2021-11-07 22:59:45

by Andy Shevchenko

[permalink] [raw]
Subject: Re: [PATCH] mfd: intel_soc_pmic: Use CPU-id check instead of _HRV check to differentiate variants

On Sun, Nov 7, 2021 at 7:26 PM Hans de Goede <[email protected]> wrote:
>
> The Intel Crystal Cove PMIC has 2 different variants, one for use with
> Bay Trail (BYT) SoCs and one for use with Cherry Trail (CHT) SoCs.
>
> So far we have been using an ACPI _HRV check to differentiate between
> the 2, but at least on the Microsoft Surface 3, which is a CHT device,
> the wrong _HRV value is reported by ACPI.
>
> So instead switch to a CPU-ID check which avoids us relying on the
> possibly wrong ACPI _HRV value.

Thanks, I hope Tsuchiya will test this soon, from code perspective it
looks good to me,
Reviewed-by: Andy Shevchenko <[email protected]>

> Reported-by: Tsuchiya Yuto <[email protected]>
> Signed-off-by: Hans de Goede <[email protected]>
> ---
> drivers/mfd/intel_soc_pmic_core.c | 28 +++-------------------------
> 1 file changed, 3 insertions(+), 25 deletions(-)
>
> diff --git a/drivers/mfd/intel_soc_pmic_core.c b/drivers/mfd/intel_soc_pmic_core.c
> index ddd64f9e3341..47cb7f00dfcf 100644
> --- a/drivers/mfd/intel_soc_pmic_core.c
> +++ b/drivers/mfd/intel_soc_pmic_core.c
> @@ -14,15 +14,12 @@
> #include <linux/module.h>
> #include <linux/mfd/core.h>
> #include <linux/mfd/intel_soc_pmic.h>
> +#include <linux/platform_data/x86/soc.h>
> #include <linux/pwm.h>
> #include <linux/regmap.h>
>
> #include "intel_soc_pmic_core.h"
>
> -/* Crystal Cove PMIC shares same ACPI ID between different platforms */
> -#define BYT_CRC_HRV 2
> -#define CHT_CRC_HRV 3
> -
> /* PWM consumed by the Intel GFX */
> static struct pwm_lookup crc_pwm_lookup[] = {
> PWM_LOOKUP("crystal_cove_pwm", 0, "0000:00:02.0", "pwm_pmic_backlight", 0, PWM_POLARITY_NORMAL),
> @@ -34,31 +31,12 @@ static int intel_soc_pmic_i2c_probe(struct i2c_client *i2c,
> struct device *dev = &i2c->dev;
> struct intel_soc_pmic_config *config;
> struct intel_soc_pmic *pmic;
> - unsigned long long hrv;
> - acpi_status status;
> int ret;
>
> - /*
> - * There are 2 different Crystal Cove PMICs a Bay Trail and Cherry
> - * Trail version, use _HRV to differentiate between the 2.
> - */
> - status = acpi_evaluate_integer(ACPI_HANDLE(dev), "_HRV", NULL, &hrv);
> - if (ACPI_FAILURE(status)) {
> - dev_err(dev, "Failed to get PMIC hardware revision\n");
> - return -ENODEV;
> - }
> -
> - switch (hrv) {
> - case BYT_CRC_HRV:
> + if (soc_intel_is_byt())
> config = &intel_soc_pmic_config_byt_crc;
> - break;
> - case CHT_CRC_HRV:
> + else
> config = &intel_soc_pmic_config_cht_crc;
> - break;
> - default:
> - dev_warn(dev, "Unknown hardware rev %llu, assuming BYT\n", hrv);
> - config = &intel_soc_pmic_config_byt_crc;
> - }
>
> pmic = devm_kzalloc(dev, sizeof(*pmic), GFP_KERNEL);
> if (!pmic)
> --
> 2.31.1
>


--
With Best Regards,
Andy Shevchenko


2021-11-09 12:52:51

by Tsuchiya Yuto

[permalink] [raw]
Subject: Re: [PATCH] mfd: intel_soc_pmic: Use CPU-id check instead of _HRV check to differentiate variants

