the
affected hardware, and can confirm that this patch also allows Turbo
Boost to function correctly. High-frequency modes are available in
cpupower-gui, and the "Turbo disabled by BIOS or unavailable on
processor" messages stop occurring in dmesg shortly after boot.

Tested-by: Aaron Rainbolt <arainbolt@kfocus.org>

--
Aaron

> 
> On Thu, 2025-11-06 at 17:48 -0800, srinivas pandruvada wrote:
> > Hi Aaron,
> > 
> > Please again verify this change. This limits the scope.
> > Patch attached.
> > 
> > Thanks,
> > Srinivas
> > 
> > On Thu, 2025-11-06 at 11:31 -0600, Aaron Rainbolt wrote:  
> > > On Thu, 06 Nov 2025 07:23:14 -0800
> > > srinivas pandruvada <srinivas.pandruvada@linux.intel.com> wrote:
> > >   
> > > > Hi Aaron,
> > > > 
> > > > On Wed, 2025-09-10 at 15:33 -0500, Aaron Rainbolt wrote:  
> > > > > On Wed, 10 Sep 2025 10:15:00 -0700
> > > > > srinivas pandruvada <srinivas.pandruvada@linux.intel.com>
> > > > > wrote:
> > > > >     
> > > > > > On Wed, 2025-09-10 at 11:36 -0500, Aaron Rainbolt wrote:    
> > > > > > > On Wed, 30 Apr 2025 16:29:09 +0200
> > > > > > > "Rafael J. Wysocki" <rafael@kernel.org> wrote:
> > > > > > >       
> > > > > > > > On Tue, Apr 29, 2025 at 11:07 PM Srinivas Pandruvada
> > > > > > > > <srinivas.pandruvada@linux.intel.com> wrote:      
> > > > > > > > > 
> > > > > > > > > When turbo mode is unavailable on a Skylake-X system,
> > > > > > > > > executing
> > > > > > > > > the
> > > > > > > > > command:
> > > > > > > > > "echo 1 >
> > > > > > > > > /sys/devices/system/cpu/intel_pstate/no_turbo"
> > > > > > > > > results in an unchecked MSR access error: WRMSR to
> > > > > > > > > 0x199
> > > > > > > > > (attempted to write 0x0000000100001300).    
> > > > Please try the attached patch, if this address this issue.  
> > > 
> > > I can confirm that this patch does resolve the issue when applied
> > > to
> > > Kubuntu Focus's 6.14 kernel. CPU frequencies are available that
> > > require
> > > turbo boost, and `cat /sys/devices/system/cpu/intel_pstate`
> > > returns `0`. The logs from `dmesg` also indicate that turbo was
> > > disabled earlier in boot, but the warnings about turbo being
> > > disabled stop appearing later on, even when manipulating the
> > > `no_turbo` file:
> > > 
> > > [   25.893012] intel_pstate: Turbo is disabled
> > > [   25.893019] intel_pstate: Turbo disabled by BIOS or unavailable
> > > on
> > > processor
> > > [   25.950587] NET: Registered PF_QIPCRTR protocol family
> > > [   26.599013] Realtek Internal NBASE-T PHY r8169-0-6c00:00:
> > > attached
> > > PHY driver (mii_bus:phy_addr=r8169-0-6c00:00, irq=MAC)
> > > [   26.725959] ACPI BIOS Error (bug): Could not resolve symbol
> > > [\_TZ.ETMD], AE_NOT_FOUND (20240827/psargs-332)
> > > 
> > > [   26.725976] No Local Variables are initialized for Method
> > > [_OSC]
> > > 
> > > [   26.725978] Initialized Arguments for Method [_OSC]:  (4
> > > arguments
> > > defined for method invocation)
> > > [   26.725979]   Arg0:   0000000030ddf166 <Obj>          
> > > Buffer(16)
> > > 5D A8 3B B2 B7 C8 42 35
> > > [   26.725991]   Arg1:   0000000002bd3ac4 <Obj>           Integer
> > > 0000000000000001
> > > [   26.725996]   Arg2:   0000000033eb047e <Obj>           Integer
> > > 0000000000000002
> > > [   26.725999]   Arg3:   00000000de6cf5f1 <Obj>
> > > Buffer(8) 00 00 00 00 05 00 00 00
> > > 
> > > [   26.726010] ACPI Error: Aborting method \_SB.IETM._OSC due to
> > > previous error (AE_NOT_FOUND) (20240827/psparse-529)
