diff mbox

[v3] Force cppc_cpufreq to report values in KHz to fix user space reporting

Message ID 1463614882-26101-1-git-send-email-ahs3@redhat.com (mailing list archive)
State Changes Requested, archived
Headers show

Commit Message

Al Stone May 18, 2016, 11:41 p.m. UTC
When CPPC is being used by ACPI on arm64, user space tools such as
cpupower report CPU frequency values from sysfs that are incorrect.

What the driver was doing was reporting the values given by ACPI tables
in whatever scale was used to provide them.  However, the ACPI spec
defines the CPPC values as unitless abstract numbers.  Internal kernel
structures such as struct perf_cap, in contrast, expect these values
to be in KHz.  When these struct values get reported via sysfs, the
user space tools also assume they are in KHz, causing them to report
incorrect values (for example, reporting a CPU frequency of 1MHz when
it should be 1.8GHz).

While the investigation for a long term fix proceeds (several options
are being explored, some of which may require spec changes or other
much more invasive fixes), this patch forces the values read by CPPC
to be read in KHz, regardless of what they actually represent.

The downside is that this approach has some assumptions:

   (1) It relies on SMBIOS3 being used, *and* that the Max Frequency
   value for a processor is set to a non-zero value.

   (2) It assumes that all processors run at the same speed, or that
   the CPPC values have all been scaled to reflect relative speed.
   This patch retrieves the first CPU Max Frequency from a type 4 DMI
   record that it can find.  This may not be an issue, however, as a
   sampling of DMI data on x86 and arm64 indicates there is often only
   one such record regardless.  Since CPPC is relatively new, it is
   unclear if the ACPI ASL will always be written to reflect any sort
   of relative performance of processors of differing speeds.

   (3) It assumes that performance and frequency both scale linearly.

For arm64 servers, this may be sufficient, but it does rely on
firmware values being set correctly.  Hence, other approaches are
also being considered.

This has been tested on three arm64 servers, with and without DMI, with
and without CPPC support.

Changes for v3:
    -- Added clarifying commentary re short-term vs long-term fix (Alexey
       Klimov)
    -- Added range checking code to ensure proper arithmetic occurs,
       especially no division by zero (Alexey Klimov)

Changes for v2:
    -- Corrected thinko: needed to have DEPENDS on DMI in Kconfig.arm,
       not SELECT DMI (found by build daemon)

Signed-off-by: Al Stone <ahs3@redhat.com>
---
 drivers/acpi/cppc_acpi.c    | 96 ++++++++++++++++++++++++++++++++++++++++++---
 drivers/cpufreq/Kconfig.arm |  1 +
 2 files changed, 92 insertions(+), 5 deletions(-)

Comments

Viresh Kumar May 19, 2016, 10:16 a.m. UTC | #1
On 18-05-16, 17:41, Al Stone wrote:
> When CPPC is being used by ACPI on arm64, user space tools such as
> cpupower report CPU frequency values from sysfs that are incorrect.
> 
> What the driver was doing was reporting the values given by ACPI tables
> in whatever scale was used to provide them.  However, the ACPI spec
> defines the CPPC values as unitless abstract numbers.  Internal kernel
> structures such as struct perf_cap, in contrast, expect these values
> to be in KHz.  When these struct values get reported via sysfs, the
> user space tools also assume they are in KHz, causing them to report
> incorrect values (for example, reporting a CPU frequency of 1MHz when
> it should be 1.8GHz).
> 
> While the investigation for a long term fix proceeds (several options
> are being explored, some of which may require spec changes or other
> much more invasive fixes), this patch forces the values read by CPPC
> to be read in KHz, regardless of what they actually represent.
> 
> The downside is that this approach has some assumptions:
> 
>    (1) It relies on SMBIOS3 being used, *and* that the Max Frequency
>    value for a processor is set to a non-zero value.
> 
>    (2) It assumes that all processors run at the same speed, or that
>    the CPPC values have all been scaled to reflect relative speed.
>    This patch retrieves the first CPU Max Frequency from a type 4 DMI
>    record that it can find.  This may not be an issue, however, as a
>    sampling of DMI data on x86 and arm64 indicates there is often only
>    one such record regardless.  Since CPPC is relatively new, it is
>    unclear if the ACPI ASL will always be written to reflect any sort
>    of relative performance of processors of differing speeds.
> 
>    (3) It assumes that performance and frequency both scale linearly.
> 
> For arm64 servers, this may be sufficient, but it does rely on
> firmware values being set correctly.  Hence, other approaches are
> also being considered.
> 
> This has been tested on three arm64 servers, with and without DMI, with
> and without CPPC support.
> 
> Changes for v3:
>     -- Added clarifying commentary re short-term vs long-term fix (Alexey
>        Klimov)
>     -- Added range checking code to ensure proper arithmetic occurs,
>        especially no division by zero (Alexey Klimov)
> 
> Changes for v2:
>     -- Corrected thinko: needed to have DEPENDS on DMI in Kconfig.arm,
>        not SELECT DMI (found by build daemon)
> 
> Signed-off-by: Al Stone <ahs3@redhat.com>
> ---
>  drivers/acpi/cppc_acpi.c    | 96 ++++++++++++++++++++++++++++++++++++++++++---
>  drivers/cpufreq/Kconfig.arm |  1 +
>  2 files changed, 92 insertions(+), 5 deletions(-)