On Sun, 2021-11-07 at 20:17 +0200, Andy Shevchenko wrote:
> On Sun, Nov 7, 2021 at 7:26 PM Hans de Goede <[email protected]> wrote:
> >
> > The Intel Crystal Cove PMIC has 2 different variants, one for use with
> > Bay Trail (BYT) SoCs and one for use with Cherry Trail (CHT) SoCs.
> >
> > So far we have been using an ACPI _HRV check to differentiate between
> > the 2, but at least on the Microsoft Surface 3, which is a CHT device,
> > the wrong _HRV value is reported by ACPI.
> >
> > So instead switch to a CPU-ID check which avoids us relying on the
> > possibly wrong ACPI _HRV value.
>
> Thanks, I hope Tsuchiya will test this soon, from code perspective it
> looks good to me,
> Reviewed-by: Andy Shevchenko <[email protected]>

Hi, thank you for the patch. I tried this patch (plus the patch ("ASoC:
Intel: Move soc_intel_is_foo() helpers to a generic header") [1], which
this patch needs) on my Surface 3 and can confirm it's using CHT variant
of Crystal Cove PMIC driver as expected.

Tested-by: Tsuchiya Yuto <[email protected]>

[1] https://lore.kernel.org/all/[email protected]/

> > Reported-by: Tsuchiya Yuto <[email protected]>
> > Signed-off-by: Hans de Goede <[email protected]>
> > ---
> > drivers/mfd/intel_soc_pmic_core.c | 28 +++-------------------------
> > 1 file changed, 3 insertions(+), 25 deletions(-)
> >
> > diff --git a/drivers/mfd/intel_soc_pmic_core.c b/drivers/mfd/intel_soc_pmic_core.c
> > index ddd64f9e3341..47cb7f00dfcf 100644
> > --- a/drivers/mfd/intel_soc_pmic_core.c
> > +++ b/drivers/mfd/intel_soc_pmic_core.c
> > @@ -14,15 +14,12 @@
> > #include <linux/module.h>
> > #include <linux/mfd/core.h>
> > #include <linux/mfd/intel_soc_pmic.h>
> > +#include <linux/platform_data/x86/soc.h>
> > #include <linux/pwm.h>
> > #include <linux/regmap.h>
> >
> > #include "intel_soc_pmic_core.h"
> >
> > -/* Crystal Cove PMIC shares same ACPI ID between different platforms */
> > -#define BYT_CRC_HRV 2
> > -#define CHT_CRC_HRV 3
> > -
> > /* PWM consumed by the Intel GFX */
> > static struct pwm_lookup crc_pwm_lookup[] = {
> > PWM_LOOKUP("crystal_cove_pwm", 0, "0000:00:02.0", "pwm_pmic_backlight", 0, PWM_POLARITY_NORMAL),
> > @@ -34,31 +31,12 @@ static int intel_soc_pmic_i2c_probe(struct i2c_client *i2c,
> > struct device *dev = &i2c->dev;
> > struct intel_soc_pmic_config *config;
> > struct intel_soc_pmic *pmic;
> > - unsigned long long hrv;
> > - acpi_status status;
> > int ret;
> >
> > - /*
> > - * There are 2 different Crystal Cove PMICs a Bay Trail and Cherry
> > - * Trail version, use _HRV to differentiate between the 2.
> > - */
> > - status = acpi_evaluate_integer(ACPI_HANDLE(dev), "_HRV", NULL, &hrv);
> > - if (ACPI_FAILURE(status)) {
> > - dev_err(dev, "Failed to get PMIC hardware revision\n");
> > - return -ENODEV;
> > - }
> > -
> > - switch (hrv) {
> > - case BYT_CRC_HRV:
> > + if (soc_intel_is_byt())
> > config = &intel_soc_pmic_config_byt_crc;
> > - break;
> > - case CHT_CRC_HRV:
> > + else
> > config = &intel_soc_pmic_config_cht_crc;
> > - break;
> > - default:
> > - dev_warn(dev, "Unknown hardware rev %llu, assuming BYT\n", hrv);
> > - config = &intel_soc_pmic_config_byt_crc;
> > - }
> >
> > pmic = devm_kzalloc(dev, sizeof(*pmic), GFP_KERNEL);
> > if (!pmic)
> > --
> > 2.31.1
> >
>
>


2021-11-09 16:06:37

by Hans de Goede

[permalink] [raw]
Subject: Re: [PATCH] mfd: intel_soc_pmic: Use CPU-id check instead of _HRV check to differentiate variants