> > > [   26.726056] Consider using thermal netlink events interface
> > > [   26.769209] r8169 0000:6c:00.0 enp108s0: Link is Down
> > > [   26.857318] zram0: detected capacity change from 0 to 195035136
> > > [   26.864390] vboxdrv: Found 32 processor cores/threads
> > > [   26.873227] Adding 97517564k swap on /dev/zram0.  Priority:-2
> > > extents:1 across:97517564k SS
> > > [   26.880588] vboxdrv: TSC mode is Invariant, tentative frequency
> > > 2419194640 Hz
> > > [   26.880592] vboxdrv: Successfully loaded version 7.2.4 r170995
> > > (interface 0x00340001)
> > > [   26.895725] intel_pstate: Turbo is disabled
> > > [   26.895730] intel_pstate: Turbo disabled by BIOS or unavailable
> > > on
> > > processor
> > > [   26.943715] iwlwifi 0000:00:14.3: WFPM_UMAC_PD_NOTIFICATION:
> > > 0x20
> > > [   26.943746] iwlwifi 0000:00:14.3: WFPM_LMAC2_PD_NOTIFICATION:
> > > 0x1f
> > > [   26.943755] iwlwifi 0000:00:14.3: WFPM_AUTH_KEY_0: 0x90
> > > [   26.943765] iwlwifi 0000:00:14.3: CNVI_SCU_SEQ_DATA_DW9: 0x0
> > > [   26.944901] iwlwifi 0000:00:14.3: RFIm is deactivated, reason =
> > > 5
> > > [   27.045437] iwlwifi 0000:00:14.3: Registered PHC clock:
> > > iwlwifi- PTP, with index: 0
> > > [   27.098590] VBoxNetFlt: Successfully started.
> > > [   27.101687] VBoxNetAdp: Successfully started.
> > > [   27.153602] bridge: filtering via arp/ip/ip6tables is no longer
> > > available by default. Update your scripts to load br_netfilter if
> > > you
> > > need this.
> > > [   27.851014] loop14: detected capacity change from 0 to 8
> > > [   27.895706] r8169 0000:6c:00.0: invalid VPD tag 0xff (size 0)
> > > at offset 0; assume missing optional EEPROM
> > > [   28.898015] intel_pstate: Turbo is disabled
> > > [   28.898021] intel_pstate: Turbo disabled by BIOS or unavailable
> > > on
> > > processor
> > > [   31.900781] intel_pstate: Turbo is disabled
> > > [   31.900788] intel_pstate: Turbo disabled by BIOS or unavailable
> > > on
> > > processor
> > > [   33.959448] Bluetooth: RFCOMM TTY layer initialized
> > > [   33.959456] Bluetooth: RFCOMM socket layer initialized
> > > [   33.959462] Bluetooth: RFCOMM ver 1.11
> > > [   36.903768] intel_pstate: Turbo is disabled
> > > [   36.903777] intel_pstate: Turbo disabled by BIOS or unavailable
> > > on
> > > processor
> > > [   38.054345] systemd-journald[883]:
> > > /var/log/journal/a9e8e3d2041547169b107e1e1a23f2ce/user-
> > > 1000.journal:
> > > Journal file uses a different sequence number ID, rotating.
> > > [   39.799560] warning: `kded5' uses wireless extensions which
> > > will stop working for Wi-Fi 7 hardware; use nl80211
> > > [   40.884365] wlp0s20f3: authenticate with 18:ee:86:8b:16:a2
> > > (local
> > > address=98:bd:80:8a:e9:27)
> > > [   40.885147] wlp0s20f3: send auth to 18:ee:86:8b:16:a2 (try 1/3)
> > > [   40.968595] wlp0s20f3: authenticate with 18:ee:86:8b:16:a2
> > > (local
> > > address=98:bd:80:8a:e9:27)
> > > [   40.968603] wlp0s20f3: send auth to 18:ee:86:8b:16:a2 (try 1/3)
> > > [   40.980941] wlp0s20f3: authenticated
> > > [   40.981904] wlp0s20f3: associate with 18:ee:86:8b:16:a2 (try
> > > 1/3)
> > > [   41.042933] wlp0s20f3: RX AssocResp from 18:ee:86:8b:16:a2
> > > (capab=0x1431 status=0 aid=14)
> > > [   41.046917] wlp0s20f3: associated
> > > 
> > > If you post the patch, I'm happy to add a `Tested-by` tag for it.
> > > Thank you for your help!
> > >   
> > > > Thanks,
> > > > Srinivas  
> > > 
> > >