I can't keep it unread in my Inbox forever and so I am replying here
to mark it read :)

I don't have enough knowledge of this stuff and so I leave it for
Ashwin and Rafael to do it. :)
Rafael J. Wysocki May 19, 2016, 1:12 p.m. UTC | #2
On Thu, May 19, 2016 at 1:41 AM, Al Stone <ahs3@redhat.com> wrote:
> When CPPC is being used by ACPI on arm64, user space tools such as
> cpupower report CPU frequency values from sysfs that are incorrect.
>
> What the driver was doing was reporting the values given by ACPI tables
> in whatever scale was used to provide them.  However, the ACPI spec
> defines the CPPC values as unitless abstract numbers.  Internal kernel
> structures such as struct perf_cap, in contrast, expect these values
> to be in KHz.  When these struct values get reported via sysfs, the
> user space tools also assume they are in KHz, causing them to report
> incorrect values (for example, reporting a CPU frequency of 1MHz when
> it should be 1.8GHz).
>
> While the investigation for a long term fix proceeds (several options
> are being explored, some of which may require spec changes or other
> much more invasive fixes), this patch forces the values read by CPPC
> to be read in KHz, regardless of what they actually represent.
>
> The downside is that this approach has some assumptions:
>
>    (1) It relies on SMBIOS3 being used, *and* that the Max Frequency
>    value for a processor is set to a non-zero value.
>
>    (2) It assumes that all processors run at the same speed, or that
>    the CPPC values have all been scaled to reflect relative speed.
>    This patch retrieves the first CPU Max Frequency from a type 4 DMI
>    record that it can find.  This may not be an issue, however, as a
>    sampling of DMI data on x86 and arm64 indicates there is often only
>    one such record regardless.  Since CPPC is relatively new, it is
>    unclear if the ACPI ASL will always be written to reflect any sort
>    of relative performance of processors of differing speeds.
>
>    (3) It assumes that performance and frequency both scale linearly.
>
> For arm64 servers, this may be sufficient, but it does rely on
> firmware values being set correctly.  Hence, other approaches are
> also being considered.
>
> This has been tested on three arm64 servers, with and without DMI, with
> and without CPPC support.
>
> Changes for v3:
>     -- Added clarifying commentary re short-term vs long-term fix (Alexey
>        Klimov)
>     -- Added range checking code to ensure proper arithmetic occurs,
>        especially no division by zero (Alexey Klimov)
>
> Changes for v2:
>     -- Corrected thinko: needed to have DEPENDS on DMI in Kconfig.arm,
>        not SELECT DMI (found by build daemon)
>
> Signed-off-by: Al Stone <ahs3@redhat.com>
> ---
>  drivers/acpi/cppc_acpi.c    | 96 ++++++++++++++++++++++++++++++++++++++++++---
>  drivers/cpufreq/Kconfig.arm |  1 +
>  2 files changed, 92 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
> index 8adac69..56a46e6 100644
> --- a/drivers/acpi/cppc_acpi.c
> +++ b/drivers/acpi/cppc_acpi.c
> @@ -40,6 +40,9 @@
>  #include <linux/cpufreq.h>
>  #include <linux/delay.h>
>  #include <linux/ktime.h>
> +#include <linux/dmi.h>
> +
> +#include <asm/unaligned.h>
>
>  #include <acpi/cppc_acpi.h>
>  /*
> @@ -709,6 +712,55 @@ static int cpc_write(struct cpc_reg *reg, u64 val)
>         return ret_val;
>  }
>
> +static u64 cppc_dmi_khz;
> +
> +static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
> +{
> +       u16 *mhz = (u16 *)private;
> +       const u8 *dmi_data = (const u8 *)dm;
> +
> +       if (dm->type == DMI_ENTRY_PROCESSOR && dm->length >= 48)
> +               *mhz = (u16)get_unaligned((const u16 *)(dmi_data + 0x14));