Hi,

On 11/9/21 04:23, Tsuchiya Yuto wrote:
> On Sun, 2021-11-07 at 20:17 +0200, Andy Shevchenko wrote:
>> On Sun, Nov 7, 2021 at 7:26 PM Hans de Goede <[email protected]> wrote:
>>>
>>> The Intel Crystal Cove PMIC has 2 different variants, one for use with
>>> Bay Trail (BYT) SoCs and one for use with Cherry Trail (CHT) SoCs.
>>>
>>> So far we have been using an ACPI _HRV check to differentiate between
>>> the 2, but at least on the Microsoft Surface 3, which is a CHT device,
>>> the wrong _HRV value is reported by ACPI.
>>>
>>> So instead switch to a CPU-ID check which avoids us relying on the
>>> possibly wrong ACPI _HRV value.
>>
>> Thanks, I hope Tsuchiya will test this soon, from code perspective it
>> looks good to me,
>> Reviewed-by: Andy Shevchenko <[email protected]>
>
> Hi, thank you for the patch. I tried this patch (plus the patch ("ASoC:
> Intel: Move soc_intel_is_foo() helpers to a generic header") [1],

Right, this patch needs to be applie don top of the upcoming v5.16-rc1
which has that patch, I wanted to mention that but I forgot.

> which
> this patch needs) on my Surface 3 and can confirm it's using CHT variant
> of Crystal Cove PMIC driver as expected.
>
> Tested-by: Tsuchiya Yuto <[email protected]>

Thank you.

Regards,

Hans



>
> [1] https://lore.kernel.org/all/[email protected]/
>
>>> Reported-by: Tsuchiya Yuto <[email protected]>
>>> Signed-off-by: Hans de Goede <[email protected]>
>>> ---
>>> drivers/mfd/intel_soc_pmic_core.c | 28 +++-------------------------
>>> 1 file changed, 3 insertions(+), 25 deletions(-)
>>>
>>> diff --git a/drivers/mfd/intel_soc_pmic_core.c b/drivers/mfd/intel_soc_pmic_core.c
>>> index ddd64f9e3341..47cb7f00dfcf 100644
>>> --- a/drivers/mfd/intel_soc_pmic_core.c
>>> +++ b/drivers/mfd/intel_soc_pmic_core.c
>>> @@ -14,15 +14,12 @@
>>> #include <linux/module.h>
>>> #include <linux/mfd/core.h>
>>> #include <linux/mfd/intel_soc_pmic.h>
>>> +#include <linux/platform_data/x86/soc.h>
>>> #include <linux/pwm.h>
>>> #include <linux/regmap.h>
>>>
>>> #include "intel_soc_pmic_core.h"
>>>
>>> -/* Crystal Cove PMIC shares same ACPI ID between different platforms */
>>> -#define BYT_CRC_HRV 2
>>> -#define CHT_CRC_HRV 3
>>> -
>>> /* PWM consumed by the Intel GFX */
>>> static struct pwm_lookup crc_pwm_lookup[] = {
>>> PWM_LOOKUP("crystal_cove_pwm", 0, "0000:00:02.0", "pwm_pmic_backlight", 0, PWM_POLARITY_NORMAL),
>>> @@ -34,31 +31,12 @@ static int intel_soc_pmic_i2c_probe(struct i2c_client *i2c,
>>> struct device *dev = &i2c->dev;
>>> struct intel_soc_pmic_config *config;
>>> struct intel_soc_pmic *pmic;
>>> - unsigned long long hrv;
>>> - acpi_status status;
>>> int ret;
>>>
>>> - /*
>>> - * There are 2 different Crystal Cove PMICs a Bay Trail and Cherry
>>> - * Trail version, use _HRV to differentiate between the 2.
>>> - */
>>> - status = acpi_evaluate_integer(ACPI_HANDLE(dev), "_HRV", NULL, &hrv);
>>> - if (ACPI_FAILURE(status)) {
>>> - dev_err(dev, "Failed to get PMIC hardware revision\n");
>>> - return -ENODEV;
>>> - }
>>> -
>>> - switch (hrv) {
>>> - case BYT_CRC_HRV:
>>> + if (soc_intel_is_byt())
>>> config = &intel_soc_pmic_config_byt_crc;
>>> - break;
>>> - case CHT_CRC_HRV:
>>> + else
>>> config = &intel_soc_pmic_config_cht_crc;
>>> - break;
>>> - default:
>>> - dev_warn(dev, "Unknown hardware rev %llu, assuming BYT\n", hrv);
>>> - config = &intel_soc_pmic_config_byt_crc;
>>> - }
>>>
>>> pmic = devm_kzalloc(dev, sizeof(*pmic), GFP_KERNEL);
>>> if (!pmic)
>>> --
>>> 2.31.1
>>>
>>
>>
>
>