Is the offset standardized across architectures (I can't recall ATM)?
If so, maybe #define a symbol for it and add a comment saying that
next to its definition?

> +}
> +
> +
> +static u64 cppc_get_dmi_khz(void)
> +{
> +       u16 mhz;
> +
> +       dmi_walk(cppc_find_dmi_mhz, &mhz);
> +
> +       /*
> +        * Real stupid fallback value, just in case there is no
> +        * actual value set.
> +        */
> +       mhz = mhz ? mhz : 1;
> +
> +       return (1000 * mhz);
> +}
> +
> +static u64 cppc_unitless_to_khz(u64 min_in, u64 max_in, u64 val)

Is the "unitless" part of the name really necessary?

> +{
> +       /*
> +        * The incoming val should be min <= val <= max.  Our
> +        * job is to convert that to KHz so it can be properly
> +        * reported to user space via cpufreq_policy.
> +        */
> +       u64 curval = val;
> +       u64 maxf = max_in;
> +       u64 minf = min_in;
> +
> +       if (!cppc_dmi_khz)
> +               cppc_dmi_khz = cppc_get_dmi_khz();

I don't like hidden initializations like this if they are avoidable
and it very much looks like it is avoidable here.

Also you seem to be using the same cppc_dmi_khz value for all
processors handled by this driver.  Is that really guaranteed to be
correct?

> +
> +       /* range check the input values */
> +       curval = curval < minf ? minf : curval;
> +       curval = curval > maxf ? maxf : curval;
> +       minf = minf >= maxf ? maxf - 1 : minf;
> +
> +       return ((curval - minf) * cppc_dmi_khz) / (maxf - minf);
> +}
> +
>  /**
>   * cppc_get_perf_caps - Get a CPUs performance capabilities.
>   * @cpunum: CPU from which to get capabilities info.
> @@ -748,17 +800,51 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
>                 }
>         }
>
> +       /*
> +        * Since these values in perf_caps will be used in setting
> +        * up the cpufreq policy, they must always be stored in units
> +        * of KHz.  If they are not, user space tools will become very
> +        * confused since they assume these are in KHz when reading
> +        * sysfs.
> +        *
> +        * NB: there may be better approaches to this problem that, as
> +        * of this writing, are still being explored.  Ideally, this is
> +        * a short term solution since correlating CPPC abstract values
> +        * with CPU frequency may or may not reflect actual performance.
> +        *
> +        * The reason longer term solutions are being explored is because
> +        * this solution requires we make the following assumptions:
> +        *
> +        *    (1) It relies on SMBIOS3 being used, *and* that the Max
> +        *        Frequency value for a processor is set to a non-zero value.
> +        *
> +        *    (2) It assumes that all processors run at the same speed, or
> +        *        that the CPPC values have all been scaled to reflect any
> +        *        relative differences.  This code retrieves the first CPU
> +        *        Max Frequency from a type 4 DMI record that it can find.
> +        *        This may not be an issue, however, as a sampling of DMI
> +        *        data on x86 and arm64 indicates there is often only one
> +        *        such record regardless.
> +        *
> +        *    (3) It assumes that performance and frequency both scale
> +        *        linearly.
> +        *
> +        * None of these are particularly horrible assumptions.  But, they
> +        * are assumptions and ultimately we'd like to be able to report
> +        * performance without quite so many of them.
> +        *
> +        */
>         cpc_read(&highest_reg->cpc_entry.reg, &high);
> -       perf_caps->highest_perf = high;
> -
>         cpc_read(&lowest_reg->cpc_entry.reg, &low);
> -       perf_caps->lowest_perf = low;
> +
> +       perf_caps->highest_perf = cppc_unitless_to_khz(low, high, high);
> +       perf_caps->lowest_perf = cppc_unitless_to_khz(low, high, low);
>
>         cpc_read(&ref_perf->cpc_entry.reg, &ref);
> -       perf_caps->reference_perf = ref;
> +       perf_caps->reference_perf = cppc_unitless_to_khz(low, high, ref);
>
>         cpc_read(&nom_perf->cpc_entry.reg, &nom);
> -       perf_caps->nominal_perf = nom;
> +       perf_caps->nominal_perf = cppc_unitless_to_khz(low, high, nom);
>
>         if (!ref)
>                 perf_caps->reference_perf = perf_caps->nominal_perf;
> diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
> index 14b1f93..0573982 100644
> --- a/drivers/cpufreq/Kconfig.arm
> +++ b/drivers/cpufreq/Kconfig.arm
> @@ -255,6 +255,7 @@ config ACPI_CPPC_CPUFREQ
>         tristate "CPUFreq driver based on the ACPI CPPC spec"
>         depends on ACPI
>         select ACPI_CPPC_LIB
> +       select DMI

What if there are unmet dependencies for DMI?  Or is that not possible?

>         default n
>         help
>           This adds a CPUFreq driver which uses CPPC methods
> --
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Al Stone May 19, 2016, 4:59 p.m. UTC | #3
On 05/19/2016 07:12 AM, Rafael J. Wysocki wrote:
> On Thu, May 19, 2016 at 1:41 AM, Al Stone <ahs3@redhat.com> wrote:
>> When CPPC is being used by ACPI on arm64, user space tools such as
>> cpupower report CPU frequency values from sysfs that are incorrect.
>>
>> What the driver was doing was reporting the values given by ACPI tables
>> in whatever scale was used to provide them.  However, the ACPI spec
>> defines the CPPC values as unitless abstract numbers.  Internal kernel
>> structures such as struct perf_cap, in contrast, expect these values
>> to be in KHz.  When these struct values get reported via sysfs, the
>> user space tools also assume they are in KHz, causing them to report
>> incorrect values (for example, reporting a CPU frequency of 1MHz when
>> it should be 1.8GHz).
>>
>> While the investigation for a long term fix proceeds (several options
>> are being explored, some of which may require spec changes or other
>> much more invasive fixes), this patch forces the values read by CPPC
>> to be read in KHz, regardless of what they actually represent.
>>
>> The downside is that this approach has some assumptions:
>>
>>    (1) It relies on SMBIOS3 being used, *and* that the Max Frequency
>>    value for a processor is set to a non-zero value.
>>
>>    (2) It assumes that all processors run at the same speed, or that
>>    the CPPC values have all been scaled to reflect relative speed.
>>    This patch retrieves the first CPU Max Frequency from a type 4 DMI
>>    record that it can find.  This may not be an issue, however, as a
>>    sampling of DMI data on x86 and arm64 indicates there is often only
>>    one such record regardless.  Since CPPC is relatively new, it is
>>    unclear if the ACPI ASL will always be written to reflect any sort
>>    of relative performance of processors of differing speeds.
>>
>>    (3) It assumes that performance and frequency both scale linearly.
>>
>> For arm64 servers, this may be sufficient, but it does rely on
>> firmware values being set correctly.  Hence, other approaches are
>> also being considered.
>>
>> This has been tested on three arm64 servers, with and without DMI, with
>> and without CPPC support.
>>
>> Changes for v3:
>>     -- Added clarifying commentary re short-term vs long-term fix (Alexey
>>        Klimov)
>>     -- Added range checking code to ensure proper arithmetic occurs,
>>        especially no division by zero (Alexey Klimov)
>>
>> Changes for v2:
>>     -- Corrected thinko: needed to have DEPENDS on DMI in Kconfig.arm,
>>        not SELECT DMI (found by build daemon)
>>
>> Signed-off-by: Al Stone <ahs3@redhat.com>
>> ---
>>  drivers/acpi/cppc_acpi.c    | 96 ++++++++++++++++++++++++++++++++++++++++++---
>>  drivers/cpufreq/Kconfig.arm |  1 +
>>  2 files changed, 92 insertions(+), 5 deletions(-)
>>
>> diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
>> index 8adac69..56a46e6 100644
>> --- a/drivers/acpi/cppc_acpi.c
>> +++ b/drivers/acpi/cppc_acpi.c
>> @@ -40,6 +40,9 @@
>>  #include <linux/cpufreq.h>
>>  #include <linux/delay.h>
>>  #include <linux/ktime.h>
>> +#include <linux/dmi.h>
>> +
>> +#include <asm/unaligned.h>
>>
>>  #include <acpi/cppc_acpi.h>
>>  /*
>> @@ -709,6 +712,55 @@ static int cpc_write(struct cpc_reg *reg, u64 val)
>>         return ret_val;
>>  }
>>
>> +static u64 cppc_dmi_khz;
>> +
>> +static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
>> +{
>> +       u16 *mhz = (u16 *)private;
>> +       const u8 *dmi_data = (const u8 *)dm;
>> +
>> +       if (dm->type == DMI_ENTRY_PROCESSOR && dm->length >= 48)
>> +               *mhz = (u16)get_unaligned((const u16 *)(dmi_data + 0x14));
> 
> Is the offset standardized across architectures (I can't recall ATM)?
> If so, maybe #define a symbol for it and add a comment saying that
> next to its definition?

It's part of the SMBIOS standard.  I'll fix it.

I feel very silly -- I just bugged somebody else about magic constants; karma
is an amazing thing :).

>> +}
>> +
>> +
>> +static u64 cppc_get_dmi_khz(void)
>> +{
>> +       u16 mhz;
>> +
>> +       dmi_walk(cppc_find_dmi_mhz, &mhz);
>> +
>> +       /*
>> +        * Real stupid fallback value, just in case there is no
>> +        * actual value set.
>> +        */
>> +       mhz = mhz ? mhz : 1;
>> +
>> +       return (1000 * mhz);
>> +}
>> +
>> +static u64 cppc_unitless_to_khz(u64 min_in, u64 max_in, u64 val)
> 
> Is the "unitless" part of the name really necessary?

Probably not essential, but descriptive.  "cppc_convert_to_khz()" instead?
Or even "cppc_to_khz()"?

> 
>> +{
>> +       /*
>> +        * The incoming val should be min <= val <= max.  Our
>> +        * job is to convert that to KHz so it can be properly
>> +        * reported to user space via cpufreq_policy.
>> +        */
>> +       u64 curval = val;
>> +       u64 maxf = max_in;
>> +       u64 minf = min_in;
>> +
>> +       if (!cppc_dmi_khz)
>> +               cppc_dmi_khz = cppc_get_dmi_khz();
> 
> I don't like hidden initializations like this if they are avoidable
> and it very much looks like it is avoidable here.

Fair enough.  I'll fix it.

> Also you seem to be using the same cppc_dmi_khz value for all
> processors handled by this driver.  Is that really guaranteed to be
> correct?

Yes and no.  It all depends on what's in the SMBIOS tables.  Let me
see about making the search for that data a bit more robust; oddly
enough, I poked at some random machines (x86 and arm64) and more often
than not only found one CPU entry in the SMBIOS data.

>> +
>> +       /* range check the input values */
>> +       curval = curval < minf ? minf : curval;
>> +       curval = curval > maxf ? maxf : curval;
>> +       minf = minf >= maxf ? maxf - 1 : minf;
>> +
>> +       return ((curval - minf) * cppc_dmi_khz) / (maxf - minf);
>> +}
>> +
>>  /**
>>   * cppc_get_perf_caps - Get a CPUs performance capabilities.
>>   * @cpunum: CPU from which to get capabilities info.
>> @@ -748,17 +800,51 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
>>                 }
>>         }
>>
>> +       /*
>> +        * Since these values in perf_caps will be used in setting
>> +        * up the cpufreq policy, they must always be stored in units
>> +        * of KHz.  If they are not, user space tools will become very
>> +        * confused since they assume these are in KHz when reading
>> +        * sysfs.
>> +        *
>> +        * NB: there may be better approaches to this problem that, as
>> +        * of this writing, are still being explored.  Ideally, this is
>> +        * a short term solution since correlating CPPC abstract values
>> +        * with CPU frequency may or may not reflect actual performance.
>> +        *
>> +        * The reason longer term solutions are being explored is because
>> +        * this solution requires we make the following assumptions:
>> +        *
>> +        *    (1) It relies on SMBIOS3 being used, *and* that the Max
>> +        *        Frequency value for a processor is set to a non-zero value.
>> +        *
>> +        *    (2) It assumes that all processors run at the same speed, or
>> +        *        that the CPPC values have all been scaled to reflect any
>> +        *        relative differences.  This code retrieves the first CPU
>> +        *        Max Frequency from a type 4 DMI record that it can find.
>> +        *        This may not be an issue, however, as a sampling of DMI
>> +        *        data on x86 and arm64 indicates there is often only one
>> +        *        such record regardless.
>> +        *
>> +        *    (3) It assumes that performance and frequency both scale
>> +        *        linearly.
>> +        *
>> +        * None of these are particularly horrible assumptions.  But, they
>> +        * are assumptions and ultimately we'd like to be able to report
>> +        * performance without quite so many of them.
>> +        *
>> +        */
>>         cpc_read(&highest_reg->cpc_entry.reg, &high);
>> -       perf_caps->highest_perf = high;
>> -
>>         cpc_read(&lowest_reg->cpc_entry.reg, &low);
>> -       perf_caps->lowest_perf = low;
>> +
>> +       perf_caps->highest_perf = cppc_unitless_to_khz(low, high, high);
>> +       perf_caps->lowest_perf = cppc_unitless_to_khz(low, high, low);
>>
>>         cpc_read(&ref_perf->cpc_entry.reg, &ref);
>> -       perf_caps->reference_perf = ref;
>> +       perf_caps->reference_perf = cppc_unitless_to_khz(low, high, ref);
>>
>>         cpc_read(&nom_perf->cpc_entry.reg, &nom);
>> -       perf_caps->nominal_perf = nom;
>> +       perf_caps->nominal_perf = cppc_unitless_to_khz(low, high, nom);
>>
>>         if (!ref)
>>                 perf_caps->reference_perf = perf_caps->nominal_perf;
>> diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
>> index 14b1f93..0573982 100644
>> --- a/drivers/cpufreq/Kconfig.arm
>> +++ b/drivers/cpufreq/Kconfig.arm
>> @@ -255,6 +255,7 @@ config ACPI_CPPC_CPUFREQ
>>         tristate "CPUFreq driver based on the ACPI CPPC spec"
>>         depends on ACPI
>>         select ACPI_CPPC_LIB
>> +       select DMI
> 
> What if there are unmet dependencies for DMI?  Or is that not possible?
>

I'll double check this.  I don't recall any, off hand.

>>         default n
>>         help
>>           This adds a CPUFreq driver which uses CPPC methods
>> --

Thanks for the feedback, Rafael!
diff mbox

Patch

diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 8adac69..56a46e6 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -40,6 +40,9 @@ 
 #include <linux/cpufreq.h>
 #include <linux/delay.h>
 #include <linux/ktime.h>
+#include <linux/dmi.h>
+
+#include <asm/unaligned.h>
 
 #include <acpi/cppc_acpi.h>
 /*
@@ -709,6 +712,55 @@  static int cpc_write(struct cpc_reg *reg, u64 val)
 	return ret_val;
 }
 
+static u64 cppc_dmi_khz;
+
+static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
+{
+	u16 *mhz = (u16 *)private;
+	const u8 *dmi_data = (const u8 *)dm;
+
+	if (dm->type == DMI_ENTRY_PROCESSOR && dm->length >= 48)
+		*mhz = (u16)get_unaligned((const u16 *)(dmi_data + 0x14));
+}
+
+
+static u64 cppc_get_dmi_khz(void)
+{
+	u16 mhz;
+
+	dmi_walk(cppc_find_dmi_mhz, &mhz);
+
+	/*
+	 * Real stupid fallback value, just in case there is no
+	 * actual value set.
+	 */
+	mhz = mhz ? mhz : 1;
+
+	return (1000 * mhz);
+}
+
+static u64 cppc_unitless_to_khz(u64 min_in, u64 max_in, u64 val)
+{
+	/*
+	 * The incoming val should be min <= val <= max.  Our
+	 * job is to convert that to KHz so it can be properly
+	 * reported to user space via cpufreq_policy.
+	 */
+	u64 curval = val;
+	u64 maxf = max_in;
+	u64 minf = min_in;
+
+	if (!cppc_dmi_khz)
+		cppc_dmi_khz = cppc_get_dmi_khz();
+
+	/* range check the input values */
+	curval = curval < minf ? minf : curval;
+	curval = curval > maxf ? maxf : curval;
+	minf = minf >= maxf ? maxf - 1 : minf;
+
+	return ((curval - minf) * cppc_dmi_khz) / (maxf - minf);
+}
+
 /**
  * cppc_get_perf_caps - Get a CPUs performance capabilities.
  * @cpunum: CPU from which to get capabilities info.
@@ -748,17 +800,51 @@  int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
 		}
 	}
 
+	/*
+	 * Since these values in perf_caps will be used in setting
+	 * up the cpufreq policy, they must always be stored in units
+	 * of KHz.  If they are not, user space tools will become very
+	 * confused since they assume these are in KHz when reading
+	 * sysfs.
+	 *
+	 * NB: there may be better approaches to this problem that, as
+	 * of this writing, are still being explored.  Ideally, this is
+	 * a short term solution since correlating CPPC abstract values
+	 * with CPU frequency may or may not reflect actual performance.
+	 *
+	 * The reason longer term solutions are being explored is because
+	 * this solution requires we make the following assumptions:
+	 *
+	 *    (1) It relies on SMBIOS3 being used, *and* that the Max
+	 *        Frequency value for a processor is set to a non-zero value.
+	 *
+	 *    (2) It assumes that all processors run at the same speed, or
+	 *        that the CPPC values have all been scaled to reflect any
+	 *        relative differences.  This code retrieves the first CPU
+	 *        Max Frequency from a type 4 DMI record that it can find.
+	 *        This may not be an issue, however, as a sampling of DMI
+	 *        data on x86 and arm64 indicates there is often only one
+	 *        such record regardless.
+	 *
+	 *    (3) It assumes that performance and frequency both scale
+	 *        linearly.
+	 *
+	 * None of these are particularly horrible assumptions.  But, they
+	 * are assumptions and ultimately we'd like to be able to report
+	 * performance without quite so many of them.
+	 *
+	 */
 	cpc_read(&highest_reg->cpc_entry.reg, &high);
-	perf_caps->highest_perf = high;
-
 	cpc_read(&lowest_reg->cpc_entry.reg, &low);
-	perf_caps->lowest_perf = low;
+
+	perf_caps->highest_perf = cppc_unitless_to_khz(low, high, high);
+	perf_caps->lowest_perf = cppc_unitless_to_khz(low, high, low);
 
 	cpc_read(&ref_perf->cpc_entry.reg, &ref);
-	perf_caps->reference_perf = ref;
+	perf_caps->reference_perf = cppc_unitless_to_khz(low, high, ref);
 
 	cpc_read(&nom_perf->cpc_entry.reg, &nom);
-	perf_caps->nominal_perf = nom;
+	perf_caps->nominal_perf = cppc_unitless_to_khz(low, high, nom);
 
 	if (!ref)
 		perf_caps->reference_perf = perf_caps->nominal_perf;
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 14b1f93..0573982 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -255,6 +255,7 @@  config ACPI_CPPC_CPUFREQ
 	tristate "CPUFreq driver based on the ACPI CPPC spec"
 	depends on ACPI
 	select ACPI_CPPC_LIB
+	select DMI
 	default n
 	help
 	  This adds a CPUFreq driver which uses CPPC methods